Merge branch 'silvio' into docs-next
commit
2fc9254d0c
|
@ -1,574 +0,0 @@
|
||||||
========================================
|
|
||||||
GENERIC ASSOCIATIVE ARRAY IMPLEMENTATION
|
|
||||||
========================================
|
|
||||||
|
|
||||||
Contents:
|
|
||||||
|
|
||||||
- Overview.
|
|
||||||
|
|
||||||
- The public API.
|
|
||||||
- Edit script.
|
|
||||||
- Operations table.
|
|
||||||
- Manipulation functions.
|
|
||||||
- Access functions.
|
|
||||||
- Index key form.
|
|
||||||
|
|
||||||
- Internal workings.
|
|
||||||
- Basic internal tree layout.
|
|
||||||
- Shortcuts.
|
|
||||||
- Splitting and collapsing nodes.
|
|
||||||
- Non-recursive iteration.
|
|
||||||
- Simultaneous alteration and iteration.
|
|
||||||
|
|
||||||
|
|
||||||
========
|
|
||||||
OVERVIEW
|
|
||||||
========
|
|
||||||
|
|
||||||
This associative array implementation is an object container with the following
|
|
||||||
properties:
|
|
||||||
|
|
||||||
(1) Objects are opaque pointers. The implementation does not care where they
|
|
||||||
point (if anywhere) or what they point to (if anything).
|
|
||||||
|
|
||||||
[!] NOTE: Pointers to objects _must_ be zero in the least significant bit.
|
|
||||||
|
|
||||||
(2) Objects do not need to contain linkage blocks for use by the array. This
|
|
||||||
permits an object to be located in multiple arrays simultaneously.
|
|
||||||
Rather, the array is made up of metadata blocks that point to objects.
|
|
||||||
|
|
||||||
(3) Objects require index keys to locate them within the array.
|
|
||||||
|
|
||||||
(4) Index keys must be unique. Inserting an object with the same key as one
|
|
||||||
already in the array will replace the old object.
|
|
||||||
|
|
||||||
(5) Index keys can be of any length and can be of different lengths.
|
|
||||||
|
|
||||||
(6) Index keys should encode the length early on, before any variation due to
|
|
||||||
length is seen.
|
|
||||||
|
|
||||||
(7) Index keys can include a hash to scatter objects throughout the array.
|
|
||||||
|
|
||||||
(8) The array can iterated over. The objects will not necessarily come out in
|
|
||||||
key order.
|
|
||||||
|
|
||||||
(9) The array can be iterated over whilst it is being modified, provided the
|
|
||||||
RCU readlock is being held by the iterator. Note, however, under these
|
|
||||||
circumstances, some objects may be seen more than once. If this is a
|
|
||||||
problem, the iterator should lock against modification. Objects will not
|
|
||||||
be missed, however, unless deleted.
|
|
||||||
|
|
||||||
(10) Objects in the array can be looked up by means of their index key.
|
|
||||||
|
|
||||||
(11) Objects can be looked up whilst the array is being modified, provided the
|
|
||||||
RCU readlock is being held by the thread doing the look up.
|
|
||||||
|
|
||||||
The implementation uses a tree of 16-pointer nodes internally that are indexed
|
|
||||||
on each level by nibbles from the index key in the same manner as in a radix
|
|
||||||
tree. To improve memory efficiency, shortcuts can be emplaced to skip over
|
|
||||||
what would otherwise be a series of single-occupancy nodes. Further, nodes
|
|
||||||
pack leaf object pointers into spare space in the node rather than making an
|
|
||||||
extra branch until as such time an object needs to be added to a full node.
|
|
||||||
|
|
||||||
|
|
||||||
==============
|
|
||||||
THE PUBLIC API
|
|
||||||
==============
|
|
||||||
|
|
||||||
The public API can be found in <linux/assoc_array.h>. The associative array is
|
|
||||||
rooted on the following structure:
|
|
||||||
|
|
||||||
struct assoc_array {
|
|
||||||
...
|
|
||||||
};
|
|
||||||
|
|
||||||
The code is selected by enabling CONFIG_ASSOCIATIVE_ARRAY.
|
|
||||||
|
|
||||||
|
|
||||||
EDIT SCRIPT
|
|
||||||
-----------
|
|
||||||
|
|
||||||
The insertion and deletion functions produce an 'edit script' that can later be
|
|
||||||
applied to effect the changes without risking ENOMEM. This retains the
|
|
||||||
preallocated metadata blocks that will be installed in the internal tree and
|
|
||||||
keeps track of the metadata blocks that will be removed from the tree when the
|
|
||||||
script is applied.
|
|
||||||
|
|
||||||
This is also used to keep track of dead blocks and dead objects after the
|
|
||||||
script has been applied so that they can be freed later. The freeing is done
|
|
||||||
after an RCU grace period has passed - thus allowing access functions to
|
|
||||||
proceed under the RCU read lock.
|
|
||||||
|
|
||||||
The script appears as outside of the API as a pointer of the type:
|
|
||||||
|
|
||||||
struct assoc_array_edit;
|
|
||||||
|
|
||||||
There are two functions for dealing with the script:
|
|
||||||
|
|
||||||
(1) Apply an edit script.
|
|
||||||
|
|
||||||
void assoc_array_apply_edit(struct assoc_array_edit *edit);
|
|
||||||
|
|
||||||
This will perform the edit functions, interpolating various write barriers
|
|
||||||
to permit accesses under the RCU read lock to continue. The edit script
|
|
||||||
will then be passed to call_rcu() to free it and any dead stuff it points
|
|
||||||
to.
|
|
||||||
|
|
||||||
(2) Cancel an edit script.
|
|
||||||
|
|
||||||
void assoc_array_cancel_edit(struct assoc_array_edit *edit);
|
|
||||||
|
|
||||||
This frees the edit script and all preallocated memory immediately. If
|
|
||||||
this was for insertion, the new object is _not_ released by this function,
|
|
||||||
but must rather be released by the caller.
|
|
||||||
|
|
||||||
These functions are guaranteed not to fail.
|
|
||||||
|
|
||||||
|
|
||||||
OPERATIONS TABLE
|
|
||||||
----------------
|
|
||||||
|
|
||||||
Various functions take a table of operations:
|
|
||||||
|
|
||||||
struct assoc_array_ops {
|
|
||||||
...
|
|
||||||
};
|
|
||||||
|
|
||||||
This points to a number of methods, all of which need to be provided:
|
|
||||||
|
|
||||||
(1) Get a chunk of index key from caller data:
|
|
||||||
|
|
||||||
unsigned long (*get_key_chunk)(const void *index_key, int level);
|
|
||||||
|
|
||||||
This should return a chunk of caller-supplied index key starting at the
|
|
||||||
*bit* position given by the level argument. The level argument will be a
|
|
||||||
multiple of ASSOC_ARRAY_KEY_CHUNK_SIZE and the function should return
|
|
||||||
ASSOC_ARRAY_KEY_CHUNK_SIZE bits. No error is possible.
|
|
||||||
|
|
||||||
|
|
||||||
(2) Get a chunk of an object's index key.
|
|
||||||
|
|
||||||
unsigned long (*get_object_key_chunk)(const void *object, int level);
|
|
||||||
|
|
||||||
As the previous function, but gets its data from an object in the array
|
|
||||||
rather than from a caller-supplied index key.
|
|
||||||
|
|
||||||
|
|
||||||
(3) See if this is the object we're looking for.
|
|
||||||
|
|
||||||
bool (*compare_object)(const void *object, const void *index_key);
|
|
||||||
|
|
||||||
Compare the object against an index key and return true if it matches and
|
|
||||||
false if it doesn't.
|
|
||||||
|
|
||||||
|
|
||||||
(4) Diff the index keys of two objects.
|
|
||||||
|
|
||||||
int (*diff_objects)(const void *object, const void *index_key);
|
|
||||||
|
|
||||||
Return the bit position at which the index key of the specified object
|
|
||||||
differs from the given index key or -1 if they are the same.
|
|
||||||
|
|
||||||
|
|
||||||
(5) Free an object.
|
|
||||||
|
|
||||||
void (*free_object)(void *object);
|
|
||||||
|
|
||||||
Free the specified object. Note that this may be called an RCU grace
|
|
||||||
period after assoc_array_apply_edit() was called, so synchronize_rcu() may
|
|
||||||
be necessary on module unloading.
|
|
||||||
|
|
||||||
|
|
||||||
MANIPULATION FUNCTIONS
|
|
||||||
----------------------
|
|
||||||
|
|
||||||
There are a number of functions for manipulating an associative array:
|
|
||||||
|
|
||||||
(1) Initialise an associative array.
|
|
||||||
|
|
||||||
void assoc_array_init(struct assoc_array *array);
|
|
||||||
|
|
||||||
This initialises the base structure for an associative array. It can't
|
|
||||||
fail.
|
|
||||||
|
|
||||||
|
|
||||||
(2) Insert/replace an object in an associative array.
|
|
||||||
|
|
||||||
struct assoc_array_edit *
|
|
||||||
assoc_array_insert(struct assoc_array *array,
|
|
||||||
const struct assoc_array_ops *ops,
|
|
||||||
const void *index_key,
|
|
||||||
void *object);
|
|
||||||
|
|
||||||
This inserts the given object into the array. Note that the least
|
|
||||||
significant bit of the pointer must be zero as it's used to type-mark
|
|
||||||
pointers internally.
|
|
||||||
|
|
||||||
If an object already exists for that key then it will be replaced with the
|
|
||||||
new object and the old one will be freed automatically.
|
|
||||||
|
|
||||||
The index_key argument should hold index key information and is
|
|
||||||
passed to the methods in the ops table when they are called.
|
|
||||||
|
|
||||||
This function makes no alteration to the array itself, but rather returns
|
|
||||||
an edit script that must be applied. -ENOMEM is returned in the case of
|
|
||||||
an out-of-memory error.
|
|
||||||
|
|
||||||
The caller should lock exclusively against other modifiers of the array.
|
|
||||||
|
|
||||||
|
|
||||||
(3) Delete an object from an associative array.
|
|
||||||
|
|
||||||
struct assoc_array_edit *
|
|
||||||
assoc_array_delete(struct assoc_array *array,
|
|
||||||
const struct assoc_array_ops *ops,
|
|
||||||
const void *index_key);
|
|
||||||
|
|
||||||
This deletes an object that matches the specified data from the array.
|
|
||||||
|
|
||||||
The index_key argument should hold index key information and is
|
|
||||||
passed to the methods in the ops table when they are called.
|
|
||||||
|
|
||||||
This function makes no alteration to the array itself, but rather returns
|
|
||||||
an edit script that must be applied. -ENOMEM is returned in the case of
|
|
||||||
an out-of-memory error. NULL will be returned if the specified object is
|
|
||||||
not found within the array.
|
|
||||||
|
|
||||||
The caller should lock exclusively against other modifiers of the array.
|
|
||||||
|
|
||||||
|
|
||||||
(4) Delete all objects from an associative array.
|
|
||||||
|
|
||||||
struct assoc_array_edit *
|
|
||||||
assoc_array_clear(struct assoc_array *array,
|
|
||||||
const struct assoc_array_ops *ops);
|
|
||||||
|
|
||||||
This deletes all the objects from an associative array and leaves it
|
|
||||||
completely empty.
|
|
||||||
|
|
||||||
This function makes no alteration to the array itself, but rather returns
|
|
||||||
an edit script that must be applied. -ENOMEM is returned in the case of
|
|
||||||
an out-of-memory error.
|
|
||||||
|
|
||||||
The caller should lock exclusively against other modifiers of the array.
|
|
||||||
|
|
||||||
|
|
||||||
(5) Destroy an associative array, deleting all objects.
|
|
||||||
|
|
||||||
void assoc_array_destroy(struct assoc_array *array,
|
|
||||||
const struct assoc_array_ops *ops);
|
|
||||||
|
|
||||||
This destroys the contents of the associative array and leaves it
|
|
||||||
completely empty. It is not permitted for another thread to be traversing
|
|
||||||
the array under the RCU read lock at the same time as this function is
|
|
||||||
destroying it as no RCU deferral is performed on memory release -
|
|
||||||
something that would require memory to be allocated.
|
|
||||||
|
|
||||||
The caller should lock exclusively against other modifiers and accessors
|
|
||||||
of the array.
|
|
||||||
|
|
||||||
|
|
||||||
(6) Garbage collect an associative array.
|
|
||||||
|
|
||||||
int assoc_array_gc(struct assoc_array *array,
|
|
||||||
const struct assoc_array_ops *ops,
|
|
||||||
bool (*iterator)(void *object, void *iterator_data),
|
|
||||||
void *iterator_data);
|
|
||||||
|
|
||||||
This iterates over the objects in an associative array and passes each one
|
|
||||||
to iterator(). If iterator() returns true, the object is kept. If it
|
|
||||||
returns false, the object will be freed. If the iterator() function
|
|
||||||
returns true, it must perform any appropriate refcount incrementing on the
|
|
||||||
object before returning.
|
|
||||||
|
|
||||||
The internal tree will be packed down if possible as part of the iteration
|
|
||||||
to reduce the number of nodes in it.
|
|
||||||
|
|
||||||
The iterator_data is passed directly to iterator() and is otherwise
|
|
||||||
ignored by the function.
|
|
||||||
|
|
||||||
The function will return 0 if successful and -ENOMEM if there wasn't
|
|
||||||
enough memory.
|
|
||||||
|
|
||||||
It is possible for other threads to iterate over or search the array under
|
|
||||||
the RCU read lock whilst this function is in progress. The caller should
|
|
||||||
lock exclusively against other modifiers of the array.
|
|
||||||
|
|
||||||
|
|
||||||
ACCESS FUNCTIONS
|
|
||||||
----------------
|
|
||||||
|
|
||||||
There are two functions for accessing an associative array:
|
|
||||||
|
|
||||||
(1) Iterate over all the objects in an associative array.
|
|
||||||
|
|
||||||
int assoc_array_iterate(const struct assoc_array *array,
|
|
||||||
int (*iterator)(const void *object,
|
|
||||||
void *iterator_data),
|
|
||||||
void *iterator_data);
|
|
||||||
|
|
||||||
This passes each object in the array to the iterator callback function.
|
|
||||||
iterator_data is private data for that function.
|
|
||||||
|
|
||||||
This may be used on an array at the same time as the array is being
|
|
||||||
modified, provided the RCU read lock is held. Under such circumstances,
|
|
||||||
it is possible for the iteration function to see some objects twice. If
|
|
||||||
this is a problem, then modification should be locked against. The
|
|
||||||
iteration algorithm should not, however, miss any objects.
|
|
||||||
|
|
||||||
The function will return 0 if no objects were in the array or else it will
|
|
||||||
return the result of the last iterator function called. Iteration stops
|
|
||||||
immediately if any call to the iteration function results in a non-zero
|
|
||||||
return.
|
|
||||||
|
|
||||||
|
|
||||||
(2) Find an object in an associative array.
|
|
||||||
|
|
||||||
void *assoc_array_find(const struct assoc_array *array,
|
|
||||||
const struct assoc_array_ops *ops,
|
|
||||||
const void *index_key);
|
|
||||||
|
|
||||||
This walks through the array's internal tree directly to the object
|
|
||||||
specified by the index key..
|
|
||||||
|
|
||||||
This may be used on an array at the same time as the array is being
|
|
||||||
modified, provided the RCU read lock is held.
|
|
||||||
|
|
||||||
The function will return the object if found (and set *_type to the object
|
|
||||||
type) or will return NULL if the object was not found.
|
|
||||||
|
|
||||||
|
|
||||||
INDEX KEY FORM
|
|
||||||
--------------
|
|
||||||
|
|
||||||
The index key can be of any form, but since the algorithms aren't told how long
|
|
||||||
the key is, it is strongly recommended that the index key includes its length
|
|
||||||
very early on before any variation due to the length would have an effect on
|
|
||||||
comparisons.
|
|
||||||
|
|
||||||
This will cause leaves with different length keys to scatter away from each
|
|
||||||
other - and those with the same length keys to cluster together.
|
|
||||||
|
|
||||||
It is also recommended that the index key begin with a hash of the rest of the
|
|
||||||
key to maximise scattering throughout keyspace.
|
|
||||||
|
|
||||||
The better the scattering, the wider and lower the internal tree will be.
|
|
||||||
|
|
||||||
Poor scattering isn't too much of a problem as there are shortcuts and nodes
|
|
||||||
can contain mixtures of leaves and metadata pointers.
|
|
||||||
|
|
||||||
The index key is read in chunks of machine word. Each chunk is subdivided into
|
|
||||||
one nibble (4 bits) per level, so on a 32-bit CPU this is good for 8 levels and
|
|
||||||
on a 64-bit CPU, 16 levels. Unless the scattering is really poor, it is
|
|
||||||
unlikely that more than one word of any particular index key will have to be
|
|
||||||
used.
|
|
||||||
|
|
||||||
|
|
||||||
=================
|
|
||||||
INTERNAL WORKINGS
|
|
||||||
=================
|
|
||||||
|
|
||||||
The associative array data structure has an internal tree. This tree is
|
|
||||||
constructed of two types of metadata blocks: nodes and shortcuts.
|
|
||||||
|
|
||||||
A node is an array of slots. Each slot can contain one of four things:
|
|
||||||
|
|
||||||
(*) A NULL pointer, indicating that the slot is empty.
|
|
||||||
|
|
||||||
(*) A pointer to an object (a leaf).
|
|
||||||
|
|
||||||
(*) A pointer to a node at the next level.
|
|
||||||
|
|
||||||
(*) A pointer to a shortcut.
|
|
||||||
|
|
||||||
|
|
||||||
BASIC INTERNAL TREE LAYOUT
|
|
||||||
--------------------------
|
|
||||||
|
|
||||||
Ignoring shortcuts for the moment, the nodes form a multilevel tree. The index
|
|
||||||
key space is strictly subdivided by the nodes in the tree and nodes occur on
|
|
||||||
fixed levels. For example:
|
|
||||||
|
|
||||||
Level: 0 1 2 3
|
|
||||||
=============== =============== =============== ===============
|
|
||||||
NODE D
|
|
||||||
NODE B NODE C +------>+---+
|
|
||||||
+------>+---+ +------>+---+ | | 0 |
|
|
||||||
NODE A | | 0 | | | 0 | | +---+
|
|
||||||
+---+ | +---+ | +---+ | : :
|
|
||||||
| 0 | | : : | : : | +---+
|
|
||||||
+---+ | +---+ | +---+ | | f |
|
|
||||||
| 1 |---+ | 3 |---+ | 7 |---+ +---+
|
|
||||||
+---+ +---+ +---+
|
|
||||||
: : : : | 8 |---+
|
|
||||||
+---+ +---+ +---+ | NODE E
|
|
||||||
| e |---+ | f | : : +------>+---+
|
|
||||||
+---+ | +---+ +---+ | 0 |
|
|
||||||
| f | | | f | +---+
|
|
||||||
+---+ | +---+ : :
|
|
||||||
| NODE F +---+
|
|
||||||
+------>+---+ | f |
|
|
||||||
| 0 | NODE G +---+
|
|
||||||
+---+ +------>+---+
|
|
||||||
: : | | 0 |
|
|
||||||
+---+ | +---+
|
|
||||||
| 6 |---+ : :
|
|
||||||
+---+ +---+
|
|
||||||
: : | f |
|
|
||||||
+---+ +---+
|
|
||||||
| f |
|
|
||||||
+---+
|
|
||||||
|
|
||||||
In the above example, there are 7 nodes (A-G), each with 16 slots (0-f).
|
|
||||||
Assuming no other meta data nodes in the tree, the key space is divided thusly:
|
|
||||||
|
|
||||||
KEY PREFIX NODE
|
|
||||||
========== ====
|
|
||||||
137* D
|
|
||||||
138* E
|
|
||||||
13[0-69-f]* C
|
|
||||||
1[0-24-f]* B
|
|
||||||
e6* G
|
|
||||||
e[0-57-f]* F
|
|
||||||
[02-df]* A
|
|
||||||
|
|
||||||
So, for instance, keys with the following example index keys will be found in
|
|
||||||
the appropriate nodes:
|
|
||||||
|
|
||||||
INDEX KEY PREFIX NODE
|
|
||||||
=============== ======= ====
|
|
||||||
13694892892489 13 C
|
|
||||||
13795289025897 137 D
|
|
||||||
13889dde88793 138 E
|
|
||||||
138bbb89003093 138 E
|
|
||||||
1394879524789 12 C
|
|
||||||
1458952489 1 B
|
|
||||||
9431809de993ba - A
|
|
||||||
b4542910809cd - A
|
|
||||||
e5284310def98 e F
|
|
||||||
e68428974237 e6 G
|
|
||||||
e7fffcbd443 e F
|
|
||||||
f3842239082 - A
|
|
||||||
|
|
||||||
To save memory, if a node can hold all the leaves in its portion of keyspace,
|
|
||||||
then the node will have all those leaves in it and will not have any metadata
|
|
||||||
pointers - even if some of those leaves would like to be in the same slot.
|
|
||||||
|
|
||||||
A node can contain a heterogeneous mix of leaves and metadata pointers.
|
|
||||||
Metadata pointers must be in the slots that match their subdivisions of key
|
|
||||||
space. The leaves can be in any slot not occupied by a metadata pointer. It
|
|
||||||
is guaranteed that none of the leaves in a node will match a slot occupied by a
|
|
||||||
metadata pointer. If the metadata pointer is there, any leaf whose key matches
|
|
||||||
the metadata key prefix must be in the subtree that the metadata pointer points
|
|
||||||
to.
|
|
||||||
|
|
||||||
In the above example list of index keys, node A will contain:
|
|
||||||
|
|
||||||
SLOT CONTENT INDEX KEY (PREFIX)
|
|
||||||
==== =============== ==================
|
|
||||||
1 PTR TO NODE B 1*
|
|
||||||
any LEAF 9431809de993ba
|
|
||||||
any LEAF b4542910809cd
|
|
||||||
e PTR TO NODE F e*
|
|
||||||
any LEAF f3842239082
|
|
||||||
|
|
||||||
and node B:
|
|
||||||
|
|
||||||
3 PTR TO NODE C 13*
|
|
||||||
any LEAF 1458952489
|
|
||||||
|
|
||||||
|
|
||||||
SHORTCUTS
|
|
||||||
---------
|
|
||||||
|
|
||||||
Shortcuts are metadata records that jump over a piece of keyspace. A shortcut
|
|
||||||
is a replacement for a series of single-occupancy nodes ascending through the
|
|
||||||
levels. Shortcuts exist to save memory and to speed up traversal.
|
|
||||||
|
|
||||||
It is possible for the root of the tree to be a shortcut - say, for example,
|
|
||||||
the tree contains at least 17 nodes all with key prefix '1111'. The insertion
|
|
||||||
algorithm will insert a shortcut to skip over the '1111' keyspace in a single
|
|
||||||
bound and get to the fourth level where these actually become different.
|
|
||||||
|
|
||||||
|
|
||||||
SPLITTING AND COLLAPSING NODES
|
|
||||||
------------------------------
|
|
||||||
|
|
||||||
Each node has a maximum capacity of 16 leaves and metadata pointers. If the
|
|
||||||
insertion algorithm finds that it is trying to insert a 17th object into a
|
|
||||||
node, that node will be split such that at least two leaves that have a common
|
|
||||||
key segment at that level end up in a separate node rooted on that slot for
|
|
||||||
that common key segment.
|
|
||||||
|
|
||||||
If the leaves in a full node and the leaf that is being inserted are
|
|
||||||
sufficiently similar, then a shortcut will be inserted into the tree.
|
|
||||||
|
|
||||||
When the number of objects in the subtree rooted at a node falls to 16 or
|
|
||||||
fewer, then the subtree will be collapsed down to a single node - and this will
|
|
||||||
ripple towards the root if possible.
|
|
||||||
|
|
||||||
|
|
||||||
NON-RECURSIVE ITERATION
|
|
||||||
-----------------------
|
|
||||||
|
|
||||||
Each node and shortcut contains a back pointer to its parent and the number of
|
|
||||||
slot in that parent that points to it. None-recursive iteration uses these to
|
|
||||||
proceed rootwards through the tree, going to the parent node, slot N + 1 to
|
|
||||||
make sure progress is made without the need for a stack.
|
|
||||||
|
|
||||||
The backpointers, however, make simultaneous alteration and iteration tricky.
|
|
||||||
|
|
||||||
|
|
||||||
SIMULTANEOUS ALTERATION AND ITERATION
|
|
||||||
-------------------------------------
|
|
||||||
|
|
||||||
There are a number of cases to consider:
|
|
||||||
|
|
||||||
(1) Simple insert/replace. This involves simply replacing a NULL or old
|
|
||||||
matching leaf pointer with the pointer to the new leaf after a barrier.
|
|
||||||
The metadata blocks don't change otherwise. An old leaf won't be freed
|
|
||||||
until after the RCU grace period.
|
|
||||||
|
|
||||||
(2) Simple delete. This involves just clearing an old matching leaf. The
|
|
||||||
metadata blocks don't change otherwise. The old leaf won't be freed until
|
|
||||||
after the RCU grace period.
|
|
||||||
|
|
||||||
(3) Insertion replacing part of a subtree that we haven't yet entered. This
|
|
||||||
may involve replacement of part of that subtree - but that won't affect
|
|
||||||
the iteration as we won't have reached the pointer to it yet and the
|
|
||||||
ancestry blocks are not replaced (the layout of those does not change).
|
|
||||||
|
|
||||||
(4) Insertion replacing nodes that we're actively processing. This isn't a
|
|
||||||
problem as we've passed the anchoring pointer and won't switch onto the
|
|
||||||
new layout until we follow the back pointers - at which point we've
|
|
||||||
already examined the leaves in the replaced node (we iterate over all the
|
|
||||||
leaves in a node before following any of its metadata pointers).
|
|
||||||
|
|
||||||
We might, however, re-see some leaves that have been split out into a new
|
|
||||||
branch that's in a slot further along than we were at.
|
|
||||||
|
|
||||||
(5) Insertion replacing nodes that we're processing a dependent branch of.
|
|
||||||
This won't affect us until we follow the back pointers. Similar to (4).
|
|
||||||
|
|
||||||
(6) Deletion collapsing a branch under us. This doesn't affect us because the
|
|
||||||
back pointers will get us back to the parent of the new node before we
|
|
||||||
could see the new node. The entire collapsed subtree is thrown away
|
|
||||||
unchanged - and will still be rooted on the same slot, so we shouldn't
|
|
||||||
process it a second time as we'll go back to slot + 1.
|
|
||||||
|
|
||||||
Note:
|
|
||||||
|
|
||||||
(*) Under some circumstances, we need to simultaneously change the parent
|
|
||||||
pointer and the parent slot pointer on a node (say, for example, we
|
|
||||||
inserted another node before it and moved it up a level). We cannot do
|
|
||||||
this without locking against a read - so we have to replace that node too.
|
|
||||||
|
|
||||||
However, when we're changing a shortcut into a node this isn't a problem
|
|
||||||
as shortcuts only have one slot and so the parent slot number isn't used
|
|
||||||
when traversing backwards over one. This means that it's okay to change
|
|
||||||
the slot number first - provided suitable barriers are used to make sure
|
|
||||||
the parent slot number is read after the back pointer.
|
|
||||||
|
|
||||||
Obsolete blocks and leaves are freed up after an RCU grace period has passed,
|
|
||||||
so as long as anyone doing walking or iteration holds the RCU read lock, the
|
|
||||||
old superstructure should not go away on them.
|
|
|
@ -0,0 +1,551 @@
|
||||||
|
========================================
|
||||||
|
Generic Associative Array Implementation
|
||||||
|
========================================
|
||||||
|
|
||||||
|
Overview
|
||||||
|
========
|
||||||
|
|
||||||
|
This associative array implementation is an object container with the following
|
||||||
|
properties:
|
||||||
|
|
||||||
|
1. Objects are opaque pointers. The implementation does not care where they
|
||||||
|
point (if anywhere) or what they point to (if anything).
|
||||||
|
.. note:: Pointers to objects _must_ be zero in the least significant bit.**
|
||||||
|
|
||||||
|
2. Objects do not need to contain linkage blocks for use by the array. This
|
||||||
|
permits an object to be located in multiple arrays simultaneously.
|
||||||
|
Rather, the array is made up of metadata blocks that point to objects.
|
||||||
|
|
||||||
|
3. Objects require index keys to locate them within the array.
|
||||||
|
|
||||||
|
4. Index keys must be unique. Inserting an object with the same key as one
|
||||||
|
already in the array will replace the old object.
|
||||||
|
|
||||||
|
5. Index keys can be of any length and can be of different lengths.
|
||||||
|
|
||||||
|
6. Index keys should encode the length early on, before any variation due to
|
||||||
|
length is seen.
|
||||||
|
|
||||||
|
7. Index keys can include a hash to scatter objects throughout the array.
|
||||||
|
|
||||||
|
8. The array can iterated over. The objects will not necessarily come out in
|
||||||
|
key order.
|
||||||
|
|
||||||
|
9. The array can be iterated over whilst it is being modified, provided the
|
||||||
|
RCU readlock is being held by the iterator. Note, however, under these
|
||||||
|
circumstances, some objects may be seen more than once. If this is a
|
||||||
|
problem, the iterator should lock against modification. Objects will not
|
||||||
|
be missed, however, unless deleted.
|
||||||
|
|
||||||
|
10. Objects in the array can be looked up by means of their index key.
|
||||||
|
|
||||||
|
11. Objects can be looked up whilst the array is being modified, provided the
|
||||||
|
RCU readlock is being held by the thread doing the look up.
|
||||||
|
|
||||||
|
The implementation uses a tree of 16-pointer nodes internally that are indexed
|
||||||
|
on each level by nibbles from the index key in the same manner as in a radix
|
||||||
|
tree. To improve memory efficiency, shortcuts can be emplaced to skip over
|
||||||
|
what would otherwise be a series of single-occupancy nodes. Further, nodes
|
||||||
|
pack leaf object pointers into spare space in the node rather than making an
|
||||||
|
extra branch until as such time an object needs to be added to a full node.
|
||||||
|
|
||||||
|
|
||||||
|
The Public API
|
||||||
|
==============
|
||||||
|
|
||||||
|
The public API can be found in ``<linux/assoc_array.h>``. The associative
|
||||||
|
array is rooted on the following structure::
|
||||||
|
|
||||||
|
struct assoc_array {
|
||||||
|
...
|
||||||
|
};
|
||||||
|
|
||||||
|
The code is selected by enabling ``CONFIG_ASSOCIATIVE_ARRAY`` with::
|
||||||
|
|
||||||
|
./script/config -e ASSOCIATIVE_ARRAY
|
||||||
|
|
||||||
|
|
||||||
|
Edit Script
|
||||||
|
-----------
|
||||||
|
|
||||||
|
The insertion and deletion functions produce an 'edit script' that can later be
|
||||||
|
applied to effect the changes without risking ``ENOMEM``. This retains the
|
||||||
|
preallocated metadata blocks that will be installed in the internal tree and
|
||||||
|
keeps track of the metadata blocks that will be removed from the tree when the
|
||||||
|
script is applied.
|
||||||
|
|
||||||
|
This is also used to keep track of dead blocks and dead objects after the
|
||||||
|
script has been applied so that they can be freed later. The freeing is done
|
||||||
|
after an RCU grace period has passed - thus allowing access functions to
|
||||||
|
proceed under the RCU read lock.
|
||||||
|
|
||||||
|
The script appears as outside of the API as a pointer of the type::
|
||||||
|
|
||||||
|
struct assoc_array_edit;
|
||||||
|
|
||||||
|
There are two functions for dealing with the script:
|
||||||
|
|
||||||
|
1. Apply an edit script::
|
||||||
|
|
||||||
|
void assoc_array_apply_edit(struct assoc_array_edit *edit);
|
||||||
|
|
||||||
|
This will perform the edit functions, interpolating various write barriers
|
||||||
|
to permit accesses under the RCU read lock to continue. The edit script
|
||||||
|
will then be passed to ``call_rcu()`` to free it and any dead stuff it points
|
||||||
|
to.
|
||||||
|
|
||||||
|
2. Cancel an edit script::
|
||||||
|
|
||||||
|
void assoc_array_cancel_edit(struct assoc_array_edit *edit);
|
||||||
|
|
||||||
|
This frees the edit script and all preallocated memory immediately. If
|
||||||
|
this was for insertion, the new object is _not_ released by this function,
|
||||||
|
but must rather be released by the caller.
|
||||||
|
|
||||||
|
These functions are guaranteed not to fail.
|
||||||
|
|
||||||
|
|
||||||
|
Operations Table
|
||||||
|
----------------
|
||||||
|
|
||||||
|
Various functions take a table of operations::
|
||||||
|
|
||||||
|
struct assoc_array_ops {
|
||||||
|
...
|
||||||
|
};
|
||||||
|
|
||||||
|
This points to a number of methods, all of which need to be provided:
|
||||||
|
|
||||||
|
1. Get a chunk of index key from caller data::
|
||||||
|
|
||||||
|
unsigned long (*get_key_chunk)(const void *index_key, int level);
|
||||||
|
|
||||||
|
This should return a chunk of caller-supplied index key starting at the
|
||||||
|
*bit* position given by the level argument. The level argument will be a
|
||||||
|
multiple of ``ASSOC_ARRAY_KEY_CHUNK_SIZE`` and the function should return
|
||||||
|
``ASSOC_ARRAY_KEY_CHUNK_SIZE bits``. No error is possible.
|
||||||
|
|
||||||
|
|
||||||
|
2. Get a chunk of an object's index key::
|
||||||
|
|
||||||
|
unsigned long (*get_object_key_chunk)(const void *object, int level);
|
||||||
|
|
||||||
|
As the previous function, but gets its data from an object in the array
|
||||||
|
rather than from a caller-supplied index key.
|
||||||
|
|
||||||
|
|
||||||
|
3. See if this is the object we're looking for::
|
||||||
|
|
||||||
|
bool (*compare_object)(const void *object, const void *index_key);
|
||||||
|
|
||||||
|
Compare the object against an index key and return ``true`` if it matches and
|
||||||
|
``false`` if it doesn't.
|
||||||
|
|
||||||
|
|
||||||
|
4. Diff the index keys of two objects::
|
||||||
|
|
||||||
|
int (*diff_objects)(const void *object, const void *index_key);
|
||||||
|
|
||||||
|
Return the bit position at which the index key of the specified object
|
||||||
|
differs from the given index key or -1 if they are the same.
|
||||||
|
|
||||||
|
|
||||||
|
5. Free an object::
|
||||||
|
|
||||||
|
void (*free_object)(void *object);
|
||||||
|
|
||||||
|
Free the specified object. Note that this may be called an RCU grace period
|
||||||
|
after ``assoc_array_apply_edit()`` was called, so ``synchronize_rcu()`` may be
|
||||||
|
necessary on module unloading.
|
||||||
|
|
||||||
|
|
||||||
|
Manipulation Functions
|
||||||
|
----------------------
|
||||||
|
|
||||||
|
There are a number of functions for manipulating an associative array:
|
||||||
|
|
||||||
|
1. Initialise an associative array::
|
||||||
|
|
||||||
|
void assoc_array_init(struct assoc_array *array);
|
||||||
|
|
||||||
|
This initialises the base structure for an associative array. It can't fail.
|
||||||
|
|
||||||
|
|
||||||
|
2. Insert/replace an object in an associative array::
|
||||||
|
|
||||||
|
struct assoc_array_edit *
|
||||||
|
assoc_array_insert(struct assoc_array *array,
|
||||||
|
const struct assoc_array_ops *ops,
|
||||||
|
const void *index_key,
|
||||||
|
void *object);
|
||||||
|
|
||||||
|
This inserts the given object into the array. Note that the least
|
||||||
|
significant bit of the pointer must be zero as it's used to type-mark
|
||||||
|
pointers internally.
|
||||||
|
|
||||||
|
If an object already exists for that key then it will be replaced with the
|
||||||
|
new object and the old one will be freed automatically.
|
||||||
|
|
||||||
|
The ``index_key`` argument should hold index key information and is
|
||||||
|
passed to the methods in the ops table when they are called.
|
||||||
|
|
||||||
|
This function makes no alteration to the array itself, but rather returns
|
||||||
|
an edit script that must be applied. ``-ENOMEM`` is returned in the case of
|
||||||
|
an out-of-memory error.
|
||||||
|
|
||||||
|
The caller should lock exclusively against other modifiers of the array.
|
||||||
|
|
||||||
|
|
||||||
|
3. Delete an object from an associative array::
|
||||||
|
|
||||||
|
struct assoc_array_edit *
|
||||||
|
assoc_array_delete(struct assoc_array *array,
|
||||||
|
const struct assoc_array_ops *ops,
|
||||||
|
const void *index_key);
|
||||||
|
|
||||||
|
This deletes an object that matches the specified data from the array.
|
||||||
|
|
||||||
|
The ``index_key`` argument should hold index key information and is
|
||||||
|
passed to the methods in the ops table when they are called.
|
||||||
|
|
||||||
|
This function makes no alteration to the array itself, but rather returns
|
||||||
|
an edit script that must be applied. ``-ENOMEM`` is returned in the case of
|
||||||
|
an out-of-memory error. ``NULL`` will be returned if the specified object is
|
||||||
|
not found within the array.
|
||||||
|
|
||||||
|
The caller should lock exclusively against other modifiers of the array.
|
||||||
|
|
||||||
|
|
||||||
|
4. Delete all objects from an associative array::
|
||||||
|
|
||||||
|
struct assoc_array_edit *
|
||||||
|
assoc_array_clear(struct assoc_array *array,
|
||||||
|
const struct assoc_array_ops *ops);
|
||||||
|
|
||||||
|
This deletes all the objects from an associative array and leaves it
|
||||||
|
completely empty.
|
||||||
|
|
||||||
|
This function makes no alteration to the array itself, but rather returns
|
||||||
|
an edit script that must be applied. ``-ENOMEM`` is returned in the case of
|
||||||
|
an out-of-memory error.
|
||||||
|
|
||||||
|
The caller should lock exclusively against other modifiers of the array.
|
||||||
|
|
||||||
|
|
||||||
|
5. Destroy an associative array, deleting all objects::
|
||||||
|
|
||||||
|
void assoc_array_destroy(struct assoc_array *array,
|
||||||
|
const struct assoc_array_ops *ops);
|
||||||
|
|
||||||
|
This destroys the contents of the associative array and leaves it
|
||||||
|
completely empty. It is not permitted for another thread to be traversing
|
||||||
|
the array under the RCU read lock at the same time as this function is
|
||||||
|
destroying it as no RCU deferral is performed on memory release -
|
||||||
|
something that would require memory to be allocated.
|
||||||
|
|
||||||
|
The caller should lock exclusively against other modifiers and accessors
|
||||||
|
of the array.
|
||||||
|
|
||||||
|
|
||||||
|
6. Garbage collect an associative array::
|
||||||
|
|
||||||
|
int assoc_array_gc(struct assoc_array *array,
|
||||||
|
const struct assoc_array_ops *ops,
|
||||||
|
bool (*iterator)(void *object, void *iterator_data),
|
||||||
|
void *iterator_data);
|
||||||
|
|
||||||
|
This iterates over the objects in an associative array and passes each one to
|
||||||
|
``iterator()``. If ``iterator()`` returns ``true``, the object is kept. If it
|
||||||
|
returns ``false``, the object will be freed. If the ``iterator()`` function
|
||||||
|
returns ``true``, it must perform any appropriate refcount incrementing on the
|
||||||
|
object before returning.
|
||||||
|
|
||||||
|
The internal tree will be packed down if possible as part of the iteration
|
||||||
|
to reduce the number of nodes in it.
|
||||||
|
|
||||||
|
The ``iterator_data`` is passed directly to ``iterator()`` and is otherwise
|
||||||
|
ignored by the function.
|
||||||
|
|
||||||
|
The function will return ``0`` if successful and ``-ENOMEM`` if there wasn't
|
||||||
|
enough memory.
|
||||||
|
|
||||||
|
It is possible for other threads to iterate over or search the array under
|
||||||
|
the RCU read lock whilst this function is in progress. The caller should
|
||||||
|
lock exclusively against other modifiers of the array.
|
||||||
|
|
||||||
|
|
||||||
|
Access Functions
|
||||||
|
----------------
|
||||||
|
|
||||||
|
There are two functions for accessing an associative array:
|
||||||
|
|
||||||
|
1. Iterate over all the objects in an associative array::
|
||||||
|
|
||||||
|
int assoc_array_iterate(const struct assoc_array *array,
|
||||||
|
int (*iterator)(const void *object,
|
||||||
|
void *iterator_data),
|
||||||
|
void *iterator_data);
|
||||||
|
|
||||||
|
This passes each object in the array to the iterator callback function.
|
||||||
|
``iterator_data`` is private data for that function.
|
||||||
|
|
||||||
|
This may be used on an array at the same time as the array is being
|
||||||
|
modified, provided the RCU read lock is held. Under such circumstances,
|
||||||
|
it is possible for the iteration function to see some objects twice. If
|
||||||
|
this is a problem, then modification should be locked against. The
|
||||||
|
iteration algorithm should not, however, miss any objects.
|
||||||
|
|
||||||
|
The function will return ``0`` if no objects were in the array or else it will
|
||||||
|
return the result of the last iterator function called. Iteration stops
|
||||||
|
immediately if any call to the iteration function results in a non-zero
|
||||||
|
return.
|
||||||
|
|
||||||
|
|
||||||
|
2. Find an object in an associative array::
|
||||||
|
|
||||||
|
void *assoc_array_find(const struct assoc_array *array,
|
||||||
|
const struct assoc_array_ops *ops,
|
||||||
|
const void *index_key);
|
||||||
|
|
||||||
|
This walks through the array's internal tree directly to the object
|
||||||
|
specified by the index key..
|
||||||
|
|
||||||
|
This may be used on an array at the same time as the array is being
|
||||||
|
modified, provided the RCU read lock is held.
|
||||||
|
|
||||||
|
The function will return the object if found (and set ``*_type`` to the object
|
||||||
|
type) or will return ``NULL`` if the object was not found.
|
||||||
|
|
||||||
|
|
||||||
|
Index Key Form
|
||||||
|
--------------
|
||||||
|
|
||||||
|
The index key can be of any form, but since the algorithms aren't told how long
|
||||||
|
the key is, it is strongly recommended that the index key includes its length
|
||||||
|
very early on before any variation due to the length would have an effect on
|
||||||
|
comparisons.
|
||||||
|
|
||||||
|
This will cause leaves with different length keys to scatter away from each
|
||||||
|
other - and those with the same length keys to cluster together.
|
||||||
|
|
||||||
|
It is also recommended that the index key begin with a hash of the rest of the
|
||||||
|
key to maximise scattering throughout keyspace.
|
||||||
|
|
||||||
|
The better the scattering, the wider and lower the internal tree will be.
|
||||||
|
|
||||||
|
Poor scattering isn't too much of a problem as there are shortcuts and nodes
|
||||||
|
can contain mixtures of leaves and metadata pointers.
|
||||||
|
|
||||||
|
The index key is read in chunks of machine word. Each chunk is subdivided into
|
||||||
|
one nibble (4 bits) per level, so on a 32-bit CPU this is good for 8 levels and
|
||||||
|
on a 64-bit CPU, 16 levels. Unless the scattering is really poor, it is
|
||||||
|
unlikely that more than one word of any particular index key will have to be
|
||||||
|
used.
|
||||||
|
|
||||||
|
|
||||||
|
Internal Workings
|
||||||
|
=================
|
||||||
|
|
||||||
|
The associative array data structure has an internal tree. This tree is
|
||||||
|
constructed of two types of metadata blocks: nodes and shortcuts.
|
||||||
|
|
||||||
|
A node is an array of slots. Each slot can contain one of four things:
|
||||||
|
|
||||||
|
* A NULL pointer, indicating that the slot is empty.
|
||||||
|
* A pointer to an object (a leaf).
|
||||||
|
* A pointer to a node at the next level.
|
||||||
|
* A pointer to a shortcut.
|
||||||
|
|
||||||
|
|
||||||
|
Basic Internal Tree Layout
|
||||||
|
--------------------------
|
||||||
|
|
||||||
|
Ignoring shortcuts for the moment, the nodes form a multilevel tree. The index
|
||||||
|
key space is strictly subdivided by the nodes in the tree and nodes occur on
|
||||||
|
fixed levels. For example::
|
||||||
|
|
||||||
|
Level: 0 1 2 3
|
||||||
|
=============== =============== =============== ===============
|
||||||
|
NODE D
|
||||||
|
NODE B NODE C +------>+---+
|
||||||
|
+------>+---+ +------>+---+ | | 0 |
|
||||||
|
NODE A | | 0 | | | 0 | | +---+
|
||||||
|
+---+ | +---+ | +---+ | : :
|
||||||
|
| 0 | | : : | : : | +---+
|
||||||
|
+---+ | +---+ | +---+ | | f |
|
||||||
|
| 1 |---+ | 3 |---+ | 7 |---+ +---+
|
||||||
|
+---+ +---+ +---+
|
||||||
|
: : : : | 8 |---+
|
||||||
|
+---+ +---+ +---+ | NODE E
|
||||||
|
| e |---+ | f | : : +------>+---+
|
||||||
|
+---+ | +---+ +---+ | 0 |
|
||||||
|
| f | | | f | +---+
|
||||||
|
+---+ | +---+ : :
|
||||||
|
| NODE F +---+
|
||||||
|
+------>+---+ | f |
|
||||||
|
| 0 | NODE G +---+
|
||||||
|
+---+ +------>+---+
|
||||||
|
: : | | 0 |
|
||||||
|
+---+ | +---+
|
||||||
|
| 6 |---+ : :
|
||||||
|
+---+ +---+
|
||||||
|
: : | f |
|
||||||
|
+---+ +---+
|
||||||
|
| f |
|
||||||
|
+---+
|
||||||
|
|
||||||
|
In the above example, there are 7 nodes (A-G), each with 16 slots (0-f).
|
||||||
|
Assuming no other meta data nodes in the tree, the key space is divided
|
||||||
|
thusly::
|
||||||
|
|
||||||
|
KEY PREFIX NODE
|
||||||
|
========== ====
|
||||||
|
137* D
|
||||||
|
138* E
|
||||||
|
13[0-69-f]* C
|
||||||
|
1[0-24-f]* B
|
||||||
|
e6* G
|
||||||
|
e[0-57-f]* F
|
||||||
|
[02-df]* A
|
||||||
|
|
||||||
|
So, for instance, keys with the following example index keys will be found in
|
||||||
|
the appropriate nodes::
|
||||||
|
|
||||||
|
INDEX KEY PREFIX NODE
|
||||||
|
=============== ======= ====
|
||||||
|
13694892892489 13 C
|
||||||
|
13795289025897 137 D
|
||||||
|
13889dde88793 138 E
|
||||||
|
138bbb89003093 138 E
|
||||||
|
1394879524789 12 C
|
||||||
|
1458952489 1 B
|
||||||
|
9431809de993ba - A
|
||||||
|
b4542910809cd - A
|
||||||
|
e5284310def98 e F
|
||||||
|
e68428974237 e6 G
|
||||||
|
e7fffcbd443 e F
|
||||||
|
f3842239082 - A
|
||||||
|
|
||||||
|
To save memory, if a node can hold all the leaves in its portion of keyspace,
|
||||||
|
then the node will have all those leaves in it and will not have any metadata
|
||||||
|
pointers - even if some of those leaves would like to be in the same slot.
|
||||||
|
|
||||||
|
A node can contain a heterogeneous mix of leaves and metadata pointers.
|
||||||
|
Metadata pointers must be in the slots that match their subdivisions of key
|
||||||
|
space. The leaves can be in any slot not occupied by a metadata pointer. It
|
||||||
|
is guaranteed that none of the leaves in a node will match a slot occupied by a
|
||||||
|
metadata pointer. If the metadata pointer is there, any leaf whose key matches
|
||||||
|
the metadata key prefix must be in the subtree that the metadata pointer points
|
||||||
|
to.
|
||||||
|
|
||||||
|
In the above example list of index keys, node A will contain::
|
||||||
|
|
||||||
|
SLOT CONTENT INDEX KEY (PREFIX)
|
||||||
|
==== =============== ==================
|
||||||
|
1 PTR TO NODE B 1*
|
||||||
|
any LEAF 9431809de993ba
|
||||||
|
any LEAF b4542910809cd
|
||||||
|
e PTR TO NODE F e*
|
||||||
|
any LEAF f3842239082
|
||||||
|
|
||||||
|
and node B::
|
||||||
|
|
||||||
|
3 PTR TO NODE C 13*
|
||||||
|
any LEAF 1458952489
|
||||||
|
|
||||||
|
|
||||||
|
Shortcuts
|
||||||
|
---------
|
||||||
|
|
||||||
|
Shortcuts are metadata records that jump over a piece of keyspace. A shortcut
|
||||||
|
is a replacement for a series of single-occupancy nodes ascending through the
|
||||||
|
levels. Shortcuts exist to save memory and to speed up traversal.
|
||||||
|
|
||||||
|
It is possible for the root of the tree to be a shortcut - say, for example,
|
||||||
|
the tree contains at least 17 nodes all with key prefix ``1111``. The
|
||||||
|
insertion algorithm will insert a shortcut to skip over the ``1111`` keyspace
|
||||||
|
in a single bound and get to the fourth level where these actually become
|
||||||
|
different.
|
||||||
|
|
||||||
|
|
||||||
|
Splitting And Collapsing Nodes
|
||||||
|
------------------------------
|
||||||
|
|
||||||
|
Each node has a maximum capacity of 16 leaves and metadata pointers. If the
|
||||||
|
insertion algorithm finds that it is trying to insert a 17th object into a
|
||||||
|
node, that node will be split such that at least two leaves that have a common
|
||||||
|
key segment at that level end up in a separate node rooted on that slot for
|
||||||
|
that common key segment.
|
||||||
|
|
||||||
|
If the leaves in a full node and the leaf that is being inserted are
|
||||||
|
sufficiently similar, then a shortcut will be inserted into the tree.
|
||||||
|
|
||||||
|
When the number of objects in the subtree rooted at a node falls to 16 or
|
||||||
|
fewer, then the subtree will be collapsed down to a single node - and this will
|
||||||
|
ripple towards the root if possible.
|
||||||
|
|
||||||
|
|
||||||
|
Non-Recursive Iteration
|
||||||
|
-----------------------
|
||||||
|
|
||||||
|
Each node and shortcut contains a back pointer to its parent and the number of
|
||||||
|
slot in that parent that points to it. None-recursive iteration uses these to
|
||||||
|
proceed rootwards through the tree, going to the parent node, slot N + 1 to
|
||||||
|
make sure progress is made without the need for a stack.
|
||||||
|
|
||||||
|
The backpointers, however, make simultaneous alteration and iteration tricky.
|
||||||
|
|
||||||
|
|
||||||
|
Simultaneous Alteration And Iteration
|
||||||
|
-------------------------------------
|
||||||
|
|
||||||
|
There are a number of cases to consider:
|
||||||
|
|
||||||
|
1. Simple insert/replace. This involves simply replacing a NULL or old
|
||||||
|
matching leaf pointer with the pointer to the new leaf after a barrier.
|
||||||
|
The metadata blocks don't change otherwise. An old leaf won't be freed
|
||||||
|
until after the RCU grace period.
|
||||||
|
|
||||||
|
2. Simple delete. This involves just clearing an old matching leaf. The
|
||||||
|
metadata blocks don't change otherwise. The old leaf won't be freed until
|
||||||
|
after the RCU grace period.
|
||||||
|
|
||||||
|
3. Insertion replacing part of a subtree that we haven't yet entered. This
|
||||||
|
may involve replacement of part of that subtree - but that won't affect
|
||||||
|
the iteration as we won't have reached the pointer to it yet and the
|
||||||
|
ancestry blocks are not replaced (the layout of those does not change).
|
||||||
|
|
||||||
|
4. Insertion replacing nodes that we're actively processing. This isn't a
|
||||||
|
problem as we've passed the anchoring pointer and won't switch onto the
|
||||||
|
new layout until we follow the back pointers - at which point we've
|
||||||
|
already examined the leaves in the replaced node (we iterate over all the
|
||||||
|
leaves in a node before following any of its metadata pointers).
|
||||||
|
|
||||||
|
We might, however, re-see some leaves that have been split out into a new
|
||||||
|
branch that's in a slot further along than we were at.
|
||||||
|
|
||||||
|
5. Insertion replacing nodes that we're processing a dependent branch of.
|
||||||
|
This won't affect us until we follow the back pointers. Similar to (4).
|
||||||
|
|
||||||
|
6. Deletion collapsing a branch under us. This doesn't affect us because the
|
||||||
|
back pointers will get us back to the parent of the new node before we
|
||||||
|
could see the new node. The entire collapsed subtree is thrown away
|
||||||
|
unchanged - and will still be rooted on the same slot, so we shouldn't
|
||||||
|
process it a second time as we'll go back to slot + 1.
|
||||||
|
|
||||||
|
.. note::
|
||||||
|
|
||||||
|
Under some circumstances, we need to simultaneously change the parent
|
||||||
|
pointer and the parent slot pointer on a node (say, for example, we
|
||||||
|
inserted another node before it and moved it up a level). We cannot do
|
||||||
|
this without locking against a read - so we have to replace that node too.
|
||||||
|
|
||||||
|
However, when we're changing a shortcut into a node this isn't a problem
|
||||||
|
as shortcuts only have one slot and so the parent slot number isn't used
|
||||||
|
when traversing backwards over one. This means that it's okay to change
|
||||||
|
the slot number first - provided suitable barriers are used to make sure
|
||||||
|
the parent slot number is read after the back pointer.
|
||||||
|
|
||||||
|
Obsolete blocks and leaves are freed up after an RCU grace period has passed,
|
||||||
|
so as long as anyone doing walking or iteration holds the RCU read lock, the
|
||||||
|
old superstructure should not go away on them.
|
|
@ -1,36 +1,42 @@
|
||||||
Semantics and Behavior of Atomic and
|
=======================================================
|
||||||
Bitmask Operations
|
Semantics and Behavior of Atomic and Bitmask Operations
|
||||||
|
=======================================================
|
||||||
|
|
||||||
David S. Miller
|
:Author: David S. Miller
|
||||||
|
|
||||||
This document is intended to serve as a guide to Linux port
|
This document is intended to serve as a guide to Linux port
|
||||||
maintainers on how to implement atomic counter, bitops, and spinlock
|
maintainers on how to implement atomic counter, bitops, and spinlock
|
||||||
interfaces properly.
|
interfaces properly.
|
||||||
|
|
||||||
The atomic_t type should be defined as a signed integer and
|
Atomic Type And Operations
|
||||||
|
==========================
|
||||||
|
|
||||||
|
The atomic_t type should be defined as a signed integer and
|
||||||
the atomic_long_t type as a signed long integer. Also, they should
|
the atomic_long_t type as a signed long integer. Also, they should
|
||||||
be made opaque such that any kind of cast to a normal C integer type
|
be made opaque such that any kind of cast to a normal C integer type
|
||||||
will fail. Something like the following should suffice:
|
will fail. Something like the following should suffice::
|
||||||
|
|
||||||
typedef struct { int counter; } atomic_t;
|
typedef struct { int counter; } atomic_t;
|
||||||
typedef struct { long counter; } atomic_long_t;
|
typedef struct { long counter; } atomic_long_t;
|
||||||
|
|
||||||
Historically, counter has been declared volatile. This is now discouraged.
|
Historically, counter has been declared volatile. This is now discouraged.
|
||||||
See Documentation/process/volatile-considered-harmful.rst for the complete rationale.
|
See :ref:`Documentation/process/volatile-considered-harmful.rst
|
||||||
|
<volatile_considered_harmful>` for the complete rationale.
|
||||||
|
|
||||||
local_t is very similar to atomic_t. If the counter is per CPU and only
|
local_t is very similar to atomic_t. If the counter is per CPU and only
|
||||||
updated by one CPU, local_t is probably more appropriate. Please see
|
updated by one CPU, local_t is probably more appropriate. Please see
|
||||||
Documentation/local_ops.txt for the semantics of local_t.
|
:ref:`Documentation/core-api/local_ops.rst <local_ops>` for the semantics of
|
||||||
|
local_t.
|
||||||
|
|
||||||
The first operations to implement for atomic_t's are the initializers and
|
The first operations to implement for atomic_t's are the initializers and
|
||||||
plain reads.
|
plain reads. ::
|
||||||
|
|
||||||
#define ATOMIC_INIT(i) { (i) }
|
#define ATOMIC_INIT(i) { (i) }
|
||||||
#define atomic_set(v, i) ((v)->counter = (i))
|
#define atomic_set(v, i) ((v)->counter = (i))
|
||||||
|
|
||||||
The first macro is used in definitions, such as:
|
The first macro is used in definitions, such as::
|
||||||
|
|
||||||
static atomic_t my_counter = ATOMIC_INIT(1);
|
static atomic_t my_counter = ATOMIC_INIT(1);
|
||||||
|
|
||||||
The initializer is atomic in that the return values of the atomic operations
|
The initializer is atomic in that the return values of the atomic operations
|
||||||
are guaranteed to be correct reflecting the initialized value if the
|
are guaranteed to be correct reflecting the initialized value if the
|
||||||
|
@ -38,10 +44,10 @@ initializer is used before runtime. If the initializer is used at runtime, a
|
||||||
proper implicit or explicit read memory barrier is needed before reading the
|
proper implicit or explicit read memory barrier is needed before reading the
|
||||||
value with atomic_read from another thread.
|
value with atomic_read from another thread.
|
||||||
|
|
||||||
As with all of the atomic_ interfaces, replace the leading "atomic_"
|
As with all of the ``atomic_`` interfaces, replace the leading ``atomic_``
|
||||||
with "atomic_long_" to operate on atomic_long_t.
|
with ``atomic_long_`` to operate on atomic_long_t.
|
||||||
|
|
||||||
The second interface can be used at runtime, as in:
|
The second interface can be used at runtime, as in::
|
||||||
|
|
||||||
struct foo { atomic_t counter; };
|
struct foo { atomic_t counter; };
|
||||||
...
|
...
|
||||||
|
@ -59,7 +65,7 @@ been set with this operation or set with another operation. A proper implicit
|
||||||
or explicit memory barrier is needed before the value set with the operation
|
or explicit memory barrier is needed before the value set with the operation
|
||||||
is guaranteed to be readable with atomic_read from another thread.
|
is guaranteed to be readable with atomic_read from another thread.
|
||||||
|
|
||||||
Next, we have:
|
Next, we have::
|
||||||
|
|
||||||
#define atomic_read(v) ((v)->counter)
|
#define atomic_read(v) ((v)->counter)
|
||||||
|
|
||||||
|
@ -73,20 +79,21 @@ initialization by any other thread is visible yet, so the user of the
|
||||||
interface must take care of that with a proper implicit or explicit memory
|
interface must take care of that with a proper implicit or explicit memory
|
||||||
barrier.
|
barrier.
|
||||||
|
|
||||||
*** WARNING: atomic_read() and atomic_set() DO NOT IMPLY BARRIERS! ***
|
.. warning::
|
||||||
|
|
||||||
Some architectures may choose to use the volatile keyword, barriers, or inline
|
``atomic_read()`` and ``atomic_set()`` DO NOT IMPLY BARRIERS!
|
||||||
assembly to guarantee some degree of immediacy for atomic_read() and
|
|
||||||
atomic_set(). This is not uniformly guaranteed, and may change in the future,
|
|
||||||
so all users of atomic_t should treat atomic_read() and atomic_set() as simple
|
|
||||||
C statements that may be reordered or optimized away entirely by the compiler
|
|
||||||
or processor, and explicitly invoke the appropriate compiler and/or memory
|
|
||||||
barrier for each use case. Failure to do so will result in code that may
|
|
||||||
suddenly break when used with different architectures or compiler
|
|
||||||
optimizations, or even changes in unrelated code which changes how the
|
|
||||||
compiler optimizes the section accessing atomic_t variables.
|
|
||||||
|
|
||||||
*** YOU HAVE BEEN WARNED! ***
|
Some architectures may choose to use the volatile keyword, barriers, or
|
||||||
|
inline assembly to guarantee some degree of immediacy for atomic_read()
|
||||||
|
and atomic_set(). This is not uniformly guaranteed, and may change in
|
||||||
|
the future, so all users of atomic_t should treat atomic_read() and
|
||||||
|
atomic_set() as simple C statements that may be reordered or optimized
|
||||||
|
away entirely by the compiler or processor, and explicitly invoke the
|
||||||
|
appropriate compiler and/or memory barrier for each use case. Failure
|
||||||
|
to do so will result in code that may suddenly break when used with
|
||||||
|
different architectures or compiler optimizations, or even changes in
|
||||||
|
unrelated code which changes how the compiler optimizes the section
|
||||||
|
accessing atomic_t variables.
|
||||||
|
|
||||||
Properly aligned pointers, longs, ints, and chars (and unsigned
|
Properly aligned pointers, longs, ints, and chars (and unsigned
|
||||||
equivalents) may be atomically loaded from and stored to in the same
|
equivalents) may be atomically loaded from and stored to in the same
|
||||||
|
@ -95,14 +102,14 @@ and WRITE_ONCE() macros should be used to prevent the compiler from using
|
||||||
optimizations that might otherwise optimize accesses out of existence on
|
optimizations that might otherwise optimize accesses out of existence on
|
||||||
the one hand, or that might create unsolicited accesses on the other.
|
the one hand, or that might create unsolicited accesses on the other.
|
||||||
|
|
||||||
For example consider the following code:
|
For example consider the following code::
|
||||||
|
|
||||||
while (a > 0)
|
while (a > 0)
|
||||||
do_something();
|
do_something();
|
||||||
|
|
||||||
If the compiler can prove that do_something() does not store to the
|
If the compiler can prove that do_something() does not store to the
|
||||||
variable a, then the compiler is within its rights transforming this to
|
variable a, then the compiler is within its rights transforming this to
|
||||||
the following:
|
the following::
|
||||||
|
|
||||||
tmp = a;
|
tmp = a;
|
||||||
if (a > 0)
|
if (a > 0)
|
||||||
|
@ -110,14 +117,14 @@ the following:
|
||||||
do_something();
|
do_something();
|
||||||
|
|
||||||
If you don't want the compiler to do this (and you probably don't), then
|
If you don't want the compiler to do this (and you probably don't), then
|
||||||
you should use something like the following:
|
you should use something like the following::
|
||||||
|
|
||||||
while (READ_ONCE(a) < 0)
|
while (READ_ONCE(a) < 0)
|
||||||
do_something();
|
do_something();
|
||||||
|
|
||||||
Alternatively, you could place a barrier() call in the loop.
|
Alternatively, you could place a barrier() call in the loop.
|
||||||
|
|
||||||
For another example, consider the following code:
|
For another example, consider the following code::
|
||||||
|
|
||||||
tmp_a = a;
|
tmp_a = a;
|
||||||
do_something_with(tmp_a);
|
do_something_with(tmp_a);
|
||||||
|
@ -125,7 +132,7 @@ For another example, consider the following code:
|
||||||
|
|
||||||
If the compiler can prove that do_something_with() does not store to the
|
If the compiler can prove that do_something_with() does not store to the
|
||||||
variable a, then the compiler is within its rights to manufacture an
|
variable a, then the compiler is within its rights to manufacture an
|
||||||
additional load as follows:
|
additional load as follows::
|
||||||
|
|
||||||
tmp_a = a;
|
tmp_a = a;
|
||||||
do_something_with(tmp_a);
|
do_something_with(tmp_a);
|
||||||
|
@ -139,7 +146,7 @@ The compiler would be likely to manufacture this additional load if
|
||||||
do_something_with() was an inline function that made very heavy use
|
do_something_with() was an inline function that made very heavy use
|
||||||
of registers: reloading from variable a could save a flush to the
|
of registers: reloading from variable a could save a flush to the
|
||||||
stack and later reload. To prevent the compiler from attacking your
|
stack and later reload. To prevent the compiler from attacking your
|
||||||
code in this manner, write the following:
|
code in this manner, write the following::
|
||||||
|
|
||||||
tmp_a = READ_ONCE(a);
|
tmp_a = READ_ONCE(a);
|
||||||
do_something_with(tmp_a);
|
do_something_with(tmp_a);
|
||||||
|
@ -147,7 +154,7 @@ code in this manner, write the following:
|
||||||
|
|
||||||
For a final example, consider the following code, assuming that the
|
For a final example, consider the following code, assuming that the
|
||||||
variable a is set at boot time before the second CPU is brought online
|
variable a is set at boot time before the second CPU is brought online
|
||||||
and never changed later, so that memory barriers are not needed:
|
and never changed later, so that memory barriers are not needed::
|
||||||
|
|
||||||
if (a)
|
if (a)
|
||||||
b = 9;
|
b = 9;
|
||||||
|
@ -155,7 +162,7 @@ and never changed later, so that memory barriers are not needed:
|
||||||
b = 42;
|
b = 42;
|
||||||
|
|
||||||
The compiler is within its rights to manufacture an additional store
|
The compiler is within its rights to manufacture an additional store
|
||||||
by transforming the above code into the following:
|
by transforming the above code into the following::
|
||||||
|
|
||||||
b = 42;
|
b = 42;
|
||||||
if (a)
|
if (a)
|
||||||
|
@ -163,7 +170,7 @@ by transforming the above code into the following:
|
||||||
|
|
||||||
This could come as a fatal surprise to other code running concurrently
|
This could come as a fatal surprise to other code running concurrently
|
||||||
that expected b to never have the value 42 if a was zero. To prevent
|
that expected b to never have the value 42 if a was zero. To prevent
|
||||||
the compiler from doing this, write something like:
|
the compiler from doing this, write something like::
|
||||||
|
|
||||||
if (a)
|
if (a)
|
||||||
WRITE_ONCE(b, 9);
|
WRITE_ONCE(b, 9);
|
||||||
|
@ -173,10 +180,12 @@ the compiler from doing this, write something like:
|
||||||
Don't even -think- about doing this without proper use of memory barriers,
|
Don't even -think- about doing this without proper use of memory barriers,
|
||||||
locks, or atomic operations if variable a can change at runtime!
|
locks, or atomic operations if variable a can change at runtime!
|
||||||
|
|
||||||
*** WARNING: READ_ONCE() OR WRITE_ONCE() DO NOT IMPLY A BARRIER! ***
|
.. warning::
|
||||||
|
|
||||||
|
``READ_ONCE()`` OR ``WRITE_ONCE()`` DO NOT IMPLY A BARRIER!
|
||||||
|
|
||||||
Now, we move onto the atomic operation interfaces typically implemented with
|
Now, we move onto the atomic operation interfaces typically implemented with
|
||||||
the help of assembly code.
|
the help of assembly code. ::
|
||||||
|
|
||||||
void atomic_add(int i, atomic_t *v);
|
void atomic_add(int i, atomic_t *v);
|
||||||
void atomic_sub(int i, atomic_t *v);
|
void atomic_sub(int i, atomic_t *v);
|
||||||
|
@ -192,7 +201,7 @@ One very important aspect of these two routines is that they DO NOT
|
||||||
require any explicit memory barriers. They need only perform the
|
require any explicit memory barriers. They need only perform the
|
||||||
atomic_t counter update in an SMP safe manner.
|
atomic_t counter update in an SMP safe manner.
|
||||||
|
|
||||||
Next, we have:
|
Next, we have::
|
||||||
|
|
||||||
int atomic_inc_return(atomic_t *v);
|
int atomic_inc_return(atomic_t *v);
|
||||||
int atomic_dec_return(atomic_t *v);
|
int atomic_dec_return(atomic_t *v);
|
||||||
|
@ -214,7 +223,7 @@ If the atomic instructions used in an implementation provide explicit
|
||||||
memory barrier semantics which satisfy the above requirements, that is
|
memory barrier semantics which satisfy the above requirements, that is
|
||||||
fine as well.
|
fine as well.
|
||||||
|
|
||||||
Let's move on:
|
Let's move on::
|
||||||
|
|
||||||
int atomic_add_return(int i, atomic_t *v);
|
int atomic_add_return(int i, atomic_t *v);
|
||||||
int atomic_sub_return(int i, atomic_t *v);
|
int atomic_sub_return(int i, atomic_t *v);
|
||||||
|
@ -224,7 +233,7 @@ explicit counter adjustment is given instead of the implicit "1".
|
||||||
This means that like atomic_{inc,dec}_return(), the memory barrier
|
This means that like atomic_{inc,dec}_return(), the memory barrier
|
||||||
semantics are required.
|
semantics are required.
|
||||||
|
|
||||||
Next:
|
Next::
|
||||||
|
|
||||||
int atomic_inc_and_test(atomic_t *v);
|
int atomic_inc_and_test(atomic_t *v);
|
||||||
int atomic_dec_and_test(atomic_t *v);
|
int atomic_dec_and_test(atomic_t *v);
|
||||||
|
@ -234,13 +243,13 @@ given atomic counter. They return a boolean indicating whether the
|
||||||
resulting counter value was zero or not.
|
resulting counter value was zero or not.
|
||||||
|
|
||||||
Again, these primitives provide explicit memory barrier semantics around
|
Again, these primitives provide explicit memory barrier semantics around
|
||||||
the atomic operation.
|
the atomic operation::
|
||||||
|
|
||||||
int atomic_sub_and_test(int i, atomic_t *v);
|
int atomic_sub_and_test(int i, atomic_t *v);
|
||||||
|
|
||||||
This is identical to atomic_dec_and_test() except that an explicit
|
This is identical to atomic_dec_and_test() except that an explicit
|
||||||
decrement is given instead of the implicit "1". This primitive must
|
decrement is given instead of the implicit "1". This primitive must
|
||||||
provide explicit memory barrier semantics around the operation.
|
provide explicit memory barrier semantics around the operation::
|
||||||
|
|
||||||
int atomic_add_negative(int i, atomic_t *v);
|
int atomic_add_negative(int i, atomic_t *v);
|
||||||
|
|
||||||
|
@ -249,7 +258,7 @@ is return which indicates whether the resulting counter value is negative.
|
||||||
This primitive must provide explicit memory barrier semantics around
|
This primitive must provide explicit memory barrier semantics around
|
||||||
the operation.
|
the operation.
|
||||||
|
|
||||||
Then:
|
Then::
|
||||||
|
|
||||||
int atomic_xchg(atomic_t *v, int new);
|
int atomic_xchg(atomic_t *v, int new);
|
||||||
|
|
||||||
|
@ -257,14 +266,14 @@ This performs an atomic exchange operation on the atomic variable v, setting
|
||||||
the given new value. It returns the old value that the atomic variable v had
|
the given new value. It returns the old value that the atomic variable v had
|
||||||
just before the operation.
|
just before the operation.
|
||||||
|
|
||||||
atomic_xchg must provide explicit memory barriers around the operation.
|
atomic_xchg must provide explicit memory barriers around the operation. ::
|
||||||
|
|
||||||
int atomic_cmpxchg(atomic_t *v, int old, int new);
|
int atomic_cmpxchg(atomic_t *v, int old, int new);
|
||||||
|
|
||||||
This performs an atomic compare exchange operation on the atomic value v,
|
This performs an atomic compare exchange operation on the atomic value v,
|
||||||
with the given old and new values. Like all atomic_xxx operations,
|
with the given old and new values. Like all atomic_xxx operations,
|
||||||
atomic_cmpxchg will only satisfy its atomicity semantics as long as all
|
atomic_cmpxchg will only satisfy its atomicity semantics as long as all
|
||||||
other accesses of *v are performed through atomic_xxx operations.
|
other accesses of \*v are performed through atomic_xxx operations.
|
||||||
|
|
||||||
atomic_cmpxchg must provide explicit memory barriers around the operation,
|
atomic_cmpxchg must provide explicit memory barriers around the operation,
|
||||||
although if the comparison fails then no memory ordering guarantees are
|
although if the comparison fails then no memory ordering guarantees are
|
||||||
|
@ -273,7 +282,7 @@ required.
|
||||||
The semantics for atomic_cmpxchg are the same as those defined for 'cas'
|
The semantics for atomic_cmpxchg are the same as those defined for 'cas'
|
||||||
below.
|
below.
|
||||||
|
|
||||||
Finally:
|
Finally::
|
||||||
|
|
||||||
int atomic_add_unless(atomic_t *v, int a, int u);
|
int atomic_add_unless(atomic_t *v, int a, int u);
|
||||||
|
|
||||||
|
@ -289,12 +298,12 @@ atomic_inc_not_zero, equivalent to atomic_add_unless(v, 1, 0)
|
||||||
|
|
||||||
If a caller requires memory barrier semantics around an atomic_t
|
If a caller requires memory barrier semantics around an atomic_t
|
||||||
operation which does not return a value, a set of interfaces are
|
operation which does not return a value, a set of interfaces are
|
||||||
defined which accomplish this:
|
defined which accomplish this::
|
||||||
|
|
||||||
void smp_mb__before_atomic(void);
|
void smp_mb__before_atomic(void);
|
||||||
void smp_mb__after_atomic(void);
|
void smp_mb__after_atomic(void);
|
||||||
|
|
||||||
For example, smp_mb__before_atomic() can be used like so:
|
For example, smp_mb__before_atomic() can be used like so::
|
||||||
|
|
||||||
obj->dead = 1;
|
obj->dead = 1;
|
||||||
smp_mb__before_atomic();
|
smp_mb__before_atomic();
|
||||||
|
@ -315,67 +324,69 @@ atomic_t implementation above can have disastrous results. Here is
|
||||||
an example, which follows a pattern occurring frequently in the Linux
|
an example, which follows a pattern occurring frequently in the Linux
|
||||||
kernel. It is the use of atomic counters to implement reference
|
kernel. It is the use of atomic counters to implement reference
|
||||||
counting, and it works such that once the counter falls to zero it can
|
counting, and it works such that once the counter falls to zero it can
|
||||||
be guaranteed that no other entity can be accessing the object:
|
be guaranteed that no other entity can be accessing the object::
|
||||||
|
|
||||||
static void obj_list_add(struct obj *obj, struct list_head *head)
|
static void obj_list_add(struct obj *obj, struct list_head *head)
|
||||||
{
|
{
|
||||||
obj->active = 1;
|
obj->active = 1;
|
||||||
list_add(&obj->list, head);
|
list_add(&obj->list, head);
|
||||||
}
|
}
|
||||||
|
|
||||||
static void obj_list_del(struct obj *obj)
|
static void obj_list_del(struct obj *obj)
|
||||||
{
|
{
|
||||||
list_del(&obj->list);
|
list_del(&obj->list);
|
||||||
obj->active = 0;
|
obj->active = 0;
|
||||||
}
|
}
|
||||||
|
|
||||||
static void obj_destroy(struct obj *obj)
|
static void obj_destroy(struct obj *obj)
|
||||||
{
|
{
|
||||||
BUG_ON(obj->active);
|
BUG_ON(obj->active);
|
||||||
kfree(obj);
|
kfree(obj);
|
||||||
}
|
}
|
||||||
|
|
||||||
struct obj *obj_list_peek(struct list_head *head)
|
struct obj *obj_list_peek(struct list_head *head)
|
||||||
{
|
{
|
||||||
if (!list_empty(head)) {
|
if (!list_empty(head)) {
|
||||||
|
struct obj *obj;
|
||||||
|
|
||||||
|
obj = list_entry(head->next, struct obj, list);
|
||||||
|
atomic_inc(&obj->refcnt);
|
||||||
|
return obj;
|
||||||
|
}
|
||||||
|
return NULL;
|
||||||
|
}
|
||||||
|
|
||||||
|
void obj_poke(void)
|
||||||
|
{
|
||||||
struct obj *obj;
|
struct obj *obj;
|
||||||
|
|
||||||
obj = list_entry(head->next, struct obj, list);
|
spin_lock(&global_list_lock);
|
||||||
atomic_inc(&obj->refcnt);
|
obj = obj_list_peek(&global_list);
|
||||||
return obj;
|
spin_unlock(&global_list_lock);
|
||||||
|
|
||||||
|
if (obj) {
|
||||||
|
obj->ops->poke(obj);
|
||||||
|
if (atomic_dec_and_test(&obj->refcnt))
|
||||||
|
obj_destroy(obj);
|
||||||
|
}
|
||||||
}
|
}
|
||||||
return NULL;
|
|
||||||
}
|
|
||||||
|
|
||||||
void obj_poke(void)
|
void obj_timeout(struct obj *obj)
|
||||||
{
|
{
|
||||||
struct obj *obj;
|
spin_lock(&global_list_lock);
|
||||||
|
obj_list_del(obj);
|
||||||
|
spin_unlock(&global_list_lock);
|
||||||
|
|
||||||
spin_lock(&global_list_lock);
|
|
||||||
obj = obj_list_peek(&global_list);
|
|
||||||
spin_unlock(&global_list_lock);
|
|
||||||
|
|
||||||
if (obj) {
|
|
||||||
obj->ops->poke(obj);
|
|
||||||
if (atomic_dec_and_test(&obj->refcnt))
|
if (atomic_dec_and_test(&obj->refcnt))
|
||||||
obj_destroy(obj);
|
obj_destroy(obj);
|
||||||
}
|
}
|
||||||
}
|
|
||||||
|
|
||||||
void obj_timeout(struct obj *obj)
|
.. note::
|
||||||
{
|
|
||||||
spin_lock(&global_list_lock);
|
|
||||||
obj_list_del(obj);
|
|
||||||
spin_unlock(&global_list_lock);
|
|
||||||
|
|
||||||
if (atomic_dec_and_test(&obj->refcnt))
|
This is a simplification of the ARP queue management in the generic
|
||||||
obj_destroy(obj);
|
neighbour discover code of the networking. Olaf Kirch found a bug wrt.
|
||||||
}
|
memory barriers in kfree_skb() that exposed the atomic_t memory barrier
|
||||||
|
requirements quite clearly.
|
||||||
(This is a simplification of the ARP queue management in the
|
|
||||||
generic neighbour discover code of the networking. Olaf Kirch
|
|
||||||
found a bug wrt. memory barriers in kfree_skb() that exposed
|
|
||||||
the atomic_t memory barrier requirements quite clearly.)
|
|
||||||
|
|
||||||
Given the above scheme, it must be the case that the obj->active
|
Given the above scheme, it must be the case that the obj->active
|
||||||
update done by the obj list deletion be visible to other processors
|
update done by the obj list deletion be visible to other processors
|
||||||
|
@ -383,7 +394,7 @@ before the atomic counter decrement is performed.
|
||||||
|
|
||||||
Otherwise, the counter could fall to zero, yet obj->active would still
|
Otherwise, the counter could fall to zero, yet obj->active would still
|
||||||
be set, thus triggering the assertion in obj_destroy(). The error
|
be set, thus triggering the assertion in obj_destroy(). The error
|
||||||
sequence looks like this:
|
sequence looks like this::
|
||||||
|
|
||||||
cpu 0 cpu 1
|
cpu 0 cpu 1
|
||||||
obj_poke() obj_timeout()
|
obj_poke() obj_timeout()
|
||||||
|
@ -420,6 +431,10 @@ same scheme.
|
||||||
Another note is that the atomic_t operations returning values are
|
Another note is that the atomic_t operations returning values are
|
||||||
extremely slow on an old 386.
|
extremely slow on an old 386.
|
||||||
|
|
||||||
|
|
||||||
|
Atomic Bitmask
|
||||||
|
==============
|
||||||
|
|
||||||
We will now cover the atomic bitmask operations. You will find that
|
We will now cover the atomic bitmask operations. You will find that
|
||||||
their SMP and memory barrier semantics are similar in shape and scope
|
their SMP and memory barrier semantics are similar in shape and scope
|
||||||
to the atomic_t ops above.
|
to the atomic_t ops above.
|
||||||
|
@ -427,7 +442,7 @@ to the atomic_t ops above.
|
||||||
Native atomic bit operations are defined to operate on objects aligned
|
Native atomic bit operations are defined to operate on objects aligned
|
||||||
to the size of an "unsigned long" C data type, and are least of that
|
to the size of an "unsigned long" C data type, and are least of that
|
||||||
size. The endianness of the bits within each "unsigned long" are the
|
size. The endianness of the bits within each "unsigned long" are the
|
||||||
native endianness of the cpu.
|
native endianness of the cpu. ::
|
||||||
|
|
||||||
void set_bit(unsigned long nr, volatile unsigned long *addr);
|
void set_bit(unsigned long nr, volatile unsigned long *addr);
|
||||||
void clear_bit(unsigned long nr, volatile unsigned long *addr);
|
void clear_bit(unsigned long nr, volatile unsigned long *addr);
|
||||||
|
@ -437,7 +452,7 @@ These routines set, clear, and change, respectively, the bit number
|
||||||
indicated by "nr" on the bit mask pointed to by "ADDR".
|
indicated by "nr" on the bit mask pointed to by "ADDR".
|
||||||
|
|
||||||
They must execute atomically, yet there are no implicit memory barrier
|
They must execute atomically, yet there are no implicit memory barrier
|
||||||
semantics required of these interfaces.
|
semantics required of these interfaces. ::
|
||||||
|
|
||||||
int test_and_set_bit(unsigned long nr, volatile unsigned long *addr);
|
int test_and_set_bit(unsigned long nr, volatile unsigned long *addr);
|
||||||
int test_and_clear_bit(unsigned long nr, volatile unsigned long *addr);
|
int test_and_clear_bit(unsigned long nr, volatile unsigned long *addr);
|
||||||
|
@ -466,7 +481,7 @@ must provide explicit memory barrier semantics around their execution.
|
||||||
All memory operations before the atomic bit operation call must be
|
All memory operations before the atomic bit operation call must be
|
||||||
made visible globally before the atomic bit operation is made visible.
|
made visible globally before the atomic bit operation is made visible.
|
||||||
Likewise, the atomic bit operation must be visible globally before any
|
Likewise, the atomic bit operation must be visible globally before any
|
||||||
subsequent memory operation is made visible. For example:
|
subsequent memory operation is made visible. For example::
|
||||||
|
|
||||||
obj->dead = 1;
|
obj->dead = 1;
|
||||||
if (test_and_set_bit(0, &obj->flags))
|
if (test_and_set_bit(0, &obj->flags))
|
||||||
|
@ -479,7 +494,7 @@ done by test_and_set_bit() becomes visible. Likewise, the atomic
|
||||||
memory operation done by test_and_set_bit() must become visible before
|
memory operation done by test_and_set_bit() must become visible before
|
||||||
"obj->killed = 1;" is visible.
|
"obj->killed = 1;" is visible.
|
||||||
|
|
||||||
Finally there is the basic operation:
|
Finally there is the basic operation::
|
||||||
|
|
||||||
int test_bit(unsigned long nr, __const__ volatile unsigned long *addr);
|
int test_bit(unsigned long nr, __const__ volatile unsigned long *addr);
|
||||||
|
|
||||||
|
@ -488,13 +503,13 @@ pointed to by "addr".
|
||||||
|
|
||||||
If explicit memory barriers are required around {set,clear}_bit() (which do
|
If explicit memory barriers are required around {set,clear}_bit() (which do
|
||||||
not return a value, and thus does not need to provide memory barrier
|
not return a value, and thus does not need to provide memory barrier
|
||||||
semantics), two interfaces are provided:
|
semantics), two interfaces are provided::
|
||||||
|
|
||||||
void smp_mb__before_atomic(void);
|
void smp_mb__before_atomic(void);
|
||||||
void smp_mb__after_atomic(void);
|
void smp_mb__after_atomic(void);
|
||||||
|
|
||||||
They are used as follows, and are akin to their atomic_t operation
|
They are used as follows, and are akin to their atomic_t operation
|
||||||
brothers:
|
brothers::
|
||||||
|
|
||||||
/* All memory operations before this call will
|
/* All memory operations before this call will
|
||||||
* be globally visible before the clear_bit().
|
* be globally visible before the clear_bit().
|
||||||
|
@ -511,7 +526,7 @@ There are two special bitops with lock barrier semantics (acquire/release,
|
||||||
same as spinlocks). These operate in the same way as their non-_lock/unlock
|
same as spinlocks). These operate in the same way as their non-_lock/unlock
|
||||||
postfixed variants, except that they are to provide acquire/release semantics,
|
postfixed variants, except that they are to provide acquire/release semantics,
|
||||||
respectively. This means they can be used for bit_spin_trylock and
|
respectively. This means they can be used for bit_spin_trylock and
|
||||||
bit_spin_unlock type operations without specifying any more barriers.
|
bit_spin_unlock type operations without specifying any more barriers. ::
|
||||||
|
|
||||||
int test_and_set_bit_lock(unsigned long nr, unsigned long *addr);
|
int test_and_set_bit_lock(unsigned long nr, unsigned long *addr);
|
||||||
void clear_bit_unlock(unsigned long nr, unsigned long *addr);
|
void clear_bit_unlock(unsigned long nr, unsigned long *addr);
|
||||||
|
@ -526,7 +541,7 @@ provided. They are used in contexts where some other higher-level SMP
|
||||||
locking scheme is being used to protect the bitmask, and thus less
|
locking scheme is being used to protect the bitmask, and thus less
|
||||||
expensive non-atomic operations may be used in the implementation.
|
expensive non-atomic operations may be used in the implementation.
|
||||||
They have names similar to the above bitmask operation interfaces,
|
They have names similar to the above bitmask operation interfaces,
|
||||||
except that two underscores are prefixed to the interface name.
|
except that two underscores are prefixed to the interface name. ::
|
||||||
|
|
||||||
void __set_bit(unsigned long nr, volatile unsigned long *addr);
|
void __set_bit(unsigned long nr, volatile unsigned long *addr);
|
||||||
void __clear_bit(unsigned long nr, volatile unsigned long *addr);
|
void __clear_bit(unsigned long nr, volatile unsigned long *addr);
|
||||||
|
@ -542,9 +557,11 @@ The routines xchg() and cmpxchg() must provide the same exact
|
||||||
memory-barrier semantics as the atomic and bit operations returning
|
memory-barrier semantics as the atomic and bit operations returning
|
||||||
values.
|
values.
|
||||||
|
|
||||||
Note: If someone wants to use xchg(), cmpxchg() and their variants,
|
.. note::
|
||||||
linux/atomic.h should be included rather than asm/cmpxchg.h, unless
|
|
||||||
the code is in arch/* and can take care of itself.
|
If someone wants to use xchg(), cmpxchg() and their variants,
|
||||||
|
linux/atomic.h should be included rather than asm/cmpxchg.h, unless the
|
||||||
|
code is in arch/* and can take care of itself.
|
||||||
|
|
||||||
Spinlocks and rwlocks have memory barrier expectations as well.
|
Spinlocks and rwlocks have memory barrier expectations as well.
|
||||||
The rule to follow is simple:
|
The rule to follow is simple:
|
||||||
|
@ -558,7 +575,7 @@ The rule to follow is simple:
|
||||||
|
|
||||||
Which finally brings us to _atomic_dec_and_lock(). There is an
|
Which finally brings us to _atomic_dec_and_lock(). There is an
|
||||||
architecture-neutral version implemented in lib/dec_and_lock.c,
|
architecture-neutral version implemented in lib/dec_and_lock.c,
|
||||||
but most platforms will wish to optimize this in assembler.
|
but most platforms will wish to optimize this in assembler. ::
|
||||||
|
|
||||||
int _atomic_dec_and_lock(atomic_t *atomic, spinlock_t *lock);
|
int _atomic_dec_and_lock(atomic_t *atomic, spinlock_t *lock);
|
||||||
|
|
||||||
|
@ -573,7 +590,7 @@ sure the spinlock operation is globally visible before any
|
||||||
subsequent memory operation.
|
subsequent memory operation.
|
||||||
|
|
||||||
We can demonstrate this operation more clearly if we define
|
We can demonstrate this operation more clearly if we define
|
||||||
an abstract atomic operation:
|
an abstract atomic operation::
|
||||||
|
|
||||||
long cas(long *mem, long old, long new);
|
long cas(long *mem, long old, long new);
|
||||||
|
|
||||||
|
@ -584,48 +601,48 @@ an abstract atomic operation:
|
||||||
3) Regardless, the current value at "mem" is returned.
|
3) Regardless, the current value at "mem" is returned.
|
||||||
|
|
||||||
As an example usage, here is what an atomic counter update
|
As an example usage, here is what an atomic counter update
|
||||||
might look like:
|
might look like::
|
||||||
|
|
||||||
void example_atomic_inc(long *counter)
|
void example_atomic_inc(long *counter)
|
||||||
{
|
{
|
||||||
long old, new, ret;
|
long old, new, ret;
|
||||||
|
|
||||||
while (1) {
|
while (1) {
|
||||||
old = *counter;
|
old = *counter;
|
||||||
new = old + 1;
|
new = old + 1;
|
||||||
|
|
||||||
ret = cas(counter, old, new);
|
ret = cas(counter, old, new);
|
||||||
if (ret == old)
|
if (ret == old)
|
||||||
break;
|
break;
|
||||||
}
|
|
||||||
}
|
|
||||||
|
|
||||||
Let's use cas() in order to build a pseudo-C atomic_dec_and_lock():
|
|
||||||
|
|
||||||
int _atomic_dec_and_lock(atomic_t *atomic, spinlock_t *lock)
|
|
||||||
{
|
|
||||||
long old, new, ret;
|
|
||||||
int went_to_zero;
|
|
||||||
|
|
||||||
went_to_zero = 0;
|
|
||||||
while (1) {
|
|
||||||
old = atomic_read(atomic);
|
|
||||||
new = old - 1;
|
|
||||||
if (new == 0) {
|
|
||||||
went_to_zero = 1;
|
|
||||||
spin_lock(lock);
|
|
||||||
}
|
|
||||||
ret = cas(atomic, old, new);
|
|
||||||
if (ret == old)
|
|
||||||
break;
|
|
||||||
if (went_to_zero) {
|
|
||||||
spin_unlock(lock);
|
|
||||||
went_to_zero = 0;
|
|
||||||
}
|
}
|
||||||
}
|
}
|
||||||
|
|
||||||
return went_to_zero;
|
Let's use cas() in order to build a pseudo-C atomic_dec_and_lock()::
|
||||||
}
|
|
||||||
|
int _atomic_dec_and_lock(atomic_t *atomic, spinlock_t *lock)
|
||||||
|
{
|
||||||
|
long old, new, ret;
|
||||||
|
int went_to_zero;
|
||||||
|
|
||||||
|
went_to_zero = 0;
|
||||||
|
while (1) {
|
||||||
|
old = atomic_read(atomic);
|
||||||
|
new = old - 1;
|
||||||
|
if (new == 0) {
|
||||||
|
went_to_zero = 1;
|
||||||
|
spin_lock(lock);
|
||||||
|
}
|
||||||
|
ret = cas(atomic, old, new);
|
||||||
|
if (ret == old)
|
||||||
|
break;
|
||||||
|
if (went_to_zero) {
|
||||||
|
spin_unlock(lock);
|
||||||
|
went_to_zero = 0;
|
||||||
|
}
|
||||||
|
}
|
||||||
|
|
||||||
|
return went_to_zero;
|
||||||
|
}
|
||||||
|
|
||||||
Now, as far as memory barriers go, as long as spin_lock()
|
Now, as far as memory barriers go, as long as spin_lock()
|
||||||
strictly orders all subsequent memory operations (including
|
strictly orders all subsequent memory operations (including
|
||||||
|
@ -635,6 +652,7 @@ Said another way, _atomic_dec_and_lock() must guarantee that
|
||||||
a counter dropping to zero is never made visible before the
|
a counter dropping to zero is never made visible before the
|
||||||
spinlock being acquired.
|
spinlock being acquired.
|
||||||
|
|
||||||
Note that this also means that for the case where the counter
|
.. note::
|
||||||
is not dropping to zero, there are no memory ordering
|
|
||||||
requirements.
|
Note that this also means that for the case where the counter is not
|
||||||
|
dropping to zero, there are no memory ordering requirements.
|
|
@ -11,6 +11,9 @@ Core utilities
|
||||||
.. toctree::
|
.. toctree::
|
||||||
:maxdepth: 1
|
:maxdepth: 1
|
||||||
|
|
||||||
|
assoc_array
|
||||||
|
atomic_ops
|
||||||
|
local_ops
|
||||||
workqueue
|
workqueue
|
||||||
|
|
||||||
Interfaces for kernel debugging
|
Interfaces for kernel debugging
|
||||||
|
|
|
@ -0,0 +1,206 @@
|
||||||
|
|
||||||
|
.. _local_ops:
|
||||||
|
|
||||||
|
=================================================
|
||||||
|
Semantics and Behavior of Local Atomic Operations
|
||||||
|
=================================================
|
||||||
|
|
||||||
|
:Author: Mathieu Desnoyers
|
||||||
|
|
||||||
|
|
||||||
|
This document explains the purpose of the local atomic operations, how
|
||||||
|
to implement them for any given architecture and shows how they can be used
|
||||||
|
properly. It also stresses on the precautions that must be taken when reading
|
||||||
|
those local variables across CPUs when the order of memory writes matters.
|
||||||
|
|
||||||
|
.. note::
|
||||||
|
|
||||||
|
Note that ``local_t`` based operations are not recommended for general
|
||||||
|
kernel use. Please use the ``this_cpu`` operations instead unless there is
|
||||||
|
really a special purpose. Most uses of ``local_t`` in the kernel have been
|
||||||
|
replaced by ``this_cpu`` operations. ``this_cpu`` operations combine the
|
||||||
|
relocation with the ``local_t`` like semantics in a single instruction and
|
||||||
|
yield more compact and faster executing code.
|
||||||
|
|
||||||
|
|
||||||
|
Purpose of local atomic operations
|
||||||
|
==================================
|
||||||
|
|
||||||
|
Local atomic operations are meant to provide fast and highly reentrant per CPU
|
||||||
|
counters. They minimize the performance cost of standard atomic operations by
|
||||||
|
removing the LOCK prefix and memory barriers normally required to synchronize
|
||||||
|
across CPUs.
|
||||||
|
|
||||||
|
Having fast per CPU atomic counters is interesting in many cases: it does not
|
||||||
|
require disabling interrupts to protect from interrupt handlers and it permits
|
||||||
|
coherent counters in NMI handlers. It is especially useful for tracing purposes
|
||||||
|
and for various performance monitoring counters.
|
||||||
|
|
||||||
|
Local atomic operations only guarantee variable modification atomicity wrt the
|
||||||
|
CPU which owns the data. Therefore, care must taken to make sure that only one
|
||||||
|
CPU writes to the ``local_t`` data. This is done by using per cpu data and
|
||||||
|
making sure that we modify it from within a preemption safe context. It is
|
||||||
|
however permitted to read ``local_t`` data from any CPU: it will then appear to
|
||||||
|
be written out of order wrt other memory writes by the owner CPU.
|
||||||
|
|
||||||
|
|
||||||
|
Implementation for a given architecture
|
||||||
|
=======================================
|
||||||
|
|
||||||
|
It can be done by slightly modifying the standard atomic operations: only
|
||||||
|
their UP variant must be kept. It typically means removing LOCK prefix (on
|
||||||
|
i386 and x86_64) and any SMP synchronization barrier. If the architecture does
|
||||||
|
not have a different behavior between SMP and UP, including
|
||||||
|
``asm-generic/local.h`` in your architecture's ``local.h`` is sufficient.
|
||||||
|
|
||||||
|
The ``local_t`` type is defined as an opaque ``signed long`` by embedding an
|
||||||
|
``atomic_long_t`` inside a structure. This is made so a cast from this type to
|
||||||
|
a ``long`` fails. The definition looks like::
|
||||||
|
|
||||||
|
typedef struct { atomic_long_t a; } local_t;
|
||||||
|
|
||||||
|
|
||||||
|
Rules to follow when using local atomic operations
|
||||||
|
==================================================
|
||||||
|
|
||||||
|
* Variables touched by local ops must be per cpu variables.
|
||||||
|
* *Only* the CPU owner of these variables must write to them.
|
||||||
|
* This CPU can use local ops from any context (process, irq, softirq, nmi, ...)
|
||||||
|
to update its ``local_t`` variables.
|
||||||
|
* Preemption (or interrupts) must be disabled when using local ops in
|
||||||
|
process context to make sure the process won't be migrated to a
|
||||||
|
different CPU between getting the per-cpu variable and doing the
|
||||||
|
actual local op.
|
||||||
|
* When using local ops in interrupt context, no special care must be
|
||||||
|
taken on a mainline kernel, since they will run on the local CPU with
|
||||||
|
preemption already disabled. I suggest, however, to explicitly
|
||||||
|
disable preemption anyway to make sure it will still work correctly on
|
||||||
|
-rt kernels.
|
||||||
|
* Reading the local cpu variable will provide the current copy of the
|
||||||
|
variable.
|
||||||
|
* Reads of these variables can be done from any CPU, because updates to
|
||||||
|
"``long``", aligned, variables are always atomic. Since no memory
|
||||||
|
synchronization is done by the writer CPU, an outdated copy of the
|
||||||
|
variable can be read when reading some *other* cpu's variables.
|
||||||
|
|
||||||
|
|
||||||
|
How to use local atomic operations
|
||||||
|
==================================
|
||||||
|
|
||||||
|
::
|
||||||
|
|
||||||
|
#include <linux/percpu.h>
|
||||||
|
#include <asm/local.h>
|
||||||
|
|
||||||
|
static DEFINE_PER_CPU(local_t, counters) = LOCAL_INIT(0);
|
||||||
|
|
||||||
|
|
||||||
|
Counting
|
||||||
|
========
|
||||||
|
|
||||||
|
Counting is done on all the bits of a signed long.
|
||||||
|
|
||||||
|
In preemptible context, use ``get_cpu_var()`` and ``put_cpu_var()`` around
|
||||||
|
local atomic operations: it makes sure that preemption is disabled around write
|
||||||
|
access to the per cpu variable. For instance::
|
||||||
|
|
||||||
|
local_inc(&get_cpu_var(counters));
|
||||||
|
put_cpu_var(counters);
|
||||||
|
|
||||||
|
If you are already in a preemption-safe context, you can use
|
||||||
|
``this_cpu_ptr()`` instead::
|
||||||
|
|
||||||
|
local_inc(this_cpu_ptr(&counters));
|
||||||
|
|
||||||
|
|
||||||
|
|
||||||
|
Reading the counters
|
||||||
|
====================
|
||||||
|
|
||||||
|
Those local counters can be read from foreign CPUs to sum the count. Note that
|
||||||
|
the data seen by local_read across CPUs must be considered to be out of order
|
||||||
|
relatively to other memory writes happening on the CPU that owns the data::
|
||||||
|
|
||||||
|
long sum = 0;
|
||||||
|
for_each_online_cpu(cpu)
|
||||||
|
sum += local_read(&per_cpu(counters, cpu));
|
||||||
|
|
||||||
|
If you want to use a remote local_read to synchronize access to a resource
|
||||||
|
between CPUs, explicit ``smp_wmb()`` and ``smp_rmb()`` memory barriers must be used
|
||||||
|
respectively on the writer and the reader CPUs. It would be the case if you use
|
||||||
|
the ``local_t`` variable as a counter of bytes written in a buffer: there should
|
||||||
|
be a ``smp_wmb()`` between the buffer write and the counter increment and also a
|
||||||
|
``smp_rmb()`` between the counter read and the buffer read.
|
||||||
|
|
||||||
|
|
||||||
|
Here is a sample module which implements a basic per cpu counter using
|
||||||
|
``local.h``::
|
||||||
|
|
||||||
|
/* test-local.c
|
||||||
|
*
|
||||||
|
* Sample module for local.h usage.
|
||||||
|
*/
|
||||||
|
|
||||||
|
|
||||||
|
#include <asm/local.h>
|
||||||
|
#include <linux/module.h>
|
||||||
|
#include <linux/timer.h>
|
||||||
|
|
||||||
|
static DEFINE_PER_CPU(local_t, counters) = LOCAL_INIT(0);
|
||||||
|
|
||||||
|
static struct timer_list test_timer;
|
||||||
|
|
||||||
|
/* IPI called on each CPU. */
|
||||||
|
static void test_each(void *info)
|
||||||
|
{
|
||||||
|
/* Increment the counter from a non preemptible context */
|
||||||
|
printk("Increment on cpu %d\n", smp_processor_id());
|
||||||
|
local_inc(this_cpu_ptr(&counters));
|
||||||
|
|
||||||
|
/* This is what incrementing the variable would look like within a
|
||||||
|
* preemptible context (it disables preemption) :
|
||||||
|
*
|
||||||
|
* local_inc(&get_cpu_var(counters));
|
||||||
|
* put_cpu_var(counters);
|
||||||
|
*/
|
||||||
|
}
|
||||||
|
|
||||||
|
static void do_test_timer(unsigned long data)
|
||||||
|
{
|
||||||
|
int cpu;
|
||||||
|
|
||||||
|
/* Increment the counters */
|
||||||
|
on_each_cpu(test_each, NULL, 1);
|
||||||
|
/* Read all the counters */
|
||||||
|
printk("Counters read from CPU %d\n", smp_processor_id());
|
||||||
|
for_each_online_cpu(cpu) {
|
||||||
|
printk("Read : CPU %d, count %ld\n", cpu,
|
||||||
|
local_read(&per_cpu(counters, cpu)));
|
||||||
|
}
|
||||||
|
del_timer(&test_timer);
|
||||||
|
test_timer.expires = jiffies + 1000;
|
||||||
|
add_timer(&test_timer);
|
||||||
|
}
|
||||||
|
|
||||||
|
static int __init test_init(void)
|
||||||
|
{
|
||||||
|
/* initialize the timer that will increment the counter */
|
||||||
|
init_timer(&test_timer);
|
||||||
|
test_timer.function = do_test_timer;
|
||||||
|
test_timer.expires = jiffies + 1;
|
||||||
|
add_timer(&test_timer);
|
||||||
|
|
||||||
|
return 0;
|
||||||
|
}
|
||||||
|
|
||||||
|
static void __exit test_exit(void)
|
||||||
|
{
|
||||||
|
del_timer_sync(&test_timer);
|
||||||
|
}
|
||||||
|
|
||||||
|
module_init(test_init);
|
||||||
|
module_exit(test_exit);
|
||||||
|
|
||||||
|
MODULE_LICENSE("GPL");
|
||||||
|
MODULE_AUTHOR("Mathieu Desnoyers");
|
||||||
|
MODULE_DESCRIPTION("Local Atomic Ops");
|
|
@ -1,191 +0,0 @@
|
||||||
Semantics and Behavior of Local Atomic Operations
|
|
||||||
|
|
||||||
Mathieu Desnoyers
|
|
||||||
|
|
||||||
|
|
||||||
This document explains the purpose of the local atomic operations, how
|
|
||||||
to implement them for any given architecture and shows how they can be used
|
|
||||||
properly. It also stresses on the precautions that must be taken when reading
|
|
||||||
those local variables across CPUs when the order of memory writes matters.
|
|
||||||
|
|
||||||
Note that local_t based operations are not recommended for general kernel use.
|
|
||||||
Please use the this_cpu operations instead unless there is really a special purpose.
|
|
||||||
Most uses of local_t in the kernel have been replaced by this_cpu operations.
|
|
||||||
this_cpu operations combine the relocation with the local_t like semantics in
|
|
||||||
a single instruction and yield more compact and faster executing code.
|
|
||||||
|
|
||||||
|
|
||||||
* Purpose of local atomic operations
|
|
||||||
|
|
||||||
Local atomic operations are meant to provide fast and highly reentrant per CPU
|
|
||||||
counters. They minimize the performance cost of standard atomic operations by
|
|
||||||
removing the LOCK prefix and memory barriers normally required to synchronize
|
|
||||||
across CPUs.
|
|
||||||
|
|
||||||
Having fast per CPU atomic counters is interesting in many cases : it does not
|
|
||||||
require disabling interrupts to protect from interrupt handlers and it permits
|
|
||||||
coherent counters in NMI handlers. It is especially useful for tracing purposes
|
|
||||||
and for various performance monitoring counters.
|
|
||||||
|
|
||||||
Local atomic operations only guarantee variable modification atomicity wrt the
|
|
||||||
CPU which owns the data. Therefore, care must taken to make sure that only one
|
|
||||||
CPU writes to the local_t data. This is done by using per cpu data and making
|
|
||||||
sure that we modify it from within a preemption safe context. It is however
|
|
||||||
permitted to read local_t data from any CPU : it will then appear to be written
|
|
||||||
out of order wrt other memory writes by the owner CPU.
|
|
||||||
|
|
||||||
|
|
||||||
* Implementation for a given architecture
|
|
||||||
|
|
||||||
It can be done by slightly modifying the standard atomic operations : only
|
|
||||||
their UP variant must be kept. It typically means removing LOCK prefix (on
|
|
||||||
i386 and x86_64) and any SMP synchronization barrier. If the architecture does
|
|
||||||
not have a different behavior between SMP and UP, including asm-generic/local.h
|
|
||||||
in your architecture's local.h is sufficient.
|
|
||||||
|
|
||||||
The local_t type is defined as an opaque signed long by embedding an
|
|
||||||
atomic_long_t inside a structure. This is made so a cast from this type to a
|
|
||||||
long fails. The definition looks like :
|
|
||||||
|
|
||||||
typedef struct { atomic_long_t a; } local_t;
|
|
||||||
|
|
||||||
|
|
||||||
* Rules to follow when using local atomic operations
|
|
||||||
|
|
||||||
- Variables touched by local ops must be per cpu variables.
|
|
||||||
- _Only_ the CPU owner of these variables must write to them.
|
|
||||||
- This CPU can use local ops from any context (process, irq, softirq, nmi, ...)
|
|
||||||
to update its local_t variables.
|
|
||||||
- Preemption (or interrupts) must be disabled when using local ops in
|
|
||||||
process context to make sure the process won't be migrated to a
|
|
||||||
different CPU between getting the per-cpu variable and doing the
|
|
||||||
actual local op.
|
|
||||||
- When using local ops in interrupt context, no special care must be
|
|
||||||
taken on a mainline kernel, since they will run on the local CPU with
|
|
||||||
preemption already disabled. I suggest, however, to explicitly
|
|
||||||
disable preemption anyway to make sure it will still work correctly on
|
|
||||||
-rt kernels.
|
|
||||||
- Reading the local cpu variable will provide the current copy of the
|
|
||||||
variable.
|
|
||||||
- Reads of these variables can be done from any CPU, because updates to
|
|
||||||
"long", aligned, variables are always atomic. Since no memory
|
|
||||||
synchronization is done by the writer CPU, an outdated copy of the
|
|
||||||
variable can be read when reading some _other_ cpu's variables.
|
|
||||||
|
|
||||||
|
|
||||||
* How to use local atomic operations
|
|
||||||
|
|
||||||
#include <linux/percpu.h>
|
|
||||||
#include <asm/local.h>
|
|
||||||
|
|
||||||
static DEFINE_PER_CPU(local_t, counters) = LOCAL_INIT(0);
|
|
||||||
|
|
||||||
|
|
||||||
* Counting
|
|
||||||
|
|
||||||
Counting is done on all the bits of a signed long.
|
|
||||||
|
|
||||||
In preemptible context, use get_cpu_var() and put_cpu_var() around local atomic
|
|
||||||
operations : it makes sure that preemption is disabled around write access to
|
|
||||||
the per cpu variable. For instance :
|
|
||||||
|
|
||||||
local_inc(&get_cpu_var(counters));
|
|
||||||
put_cpu_var(counters);
|
|
||||||
|
|
||||||
If you are already in a preemption-safe context, you can use
|
|
||||||
this_cpu_ptr() instead.
|
|
||||||
|
|
||||||
local_inc(this_cpu_ptr(&counters));
|
|
||||||
|
|
||||||
|
|
||||||
|
|
||||||
* Reading the counters
|
|
||||||
|
|
||||||
Those local counters can be read from foreign CPUs to sum the count. Note that
|
|
||||||
the data seen by local_read across CPUs must be considered to be out of order
|
|
||||||
relatively to other memory writes happening on the CPU that owns the data.
|
|
||||||
|
|
||||||
long sum = 0;
|
|
||||||
for_each_online_cpu(cpu)
|
|
||||||
sum += local_read(&per_cpu(counters, cpu));
|
|
||||||
|
|
||||||
If you want to use a remote local_read to synchronize access to a resource
|
|
||||||
between CPUs, explicit smp_wmb() and smp_rmb() memory barriers must be used
|
|
||||||
respectively on the writer and the reader CPUs. It would be the case if you use
|
|
||||||
the local_t variable as a counter of bytes written in a buffer : there should
|
|
||||||
be a smp_wmb() between the buffer write and the counter increment and also a
|
|
||||||
smp_rmb() between the counter read and the buffer read.
|
|
||||||
|
|
||||||
|
|
||||||
Here is a sample module which implements a basic per cpu counter using local.h.
|
|
||||||
|
|
||||||
--- BEGIN ---
|
|
||||||
/* test-local.c
|
|
||||||
*
|
|
||||||
* Sample module for local.h usage.
|
|
||||||
*/
|
|
||||||
|
|
||||||
|
|
||||||
#include <asm/local.h>
|
|
||||||
#include <linux/module.h>
|
|
||||||
#include <linux/timer.h>
|
|
||||||
|
|
||||||
static DEFINE_PER_CPU(local_t, counters) = LOCAL_INIT(0);
|
|
||||||
|
|
||||||
static struct timer_list test_timer;
|
|
||||||
|
|
||||||
/* IPI called on each CPU. */
|
|
||||||
static void test_each(void *info)
|
|
||||||
{
|
|
||||||
/* Increment the counter from a non preemptible context */
|
|
||||||
printk("Increment on cpu %d\n", smp_processor_id());
|
|
||||||
local_inc(this_cpu_ptr(&counters));
|
|
||||||
|
|
||||||
/* This is what incrementing the variable would look like within a
|
|
||||||
* preemptible context (it disables preemption) :
|
|
||||||
*
|
|
||||||
* local_inc(&get_cpu_var(counters));
|
|
||||||
* put_cpu_var(counters);
|
|
||||||
*/
|
|
||||||
}
|
|
||||||
|
|
||||||
static void do_test_timer(unsigned long data)
|
|
||||||
{
|
|
||||||
int cpu;
|
|
||||||
|
|
||||||
/* Increment the counters */
|
|
||||||
on_each_cpu(test_each, NULL, 1);
|
|
||||||
/* Read all the counters */
|
|
||||||
printk("Counters read from CPU %d\n", smp_processor_id());
|
|
||||||
for_each_online_cpu(cpu) {
|
|
||||||
printk("Read : CPU %d, count %ld\n", cpu,
|
|
||||||
local_read(&per_cpu(counters, cpu)));
|
|
||||||
}
|
|
||||||
del_timer(&test_timer);
|
|
||||||
test_timer.expires = jiffies + 1000;
|
|
||||||
add_timer(&test_timer);
|
|
||||||
}
|
|
||||||
|
|
||||||
static int __init test_init(void)
|
|
||||||
{
|
|
||||||
/* initialize the timer that will increment the counter */
|
|
||||||
init_timer(&test_timer);
|
|
||||||
test_timer.function = do_test_timer;
|
|
||||||
test_timer.expires = jiffies + 1;
|
|
||||||
add_timer(&test_timer);
|
|
||||||
|
|
||||||
return 0;
|
|
||||||
}
|
|
||||||
|
|
||||||
static void __exit test_exit(void)
|
|
||||||
{
|
|
||||||
del_timer_sync(&test_timer);
|
|
||||||
}
|
|
||||||
|
|
||||||
module_init(test_init);
|
|
||||||
module_exit(test_exit);
|
|
||||||
|
|
||||||
MODULE_LICENSE("GPL");
|
|
||||||
MODULE_AUTHOR("Mathieu Desnoyers");
|
|
||||||
MODULE_DESCRIPTION("Local Atomic Ops");
|
|
||||||
--- END ---
|
|
|
@ -1,3 +1,6 @@
|
||||||
|
|
||||||
|
.. _volatile_considered_harmful:
|
||||||
|
|
||||||
Why the "volatile" type class should not be used
|
Why the "volatile" type class should not be used
|
||||||
------------------------------------------------
|
------------------------------------------------
|
||||||
|
|
||||||
|
|
Loading…
Reference in New Issue