| blob | 4202d1bc583c57fc6ca98271688c414b743896f8 |
1 Introduction
2 ============
4 The IBM Power architecture provides support for CAPI (Coherent
5 Accelerator Power Interface), which is available to certain PCIe slots
6 on Power 8 systems. CAPI can be thought of as a special tunneling
7 protocol through PCIe that allow PCIe adapters to look like special
8 purpose co-processors which can read or write an application's
9 memory and generate page faults. As a result, the host interface to
10 an adapter running in CAPI mode does not require the data buffers to
11 be mapped to the device's memory (IOMMU bypass) nor does it require
12 memory to be pinned.
14 On Linux, Coherent Accelerator (CXL) kernel services present CAPI
15 devices as a PCI device by implementing a virtual PCI host bridge.
16 This abstraction simplifies the infrastructure and programming
17 model, allowing for drivers to look similar to other native PCI
18 device drivers.
20 CXL provides a mechanism by which user space applications can
21 directly talk to a device (network or storage) bypassing the typical
22 kernel/device driver stack. The CXL Flash Adapter Driver enables a
23 user space application direct access to Flash storage.
25 The CXL Flash Adapter Driver is a kernel module that sits in the
26 SCSI stack as a low level device driver (below the SCSI disk and
27 protocol drivers) for the IBM CXL Flash Adapter. This driver is
28 responsible for the initialization of the adapter, setting up the
29 special path for user space access, and performing error recovery. It
30 communicates directly the Flash Accelerator Functional Unit (AFU)
31 as described in Documentation/powerpc/cxl.txt.
33 The cxlflash driver supports two, mutually exclusive, modes of
34 operation at the device (LUN) level:
36 - Any flash device (LUN) can be configured to be accessed as a
37 regular disk device (i.e.: /dev/sdc). This is the default mode.
39 - Any flash device (LUN) can be configured to be accessed from
40 user space with a special block library. This mode further
41 specifies the means of accessing the device and provides for
42 either raw access to the entire LUN (referred to as direct
43 or physical LUN access) or access to a kernel/AFU-mediated
44 partition of the LUN (referred to as virtual LUN access). The
45 segmentation of a disk device into virtual LUNs is assisted
46 by special translation services provided by the Flash AFU.
48 Overview
49 ========
51 The Coherent Accelerator Interface Architecture (CAIA) introduces a
52 concept of a master context. A master typically has special privileges
53 granted to it by the kernel or hypervisor allowing it to perform AFU
54 wide management and control. The master may or may not be involved
55 directly in each user I/O, but at the minimum is involved in the
56 initial setup before the user application is allowed to send requests
57 directly to the AFU.
59 The CXL Flash Adapter Driver establishes a master context with the
60 AFU. It uses memory mapped I/O (MMIO) for this control and setup. The
61 Adapter Problem Space Memory Map looks like this:
63 +-------------------------------+
64 | 512 * 64 KB User MMIO |
65 | (per context) |
66 | User Accessible |
67 +-------------------------------+
68 | 512 * 128 B per context |
69 | Provisioning and Control |
70 | Trusted Process accessible |
71 +-------------------------------+
72 | 64 KB Global |
73 | Trusted Process accessible |
74 +-------------------------------+
76 This driver configures itself into the SCSI software stack as an
77 adapter driver. The driver is the only entity that is considered a
78 Trusted Process to program the Provisioning and Control and Global
79 areas in the MMIO Space shown above. The master context driver
80 discovers all LUNs attached to the CXL Flash adapter and instantiates
81 scsi block devices (/dev/sdb, /dev/sdc etc.) for each unique LUN
82 seen from each path.
84 Once these scsi block devices are instantiated, an application
85 written to a specification provided by the block library may get
86 access to the Flash from user space (without requiring a system call).
88 This master context driver also provides a series of ioctls for this
89 block library to enable this user space access. The driver supports
90 two modes for accessing the block device.
92 The first mode is called a virtual mode. In this mode a single scsi
93 block device (/dev/sdb) may be carved up into any number of distinct
94 virtual LUNs. The virtual LUNs may be resized as long as the sum of
95 the sizes of all the virtual LUNs, along with the meta-data associated
96 with it does not exceed the physical capacity.
98 The second mode is called the physical mode. In this mode a single
99 block device (/dev/sdb) may be opened directly by the block library
100 and the entire space for the LUN is available to the application.
102 Only the physical mode provides persistence of the data. i.e. The
103 data written to the block device will survive application exit and
104 restart and also reboot. The virtual LUNs do not persist (i.e. do
105 not survive after the application terminates or the system reboots).
108 Block library API
109 =================
111 Applications intending to get access to the CXL Flash from user
112 space should use the block library, as it abstracts the details of
113 interfacing directly with the cxlflash driver that are necessary for
114 performing administrative actions (i.e.: setup, tear down, resize).
115 The block library can be thought of as a 'user' of services,
116 implemented as IOCTLs, that are provided by the cxlflash driver
117 specifically for devices (LUNs) operating in user space access
118 mode. While it is not a requirement that applications understand
119 the interface between the block library and the cxlflash driver,
120 a high-level overview of each supported service (IOCTL) is provided
121 below.
123 The block library can be found on GitHub:
124 http://www.github.com/mikehollinger/ibmcapikv
127 CXL Flash Driver IOCTLs
128 =======================
130 Users, such as the block library, that wish to interface with a flash
131 device (LUN) via user space access need to use the services provided
132 by the cxlflash driver. As these services are implemented as ioctls,
133 a file descriptor handle must first be obtained in order to establish
134 the communication channel between a user and the kernel. This file
135 descriptor is obtained by opening the device special file associated
136 with the scsi disk device (/dev/sdb) that was created during LUN
137 discovery. As per the location of the cxlflash driver within the
138 SCSI protocol stack, this open is actually not seen by the cxlflash
139 driver. Upon successful open, the user receives a file descriptor
140 (herein referred to as fd1) that should be used for issuing the
141 subsequent ioctls listed below.
143 The structure definitions for these IOCTLs are available in:
144 uapi/scsi/cxlflash_ioctl.h
146 DK_CXLFLASH_ATTACH
147 ------------------
149 This ioctl obtains, initializes, and starts a context using the CXL
150 kernel services. These services specify a context id (u16) by which
151 to uniquely identify the context and its allocated resources. The
152 services additionally provide a second file descriptor (herein
153 referred to as fd2) that is used by the block library to initiate
154 memory mapped I/O (via mmap()) to the CXL flash device and poll for
155 completion events. This file descriptor is intentionally installed by
156 this driver and not the CXL kernel services to allow for intermediary
157 notification and access in the event of a non-user-initiated close(),
158 such as a killed process. This design point is described in further
159 detail in the description for the DK_CXLFLASH_DETACH ioctl.
161 There are a few important aspects regarding the "tokens" (context id
162 and fd2) that are provided back to the user:
164 - These tokens are only valid for the process under which they
165 were created. The child of a forked process cannot continue
166 to use the context id or file descriptor created by its parent
167 (see DK_CXLFLASH_VLUN_CLONE for further details).
169 - These tokens are only valid for the lifetime of the context and
170 the process under which they were created. Once either is
171 destroyed, the tokens are to be considered stale and subsequent
172 usage will result in errors.
174 - When a context is no longer needed, the user shall detach from
175 the context via the DK_CXLFLASH_DETACH ioctl.
177 - A close on fd2 will invalidate the tokens. This operation is not
178 required by the user.
180 DK_CXLFLASH_USER_DIRECT
181 -----------------------
182 This ioctl is responsible for transitioning the LUN to direct
183 (physical) mode access and configuring the AFU for direct access from
184 user space on a per-context basis. Additionally, the block size and
185 last logical block address (LBA) are returned to the user.
187 As mentioned previously, when operating in user space access mode,
188 LUNs may be accessed in whole or in part. Only one mode is allowed
189 at a time and if one mode is active (outstanding references exist),
190 requests to use the LUN in a different mode are denied.
192 The AFU is configured for direct access from user space by adding an
193 entry to the AFU's resource handle table. The index of the entry is
194 treated as a resource handle that is returned to the user. The user
195 is then able to use the handle to reference the LUN during I/O.
197 DK_CXLFLASH_USER_VIRTUAL
198 ------------------------
199 This ioctl is responsible for transitioning the LUN to virtual mode
200 of access and configuring the AFU for virtual access from user space
201 on a per-context basis. Additionally, the block size and last logical
202 block address (LBA) are returned to the user.
204 As mentioned previously, when operating in user space access mode,
205 LUNs may be accessed in whole or in part. Only one mode is allowed
206 at a time and if one mode is active (outstanding references exist),
207 requests to use the LUN in a different mode are denied.
209 The AFU is configured for virtual access from user space by adding
210 an entry to the AFU's resource handle table. The index of the entry
211 is treated as a resource handle that is returned to the user. The
212 user is then able to use the handle to reference the LUN during I/O.
214 By default, the virtual LUN is created with a size of 0. The user
215 would need to use the DK_CXLFLASH_VLUN_RESIZE ioctl to adjust the grow
216 the virtual LUN to a desired size. To avoid having to perform this
217 resize for the initial creation of the virtual LUN, the user has the
218 option of specifying a size as part of the DK_CXLFLASH_USER_VIRTUAL
219 ioctl, such that when success is returned to the user, the
220 resource handle that is provided is already referencing provisioned
221 storage. This is reflected by the last LBA being a non-zero value.
223 DK_CXLFLASH_VLUN_RESIZE
224 -----------------------
225 This ioctl is responsible for resizing a previously created virtual
226 LUN and will fail if invoked upon a LUN that is not in virtual
227 mode. Upon success, an updated last LBA is returned to the user
228 indicating the new size of the virtual LUN associated with the
229 resource handle.
231 The partitioning of virtual LUNs is jointly mediated by the cxlflash
232 driver and the AFU. An allocation table is kept for each LUN that is
233 operating in the virtual mode and used to program a LUN translation
234 table that the AFU references when provided with a resource handle.
236 DK_CXLFLASH_RELEASE
237 -------------------
238 This ioctl is responsible for releasing a previously obtained
239 reference to either a physical or virtual LUN. This can be
240 thought of as the inverse of the DK_CXLFLASH_USER_DIRECT or
241 DK_CXLFLASH_USER_VIRTUAL ioctls. Upon success, the resource handle
242 is no longer valid and the entry in the resource handle table is
243 made available to be used again.
245 As part of the release process for virtual LUNs, the virtual LUN
246 is first resized to 0 to clear out and free the translation tables
247 associated with the virtual LUN reference.
249 DK_CXLFLASH_DETACH
250 ------------------
251 This ioctl is responsible for unregistering a context with the
252 cxlflash driver and release outstanding resources that were
253 not explicitly released via the DK_CXLFLASH_RELEASE ioctl. Upon
254 success, all "tokens" which had been provided to the user from the
255 DK_CXLFLASH_ATTACH onward are no longer valid.
257 DK_CXLFLASH_VLUN_CLONE
258 ----------------------
259 This ioctl is responsible for cloning a previously created
260 context to a more recently created context. It exists solely to
261 support maintaining user space access to storage after a process
262 forks. Upon success, the child process (which invoked the ioctl)
263 will have access to the same LUNs via the same resource handle(s)
264 and fd2 as the parent, but under a different context.
266 Context sharing across processes is not supported with CXL and
267 therefore each fork must be met with establishing a new context
268 for the child process. This ioctl simplifies the state management
269 and playback required by a user in such a scenario. When a process
270 forks, child process can clone the parents context by first creating
271 a context (via DK_CXLFLASH_ATTACH) and then using this ioctl to
272 perform the clone from the parent to the child.
274 The clone itself is fairly simple. The resource handle and lun
275 translation tables are copied from the parent context to the child's
276 and then synced with the AFU.
278 DK_CXLFLASH_VERIFY
279 ------------------
280 This ioctl is used to detect various changes such as the capacity of
281 the disk changing, the number of LUNs visible changing, etc. In cases
282 where the changes affect the application (such as a LUN resize), the
283 cxlflash driver will report the changed state to the application.
285 The user calls in when they want to validate that a LUN hasn't been
286 changed in response to a check condition. As the user is operating out
287 of band from the kernel, they will see these types of events without
288 the kernel's knowledge. When encountered, the user's architected
289 behavior is to call in to this ioctl, indicating what they want to
290 verify and passing along any appropriate information. For now, only
291 verifying a LUN change (ie: size different) with sense data is
292 supported.
294 DK_CXLFLASH_RECOVER_AFU
295 -----------------------
296 This ioctl is used to drive recovery (if such an action is warranted)
297 of a specified user context. Any state associated with the user context
298 is re-established upon successful recovery.
300 User contexts are put into an error condition when the device needs to
301 be reset or is terminating. Users are notified of this error condition
302 by seeing all 0xF's on an MMIO read. Upon encountering this, the
303 architected behavior for a user is to call into this ioctl to recover
304 their context. A user may also call into this ioctl at any time to
305 check if the device is operating normally. If a failure is returned
306 from this ioctl, the user is expected to gracefully clean up their
307 context via release/detach ioctls. Until they do, the context they
308 hold is not relinquished. The user may also optionally exit the process
309 at which time the context/resources they held will be freed as part of
310 the release fop.
312 DK_CXLFLASH_MANAGE_LUN
313 ----------------------
314 This ioctl is used to switch a LUN from a mode where it is available
315 for file-system access (legacy), to a mode where it is set aside for
316 exclusive user space access (superpipe). In case a LUN is visible
317 across multiple ports and adapters, this ioctl is used to uniquely
318 identify each LUN by its World Wide Node Name (WWNN).