OpenCloudOS-Kernel/include/linux/nfs_fs.h

554 lines
16 KiB
C
Raw Normal View History

/*
* linux/include/linux/nfs_fs.h
*
* Copyright (C) 1992 Rick Sladkey
*
* OS-specific nfs filesystem definitions and declarations
*/
#ifndef _LINUX_NFS_FS_H
#define _LINUX_NFS_FS_H
#include <uapi/linux/nfs_fs.h>
/*
* Enable dprintk() debugging support for nfs client.
*/
#ifdef CONFIG_NFS_DEBUG
# define NFS_DEBUG
#endif
#include <linux/in.h>
#include <linux/mm.h>
#include <linux/pagemap.h>
#include <linux/rbtree.h>
#include <linux/rwsem.h>
#include <linux/wait.h>
#include <linux/sunrpc/debug.h>
#include <linux/sunrpc/auth.h>
#include <linux/sunrpc/clnt.h>
#include <linux/nfs.h>
#include <linux/nfs2.h>
#include <linux/nfs3.h>
#include <linux/nfs4.h>
#include <linux/nfs_xdr.h>
#include <linux/nfs_fs_sb.h>
#include <linux/mempool.h>
/*
* These are the default flags for swap requests
*/
#define NFS_RPC_SWAPFLAGS (RPC_TASK_SWAPPER|RPC_TASK_ROOTCREDS)
/*
* NFSv3/v4 Access mode cache entry
*/
struct nfs_access_entry {
struct rb_node rb_node;
struct list_head lru;
unsigned long jiffies;
struct rpc_cred * cred;
int mask;
struct rcu_head rcu_head;
};
struct nfs_lock_context {
atomic_t count;
struct list_head list;
struct nfs_open_context *open_context;
fl_owner_t lockowner;
atomic_t io_count;
};
struct nfs4_state;
struct nfs_open_context {
struct nfs_lock_context lock_context;
2016-10-13 12:26:47 +08:00
fl_owner_t flock_owner;
struct dentry *dentry;
struct rpc_cred *cred;
struct nfs4_state *state;
fmode_t mode;
unsigned long flags;
#define NFS_CONTEXT_ERROR_WRITE (0)
#define NFS_CONTEXT_RESEND_WRITES (1)
#define NFS_CONTEXT_BAD (2)
#define NFS_CONTEXT_UNLOCK (3)
int error;
struct list_head list;
struct nfs4_threshold *mdsthreshold;
};
struct nfs_open_dir_context {
struct list_head list;
struct rpc_cred *cred;
unsigned long attr_gencount;
__u64 dir_cookie;
__u64 dup_cookie;
signed char duped;
};
/*
* NFSv4 delegation
*/
struct nfs_delegation;
struct posix_acl;
/*
* nfs fs inode data in memory
*/
struct nfs_inode {
/*
* The 64bit 'inode number'
*/
__u64 fileid;
/*
* NFS file handle
*/
struct nfs_fh fh;
/*
* Various flags
*/
unsigned long flags; /* atomic bit ops */
unsigned long cache_validity; /* bit mask */
/*
* read_cache_jiffies is when we started read-caching this inode.
* attrtimeo is for how long the cached information is assumed
* to be valid. A successful attribute revalidation doubles
* attrtimeo (up to acregmax/acdirmax), a failure resets it to
* acregmin/acdirmin.
*
* We need to revalidate the cached attrs for this inode if
*
* jiffies - read_cache_jiffies >= attrtimeo
*
* Please note the comparison is greater than or equal
* so that zero timeout values can be specified.
*/
unsigned long read_cache_jiffies;
unsigned long attrtimeo;
unsigned long attrtimeo_timestamp;
unsigned long attr_gencount;
/* "Generation counter" for the attribute cache. This is
* bumped whenever we update the metadata on the
* server.
*/
unsigned long cache_change_attribute;
struct rb_root access_cache;
struct list_head access_cache_entry_lru;
struct list_head access_cache_inode_lru;
/*
* This is the cookie verifier used for NFSv3 readdir
* operations
*/
__be32 cookieverf[2];
unsigned long nrequests;
struct nfs_mds_commit_info commit_info;
/* Open contexts for shared mmap writes */
struct list_head open_files;
/* Readers: in-flight sillydelete RPC calls */
/* Writers: rmdir */
struct rw_semaphore rmdir_sem;
#if IS_ENABLED(CONFIG_NFS_V4)
struct nfs4_cached_acl *nfs4_acl;
/* NFSv4 state */
struct list_head open_states;
struct nfs_delegation __rcu *delegation;
struct rw_semaphore rwsem;
/* pNFS layout information */
struct pnfs_layout_hdr *layout;
#endif /* CONFIG_NFS_V4*/
/* how many bytes have been written/read and how many bytes queued up */
__u64 write_io;
__u64 read_io;
#ifdef CONFIG_NFS_FSCACHE
struct fscache_cookie *fscache;
#endif
struct inode vfs_inode;
};
/*
* Cache validity bit flags
*/
#define NFS_INO_INVALID_ATTR 0x0001 /* cached attrs are invalid */
#define NFS_INO_INVALID_DATA 0x0002 /* cached data is invalid */
#define NFS_INO_INVALID_ATIME 0x0004 /* cached atime is invalid */
#define NFS_INO_INVALID_ACCESS 0x0008 /* cached access cred invalid */
#define NFS_INO_INVALID_ACL 0x0010 /* cached acls are invalid */
#define NFS_INO_REVAL_PAGECACHE 0x0020 /* must revalidate pagecache */
#define NFS_INO_REVAL_FORCED 0x0040 /* force revalidation ignoring a delegation */
#define NFS_INO_INVALID_LABEL 0x0080 /* cached label is invalid */
/*
* Bit offsets in flags field
*/
#define NFS_INO_ADVISE_RDPLUS (0) /* advise readdirplus */
#define NFS_INO_STALE (1) /* possible stale inode */
#define NFS_INO_ACL_LRU_SET (2) /* Inode is on the LRU list */
NFS: fix the handling of NFS_INO_INVALID_DATA flag in nfs_revalidate_mapping There is a possible race in how the nfs_invalidate_mapping function is handled. Currently, we go and invalidate the pages in the file and then clear NFS_INO_INVALID_DATA. The problem is that it's possible for a stale page to creep into the mapping after the page was invalidated (i.e., via readahead). If another writer comes along and sets the flag after that happens but before invalidate_inode_pages2 returns then we could clear the flag without the cache having been properly invalidated. So, we must clear the flag first and then invalidate the pages. Doing this however, opens another race: It's possible to have two concurrent read() calls that end up in nfs_revalidate_mapping at the same time. The first one clears the NFS_INO_INVALID_DATA flag and then goes to call nfs_invalidate_mapping. Just before calling that though, the other task races in, checks the flag and finds it cleared. At that point, it trusts that the mapping is good and gets the lock on the page, allowing the read() to be satisfied from the cache even though the data is no longer valid. These effects are easily manifested by running diotest3 from the LTP test suite on NFS. That program does a series of DIO writes and buffered reads. The operations are serialized and page-aligned but the existing code fails the test since it occasionally allows a read to come out of the cache incorrectly. While mixing direct and buffered I/O isn't recommended, I believe it's possible to hit this in other ways that just use buffered I/O, though that situation is much harder to reproduce. The problem is that the checking/clearing of that flag and the invalidation of the mapping really need to be atomic. Fix this by serializing concurrent invalidations with a bitlock. At the same time, we also need to allow other places that check NFS_INO_INVALID_DATA to check whether we might be in the middle of invalidating the file, so fix up a couple of places that do that to look for the new NFS_INO_INVALIDATING flag. Doing this requires us to be careful not to set the bitlock unnecessarily, so this code only does that if it believes it will be doing an invalidation. Signed-off-by: Jeff Layton <jlayton@redhat.com> Signed-off-by: Trond Myklebust <trond.myklebust@primarydata.com>
2014-01-28 02:46:15 +08:00
#define NFS_INO_INVALIDATING (3) /* inode is being invalidated */
#define NFS_INO_FSCACHE (5) /* inode can be cached by FS-Cache */
#define NFS_INO_FSCACHE_LOCK (6) /* FS-Cache cookie management lock */
#define NFS_INO_LAYOUTCOMMIT (9) /* layoutcommit required */
#define NFS_INO_LAYOUTCOMMITTING (10) /* layoutcommit inflight */
#define NFS_INO_LAYOUTSTATS (11) /* layoutstats inflight */
#define NFS_INO_ODIRECT (12) /* I/O setting is O_DIRECT */
static inline struct nfs_inode *NFS_I(const struct inode *inode)
{
return container_of(inode, struct nfs_inode, vfs_inode);
}
static inline struct nfs_server *NFS_SB(const struct super_block *s)
{
return (struct nfs_server *)(s->s_fs_info);
}
static inline struct nfs_fh *NFS_FH(const struct inode *inode)
{
return &NFS_I(inode)->fh;
}
static inline struct nfs_server *NFS_SERVER(const struct inode *inode)
{
return NFS_SB(inode->i_sb);
}
static inline struct rpc_clnt *NFS_CLIENT(const struct inode *inode)
{
return NFS_SERVER(inode)->client;
}
static inline const struct nfs_rpc_ops *NFS_PROTO(const struct inode *inode)
{
return NFS_SERVER(inode)->nfs_client->rpc_ops;
}
static inline unsigned NFS_MINATTRTIMEO(const struct inode *inode)
{
struct nfs_server *nfss = NFS_SERVER(inode);
return S_ISDIR(inode->i_mode) ? nfss->acdirmin : nfss->acregmin;
}
static inline unsigned NFS_MAXATTRTIMEO(const struct inode *inode)
{
struct nfs_server *nfss = NFS_SERVER(inode);
return S_ISDIR(inode->i_mode) ? nfss->acdirmax : nfss->acregmax;
}
static inline int NFS_STALE(const struct inode *inode)
{
return test_bit(NFS_INO_STALE, &NFS_I(inode)->flags);
}
NFS: Use i_writecount to control whether to get an fscache cookie in nfs_open() Use i_writecount to control whether to get an fscache cookie in nfs_open() as NFS does not do write caching yet. I *think* this is the cause of a problem encountered by Mark Moseley whereby __fscache_uncache_page() gets a NULL pointer dereference because cookie->def is NULL: BUG: unable to handle kernel NULL pointer dereference at 0000000000000010 IP: [<ffffffff812a1903>] __fscache_uncache_page+0x23/0x160 PGD 0 Thread overran stack, or stack corrupted Oops: 0000 [#1] SMP Modules linked in: ... CPU: 7 PID: 18993 Comm: php Not tainted 3.11.1 #1 Hardware name: Dell Inc. PowerEdge R420/072XWF, BIOS 1.3.5 08/21/2012 task: ffff8804203460c0 ti: ffff880420346640 RIP: 0010:[<ffffffff812a1903>] __fscache_uncache_page+0x23/0x160 RSP: 0018:ffff8801053af878 EFLAGS: 00210286 RAX: 0000000000000000 RBX: ffff8800be2f8780 RCX: ffff88022ffae5e8 RDX: 0000000000004c66 RSI: ffffea00055ff440 RDI: ffff8800be2f8780 RBP: ffff8801053af898 R08: 0000000000000001 R09: 0000000000000003 R10: 0000000000000000 R11: 0000000000000000 R12: ffffea00055ff440 R13: 0000000000001000 R14: ffff8800c50be538 R15: 0000000000000000 FS: 0000000000000000(0000) GS:ffff88042fc60000(0063) knlGS:00000000e439c700 CS: 0010 DS: 002b ES: 002b CR0: 0000000080050033 CR2: 0000000000000010 CR3: 0000000001d8f000 CR4: 00000000000607f0 Stack: ... Call Trace: [<ffffffff81365a72>] __nfs_fscache_invalidate_page+0x42/0x70 [<ffffffff813553d5>] nfs_invalidate_page+0x75/0x90 [<ffffffff811b8f5e>] truncate_inode_page+0x8e/0x90 [<ffffffff811b90ad>] truncate_inode_pages_range.part.12+0x14d/0x620 [<ffffffff81d6387d>] ? __mutex_lock_slowpath+0x1fd/0x2e0 [<ffffffff811b95d3>] truncate_inode_pages_range+0x53/0x70 [<ffffffff811b969d>] truncate_inode_pages+0x2d/0x40 [<ffffffff811b96ff>] truncate_pagecache+0x4f/0x70 [<ffffffff81356840>] nfs_setattr_update_inode+0xa0/0x120 [<ffffffff81368de4>] nfs3_proc_setattr+0xc4/0xe0 [<ffffffff81357f78>] nfs_setattr+0xc8/0x150 [<ffffffff8122d95b>] notify_change+0x1cb/0x390 [<ffffffff8120a55b>] do_truncate+0x7b/0xc0 [<ffffffff8121f96c>] do_last+0xa4c/0xfd0 [<ffffffff8121ffbc>] path_openat+0xcc/0x670 [<ffffffff81220a0e>] do_filp_open+0x4e/0xb0 [<ffffffff8120ba1f>] do_sys_open+0x13f/0x2b0 [<ffffffff8126aaf6>] compat_SyS_open+0x36/0x50 [<ffffffff81d7204c>] sysenter_dispatch+0x7/0x24 The code at the instruction pointer was disassembled: > (gdb) disas __fscache_uncache_page > Dump of assembler code for function __fscache_uncache_page: > ... > 0xffffffff812a18ff <+31>: mov 0x48(%rbx),%rax > 0xffffffff812a1903 <+35>: cmpb $0x0,0x10(%rax) > 0xffffffff812a1907 <+39>: je 0xffffffff812a19cd <__fscache_uncache_page+237> These instructions make up: ASSERTCMP(cookie->def->type, !=, FSCACHE_COOKIE_TYPE_INDEX); That cmpb is the faulting instruction (%rax is 0). So cookie->def is NULL - which presumably means that the cookie has already been at least partway through __fscache_relinquish_cookie(). What I think may be happening is something like a three-way race on the same file: PROCESS 1 PROCESS 2 PROCESS 3 =============== =============== =============== open(O_TRUNC|O_WRONLY) open(O_RDONLY) open(O_WRONLY) -->nfs_open() -->nfs_fscache_set_inode_cookie() nfs_fscache_inode_lock() nfs_fscache_disable_inode_cookie() __fscache_relinquish_cookie() nfs_inode->fscache = NULL <--nfs_fscache_set_inode_cookie() -->nfs_open() -->nfs_fscache_set_inode_cookie() nfs_fscache_inode_lock() nfs_fscache_enable_inode_cookie() __fscache_acquire_cookie() nfs_inode->fscache = cookie <--nfs_fscache_set_inode_cookie() <--nfs_open() -->nfs_setattr() ... ... -->nfs_invalidate_page() -->__nfs_fscache_invalidate_page() cookie = nfsi->fscache -->nfs_open() -->nfs_fscache_set_inode_cookie() nfs_fscache_inode_lock() nfs_fscache_disable_inode_cookie() -->__fscache_relinquish_cookie() -->__fscache_uncache_page(cookie) <crash> <--__fscache_relinquish_cookie() nfs_inode->fscache = NULL <--nfs_fscache_set_inode_cookie() What is needed is something to prevent process #2 from reacquiring the cookie - and I think checking i_writecount should do the trick. It's also possible to have a two-way race on this if the file is opened O_TRUNC|O_RDONLY instead. Reported-by: Mark Moseley <moseleymark@gmail.com> Signed-off-by: David Howells <dhowells@redhat.com>
2013-09-27 18:20:03 +08:00
static inline struct fscache_cookie *nfs_i_fscache(struct inode *inode)
{
NFS: Use i_writecount to control whether to get an fscache cookie in nfs_open() Use i_writecount to control whether to get an fscache cookie in nfs_open() as NFS does not do write caching yet. I *think* this is the cause of a problem encountered by Mark Moseley whereby __fscache_uncache_page() gets a NULL pointer dereference because cookie->def is NULL: BUG: unable to handle kernel NULL pointer dereference at 0000000000000010 IP: [<ffffffff812a1903>] __fscache_uncache_page+0x23/0x160 PGD 0 Thread overran stack, or stack corrupted Oops: 0000 [#1] SMP Modules linked in: ... CPU: 7 PID: 18993 Comm: php Not tainted 3.11.1 #1 Hardware name: Dell Inc. PowerEdge R420/072XWF, BIOS 1.3.5 08/21/2012 task: ffff8804203460c0 ti: ffff880420346640 RIP: 0010:[<ffffffff812a1903>] __fscache_uncache_page+0x23/0x160 RSP: 0018:ffff8801053af878 EFLAGS: 00210286 RAX: 0000000000000000 RBX: ffff8800be2f8780 RCX: ffff88022ffae5e8 RDX: 0000000000004c66 RSI: ffffea00055ff440 RDI: ffff8800be2f8780 RBP: ffff8801053af898 R08: 0000000000000001 R09: 0000000000000003 R10: 0000000000000000 R11: 0000000000000000 R12: ffffea00055ff440 R13: 0000000000001000 R14: ffff8800c50be538 R15: 0000000000000000 FS: 0000000000000000(0000) GS:ffff88042fc60000(0063) knlGS:00000000e439c700 CS: 0010 DS: 002b ES: 002b CR0: 0000000080050033 CR2: 0000000000000010 CR3: 0000000001d8f000 CR4: 00000000000607f0 Stack: ... Call Trace: [<ffffffff81365a72>] __nfs_fscache_invalidate_page+0x42/0x70 [<ffffffff813553d5>] nfs_invalidate_page+0x75/0x90 [<ffffffff811b8f5e>] truncate_inode_page+0x8e/0x90 [<ffffffff811b90ad>] truncate_inode_pages_range.part.12+0x14d/0x620 [<ffffffff81d6387d>] ? __mutex_lock_slowpath+0x1fd/0x2e0 [<ffffffff811b95d3>] truncate_inode_pages_range+0x53/0x70 [<ffffffff811b969d>] truncate_inode_pages+0x2d/0x40 [<ffffffff811b96ff>] truncate_pagecache+0x4f/0x70 [<ffffffff81356840>] nfs_setattr_update_inode+0xa0/0x120 [<ffffffff81368de4>] nfs3_proc_setattr+0xc4/0xe0 [<ffffffff81357f78>] nfs_setattr+0xc8/0x150 [<ffffffff8122d95b>] notify_change+0x1cb/0x390 [<ffffffff8120a55b>] do_truncate+0x7b/0xc0 [<ffffffff8121f96c>] do_last+0xa4c/0xfd0 [<ffffffff8121ffbc>] path_openat+0xcc/0x670 [<ffffffff81220a0e>] do_filp_open+0x4e/0xb0 [<ffffffff8120ba1f>] do_sys_open+0x13f/0x2b0 [<ffffffff8126aaf6>] compat_SyS_open+0x36/0x50 [<ffffffff81d7204c>] sysenter_dispatch+0x7/0x24 The code at the instruction pointer was disassembled: > (gdb) disas __fscache_uncache_page > Dump of assembler code for function __fscache_uncache_page: > ... > 0xffffffff812a18ff <+31>: mov 0x48(%rbx),%rax > 0xffffffff812a1903 <+35>: cmpb $0x0,0x10(%rax) > 0xffffffff812a1907 <+39>: je 0xffffffff812a19cd <__fscache_uncache_page+237> These instructions make up: ASSERTCMP(cookie->def->type, !=, FSCACHE_COOKIE_TYPE_INDEX); That cmpb is the faulting instruction (%rax is 0). So cookie->def is NULL - which presumably means that the cookie has already been at least partway through __fscache_relinquish_cookie(). What I think may be happening is something like a three-way race on the same file: PROCESS 1 PROCESS 2 PROCESS 3 =============== =============== =============== open(O_TRUNC|O_WRONLY) open(O_RDONLY) open(O_WRONLY) -->nfs_open() -->nfs_fscache_set_inode_cookie() nfs_fscache_inode_lock() nfs_fscache_disable_inode_cookie() __fscache_relinquish_cookie() nfs_inode->fscache = NULL <--nfs_fscache_set_inode_cookie() -->nfs_open() -->nfs_fscache_set_inode_cookie() nfs_fscache_inode_lock() nfs_fscache_enable_inode_cookie() __fscache_acquire_cookie() nfs_inode->fscache = cookie <--nfs_fscache_set_inode_cookie() <--nfs_open() -->nfs_setattr() ... ... -->nfs_invalidate_page() -->__nfs_fscache_invalidate_page() cookie = nfsi->fscache -->nfs_open() -->nfs_fscache_set_inode_cookie() nfs_fscache_inode_lock() nfs_fscache_disable_inode_cookie() -->__fscache_relinquish_cookie() -->__fscache_uncache_page(cookie) <crash> <--__fscache_relinquish_cookie() nfs_inode->fscache = NULL <--nfs_fscache_set_inode_cookie() What is needed is something to prevent process #2 from reacquiring the cookie - and I think checking i_writecount should do the trick. It's also possible to have a two-way race on this if the file is opened O_TRUNC|O_RDONLY instead. Reported-by: Mark Moseley <moseleymark@gmail.com> Signed-off-by: David Howells <dhowells@redhat.com>
2013-09-27 18:20:03 +08:00
#ifdef CONFIG_NFS_FSCACHE
return NFS_I(inode)->fscache;
#else
return NULL;
#endif
}
static inline __u64 NFS_FILEID(const struct inode *inode)
{
return NFS_I(inode)->fileid;
}
static inline void set_nfs_fileid(struct inode *inode, __u64 fileid)
{
NFS_I(inode)->fileid = fileid;
}
static inline void nfs_mark_for_revalidate(struct inode *inode)
{
struct nfs_inode *nfsi = NFS_I(inode);
spin_lock(&inode->i_lock);
nfsi->cache_validity |= NFS_INO_INVALID_ATTR |
NFS_INO_REVAL_PAGECACHE |
NFS_INO_INVALID_ACCESS |
NFS_INO_INVALID_ACL;
if (S_ISDIR(inode->i_mode))
nfsi->cache_validity |= NFS_INO_INVALID_DATA;
spin_unlock(&inode->i_lock);
}
static inline int nfs_server_capable(struct inode *inode, int cap)
{
return NFS_SERVER(inode)->caps & cap;
}
static inline void nfs_set_verifier(struct dentry * dentry, unsigned long verf)
{
dentry->d_time = verf;
}
/**
* nfs_save_change_attribute - Returns the inode attribute change cookie
* @dir - pointer to parent directory inode
* The "change attribute" is updated every time we finish an operation
* that will result in a metadata change on the server.
*/
static inline unsigned long nfs_save_change_attribute(struct inode *dir)
{
return NFS_I(dir)->cache_change_attribute;
}
/**
* nfs_verify_change_attribute - Detects NFS remote directory changes
* @dir - pointer to parent directory inode
* @chattr - previously saved change attribute
* Return "false" if the verifiers doesn't match the change attribute.
* This would usually indicate that the directory contents have changed on
* the server, and that any dentries need revalidating.
*/
static inline int nfs_verify_change_attribute(struct inode *dir, unsigned long chattr)
{
return chattr == NFS_I(dir)->cache_change_attribute;
}
/*
* linux/fs/nfs/inode.c
*/
extern int nfs_sync_mapping(struct address_space *mapping);
extern void nfs_zap_mapping(struct inode *inode, struct address_space *mapping);
extern void nfs_zap_caches(struct inode *);
extern void nfs_invalidate_atime(struct inode *);
extern struct inode *nfs_fhget(struct super_block *, struct nfs_fh *,
struct nfs_fattr *, struct nfs4_label *);
extern int nfs_refresh_inode(struct inode *, struct nfs_fattr *);
extern int nfs_post_op_update_inode(struct inode *inode, struct nfs_fattr *fattr);
extern int nfs_post_op_update_inode_force_wcc(struct inode *inode, struct nfs_fattr *fattr);
extern int nfs_post_op_update_inode_force_wcc_locked(struct inode *inode, struct nfs_fattr *fattr);
statx: Add a system call to make enhanced file info available Add a system call to make extended file information available, including file creation and some attribute flags where available through the underlying filesystem. The getattr inode operation is altered to take two additional arguments: a u32 request_mask and an unsigned int flags that indicate the synchronisation mode. This change is propagated to the vfs_getattr*() function. Functions like vfs_stat() are now inline wrappers around new functions vfs_statx() and vfs_statx_fd() to reduce stack usage. ======== OVERVIEW ======== The idea was initially proposed as a set of xattrs that could be retrieved with getxattr(), but the general preference proved to be for a new syscall with an extended stat structure. A number of requests were gathered for features to be included. The following have been included: (1) Make the fields a consistent size on all arches and make them large. (2) Spare space, request flags and information flags are provided for future expansion. (3) Better support for the y2038 problem [Arnd Bergmann] (tv_sec is an __s64). (4) Creation time: The SMB protocol carries the creation time, which could be exported by Samba, which will in turn help CIFS make use of FS-Cache as that can be used for coherency data (stx_btime). This is also specified in NFSv4 as a recommended attribute and could be exported by NFSD [Steve French]. (5) Lightweight stat: Ask for just those details of interest, and allow a netfs (such as NFS) to approximate anything not of interest, possibly without going to the server [Trond Myklebust, Ulrich Drepper, Andreas Dilger] (AT_STATX_DONT_SYNC). (6) Heavyweight stat: Force a netfs to go to the server, even if it thinks its cached attributes are up to date [Trond Myklebust] (AT_STATX_FORCE_SYNC). And the following have been left out for future extension: (7) Data version number: Could be used by userspace NFS servers [Aneesh Kumar]. Can also be used to modify fill_post_wcc() in NFSD which retrieves i_version directly, but has just called vfs_getattr(). It could get it from the kstat struct if it used vfs_xgetattr() instead. (There's disagreement on the exact semantics of a single field, since not all filesystems do this the same way). (8) BSD stat compatibility: Including more fields from the BSD stat such as creation time (st_btime) and inode generation number (st_gen) [Jeremy Allison, Bernd Schubert]. (9) Inode generation number: Useful for FUSE and userspace NFS servers [Bernd Schubert]. (This was asked for but later deemed unnecessary with the open-by-handle capability available and caused disagreement as to whether it's a security hole or not). (10) Extra coherency data may be useful in making backups [Andreas Dilger]. (No particular data were offered, but things like last backup timestamp, the data version number and the DOS archive bit would come into this category). (11) Allow the filesystem to indicate what it can/cannot provide: A filesystem can now say it doesn't support a standard stat feature if that isn't available, so if, for instance, inode numbers or UIDs don't exist or are fabricated locally... (This requires a separate system call - I have an fsinfo() call idea for this). (12) Store a 16-byte volume ID in the superblock that can be returned in struct xstat [Steve French]. (Deferred to fsinfo). (13) Include granularity fields in the time data to indicate the granularity of each of the times (NFSv4 time_delta) [Steve French]. (Deferred to fsinfo). (14) FS_IOC_GETFLAGS value. These could be translated to BSD's st_flags. Note that the Linux IOC flags are a mess and filesystems such as Ext4 define flags that aren't in linux/fs.h, so translation in the kernel may be a necessity (or, possibly, we provide the filesystem type too). (Some attributes are made available in stx_attributes, but the general feeling was that the IOC flags were to ext[234]-specific and shouldn't be exposed through statx this way). (15) Mask of features available on file (eg: ACLs, seclabel) [Brad Boyer, Michael Kerrisk]. (Deferred, probably to fsinfo. Finding out if there's an ACL or seclabal might require extra filesystem operations). (16) Femtosecond-resolution timestamps [Dave Chinner]. (A __reserved field has been left in the statx_timestamp struct for this - if there proves to be a need). (17) A set multiple attributes syscall to go with this. =============== NEW SYSTEM CALL =============== The new system call is: int ret = statx(int dfd, const char *filename, unsigned int flags, unsigned int mask, struct statx *buffer); The dfd, filename and flags parameters indicate the file to query, in a similar way to fstatat(). There is no equivalent of lstat() as that can be emulated with statx() by passing AT_SYMLINK_NOFOLLOW in flags. There is also no equivalent of fstat() as that can be emulated by passing a NULL filename to statx() with the fd of interest in dfd. Whether or not statx() synchronises the attributes with the backing store can be controlled by OR'ing a value into the flags argument (this typically only affects network filesystems): (1) AT_STATX_SYNC_AS_STAT tells statx() to behave as stat() does in this respect. (2) AT_STATX_FORCE_SYNC will require a network filesystem to synchronise its attributes with the server - which might require data writeback to occur to get the timestamps correct. (3) AT_STATX_DONT_SYNC will suppress synchronisation with the server in a network filesystem. The resulting values should be considered approximate. mask is a bitmask indicating the fields in struct statx that are of interest to the caller. The user should set this to STATX_BASIC_STATS to get the basic set returned by stat(). It should be noted that asking for more information may entail extra I/O operations. buffer points to the destination for the data. This must be 256 bytes in size. ====================== MAIN ATTRIBUTES RECORD ====================== The following structures are defined in which to return the main attribute set: struct statx_timestamp { __s64 tv_sec; __s32 tv_nsec; __s32 __reserved; }; struct statx { __u32 stx_mask; __u32 stx_blksize; __u64 stx_attributes; __u32 stx_nlink; __u32 stx_uid; __u32 stx_gid; __u16 stx_mode; __u16 __spare0[1]; __u64 stx_ino; __u64 stx_size; __u64 stx_blocks; __u64 __spare1[1]; struct statx_timestamp stx_atime; struct statx_timestamp stx_btime; struct statx_timestamp stx_ctime; struct statx_timestamp stx_mtime; __u32 stx_rdev_major; __u32 stx_rdev_minor; __u32 stx_dev_major; __u32 stx_dev_minor; __u64 __spare2[14]; }; The defined bits in request_mask and stx_mask are: STATX_TYPE Want/got stx_mode & S_IFMT STATX_MODE Want/got stx_mode & ~S_IFMT STATX_NLINK Want/got stx_nlink STATX_UID Want/got stx_uid STATX_GID Want/got stx_gid STATX_ATIME Want/got stx_atime{,_ns} STATX_MTIME Want/got stx_mtime{,_ns} STATX_CTIME Want/got stx_ctime{,_ns} STATX_INO Want/got stx_ino STATX_SIZE Want/got stx_size STATX_BLOCKS Want/got stx_blocks STATX_BASIC_STATS [The stuff in the normal stat struct] STATX_BTIME Want/got stx_btime{,_ns} STATX_ALL [All currently available stuff] stx_btime is the file creation time, stx_mask is a bitmask indicating the data provided and __spares*[] are where as-yet undefined fields can be placed. Time fields are structures with separate seconds and nanoseconds fields plus a reserved field in case we want to add even finer resolution. Note that times will be negative if before 1970; in such a case, the nanosecond fields will also be negative if not zero. The bits defined in the stx_attributes field convey information about a file, how it is accessed, where it is and what it does. The following attributes map to FS_*_FL flags and are the same numerical value: STATX_ATTR_COMPRESSED File is compressed by the fs STATX_ATTR_IMMUTABLE File is marked immutable STATX_ATTR_APPEND File is append-only STATX_ATTR_NODUMP File is not to be dumped STATX_ATTR_ENCRYPTED File requires key to decrypt in fs Within the kernel, the supported flags are listed by: KSTAT_ATTR_FS_IOC_FLAGS [Are any other IOC flags of sufficient general interest to be exposed through this interface?] New flags include: STATX_ATTR_AUTOMOUNT Object is an automount trigger These are for the use of GUI tools that might want to mark files specially, depending on what they are. Fields in struct statx come in a number of classes: (0) stx_dev_*, stx_blksize. These are local system information and are always available. (1) stx_mode, stx_nlinks, stx_uid, stx_gid, stx_[amc]time, stx_ino, stx_size, stx_blocks. These will be returned whether the caller asks for them or not. The corresponding bits in stx_mask will be set to indicate whether they actually have valid values. If the caller didn't ask for them, then they may be approximated. For example, NFS won't waste any time updating them from the server, unless as a byproduct of updating something requested. If the values don't actually exist for the underlying object (such as UID or GID on a DOS file), then the bit won't be set in the stx_mask, even if the caller asked for the value. In such a case, the returned value will be a fabrication. Note that there are instances where the type might not be valid, for instance Windows reparse points. (2) stx_rdev_*. This will be set only if stx_mode indicates we're looking at a blockdev or a chardev, otherwise will be 0. (3) stx_btime. Similar to (1), except this will be set to 0 if it doesn't exist. ======= TESTING ======= The following test program can be used to test the statx system call: samples/statx/test-statx.c Just compile and run, passing it paths to the files you want to examine. The file is built automatically if CONFIG_SAMPLES is enabled. Here's some example output. Firstly, an NFS directory that crosses to another FSID. Note that the AUTOMOUNT attribute is set because transiting this directory will cause d_automount to be invoked by the VFS. [root@andromeda ~]# /tmp/test-statx -A /warthog/data statx(/warthog/data) = 0 results=7ff Size: 4096 Blocks: 8 IO Block: 1048576 directory Device: 00:26 Inode: 1703937 Links: 125 Access: (3777/drwxrwxrwx) Uid: 0 Gid: 4041 Access: 2016-11-24 09:02:12.219699527+0000 Modify: 2016-11-17 10:44:36.225653653+0000 Change: 2016-11-17 10:44:36.225653653+0000 Attributes: 0000000000001000 (-------- -------- -------- -------- -------- -------- ---m---- --------) Secondly, the result of automounting on that directory. [root@andromeda ~]# /tmp/test-statx /warthog/data statx(/warthog/data) = 0 results=7ff Size: 4096 Blocks: 8 IO Block: 1048576 directory Device: 00:27 Inode: 2 Links: 125 Access: (3777/drwxrwxrwx) Uid: 0 Gid: 4041 Access: 2016-11-24 09:02:12.219699527+0000 Modify: 2016-11-17 10:44:36.225653653+0000 Change: 2016-11-17 10:44:36.225653653+0000 Signed-off-by: David Howells <dhowells@redhat.com> Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
2017-02-01 00:46:22 +08:00
extern int nfs_getattr(const struct path *, struct kstat *, u32, unsigned int);
extern void nfs_access_add_cache(struct inode *, struct nfs_access_entry *);
extern void nfs_access_set_mask(struct nfs_access_entry *, u32);
extern int nfs_permission(struct inode *, int);
extern int nfs_open(struct inode *, struct file *);
extern int nfs_attribute_cache_expired(struct inode *inode);
extern int nfs_revalidate_inode(struct nfs_server *server, struct inode *inode);
extern int __nfs_revalidate_inode(struct nfs_server *, struct inode *);
extern bool nfs_mapping_need_revalidate_inode(struct inode *inode);
extern int nfs_revalidate_mapping(struct inode *inode, struct address_space *mapping);
extern int nfs_revalidate_mapping_rcu(struct inode *inode);
extern int nfs_setattr(struct dentry *, struct iattr *);
extern void nfs_setattr_update_inode(struct inode *inode, struct iattr *attr, struct nfs_fattr *);
extern void nfs_setsecurity(struct inode *inode, struct nfs_fattr *fattr,
struct nfs4_label *label);
extern struct nfs_open_context *get_nfs_open_context(struct nfs_open_context *ctx);
extern void put_nfs_open_context(struct nfs_open_context *ctx);
extern struct nfs_open_context *nfs_find_open_context(struct inode *inode, struct rpc_cred *cred, fmode_t mode);
2016-10-13 12:26:47 +08:00
extern struct nfs_open_context *alloc_nfs_open_context(struct dentry *dentry, fmode_t f_mode, struct file *filp);
extern void nfs_inode_attach_open_context(struct nfs_open_context *ctx);
extern void nfs_file_set_open_context(struct file *filp, struct nfs_open_context *ctx);
extern void nfs_file_clear_open_context(struct file *flip);
extern struct nfs_lock_context *nfs_get_lock_context(struct nfs_open_context *ctx);
extern void nfs_put_lock_context(struct nfs_lock_context *l_ctx);
extern u64 nfs_compat_user_ino64(u64 fileid);
extern void nfs_fattr_init(struct nfs_fattr *fattr);
extern void nfs_fattr_set_barrier(struct nfs_fattr *fattr);
extern unsigned long nfs_inc_attr_generation_counter(void);
extern struct nfs_fattr *nfs_alloc_fattr(void);
static inline void nfs_free_fattr(const struct nfs_fattr *fattr)
{
kfree(fattr);
}
extern struct nfs_fh *nfs_alloc_fhandle(void);
static inline void nfs_free_fhandle(const struct nfs_fh *fh)
{
kfree(fh);
}
#ifdef NFS_DEBUG
extern u32 _nfs_display_fhandle_hash(const struct nfs_fh *fh);
static inline u32 nfs_display_fhandle_hash(const struct nfs_fh *fh)
{
return _nfs_display_fhandle_hash(fh);
}
extern void _nfs_display_fhandle(const struct nfs_fh *fh, const char *caption);
#define nfs_display_fhandle(fh, caption) \
do { \
if (unlikely(nfs_debug & NFSDBG_FACILITY)) \
_nfs_display_fhandle(fh, caption); \
} while (0)
#else
static inline u32 nfs_display_fhandle_hash(const struct nfs_fh *fh)
{
return 0;
}
static inline void nfs_display_fhandle(const struct nfs_fh *fh,
const char *caption)
{
}
#endif
/*
* linux/fs/nfs/nfsroot.c
*/
extern int nfs_root_data(char **root_device, char **root_data); /*__init*/
/* linux/net/ipv4/ipconfig.c: trims ip addr off front of name, too. */
extern __be32 root_nfs_parse_addr(char *name); /*__init*/
/*
* linux/fs/nfs/file.c
*/
extern const struct file_operations nfs_file_operations;
#if IS_ENABLED(CONFIG_NFS_V4)
extern const struct file_operations nfs4_file_operations;
#endif /* CONFIG_NFS_V4 */
extern const struct address_space_operations nfs_file_aops;
extern const struct address_space_operations nfs_dir_aops;
static inline struct nfs_open_context *nfs_file_open_context(struct file *filp)
{
return filp->private_data;
}
static inline struct rpc_cred *nfs_file_cred(struct file *file)
{
if (file != NULL) {
struct nfs_open_context *ctx =
nfs_file_open_context(file);
if (ctx)
return ctx->cred;
}
return NULL;
}
/*
* linux/fs/nfs/direct.c
*/
extern ssize_t nfs_direct_IO(struct kiocb *, struct iov_iter *);
extern ssize_t nfs_file_direct_read(struct kiocb *iocb,
struct iov_iter *iter);
extern ssize_t nfs_file_direct_write(struct kiocb *iocb,
struct iov_iter *iter);
/*
* linux/fs/nfs/dir.c
*/
extern const struct file_operations nfs_dir_operations;
extern const struct dentry_operations nfs_dentry_operations;
extern void nfs_force_lookup_revalidate(struct inode *dir);
extern int nfs_instantiate(struct dentry *dentry, struct nfs_fh *fh,
struct nfs_fattr *fattr, struct nfs4_label *label);
extern int nfs_may_open(struct inode *inode, struct rpc_cred *cred, int openflags);
extern void nfs_access_zap_cache(struct inode *inode);
/*
* linux/fs/nfs/symlink.c
*/
extern const struct inode_operations nfs_symlink_inode_operations;
/*
* linux/fs/nfs/sysctl.c
*/
#ifdef CONFIG_SYSCTL
extern int nfs_register_sysctl(void);
extern void nfs_unregister_sysctl(void);
#else
#define nfs_register_sysctl() 0
#define nfs_unregister_sysctl() do { } while(0)
#endif
/*
* linux/fs/nfs/namespace.c
*/
extern const struct inode_operations nfs_mountpoint_inode_operations;
extern const struct inode_operations nfs_referral_inode_operations;
extern int nfs_mountpoint_expiry_timeout;
extern void nfs_release_automount_timer(void);
/*
* linux/fs/nfs/unlink.c
*/
extern void nfs_complete_unlink(struct dentry *dentry, struct inode *);
/*
* linux/fs/nfs/write.c
*/
extern int nfs_congestion_kb;
extern int nfs_writepage(struct page *page, struct writeback_control *wbc);
extern int nfs_writepages(struct address_space *, struct writeback_control *);
extern int nfs_flush_incompatible(struct file *file, struct page *page);
extern int nfs_updatepage(struct file *, struct page *, unsigned int, unsigned int);
/*
* Try to write back everything synchronously (but check the
* return value!)
*/
extern int nfs_sync_inode(struct inode *inode);
extern int nfs_wb_all(struct inode *inode);
extern int nfs_wb_page(struct inode *inode, struct page *page);
extern int nfs_wb_page_cancel(struct inode *inode, struct page* page);
extern int nfs_commit_inode(struct inode *, int);
NFS: fix usage of mempools. When passed GFP flags that allow sleeping (such as GFP_NOIO), mempool_alloc() will never return NULL, it will wait until memory is available. This means that we don't need to handle failure, but that we do need to ensure one thread doesn't call mempool_alloc() twice on the one pool without queuing or freeing the first allocation. If multiple threads did this during times of high memory pressure, the pool could be exhausted and a deadlock could result. pnfs_generic_alloc_ds_commits() attempts to allocate from the nfs_commit_mempool while already holding an allocation from that pool. This is not safe. So change nfs_commitdata_alloc() to take a flag that indicates whether failure is acceptable. In pnfs_generic_alloc_ds_commits(), accept failure and handle it as we currently do. Else where, do not accept failure, and do not handle it. Even when failure is acceptable, we want to succeed if possible. That means both - using an entry from the pool if there is one - waiting for direct reclaim is there isn't. We call mempool_alloc(GFP_NOWAIT) to achieve the first, then kmem_cache_alloc(GFP_NOIO|__GFP_NORETRY) to achieve the second. Each of these can fail, but together they do the best they can without blocking indefinitely. The objects returned by kmem_cache_alloc() will still be freed by mempool_free(). This is safe as mempool_alloc() uses exactly the same function to allocate objects (since the mempool was created with mempool_create_slab_pool()). The object returned by mempool_alloc() and kmem_cache_alloc() are indistinguishable so mempool_free() will handle both identically, either adding to the pool or calling kmem_cache_free(). Also, don't test for failure when allocating from nfs_wdata_mempool. Signed-off-by: NeilBrown <neilb@suse.com> Signed-off-by: Trond Myklebust <trond.myklebust@primarydata.com>
2017-04-10 10:22:09 +08:00
extern struct nfs_commit_data *nfs_commitdata_alloc(bool never_fail);
extern void nfs_commit_free(struct nfs_commit_data *data);
static inline int
nfs_have_writebacks(struct inode *inode)
{
return NFS_I(inode)->nrequests != 0;
}
/*
* linux/fs/nfs/read.c
*/
extern int nfs_readpage(struct file *, struct page *);
extern int nfs_readpages(struct file *, struct address_space *,
struct list_head *, unsigned);
extern int nfs_readpage_async(struct nfs_open_context *, struct inode *,
struct page *);
/*
* inline functions
*/
static inline loff_t nfs_size_to_loff_t(__u64 size)
{
return min_t(u64, size, OFFSET_MAX);
}
static inline ino_t
nfs_fileid_to_ino_t(u64 fileid)
{
ino_t ino = (ino_t) fileid;
if (sizeof(ino_t) < sizeof(u64))
ino ^= fileid >> (sizeof(u64)-sizeof(ino_t)) * 8;
return ino;
}
#define NFS_JUKEBOX_RETRY_TIME (5 * HZ)
# undef ifdebug
# ifdef NFS_DEBUG
# define ifdebug(fac) if (unlikely(nfs_debug & NFSDBG_##fac))
# define NFS_IFDEBUG(x) x
# else
# define ifdebug(fac) if (0)
# define NFS_IFDEBUG(x)
# endif
#endif