xref: /freebsd/sys/dev/cxgbe/firmware/t5fw_cfg_fpga.txt (revision 5ca8e32633c4ffbbcd6762e5888b6a4ba0708c6c)
1# Chelsio T5 Factory Default configuration file.
2#
3# Copyright (C) 2010-2013 Chelsio Communications.  All rights reserved.
4#
5#   DO NOT MODIFY THIS FILE UNDER ANY CIRCUMSTANCES.  MODIFICATION OF
6#   THIS FILE WILL RESULT IN A NON-FUNCTIONAL T4 ADAPTER AND MAY RESULT
7#   IN PHYSICAL DAMAGE TO T4 ADAPTERS.
8
9# This file provides the default, power-on configuration for 4-port T4-based
10# adapters shipped from the factory.  These defaults are designed to address
11# the needs of the vast majority of T4 customers.  The basic idea is to have
12# a default configuration which allows a customer to plug a T4 adapter in and
13# have it work regardless of OS, driver or application except in the most
14# unusual and/or demanding customer applications.
15#
16# Many of the T4 resources which are described by this configuration are
17# finite.  This requires balancing the configuration/operation needs of
18# device drivers across OSes and a large number of customer application.
19#
20# Some of the more important resources to allocate and their constaints are:
21#  1. Virtual Interfaces: 128.
22#  2. Ingress Queues with Free Lists: 1024.  PCI-E SR-IOV Virtual Functions
23#     must use a power of 2 Ingress Queues.
24#  3. Egress Queues: 128K.  PCI-E SR-IOV Virtual Functions must use a
25#     power of 2 Egress Queues.
26#  4. MSI-X Vectors: 1088.  A complication here is that the PCI-E SR-IOV
27#     Virtual Functions based off of a Physical Function all get the
28#     same umber of MSI-X Vectors as the base Physical Function.
29#     Additionally, regardless of whether Virtual Functions are enabled or
30#     not, their MSI-X "needs" are counted by the PCI-E implementation.
31#     And finally, all Physical Funcations capable of supporting Virtual
32#     Functions (PF0-3) must have the same number of configured TotalVFs in
33#     their SR-IOV Capabilities.
34#  5. Multi-Port Support (MPS) TCAM: 336 entries to support MAC destination
35#     address matching on Ingress Packets.
36#
37# Some of the important OS/Driver resource needs are:
38#  6. Some OS Drivers will manage all resources through a single Physical
39#     Function (currently PF0 but it could be any Physical Function).  Thus,
40#     this "Unified PF"  will need to have enough resources allocated to it
41#     to allow for this.  And because of the MSI-X resource allocation
42#     constraints mentioned above, this probably means we'll either have to
43#     severely limit the TotalVFs if we continue to use PF0 as the Unified PF
44#     or we'll need to move the Unified PF into the PF4-7 range since those
45#     Physical Functions don't have any Virtual Functions associated with
46#     them.
47#  7. Some OS Drivers will manage different ports and functions (NIC,
48#     storage, etc.) on different Physical Functions.  For example, NIC
49#     functions for ports 0-3 on PF0-3, FCoE on PF4, iSCSI on PF5, etc.
50#
51# Some of the customer application needs which need to be accommodated:
52#  8. Some customers will want to support large CPU count systems with
53#     good scaling.  Thus, we'll need to accommodate a number of
54#     Ingress Queues and MSI-X Vectors to allow up to some number of CPUs
55#     to be involved per port and per application function.  For example,
56#     in the case where all ports and application functions will be
57#     managed via a single Unified PF and we want to accommodate scaling up
58#     to 8 CPUs, we would want:
59#
60#         4 ports *
61#         3 application functions (NIC, FCoE, iSCSI) per port *
62#         8 Ingress Queue/MSI-X Vectors per application function
63#
64#     for a total of 96 Ingress Queues and MSI-X Vectors on the Unified PF.
65#     (Plus a few for Firmware Event Queues, etc.)
66#
67#  9. Some customers will want to use T4's PCI-E SR-IOV Capability to allow
68#     Virtual Machines to directly access T4 functionality via SR-IOV
69#     Virtual Functions and "PCI Device Passthrough" -- this is especially
70#     true for the NIC application functionality.  (Note that there is
71#     currently no ability to use the TOE, FCoE, iSCSI, etc. via Virtual
72#     Functions so this is in fact solely limited to NIC.)
73#
74
75
76# Global configuration settings.
77#
78[global]
79	rss_glb_config_mode = basicvirtual
80	rss_glb_config_options = tnlmapen,hashtoeplitz,tnlalllkp
81
82	# PCIE_MA_RSP register
83	pcie_ma_rsp_timervalue = 500	# the timer value in units of us
84	reg[0x59c4] = 0x3/0x3		# enable the timers
85
86	# PL_TIMEOUT register
87	pl_timeout_value = 200		# the timeout value in units of us
88
89	# The following Scatter Gather Engine (SGE) settings assume a 4KB Host
90	# Page Size and a 64B L1 Cache Line Size. It programs the
91	# EgrStatusPageSize and IngPadBoundary to 64B and the PktShift to 2.
92	# If a Master PF Driver finds itself on a machine with different
93	# parameters, then the Master PF Driver is responsible for initializing
94	# these parameters to appropriate values.
95	#
96	# Notes:
97	#  1. The Free List Buffer Sizes below are raw and the firmware will
98	#     round them up to the Ingress Padding Boundary.
99	#  2. The SGE Timer Values below are expressed below in microseconds.
100	#     The firmware will convert these values to Core Clock Ticks when
101	#     it processes the configuration parameters.
102	#
103	reg[0x1008] = 0x40810/0x21c70	# SGE_CONTROL
104	reg[0x100c] = 0x22222222	# SGE_HOST_PAGE_SIZE
105	reg[0x10a0] = 0x01040810	# SGE_INGRESS_RX_THRESHOLD
106	reg[0x1044] = 4096		# SGE_FL_BUFFER_SIZE0
107	reg[0x1048] = 65536		# SGE_FL_BUFFER_SIZE1
108	reg[0x104c] = 1536		# SGE_FL_BUFFER_SIZE2
109	reg[0x1050] = 9024		# SGE_FL_BUFFER_SIZE3
110	reg[0x1054] = 9216		# SGE_FL_BUFFER_SIZE4
111	reg[0x1058] = 2048		# SGE_FL_BUFFER_SIZE5
112	reg[0x105c] = 128		# SGE_FL_BUFFER_SIZE6
113	reg[0x1060] = 8192		# SGE_FL_BUFFER_SIZE7
114	reg[0x1064] = 16384		# SGE_FL_BUFFER_SIZE8
115	reg[0x10a4] = 0xa000a000/0xf000f000 # SGE_DBFIFO_STATUS
116	reg[0x10a8] = 0x402000/0x402000	# SGE_DOORBELL_CONTROL
117
118	# SGE_THROTTLE_CONTROL
119	bar2throttlecount = 500		# bar2throttlecount in us
120
121	sge_timer_value = 5, 10, 20, 50, 100, 200 # SGE_TIMER_VALUE* in usecs
122
123
124	reg[0x1124] = 0x00000400/0x00000400 # SGE_CONTROL2, enable VFIFO; if
125					# SGE_VFIFO_SIZE is not set, then
126					# firmware will set it up in function
127					# of number of egress queues used
128
129	reg[0x1130] = 0x00d5ffeb	# SGE_DBP_FETCH_THRESHOLD, fetch
130					# threshold set to queue depth
131					# minus 128-entries for FL and HP
132					# queues, and 0xfff for LP which
133					# prompts the firmware to set it up
134					# in function of egress queues
135					# used
136
137	reg[0x113c] = 0x0002ffc0	# SGE_VFIFO_SIZE, set to 0x2ffc0 which
138					# prompts the firmware to set it up in
139					# function of number of egress queues
140					# used
141
142	reg[0x7dc0] = 0x062f8849	# TP_SHIFT_CNT
143
144	# Selection of tuples for LE filter lookup, fields (and widths which
145	# must sum to <= 36): { IP Fragment (1), MPS Match Type (3),
146	# IP Protocol (8), [Inner] VLAN (17), Port (3), FCoE (1) }
147	#
148	filterMode = fragmentation, mpshittype, protocol, vlan, port, fcoe, srvrsram
149
150	# Percentage of dynamic memory (in either the EDRAM or external MEM)
151	# to use for TP RX payload
152	tp_pmrx = 30, 512
153
154	# TP RX payload page size
155	tp_pmrx_pagesize = 64K
156
157	# TP number of RX channels
158	tp_nrxch = 0		# 0 (auto) = 1
159
160	# Percentage of dynamic memory (in either the EDRAM or external MEM)
161	# to use for TP TX payload
162	tp_pmtx = 50, 512
163
164	# TP TX payload page size
165	tp_pmtx_pagesize = 64K
166
167	# TP number of TX channels
168	tp_ntxch = 0		# 0 (auto) = equal number of ports
169
170	reg[0x19c04] = 0x00400000/0x00400000 # LE Server SRAM Enable
171
172# Some "definitions" to make the rest of this a bit more readable.  We support
173# 4 ports, 3 functions (NIC, FCoE and iSCSI), scaling up to 8 "CPU Queue Sets"
174# per function per port ...
175#
176# NMSIX = 1088			# available MSI-X Vectors
177# NVI = 128			# available Virtual Interfaces
178# NMPSTCAM = 336		# MPS TCAM entries
179#
180# NPORTS = 4			# ports
181# NCPUS = 8			# CPUs we want to support scalably
182# NFUNCS = 3			# functions per port (NIC, FCoE, iSCSI)
183
184# Breakdown of Virtual Interface/Queue/Interrupt resources for the "Unified
185# PF" which many OS Drivers will use to manage most or all functions.
186#
187# Each Ingress Queue can use one MSI-X interrupt but some Ingress Queues can
188# use Forwarded Interrupt Ingress Queues.  For these latter, an Ingress Queue
189# would be created and the Queue ID of a Forwarded Interrupt Ingress Queue
190# will be specified as the "Ingress Queue Asynchronous Destination Index."
191# Thus, the number of MSI-X Vectors assigned to the Unified PF will be less
192# than or equal to the number of Ingress Queues ...
193#
194# NVI_NIC = 4			# NIC access to NPORTS
195# NFLIQ_NIC = 32		# NIC Ingress Queues with Free Lists
196# NETHCTRL_NIC = 32		# NIC Ethernet Control/TX Queues
197# NEQ_NIC = 64			# NIC Egress Queues (FL, ETHCTRL/TX)
198# NMPSTCAM_NIC = 16		# NIC MPS TCAM Entries (NPORTS*4)
199# NMSIX_NIC = 32		# NIC MSI-X Interrupt Vectors (FLIQ)
200#
201# NVI_OFLD = 0			# Offload uses NIC function to access ports
202# NFLIQ_OFLD = 16		# Offload Ingress Queues with Free Lists
203# NETHCTRL_OFLD = 0		# Offload Ethernet Control/TX Queues
204# NEQ_OFLD = 16			# Offload Egress Queues (FL)
205# NMPSTCAM_OFLD = 0		# Offload MPS TCAM Entries (uses NIC's)
206# NMSIX_OFLD = 16		# Offload MSI-X Interrupt Vectors (FLIQ)
207#
208# NVI_RDMA = 0			# RDMA uses NIC function to access ports
209# NFLIQ_RDMA = 4		# RDMA Ingress Queues with Free Lists
210# NETHCTRL_RDMA = 0		# RDMA Ethernet Control/TX Queues
211# NEQ_RDMA = 4			# RDMA Egress Queues (FL)
212# NMPSTCAM_RDMA = 0		# RDMA MPS TCAM Entries (uses NIC's)
213# NMSIX_RDMA = 4		# RDMA MSI-X Interrupt Vectors (FLIQ)
214#
215# NEQ_WD = 128			# Wire Direct TX Queues and FLs
216# NETHCTRL_WD = 64		# Wire Direct TX Queues
217# NFLIQ_WD = 64	`		# Wire Direct Ingress Queues with Free Lists
218#
219# NVI_ISCSI = 4			# ISCSI access to NPORTS
220# NFLIQ_ISCSI = 4		# ISCSI Ingress Queues with Free Lists
221# NETHCTRL_ISCSI = 0		# ISCSI Ethernet Control/TX Queues
222# NEQ_ISCSI = 4			# ISCSI Egress Queues (FL)
223# NMPSTCAM_ISCSI = 4		# ISCSI MPS TCAM Entries (NPORTS)
224# NMSIX_ISCSI = 4		# ISCSI MSI-X Interrupt Vectors (FLIQ)
225#
226# NVI_FCOE = 4			# FCOE access to NPORTS
227# NFLIQ_FCOE = 34		# FCOE Ingress Queues with Free Lists
228# NETHCTRL_FCOE = 32		# FCOE Ethernet Control/TX Queues
229# NEQ_FCOE = 66			# FCOE Egress Queues (FL)
230# NMPSTCAM_FCOE = 32 		# FCOE MPS TCAM Entries (NPORTS)
231# NMSIX_FCOE = 34		# FCOE MSI-X Interrupt Vectors (FLIQ)
232
233# Two extra Ingress Queues per function for Firmware Events and Forwarded
234# Interrupts, and two extra interrupts per function for Firmware Events (or a
235# Forwarded Interrupt Queue) and General Interrupts per function.
236#
237# NFLIQ_EXTRA = 6		# "extra" Ingress Queues 2*NFUNCS (Firmware and
238# 				#   Forwarded Interrupts
239# NMSIX_EXTRA = 6		# extra interrupts 2*NFUNCS (Firmware and
240# 				#   General Interrupts
241
242# Microsoft HyperV resources.  The HyperV Virtual Ingress Queues will have
243# their interrupts forwarded to another set of Forwarded Interrupt Queues.
244#
245# NVI_HYPERV = 16		# VMs we want to support
246# NVIIQ_HYPERV = 2		# Virtual Ingress Queues with Free Lists per VM
247# NFLIQ_HYPERV = 40		# VIQs + NCPUS Forwarded Interrupt Queues
248# NEQ_HYPERV = 32		# VIQs Free Lists
249# NMPSTCAM_HYPERV = 16		# MPS TCAM Entries (NVI_HYPERV)
250# NMSIX_HYPERV = 8		# NCPUS Forwarded Interrupt Queues
251
252# Adding all of the above Unified PF resource needs together: (NIC + OFLD +
253# RDMA + ISCSI + FCOE + EXTRA + HYPERV)
254#
255# NVI_UNIFIED = 28
256# NFLIQ_UNIFIED = 106
257# NETHCTRL_UNIFIED = 32
258# NEQ_UNIFIED = 124
259# NMPSTCAM_UNIFIED = 40
260#
261# The sum of all the MSI-X resources above is 74 MSI-X Vectors but we'll round
262# that up to 128 to make sure the Unified PF doesn't run out of resources.
263#
264# NMSIX_UNIFIED = 128
265#
266# The Storage PFs could need up to NPORTS*NCPUS + NMSIX_EXTRA MSI-X Vectors
267# which is 34 but they're probably safe with 32.
268#
269# NMSIX_STORAGE = 32
270
271# Note: The UnifiedPF is PF4 which doesn't have any Virtual Functions
272# associated with it.  Thus, the MSI-X Vector allocations we give to the
273# UnifiedPF aren't inherited by any Virtual Functions.  As a result we can
274# provision many more Virtual Functions than we can if the UnifiedPF were
275# one of PF0-3.
276#
277
278# All of the below PCI-E parameters are actually stored in various *_init.txt
279# files.  We include them below essentially as comments.
280#
281# For PF0-3 we assign 8 vectors each for NIC Ingress Queues of the associated
282# ports 0-3.
283#
284# For PF4, the Unified PF, we give it an MSI-X Table Size as outlined above.
285#
286# For PF5-6 we assign enough MSI-X Vectors to support FCoE and iSCSI
287# storage applications across all four possible ports.
288#
289# Additionally, since the UnifiedPF isn't one of the per-port Physical
290# Functions, we give the UnifiedPF and the PF0-3 Physical Functions
291# different PCI Device IDs which will allow Unified and Per-Port Drivers
292# to directly select the type of Physical Function to which they wish to be
293# attached.
294#
295# Note that the actual values used for the PCI-E Intelectual Property will be
296# 1 less than those below since that's the way it "counts" things.  For
297# readability, we use the number we actually mean ...
298#
299# PF0_INT = 8			# NCPUS
300# PF1_INT = 8			# NCPUS
301# PF2_INT = 8			# NCPUS
302# PF3_INT = 8			# NCPUS
303# PF0_3_INT = 32		# PF0_INT + PF1_INT + PF2_INT + PF3_INT
304#
305# PF4_INT = 128			# NMSIX_UNIFIED
306# PF5_INT = 32			# NMSIX_STORAGE
307# PF6_INT = 32			# NMSIX_STORAGE
308# PF7_INT = 0			# Nothing Assigned
309# PF4_7_INT = 192		# PF4_INT + PF5_INT + PF6_INT + PF7_INT
310#
311# PF0_7_INT = 224		# PF0_3_INT + PF4_7_INT
312#
313# With the above we can get 17 VFs/PF0-3 (limited by 336 MPS TCAM entries)
314# but we'll lower that to 16 to make our total 64 and a nice power of 2 ...
315#
316# NVF = 16
317
318# For those OSes which manage different ports on different PFs, we need
319# only enough resources to support a single port's NIC application functions
320# on PF0-3.  The below assumes that we're only doing NIC with NCPUS "Queue
321# Sets" for ports 0-3.  The FCoE and iSCSI functions for such OSes will be
322# managed on the "storage PFs" (see below).
323#
324
325# Some OS Drivers manage all application functions for all ports via PF4.
326# Thus we need to provide a large number of resources here.  For Egress
327# Queues we need to account for both TX Queues as well as Free List Queues
328# (because the host is responsible for producing Free List Buffers for the
329# hardware to consume).
330#
331[function "0"]
332	wx_caps = all		# write/execute permissions for all commands
333	r_caps = all		# read permissions for all commands
334	nvi = 28		# NVI_UNIFIED
335	niqflint = 170		# NFLIQ_UNIFIED + NLFIQ_WD
336	nethctrl = 96 		# NETHCTRL_UNIFIED + NETHCTRL_WD
337	neq = 252		# NEQ_UNIFIED + NEQ_WD
338	nexactf = 40		# NMPSTCAM_UNIFIED
339	cmask = all		# access to all channels
340	pmask = all		# access to all four ports ...
341	nroute = 32		# number of routing region entries
342	nclip = 32		# number of clip region entries
343	nfilter = 48		# number of filter region entries
344	nserver = 32		# number of server region entries
345	nhash = 2048		# number of hash region entries
346	protocol = nic_vm, ofld, rddp, rdmac, iscsi_initiator_pdu, iscsi_target_pdu
347	tp_l2t = 3072
348	tp_ddp = 2
349	tp_ddp_iscsi = 2
350	tp_stag = 2
351	tp_pbl = 5
352	tp_rq = 7
353
354# We have FCoE and iSCSI storage functions on PF5 and PF6 each of which may
355# need to have Virtual Interfaces on each of the four ports with up to NCPUS
356# "Queue Sets" each.
357#
358[function "1"]
359	wx_caps = all		# write/execute permissions for all commands
360	r_caps = all		# read permissions for all commands
361	nvi = 4			# NPORTS
362	niqflint = 34		# NPORTS*NCPUS + NMSIX_EXTRA
363	nethctrl = 32		# NPORTS*NCPUS
364	neq = 66		# NPORTS*NCPUS * 2 (FL, ETHCTRL/TX) + 2 (EXTRA)
365	nexactf = 32		# NPORTS + adding 28 exact entries for FCoE
366				# which is OK since < MIN(SUM PF0..3, PF4)
367				# and we never load PF0..3 and PF4 concurrently
368	cmask = all		# access to all channels
369	pmask = all		# access to all four ports ...
370	nhash = 2048
371	protocol = fcoe_initiator
372	tp_ddp = 2
373	fcoe_nfcf = 16
374	fcoe_nvnp = 32
375	fcoe_nssn = 1024
376
377# The following function, 1023, is not an actual PCIE function but is used to
378# configure and reserve firmware internal resources that come from the global
379# resource pool.
380#
381[function "1023"]
382	wx_caps = all		# write/execute permissions for all commands
383	r_caps = all		# read permissions for all commands
384	nvi = 4			# NVI_UNIFIED
385	cmask = all		# access to all channels
386	pmask = all		# access to all four ports ...
387	nexactf = 8		# NPORTS + DCBX +
388	nfilter = 16		# number of filter region entries
389
390# For Virtual functions, we only allow NIC functionality and we only allow
391# access to one port (1 << PF).  Note that because of limitations in the
392# Scatter Gather Engine (SGE) hardware which checks writes to VF KDOORBELL
393# and GTS registers, the number of Ingress and Egress Queues must be a power
394# of 2.
395#
396[function "0/*"]		# NVF
397	wx_caps = 0x82		# DMAQ | VF
398	r_caps = 0x86		# DMAQ | VF | PORT
399	nvi = 1			# 1 port
400	niqflint = 4		# 2 "Queue Sets" + NXIQ
401	nethctrl = 2		# 2 "Queue Sets"
402	neq = 4			# 2 "Queue Sets" * 2
403	nexactf = 4
404	cmask = all		# access to all channels
405	pmask = 0x1		# access to only one port ...
406
407[function "1/*"]		# NVF
408	wx_caps = 0x82		# DMAQ | VF
409	r_caps = 0x86		# DMAQ | VF | PORT
410	nvi = 1			# 1 port
411	niqflint = 4		# 2 "Queue Sets" + NXIQ
412	nethctrl = 2		# 2 "Queue Sets"
413	neq = 4			# 2 "Queue Sets" * 2
414	nexactf = 4
415	cmask = all		# access to all channels
416	pmask = 0x2		# access to only one port ...
417
418# MPS features a 196608 bytes ingress buffer that is used for ingress buffering
419# for packets from the wire as well as the loopback path of the L2 switch. The
420# folling params control how the buffer memory is distributed and the L2 flow
421# control settings:
422#
423# bg_mem:	%-age of mem to use for port/buffer group
424# lpbk_mem:	%-age of port/bg mem to use for loopback
425# hwm:		high watermark; bytes available when starting to send pause
426#		frames (in units of 0.1 MTU)
427# lwm:		low watermark; bytes remaining when sending 'unpause' frame
428#		(in inuits of 0.1 MTU)
429# dwm:		minimum delta between high and low watermark (in units of 100
430#		Bytes)
431#
432[port "0"]
433	dcb = ppp, dcbx		# configure for DCB PPP and enable DCBX offload
434	bg_mem = 25
435	lpbk_mem = 25
436	hwm = 30
437	lwm = 15
438	dwm = 30
439
440[port "1"]
441	dcb = ppp, dcbx
442	bg_mem = 25
443	lpbk_mem = 25
444	hwm = 30
445	lwm = 15
446	dwm = 30
447
448[port "2"]
449	dcb = ppp, dcbx
450	bg_mem = 25
451	lpbk_mem = 25
452	hwm = 30
453	lwm = 15
454	dwm = 30
455
456[port "3"]
457	dcb = ppp, dcbx
458	bg_mem = 25
459	lpbk_mem = 25
460	hwm = 30
461	lwm = 15
462	dwm = 30
463
464[fini]
465	version = 0x1425000d
466	checksum = 0x22f1530b
467
468# Total resources used by above allocations:
469#   Virtual Interfaces: 104
470#   Ingress Queues/w Free Lists and Interrupts: 526
471#   Egress Queues: 702
472#   MPS TCAM Entries: 336
473#   MSI-X Vectors: 736
474#   Virtual Functions: 64
475#
476#
477