You can not select more than 25 topics Topics must start with a letter or number, can include dashes ('-') and can be up to 35 characters long.

Nick Piggin 05fe478dd0 mm: write_cache_pages integrity fix ... In write_cache_pages, nr_to_write is heeded even for data-integrity syncs, so the function will return success after writing out nr_to_write pages, even if that was not sufficient to guarantee data integrity. The callers tend to set it to values that could break data interity semantics easily in practice. For example, nr_to_write can be set to mapping->nr_pages * 2, however if a file has a single, dirty page, then fsync is called, subsequent pages might be concurrently added and dirtied, then write_cache_pages might writeout two of these newly dirty pages, while not writing out the old page that should have been written out. Fix this by ignoring nr_to_write if it is a data integrity sync. This is a data integrity bug. The reason this has been done in the past is to avoid stalling sync operations behind page dirtiers. "If a file has one dirty page at offset 1000000000000000 then someone does an fsync() and someone else gets in first and starts madly writing pages at offset 0, we want to write that page at 1000000000000000. Somehow." What we do today is return success after an arbitrary amount of pages are written, whether or not we have provided the data-integrity semantics that the caller has asked for. Even this doesn't actually fix all stall cases completely: in the above situation, if the file has a huge number of pages in pagecache (but not dirty), then mapping->nrpages is going to be huge, even if pages are being dirtied. This change does indeed make the possibility of long stalls lager, and that's not a good thing, but lying about data integrity is even worse. We have to either perform the sync, or return -ELINUXISLAME so at least the caller knows what has happened. There are subsequent competing approaches in the works to solve the stall problems properly, without compromising data integrity. Signed-off-by: Nick Piggin <npiggin@suse.de> Cc: Chris Mason <chris.mason@oracle.com> Cc: Dave Chinner <david@fromorbit.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>		16 years ago
..
Kconfig	Unevictable LRU Infrastructure	16 years ago
Makefile	SLUB: failslab support	16 years ago
allocpercpu.c	mm/allocpercpu.c: make 4 functions static	17 years ago
backing-dev.c	mm/backing-dev.c: remove recently-added WARN_ON()	16 years ago
bootmem.c	misc: replace __FUNCTION__ with __func__	17 years ago
bounce.c	bounce: don't rely on a zeroed bio_vec list	16 years ago
dmapool.c	dmapool: enable debugging for CONFIG_SLUB_DEBUG_ON too	17 years ago
fadvise.c	Remove Andrew Morton's old email accounts	17 years ago
failslab.c	SLUB: failslab support	16 years ago
filemap.c	mm: write_cache_pages integrity fix	16 years ago
filemap_xip.c	mm: xip/ext2 fix block allocation race	17 years ago
fremap.c	mmap: handle mlocked pages during map, remap, unmap	16 years ago
highmem.c	x86, pat: avoid highmem cache attribute aliasing	17 years ago
hugetlb.c	mm: report the MMU pagesize in /proc/pid/smaps	16 years ago
internal.h	hugetlb: pull gigantic page initialisation out of the default path	16 years ago
maccess.c	kgdb: fix optional arch functions and probe_kernel_*	17 years ago
madvise.c	madvise: update function comment of madvise_dontneed	17 years ago
memcontrol.c	memcg: fix page_cgroup allocation	16 years ago
memory.c	mm: don't mark_page_accessed in fault path	16 years ago
memory_hotplug.c	meminit section warnings	16 years ago
mempolicy.c	Merge branch 'master' into next	16 years ago
mempool.c	spelling fixes: mm/	18 years ago
migrate.c	mm: move_pages: no need to set pp->page to ZERO_PAGE(0) by default	16 years ago
mincore.c	mm: remove nopage	17 years ago
mlock.c	x86, bts: memory accounting	16 years ago
mm_init.c	mm: mminit_loglevel cannot be __meminitdata anymore	17 years ago
mmap.c	mm: update my address	16 years ago
mmu_notifier.c	mmu-notifiers: core	17 years ago
mmzone.c	mm: mark the correct zone as full when scanning zonelists	17 years ago
mprotect.c	mm: update my address	16 years ago
mremap.c	mm: update my address	16 years ago
msync.c	add a vfs_fsync helper	16 years ago
nommu.c	inode->i_op is never NULL	16 years ago
oom_kill.c	oom: print triggering task's cpuset and mems allowed	16 years ago
page-writeback.c	mm: write_cache_pages integrity fix	16 years ago
page_alloc.c	cpusets: update mems allowed in page allocator	16 years ago
page_cgroup.c	page_cgroup should ignore empty nodes	16 years ago
page_io.c	mm: fix PageUptodate data race	17 years ago
page_isolation.c	memory hotplug: fix page_zone() calculation in test_pages_isolated()	16 years ago
pagewalk.c	pagemap: pass mm into pagewalkers	17 years ago
pdflush.c	cpumask: convert mm/	16 years ago
prio_tree.c	spelling fixes: mm/	18 years ago
quicklist.c	mm: size of quicklists shouldn't be proportional to the number of CPUs	17 years ago
readahead.c	vmscan: split LRU lists into anon & file sets	16 years ago
rmap.c	make mm/rmap.c:anon_vma_cachep static	16 years ago
shmem.c	mm: don't mark_page_accessed in shmem_fault	16 years ago
shmem_acl.c	[PATCH] sanitize ->permission() prototype	17 years ago
slab.c	cpumask: convert mm/	16 years ago
slob.c	slob: do not pass the SLAB flags as GFP in kmem_cache_create()	16 years ago
slub.c	cpumask: convert mm/	16 years ago
sparse-vmemmap.c	vmemmap: warn about page_structs with remote distance	16 years ago
sparse.c	meminit section warnings	16 years ago
swap.c	mm: remove UP version of lru_add_drain_all()	16 years ago
swap_state.c	mm: pagecache insertion fewer atomics	16 years ago
swapfile.c	x86: consolidate __swp_XXX() macros	16 years ago
thrash.c	…
tiny-shmem.c	Export tiny shmem_file_setup for DRM-GEM	16 years ago
truncate.c	mmap: handle mlocked pages during map, remap, unmap	16 years ago
util.c	mm: Make generic weak get_user_pages_fast and EXPORT_GPL it	17 years ago
vmalloc.c	vmalloc.c: fix flushing in vmap_page_range()	16 years ago
vmscan.c	cpumask: convert mm/	16 years ago
vmstat.c	cpumask: convert mm/	16 years ago