linux/fs/ncpfs/mmap.c

130 lines
3.0 KiB
C
Raw Normal View History

/*
* mmap.c
*
* Copyright (C) 1995, 1996 by Volker Lendecke
* Modified 1997 Peter Waltenberg, Bill Hawes, David Woodhouse for 2.1 dcache
*
*/
#include <linux/stat.h>
#include <linux/time.h>
#include <linux/kernel.h>
#include <linux/mm.h>
#include <linux/shm.h>
#include <linux/errno.h>
#include <linux/mman.h>
#include <linux/string.h>
#include <linux/slab.h>
#include <linux/fcntl.h>
#include <linux/ncp_fs.h>
#include "ncplib_kernel.h"
#include <asm/uaccess.h>
#include <asm/system.h>
/*
* Fill in the supplied page for mmap
*/
static struct page* ncp_file_mmap_nopage(struct vm_area_struct *area,
unsigned long address, int *type)
{
struct file *file = area->vm_file;
struct dentry *dentry = file->f_path.dentry;
struct inode *inode = dentry->d_inode;
struct page* page;
char *pg_addr;
unsigned int already_read;
unsigned int count;
int bufsize;
int pos;
page = alloc_page(GFP_HIGHUSER); /* ncpfs has nothing against high pages
as long as recvmsg and memset works on it */
if (!page)
return page;
pg_addr = kmap(page);
address &= PAGE_MASK;
pos = address - area->vm_start + (area->vm_pgoff << PAGE_SHIFT);
count = PAGE_SIZE;
if (address + PAGE_SIZE > area->vm_end) {
count = area->vm_end - address;
}
/* what we can read in one go */
bufsize = NCP_SERVER(inode)->buffer_size;
already_read = 0;
if (ncp_make_open(inode, O_RDONLY) >= 0) {
while (already_read < count) {
int read_this_time;
int to_read;
to_read = bufsize - (pos % bufsize);
to_read = min_t(unsigned int, to_read, count - already_read);
if (ncp_read_kernel(NCP_SERVER(inode),
NCP_FINFO(inode)->file_handle,
pos, to_read,
pg_addr + already_read,
&read_this_time) != 0) {
read_this_time = 0;
}
pos += read_this_time;
already_read += read_this_time;
if (read_this_time < to_read) {
break;
}
}
ncp_inode_close(inode);
}
if (already_read < PAGE_SIZE)
memset(pg_addr + already_read, 0, PAGE_SIZE - already_read);
flush_dcache_page(page);
kunmap(page);
/*
* If I understand ncp_read_kernel() properly, the above always
* fetches from the network, here the analogue of disk.
* -- wli
*/
if (type)
*type = 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 16:55:45 +08:00
count_vm_event(PGMAJFAULT);
return page;
}
static struct vm_operations_struct ncp_file_mmap =
{
.nopage = ncp_file_mmap_nopage,
};
/* This is used for a general mmap of a ncp file */
int ncp_mmap(struct file *file, struct vm_area_struct *vma)
{
struct inode *inode = file->f_path.dentry->d_inode;
DPRINTK("ncp_mmap: called\n");
if (!ncp_conn_valid(NCP_SERVER(inode)))
return -EIO;
/* only PAGE_COW or read-only supported now */
if (vma->vm_flags & VM_SHARED)
return -EINVAL;
/* we do not support files bigger than 4GB... We eventually
supports just 4GB... */
if (((vma->vm_end - vma->vm_start) >> PAGE_SHIFT) + vma->vm_pgoff
> (1U << (32 - PAGE_SHIFT)))
return -EFBIG;
vma->vm_ops = &ncp_file_mmap;
mm: fix fault vs invalidate race for linear mappings Fix the race between invalidate_inode_pages and do_no_page. Andrea Arcangeli identified a subtle race between invalidation of pages from pagecache with userspace mappings, and do_no_page. The issue is that invalidation has to shoot down all mappings to the page, before it can be discarded from the pagecache. Between shooting down ptes to a particular page, and actually dropping the struct page from the pagecache, do_no_page from any process might fault on that page and establish a new mapping to the page just before it gets discarded from the pagecache. The most common case where such invalidation is used is in file truncation. This case was catered for by doing a sort of open-coded seqlock between the file's i_size, and its truncate_count. Truncation will decrease i_size, then increment truncate_count before unmapping userspace pages; do_no_page will read truncate_count, then find the page if it is within i_size, and then check truncate_count under the page table lock and back out and retry if it had subsequently been changed (ptl will serialise against unmapping, and ensure a potentially updated truncate_count is actually visible). Complexity and documentation issues aside, the locking protocol fails in the case where we would like to invalidate pagecache inside i_size. do_no_page can come in anytime and filemap_nopage is not aware of the invalidation in progress (as it is when it is outside i_size). The end result is that dangling (->mapping == NULL) pages that appear to be from a particular file may be mapped into userspace with nonsense data. Valid mappings to the same place will see a different page. Andrea implemented two working fixes, one using a real seqlock, another using a page->flags bit. He also proposed using the page lock in do_no_page, but that was initially considered too heavyweight. However, it is not a global or per-file lock, and the page cacheline is modified in do_no_page to increment _count and _mapcount anyway, so a further modification should not be a large performance hit. Scalability is not an issue. This patch implements this latter approach. ->nopage implementations return with the page locked if it is possible for their underlying file to be invalidated (in that case, they must set a special vm_flags bit to indicate so). do_no_page only unlocks the page after setting up the mapping completely. invalidation is excluded because it holds the page lock during invalidation of each page (and ensures that the page is not mapped while holding the lock). This also allows significant simplifications in do_no_page, because we have the page locked in the right place in the pagecache from the start. Signed-off-by: Nick Piggin <npiggin@suse.de> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2007-07-19 16:46:57 +08:00
vma->vm_flags |= VM_CAN_INVALIDATE;
file_accessed(file);
return 0;
}