Skip to content

cloud-kernel
cloud-kernel

openanolis / cloud-kernel
1 年多 前同步成功

通知 161
Star 36
Fork 7
cloud-kernel
cloud-kernel
切换分支/标签
  1. 26 7月, 2018 4 次提交
  3. 06 6月, 2018 1 次提交
    • D
      vfs: change inode times to use struct timespec64 · 95582b00
      由 Deepa Dinamani 提交于 
      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: NDeepa 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>
      95582b00
  5. 31 5月, 2018 3 次提交
  7. 23 3月, 2018 1 次提交
    • M
      fuse: define the filesystem as untrusted · 0834136a
      由 Mimi Zohar 提交于 
      Files on FUSE can change at any point in time without IMA being able
to detect it.  The file data read for the file signature verification
could be totally different from what is subsequently read, making the
signature verification useless.

FUSE can be mounted by unprivileged users either today with fusermount
installed with setuid, or soon with the upcoming patches to allow FUSE
mounts in a non-init user namespace.

This patch sets the SB_I_IMA_UNVERIFIABLE_SIGNATURE flag and when
appropriate sets the SB_I_UNTRUSTED_MOUNTER flag.
Signed-off-by: NMimi Zohar <zohar@linux.vnet.ibm.com>
Cc: Miklos Szeredi <miklos@szeredi.hu>
Cc: Seth Forshee <seth.forshee@canonical.com>
Cc: Dongsu Park <dongsu@kinvolk.io>
Cc: Alban Crequy <alban@kinvolk.io>
Acked-by: NSerge Hallyn <serge@hallyn.com>
Acked-by: N"Eric W. Biederman" <ebiederm@xmission.com>
      0834136a
  9. 21 3月, 2018 2 次提交
    • E
      fuse: Support fuse filesystems outside of init_user_ns · 8cb08329
      由 Eric W. Biederman 提交于 
      In order to support mounts from namespaces other than init_user_ns, fuse
must translate uids and gids to/from the userns of the process servicing
requests on /dev/fuse. This patch does that, with a couple of restrictions
on the namespace:

 - The userns for the fuse connection is fixed to the namespace
   from which /dev/fuse is opened.

 - The namespace must be the same as s_user_ns.

These restrictions simplify the implementation by avoiding the need to pass
around userns references and by allowing fuse to rely on the checks in
setattr_prepare for ownership changes.  Either restriction could be relaxed
in the future if needed.

For cuse the userns used is the opener of /dev/cuse.  Semantically the cuse
support does not appear safe for unprivileged users.  Practically the
permissions on /dev/cuse only make it accessible to the global root user.
If something slips through the cracks in a user namespace the only users
who will be able to use the cuse device are those users mapped into the
user namespace.

Translation in the posix acl is updated to use the uuser namespace of the
filesystem.  Avoiding cases which might bypass this translation is handled
in a following change.

This change is stronlgy based on a similar change from Seth Forshee and
Dongsu Park.

Cc: Seth Forshee <seth.forshee@canonical.com>
Cc: Dongsu Park <dongsu@kinvolk.io>
Signed-off-by: NEric W. Biederman <ebiederm@xmission.com>
Signed-off-by: NMiklos Szeredi <mszeredi@redhat.com>
      8cb08329
    • S
      fuse: return -ECONNABORTED on /dev/fuse read after abort · 3b7008b2
      由 Szymon Lukasz 提交于 
      Currently the userspace has no way of knowing whether the fuse
connection ended because of umount or abort via sysfs. It makes it hard
for filesystems to free the mountpoint after abort without worrying
about removing some new mount.

The patch fixes it by returning different errors when userspace reads
from /dev/fuse (-ENODEV for umount and -ECONNABORTED for abort).

Add a new capability flag FUSE_ABORT_ERROR. If set and the connection is
gone because of sysfs abort, reading from the device will return
-ECONNABORTED.
Signed-off-by: NSzymon Lukasz <noh4hss@gmail.com>
Signed-off-by: NMiklos Szeredi <mszeredi@redhat.com>
      3b7008b2
  11. 28 11月, 2017 1 次提交
    • L
      Rename superblock flags (MS_xyz -> SB_xyz) · 1751e8a6
      由 Linus Torvalds 提交于 
      This is a pure automated search-and-replace of the internal kernel
superblock flags.

The s_flags are now called SB_*, with the names and the values for the
moment mirroring the MS_* flags that they're equivalent to.

Note how the MS_xyz flags are the ones passed to the mount system call,
while the SB_xyz flags are what we then use in sb->s_flags.

The script to do this was:

    # places to look in; re security/*: it generally should *not* be
    # touched (that stuff parses mount(2) arguments directly), but
    # there are two places where we really deal with superblock flags.
    FILES="drivers/mtd drivers/staging/lustre fs ipc mm \
            include/linux/fs.h include/uapi/linux/bfs_fs.h \
            security/apparmor/apparmorfs.c security/apparmor/include/lib.h"
    # the list of MS_... constants
    SYMS="RDONLY NOSUID NODEV NOEXEC SYNCHRONOUS REMOUNT MANDLOCK \
          DIRSYNC NOATIME NODIRATIME BIND MOVE REC VERBOSE SILENT \
          POSIXACL UNBINDABLE PRIVATE SLAVE SHARED RELATIME KERNMOUNT \
          I_VERSION STRICTATIME LAZYTIME SUBMOUNT NOREMOTELOCK NOSEC BORN \
          ACTIVE NOUSER"

    SED_PROG=
    for i in $SYMS; do SED_PROG="$SED_PROG -e s/MS_$i/SB_$i/g"; done

    # we want files that contain at least one of MS_...,
    # with fs/namespace.c and fs/pnode.c excluded.
    L=$(for i in $SYMS; do git grep -w -l MS_$i $FILES; done| sort|uniq|grep -v '^fs/namespace.c'|grep -v '^fs/pnode.c')

    for f in $L; do sed -i $f $SED_PROG; done
Requested-by: NAl Viro <viro@zeniv.linux.org.uk>
Signed-off-by: NLinus Torvalds <torvalds@linux-foundation.org>
      1751e8a6
  13. 16 11月, 2017 1 次提交
  15. 31 10月, 2017 1 次提交
    • K
      treewide: Fix function prototypes for module_param_call() · e4dca7b7
      由 Kees Cook 提交于 
      Several function prototypes for the set/get functions defined by
module_param_call() have a slightly wrong argument types. This fixes
those in an effort to clean up the calls when running under type-enforced
compiler instrumentation for CFI. This is the result of running the
following semantic patch:

@match_module_param_call_function@
declarer name module_param_call;
identifier _name, _set_func, _get_func;
expression _arg, _mode;
@@

 module_param_call(_name, _set_func, _get_func, _arg, _mode);

@fix_set_prototype
 depends on match_module_param_call_function@
identifier match_module_param_call_function._set_func;
identifier _val, _param;
type _val_type, _param_type;
@@

 int _set_func(
-_val_type _val
+const char * _val
 ,
-_param_type _param
+const struct kernel_param * _param
 ) { ... }

@fix_get_prototype
 depends on match_module_param_call_function@
identifier match_module_param_call_function._get_func;
identifier _val, _param;
type _val_type, _param_type;
@@

 int _get_func(
-_val_type _val
+char * _val
 ,
-_param_type _param
+const struct kernel_param * _param
 ) { ... }

Two additional by-hand changes are included for places where the above
Coccinelle script didn't notice them:

	drivers/platform/x86/thinkpad_acpi.c
	fs/lockd/svc.c
Signed-off-by: NKees Cook <keescook@chromium.org>
Signed-off-by: NJessica Yu <jeyu@kernel.org>
      e4dca7b7
  17. 19 10月, 2017 1 次提交
  19. 17 5月, 2017 1 次提交
  21. 21 4月, 2017 2 次提交
  23. 18 4月, 2017 2 次提交
  25. 18 10月, 2016 1 次提交
  27. 01 10月, 2016 4 次提交
  29. 31 7月, 2016 1 次提交
  31. 29 7月, 2016 1 次提交
  33. 30 6月, 2016 1 次提交
  35. 05 4月, 2016 1 次提交
    • K
      mm, fs: get rid of PAGE_CACHE_* and page_cache_{get,release} macros · 09cbfeaf
      由 Kirill A. Shutemov 提交于 
      PAGE_CACHE_{SIZE,SHIFT,MASK,ALIGN} macros were introduced *long* time
ago with promise that one day it will be possible to implement page
cache with bigger chunks than PAGE_SIZE.

This promise never materialized.  And unlikely will.

We have many places where PAGE_CACHE_SIZE assumed to be equal to
PAGE_SIZE.  And it's constant source of confusion on whether
PAGE_CACHE_* or PAGE_* constant should be used in a particular case,
especially on the border between fs and mm.

Global switching to PAGE_CACHE_SIZE != PAGE_SIZE would cause to much
breakage to be doable.

Let's stop pretending that pages in page cache are special.  They are
not.

The changes are pretty straight-forward:

 - <foo> << (PAGE_CACHE_SHIFT - PAGE_SHIFT) -> <foo>;

 - <foo> >> (PAGE_CACHE_SHIFT - PAGE_SHIFT) -> <foo>;

 - PAGE_CACHE_{SIZE,SHIFT,MASK,ALIGN} -> PAGE_{SIZE,SHIFT,MASK,ALIGN};

 - page_cache_get() -> get_page();

 - page_cache_release() -> put_page();

This patch contains automated changes generated with coccinelle using
script below.  For some reason, coccinelle doesn't patch header files.
I've called spatch for them manually.

The only adjustment after coccinelle is revert of changes to
PAGE_CAHCE_ALIGN definition: we are going to drop it later.

There are few places in the code where coccinelle didn't reach.  I'll
fix them manually in a separate patch.  Comments and documentation also
will be addressed with the separate patch.

virtual patch

@@
expression E;
@@
- E << (PAGE_CACHE_SHIFT - PAGE_SHIFT)
+ E

@@
expression E;
@@
- E >> (PAGE_CACHE_SHIFT - PAGE_SHIFT)
+ E

@@
@@
- PAGE_CACHE_SHIFT
+ PAGE_SHIFT

@@
@@
- PAGE_CACHE_SIZE
+ PAGE_SIZE

@@
@@
- PAGE_CACHE_MASK
+ PAGE_MASK

@@
expression E;
@@
- PAGE_CACHE_ALIGN(E)
+ PAGE_ALIGN(E)

@@
expression E;
@@
- page_cache_get(E)
+ get_page(E)

@@
expression E;
@@
- page_cache_release(E)
+ put_page(E)
Signed-off-by: NKirill A. Shutemov <kirill.shutemov@linux.intel.com>
Acked-by: NMichal Hocko <mhocko@suse.com>
Signed-off-by: NLinus Torvalds <torvalds@linux-foundation.org>
      09cbfeaf
  37. 15 1月, 2016 1 次提交
    • V
      kmemcg: account certain kmem allocations to memcg · 5d097056
      由 Vladimir Davydov 提交于 
      Mark those kmem allocations that are known to be easily triggered from
userspace as __GFP_ACCOUNT/SLAB_ACCOUNT, which makes them accounted to
memcg.  For the list, see below:

 - threadinfo
 - task_struct
 - task_delay_info
 - pid
 - cred
 - mm_struct
 - vm_area_struct and vm_region (nommu)
 - anon_vma and anon_vma_chain
 - signal_struct
 - sighand_struct
 - fs_struct
 - files_struct
 - fdtable and fdtable->full_fds_bits
 - dentry and external_name
 - inode for all filesystems. This is the most tedious part, because
   most filesystems overwrite the alloc_inode method.

The list is far from complete, so feel free to add more objects.
Nevertheless, it should be close to "account everything" approach and
keep most workloads within bounds.  Malevolent users will be able to
breach the limit, but this was possible even with the former "account
everything" approach (simply because it did not account everything in
fact).

[akpm@linux-foundation.org: coding-style fixes]
Signed-off-by: NVladimir Davydov <vdavydov@virtuozzo.com>
Acked-by: NJohannes Weiner <hannes@cmpxchg.org>
Acked-by: NMichal Hocko <mhocko@suse.com>
Cc: Tejun Heo <tj@kernel.org>
Cc: Greg Thelen <gthelen@google.com>
Cc: Christoph Lameter <cl@linux.com>
Cc: Pekka Enberg <penberg@kernel.org>
Cc: David Rientjes <rientjes@google.com>
Cc: Joonsoo Kim <iamjoonsoo.kim@lge.com>
Signed-off-by: NAndrew Morton <akpm@linux-foundation.org>
Signed-off-by: NLinus Torvalds <torvalds@linux-foundation.org>
      5d097056
  39. 01 7月, 2015 10 次提交