linux/mm/filemap.c

2470 lines
64 KiB
C
Raw Normal View History

/*
* linux/mm/filemap.c
*
* Copyright (C) 1994-1999 Linus Torvalds
*/
/*
* This file handles the generic file mmap semantics used by
* most "normal" filesystems (but you don't /have/ to use this:
* the NFS filesystem used to do this differently, for example)
*/
#include <linux/module.h>
#include <linux/slab.h>
#include <linux/compiler.h>
#include <linux/fs.h>
[PATCH] x86: cache pollution aware __copy_from_user_ll() Use the x86 cache-bypassing copy instructions for copy_from_user(). Some performance data are Total of GLOBAL_POWER_EVENTS (CPU cycle samples) 2.6.12.4.orig 1921587 2.6.12.4.nt 1599424 1599424/1921587=83.23% (16.77% reduction) BSQ_CACHE_REFERENCE (L3 cache miss) 2.6.12.4.orig 57427 2.6.12.4.nt 20858 20858/57427=36.32% (63.7% reduction) L3 cache miss reduction of __copy_from_user_ll samples % 37408 65.1412 vmlinux __copy_from_user_ll 23 0.1103 vmlinux __copy_user_zeroing_intel_nocache 23/37408=0.061% (99.94% reduction) Top 5 of 2.6.12.4.nt Counted GLOBAL_POWER_EVENTS events (time during which processor is not stopped) with a unit mask of 0x01 (mandatory) count 100000 samples % app name symbol name 128392 8.0274 vmlinux __copy_user_zeroing_intel_nocache 64206 4.0143 vmlinux journal_add_journal_head 59746 3.7355 vmlinux do_get_write_access 47674 2.9807 vmlinux journal_put_journal_head 46021 2.8774 vmlinux journal_dirty_metadata pattern9-0-cpu4-0-09011728/summary.out Counted BSQ_CACHE_REFERENCE events (cache references seen by the bus unit) with a unit mask of 0x3f (multiple flags) count 3000 samples % app name symbol name 69755 4.2861 vmlinux __copy_user_zeroing_intel_nocache 55685 3.4215 vmlinux journal_add_journal_head 52371 3.2179 vmlinux __find_get_block 45504 2.7960 vmlinux journal_put_journal_head 36005 2.2123 vmlinux journal_stop pattern9-0-cpu4-0-09011744/summary.out Counted BSQ_CACHE_REFERENCE events (cache references seen by the bus unit) with a unit mask of 0x200 (read 3rd level cache miss) count 3000 samples % app name symbol name 1147 5.4994 vmlinux journal_add_journal_head 881 4.2240 vmlinux journal_dirty_data 872 4.1809 vmlinux blk_rq_map_sg 734 3.5192 vmlinux journal_commit_transaction 617 2.9582 vmlinux radix_tree_delete pattern9-0-cpu4-0-09011731/summary.out iozone results are original 2.6.12.4 CPU time = 207.768 sec cache aware CPU time = 184.783 sec (three times run) 184.783/207.768=88.94% (11.06% reduction) original: pattern9-0-cpu4-0-08191720/iozone.out: CPU Utilization: Wall time 45.997 CPU time 64.527 CPU utilization 140.28 % pattern9-0-cpu4-0-08191741/iozone.out: CPU Utilization: Wall time 46.878 CPU time 71.933 CPU utilization 153.45 % pattern9-0-cpu4-0-08191743/iozone.out: CPU Utilization: Wall time 45.152 CPU time 71.308 CPU utilization 157.93 % cache awre: pattern9-0-cpu4-0-09011728/iozone.out: CPU Utilization: Wall time 44.842 CPU time 62.465 CPU utilization 139.30 % pattern9-0-cpu4-0-09011731/iozone.out: CPU Utilization: Wall time 44.718 CPU time 59.273 CPU utilization 132.55 % pattern9-0-cpu4-0-09011744/iozone.out: CPU Utilization: Wall time 44.367 CPU time 63.045 CPU utilization 142.10 % Signed-off-by: Hiro Yoshioka <hyoshiok@miraclelinux.com> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2006-06-23 09:04:16 +00:00
#include <linux/uaccess.h>
#include <linux/aio.h>
#include <linux/capability.h>
#include <linux/kernel_stat.h>
#include <linux/mm.h>
#include <linux/swap.h>
#include <linux/mman.h>
#include <linux/pagemap.h>
#include <linux/file.h>
#include <linux/uio.h>
#include <linux/hash.h>
#include <linux/writeback.h>
#include <linux/pagevec.h>
#include <linux/blkdev.h>
#include <linux/security.h>
#include <linux/syscalls.h>
#include <linux/cpuset.h>
#include "filemap.h"
#include "internal.h"
/*
* FIXME: remove all knowledge of the buffer layer from the core VM
*/
#include <linux/buffer_head.h> /* for generic_osync_inode */
#include <asm/mman.h>
static ssize_t
generic_file_direct_IO(int rw, struct kiocb *iocb, const struct iovec *iov,
loff_t offset, unsigned long nr_segs);
/*
* Shared mappings implemented 30.11.1994. It's not fully working yet,
* though.
*
* Shared mappings now work. 15.8.1995 Bruno.
*
* finished 'unifying' the page and buffer cache and SMP-threaded the
* page-cache, 21.05.1999, Ingo Molnar <mingo@redhat.com>
*
* SMP-threaded pagemap-LRU 1999, Andrea Arcangeli <andrea@suse.de>
*/
/*
* Lock ordering:
*
* ->i_mmap_lock (vmtruncate)
* ->private_lock (__free_pte->__set_page_dirty_buffers)
* ->swap_lock (exclusive_swap_page, others)
* ->mapping->tree_lock
*
* ->i_mutex
* ->i_mmap_lock (truncate->unmap_mapping_range)
*
* ->mmap_sem
* ->i_mmap_lock
* ->page_table_lock or pte_lock (various, mainly in memory.c)
* ->mapping->tree_lock (arch-dependent flush_dcache_mmap_lock)
*
* ->mmap_sem
* ->lock_page (access_process_vm)
*
* ->i_mutex (generic_file_buffered_write)
* ->mmap_sem (fault_in_pages_readable->do_page_fault)
*
* ->i_mutex
* ->i_alloc_sem (various)
*
* ->inode_lock
* ->sb_lock (fs/fs-writeback.c)
* ->mapping->tree_lock (__sync_single_inode)
*
* ->i_mmap_lock
* ->anon_vma.lock (vma_adjust)
*
* ->anon_vma.lock
* ->page_table_lock or pte_lock (anon_vma_prepare and various)
*
* ->page_table_lock or pte_lock
* ->swap_lock (try_to_unmap_one)
* ->private_lock (try_to_unmap_one)
* ->tree_lock (try_to_unmap_one)
* ->zone.lru_lock (follow_page->mark_page_accessed)
* ->zone.lru_lock (check_pte_range->isolate_lru_page)
* ->private_lock (page_remove_rmap->set_page_dirty)
* ->tree_lock (page_remove_rmap->set_page_dirty)
* ->inode_lock (page_remove_rmap->set_page_dirty)
* ->inode_lock (zap_pte_range->set_page_dirty)
* ->private_lock (zap_pte_range->__set_page_dirty_buffers)
*
* ->task->proc_lock
* ->dcache_lock (proc_pid_lookup)
*/
/*
* Remove a page from the page cache and free it. Caller has to make
* sure the page is locked and that nobody else uses it - or that usage
* is safe. The caller must hold a write_lock on the mapping's tree_lock.
*/
void __remove_from_page_cache(struct page *page)
{
struct address_space *mapping = page->mapping;
radix_tree_delete(&mapping->page_tree, page->index);
page->mapping = NULL;
mapping->nrpages--;
__dec_zone_page_state(page, NR_FILE_PAGES);
}
void remove_from_page_cache(struct page *page)
{
struct address_space *mapping = page->mapping;
BUG_ON(!PageLocked(page));
write_lock_irq(&mapping->tree_lock);
__remove_from_page_cache(page);
write_unlock_irq(&mapping->tree_lock);
}
static int sync_page(void *word)
{
struct address_space *mapping;
struct page *page;
page = container_of((unsigned long *)word, struct page, flags);
/*
* page_mapping() is being called without PG_locked held.
* Some knowledge of the state and use of the page is used to
* reduce the requirements down to a memory barrier.
* The danger here is of a stale page_mapping() return value
* indicating a struct address_space different from the one it's
* associated with when it is associated with one.
* After smp_mb(), it's either the correct page_mapping() for
* the page, or an old page_mapping() and the page's own
* page_mapping() has gone NULL.
* The ->sync_page() address_space operation must tolerate
* page_mapping() going NULL. By an amazing coincidence,
* this comes about because none of the users of the page
* in the ->sync_page() methods make essential use of the
* page_mapping(), merely passing the page down to the backing
* device's unplug functions when it's non-NULL, which in turn
[PATCH] mm: split page table lock Christoph Lameter demonstrated very poor scalability on the SGI 512-way, with a many-threaded application which concurrently initializes different parts of a large anonymous area. This patch corrects that, by using a separate spinlock per page table page, to guard the page table entries in that page, instead of using the mm's single page_table_lock. (But even then, page_table_lock is still used to guard page table allocation, and anon_vma allocation.) In this implementation, the spinlock is tucked inside the struct page of the page table page: with a BUILD_BUG_ON in case it overflows - which it would in the case of 32-bit PA-RISC with spinlock debugging enabled. Splitting the lock is not quite for free: another cacheline access. Ideally, I suppose we would use split ptlock only for multi-threaded processes on multi-cpu machines; but deciding that dynamically would have its own costs. So for now enable it by config, at some number of cpus - since the Kconfig language doesn't support inequalities, let preprocessor compare that with NR_CPUS. But I don't think it's worth being user-configurable: for good testing of both split and unsplit configs, split now at 4 cpus, and perhaps change that to 8 later. There is a benefit even for singly threaded processes: kswapd can be attacking one part of the mm while another part is busy faulting. Signed-off-by: Hugh Dickins <hugh@veritas.com> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2005-10-30 01:16:40 +00:00
* ignore it for all cases but swap, where only page_private(page) is
* of interest. When page_mapping() does go NULL, the entire
* call stack gracefully ignores the page and returns.
* -- wli
*/
smp_mb();
mapping = page_mapping(page);
if (mapping && mapping->a_ops && mapping->a_ops->sync_page)
mapping->a_ops->sync_page(page);
io_schedule();
return 0;
}
/**
* __filemap_fdatawrite_range - start writeback on mapping dirty pages in range
* @mapping: address space structure to write
* @start: offset in bytes where the range starts
* @end: offset in bytes where the range ends (inclusive)
* @sync_mode: enable synchronous operation
*
* Start writeback against all of a mapping's dirty pages that lie
* within the byte offsets <start, end> inclusive.
*
* If sync_mode is WB_SYNC_ALL then this is a "data integrity" operation, as
* opposed to a regular memory cleansing writeback. The difference between
* these two operations is that if a dirty page/buffer is encountered, it must
* be waited upon, and not just skipped over.
*/
[PATCH] fadvise(): write commands Add two new linux-specific fadvise extensions(): LINUX_FADV_ASYNC_WRITE: start async writeout of any dirty pages between file offsets `offset' and `offset+len'. Any pages which are currently under writeout are skipped, whether or not they are dirty. LINUX_FADV_WRITE_WAIT: wait upon writeout of any dirty pages between file offsets `offset' and `offset+len'. By combining these two operations the application may do several things: LINUX_FADV_ASYNC_WRITE: push some or all of the dirty pages at the disk. LINUX_FADV_WRITE_WAIT, LINUX_FADV_ASYNC_WRITE: push all of the currently dirty pages at the disk. LINUX_FADV_WRITE_WAIT, LINUX_FADV_ASYNC_WRITE, LINUX_FADV_WRITE_WAIT: push all of the currently dirty pages at the disk, wait until they have been written. It should be noted that none of these operations write out the file's metadata. So unless the application is strictly performing overwrites of already-instantiated disk blocks, there are no guarantees here that the data will be available after a crash. To complete this suite of operations I guess we should have a "sync file metadata only" operation. This gives applications access to all the building blocks needed for all sorts of sync operations. But sync-metadata doesn't fit well with the fadvise() interface. Probably it should be a new syscall: sys_fmetadatasync(). The patch also diddles with the meaning of `endbyte' in sys_fadvise64_64(). It is made to represent that last affected byte in the file (ie: it is inclusive). Generally, all these byterange and pagerange functions are inclusive so we can easily represent EOF with -1. As Ulrich notes, these two functions are somewhat abusive of the fadvise() concept, which appears to be "set the future policy for this fd". But these commands are a perfect fit with the fadvise() impementation, and several of the existing fadvise() commands are synchronous and don't affect future policy either. I think we can live with the slight incongruity. Cc: Michael Kerrisk <mtk-manpages@gmx.net> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2006-03-24 11:18:04 +00:00
int __filemap_fdatawrite_range(struct address_space *mapping, loff_t start,
loff_t end, int sync_mode)
{
int ret;
struct writeback_control wbc = {
.sync_mode = sync_mode,
.nr_to_write = mapping->nrpages * 2,
[PATCH] writeback: fix range handling When a writeback_control's `start' and `end' fields are used to indicate a one-byte-range starting at file offset zero, the required values of .start=0,.end=0 mean that the ->writepages() implementation has no way of telling that it is being asked to perform a range request. Because we're currently overloading (start == 0 && end == 0) to mean "this is not a write-a-range request". To make all this sane, the patch changes range of writeback_control. So caller does: If it is calling ->writepages() to write pages, it sets range (range_start/end or range_cyclic) always. And if range_cyclic is true, ->writepages() thinks the range is cyclic, otherwise it just uses range_start and range_end. This patch does, - Add LLONG_MAX, LLONG_MIN, ULLONG_MAX to include/linux/kernel.h -1 is usually ok for range_end (type is long long). But, if someone did, range_end += val; range_end is "val - 1" u64val = range_end >> bits; u64val is "~(0ULL)" or something, they are wrong. So, this adds LLONG_MAX to avoid nasty things, and uses LLONG_MAX for range_end. - All callers of ->writepages() sets range_start/end or range_cyclic. - Fix updates of ->writeback_index. It seems already bit strange. If it starts at 0 and ended by check of nr_to_write, this last index may reduce chance to scan end of file. So, this updates ->writeback_index only if range_cyclic is true or whole-file is scanned. Signed-off-by: OGAWA Hirofumi <hirofumi@mail.parknet.co.jp> Cc: Nathan Scott <nathans@sgi.com> Cc: Anton Altaparmakov <aia21@cantab.net> Cc: Steven French <sfrench@us.ibm.com> Cc: "Vladimir V. Saveliev" <vs@namesys.com> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2006-06-23 09:03:26 +00:00
.range_start = start,
.range_end = end,
};
if (!mapping_cap_writeback_dirty(mapping))
return 0;
ret = do_writepages(mapping, &wbc);
return ret;
}
static inline int __filemap_fdatawrite(struct address_space *mapping,
int sync_mode)
{
[PATCH] writeback: fix range handling When a writeback_control's `start' and `end' fields are used to indicate a one-byte-range starting at file offset zero, the required values of .start=0,.end=0 mean that the ->writepages() implementation has no way of telling that it is being asked to perform a range request. Because we're currently overloading (start == 0 && end == 0) to mean "this is not a write-a-range request". To make all this sane, the patch changes range of writeback_control. So caller does: If it is calling ->writepages() to write pages, it sets range (range_start/end or range_cyclic) always. And if range_cyclic is true, ->writepages() thinks the range is cyclic, otherwise it just uses range_start and range_end. This patch does, - Add LLONG_MAX, LLONG_MIN, ULLONG_MAX to include/linux/kernel.h -1 is usually ok for range_end (type is long long). But, if someone did, range_end += val; range_end is "val - 1" u64val = range_end >> bits; u64val is "~(0ULL)" or something, they are wrong. So, this adds LLONG_MAX to avoid nasty things, and uses LLONG_MAX for range_end. - All callers of ->writepages() sets range_start/end or range_cyclic. - Fix updates of ->writeback_index. It seems already bit strange. If it starts at 0 and ended by check of nr_to_write, this last index may reduce chance to scan end of file. So, this updates ->writeback_index only if range_cyclic is true or whole-file is scanned. Signed-off-by: OGAWA Hirofumi <hirofumi@mail.parknet.co.jp> Cc: Nathan Scott <nathans@sgi.com> Cc: Anton Altaparmakov <aia21@cantab.net> Cc: Steven French <sfrench@us.ibm.com> Cc: "Vladimir V. Saveliev" <vs@namesys.com> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2006-06-23 09:03:26 +00:00
return __filemap_fdatawrite_range(mapping, 0, LLONG_MAX, sync_mode);
}
int filemap_fdatawrite(struct address_space *mapping)
{
return __filemap_fdatawrite(mapping, WB_SYNC_ALL);
}
EXPORT_SYMBOL(filemap_fdatawrite);
[PATCH] fadvise(): write commands Add two new linux-specific fadvise extensions(): LINUX_FADV_ASYNC_WRITE: start async writeout of any dirty pages between file offsets `offset' and `offset+len'. Any pages which are currently under writeout are skipped, whether or not they are dirty. LINUX_FADV_WRITE_WAIT: wait upon writeout of any dirty pages between file offsets `offset' and `offset+len'. By combining these two operations the application may do several things: LINUX_FADV_ASYNC_WRITE: push some or all of the dirty pages at the disk. LINUX_FADV_WRITE_WAIT, LINUX_FADV_ASYNC_WRITE: push all of the currently dirty pages at the disk. LINUX_FADV_WRITE_WAIT, LINUX_FADV_ASYNC_WRITE, LINUX_FADV_WRITE_WAIT: push all of the currently dirty pages at the disk, wait until they have been written. It should be noted that none of these operations write out the file's metadata. So unless the application is strictly performing overwrites of already-instantiated disk blocks, there are no guarantees here that the data will be available after a crash. To complete this suite of operations I guess we should have a "sync file metadata only" operation. This gives applications access to all the building blocks needed for all sorts of sync operations. But sync-metadata doesn't fit well with the fadvise() interface. Probably it should be a new syscall: sys_fmetadatasync(). The patch also diddles with the meaning of `endbyte' in sys_fadvise64_64(). It is made to represent that last affected byte in the file (ie: it is inclusive). Generally, all these byterange and pagerange functions are inclusive so we can easily represent EOF with -1. As Ulrich notes, these two functions are somewhat abusive of the fadvise() concept, which appears to be "set the future policy for this fd". But these commands are a perfect fit with the fadvise() impementation, and several of the existing fadvise() commands are synchronous and don't affect future policy either. I think we can live with the slight incongruity. Cc: Michael Kerrisk <mtk-manpages@gmx.net> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2006-03-24 11:18:04 +00:00
static int filemap_fdatawrite_range(struct address_space *mapping, loff_t start,
loff_t end)
{
return __filemap_fdatawrite_range(mapping, start, end, WB_SYNC_ALL);
}
/**
* filemap_flush - mostly a non-blocking flush
* @mapping: target address_space
*
* This is a mostly non-blocking flush. Not suitable for data-integrity
* purposes - I/O may not be started against all dirty pages.
*/
int filemap_flush(struct address_space *mapping)
{
return __filemap_fdatawrite(mapping, WB_SYNC_NONE);
}
EXPORT_SYMBOL(filemap_flush);
/**
* wait_on_page_writeback_range - wait for writeback to complete
* @mapping: target address_space
* @start: beginning page index
* @end: ending page index
*
* Wait for writeback to complete against pages indexed by start->end
* inclusive
*/
[PATCH] fadvise(): write commands Add two new linux-specific fadvise extensions(): LINUX_FADV_ASYNC_WRITE: start async writeout of any dirty pages between file offsets `offset' and `offset+len'. Any pages which are currently under writeout are skipped, whether or not they are dirty. LINUX_FADV_WRITE_WAIT: wait upon writeout of any dirty pages between file offsets `offset' and `offset+len'. By combining these two operations the application may do several things: LINUX_FADV_ASYNC_WRITE: push some or all of the dirty pages at the disk. LINUX_FADV_WRITE_WAIT, LINUX_FADV_ASYNC_WRITE: push all of the currently dirty pages at the disk. LINUX_FADV_WRITE_WAIT, LINUX_FADV_ASYNC_WRITE, LINUX_FADV_WRITE_WAIT: push all of the currently dirty pages at the disk, wait until they have been written. It should be noted that none of these operations write out the file's metadata. So unless the application is strictly performing overwrites of already-instantiated disk blocks, there are no guarantees here that the data will be available after a crash. To complete this suite of operations I guess we should have a "sync file metadata only" operation. This gives applications access to all the building blocks needed for all sorts of sync operations. But sync-metadata doesn't fit well with the fadvise() interface. Probably it should be a new syscall: sys_fmetadatasync(). The patch also diddles with the meaning of `endbyte' in sys_fadvise64_64(). It is made to represent that last affected byte in the file (ie: it is inclusive). Generally, all these byterange and pagerange functions are inclusive so we can easily represent EOF with -1. As Ulrich notes, these two functions are somewhat abusive of the fadvise() concept, which appears to be "set the future policy for this fd". But these commands are a perfect fit with the fadvise() impementation, and several of the existing fadvise() commands are synchronous and don't affect future policy either. I think we can live with the slight incongruity. Cc: Michael Kerrisk <mtk-manpages@gmx.net> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2006-03-24 11:18:04 +00:00
int wait_on_page_writeback_range(struct address_space *mapping,
pgoff_t start, pgoff_t end)
{
struct pagevec pvec;
int nr_pages;
int ret = 0;
pgoff_t index;
if (end < start)
return 0;
pagevec_init(&pvec, 0);
index = start;
while ((index <= end) &&
(nr_pages = pagevec_lookup_tag(&pvec, mapping, &index,
PAGECACHE_TAG_WRITEBACK,
min(end - index, (pgoff_t)PAGEVEC_SIZE-1) + 1)) != 0) {
unsigned i;
for (i = 0; i < nr_pages; i++) {
struct page *page = pvec.pages[i];
/* until radix tree lookup accepts end_index */
if (page->index > end)
continue;
wait_on_page_writeback(page);
if (PageError(page))
ret = -EIO;
}
pagevec_release(&pvec);
cond_resched();
}
/* Check for outstanding write errors */
if (test_and_clear_bit(AS_ENOSPC, &mapping->flags))
ret = -ENOSPC;
if (test_and_clear_bit(AS_EIO, &mapping->flags))
ret = -EIO;
return ret;
}
/**
* sync_page_range - write and wait on all pages in the passed range
* @inode: target inode
* @mapping: target address_space
* @pos: beginning offset in pages to write
* @count: number of bytes to write
*
* Write and wait upon all the pages in the passed range. This is a "data
* integrity" operation. It waits upon in-flight writeout before starting and
* waiting upon new writeout. If there was an IO error, return it.
*
* We need to re-take i_mutex during the generic_osync_inode list walk because
* it is otherwise livelockable.
*/
int sync_page_range(struct inode *inode, struct address_space *mapping,
loff_t pos, loff_t count)
{
pgoff_t start = pos >> PAGE_CACHE_SHIFT;
pgoff_t end = (pos + count - 1) >> PAGE_CACHE_SHIFT;
int ret;
if (!mapping_cap_writeback_dirty(mapping) || !count)
return 0;
ret = filemap_fdatawrite_range(mapping, pos, pos + count - 1);
if (ret == 0) {
mutex_lock(&inode->i_mutex);
ret = generic_osync_inode(inode, mapping, OSYNC_METADATA);
mutex_unlock(&inode->i_mutex);
}
if (ret == 0)
ret = wait_on_page_writeback_range(mapping, start, end);
return ret;
}
EXPORT_SYMBOL(sync_page_range);
/**
* sync_page_range_nolock
* @inode: target inode
* @mapping: target address_space
* @pos: beginning offset in pages to write
* @count: number of bytes to write
*
* Note: Holding i_mutex across sync_page_range_nolock() is not a good idea
* as it forces O_SYNC writers to different parts of the same file
* to be serialised right until io completion.
*/
int sync_page_range_nolock(struct inode *inode, struct address_space *mapping,
loff_t pos, loff_t count)
{
pgoff_t start = pos >> PAGE_CACHE_SHIFT;
pgoff_t end = (pos + count - 1) >> PAGE_CACHE_SHIFT;
int ret;
if (!mapping_cap_writeback_dirty(mapping) || !count)
return 0;
ret = filemap_fdatawrite_range(mapping, pos, pos + count - 1);
if (ret == 0)
ret = generic_osync_inode(inode, mapping, OSYNC_METADATA);
if (ret == 0)
ret = wait_on_page_writeback_range(mapping, start, end);
return ret;
}
EXPORT_SYMBOL(sync_page_range_nolock);
/**
* filemap_fdatawait - wait for all under-writeback pages to complete
* @mapping: address space structure to wait for
*
* Walk the list of under-writeback pages of the given address space
* and wait for all of them.
*/
int filemap_fdatawait(struct address_space *mapping)
{
loff_t i_size = i_size_read(mapping->host);
if (i_size == 0)
return 0;
return wait_on_page_writeback_range(mapping, 0,
(i_size - 1) >> PAGE_CACHE_SHIFT);
}
EXPORT_SYMBOL(filemap_fdatawait);
int filemap_write_and_wait(struct address_space *mapping)
{
int err = 0;
if (mapping->nrpages) {
err = filemap_fdatawrite(mapping);
/*
* Even if the above returned error, the pages may be
* written partially (e.g. -ENOSPC), so we wait for it.
* But the -EIO is special case, it may indicate the worst
* thing (e.g. bug) happened, so we avoid waiting for it.
*/
if (err != -EIO) {
int err2 = filemap_fdatawait(mapping);
if (!err)
err = err2;
}
}
return err;
}
EXPORT_SYMBOL(filemap_write_and_wait);
/**
* filemap_write_and_wait_range - write out & wait on a file range
* @mapping: the address_space for the pages
* @lstart: offset in bytes where the range starts
* @lend: offset in bytes where the range ends (inclusive)
*
* Write out and wait upon file offsets lstart->lend, inclusive.
*
* Note that `lend' is inclusive (describes the last byte to be written) so
* that this function can be used to write to the very end-of-file (end = -1).
*/
int filemap_write_and_wait_range(struct address_space *mapping,
loff_t lstart, loff_t lend)
{
int err = 0;
if (mapping->nrpages) {
err = __filemap_fdatawrite_range(mapping, lstart, lend,
WB_SYNC_ALL);
/* See comment of filemap_write_and_wait() */
if (err != -EIO) {
int err2 = wait_on_page_writeback_range(mapping,
lstart >> PAGE_CACHE_SHIFT,
lend >> PAGE_CACHE_SHIFT);
if (!err)
err = err2;
}
}
return err;
}
/**
* add_to_page_cache - add newly allocated pagecache pages
* @page: page to add
* @mapping: the page's address_space
* @offset: page index
* @gfp_mask: page allocation mode
*
* This function is used to add newly allocated pagecache pages;
* the page is new, so we can just run SetPageLocked() against it.
* The other page state flags were set by rmqueue().
*
* This function does not add the page to the LRU. The caller must do that.
*/
int add_to_page_cache(struct page *page, struct address_space *mapping,
pgoff_t offset, gfp_t gfp_mask)
{
int error = radix_tree_preload(gfp_mask & ~__GFP_HIGHMEM);
if (error == 0) {
write_lock_irq(&mapping->tree_lock);
error = radix_tree_insert(&mapping->page_tree, offset, page);
if (!error) {
page_cache_get(page);
SetPageLocked(page);
page->mapping = mapping;
page->index = offset;
mapping->nrpages++;
__inc_zone_page_state(page, NR_FILE_PAGES);
}
write_unlock_irq(&mapping->tree_lock);
radix_tree_preload_end();
}
return error;
}
EXPORT_SYMBOL(add_to_page_cache);
int add_to_page_cache_lru(struct page *page, struct address_space *mapping,
pgoff_t offset, gfp_t gfp_mask)
{
int ret = add_to_page_cache(page, mapping, offset, gfp_mask);
if (ret == 0)
lru_cache_add(page);
return ret;
}
#ifdef CONFIG_NUMA
struct page *__page_cache_alloc(gfp_t gfp)
{
if (cpuset_do_page_mem_spread()) {
int n = cpuset_mem_spread_node();
return alloc_pages_node(n, gfp, 0);
}
return alloc_pages(gfp, 0);
}
EXPORT_SYMBOL(__page_cache_alloc);
#endif
static int __sleep_on_page_lock(void *word)
{
io_schedule();
return 0;
}
/*
* In order to wait for pages to become available there must be
* waitqueues associated with pages. By using a hash table of
* waitqueues where the bucket discipline is to maintain all
* waiters on the same queue and wake all when any of the pages
* become available, and for the woken contexts to check to be
* sure the appropriate page became available, this saves space
* at a cost of "thundering herd" phenomena during rare hash
* collisions.
*/
static wait_queue_head_t *page_waitqueue(struct page *page)
{
const struct zone *zone = page_zone(page);
return &zone->wait_table[hash_ptr(page, zone->wait_table_bits)];
}
static inline void wake_up_page(struct page *page, int bit)
{
__wake_up_bit(page_waitqueue(page), &page->flags, bit);
}
void fastcall wait_on_page_bit(struct page *page, int bit_nr)
{
DEFINE_WAIT_BIT(wait, &page->flags, bit_nr);
if (test_bit(bit_nr, &page->flags))
__wait_on_bit(page_waitqueue(page), &wait, sync_page,
TASK_UNINTERRUPTIBLE);
}
EXPORT_SYMBOL(wait_on_page_bit);
/**
* unlock_page - unlock a locked page
* @page: the page
*
* Unlocks the page and wakes up sleepers in ___wait_on_page_locked().
* Also wakes sleepers in wait_on_page_writeback() because the wakeup
* mechananism between PageLocked pages and PageWriteback pages is shared.
* But that's OK - sleepers in wait_on_page_writeback() just go back to sleep.
*
* The first mb is necessary to safely close the critical section opened by the
* TestSetPageLocked(), the second mb is necessary to enforce ordering between
* the clear_bit and the read of the waitqueue (to avoid SMP races with a
* parallel wait_on_page_locked()).
*/
void fastcall unlock_page(struct page *page)
{
smp_mb__before_clear_bit();
if (!TestClearPageLocked(page))
BUG();
smp_mb__after_clear_bit();
wake_up_page(page, PG_locked);
}
EXPORT_SYMBOL(unlock_page);
/**
* end_page_writeback - end writeback against a page
* @page: the page
*/
void end_page_writeback(struct page *page)
{
if (!TestClearPageReclaim(page) || rotate_reclaimable_page(page)) {
if (!test_clear_page_writeback(page))
BUG();
}
smp_mb__after_clear_bit();
wake_up_page(page, PG_writeback);
}
EXPORT_SYMBOL(end_page_writeback);
/**
* __lock_page - get a lock on the page, assuming we need to sleep to get it
* @page: the page to lock
*
* Ugly. Running sync_page() in state TASK_UNINTERRUPTIBLE is scary. If some
* random driver's requestfn sets TASK_RUNNING, we could busywait. However
* chances are that on the second loop, the block layer's plug list is empty,
* so sync_page() will then return in state TASK_UNINTERRUPTIBLE.
*/
void fastcall __lock_page(struct page *page)
{
DEFINE_WAIT_BIT(wait, &page->flags, PG_locked);
__wait_on_bit_lock(page_waitqueue(page), &wait, sync_page,
TASK_UNINTERRUPTIBLE);
}
EXPORT_SYMBOL(__lock_page);
/*
* Variant of lock_page that does not require the caller to hold a reference
* on the page's mapping.
*/
void fastcall __lock_page_nosync(struct page *page)
{
DEFINE_WAIT_BIT(wait, &page->flags, PG_locked);
__wait_on_bit_lock(page_waitqueue(page), &wait, __sleep_on_page_lock,
TASK_UNINTERRUPTIBLE);
}
/**
* find_get_page - find and get a page reference
* @mapping: the address_space to search
* @offset: the page index
*
* Is there a pagecache struct page at the given (mapping, offset) tuple?
* If yes, increment its refcount and return it; if no, return NULL.
*/
struct page * find_get_page(struct address_space *mapping, unsigned long offset)
{
struct page *page;
read_lock_irq(&mapping->tree_lock);
page = radix_tree_lookup(&mapping->page_tree, offset);
if (page)
page_cache_get(page);
read_unlock_irq(&mapping->tree_lock);
return page;
}
EXPORT_SYMBOL(find_get_page);
/**
* find_lock_page - locate, pin and lock a pagecache page
* @mapping: the address_space to search
* @offset: the page index
*
* Locates the desired pagecache page, locks it, increments its reference
* count and returns its address.
*
* Returns zero if the page was not present. find_lock_page() may sleep.
*/
struct page *find_lock_page(struct address_space *mapping,
unsigned long offset)
{
struct page *page;
read_lock_irq(&mapping->tree_lock);
repeat:
page = radix_tree_lookup(&mapping->page_tree, offset);
if (page) {
page_cache_get(page);
if (TestSetPageLocked(page)) {
read_unlock_irq(&mapping->tree_lock);
__lock_page(page);
read_lock_irq(&mapping->tree_lock);
/* Has the page been truncated while we slept? */
if (unlikely(page->mapping != mapping ||
page->index != offset)) {
unlock_page(page);
page_cache_release(page);
goto repeat;
}
}
}
read_unlock_irq(&mapping->tree_lock);
return page;
}
EXPORT_SYMBOL(find_lock_page);
/**
* find_or_create_page - locate or add a pagecache page
* @mapping: the page's address_space
* @index: the page's index into the mapping
* @gfp_mask: page allocation mode
*
* Locates a page in the pagecache. If the page is not present, a new page
* is allocated using @gfp_mask and is added to the pagecache and to the VM's
* LRU list. The returned page is locked and has its reference count
* incremented.
*
* find_or_create_page() may sleep, even if @gfp_flags specifies an atomic
* allocation!
*
* find_or_create_page() returns the desired page's address, or zero on
* memory exhaustion.
*/
struct page *find_or_create_page(struct address_space *mapping,
unsigned long index, gfp_t gfp_mask)
{
struct page *page, *cached_page = NULL;
int err;
repeat:
page = find_lock_page(mapping, index);
if (!page) {
if (!cached_page) {
cached_page = alloc_page(gfp_mask);
if (!cached_page)
return NULL;
}
err = add_to_page_cache_lru(cached_page, mapping,
index, gfp_mask);
if (!err) {
page = cached_page;
cached_page = NULL;
} else if (err == -EEXIST)
goto repeat;
}
if (cached_page)
page_cache_release(cached_page);
return page;
}
EXPORT_SYMBOL(find_or_create_page);
/**
* find_get_pages - gang pagecache lookup
* @mapping: The address_space to search
* @start: The starting page index
* @nr_pages: The maximum number of pages
* @pages: Where the resulting pages are placed
*
* find_get_pages() will search for and return a group of up to
* @nr_pages pages in the mapping. The pages are placed at @pages.
* find_get_pages() takes a reference against the returned pages.
*
* The search returns a group of mapping-contiguous pages with ascending
* indexes. There may be holes in the indices due to not-present pages.
*
* find_get_pages() returns the number of pages which were found.
*/
unsigned find_get_pages(struct address_space *mapping, pgoff_t start,
unsigned int nr_pages, struct page **pages)
{
unsigned int i;
unsigned int ret;
read_lock_irq(&mapping->tree_lock);
ret = radix_tree_gang_lookup(&mapping->page_tree,
(void **)pages, start, nr_pages);
for (i = 0; i < ret; i++)
page_cache_get(pages[i]);
read_unlock_irq(&mapping->tree_lock);
return ret;
}
/**
* find_get_pages_contig - gang contiguous pagecache lookup
* @mapping: The address_space to search
* @index: The starting page index
* @nr_pages: The maximum number of pages
* @pages: Where the resulting pages are placed
*
* find_get_pages_contig() works exactly like find_get_pages(), except
* that the returned number of pages are guaranteed to be contiguous.
*
* find_get_pages_contig() returns the number of pages which were found.
*/
unsigned find_get_pages_contig(struct address_space *mapping, pgoff_t index,
unsigned int nr_pages, struct page **pages)
{
unsigned int i;
unsigned int ret;
read_lock_irq(&mapping->tree_lock);
ret = radix_tree_gang_lookup(&mapping->page_tree,
(void **)pages, index, nr_pages);
for (i = 0; i < ret; i++) {
if (pages[i]->mapping == NULL || pages[i]->index != index)
break;
page_cache_get(pages[i]);
index++;
}
read_unlock_irq(&mapping->tree_lock);
return i;
}
/**
* find_get_pages_tag - find and return pages that match @tag
* @mapping: the address_space to search
* @index: the starting page index
* @tag: the tag index
* @nr_pages: the maximum number of pages
* @pages: where the resulting pages are placed
*
* Like find_get_pages, except we only return pages which are tagged with
* @tag. We update @index to index the next page for the traversal.
*/
unsigned find_get_pages_tag(struct address_space *mapping, pgoff_t *index,
int tag, unsigned int nr_pages, struct page **pages)
{
unsigned int i;
unsigned int ret;
read_lock_irq(&mapping->tree_lock);
ret = radix_tree_gang_lookup_tag(&mapping->page_tree,
(void **)pages, *index, nr_pages, tag);
for (i = 0; i < ret; i++)
page_cache_get(pages[i]);
if (ret)
*index = pages[ret - 1]->index + 1;
read_unlock_irq(&mapping->tree_lock);
return ret;
}
/**
* grab_cache_page_nowait - returns locked page at given index in given cache
* @mapping: target address_space
* @index: the page index
*
* Same as grab_cache_page(), but do not wait if the page is unavailable.
* This is intended for speculative data generators, where the data can
* be regenerated if the page couldn't be grabbed. This routine should
* be safe to call while holding the lock for another page.
*
* Clear __GFP_FS when allocating the page to avoid recursion into the fs
* and deadlock against the caller's locked page.
*/
struct page *
grab_cache_page_nowait(struct address_space *mapping, unsigned long index)
{
struct page *page = find_get_page(mapping, index);
if (page) {
if (!TestSetPageLocked(page))
return page;
page_cache_release(page);
return NULL;
}
page = __page_cache_alloc(mapping_gfp_mask(mapping) & ~__GFP_FS);
if (page && add_to_page_cache_lru(page, mapping, index, GFP_KERNEL)) {
page_cache_release(page);
page = NULL;
}
return page;
}
EXPORT_SYMBOL(grab_cache_page_nowait);
[PATCH] readahead: backoff on I/O error Backoff readahead size exponentially on I/O error. Michael Tokarev <mjt@tls.msk.ru> described the problem as: [QUOTE] Suppose there's a CD-rom with a scratch/etc, one sector is unreadable. In order to "fix" it, one have to read it and write to another CD-rom, or something.. or just ignore the error (if it's just a skip in a video stream). Let's assume the unreadable block is number U. But current behavior is just insane. An application requests block number N, which is before U. Kernel tries to read-ahead blocks N..U. Cdrom drive tries to read it, re-read it.. for some time. Finally, when all the N..U-1 blocks are read, kernel returns block number N (as requested) to an application, successefully. Now an app requests block number N+1, and kernel tries to read blocks N+1..U+1. Retrying again as in previous step. And so on, up to when an app requests block number U-1. And when, finally, it requests block U, it receives read error. So, kernel currentry tries to re-read the same failing block as many times as the current readahead value (256 (times?) by default). This whole process already killed my cdrom drive (I posted about it to LKML several months ago) - literally, the drive has fried, and does not work anymore. Ofcourse that problem was a bug in firmware (or whatever) of the drive *too*, but.. main problem with that is current readahead logic as described above. [/QUOTE] Which was confirmed by Jens Axboe <axboe@suse.de>: [QUOTE] For ide-cd, it tends do only end the first part of the request on a medium error. So you may see a lot of repeats :/ [/QUOTE] With this patch, retries are expected to be reduced from, say, 256, to 5. [akpm@osdl.org: cleanups] Signed-off-by: Wu Fengguang <wfg@mail.ustc.edu.cn> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2006-06-25 12:48:43 +00:00
/*
* CD/DVDs are error prone. When a medium error occurs, the driver may fail
* a _large_ part of the i/o request. Imagine the worst scenario:
*
* ---R__________________________________________B__________
* ^ reading here ^ bad block(assume 4k)
*
* read(R) => miss => readahead(R...B) => media error => frustrating retries
* => failing the whole request => read(R) => read(R+1) =>
* readahead(R+1...B+1) => bang => read(R+2) => read(R+3) =>
* readahead(R+3...B+2) => bang => read(R+3) => read(R+4) =>
* readahead(R+4...B+3) => bang => read(R+4) => read(R+5) => ......
*
* It is going insane. Fix it by quickly scaling down the readahead size.
*/
static void shrink_readahead_size_eio(struct file *filp,
struct file_ra_state *ra)
{
if (!ra->ra_pages)
return;
ra->ra_pages /= 4;
}
/**
* do_generic_mapping_read - generic file read routine
* @mapping: address_space to be read
* @_ra: file's readahead state
* @filp: the file to read
* @ppos: current file position
* @desc: read_descriptor
* @actor: read method
*
* This is a generic file read routine, and uses the
* mapping->a_ops->readpage() function for the actual low-level stuff.
*
* This is really ugly. But the goto's actually try to clarify some
* of the logic when it comes to error handling etc.
*
* Note the struct file* is only passed for the use of readpage.
* It may be NULL.
*/
void do_generic_mapping_read(struct address_space *mapping,
struct file_ra_state *_ra,
struct file *filp,
loff_t *ppos,
read_descriptor_t *desc,
read_actor_t actor)
{
struct inode *inode = mapping->host;
unsigned long index;
unsigned long end_index;
unsigned long offset;
unsigned long last_index;
unsigned long next_index;
unsigned long prev_index;
unsigned int prev_offset;
loff_t isize;
struct page *cached_page;
int error;
struct file_ra_state ra = *_ra;
cached_page = NULL;
index = *ppos >> PAGE_CACHE_SHIFT;
next_index = index;
prev_index = ra.prev_page;
prev_offset = ra.offset;
last_index = (*ppos + desc->count + PAGE_CACHE_SIZE-1) >> PAGE_CACHE_SHIFT;
offset = *ppos & ~PAGE_CACHE_MASK;
isize = i_size_read(inode);
if (!isize)
goto out;
end_index = (isize - 1) >> PAGE_CACHE_SHIFT;
for (;;) {
struct page *page;
unsigned long nr, ret;
/* nr is the maximum number of bytes to copy from this page */
nr = PAGE_CACHE_SIZE;
if (index >= end_index) {
if (index > end_index)
goto out;
nr = ((isize - 1) & ~PAGE_CACHE_MASK) + 1;
if (nr <= offset) {
goto out;
}
}
nr = nr - offset;
cond_resched();
if (index == next_index)
next_index = page_cache_readahead(mapping, &ra, filp,
index, last_index - index);
find_page:
page = find_get_page(mapping, index);
if (unlikely(page == NULL)) {
handle_ra_miss(mapping, &ra, index);
goto no_cached_page;
}
if (!PageUptodate(page))
goto page_not_up_to_date;
page_ok:
/* If users can be writing to this page using arbitrary
* virtual addresses, take care about potential aliasing
* before reading the page on the kernel side.
*/
if (mapping_writably_mapped(mapping))
flush_dcache_page(page);
/*
* When a sequential read accesses a page several times,
* only mark it as accessed the first time.
*/
if (prev_index != index || offset != prev_offset)
mark_page_accessed(page);
prev_index = index;
/*
* Ok, we have the page, and it's up-to-date, so
* now we can copy it to user space...
*
* The actor routine returns how many bytes were actually used..
* NOTE! This may not be the same as how much of a user buffer
* we filled up (we may be padding etc), so we can only update
* "pos" here (the actor routine has to update the user buffer
* pointers and the remaining count).
*/
ret = actor(desc, page, offset, nr);
offset += ret;
index += offset >> PAGE_CACHE_SHIFT;
offset &= ~PAGE_CACHE_MASK;
prev_offset = ra.offset = offset;
page_cache_release(page);
if (ret == nr && desc->count)
continue;
goto out;
page_not_up_to_date:
/* Get exclusive access to the page ... */
lock_page(page);
/* Did it get truncated before we got the lock? */
if (!page->mapping) {
unlock_page(page);
page_cache_release(page);
continue;
}
/* Did somebody else fill it already? */
if (PageUptodate(page)) {
unlock_page(page);
goto page_ok;
}
readpage:
/* Start the actual read. The read will unlock the page. */
error = mapping->a_ops->readpage(filp, page);
if (unlikely(error)) {
if (error == AOP_TRUNCATED_PAGE) {
page_cache_release(page);
goto find_page;
}
goto readpage_error;
}
if (!PageUptodate(page)) {
lock_page(page);
if (!PageUptodate(page)) {
if (page->mapping == NULL) {
/*
* invalidate_inode_pages got it
*/
unlock_page(page);
page_cache_release(page);
goto find_page;
}
unlock_page(page);
error = -EIO;
[PATCH] readahead: backoff on I/O error Backoff readahead size exponentially on I/O error. Michael Tokarev <mjt@tls.msk.ru> described the problem as: [QUOTE] Suppose there's a CD-rom with a scratch/etc, one sector is unreadable. In order to "fix" it, one have to read it and write to another CD-rom, or something.. or just ignore the error (if it's just a skip in a video stream). Let's assume the unreadable block is number U. But current behavior is just insane. An application requests block number N, which is before U. Kernel tries to read-ahead blocks N..U. Cdrom drive tries to read it, re-read it.. for some time. Finally, when all the N..U-1 blocks are read, kernel returns block number N (as requested) to an application, successefully. Now an app requests block number N+1, and kernel tries to read blocks N+1..U+1. Retrying again as in previous step. And so on, up to when an app requests block number U-1. And when, finally, it requests block U, it receives read error. So, kernel currentry tries to re-read the same failing block as many times as the current readahead value (256 (times?) by default). This whole process already killed my cdrom drive (I posted about it to LKML several months ago) - literally, the drive has fried, and does not work anymore. Ofcourse that problem was a bug in firmware (or whatever) of the drive *too*, but.. main problem with that is current readahead logic as described above. [/QUOTE] Which was confirmed by Jens Axboe <axboe@suse.de>: [QUOTE] For ide-cd, it tends do only end the first part of the request on a medium error. So you may see a lot of repeats :/ [/QUOTE] With this patch, retries are expected to be reduced from, say, 256, to 5. [akpm@osdl.org: cleanups] Signed-off-by: Wu Fengguang <wfg@mail.ustc.edu.cn> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2006-06-25 12:48:43 +00:00
shrink_readahead_size_eio(filp, &ra);
goto readpage_error;
}
unlock_page(page);
}
/*
* i_size must be checked after we have done ->readpage.
*
* Checking i_size after the readpage allows us to calculate
* the correct value for "nr", which means the zero-filled
* part of the page is not copied back to userspace (unless
* another truncate extends the file - this is desired though).
*/
isize = i_size_read(inode);
end_index = (isize - 1) >> PAGE_CACHE_SHIFT;
if (unlikely(!isize || index > end_index)) {
page_cache_release(page);
goto out;
}
/* nr is the maximum number of bytes to copy from this page */
nr = PAGE_CACHE_SIZE;
if (index == end_index) {
nr = ((isize - 1) & ~PAGE_CACHE_MASK) + 1;
if (nr <= offset) {
page_cache_release(page);
goto out;
}
}
nr = nr - offset;
goto page_ok;
readpage_error:
/* UHHUH! A synchronous read error occurred. Report it */
desc->error = error;
page_cache_release(page);
goto out;
no_cached_page:
/*
* Ok, it wasn't cached, so we need to create a new
* page..
*/
if (!cached_page) {
cached_page = page_cache_alloc_cold(mapping);
if (!cached_page) {
desc->error = -ENOMEM;
goto out;
}
}
error = add_to_page_cache_lru(cached_page, mapping,
index, GFP_KERNEL);
if (error) {
if (error == -EEXIST)
goto find_page;
desc->error = error;
goto out;
}
page = cached_page;
cached_page = NULL;
goto readpage;
}
out:
*_ra = ra;
*ppos = ((loff_t) index << PAGE_CACHE_SHIFT) + offset;
if (cached_page)
page_cache_release(cached_page);
if (filp)
file_accessed(filp);
}
EXPORT_SYMBOL(do_generic_mapping_read);
int file_read_actor(read_descriptor_t *desc, struct page *page,
unsigned long offset, unsigned long size)
{
char *kaddr;
unsigned long left, count = desc->count;
if (size > count)
size = count;
/*
* Faults on the destination of a read are common, so do it before
* taking the kmap.
*/
if (!fault_in_pages_writeable(desc->arg.buf, size)) {
kaddr = kmap_atomic(page, KM_USER0);
left = __copy_to_user_inatomic(desc->arg.buf,
kaddr + offset, size);
kunmap_atomic(kaddr, KM_USER0);
if (left == 0)
goto success;
}
/* Do it the slow way */
kaddr = kmap(page);
left = __copy_to_user(desc->arg.buf, kaddr + offset, size);
kunmap(page);
if (left) {
size -= left;
desc->error = -EFAULT;
}
success:
desc->count = count - size;
desc->written += size;
desc->arg.buf += size;
return size;
}
/**
* generic_file_aio_read - generic filesystem read routine
* @iocb: kernel I/O control block
* @iov: io vector request
* @nr_segs: number of segments in the iovec
* @pos: current file position
*
* This is the "read()" routine for all filesystems
* that can use the page cache directly.
*/
ssize_t
generic_file_aio_read(struct kiocb *iocb, const struct iovec *iov,
unsigned long nr_segs, loff_t pos)
{
struct file *filp = iocb->ki_filp;
ssize_t retval;
unsigned long seg;
size_t count;
loff_t *ppos = &iocb->ki_pos;
count = 0;
for (seg = 0; seg < nr_segs; seg++) {
const struct iovec *iv = &iov[seg];
/*
* If any segment has a negative length, or the cumulative
* length ever wraps negative then return -EINVAL.
*/
count += iv->iov_len;
if (unlikely((ssize_t)(count|iv->iov_len) < 0))
return -EINVAL;
if (access_ok(VERIFY_WRITE, iv->iov_base, iv->iov_len))
continue;
if (seg == 0)
return -EFAULT;
nr_segs = seg;
count -= iv->iov_len; /* This segment is no good */
break;
}
/* coalesce the iovecs and go direct-to-BIO for O_DIRECT */
if (filp->f_flags & O_DIRECT) {
loff_t size;
struct address_space *mapping;
struct inode *inode;
mapping = filp->f_mapping;
inode = mapping->host;
retval = 0;
if (!count)
goto out; /* skip atime */
size = i_size_read(inode);
if (pos < size) {
retval = generic_file_direct_IO(READ, iocb,
iov, pos, nr_segs);
if (retval > 0)
*ppos = pos + retval;
}
if (likely(retval != 0)) {
file_accessed(filp);
goto out;
}
}
retval = 0;
if (count) {
for (seg = 0; seg < nr_segs; seg++) {
read_descriptor_t desc;
desc.written = 0;
desc.arg.buf = iov[seg].iov_base;
desc.count = iov[seg].iov_len;
if (desc.count == 0)
continue;
desc.error = 0;
do_generic_file_read(filp,ppos,&desc,file_read_actor);
retval += desc.written;
[PATCH] fs: error case fix in __generic_file_aio_read When __generic_file_aio_read() hits an error during reading, it reports the error iff nothing has successfully been read yet. This is condition - when an error occurs, if nothing has been read/written, report the error code; otherwise, report the amount of bytes successfully transferred upto that point. This corner case can be exposed by performing readv(2) with the following iov. iov[0] = len0 @ ptr0 iov[1] = len1 @ NULL (or any other invalid pointer) iov[2] = len2 @ ptr2 When file size is enough, performing above readv(2) results in len0 bytes from file_pos @ ptr0 len2 bytes from file_pos + len0 @ ptr2 And the return value is len0 + len2. Test program is attached to this mail. This patch makes __generic_file_aio_read()'s error handling identical to other functions. #include <stdio.h> #include <stdlib.h> #include <sys/types.h> #include <sys/stat.h> #include <fcntl.h> #include <unistd.h> #include <sys/uio.h> #include <errno.h> #include <string.h> int main(int argc, char **argv) { const char *path; struct stat stbuf; size_t len0, len1; void *buf0, *buf1; struct iovec iov[3]; int fd, i; ssize_t ret; if (argc < 2) { fprintf(stderr, "Usage: testreadv path (better be a " "small text file)\n"); return 1; } path = argv[1]; if (stat(path, &stbuf) < 0) { perror("stat"); return 1; } len0 = stbuf.st_size / 2; len1 = stbuf.st_size - len0; if (!len0 || !len1) { fprintf(stderr, "Dude, file is too small\n"); return 1; } if ((fd = open(path, O_RDONLY)) < 0) { perror("open"); return 1; } if (!(buf0 = malloc(len0)) || !(buf1 = malloc(len1))) { perror("malloc"); return 1; } memset(buf0, 0, len0); memset(buf1, 0, len1); iov[0].iov_base = buf0; iov[0].iov_len = len0; iov[1].iov_base = NULL; iov[1].iov_len = len1; iov[2].iov_base = buf1; iov[2].iov_len = len1; printf("vector "); for (i = 0; i < 3; i++) printf("%p:%zu ", iov[i].iov_base, iov[i].iov_len); printf("\n"); ret = readv(fd, iov, 3); if (ret < 0) perror("readv"); printf("readv returned %zd\nbuf0 = [%s]\nbuf1 = [%s]\n", ret, (char *)buf0, (char *)buf1); return 0; } Signed-off-by: Tejun Heo <htejun@gmail.com> Cc: Benjamin LaHaise <bcrl@kvack.org> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2005-10-30 23:02:40 +00:00
if (desc.error) {
retval = retval ?: desc.error;
break;
}
}
}
out:
return retval;
}
EXPORT_SYMBOL(generic_file_aio_read);
int file_send_actor(read_descriptor_t * desc, struct page *page, unsigned long offset, unsigned long size)
{
ssize_t written;
unsigned long count = desc->count;
struct file *file = desc->arg.data;
if (size > count)
size = count;
written = file->f_op->sendpage(file, page, offset,
size, &file->f_pos, size<count);
if (written < 0) {
desc->error = written;
written = 0;
}
desc->count = count - written;
desc->written += written;
return written;
}
ssize_t generic_file_sendfile(struct file *in_file, loff_t *ppos,
size_t count, read_actor_t actor, void *target)
{
read_descriptor_t desc;
if (!count)
return 0;
desc.written = 0;
desc.count = count;
desc.arg.data = target;
desc.error = 0;
do_generic_file_read(in_file, ppos, &desc, actor);
if (desc.written)
return desc.written;
return desc.error;
}
EXPORT_SYMBOL(generic_file_sendfile);
static ssize_t
do_readahead(struct address_space *mapping, struct file *filp,
unsigned long index, unsigned long nr)
{
if (!mapping || !mapping->a_ops || !mapping->a_ops->readpage)
return -EINVAL;
force_page_cache_readahead(mapping, filp, index,
max_sane_readahead(nr));
return 0;
}
asmlinkage ssize_t sys_readahead(int fd, loff_t offset, size_t count)
{
ssize_t ret;
struct file *file;
ret = -EBADF;
file = fget(fd);
if (file) {
if (file->f_mode & FMODE_READ) {
struct address_space *mapping = file->f_mapping;
unsigned long start = offset >> PAGE_CACHE_SHIFT;
unsigned long end = (offset + count - 1) >> PAGE_CACHE_SHIFT;
unsigned long len = end - start + 1;
ret = do_readahead(mapping, file, start, len);
}
fput(file);
}
return ret;
}
#ifdef CONFIG_MMU
static int FASTCALL(page_cache_read(struct file * file, unsigned long offset));
/**
* page_cache_read - adds requested page to the page cache if not already there
* @file: file to read
* @offset: page index
*
* This adds the requested page to the page cache if it isn't already there,
* and schedules an I/O to read in its contents from disk.
*/
static int fastcall page_cache_read(struct file * file, unsigned long offset)
{
struct address_space *mapping = file->f_mapping;
struct page *page;
int ret;
do {
page = page_cache_alloc_cold(mapping);
if (!page)
return -ENOMEM;
ret = add_to_page_cache_lru(page, mapping, offset, GFP_KERNEL);
if (ret == 0)
ret = mapping->a_ops->readpage(file, page);
else if (ret == -EEXIST)
ret = 0; /* losing race to add is OK */
page_cache_release(page);
} while (ret == AOP_TRUNCATED_PAGE);
return ret;
}
#define MMAP_LOTSAMISS (100)
/**
* filemap_nopage - read in file data for page fault handling
* @area: the applicable vm_area
* @address: target address to read in
* @type: returned with VM_FAULT_{MINOR,MAJOR} if not %NULL
*
* filemap_nopage() is invoked via the vma operations vector for a
* mapped memory region to read in file data during a page fault.
*
* The goto's are kind of ugly, but this streamlines the normal case of having
* it in the page cache, and handles the special cases reasonably without
* having a lot of duplicated code.
*/
struct page *filemap_nopage(struct vm_area_struct *area,
unsigned long address, int *type)
{
int error;
struct file *file = area->vm_file;
struct address_space *mapping = file->f_mapping;
struct file_ra_state *ra = &file->f_ra;
struct inode *inode = mapping->host;
struct page *page;
unsigned long size, pgoff;
int did_readaround = 0, majmin = VM_FAULT_MINOR;
pgoff = ((address-area->vm_start) >> PAGE_CACHE_SHIFT) + area->vm_pgoff;
retry_all:
size = (i_size_read(inode) + PAGE_CACHE_SIZE - 1) >> PAGE_CACHE_SHIFT;
if (pgoff >= size)
goto outside_data_content;
/* If we don't want any read-ahead, don't bother */
if (VM_RandomReadHint(area))
goto no_cached_page;
/*
* The readahead code wants to be told about each and every page
* so it can build and shrink its windows appropriately
*
* For sequential accesses, we use the generic readahead logic.
*/
if (VM_SequentialReadHint(area))
page_cache_readahead(mapping, ra, file, pgoff, 1);
/*
* Do we have something in the page cache already?
*/
retry_find:
page = find_get_page(mapping, pgoff);
if (!page) {
unsigned long ra_pages;
if (VM_SequentialReadHint(area)) {
handle_ra_miss(mapping, ra, pgoff);
goto no_cached_page;
}
ra->mmap_miss++;
/*
* Do we miss much more than hit in this file? If so,
* stop bothering with read-ahead. It will only hurt.
*/
if (ra->mmap_miss > ra->mmap_hit + MMAP_LOTSAMISS)
goto no_cached_page;
/*
* To keep the pgmajfault counter straight, we need to
* check did_readaround, as this is an inner loop.
*/
if (!did_readaround) {
majmin = VM_FAULT_MAJOR;
[PATCH] Light weight event counters The remaining counters in page_state after the zoned VM counter patches have been applied are all just for show in /proc/vmstat. They have no essential function for the VM. We use a simple increment of per cpu variables. In order to avoid the most severe races we disable preempt. Preempt does not prevent the race between an increment and an interrupt handler incrementing the same statistics counter. However, that race is exceedingly rare, we may only loose one increment or so and there is no requirement (at least not in kernel) that the vm event counters have to be accurate. In the non preempt case this results in a simple increment for each counter. For many architectures this will be reduced by the compiler to a single instruction. This single instruction is atomic for i386 and x86_64. And therefore even the rare race condition in an interrupt is avoided for both architectures in most cases. The patchset also adds an off switch for embedded systems that allows a building of linux kernels without these counters. The implementation of these counters is through inline code that hopefully results in only a single instruction increment instruction being emitted (i386, x86_64) or in the increment being hidden though instruction concurrency (EPIC architectures such as ia64 can get that done). Benefits: - VM event counter operations usually reduce to a single inline instruction on i386 and x86_64. - No interrupt disable, only preempt disable for the preempt case. Preempt disable can also be avoided by moving the counter into a spinlock. - Handling is similar to zoned VM counters. - Simple and easily extendable. - Can be omitted to reduce memory use for embedded use. References: RFC http://marc.theaimsgroup.com/?l=linux-kernel&m=113512330605497&w=2 RFC http://marc.theaimsgroup.com/?l=linux-kernel&m=114988082814934&w=2 local_t http://marc.theaimsgroup.com/?l=linux-kernel&m=114991748606690&w=2 V2 http://marc.theaimsgroup.com/?t=115014808400007&r=1&w=2 V3 http://marc.theaimsgroup.com/?l=linux-kernel&m=115024767022346&w=2 V4 http://marc.theaimsgroup.com/?l=linux-kernel&m=115047968808926&w=2 Signed-off-by: Christoph Lameter <clameter@sgi.com> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2006-06-30 08:55:45 +00:00
count_vm_event(PGMAJFAULT);
}
did_readaround = 1;
ra_pages = max_sane_readahead(file->f_ra.ra_pages);
if (ra_pages) {
pgoff_t start = 0;
if (pgoff > ra_pages / 2)
start = pgoff - ra_pages / 2;
do_page_cache_readahead(mapping, file, start, ra_pages);
}
page = find_get_page(mapping, pgoff);
if (!page)
goto no_cached_page;
}
if (!did_readaround)
ra->mmap_hit++;
/*
* Ok, found a page in the page cache, now we need to check
* that it's up-to-date.
*/
if (!PageUptodate(page))
goto page_not_uptodate;
success:
/*
* Found the page and have a reference on it.
*/
mark_page_accessed(page);
if (type)
*type = majmin;
return page;
outside_data_content:
/*
* An external ptracer can access pages that normally aren't
* accessible..
*/
if (area->vm_mm == current->mm)
return NOPAGE_SIGBUS;
/* Fall through to the non-read-ahead case */
no_cached_page:
/*
* We're only likely to ever get here if MADV_RANDOM is in
* effect.
*/
error = page_cache_read(file, pgoff);
/*
* The page we want has now been added to the page cache.
* In the unlikely event that someone removed it in the
* meantime, we'll just come back here and read it again.
*/
if (error >= 0)
goto retry_find;
/*
* An error return from page_cache_read can result if the
* system is low on memory, or a problem occurs while trying
* to schedule I/O.
*/
if (error == -ENOMEM)
return NOPAGE_OOM;
return NOPAGE_SIGBUS;
page_not_uptodate:
if (!did_readaround) {
majmin = VM_FAULT_MAJOR;
[PATCH] Light weight event counters The remaining counters in page_state after the zoned VM counter patches have been applied are all just for show in /proc/vmstat. They have no essential function for the VM. We use a simple increment of per cpu variables. In order to avoid the most severe races we disable preempt. Preempt does not prevent the race between an increment and an interrupt handler incrementing the same statistics counter. However, that race is exceedingly rare, we may only loose one increment or so and there is no requirement (at least not in kernel) that the vm event counters have to be accurate. In the non preempt case this results in a simple increment for each counter. For many architectures this will be reduced by the compiler to a single instruction. This single instruction is atomic for i386 and x86_64. And therefore even the rare race condition in an interrupt is avoided for both architectures in most cases. The patchset also adds an off switch for embedded systems that allows a building of linux kernels without these counters. The implementation of these counters is through inline code that hopefully results in only a single instruction increment instruction being emitted (i386, x86_64) or in the increment being hidden though instruction concurrency (EPIC architectures such as ia64 can get that done). Benefits: - VM event counter operations usually reduce to a single inline instruction on i386 and x86_64. - No interrupt disable, only preempt disable for the preempt case. Preempt disable can also be avoided by moving the counter into a spinlock. - Handling is similar to zoned VM counters. - Simple and easily extendable. - Can be omitted to reduce memory use for embedded use. References: RFC http://marc.theaimsgroup.com/?l=linux-kernel&m=113512330605497&w=2 RFC http://marc.theaimsgroup.com/?l=linux-kernel&m=114988082814934&w=2 local_t http://marc.theaimsgroup.com/?l=linux-kernel&m=114991748606690&w=2 V2 http://marc.theaimsgroup.com/?t=115014808400007&r=1&w=2 V3 http://marc.theaimsgroup.com/?l=linux-kernel&m=115024767022346&w=2 V4 http://marc.theaimsgroup.com/?l=linux-kernel&m=115047968808926&w=2 Signed-off-by: Christoph Lameter <clameter@sgi.com> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2006-06-30 08:55:45 +00:00
count_vm_event(PGMAJFAULT);
}
/*
* Umm, take care of errors if the page isn't up-to-date.
* Try to re-read it _once_. We do this synchronously,
* because there really aren't any performance issues here
* and we need to check for errors.
*/
lock_page(page);
/* Somebody truncated the page on us? */
if (!page->mapping) {
unlock_page(page);
page_cache_release(page);
goto retry_all;
}
/* Somebody else successfully read it in? */
if (PageUptodate(page)) {
unlock_page(page);
goto success;
}
ClearPageError(page);
error = mapping->a_ops->readpage(file, page);
if (!error) {
wait_on_page_locked(page);
if (PageUptodate(page))
goto success;
} else if (error == AOP_TRUNCATED_PAGE) {
page_cache_release(page);
goto retry_find;
}
/*
* Things didn't work out. Return zero to tell the
* mm layer so, possibly freeing the page cache page first.
*/
[PATCH] readahead: backoff on I/O error Backoff readahead size exponentially on I/O error. Michael Tokarev <mjt@tls.msk.ru> described the problem as: [QUOTE] Suppose there's a CD-rom with a scratch/etc, one sector is unreadable. In order to "fix" it, one have to read it and write to another CD-rom, or something.. or just ignore the error (if it's just a skip in a video stream). Let's assume the unreadable block is number U. But current behavior is just insane. An application requests block number N, which is before U. Kernel tries to read-ahead blocks N..U. Cdrom drive tries to read it, re-read it.. for some time. Finally, when all the N..U-1 blocks are read, kernel returns block number N (as requested) to an application, successefully. Now an app requests block number N+1, and kernel tries to read blocks N+1..U+1. Retrying again as in previous step. And so on, up to when an app requests block number U-1. And when, finally, it requests block U, it receives read error. So, kernel currentry tries to re-read the same failing block as many times as the current readahead value (256 (times?) by default). This whole process already killed my cdrom drive (I posted about it to LKML several months ago) - literally, the drive has fried, and does not work anymore. Ofcourse that problem was a bug in firmware (or whatever) of the drive *too*, but.. main problem with that is current readahead logic as described above. [/QUOTE] Which was confirmed by Jens Axboe <axboe@suse.de>: [QUOTE] For ide-cd, it tends do only end the first part of the request on a medium error. So you may see a lot of repeats :/ [/QUOTE] With this patch, retries are expected to be reduced from, say, 256, to 5. [akpm@osdl.org: cleanups] Signed-off-by: Wu Fengguang <wfg@mail.ustc.edu.cn> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2006-06-25 12:48:43 +00:00
shrink_readahead_size_eio(file, ra);
page_cache_release(page);
return NOPAGE_SIGBUS;
}
EXPORT_SYMBOL(filemap_nopage);
static struct page * filemap_getpage(struct file *file, unsigned long pgoff,
int nonblock)
{
struct address_space *mapping = file->f_mapping;
struct page *page;
int error;
/*
* Do we have something in the page cache already?
*/
retry_find:
page = find_get_page(mapping, pgoff);
if (!page) {
if (nonblock)
return NULL;
goto no_cached_page;
}
/*
* Ok, found a page in the page cache, now we need to check
* that it's up-to-date.
*/
if (!PageUptodate(page)) {
if (nonblock) {
page_cache_release(page);
return NULL;
}
goto page_not_uptodate;
}
success:
/*
* Found the page and have a reference on it.
*/
mark_page_accessed(page);
return page;
no_cached_page:
error = page_cache_read(file, pgoff);
/*
* The page we want has now been added to the page cache.
* In the unlikely event that someone removed it in the
* meantime, we'll just come back here and read it again.
*/
if (error >= 0)
goto retry_find;
/*
* An error return from page_cache_read can result if the
* system is low on memory, or a problem occurs while trying
* to schedule I/O.
*/
return NULL;
page_not_uptodate:
lock_page(page);
/* Did it get truncated while we waited for it? */
if (!page->mapping) {
unlock_page(page);
goto err;
}
/* Did somebody else get it up-to-date? */
if (PageUptodate(page)) {
unlock_page(page);
goto success;
}
error = mapping->a_ops->readpage(file, page);
if (!error) {
wait_on_page_locked(page);
if (PageUptodate(page))
goto success;
} else if (error == AOP_TRUNCATED_PAGE) {
page_cache_release(page);
goto retry_find;
}
/*
* Umm, take care of errors if the page isn't up-to-date.
* Try to re-read it _once_. We do this synchronously,
* because there really aren't any performance issues here
* and we need to check for errors.
*/
lock_page(page);
/* Somebody truncated the page on us? */
if (!page->mapping) {
unlock_page(page);
goto err;
}
/* Somebody else successfully read it in? */
if (PageUptodate(page)) {
unlock_page(page);
goto success;
}
ClearPageError(page);
error = mapping->a_ops->readpage(file, page);
if (!error) {
wait_on_page_locked(page);
if (PageUptodate(page))
goto success;
} else if (error == AOP_TRUNCATED_PAGE) {
page_cache_release(page);
goto retry_find;
}
/*
* Things didn't work out. Return zero to tell the
* mm layer so, possibly freeing the page cache page first.
*/
err:
page_cache_release(page);
return NULL;
}
int filemap_populate(struct vm_area_struct *vma, unsigned long addr,
unsigned long len, pgprot_t prot, unsigned long pgoff,
int nonblock)
{
struct file *file = vma->vm_file;
struct address_space *mapping = file->f_mapping;
struct inode *inode = mapping->host;
unsigned long size;
struct mm_struct *mm = vma->vm_mm;
struct page *page;
int err;
if (!nonblock)
force_page_cache_readahead(mapping, vma->vm_file,
pgoff, len >> PAGE_CACHE_SHIFT);
repeat:
size = (i_size_read(inode) + PAGE_CACHE_SIZE - 1) >> PAGE_CACHE_SHIFT;
if (pgoff + (len >> PAGE_CACHE_SHIFT) > size)
return -EINVAL;
page = filemap_getpage(file, pgoff, nonblock);
/* XXX: This is wrong, a filesystem I/O error may have happened. Fix that as
* done in shmem_populate calling shmem_getpage */
if (!page && !nonblock)
return -ENOMEM;
if (page) {
err = install_page(mm, vma, addr, page, prot);
if (err) {
page_cache_release(page);
return err;
}
} else if (vma->vm_flags & VM_NONLINEAR) {
/* No page was found just because we can't read it in now (being
* here implies nonblock != 0), but the page may exist, so set
* the PTE to fault it in later. */
err = install_file_pte(mm, vma, addr, pgoff, prot);
if (err)
return err;
}
len -= PAGE_SIZE;
addr += PAGE_SIZE;
pgoff++;
if (len)
goto repeat;
return 0;
}
EXPORT_SYMBOL(filemap_populate);
struct vm_operations_struct generic_file_vm_ops = {
.nopage = filemap_nopage,
.populate = filemap_populate,
};
/* This is used for a general mmap of a disk file */
int generic_file_mmap(struct file * file, struct vm_area_struct * vma)
{
struct address_space *mapping = file->f_mapping;
if (!mapping->a_ops->readpage)
return -ENOEXEC;
file_accessed(file);
vma->vm_ops = &generic_file_vm_ops;
return 0;
}
/*
* This is for filesystems which do not implement ->writepage.
*/
int generic_file_readonly_mmap(struct file *file, struct vm_area_struct *vma)
{
if ((vma->vm_flags & VM_SHARED) && (vma->vm_flags & VM_MAYWRITE))
return -EINVAL;
return generic_file_mmap(file, vma);
}
#else
int generic_file_mmap(struct file * file, struct vm_area_struct * vma)
{
return -ENOSYS;
}
int generic_file_readonly_mmap(struct file * file, struct vm_area_struct * vma)
{
return -ENOSYS;
}
#endif /* CONFIG_MMU */
EXPORT_SYMBOL(generic_file_mmap);
EXPORT_SYMBOL(generic_file_readonly_mmap);
static struct page *__read_cache_page(struct address_space *mapping,
unsigned long index,
int (*filler)(void *,struct page*),
void *data)
{
struct page *page, *cached_page = NULL;
int err;
repeat:
page = find_get_page(mapping, index);
if (!page) {
if (!cached_page) {
cached_page = page_cache_alloc_cold(mapping);
if (!cached_page)
return ERR_PTR(-ENOMEM);
}
err = add_to_page_cache_lru(cached_page, mapping,
index, GFP_KERNEL);
if (err == -EEXIST)
goto repeat;
if (err < 0) {
/* Presumably ENOMEM for radix tree node */
page_cache_release(cached_page);
return ERR_PTR(err);
}
page = cached_page;
cached_page = NULL;
err = filler(data, page);
if (err < 0) {
page_cache_release(page);
page = ERR_PTR(err);
}
}
if (cached_page)
page_cache_release(cached_page);
return page;
}
/*
* Same as read_cache_page, but don't wait for page to become unlocked
* after submitting it to the filler.
*/
struct page *read_cache_page_async(struct address_space *mapping,
unsigned long index,
int (*filler)(void *,struct page*),
void *data)
{
struct page *page;
int err;
retry:
page = __read_cache_page(mapping, index, filler, data);
if (IS_ERR(page))
goto out;
mark_page_accessed(page);
if (PageUptodate(page))
goto out;
lock_page(page);
if (!page->mapping) {
unlock_page(page);
page_cache_release(page);
goto retry;
}
if (PageUptodate(page)) {
unlock_page(page);
goto out;
}
err = filler(data, page);
if (err < 0) {
page_cache_release(page);
page = ERR_PTR(err);
}
out:
mark_page_accessed(page);
return page;
}
EXPORT_SYMBOL(read_cache_page_async);
/**
* read_cache_page - read into page cache, fill it if needed
* @mapping: the page's address_space
* @index: the page index
* @filler: function to perform the read
* @data: destination for read data
*
* Read into the page cache. If a page already exists, and PageUptodate() is
* not set, try to fill the page then wait for it to become unlocked.
*
* If the page does not get brought uptodate, return -EIO.
*/
struct page *read_cache_page(struct address_space *mapping,
unsigned long index,
int (*filler)(void *,struct page*),
void *data)
{
struct page *page;
page = read_cache_page_async(mapping, index, filler, data);
if (IS_ERR(page))
goto out;
wait_on_page_locked(page);
if (!PageUptodate(page)) {
page_cache_release(page);
page = ERR_PTR(-EIO);
}
out:
return page;
}
EXPORT_SYMBOL(read_cache_page);
/*
* If the page was newly created, increment its refcount and add it to the
* caller's lru-buffering pagevec. This function is specifically for
* generic_file_write().
*/
static inline struct page *
__grab_cache_page(struct address_space *mapping, unsigned long index,
struct page **cached_page, struct pagevec *lru_pvec)
{
int err;
struct page *page;
repeat:
page = find_lock_page(mapping, index);
if (!page) {
if (!*cached_page) {
*cached_page = page_cache_alloc(mapping);
if (!*cached_page)
return NULL;
}
err = add_to_page_cache(*cached_page, mapping,
index, GFP_KERNEL);
if (err == -EEXIST)
goto repeat;
if (err == 0) {
page = *cached_page;
page_cache_get(page);
if (!pagevec_add(lru_pvec, page))
__pagevec_lru_add(lru_pvec);
*cached_page = NULL;
}
}
return page;
}
/*
* The logic we want is
*
* if suid or (sgid and xgrp)
* remove privs
*/
int should_remove_suid(struct dentry *dentry)
{
mode_t mode = dentry->d_inode->i_mode;
int kill = 0;
/* suid always must be killed */
if (unlikely(mode & S_ISUID))
kill = ATTR_KILL_SUID;
/*
* sgid without any exec bits is just a mandatory locking mark; leave
* it alone. If some exec bits are set, it's a real sgid; kill it.
*/
if (unlikely((mode & S_ISGID) && (mode & S_IXGRP)))
kill |= ATTR_KILL_SGID;
if (unlikely(kill && !capable(CAP_FSETID)))
return kill;
return 0;
}
EXPORT_SYMBOL(should_remove_suid);
int __remove_suid(struct dentry *dentry, int kill)
{
struct iattr newattrs;
newattrs.ia_valid = ATTR_FORCE | kill;
return notify_change(dentry, &newattrs);
}
int remove_suid(struct dentry *dentry)
{
int kill = should_remove_suid(dentry);
if (unlikely(kill))
return __remove_suid(dentry, kill);
return 0;
}
EXPORT_SYMBOL(remove_suid);
size_t
[PATCH] Prepare for __copy_from_user_inatomic to not zero missed bytes The problem is that when we write to a file, the copy from userspace to pagecache is first done with preemption disabled, so if the source address is not immediately available the copy fails *and* *zeros* *the* *destination*. This is a problem because a concurrent read (which admittedly is an odd thing to do) might see zeros rather that was there before the write, or what was there after, or some mixture of the two (any of these being a reasonable thing to see). If the copy did fail, it will immediately be retried with preemption re-enabled so any transient problem with accessing the source won't cause an error. The first copying does not need to zero any uncopied bytes, and doing so causes the problem. It uses copy_from_user_atomic rather than copy_from_user so the simple expedient is to change copy_from_user_atomic to *not* zero out bytes on failure. The first of these two patches prepares for the change by fixing two places which assume copy_from_user_atomic does zero the tail. The two usages are very similar pieces of code which copy from a userspace iovec into one or more page-cache pages. These are changed to remove the assumption. The second patch changes __copy_from_user_inatomic* to not zero the tail. Once these are accepted, I will look at similar patches of other architectures where this is important (ppc, mips and sparc being the ones I can find). This patch: There is a problem with __copy_from_user_inatomic zeroing the tail of the buffer in the case of an error. As it is called in atomic context, the error may be transient, so it results in zeros being written where maybe they shouldn't be. In the usage in filemap, this opens a window for a well timed read to see data (zeros) which is not consistent with any ordering of reads and writes. Most cases where __copy_from_user_inatomic is called, a failure results in __copy_from_user being called immediately. As long as the latter zeros the tail, the former doesn't need to. However in *copy_from_user_iovec implementations (in both filemap and ntfs/file), it is assumed that copy_from_user_inatomic will zero the tail. This patch removes that assumption, so that after this patch it will be safe for copy_from_user_inatomic to not zero the tail. This patch also adds some commentary to filemap.h and asm-i386/uaccess.h. After this patch, all architectures that might disable preempt when kmap_atomic is called need to have their __copy_from_user_inatomic* "fixed". This includes - powerpc - i386 - mips - sparc Signed-off-by: Neil Brown <neilb@suse.de> Cc: David Howells <dhowells@redhat.com> Cc: Anton Altaparmakov <aia21@cantab.net> Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org> Cc: Paul Mackerras <paulus@samba.org> Cc: Ralf Baechle <ralf@linux-mips.org> Cc: William Lee Irwin III <wli@holomorphy.com> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2006-06-25 12:47:58 +00:00
__filemap_copy_from_user_iovec_inatomic(char *vaddr,
const struct iovec *iov, size_t base, size_t bytes)
{
size_t copied = 0, left = 0;
while (bytes) {
char __user *buf = iov->iov_base + base;
int copy = min(bytes, iov->iov_len - base);
base = 0;
[PATCH] x86: cache pollution aware __copy_from_user_ll() Use the x86 cache-bypassing copy instructions for copy_from_user(). Some performance data are Total of GLOBAL_POWER_EVENTS (CPU cycle samples) 2.6.12.4.orig 1921587 2.6.12.4.nt 1599424 1599424/1921587=83.23% (16.77% reduction) BSQ_CACHE_REFERENCE (L3 cache miss) 2.6.12.4.orig 57427 2.6.12.4.nt 20858 20858/57427=36.32% (63.7% reduction) L3 cache miss reduction of __copy_from_user_ll samples % 37408 65.1412 vmlinux __copy_from_user_ll 23 0.1103 vmlinux __copy_user_zeroing_intel_nocache 23/37408=0.061% (99.94% reduction) Top 5 of 2.6.12.4.nt Counted GLOBAL_POWER_EVENTS events (time during which processor is not stopped) with a unit mask of 0x01 (mandatory) count 100000 samples % app name symbol name 128392 8.0274 vmlinux __copy_user_zeroing_intel_nocache 64206 4.0143 vmlinux journal_add_journal_head 59746 3.7355 vmlinux do_get_write_access 47674 2.9807 vmlinux journal_put_journal_head 46021 2.8774 vmlinux journal_dirty_metadata pattern9-0-cpu4-0-09011728/summary.out Counted BSQ_CACHE_REFERENCE events (cache references seen by the bus unit) with a unit mask of 0x3f (multiple flags) count 3000 samples % app name symbol name 69755 4.2861 vmlinux __copy_user_zeroing_intel_nocache 55685 3.4215 vmlinux journal_add_journal_head 52371 3.2179 vmlinux __find_get_block 45504 2.7960 vmlinux journal_put_journal_head 36005 2.2123 vmlinux journal_stop pattern9-0-cpu4-0-09011744/summary.out Counted BSQ_CACHE_REFERENCE events (cache references seen by the bus unit) with a unit mask of 0x200 (read 3rd level cache miss) count 3000 samples % app name symbol name 1147 5.4994 vmlinux journal_add_journal_head 881 4.2240 vmlinux journal_dirty_data 872 4.1809 vmlinux blk_rq_map_sg 734 3.5192 vmlinux journal_commit_transaction 617 2.9582 vmlinux radix_tree_delete pattern9-0-cpu4-0-09011731/summary.out iozone results are original 2.6.12.4 CPU time = 207.768 sec cache aware CPU time = 184.783 sec (three times run) 184.783/207.768=88.94% (11.06% reduction) original: pattern9-0-cpu4-0-08191720/iozone.out: CPU Utilization: Wall time 45.997 CPU time 64.527 CPU utilization 140.28 % pattern9-0-cpu4-0-08191741/iozone.out: CPU Utilization: Wall time 46.878 CPU time 71.933 CPU utilization 153.45 % pattern9-0-cpu4-0-08191743/iozone.out: CPU Utilization: Wall time 45.152 CPU time 71.308 CPU utilization 157.93 % cache awre: pattern9-0-cpu4-0-09011728/iozone.out: CPU Utilization: Wall time 44.842 CPU time 62.465 CPU utilization 139.30 % pattern9-0-cpu4-0-09011731/iozone.out: CPU Utilization: Wall time 44.718 CPU time 59.273 CPU utilization 132.55 % pattern9-0-cpu4-0-09011744/iozone.out: CPU Utilization: Wall time 44.367 CPU time 63.045 CPU utilization 142.10 % Signed-off-by: Hiro Yoshioka <hyoshiok@miraclelinux.com> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2006-06-23 09:04:16 +00:00
left = __copy_from_user_inatomic_nocache(vaddr, buf, copy);
copied += copy;
bytes -= copy;
vaddr += copy;
iov++;
[PATCH] Prepare for __copy_from_user_inatomic to not zero missed bytes The problem is that when we write to a file, the copy from userspace to pagecache is first done with preemption disabled, so if the source address is not immediately available the copy fails *and* *zeros* *the* *destination*. This is a problem because a concurrent read (which admittedly is an odd thing to do) might see zeros rather that was there before the write, or what was there after, or some mixture of the two (any of these being a reasonable thing to see). If the copy did fail, it will immediately be retried with preemption re-enabled so any transient problem with accessing the source won't cause an error. The first copying does not need to zero any uncopied bytes, and doing so causes the problem. It uses copy_from_user_atomic rather than copy_from_user so the simple expedient is to change copy_from_user_atomic to *not* zero out bytes on failure. The first of these two patches prepares for the change by fixing two places which assume copy_from_user_atomic does zero the tail. The two usages are very similar pieces of code which copy from a userspace iovec into one or more page-cache pages. These are changed to remove the assumption. The second patch changes __copy_from_user_inatomic* to not zero the tail. Once these are accepted, I will look at similar patches of other architectures where this is important (ppc, mips and sparc being the ones I can find). This patch: There is a problem with __copy_from_user_inatomic zeroing the tail of the buffer in the case of an error. As it is called in atomic context, the error may be transient, so it results in zeros being written where maybe they shouldn't be. In the usage in filemap, this opens a window for a well timed read to see data (zeros) which is not consistent with any ordering of reads and writes. Most cases where __copy_from_user_inatomic is called, a failure results in __copy_from_user being called immediately. As long as the latter zeros the tail, the former doesn't need to. However in *copy_from_user_iovec implementations (in both filemap and ntfs/file), it is assumed that copy_from_user_inatomic will zero the tail. This patch removes that assumption, so that after this patch it will be safe for copy_from_user_inatomic to not zero the tail. This patch also adds some commentary to filemap.h and asm-i386/uaccess.h. After this patch, all architectures that might disable preempt when kmap_atomic is called need to have their __copy_from_user_inatomic* "fixed". This includes - powerpc - i386 - mips - sparc Signed-off-by: Neil Brown <neilb@suse.de> Cc: David Howells <dhowells@redhat.com> Cc: Anton Altaparmakov <aia21@cantab.net> Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org> Cc: Paul Mackerras <paulus@samba.org> Cc: Ralf Baechle <ralf@linux-mips.org> Cc: William Lee Irwin III <wli@holomorphy.com> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2006-06-25 12:47:58 +00:00
if (unlikely(left))
break;
}
return copied - left;
}
/*
* Performs necessary checks before doing a write
*
* Can adjust writing position or amount of bytes to write.
* Returns appropriate error code that caller should return or
* zero in case that write should be allowed.
*/
inline int generic_write_checks(struct file *file, loff_t *pos, size_t *count, int isblk)
{
struct inode *inode = file->f_mapping->host;
unsigned long limit = current->signal->rlim[RLIMIT_FSIZE].rlim_cur;
if (unlikely(*pos < 0))
return -EINVAL;
if (!isblk) {
/* FIXME: this is for backwards compatibility with 2.4 */
if (file->f_flags & O_APPEND)
*pos = i_size_read(inode);
if (limit != RLIM_INFINITY) {
if (*pos >= limit) {
send_sig(SIGXFSZ, current, 0);
return -EFBIG;
}
if (*count > limit - (typeof(limit))*pos) {
*count = limit - (typeof(limit))*pos;
}
}
}
/*
* LFS rule
*/
if (unlikely(*pos + *count > MAX_NON_LFS &&
!(file->f_flags & O_LARGEFILE))) {
if (*pos >= MAX_NON_LFS) {
send_sig(SIGXFSZ, current, 0);
return -EFBIG;
}
if (*count > MAX_NON_LFS - (unsigned long)*pos) {
*count = MAX_NON_LFS - (unsigned long)*pos;
}
}
/*
* Are we about to exceed the fs block limit ?
*
* If we have written data it becomes a short write. If we have
* exceeded without writing data we send a signal and return EFBIG.
* Linus frestrict idea will clean these up nicely..
*/
if (likely(!isblk)) {
if (unlikely(*pos >= inode->i_sb->s_maxbytes)) {
if (*count || *pos > inode->i_sb->s_maxbytes) {
send_sig(SIGXFSZ, current, 0);
return -EFBIG;
}
/* zero-length writes at ->s_maxbytes are OK */
}
if (unlikely(*pos + *count > inode->i_sb->s_maxbytes))
*count = inode->i_sb->s_maxbytes - *pos;
} else {
[PATCH] BLOCK: Make it possible to disable the block layer [try #6] Make it possible to disable the block layer. Not all embedded devices require it, some can make do with just JFFS2, NFS, ramfs, etc - none of which require the block layer to be present. This patch does the following: (*) Introduces CONFIG_BLOCK to disable the block layer, buffering and blockdev support. (*) Adds dependencies on CONFIG_BLOCK to any configuration item that controls an item that uses the block layer. This includes: (*) Block I/O tracing. (*) Disk partition code. (*) All filesystems that are block based, eg: Ext3, ReiserFS, ISOFS. (*) The SCSI layer. As far as I can tell, even SCSI chardevs use the block layer to do scheduling. Some drivers that use SCSI facilities - such as USB storage - end up disabled indirectly from this. (*) Various block-based device drivers, such as IDE and the old CDROM drivers. (*) MTD blockdev handling and FTL. (*) JFFS - which uses set_bdev_super(), something it could avoid doing by taking a leaf out of JFFS2's book. (*) Makes most of the contents of linux/blkdev.h, linux/buffer_head.h and linux/elevator.h contingent on CONFIG_BLOCK being set. sector_div() is, however, still used in places, and so is still available. (*) Also made contingent are the contents of linux/mpage.h, linux/genhd.h and parts of linux/fs.h. (*) Makes a number of files in fs/ contingent on CONFIG_BLOCK. (*) Makes mm/bounce.c (bounce buffering) contingent on CONFIG_BLOCK. (*) set_page_dirty() doesn't call __set_page_dirty_buffers() if CONFIG_BLOCK is not enabled. (*) fs/no-block.c is created to hold out-of-line stubs and things that are required when CONFIG_BLOCK is not set: (*) Default blockdev file operations (to give error ENODEV on opening). (*) Makes some /proc changes: (*) /proc/devices does not list any blockdevs. (*) /proc/diskstats and /proc/partitions are contingent on CONFIG_BLOCK. (*) Makes some compat ioctl handling contingent on CONFIG_BLOCK. (*) If CONFIG_BLOCK is not defined, makes sys_quotactl() return -ENODEV if given command other than Q_SYNC or if a special device is specified. (*) In init/do_mounts.c, no reference is made to the blockdev routines if CONFIG_BLOCK is not defined. This does not prohibit NFS roots or JFFS2. (*) The bdflush, ioprio_set and ioprio_get syscalls can now be absent (return error ENOSYS by way of cond_syscall if so). (*) The seclvl_bd_claim() and seclvl_bd_release() security calls do nothing if CONFIG_BLOCK is not set, since they can't then happen. Signed-Off-By: David Howells <dhowells@redhat.com> Signed-off-by: Jens Axboe <axboe@kernel.dk>
2006-09-30 18:45:40 +00:00
#ifdef CONFIG_BLOCK
loff_t isize;
if (bdev_read_only(I_BDEV(inode)))
return -EPERM;
isize = i_size_read(inode);
if (*pos >= isize) {
if (*count || *pos > isize)
return -ENOSPC;
}
if (*pos + *count > isize)
*count = isize - *pos;
[PATCH] BLOCK: Make it possible to disable the block layer [try #6] Make it possible to disable the block layer. Not all embedded devices require it, some can make do with just JFFS2, NFS, ramfs, etc - none of which require the block layer to be present. This patch does the following: (*) Introduces CONFIG_BLOCK to disable the block layer, buffering and blockdev support. (*) Adds dependencies on CONFIG_BLOCK to any configuration item that controls an item that uses the block layer. This includes: (*) Block I/O tracing. (*) Disk partition code. (*) All filesystems that are block based, eg: Ext3, ReiserFS, ISOFS. (*) The SCSI layer. As far as I can tell, even SCSI chardevs use the block layer to do scheduling. Some drivers that use SCSI facilities - such as USB storage - end up disabled indirectly from this. (*) Various block-based device drivers, such as IDE and the old CDROM drivers. (*) MTD blockdev handling and FTL. (*) JFFS - which uses set_bdev_super(), something it could avoid doing by taking a leaf out of JFFS2's book. (*) Makes most of the contents of linux/blkdev.h, linux/buffer_head.h and linux/elevator.h contingent on CONFIG_BLOCK being set. sector_div() is, however, still used in places, and so is still available. (*) Also made contingent are the contents of linux/mpage.h, linux/genhd.h and parts of linux/fs.h. (*) Makes a number of files in fs/ contingent on CONFIG_BLOCK. (*) Makes mm/bounce.c (bounce buffering) contingent on CONFIG_BLOCK. (*) set_page_dirty() doesn't call __set_page_dirty_buffers() if CONFIG_BLOCK is not enabled. (*) fs/no-block.c is created to hold out-of-line stubs and things that are required when CONFIG_BLOCK is not set: (*) Default blockdev file operations (to give error ENODEV on opening). (*) Makes some /proc changes: (*) /proc/devices does not list any blockdevs. (*) /proc/diskstats and /proc/partitions are contingent on CONFIG_BLOCK. (*) Makes some compat ioctl handling contingent on CONFIG_BLOCK. (*) If CONFIG_BLOCK is not defined, makes sys_quotactl() return -ENODEV if given command other than Q_SYNC or if a special device is specified. (*) In init/do_mounts.c, no reference is made to the blockdev routines if CONFIG_BLOCK is not defined. This does not prohibit NFS roots or JFFS2. (*) The bdflush, ioprio_set and ioprio_get syscalls can now be absent (return error ENOSYS by way of cond_syscall if so). (*) The seclvl_bd_claim() and seclvl_bd_release() security calls do nothing if CONFIG_BLOCK is not set, since they can't then happen. Signed-Off-By: David Howells <dhowells@redhat.com> Signed-off-by: Jens Axboe <axboe@kernel.dk>
2006-09-30 18:45:40 +00:00
#else
return -EPERM;
#endif
}
return 0;
}
EXPORT_SYMBOL(generic_write_checks);
ssize_t
generic_file_direct_write(struct kiocb *iocb, const struct iovec *iov,
unsigned long *nr_segs, loff_t pos, loff_t *ppos,
size_t count, size_t ocount)
{
struct file *file = iocb->ki_filp;
struct address_space *mapping = file->f_mapping;
struct inode *inode = mapping->host;
ssize_t written;
if (count != ocount)
*nr_segs = iov_shorten((struct iovec *)iov, *nr_segs, count);
written = generic_file_direct_IO(WRITE, iocb, iov, pos, *nr_segs);
if (written > 0) {
loff_t end = pos + written;
if (end > i_size_read(inode) && !S_ISBLK(inode->i_mode)) {
i_size_write(inode, end);
mark_inode_dirty(inode);
}
*ppos = end;
}
/*
* Sync the fs metadata but not the minor inode changes and
* of course not the data as we did direct DMA for the IO.
* i_mutex is held, which protects generic_osync_inode() from
[PATCH] dio: only call aio_complete() after returning -EIOCBQUEUED The only time it is safe to call aio_complete() is when the ->ki_retry function returns -EIOCBQUEUED to the AIO core. direct_io_worker() has historically done this by relying on its caller to translate positive return codes into -EIOCBQUEUED for the aio case. It did this by trying to keep conditionals in sync. direct_io_worker() knew when finished_one_bio() was going to call aio_complete(). It would reverse the test and wait and free the dio in the cases it thought that finished_one_bio() wasn't going to. Not surprisingly, it ended up getting it wrong. 'ret' could be a negative errno from the submission path but it failed to communicate this to finished_one_bio(). direct_io_worker() would return < 0, it's callers wouldn't raise -EIOCBQUEUED, and aio_complete() would be called. In the future finished_one_bio()'s tests wouldn't reflect this and aio_complete() would be called for a second time which can manifest as an oops. The previous cleanups have whittled the sync and async completion paths down to the point where we can collapse them and clearly reassert the invariant that we must only call aio_complete() after returning -EIOCBQUEUED. direct_io_worker() will only return -EIOCBQUEUED when it is not the last to drop the dio refcount and the aio bio completion path will only call aio_complete() when it is the last to drop the dio refcount. direct_io_worker() can ensure that it is the last to drop the reference count by waiting for bios to drain. It does this for sync ops, of course, and for partial dio writes that must fall back to buffered and for aio ops that saw errors during submission. This means that operations that end up waiting, even if they were issued as aio ops, will not call aio_complete() from dio. Instead we return the return code of the operation and let the aio core call aio_complete(). This is purposely done to fix a bug where AIO DIO file extensions would call aio_complete() before their callers have a chance to update i_size. Now that direct_io_worker() is explicitly returning -EIOCBQUEUED its callers no longer have to translate for it. XFS needs to be careful not to free resources that will be used during AIO completion if -EIOCBQUEUED is returned. We maintain the previous behaviour of trying to write fs metadata for O_SYNC aio+dio writes. Signed-off-by: Zach Brown <zach.brown@oracle.com> Cc: Badari Pulavarty <pbadari@us.ibm.com> Cc: Suparna Bhattacharya <suparna@in.ibm.com> Acked-by: Jeff Moyer <jmoyer@redhat.com> Cc: <xfs-masters@oss.sgi.com> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2006-12-10 10:21:05 +00:00
* livelocking. AIO O_DIRECT ops attempt to sync metadata here.
*/
[PATCH] dio: only call aio_complete() after returning -EIOCBQUEUED The only time it is safe to call aio_complete() is when the ->ki_retry function returns -EIOCBQUEUED to the AIO core. direct_io_worker() has historically done this by relying on its caller to translate positive return codes into -EIOCBQUEUED for the aio case. It did this by trying to keep conditionals in sync. direct_io_worker() knew when finished_one_bio() was going to call aio_complete(). It would reverse the test and wait and free the dio in the cases it thought that finished_one_bio() wasn't going to. Not surprisingly, it ended up getting it wrong. 'ret' could be a negative errno from the submission path but it failed to communicate this to finished_one_bio(). direct_io_worker() would return < 0, it's callers wouldn't raise -EIOCBQUEUED, and aio_complete() would be called. In the future finished_one_bio()'s tests wouldn't reflect this and aio_complete() would be called for a second time which can manifest as an oops. The previous cleanups have whittled the sync and async completion paths down to the point where we can collapse them and clearly reassert the invariant that we must only call aio_complete() after returning -EIOCBQUEUED. direct_io_worker() will only return -EIOCBQUEUED when it is not the last to drop the dio refcount and the aio bio completion path will only call aio_complete() when it is the last to drop the dio refcount. direct_io_worker() can ensure that it is the last to drop the reference count by waiting for bios to drain. It does this for sync ops, of course, and for partial dio writes that must fall back to buffered and for aio ops that saw errors during submission. This means that operations that end up waiting, even if they were issued as aio ops, will not call aio_complete() from dio. Instead we return the return code of the operation and let the aio core call aio_complete(). This is purposely done to fix a bug where AIO DIO file extensions would call aio_complete() before their callers have a chance to update i_size. Now that direct_io_worker() is explicitly returning -EIOCBQUEUED its callers no longer have to translate for it. XFS needs to be careful not to free resources that will be used during AIO completion if -EIOCBQUEUED is returned. We maintain the previous behaviour of trying to write fs metadata for O_SYNC aio+dio writes. Signed-off-by: Zach Brown <zach.brown@oracle.com> Cc: Badari Pulavarty <pbadari@us.ibm.com> Cc: Suparna Bhattacharya <suparna@in.ibm.com> Acked-by: Jeff Moyer <jmoyer@redhat.com> Cc: <xfs-masters@oss.sgi.com> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2006-12-10 10:21:05 +00:00
if ((written >= 0 || written == -EIOCBQUEUED) &&
((file->f_flags & O_SYNC) || IS_SYNC(inode))) {
int err = generic_osync_inode(inode, mapping, OSYNC_METADATA);
if (err < 0)
written = err;
}
return written;
}
EXPORT_SYMBOL(generic_file_direct_write);
ssize_t
generic_file_buffered_write(struct kiocb *iocb, const struct iovec *iov,
unsigned long nr_segs, loff_t pos, loff_t *ppos,
size_t count, ssize_t written)
{
struct file *file = iocb->ki_filp;
struct address_space * mapping = file->f_mapping;
const struct address_space_operations *a_ops = mapping->a_ops;
struct inode *inode = mapping->host;
long status = 0;
struct page *page;
struct page *cached_page = NULL;
size_t bytes;
struct pagevec lru_pvec;
const struct iovec *cur_iov = iov; /* current iovec */
size_t iov_base = 0; /* offset in the current iovec */
char __user *buf;
pagevec_init(&lru_pvec, 0);
/*
* handle partial DIO write. Adjust cur_iov if needed.
*/
if (likely(nr_segs == 1))
buf = iov->iov_base + written;
else {
filemap_set_next_iovec(&cur_iov, &iov_base, written);
buf = cur_iov->iov_base + iov_base;
}
do {
unsigned long index;
unsigned long offset;
size_t copied;
offset = (pos & (PAGE_CACHE_SIZE -1)); /* Within page */
index = pos >> PAGE_CACHE_SHIFT;
bytes = PAGE_CACHE_SIZE - offset;
/* Limit the size of the copy to the caller's write size */
bytes = min(bytes, count);
/* We only need to worry about prefaulting when writes are from
* user-space. NFSd uses vfs_writev with several non-aligned
* segments in the vector, and limiting to one segment a time is
* a noticeable performance for re-write
*/
if (!segment_eq(get_fs(), KERNEL_DS)) {
/*
* Limit the size of the copy to that of the current
* segment, because fault_in_pages_readable() doesn't
* know how to walk segments.
*/
bytes = min(bytes, cur_iov->iov_len - iov_base);
/*
* Bring in the user page that we will copy from
* _first_. Otherwise there's a nasty deadlock on
* copying from the same page as we're writing to,
* without it being marked up-to-date.
*/
fault_in_pages_readable(buf, bytes);
}
page = __grab_cache_page(mapping,index,&cached_page,&lru_pvec);
if (!page) {
status = -ENOMEM;
break;
}
if (unlikely(bytes == 0)) {
status = 0;
copied = 0;
goto zero_length_segment;
}
status = a_ops->prepare_write(file, page, offset, offset+bytes);
if (unlikely(status)) {
loff_t isize = i_size_read(inode);
if (status != AOP_TRUNCATED_PAGE)
unlock_page(page);
page_cache_release(page);
if (status == AOP_TRUNCATED_PAGE)
continue;
/*
* prepare_write() may have instantiated a few blocks
* outside i_size. Trim these off again.
*/
if (pos + bytes > isize)
vmtruncate(inode, isize);
break;
}
if (likely(nr_segs == 1))
copied = filemap_copy_from_user(page, offset,
buf, bytes);
else
copied = filemap_copy_from_user_iovec(page, offset,
cur_iov, iov_base, bytes);
flush_dcache_page(page);
status = a_ops->commit_write(file, page, offset, offset+bytes);
if (status == AOP_TRUNCATED_PAGE) {
page_cache_release(page);
continue;
}
zero_length_segment:
if (likely(copied >= 0)) {
if (!status)
status = copied;
if (status >= 0) {
written += status;
count -= status;
pos += status;
buf += status;
if (unlikely(nr_segs > 1)) {
filemap_set_next_iovec(&cur_iov,
&iov_base, status);
if (count)
buf = cur_iov->iov_base +
iov_base;
} else {
iov_base += status;
}
}
}
if (unlikely(copied != bytes))
if (status >= 0)
status = -EFAULT;
unlock_page(page);
mark_page_accessed(page);
page_cache_release(page);
if (status < 0)
break;
balance_dirty_pages_ratelimited(mapping);
cond_resched();
} while (count);
*ppos = pos;
if (cached_page)
page_cache_release(cached_page);
/*
* For now, when the user asks for O_SYNC, we'll actually give O_DSYNC
*/
if (likely(status >= 0)) {
if (unlikely((file->f_flags & O_SYNC) || IS_SYNC(inode))) {
if (!a_ops->writepage || !is_sync_kiocb(iocb))
status = generic_osync_inode(inode, mapping,
OSYNC_METADATA|OSYNC_DATA);
}
}
/*
* If we get here for O_DIRECT writes then we must have fallen through
* to buffered writes (block instantiation inside i_size). So we sync
* the file data here, to try to honour O_DIRECT expectations.
*/
if (unlikely(file->f_flags & O_DIRECT) && written)
status = filemap_write_and_wait(mapping);
pagevec_lru_add(&lru_pvec);
return written ? written : status;
}
EXPORT_SYMBOL(generic_file_buffered_write);
static ssize_t
__generic_file_aio_write_nolock(struct kiocb *iocb, const struct iovec *iov,
unsigned long nr_segs, loff_t *ppos)
{
struct file *file = iocb->ki_filp;
struct address_space * mapping = file->f_mapping;
size_t ocount; /* original count */
size_t count; /* after file limit checks */
struct inode *inode = mapping->host;
unsigned long seg;
loff_t pos;
ssize_t written;
ssize_t err;
ocount = 0;
for (seg = 0; seg < nr_segs; seg++) {
const struct iovec *iv = &iov[seg];
/*
* If any segment has a negative length, or the cumulative
* length ever wraps negative then return -EINVAL.
*/
ocount += iv->iov_len;
if (unlikely((ssize_t)(ocount|iv->iov_len) < 0))
return -EINVAL;
if (access_ok(VERIFY_READ, iv->iov_base, iv->iov_len))
continue;
if (seg == 0)
return -EFAULT;
nr_segs = seg;
ocount -= iv->iov_len; /* This segment is no good */
break;
}
count = ocount;
pos = *ppos;
vfs_check_frozen(inode->i_sb, SB_FREEZE_WRITE);
/* We can write back this queue in page reclaim */
current->backing_dev_info = mapping->backing_dev_info;
written = 0;
err = generic_write_checks(file, &pos, &count, S_ISBLK(inode->i_mode));
if (err)
goto out;
if (count == 0)
goto out;
err = remove_suid(file->f_path.dentry);
if (err)
goto out;
file_update_time(file);
/* coalesce the iovecs and go direct-to-BIO for O_DIRECT */
if (unlikely(file->f_flags & O_DIRECT)) {
loff_t endbyte;
ssize_t written_buffered;
written = generic_file_direct_write(iocb, iov, &nr_segs, pos,
ppos, count, ocount);
if (written < 0 || written == count)
goto out;
/*
* direct-io write to a hole: fall through to buffered I/O
* for completing the rest of the request.
*/
pos += written;
count -= written;
written_buffered = generic_file_buffered_write(iocb, iov,
nr_segs, pos, ppos, count,
written);
/*
* If generic_file_buffered_write() retuned a synchronous error
* then we want to return the number of bytes which were
* direct-written, or the error code if that was zero. Note
* that this differs from normal direct-io semantics, which
* will return -EFOO even if some bytes were written.
*/
if (written_buffered < 0) {
err = written_buffered;
goto out;
}
/*
* We need to ensure that the page cache pages are written to
* disk and invalidated to preserve the expected O_DIRECT
* semantics.
*/
endbyte = pos + written_buffered - written - 1;
err = do_sync_file_range(file, pos, endbyte,
SYNC_FILE_RANGE_WAIT_BEFORE|
SYNC_FILE_RANGE_WRITE|
SYNC_FILE_RANGE_WAIT_AFTER);
if (err == 0) {
written = written_buffered;
invalidate_mapping_pages(mapping,
pos >> PAGE_CACHE_SHIFT,
endbyte >> PAGE_CACHE_SHIFT);
} else {
/*
* We don't know how much we wrote, so just return
* the number of bytes which were direct-written
*/
}
} else {
written = generic_file_buffered_write(iocb, iov, nr_segs,
pos, ppos, count, written);
}
out:
current->backing_dev_info = NULL;
return written ? written : err;
}
ssize_t generic_file_aio_write_nolock(struct kiocb *iocb,
const struct iovec *iov, unsigned long nr_segs, loff_t pos)
{
struct file *file = iocb->ki_filp;
struct address_space *mapping = file->f_mapping;
struct inode *inode = mapping->host;
ssize_t ret;
BUG_ON(iocb->ki_pos != pos);
ret = __generic_file_aio_write_nolock(iocb, iov, nr_segs,
&iocb->ki_pos);
if (ret > 0 && ((file->f_flags & O_SYNC) || IS_SYNC(inode))) {
ssize_t err;
err = sync_page_range_nolock(inode, mapping, pos, ret);
if (err < 0)
ret = err;
}
return ret;
}
EXPORT_SYMBOL(generic_file_aio_write_nolock);
ssize_t generic_file_aio_write(struct kiocb *iocb, const struct iovec *iov,
unsigned long nr_segs, loff_t pos)
{
struct file *file = iocb->ki_filp;
struct address_space *mapping = file->f_mapping;
struct inode *inode = mapping->host;
ssize_t ret;
BUG_ON(iocb->ki_pos != pos);
mutex_lock(&inode->i_mutex);
ret = __generic_file_aio_write_nolock(iocb, iov, nr_segs,
&iocb->ki_pos);
mutex_unlock(&inode->i_mutex);
if (ret > 0 && ((file->f_flags & O_SYNC) || IS_SYNC(inode))) {
ssize_t err;
err = sync_page_range(inode, mapping, pos, ret);
if (err < 0)
ret = err;
}
return ret;
}
EXPORT_SYMBOL(generic_file_aio_write);
/*
* Called under i_mutex for writes to S_ISREG files. Returns -EIO if something
* went wrong during pagecache shootdown.
*/
static ssize_t
generic_file_direct_IO(int rw, struct kiocb *iocb, const struct iovec *iov,
loff_t offset, unsigned long nr_segs)
{
struct file *file = iocb->ki_filp;
struct address_space *mapping = file->f_mapping;
ssize_t retval;
[PATCH] dio: invalidate clean pages before dio write This patch fixes a user-triggerable oops that was reported by Leonid Ananiev as archived at http://lkml.org/lkml/2007/2/8/337. dio writes invalidate clean pages that intersect the written region so that subsequent buffered reads go to disk to read the new data. If this fails the interface tries to tell the caller that the cache is inconsistent by returning EIO. Before this patch we had the problem where this invalidation failure would clobber -EIOCBQUEUED as it made its way from fs/direct-io.c to fs/aio.c. Both fs/aio.c and bio completion call aio_complete() and we reference freed memory, usually oopsing. This patch addresses this problem by invalidating before the write so that we can cleanly return -EIO before ->direct_IO() has had a chance to return -EIOCBQUEUED. There is a compromise here. During the dio write we can fault in mmap()ed pages which intersect the written range with get_user_pages() if the user provided them for the source buffer. This is a crazy thing to do, but we can make it mostly work in most cases by trying the invalidation again. The compromise is that we won't return an error if this second invalidation fails if it's an AIO write and we have -EIOCBQUEUED. This was tested by having two processes race performing large O_DIRECT and buffered ordered writes. Within minutes ext3 would see a race between ext3_releasepage() and jbd holding a reference on ordered data buffers and would cause invalidation to fail, panicing the box. The test can be found in the 'aio_dio_bugs' test group in test.kernel.org/autotest. After this patch the test passes. Signed-off-by: Zach Brown <zach.brown@oracle.com> Signed-off-by: Benjamin LaHaise <bcrl@kvack.org> Cc: Leonid Ananiev <leonid.i.ananiev@linux.intel.com> Cc: Nick Piggin <nickpiggin@yahoo.com.au> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2007-03-16 21:38:11 +00:00
size_t write_len;
pgoff_t end = 0; /* silence gcc */
/*
* If it's a write, unmap all mmappings of the file up-front. This
* will cause any pte dirty bits to be propagated into the pageframes
* for the subsequent filemap_write_and_wait().
*/
if (rw == WRITE) {
write_len = iov_length(iov, nr_segs);
[PATCH] dio: invalidate clean pages before dio write This patch fixes a user-triggerable oops that was reported by Leonid Ananiev as archived at http://lkml.org/lkml/2007/2/8/337. dio writes invalidate clean pages that intersect the written region so that subsequent buffered reads go to disk to read the new data. If this fails the interface tries to tell the caller that the cache is inconsistent by returning EIO. Before this patch we had the problem where this invalidation failure would clobber -EIOCBQUEUED as it made its way from fs/direct-io.c to fs/aio.c. Both fs/aio.c and bio completion call aio_complete() and we reference freed memory, usually oopsing. This patch addresses this problem by invalidating before the write so that we can cleanly return -EIO before ->direct_IO() has had a chance to return -EIOCBQUEUED. There is a compromise here. During the dio write we can fault in mmap()ed pages which intersect the written range with get_user_pages() if the user provided them for the source buffer. This is a crazy thing to do, but we can make it mostly work in most cases by trying the invalidation again. The compromise is that we won't return an error if this second invalidation fails if it's an AIO write and we have -EIOCBQUEUED. This was tested by having two processes race performing large O_DIRECT and buffered ordered writes. Within minutes ext3 would see a race between ext3_releasepage() and jbd holding a reference on ordered data buffers and would cause invalidation to fail, panicing the box. The test can be found in the 'aio_dio_bugs' test group in test.kernel.org/autotest. After this patch the test passes. Signed-off-by: Zach Brown <zach.brown@oracle.com> Signed-off-by: Benjamin LaHaise <bcrl@kvack.org> Cc: Leonid Ananiev <leonid.i.ananiev@linux.intel.com> Cc: Nick Piggin <nickpiggin@yahoo.com.au> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2007-03-16 21:38:11 +00:00
end = (offset + write_len - 1) >> PAGE_CACHE_SHIFT;
if (mapping_mapped(mapping))
unmap_mapping_range(mapping, offset, write_len, 0);
}
retval = filemap_write_and_wait(mapping);
[PATCH] dio: invalidate clean pages before dio write This patch fixes a user-triggerable oops that was reported by Leonid Ananiev as archived at http://lkml.org/lkml/2007/2/8/337. dio writes invalidate clean pages that intersect the written region so that subsequent buffered reads go to disk to read the new data. If this fails the interface tries to tell the caller that the cache is inconsistent by returning EIO. Before this patch we had the problem where this invalidation failure would clobber -EIOCBQUEUED as it made its way from fs/direct-io.c to fs/aio.c. Both fs/aio.c and bio completion call aio_complete() and we reference freed memory, usually oopsing. This patch addresses this problem by invalidating before the write so that we can cleanly return -EIO before ->direct_IO() has had a chance to return -EIOCBQUEUED. There is a compromise here. During the dio write we can fault in mmap()ed pages which intersect the written range with get_user_pages() if the user provided them for the source buffer. This is a crazy thing to do, but we can make it mostly work in most cases by trying the invalidation again. The compromise is that we won't return an error if this second invalidation fails if it's an AIO write and we have -EIOCBQUEUED. This was tested by having two processes race performing large O_DIRECT and buffered ordered writes. Within minutes ext3 would see a race between ext3_releasepage() and jbd holding a reference on ordered data buffers and would cause invalidation to fail, panicing the box. The test can be found in the 'aio_dio_bugs' test group in test.kernel.org/autotest. After this patch the test passes. Signed-off-by: Zach Brown <zach.brown@oracle.com> Signed-off-by: Benjamin LaHaise <bcrl@kvack.org> Cc: Leonid Ananiev <leonid.i.ananiev@linux.intel.com> Cc: Nick Piggin <nickpiggin@yahoo.com.au> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2007-03-16 21:38:11 +00:00
if (retval)
goto out;
/*
* After a write we want buffered reads to be sure to go to disk to get
* the new data. We invalidate clean cached page from the region we're
* about to write. We do this *before* the write so that we can return
* -EIO without clobbering -EIOCBQUEUED from ->direct_IO().
*/
if (rw == WRITE && mapping->nrpages) {
retval = invalidate_inode_pages2_range(mapping,
offset >> PAGE_CACHE_SHIFT, end);
[PATCH] dio: invalidate clean pages before dio write This patch fixes a user-triggerable oops that was reported by Leonid Ananiev as archived at http://lkml.org/lkml/2007/2/8/337. dio writes invalidate clean pages that intersect the written region so that subsequent buffered reads go to disk to read the new data. If this fails the interface tries to tell the caller that the cache is inconsistent by returning EIO. Before this patch we had the problem where this invalidation failure would clobber -EIOCBQUEUED as it made its way from fs/direct-io.c to fs/aio.c. Both fs/aio.c and bio completion call aio_complete() and we reference freed memory, usually oopsing. This patch addresses this problem by invalidating before the write so that we can cleanly return -EIO before ->direct_IO() has had a chance to return -EIOCBQUEUED. There is a compromise here. During the dio write we can fault in mmap()ed pages which intersect the written range with get_user_pages() if the user provided them for the source buffer. This is a crazy thing to do, but we can make it mostly work in most cases by trying the invalidation again. The compromise is that we won't return an error if this second invalidation fails if it's an AIO write and we have -EIOCBQUEUED. This was tested by having two processes race performing large O_DIRECT and buffered ordered writes. Within minutes ext3 would see a race between ext3_releasepage() and jbd holding a reference on ordered data buffers and would cause invalidation to fail, panicing the box. The test can be found in the 'aio_dio_bugs' test group in test.kernel.org/autotest. After this patch the test passes. Signed-off-by: Zach Brown <zach.brown@oracle.com> Signed-off-by: Benjamin LaHaise <bcrl@kvack.org> Cc: Leonid Ananiev <leonid.i.ananiev@linux.intel.com> Cc: Nick Piggin <nickpiggin@yahoo.com.au> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2007-03-16 21:38:11 +00:00
if (retval)
goto out;
}
[PATCH] dio: invalidate clean pages before dio write This patch fixes a user-triggerable oops that was reported by Leonid Ananiev as archived at http://lkml.org/lkml/2007/2/8/337. dio writes invalidate clean pages that intersect the written region so that subsequent buffered reads go to disk to read the new data. If this fails the interface tries to tell the caller that the cache is inconsistent by returning EIO. Before this patch we had the problem where this invalidation failure would clobber -EIOCBQUEUED as it made its way from fs/direct-io.c to fs/aio.c. Both fs/aio.c and bio completion call aio_complete() and we reference freed memory, usually oopsing. This patch addresses this problem by invalidating before the write so that we can cleanly return -EIO before ->direct_IO() has had a chance to return -EIOCBQUEUED. There is a compromise here. During the dio write we can fault in mmap()ed pages which intersect the written range with get_user_pages() if the user provided them for the source buffer. This is a crazy thing to do, but we can make it mostly work in most cases by trying the invalidation again. The compromise is that we won't return an error if this second invalidation fails if it's an AIO write and we have -EIOCBQUEUED. This was tested by having two processes race performing large O_DIRECT and buffered ordered writes. Within minutes ext3 would see a race between ext3_releasepage() and jbd holding a reference on ordered data buffers and would cause invalidation to fail, panicing the box. The test can be found in the 'aio_dio_bugs' test group in test.kernel.org/autotest. After this patch the test passes. Signed-off-by: Zach Brown <zach.brown@oracle.com> Signed-off-by: Benjamin LaHaise <bcrl@kvack.org> Cc: Leonid Ananiev <leonid.i.ananiev@linux.intel.com> Cc: Nick Piggin <nickpiggin@yahoo.com.au> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2007-03-16 21:38:11 +00:00
retval = mapping->a_ops->direct_IO(rw, iocb, iov, offset, nr_segs);
if (retval)
goto out;
/*
* Finally, try again to invalidate clean pages which might have been
* faulted in by get_user_pages() if the source of the write was an
* mmap()ed region of the file we're writing. That's a pretty crazy
* thing to do, so we don't support it 100%. If this invalidation
* fails and we have -EIOCBQUEUED we ignore the failure.
*/
if (rw == WRITE && mapping->nrpages) {
int err = invalidate_inode_pages2_range(mapping,
offset >> PAGE_CACHE_SHIFT, end);
if (err && retval >= 0)
retval = err;
}
out:
return retval;
}
/**
* try_to_release_page() - release old fs-specific metadata on a page
*
* @page: the page which the kernel is trying to free
* @gfp_mask: memory allocation flags (and I/O mode)
*
* The address_space is to try to release any data against the page
* (presumably at page->private). If the release was successful, return `1'.
* Otherwise return zero.
*
* The @gfp_mask argument specifies whether I/O may be performed to release
* this page (__GFP_IO), and whether the call may block (__GFP_WAIT).
*
* NOTE: @gfp_mask may go away, and this function may become non-blocking.
*/
int try_to_release_page(struct page *page, gfp_t gfp_mask)
{
struct address_space * const mapping = page->mapping;
BUG_ON(!PageLocked(page));
if (PageWriteback(page))
return 0;
if (mapping && mapping->a_ops->releasepage)
return mapping->a_ops->releasepage(page, gfp_mask);
return try_to_free_buffers(page);
}
EXPORT_SYMBOL(try_to_release_page);