Cyclone® V SX, ST and SE SoC Device Errata

Download PDF
ID 683618
Date 9/25/2015
Public
Document Table of Contents
Document Table of Contents x
1. Cyclone® V SX, ST and SE SoC Device Errata
1. Cyclone® V SX, ST and SE SoC Device Errata x
1.1. Intel® -Specific SoC Errata for Cyclone® V SX, ST, and SE SoC Devices 1.2. Arm* Cortex* -A9 MPCore* and L2 Cache Errata 1.3. Revision History for Cyclone® V SX, ST, and SE SoC Device Errata
1.1. Intel® -Specific SoC Errata for Cyclone® V SX, ST, and SE SoC Devices x
1.1.1. Hard Processor System (HPS) 1.1.2. FPGA
1.1.1. Hard Processor System (HPS) x
1.1.1.1. EMAC RMII PHY Interface is Only Supported Through the FPGA Fabric 1.1.1.2. Hard Processor System Level 2 Cache Error Correction Code 1.1.1.3. Hard Processor System PLL Lock Issue After Power-on Reset or Cold Reset 1.1.1.4. HPS TAP Controller Is Reset By Cold Reset 1.1.1.5. SPI Slave Output Signals Cannot Be Isolated When Routed to the HPS Pins
1.1.2. FPGA x
1.1.2.1. External Memory Interface (EMIF) Maximum Frequency Specification Updage 1.1.2.2. Fractional PLL Phase Alignment Error 1.1.2.3. Power Connection Recommendation for Cyclone® V SoC ES Devices 1.1.2.4. Configuration via Protocol (CvP) 1.1.2.5. Usermode High Icc 1.1.2.6. False Configuration Failure in Active Serial Multi-Device Configuration x1 Mode 1.1.2.7. JTAG Programming Operation Issue
1.2. Arm* Cortex* -A9 MPCore* and L2 Cache Errata x
1.2.1. Arm* Cortex* -A9 MPU 1.2.2. Arm* L2 Cache Controller 1.2.3. Arm* CoreSight PTM
1.2.1. Arm* Cortex* -A9 MPU x
1.2.1.1. 761319: Ordering of Read Accesses to the Same Memory Location Might Be Uncertain 1.2.1.2. 775420: Particular Data Cache Maintenance Operation Which Aborts Might Lead to Deadlock 1.2.1.3. 782772: Speculative Execution of LDREX or STREX Instruction After a Write to Strongly Ordered Memory Might Lead to Deadlock 1.2.1.4. 761320: Full Cache Line Writes to the Same Memory Region From Both Processors Might Cause Deadlock Description Impact Workaround Category 1.2.1.5. 845369: Under Very Rare Timing Circumstances Transition into Streaming Mode Might Create Data Corruption 1.2.1.6. 740657: Global Timer Can Send Two Interrupts for the Same Event 1.2.1.7. 751476: Missed Watchpoint on the Second Part of an Unaligned Access Crossing a Page Boundary 1.2.1.8. 754322: Faulty MMU Translations Following ASID Switch 1.2.1.9. 764369: Data or Unified Cache Line Maintenance by MVA Fails on Inner-Shareable Memory 1.2.1.10. 782773: Updating a Translation Entry to Move a Page Mapping Might Erroneously Cause an Unexpected Translation Fault 1.2.1.11. 794072: A Short Loop Including DMB Instruction Might Cause a Denial of Service When the Other Processor Executes a CP15 Broadcast Operation 1.2.1.12. 794073: Speculative Instruction Fetches with MMU Disabled Might Not Comply with Architectural Requirements 1.2.1.13. 794074: A Write Request to an Uncacheable, Shareable Normal Memory Region Might be Executed Twice, Possibly Causing a Software Synchronization Issue 1.2.1.14. 725631: ISB is Counted in Performance Monitor Events 0x0C and 0x0D 1.2.1.15. 729817: MainID Register Alias Addresses Are Not Mapped on Debug APB Interface 1.2.1.16. 729818: In Debug State, the Next Instruction is Stalled When the SDABORT Flag is Set Instead of Being Discarded 1.2.1.17. 751471: DBGPCSR Format Is Incorrect 1.2.1.18. 752519: An Imprecise Abort Might Be Reported Twice on Non-Cacheable Reads 1.2.1.19. 754323: Repeated Store in the Same Cache Line Might Delay the Visibility of the Store 1.2.1.20. 756421: Sticky Pipeline Advance Bit Cannot be Cleared from Debug APB Accesses 1.2.1.21. 757119: Some Unallocated Memory Hint Instructions Generate an UNDEFINED Exception Instead of Being Treated as a NOP 1.2.1.22. 761321: MRC and MCR Are Not Counted in Event 0x68 1.2.1.23. 764319: Read Accesses to DBGPRSR and DBGPRCR May Generate an Unexpected UNDEF 1.2.1.24. 771221: PLD Instructions Might Allocate Data in the Data Cache Regardless of the Cache Enable Bit Value 1.2.1.25. 771224: Visibility of Debug Enable Access Rights to Enable/Disable Tracking is Not Ensured by an ISB 1.2.1.26. 771225: Speculative Cacheable Reads to Aborting Memory Regions Clear the Internal Exclusive Monitor and May Lead to Livelock 1.2.1.27. 775419: PMU Event 0x0A Might Count Twice the LDM PC ^ Instruction with Base Address Register Write-Back 1.2.1.28. 782774: A Spurious Event 0x63 Can be Reported on an LDREX That is preceded by a Write to Strongly Ordered Memory Region
1.2.2. Arm* L2 Cache Controller x
1.2.2.1. 754670: A Continuous Write Flow Can Stall a Read Targeting the Same Memory Area 1.2.2.2. 765569: Prefetcher Can Cross 4 KB Boundary if Offset is Programmed with Value 23 1.2.2.3. 729815: The High Priority for SO and Dev Reads Feature Can Cause Quality of Service Issues to Cacheable Read Transactions
1.2.3. Arm* CoreSight PTM x
1.2.3.1. 720107: Periodic Synchronization Can Be Delayed and Cause Overflow 1.2.3.2. 711668: Configuration Extension Register Has Wrong Value Status
1. Cyclone® V SX, ST and SE SoC Device Errata

1.2.1.4. 761320: Full Cache Line Writes to the Same Memory Region From Both Processors Might Cause Deadlock

Description

Under very rare circumstances, full cache line writes from the two processors on cache lines in hazard with other request may cause arbitration issues in the SCU, leading to processor deadlock.

This erratum only affects dual-core devices. To trigger this erratum, the two processors must be performing full cache line writes to cache lines which are in coherent memory regions and are in hazard with other access requests in the Snoop Control Unit (SCU). The hazard in the SCU happens when the Accelerator Coherency Port (ACP) is performing a read or a write of the same cache line.

Under certain rare timing circumstances, the requests might create a loop of dependencies causing a processor deadlock.

Impact

This erratum can cause system deadlock. It is important to note that any scenario leading to this deadlock situation is uncommon. It requires both processors writing full cache lines to a coherent memory region, without taking any semaphore, with the ACP assessing the same lines at the same time, meaning that these latter accesses are not deterministic. This condition, combined with the extremely rare microarchitectural timing conditions under which the defect can happen, explains why this erratum is not expected to cause any significant malfunction in real systems.

Workaround

This erratum can be worked around by setting bit[21] of the undocumented Diagnostic Control Register to 1. This register is encoded as CP15 c15 0 c0 1.

This bit can be written in secure state only, with the following read/modify/write code sequence: 
MCR p15, 0, rt, c15, c0, 1
ORR rt, rt #0x200000
MCR p15, 0, rt, c15, c0, 1
When this bit is set, the "direct eviction" optimization in the bus interface unit is disabled, which means this erratum cannot occur.

Setting this bit might prevent the Cortex-A9 from utilizing the full bandwidth when performing intensive full cache line writes and therefore a slight performance drop might be visible.

In addition, this erratum cannot occur if at least one of the following bits in the diagnostic control register is set to 1:

  • bit[23]: Disable read-allocate mode
  • bit[22]: Disable write-allocate wait mode

Category

Category 2

Level Two Title