linux_dsm_epyc7002/fs/afs/mntpt.c

298 lines
7.0 KiB
C
Raw Normal View History

/* mountpoint management
*
* Copyright (C) 2002 Red Hat, Inc. All Rights Reserved.
* Written by David Howells (dhowells@redhat.com)
*
* This program is free software; you can redistribute it and/or
* modify it under the terms of the GNU General Public License
* as published by the Free Software Foundation; either version
* 2 of the License, or (at your option) any later version.
*/
#include <linux/kernel.h>
#include <linux/module.h>
#include <linux/init.h>
#include <linux/fs.h>
#include <linux/pagemap.h>
#include <linux/mount.h>
#include <linux/namei.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 15:04:11 +07:00
#include <linux/gfp.h>
#include "internal.h"
static struct dentry *afs_mntpt_lookup(struct inode *dir,
struct dentry *dentry,
struct nameidata *nd);
static int afs_mntpt_open(struct inode *inode, struct file *file);
static void afs_mntpt_expiry_timed_out(struct work_struct *work);
const struct file_operations afs_mntpt_file_operations = {
.open = afs_mntpt_open,
llseek: automatically add .llseek fop All file_operations should get a .llseek operation so we can make nonseekable_open the default for future file operations without a .llseek pointer. The three cases that we can automatically detect are no_llseek, seq_lseek and default_llseek. For cases where we can we can automatically prove that the file offset is always ignored, we use noop_llseek, which maintains the current behavior of not returning an error from a seek. New drivers should normally not use noop_llseek but instead use no_llseek and call nonseekable_open at open time. Existing drivers can be converted to do the same when the maintainer knows for certain that no user code relies on calling seek on the device file. The generated code is often incorrectly indented and right now contains comments that clarify for each added line why a specific variant was chosen. In the version that gets submitted upstream, the comments will be gone and I will manually fix the indentation, because there does not seem to be a way to do that using coccinelle. Some amount of new code is currently sitting in linux-next that should get the same modifications, which I will do at the end of the merge window. Many thanks to Julia Lawall for helping me learn to write a semantic patch that does all this. ===== begin semantic patch ===== // This adds an llseek= method to all file operations, // as a preparation for making no_llseek the default. // // The rules are // - use no_llseek explicitly if we do nonseekable_open // - use seq_lseek for sequential files // - use default_llseek if we know we access f_pos // - use noop_llseek if we know we don't access f_pos, // but we still want to allow users to call lseek // @ open1 exists @ identifier nested_open; @@ nested_open(...) { <+... nonseekable_open(...) ...+> } @ open exists@ identifier open_f; identifier i, f; identifier open1.nested_open; @@ int open_f(struct inode *i, struct file *f) { <+... ( nonseekable_open(...) | nested_open(...) ) ...+> } @ read disable optional_qualifier exists @ identifier read_f; identifier f, p, s, off; type ssize_t, size_t, loff_t; expression E; identifier func; @@ ssize_t read_f(struct file *f, char *p, size_t s, loff_t *off) { <+... ( *off = E | *off += E | func(..., off, ...) | E = *off ) ...+> } @ read_no_fpos disable optional_qualifier exists @ identifier read_f; identifier f, p, s, off; type ssize_t, size_t, loff_t; @@ ssize_t read_f(struct file *f, char *p, size_t s, loff_t *off) { ... when != off } @ write @ identifier write_f; identifier f, p, s, off; type ssize_t, size_t, loff_t; expression E; identifier func; @@ ssize_t write_f(struct file *f, const char *p, size_t s, loff_t *off) { <+... ( *off = E | *off += E | func(..., off, ...) | E = *off ) ...+> } @ write_no_fpos @ identifier write_f; identifier f, p, s, off; type ssize_t, size_t, loff_t; @@ ssize_t write_f(struct file *f, const char *p, size_t s, loff_t *off) { ... when != off } @ fops0 @ identifier fops; @@ struct file_operations fops = { ... }; @ has_llseek depends on fops0 @ identifier fops0.fops; identifier llseek_f; @@ struct file_operations fops = { ... .llseek = llseek_f, ... }; @ has_read depends on fops0 @ identifier fops0.fops; identifier read_f; @@ struct file_operations fops = { ... .read = read_f, ... }; @ has_write depends on fops0 @ identifier fops0.fops; identifier write_f; @@ struct file_operations fops = { ... .write = write_f, ... }; @ has_open depends on fops0 @ identifier fops0.fops; identifier open_f; @@ struct file_operations fops = { ... .open = open_f, ... }; // use no_llseek if we call nonseekable_open //////////////////////////////////////////// @ nonseekable1 depends on !has_llseek && has_open @ identifier fops0.fops; identifier nso ~= "nonseekable_open"; @@ struct file_operations fops = { ... .open = nso, ... +.llseek = no_llseek, /* nonseekable */ }; @ nonseekable2 depends on !has_llseek @ identifier fops0.fops; identifier open.open_f; @@ struct file_operations fops = { ... .open = open_f, ... +.llseek = no_llseek, /* open uses nonseekable */ }; // use seq_lseek for sequential files ///////////////////////////////////// @ seq depends on !has_llseek @ identifier fops0.fops; identifier sr ~= "seq_read"; @@ struct file_operations fops = { ... .read = sr, ... +.llseek = seq_lseek, /* we have seq_read */ }; // use default_llseek if there is a readdir /////////////////////////////////////////// @ fops1 depends on !has_llseek && !nonseekable1 && !nonseekable2 && !seq @ identifier fops0.fops; identifier readdir_e; @@ // any other fop is used that changes pos struct file_operations fops = { ... .readdir = readdir_e, ... +.llseek = default_llseek, /* readdir is present */ }; // use default_llseek if at least one of read/write touches f_pos ///////////////////////////////////////////////////////////////// @ fops2 depends on !fops1 && !has_llseek && !nonseekable1 && !nonseekable2 && !seq @ identifier fops0.fops; identifier read.read_f; @@ // read fops use offset struct file_operations fops = { ... .read = read_f, ... +.llseek = default_llseek, /* read accesses f_pos */ }; @ fops3 depends on !fops1 && !fops2 && !has_llseek && !nonseekable1 && !nonseekable2 && !seq @ identifier fops0.fops; identifier write.write_f; @@ // write fops use offset struct file_operations fops = { ... .write = write_f, ... + .llseek = default_llseek, /* write accesses f_pos */ }; // Use noop_llseek if neither read nor write accesses f_pos /////////////////////////////////////////////////////////// @ fops4 depends on !fops1 && !fops2 && !fops3 && !has_llseek && !nonseekable1 && !nonseekable2 && !seq @ identifier fops0.fops; identifier read_no_fpos.read_f; identifier write_no_fpos.write_f; @@ // write fops use offset struct file_operations fops = { ... .write = write_f, .read = read_f, ... +.llseek = noop_llseek, /* read and write both use no f_pos */ }; @ depends on has_write && !has_read && !fops1 && !fops2 && !has_llseek && !nonseekable1 && !nonseekable2 && !seq @ identifier fops0.fops; identifier write_no_fpos.write_f; @@ struct file_operations fops = { ... .write = write_f, ... +.llseek = noop_llseek, /* write uses no f_pos */ }; @ depends on has_read && !has_write && !fops1 && !fops2 && !has_llseek && !nonseekable1 && !nonseekable2 && !seq @ identifier fops0.fops; identifier read_no_fpos.read_f; @@ struct file_operations fops = { ... .read = read_f, ... +.llseek = noop_llseek, /* read uses no f_pos */ }; @ depends on !has_read && !has_write && !fops1 && !fops2 && !has_llseek && !nonseekable1 && !nonseekable2 && !seq @ identifier fops0.fops; @@ struct file_operations fops = { ... +.llseek = noop_llseek, /* no read or write fn */ }; ===== End semantic patch ===== Signed-off-by: Arnd Bergmann <arnd@arndb.de> Cc: Julia Lawall <julia@diku.dk> Cc: Christoph Hellwig <hch@infradead.org>
2010-08-15 23:52:59 +07:00
.llseek = noop_llseek,
};
const struct inode_operations afs_mntpt_inode_operations = {
.lookup = afs_mntpt_lookup,
.readlink = page_readlink,
.getattr = afs_getattr,
};
const struct inode_operations afs_autocell_inode_operations = {
.getattr = afs_getattr,
};
static LIST_HEAD(afs_vfsmounts);
static DECLARE_DELAYED_WORK(afs_mntpt_expiry_timer, afs_mntpt_expiry_timed_out);
static unsigned long afs_mntpt_expiry_timeout = 10 * 60;
/*
* check a symbolic link to see whether it actually encodes a mountpoint
* - sets the AFS_VNODE_MOUNTPOINT flag on the vnode appropriately
*/
int afs_mntpt_check_symlink(struct afs_vnode *vnode, struct key *key)
{
struct page *page;
size_t size;
char *buf;
int ret;
_enter("{%x:%u,%u}",
vnode->fid.vid, vnode->fid.vnode, vnode->fid.unique);
/* read the contents of the symlink into the pagecache */
page = read_cache_page(AFS_VNODE_TO_I(vnode)->i_mapping, 0,
afs_page_filler, key);
if (IS_ERR(page)) {
ret = PTR_ERR(page);
goto out;
}
ret = -EIO;
if (PageError(page))
goto out_free;
buf = kmap(page);
/* examine the symlink's contents */
size = vnode->status.size;
_debug("symlink to %*.*s", (int) size, (int) size, buf);
if (size > 2 &&
(buf[0] == '%' || buf[0] == '#') &&
buf[size - 1] == '.'
) {
_debug("symlink is a mountpoint");
spin_lock(&vnode->lock);
set_bit(AFS_VNODE_MOUNTPOINT, &vnode->flags);
vnode->vfs_inode.i_flags |= S_AUTOMOUNT;
spin_unlock(&vnode->lock);
}
ret = 0;
kunmap(page);
out_free:
page_cache_release(page);
out:
_leave(" = %d", ret);
return ret;
}
/*
* no valid lookup procedure on this sort of dir
*/
static struct dentry *afs_mntpt_lookup(struct inode *dir,
struct dentry *dentry,
struct nameidata *nd)
{
_enter("%p,%p{%p{%s},%s}",
dir,
dentry,
dentry->d_parent,
dentry->d_parent ?
dentry->d_parent->d_name.name : (const unsigned char *) "",
dentry->d_name.name);
return ERR_PTR(-EREMOTE);
}
/*
* no valid open procedure on this sort of dir
*/
static int afs_mntpt_open(struct inode *inode, struct file *file)
{
_enter("%p,%p{%p{%s},%s}",
inode, file,
file->f_path.dentry->d_parent,
file->f_path.dentry->d_parent ?
file->f_path.dentry->d_parent->d_name.name :
(const unsigned char *) "",
file->f_path.dentry->d_name.name);
return -EREMOTE;
}
/*
* create a vfsmount to be automounted
*/
static struct vfsmount *afs_mntpt_do_automount(struct dentry *mntpt)
{
struct afs_super_info *super;
struct vfsmount *mnt;
struct afs_vnode *vnode;
struct page *page;
char *devname, *options;
bool rwpath = false;
int ret;
_enter("{%s}", mntpt->d_name.name);
BUG_ON(!mntpt->d_inode);
ret = -ENOMEM;
devname = (char *) get_zeroed_page(GFP_KERNEL);
if (!devname)
goto error_no_devname;
options = (char *) get_zeroed_page(GFP_KERNEL);
if (!options)
goto error_no_options;
vnode = AFS_FS_I(mntpt->d_inode);
if (test_bit(AFS_VNODE_PSEUDODIR, &vnode->flags)) {
/* if the directory is a pseudo directory, use the d_name */
static const char afs_root_cell[] = ":root.cell.";
unsigned size = mntpt->d_name.len;
ret = -ENOENT;
if (size < 2 || size > AFS_MAXCELLNAME)
goto error_no_page;
if (mntpt->d_name.name[0] == '.') {
devname[0] = '#';
memcpy(devname + 1, mntpt->d_name.name, size - 1);
memcpy(devname + size, afs_root_cell,
sizeof(afs_root_cell));
rwpath = true;
} else {
devname[0] = '%';
memcpy(devname + 1, mntpt->d_name.name, size);
memcpy(devname + size + 1, afs_root_cell,
sizeof(afs_root_cell));
}
} else {
/* read the contents of the AFS special symlink */
loff_t size = i_size_read(mntpt->d_inode);
char *buf;
ret = -EINVAL;
if (size > PAGE_SIZE - 1)
goto error_no_page;
page = read_mapping_page(mntpt->d_inode->i_mapping, 0, NULL);
if (IS_ERR(page)) {
ret = PTR_ERR(page);
goto error_no_page;
}
ret = -EIO;
if (PageError(page))
goto error;
buf = kmap_atomic(page, KM_USER0);
memcpy(devname, buf, size);
kunmap_atomic(buf, KM_USER0);
page_cache_release(page);
page = NULL;
}
/* work out what options we want */
super = AFS_FS_S(mntpt->d_sb);
memcpy(options, "cell=", 5);
strcpy(options + 5, super->volume->cell->name);
if (super->volume->type == AFSVL_RWVOL || rwpath)
strcat(options, ",rwpath");
/* try and do the mount */
_debug("--- attempting mount %s -o %s ---", devname, options);
mnt = vfs_kern_mount(&afs_fs_type, 0, devname, options);
_debug("--- mount result %p ---", mnt);
free_page((unsigned long) devname);
free_page((unsigned long) options);
_leave(" = %p", mnt);
return mnt;
error:
page_cache_release(page);
error_no_page:
free_page((unsigned long) options);
error_no_options:
free_page((unsigned long) devname);
error_no_devname:
_leave(" = %d", ret);
return ERR_PTR(ret);
}
/*
* handle an automount point
*/
struct vfsmount *afs_d_automount(struct path *path)
{
struct vfsmount *newmnt;
int err;
_enter("{%s,%s}", path->mnt->mnt_devname, path->dentry->d_name.name);
newmnt = afs_mntpt_do_automount(path->dentry);
if (IS_ERR(newmnt))
return newmnt;
mntget(newmnt);
err = do_add_mount(newmnt, path, MNT_SHRINKABLE, &afs_vfsmounts);
switch (err) {
case 0:
queue_delayed_work(afs_wq, &afs_mntpt_expiry_timer,
afs_mntpt_expiry_timeout * HZ);
_leave(" = %p {%s}", newmnt, newmnt->mnt_devname);
return newmnt;
case -EBUSY:
/* someone else made a mount here whilst we were busy */
mntput(newmnt);
_leave(" = NULL [EBUSY]");
return NULL;
default:
mntput(newmnt);
_leave(" = %d", err);
return ERR_PTR(err);
}
}
/*
* handle mountpoint expiry timer going off
*/
static void afs_mntpt_expiry_timed_out(struct work_struct *work)
{
_enter("");
if (!list_empty(&afs_vfsmounts)) {
mark_mounts_for_expiry(&afs_vfsmounts);
queue_delayed_work(afs_wq, &afs_mntpt_expiry_timer,
afs_mntpt_expiry_timeout * HZ);
}
_leave("");
}
/*
* kill the AFS mountpoint timer if it's still running
*/
void afs_mntpt_kill_timer(void)
{
_enter("");
ASSERT(list_empty(&afs_vfsmounts));
cancel_delayed_work_sync(&afs_mntpt_expiry_timer);
}