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.
102 Multi-process Support
103 ~~~~~~~~~~~~~~~~~~~~~
105 The Linuxapp EAL allows a multi-process as well as a multi-threaded (pthread) deployment model.
107 :ref:`Multi-process Support <Multi-process_Support>` for more details.
109 Memory Mapping Discovery and Memory Reservation
110 ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
112 The allocation of large contiguous physical memory is done using the hugetlbfs kernel filesystem.
113 The EAL provides an API to reserve named memory zones in this contiguous memory.
114 The physical address of the reserved memory for that memory zone is also returned to the user by the memory zone reservation API.
118 Memory reservations done using the APIs provided by rte_malloc are also backed by pages from the hugetlbfs filesystem.
120 Xen Dom0 support without hugetbls
121 ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
123 The existing memory management implementation is based on the Linux kernel hugepage mechanism.
124 However, Xen Dom0 does not support hugepages, so a new Linux kernel module rte_dom0_mm is added to workaround this limitation.
126 The EAL uses IOCTL interface to notify the Linux kernel module rte_dom0_mm to allocate memory of specified size,
127 and get all memory segments information from the module,
128 and the EAL uses MMAP interface to map the allocated memory.
129 For each memory segment, the physical addresses are contiguous within it but actual hardware addresses are contiguous within 2MB.
134 The EAL uses the /sys/bus/pci utilities provided by the kernel to scan the content on the PCI bus.
135 To access PCI memory, a kernel module called uio_pci_generic provides a /dev/uioX device file
136 and resource files in /sys
137 that can be mmap'd to obtain access to PCI address space from the application.
138 The DPDK-specific igb_uio module can also be used for this. Both drivers use the uio kernel feature (userland driver).
140 Per-lcore and Shared Variables
141 ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
145 lcore refers to a logical execution unit of the processor, sometimes called a hardware *thread*.
147 Shared variables are the default behavior.
148 Per-lcore variables are implemented using *Thread Local Storage* (TLS) to provide per-thread local storage.
153 A logging API is provided by EAL.
154 By default, in a Linux application, logs are sent to syslog and also to the console.
155 However, the log function can be overridden by the user to use a different logging mechanism.
157 Trace and Debug Functions
158 ^^^^^^^^^^^^^^^^^^^^^^^^^
160 There are some debug functions to dump the stack in glibc.
161 The rte_panic() function can voluntarily provoke a SIG_ABORT,
162 which can trigger the generation of a core file, readable by gdb.
164 CPU Feature Identification
165 ~~~~~~~~~~~~~~~~~~~~~~~~~~
167 The EAL can query the CPU at runtime (using the rte_cpu_get_feature() function) to determine which CPU features are available.
169 User Space Interrupt Event
170 ~~~~~~~~~~~~~~~~~~~~~~~~~~
172 + User Space Interrupt and Alarm Handling in Host Thread
174 The EAL creates a host thread to poll the UIO device file descriptors to detect the interrupts.
175 Callbacks can be registered or unregistered by the EAL functions for a specific interrupt event
176 and are called in the host thread asynchronously.
177 The EAL also allows timed callbacks to be used in the same way as for NIC interrupts.
181 In DPDK PMD, the only interrupts handled by the dedicated host thread are those for link status change,
182 i.e. link up and link down notification.
187 The receive and transmit routines provided by each PMD don't limit themselves to execute in polling thread mode.
188 To ease the idle polling with tiny throughput, it's useful to pause the polling and wait until the wake-up event happens.
189 The RX interrupt is the first choice to be such kind of wake-up event, but probably won't be the only one.
191 EAL provides the event APIs for this event-driven thread mode.
192 Taking linuxapp as an example, the implementation relies on epoll. Each thread can monitor an epoll instance
193 in which all the wake-up events' file descriptors are added. The event file descriptors are created and mapped to
194 the interrupt vectors according to the UIO/VFIO spec.
195 From bsdapp's perspective, kqueue is the alternative way, but not implemented yet.
197 EAL initializes the mapping between event file descriptors and interrupt vectors, while each device initializes the mapping
198 between interrupt vectors and queues. In this way, EAL actually is unaware of the interrupt cause on the specific vector.
199 The eth_dev driver takes responsibility to program the latter mapping.
203 Per queue RX interrupt event is only allowed in VFIO which supports multiple MSI-X vector. In UIO, the RX interrupt
204 together with other interrupt causes shares the same vector. In this case, when RX interrupt and LSC(link status change)
205 interrupt are both enabled(intr_conf.lsc == 1 && intr_conf.rxq == 1), only the former is capable.
207 The RX interrupt are controlled/enabled/disabled by ethdev APIs - 'rte_eth_dev_rx_intr_*'. They return failure if the PMD
208 hasn't support them yet. The intr_conf.rxq flag is used to turn on the capability of RX interrupt per device.
213 The EAL PCI device blacklist functionality can be used to mark certain NIC ports as blacklisted,
214 so they are ignored by the DPDK.
215 The ports to be blacklisted are identified using the PCIe* description (Domain:Bus:Device.Function).
220 Locks and atomic operations are per-architecture (i686 and x86_64).
222 Memory Segments and Memory Zones (memzone)
223 ------------------------------------------
225 The mapping of physical memory is provided by this feature in the EAL.
226 As physical memory can have gaps, the memory is described in a table of descriptors,
227 and each descriptor (called rte_memseg ) describes a contiguous portion of memory.
229 On top of this, the memzone allocator's role is to reserve contiguous portions of physical memory.
230 These zones are identified by a unique name when the memory is reserved.
232 The rte_memzone descriptors are also located in the configuration structure.
233 This structure is accessed using rte_eal_get_configuration().
234 The lookup (by name) of a memory zone returns a descriptor containing the physical address of the memory zone.
236 Memory zones can be reserved with specific start address alignment by supplying the align parameter
237 (by default, they are aligned to cache line size).
238 The alignment value should be a power of two and not less than the cache line size (64 bytes).
239 Memory zones can also be reserved from either 2 MB or 1 GB hugepages, provided that both are available on the system.
245 DPDK usually pins one pthread per core to avoid the overhead of task switching.
246 This allows for significant performance gains, but lacks flexibility and is not always efficient.
248 Power management helps to improve the CPU efficiency by limiting the CPU runtime frequency.
249 However, alternately it is possible to utilize the idle cycles available to take advantage of
250 the full capability of the CPU.
252 By taking advantage of cgroup, the CPU utilization quota can be simply assigned.
253 This gives another way to improve the CPU efficiency, however, there is a prerequisite;
254 DPDK must handle the context switching between multiple pthreads per core.
256 For further flexibility, it is useful to set pthread affinity not only to a CPU but to a CPU set.
258 EAL pthread and lcore Affinity
259 ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
261 The term "lcore" refers to an EAL thread, which is really a Linux/FreeBSD pthread.
262 "EAL pthreads" are created and managed by EAL and execute the tasks issued by *remote_launch*.
263 In each EAL pthread, there is a TLS (Thread Local Storage) called *_lcore_id* for unique identification.
264 As EAL pthreads usually bind 1:1 to the physical CPU, the *_lcore_id* is typically equal to the CPU ID.
266 When using multiple pthreads, however, the binding is no longer always 1:1 between an EAL pthread and a specified physical CPU.
267 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.
268 For this reason, there is an EAL long option '--lcores' defined to assign the CPU affinity of lcores.
269 For a specified lcore ID or ID group, the option allows setting the CPU set for that EAL pthread.
272 --lcores='<lcore_set>[@cpu_set][,<lcore_set>[@cpu_set],...]'
274 'lcore_set' and 'cpu_set' can be a single number, range or a group.
276 A number is a "digit([0-9]+)"; a range is "<number>-<number>"; a group is "(<number|range>[,<number|range>,...])".
278 If a '\@cpu_set' value is not supplied, the value of 'cpu_set' will default to the value of 'lcore_set'.
282 For example, "--lcores='1,2@(5-7),(3-5)@(0,2),(0,6),7-8'" which means start 9 EAL thread;
283 lcore 0 runs on cpuset 0x41 (cpu 0,6);
284 lcore 1 runs on cpuset 0x2 (cpu 1);
285 lcore 2 runs on cpuset 0xe0 (cpu 5,6,7);
286 lcore 3,4,5 runs on cpuset 0x5 (cpu 0,2);
287 lcore 6 runs on cpuset 0x41 (cpu 0,6);
288 lcore 7 runs on cpuset 0x80 (cpu 7);
289 lcore 8 runs on cpuset 0x100 (cpu 8).
291 Using this option, for each given lcore ID, the associated CPUs can be assigned.
292 It's also compatible with the pattern of corelist('-l') option.
294 non-EAL pthread support
295 ~~~~~~~~~~~~~~~~~~~~~~~
297 It is possible to use the DPDK execution context with any user pthread (aka. Non-EAL pthreads).
298 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*.
299 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).
301 All these impacts are mentioned in :ref:`known_issue_label` section.
306 There are two public APIs ``rte_thread_set_affinity()`` and ``rte_pthread_get_affinity()`` introduced for threads.
307 When they're used in any pthread context, the Thread Local Storage(TLS) will be set/get.
309 Those TLS include *_cpuset* and *_socket_id*:
311 * *_cpuset* stores the CPUs bitmap to which the pthread is affinitized.
313 * *_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.
316 .. _known_issue_label:
323 The rte_mempool uses a per-lcore cache inside the mempool.
324 For non-EAL pthreads, ``rte_lcore_id()`` will not return a valid number.
325 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.
326 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.
330 rte_ring supports multi-producer enqueue and multi-consumer dequeue.
331 However, it is non-preemptive, this has a knock on effect of making rte_mempool non-preemptable.
335 The "non-preemptive" constraint means:
337 - a pthread doing multi-producers enqueues on a given ring must not
338 be preempted by another pthread doing a multi-producer enqueue on
340 - a pthread doing multi-consumers dequeues on a given ring must not
341 be preempted by another pthread doing a multi-consumer dequeue on
344 Bypassing this constraint may cause the 2nd pthread to spin until the 1st one is scheduled again.
345 Moreover, if the 1st pthread is preempted by a context that has an higher priority, it may even cause a dead lock.
347 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.
349 1. It CAN be used for any single-producer or single-consumer situation.
351 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.
353 3. It MUST not be used by multi-producer/consumer pthreads, whose scheduling policies are SCHED_FIFO or SCHED_RR.
357 Running ``rte_timer_manager()`` on a non-EAL pthread is not allowed. However, resetting/stopping the timer from a non-EAL pthread is allowed.
361 In non-EAL pthreads, there is no per thread loglevel and logtype, global loglevels are used.
365 The debug statistics of rte_ring, rte_mempool and rte_timer are not supported in a non-EAL pthread.
370 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).
371 We expect only 50% of CPU spend on packet IO.
373 .. code-block:: console
375 mkdir /sys/fs/cgroup/cpu/pkt_io
376 mkdir /sys/fs/cgroup/cpuset/pkt_io
378 echo $cpu > /sys/fs/cgroup/cpuset/cpuset.cpus
380 echo $t0 > /sys/fs/cgroup/cpu/pkt_io/tasks
381 echo $t0 > /sys/fs/cgroup/cpuset/pkt_io/tasks
383 echo $t1 > /sys/fs/cgroup/cpu/pkt_io/tasks
384 echo $t1 > /sys/fs/cgroup/cpuset/pkt_io/tasks
386 cd /sys/fs/cgroup/cpu/pkt_io
387 echo 100000 > pkt_io/cpu.cfs_period_us
388 echo 50000 > pkt_io/cpu.cfs_quota_us
394 The EAL provides a malloc API to allocate any-sized memory.
396 The objective of this API is to provide malloc-like functions to allow
397 allocation from hugepage memory and to facilitate application porting.
398 The *DPDK API Reference* manual describes the available functions.
400 Typically, these kinds of allocations should not be done in data plane
401 processing because they are slower than pool-based allocation and make
402 use of locks within the allocation and free paths.
403 However, they can be used in configuration code.
405 Refer to the rte_malloc() function description in the *DPDK API Reference*
406 manual for more information.
411 When CONFIG_RTE_MALLOC_DEBUG is enabled, the allocated memory contains
412 overwrite protection fields to help identify buffer overflows.
414 Alignment and NUMA Constraints
415 ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
417 The rte_malloc() takes an align argument that can be used to request a memory
418 area that is aligned on a multiple of this value (which must be a power of two).
420 On systems with NUMA support, a call to the rte_malloc() function will return
421 memory that has been allocated on the NUMA socket of the core which made the call.
422 A set of APIs is also provided, to allow memory to be explicitly allocated on a
423 NUMA socket directly, or by allocated on the NUMA socket where another core is
424 located, in the case where the memory is to be used by a logical core other than
425 on the one doing the memory allocation.
430 This API is meant to be used by an application that requires malloc-like
431 functions at initialization time.
433 For allocating/freeing data at runtime, in the fast-path of an application,
434 the memory pool library should be used instead.
436 Internal Implementation
437 ~~~~~~~~~~~~~~~~~~~~~~~
442 There are two data structure types used internally in the malloc library:
444 * struct malloc_heap - used to track free space on a per-socket basis
446 * struct malloc_elem - the basic element of allocation and free-space
447 tracking inside the library.
449 Structure: malloc_heap
450 """"""""""""""""""""""
452 The malloc_heap structure is used to manage free space on a per-socket basis.
453 Internally, there is one heap structure per NUMA node, which allows us to
454 allocate memory to a thread based on the NUMA node on which this thread runs.
455 While this does not guarantee that the memory will be used on that NUMA node,
456 it is no worse than a scheme where the memory is always allocated on a fixed
459 The key fields of the heap structure and their function are described below
460 (see also diagram above):
462 * lock - the lock field is needed to synchronize access to the heap.
463 Given that the free space in the heap is tracked using a linked list,
464 we need a lock to prevent two threads manipulating the list at the same time.
466 * free_head - this points to the first element in the list of free nodes for
471 The malloc_heap structure does not keep track of in-use blocks of memory,
472 since these are never touched except when they are to be freed again -
473 at which point the pointer to the block is an input to the free() function.
475 .. _figure_malloc_heap:
477 .. figure:: img/malloc_heap.*
479 Example of a malloc heap and malloc elements within the malloc library
484 Structure: malloc_elem
485 """"""""""""""""""""""
487 The malloc_elem structure is used as a generic header structure for various
489 It is used in three different ways - all shown in the diagram above:
491 #. As a header on a block of free or allocated memory - normal case
493 #. As a padding header inside a block of memory
495 #. As an end-of-memseg marker
497 The most important fields in the structure and how they are used are described below.
501 If the usage of a particular field in one of the above three usages is not
502 described, the field can be assumed to have an undefined value in that
503 situation, for example, for padding headers only the "state" and "pad"
504 fields have valid values.
506 * heap - this pointer is a reference back to the heap structure from which
507 this block was allocated.
508 It is used for normal memory blocks when they are being freed, to add the
509 newly-freed block to the heap's free-list.
511 * prev - this pointer points to the header element/block in the memseg
512 immediately behind the current one. When freeing a block, this pointer is
513 used to reference the previous block to check if that block is also free.
514 If so, then the two free blocks are merged to form a single larger block.
516 * next_free - this pointer is used to chain the free-list of unallocated
517 memory blocks together.
518 It is only used in normal memory blocks; on ``malloc()`` to find a suitable
519 free block to allocate and on ``free()`` to add the newly freed element to
522 * state - This field can have one of three values: ``FREE``, ``BUSY`` or
524 The former two are to indicate the allocation state of a normal memory block
525 and the latter is to indicate that the element structure is a dummy structure
526 at the end of the start-of-block padding, i.e. where the start of the data
527 within a block is not at the start of the block itself, due to alignment
529 In that case, the pad header is used to locate the actual malloc element
530 header for the block.
531 For the end-of-memseg structure, this is always a ``BUSY`` value, which
532 ensures that no element, on being freed, searches beyond the end of the
533 memseg for other blocks to merge with into a larger free area.
535 * pad - this holds the length of the padding present at the start of the block.
536 In the case of a normal block header, it is added to the address of the end
537 of the header to give the address of the start of the data area, i.e. the
538 value passed back to the application on a malloc.
539 Within a dummy header inside the padding, this same value is stored, and is
540 subtracted from the address of the dummy header to yield the address of the
543 * size - the size of the data block, including the header itself.
544 For end-of-memseg structures, this size is given as zero, though it is never
546 For normal blocks which are being freed, this size value is used in place of
547 a "next" pointer to identify the location of the next block of memory that
548 in the case of being ``FREE``, the two free blocks can be merged into one.
553 On EAL initialization, all memsegs are setup as part of the malloc heap.
554 This setup involves placing a dummy structure at the end with ``BUSY`` state,
555 which may contain a sentinel value if ``CONFIG_RTE_MALLOC_DEBUG`` is enabled,
556 and a proper :ref:`element header<malloc_elem>` with ``FREE`` at the start
558 The ``FREE`` element is then added to the ``free_list`` for the malloc heap.
560 When an application makes a call to a malloc-like function, the malloc function
561 will first index the ``lcore_config`` structure for the calling thread, and
562 determine the NUMA node of that thread.
563 The NUMA node is used to index the array of ``malloc_heap`` structures which is
564 passed as a parameter to the ``heap_alloc()`` function, along with the
565 requested size, type, alignment and boundary parameters.
567 The ``heap_alloc()`` function will scan the free_list of the heap, and attempt
568 to find a free block suitable for storing data of the requested size, with the
569 requested alignment and boundary constraints.
571 When a suitable free element has been identified, the pointer to be returned
572 to the user is calculated.
573 The cache-line of memory immediately preceding this pointer is filled with a
574 struct malloc_elem header.
575 Because of alignment and boundary constraints, there could be free space at
576 the start and/or end of the element, resulting in the following behavior:
578 #. Check for trailing space.
579 If the trailing space is big enough, i.e. > 128 bytes, then the free element
581 If it is not, then we just ignore it (wasted space).
583 #. Check for space at the start of the element.
584 If the space at the start is small, i.e. <=128 bytes, then a pad header is
585 used, and the remaining space is wasted.
586 If, however, the remaining space is greater, then the free element is split.
588 The advantage of allocating the memory from the end of the existing element is
589 that no adjustment of the free list needs to take place - the existing element
590 on the free list just has its size pointer adjusted, and the following element
591 has its "prev" pointer redirected to the newly created element.
596 To free an area of memory, the pointer to the start of the data area is passed
597 to the free function.
598 The size of the ``malloc_elem`` structure is subtracted from this pointer to get
599 the element header for the block.
600 If this header is of type ``PAD`` then the pad length is further subtracted from
601 the pointer to get the proper element header for the entire block.
603 From this element header, we get pointers to the heap from which the block was
604 allocated and to where it must be freed, as well as the pointer to the previous
605 element, and via the size field, we can calculate the pointer to the next element.
606 These next and previous elements are then checked to see if they are also
607 ``FREE``, and if so, they are merged with the current element.
608 This means that we can never have two ``FREE`` memory blocks adjacent to one
609 another, as they are always merged into a single block.