[OLK-6.6] AMD Address Translation Library (ATL) patches · Pull Request !12300 · openEuler/kernel

*Description:*
--------------

Patches to introduce AMD Address Translation Library (ATL) on Turin systems.

RAS: Introduce AMD Address Translation Library
RAS/AMD/ATL: Add MI300 support
RAS/AMD/ATL: Add MI300 DRAM to normalized address translation support
RAS/AMD/ATL: Add MI300 row retirement support
RAS: Export helper to get ras_debugfs_dir
EDAC/amd64: Use new AMD Address Translation Library
RAS/AMD/ATL: Add amd_atl pr_fmt() prefix
RAS/AMD/ATL: Read DRAM hole base early
RAS/AMD/ATL: Expand helpers for adding and removing base and hole
RAS/AMD/ATL: Validate address map when information is gathered
RAS/AMD/ATL: Implement DF 4.5 NP2 denormalization
RAS: Introduce a FRU memory poison manager
RAS/AMD/FMPM: Save SPA values
RAS/AMD/FMPM: Add debugfs interface to print record entries
RAS/AMD/FMPM: Fix off by one when unwinding on error
RAS/AMD/FMPM: Avoid NULL ptr deref in get_saved_records()
RAS/AMD/FMPM: Safely handle saved records of various sizes
RAS/AMD/FMPM: Use atl internal.h for INVALID_SPA

By using RAS error injection tests we have captured the following logs
**Without ATL patches in Turin systems**
```javascript
[  333.395989] mce: [Hardware Error]: Machine check events logged
[  333.396016] [Hardware Error]: Corrected error, no action required.
[  333.396028] [Hardware Error]: CPU:0 (1a:1:0) MC21_STATUS[Over|CE|MiscV|AddrV|-|-|SyndV|CECC|-|-|-]: 0xdc2040000400011b
[  333.396050] [Hardware Error]: Error Addr: 0x0000000000000000
[  333.396058] [Hardware Error]: PPIN: 0x008319f6b6f24004
[  333.396066] [Hardware Error]: IPID: 0x0000009600050f00, Syndrome: 0x7c7600010a800100
[  333.396078] [Hardware Error]: Unified Memory Controller Ext. Error Code: 0, DRAM ECC error.
[  333.396096] umc_normaddr_to_sysaddr: Invalid DramBaseAddress range: 0x0.
[  333.396119] EDAC MC0: 1 CE Cannot decode normalized address on mc#0csrow#0channel#0 (csrow:0 channel:0 page:0x0 offset:0x0 grain:64 syndrome:0x1)
[  333.396139] [Hardware Error]: cache level: L3/GEN, tx: GEN, mem-tx: RD
```

**With ATL patches in turin systems**
```javascript
[  333.098899] [Hardware Error]: Corrected error, no action required.
[  333.098910] [Hardware Error]: CPU:0 (1a:1:0) MC21_STATUS[Over|CE|MiscV|AddrV|-|-|SyndV|CECC|-|-|-]: 0xdc2040000400011b
[  333.098929] [Hardware Error]: Error Addr: 0x0000000000000000
[  333.098936] [Hardware Error]: PPIN: 0x008319f6b6f24004
[  333.098943] [Hardware Error]: IPID: 0x0000009600050f00, Syndrome: 0x7c7600010a800100
[  333.098954] [Hardware Error]: Unified Memory Controller Ext. Error Code: 0, DRAM ECC error.
[  333.098992] EDAC MC0: 1 CE on mc#0csrow#0channel#0 (csrow:0 channel:0 page:0x0 offset:0x0 grain:64 syndrome:0x1)
[  333.099005] [Hardware Error]: cache level: L3/GEN, tx: GEN, mem-tx: RD
```

The Address Translational Library (ATL) backport has also been system tested.

GVPopenEuler/kernel关闭

搜索帮助

GVP openEuler/kernel
关闭