mirror of
https://mirrors.bfsu.edu.cn/git/linux.git
synced 2024-11-16 16:54:20 +08:00
e4b3448bc3
21 Commits
| Author | SHA1 | Message | Date | |
|---|---|---|---|---|
Deepa Dinamani
|
95582b0083 |
vfs: change inode times to use struct timespec64
struct timespec is not y2038 safe. Transition vfs to use
y2038 safe struct timespec64 instead.
The change was made with the help of the following cocinelle
script. This catches about 80% of the changes.
All the header file and logic changes are included in the
first 5 rules. The rest are trivial substitutions.
I avoid changing any of the function signatures or any other
filesystem specific data structures to keep the patch simple
for review.
The script can be a little shorter by combining different cases.
But, this version was sufficient for my usecase.
virtual patch
@ depends on patch @
identifier now;
@@
- struct timespec
+ struct timespec64
current_time ( ... )
{
- struct timespec now = current_kernel_time();
+ struct timespec64 now = current_kernel_time64();
...
- return timespec_trunc(
+ return timespec64_trunc(
... );
}
@ depends on patch @
identifier xtime;
@@
struct \( iattr \| inode \| kstat \) {
...
- struct timespec xtime;
+ struct timespec64 xtime;
...
}
@ depends on patch @
identifier t;
@@
struct inode_operations {
...
int (*update_time) (...,
- struct timespec t,
+ struct timespec64 t,
...);
...
}
@ depends on patch @
identifier t;
identifier fn_update_time =~ "update_time$";
@@
fn_update_time (...,
- struct timespec *t,
+ struct timespec64 *t,
...) { ... }
@ depends on patch @
identifier t;
@@
lease_get_mtime( ... ,
- struct timespec *t
+ struct timespec64 *t
) { ... }
@te depends on patch forall@
identifier ts;
local idexpression struct inode *inode_node;
identifier i_xtime =~ "^i_[acm]time$";
identifier ia_xtime =~ "^ia_[acm]time$";
identifier fn_update_time =~ "update_time$";
identifier fn;
expression e, E3;
local idexpression struct inode *node1;
local idexpression struct inode *node2;
local idexpression struct iattr *attr1;
local idexpression struct iattr *attr2;
local idexpression struct iattr attr;
identifier i_xtime1 =~ "^i_[acm]time$";
identifier i_xtime2 =~ "^i_[acm]time$";
identifier ia_xtime1 =~ "^ia_[acm]time$";
identifier ia_xtime2 =~ "^ia_[acm]time$";
@@
(
(
- struct timespec ts;
+ struct timespec64 ts;
|
- struct timespec ts = current_time(inode_node);
+ struct timespec64 ts = current_time(inode_node);
)
<+... when != ts
(
- timespec_equal(&inode_node->i_xtime, &ts)
+ timespec64_equal(&inode_node->i_xtime, &ts)
|
- timespec_equal(&ts, &inode_node->i_xtime)
+ timespec64_equal(&ts, &inode_node->i_xtime)
|
- timespec_compare(&inode_node->i_xtime, &ts)
+ timespec64_compare(&inode_node->i_xtime, &ts)
|
- timespec_compare(&ts, &inode_node->i_xtime)
+ timespec64_compare(&ts, &inode_node->i_xtime)
|
ts = current_time(e)
|
fn_update_time(..., &ts,...)
|
inode_node->i_xtime = ts
|
node1->i_xtime = ts
|
ts = inode_node->i_xtime
|
<+... attr1->ia_xtime ...+> = ts
|
ts = attr1->ia_xtime
|
ts.tv_sec
|
ts.tv_nsec
|
btrfs_set_stack_timespec_sec(..., ts.tv_sec)
|
btrfs_set_stack_timespec_nsec(..., ts.tv_nsec)
|
- ts = timespec64_to_timespec(
+ ts =
...
-)
|
- ts = ktime_to_timespec(
+ ts = ktime_to_timespec64(
...)
|
- ts = E3
+ ts = timespec_to_timespec64(E3)
|
- ktime_get_real_ts(&ts)
+ ktime_get_real_ts64(&ts)
|
fn(...,
- ts
+ timespec64_to_timespec(ts)
,...)
)
...+>
(
<... when != ts
- return ts;
+ return timespec64_to_timespec(ts);
...>
)
|
- timespec_equal(&node1->i_xtime1, &node2->i_xtime2)
+ timespec64_equal(&node1->i_xtime2, &node2->i_xtime2)
|
- timespec_equal(&node1->i_xtime1, &attr2->ia_xtime2)
+ timespec64_equal(&node1->i_xtime2, &attr2->ia_xtime2)
|
- timespec_compare(&node1->i_xtime1, &node2->i_xtime2)
+ timespec64_compare(&node1->i_xtime1, &node2->i_xtime2)
|
node1->i_xtime1 =
- timespec_trunc(attr1->ia_xtime1,
+ timespec64_trunc(attr1->ia_xtime1,
...)
|
- attr1->ia_xtime1 = timespec_trunc(attr2->ia_xtime2,
+ attr1->ia_xtime1 = timespec64_trunc(attr2->ia_xtime2,
...)
|
- ktime_get_real_ts(&attr1->ia_xtime1)
+ ktime_get_real_ts64(&attr1->ia_xtime1)
|
- ktime_get_real_ts(&attr.ia_xtime1)
+ ktime_get_real_ts64(&attr.ia_xtime1)
)
@ depends on patch @
struct inode *node;
struct iattr *attr;
identifier fn;
identifier i_xtime =~ "^i_[acm]time$";
identifier ia_xtime =~ "^ia_[acm]time$";
expression e;
@@
(
- fn(node->i_xtime);
+ fn(timespec64_to_timespec(node->i_xtime));
|
fn(...,
- node->i_xtime);
+ timespec64_to_timespec(node->i_xtime));
|
- e = fn(attr->ia_xtime);
+ e = fn(timespec64_to_timespec(attr->ia_xtime));
)
@ depends on patch forall @
struct inode *node;
struct iattr *attr;
identifier i_xtime =~ "^i_[acm]time$";
identifier ia_xtime =~ "^ia_[acm]time$";
identifier fn;
@@
{
+ struct timespec ts;
<+...
(
+ ts = timespec64_to_timespec(node->i_xtime);
fn (...,
- &node->i_xtime,
+ &ts,
...);
|
+ ts = timespec64_to_timespec(attr->ia_xtime);
fn (...,
- &attr->ia_xtime,
+ &ts,
...);
)
...+>
}
@ depends on patch forall @
struct inode *node;
struct iattr *attr;
struct kstat *stat;
identifier ia_xtime =~ "^ia_[acm]time$";
identifier i_xtime =~ "^i_[acm]time$";
identifier xtime =~ "^[acm]time$";
identifier fn, ret;
@@
{
+ struct timespec ts;
<+...
(
+ ts = timespec64_to_timespec(node->i_xtime);
ret = fn (...,
- &node->i_xtime,
+ &ts,
...);
|
+ ts = timespec64_to_timespec(node->i_xtime);
ret = fn (...,
- &node->i_xtime);
+ &ts);
|
+ ts = timespec64_to_timespec(attr->ia_xtime);
ret = fn (...,
- &attr->ia_xtime,
+ &ts,
...);
|
+ ts = timespec64_to_timespec(attr->ia_xtime);
ret = fn (...,
- &attr->ia_xtime);
+ &ts);
|
+ ts = timespec64_to_timespec(stat->xtime);
ret = fn (...,
- &stat->xtime);
+ &ts);
)
...+>
}
@ depends on patch @
struct inode *node;
struct inode *node2;
identifier i_xtime1 =~ "^i_[acm]time$";
identifier i_xtime2 =~ "^i_[acm]time$";
identifier i_xtime3 =~ "^i_[acm]time$";
struct iattr *attrp;
struct iattr *attrp2;
struct iattr attr ;
identifier ia_xtime1 =~ "^ia_[acm]time$";
identifier ia_xtime2 =~ "^ia_[acm]time$";
struct kstat *stat;
struct kstat stat1;
struct timespec64 ts;
identifier xtime =~ "^[acmb]time$";
expression e;
@@
(
( node->i_xtime2 \| attrp->ia_xtime2 \| attr.ia_xtime2 \) = node->i_xtime1 ;
|
node->i_xtime2 = \( node2->i_xtime1 \| timespec64_trunc(...) \);
|
node->i_xtime2 = node->i_xtime1 = node->i_xtime3 = \(ts \| current_time(...) \);
|
node->i_xtime1 = node->i_xtime3 = \(ts \| current_time(...) \);
|
stat->xtime = node2->i_xtime1;
|
stat1.xtime = node2->i_xtime1;
|
( node->i_xtime2 \| attrp->ia_xtime2 \) = attrp->ia_xtime1 ;
|
( attrp->ia_xtime1 \| attr.ia_xtime1 \) = attrp2->ia_xtime2;
|
- e = node->i_xtime1;
+ e = timespec64_to_timespec( node->i_xtime1 );
|
- e = attrp->ia_xtime1;
+ e = timespec64_to_timespec( attrp->ia_xtime1 );
|
node->i_xtime1 = current_time(...);
|
node->i_xtime2 = node->i_xtime1 = node->i_xtime3 =
- e;
+ timespec_to_timespec64(e);
|
node->i_xtime1 = node->i_xtime3 =
- e;
+ timespec_to_timespec64(e);
|
- node->i_xtime1 = e;
+ node->i_xtime1 = timespec_to_timespec64(e);
)
Signed-off-by: Deepa Dinamani <deepa.kernel@gmail.com>
Cc: <anton@tuxera.com>
Cc: <balbi@kernel.org>
Cc: <bfields@fieldses.org>
Cc: <darrick.wong@oracle.com>
Cc: <dhowells@redhat.com>
Cc: <dsterba@suse.com>
Cc: <dwmw2@infradead.org>
Cc: <hch@lst.de>
Cc: <hirofumi@mail.parknet.co.jp>
Cc: <hubcap@omnibond.com>
Cc: <jack@suse.com>
Cc: <jaegeuk@kernel.org>
Cc: <jaharkes@cs.cmu.edu>
Cc: <jslaby@suse.com>
Cc: <keescook@chromium.org>
Cc: <mark@fasheh.com>
Cc: <miklos@szeredi.hu>
Cc: <nico@linaro.org>
Cc: <reiserfs-devel@vger.kernel.org>
Cc: <richard@nod.at>
Cc: <sage@redhat.com>
Cc: <sfrench@samba.org>
Cc: <swhiteho@redhat.com>
Cc: <tj@kernel.org>
Cc: <trond.myklebust@primarydata.com>
Cc: <tytso@mit.edu>
Cc: <viro@zeniv.linux.org.uk>
|
||
David Howells
|
ee1235a9a0 |
fscache: Pass object size in rather than calling back for it
Pass the object size in to fscache_acquire_cookie() and fscache_write_page() rather than the netfs providing a callback by which it can be received. This makes it easier to update the size of the object when a new page is written that extends the object. The current object size is also passed by fscache to the check_aux function, obviating the need to store it in the aux data. Signed-off-by: David Howells <dhowells@redhat.com> Acked-by: Anna Schumaker <anna.schumaker@netapp.com> Tested-by: Steve Dickson <steved@redhat.com> |
||
|
David Howells
|
402cb8dda9 |
fscache: Attach the index key and aux data to the cookie
Attach copies of the index key and auxiliary data to the fscache cookie so
that:
(1) The callbacks to the netfs for this stuff can be eliminated. This
can simplify things in the cache as the information is still
available, even after the cache has relinquished the cookie.
(2) Simplifies the locking requirements of accessing the information as we
don't have to worry about the netfs object going away on us.
(3) The cache can do lazy updating of the coherency information on disk.
As long as the cache is flushed before reboot/poweroff, there's no
need to update the coherency info on disk every time it changes.
(4) Cookies can be hashed or put in a tree as the index key is easily
available. This allows:
(a) Checks for duplicate cookies can be made at the top fscache layer
rather than down in the bowels of the cache backend.
(b) Caching can be added to a netfs object that has a cookie if the
cache is brought online after the netfs object is allocated.
A certain amount of space is made in the cookie for inline copies of the
data, but if it won't fit there, extra memory will be allocated for it.
The downside of this is that live cache operation requires more memory.
Signed-off-by: David Howells <dhowells@redhat.com>
Acked-by: Anna Schumaker <anna.schumaker@netapp.com>
Tested-by: Steve Dickson <steved@redhat.com>
|
||
Li RongQing
|
e9f456ca50 |
nfs: define nfs_inc_fscache_stats and using it as possible
Define and use nfs_inc_fscache_stats when plus one, which can save to pass one parameter. Signed-off-by: Li RongQing <roy.qing.li@gmail.com> Signed-off-by: Trond Myklebust <trond.myklebust@primarydata.com> |
||
|
David Howells
|
f1fe29b4a0 |
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> |
||
|
David Howells
|
94d30ae90a |
FS-Cache: Provide the ability to enable/disable cookies
Provide the ability to enable and disable fscache cookies. A disabled cookie
will reject or ignore further requests to:
Acquire a child cookie
Invalidate and update backing objects
Check the consistency of a backing object
Allocate storage for backing page
Read backing pages
Write to backing pages
but still allows:
Checks/waits on the completion of already in-progress objects
Uncaching of pages
Relinquishment of cookies
Two new operations are provided:
(1) Disable a cookie:
void fscache_disable_cookie(struct fscache_cookie *cookie,
bool invalidate);
If the cookie is not already disabled, this locks the cookie against other
dis/enablement ops, marks the cookie as being disabled, discards or
invalidates any backing objects and waits for cessation of activity on any
associated object.
This is a wrapper around a chunk split out of fscache_relinquish_cookie(),
but it reinitialises the cookie such that it can be reenabled.
All possible failures are handled internally. The caller should consider
calling fscache_uncache_all_inode_pages() afterwards to make sure all page
markings are cleared up.
(2) Enable a cookie:
void fscache_enable_cookie(struct fscache_cookie *cookie,
bool (*can_enable)(void *data),
void *data)
If the cookie is not already enabled, this locks the cookie against other
dis/enablement ops, invokes can_enable() and, if the cookie is not an
index cookie, will begin the procedure of acquiring backing objects.
The optional can_enable() function is passed the data argument and returns
a ruling as to whether or not enablement should actually be permitted to
begin.
All possible failures are handled internally. The cookie will only be
marked as enabled if provisional backing objects are allocated.
A later patch will introduce these to NFS. Cookie enablement during nfs_open()
is then contingent on i_writecount <= 0. can_enable() checks for a race
between open(O_RDONLY) and open(O_WRONLY/O_RDWR). This simplifies NFS's cookie
handling and allows us to get rid of open(O_RDONLY) accidentally introducing
caching to an inode that's open for writing already.
One operation has its API modified:
(3) Acquire a cookie.
struct fscache_cookie *fscache_acquire_cookie(
struct fscache_cookie *parent,
const struct fscache_cookie_def *def,
void *netfs_data,
bool enable);
This now has an additional argument that indicates whether the requested
cookie should be enabled by default. It doesn't need the can_enable()
function because the caller must prevent multiple calls for the same netfs
object and it doesn't need to take the enablement lock because no one else
can get at the cookie before this returns.
Signed-off-by: David Howells <dhowells@redhat.com
|
||
|
David Howells
|
a4ff146881 |
NFS4: Open files for fscaching
nfs4_file_open() should open files for fscaching. Signed-off-by: David Howells <dhowells@redhat.com> |
||
Bryan Schumaker
|
2311b9439c |
NFS: Don't pass mount data to nfs_fscache_get_super_cookie()
I intend on creating a single nfs_fs_mount() function used by all our mount paths. To avoid checking between new mounts and clone mounts, I instead pass both structures to a new function in super.c that finds the cache key and then looks up the super cookie. Signed-off-by: Bryan Schumaker <bjschuma@netapp.com> Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com> |
||
Trond Myklebust
|
6f00866ddd |
NFS: Fix more NFS debug related build warnings
Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com> |
||
|
David Howells
|
c902ce1bfb |
FS-Cache: Add a helper to bulk uncache pages on an inode
Add an FS-Cache helper to bulk uncache pages on an inode. This will only work for the circumstance where the pages in the cache correspond 1:1 with the pages attached to an inode's page cache. This is required for CIFS and NFS: When disabling inode cookie, we were returning the cookie and setting cifsi->fscache to NULL but failed to invalidate any previously mapped pages. This resulted in "Bad page state" errors and manifested in other kind of errors when running fsstress. Fix it by uncaching mapped pages when we disable the inode cookie. This patch should fix the following oops and "Bad page state" errors seen during fsstress testing. ------------[ cut here ]------------ kernel BUG at fs/cachefiles/namei.c:201! invalid opcode: 0000 [#1] SMP Pid: 5, comm: kworker/u:0 Not tainted 2.6.38.7-30.fc15.x86_64 #1 Bochs Bochs RIP: 0010: cachefiles_walk_to_object+0x436/0x745 [cachefiles] RSP: 0018:ffff88002ce6dd00 EFLAGS: 00010282 RAX: ffff88002ef165f0 RBX: ffff88001811f500 RCX: 0000000000000000 RDX: 0000000000000000 RSI: 0000000000000100 RDI: 0000000000000282 RBP: ffff88002ce6dda0 R08: 0000000000000100 R09: ffffffff81b3a300 R10: 0000ffff00066c0a R11: 0000000000000003 R12: ffff88002ae54840 R13: ffff88002ae54840 R14: ffff880029c29c00 R15: ffff88001811f4b0 FS: 00007f394dd32720(0000) GS:ffff88002ef00000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 000000008005003b CR2: 00007fffcb62ddf8 CR3: 000000001825f000 CR4: 00000000000006e0 DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 DR3: 0000000000000000 DR6: 00000000ffff0ff0 DR7: 0000000000000400 Process kworker/u:0 (pid: 5, threadinfo ffff88002ce6c000, task ffff88002ce55cc0) Stack: 0000000000000246 ffff88002ce55cc0 ffff88002ce6dd58 ffff88001815dc00 ffff8800185246c0 ffff88001811f618 ffff880029c29d18 ffff88001811f380 ffff88002ce6dd50 ffffffff814757e4 ffff88002ce6dda0 ffffffff8106ac56 Call Trace: cachefiles_lookup_object+0x78/0xd4 [cachefiles] fscache_lookup_object+0x131/0x16d [fscache] fscache_object_work_func+0x1bc/0x669 [fscache] process_one_work+0x186/0x298 worker_thread+0xda/0x15d kthread+0x84/0x8c kernel_thread_helper+0x4/0x10 RIP cachefiles_walk_to_object+0x436/0x745 [cachefiles] ---[ end trace 1d481c9af1804caa ]--- I tested the uncaching by the following means: (1) Create a big file on my NFS server (104857600 bytes). (2) Read the file into the cache with md5sum on the NFS client. Look in /proc/fs/fscache/stats: Pages : mrk=25601 unc=0 (3) Open the file for read/write ("bash 5<>/warthog/bigfile"). Look in proc again: Pages : mrk=25601 unc=25601 Reported-by: Jeff Layton <jlayton@redhat.com> Signed-off-by: David Howells <dhowells@redhat.com> Reviewed-and-Tested-by: Suresh Jayaraman <sjayaraman@suse.de> cc: stable@kernel.org Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org> |
||
Chuck Lever
|
0f15c53d5b |
NFS: Squelch compiler warning
Seen with -Wextra: /home/cel/linux/fs/nfs/fscache.c: In function ‘__nfs_readpages_from_fscache’: /home/cel/linux/fs/nfs/fscache.c:479: warning: comparison between signed and unsigned integer expressions The comparison implicitly converts "int" to "unsigned", making it safe. But there's no need for the implicit type conversions here, and the dfprintk() already uses a "%u" formatter for "npages." Better to reduce confusion. Signed-off-by: Chuck Lever <chuck.lever@oracle.com> Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com> |
||
Tejun Heo
|
5a0e3ad6af |
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> |
||
|
Trond Myklebust
|
2c1740098c |
NFS: Fix a bug in nfs_fscache_release_page()
Not having an fscache cookie is perfectly valid if the user didn't mount with the fscache option. This patch fixes http://bugzilla.kernel.org/show_bug.cgi?id=15234 Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com> Acked-by: David Howells <dhowells@redhat.com> Cc: stable@kernel.org |
||
|
David Howells
|
201a15428b |
FS-Cache: Handle pages pending storage that get evicted under OOM conditions
Handle netfs pages that the vmscan algorithm wants to evict from the pagecache
under OOM conditions, but that are waiting for write to the cache. Under these
conditions, vmscan calls the releasepage() function of the netfs, asking if a
page can be discarded.
The problem is typified by the following trace of a stuck process:
kslowd005 D 0000000000000000 0 4253 2 0x00000080
ffff88001b14f370 0000000000000046 ffff880020d0d000 0000000000000007
0000000000000006 0000000000000001 ffff88001b14ffd8 ffff880020d0d2a8
000000000000ddf0 00000000000118c0 00000000000118c0 ffff880020d0d2a8
Call Trace:
[<ffffffffa00782d8>] __fscache_wait_on_page_write+0x8b/0xa7 [fscache]
[<ffffffff8104c0f1>] ? autoremove_wake_function+0x0/0x34
[<ffffffffa0078240>] ? __fscache_check_page_write+0x63/0x70 [fscache]
[<ffffffffa00b671d>] nfs_fscache_release_page+0x4e/0xc4 [nfs]
[<ffffffffa00927f0>] nfs_release_page+0x3c/0x41 [nfs]
[<ffffffff810885d3>] try_to_release_page+0x32/0x3b
[<ffffffff81093203>] shrink_page_list+0x316/0x4ac
[<ffffffff8109372b>] shrink_inactive_list+0x392/0x67c
[<ffffffff813532fa>] ? __mutex_unlock_slowpath+0x100/0x10b
[<ffffffff81058df0>] ? trace_hardirqs_on_caller+0x10c/0x130
[<ffffffff8135330e>] ? mutex_unlock+0x9/0xb
[<ffffffff81093aa2>] shrink_list+0x8d/0x8f
[<ffffffff81093d1c>] shrink_zone+0x278/0x33c
[<ffffffff81052d6c>] ? ktime_get_ts+0xad/0xba
[<ffffffff81094b13>] try_to_free_pages+0x22e/0x392
[<ffffffff81091e24>] ? isolate_pages_global+0x0/0x212
[<ffffffff8108e743>] __alloc_pages_nodemask+0x3dc/0x5cf
[<ffffffff81089529>] grab_cache_page_write_begin+0x65/0xaa
[<ffffffff8110f8c0>] ext3_write_begin+0x78/0x1eb
[<ffffffff81089ec5>] generic_file_buffered_write+0x109/0x28c
[<ffffffff8103cb69>] ? current_fs_time+0x22/0x29
[<ffffffff8108a509>] __generic_file_aio_write+0x350/0x385
[<ffffffff8108a588>] ? generic_file_aio_write+0x4a/0xae
[<ffffffff8108a59e>] generic_file_aio_write+0x60/0xae
[<ffffffff810b2e82>] do_sync_write+0xe3/0x120
[<ffffffff8104c0f1>] ? autoremove_wake_function+0x0/0x34
[<ffffffff810b18e1>] ? __dentry_open+0x1a5/0x2b8
[<ffffffff810b1a76>] ? dentry_open+0x82/0x89
[<ffffffffa00e693c>] cachefiles_write_page+0x298/0x335 [cachefiles]
[<ffffffffa0077147>] fscache_write_op+0x178/0x2c2 [fscache]
[<ffffffffa0075656>] fscache_op_execute+0x7a/0xd1 [fscache]
[<ffffffff81082093>] slow_work_execute+0x18f/0x2d1
[<ffffffff8108239a>] slow_work_thread+0x1c5/0x308
[<ffffffff8104c0f1>] ? autoremove_wake_function+0x0/0x34
[<ffffffff810821d5>] ? slow_work_thread+0x0/0x308
[<ffffffff8104be91>] kthread+0x7a/0x82
[<ffffffff8100beda>] child_rip+0xa/0x20
[<ffffffff8100b87c>] ? restore_args+0x0/0x30
[<ffffffff8102ef83>] ? tg_shares_up+0x171/0x227
[<ffffffff8104be17>] ? kthread+0x0/0x82
[<ffffffff8100bed0>] ? child_rip+0x0/0x20
In the above backtrace, the following is happening:
(1) A page storage operation is being executed by a slow-work thread
(fscache_write_op()).
(2) FS-Cache farms the operation out to the cache to perform
(cachefiles_write_page()).
(3) CacheFiles is then calling Ext3 to perform the actual write, using Ext3's
standard write (do_sync_write()) under KERNEL_DS directly from the netfs
page.
(4) However, for Ext3 to perform the write, it must allocate some memory, in
particular, it must allocate at least one page cache page into which it
can copy the data from the netfs page.
(5) Under OOM conditions, the memory allocator can't immediately come up with
a page, so it uses vmscan to find something to discard
(try_to_free_pages()).
(6) vmscan finds a clean netfs page it might be able to discard (possibly the
one it's trying to write out).
(7) The netfs is called to throw the page away (nfs_release_page()) - but it's
called with __GFP_WAIT, so the netfs decides to wait for the store to
complete (__fscache_wait_on_page_write()).
(8) This blocks a slow-work processing thread - possibly against itself.
The system ends up stuck because it can't write out any netfs pages to the
cache without allocating more memory.
To avoid this, we make FS-Cache cancel some writes that aren't in the middle of
actually being performed. This means that some data won't make it into the
cache this time. To support this, a new FS-Cache function is added
fscache_maybe_release_page() that replaces what the netfs releasepage()
functions used to do with respect to the cache.
The decisions fscache_maybe_release_page() makes are counted and displayed
through /proc/fs/fscache/stats on a line labelled "VmScan". There are four
counters provided: "nos=N" - pages that weren't pending storage; "gon=N" -
pages that were pending storage when we first looked, but weren't by the time
we got the object lock; "bsy=N" - pages that we ignored as they were actively
being written when we looked; and "can=N" - pages that we cancelled the storage
of.
What I'd really like to do is alter the behaviour of the cancellation
heuristics, depending on how necessary it is to expel pages. If there are
plenty of other pages that aren't waiting to be written to the cache that
could be ejected first, then it would be nice to hold up on immediate
cancellation of cache writes - but I don't see a way of doing that.
Signed-off-by: David Howells <dhowells@redhat.com>
|
||
|
David Howells
|
2df5480638 |
NFS: Propagate 'fsc' mount option through automounts
Propagate the NFS 'fsc' mount option through NFS automounts of various types.
This is now required as commit:
commit
|
||
|
David Howells
|
7f8e05f60c |
NFS: Store pages from an NFS inode into a local cache
Store pages from an NFS inode into the cache data storage object associated with that inode. Signed-off-by: David Howells <dhowells@redhat.com> Acked-by: Steve Dickson <steved@redhat.com> Acked-by: Trond Myklebust <Trond.Myklebust@netapp.com> Acked-by: Al Viro <viro@zeniv.linux.org.uk> Tested-by: Daire Byrne <Daire.Byrne@framestore.com> |
||
|
David Howells
|
9a9fc1c033 |
NFS: Read pages from FS-Cache into an NFS inode
Read pages from an FS-Cache data storage object representing an inode into an NFS inode. Signed-off-by: David Howells <dhowells@redhat.com> Acked-by: Steve Dickson <steved@redhat.com> Acked-by: Trond Myklebust <Trond.Myklebust@netapp.com> Acked-by: Al Viro <viro@zeniv.linux.org.uk> Tested-by: Daire Byrne <Daire.Byrne@framestore.com> |
||
|
David Howells
|
545db45f0f |
NFS: FS-Cache page management
FS-Cache page management for NFS. This includes hooking the releasing and invalidation of pages marked with PG_fscache (aka PG_private_2) and waiting for completion of the write-to-cache flag (PG_fscache_write aka PG_owner_priv_2). Signed-off-by: David Howells <dhowells@redhat.com> Acked-by: Steve Dickson <steved@redhat.com> Acked-by: Trond Myklebust <Trond.Myklebust@netapp.com> Acked-by: Al Viro <viro@zeniv.linux.org.uk> Tested-by: Daire Byrne <Daire.Byrne@framestore.com> |
||
|
David Howells
|
ef79c097bb |
NFS: Use local disk inode cache
Bind data storage objects in the local cache to NFS inodes. Signed-off-by: David Howells <dhowells@redhat.com> Acked-by: Steve Dickson <steved@redhat.com> Acked-by: Trond Myklebust <Trond.Myklebust@netapp.com> Acked-by: Al Viro <viro@zeniv.linux.org.uk> Tested-by: Daire Byrne <Daire.Byrne@framestore.com> |
||
|
David Howells
|
08734048b3 |
NFS: Define and create superblock-level objects
Define and create superblock-level cache index objects (as managed by
nfs_server structs).
Each superblock object is created in a server level index object and is itself
an index into which inode-level objects are inserted.
Ideally there would be one superblock-level object per server, and the former
would be folded into the latter; however, since the "nosharecache" option
exists this isn't possible.
The superblock object key is a sequence consisting of:
(1) Certain superblock s_flags.
(2) Various connection parameters that serve to distinguish superblocks for
sget().
(3) The volume FSID.
(4) The security flavour.
(5) The uniquifier length.
(6) The uniquifier text. This is normally an empty string, unless the fsc=xyz
mount option was used to explicitly specify a uniquifier.
The key blob is of variable length, depending on the length of (6).
The superblock object is given no coherency data to carry in the auxiliary data
permitted by the cache. It is assumed that the superblock is always coherent.
This patch also adds uniquification handling such that two otherwise identical
superblocks, at least one of which is marked "nosharecache", won't end up
trying to share the on-disk cache. It will be possible to manually provide a
uniquifier through a mount option with a later patch to avoid the error
otherwise produced.
Signed-off-by: David Howells <dhowells@redhat.com>
Acked-by: Steve Dickson <steved@redhat.com>
Acked-by: Trond Myklebust <Trond.Myklebust@netapp.com>
Acked-by: Al Viro <viro@zeniv.linux.org.uk>
Tested-by: Daire Byrne <Daire.Byrne@framestore.com>
|
||
|
David Howells
|
147272813e |
NFS: Define and create server-level objects
Define and create server-level cache index objects (as managed by nfs_client structs). Each server object is created in the NFS top-level index object and is itself an index into which superblock-level objects are inserted. Ideally there would be one superblock-level object per server, and the former would be folded into the latter; however, since the "nosharecache" option exists this isn't possible. The server object key is a sequence consisting of: (1) NFS version (2) Server address family (eg: AF_INET or AF_INET6) (3) Server port. (4) Server IP address. The key blob is of variable length, depending on the length of (4). The server object is given no coherency data to carry in the auxiliary data permitted by the cache. Signed-off-by: David Howells <dhowells@redhat.com> Acked-by: Steve Dickson <steved@redhat.com> Acked-by: Trond Myklebust <Trond.Myklebust@netapp.com> Acked-by: Al Viro <viro@zeniv.linux.org.uk> Tested-by: Daire Byrne <Daire.Byrne@framestore.com> |