User manual

Table Of Contents
Zynq-7000 AP SoC Technical Reference Manual www.xilinx.com 88
UG585 (v1.11) September 27, 2016
Chapter 3: Application Processing Unit
°
The execution of a DSB instruction to ensure the completion of the TLB operation.
°
A subsequent ISB instruction, or taking an exception, or returning from an exception.
The execution of an instruction or unified TLB maintenance operation is only guaranteed to be
visible to subsequent instruction fetch after both:
°
The execution of a DSB instruction to ensure the completion of the TLB operation.
°
A subsequent ISB instruction, or taking an exception, or returning from an exception.
The following rules apply when writing translation table entries. They ensure that the updated entries
are visible to subsequent accesses and cache maintenance operations.
A write to the translation tables, after it has been cleaned from the cache if appropriate, is only
guaranteed to be seen by a translation table walk caused by an explicit load or store after the
execution of both a DSB and an ISB. However, it is guaranteed that any writes to the translation
tables are not seen by any explicit memory access that occurs in program order before the write
to the translation tables.
If the translation tables are held in write-back cacheable memory, the caches must be cleaned to
the point of unification after writing to the translation tables and before the DSB instruction.
This ensures that the updated translation table is visible to a hardware translation table walk.
A write to the translation tables, after it has been cleaned from the cache if appropriate, is only
guaranteed to be seen by a translation table walk caused by the instruction fetch of an
instruction that follows the write to the translation tables after both a DSB and an ISB.
TLB Lockdown
The TLB supports the TLB lock-by-entry model as described in the ARM Architecture Reference
Manual. See the TLB Lockdown register description in the ARM Cortex-A9 Technical Reference
Manual.
3.2.6 Interfaces
AXI and Coherency Interfaces
Each Cortex-A9 processor provides two 64-bit pseudo AXI master interfaces for independent
instruction fetch and data transactions. These interfaces operate at the speed of the processor cores
(CPU_6x4x clock) and are capable of sustaining four double-word writes every five processor cycles
when copying data across a cached region of memory. The instruction side interface is a read-only
interface and does not have the write channel. These interfaces implement an extended version of
the AXI protocol that also provides multiple optimizations to the L2 cache including support for L2
pre-fetch hints and speculative memory accesses. These optimizations are explained in more detail
in the L2-Cache section of this chapter.
The AXI transactions are all routed through the SCU to the OCM or the L2 cache controller based on
their addresses. Each Cortex-A9 also provides a cache coherency bus (CCB) to the SCU to provide the
information required for coherency management between the L1 and L2 caches.