Skip to content

K
Kernel

openeuler / Kernel
接近 2 年 前同步成功

通知 8
Star 0
Fork 0
K
Kernel
切换分支/标签
  1. 30 10月, 2018 3 次提交
  3. 03 10月, 2018 1 次提交
  5. 13 6月, 2018 1 次提交
    • K
      treewide: kzalloc() -> kcalloc() · 6396bb22
      由 Kees Cook 提交于 
      The kzalloc() function has a 2-factor argument form, kcalloc(). This
patch replaces cases of:

        kzalloc(a * b, gfp)

with:
        kcalloc(a * b, gfp)

as well as handling cases of:

        kzalloc(a * b * c, gfp)

with:

        kzalloc(array3_size(a, b, c), gfp)

as it's slightly less ugly than:

        kzalloc_array(array_size(a, b), c, gfp)

This does, however, attempt to ignore constant size factors like:

        kzalloc(4 * 1024, gfp)

though any constants defined via macros get caught up in the conversion.

Any factors with a sizeof() of "unsigned char", "char", and "u8" were
dropped, since they're redundant.

The Coccinelle script used for this was:

// Fix redundant parens around sizeof().
@@
type TYPE;
expression THING, E;
@@

(
  kzalloc(
-	(sizeof(TYPE)) * E
+	sizeof(TYPE) * E
  , ...)
|
  kzalloc(
-	(sizeof(THING)) * E
+	sizeof(THING) * E
  , ...)
)

// Drop single-byte sizes and redundant parens.
@@
expression COUNT;
typedef u8;
typedef __u8;
@@

(
  kzalloc(
-	sizeof(u8) * (COUNT)
+	COUNT
  , ...)
|
  kzalloc(
-	sizeof(__u8) * (COUNT)
+	COUNT
  , ...)
|
  kzalloc(
-	sizeof(char) * (COUNT)
+	COUNT
  , ...)
|
  kzalloc(
-	sizeof(unsigned char) * (COUNT)
+	COUNT
  , ...)
|
  kzalloc(
-	sizeof(u8) * COUNT
+	COUNT
  , ...)
|
  kzalloc(
-	sizeof(__u8) * COUNT
+	COUNT
  , ...)
|
  kzalloc(
-	sizeof(char) * COUNT
+	COUNT
  , ...)
|
  kzalloc(
-	sizeof(unsigned char) * COUNT
+	COUNT
  , ...)
)

// 2-factor product with sizeof(type/expression) and identifier or constant.
@@
type TYPE;
expression THING;
identifier COUNT_ID;
constant COUNT_CONST;
@@

(
- kzalloc
+ kcalloc
  (
-	sizeof(TYPE) * (COUNT_ID)
+	COUNT_ID, sizeof(TYPE)
  , ...)
|
- kzalloc
+ kcalloc
  (
-	sizeof(TYPE) * COUNT_ID
+	COUNT_ID, sizeof(TYPE)
  , ...)
|
- kzalloc
+ kcalloc
  (
-	sizeof(TYPE) * (COUNT_CONST)
+	COUNT_CONST, sizeof(TYPE)
  , ...)
|
- kzalloc
+ kcalloc
  (
-	sizeof(TYPE) * COUNT_CONST
+	COUNT_CONST, sizeof(TYPE)
  , ...)
|
- kzalloc
+ kcalloc
  (
-	sizeof(THING) * (COUNT_ID)
+	COUNT_ID, sizeof(THING)
  , ...)
|
- kzalloc
+ kcalloc
  (
-	sizeof(THING) * COUNT_ID
+	COUNT_ID, sizeof(THING)
  , ...)
|
- kzalloc
+ kcalloc
  (
-	sizeof(THING) * (COUNT_CONST)
+	COUNT_CONST, sizeof(THING)
  , ...)
|
- kzalloc
+ kcalloc
  (
-	sizeof(THING) * COUNT_CONST
+	COUNT_CONST, sizeof(THING)
  , ...)
)

// 2-factor product, only identifiers.
@@
identifier SIZE, COUNT;
@@

- kzalloc
+ kcalloc
  (
-	SIZE * COUNT
+	COUNT, SIZE
  , ...)

// 3-factor product with 1 sizeof(type) or sizeof(expression), with
// redundant parens removed.
@@
expression THING;
identifier STRIDE, COUNT;
type TYPE;
@@

(
  kzalloc(
-	sizeof(TYPE) * (COUNT) * (STRIDE)
+	array3_size(COUNT, STRIDE, sizeof(TYPE))
  , ...)
|
  kzalloc(
-	sizeof(TYPE) * (COUNT) * STRIDE
+	array3_size(COUNT, STRIDE, sizeof(TYPE))
  , ...)
|
  kzalloc(
-	sizeof(TYPE) * COUNT * (STRIDE)
+	array3_size(COUNT, STRIDE, sizeof(TYPE))
  , ...)
|
  kzalloc(
-	sizeof(TYPE) * COUNT * STRIDE
+	array3_size(COUNT, STRIDE, sizeof(TYPE))
  , ...)
|
  kzalloc(
-	sizeof(THING) * (COUNT) * (STRIDE)
+	array3_size(COUNT, STRIDE, sizeof(THING))
  , ...)
|
  kzalloc(
-	sizeof(THING) * (COUNT) * STRIDE
+	array3_size(COUNT, STRIDE, sizeof(THING))
  , ...)
|
  kzalloc(
-	sizeof(THING) * COUNT * (STRIDE)
+	array3_size(COUNT, STRIDE, sizeof(THING))
  , ...)
|
  kzalloc(
-	sizeof(THING) * COUNT * STRIDE
+	array3_size(COUNT, STRIDE, sizeof(THING))
  , ...)
)

// 3-factor product with 2 sizeof(variable), with redundant parens removed.
@@
expression THING1, THING2;
identifier COUNT;
type TYPE1, TYPE2;
@@

(
  kzalloc(
-	sizeof(TYPE1) * sizeof(TYPE2) * COUNT
+	array3_size(COUNT, sizeof(TYPE1), sizeof(TYPE2))
  , ...)
|
  kzalloc(
-	sizeof(TYPE1) * sizeof(THING2) * (COUNT)
+	array3_size(COUNT, sizeof(TYPE1), sizeof(TYPE2))
  , ...)
|
  kzalloc(
-	sizeof(THING1) * sizeof(THING2) * COUNT
+	array3_size(COUNT, sizeof(THING1), sizeof(THING2))
  , ...)
|
  kzalloc(
-	sizeof(THING1) * sizeof(THING2) * (COUNT)
+	array3_size(COUNT, sizeof(THING1), sizeof(THING2))
  , ...)
|
  kzalloc(
-	sizeof(TYPE1) * sizeof(THING2) * COUNT
+	array3_size(COUNT, sizeof(TYPE1), sizeof(THING2))
  , ...)
|
  kzalloc(
-	sizeof(TYPE1) * sizeof(THING2) * (COUNT)
+	array3_size(COUNT, sizeof(TYPE1), sizeof(THING2))
  , ...)
)

// 3-factor product, only identifiers, with redundant parens removed.
@@
identifier STRIDE, SIZE, COUNT;
@@

(
  kzalloc(
-	(COUNT) * STRIDE * SIZE
+	array3_size(COUNT, STRIDE, SIZE)
  , ...)
|
  kzalloc(
-	COUNT * (STRIDE) * SIZE
+	array3_size(COUNT, STRIDE, SIZE)
  , ...)
|
  kzalloc(
-	COUNT * STRIDE * (SIZE)
+	array3_size(COUNT, STRIDE, SIZE)
  , ...)
|
  kzalloc(
-	(COUNT) * (STRIDE) * SIZE
+	array3_size(COUNT, STRIDE, SIZE)
  , ...)
|
  kzalloc(
-	COUNT * (STRIDE) * (SIZE)
+	array3_size(COUNT, STRIDE, SIZE)
  , ...)
|
  kzalloc(
-	(COUNT) * STRIDE * (SIZE)
+	array3_size(COUNT, STRIDE, SIZE)
  , ...)
|
  kzalloc(
-	(COUNT) * (STRIDE) * (SIZE)
+	array3_size(COUNT, STRIDE, SIZE)
  , ...)
|
  kzalloc(
-	COUNT * STRIDE * SIZE
+	array3_size(COUNT, STRIDE, SIZE)
  , ...)
)

// Any remaining multi-factor products, first at least 3-factor products,
// when they're not all constants...
@@
expression E1, E2, E3;
constant C1, C2, C3;
@@

(
  kzalloc(C1 * C2 * C3, ...)
|
  kzalloc(
-	(E1) * E2 * E3
+	array3_size(E1, E2, E3)
  , ...)
|
  kzalloc(
-	(E1) * (E2) * E3
+	array3_size(E1, E2, E3)
  , ...)
|
  kzalloc(
-	(E1) * (E2) * (E3)
+	array3_size(E1, E2, E3)
  , ...)
|
  kzalloc(
-	E1 * E2 * E3
+	array3_size(E1, E2, E3)
  , ...)
)

// And then all remaining 2 factors products when they're not all constants,
// keeping sizeof() as the second factor argument.
@@
expression THING, E1, E2;
type TYPE;
constant C1, C2, C3;
@@

(
  kzalloc(sizeof(THING) * C2, ...)
|
  kzalloc(sizeof(TYPE) * C2, ...)
|
  kzalloc(C1 * C2 * C3, ...)
|
  kzalloc(C1 * C2, ...)
|
- kzalloc
+ kcalloc
  (
-	sizeof(TYPE) * (E2)
+	E2, sizeof(TYPE)
  , ...)
|
- kzalloc
+ kcalloc
  (
-	sizeof(TYPE) * E2
+	E2, sizeof(TYPE)
  , ...)
|
- kzalloc
+ kcalloc
  (
-	sizeof(THING) * (E2)
+	E2, sizeof(THING)
  , ...)
|
- kzalloc
+ kcalloc
  (
-	sizeof(THING) * E2
+	E2, sizeof(THING)
  , ...)
|
- kzalloc
+ kcalloc
  (
-	(E1) * E2
+	E1, E2
  , ...)
|
- kzalloc
+ kcalloc
  (
-	(E1) * (E2)
+	E1, E2
  , ...)
|
- kzalloc
+ kcalloc
  (
-	E1 * E2
+	E1, E2
  , ...)
)
Signed-off-by: NKees Cook <keescook@chromium.org>
      6396bb22
  7. 27 3月, 2018 1 次提交
  9. 20 3月, 2018 1 次提交
    • N
      SUNRPC: cache: ignore timestamp written to 'flush' file. · 3b68e6ee
      由 NeilBrown 提交于 
      The interface for flushing the sunrpc auth cache was poorly
designed and has caused problems a number of times.

The design is that you write a timestamp, and all entries
created before that time are discarded.
The most obvious problem is that this is not what people
actually want.  They want to just flush the whole cache.
The 1-second granularity can be a problem, as can the use
of wall-clock time.

A current problem is that code will write the current time to
this file - expecting it to clear everything - and if the
seconds number ticks over before this timestamp is checked,
the test "then >= now" fails, and a full flush isn't forced.

So lets just drop the subtleties and always flush the whole
cache.  The worst this could do is impose an extra cost
refilling it, but that would require someone to be using
non-standard tools.

We still report an error if the string written is not a number,
but we cause any valid number to flush the whole cache.
Reported-by: N"Wang, Alan 1. (NSB - CN/Hangzhou)" <alan.1.wang@nokia-sbell.com>
Signed-off-by: NNeilBrown <neilb@suse.com>
Signed-off-by: NJ. Bruce Fields <bfields@redhat.com>
      3b68e6ee
  11. 12 2月, 2018 1 次提交
    • L
      vfs: do bulk POLL* -> EPOLL* replacement · a9a08845
      由 Linus Torvalds 提交于 
      This is the mindless scripted replacement of kernel use of POLL*
variables as described by Al, done by this script:

    for V in IN OUT PRI ERR RDNORM RDBAND WRNORM WRBAND HUP RDHUP NVAL MSG; do
        L=`git grep -l -w POLL$V | grep -v '^t' | grep -v /um/ | grep -v '^sa' | grep -v '/poll.h$'|grep -v '^D'`
        for f in $L; do sed -i "-es/^\([^\"]*\)\(\<POLL$V\>\)/\\1E\\2/" $f; done
    done

with de-mangling cleanups yet to come.

NOTE! On almost all architectures, the EPOLL* constants have the same
values as the POLL* constants do.  But they keyword here is "almost".
For various bad reasons they aren't the same, and epoll() doesn't
actually work quite correctly in some cases due to this on Sparc et al.

The next patch from Al will sort out the final differences, and we
should be all done.
Scripted-by: NAl Viro <viro@zeniv.linux.org.uk>
Signed-off-by: NLinus Torvalds <torvalds@linux-foundation.org>
      a9a08845
  13. 28 11月, 2017 2 次提交
  15. 09 2月, 2017 4 次提交
  17. 01 2月, 2017 1 次提交
  19. 14 1月, 2017 1 次提交
    • P
      locking/atomic, kref: Add kref_read() · 2c935bc5
      由 Peter Zijlstra 提交于 
      Since we need to change the implementation, stop exposing internals.

Provide kref_read() to read the current reference count; typically
used for debug messages.

Kills two anti-patterns:

	atomic_read(&kref->refcount)
	kref->refcount.counter
Signed-off-by: NPeter Zijlstra (Intel) <peterz@infradead.org>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: linux-kernel@vger.kernel.org
Signed-off-by: NIngo Molnar <mingo@kernel.org>
      2c935bc5
  21. 25 12月, 2016 1 次提交
  23. 28 9月, 2016 1 次提交
    • K
      sunrpc: queue work on system_power_efficient_wq · 77b00bc0
      由 Ke Wang 提交于 
      sunrpc uses workqueue to clean cache regulary. There is no real dependency
of executing work on the cpu which queueing it.

On a idle system, especially for a heterogeneous systems like big.LITTLE,
it is observed that the big idle cpu was woke up many times just to service
this work, which against the principle of power saving. It would be better
if we can schedule it on a cpu which the scheduler believes to be the most
appropriate one.

After apply this patch, system_wq will be replaced by
system_power_efficient_wq for sunrpc. This functionality is enabled when
CONFIG_WQ_POWER_EFFICIENT is selected.
Signed-off-by: NKe Wang <ke.wang@spreadtrum.com>
Signed-off-by: NAnna Schumaker <Anna.Schumaker@Netapp.com>
      77b00bc0
  25. 14 7月, 2016 1 次提交
  27. 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
  29. 18 3月, 2016 1 次提交
  31. 24 2月, 2016 1 次提交
    • S
      sunrpc/cache: fix off-by-one in qword_get() · b7052cd7
      由 Stefan Hajnoczi 提交于 
      The qword_get() function NUL-terminates its output buffer.  If the input
string is in hex format \xXXXX... and the same length as the output
buffer, there is an off-by-one:

  int qword_get(char **bpp, char *dest, int bufsize)
  {
      ...
      while (len < bufsize) {
          ...
          *dest++ = (h << 4) | l;
          len++;
      }
      ...
      *dest = '\0';
      return len;
  }

This patch ensures the NUL terminator doesn't fall outside the output
buffer.
Signed-off-by: NStefan Hajnoczi <stefanha@redhat.com>
Cc: stable@vger.kernel.org
Signed-off-by: NJ. Bruce Fields <bfields@redhat.com>
      b7052cd7
  33. 23 1月, 2016 1 次提交
    • A
      wrappers for ->i_mutex access · 5955102c
      由 Al Viro 提交于 
      parallel to mutex_{lock,unlock,trylock,is_locked,lock_nested},
inode_foo(inode) being mutex_foo(&inode->i_mutex).

Please, use those for access to ->i_mutex; over the coming cycle
->i_mutex will become rwsem, with ->lookup() done with it held
only shared.
Signed-off-by: NAl Viro <viro@zeniv.linux.org.uk>
      5955102c
  35. 24 10月, 2015 1 次提交
    • N
      sunrpc/cache: make cache flushing more reliable. · 77862036
      由 Neil Brown 提交于 
      The caches used to store sunrpc authentication information can be
flushed by writing a timestamp to a file in /proc.

This timestamp has a one-second resolution and any entry in cache that
was last_refreshed *before* that time is treated as expired.

This is problematic as it is not possible to reliably flush the cache
without interrupting NFS service.
If the current time is written to the "flush" file, any entry that was
added since the current second started will still be treated as valid.
If one second beyond than the current time is written to the file
then no entries can be valid until the second ticks over.  This will
mean that no NFS request will be handled for up to 1 second.

To resolve this issue we make two changes:

1/ treat an entry as expired if the timestamp when it was last_refreshed
  is before *or the same as* the expiry time.  This means that current
  code which writes out the current time will now flush the cache
  reliably.

2/ when a new entry in added to the cache -  set the last_refresh timestamp
  to 1 second *beyond* the current flush time, when that not in the
  past.
  This ensures that newly added entries will always be valid.

Now that we have a very reliable way to flush the cache, and also
since we are using "since-boot" timestamps which are monotonic,
change cache_purge() to set the smallest future flush_time which
will work, and leave it there: don't revert to '1'.

Also disable the setting of the 'flush_time' far into the future.
That has never been useful and is now awkward as it would cause
last_refresh times to be strange.
Finally: if a request is made to set the 'flush_time' to the current
second, assume the intent is to flush the cache and advance it, if
necessary, to 1 second beyond the current 'flush_time' so that all
active entries will be deemed to be expired.

As part of this we need to add a 'cache_detail' arg to cache_init()
and cache_fresh_locked() so they can find the current ->flush_time.
Signed-off-by: NNeilBrown <neilb@suse.com>
Reported-by: NOlaf Kirch <okir@suse.com>
Signed-off-by: NJ. Bruce Fields <bfields@redhat.com>
      77862036
  37. 13 8月, 2015 3 次提交
  39. 16 4月, 2015 1 次提交
    • R
      lib/string_helpers.c: change semantics of string_escape_mem · 41416f23
      由 Rasmus Villemoes 提交于 
      The current semantics of string_escape_mem are inadequate for one of its
current users, vsnprintf().  If that is to honour its contract, it must
know how much space would be needed for the entire escaped buffer, and
string_escape_mem provides no way of obtaining that (short of allocating a
large enough buffer (~4 times input string) to let it play with, and
that's definitely a big no-no inside vsnprintf).

So change the semantics for string_escape_mem to be more snprintf-like:
Return the size of the output that would be generated if the destination
buffer was big enough, but of course still only write to the part of dst
it is allowed to, and (contrary to snprintf) don't do '\0'-termination.
It is then up to the caller to detect whether output was truncated and to
append a '\0' if desired.  Also, we must output partial escape sequences,
otherwise a call such as snprintf(buf, 3, "%1pE", "\123") would cause
printf to write a \0 to buf[2] but leaving buf[0] and buf[1] with whatever
they previously contained.

This also fixes a bug in the escaped_string() helper function, which used
to unconditionally pass a length of "end-buf" to string_escape_mem();
since the latter doesn't check osz for being insanely large, it would
happily write to dst.  For example, kasprintf(GFP_KERNEL, "something and
then %pE", ...); is an easy way to trigger an oops.

In test-string_helpers.c, the -ENOMEM test is replaced with testing for
getting the expected return value even if the buffer is too small.  We
also ensure that nothing is written (by relying on a NULL pointer deref)
if the output size is 0 by passing NULL - this has to work for
kasprintf("%pE") to work.

In net/sunrpc/cache.c, I think qword_add still has the same semantics.
Someone should definitely double-check this.

In fs/proc/array.c, I made the minimum possible change, but longer-term it
should stop poking around in seq_file internals.

[andriy.shevchenko@linux.intel.com: simplify qword_add]
[andriy.shevchenko@linux.intel.com: add missed curly braces]
Signed-off-by: NRasmus Villemoes <linux@rasmusvillemoes.dk>
Acked-by: NAndy Shevchenko <andriy.shevchenko@linux.intel.com>
Signed-off-by: NAndy Shevchenko <andriy.shevchenko@linux.intel.com>
Signed-off-by: NAndrew Morton <akpm@linux-foundation.org>
Signed-off-by: NLinus Torvalds <torvalds@linux-foundation.org>
      41416f23
  41. 09 3月, 2015 1 次提交
  43. 10 12月, 2014 1 次提交
  45. 09 5月, 2014 1 次提交
  47. 15 1月, 2014 1 次提交
  49. 13 12月, 2013 1 次提交
  51. 14 7月, 2013 1 次提交
  53. 02 7月, 2013 5 次提交
    • N
      sunrpc: Don't schedule an upcall on a replaced cache entry. · 0bebc633
      由 NeilBrown 提交于 
      When a cache entry is replaced, the "expiry_time" get set to
zero by a call to "cache_fresh_locked(..., 0)" at the end of
"sunrpc_cache_update".

This low expiry time makes cache_check() think that the 'refresh_age'
is negative, so the 'age' is comparatively large and a refresh is
triggered.
However refreshing a replaced entry it pointless, it cannot achieve
anything useful.

So teach cache_check to ignore a low refresh_age when expiry_time
is zero.
Reported-by: NBodo Stroesser <bstroesser@ts.fujitsu.com>
Signed-off-by: NNeilBrown <neilb@suse.de>
Signed-off-by: NJ. Bruce Fields <bfields@redhat.com>
      0bebc633
    • N
      net/sunrpc: xpt_auth_cache should be ignored when expired. · 7715cde8
      由 NeilBrown 提交于 
      commit d202cce8
    sunrpc: never return expired entries in sunrpc_cache_lookup

moved the 'entry is expired' test from cache_check to
sunrpc_cache_lookup, so that it happened early and some races could
safely be ignored.

However the ip_map (in svcauth_unix.c) has a separate single-item
cache which allows quick lookup without locking.  An entry in this
case would not be subject to the expiry test and so could be used
well after it has expired.

This is not normally a big problem because the first time it is used
after it is expired an up-call will be scheduled to refresh the entry
(if it hasn't been scheduled already) and the old entry will then
be invalidated.  So on the second attempt to use it after it has
expired, ip_map_cached_get will discard it.

However that is subtle and not ideal, so replace the "!cache_valid"
test with "cache_is_expired".
In doing this we drop the test on the "CACHE_VALID" bit.  This is
unnecessary as the bit is never cleared, and an entry will only
be cached if the bit is set.
Reported-by: NBodo Stroesser <bstroesser@ts.fujitsu.com>
Signed-off-by: NNeilBrown <neilb@suse.de>
Signed-off-by: NJ. Bruce Fields <bfields@redhat.com>
      7715cde8
    • N
      sunrpc/cache: ensure items removed from cache do not have pending upcalls. · 013920eb
      由 NeilBrown 提交于 
      It is possible for a race to set CACHE_PENDING after cache_clean()
has removed a cache entry from the cache.
If CACHE_PENDING is still set when the entry is finally 'put',
the cache_dequeue() will never happen and we can leak memory.

So set a new flag 'CACHE_CLEANED' when we remove something from
the cache, and don't queue any upcall if it is set.

If CACHE_PENDING is set before CACHE_CLEANED, the call that
cache_clean() makes to cache_fresh_unlocked() will free memory
as needed.  If CACHE_PENDING is set after CACHE_CLEANED, the
test in sunrpc_cache_pipe_upcall will ensure that the memory
is not allocated.

Reported-by: <bstroesser@ts.fujitsu.com>
Signed-off-by: NNeilBrown <neilb@suse.de>
Signed-off-by: NJ. Bruce Fields <bfields@redhat.com>
      013920eb
    • N
      sunrpc/cache: use cache_fresh_unlocked consistently and correctly. · 2a1c7f53
      由 NeilBrown 提交于 
      cache_fresh_unlocked() is called when a cache entry
has been updated and ensures that if there were any
pending upcalls, they are cleared.

So every time we update a cache entry, we should call this,
and this should be the only way that we try to clear
pending calls (that sort of uniformity makes code sooo much
easier to read).

try_to_negate_entry() will (possibly) mark an entry as
negative.  If it doesn't, it is because the entry already
is VALID.
So the entry will be valid on exit, so it is appropriate to
call cache_fresh_unlocked().
So tidy up try_to_negate_entry() to do that, and remove
partial open-coded cache_fresh_unlocked() from the one
call-site of try_to_negate_entry().

In the other branch of the 'switch(cache_make_upcall())',
we again have a partial open-coded version of cache_fresh_unlocked().
Replace that with a real call.

And again in cache_clean(), use a real call to cache_fresh_unlocked().

These call sites might previously have called
cache_revisit_request() if CACHE_PENDING wasn't set.
This is never necessary because cache_revisit_request() can
only do anything if the item is in the cache_defer_hash,
However any time that an item is added to the cache_defer_hash
(setup_deferral), the code immediately tests CACHE_PENDING,
and removes the entry again if it is clear.  So all other
places we only need to 'cache_revisit_request' if we've
just cleared CACHE_PENDING.
Reported-by: NBodo Stroesser <bstroesser@ts.fujitsu.com>
Signed-off-by: NNeilBrown  <neilb@suse.de>
Signed-off-by: NJ. Bruce Fields <bfields@redhat.com>
      2a1c7f53
    • N
      sunrpc/cache: remove races with queuing an upcall. · f9e1aedc
      由 NeilBrown 提交于 
      We currently queue an upcall after setting CACHE_PENDING,
and dequeue after clearing CACHE_PENDING.
So a request should only be present when CACHE_PENDING is set.

However we don't combine the test and the enqueue/dequeue in
a protected region, so it is possible (if unlikely) for a race
to result in a request being queued without CACHE_PENDING set,
or a request to be absent despite CACHE_PENDING.

So: include a test for CACHE_PENDING inside the regions of
enqueue and dequeue where queue_lock is held, and abort
the operation if the value is not as expected.

Also remove the early 'return' from cache_dequeue() to ensure that it
always removes all entries: As there is no locking between setting
CACHE_PENDING and calling sunrpc_cache_pipe_upcall it is not
inconceivable for some other thread to clear CACHE_PENDING and then
someone else to set it and call sunrpc_cache_pipe_upcall, both before
the original threads completed the call.

With this, it perfectly safe and correct to:
 - call cache_dequeue() if and only if we have just
   cleared CACHE_PENDING
 - call sunrpc_cache_pipe_upcall() (via cache_make_upcall)
   if and only if we have just set CACHE_PENDING.
Reported-by: NBodo Stroesser <bstroesser@ts.fujitsu.com>
Signed-off-by: NNeilBrown <neilb@suse.de>
Signed-off-by: NBodo Stroesser <bstroesser@ts.fujitsu.com>
Signed-off-by: NJ. Bruce Fields <bfields@redhat.com>
      f9e1aedc
  55. 21 5月, 2013 1 次提交