![Christoph Hellwig](/assets/img/avatar_default.png)
While Linux provided an O_SYNC flag basically since day 1, it took until Linux 2.4.0-test12pre2 to actually get it implemented for filesystems, since that day we had generic_osync_around with only minor changes and the great "For now, when the user asks for O_SYNC, we'll actually give O_DSYNC" comment. This patch intends to actually give us real O_SYNC semantics in addition to the O_DSYNC semantics. After Jan's O_SYNC patches which are required before this patch it's actually surprisingly simple, we just need to figure out when to set the datasync flag to vfs_fsync_range and when not. This patch renames the existing O_SYNC flag to O_DSYNC while keeping it's numerical value to keep binary compatibility, and adds a new real O_SYNC flag. To guarantee backwards compatiblity it is defined as expanding to both the O_DSYNC and the new additional binary flag (__O_SYNC) to make sure we are backwards-compatible when compiled against the new headers. This also means that all places that don't care about the differences can just check O_DSYNC and get the right behaviour for O_SYNC, too - only places that actuall care need to check __O_SYNC in addition. Drivers and network filesystems have been updated in a fail safe way to always do the full sync magic if O_DSYNC is set. The few places setting O_SYNC for lower layers are kept that way for now to stay failsafe. We enforce that O_DSYNC is set when __O_SYNC is set early in the open path to make sure we always get these sane options. Note that parisc really screwed up their headers as they already define a O_DSYNC that has always been a no-op. We try to repair it by using it for the new O_DSYNC and redefinining O_SYNC to send both the traditional O_SYNC numerical value _and_ the O_DSYNC one. Cc: Richard Henderson <rth@twiddle.net> Cc: Ivan Kokshaysky <ink@jurassic.park.msu.ru> Cc: Grant Grundler <grundler@parisc-linux.org> Cc: "David S. Miller" <davem@davemloft.net> Cc: Ingo Molnar <mingo@elte.hu> Cc: "H. Peter Anvin" <hpa@zytor.com> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Al Viro <viro@zeniv.linux.org.uk> Cc: Andreas Dilger <adilger@sun.com> Acked-by: Trond Myklebust <Trond.Myklebust@netapp.com> Acked-by: Kyle McMartin <kyle@mcmartin.ca> Acked-by: Ulrich Drepper <drepper@redhat.com> Signed-off-by: Christoph Hellwig <hch@lst.de> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Jan Kara <jack@suse.cz>
202 lines
5 KiB
C
202 lines
5 KiB
C
/*
|
|
* This file is subject to the terms and conditions of the GNU General Public
|
|
* License. See the file "COPYING" in the main directory of this archive
|
|
* for more details.
|
|
*
|
|
* Copyright (C) 1994 - 2003, 06, 07 by Ralf Baechle (ralf@linux-mips.org)
|
|
* Copyright (C) 2007 MIPS Technologies, Inc.
|
|
*/
|
|
#include <linux/fs.h>
|
|
#include <linux/fcntl.h>
|
|
#include <linux/init.h>
|
|
#include <linux/kernel.h>
|
|
#include <linux/linkage.h>
|
|
#include <linux/module.h>
|
|
#include <linux/sched.h>
|
|
#include <linux/syscalls.h>
|
|
#include <linux/mm.h>
|
|
|
|
#include <asm/cacheflush.h>
|
|
#include <asm/processor.h>
|
|
#include <asm/cpu.h>
|
|
#include <asm/cpu-features.h>
|
|
|
|
/* Cache operations. */
|
|
void (*flush_cache_all)(void);
|
|
void (*__flush_cache_all)(void);
|
|
void (*flush_cache_mm)(struct mm_struct *mm);
|
|
void (*flush_cache_range)(struct vm_area_struct *vma, unsigned long start,
|
|
unsigned long end);
|
|
void (*flush_cache_page)(struct vm_area_struct *vma, unsigned long page,
|
|
unsigned long pfn);
|
|
void (*flush_icache_range)(unsigned long start, unsigned long end);
|
|
void (*local_flush_icache_range)(unsigned long start, unsigned long end);
|
|
|
|
void (*__flush_cache_vmap)(void);
|
|
void (*__flush_cache_vunmap)(void);
|
|
|
|
/* MIPS specific cache operations */
|
|
void (*flush_cache_sigtramp)(unsigned long addr);
|
|
void (*local_flush_data_cache_page)(void * addr);
|
|
void (*flush_data_cache_page)(unsigned long addr);
|
|
void (*flush_icache_all)(void);
|
|
|
|
EXPORT_SYMBOL_GPL(local_flush_data_cache_page);
|
|
EXPORT_SYMBOL(flush_data_cache_page);
|
|
|
|
#ifdef CONFIG_DMA_NONCOHERENT
|
|
|
|
/* DMA cache operations. */
|
|
void (*_dma_cache_wback_inv)(unsigned long start, unsigned long size);
|
|
void (*_dma_cache_wback)(unsigned long start, unsigned long size);
|
|
void (*_dma_cache_inv)(unsigned long start, unsigned long size);
|
|
|
|
EXPORT_SYMBOL(_dma_cache_wback_inv);
|
|
|
|
#endif /* CONFIG_DMA_NONCOHERENT */
|
|
|
|
/*
|
|
* We could optimize the case where the cache argument is not BCACHE but
|
|
* that seems very atypical use ...
|
|
*/
|
|
SYSCALL_DEFINE3(cacheflush, unsigned long, addr, unsigned long, bytes,
|
|
unsigned int, cache)
|
|
{
|
|
if (bytes == 0)
|
|
return 0;
|
|
if (!access_ok(VERIFY_WRITE, (void __user *) addr, bytes))
|
|
return -EFAULT;
|
|
|
|
flush_icache_range(addr, addr + bytes);
|
|
|
|
return 0;
|
|
}
|
|
|
|
void __flush_dcache_page(struct page *page)
|
|
{
|
|
struct address_space *mapping = page_mapping(page);
|
|
unsigned long addr;
|
|
|
|
if (PageHighMem(page))
|
|
return;
|
|
if (mapping && !mapping_mapped(mapping)) {
|
|
SetPageDcacheDirty(page);
|
|
return;
|
|
}
|
|
|
|
/*
|
|
* We could delay the flush for the !page_mapping case too. But that
|
|
* case is for exec env/arg pages and those are %99 certainly going to
|
|
* get faulted into the tlb (and thus flushed) anyways.
|
|
*/
|
|
addr = (unsigned long) page_address(page);
|
|
flush_data_cache_page(addr);
|
|
}
|
|
|
|
EXPORT_SYMBOL(__flush_dcache_page);
|
|
|
|
void __flush_anon_page(struct page *page, unsigned long vmaddr)
|
|
{
|
|
unsigned long addr = (unsigned long) page_address(page);
|
|
|
|
if (pages_do_alias(addr, vmaddr)) {
|
|
if (page_mapped(page) && !Page_dcache_dirty(page)) {
|
|
void *kaddr;
|
|
|
|
kaddr = kmap_coherent(page, vmaddr);
|
|
flush_data_cache_page((unsigned long)kaddr);
|
|
kunmap_coherent();
|
|
} else
|
|
flush_data_cache_page(addr);
|
|
}
|
|
}
|
|
|
|
EXPORT_SYMBOL(__flush_anon_page);
|
|
|
|
void __update_cache(struct vm_area_struct *vma, unsigned long address,
|
|
pte_t pte)
|
|
{
|
|
struct page *page;
|
|
unsigned long pfn, addr;
|
|
int exec = (vma->vm_flags & VM_EXEC) && !cpu_has_ic_fills_f_dc;
|
|
|
|
pfn = pte_pfn(pte);
|
|
if (unlikely(!pfn_valid(pfn)))
|
|
return;
|
|
page = pfn_to_page(pfn);
|
|
if (page_mapping(page) && Page_dcache_dirty(page)) {
|
|
addr = (unsigned long) page_address(page);
|
|
if (exec || pages_do_alias(addr, address & PAGE_MASK))
|
|
flush_data_cache_page(addr);
|
|
ClearPageDcacheDirty(page);
|
|
}
|
|
}
|
|
|
|
unsigned long _page_cachable_default;
|
|
EXPORT_SYMBOL_GPL(_page_cachable_default);
|
|
|
|
static inline void setup_protection_map(void)
|
|
{
|
|
protection_map[0] = PAGE_NONE;
|
|
protection_map[1] = PAGE_READONLY;
|
|
protection_map[2] = PAGE_COPY;
|
|
protection_map[3] = PAGE_COPY;
|
|
protection_map[4] = PAGE_READONLY;
|
|
protection_map[5] = PAGE_READONLY;
|
|
protection_map[6] = PAGE_COPY;
|
|
protection_map[7] = PAGE_COPY;
|
|
protection_map[8] = PAGE_NONE;
|
|
protection_map[9] = PAGE_READONLY;
|
|
protection_map[10] = PAGE_SHARED;
|
|
protection_map[11] = PAGE_SHARED;
|
|
protection_map[12] = PAGE_READONLY;
|
|
protection_map[13] = PAGE_READONLY;
|
|
protection_map[14] = PAGE_SHARED;
|
|
protection_map[15] = PAGE_SHARED;
|
|
}
|
|
|
|
void __devinit cpu_cache_init(void)
|
|
{
|
|
if (cpu_has_3k_cache) {
|
|
extern void __weak r3k_cache_init(void);
|
|
|
|
r3k_cache_init();
|
|
}
|
|
if (cpu_has_6k_cache) {
|
|
extern void __weak r6k_cache_init(void);
|
|
|
|
r6k_cache_init();
|
|
}
|
|
if (cpu_has_4k_cache) {
|
|
extern void __weak r4k_cache_init(void);
|
|
|
|
r4k_cache_init();
|
|
}
|
|
if (cpu_has_8k_cache) {
|
|
extern void __weak r8k_cache_init(void);
|
|
|
|
r8k_cache_init();
|
|
}
|
|
if (cpu_has_tx39_cache) {
|
|
extern void __weak tx39_cache_init(void);
|
|
|
|
tx39_cache_init();
|
|
}
|
|
|
|
if (cpu_has_octeon_cache) {
|
|
extern void __weak octeon_cache_init(void);
|
|
|
|
octeon_cache_init();
|
|
}
|
|
|
|
setup_protection_map();
|
|
}
|
|
|
|
int __weak __uncached_access(struct file *file, unsigned long addr)
|
|
{
|
|
if (file->f_flags & O_DSYNC)
|
|
return 1;
|
|
|
|
return addr >= __pa(high_memory);
|
|
}
|