<?xml version="1.0" encoding="UTF-8"?>
<chapter id="mm">
<?dbhtml filename="mm.html"?>
<title>Memory management</title>
<section>
<title>Virtual memory management</title>
<section>
<title>Introduction</title>
<para>Virtual memory is a special memory management technique, used by
kernel to achieve a bunch of mission critical goals. <itemizedlist>
<listitem>
Isolate each task from other tasks that are running on the system at the same time.
</listitem>
<listitem>
Allow to allocate more memory, than is actual physical memory size of the machine.
</listitem>
<listitem>
Allowing, in general, to load and execute two programs that are linked on the same address without complicated relocations.
</listitem>
</itemizedlist></para>
<para><!--
<para>
Address spaces. Address space area (B+ tree). Only for uspace. Set of syscalls (shrink/extend etc).
Special address space area type - device - prohibits shrink/extend syscalls to call on it.
Address space has link to mapping tables (hierarchical - per Address space, hash - global tables).
</para>
--></para>
</section>
<section>
<title>Address spaces</title>
<section>
<title>Address space areas</title>
<para>Each address space consists of mutually disjunctive continuous
address space areas. Address space area is precisely defined by its
base address and the number of frames/pages is contains.</para>
<para>Address space area , that define behaviour and permissions on
the particular area. <itemizedlist>
<listitem>
<emphasis>AS_AREA_READ</emphasis>
flag indicates reading permission.
</listitem>
<listitem>
<emphasis>AS_AREA_WRITE</emphasis>
flag indicates writing permission.
</listitem>
<listitem>
<emphasis>AS_AREA_EXEC</emphasis>
flag indicates code execution permission. Some architectures do not support execution persmission restriction. In this case this flag has no effect.
</listitem>
<listitem>
<emphasis>AS_AREA_DEVICE</emphasis>
marks area as mapped to the device memory.
</listitem>
</itemizedlist></para>
<para>Kernel provides possibility tasks create/expand/shrink/share its
address space via the set of syscalls.</para>
</section>
<section>
<title>Address Space ID (ASID)</title>
<para>When switching to the different task, kernel also require to
switch mappings to the different address space. In case TLB cannot
distinguish address space mappings, all mapping information in TLB
from the old address space must be flushed, which can create certain
uncessary overhead during the task switching. To avoid this, some
architectures have capability to segregate different address spaces on
hardware level introducing the address space identifier as a part of
TLB record, telling the virtual address space translation unit to
which address space this record is applicable.</para>
<para>HelenOS kernel can take advantage of this hardware supported
identifier by having an ASID abstraction which is somehow related to
the corresponding architecture identifier. I.e. on ia64 kernel ASID is
derived from RID (region identifier) and on the mips32 kernel ASID is
actually the hardware identifier. As expected, this ASID information
record is the part of <emphasis>as_t</emphasis> structure.</para>
<para>Due to the hardware limitations, hardware ASID has limited
length from 8 bits on ia64 to 24 bits on mips32, which makes it
impossible to use it as unique address space identifier for all tasks
running in the system. In such situations special ASID stealing
algoritm is used, which takes ASID from inactive task and assigns it
to the active task.<classname></classname></para>
</section>
</section>
<section>
<title>Virtual address translation</title>
<section id="pagING">
<title>Paging</title>
<section>
<title>Introduction</title>
<para>Virtual memory is usually using paged memory model, where
virtual memory address space is divided into the
<emphasis>pages</emphasis> (usually having size 4096 bytes) and
physical memory is divided into the frames (same sized as a page, of
course). Each page may be mapped to some frame and then, upon memory
access to the virtual address, CPU performs <emphasis>address
translation</emphasis> during the instruction execution.
Non-existing mapping generates page fault exception, calling kernel
exception handler, thus allowing kernel to manipulate rules of
memory access. Information for pages mapping is stored by kernel in
the <link linkend="page_tables">page tables</link></para>
<para>The majority of the architectures use multi-level page tables,
which means need to access physical memory several times before
getting physical address. This fact would make serios performance
overhead in virtual memory management. To avoid this <link
linkend="tlb">Traslation Lookaside Buffer (TLB)</link> is
used.</para>
<para>HelenOS kernel has two different approaches to the paging
implementation: <emphasis>4 level page tables</emphasis> and
<emphasis>global hash table</emphasis>, which are accessible via
generic paging abstraction layer. Such different functionality was
caused by the major architectural differences between supported
platforms. This abstraction is implemented with help of the global
structure of pointers to basic mapping functions
<emphasis>page_mapping_operations</emphasis>. To achieve different
functionality of page tables, corresponding layer must implement
functions, declared in
<emphasis>page_mapping_operations</emphasis></para>
<para>Thanks to the abstract paging interface, there was a place
left for more paging implementations (besides already implemented
hieararchical page tables and hash table), for example B-Tree based
page tables.</para>
</section>
<section>
<title>Hierarchical 4-level page tables</title>
<para>Hierarchical 4-level page tables are the generalization of the
hardware capabilities of most architectures. Each address space has
its own page tables.<itemizedlist>
<listitem>
ia32 uses 2-level page tables, with full hardware support.
</listitem>
<listitem>
amd64 uses 4-level page tables, also coming with full hardware support.
</listitem>
<listitem>
mips and ppc32 have 2-level tables, software simulated support.
</listitem>
</itemizedlist></para>
</section>
<section>
<title>Global hash table</title>
<para>Implementation of the global hash table was encouraged by the
ia64 architecture support. One of the major differences between
global hash table and hierarchical tables is that global hash table
exists only once in the system and the hierarchical tables are
maintained per address space. </para>
<para>Thus, hash table contains information about all address spaces
mappings in the system, so, the hash of an entry must contain
information of both address space pointer or id and the virtual
address of the page. Generic hash table implementation assumes that
the addresses of the pointers to the address spaces are likely to be
on the close addresses, so it uses least significant bits for hash;
also it assumes that the virtual page addresses have roughly the
same probability of occurring, so the least significant bits of VPN
compose the hash index.</para>
<para>- global page hash table: existuje jen jedna v celem systemu
(vyuziva ji ia64), pozn. ia64 ma zatim vypnuty VHPT. Pouziva se
genericke hash table s oddelenymi collision chains. ASID support is
required to use global hash tables.</para>
</section>
</section>
<section id="tlb">
<title>Translation Lookaside buffer</title>
<para>Due to the extensive overhead during the page mapping lookup in
the page tables, all architectures has fast assotiative cache memory
built-in CPU. This memory called TLB stores recently used page table
entries.</para>
<section id="tlb_shootdown">
<title>TLB consistency. TLB shootdown algorithm.</title>
<para>Operating system is responsible for keeping TLB consistent by
invalidating the contents of TLB, whenever there is some change in
page tables. Those changes may occur when page or group of pages
were unmapped, mapping is changed or system switching active address
space to schedule a new system task. Moreover, this invalidation
operation must be done an all system CPUs because each CPU has its
own independent TLB cache. Thus maintaining TLB consistency on SMP
configuration as not as trivial task as it looks on the first
glance. Naive solution would assume that is the CPU which wants to
invalidate TLB will invalidate TLB caches on other CPUs. It is not
possible on the most of the architectures, because of the simple
fact - flushing TLB is allowed only on the local CPU and there is no
possibility to access other CPUs' TLB caches, thus invalidate TLB
remotely.</para>
<para>Technique of remote invalidation of TLB entries is called "TLB
shootdown". HelenOS uses a variation of the algorithm described by
D. Black et al., "Translation Lookaside Buffer Consistency: A
Software Approach," Proc. Third Int'l Conf. Architectural Support
for Programming Languages and Operating Systems, 1989, pp.
113-122.</para>
<para>As the situation demands, you will want partitial invalidation
of TLB caches. In case of simple memory mapping change it is
necessary to invalidate only one or more adjacent pages. In case if
the architecture is aware of ASIDs, when kernel needs to dump some
ASID to use by another task, it invalidates only entries from this
particular address space. Final option of the TLB invalidation is
the complete TLB cache invalidation, which is the operation that
flushes all entries in TLB.</para>
<para>TLB shootdown is performed in two phases.</para>
<formalpara>
<title>Phase 1.</title>
<para>First, initiator locks a global TLB spinlock, then request
is being put to the local request cache of every other CPU in the
system protected by its spinlock. In case the cache is full, all
requests in the cache are replaced by one request, indicating
global TLB flush. Then the initiator thread sends an IPI message
indicating the TLB shootdown request to the rest of the CPUs and
waits actively until all CPUs confirm TLB invalidating action
execution by setting up a special flag. After setting this flag
this thread is blocked on the TLB spinlock, held by the
initiator.</para>
</formalpara>
<formalpara>
<title>Phase 2.</title>
<para>All CPUs are waiting on the TLB spinlock to execute TLB
invalidation action and have indicated their intention to the
initiator. Initiator continues, cleaning up its TLB and releasing
the global TLB spinlock. After this all other CPUs gain and
immidiately release TLB spinlock and perform TLB invalidation
actions.</para>
</formalpara>
</section>
</section>
</section>
<section>
<title>---</title>
<para>At the moment HelenOS does not support swapping.</para>
<para>- pouzivame vypadky stranky k alokaci ramcu on-demand v ramci
as_area - na architekturach, ktere to podporuji, podporujeme non-exec
stranky</para>
</section>
</section>
<section>
<title>Physical memory management</title>
<section id="zones_and_frames">
<title>Zones and frames</title>
<para>On some architectures not whole physical memory is available for
conventional usage. This limitations require from kernel to maintain a
table of available and unavailable ranges of physical memory addresses.
Main idea of zones is in creating memory zone entity, that is a
continuous chunk of memory available for allocation. If some chunk is
not available, we simply do not put it in any zone.</para>
<para>Zone is also serves for informational purposes, containing
information about number of free and busy frames. Physical memory
allocation is also done inside the certain zone. Allocation of zone
frame must be organized by the <link linkend="frame_allocator">frame
allocator</link> associated with the zone.</para>
<para>Some of the architectures (mips32, ppc32) have only one zone, that
covers whole physical memory, and the others (like ia32) may have
multiple zones. Information about zones on current machine is stored in
BIOS hardware tables or can be hardcoded into kernel during compile
time.</para>
</section>
<section id="frame_allocator">
<title>Frame allocator</title>
<figure>
<mediaobject id="frame_alloc">
<imageobject role="html">
<imagedata fileref="images/frame_alloc.png" format="PNG" />
</imageobject>
<imageobject role="fop">
<imagedata fileref="images.vector/frame_alloc.svg" format="SVG" />
</imageobject>
</mediaobject>
<title>Frame allocator scheme.</title>
</figure>
<formalpara>
<title>Overview</title>
<para>Frame allocator provides physical memory allocation for the
kernel. Because of zonal organization of physical memory, frame
allocator is always working in context of some zone, thus making
impossible to allocate a piece of memory, which lays in different
zone, which cannot happen, because two adjacent zones can be merged
into one. Frame allocator is also being responsible to update
information on the number of free/busy frames in zone. Physical memory
allocation inside one <link linkend="zones_and_frames">memory
zone</link> is being handled by an instance of <link
linkend="buddy_allocator">buddy allocator</link> tailored to allocate
blocks of physical memory frames.</para>
</formalpara>
<formalpara>
<title>Allocation / deallocation</title>
<para>Upon allocation request, frame allocator tries to find first
zone, that can satisfy the incoming request (has required amount of
free frames to allocate). During deallocation, frame allocator needs
to find zone, that contain deallocated frame. This approach could
bring up two potential problems: <itemizedlist>
<listitem>
Linear search of zones does not any good to performance, but number of zones is not expected to be high. And if yes, list of zones can be replaced with more time-efficient B-tree.
</listitem>
<listitem>
Quickly find out if zone contains required number of frames to allocate and if this chunk of memory is properly aligned. This issue is perfectly solved bu the buddy allocator.
</listitem>
</itemizedlist></para>
</formalpara>
</section>
<section id="buddy_allocator">
<title>Buddy allocator</title>
<section>
<title>Overview</title>
<figure>
<mediaobject id="buddy_alloc">
<imageobject role="html">
<imagedata fileref="images/buddy_alloc.png" format="PNG" />
</imageobject>
<imageobject role="fop">
<imagedata fileref="images.vector/buddy_alloc.svg" format="SVG" />
</imageobject>
</mediaobject>
<title>Buddy system scheme.</title>
</figure>
<para>In the buddy allocator, the memory is broken down into
power-of-two sized naturally aligned blocks. These blocks are
organized in an array of lists, in which the list with index i
contains all unallocated blocks of size
<mathphrase>2<superscript>i</superscript></mathphrase>. The index i is
called the order of block. Should there be two adjacent equally sized
blocks in the list i<mathphrase />(i.e. buddies), the buddy allocator
would coalesce them and put the resulting block in list <mathphrase>i
+ 1</mathphrase>, provided that the resulting block would be naturally
aligned. Similarily, when the allocator is asked to allocate a block
of size <mathphrase>2<superscript>i</superscript></mathphrase>, it
first tries to satisfy the request from the list with index i. If the
request cannot be satisfied (i.e. the list i is empty), the buddy
allocator will try to allocate and split a larger block from the list
with index i + 1. Both of these algorithms are recursive. The
recursion ends either when there are no blocks to coalesce in the
former case or when there are no blocks that can be split in the
latter case.</para>
<!--graphic fileref="images/mm1.png" format="EPS" /-->
<para>This approach greatly reduces external fragmentation of memory
and helps in allocating bigger continuous blocks of memory aligned to
their size. On the other hand, the buddy allocator suffers increased
internal fragmentation of memory and is not suitable for general
kernel allocations. This purpose is better addressed by the <link
linkend="slab">slab allocator</link>.</para>
</section>
<section>
<title>Implementation</title>
<para>The buddy allocator is, in fact, an abstract framework wich can
be easily specialized to serve one particular task. It knows nothing
about the nature of memory it helps to allocate. In order to beat the
lack of this knowledge, the buddy allocator exports an interface that
each of its clients is required to implement. When supplied with an
implementation of this interface, the buddy allocator can use
specialized external functions to find a buddy for a block, split and
coalesce blocks, manipulate block order and mark blocks busy or
available. For precise documentation of this interface, refer to
<emphasis>"HelenOS Generic Kernel Reference Manual"</emphasis>.</para>
<formalpara>
<title>Data organization</title>
<para>Each entity allocable by the buddy allocator is required to
contain space for storing block order number and a link variable
used to interconnect blocks within the same order.</para>
<para>Whatever entities are allocated by the buddy allocator, the
first entity within a block is used to represent the entire block.
The first entity keeps the order of the whole block. Other entities
within the block are assigned the magic value
<constant>BUDDY_INNER_BLOCK</constant>. This is especially important
for effective identification of buddies in a one-dimensional array
because the entity that represents a potential buddy cannot be
associated with <constant>BUDDY_INNER_BLOCK</constant> (i.e. if it
is associated with <constant>BUDDY_INNER_BLOCK</constant> then it is
not a buddy).</para>
<para>The buddy allocator always uses the first frame to represent
the frame block. This frame contains <varname>buddy_order</varname>
variable to provide information about the block size it actually
represents (
<mathphrase>2<superscript>buddy_order</superscript></mathphrase>
frames block). Other frames in block have this value set to magic
<constant>BUDDY_INNER_BLOCK</constant> that is much greater than
buddy <varname>max_order</varname> value.</para>
<para>Each <varname>frame_t</varname> also contains pointer member
to hold frame structure in the linked list inside one order.</para>
</formalpara>
<formalpara>
<title>Allocation algorithm</title>
<para>Upon <mathphrase>2<superscript>i</superscript></mathphrase>
frames block allocation request, allocator checks if there are any
blocks available at the order list <varname>i</varname>. If yes,
removes block from order list and returns its address. If no,
recursively allocates
<mathphrase>2<superscript>i+1</superscript></mathphrase> frame
block, splits it into two
<mathphrase>2<superscript>i</superscript></mathphrase> frame blocks.
Then adds one of the blocks to the <varname>i</varname> order list
and returns address of another.</para>
</formalpara>
<formalpara>
<title>Deallocation algorithm</title>
<para>Check if block has so called buddy (another free
<mathphrase>2<superscript>i</superscript></mathphrase> frame block
that can be linked with freed block into the
<mathphrase>2<superscript>i+1</superscript></mathphrase> block).
Technically, buddy is a odd/even block for even/odd block
respectively. Plus we can put an extra requirement, that resulting
block must be aligned to its size. This requirement guarantees
natural block alignment for the blocks coming out the allocation
system.</para>
<para>Using direct pointer arithmetics,
<varname>frame_t::ref_count</varname> and
<varname>frame_t::buddy_order</varname> variables, finding buddy is
done at constant time.</para>
</formalpara>
</section>
</section>
<section id="slab">
<title>Slab allocator</title>
<section>
<title>Overview</title>
<para><termdef><glossterm>Slab</glossterm> represents a contiguous
piece of memory, usually made of several physically contiguous
pages.</termdef> <termdef><glossterm>Slab cache</glossterm> consists
of one or more slabs.</termdef></para>
<para>The majority of memory allocation requests in the kernel are for
small, frequently used data structures. For this purpose the slab
allocator is a perfect solution. The basic idea behind the slab
allocator is to have lists of commonly used objects available packed
into pages. This avoids the overhead of allocating and destroying
commonly used types of objects such threads, virtual memory structures
etc. Also due to the exact allocated size matching, slab allocation
completely eliminates internal fragmentation issue.</para>
</section>
<section>
<title>Implementation</title>
<figure>
<mediaobject id="slab_alloc">
<imageobject role="html">
<imagedata fileref="images/slab_alloc.png" format="PNG" />
</imageobject>
<imageobject role="fop">
<imagedata fileref="images.vector/slab_alloc.svg" format="SVG" />
</imageobject>
</mediaobject>
<title>Slab allocator scheme.</title>
</figure>
<para>The slab allocator is closely modelled after <ulink
url="http://www.usenix.org/events/usenix01/full_papers/bonwick/bonwick_html/">
OpenSolaris slab allocator by Jeff Bonwick and Jonathan Adams </ulink>
with the following exceptions: <itemizedlist>
<listitem>
empty slabs are deallocated immediately (in Linux they are kept in linked list, in Solaris ???)
</listitem>
<listitem>
empty magazines are deallocated when not needed (in Solaris they are held in linked list in slab cache)
</listitem>
</itemizedlist> Following features are not currently supported but
would be easy to do: <itemizedlist>
<listitem>
- cache coloring
</listitem>
<listitem>
- dynamic magazine grow (different magazine sizes are already supported, but we would need to adjust allocation strategy)
</listitem>
</itemizedlist></para>
<section>
<title>Magazine layer</title>
<para>Due to the extensive bottleneck on SMP architures, caused by
global slab locking mechanism, making processing of all slab
allocation requests serialized, a new layer was introduced to the
classic slab allocator design. Slab allocator was extended to
support per-CPU caches 'magazines' to achieve good SMP scaling.
<termdef>Slab SMP perfromance bottleneck was resolved by introducing
a per-CPU caching scheme called as <glossterm>magazine
layer</glossterm></termdef>.</para>
<para>Magazine is a N-element cache of objects, so each magazine can
satisfy N allocations. Magazine behaves like a automatic weapon
magazine (LIFO, stack), so the allocation/deallocation become simple
push/pop pointer operation. Trick is that CPU does not access global
slab allocator data during the allocation from its magazine, thus
making possible parallel allocations between CPUs.</para>
<para>Implementation also requires adding another feature as the
CPU-bound magazine is actually a pair of magazines to avoid
thrashing when during allocation/deallocatiion of 1 item at the
magazine size boundary. LIFO order is enforced, which should avoid
fragmentation as much as possible.</para>
<para>Another important entity of magazine layer is the common full
magazine list (also called a depot), that stores full magazines that
may be used by any of the CPU magazine caches to reload active CPU
magazine. This list of magazines can be pre-filled with full
magazines during initialization, but in current implementation it is
filled during object deallocation, when CPU magazine becomes
full.</para>
<para>Slab allocator control structures are allocated from special
slabs, that are marked by special flag, indicating that it should
not be used for slab magazine layer. This is done to avoid possible
infinite recursions and deadlock during conventional slab allocaiton
requests.</para>
</section>
<section>
<title>Allocation/deallocation</title>
<para>Every cache contains list of full slabs and list of partialy
full slabs. Empty slabs are immediately freed (thrashing will be
avoided because of magazines).</para>
<para>The SLAB allocator allocates lots of space and does not free
it. When frame allocator fails to allocate the frame, it calls
slab_reclaim(). It tries 'light reclaim' first, then brutal reclaim.
The light reclaim releases slabs from cpu-shared magazine-list,
until at least 1 slab is deallocated in each cache (this algorithm
should probably change). The brutal reclaim removes all cached
objects, even from CPU-bound magazines.</para>
<formalpara>
<title>Allocation</title>
<para><emphasis>Step 1.</emphasis> When it comes to the allocation
request, slab allocator first of all checks availability of memory
in local CPU-bound magazine. If it is there, we would just "pop"
the CPU magazine and return the pointer to object.</para>
<para><emphasis>Step 2.</emphasis> If the CPU-bound magazine is
empty, allocator will attempt to reload magazin, swapping it with
second CPU magazine and returns to the first step.</para>
<para><emphasis>Step 3.</emphasis> Now we are in the situation
when both CPU-bound magazines are empty, which makes allocator to
access shared full-magazines depot to reload CPU-bound magazines.
If reload is succesful (meaning there are full magazines in depot)
algoritm continues at Step 1.</para>
<para><emphasis>Step 4.</emphasis> Final step of the allocation.
In this step object is allocated from the conventional slab layer
and pointer is returned.</para>
</formalpara>
<formalpara>
<title>Deallocation</title>
<para><emphasis>Step 1.</emphasis> During deallocation request,
slab allocator will check if the local CPU-bound magazine is not
full. In this case we will just push the pointer to this
magazine.</para>
<para><emphasis>Step 2.</emphasis> If the CPU-bound magazine is
full, allocator will attempt to reload magazin, swapping it with
second CPU magazine and returns to the first step.</para>
<para><emphasis>Step 3.</emphasis> Now we are in the situation
when both CPU-bound magazines are full, which makes allocator to
access shared full-magazines depot to put one of the magazines to
the depot and creating new empty magazine. Algoritm continues at
Step 1.</para>
</formalpara>
</section>
</section>
</section>
<!-- End of Physmem -->
</section>
<section>
<title>Memory sharing</title>
<para>Not implemented yet(?)</para>
</section>
</chapter>