www.ti.com
2.3.10.3
Software Shutdown Details
2.3.11
Emulation
SRIO Functional Description
Power consumption is minimized for all logical blocks that are in shutdown. In addition to simply asserting
the appropriate reset signal to each logical block within the peripheral, clocks are gated off to the
corresponding logical block as well. Clocks are allowed to run for 32 clock cycles, which is necessary to
fully reset each logical block. When the appropriate logical block is fully reset, the clock input to that
subblock is gated off. When software asserts GBL_EN/BLKn_EN to release the logical block from reset,
the clocks are un-gated and the GBL_EN_STAT/BLKn_EN_STAT bit(s) indicate a value of 1b.
Note:
The BLK_EN bits allow you to shut down and gate clocks to unused portions of the logic,
while other parts of the peripheral continue to operate. When shutting down an individual
block, if TXU and RXU queues are not torn down correctly, the DMA bus could hang. For
example, setting BLK3_EN = 0 (disabling the TXU) before a teardown of the queue could
cause any outstanding DMA request returned to the peripheral for the TXU to hang the
bus.
When using the GBL_EN to shutdown/reset the entire peripheral, it is important to first stop all
master-initiated commands on the DMA bus interface. For example, if the GBL_EN is asserted in the
middle of a DMA transfer from the peripheral, this could hang the bus. The procedure to follow is:
1. Stop all RapidIO source transactions, including LSU and TXU operations. The four LSU blocks should
indiciate a BSY status of 0b (offsets 0418h, 0438h, 0458h, 0478h). If an EDMA channel is used for
driving the LSU, it must be stopped to prevent new/additional transfers. This procedure is outside the
scope of this specification. Teardown of the TXU queues is accomplished by writing 0000FFFFh to
RIO_TX_QUEUE_TEAR_DOWN (offset 0700h). Hardware will then tear down the queues and clear
these bits automatically when the teardown is complete.
2. Stop all RapidIO message receive, RXU, operations. Teardown of the RXU queues is accomplished by
writing 0000FFFFh to RIO_RX_QUEUE_TEAR_DOWN (offset 0740h). Hardware will then tear down
the queues and clear these bits automatically when complete.
3. Once teardown is complete, clear the PEREN bit of the RIO_PCR (offset 0004h) to stop all new logical
layer transactions.
4. Wait 1 second to finish any current DMA transfer.
5. Deassert GBL_EN (offset 0030h).
Expected behavior during emulation halt is controlled within the peripheral by the SOFT and FREE bits of
the peripheral control register (PCR). These bits are shown in
Figure 40
and described in
Table 29
.
Figure 40. Peripheral Control Register (PCR) - Address Offset 0004h
31
16
Reserved
R-0
15
3
2
1
0
Reserved
PEREN
SOFT
FREE
R-0
R/W-0
R/W-0
R/W-1
LEGEND: R/W = Read/Write; R = Read only; -n = Value after reset
Table 29. Peripheral Control Register (PCR) Field Descriptions
Bit
Field
Value
Description
31–3
Reserved
0
These read-only bits return 0s when read.
2
PEREN
Peripheral enable. Controls the flow of data in the logical layer of the peripheral. As an initiator, it
will prevent TX transaction generation; as a target, it will disable incoming requests. This should be
the last enable bit to toggle when bringing the device out of reset to begin normal operation.
0
Data flow control is disabled.
1
Data flow control is enabled.
74
Serial RapidIO (SRIO)
SPRUE13A – September 2006
Submit Documentation Feedback
