1 .. SPDX-License-Identifier: GPL-2.0
3 ============================================================
4 Linux kernel driver for Elastic Network Adapter (ENA) family
5 ============================================================
10 ENA is a networking interface designed to make good use of modern CPU
11 features and system architectures.
13 The ENA device exposes a lightweight management interface with a
14 minimal set of memory mapped registers and extendable command set
15 through an Admin Queue.
17 The driver supports a range of ENA devices, is link-speed independent
18 (i.e., the same driver is used for 10GbE, 25GbE, 40GbE, etc.), and has
19 a negotiated and extendable feature set.
21 Some ENA devices support SR-IOV. This driver is used for both the
22 SR-IOV Physical Function (PF) and Virtual Function (VF) devices.
24 ENA devices enable high speed and low overhead network traffic
25 processing by providing multiple Tx/Rx queue pairs (the maximum number
26 is advertised by the device via the Admin Queue), a dedicated MSI-X
27 interrupt vector per Tx/Rx queue pair, adaptive interrupt moderation,
28 and CPU cacheline optimized data placement.
30 The ENA driver supports industry standard TCP/IP offload features such
31 as checksum offload and TCP transmit segmentation offload (TSO).
32 Receive-side scaling (RSS) is supported for multi-core scaling.
34 The ENA driver and its corresponding devices implement health
35 monitoring mechanisms such as watchdog, enabling the device and driver
36 to recover in a manner transparent to the application, as well as
39 Some of the ENA devices support a working mode called Low-latency
40 Queue (LLQ), which saves several more microseconds.
42 ENA Source Code Directory Structure
43 ===================================
45 ================= ======================================================
46 ena_com.[ch] Management communication layer. This layer is
47 responsible for the handling all the management
48 (admin) communication between the device and the
50 ena_eth_com.[ch] Tx/Rx data path.
51 ena_admin_defs.h Definition of ENA management interface.
52 ena_eth_io_defs.h Definition of ENA data path interface.
53 ena_common_defs.h Common definitions for ena_com layer.
54 ena_regs_defs.h Definition of ENA PCI memory-mapped (MMIO) registers.
55 ena_netdev.[ch] Main Linux kernel driver.
56 ena_syfsfs.[ch] Sysfs files.
57 ena_ethtool.c ethtool callbacks.
58 ena_pci_id_tbl.h Supported device IDs.
59 ================= ======================================================
64 ENA management interface is exposed by means of:
66 - PCIe Configuration Space
68 - Admin Queue (AQ) and Admin Completion Queue (ACQ)
69 - Asynchronous Event Notification Queue (AENQ)
71 ENA device MMIO Registers are accessed only during driver
72 initialization and are not involved in further normal device
75 AQ is used for submitting management commands, and the
76 results/responses are reported asynchronously through ACQ.
78 ENA introduces a small set of management commands with room for
79 vendor-specific extensions. Most of the management operations are
80 framed in a generic Get/Set feature command.
82 The following admin queue commands are supported:
84 - Create I/O submission queue
85 - Create I/O completion queue
86 - Destroy I/O submission queue
87 - Destroy I/O completion queue
93 Refer to ena_admin_defs.h for the list of supported Get/Set Feature
96 The Asynchronous Event Notification Queue (AENQ) is a uni-directional
97 queue used by the ENA device to send to the driver events that cannot
98 be reported using ACQ. AENQ events are subdivided into groups. Each
99 group may have multiple syndromes, as shown below
103 ==================== ===============
105 ==================== ===============
106 Link state change **X**
108 Notification Suspend traffic
109 Notification Resume traffic
111 ==================== ===============
113 ACQ and AENQ share the same MSI-X vector.
115 Keep-Alive is a special mechanism that allows monitoring of the
116 device's health. The driver maintains a watchdog (WD) handler which,
117 if fired, logs the current state and statistics then resets and
118 restarts the ENA device and driver. A Keep-Alive event is delivered by
119 the device every second. The driver re-arms the WD upon reception of a
120 Keep-Alive event. A missed Keep-Alive event causes the WD handler to
125 I/O operations are based on Tx and Rx Submission Queues (Tx SQ and Rx
126 SQ correspondingly). Each SQ has a completion queue (CQ) associated
129 The SQs and CQs are implemented as descriptor rings in contiguous
132 The ENA driver supports two Queue Operation modes for Tx SQs:
136 * In this mode the Tx SQs reside in the host's memory. The ENA
137 device fetches the ENA Tx descriptors and packet data from host
140 - Low Latency Queue (LLQ) mode or "push-mode".
142 * In this mode the driver pushes the transmit descriptors and the
143 first 128 bytes of the packet directly to the ENA device memory
144 space. The rest of the packet payload is fetched by the
145 device. For this operation mode, the driver uses a dedicated PCI
146 device memory BAR, which is mapped with write-combine capability.
148 The Rx SQs support only the regular mode.
150 Note: Not all ENA devices support LLQ, and this feature is negotiated
151 with the device upon initialization. If the ENA device does not
152 support LLQ mode, the driver falls back to the regular mode.
154 The driver supports multi-queue for both Tx and Rx. This has various
157 - Reduced CPU/thread/process contention on a given Ethernet interface.
158 - Cache miss rate on completion is reduced, particularly for data
159 cache lines that hold the sk_buff structures.
160 - Increased process-level parallelism when handling received packets.
161 - Increased data cache hit rate, by steering kernel processing of
162 packets to the CPU, where the application thread consuming the
164 - In hardware interrupt re-direction.
168 The driver assigns a single MSI-X vector per queue pair (for both Tx
169 and Rx directions). The driver assigns an additional dedicated MSI-X vector
170 for management (for ACQ and AENQ).
172 Management interrupt registration is performed when the Linux kernel
173 probes the adapter, and it is de-registered when the adapter is
174 removed. I/O queue interrupt registration is performed when the Linux
175 interface of the adapter is opened, and it is de-registered when the
178 The management interrupt is named::
180 ena-mgmnt@pci:<PCI domain:bus:slot.function>
182 and for each queue pair, an interrupt is named::
184 <interface name>-Tx-Rx-<queue index>
186 The ENA device operates in auto-mask and auto-clear interrupt
187 modes. That is, once MSI-X is delivered to the host, its Cause bit is
188 automatically cleared and the interrupt is masked. The interrupt is
189 unmasked by the driver after NAPI processing is complete.
193 ENA driver and device can operate in conventional or adaptive interrupt
196 In conventional mode the driver instructs device to postpone interrupt
197 posting according to static interrupt delay value. The interrupt delay
198 value can be configured through ethtool(8). The following ethtool
199 parameters are supported by the driver: tx-usecs, rx-usecs
201 In adaptive interrupt moderation mode the interrupt delay value is
202 updated by the driver dynamically and adjusted every NAPI cycle
203 according to the traffic nature.
205 Adaptive coalescing can be switched on/off through ethtool(8)
206 adaptive_rx on|off parameter.
208 More information about Adaptive Interrupt Moderation (DIM) can be found in
209 Documentation/networking/net_dim.rst
213 The rx_copybreak is initialized by default to ENA_DEFAULT_RX_COPYBREAK
214 and can be configured by the ETHTOOL_STUNABLE command of the
219 The driver-allocated SKB for frames received from Rx handling using
220 NAPI context. The allocation method depends on the size of the packet.
221 If the frame length is larger than rx_copybreak, napi_get_frags()
222 is used, otherwise netdev_alloc_skb_ip_align() is used, the buffer
223 content is copied (by CPU) to the SKB, and the buffer is recycled.
227 The user can obtain ENA device and driver statistics using ethtool.
228 The driver can collect regular or extended statistics (including
229 per-queue stats) from the device.
231 In addition the driver logs the stats to syslog upon device reset.
235 The driver supports an arbitrarily large MTU with a maximum that is
236 negotiated with the device. The driver configures MTU using the
237 SetFeature command (ENA_ADMIN_MTU property). The user can change MTU
238 via ip(8) and similar legacy tools.
242 The ENA driver supports:
246 - IPv4 header checksum offload
247 - TCP/UDP over IPv4/IPv6 checksum offloads
251 - The ENA device supports RSS that allows flexible Rx traffic
253 - Toeplitz and CRC32 hash functions are supported.
254 - Different combinations of L2/L3/L4 fields can be configured as
255 inputs for hash functions.
256 - The driver configures RSS settings using the AQ SetFeature command
257 (ENA_ADMIN_RSS_HASH_FUNCTION, ENA_ADMIN_RSS_HASH_INPUT and
258 ENA_ADMIN_RSS_INDIRECTION_TABLE_CONFIG properties).
259 - If the NETIF_F_RXHASH flag is set, the 32-bit result of the hash
260 function delivered in the Rx CQ descriptor is set in the received
262 - The user can provide a hash key, hash function, and configure the
263 indirection table through ethtool(8).
270 end_start_xmit() is called by the stack. This function does the following:
272 - Maps data buffers (skb->data and frags).
273 - Populates ena_buf for the push buffer (if the driver and device are
275 - Prepares ENA bufs for the remaining frags.
276 - Allocates a new request ID from the empty req_id ring. The request
277 ID is the index of the packet in the Tx info. This is used for
278 out-of-order TX completions.
279 - Adds the packet to the proper place in the Tx ring.
280 - Calls ena_com_prepare_tx(), an ENA communication layer that converts
281 the ena_bufs to ENA descriptors (and adds meta ENA descriptors as
284 * This function also copies the ENA descriptors and the push buffer
285 to the Device memory space (if in push mode.)
287 - Writes doorbell to the ENA device.
288 - When the ENA device finishes sending the packet, a completion
290 - The interrupt handler schedules NAPI.
291 - The ena_clean_tx_irq() function is called. This function handles the
292 completion descriptors generated by the ENA, with a single
293 completion descriptor per completed packet.
295 * req_id is retrieved from the completion descriptor. The tx_info of
296 the packet is retrieved via the req_id. The data buffers are
297 unmapped and req_id is returned to the empty req_id ring.
298 * The function stops when the completion descriptors are completed or
299 the budget is reached.
304 - When a packet is received from the ENA device.
305 - The interrupt handler schedules NAPI.
306 - The ena_clean_rx_irq() function is called. This function calls
307 ena_rx_pkt(), an ENA communication layer function, which returns the
308 number of descriptors used for a new unhandled packet, and zero if
309 no new packet is found.
310 - Then it calls the ena_clean_rx_irq() function.
311 - ena_eth_rx_skb() checks packet length:
313 * If the packet is small (len < rx_copybreak), the driver allocates
314 a SKB for the new packet, and copies the packet payload into the
317 - In this way the original data buffer is not passed to the stack
318 and is reused for future Rx packets.
320 * Otherwise the function unmaps the Rx buffer, then allocates the
321 new SKB structure and hooks the Rx buffer to the SKB frags.
323 - The new SKB is updated with the necessary information (protocol,
324 checksum hw verify result, etc.), and then passed to the network
325 stack, using the NAPI interface function napi_gro_receive().