2 Copyright(c) 2010-2014 Intel Corporation. All rights reserved.
5 Redistribution and use in source and binary forms, with or without
6 modification, are permitted provided that the following conditions
9 * Redistributions of source code must retain the above copyright
10 notice, this list of conditions and the following disclaimer.
11 * Redistributions in binary form must reproduce the above copyright
12 notice, this list of conditions and the following disclaimer in
13 the documentation and/or other materials provided with the
15 * Neither the name of Intel Corporation nor the names of its
16 contributors may be used to endorse or promote products derived
17 from this software without specific prior written permission.
19 THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
20 "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
21 LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR
22 A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT
23 OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
24 SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
25 LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
26 DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY
27 THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
28 (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
29 OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
31 .. _Environment_Abstraction_Layer:
33 Environment Abstraction Layer
34 =============================
36 The Environment Abstraction Layer (EAL) is responsible for gaining access to low-level resources such as hardware and memory space.
37 It provides a generic interface that hides the environment specifics from the applications and libraries.
38 It is the responsibility of the initialization routine to decide how to allocate these resources
39 (that is, memory space, PCI devices, timers, consoles, and so on).
41 Typical services expected from the EAL are:
43 * DPDK Loading and Launching:
44 The DPDK and its application are linked as a single application and must be loaded by some means.
46 * Core Affinity/Assignment Procedures:
47 The EAL provides mechanisms for assigning execution units to specific cores as well as creating execution instances.
49 * System Memory Reservation:
50 The EAL facilitates the reservation of different memory zones, for example, physical memory areas for device interactions.
52 * PCI Address Abstraction: The EAL provides an interface to access PCI address space.
54 * Trace and Debug Functions: Logs, dump_stack, panic and so on.
56 * Utility Functions: Spinlocks and atomic counters that are not provided in libc.
58 * CPU Feature Identification: Determine at runtime if a particular feature, for example, IntelĀ® AVX is supported.
59 Determine if the current CPU supports the feature set that the binary was compiled for.
61 * Interrupt Handling: Interfaces to register/unregister callbacks to specific interrupt sources.
63 * Alarm Functions: Interfaces to set/remove callbacks to be run at a specific time.
65 EAL in a Linux-userland Execution Environment
66 ---------------------------------------------
68 In a Linux user space environment, the DPDK application runs as a user-space application using the pthread library.
69 PCI information about devices and address space is discovered through the /sys kernel interface and through kernel modules such as uio_pci_generic, or igb_uio.
70 Refer to the UIO: User-space drivers documentation in the Linux kernel. This memory is mmap'd in the application.
72 The EAL performs physical memory allocation using mmap() in hugetlbfs (using huge page sizes to increase performance).
73 This memory is exposed to DPDK service layers such as the :ref:`Mempool Library <Mempool_Library>`.
75 At this point, the DPDK services layer will be initialized, then through pthread setaffinity calls,
76 each execution unit will be assigned to a specific logical core to run as a user-level thread.
78 The time reference is provided by the CPU Time-Stamp Counter (TSC) or by the HPET kernel API through a mmap() call.
80 Initialization and Core Launching
81 ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
83 Part of the initialization is done by the start function of glibc.
84 A check is also performed at initialization time to ensure that the micro architecture type chosen in the config file is supported by the CPU.
85 Then, the main() function is called. The core initialization and launch is done in rte_eal_init() (see the API documentation).
86 It consist of calls to the pthread library (more specifically, pthread_self(), pthread_create(), and pthread_setaffinity_np()).
88 .. _figure_linuxapp_launch:
90 .. figure:: img/linuxapp_launch.*
92 EAL Initialization in a Linux Application Environment
97 Initialization of objects, such as memory zones, rings, memory pools, lpm tables and hash tables,
98 should be done as part of the overall application initialization on the master lcore.
99 The creation and initialization functions for these objects are not multi-thread safe.
100 However, once initialized, the objects themselves can safely be used in multiple threads simultaneously.
105 During the initialization of EAL resources such as hugepage backed memory can be
106 allocated by core components. The memory allocated during ``rte_eal_init()``
107 can be released by calling the ``rte_eal_cleanup()`` function. Refer to the
108 API documentation for details.
110 Multi-process Support
111 ~~~~~~~~~~~~~~~~~~~~~
113 The Linuxapp EAL allows a multi-process as well as a multi-threaded (pthread) deployment model.
115 :ref:`Multi-process Support <Multi-process_Support>` for more details.
117 Memory Mapping Discovery and Memory Reservation
118 ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
120 The allocation of large contiguous physical memory is done using the hugetlbfs kernel filesystem.
121 The EAL provides an API to reserve named memory zones in this contiguous memory.
122 The physical address of the reserved memory for that memory zone is also returned to the user by the memory zone reservation API.
126 Memory reservations done using the APIs provided by rte_malloc are also backed by pages from the hugetlbfs filesystem.
131 The EAL uses the /sys/bus/pci utilities provided by the kernel to scan the content on the PCI bus.
132 To access PCI memory, a kernel module called uio_pci_generic provides a /dev/uioX device file
133 and resource files in /sys
134 that can be mmap'd to obtain access to PCI address space from the application.
135 The DPDK-specific igb_uio module can also be used for this. Both drivers use the uio kernel feature (userland driver).
137 Per-lcore and Shared Variables
138 ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
142 lcore refers to a logical execution unit of the processor, sometimes called a hardware *thread*.
144 Shared variables are the default behavior.
145 Per-lcore variables are implemented using *Thread Local Storage* (TLS) to provide per-thread local storage.
150 A logging API is provided by EAL.
151 By default, in a Linux application, logs are sent to syslog and also to the console.
152 However, the log function can be overridden by the user to use a different logging mechanism.
154 Trace and Debug Functions
155 ^^^^^^^^^^^^^^^^^^^^^^^^^
157 There are some debug functions to dump the stack in glibc.
158 The rte_panic() function can voluntarily provoke a SIG_ABORT,
159 which can trigger the generation of a core file, readable by gdb.
161 CPU Feature Identification
162 ~~~~~~~~~~~~~~~~~~~~~~~~~~
164 The EAL can query the CPU at runtime (using the rte_cpu_get_features() function) to determine which CPU features are available.
166 User Space Interrupt Event
167 ~~~~~~~~~~~~~~~~~~~~~~~~~~
169 + User Space Interrupt and Alarm Handling in Host Thread
171 The EAL creates a host thread to poll the UIO device file descriptors to detect the interrupts.
172 Callbacks can be registered or unregistered by the EAL functions for a specific interrupt event
173 and are called in the host thread asynchronously.
174 The EAL also allows timed callbacks to be used in the same way as for NIC interrupts.
178 In DPDK PMD, the only interrupts handled by the dedicated host thread are those for link status change
179 (link up and link down notification) and for sudden device removal.
184 The receive and transmit routines provided by each PMD don't limit themselves to execute in polling thread mode.
185 To ease the idle polling with tiny throughput, it's useful to pause the polling and wait until the wake-up event happens.
186 The RX interrupt is the first choice to be such kind of wake-up event, but probably won't be the only one.
188 EAL provides the event APIs for this event-driven thread mode.
189 Taking linuxapp as an example, the implementation relies on epoll. Each thread can monitor an epoll instance
190 in which all the wake-up events' file descriptors are added. The event file descriptors are created and mapped to
191 the interrupt vectors according to the UIO/VFIO spec.
192 From bsdapp's perspective, kqueue is the alternative way, but not implemented yet.
194 EAL initializes the mapping between event file descriptors and interrupt vectors, while each device initializes the mapping
195 between interrupt vectors and queues. In this way, EAL actually is unaware of the interrupt cause on the specific vector.
196 The eth_dev driver takes responsibility to program the latter mapping.
200 Per queue RX interrupt event is only allowed in VFIO which supports multiple MSI-X vector. In UIO, the RX interrupt
201 together with other interrupt causes shares the same vector. In this case, when RX interrupt and LSC(link status change)
202 interrupt are both enabled(intr_conf.lsc == 1 && intr_conf.rxq == 1), only the former is capable.
204 The RX interrupt are controlled/enabled/disabled by ethdev APIs - 'rte_eth_dev_rx_intr_*'. They return failure if the PMD
205 hasn't support them yet. The intr_conf.rxq flag is used to turn on the capability of RX interrupt per device.
207 + Device Removal Event
209 This event is triggered by a device being removed at a bus level. Its
210 underlying resources may have been made unavailable (i.e. PCI mappings
211 unmapped). The PMD must make sure that on such occurrence, the application can
212 still safely use its callbacks.
214 This event can be subscribed to in the same way one would subscribe to a link
215 status change event. The execution context is thus the same, i.e. it is the
216 dedicated interrupt host thread.
218 Considering this, it is likely that an application would want to close a
219 device having emitted a Device Removal Event. In such case, calling
220 ``rte_eth_dev_close()`` can trigger it to unregister its own Device Removal Event
221 callback. Care must be taken not to close the device from the interrupt handler
222 context. It is necessary to reschedule such closing operation.
227 The EAL PCI device blacklist functionality can be used to mark certain NIC ports as blacklisted,
228 so they are ignored by the DPDK.
229 The ports to be blacklisted are identified using the PCIe* description (Domain:Bus:Device.Function).
234 Locks and atomic operations are per-architecture (i686 and x86_64).
236 Memory Segments and Memory Zones (memzone)
237 ------------------------------------------
239 The mapping of physical memory is provided by this feature in the EAL.
240 As physical memory can have gaps, the memory is described in a table of descriptors,
241 and each descriptor (called rte_memseg ) describes a contiguous portion of memory.
243 On top of this, the memzone allocator's role is to reserve contiguous portions of physical memory.
244 These zones are identified by a unique name when the memory is reserved.
246 The rte_memzone descriptors are also located in the configuration structure.
247 This structure is accessed using rte_eal_get_configuration().
248 The lookup (by name) of a memory zone returns a descriptor containing the physical address of the memory zone.
250 Memory zones can be reserved with specific start address alignment by supplying the align parameter
251 (by default, they are aligned to cache line size).
252 The alignment value should be a power of two and not less than the cache line size (64 bytes).
253 Memory zones can also be reserved from either 2 MB or 1 GB hugepages, provided that both are available on the system.
259 DPDK usually pins one pthread per core to avoid the overhead of task switching.
260 This allows for significant performance gains, but lacks flexibility and is not always efficient.
262 Power management helps to improve the CPU efficiency by limiting the CPU runtime frequency.
263 However, alternately it is possible to utilize the idle cycles available to take advantage of
264 the full capability of the CPU.
266 By taking advantage of cgroup, the CPU utilization quota can be simply assigned.
267 This gives another way to improve the CPU efficiency, however, there is a prerequisite;
268 DPDK must handle the context switching between multiple pthreads per core.
270 For further flexibility, it is useful to set pthread affinity not only to a CPU but to a CPU set.
272 EAL pthread and lcore Affinity
273 ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
275 The term "lcore" refers to an EAL thread, which is really a Linux/FreeBSD pthread.
276 "EAL pthreads" are created and managed by EAL and execute the tasks issued by *remote_launch*.
277 In each EAL pthread, there is a TLS (Thread Local Storage) called *_lcore_id* for unique identification.
278 As EAL pthreads usually bind 1:1 to the physical CPU, the *_lcore_id* is typically equal to the CPU ID.
280 When using multiple pthreads, however, the binding is no longer always 1:1 between an EAL pthread and a specified physical CPU.
281 The EAL pthread may have affinity to a CPU set, and as such the *_lcore_id* will not be the same as the CPU ID.
282 For this reason, there is an EAL long option '--lcores' defined to assign the CPU affinity of lcores.
283 For a specified lcore ID or ID group, the option allows setting the CPU set for that EAL pthread.
286 --lcores='<lcore_set>[@cpu_set][,<lcore_set>[@cpu_set],...]'
288 'lcore_set' and 'cpu_set' can be a single number, range or a group.
290 A number is a "digit([0-9]+)"; a range is "<number>-<number>"; a group is "(<number|range>[,<number|range>,...])".
292 If a '\@cpu_set' value is not supplied, the value of 'cpu_set' will default to the value of 'lcore_set'.
296 For example, "--lcores='1,2@(5-7),(3-5)@(0,2),(0,6),7-8'" which means start 9 EAL thread;
297 lcore 0 runs on cpuset 0x41 (cpu 0,6);
298 lcore 1 runs on cpuset 0x2 (cpu 1);
299 lcore 2 runs on cpuset 0xe0 (cpu 5,6,7);
300 lcore 3,4,5 runs on cpuset 0x5 (cpu 0,2);
301 lcore 6 runs on cpuset 0x41 (cpu 0,6);
302 lcore 7 runs on cpuset 0x80 (cpu 7);
303 lcore 8 runs on cpuset 0x100 (cpu 8).
305 Using this option, for each given lcore ID, the associated CPUs can be assigned.
306 It's also compatible with the pattern of corelist('-l') option.
308 non-EAL pthread support
309 ~~~~~~~~~~~~~~~~~~~~~~~
311 It is possible to use the DPDK execution context with any user pthread (aka. Non-EAL pthreads).
312 In a non-EAL pthread, the *_lcore_id* is always LCORE_ID_ANY which identifies that it is not an EAL thread with a valid, unique, *_lcore_id*.
313 Some libraries will use an alternative unique ID (e.g. TID), some will not be impacted at all, and some will work but with limitations (e.g. timer and mempool libraries).
315 All these impacts are mentioned in :ref:`known_issue_label` section.
320 There are two public APIs ``rte_thread_set_affinity()`` and ``rte_thread_get_affinity()`` introduced for threads.
321 When they're used in any pthread context, the Thread Local Storage(TLS) will be set/get.
323 Those TLS include *_cpuset* and *_socket_id*:
325 * *_cpuset* stores the CPUs bitmap to which the pthread is affinitized.
327 * *_socket_id* stores the NUMA node of the CPU set. If the CPUs in CPU set belong to different NUMA node, the *_socket_id* will be set to SOCKET_ID_ANY.
330 .. _known_issue_label:
337 The rte_mempool uses a per-lcore cache inside the mempool.
338 For non-EAL pthreads, ``rte_lcore_id()`` will not return a valid number.
339 So for now, when rte_mempool is used with non-EAL pthreads, the put/get operations will bypass the default mempool cache and there is a performance penalty because of this bypass.
340 Only user-owned external caches can be used in a non-EAL context in conjunction with ``rte_mempool_generic_put()`` and ``rte_mempool_generic_get()`` that accept an explicit cache parameter.
344 rte_ring supports multi-producer enqueue and multi-consumer dequeue.
345 However, it is non-preemptive, this has a knock on effect of making rte_mempool non-preemptable.
349 The "non-preemptive" constraint means:
351 - a pthread doing multi-producers enqueues on a given ring must not
352 be preempted by another pthread doing a multi-producer enqueue on
354 - a pthread doing multi-consumers dequeues on a given ring must not
355 be preempted by another pthread doing a multi-consumer dequeue on
358 Bypassing this constraint may cause the 2nd pthread to spin until the 1st one is scheduled again.
359 Moreover, if the 1st pthread is preempted by a context that has an higher priority, it may even cause a dead lock.
361 This does not mean it cannot be used, simply, there is a need to narrow down the situation when it is used by multi-pthread on the same core.
363 1. It CAN be used for any single-producer or single-consumer situation.
365 2. It MAY be used by multi-producer/consumer pthread whose scheduling policy are all SCHED_OTHER(cfs). User SHOULD be aware of the performance penalty before using it.
367 3. It MUST not be used by multi-producer/consumer pthreads, whose scheduling policies are SCHED_FIFO or SCHED_RR.
371 Running ``rte_timer_manager()`` on a non-EAL pthread is not allowed. However, resetting/stopping the timer from a non-EAL pthread is allowed.
375 In non-EAL pthreads, there is no per thread loglevel and logtype, global loglevels are used.
379 The debug statistics of rte_ring, rte_mempool and rte_timer are not supported in a non-EAL pthread.
384 The following is a simple example of cgroup control usage, there are two pthreads(t0 and t1) doing packet I/O on the same core ($CPU).
385 We expect only 50% of CPU spend on packet IO.
387 .. code-block:: console
389 mkdir /sys/fs/cgroup/cpu/pkt_io
390 mkdir /sys/fs/cgroup/cpuset/pkt_io
392 echo $cpu > /sys/fs/cgroup/cpuset/cpuset.cpus
394 echo $t0 > /sys/fs/cgroup/cpu/pkt_io/tasks
395 echo $t0 > /sys/fs/cgroup/cpuset/pkt_io/tasks
397 echo $t1 > /sys/fs/cgroup/cpu/pkt_io/tasks
398 echo $t1 > /sys/fs/cgroup/cpuset/pkt_io/tasks
400 cd /sys/fs/cgroup/cpu/pkt_io
401 echo 100000 > pkt_io/cpu.cfs_period_us
402 echo 50000 > pkt_io/cpu.cfs_quota_us
408 The EAL provides a malloc API to allocate any-sized memory.
410 The objective of this API is to provide malloc-like functions to allow
411 allocation from hugepage memory and to facilitate application porting.
412 The *DPDK API Reference* manual describes the available functions.
414 Typically, these kinds of allocations should not be done in data plane
415 processing because they are slower than pool-based allocation and make
416 use of locks within the allocation and free paths.
417 However, they can be used in configuration code.
419 Refer to the rte_malloc() function description in the *DPDK API Reference*
420 manual for more information.
425 When CONFIG_RTE_MALLOC_DEBUG is enabled, the allocated memory contains
426 overwrite protection fields to help identify buffer overflows.
428 Alignment and NUMA Constraints
429 ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
431 The rte_malloc() takes an align argument that can be used to request a memory
432 area that is aligned on a multiple of this value (which must be a power of two).
434 On systems with NUMA support, a call to the rte_malloc() function will return
435 memory that has been allocated on the NUMA socket of the core which made the call.
436 A set of APIs is also provided, to allow memory to be explicitly allocated on a
437 NUMA socket directly, or by allocated on the NUMA socket where another core is
438 located, in the case where the memory is to be used by a logical core other than
439 on the one doing the memory allocation.
444 This API is meant to be used by an application that requires malloc-like
445 functions at initialization time.
447 For allocating/freeing data at runtime, in the fast-path of an application,
448 the memory pool library should be used instead.
450 Internal Implementation
451 ~~~~~~~~~~~~~~~~~~~~~~~
456 There are two data structure types used internally in the malloc library:
458 * struct malloc_heap - used to track free space on a per-socket basis
460 * struct malloc_elem - the basic element of allocation and free-space
461 tracking inside the library.
463 Structure: malloc_heap
464 """"""""""""""""""""""
466 The malloc_heap structure is used to manage free space on a per-socket basis.
467 Internally, there is one heap structure per NUMA node, which allows us to
468 allocate memory to a thread based on the NUMA node on which this thread runs.
469 While this does not guarantee that the memory will be used on that NUMA node,
470 it is no worse than a scheme where the memory is always allocated on a fixed
473 The key fields of the heap structure and their function are described below
474 (see also diagram above):
476 * lock - the lock field is needed to synchronize access to the heap.
477 Given that the free space in the heap is tracked using a linked list,
478 we need a lock to prevent two threads manipulating the list at the same time.
480 * free_head - this points to the first element in the list of free nodes for
485 The malloc_heap structure does not keep track of in-use blocks of memory,
486 since these are never touched except when they are to be freed again -
487 at which point the pointer to the block is an input to the free() function.
489 .. _figure_malloc_heap:
491 .. figure:: img/malloc_heap.*
493 Example of a malloc heap and malloc elements within the malloc library
498 Structure: malloc_elem
499 """"""""""""""""""""""
501 The malloc_elem structure is used as a generic header structure for various
503 It is used in three different ways - all shown in the diagram above:
505 #. As a header on a block of free or allocated memory - normal case
507 #. As a padding header inside a block of memory
509 #. As an end-of-memseg marker
511 The most important fields in the structure and how they are used are described below.
515 If the usage of a particular field in one of the above three usages is not
516 described, the field can be assumed to have an undefined value in that
517 situation, for example, for padding headers only the "state" and "pad"
518 fields have valid values.
520 * heap - this pointer is a reference back to the heap structure from which
521 this block was allocated.
522 It is used for normal memory blocks when they are being freed, to add the
523 newly-freed block to the heap's free-list.
525 * prev - this pointer points to the header element/block in the memseg
526 immediately behind the current one. When freeing a block, this pointer is
527 used to reference the previous block to check if that block is also free.
528 If so, then the two free blocks are merged to form a single larger block.
530 * next_free - this pointer is used to chain the free-list of unallocated
531 memory blocks together.
532 It is only used in normal memory blocks; on ``malloc()`` to find a suitable
533 free block to allocate and on ``free()`` to add the newly freed element to
536 * state - This field can have one of three values: ``FREE``, ``BUSY`` or
538 The former two are to indicate the allocation state of a normal memory block
539 and the latter is to indicate that the element structure is a dummy structure
540 at the end of the start-of-block padding, i.e. where the start of the data
541 within a block is not at the start of the block itself, due to alignment
543 In that case, the pad header is used to locate the actual malloc element
544 header for the block.
545 For the end-of-memseg structure, this is always a ``BUSY`` value, which
546 ensures that no element, on being freed, searches beyond the end of the
547 memseg for other blocks to merge with into a larger free area.
549 * pad - this holds the length of the padding present at the start of the block.
550 In the case of a normal block header, it is added to the address of the end
551 of the header to give the address of the start of the data area, i.e. the
552 value passed back to the application on a malloc.
553 Within a dummy header inside the padding, this same value is stored, and is
554 subtracted from the address of the dummy header to yield the address of the
557 * size - the size of the data block, including the header itself.
558 For end-of-memseg structures, this size is given as zero, though it is never
560 For normal blocks which are being freed, this size value is used in place of
561 a "next" pointer to identify the location of the next block of memory that
562 in the case of being ``FREE``, the two free blocks can be merged into one.
567 On EAL initialization, all memsegs are setup as part of the malloc heap.
568 This setup involves placing a dummy structure at the end with ``BUSY`` state,
569 which may contain a sentinel value if ``CONFIG_RTE_MALLOC_DEBUG`` is enabled,
570 and a proper :ref:`element header<malloc_elem>` with ``FREE`` at the start
572 The ``FREE`` element is then added to the ``free_list`` for the malloc heap.
574 When an application makes a call to a malloc-like function, the malloc function
575 will first index the ``lcore_config`` structure for the calling thread, and
576 determine the NUMA node of that thread.
577 The NUMA node is used to index the array of ``malloc_heap`` structures which is
578 passed as a parameter to the ``heap_alloc()`` function, along with the
579 requested size, type, alignment and boundary parameters.
581 The ``heap_alloc()`` function will scan the free_list of the heap, and attempt
582 to find a free block suitable for storing data of the requested size, with the
583 requested alignment and boundary constraints.
585 When a suitable free element has been identified, the pointer to be returned
586 to the user is calculated.
587 The cache-line of memory immediately preceding this pointer is filled with a
588 struct malloc_elem header.
589 Because of alignment and boundary constraints, there could be free space at
590 the start and/or end of the element, resulting in the following behavior:
592 #. Check for trailing space.
593 If the trailing space is big enough, i.e. > 128 bytes, then the free element
595 If it is not, then we just ignore it (wasted space).
597 #. Check for space at the start of the element.
598 If the space at the start is small, i.e. <=128 bytes, then a pad header is
599 used, and the remaining space is wasted.
600 If, however, the remaining space is greater, then the free element is split.
602 The advantage of allocating the memory from the end of the existing element is
603 that no adjustment of the free list needs to take place - the existing element
604 on the free list just has its size pointer adjusted, and the following element
605 has its "prev" pointer redirected to the newly created element.
610 To free an area of memory, the pointer to the start of the data area is passed
611 to the free function.
612 The size of the ``malloc_elem`` structure is subtracted from this pointer to get
613 the element header for the block.
614 If this header is of type ``PAD`` then the pad length is further subtracted from
615 the pointer to get the proper element header for the entire block.
617 From this element header, we get pointers to the heap from which the block was
618 allocated and to where it must be freed, as well as the pointer to the previous
619 element, and via the size field, we can calculate the pointer to the next element.
620 These next and previous elements are then checked to see if they are also
621 ``FREE``, and if so, they are merged with the current element.
622 This means that we can never have two ``FREE`` memory blocks adjacent to one
623 another, as they are always merged into a single block.