1.. SPDX-License-Identifier: BSD-3-Clause 2 Copyright(c) 2010-2014 Intel Corporation. 3 4.. _Environment_Abstraction_Layer: 5 6Environment Abstraction Layer 7============================= 8 9The Environment Abstraction Layer (EAL) is responsible for gaining access to low-level resources such as hardware and memory space. 10It provides a generic interface that hides the environment specifics from the applications and libraries. 11It is the responsibility of the initialization routine to decide how to allocate these resources 12(that is, memory space, devices, timers, consoles, and so on). 13 14Typical services expected from the EAL are: 15 16* DPDK Loading and Launching: 17 The DPDK and its application are linked as a single application and must be loaded by some means. 18 19* Core Affinity/Assignment Procedures: 20 The EAL provides mechanisms for assigning execution units to specific cores as well as creating execution instances. 21 22* System Memory Reservation: 23 The EAL facilitates the reservation of different memory zones, for example, physical memory areas for device interactions. 24 25* Trace and Debug Functions: Logs, dump_stack, panic and so on. 26 27* Utility Functions: Spinlocks and atomic counters that are not provided in libc. 28 29* CPU Feature Identification: Determine at runtime if a particular feature, for example, Intel® AVX is supported. 30 Determine if the current CPU supports the feature set that the binary was compiled for. 31 32* Interrupt Handling: Interfaces to register/unregister callbacks to specific interrupt sources. 33 34* Alarm Functions: Interfaces to set/remove callbacks to be run at a specific time. 35 36EAL in a Linux-userland Execution Environment 37--------------------------------------------- 38 39In a Linux user space environment, the DPDK application runs as a user-space application using the pthread library. 40 41The EAL performs physical memory allocation using mmap() in hugetlbfs (using huge page sizes to increase performance). 42This memory is exposed to DPDK service layers such as the :ref:`Mempool Library <Mempool_Library>`. 43 44At this point, the DPDK services layer will be initialized, then through pthread setaffinity calls, 45each execution unit will be assigned to a specific logical core to run as a user-level thread. 46 47The time reference is provided by the CPU Time-Stamp Counter (TSC) or by the HPET kernel API through a mmap() call. 48 49Initialization and Core Launching 50~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 51 52Part of the initialization is done by the start function of glibc. 53A check is also performed at initialization time to ensure that the micro architecture type chosen in the config file is supported by the CPU. 54Then, the main() function is called. The core initialization and launch is done in rte_eal_init() (see the API documentation). 55It consist of calls to the pthread library (more specifically, pthread_self(), pthread_create(), and pthread_setaffinity_np()). 56 57.. _figure_linux_launch: 58 59.. figure:: img/linuxapp_launch.* 60 61 EAL Initialization in a Linux Application Environment 62 63 64.. note:: 65 66 Initialization of objects, such as memory zones, rings, memory pools, lpm tables and hash tables, 67 should be done as part of the overall application initialization on the master lcore. 68 The creation and initialization functions for these objects are not multi-thread safe. 69 However, once initialized, the objects themselves can safely be used in multiple threads simultaneously. 70 71Shutdown and Cleanup 72~~~~~~~~~~~~~~~~~~~~ 73 74During the initialization of EAL resources such as hugepage backed memory can be 75allocated by core components. The memory allocated during ``rte_eal_init()`` 76can be released by calling the ``rte_eal_cleanup()`` function. Refer to the 77API documentation for details. 78 79Multi-process Support 80~~~~~~~~~~~~~~~~~~~~~ 81 82The Linux EAL allows a multi-process as well as a multi-threaded (pthread) deployment model. 83See chapter 84:ref:`Multi-process Support <Multi-process_Support>` for more details. 85 86Memory Mapping Discovery and Memory Reservation 87~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 88 89The allocation of large contiguous physical memory is done using the hugetlbfs kernel filesystem. 90The EAL provides an API to reserve named memory zones in this contiguous memory. 91The physical address of the reserved memory for that memory zone is also returned to the user by the memory zone reservation API. 92 93There are two modes in which DPDK memory subsystem can operate: dynamic mode, 94and legacy mode. Both modes are explained below. 95 96.. note:: 97 98 Memory reservations done using the APIs provided by rte_malloc are also backed by pages from the hugetlbfs filesystem. 99 100+ Dynamic memory mode 101 102Currently, this mode is only supported on Linux. 103 104In this mode, usage of hugepages by DPDK application will grow and shrink based 105on application's requests. Any memory allocation through ``rte_malloc()``, 106``rte_memzone_reserve()`` or other methods, can potentially result in more 107hugepages being reserved from the system. Similarly, any memory deallocation can 108potentially result in hugepages being released back to the system. 109 110Memory allocated in this mode is not guaranteed to be IOVA-contiguous. If large 111chunks of IOVA-contiguous are required (with "large" defined as "more than one 112page"), it is recommended to either use VFIO driver for all physical devices (so 113that IOVA and VA addresses can be the same, thereby bypassing physical addresses 114entirely), or use legacy memory mode. 115 116For chunks of memory which must be IOVA-contiguous, it is recommended to use 117``rte_memzone_reserve()`` function with ``RTE_MEMZONE_IOVA_CONTIG`` flag 118specified. This way, memory allocator will ensure that, whatever memory mode is 119in use, either reserved memory will satisfy the requirements, or the allocation 120will fail. 121 122There is no need to preallocate any memory at startup using ``-m`` or 123``--socket-mem`` command-line parameters, however it is still possible to do so, 124in which case preallocate memory will be "pinned" (i.e. will never be released 125by the application back to the system). It will be possible to allocate more 126hugepages, and deallocate those, but any preallocated pages will not be freed. 127If neither ``-m`` nor ``--socket-mem`` were specified, no memory will be 128preallocated, and all memory will be allocated at runtime, as needed. 129 130Another available option to use in dynamic memory mode is 131``--single-file-segments`` command-line option. This option will put pages in 132single files (per memseg list), as opposed to creating a file per page. This is 133normally not needed, but can be useful for use cases like userspace vhost, where 134there is limited number of page file descriptors that can be passed to VirtIO. 135 136If the application (or DPDK-internal code, such as device drivers) wishes to 137receive notifications about newly allocated memory, it is possible to register 138for memory event callbacks via ``rte_mem_event_callback_register()`` function. 139This will call a callback function any time DPDK's memory map has changed. 140 141If the application (or DPDK-internal code, such as device drivers) wishes to be 142notified about memory allocations above specified threshold (and have a chance 143to deny them), allocation validator callbacks are also available via 144``rte_mem_alloc_validator_callback_register()`` function. 145 146A default validator callback is provided by EAL, which can be enabled with a 147``--socket-limit`` command-line option, for a simple way to limit maximum amount 148of memory that can be used by DPDK application. 149 150.. warning:: 151 Memory subsystem uses DPDK IPC internally, so memory allocations/callbacks 152 and IPC must not be mixed: it is not safe to allocate/free memory inside 153 memory-related or IPC callbacks, and it is not safe to use IPC inside 154 memory-related callbacks. See chapter 155 :ref:`Multi-process Support <Multi-process_Support>` for more details about 156 DPDK IPC. 157 158+ Legacy memory mode 159 160This mode is enabled by specifying ``--legacy-mem`` command-line switch to the 161EAL. This switch will have no effect on FreeBSD as FreeBSD only supports 162legacy mode anyway. 163 164This mode mimics historical behavior of EAL. That is, EAL will reserve all 165memory at startup, sort all memory into large IOVA-contiguous chunks, and will 166not allow acquiring or releasing hugepages from the system at runtime. 167 168If neither ``-m`` nor ``--socket-mem`` were specified, the entire available 169hugepage memory will be preallocated. 170 171+ Hugepage allocation matching 172 173This behavior is enabled by specifying the ``--match-allocations`` command-line 174switch to the EAL. This switch is Linux-only and not supported with 175``--legacy-mem`` nor ``--no-huge``. 176 177Some applications using memory event callbacks may require that hugepages be 178freed exactly as they were allocated. These applications may also require 179that any allocation from the malloc heap not span across allocations 180associated with two different memory event callbacks. Hugepage allocation 181matching can be used by these types of applications to satisfy both of these 182requirements. This can result in some increased memory usage which is 183very dependent on the memory allocation patterns of the application. 184 185+ 32-bit support 186 187Additional restrictions are present when running in 32-bit mode. In dynamic 188memory mode, by default maximum of 2 gigabytes of VA space will be preallocated, 189and all of it will be on master lcore NUMA node unless ``--socket-mem`` flag is 190used. 191 192In legacy mode, VA space will only be preallocated for segments that were 193requested (plus padding, to keep IOVA-contiguousness). 194 195+ Maximum amount of memory 196 197All possible virtual memory space that can ever be used for hugepage mapping in 198a DPDK process is preallocated at startup, thereby placing an upper limit on how 199much memory a DPDK application can have. DPDK memory is stored in segment lists, 200each segment is strictly one physical page. It is possible to change the amount 201of virtual memory being preallocated at startup by editing the following config 202variables: 203 204* ``CONFIG_RTE_MAX_MEMSEG_LISTS`` controls how many segment lists can DPDK have 205* ``CONFIG_RTE_MAX_MEM_MB_PER_LIST`` controls how much megabytes of memory each 206 segment list can address 207* ``CONFIG_RTE_MAX_MEMSEG_PER_LIST`` controls how many segments each segment can 208 have 209* ``CONFIG_RTE_MAX_MEMSEG_PER_TYPE`` controls how many segments each memory type 210 can have (where "type" is defined as "page size + NUMA node" combination) 211* ``CONFIG_RTE_MAX_MEM_MB_PER_TYPE`` controls how much megabytes of memory each 212 memory type can address 213* ``CONFIG_RTE_MAX_MEM_MB`` places a global maximum on the amount of memory 214 DPDK can reserve 215 216Normally, these options do not need to be changed. 217 218.. note:: 219 220 Preallocated virtual memory is not to be confused with preallocated hugepage 221 memory! All DPDK processes preallocate virtual memory at startup. Hugepages 222 can later be mapped into that preallocated VA space (if dynamic memory mode 223 is enabled), and can optionally be mapped into it at startup. 224 225+ Segment file descriptors 226 227On Linux, in most cases, EAL will store segment file descriptors in EAL. This 228can become a problem when using smaller page sizes due to underlying limitations 229of ``glibc`` library. For example, Linux API calls such as ``select()`` may not 230work correctly because ``glibc`` does not support more than certain number of 231file descriptors. 232 233There are two possible solutions for this problem. The recommended solution is 234to use ``--single-file-segments`` mode, as that mode will not use a file 235descriptor per each page, and it will keep compatibility with Virtio with 236vhost-user backend. This option is not available when using ``--legacy-mem`` 237mode. 238 239Another option is to use bigger page sizes. Since fewer pages are required to 240cover the same memory area, fewer file descriptors will be stored internally 241by EAL. 242 243Support for Externally Allocated Memory 244~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 245 246It is possible to use externally allocated memory in DPDK. There are two ways in 247which using externally allocated memory can work: the malloc heap API's, and 248manual memory management. 249 250+ Using heap API's for externally allocated memory 251 252Using a set of malloc heap API's is the recommended way to use externally 253allocated memory in DPDK. In this way, support for externally allocated memory 254is implemented through overloading the socket ID - externally allocated heaps 255will have socket ID's that would be considered invalid under normal 256circumstances. Requesting an allocation to take place from a specified 257externally allocated memory is a matter of supplying the correct socket ID to 258DPDK allocator, either directly (e.g. through a call to ``rte_malloc``) or 259indirectly (through data structure-specific allocation API's such as 260``rte_ring_create``). Using these API's also ensures that mapping of externally 261allocated memory for DMA is also performed on any memory segment that is added 262to a DPDK malloc heap. 263 264Since there is no way DPDK can verify whether memory is available or valid, this 265responsibility falls on the shoulders of the user. All multiprocess 266synchronization is also user's responsibility, as well as ensuring that all 267calls to add/attach/detach/remove memory are done in the correct order. It is 268not required to attach to a memory area in all processes - only attach to memory 269areas as needed. 270 271The expected workflow is as follows: 272 273* Get a pointer to memory area 274* Create a named heap 275* Add memory area(s) to the heap 276 - If IOVA table is not specified, IOVA addresses will be assumed to be 277 unavailable, and DMA mappings will not be performed 278 - Other processes must attach to the memory area before they can use it 279* Get socket ID used for the heap 280* Use normal DPDK allocation procedures, using supplied socket ID 281* If memory area is no longer needed, it can be removed from the heap 282 - Other processes must detach from this memory area before it can be removed 283* If heap is no longer needed, remove it 284 - Socket ID will become invalid and will not be reused 285 286For more information, please refer to ``rte_malloc`` API documentation, 287specifically the ``rte_malloc_heap_*`` family of function calls. 288 289+ Using externally allocated memory without DPDK API's 290 291While using heap API's is the recommended method of using externally allocated 292memory in DPDK, there are certain use cases where the overhead of DPDK heap API 293is undesirable - for example, when manual memory management is performed on an 294externally allocated area. To support use cases where externally allocated 295memory will not be used as part of normal DPDK workflow, there is also another 296set of API's under the ``rte_extmem_*`` namespace. 297 298These API's are (as their name implies) intended to allow registering or 299unregistering externally allocated memory to/from DPDK's internal page table, to 300allow API's like ``rte_virt2memseg`` etc. to work with externally allocated 301memory. Memory added this way will not be available for any regular DPDK 302allocators; DPDK will leave this memory for the user application to manage. 303 304The expected workflow is as follows: 305 306* Get a pointer to memory area 307* Register memory within DPDK 308 - If IOVA table is not specified, IOVA addresses will be assumed to be 309 unavailable 310 - Other processes must attach to the memory area before they can use it 311* Perform DMA mapping with ``rte_dev_dma_map`` if needed 312* Use the memory area in your application 313* If memory area is no longer needed, it can be unregistered 314 - If the area was mapped for DMA, unmapping must be performed before 315 unregistering memory 316 - Other processes must detach from the memory area before it can be 317 unregistered 318 319Since these externally allocated memory areas will not be managed by DPDK, it is 320therefore up to the user application to decide how to use them and what to do 321with them once they're registered. 322 323Per-lcore and Shared Variables 324~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 325 326.. note:: 327 328 lcore refers to a logical execution unit of the processor, sometimes called a hardware *thread*. 329 330Shared variables are the default behavior. 331Per-lcore variables are implemented using *Thread Local Storage* (TLS) to provide per-thread local storage. 332 333Logs 334~~~~ 335 336A logging API is provided by EAL. 337By default, in a Linux application, logs are sent to syslog and also to the console. 338However, the log function can be overridden by the user to use a different logging mechanism. 339 340Trace and Debug Functions 341^^^^^^^^^^^^^^^^^^^^^^^^^ 342 343There are some debug functions to dump the stack in glibc. 344The rte_panic() function can voluntarily provoke a SIG_ABORT, 345which can trigger the generation of a core file, readable by gdb. 346 347CPU Feature Identification 348~~~~~~~~~~~~~~~~~~~~~~~~~~ 349 350The EAL can query the CPU at runtime (using the rte_cpu_get_features() function) to determine which CPU features are available. 351 352User Space Interrupt Event 353~~~~~~~~~~~~~~~~~~~~~~~~~~ 354 355+ User Space Interrupt and Alarm Handling in Host Thread 356 357The EAL creates a host thread to poll the UIO device file descriptors to detect the interrupts. 358Callbacks can be registered or unregistered by the EAL functions for a specific interrupt event 359and are called in the host thread asynchronously. 360The EAL also allows timed callbacks to be used in the same way as for NIC interrupts. 361 362.. note:: 363 364 In DPDK PMD, the only interrupts handled by the dedicated host thread are those for link status change 365 (link up and link down notification) and for sudden device removal. 366 367 368+ RX Interrupt Event 369 370The receive and transmit routines provided by each PMD don't limit themselves to execute in polling thread mode. 371To ease the idle polling with tiny throughput, it's useful to pause the polling and wait until the wake-up event happens. 372The RX interrupt is the first choice to be such kind of wake-up event, but probably won't be the only one. 373 374EAL provides the event APIs for this event-driven thread mode. 375Taking Linux as an example, the implementation relies on epoll. Each thread can monitor an epoll instance 376in which all the wake-up events' file descriptors are added. The event file descriptors are created and mapped to 377the interrupt vectors according to the UIO/VFIO spec. 378From FreeBSD's perspective, kqueue is the alternative way, but not implemented yet. 379 380EAL initializes the mapping between event file descriptors and interrupt vectors, while each device initializes the mapping 381between interrupt vectors and queues. In this way, EAL actually is unaware of the interrupt cause on the specific vector. 382The eth_dev driver takes responsibility to program the latter mapping. 383 384.. note:: 385 386 Per queue RX interrupt event is only allowed in VFIO which supports multiple MSI-X vector. In UIO, the RX interrupt 387 together with other interrupt causes shares the same vector. In this case, when RX interrupt and LSC(link status change) 388 interrupt are both enabled(intr_conf.lsc == 1 && intr_conf.rxq == 1), only the former is capable. 389 390The RX interrupt are controlled/enabled/disabled by ethdev APIs - 'rte_eth_dev_rx_intr_*'. They return failure if the PMD 391hasn't support them yet. The intr_conf.rxq flag is used to turn on the capability of RX interrupt per device. 392 393+ Device Removal Event 394 395This event is triggered by a device being removed at a bus level. Its 396underlying resources may have been made unavailable (i.e. PCI mappings 397unmapped). The PMD must make sure that on such occurrence, the application can 398still safely use its callbacks. 399 400This event can be subscribed to in the same way one would subscribe to a link 401status change event. The execution context is thus the same, i.e. it is the 402dedicated interrupt host thread. 403 404Considering this, it is likely that an application would want to close a 405device having emitted a Device Removal Event. In such case, calling 406``rte_eth_dev_close()`` can trigger it to unregister its own Device Removal Event 407callback. Care must be taken not to close the device from the interrupt handler 408context. It is necessary to reschedule such closing operation. 409 410Blacklisting 411~~~~~~~~~~~~ 412 413The EAL PCI device blacklist functionality can be used to mark certain NIC ports as blacklisted, 414so they are ignored by the DPDK. 415The ports to be blacklisted are identified using the PCIe* description (Domain:Bus:Device.Function). 416 417Misc Functions 418~~~~~~~~~~~~~~ 419 420Locks and atomic operations are per-architecture (i686 and x86_64). 421 422IOVA Mode Detection 423~~~~~~~~~~~~~~~~~~~ 424 425IOVA Mode is selected by considering what the current usable Devices on the 426system require and/or support. 427 428On FreeBSD, RTE_IOVA_PA is always the default. On Linux, the IOVA mode is 429detected based on a 2-step heuristic detailed below. 430 431For the first step, EAL asks each bus its requirement in terms of IOVA mode 432and decides on a preferred IOVA mode. 433 434- if all buses report RTE_IOVA_PA, then the preferred IOVA mode is RTE_IOVA_PA, 435- if all buses report RTE_IOVA_VA, then the preferred IOVA mode is RTE_IOVA_VA, 436- if all buses report RTE_IOVA_DC, no bus expressed a preferrence, then the 437 preferred mode is RTE_IOVA_DC, 438- if the buses disagree (at least one wants RTE_IOVA_PA and at least one wants 439 RTE_IOVA_VA), then the preferred IOVA mode is RTE_IOVA_DC (see below with the 440 check on Physical Addresses availability), 441 442If the buses have expressed no preference on which IOVA mode to pick, then a 443default is selected using the following logic: 444 445- if physical addresses are not available, RTE_IOVA_VA mode is used 446- if /sys/kernel/iommu_groups is not empty, RTE_IOVA_VA mode is used 447- otherwise, RTE_IOVA_PA mode is used 448 449In the case when the buses had disagreed on their preferred IOVA mode, part of 450the buses won't work because of this decision. 451 452The second step checks if the preferred mode complies with the Physical 453Addresses availability since those are only available to root user in recent 454kernels. Namely, if the preferred mode is RTE_IOVA_PA but there is no access to 455Physical Addresses, then EAL init fails early, since later probing of the 456devices would fail anyway. 457 458.. note:: 459 460 The RTE_IOVA_VA mode is preferred as the default in most cases for the 461 following reasons: 462 463 - All drivers are expected to work in RTE_IOVA_VA mode, irrespective of 464 physical address availability. 465 - By default, the mempool, first asks for IOVA-contiguous memory using 466 ``RTE_MEMZONE_IOVA_CONTIG``. This is slow in RTE_IOVA_PA mode and it may 467 affect the application boot time. 468 - It is easy to enable large amount of IOVA-contiguous memory use-cases 469 with IOVA in VA mode. 470 471 It is expected that all PCI drivers work in both RTE_IOVA_PA and 472 RTE_IOVA_VA modes. 473 474 If a PCI driver does not support RTE_IOVA_PA mode, the 475 ``RTE_PCI_DRV_NEED_IOVA_AS_VA`` flag is used to dictate that this PCI 476 driver can only work in RTE_IOVA_VA mode. 477 478 When the KNI kernel module is detected, RTE_IOVA_PA mode is preferred as a 479 performance penalty is expected in RTE_IOVA_VA mode. 480 481IOVA Mode Configuration 482~~~~~~~~~~~~~~~~~~~~~~~ 483 484Auto detection of the IOVA mode, based on probing the bus and IOMMU configuration, may not report 485the desired addressing mode when virtual devices that are not directly attached to the bus are present. 486To facilitate forcing the IOVA mode to a specific value the EAL command line option ``--iova-mode`` can 487be used to select either physical addressing('pa') or virtual addressing('va'). 488 489Memory Segments and Memory Zones (memzone) 490------------------------------------------ 491 492The mapping of physical memory is provided by this feature in the EAL. 493As physical memory can have gaps, the memory is described in a table of descriptors, 494and each descriptor (called rte_memseg ) describes a physical page. 495 496On top of this, the memzone allocator's role is to reserve contiguous portions of physical memory. 497These zones are identified by a unique name when the memory is reserved. 498 499The rte_memzone descriptors are also located in the configuration structure. 500This structure is accessed using rte_eal_get_configuration(). 501The lookup (by name) of a memory zone returns a descriptor containing the physical address of the memory zone. 502 503Memory zones can be reserved with specific start address alignment by supplying the align parameter 504(by default, they are aligned to cache line size). 505The alignment value should be a power of two and not less than the cache line size (64 bytes). 506Memory zones can also be reserved from either 2 MB or 1 GB hugepages, provided that both are available on the system. 507 508Both memsegs and memzones are stored using ``rte_fbarray`` structures. Please 509refer to *DPDK API Reference* for more information. 510 511 512Multiple pthread 513---------------- 514 515DPDK usually pins one pthread per core to avoid the overhead of task switching. 516This allows for significant performance gains, but lacks flexibility and is not always efficient. 517 518Power management helps to improve the CPU efficiency by limiting the CPU runtime frequency. 519However, alternately it is possible to utilize the idle cycles available to take advantage of 520the full capability of the CPU. 521 522By taking advantage of cgroup, the CPU utilization quota can be simply assigned. 523This gives another way to improve the CPU efficiency, however, there is a prerequisite; 524DPDK must handle the context switching between multiple pthreads per core. 525 526For further flexibility, it is useful to set pthread affinity not only to a CPU but to a CPU set. 527 528EAL pthread and lcore Affinity 529~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 530 531The term "lcore" refers to an EAL thread, which is really a Linux/FreeBSD pthread. 532"EAL pthreads" are created and managed by EAL and execute the tasks issued by *remote_launch*. 533In each EAL pthread, there is a TLS (Thread Local Storage) called *_lcore_id* for unique identification. 534As EAL pthreads usually bind 1:1 to the physical CPU, the *_lcore_id* is typically equal to the CPU ID. 535 536When using multiple pthreads, however, the binding is no longer always 1:1 between an EAL pthread and a specified physical CPU. 537The EAL pthread may have affinity to a CPU set, and as such the *_lcore_id* will not be the same as the CPU ID. 538For this reason, there is an EAL long option '--lcores' defined to assign the CPU affinity of lcores. 539For a specified lcore ID or ID group, the option allows setting the CPU set for that EAL pthread. 540 541The format pattern: 542 --lcores='<lcore_set>[@cpu_set][,<lcore_set>[@cpu_set],...]' 543 544'lcore_set' and 'cpu_set' can be a single number, range or a group. 545 546A number is a "digit([0-9]+)"; a range is "<number>-<number>"; a group is "(<number|range>[,<number|range>,...])". 547 548If a '\@cpu_set' value is not supplied, the value of 'cpu_set' will default to the value of 'lcore_set'. 549 550 :: 551 552 For example, "--lcores='1,2@(5-7),(3-5)@(0,2),(0,6),7-8'" which means start 9 EAL thread; 553 lcore 0 runs on cpuset 0x41 (cpu 0,6); 554 lcore 1 runs on cpuset 0x2 (cpu 1); 555 lcore 2 runs on cpuset 0xe0 (cpu 5,6,7); 556 lcore 3,4,5 runs on cpuset 0x5 (cpu 0,2); 557 lcore 6 runs on cpuset 0x41 (cpu 0,6); 558 lcore 7 runs on cpuset 0x80 (cpu 7); 559 lcore 8 runs on cpuset 0x100 (cpu 8). 560 561Using this option, for each given lcore ID, the associated CPUs can be assigned. 562It's also compatible with the pattern of corelist('-l') option. 563 564non-EAL pthread support 565~~~~~~~~~~~~~~~~~~~~~~~ 566 567It is possible to use the DPDK execution context with any user pthread (aka. Non-EAL pthreads). 568In 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*. 569Some 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). 570 571All these impacts are mentioned in :ref:`known_issue_label` section. 572 573Public Thread API 574~~~~~~~~~~~~~~~~~ 575 576There are two public APIs ``rte_thread_set_affinity()`` and ``rte_thread_get_affinity()`` introduced for threads. 577When they're used in any pthread context, the Thread Local Storage(TLS) will be set/get. 578 579Those TLS include *_cpuset* and *_socket_id*: 580 581* *_cpuset* stores the CPUs bitmap to which the pthread is affinitized. 582 583* *_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. 584 585 586Control Thread API 587~~~~~~~~~~~~~~~~~~ 588 589It is possible to create Control Threads using the public API 590``rte_ctrl_thread_create()``. 591Those threads can be used for management/infrastructure tasks and are used 592internally by DPDK for multi process support and interrupt handling. 593 594Those threads will be scheduled on CPUs part of the original process CPU 595affinity from which the dataplane and service lcores are excluded. 596 597For example, on a 8 CPUs system, starting a dpdk application with -l 2,3 598(dataplane cores), then depending on the affinity configuration which can be 599controlled with tools like taskset (Linux) or cpuset (FreeBSD), 600 601- with no affinity configuration, the Control Threads will end up on 602 0-1,4-7 CPUs. 603- with affinity restricted to 2-4, the Control Threads will end up on 604 CPU 4. 605- with affinity restricted to 2-3, the Control Threads will end up on 606 CPU 2 (master lcore, which is the default when no CPU is available). 607 608.. _known_issue_label: 609 610Known Issues 611~~~~~~~~~~~~ 612 613+ rte_mempool 614 615 The rte_mempool uses a per-lcore cache inside the mempool. 616 For non-EAL pthreads, ``rte_lcore_id()`` will not return a valid number. 617 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. 618 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. 619 620+ rte_ring 621 622 rte_ring supports multi-producer enqueue and multi-consumer dequeue. 623 However, it is non-preemptive, this has a knock on effect of making rte_mempool non-preemptable. 624 625 .. note:: 626 627 The "non-preemptive" constraint means: 628 629 - a pthread doing multi-producers enqueues on a given ring must not 630 be preempted by another pthread doing a multi-producer enqueue on 631 the same ring. 632 - a pthread doing multi-consumers dequeues on a given ring must not 633 be preempted by another pthread doing a multi-consumer dequeue on 634 the same ring. 635 636 Bypassing this constraint may cause the 2nd pthread to spin until the 1st one is scheduled again. 637 Moreover, if the 1st pthread is preempted by a context that has an higher priority, it may even cause a dead lock. 638 639 This means, use cases involving preemptible pthreads should consider using rte_ring carefully. 640 641 1. It CAN be used for preemptible single-producer and single-consumer use case. 642 643 2. It CAN be used for non-preemptible multi-producer and preemptible single-consumer use case. 644 645 3. It CAN be used for preemptible single-producer and non-preemptible multi-consumer use case. 646 647 4. It MAY be used by preemptible multi-producer and/or preemptible multi-consumer pthreads whose scheduling policy are all SCHED_OTHER(cfs), SCHED_IDLE or SCHED_BATCH. User SHOULD be aware of the performance penalty before using it. 648 649 5. It MUST not be used by multi-producer/consumer pthreads, whose scheduling policies are SCHED_FIFO or SCHED_RR. 650 651 Alternatively, applications can use the lock-free stack mempool handler. When 652 considering this handler, note that: 653 654 - It is currently limited to the aarch64 and x86_64 platforms, because it uses 655 an instruction (16-byte compare-and-swap) that is not yet available on other 656 platforms. 657 - It has worse average-case performance than the non-preemptive rte_ring, but 658 software caching (e.g. the mempool cache) can mitigate this by reducing the 659 number of stack accesses. 660 661+ rte_timer 662 663 Running ``rte_timer_manage()`` on a non-EAL pthread is not allowed. However, resetting/stopping the timer from a non-EAL pthread is allowed. 664 665+ rte_log 666 667 In non-EAL pthreads, there is no per thread loglevel and logtype, global loglevels are used. 668 669+ misc 670 671 The debug statistics of rte_ring, rte_mempool and rte_timer are not supported in a non-EAL pthread. 672 673cgroup control 674~~~~~~~~~~~~~~ 675 676The 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). 677We expect only 50% of CPU spend on packet IO. 678 679 .. code-block:: console 680 681 mkdir /sys/fs/cgroup/cpu/pkt_io 682 mkdir /sys/fs/cgroup/cpuset/pkt_io 683 684 echo $cpu > /sys/fs/cgroup/cpuset/cpuset.cpus 685 686 echo $t0 > /sys/fs/cgroup/cpu/pkt_io/tasks 687 echo $t0 > /sys/fs/cgroup/cpuset/pkt_io/tasks 688 689 echo $t1 > /sys/fs/cgroup/cpu/pkt_io/tasks 690 echo $t1 > /sys/fs/cgroup/cpuset/pkt_io/tasks 691 692 cd /sys/fs/cgroup/cpu/pkt_io 693 echo 100000 > pkt_io/cpu.cfs_period_us 694 echo 50000 > pkt_io/cpu.cfs_quota_us 695 696 697Malloc 698------ 699 700The EAL provides a malloc API to allocate any-sized memory. 701 702The objective of this API is to provide malloc-like functions to allow 703allocation from hugepage memory and to facilitate application porting. 704The *DPDK API Reference* manual describes the available functions. 705 706Typically, these kinds of allocations should not be done in data plane 707processing because they are slower than pool-based allocation and make 708use of locks within the allocation and free paths. 709However, they can be used in configuration code. 710 711Refer to the rte_malloc() function description in the *DPDK API Reference* 712manual for more information. 713 714Cookies 715~~~~~~~ 716 717When CONFIG_RTE_MALLOC_DEBUG is enabled, the allocated memory contains 718overwrite protection fields to help identify buffer overflows. 719 720Alignment and NUMA Constraints 721~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 722 723The rte_malloc() takes an align argument that can be used to request a memory 724area that is aligned on a multiple of this value (which must be a power of two). 725 726On systems with NUMA support, a call to the rte_malloc() function will return 727memory that has been allocated on the NUMA socket of the core which made the call. 728A set of APIs is also provided, to allow memory to be explicitly allocated on a 729NUMA socket directly, or by allocated on the NUMA socket where another core is 730located, in the case where the memory is to be used by a logical core other than 731on the one doing the memory allocation. 732 733Use Cases 734~~~~~~~~~ 735 736This API is meant to be used by an application that requires malloc-like 737functions at initialization time. 738 739For allocating/freeing data at runtime, in the fast-path of an application, 740the memory pool library should be used instead. 741 742Internal Implementation 743~~~~~~~~~~~~~~~~~~~~~~~ 744 745Data Structures 746^^^^^^^^^^^^^^^ 747 748There are two data structure types used internally in the malloc library: 749 750* struct malloc_heap - used to track free space on a per-socket basis 751 752* struct malloc_elem - the basic element of allocation and free-space 753 tracking inside the library. 754 755Structure: malloc_heap 756"""""""""""""""""""""" 757 758The malloc_heap structure is used to manage free space on a per-socket basis. 759Internally, there is one heap structure per NUMA node, which allows us to 760allocate memory to a thread based on the NUMA node on which this thread runs. 761While this does not guarantee that the memory will be used on that NUMA node, 762it is no worse than a scheme where the memory is always allocated on a fixed 763or random node. 764 765The key fields of the heap structure and their function are described below 766(see also diagram above): 767 768* lock - the lock field is needed to synchronize access to the heap. 769 Given that the free space in the heap is tracked using a linked list, 770 we need a lock to prevent two threads manipulating the list at the same time. 771 772* free_head - this points to the first element in the list of free nodes for 773 this malloc heap. 774 775* first - this points to the first element in the heap. 776 777* last - this points to the last element in the heap. 778 779.. _figure_malloc_heap: 780 781.. figure:: img/malloc_heap.* 782 783 Example of a malloc heap and malloc elements within the malloc library 784 785 786.. _malloc_elem: 787 788Structure: malloc_elem 789"""""""""""""""""""""" 790 791The malloc_elem structure is used as a generic header structure for various 792blocks of memory. 793It is used in two different ways - all shown in the diagram above: 794 795#. As a header on a block of free or allocated memory - normal case 796 797#. As a padding header inside a block of memory 798 799The most important fields in the structure and how they are used are described below. 800 801Malloc heap is a doubly-linked list, where each element keeps track of its 802previous and next elements. Due to the fact that hugepage memory can come and 803go, neighboring malloc elements may not necessarily be adjacent in memory. 804Also, since a malloc element may span multiple pages, its contents may not 805necessarily be IOVA-contiguous either - each malloc element is only guaranteed 806to be virtually contiguous. 807 808.. note:: 809 810 If the usage of a particular field in one of the above three usages is not 811 described, the field can be assumed to have an undefined value in that 812 situation, for example, for padding headers only the "state" and "pad" 813 fields have valid values. 814 815* heap - this pointer is a reference back to the heap structure from which 816 this block was allocated. 817 It is used for normal memory blocks when they are being freed, to add the 818 newly-freed block to the heap's free-list. 819 820* prev - this pointer points to previous header element/block in memory. When 821 freeing a block, this pointer is used to reference the previous block to 822 check if that block is also free. If so, and the two blocks are immediately 823 adjacent to each other, then the two free blocks are merged to form a single 824 larger block. 825 826* next - this pointer points to next header element/block in memory. When 827 freeing a block, this pointer is used to reference the next block to check 828 if that block is also free. If so, and the two blocks are immediately 829 adjacent to each other, then the two free blocks are merged to form a single 830 larger block. 831 832* free_list - this is a structure pointing to previous and next elements in 833 this heap's free list. 834 It is only used in normal memory blocks; on ``malloc()`` to find a suitable 835 free block to allocate and on ``free()`` to add the newly freed element to 836 the free-list. 837 838* state - This field can have one of three values: ``FREE``, ``BUSY`` or 839 ``PAD``. 840 The former two are to indicate the allocation state of a normal memory block 841 and the latter is to indicate that the element structure is a dummy structure 842 at the end of the start-of-block padding, i.e. where the start of the data 843 within a block is not at the start of the block itself, due to alignment 844 constraints. 845 In that case, the pad header is used to locate the actual malloc element 846 header for the block. 847 848* pad - this holds the length of the padding present at the start of the block. 849 In the case of a normal block header, it is added to the address of the end 850 of the header to give the address of the start of the data area, i.e. the 851 value passed back to the application on a malloc. 852 Within a dummy header inside the padding, this same value is stored, and is 853 subtracted from the address of the dummy header to yield the address of the 854 actual block header. 855 856* size - the size of the data block, including the header itself. 857 858Memory Allocation 859^^^^^^^^^^^^^^^^^ 860 861On EAL initialization, all preallocated memory segments are setup as part of the 862malloc heap. This setup involves placing an :ref:`element header<malloc_elem>` 863with ``FREE`` at the start of each virtually contiguous segment of memory. 864The ``FREE`` element is then added to the ``free_list`` for the malloc heap. 865 866This setup also happens whenever memory is allocated at runtime (if supported), 867in which case newly allocated pages are also added to the heap, merging with any 868adjacent free segments if there are any. 869 870When an application makes a call to a malloc-like function, the malloc function 871will first index the ``lcore_config`` structure for the calling thread, and 872determine the NUMA node of that thread. 873The NUMA node is used to index the array of ``malloc_heap`` structures which is 874passed as a parameter to the ``heap_alloc()`` function, along with the 875requested size, type, alignment and boundary parameters. 876 877The ``heap_alloc()`` function will scan the free_list of the heap, and attempt 878to find a free block suitable for storing data of the requested size, with the 879requested alignment and boundary constraints. 880 881When a suitable free element has been identified, the pointer to be returned 882to the user is calculated. 883The cache-line of memory immediately preceding this pointer is filled with a 884struct malloc_elem header. 885Because of alignment and boundary constraints, there could be free space at 886the start and/or end of the element, resulting in the following behavior: 887 888#. Check for trailing space. 889 If the trailing space is big enough, i.e. > 128 bytes, then the free element 890 is split. 891 If it is not, then we just ignore it (wasted space). 892 893#. Check for space at the start of the element. 894 If the space at the start is small, i.e. <=128 bytes, then a pad header is 895 used, and the remaining space is wasted. 896 If, however, the remaining space is greater, then the free element is split. 897 898The advantage of allocating the memory from the end of the existing element is 899that no adjustment of the free list needs to take place - the existing element 900on the free list just has its size value adjusted, and the next/previous elements 901have their "prev"/"next" pointers redirected to the newly created element. 902 903In case when there is not enough memory in the heap to satisfy allocation 904request, EAL will attempt to allocate more memory from the system (if supported) 905and, following successful allocation, will retry reserving the memory again. In 906a multiprocessing scenario, all primary and secondary processes will synchronize 907their memory maps to ensure that any valid pointer to DPDK memory is guaranteed 908to be valid at all times in all currently running processes. 909 910Failure to synchronize memory maps in one of the processes will cause allocation 911to fail, even though some of the processes may have allocated the memory 912successfully. The memory is not added to the malloc heap unless primary process 913has ensured that all other processes have mapped this memory successfully. 914 915Any successful allocation event will trigger a callback, for which user 916applications and other DPDK subsystems can register. Additionally, validation 917callbacks will be triggered before allocation if the newly allocated memory will 918exceed threshold set by the user, giving a chance to allow or deny allocation. 919 920.. note:: 921 922 Any allocation of new pages has to go through primary process. If the 923 primary process is not active, no memory will be allocated even if it was 924 theoretically possible to do so. This is because primary's process map acts 925 as an authority on what should or should not be mapped, while each secondary 926 process has its own, local memory map. Secondary processes do not update the 927 shared memory map, they only copy its contents to their local memory map. 928 929Freeing Memory 930^^^^^^^^^^^^^^ 931 932To free an area of memory, the pointer to the start of the data area is passed 933to the free function. 934The size of the ``malloc_elem`` structure is subtracted from this pointer to get 935the element header for the block. 936If this header is of type ``PAD`` then the pad length is further subtracted from 937the pointer to get the proper element header for the entire block. 938 939From this element header, we get pointers to the heap from which the block was 940allocated and to where it must be freed, as well as the pointer to the previous 941and next elements. These next and previous elements are then checked to see if 942they are also ``FREE`` and are immediately adjacent to the current one, and if 943so, they are merged with the current element. This means that we can never have 944two ``FREE`` memory blocks adjacent to one another, as they are always merged 945into a single block. 946 947If deallocating pages at runtime is supported, and the free element encloses 948one or more pages, those pages can be deallocated and be removed from the heap. 949If DPDK was started with command-line parameters for preallocating memory 950(``-m`` or ``--socket-mem``), then those pages that were allocated at startup 951will not be deallocated. 952 953Any successful deallocation event will trigger a callback, for which user 954applications and other DPDK subsystems can register. 955