mirror of
https://github.com/torvalds/linux
synced 2024-09-06 18:01:05 +00:00
![Linus Torvalds](/assets/img/avatar_default.png)
F_SEAL_EXEC") which permits the setting of the memfd execute bit at memfd creation time, with the option of sealing the state of the X bit. - Peter Xu adds a patch series ("mm/hugetlb: Make huge_pte_offset() thread-safe for pmd unshare") which addresses a rare race condition related to PMD unsharing. - Several folioification patch serieses from Matthew Wilcox, Vishal Moola, Sidhartha Kumar and Lorenzo Stoakes - Johannes Weiner has a series ("mm: push down lock_page_memcg()") which does perform some memcg maintenance and cleanup work. - SeongJae Park has added DAMOS filtering to DAMON, with the series "mm/damon/core: implement damos filter". These filters provide users with finer-grained control over DAMOS's actions. SeongJae has also done some DAMON cleanup work. - Kairui Song adds a series ("Clean up and fixes for swap"). - Vernon Yang contributed the series "Clean up and refinement for maple tree". - Yu Zhao has contributed the "mm: multi-gen LRU: memcg LRU" series. It adds to MGLRU an LRU of memcgs, to improve the scalability of global reclaim. - David Hildenbrand has added some userfaultfd cleanup work in the series "mm: uffd-wp + change_protection() cleanups". - Christoph Hellwig has removed the generic_writepages() library function in the series "remove generic_writepages". - Baolin Wang has performed some maintenance on the compaction code in his series "Some small improvements for compaction". - Sidhartha Kumar is doing some maintenance work on struct page in his series "Get rid of tail page fields". - David Hildenbrand contributed some cleanup, bugfixing and generalization of pte management and of pte debugging in his series "mm: support __HAVE_ARCH_PTE_SWP_EXCLUSIVE on all architectures with swap PTEs". - Mel Gorman and Neil Brown have removed the __GFP_ATOMIC allocation flag in the series "Discard __GFP_ATOMIC". - Sergey Senozhatsky has improved zsmalloc's memory utilization with his series "zsmalloc: make zspage chain size configurable". - Joey Gouly has added prctl() support for prohibiting the creation of writeable+executable mappings. The previous BPF-based approach had shortcomings. See "mm: In-kernel support for memory-deny-write-execute (MDWE)". - Waiman Long did some kmemleak cleanup and bugfixing in the series "mm/kmemleak: Simplify kmemleak_cond_resched() & fix UAF". - T.J. Alumbaugh has contributed some MGLRU cleanup work in his series "mm: multi-gen LRU: improve". - Jiaqi Yan has provided some enhancements to our memory error statistics reporting, mainly by presenting the statistics on a per-node basis. See the series "Introduce per NUMA node memory error statistics". - Mel Gorman has a second and hopefully final shot at fixing a CPU-hog regression in compaction via his series "Fix excessive CPU usage during compaction". - Christoph Hellwig does some vmalloc maintenance work in the series "cleanup vfree and vunmap". - Christoph Hellwig has removed block_device_operations.rw_page() in ths series "remove ->rw_page". - We get some maple_tree improvements and cleanups in Liam Howlett's series "VMA tree type safety and remove __vma_adjust()". - Suren Baghdasaryan has done some work on the maintainability of our vm_flags handling in the series "introduce vm_flags modifier functions". - Some pagemap cleanup and generalization work in Mike Rapoport's series "mm, arch: add generic implementation of pfn_valid() for FLATMEM" and "fixups for generic implementation of pfn_valid()" - Baoquan He has done some work to make /proc/vmallocinfo and /proc/kcore better represent the real state of things in his series "mm/vmalloc.c: allow vread() to read out vm_map_ram areas". - Jason Gunthorpe rationalized the GUP system's interface to the rest of the kernel in the series "Simplify the external interface for GUP". - SeongJae Park wishes to migrate people from DAMON's debugfs interface over to its sysfs interface. To support this, we'll temporarily be printing warnings when people use the debugfs interface. See the series "mm/damon: deprecate DAMON debugfs interface". - Andrey Konovalov provided the accurately named "lib/stackdepot: fixes and clean-ups" series. - Huang Ying has provided a dramatic reduction in migration's TLB flush IPI rates with the series "migrate_pages(): batch TLB flushing". - Arnd Bergmann has some objtool fixups in "objtool warning fixes". -----BEGIN PGP SIGNATURE----- iHUEABYIAB0WIQTTMBEPP41GrTpTJgfdBJ7gKXxAjgUCY/PoPQAKCRDdBJ7gKXxA jlvpAPsFECUBBl20qSue2zCYWnHC7Yk4q9ytTkPB/MMDrFEN9wD/SNKEm2UoK6/K DmxHkn0LAitGgJRS/W9w81yrgig9tAQ= =MlGs -----END PGP SIGNATURE----- Merge tag 'mm-stable-2023-02-20-13-37' of git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm Pull MM updates from Andrew Morton: - Daniel Verkamp has contributed a memfd series ("mm/memfd: add F_SEAL_EXEC") which permits the setting of the memfd execute bit at memfd creation time, with the option of sealing the state of the X bit. - Peter Xu adds a patch series ("mm/hugetlb: Make huge_pte_offset() thread-safe for pmd unshare") which addresses a rare race condition related to PMD unsharing. - Several folioification patch serieses from Matthew Wilcox, Vishal Moola, Sidhartha Kumar and Lorenzo Stoakes - Johannes Weiner has a series ("mm: push down lock_page_memcg()") which does perform some memcg maintenance and cleanup work. - SeongJae Park has added DAMOS filtering to DAMON, with the series "mm/damon/core: implement damos filter". These filters provide users with finer-grained control over DAMOS's actions. SeongJae has also done some DAMON cleanup work. - Kairui Song adds a series ("Clean up and fixes for swap"). - Vernon Yang contributed the series "Clean up and refinement for maple tree". - Yu Zhao has contributed the "mm: multi-gen LRU: memcg LRU" series. It adds to MGLRU an LRU of memcgs, to improve the scalability of global reclaim. - David Hildenbrand has added some userfaultfd cleanup work in the series "mm: uffd-wp + change_protection() cleanups". - Christoph Hellwig has removed the generic_writepages() library function in the series "remove generic_writepages". - Baolin Wang has performed some maintenance on the compaction code in his series "Some small improvements for compaction". - Sidhartha Kumar is doing some maintenance work on struct page in his series "Get rid of tail page fields". - David Hildenbrand contributed some cleanup, bugfixing and generalization of pte management and of pte debugging in his series "mm: support __HAVE_ARCH_PTE_SWP_EXCLUSIVE on all architectures with swap PTEs". - Mel Gorman and Neil Brown have removed the __GFP_ATOMIC allocation flag in the series "Discard __GFP_ATOMIC". - Sergey Senozhatsky has improved zsmalloc's memory utilization with his series "zsmalloc: make zspage chain size configurable". - Joey Gouly has added prctl() support for prohibiting the creation of writeable+executable mappings. The previous BPF-based approach had shortcomings. See "mm: In-kernel support for memory-deny-write-execute (MDWE)". - Waiman Long did some kmemleak cleanup and bugfixing in the series "mm/kmemleak: Simplify kmemleak_cond_resched() & fix UAF". - T.J. Alumbaugh has contributed some MGLRU cleanup work in his series "mm: multi-gen LRU: improve". - Jiaqi Yan has provided some enhancements to our memory error statistics reporting, mainly by presenting the statistics on a per-node basis. See the series "Introduce per NUMA node memory error statistics". - Mel Gorman has a second and hopefully final shot at fixing a CPU-hog regression in compaction via his series "Fix excessive CPU usage during compaction". - Christoph Hellwig does some vmalloc maintenance work in the series "cleanup vfree and vunmap". - Christoph Hellwig has removed block_device_operations.rw_page() in ths series "remove ->rw_page". - We get some maple_tree improvements and cleanups in Liam Howlett's series "VMA tree type safety and remove __vma_adjust()". - Suren Baghdasaryan has done some work on the maintainability of our vm_flags handling in the series "introduce vm_flags modifier functions". - Some pagemap cleanup and generalization work in Mike Rapoport's series "mm, arch: add generic implementation of pfn_valid() for FLATMEM" and "fixups for generic implementation of pfn_valid()" - Baoquan He has done some work to make /proc/vmallocinfo and /proc/kcore better represent the real state of things in his series "mm/vmalloc.c: allow vread() to read out vm_map_ram areas". - Jason Gunthorpe rationalized the GUP system's interface to the rest of the kernel in the series "Simplify the external interface for GUP". - SeongJae Park wishes to migrate people from DAMON's debugfs interface over to its sysfs interface. To support this, we'll temporarily be printing warnings when people use the debugfs interface. See the series "mm/damon: deprecate DAMON debugfs interface". - Andrey Konovalov provided the accurately named "lib/stackdepot: fixes and clean-ups" series. - Huang Ying has provided a dramatic reduction in migration's TLB flush IPI rates with the series "migrate_pages(): batch TLB flushing". - Arnd Bergmann has some objtool fixups in "objtool warning fixes". * tag 'mm-stable-2023-02-20-13-37' of git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm: (505 commits) include/linux/migrate.h: remove unneeded externs mm/memory_hotplug: cleanup return value handing in do_migrate_range() mm/uffd: fix comment in handling pte markers mm: change to return bool for isolate_movable_page() mm: hugetlb: change to return bool for isolate_hugetlb() mm: change to return bool for isolate_lru_page() mm: change to return bool for folio_isolate_lru() objtool: add UACCESS exceptions for __tsan_volatile_read/write kmsan: disable ftrace in kmsan core code kasan: mark addr_has_metadata __always_inline mm: memcontrol: rename memcg_kmem_enabled() sh: initialize max_mapnr m68k/nommu: add missing definition of ARCH_PFN_OFFSET mm: percpu: fix incorrect size in pcpu_obj_full_size() maple_tree: reduce stack usage with gcc-9 and earlier mm: page_alloc: call panic() when memoryless node allocation fails mm: multi-gen LRU: avoid futile retries migrate_pages: move THP/hugetlb migration support check to simplify code migrate_pages: batch flushing TLB migrate_pages: share more code between _unmap and _move ...
440 lines
11 KiB
C
440 lines
11 KiB
C
// SPDX-License-Identifier: GPL-2.0-only
|
|
/*
|
|
* Copyright (C) 2017-2018 HUAWEI, Inc.
|
|
* https://www.huawei.com/
|
|
* Copyright (C) 2021, Alibaba Cloud
|
|
*/
|
|
#include "internal.h"
|
|
#include <linux/prefetch.h>
|
|
#include <linux/sched/mm.h>
|
|
#include <linux/dax.h>
|
|
#include <trace/events/erofs.h>
|
|
|
|
void erofs_unmap_metabuf(struct erofs_buf *buf)
|
|
{
|
|
if (buf->kmap_type == EROFS_KMAP)
|
|
kunmap_local(buf->base);
|
|
buf->base = NULL;
|
|
buf->kmap_type = EROFS_NO_KMAP;
|
|
}
|
|
|
|
void erofs_put_metabuf(struct erofs_buf *buf)
|
|
{
|
|
if (!buf->page)
|
|
return;
|
|
erofs_unmap_metabuf(buf);
|
|
put_page(buf->page);
|
|
buf->page = NULL;
|
|
}
|
|
|
|
void *erofs_bread(struct erofs_buf *buf, struct inode *inode,
|
|
erofs_blk_t blkaddr, enum erofs_kmap_type type)
|
|
{
|
|
struct address_space *const mapping = inode->i_mapping;
|
|
erofs_off_t offset = blknr_to_addr(blkaddr);
|
|
pgoff_t index = offset >> PAGE_SHIFT;
|
|
struct page *page = buf->page;
|
|
struct folio *folio;
|
|
unsigned int nofs_flag;
|
|
|
|
if (!page || page->index != index) {
|
|
erofs_put_metabuf(buf);
|
|
|
|
nofs_flag = memalloc_nofs_save();
|
|
folio = read_cache_folio(mapping, index, NULL, NULL);
|
|
memalloc_nofs_restore(nofs_flag);
|
|
if (IS_ERR(folio))
|
|
return folio;
|
|
|
|
/* should already be PageUptodate, no need to lock page */
|
|
page = folio_file_page(folio, index);
|
|
buf->page = page;
|
|
}
|
|
if (buf->kmap_type == EROFS_NO_KMAP) {
|
|
if (type == EROFS_KMAP)
|
|
buf->base = kmap_local_page(page);
|
|
buf->kmap_type = type;
|
|
} else if (buf->kmap_type != type) {
|
|
DBG_BUGON(1);
|
|
return ERR_PTR(-EFAULT);
|
|
}
|
|
if (type == EROFS_NO_KMAP)
|
|
return NULL;
|
|
return buf->base + (offset & ~PAGE_MASK);
|
|
}
|
|
|
|
void *erofs_read_metabuf(struct erofs_buf *buf, struct super_block *sb,
|
|
erofs_blk_t blkaddr, enum erofs_kmap_type type)
|
|
{
|
|
if (erofs_is_fscache_mode(sb))
|
|
return erofs_bread(buf, EROFS_SB(sb)->s_fscache->inode,
|
|
blkaddr, type);
|
|
|
|
return erofs_bread(buf, sb->s_bdev->bd_inode, blkaddr, type);
|
|
}
|
|
|
|
static int erofs_map_blocks_flatmode(struct inode *inode,
|
|
struct erofs_map_blocks *map)
|
|
{
|
|
erofs_blk_t nblocks, lastblk;
|
|
u64 offset = map->m_la;
|
|
struct erofs_inode *vi = EROFS_I(inode);
|
|
bool tailendpacking = (vi->datalayout == EROFS_INODE_FLAT_INLINE);
|
|
|
|
nblocks = DIV_ROUND_UP(inode->i_size, EROFS_BLKSIZ);
|
|
lastblk = nblocks - tailendpacking;
|
|
|
|
/* there is no hole in flatmode */
|
|
map->m_flags = EROFS_MAP_MAPPED;
|
|
if (offset < blknr_to_addr(lastblk)) {
|
|
map->m_pa = blknr_to_addr(vi->raw_blkaddr) + map->m_la;
|
|
map->m_plen = blknr_to_addr(lastblk) - offset;
|
|
} else if (tailendpacking) {
|
|
map->m_pa = erofs_iloc(inode) + vi->inode_isize +
|
|
vi->xattr_isize + erofs_blkoff(offset);
|
|
map->m_plen = inode->i_size - offset;
|
|
|
|
/* inline data should be located in the same meta block */
|
|
if (erofs_blkoff(map->m_pa) + map->m_plen > EROFS_BLKSIZ) {
|
|
erofs_err(inode->i_sb,
|
|
"inline data cross block boundary @ nid %llu",
|
|
vi->nid);
|
|
DBG_BUGON(1);
|
|
return -EFSCORRUPTED;
|
|
}
|
|
map->m_flags |= EROFS_MAP_META;
|
|
} else {
|
|
erofs_err(inode->i_sb,
|
|
"internal error @ nid: %llu (size %llu), m_la 0x%llx",
|
|
vi->nid, inode->i_size, map->m_la);
|
|
DBG_BUGON(1);
|
|
return -EIO;
|
|
}
|
|
return 0;
|
|
}
|
|
|
|
int erofs_map_blocks(struct inode *inode, struct erofs_map_blocks *map)
|
|
{
|
|
struct super_block *sb = inode->i_sb;
|
|
struct erofs_inode *vi = EROFS_I(inode);
|
|
struct erofs_inode_chunk_index *idx;
|
|
struct erofs_buf buf = __EROFS_BUF_INITIALIZER;
|
|
u64 chunknr;
|
|
unsigned int unit;
|
|
erofs_off_t pos;
|
|
void *kaddr;
|
|
int err = 0;
|
|
|
|
trace_erofs_map_blocks_enter(inode, map, 0);
|
|
map->m_deviceid = 0;
|
|
if (map->m_la >= inode->i_size) {
|
|
/* leave out-of-bound access unmapped */
|
|
map->m_flags = 0;
|
|
map->m_plen = 0;
|
|
goto out;
|
|
}
|
|
|
|
if (vi->datalayout != EROFS_INODE_CHUNK_BASED) {
|
|
err = erofs_map_blocks_flatmode(inode, map);
|
|
goto out;
|
|
}
|
|
|
|
if (vi->chunkformat & EROFS_CHUNK_FORMAT_INDEXES)
|
|
unit = sizeof(*idx); /* chunk index */
|
|
else
|
|
unit = EROFS_BLOCK_MAP_ENTRY_SIZE; /* block map */
|
|
|
|
chunknr = map->m_la >> vi->chunkbits;
|
|
pos = ALIGN(erofs_iloc(inode) + vi->inode_isize +
|
|
vi->xattr_isize, unit) + unit * chunknr;
|
|
|
|
kaddr = erofs_read_metabuf(&buf, sb, erofs_blknr(pos), EROFS_KMAP);
|
|
if (IS_ERR(kaddr)) {
|
|
err = PTR_ERR(kaddr);
|
|
goto out;
|
|
}
|
|
map->m_la = chunknr << vi->chunkbits;
|
|
map->m_plen = min_t(erofs_off_t, 1UL << vi->chunkbits,
|
|
roundup(inode->i_size - map->m_la, EROFS_BLKSIZ));
|
|
|
|
/* handle block map */
|
|
if (!(vi->chunkformat & EROFS_CHUNK_FORMAT_INDEXES)) {
|
|
__le32 *blkaddr = kaddr + erofs_blkoff(pos);
|
|
|
|
if (le32_to_cpu(*blkaddr) == EROFS_NULL_ADDR) {
|
|
map->m_flags = 0;
|
|
} else {
|
|
map->m_pa = blknr_to_addr(le32_to_cpu(*blkaddr));
|
|
map->m_flags = EROFS_MAP_MAPPED;
|
|
}
|
|
goto out_unlock;
|
|
}
|
|
/* parse chunk indexes */
|
|
idx = kaddr + erofs_blkoff(pos);
|
|
switch (le32_to_cpu(idx->blkaddr)) {
|
|
case EROFS_NULL_ADDR:
|
|
map->m_flags = 0;
|
|
break;
|
|
default:
|
|
map->m_deviceid = le16_to_cpu(idx->device_id) &
|
|
EROFS_SB(sb)->device_id_mask;
|
|
map->m_pa = blknr_to_addr(le32_to_cpu(idx->blkaddr));
|
|
map->m_flags = EROFS_MAP_MAPPED;
|
|
break;
|
|
}
|
|
out_unlock:
|
|
erofs_put_metabuf(&buf);
|
|
out:
|
|
if (!err)
|
|
map->m_llen = map->m_plen;
|
|
trace_erofs_map_blocks_exit(inode, map, 0, err);
|
|
return err;
|
|
}
|
|
|
|
int erofs_map_dev(struct super_block *sb, struct erofs_map_dev *map)
|
|
{
|
|
struct erofs_dev_context *devs = EROFS_SB(sb)->devs;
|
|
struct erofs_device_info *dif;
|
|
int id;
|
|
|
|
/* primary device by default */
|
|
map->m_bdev = sb->s_bdev;
|
|
map->m_daxdev = EROFS_SB(sb)->dax_dev;
|
|
map->m_dax_part_off = EROFS_SB(sb)->dax_part_off;
|
|
map->m_fscache = EROFS_SB(sb)->s_fscache;
|
|
|
|
if (map->m_deviceid) {
|
|
down_read(&devs->rwsem);
|
|
dif = idr_find(&devs->tree, map->m_deviceid - 1);
|
|
if (!dif) {
|
|
up_read(&devs->rwsem);
|
|
return -ENODEV;
|
|
}
|
|
map->m_bdev = dif->bdev;
|
|
map->m_daxdev = dif->dax_dev;
|
|
map->m_dax_part_off = dif->dax_part_off;
|
|
map->m_fscache = dif->fscache;
|
|
up_read(&devs->rwsem);
|
|
} else if (devs->extra_devices) {
|
|
down_read(&devs->rwsem);
|
|
idr_for_each_entry(&devs->tree, dif, id) {
|
|
erofs_off_t startoff, length;
|
|
|
|
if (!dif->mapped_blkaddr)
|
|
continue;
|
|
startoff = blknr_to_addr(dif->mapped_blkaddr);
|
|
length = blknr_to_addr(dif->blocks);
|
|
|
|
if (map->m_pa >= startoff &&
|
|
map->m_pa < startoff + length) {
|
|
map->m_pa -= startoff;
|
|
map->m_bdev = dif->bdev;
|
|
map->m_daxdev = dif->dax_dev;
|
|
map->m_dax_part_off = dif->dax_part_off;
|
|
map->m_fscache = dif->fscache;
|
|
break;
|
|
}
|
|
}
|
|
up_read(&devs->rwsem);
|
|
}
|
|
return 0;
|
|
}
|
|
|
|
static int erofs_iomap_begin(struct inode *inode, loff_t offset, loff_t length,
|
|
unsigned int flags, struct iomap *iomap, struct iomap *srcmap)
|
|
{
|
|
int ret;
|
|
struct erofs_map_blocks map;
|
|
struct erofs_map_dev mdev;
|
|
|
|
map.m_la = offset;
|
|
map.m_llen = length;
|
|
|
|
ret = erofs_map_blocks(inode, &map);
|
|
if (ret < 0)
|
|
return ret;
|
|
|
|
mdev = (struct erofs_map_dev) {
|
|
.m_deviceid = map.m_deviceid,
|
|
.m_pa = map.m_pa,
|
|
};
|
|
ret = erofs_map_dev(inode->i_sb, &mdev);
|
|
if (ret)
|
|
return ret;
|
|
|
|
iomap->offset = map.m_la;
|
|
if (flags & IOMAP_DAX)
|
|
iomap->dax_dev = mdev.m_daxdev;
|
|
else
|
|
iomap->bdev = mdev.m_bdev;
|
|
iomap->length = map.m_llen;
|
|
iomap->flags = 0;
|
|
iomap->private = NULL;
|
|
|
|
if (!(map.m_flags & EROFS_MAP_MAPPED)) {
|
|
iomap->type = IOMAP_HOLE;
|
|
iomap->addr = IOMAP_NULL_ADDR;
|
|
if (!iomap->length)
|
|
iomap->length = length;
|
|
return 0;
|
|
}
|
|
|
|
if (map.m_flags & EROFS_MAP_META) {
|
|
void *ptr;
|
|
struct erofs_buf buf = __EROFS_BUF_INITIALIZER;
|
|
|
|
iomap->type = IOMAP_INLINE;
|
|
ptr = erofs_read_metabuf(&buf, inode->i_sb,
|
|
erofs_blknr(mdev.m_pa), EROFS_KMAP);
|
|
if (IS_ERR(ptr))
|
|
return PTR_ERR(ptr);
|
|
iomap->inline_data = ptr + erofs_blkoff(mdev.m_pa);
|
|
iomap->private = buf.base;
|
|
} else {
|
|
iomap->type = IOMAP_MAPPED;
|
|
iomap->addr = mdev.m_pa;
|
|
if (flags & IOMAP_DAX)
|
|
iomap->addr += mdev.m_dax_part_off;
|
|
}
|
|
return 0;
|
|
}
|
|
|
|
static int erofs_iomap_end(struct inode *inode, loff_t pos, loff_t length,
|
|
ssize_t written, unsigned int flags, struct iomap *iomap)
|
|
{
|
|
void *ptr = iomap->private;
|
|
|
|
if (ptr) {
|
|
struct erofs_buf buf = {
|
|
.page = kmap_to_page(ptr),
|
|
.base = ptr,
|
|
.kmap_type = EROFS_KMAP,
|
|
};
|
|
|
|
DBG_BUGON(iomap->type != IOMAP_INLINE);
|
|
erofs_put_metabuf(&buf);
|
|
} else {
|
|
DBG_BUGON(iomap->type == IOMAP_INLINE);
|
|
}
|
|
return written;
|
|
}
|
|
|
|
static const struct iomap_ops erofs_iomap_ops = {
|
|
.iomap_begin = erofs_iomap_begin,
|
|
.iomap_end = erofs_iomap_end,
|
|
};
|
|
|
|
int erofs_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo,
|
|
u64 start, u64 len)
|
|
{
|
|
if (erofs_inode_is_data_compressed(EROFS_I(inode)->datalayout)) {
|
|
#ifdef CONFIG_EROFS_FS_ZIP
|
|
return iomap_fiemap(inode, fieinfo, start, len,
|
|
&z_erofs_iomap_report_ops);
|
|
#else
|
|
return -EOPNOTSUPP;
|
|
#endif
|
|
}
|
|
return iomap_fiemap(inode, fieinfo, start, len, &erofs_iomap_ops);
|
|
}
|
|
|
|
/*
|
|
* since we dont have write or truncate flows, so no inode
|
|
* locking needs to be held at the moment.
|
|
*/
|
|
static int erofs_read_folio(struct file *file, struct folio *folio)
|
|
{
|
|
return iomap_read_folio(folio, &erofs_iomap_ops);
|
|
}
|
|
|
|
static void erofs_readahead(struct readahead_control *rac)
|
|
{
|
|
return iomap_readahead(rac, &erofs_iomap_ops);
|
|
}
|
|
|
|
static sector_t erofs_bmap(struct address_space *mapping, sector_t block)
|
|
{
|
|
return iomap_bmap(mapping, block, &erofs_iomap_ops);
|
|
}
|
|
|
|
static ssize_t erofs_file_read_iter(struct kiocb *iocb, struct iov_iter *to)
|
|
{
|
|
struct inode *inode = file_inode(iocb->ki_filp);
|
|
|
|
/* no need taking (shared) inode lock since it's a ro filesystem */
|
|
if (!iov_iter_count(to))
|
|
return 0;
|
|
|
|
#ifdef CONFIG_FS_DAX
|
|
if (IS_DAX(inode))
|
|
return dax_iomap_rw(iocb, to, &erofs_iomap_ops);
|
|
#endif
|
|
if (iocb->ki_flags & IOCB_DIRECT) {
|
|
struct block_device *bdev = inode->i_sb->s_bdev;
|
|
unsigned int blksize_mask;
|
|
|
|
if (bdev)
|
|
blksize_mask = bdev_logical_block_size(bdev) - 1;
|
|
else
|
|
blksize_mask = (1 << inode->i_blkbits) - 1;
|
|
|
|
if ((iocb->ki_pos | iov_iter_count(to) |
|
|
iov_iter_alignment(to)) & blksize_mask)
|
|
return -EINVAL;
|
|
|
|
return iomap_dio_rw(iocb, to, &erofs_iomap_ops,
|
|
NULL, 0, NULL, 0);
|
|
}
|
|
return filemap_read(iocb, to, 0);
|
|
}
|
|
|
|
/* for uncompressed (aligned) files and raw access for other files */
|
|
const struct address_space_operations erofs_raw_access_aops = {
|
|
.read_folio = erofs_read_folio,
|
|
.readahead = erofs_readahead,
|
|
.bmap = erofs_bmap,
|
|
.direct_IO = noop_direct_IO,
|
|
.release_folio = iomap_release_folio,
|
|
.invalidate_folio = iomap_invalidate_folio,
|
|
};
|
|
|
|
#ifdef CONFIG_FS_DAX
|
|
static vm_fault_t erofs_dax_huge_fault(struct vm_fault *vmf,
|
|
enum page_entry_size pe_size)
|
|
{
|
|
return dax_iomap_fault(vmf, pe_size, NULL, NULL, &erofs_iomap_ops);
|
|
}
|
|
|
|
static vm_fault_t erofs_dax_fault(struct vm_fault *vmf)
|
|
{
|
|
return erofs_dax_huge_fault(vmf, PE_SIZE_PTE);
|
|
}
|
|
|
|
static const struct vm_operations_struct erofs_dax_vm_ops = {
|
|
.fault = erofs_dax_fault,
|
|
.huge_fault = erofs_dax_huge_fault,
|
|
};
|
|
|
|
static int erofs_file_mmap(struct file *file, struct vm_area_struct *vma)
|
|
{
|
|
if (!IS_DAX(file_inode(file)))
|
|
return generic_file_readonly_mmap(file, vma);
|
|
|
|
if ((vma->vm_flags & VM_SHARED) && (vma->vm_flags & VM_MAYWRITE))
|
|
return -EINVAL;
|
|
|
|
vma->vm_ops = &erofs_dax_vm_ops;
|
|
vm_flags_set(vma, VM_HUGEPAGE);
|
|
return 0;
|
|
}
|
|
#else
|
|
#define erofs_file_mmap generic_file_readonly_mmap
|
|
#endif
|
|
|
|
const struct file_operations erofs_file_fops = {
|
|
.llseek = generic_file_llseek,
|
|
.read_iter = erofs_file_read_iter,
|
|
.mmap = erofs_file_mmap,
|
|
.splice_read = generic_file_splice_read,
|
|
};
|