![Freescale Semiconductor MCF54455 Скачать руководство пользователя страница 563](http://html1.mh-extra.com/html/freescale-semiconductor/mcf54455/mcf54455_reference-manual_2330541563.webp)
PCI Bus Controller
22-46
Freescale Semiconductor
22.4.4.4
Target Abort
A target abort occurs if PCI address falls within a base address window (BAR0–5) whose corresponding
PCIBTAR
n
Section 22.3.2.10, “Target Base Address Translation Register n
Target aborts also issue on the PCI bus when a delayed read results in an error in the
internal system.
22.4.4.5
Latency Rule Disable
The latency rule disable bit in the interface control register, PCITCR1[LD], (see
”) prevents the PCI controller from automatically disconnecting a target
transaction due to the PCI 16/8 clock rule. With this bit set, it is possible to hang the PCI bus if the internal
bus does not complete the data transfer.
22.4.5
PCI Arbiter
Out of reset, the PCI arbiter is disabled. If the application wants to enable the use of the internal PCI arbiter,
initialization software must clear the PACR[DS] bit before PCI bus operation begins. The following
sections detail the PCI arbiter functionality if enabled.
22.4.5.1
External PCI Requests
An external PCI master may target this device or external slaves. The request/grant handshake always
precedes any PCI bus operation. The PCI arbiter must service access requests for an external
master-to-external target transactions as well as external master-to-PCI controller transactions.
22.4.5.2
Hidden Bus Arbitration
PCI bus arbitration can take place while the currently granted device performs a bus transaction if another
master requests access to the bus. As long as the bus is active, the arbiter can deassert PCI_GNT to one
master and assert PCI_GNT to the next in the same cycle and no PCI bus cycles are consumed due to
arbitration. The newly granted device must wait until the current master relinquishes the bus before
initiating a transaction.
22.4.5.3
Arbitration Scheme
The PCI bus arbiter logic provides a programmable two-level least recently used (LRU) priority algorithm.
Two groups of masters are assigned, a high-priority group and a low-priority group. The low-priority group
as a whole represents one entry in the high-priority group. If the high-priority group consists of
n
masters
in at least every
n
+1 transactions, the highest priority is assigned to the low-priority group. Low-priority
masters have equal access to the bus with respect to other low-priority masters. If there are masters
programmed into both groups, masters in the high-priority group can be serviced
n
transactions out of
n
+1
while one master in the low-priority group is serviced once every
n
+1 transactions. If all masters are
programmed to the same group and only one master is assigned to the low-priority group, no priority
distinction among masters exists.
Содержание MCF54455
Страница 33: ...xxviii Freescale Semiconductor ...
Страница 67: ...Freescale Semiconductor 1 ...
Страница 125: ...Freescale Semiconductor 1 ...
Страница 145: ...Enhanced Multiply Accumulate Unit EMAC 5 21 Freescale Semiconductor ...
Страница 173: ...Cache 6 28 Freescale Semiconductor ...
Страница 179: ...Static RAM SRAM 7 6 Freescale Semiconductor ...
Страница 207: ...Power Management 9 16 Freescale Semiconductor ...
Страница 323: ...Reset Controller Module 13 8 Freescale Semiconductor ...
Страница 389: ...Pin Multiplexing and Control 16 44 Freescale Semiconductor ...
Страница 575: ...PCI Bus Controller 22 58 Freescale Semiconductor ...
Страница 600: ...Advanced Technology Attachment ATA Freescale Semiconductor 23 25 ...
Страница 601: ...Freescale Semiconductor 1 ...
Страница 842: ...I2 C Interface Freescale Semiconductor 33 16 ...
Страница 843: ...Freescale Semiconductor 1 ...
Страница 921: ...Revision History A 6 Freescale Semiconductor ...