linux/fs/nfs/file.c

917 lines
24 KiB
C
Raw Normal View History

/*
* linux/fs/nfs/file.c
*
* Copyright (C) 1992 Rick Sladkey
*
* Changes Copyright (C) 1994 by Florian La Roche
* - Do not copy data too often around in the kernel.
* - In nfs_file_read the return value of kmalloc wasn't checked.
* - Put in a better version of read look-ahead buffering. Original idea
* and implementation by Wai S Kok elekokws@ee.nus.sg.
*
* Expire cache on write to a file by Wai S Kok (Oct 1994).
*
* Total rewrite of read side for new NFS buffer cache.. Linus.
*
* nfs regular file handling functions
*/
#include <linux/module.h>
#include <linux/time.h>
#include <linux/kernel.h>
#include <linux/errno.h>
#include <linux/fcntl.h>
#include <linux/stat.h>
#include <linux/nfs_fs.h>
#include <linux/nfs_mount.h>
#include <linux/mm.h>
#include <linux/pagemap.h>
include cleanup: Update gfp.h and slab.h includes to prepare for breaking implicit slab.h inclusion from percpu.h percpu.h is included by sched.h and module.h and thus ends up being included when building most .c files. percpu.h includes slab.h which in turn includes gfp.h making everything defined by the two files universally available and complicating inclusion dependencies. percpu.h -> slab.h dependency is about to be removed. Prepare for this change by updating users of gfp and slab facilities include those headers directly instead of assuming availability. As this conversion needs to touch large number of source files, the following script is used as the basis of conversion. http://userweb.kernel.org/~tj/misc/slabh-sweep.py The script does the followings. * Scan files for gfp and slab usages and update includes such that only the necessary includes are there. ie. if only gfp is used, gfp.h, if slab is used, slab.h. * When the script inserts a new include, it looks at the include blocks and try to put the new include such that its order conforms to its surrounding. It's put in the include block which contains core kernel includes, in the same order that the rest are ordered - alphabetical, Christmas tree, rev-Xmas-tree or at the end if there doesn't seem to be any matching order. * If the script can't find a place to put a new include (mostly because the file doesn't have fitting include block), it prints out an error message indicating which .h file needs to be added to the file. The conversion was done in the following steps. 1. The initial automatic conversion of all .c files updated slightly over 4000 files, deleting around 700 includes and adding ~480 gfp.h and ~3000 slab.h inclusions. The script emitted errors for ~400 files. 2. Each error was manually checked. Some didn't need the inclusion, some needed manual addition while adding it to implementation .h or embedding .c file was more appropriate for others. This step added inclusions to around 150 files. 3. The script was run again and the output was compared to the edits from #2 to make sure no file was left behind. 4. Several build tests were done and a couple of problems were fixed. e.g. lib/decompress_*.c used malloc/free() wrappers around slab APIs requiring slab.h to be added manually. 5. The script was run on all .h files but without automatically editing them as sprinkling gfp.h and slab.h inclusions around .h files could easily lead to inclusion dependency hell. Most gfp.h inclusion directives were ignored as stuff from gfp.h was usually wildly available and often used in preprocessor macros. Each slab.h inclusion directive was examined and added manually as necessary. 6. percpu.h was updated not to include slab.h. 7. Build test were done on the following configurations and failures were fixed. CONFIG_GCOV_KERNEL was turned off for all tests (as my distributed build env didn't work with gcov compiles) and a few more options had to be turned off depending on archs to make things build (like ipr on powerpc/64 which failed due to missing writeq). * x86 and x86_64 UP and SMP allmodconfig and a custom test config. * powerpc and powerpc64 SMP allmodconfig * sparc and sparc64 SMP allmodconfig * ia64 SMP allmodconfig * s390 SMP allmodconfig * alpha SMP allmodconfig * um on x86_64 SMP allmodconfig 8. percpu.h modifications were reverted so that it could be applied as a separate patch and serve as bisection point. Given the fact that I had only a couple of failures from tests on step 6, I'm fairly confident about the coverage of this conversion patch. If there is a breakage, it's likely to be something in one of the arch headers which should be easily discoverable easily on most builds of the specific arch. Signed-off-by: Tejun Heo <tj@kernel.org> Guess-its-ok-by: Christoph Lameter <cl@linux-foundation.org> Cc: Ingo Molnar <mingo@redhat.com> Cc: Lee Schermerhorn <Lee.Schermerhorn@hp.com>
2010-03-24 08:04:11 +00:00
#include <linux/gfp.h>
#include <linux/swap.h>
#include <asm/uaccess.h>
#include "delegation.h"
#include "internal.h"
#include "iostat.h"
#include "fscache.h"
#include "pnfs.h"
#include "nfstrace.h"
#define NFSDBG_FACILITY NFSDBG_FILE
static const struct vm_operations_struct nfs_file_vm_ops;
/* Hack for future NFS swap support */
#ifndef IS_SWAPFILE
# define IS_SWAPFILE(inode) (0)
#endif
int nfs_check_flags(int flags)
{
if ((flags & (O_APPEND | O_DIRECT)) == (O_APPEND | O_DIRECT))
return -EINVAL;
return 0;
}
EXPORT_SYMBOL_GPL(nfs_check_flags);
/*
* Open file
*/
static int
nfs_file_open(struct inode *inode, struct file *filp)
{
int res;
dprintk("NFS: open file(%pD2)\n", filp);
nfs_inc_stats(inode, NFSIOS_VFSOPEN);
res = nfs_check_flags(filp->f_flags);
if (res)
return res;
res = nfs_open(inode, filp);
return res;
}
int
nfs_file_release(struct inode *inode, struct file *filp)
{
dprintk("NFS: release(%pD2)\n", filp);
nfs_inc_stats(inode, NFSIOS_VFSRELEASE);
nfs_file_clear_open_context(filp);
return 0;
}
EXPORT_SYMBOL_GPL(nfs_file_release);
/**
* nfs_revalidate_size - Revalidate the file size
* @inode - pointer to inode struct
* @file - pointer to struct file
*
* Revalidates the file length. This is basically a wrapper around
* nfs_revalidate_inode() that takes into account the fact that we may
* have cached writes (in which case we don't care about the server's
* idea of what the file length is), or O_DIRECT (in which case we
* shouldn't trust the cache).
*/
static int nfs_revalidate_file_size(struct inode *inode, struct file *filp)
{
struct nfs_server *server = NFS_SERVER(inode);
struct nfs_inode *nfsi = NFS_I(inode);
if (nfs_have_delegated_attributes(inode))
goto out_noreval;
if (filp->f_flags & O_DIRECT)
goto force_reval;
if (nfsi->cache_validity & NFS_INO_REVAL_PAGECACHE)
goto force_reval;
if (nfs_attribute_timeout(inode))
goto force_reval;
out_noreval:
return 0;
force_reval:
return __nfs_revalidate_inode(server, inode);
}
loff_t nfs_file_llseek(struct file *filp, loff_t offset, int whence)
{
dprintk("NFS: llseek file(%pD2, %lld, %d)\n",
filp, offset, whence);
/*
* whence == SEEK_END || SEEK_DATA || SEEK_HOLE => we must revalidate
* the cached file length
*/
if (whence != SEEK_SET && whence != SEEK_CUR) {
struct inode *inode = filp->f_mapping->host;
int retval = nfs_revalidate_file_size(inode, filp);
if (retval < 0)
return (loff_t)retval;
}
return generic_file_llseek(filp, offset, whence);
}
EXPORT_SYMBOL_GPL(nfs_file_llseek);
/*
* Flush all dirty pages, and check for write errors.
*/
static int
nfs_file_flush(struct file *file, fl_owner_t id)
{
struct inode *inode = file_inode(file);
dprintk("NFS: flush(%pD2)\n", file);
nfs_inc_stats(inode, NFSIOS_VFSFLUSH);
if ((file->f_mode & FMODE_WRITE) == 0)
return 0;
/* Flush writes to the server and return any errors */
return vfs_fsync(file, 0);
}
ssize_t
nfs_file_read(struct kiocb *iocb, struct iov_iter *to)
{
struct inode *inode = file_inode(iocb->ki_filp);
ssize_t result;
if (iocb->ki_flags & IOCB_DIRECT)
return nfs_file_direct_read(iocb, to, iocb->ki_pos);
dprintk("NFS: read(%pD2, %zu@%lu)\n",
iocb->ki_filp,
iov_iter_count(to), (unsigned long) iocb->ki_pos);
result = nfs_revalidate_mapping_protected(inode, iocb->ki_filp->f_mapping);
if (!result) {
result = generic_file_read_iter(iocb, to);
if (result > 0)
nfs_add_stats(inode, NFSIOS_NORMALREADBYTES, result);
}
return result;
}
EXPORT_SYMBOL_GPL(nfs_file_read);
ssize_t
nfs_file_splice_read(struct file *filp, loff_t *ppos,
struct pipe_inode_info *pipe, size_t count,
unsigned int flags)
{
struct inode *inode = file_inode(filp);
ssize_t res;
dprintk("NFS: splice_read(%pD2, %lu@%Lu)\n",
filp, (unsigned long) count, (unsigned long long) *ppos);
res = nfs_revalidate_mapping_protected(inode, filp->f_mapping);
if (!res) {
res = generic_file_splice_read(filp, ppos, pipe, count, flags);
if (res > 0)
nfs_add_stats(inode, NFSIOS_NORMALREADBYTES, res);
}
return res;
}
EXPORT_SYMBOL_GPL(nfs_file_splice_read);
int
nfs_file_mmap(struct file * file, struct vm_area_struct * vma)
{
struct inode *inode = file_inode(file);
int status;
dprintk("NFS: mmap(%pD2)\n", file);
/* Note: generic_file_mmap() returns ENOSYS on nommu systems
* so we call that before revalidating the mapping
*/
status = generic_file_mmap(file, vma);
if (!status) {
vma->vm_ops = &nfs_file_vm_ops;
status = nfs_revalidate_mapping(inode, file->f_mapping);
}
return status;
}
EXPORT_SYMBOL_GPL(nfs_file_mmap);
/*
* Flush any dirty pages for this process, and check for write errors.
* The return status from this call provides a reliable indication of
* whether any write errors occurred for this process.
*
* Notice that it clears the NFS_CONTEXT_ERROR_WRITE before synching to
* disk, but it retrieves and clears ctx->error after synching, despite
* the two being set at the same time in nfs_context_set_write_error().
* This is because the former is used to notify the _next_ call to
* nfs_file_write() that a write error occurred, and hence cause it to
* fall back to doing a synchronous write.
*/
int
nfs_file_fsync_commit(struct file *file, loff_t start, loff_t end, int datasync)
{
struct nfs_open_context *ctx = nfs_file_open_context(file);
struct inode *inode = file_inode(file);
int have_error, do_resend, status;
int ret = 0;
dprintk("NFS: fsync file(%pD2) datasync %d\n", file, datasync);
nfs_inc_stats(inode, NFSIOS_VFSFSYNC);
do_resend = test_and_clear_bit(NFS_CONTEXT_RESEND_WRITES, &ctx->flags);
have_error = test_and_clear_bit(NFS_CONTEXT_ERROR_WRITE, &ctx->flags);
status = nfs_commit_inode(inode, FLUSH_SYNC);
have_error |= test_bit(NFS_CONTEXT_ERROR_WRITE, &ctx->flags);
if (have_error) {
ret = xchg(&ctx->error, 0);
if (ret)
goto out;
}
if (status < 0) {
ret = status;
goto out;
}
do_resend |= test_bit(NFS_CONTEXT_RESEND_WRITES, &ctx->flags);
if (do_resend)
ret = -EAGAIN;
out:
return ret;
}
EXPORT_SYMBOL_GPL(nfs_file_fsync_commit);
static int
nfs_file_fsync(struct file *file, loff_t start, loff_t end, int datasync)
{
int ret;
struct inode *inode = file_inode(file);
trace_nfs_fsync_enter(inode);
nfs_inode_dio_wait(inode);
do {
ret = filemap_write_and_wait_range(inode->i_mapping, start, end);
if (ret != 0)
break;
inode_lock(inode);
ret = nfs_file_fsync_commit(file, start, end, datasync);
inode_unlock(inode);
/*
* If nfs_file_fsync_commit detected a server reboot, then
* resend all dirty pages that might have been covered by
* the NFS_CONTEXT_RESEND_WRITES flag
*/
start = 0;
end = LLONG_MAX;
} while (ret == -EAGAIN);
trace_nfs_fsync_exit(inode, ret);
return ret;
}
NFS: read-modify-write page updating Hi. I have a proposal for possibly resolving this issue. I believe that this situation occurs due to the way that the Linux NFS client handles writes which modify partial pages. The Linux NFS client handles partial page modifications by allocating a page from the page cache, copying the data from the user level into the page, and then keeping track of the offset and length of the modified portions of the page. The page is not marked as up to date because there are portions of the page which do not contain valid file contents. When a read call comes in for a portion of the page, the contents of the page must be read in the from the server. However, since the page may already contain some modified data, that modified data must be written to the server before the file contents can be read back in the from server. And, since the writing and reading can not be done atomically, the data must be written and committed to stable storage on the server for safety purposes. This means either a FILE_SYNC WRITE or a UNSTABLE WRITE followed by a COMMIT. This has been discussed at length previously. This algorithm could be described as modify-write-read. It is most efficient when the application only updates pages and does not read them. My proposed solution is to add a heuristic to decide whether to do this modify-write-read algorithm or switch to a read- modify-write algorithm when initially allocating the page in the write system call path. The heuristic uses the modes that the file was opened with, the offset in the page to read from, and the size of the region to read. If the file was opened for reading in addition to writing and the page would not be filled completely with data from the user level, then read in the old contents of the page and mark it as Uptodate before copying in the new data. If the page would be completely filled with data from the user level, then there would be no reason to read in the old contents because they would just be copied over. This would optimize for applications which randomly access and update portions of files. The linkage editor for the C compiler is an example of such a thing. I tested the attached patch by using rpmbuild to build the current Fedora rawhide kernel. The kernel without the patch generated about 269,500 WRITE requests. The modified kernel containing the patch generated about 261,000 WRITE requests. Thus, about 8,500 fewer WRITE requests were generated. I suspect that many of these additional WRITE requests were probably FILE_SYNC requests to WRITE a single page, but I didn't test this theory. The difference between this patch and the previous one was to remove the unneeded PageDirty() test. I then retested to ensure that the resulting system continued to behave as desired. Thanx... ps Signed-off-by: Peter Staubach <staubach@redhat.com> Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com>
2009-08-10 12:54:16 +00:00
/*
* Decide whether a read/modify/write cycle may be more efficient
* then a modify/write/read cycle when writing to a page in the
* page cache.
*
* The modify/write/read cycle may occur if a page is read before
* being completely filled by the writer. In this situation, the
* page must be completely written to stable storage on the server
* before it can be refilled by reading in the page from the server.
* This can lead to expensive, small, FILE_SYNC mode writes being
* done.
*
* It may be more efficient to read the page first if the file is
* open for reading in addition to writing, the page is not marked
* as Uptodate, it is not dirty or waiting to be committed,
* indicating that it was previously allocated and then modified,
* that there were valid bytes of data in that range of the file,
* and that the new data won't completely replace the old data in
* that range of the file.
*/
static int nfs_want_read_modify_write(struct file *file, struct page *page,
loff_t pos, unsigned len)
{
unsigned int pglen = nfs_page_length(page);
unsigned int offset = pos & (PAGE_CACHE_SIZE - 1);
unsigned int end = offset + len;
if (pnfs_ld_read_whole_page(file->f_mapping->host)) {
if (!PageUptodate(page))
return 1;
return 0;
}
NFS: read-modify-write page updating Hi. I have a proposal for possibly resolving this issue. I believe that this situation occurs due to the way that the Linux NFS client handles writes which modify partial pages. The Linux NFS client handles partial page modifications by allocating a page from the page cache, copying the data from the user level into the page, and then keeping track of the offset and length of the modified portions of the page. The page is not marked as up to date because there are portions of the page which do not contain valid file contents. When a read call comes in for a portion of the page, the contents of the page must be read in the from the server. However, since the page may already contain some modified data, that modified data must be written to the server before the file contents can be read back in the from server. And, since the writing and reading can not be done atomically, the data must be written and committed to stable storage on the server for safety purposes. This means either a FILE_SYNC WRITE or a UNSTABLE WRITE followed by a COMMIT. This has been discussed at length previously. This algorithm could be described as modify-write-read. It is most efficient when the application only updates pages and does not read them. My proposed solution is to add a heuristic to decide whether to do this modify-write-read algorithm or switch to a read- modify-write algorithm when initially allocating the page in the write system call path. The heuristic uses the modes that the file was opened with, the offset in the page to read from, and the size of the region to read. If the file was opened for reading in addition to writing and the page would not be filled completely with data from the user level, then read in the old contents of the page and mark it as Uptodate before copying in the new data. If the page would be completely filled with data from the user level, then there would be no reason to read in the old contents because they would just be copied over. This would optimize for applications which randomly access and update portions of files. The linkage editor for the C compiler is an example of such a thing. I tested the attached patch by using rpmbuild to build the current Fedora rawhide kernel. The kernel without the patch generated about 269,500 WRITE requests. The modified kernel containing the patch generated about 261,000 WRITE requests. Thus, about 8,500 fewer WRITE requests were generated. I suspect that many of these additional WRITE requests were probably FILE_SYNC requests to WRITE a single page, but I didn't test this theory. The difference between this patch and the previous one was to remove the unneeded PageDirty() test. I then retested to ensure that the resulting system continued to behave as desired. Thanx... ps Signed-off-by: Peter Staubach <staubach@redhat.com> Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com>
2009-08-10 12:54:16 +00:00
if ((file->f_mode & FMODE_READ) && /* open for read? */
!PageUptodate(page) && /* Uptodate? */
!PagePrivate(page) && /* i/o request already? */
pglen && /* valid bytes of file? */
(end < pglen || offset)) /* replace all valid bytes? */
return 1;
return 0;
}
/*
* This does the "real" work of the write. We must allocate and lock the
* page to be sent back to the generic routine, which then copies the
* data from user space.
*
* If the writer ends up delaying the write, the writer needs to
* increment the page use counts until he is done with the page.
*/
static int nfs_write_begin(struct file *file, struct address_space *mapping,
loff_t pos, unsigned len, unsigned flags,
struct page **pagep, void **fsdata)
{
int ret;
NFS: read-modify-write page updating Hi. I have a proposal for possibly resolving this issue. I believe that this situation occurs due to the way that the Linux NFS client handles writes which modify partial pages. The Linux NFS client handles partial page modifications by allocating a page from the page cache, copying the data from the user level into the page, and then keeping track of the offset and length of the modified portions of the page. The page is not marked as up to date because there are portions of the page which do not contain valid file contents. When a read call comes in for a portion of the page, the contents of the page must be read in the from the server. However, since the page may already contain some modified data, that modified data must be written to the server before the file contents can be read back in the from server. And, since the writing and reading can not be done atomically, the data must be written and committed to stable storage on the server for safety purposes. This means either a FILE_SYNC WRITE or a UNSTABLE WRITE followed by a COMMIT. This has been discussed at length previously. This algorithm could be described as modify-write-read. It is most efficient when the application only updates pages and does not read them. My proposed solution is to add a heuristic to decide whether to do this modify-write-read algorithm or switch to a read- modify-write algorithm when initially allocating the page in the write system call path. The heuristic uses the modes that the file was opened with, the offset in the page to read from, and the size of the region to read. If the file was opened for reading in addition to writing and the page would not be filled completely with data from the user level, then read in the old contents of the page and mark it as Uptodate before copying in the new data. If the page would be completely filled with data from the user level, then there would be no reason to read in the old contents because they would just be copied over. This would optimize for applications which randomly access and update portions of files. The linkage editor for the C compiler is an example of such a thing. I tested the attached patch by using rpmbuild to build the current Fedora rawhide kernel. The kernel without the patch generated about 269,500 WRITE requests. The modified kernel containing the patch generated about 261,000 WRITE requests. Thus, about 8,500 fewer WRITE requests were generated. I suspect that many of these additional WRITE requests were probably FILE_SYNC requests to WRITE a single page, but I didn't test this theory. The difference between this patch and the previous one was to remove the unneeded PageDirty() test. I then retested to ensure that the resulting system continued to behave as desired. Thanx... ps Signed-off-by: Peter Staubach <staubach@redhat.com> Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com>
2009-08-10 12:54:16 +00:00
pgoff_t index = pos >> PAGE_CACHE_SHIFT;
struct page *page;
NFS: read-modify-write page updating Hi. I have a proposal for possibly resolving this issue. I believe that this situation occurs due to the way that the Linux NFS client handles writes which modify partial pages. The Linux NFS client handles partial page modifications by allocating a page from the page cache, copying the data from the user level into the page, and then keeping track of the offset and length of the modified portions of the page. The page is not marked as up to date because there are portions of the page which do not contain valid file contents. When a read call comes in for a portion of the page, the contents of the page must be read in the from the server. However, since the page may already contain some modified data, that modified data must be written to the server before the file contents can be read back in the from server. And, since the writing and reading can not be done atomically, the data must be written and committed to stable storage on the server for safety purposes. This means either a FILE_SYNC WRITE or a UNSTABLE WRITE followed by a COMMIT. This has been discussed at length previously. This algorithm could be described as modify-write-read. It is most efficient when the application only updates pages and does not read them. My proposed solution is to add a heuristic to decide whether to do this modify-write-read algorithm or switch to a read- modify-write algorithm when initially allocating the page in the write system call path. The heuristic uses the modes that the file was opened with, the offset in the page to read from, and the size of the region to read. If the file was opened for reading in addition to writing and the page would not be filled completely with data from the user level, then read in the old contents of the page and mark it as Uptodate before copying in the new data. If the page would be completely filled with data from the user level, then there would be no reason to read in the old contents because they would just be copied over. This would optimize for applications which randomly access and update portions of files. The linkage editor for the C compiler is an example of such a thing. I tested the attached patch by using rpmbuild to build the current Fedora rawhide kernel. The kernel without the patch generated about 269,500 WRITE requests. The modified kernel containing the patch generated about 261,000 WRITE requests. Thus, about 8,500 fewer WRITE requests were generated. I suspect that many of these additional WRITE requests were probably FILE_SYNC requests to WRITE a single page, but I didn't test this theory. The difference between this patch and the previous one was to remove the unneeded PageDirty() test. I then retested to ensure that the resulting system continued to behave as desired. Thanx... ps Signed-off-by: Peter Staubach <staubach@redhat.com> Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com>
2009-08-10 12:54:16 +00:00
int once_thru = 0;
dfprintk(PAGECACHE, "NFS: write_begin(%pD2(%lu), %u@%lld)\n",
file, mapping->host->i_ino, len, (long long) pos);
NFS: read-modify-write page updating Hi. I have a proposal for possibly resolving this issue. I believe that this situation occurs due to the way that the Linux NFS client handles writes which modify partial pages. The Linux NFS client handles partial page modifications by allocating a page from the page cache, copying the data from the user level into the page, and then keeping track of the offset and length of the modified portions of the page. The page is not marked as up to date because there are portions of the page which do not contain valid file contents. When a read call comes in for a portion of the page, the contents of the page must be read in the from the server. However, since the page may already contain some modified data, that modified data must be written to the server before the file contents can be read back in the from server. And, since the writing and reading can not be done atomically, the data must be written and committed to stable storage on the server for safety purposes. This means either a FILE_SYNC WRITE or a UNSTABLE WRITE followed by a COMMIT. This has been discussed at length previously. This algorithm could be described as modify-write-read. It is most efficient when the application only updates pages and does not read them. My proposed solution is to add a heuristic to decide whether to do this modify-write-read algorithm or switch to a read- modify-write algorithm when initially allocating the page in the write system call path. The heuristic uses the modes that the file was opened with, the offset in the page to read from, and the size of the region to read. If the file was opened for reading in addition to writing and the page would not be filled completely with data from the user level, then read in the old contents of the page and mark it as Uptodate before copying in the new data. If the page would be completely filled with data from the user level, then there would be no reason to read in the old contents because they would just be copied over. This would optimize for applications which randomly access and update portions of files. The linkage editor for the C compiler is an example of such a thing. I tested the attached patch by using rpmbuild to build the current Fedora rawhide kernel. The kernel without the patch generated about 269,500 WRITE requests. The modified kernel containing the patch generated about 261,000 WRITE requests. Thus, about 8,500 fewer WRITE requests were generated. I suspect that many of these additional WRITE requests were probably FILE_SYNC requests to WRITE a single page, but I didn't test this theory. The difference between this patch and the previous one was to remove the unneeded PageDirty() test. I then retested to ensure that the resulting system continued to behave as desired. Thanx... ps Signed-off-by: Peter Staubach <staubach@redhat.com> Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com>
2009-08-10 12:54:16 +00:00
start:
2009-03-11 18:10:30 +00:00
/*
* Prevent starvation issues if someone is doing a consistency
* sync-to-disk
*/
sched: Remove proliferation of wait_on_bit() action functions The current "wait_on_bit" interface requires an 'action' function to be provided which does the actual waiting. There are over 20 such functions, many of them identical. Most cases can be satisfied by one of just two functions, one which uses io_schedule() and one which just uses schedule(). So: Rename wait_on_bit and wait_on_bit_lock to wait_on_bit_action and wait_on_bit_lock_action to make it explicit that they need an action function. Introduce new wait_on_bit{,_lock} and wait_on_bit{,_lock}_io which are *not* given an action function but implicitly use a standard one. The decision to error-out if a signal is pending is now made based on the 'mode' argument rather than being encoded in the action function. All instances of the old wait_on_bit and wait_on_bit_lock which can use the new version have been changed accordingly and their action functions have been discarded. wait_on_bit{_lock} does not return any specific error code in the event of a signal so the caller must check for non-zero and interpolate their own error code as appropriate. The wait_on_bit() call in __fscache_wait_on_invalidate() was ambiguous as it specified TASK_UNINTERRUPTIBLE but used fscache_wait_bit_interruptible as an action function. David Howells confirms this should be uniformly "uninterruptible" The main remaining user of wait_on_bit{,_lock}_action is NFS which needs to use a freezer-aware schedule() call. A comment in fs/gfs2/glock.c notes that having multiple 'action' functions is useful as they display differently in the 'wchan' field of 'ps'. (and /proc/$PID/wchan). As the new bit_wait{,_io} functions are tagged "__sched", they will not show up at all, but something higher in the stack. So the distinction will still be visible, only with different function names (gds2_glock_wait versus gfs2_glock_dq_wait in the gfs2/glock.c case). Since first version of this patch (against 3.15) two new action functions appeared, on in NFS and one in CIFS. CIFS also now uses an action function that makes the same freezer aware schedule call as NFS. Signed-off-by: NeilBrown <neilb@suse.de> Acked-by: David Howells <dhowells@redhat.com> (fscache, keys) Acked-by: Steven Whitehouse <swhiteho@redhat.com> (gfs2) Acked-by: Peter Zijlstra <peterz@infradead.org> Cc: Oleg Nesterov <oleg@redhat.com> Cc: Steve French <sfrench@samba.org> Cc: Linus Torvalds <torvalds@linux-foundation.org> Link: http://lkml.kernel.org/r/20140707051603.28027.72349.stgit@notabene.brown Signed-off-by: Ingo Molnar <mingo@kernel.org>
2014-07-07 05:16:04 +00:00
ret = wait_on_bit_action(&NFS_I(mapping->host)->flags, NFS_INO_FLUSHING,
nfs_wait_bit_killable, TASK_KILLABLE);
2009-03-11 18:10:30 +00:00
if (ret)
return ret;
/*
* Wait for O_DIRECT to complete
*/
nfs_inode_dio_wait(mapping->host);
2009-03-11 18:10:30 +00:00
fs: symlink write_begin allocation context fix With the write_begin/write_end aops, page_symlink was broken because it could no longer pass a GFP_NOFS type mask into the point where the allocations happened. They are done in write_begin, which would always assume that the filesystem can be entered from reclaim. This bug could cause filesystem deadlocks. The funny thing with having a gfp_t mask there is that it doesn't really allow the caller to arbitrarily tinker with the context in which it can be called. It couldn't ever be GFP_ATOMIC, for example, because it needs to take the page lock. The only thing any callers care about is __GFP_FS anyway, so turn that into a single flag. Add a new flag for write_begin, AOP_FLAG_NOFS. Filesystems can now act on this flag in their write_begin function. Change __grab_cache_page to accept a nofs argument as well, to honour that flag (while we're there, change the name to grab_cache_page_write_begin which is more instructive and does away with random leading underscores). This is really a more flexible way to go in the end anyway -- if a filesystem happens to want any extra allocations aside from the pagecache ones in ints write_begin function, it may now use GFP_KERNEL (rather than GFP_NOFS) for common case allocations (eg. ocfs2_alloc_write_ctxt, for a random example). [kosaki.motohiro@jp.fujitsu.com: fix ubifs] [kosaki.motohiro@jp.fujitsu.com: fix fuse] Signed-off-by: Nick Piggin <npiggin@suse.de> Reviewed-by: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com> Cc: <stable@kernel.org> [2.6.28.x] Signed-off-by: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> [ Cleaned up the calling convention: just pass in the AOP flags untouched to the grab_cache_page_write_begin() function. That just simplifies everybody, and may even allow future expansion of the logic. - Linus ] Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2009-01-04 20:00:53 +00:00
page = grab_cache_page_write_begin(mapping, index, flags);
if (!page)
return -ENOMEM;
*pagep = page;
ret = nfs_flush_incompatible(file, page);
if (ret) {
unlock_page(page);
page_cache_release(page);
NFS: read-modify-write page updating Hi. I have a proposal for possibly resolving this issue. I believe that this situation occurs due to the way that the Linux NFS client handles writes which modify partial pages. The Linux NFS client handles partial page modifications by allocating a page from the page cache, copying the data from the user level into the page, and then keeping track of the offset and length of the modified portions of the page. The page is not marked as up to date because there are portions of the page which do not contain valid file contents. When a read call comes in for a portion of the page, the contents of the page must be read in the from the server. However, since the page may already contain some modified data, that modified data must be written to the server before the file contents can be read back in the from server. And, since the writing and reading can not be done atomically, the data must be written and committed to stable storage on the server for safety purposes. This means either a FILE_SYNC WRITE or a UNSTABLE WRITE followed by a COMMIT. This has been discussed at length previously. This algorithm could be described as modify-write-read. It is most efficient when the application only updates pages and does not read them. My proposed solution is to add a heuristic to decide whether to do this modify-write-read algorithm or switch to a read- modify-write algorithm when initially allocating the page in the write system call path. The heuristic uses the modes that the file was opened with, the offset in the page to read from, and the size of the region to read. If the file was opened for reading in addition to writing and the page would not be filled completely with data from the user level, then read in the old contents of the page and mark it as Uptodate before copying in the new data. If the page would be completely filled with data from the user level, then there would be no reason to read in the old contents because they would just be copied over. This would optimize for applications which randomly access and update portions of files. The linkage editor for the C compiler is an example of such a thing. I tested the attached patch by using rpmbuild to build the current Fedora rawhide kernel. The kernel without the patch generated about 269,500 WRITE requests. The modified kernel containing the patch generated about 261,000 WRITE requests. Thus, about 8,500 fewer WRITE requests were generated. I suspect that many of these additional WRITE requests were probably FILE_SYNC requests to WRITE a single page, but I didn't test this theory. The difference between this patch and the previous one was to remove the unneeded PageDirty() test. I then retested to ensure that the resulting system continued to behave as desired. Thanx... ps Signed-off-by: Peter Staubach <staubach@redhat.com> Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com>
2009-08-10 12:54:16 +00:00
} else if (!once_thru &&
nfs_want_read_modify_write(file, page, pos, len)) {
once_thru = 1;
ret = nfs_readpage(file, page);
page_cache_release(page);
if (!ret)
goto start;
}
return ret;
}
static int nfs_write_end(struct file *file, struct address_space *mapping,
loff_t pos, unsigned len, unsigned copied,
struct page *page, void *fsdata)
{
unsigned offset = pos & (PAGE_CACHE_SIZE - 1);
struct nfs_open_context *ctx = nfs_file_open_context(file);
int status;
dfprintk(PAGECACHE, "NFS: write_end(%pD2(%lu), %u@%lld)\n",
file, mapping->host->i_ino, len, (long long) pos);
/*
* Zero any uninitialised parts of the page, and then mark the page
* as up to date if it turns out that we're extending the file.
*/
if (!PageUptodate(page)) {
unsigned pglen = nfs_page_length(page);
unsigned end = offset + len;
if (pglen == 0) {
zero_user_segments(page, 0, offset,
end, PAGE_CACHE_SIZE);
SetPageUptodate(page);
} else if (end >= pglen) {
zero_user_segment(page, end, PAGE_CACHE_SIZE);
if (offset == 0)
SetPageUptodate(page);
} else
zero_user_segment(page, pglen, PAGE_CACHE_SIZE);
}
status = nfs_updatepage(file, page, offset, copied);
unlock_page(page);
page_cache_release(page);
if (status < 0)
return status;
NFS_I(mapping->host)->write_io += copied;
if (nfs_ctx_key_to_expire(ctx)) {
status = nfs_wb_all(mapping->host);
if (status < 0)
return status;
}
return copied;
}
/*
* Partially or wholly invalidate a page
* - Release the private state associated with a page if undergoing complete
* page invalidation
* - Called if either PG_private or PG_fscache is set on the page
* - Caller holds page lock
*/
static void nfs_invalidate_page(struct page *page, unsigned int offset,
unsigned int length)
{
dfprintk(PAGECACHE, "NFS: invalidate_page(%p, %u, %u)\n",
page, offset, length);
if (offset != 0 || length < PAGE_CACHE_SIZE)
return;
/* Cancel any unstarted writes on this page */
nfs_wb_page_cancel(page_file_mapping(page)->host, page);
nfs_fscache_invalidate_page(page, page->mapping->host);
}
/*
* Attempt to release the private state associated with a page
* - Called if either PG_private or PG_fscache is set on the page
* - Caller holds page lock
* - Return true (may release page) or false (may not)
*/
static int nfs_release_page(struct page *page, gfp_t gfp)
{
struct address_space *mapping = page->mapping;
dfprintk(PAGECACHE, "NFS: release_page(%p)\n", page);
NFS: avoid deadlocks with loop-back mounted NFS filesystems. Support for loop-back mounted NFS filesystems is useful when NFS is used to access shared storage in a high-availability cluster. If the node running the NFS server fails, some other node can mount the filesystem and start providing NFS service. If that node already had the filesystem NFS mounted, it will now have it loop-back mounted. nfsd can suffer a deadlock when allocating memory and entering direct reclaim. While direct reclaim does not write to the NFS filesystem it can send and wait for a COMMIT through nfs_release_page(). This patch modifies nfs_release_page() to wait a limited time for the commit to complete - one second. If the commit doesn't complete in this time, nfs_release_page() will fail. This means it might now fail in some cases where it wouldn't before. These cases are only when 'gfp' includes '__GFP_WAIT'. nfs_release_page() is only called by try_to_release_page(), and that can only be called on an NFS page with required 'gfp' flags from - page_cache_pipe_buf_steal() in splice.c - shrink_page_list() in vmscan.c - invalidate_inode_pages2_range() in truncate.c The first two handle failure quite safely. The last is only called after ->launder_page() has been called, and that will have waited for the commit to finish already. So aborting if the commit takes longer than 1 second is perfectly safe. Signed-off-by: NeilBrown <neilb@suse.de> Acked-by: Jeff Layton <jlayton@primarydata.com> Signed-off-by: Trond Myklebust <trond.myklebust@primarydata.com>
2014-09-24 01:28:32 +00:00
/* Always try to initiate a 'commit' if relevant, but only
mm, page_alloc: distinguish between being unable to sleep, unwilling to sleep and avoiding waking kswapd __GFP_WAIT has been used to identify atomic context in callers that hold spinlocks or are in interrupts. They are expected to be high priority and have access one of two watermarks lower than "min" which can be referred to as the "atomic reserve". __GFP_HIGH users get access to the first lower watermark and can be called the "high priority reserve". Over time, callers had a requirement to not block when fallback options were available. Some have abused __GFP_WAIT leading to a situation where an optimisitic allocation with a fallback option can access atomic reserves. This patch uses __GFP_ATOMIC to identify callers that are truely atomic, cannot sleep and have no alternative. High priority users continue to use __GFP_HIGH. __GFP_DIRECT_RECLAIM identifies callers that can sleep and are willing to enter direct reclaim. __GFP_KSWAPD_RECLAIM to identify callers that want to wake kswapd for background reclaim. __GFP_WAIT is redefined as a caller that is willing to enter direct reclaim and wake kswapd for background reclaim. This patch then converts a number of sites o __GFP_ATOMIC is used by callers that are high priority and have memory pools for those requests. GFP_ATOMIC uses this flag. o Callers that have a limited mempool to guarantee forward progress clear __GFP_DIRECT_RECLAIM but keep __GFP_KSWAPD_RECLAIM. bio allocations fall into this category where kswapd will still be woken but atomic reserves are not used as there is a one-entry mempool to guarantee progress. o Callers that are checking if they are non-blocking should use the helper gfpflags_allow_blocking() where possible. This is because checking for __GFP_WAIT as was done historically now can trigger false positives. Some exceptions like dm-crypt.c exist where the code intent is clearer if __GFP_DIRECT_RECLAIM is used instead of the helper due to flag manipulations. o Callers that built their own GFP flags instead of starting with GFP_KERNEL and friends now also need to specify __GFP_KSWAPD_RECLAIM. The first key hazard to watch out for is callers that removed __GFP_WAIT and was depending on access to atomic reserves for inconspicuous reasons. In some cases it may be appropriate for them to use __GFP_HIGH. The second key hazard is callers that assembled their own combination of GFP flags instead of starting with something like GFP_KERNEL. They may now wish to specify __GFP_KSWAPD_RECLAIM. It's almost certainly harmless if it's missed in most cases as other activity will wake kswapd. Signed-off-by: Mel Gorman <mgorman@techsingularity.net> Acked-by: Vlastimil Babka <vbabka@suse.cz> Acked-by: Michal Hocko <mhocko@suse.com> Acked-by: Johannes Weiner <hannes@cmpxchg.org> Cc: Christoph Lameter <cl@linux.com> Cc: David Rientjes <rientjes@google.com> Cc: Vitaly Wool <vitalywool@gmail.com> Cc: Rik van Riel <riel@redhat.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2015-11-07 00:28:21 +00:00
* wait for it if the caller allows blocking. Even then,
* only wait 1 second and only if the 'bdi' is not congested.
NFS: avoid deadlocks with loop-back mounted NFS filesystems. Support for loop-back mounted NFS filesystems is useful when NFS is used to access shared storage in a high-availability cluster. If the node running the NFS server fails, some other node can mount the filesystem and start providing NFS service. If that node already had the filesystem NFS mounted, it will now have it loop-back mounted. nfsd can suffer a deadlock when allocating memory and entering direct reclaim. While direct reclaim does not write to the NFS filesystem it can send and wait for a COMMIT through nfs_release_page(). This patch modifies nfs_release_page() to wait a limited time for the commit to complete - one second. If the commit doesn't complete in this time, nfs_release_page() will fail. This means it might now fail in some cases where it wouldn't before. These cases are only when 'gfp' includes '__GFP_WAIT'. nfs_release_page() is only called by try_to_release_page(), and that can only be called on an NFS page with required 'gfp' flags from - page_cache_pipe_buf_steal() in splice.c - shrink_page_list() in vmscan.c - invalidate_inode_pages2_range() in truncate.c The first two handle failure quite safely. The last is only called after ->launder_page() has been called, and that will have waited for the commit to finish already. So aborting if the commit takes longer than 1 second is perfectly safe. Signed-off-by: NeilBrown <neilb@suse.de> Acked-by: Jeff Layton <jlayton@primarydata.com> Signed-off-by: Trond Myklebust <trond.myklebust@primarydata.com>
2014-09-24 01:28:32 +00:00
* Waiting indefinitely can cause deadlocks when the NFS
* server is on this machine, when a new TCP connection is
* needed and in other rare cases. There is no particular
* need to wait extensively here. A short wait has the
* benefit that someone else can worry about the freezer.
nfs: skip commit in releasepage if we're freeing memory for fs-related reasons We've had some reports of a deadlock where rpciod ends up with a stack trace like this: PID: 2507 TASK: ffff88103691ab40 CPU: 14 COMMAND: "rpciod/14" #0 [ffff8810343bf2f0] schedule at ffffffff814dabd9 #1 [ffff8810343bf3b8] nfs_wait_bit_killable at ffffffffa038fc04 [nfs] #2 [ffff8810343bf3c8] __wait_on_bit at ffffffff814dbc2f #3 [ffff8810343bf418] out_of_line_wait_on_bit at ffffffff814dbcd8 #4 [ffff8810343bf488] nfs_commit_inode at ffffffffa039e0c1 [nfs] #5 [ffff8810343bf4f8] nfs_release_page at ffffffffa038bef6 [nfs] #6 [ffff8810343bf528] try_to_release_page at ffffffff8110c670 #7 [ffff8810343bf538] shrink_page_list.clone.0 at ffffffff81126271 #8 [ffff8810343bf668] shrink_inactive_list at ffffffff81126638 #9 [ffff8810343bf818] shrink_zone at ffffffff8112788f #10 [ffff8810343bf8c8] do_try_to_free_pages at ffffffff81127b1e #11 [ffff8810343bf958] try_to_free_pages at ffffffff8112812f #12 [ffff8810343bfa08] __alloc_pages_nodemask at ffffffff8111fdad #13 [ffff8810343bfb28] kmem_getpages at ffffffff81159942 #14 [ffff8810343bfb58] fallback_alloc at ffffffff8115a55a #15 [ffff8810343bfbd8] ____cache_alloc_node at ffffffff8115a2d9 #16 [ffff8810343bfc38] kmem_cache_alloc at ffffffff8115b09b #17 [ffff8810343bfc78] sk_prot_alloc at ffffffff81411808 #18 [ffff8810343bfcb8] sk_alloc at ffffffff8141197c #19 [ffff8810343bfce8] inet_create at ffffffff81483ba6 #20 [ffff8810343bfd38] __sock_create at ffffffff8140b4a7 #21 [ffff8810343bfd98] xs_create_sock at ffffffffa01f649b [sunrpc] #22 [ffff8810343bfdd8] xs_tcp_setup_socket at ffffffffa01f6965 [sunrpc] #23 [ffff8810343bfe38] worker_thread at ffffffff810887d0 #24 [ffff8810343bfee8] kthread at ffffffff8108dd96 #25 [ffff8810343bff48] kernel_thread at ffffffff8100c1ca rpciod is trying to allocate memory for a new socket to talk to the server. The VM ends up calling ->releasepage to get more memory, and it tries to do a blocking commit. That commit can't succeed however without a connected socket, so we deadlock. Fix this by setting PF_FSTRANS on the workqueue task prior to doing the socket allocation, and having nfs_release_page check for that flag when deciding whether to do a commit call. Also, set PF_FSTRANS unconditionally in rpc_async_schedule since that function can also do allocations sometimes. Signed-off-by: Jeff Layton <jlayton@redhat.com> Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com> Cc: stable@vger.kernel.org
2012-07-23 17:58:51 +00:00
*/
NFS: avoid deadlocks with loop-back mounted NFS filesystems. Support for loop-back mounted NFS filesystems is useful when NFS is used to access shared storage in a high-availability cluster. If the node running the NFS server fails, some other node can mount the filesystem and start providing NFS service. If that node already had the filesystem NFS mounted, it will now have it loop-back mounted. nfsd can suffer a deadlock when allocating memory and entering direct reclaim. While direct reclaim does not write to the NFS filesystem it can send and wait for a COMMIT through nfs_release_page(). This patch modifies nfs_release_page() to wait a limited time for the commit to complete - one second. If the commit doesn't complete in this time, nfs_release_page() will fail. This means it might now fail in some cases where it wouldn't before. These cases are only when 'gfp' includes '__GFP_WAIT'. nfs_release_page() is only called by try_to_release_page(), and that can only be called on an NFS page with required 'gfp' flags from - page_cache_pipe_buf_steal() in splice.c - shrink_page_list() in vmscan.c - invalidate_inode_pages2_range() in truncate.c The first two handle failure quite safely. The last is only called after ->launder_page() has been called, and that will have waited for the commit to finish already. So aborting if the commit takes longer than 1 second is perfectly safe. Signed-off-by: NeilBrown <neilb@suse.de> Acked-by: Jeff Layton <jlayton@primarydata.com> Signed-off-by: Trond Myklebust <trond.myklebust@primarydata.com>
2014-09-24 01:28:32 +00:00
if (mapping) {
struct nfs_server *nfss = NFS_SERVER(mapping->host);
nfs_commit_inode(mapping->host, 0);
mm, page_alloc: distinguish between being unable to sleep, unwilling to sleep and avoiding waking kswapd __GFP_WAIT has been used to identify atomic context in callers that hold spinlocks or are in interrupts. They are expected to be high priority and have access one of two watermarks lower than "min" which can be referred to as the "atomic reserve". __GFP_HIGH users get access to the first lower watermark and can be called the "high priority reserve". Over time, callers had a requirement to not block when fallback options were available. Some have abused __GFP_WAIT leading to a situation where an optimisitic allocation with a fallback option can access atomic reserves. This patch uses __GFP_ATOMIC to identify callers that are truely atomic, cannot sleep and have no alternative. High priority users continue to use __GFP_HIGH. __GFP_DIRECT_RECLAIM identifies callers that can sleep and are willing to enter direct reclaim. __GFP_KSWAPD_RECLAIM to identify callers that want to wake kswapd for background reclaim. __GFP_WAIT is redefined as a caller that is willing to enter direct reclaim and wake kswapd for background reclaim. This patch then converts a number of sites o __GFP_ATOMIC is used by callers that are high priority and have memory pools for those requests. GFP_ATOMIC uses this flag. o Callers that have a limited mempool to guarantee forward progress clear __GFP_DIRECT_RECLAIM but keep __GFP_KSWAPD_RECLAIM. bio allocations fall into this category where kswapd will still be woken but atomic reserves are not used as there is a one-entry mempool to guarantee progress. o Callers that are checking if they are non-blocking should use the helper gfpflags_allow_blocking() where possible. This is because checking for __GFP_WAIT as was done historically now can trigger false positives. Some exceptions like dm-crypt.c exist where the code intent is clearer if __GFP_DIRECT_RECLAIM is used instead of the helper due to flag manipulations. o Callers that built their own GFP flags instead of starting with GFP_KERNEL and friends now also need to specify __GFP_KSWAPD_RECLAIM. The first key hazard to watch out for is callers that removed __GFP_WAIT and was depending on access to atomic reserves for inconspicuous reasons. In some cases it may be appropriate for them to use __GFP_HIGH. The second key hazard is callers that assembled their own combination of GFP flags instead of starting with something like GFP_KERNEL. They may now wish to specify __GFP_KSWAPD_RECLAIM. It's almost certainly harmless if it's missed in most cases as other activity will wake kswapd. Signed-off-by: Mel Gorman <mgorman@techsingularity.net> Acked-by: Vlastimil Babka <vbabka@suse.cz> Acked-by: Michal Hocko <mhocko@suse.com> Acked-by: Johannes Weiner <hannes@cmpxchg.org> Cc: Christoph Lameter <cl@linux.com> Cc: David Rientjes <rientjes@google.com> Cc: Vitaly Wool <vitalywool@gmail.com> Cc: Rik van Riel <riel@redhat.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2015-11-07 00:28:21 +00:00
if (gfpflags_allow_blocking(gfp) &&
!bdi_write_congested(&nfss->backing_dev_info)) {
NFS: avoid deadlocks with loop-back mounted NFS filesystems. Support for loop-back mounted NFS filesystems is useful when NFS is used to access shared storage in a high-availability cluster. If the node running the NFS server fails, some other node can mount the filesystem and start providing NFS service. If that node already had the filesystem NFS mounted, it will now have it loop-back mounted. nfsd can suffer a deadlock when allocating memory and entering direct reclaim. While direct reclaim does not write to the NFS filesystem it can send and wait for a COMMIT through nfs_release_page(). This patch modifies nfs_release_page() to wait a limited time for the commit to complete - one second. If the commit doesn't complete in this time, nfs_release_page() will fail. This means it might now fail in some cases where it wouldn't before. These cases are only when 'gfp' includes '__GFP_WAIT'. nfs_release_page() is only called by try_to_release_page(), and that can only be called on an NFS page with required 'gfp' flags from - page_cache_pipe_buf_steal() in splice.c - shrink_page_list() in vmscan.c - invalidate_inode_pages2_range() in truncate.c The first two handle failure quite safely. The last is only called after ->launder_page() has been called, and that will have waited for the commit to finish already. So aborting if the commit takes longer than 1 second is perfectly safe. Signed-off-by: NeilBrown <neilb@suse.de> Acked-by: Jeff Layton <jlayton@primarydata.com> Signed-off-by: Trond Myklebust <trond.myklebust@primarydata.com>
2014-09-24 01:28:32 +00:00
wait_on_page_bit_killable_timeout(page, PG_private,
HZ);
if (PagePrivate(page))
set_bdi_congested(&nfss->backing_dev_info,
BLK_RW_ASYNC);
NFS: avoid deadlocks with loop-back mounted NFS filesystems. Support for loop-back mounted NFS filesystems is useful when NFS is used to access shared storage in a high-availability cluster. If the node running the NFS server fails, some other node can mount the filesystem and start providing NFS service. If that node already had the filesystem NFS mounted, it will now have it loop-back mounted. nfsd can suffer a deadlock when allocating memory and entering direct reclaim. While direct reclaim does not write to the NFS filesystem it can send and wait for a COMMIT through nfs_release_page(). This patch modifies nfs_release_page() to wait a limited time for the commit to complete - one second. If the commit doesn't complete in this time, nfs_release_page() will fail. This means it might now fail in some cases where it wouldn't before. These cases are only when 'gfp' includes '__GFP_WAIT'. nfs_release_page() is only called by try_to_release_page(), and that can only be called on an NFS page with required 'gfp' flags from - page_cache_pipe_buf_steal() in splice.c - shrink_page_list() in vmscan.c - invalidate_inode_pages2_range() in truncate.c The first two handle failure quite safely. The last is only called after ->launder_page() has been called, and that will have waited for the commit to finish already. So aborting if the commit takes longer than 1 second is perfectly safe. Signed-off-by: NeilBrown <neilb@suse.de> Acked-by: Jeff Layton <jlayton@primarydata.com> Signed-off-by: Trond Myklebust <trond.myklebust@primarydata.com>
2014-09-24 01:28:32 +00:00
}
}
/* If PagePrivate() is set, then the page is not freeable */
if (PagePrivate(page))
return 0;
return nfs_fscache_release_page(page, gfp);
}
static void nfs_check_dirty_writeback(struct page *page,
bool *dirty, bool *writeback)
{
struct nfs_inode *nfsi;
struct address_space *mapping = page_file_mapping(page);
if (!mapping || PageSwapCache(page))
return;
/*
* Check if an unstable page is currently being committed and
* if so, have the VM treat it as if the page is under writeback
* so it will not block due to pages that will shortly be freeable.
*/
nfsi = NFS_I(mapping->host);
if (atomic_read(&nfsi->commit_info.rpcs_out)) {
*writeback = true;
return;
}
/*
* If PagePrivate() is set, then the page is not freeable and as the
* inode is not being committed, it's not going to be cleaned in the
* near future so treat it as dirty
*/
if (PagePrivate(page))
*dirty = true;
}
/*
* Attempt to clear the private state associated with a page when an error
* occurs that requires the cached contents of an inode to be written back or
* destroyed
* - Called if either PG_private or fscache is set on the page
* - Caller holds page lock
* - Return 0 if successful, -error otherwise
*/
static int nfs_launder_page(struct page *page)
{
struct inode *inode = page_file_mapping(page)->host;
struct nfs_inode *nfsi = NFS_I(inode);
dfprintk(PAGECACHE, "NFS: launder_page(%ld, %llu)\n",
inode->i_ino, (long long)page_offset(page));
nfs_fscache_wait_on_page_write(nfsi, page);
return nfs_wb_launder_page(inode, page);
}
static int nfs_swap_activate(struct swap_info_struct *sis, struct file *file,
sector_t *span)
{
struct rpc_clnt *clnt = NFS_CLIENT(file->f_mapping->host);
*span = sis->pages;
return rpc_clnt_swap_activate(clnt);
}
static void nfs_swap_deactivate(struct file *file)
{
struct rpc_clnt *clnt = NFS_CLIENT(file->f_mapping->host);
rpc_clnt_swap_deactivate(clnt);
}
const struct address_space_operations nfs_file_aops = {
.readpage = nfs_readpage,
.readpages = nfs_readpages,
.set_page_dirty = __set_page_dirty_nobuffers,
.writepage = nfs_writepage,
.writepages = nfs_writepages,
.write_begin = nfs_write_begin,
.write_end = nfs_write_end,
.invalidatepage = nfs_invalidate_page,
.releasepage = nfs_release_page,
.direct_IO = nfs_direct_IO,
.migratepage = nfs_migrate_page,
.launder_page = nfs_launder_page,
.is_dirty_writeback = nfs_check_dirty_writeback,
.error_remove_page = generic_error_remove_page,
.swap_activate = nfs_swap_activate,
.swap_deactivate = nfs_swap_deactivate,
};
/*
* Notification that a PTE pointing to an NFS page is about to be made
* writable, implying that someone is about to modify the page through a
* shared-writable mapping
*/
static int nfs_vm_page_mkwrite(struct vm_area_struct *vma, struct vm_fault *vmf)
{
struct page *page = vmf->page;
struct file *filp = vma->vm_file;
struct inode *inode = file_inode(filp);
unsigned pagelen;
int ret = VM_FAULT_NOPAGE;
struct address_space *mapping;
dfprintk(PAGECACHE, "NFS: vm_page_mkwrite(%pD2(%lu), offset %lld)\n",
filp, filp->f_mapping->host->i_ino,
(long long)page_offset(page));
/* make sure the cache has finished storing the page */
nfs_fscache_wait_on_page_write(NFS_I(inode), page);
wait_on_bit_action(&NFS_I(inode)->flags, NFS_INO_INVALIDATING,
nfs_wait_bit_killable, TASK_KILLABLE);
lock_page(page);
mapping = page_file_mapping(page);
if (mapping != inode->i_mapping)
goto out_unlock;
wait_on_page_writeback(page);
pagelen = nfs_page_length(page);
if (pagelen == 0)
goto out_unlock;
ret = VM_FAULT_LOCKED;
if (nfs_flush_incompatible(filp, page) == 0 &&
nfs_updatepage(filp, page, 0, pagelen) == 0)
goto out;
ret = VM_FAULT_SIGBUS;
out_unlock:
unlock_page(page);
out:
return ret;
}
static const struct vm_operations_struct nfs_file_vm_ops = {
.fault = filemap_fault,
.map_pages = filemap_map_pages,
.page_mkwrite = nfs_vm_page_mkwrite,
};
static int nfs_need_check_write(struct file *filp, struct inode *inode)
{
struct nfs_open_context *ctx;
ctx = nfs_file_open_context(filp);
if (test_bit(NFS_CONTEXT_ERROR_WRITE, &ctx->flags) ||
nfs_ctx_key_to_expire(ctx))
return 1;
return 0;
}
ssize_t nfs_file_write(struct kiocb *iocb, struct iov_iter *from)
{
struct file *file = iocb->ki_filp;
struct inode *inode = file_inode(file);
unsigned long written = 0;
ssize_t result;
size_t count = iov_iter_count(from);
result = nfs_key_timeout_notify(file, inode);
if (result)
return result;
if (iocb->ki_flags & IOCB_DIRECT) {
result = generic_write_checks(iocb, from);
if (result <= 0)
return result;
return nfs_file_direct_write(iocb, from);
}
dprintk("NFS: write(%pD2, %zu@%Ld)\n",
file, count, (long long) iocb->ki_pos);
result = -EBUSY;
if (IS_SWAPFILE(inode))
goto out_swapfile;
/*
* O_APPEND implies that we must revalidate the file length.
*/
if (iocb->ki_flags & IOCB_APPEND) {
result = nfs_revalidate_file_size(inode, file);
if (result)
goto out;
}
result = count;
if (!count)
goto out;
result = generic_file_write_iter(iocb, from);
if (result > 0)
written = result;
/* Return error values */
if (result >= 0 && nfs_need_check_write(file, inode)) {
int err = vfs_fsync(file, 0);
if (err < 0)
result = err;
}
if (result > 0)
nfs_add_stats(inode, NFSIOS_NORMALWRITTENBYTES, written);
out:
return result;
out_swapfile:
printk(KERN_INFO "NFS: attempt to write to active swap file!\n");
goto out;
}
EXPORT_SYMBOL_GPL(nfs_file_write);
nfs: introduce mount option '-olocal_lock' to make locks local NFS clients since 2.6.12 support flock locks by emulating fcntl byte-range locks. Due to this, some windows applications which seem to use both flock (share mode lock mapped as flock by Samba) and fcntl locks sequentially on the same file, can't lock as they falsely assume the file is already locked. The problem was reported on a setup with windows clients accessing excel files on a Samba exported share which is originally a NFS mount from a NetApp filer. Older NFS clients (< 2.6.12) did not see this problem as flock locks were considered local. To support legacy flock behavior, this patch adds a mount option "-olocal_lock=" which can take the following values: 'none' - Neither flock locks nor POSIX locks are local 'flock' - flock locks are local 'posix' - fcntl/POSIX locks are local 'all' - Both flock locks and POSIX locks are local Testing: - This patch was tested by using -olocal_lock option with different values and the NLM calls were noted from the network packet captured. 'none' - NLM calls were seen during both flock() and fcntl(), flock lock was granted, fcntl was denied 'flock' - no NLM calls for flock(), NLM call was seen for fcntl(), granted 'posix' - NLM call was seen for flock() - granted, no NLM call for fcntl() 'all' - no NLM calls were seen during both flock() and fcntl() - No bugs were seen during NFSv4 locking/unlocking in general and NFSv4 reboot recovery. Cc: Neil Brown <neilb@suse.de> Signed-off-by: Suresh Jayaraman <sjayaraman@suse.de> Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com>
2010-09-23 12:55:58 +00:00
static int
do_getlk(struct file *filp, int cmd, struct file_lock *fl, int is_local)
{
struct inode *inode = filp->f_mapping->host;
int status = 0;
unsigned int saved_type = fl->fl_type;
/* Try local locking first */
posix_test_lock(filp, fl);
if (fl->fl_type != F_UNLCK) {
/* found a conflict */
goto out;
}
fl->fl_type = saved_type;
if (NFS_PROTO(inode)->have_delegation(inode, FMODE_READ))
goto out_noconflict;
nfs: introduce mount option '-olocal_lock' to make locks local NFS clients since 2.6.12 support flock locks by emulating fcntl byte-range locks. Due to this, some windows applications which seem to use both flock (share mode lock mapped as flock by Samba) and fcntl locks sequentially on the same file, can't lock as they falsely assume the file is already locked. The problem was reported on a setup with windows clients accessing excel files on a Samba exported share which is originally a NFS mount from a NetApp filer. Older NFS clients (< 2.6.12) did not see this problem as flock locks were considered local. To support legacy flock behavior, this patch adds a mount option "-olocal_lock=" which can take the following values: 'none' - Neither flock locks nor POSIX locks are local 'flock' - flock locks are local 'posix' - fcntl/POSIX locks are local 'all' - Both flock locks and POSIX locks are local Testing: - This patch was tested by using -olocal_lock option with different values and the NLM calls were noted from the network packet captured. 'none' - NLM calls were seen during both flock() and fcntl(), flock lock was granted, fcntl was denied 'flock' - no NLM calls for flock(), NLM call was seen for fcntl(), granted 'posix' - NLM call was seen for flock() - granted, no NLM call for fcntl() 'all' - no NLM calls were seen during both flock() and fcntl() - No bugs were seen during NFSv4 locking/unlocking in general and NFSv4 reboot recovery. Cc: Neil Brown <neilb@suse.de> Signed-off-by: Suresh Jayaraman <sjayaraman@suse.de> Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com>
2010-09-23 12:55:58 +00:00
if (is_local)
goto out_noconflict;
status = NFS_PROTO(inode)->lock(filp, cmd, fl);
out:
return status;
out_noconflict:
fl->fl_type = F_UNLCK;
goto out;
}
static int do_vfs_lock(struct file *file, struct file_lock *fl)
{
return locks_lock_file_wait(file, fl);
}
nfs: introduce mount option '-olocal_lock' to make locks local NFS clients since 2.6.12 support flock locks by emulating fcntl byte-range locks. Due to this, some windows applications which seem to use both flock (share mode lock mapped as flock by Samba) and fcntl locks sequentially on the same file, can't lock as they falsely assume the file is already locked. The problem was reported on a setup with windows clients accessing excel files on a Samba exported share which is originally a NFS mount from a NetApp filer. Older NFS clients (< 2.6.12) did not see this problem as flock locks were considered local. To support legacy flock behavior, this patch adds a mount option "-olocal_lock=" which can take the following values: 'none' - Neither flock locks nor POSIX locks are local 'flock' - flock locks are local 'posix' - fcntl/POSIX locks are local 'all' - Both flock locks and POSIX locks are local Testing: - This patch was tested by using -olocal_lock option with different values and the NLM calls were noted from the network packet captured. 'none' - NLM calls were seen during both flock() and fcntl(), flock lock was granted, fcntl was denied 'flock' - no NLM calls for flock(), NLM call was seen for fcntl(), granted 'posix' - NLM call was seen for flock() - granted, no NLM call for fcntl() 'all' - no NLM calls were seen during both flock() and fcntl() - No bugs were seen during NFSv4 locking/unlocking in general and NFSv4 reboot recovery. Cc: Neil Brown <neilb@suse.de> Signed-off-by: Suresh Jayaraman <sjayaraman@suse.de> Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com>
2010-09-23 12:55:58 +00:00
static int
do_unlk(struct file *filp, int cmd, struct file_lock *fl, int is_local)
{
struct inode *inode = filp->f_mapping->host;
struct nfs_lock_context *l_ctx;
int status;
/*
* Flush all pending writes before doing anything
* with locks..
*/
vfs_fsync(filp, 0);
l_ctx = nfs_get_lock_context(nfs_file_open_context(filp));
if (!IS_ERR(l_ctx)) {
status = nfs_iocounter_wait(l_ctx);
nfs_put_lock_context(l_ctx);
if (status < 0)
return status;
}
/* NOTE: special case
* If we're signalled while cleaning up locks on process exit, we
* still need to complete the unlock.
*/
nfs: introduce mount option '-olocal_lock' to make locks local NFS clients since 2.6.12 support flock locks by emulating fcntl byte-range locks. Due to this, some windows applications which seem to use both flock (share mode lock mapped as flock by Samba) and fcntl locks sequentially on the same file, can't lock as they falsely assume the file is already locked. The problem was reported on a setup with windows clients accessing excel files on a Samba exported share which is originally a NFS mount from a NetApp filer. Older NFS clients (< 2.6.12) did not see this problem as flock locks were considered local. To support legacy flock behavior, this patch adds a mount option "-olocal_lock=" which can take the following values: 'none' - Neither flock locks nor POSIX locks are local 'flock' - flock locks are local 'posix' - fcntl/POSIX locks are local 'all' - Both flock locks and POSIX locks are local Testing: - This patch was tested by using -olocal_lock option with different values and the NLM calls were noted from the network packet captured. 'none' - NLM calls were seen during both flock() and fcntl(), flock lock was granted, fcntl was denied 'flock' - no NLM calls for flock(), NLM call was seen for fcntl(), granted 'posix' - NLM call was seen for flock() - granted, no NLM call for fcntl() 'all' - no NLM calls were seen during both flock() and fcntl() - No bugs were seen during NFSv4 locking/unlocking in general and NFSv4 reboot recovery. Cc: Neil Brown <neilb@suse.de> Signed-off-by: Suresh Jayaraman <sjayaraman@suse.de> Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com>
2010-09-23 12:55:58 +00:00
/*
* Use local locking if mounted with "-onolock" or with appropriate
* "-olocal_lock="
*/
if (!is_local)
status = NFS_PROTO(inode)->lock(filp, cmd, fl);
else
status = do_vfs_lock(filp, fl);
return status;
}
static int
is_time_granular(struct timespec *ts) {
return ((ts->tv_sec == 0) && (ts->tv_nsec <= 1000));
}
nfs: introduce mount option '-olocal_lock' to make locks local NFS clients since 2.6.12 support flock locks by emulating fcntl byte-range locks. Due to this, some windows applications which seem to use both flock (share mode lock mapped as flock by Samba) and fcntl locks sequentially on the same file, can't lock as they falsely assume the file is already locked. The problem was reported on a setup with windows clients accessing excel files on a Samba exported share which is originally a NFS mount from a NetApp filer. Older NFS clients (< 2.6.12) did not see this problem as flock locks were considered local. To support legacy flock behavior, this patch adds a mount option "-olocal_lock=" which can take the following values: 'none' - Neither flock locks nor POSIX locks are local 'flock' - flock locks are local 'posix' - fcntl/POSIX locks are local 'all' - Both flock locks and POSIX locks are local Testing: - This patch was tested by using -olocal_lock option with different values and the NLM calls were noted from the network packet captured. 'none' - NLM calls were seen during both flock() and fcntl(), flock lock was granted, fcntl was denied 'flock' - no NLM calls for flock(), NLM call was seen for fcntl(), granted 'posix' - NLM call was seen for flock() - granted, no NLM call for fcntl() 'all' - no NLM calls were seen during both flock() and fcntl() - No bugs were seen during NFSv4 locking/unlocking in general and NFSv4 reboot recovery. Cc: Neil Brown <neilb@suse.de> Signed-off-by: Suresh Jayaraman <sjayaraman@suse.de> Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com>
2010-09-23 12:55:58 +00:00
static int
do_setlk(struct file *filp, int cmd, struct file_lock *fl, int is_local)
{
struct inode *inode = filp->f_mapping->host;
int status;
/*
* Flush all pending writes before doing anything
* with locks..
*/
status = nfs_sync_mapping(filp->f_mapping);
if (status != 0)
goto out;
nfs: introduce mount option '-olocal_lock' to make locks local NFS clients since 2.6.12 support flock locks by emulating fcntl byte-range locks. Due to this, some windows applications which seem to use both flock (share mode lock mapped as flock by Samba) and fcntl locks sequentially on the same file, can't lock as they falsely assume the file is already locked. The problem was reported on a setup with windows clients accessing excel files on a Samba exported share which is originally a NFS mount from a NetApp filer. Older NFS clients (< 2.6.12) did not see this problem as flock locks were considered local. To support legacy flock behavior, this patch adds a mount option "-olocal_lock=" which can take the following values: 'none' - Neither flock locks nor POSIX locks are local 'flock' - flock locks are local 'posix' - fcntl/POSIX locks are local 'all' - Both flock locks and POSIX locks are local Testing: - This patch was tested by using -olocal_lock option with different values and the NLM calls were noted from the network packet captured. 'none' - NLM calls were seen during both flock() and fcntl(), flock lock was granted, fcntl was denied 'flock' - no NLM calls for flock(), NLM call was seen for fcntl(), granted 'posix' - NLM call was seen for flock() - granted, no NLM call for fcntl() 'all' - no NLM calls were seen during both flock() and fcntl() - No bugs were seen during NFSv4 locking/unlocking in general and NFSv4 reboot recovery. Cc: Neil Brown <neilb@suse.de> Signed-off-by: Suresh Jayaraman <sjayaraman@suse.de> Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com>
2010-09-23 12:55:58 +00:00
/*
* Use local locking if mounted with "-onolock" or with appropriate
* "-olocal_lock="
*/
if (!is_local)
status = NFS_PROTO(inode)->lock(filp, cmd, fl);
else
status = do_vfs_lock(filp, fl);
if (status < 0)
goto out;
/*
* Revalidate the cache if the server has time stamps granular
* enough to detect subsecond changes. Otherwise, clear the
* cache to prevent missing any changes.
*
* This makes locking act as a cache coherency point.
*/
nfs_sync_mapping(filp->f_mapping);
if (!NFS_PROTO(inode)->have_delegation(inode, FMODE_READ)) {
if (is_time_granular(&NFS_SERVER(inode)->time_delta))
__nfs_revalidate_inode(NFS_SERVER(inode), inode);
else
nfs_zap_caches(inode);
}
out:
return status;
}
/*
* Lock a (portion of) a file
*/
int nfs_lock(struct file *filp, int cmd, struct file_lock *fl)
{
struct inode *inode = filp->f_mapping->host;
int ret = -ENOLCK;
nfs: introduce mount option '-olocal_lock' to make locks local NFS clients since 2.6.12 support flock locks by emulating fcntl byte-range locks. Due to this, some windows applications which seem to use both flock (share mode lock mapped as flock by Samba) and fcntl locks sequentially on the same file, can't lock as they falsely assume the file is already locked. The problem was reported on a setup with windows clients accessing excel files on a Samba exported share which is originally a NFS mount from a NetApp filer. Older NFS clients (< 2.6.12) did not see this problem as flock locks were considered local. To support legacy flock behavior, this patch adds a mount option "-olocal_lock=" which can take the following values: 'none' - Neither flock locks nor POSIX locks are local 'flock' - flock locks are local 'posix' - fcntl/POSIX locks are local 'all' - Both flock locks and POSIX locks are local Testing: - This patch was tested by using -olocal_lock option with different values and the NLM calls were noted from the network packet captured. 'none' - NLM calls were seen during both flock() and fcntl(), flock lock was granted, fcntl was denied 'flock' - no NLM calls for flock(), NLM call was seen for fcntl(), granted 'posix' - NLM call was seen for flock() - granted, no NLM call for fcntl() 'all' - no NLM calls were seen during both flock() and fcntl() - No bugs were seen during NFSv4 locking/unlocking in general and NFSv4 reboot recovery. Cc: Neil Brown <neilb@suse.de> Signed-off-by: Suresh Jayaraman <sjayaraman@suse.de> Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com>
2010-09-23 12:55:58 +00:00
int is_local = 0;
dprintk("NFS: lock(%pD2, t=%x, fl=%x, r=%lld:%lld)\n",
filp, fl->fl_type, fl->fl_flags,
(long long)fl->fl_start, (long long)fl->fl_end);
nfs_inc_stats(inode, NFSIOS_VFSLOCK);
/* No mandatory locks over NFS */
if (__mandatory_lock(inode) && fl->fl_type != F_UNLCK)
goto out_err;
nfs: introduce mount option '-olocal_lock' to make locks local NFS clients since 2.6.12 support flock locks by emulating fcntl byte-range locks. Due to this, some windows applications which seem to use both flock (share mode lock mapped as flock by Samba) and fcntl locks sequentially on the same file, can't lock as they falsely assume the file is already locked. The problem was reported on a setup with windows clients accessing excel files on a Samba exported share which is originally a NFS mount from a NetApp filer. Older NFS clients (< 2.6.12) did not see this problem as flock locks were considered local. To support legacy flock behavior, this patch adds a mount option "-olocal_lock=" which can take the following values: 'none' - Neither flock locks nor POSIX locks are local 'flock' - flock locks are local 'posix' - fcntl/POSIX locks are local 'all' - Both flock locks and POSIX locks are local Testing: - This patch was tested by using -olocal_lock option with different values and the NLM calls were noted from the network packet captured. 'none' - NLM calls were seen during both flock() and fcntl(), flock lock was granted, fcntl was denied 'flock' - no NLM calls for flock(), NLM call was seen for fcntl(), granted 'posix' - NLM call was seen for flock() - granted, no NLM call for fcntl() 'all' - no NLM calls were seen during both flock() and fcntl() - No bugs were seen during NFSv4 locking/unlocking in general and NFSv4 reboot recovery. Cc: Neil Brown <neilb@suse.de> Signed-off-by: Suresh Jayaraman <sjayaraman@suse.de> Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com>
2010-09-23 12:55:58 +00:00
if (NFS_SERVER(inode)->flags & NFS_MOUNT_LOCAL_FCNTL)
is_local = 1;
if (NFS_PROTO(inode)->lock_check_bounds != NULL) {
ret = NFS_PROTO(inode)->lock_check_bounds(fl);
if (ret < 0)
goto out_err;
}
if (IS_GETLK(cmd))
nfs: introduce mount option '-olocal_lock' to make locks local NFS clients since 2.6.12 support flock locks by emulating fcntl byte-range locks. Due to this, some windows applications which seem to use both flock (share mode lock mapped as flock by Samba) and fcntl locks sequentially on the same file, can't lock as they falsely assume the file is already locked. The problem was reported on a setup with windows clients accessing excel files on a Samba exported share which is originally a NFS mount from a NetApp filer. Older NFS clients (< 2.6.12) did not see this problem as flock locks were considered local. To support legacy flock behavior, this patch adds a mount option "-olocal_lock=" which can take the following values: 'none' - Neither flock locks nor POSIX locks are local 'flock' - flock locks are local 'posix' - fcntl/POSIX locks are local 'all' - Both flock locks and POSIX locks are local Testing: - This patch was tested by using -olocal_lock option with different values and the NLM calls were noted from the network packet captured. 'none' - NLM calls were seen during both flock() and fcntl(), flock lock was granted, fcntl was denied 'flock' - no NLM calls for flock(), NLM call was seen for fcntl(), granted 'posix' - NLM call was seen for flock() - granted, no NLM call for fcntl() 'all' - no NLM calls were seen during both flock() and fcntl() - No bugs were seen during NFSv4 locking/unlocking in general and NFSv4 reboot recovery. Cc: Neil Brown <neilb@suse.de> Signed-off-by: Suresh Jayaraman <sjayaraman@suse.de> Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com>
2010-09-23 12:55:58 +00:00
ret = do_getlk(filp, cmd, fl, is_local);
else if (fl->fl_type == F_UNLCK)
nfs: introduce mount option '-olocal_lock' to make locks local NFS clients since 2.6.12 support flock locks by emulating fcntl byte-range locks. Due to this, some windows applications which seem to use both flock (share mode lock mapped as flock by Samba) and fcntl locks sequentially on the same file, can't lock as they falsely assume the file is already locked. The problem was reported on a setup with windows clients accessing excel files on a Samba exported share which is originally a NFS mount from a NetApp filer. Older NFS clients (< 2.6.12) did not see this problem as flock locks were considered local. To support legacy flock behavior, this patch adds a mount option "-olocal_lock=" which can take the following values: 'none' - Neither flock locks nor POSIX locks are local 'flock' - flock locks are local 'posix' - fcntl/POSIX locks are local 'all' - Both flock locks and POSIX locks are local Testing: - This patch was tested by using -olocal_lock option with different values and the NLM calls were noted from the network packet captured. 'none' - NLM calls were seen during both flock() and fcntl(), flock lock was granted, fcntl was denied 'flock' - no NLM calls for flock(), NLM call was seen for fcntl(), granted 'posix' - NLM call was seen for flock() - granted, no NLM call for fcntl() 'all' - no NLM calls were seen during both flock() and fcntl() - No bugs were seen during NFSv4 locking/unlocking in general and NFSv4 reboot recovery. Cc: Neil Brown <neilb@suse.de> Signed-off-by: Suresh Jayaraman <sjayaraman@suse.de> Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com>
2010-09-23 12:55:58 +00:00
ret = do_unlk(filp, cmd, fl, is_local);
else
nfs: introduce mount option '-olocal_lock' to make locks local NFS clients since 2.6.12 support flock locks by emulating fcntl byte-range locks. Due to this, some windows applications which seem to use both flock (share mode lock mapped as flock by Samba) and fcntl locks sequentially on the same file, can't lock as they falsely assume the file is already locked. The problem was reported on a setup with windows clients accessing excel files on a Samba exported share which is originally a NFS mount from a NetApp filer. Older NFS clients (< 2.6.12) did not see this problem as flock locks were considered local. To support legacy flock behavior, this patch adds a mount option "-olocal_lock=" which can take the following values: 'none' - Neither flock locks nor POSIX locks are local 'flock' - flock locks are local 'posix' - fcntl/POSIX locks are local 'all' - Both flock locks and POSIX locks are local Testing: - This patch was tested by using -olocal_lock option with different values and the NLM calls were noted from the network packet captured. 'none' - NLM calls were seen during both flock() and fcntl(), flock lock was granted, fcntl was denied 'flock' - no NLM calls for flock(), NLM call was seen for fcntl(), granted 'posix' - NLM call was seen for flock() - granted, no NLM call for fcntl() 'all' - no NLM calls were seen during both flock() and fcntl() - No bugs were seen during NFSv4 locking/unlocking in general and NFSv4 reboot recovery. Cc: Neil Brown <neilb@suse.de> Signed-off-by: Suresh Jayaraman <sjayaraman@suse.de> Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com>
2010-09-23 12:55:58 +00:00
ret = do_setlk(filp, cmd, fl, is_local);
out_err:
return ret;
}
EXPORT_SYMBOL_GPL(nfs_lock);
/*
* Lock a (portion of) a file
*/
int nfs_flock(struct file *filp, int cmd, struct file_lock *fl)
{
nfs: introduce mount option '-olocal_lock' to make locks local NFS clients since 2.6.12 support flock locks by emulating fcntl byte-range locks. Due to this, some windows applications which seem to use both flock (share mode lock mapped as flock by Samba) and fcntl locks sequentially on the same file, can't lock as they falsely assume the file is already locked. The problem was reported on a setup with windows clients accessing excel files on a Samba exported share which is originally a NFS mount from a NetApp filer. Older NFS clients (< 2.6.12) did not see this problem as flock locks were considered local. To support legacy flock behavior, this patch adds a mount option "-olocal_lock=" which can take the following values: 'none' - Neither flock locks nor POSIX locks are local 'flock' - flock locks are local 'posix' - fcntl/POSIX locks are local 'all' - Both flock locks and POSIX locks are local Testing: - This patch was tested by using -olocal_lock option with different values and the NLM calls were noted from the network packet captured. 'none' - NLM calls were seen during both flock() and fcntl(), flock lock was granted, fcntl was denied 'flock' - no NLM calls for flock(), NLM call was seen for fcntl(), granted 'posix' - NLM call was seen for flock() - granted, no NLM call for fcntl() 'all' - no NLM calls were seen during both flock() and fcntl() - No bugs were seen during NFSv4 locking/unlocking in general and NFSv4 reboot recovery. Cc: Neil Brown <neilb@suse.de> Signed-off-by: Suresh Jayaraman <sjayaraman@suse.de> Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com>
2010-09-23 12:55:58 +00:00
struct inode *inode = filp->f_mapping->host;
int is_local = 0;
dprintk("NFS: flock(%pD2, t=%x, fl=%x)\n",
filp, fl->fl_type, fl->fl_flags);
if (!(fl->fl_flags & FL_FLOCK))
return -ENOLCK;
/*
* The NFSv4 protocol doesn't support LOCK_MAND, which is not part of
* any standard. In principle we might be able to support LOCK_MAND
* on NFSv2/3 since NLMv3/4 support DOS share modes, but for now the
* NFS code is not set up for it.
*/
if (fl->fl_type & LOCK_MAND)
return -EINVAL;
nfs: introduce mount option '-olocal_lock' to make locks local NFS clients since 2.6.12 support flock locks by emulating fcntl byte-range locks. Due to this, some windows applications which seem to use both flock (share mode lock mapped as flock by Samba) and fcntl locks sequentially on the same file, can't lock as they falsely assume the file is already locked. The problem was reported on a setup with windows clients accessing excel files on a Samba exported share which is originally a NFS mount from a NetApp filer. Older NFS clients (< 2.6.12) did not see this problem as flock locks were considered local. To support legacy flock behavior, this patch adds a mount option "-olocal_lock=" which can take the following values: 'none' - Neither flock locks nor POSIX locks are local 'flock' - flock locks are local 'posix' - fcntl/POSIX locks are local 'all' - Both flock locks and POSIX locks are local Testing: - This patch was tested by using -olocal_lock option with different values and the NLM calls were noted from the network packet captured. 'none' - NLM calls were seen during both flock() and fcntl(), flock lock was granted, fcntl was denied 'flock' - no NLM calls for flock(), NLM call was seen for fcntl(), granted 'posix' - NLM call was seen for flock() - granted, no NLM call for fcntl() 'all' - no NLM calls were seen during both flock() and fcntl() - No bugs were seen during NFSv4 locking/unlocking in general and NFSv4 reboot recovery. Cc: Neil Brown <neilb@suse.de> Signed-off-by: Suresh Jayaraman <sjayaraman@suse.de> Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com>
2010-09-23 12:55:58 +00:00
if (NFS_SERVER(inode)->flags & NFS_MOUNT_LOCAL_FLOCK)
is_local = 1;
/* We're simulating flock() locks using posix locks on the server */
if (fl->fl_type == F_UNLCK)
nfs: introduce mount option '-olocal_lock' to make locks local NFS clients since 2.6.12 support flock locks by emulating fcntl byte-range locks. Due to this, some windows applications which seem to use both flock (share mode lock mapped as flock by Samba) and fcntl locks sequentially on the same file, can't lock as they falsely assume the file is already locked. The problem was reported on a setup with windows clients accessing excel files on a Samba exported share which is originally a NFS mount from a NetApp filer. Older NFS clients (< 2.6.12) did not see this problem as flock locks were considered local. To support legacy flock behavior, this patch adds a mount option "-olocal_lock=" which can take the following values: 'none' - Neither flock locks nor POSIX locks are local 'flock' - flock locks are local 'posix' - fcntl/POSIX locks are local 'all' - Both flock locks and POSIX locks are local Testing: - This patch was tested by using -olocal_lock option with different values and the NLM calls were noted from the network packet captured. 'none' - NLM calls were seen during both flock() and fcntl(), flock lock was granted, fcntl was denied 'flock' - no NLM calls for flock(), NLM call was seen for fcntl(), granted 'posix' - NLM call was seen for flock() - granted, no NLM call for fcntl() 'all' - no NLM calls were seen during both flock() and fcntl() - No bugs were seen during NFSv4 locking/unlocking in general and NFSv4 reboot recovery. Cc: Neil Brown <neilb@suse.de> Signed-off-by: Suresh Jayaraman <sjayaraman@suse.de> Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com>
2010-09-23 12:55:58 +00:00
return do_unlk(filp, cmd, fl, is_local);
return do_setlk(filp, cmd, fl, is_local);
}
EXPORT_SYMBOL_GPL(nfs_flock);
const struct file_operations nfs_file_operations = {
.llseek = nfs_file_llseek,
.read_iter = nfs_file_read,
.write_iter = nfs_file_write,
.mmap = nfs_file_mmap,
.open = nfs_file_open,
.flush = nfs_file_flush,
.release = nfs_file_release,
.fsync = nfs_file_fsync,
.lock = nfs_lock,
.flock = nfs_flock,
.splice_read = nfs_file_splice_read,
.splice_write = iter_file_splice_write,
.check_flags = nfs_check_flags,
.setlease = simple_nosetlease,
};
EXPORT_SYMBOL_GPL(nfs_file_operations);