* [PATCH v6 01/14] baseband/acc100: remove unused registers
2022-09-24 0:50 From: Nicolas Chautru <nicolas.chautru@intel.com> Nicolas Chautru
@ 2022-09-24 0:50 ` Nicolas Chautru
2022-09-24 0:50 ` [PATCH v6 02/14] baseband/acc100: refactor to segregate common code Nicolas Chautru
` (12 subsequent siblings)
13 siblings, 0 replies; 28+ messages in thread
From: Nicolas Chautru @ 2022-09-24 0:50 UTC (permalink / raw)
To: dev, thomas
Cc: maxime.coquelin, trix, mdr, bruce.richardson, hemant.agrawal,
david.marchand, stephen, hernan.vargas, Nic Chautru
From: Nic Chautru <nicolas.chautru@intel.com>
Cleaning up the enum files to remove un-used registers definitions.
No functionality change.
Signed-off-by: Nic Chautru <nicolas.chautru@intel.com>
Reviewed-by: Maxime Coquelin <maxime.coquelin@redhat.com>
---
drivers/baseband/acc100/acc100_pf_enum.h | 939 -----------------------
1 file changed, 939 deletions(-)
diff --git a/drivers/baseband/acc100/acc100_pf_enum.h b/drivers/baseband/acc100/acc100_pf_enum.h
index 2fba667627..f4e5002762 100644
--- a/drivers/baseband/acc100/acc100_pf_enum.h
+++ b/drivers/baseband/acc100/acc100_pf_enum.h
@@ -14,32 +14,6 @@
enum {
HWPfQmgrEgressQueuesTemplate = 0x0007FE00,
HWPfQmgrIngressAq = 0x00080000,
- HWPfQmgrArbQAvail = 0x00A00010,
- HWPfQmgrArbQBlock = 0x00A00014,
- HWPfQmgrAqueueDropNotifEn = 0x00A00024,
- HWPfQmgrAqueueDisableNotifEn = 0x00A00028,
- HWPfQmgrSoftReset = 0x00A00038,
- HWPfQmgrInitStatus = 0x00A0003C,
- HWPfQmgrAramWatchdogCount = 0x00A00040,
- HWPfQmgrAramWatchdogCounterEn = 0x00A00044,
- HWPfQmgrAxiWatchdogCount = 0x00A00048,
- HWPfQmgrAxiWatchdogCounterEn = 0x00A0004C,
- HWPfQmgrProcessWatchdogCount = 0x00A00050,
- HWPfQmgrProcessWatchdogCounterEn = 0x00A00054,
- HWPfQmgrProcessUl4GWatchdogCounter = 0x00A00058,
- HWPfQmgrProcessDl4GWatchdogCounter = 0x00A0005C,
- HWPfQmgrProcessUl5GWatchdogCounter = 0x00A00060,
- HWPfQmgrProcessDl5GWatchdogCounter = 0x00A00064,
- HWPfQmgrProcessMldWatchdogCounter = 0x00A00068,
- HWPfQmgrMsiOverflowUpperVf = 0x00A00070,
- HWPfQmgrMsiOverflowLowerVf = 0x00A00074,
- HWPfQmgrMsiWatchdogOverflow = 0x00A00078,
- HWPfQmgrMsiOverflowEnable = 0x00A0007C,
- HWPfQmgrDebugAqPointerMemGrp = 0x00A00100,
- HWPfQmgrDebugOutputArbQFifoGrp = 0x00A00140,
- HWPfQmgrDebugMsiFifoGrp = 0x00A00180,
- HWPfQmgrDebugAxiWdTimeoutMsiFifo = 0x00A001C0,
- HWPfQmgrDebugProcessWdTimeoutMsiFifo = 0x00A001C4,
HWPfQmgrDepthLog2Grp = 0x00A00200,
HWPfQmgrTholdGrp = 0x00A00300,
HWPfQmgrGrpTmplateReg0Indx = 0x00A00600,
@@ -48,85 +22,23 @@ enum {
HWPfQmgrGrpTmplateReg3Indx = 0x00A00780,
HWPfQmgrGrpTmplateReg4Indx = 0x00A00800,
HWPfQmgrVfBaseAddr = 0x00A01000,
- HWPfQmgrUl4GWeightRrVf = 0x00A02000,
- HWPfQmgrDl4GWeightRrVf = 0x00A02100,
- HWPfQmgrUl5GWeightRrVf = 0x00A02200,
- HWPfQmgrDl5GWeightRrVf = 0x00A02300,
- HWPfQmgrMldWeightRrVf = 0x00A02400,
HWPfQmgrArbQDepthGrp = 0x00A02F00,
HWPfQmgrGrpFunction0 = 0x00A02F40,
- HWPfQmgrGrpFunction1 = 0x00A02F44,
HWPfQmgrGrpPriority = 0x00A02F48,
- HWPfQmgrWeightSync = 0x00A03000,
HWPfQmgrAqEnableVf = 0x00A10000,
- HWPfQmgrAqResetVf = 0x00A20000,
HWPfQmgrRingSizeVf = 0x00A20004,
HWPfQmgrGrpDepthLog20Vf = 0x00A20008,
HWPfQmgrGrpDepthLog21Vf = 0x00A2000C,
- HWPfQmgrGrpFunction0Vf = 0x00A20010,
- HWPfQmgrGrpFunction1Vf = 0x00A20014,
HWPfDmaConfig0Reg = 0x00B80000,
HWPfDmaConfig1Reg = 0x00B80004,
HWPfDmaQmgrAddrReg = 0x00B80008,
- HWPfDmaSoftResetReg = 0x00B8000C,
HWPfDmaAxcacheReg = 0x00B80010,
- HWPfDmaVersionReg = 0x00B80014,
- HWPfDmaFrameThreshold = 0x00B80018,
- HWPfDmaTimestampLo = 0x00B8001C,
- HWPfDmaTimestampHi = 0x00B80020,
- HWPfDmaAxiStatus = 0x00B80028,
HWPfDmaAxiControl = 0x00B8002C,
- HWPfDmaNoQmgr = 0x00B80030,
- HWPfDmaQosScale = 0x00B80034,
HWPfDmaQmanen = 0x00B80040,
- HWPfDmaQmgrQosBase = 0x00B80060,
- HWPfDmaFecClkGatingEnable = 0x00B80080,
- HWPfDmaPmEnable = 0x00B80084,
- HWPfDmaQosEnable = 0x00B80088,
- HWPfDmaHarqWeightedRrFrameThreshold = 0x00B800B0,
- HWPfDmaDataSmallWeightedRrFrameThresh = 0x00B800B4,
- HWPfDmaDataLargeWeightedRrFrameThresh = 0x00B800B8,
- HWPfDmaInboundCbMaxSize = 0x00B800BC,
HWPfDmaInboundDrainDataSize = 0x00B800C0,
HWPfDmaVfDdrBaseRw = 0x00B80400,
- HWPfDmaCmplTmOutCnt = 0x00B80800,
- HWPfDmaProcTmOutCnt = 0x00B80804,
- HWPfDmaStatusRrespBresp = 0x00B80810,
- HWPfDmaCfgRrespBresp = 0x00B80814,
- HWPfDmaStatusMemParErr = 0x00B80818,
- HWPfDmaCfgMemParErrEn = 0x00B8081C,
- HWPfDmaStatusDmaHwErr = 0x00B80820,
- HWPfDmaCfgDmaHwErrEn = 0x00B80824,
- HWPfDmaStatusFecCoreErr = 0x00B80828,
- HWPfDmaCfgFecCoreErrEn = 0x00B8082C,
- HWPfDmaStatusFcwDescrErr = 0x00B80830,
- HWPfDmaCfgFcwDescrErrEn = 0x00B80834,
- HWPfDmaStatusBlockTransmit = 0x00B80838,
- HWPfDmaBlockOnErrEn = 0x00B8083C,
- HWPfDmaStatusFlushDma = 0x00B80840,
- HWPfDmaFlushDmaOnErrEn = 0x00B80844,
- HWPfDmaStatusSdoneFifoFull = 0x00B80848,
- HWPfDmaStatusDescriptorErrLoVf = 0x00B8084C,
- HWPfDmaStatusDescriptorErrHiVf = 0x00B80850,
- HWPfDmaStatusFcwErrLoVf = 0x00B80854,
- HWPfDmaStatusFcwErrHiVf = 0x00B80858,
- HWPfDmaStatusDataErrLoVf = 0x00B8085C,
- HWPfDmaStatusDataErrHiVf = 0x00B80860,
- HWPfDmaCfgMsiEnSoftwareErr = 0x00B80864,
HWPfDmaDescriptorSignatuture = 0x00B80868,
- HWPfDmaFcwSignature = 0x00B8086C,
HWPfDmaErrorDetectionEn = 0x00B80870,
- HWPfDmaErrCntrlFifoDebug = 0x00B8087C,
- HWPfDmaStatusToutData = 0x00B80880,
- HWPfDmaStatusToutDesc = 0x00B80884,
- HWPfDmaStatusToutUnexpData = 0x00B80888,
- HWPfDmaStatusToutUnexpDesc = 0x00B8088C,
- HWPfDmaStatusToutProcess = 0x00B80890,
- HWPfDmaConfigCtoutOutDataEn = 0x00B808A0,
- HWPfDmaConfigCtoutOutDescrEn = 0x00B808A4,
- HWPfDmaConfigUnexpComplDataEn = 0x00B808A8,
- HWPfDmaConfigUnexpComplDescrEn = 0x00B808AC,
- HWPfDmaConfigPtoutOutEn = 0x00B808B0,
HWPfDmaFec5GulDescBaseLoRegVf = 0x00B88020,
HWPfDmaFec5GulDescBaseHiRegVf = 0x00B88024,
HWPfDmaFec5GulRespPtrLoRegVf = 0x00B88028,
@@ -143,414 +55,34 @@ enum {
HWPfDmaFec4GdlDescBaseHiRegVf = 0x00B88084,
HWPfDmaFec4GdlRespPtrLoRegVf = 0x00B88088,
HWPfDmaFec4GdlRespPtrHiRegVf = 0x00B8808C,
- HWPfDmaVfDdrBaseRangeRo = 0x00B880A0,
- HWPfQosmonACntrlReg = 0x00B90000,
HWPfQosmonAEvalOverflow0 = 0x00B90008,
- HWPfQosmonAEvalOverflow1 = 0x00B9000C,
- HWPfQosmonADivTerm = 0x00B90010,
- HWPfQosmonATickTerm = 0x00B90014,
- HWPfQosmonAEvalTerm = 0x00B90018,
- HWPfQosmonAAveTerm = 0x00B9001C,
- HWPfQosmonAForceEccErr = 0x00B90020,
- HWPfQosmonAEccErrDetect = 0x00B90024,
- HWPfQosmonAIterationConfig0Low = 0x00B90060,
- HWPfQosmonAIterationConfig0High = 0x00B90064,
- HWPfQosmonAIterationConfig1Low = 0x00B90068,
- HWPfQosmonAIterationConfig1High = 0x00B9006C,
- HWPfQosmonAIterationConfig2Low = 0x00B90070,
- HWPfQosmonAIterationConfig2High = 0x00B90074,
- HWPfQosmonAIterationConfig3Low = 0x00B90078,
- HWPfQosmonAIterationConfig3High = 0x00B9007C,
- HWPfQosmonAEvalMemAddr = 0x00B90080,
- HWPfQosmonAEvalMemData = 0x00B90084,
- HWPfQosmonAXaction = 0x00B900C0,
- HWPfQosmonARemThres1Vf = 0x00B90400,
- HWPfQosmonAThres2Vf = 0x00B90404,
- HWPfQosmonAWeiFracVf = 0x00B90408,
- HWPfQosmonARrWeiVf = 0x00B9040C,
HWPfPermonACntrlRegVf = 0x00B98000,
- HWPfPermonACountVf = 0x00B98008,
- HWPfPermonAKCntLoVf = 0x00B98010,
- HWPfPermonAKCntHiVf = 0x00B98014,
- HWPfPermonADeltaCntLoVf = 0x00B98020,
- HWPfPermonADeltaCntHiVf = 0x00B98024,
- HWPfPermonAVersionReg = 0x00B9C000,
- HWPfPermonACbControlFec = 0x00B9C0F0,
- HWPfPermonADltTimerLoFec = 0x00B9C0F4,
- HWPfPermonADltTimerHiFec = 0x00B9C0F8,
- HWPfPermonACbCountFec = 0x00B9C100,
- HWPfPermonAAccExecTimerLoFec = 0x00B9C104,
- HWPfPermonAAccExecTimerHiFec = 0x00B9C108,
- HWPfPermonAExecTimerMinFec = 0x00B9C200,
- HWPfPermonAExecTimerMaxFec = 0x00B9C204,
- HWPfPermonAControlBusMon = 0x00B9C400,
- HWPfPermonAConfigBusMon = 0x00B9C404,
- HWPfPermonASkipCountBusMon = 0x00B9C408,
- HWPfPermonAMinLatBusMon = 0x00B9C40C,
- HWPfPermonAMaxLatBusMon = 0x00B9C500,
- HWPfPermonATotalLatLowBusMon = 0x00B9C504,
- HWPfPermonATotalLatUpperBusMon = 0x00B9C508,
- HWPfPermonATotalReqCntBusMon = 0x00B9C50C,
- HWPfQosmonBCntrlReg = 0x00BA0000,
HWPfQosmonBEvalOverflow0 = 0x00BA0008,
- HWPfQosmonBEvalOverflow1 = 0x00BA000C,
- HWPfQosmonBDivTerm = 0x00BA0010,
- HWPfQosmonBTickTerm = 0x00BA0014,
- HWPfQosmonBEvalTerm = 0x00BA0018,
- HWPfQosmonBAveTerm = 0x00BA001C,
- HWPfQosmonBForceEccErr = 0x00BA0020,
- HWPfQosmonBEccErrDetect = 0x00BA0024,
- HWPfQosmonBIterationConfig0Low = 0x00BA0060,
- HWPfQosmonBIterationConfig0High = 0x00BA0064,
- HWPfQosmonBIterationConfig1Low = 0x00BA0068,
- HWPfQosmonBIterationConfig1High = 0x00BA006C,
- HWPfQosmonBIterationConfig2Low = 0x00BA0070,
- HWPfQosmonBIterationConfig2High = 0x00BA0074,
- HWPfQosmonBIterationConfig3Low = 0x00BA0078,
- HWPfQosmonBIterationConfig3High = 0x00BA007C,
- HWPfQosmonBEvalMemAddr = 0x00BA0080,
- HWPfQosmonBEvalMemData = 0x00BA0084,
- HWPfQosmonBXaction = 0x00BA00C0,
- HWPfQosmonBRemThres1Vf = 0x00BA0400,
- HWPfQosmonBThres2Vf = 0x00BA0404,
- HWPfQosmonBWeiFracVf = 0x00BA0408,
- HWPfQosmonBRrWeiVf = 0x00BA040C,
HWPfPermonBCntrlRegVf = 0x00BA8000,
- HWPfPermonBCountVf = 0x00BA8008,
- HWPfPermonBKCntLoVf = 0x00BA8010,
- HWPfPermonBKCntHiVf = 0x00BA8014,
- HWPfPermonBDeltaCntLoVf = 0x00BA8020,
- HWPfPermonBDeltaCntHiVf = 0x00BA8024,
- HWPfPermonBVersionReg = 0x00BAC000,
- HWPfPermonBCbControlFec = 0x00BAC0F0,
- HWPfPermonBDltTimerLoFec = 0x00BAC0F4,
- HWPfPermonBDltTimerHiFec = 0x00BAC0F8,
- HWPfPermonBCbCountFec = 0x00BAC100,
- HWPfPermonBAccExecTimerLoFec = 0x00BAC104,
- HWPfPermonBAccExecTimerHiFec = 0x00BAC108,
- HWPfPermonBExecTimerMinFec = 0x00BAC200,
- HWPfPermonBExecTimerMaxFec = 0x00BAC204,
- HWPfPermonBControlBusMon = 0x00BAC400,
- HWPfPermonBConfigBusMon = 0x00BAC404,
- HWPfPermonBSkipCountBusMon = 0x00BAC408,
- HWPfPermonBMinLatBusMon = 0x00BAC40C,
- HWPfPermonBMaxLatBusMon = 0x00BAC500,
- HWPfPermonBTotalLatLowBusMon = 0x00BAC504,
- HWPfPermonBTotalLatUpperBusMon = 0x00BAC508,
- HWPfPermonBTotalReqCntBusMon = 0x00BAC50C,
- HwPfFabI2MArbCntrlReg = 0x00BB0000,
HWPfFabricMode = 0x00BB1000,
- HwPfFabI2MGrp0DebugReg = 0x00BBF000,
- HwPfFabI2MGrp1DebugReg = 0x00BBF004,
- HwPfFabI2MGrp2DebugReg = 0x00BBF008,
- HwPfFabI2MGrp3DebugReg = 0x00BBF00C,
- HwPfFabI2MBuf0DebugReg = 0x00BBF010,
- HwPfFabI2MBuf1DebugReg = 0x00BBF014,
- HwPfFabI2MBuf2DebugReg = 0x00BBF018,
- HwPfFabI2MBuf3DebugReg = 0x00BBF01C,
- HwPfFabM2IBuf0Grp0DebugReg = 0x00BBF020,
- HwPfFabM2IBuf1Grp0DebugReg = 0x00BBF024,
- HwPfFabM2IBuf0Grp1DebugReg = 0x00BBF028,
- HwPfFabM2IBuf1Grp1DebugReg = 0x00BBF02C,
- HwPfFabM2IBuf0Grp2DebugReg = 0x00BBF030,
- HwPfFabM2IBuf1Grp2DebugReg = 0x00BBF034,
- HwPfFabM2IBuf0Grp3DebugReg = 0x00BBF038,
- HwPfFabM2IBuf1Grp3DebugReg = 0x00BBF03C,
HWPfFecUl5gCntrlReg = 0x00BC0000,
- HWPfFecUl5gI2MThreshReg = 0x00BC0004,
- HWPfFecUl5gVersionReg = 0x00BC0100,
- HWPfFecUl5gFcwStatusReg = 0x00BC0104,
- HWPfFecUl5gWarnReg = 0x00BC0108,
HwPfFecUl5gIbDebugReg = 0x00BC0200,
- HwPfFecUl5gObLlrDebugReg = 0x00BC0204,
- HwPfFecUl5gObHarqDebugReg = 0x00BC0208,
- HwPfFecUl5g1CntrlReg = 0x00BC1000,
- HwPfFecUl5g1I2MThreshReg = 0x00BC1004,
- HwPfFecUl5g1VersionReg = 0x00BC1100,
- HwPfFecUl5g1FcwStatusReg = 0x00BC1104,
- HwPfFecUl5g1WarnReg = 0x00BC1108,
- HwPfFecUl5g1IbDebugReg = 0x00BC1200,
- HwPfFecUl5g1ObLlrDebugReg = 0x00BC1204,
- HwPfFecUl5g1ObHarqDebugReg = 0x00BC1208,
- HwPfFecUl5g2CntrlReg = 0x00BC2000,
- HwPfFecUl5g2I2MThreshReg = 0x00BC2004,
- HwPfFecUl5g2VersionReg = 0x00BC2100,
- HwPfFecUl5g2FcwStatusReg = 0x00BC2104,
- HwPfFecUl5g2WarnReg = 0x00BC2108,
- HwPfFecUl5g2IbDebugReg = 0x00BC2200,
- HwPfFecUl5g2ObLlrDebugReg = 0x00BC2204,
- HwPfFecUl5g2ObHarqDebugReg = 0x00BC2208,
- HwPfFecUl5g3CntrlReg = 0x00BC3000,
- HwPfFecUl5g3I2MThreshReg = 0x00BC3004,
- HwPfFecUl5g3VersionReg = 0x00BC3100,
- HwPfFecUl5g3FcwStatusReg = 0x00BC3104,
- HwPfFecUl5g3WarnReg = 0x00BC3108,
- HwPfFecUl5g3IbDebugReg = 0x00BC3200,
- HwPfFecUl5g3ObLlrDebugReg = 0x00BC3204,
- HwPfFecUl5g3ObHarqDebugReg = 0x00BC3208,
- HwPfFecUl5g4CntrlReg = 0x00BC4000,
- HwPfFecUl5g4I2MThreshReg = 0x00BC4004,
- HwPfFecUl5g4VersionReg = 0x00BC4100,
- HwPfFecUl5g4FcwStatusReg = 0x00BC4104,
- HwPfFecUl5g4WarnReg = 0x00BC4108,
- HwPfFecUl5g4IbDebugReg = 0x00BC4200,
- HwPfFecUl5g4ObLlrDebugReg = 0x00BC4204,
- HwPfFecUl5g4ObHarqDebugReg = 0x00BC4208,
- HwPfFecUl5g5CntrlReg = 0x00BC5000,
- HwPfFecUl5g5I2MThreshReg = 0x00BC5004,
- HwPfFecUl5g5VersionReg = 0x00BC5100,
- HwPfFecUl5g5FcwStatusReg = 0x00BC5104,
- HwPfFecUl5g5WarnReg = 0x00BC5108,
- HwPfFecUl5g5IbDebugReg = 0x00BC5200,
- HwPfFecUl5g5ObLlrDebugReg = 0x00BC5204,
- HwPfFecUl5g5ObHarqDebugReg = 0x00BC5208,
- HwPfFecUl5g6CntrlReg = 0x00BC6000,
- HwPfFecUl5g6I2MThreshReg = 0x00BC6004,
- HwPfFecUl5g6VersionReg = 0x00BC6100,
- HwPfFecUl5g6FcwStatusReg = 0x00BC6104,
- HwPfFecUl5g6WarnReg = 0x00BC6108,
- HwPfFecUl5g6IbDebugReg = 0x00BC6200,
- HwPfFecUl5g6ObLlrDebugReg = 0x00BC6204,
- HwPfFecUl5g6ObHarqDebugReg = 0x00BC6208,
- HwPfFecUl5g7CntrlReg = 0x00BC7000,
- HwPfFecUl5g7I2MThreshReg = 0x00BC7004,
- HwPfFecUl5g7VersionReg = 0x00BC7100,
- HwPfFecUl5g7FcwStatusReg = 0x00BC7104,
- HwPfFecUl5g7WarnReg = 0x00BC7108,
- HwPfFecUl5g7IbDebugReg = 0x00BC7200,
- HwPfFecUl5g7ObLlrDebugReg = 0x00BC7204,
- HwPfFecUl5g7ObHarqDebugReg = 0x00BC7208,
- HwPfFecUl5g8CntrlReg = 0x00BC8000,
- HwPfFecUl5g8I2MThreshReg = 0x00BC8004,
- HwPfFecUl5g8VersionReg = 0x00BC8100,
- HwPfFecUl5g8FcwStatusReg = 0x00BC8104,
- HwPfFecUl5g8WarnReg = 0x00BC8108,
- HwPfFecUl5g8IbDebugReg = 0x00BC8200,
- HwPfFecUl5g8ObLlrDebugReg = 0x00BC8204,
- HwPfFecUl5g8ObHarqDebugReg = 0x00BC8208,
- HWPfFecDl5gCntrlReg = 0x00BCF000,
- HWPfFecDl5gI2MThreshReg = 0x00BCF004,
- HWPfFecDl5gVersionReg = 0x00BCF100,
- HWPfFecDl5gFcwStatusReg = 0x00BCF104,
- HWPfFecDl5gWarnReg = 0x00BCF108,
- HWPfFecUlVersionReg = 0x00BD0000,
- HWPfFecUlControlReg = 0x00BD0004,
- HWPfFecUlStatusReg = 0x00BD0008,
- HWPfFecDlVersionReg = 0x00BDF000,
- HWPfFecDlClusterConfigReg = 0x00BDF004,
- HWPfFecDlBurstThres = 0x00BDF00C,
- HWPfFecDlClusterStatusReg0 = 0x00BDF040,
- HWPfFecDlClusterStatusReg1 = 0x00BDF044,
- HWPfFecDlClusterStatusReg2 = 0x00BDF048,
- HWPfFecDlClusterStatusReg3 = 0x00BDF04C,
- HWPfFecDlClusterStatusReg4 = 0x00BDF050,
- HWPfFecDlClusterStatusReg5 = 0x00BDF054,
- HWPfChaFabPllPllrst = 0x00C40000,
- HWPfChaFabPllClk0 = 0x00C40004,
- HWPfChaFabPllClk1 = 0x00C40008,
- HWPfChaFabPllBwadj = 0x00C4000C,
- HWPfChaFabPllLbw = 0x00C40010,
- HWPfChaFabPllResetq = 0x00C40014,
- HWPfChaFabPllPhshft0 = 0x00C40018,
- HWPfChaFabPllPhshft1 = 0x00C4001C,
- HWPfChaFabPllDivq0 = 0x00C40020,
- HWPfChaFabPllDivq1 = 0x00C40024,
- HWPfChaFabPllDivq2 = 0x00C40028,
- HWPfChaFabPllDivq3 = 0x00C4002C,
- HWPfChaFabPllDivq4 = 0x00C40030,
- HWPfChaFabPllDivq5 = 0x00C40034,
- HWPfChaFabPllDivq6 = 0x00C40038,
- HWPfChaFabPllDivq7 = 0x00C4003C,
- HWPfChaDl5gPllPllrst = 0x00C40080,
- HWPfChaDl5gPllClk0 = 0x00C40084,
- HWPfChaDl5gPllClk1 = 0x00C40088,
- HWPfChaDl5gPllBwadj = 0x00C4008C,
- HWPfChaDl5gPllLbw = 0x00C40090,
- HWPfChaDl5gPllResetq = 0x00C40094,
HWPfChaDl5gPllPhshft0 = 0x00C40098,
- HWPfChaDl5gPllPhshft1 = 0x00C4009C,
- HWPfChaDl5gPllDivq0 = 0x00C400A0,
- HWPfChaDl5gPllDivq1 = 0x00C400A4,
- HWPfChaDl5gPllDivq2 = 0x00C400A8,
- HWPfChaDl5gPllDivq3 = 0x00C400AC,
- HWPfChaDl5gPllDivq4 = 0x00C400B0,
- HWPfChaDl5gPllDivq5 = 0x00C400B4,
- HWPfChaDl5gPllDivq6 = 0x00C400B8,
- HWPfChaDl5gPllDivq7 = 0x00C400BC,
- HWPfChaDl4gPllPllrst = 0x00C40100,
- HWPfChaDl4gPllClk0 = 0x00C40104,
- HWPfChaDl4gPllClk1 = 0x00C40108,
- HWPfChaDl4gPllBwadj = 0x00C4010C,
- HWPfChaDl4gPllLbw = 0x00C40110,
- HWPfChaDl4gPllResetq = 0x00C40114,
- HWPfChaDl4gPllPhshft0 = 0x00C40118,
- HWPfChaDl4gPllPhshft1 = 0x00C4011C,
- HWPfChaDl4gPllDivq0 = 0x00C40120,
- HWPfChaDl4gPllDivq1 = 0x00C40124,
- HWPfChaDl4gPllDivq2 = 0x00C40128,
- HWPfChaDl4gPllDivq3 = 0x00C4012C,
- HWPfChaDl4gPllDivq4 = 0x00C40130,
- HWPfChaDl4gPllDivq5 = 0x00C40134,
- HWPfChaDl4gPllDivq6 = 0x00C40138,
- HWPfChaDl4gPllDivq7 = 0x00C4013C,
- HWPfChaUl5gPllPllrst = 0x00C40180,
- HWPfChaUl5gPllClk0 = 0x00C40184,
- HWPfChaUl5gPllClk1 = 0x00C40188,
- HWPfChaUl5gPllBwadj = 0x00C4018C,
- HWPfChaUl5gPllLbw = 0x00C40190,
- HWPfChaUl5gPllResetq = 0x00C40194,
- HWPfChaUl5gPllPhshft0 = 0x00C40198,
- HWPfChaUl5gPllPhshft1 = 0x00C4019C,
- HWPfChaUl5gPllDivq0 = 0x00C401A0,
- HWPfChaUl5gPllDivq1 = 0x00C401A4,
- HWPfChaUl5gPllDivq2 = 0x00C401A8,
- HWPfChaUl5gPllDivq3 = 0x00C401AC,
- HWPfChaUl5gPllDivq4 = 0x00C401B0,
- HWPfChaUl5gPllDivq5 = 0x00C401B4,
- HWPfChaUl5gPllDivq6 = 0x00C401B8,
- HWPfChaUl5gPllDivq7 = 0x00C401BC,
- HWPfChaUl4gPllPllrst = 0x00C40200,
- HWPfChaUl4gPllClk0 = 0x00C40204,
- HWPfChaUl4gPllClk1 = 0x00C40208,
- HWPfChaUl4gPllBwadj = 0x00C4020C,
- HWPfChaUl4gPllLbw = 0x00C40210,
- HWPfChaUl4gPllResetq = 0x00C40214,
- HWPfChaUl4gPllPhshft0 = 0x00C40218,
- HWPfChaUl4gPllPhshft1 = 0x00C4021C,
- HWPfChaUl4gPllDivq0 = 0x00C40220,
- HWPfChaUl4gPllDivq1 = 0x00C40224,
- HWPfChaUl4gPllDivq2 = 0x00C40228,
- HWPfChaUl4gPllDivq3 = 0x00C4022C,
- HWPfChaUl4gPllDivq4 = 0x00C40230,
- HWPfChaUl4gPllDivq5 = 0x00C40234,
- HWPfChaUl4gPllDivq6 = 0x00C40238,
- HWPfChaUl4gPllDivq7 = 0x00C4023C,
- HWPfChaDdrPllPllrst = 0x00C40280,
- HWPfChaDdrPllClk0 = 0x00C40284,
- HWPfChaDdrPllClk1 = 0x00C40288,
- HWPfChaDdrPllBwadj = 0x00C4028C,
- HWPfChaDdrPllLbw = 0x00C40290,
- HWPfChaDdrPllResetq = 0x00C40294,
- HWPfChaDdrPllPhshft0 = 0x00C40298,
- HWPfChaDdrPllPhshft1 = 0x00C4029C,
- HWPfChaDdrPllDivq0 = 0x00C402A0,
- HWPfChaDdrPllDivq1 = 0x00C402A4,
- HWPfChaDdrPllDivq2 = 0x00C402A8,
- HWPfChaDdrPllDivq3 = 0x00C402AC,
- HWPfChaDdrPllDivq4 = 0x00C402B0,
- HWPfChaDdrPllDivq5 = 0x00C402B4,
- HWPfChaDdrPllDivq6 = 0x00C402B8,
- HWPfChaDdrPllDivq7 = 0x00C402BC,
- HWPfChaErrStatus = 0x00C40400,
- HWPfChaErrMask = 0x00C40404,
- HWPfChaDebugPcieMsiFifo = 0x00C40410,
- HWPfChaDebugDdrMsiFifo = 0x00C40414,
- HWPfChaDebugMiscMsiFifo = 0x00C40418,
- HWPfChaPwmSet = 0x00C40420,
- HWPfChaDdrRstStatus = 0x00C40430,
HWPfChaDdrStDoneStatus = 0x00C40434,
HWPfChaDdrWbRstCfg = 0x00C40438,
HWPfChaDdrApbRstCfg = 0x00C4043C,
HWPfChaDdrPhyRstCfg = 0x00C40440,
HWPfChaDdrCpuRstCfg = 0x00C40444,
HWPfChaDdrSifRstCfg = 0x00C40448,
- HWPfChaPadcfgPcomp0 = 0x00C41000,
- HWPfChaPadcfgNcomp0 = 0x00C41004,
- HWPfChaPadcfgOdt0 = 0x00C41008,
- HWPfChaPadcfgProtect0 = 0x00C4100C,
- HWPfChaPreemphasisProtect0 = 0x00C41010,
- HWPfChaPreemphasisCompen0 = 0x00C41040,
- HWPfChaPreemphasisOdten0 = 0x00C41044,
- HWPfChaPadcfgPcomp1 = 0x00C41100,
- HWPfChaPadcfgNcomp1 = 0x00C41104,
- HWPfChaPadcfgOdt1 = 0x00C41108,
- HWPfChaPadcfgProtect1 = 0x00C4110C,
- HWPfChaPreemphasisProtect1 = 0x00C41110,
- HWPfChaPreemphasisCompen1 = 0x00C41140,
- HWPfChaPreemphasisOdten1 = 0x00C41144,
- HWPfChaPadcfgPcomp2 = 0x00C41200,
- HWPfChaPadcfgNcomp2 = 0x00C41204,
- HWPfChaPadcfgOdt2 = 0x00C41208,
- HWPfChaPadcfgProtect2 = 0x00C4120C,
- HWPfChaPreemphasisProtect2 = 0x00C41210,
- HWPfChaPreemphasisCompen2 = 0x00C41240,
- HWPfChaPreemphasisOdten4 = 0x00C41444,
- HWPfChaPreemphasisOdten2 = 0x00C41244,
- HWPfChaPadcfgPcomp3 = 0x00C41300,
- HWPfChaPadcfgNcomp3 = 0x00C41304,
- HWPfChaPadcfgOdt3 = 0x00C41308,
- HWPfChaPadcfgProtect3 = 0x00C4130C,
- HWPfChaPreemphasisProtect3 = 0x00C41310,
- HWPfChaPreemphasisCompen3 = 0x00C41340,
- HWPfChaPreemphasisOdten3 = 0x00C41344,
- HWPfChaPadcfgPcomp4 = 0x00C41400,
- HWPfChaPadcfgNcomp4 = 0x00C41404,
- HWPfChaPadcfgOdt4 = 0x00C41408,
- HWPfChaPadcfgProtect4 = 0x00C4140C,
- HWPfChaPreemphasisProtect4 = 0x00C41410,
- HWPfChaPreemphasisCompen4 = 0x00C41440,
- HWPfHiVfToPfDbellVf = 0x00C80000,
- HWPfHiPfToVfDbellVf = 0x00C80008,
- HWPfHiInfoRingBaseLoVf = 0x00C80010,
- HWPfHiInfoRingBaseHiVf = 0x00C80014,
- HWPfHiInfoRingPointerVf = 0x00C80018,
- HWPfHiInfoRingIntWrEnVf = 0x00C80020,
- HWPfHiInfoRingPf2VfWrEnVf = 0x00C80024,
- HWPfHiMsixVectorMapperVf = 0x00C80060,
- HWPfHiModuleVersionReg = 0x00C84000,
- HWPfHiIosf2axiErrLogReg = 0x00C84004,
- HWPfHiHardResetReg = 0x00C84008,
HWPfHi5GHardResetReg = 0x00C8400C,
HWPfHiInfoRingBaseLoRegPf = 0x00C84010,
HWPfHiInfoRingBaseHiRegPf = 0x00C84014,
HWPfHiInfoRingPointerRegPf = 0x00C84018,
HWPfHiInfoRingIntWrEnRegPf = 0x00C84020,
HWPfHiInfoRingVf2pfLoWrEnReg = 0x00C84024,
- HWPfHiInfoRingVf2pfHiWrEnReg = 0x00C84028,
- HWPfHiLogParityErrStatusReg = 0x00C8402C,
- HWPfHiLogDataParityErrorVfStatusLo = 0x00C84030,
- HWPfHiLogDataParityErrorVfStatusHi = 0x00C84034,
HWPfHiBlockTransmitOnErrorEn = 0x00C84038,
HWPfHiCfgMsiIntWrEnRegPf = 0x00C84040,
HWPfHiCfgMsiVf2pfLoWrEnReg = 0x00C84044,
- HWPfHiCfgMsiVf2pfHighWrEnReg = 0x00C84048,
- HWPfHiMsixVectorMapperPf = 0x00C84060,
- HWPfHiApbWrWaitTime = 0x00C84100,
- HWPfHiXCounterMaxValue = 0x00C84104,
HWPfHiPfMode = 0x00C84108,
HWPfHiClkGateHystReg = 0x00C8410C,
- HWPfHiSnoopBitsReg = 0x00C84110,
HWPfHiMsiDropEnableReg = 0x00C84114,
- HWPfHiMsiStatReg = 0x00C84120,
- HWPfHiFifoOflStatReg = 0x00C84124,
- HWPfHiHiDebugReg = 0x00C841F4,
- HWPfHiDebugMemSnoopMsiFifo = 0x00C841F8,
- HWPfHiDebugMemSnoopInputFifo = 0x00C841FC,
- HWPfHiMsixMappingConfig = 0x00C84200,
- HWPfHiJunkReg = 0x00C8FF00,
- HWPfDdrUmmcVer = 0x00D00000,
- HWPfDdrUmmcCap = 0x00D00010,
HWPfDdrUmmcCtrl = 0x00D00020,
- HWPfDdrMpcPe = 0x00D00080,
- HWPfDdrMpcPpri3 = 0x00D00090,
- HWPfDdrMpcPpri2 = 0x00D000A0,
- HWPfDdrMpcPpri1 = 0x00D000B0,
- HWPfDdrMpcPpri0 = 0x00D000C0,
- HWPfDdrMpcPrwgrpCtrl = 0x00D000D0,
- HWPfDdrMpcPbw7 = 0x00D000E0,
- HWPfDdrMpcPbw6 = 0x00D000F0,
- HWPfDdrMpcPbw5 = 0x00D00100,
- HWPfDdrMpcPbw4 = 0x00D00110,
- HWPfDdrMpcPbw3 = 0x00D00120,
- HWPfDdrMpcPbw2 = 0x00D00130,
- HWPfDdrMpcPbw1 = 0x00D00140,
- HWPfDdrMpcPbw0 = 0x00D00150,
- HWPfDdrMemoryInit = 0x00D00200,
- HWPfDdrMemoryInitDone = 0x00D00210,
HWPfDdrMemInitPhyTrng0 = 0x00D00240,
- HWPfDdrMemInitPhyTrng1 = 0x00D00250,
- HWPfDdrMemInitPhyTrng2 = 0x00D00260,
- HWPfDdrMemInitPhyTrng3 = 0x00D00270,
HWPfDdrBcDram = 0x00D003C0,
HWPfDdrBcAddrMap = 0x00D003D0,
HWPfDdrBcRef = 0x00D003E0,
@@ -565,502 +97,31 @@ enum {
HWPfDdrBcTim8 = 0x00D00480,
HWPfDdrBcTim9 = 0x00D00490,
HWPfDdrBcTim10 = 0x00D004A0,
- HWPfDdrBcTim12 = 0x00D004C0,
HWPfDdrDfiInit = 0x00D004D0,
- HWPfDdrDfiInitComplete = 0x00D004E0,
HWPfDdrDfiTim0 = 0x00D004F0,
HWPfDdrDfiTim1 = 0x00D00500,
HWPfDdrDfiPhyUpdEn = 0x00D00530,
- HWPfDdrMemStatus = 0x00D00540,
- HWPfDdrUmmcErrStatus = 0x00D00550,
- HWPfDdrUmmcIntStatus = 0x00D00560,
HWPfDdrUmmcIntEn = 0x00D00570,
HWPfDdrPhyRdLatency = 0x00D48400,
HWPfDdrPhyRdLatencyDbi = 0x00D48410,
HWPfDdrPhyWrLatency = 0x00D48420,
HWPfDdrPhyTrngType = 0x00D48430,
- HWPfDdrPhyMrsTiming2 = 0x00D48440,
- HWPfDdrPhyMrsTiming0 = 0x00D48450,
- HWPfDdrPhyMrsTiming1 = 0x00D48460,
- HWPfDdrPhyDramTmrd = 0x00D48470,
- HWPfDdrPhyDramTmod = 0x00D48480,
- HWPfDdrPhyDramTwpre = 0x00D48490,
- HWPfDdrPhyDramTrfc = 0x00D484A0,
- HWPfDdrPhyDramTrwtp = 0x00D484B0,
HWPfDdrPhyMr01Dimm = 0x00D484C0,
HWPfDdrPhyMr01DimmDbi = 0x00D484D0,
HWPfDdrPhyMr23Dimm = 0x00D484E0,
HWPfDdrPhyMr45Dimm = 0x00D484F0,
HWPfDdrPhyMr67Dimm = 0x00D48500,
HWPfDdrPhyWrlvlWwRdlvlRr = 0x00D48510,
- HWPfDdrPhyOdtEn = 0x00D48520,
- HWPfDdrPhyFastTrng = 0x00D48530,
- HWPfDdrPhyDynTrngGap = 0x00D48540,
- HWPfDdrPhyDynRcalGap = 0x00D48550,
HWPfDdrPhyIdletimeout = 0x00D48560,
- HWPfDdrPhyRstCkeGap = 0x00D48570,
- HWPfDdrPhyCkeMrsGap = 0x00D48580,
- HWPfDdrPhyMemVrefMidVal = 0x00D48590,
- HWPfDdrPhyVrefStep = 0x00D485A0,
- HWPfDdrPhyVrefThreshold = 0x00D485B0,
- HWPfDdrPhyPhyVrefMidVal = 0x00D485C0,
HWPfDdrPhyDqsCountMax = 0x00D485D0,
HWPfDdrPhyDqsCountNum = 0x00D485E0,
- HWPfDdrPhyDramRow = 0x00D485F0,
- HWPfDdrPhyDramCol = 0x00D48600,
- HWPfDdrPhyDramBgBa = 0x00D48610,
- HWPfDdrPhyDynamicUpdreqrel = 0x00D48620,
- HWPfDdrPhyVrefLimits = 0x00D48630,
- HWPfDdrPhyIdtmTcStatus = 0x00D6C020,
HWPfDdrPhyIdtmFwVersion = 0x00D6C410,
- HWPfDdrPhyRdlvlGateInitDelay = 0x00D70000,
- HWPfDdrPhyRdenSmplabc = 0x00D70008,
- HWPfDdrPhyVrefNibble0 = 0x00D7000C,
- HWPfDdrPhyVrefNibble1 = 0x00D70010,
- HWPfDdrPhyRdlvlGateDqsSmpl0 = 0x00D70014,
- HWPfDdrPhyRdlvlGateDqsSmpl1 = 0x00D70018,
- HWPfDdrPhyRdlvlGateDqsSmpl2 = 0x00D7001C,
HWPfDdrPhyDqsCount = 0x00D70020,
- HWPfDdrPhyWrlvlRdlvlGateStatus = 0x00D70024,
- HWPfDdrPhyErrorFlags = 0x00D70028,
- HWPfDdrPhyPowerDown = 0x00D70030,
- HWPfDdrPhyPrbsSeedByte0 = 0x00D70034,
- HWPfDdrPhyPrbsSeedByte1 = 0x00D70038,
- HWPfDdrPhyPcompDq = 0x00D70040,
- HWPfDdrPhyNcompDq = 0x00D70044,
- HWPfDdrPhyPcompDqs = 0x00D70048,
- HWPfDdrPhyNcompDqs = 0x00D7004C,
- HWPfDdrPhyPcompCmd = 0x00D70050,
- HWPfDdrPhyNcompCmd = 0x00D70054,
- HWPfDdrPhyPcompCk = 0x00D70058,
- HWPfDdrPhyNcompCk = 0x00D7005C,
- HWPfDdrPhyRcalOdtDq = 0x00D70060,
- HWPfDdrPhyRcalOdtDqs = 0x00D70064,
- HWPfDdrPhyRcalMask1 = 0x00D70068,
- HWPfDdrPhyRcalMask2 = 0x00D7006C,
- HWPfDdrPhyRcalCtrl = 0x00D70070,
- HWPfDdrPhyRcalCnt = 0x00D70074,
- HWPfDdrPhyRcalOverride = 0x00D70078,
- HWPfDdrPhyRcalGateen = 0x00D7007C,
- HWPfDdrPhyCtrl = 0x00D70080,
- HWPfDdrPhyWrlvlAlg = 0x00D70084,
- HWPfDdrPhyRcalVreftTxcmdOdt = 0x00D70088,
- HWPfDdrPhyRdlvlGateParam = 0x00D7008C,
- HWPfDdrPhyRdlvlGateParam2 = 0x00D70090,
- HWPfDdrPhyRcalVreftTxdata = 0x00D70094,
- HWPfDdrPhyCmdIntDelay = 0x00D700A4,
- HWPfDdrPhyAlertN = 0x00D700A8,
- HWPfDdrPhyTrngReqWpre2tck = 0x00D700AC,
- HWPfDdrPhyCmdPhaseSel = 0x00D700B4,
- HWPfDdrPhyCmdDcdl = 0x00D700B8,
- HWPfDdrPhyCkDcdl = 0x00D700BC,
- HWPfDdrPhySwTrngCtrl1 = 0x00D700C0,
- HWPfDdrPhySwTrngCtrl2 = 0x00D700C4,
- HWPfDdrPhyRcalPcompRden = 0x00D700C8,
- HWPfDdrPhyRcalNcompRden = 0x00D700CC,
- HWPfDdrPhyRcalCompen = 0x00D700D0,
- HWPfDdrPhySwTrngRdqs = 0x00D700D4,
- HWPfDdrPhySwTrngWdqs = 0x00D700D8,
- HWPfDdrPhySwTrngRdena = 0x00D700DC,
- HWPfDdrPhySwTrngRdenb = 0x00D700E0,
- HWPfDdrPhySwTrngRdenc = 0x00D700E4,
- HWPfDdrPhySwTrngWdq = 0x00D700E8,
- HWPfDdrPhySwTrngRdq = 0x00D700EC,
- HWPfDdrPhyPcfgHmValue = 0x00D700F0,
- HWPfDdrPhyPcfgTimerValue = 0x00D700F4,
- HWPfDdrPhyPcfgSoftwareTraining = 0x00D700F8,
- HWPfDdrPhyPcfgMcStatus = 0x00D700FC,
- HWPfDdrPhyWrlvlPhRank0 = 0x00D70100,
- HWPfDdrPhyRdenPhRank0 = 0x00D70104,
- HWPfDdrPhyRdenIntRank0 = 0x00D70108,
- HWPfDdrPhyRdqsDcdlRank0 = 0x00D7010C,
- HWPfDdrPhyRdqsShadowDcdlRank0 = 0x00D70110,
- HWPfDdrPhyWdqsDcdlRank0 = 0x00D70114,
- HWPfDdrPhyWdmDcdlShadowRank0 = 0x00D70118,
- HWPfDdrPhyWdmDcdlRank0 = 0x00D7011C,
- HWPfDdrPhyDbiDcdlRank0 = 0x00D70120,
- HWPfDdrPhyRdenDcdlaRank0 = 0x00D70124,
- HWPfDdrPhyDbiDcdlShadowRank0 = 0x00D70128,
- HWPfDdrPhyRdenDcdlbRank0 = 0x00D7012C,
- HWPfDdrPhyWdqsShadowDcdlRank0 = 0x00D70130,
- HWPfDdrPhyRdenDcdlcRank0 = 0x00D70134,
- HWPfDdrPhyRdenShadowDcdlaRank0 = 0x00D70138,
- HWPfDdrPhyWrlvlIntRank0 = 0x00D7013C,
- HWPfDdrPhyRdqDcdlBit0Rank0 = 0x00D70200,
- HWPfDdrPhyRdqDcdlShadowBit0Rank0 = 0x00D70204,
- HWPfDdrPhyWdqDcdlBit0Rank0 = 0x00D70208,
- HWPfDdrPhyWdqDcdlShadowBit0Rank0 = 0x00D7020C,
- HWPfDdrPhyRdqDcdlBit1Rank0 = 0x00D70240,
- HWPfDdrPhyRdqDcdlShadowBit1Rank0 = 0x00D70244,
- HWPfDdrPhyWdqDcdlBit1Rank0 = 0x00D70248,
- HWPfDdrPhyWdqDcdlShadowBit1Rank0 = 0x00D7024C,
- HWPfDdrPhyRdqDcdlBit2Rank0 = 0x00D70280,
- HWPfDdrPhyRdqDcdlShadowBit2Rank0 = 0x00D70284,
- HWPfDdrPhyWdqDcdlBit2Rank0 = 0x00D70288,
- HWPfDdrPhyWdqDcdlShadowBit2Rank0 = 0x00D7028C,
- HWPfDdrPhyRdqDcdlBit3Rank0 = 0x00D702C0,
- HWPfDdrPhyRdqDcdlShadowBit3Rank0 = 0x00D702C4,
- HWPfDdrPhyWdqDcdlBit3Rank0 = 0x00D702C8,
- HWPfDdrPhyWdqDcdlShadowBit3Rank0 = 0x00D702CC,
- HWPfDdrPhyRdqDcdlBit4Rank0 = 0x00D70300,
- HWPfDdrPhyRdqDcdlShadowBit4Rank0 = 0x00D70304,
- HWPfDdrPhyWdqDcdlBit4Rank0 = 0x00D70308,
- HWPfDdrPhyWdqDcdlShadowBit4Rank0 = 0x00D7030C,
- HWPfDdrPhyRdqDcdlBit5Rank0 = 0x00D70340,
- HWPfDdrPhyRdqDcdlShadowBit5Rank0 = 0x00D70344,
- HWPfDdrPhyWdqDcdlBit5Rank0 = 0x00D70348,
- HWPfDdrPhyWdqDcdlShadowBit5Rank0 = 0x00D7034C,
- HWPfDdrPhyRdqDcdlBit6Rank0 = 0x00D70380,
- HWPfDdrPhyRdqDcdlShadowBit6Rank0 = 0x00D70384,
- HWPfDdrPhyWdqDcdlBit6Rank0 = 0x00D70388,
- HWPfDdrPhyWdqDcdlShadowBit6Rank0 = 0x00D7038C,
- HWPfDdrPhyRdqDcdlBit7Rank0 = 0x00D703C0,
- HWPfDdrPhyRdqDcdlShadowBit7Rank0 = 0x00D703C4,
- HWPfDdrPhyWdqDcdlBit7Rank0 = 0x00D703C8,
- HWPfDdrPhyWdqDcdlShadowBit7Rank0 = 0x00D703CC,
- HWPfDdrPhyIdtmStatus = 0x00D740D0,
- HWPfDdrPhyIdtmError = 0x00D74110,
- HWPfDdrPhyIdtmDebug = 0x00D74120,
- HWPfDdrPhyIdtmDebugInt = 0x00D74130,
- HwPfPcieLnAsicCfgovr = 0x00D80000,
- HwPfPcieLnAclkmixer = 0x00D80004,
- HwPfPcieLnTxrampfreq = 0x00D80008,
- HwPfPcieLnLanetest = 0x00D8000C,
- HwPfPcieLnDcctrl = 0x00D80010,
- HwPfPcieLnDccmeas = 0x00D80014,
- HwPfPcieLnDccovrAclk = 0x00D80018,
- HwPfPcieLnDccovrTxa = 0x00D8001C,
- HwPfPcieLnDccovrTxk = 0x00D80020,
- HwPfPcieLnDccovrDclk = 0x00D80024,
- HwPfPcieLnDccovrEclk = 0x00D80028,
- HwPfPcieLnDcctrimAclk = 0x00D8002C,
- HwPfPcieLnDcctrimTx = 0x00D80030,
- HwPfPcieLnDcctrimDclk = 0x00D80034,
- HwPfPcieLnDcctrimEclk = 0x00D80038,
- HwPfPcieLnQuadCtrl = 0x00D8003C,
- HwPfPcieLnQuadCorrIndex = 0x00D80040,
- HwPfPcieLnQuadCorrStatus = 0x00D80044,
- HwPfPcieLnAsicRxovr1 = 0x00D80048,
- HwPfPcieLnAsicRxovr2 = 0x00D8004C,
- HwPfPcieLnAsicEqinfovr = 0x00D80050,
- HwPfPcieLnRxcsr = 0x00D80054,
- HwPfPcieLnRxfectrl = 0x00D80058,
- HwPfPcieLnRxtest = 0x00D8005C,
- HwPfPcieLnEscount = 0x00D80060,
- HwPfPcieLnCdrctrl = 0x00D80064,
- HwPfPcieLnCdrctrl2 = 0x00D80068,
- HwPfPcieLnCdrcfg0Ctrl0 = 0x00D8006C,
- HwPfPcieLnCdrcfg0Ctrl1 = 0x00D80070,
- HwPfPcieLnCdrcfg0Ctrl2 = 0x00D80074,
- HwPfPcieLnCdrcfg1Ctrl0 = 0x00D80078,
- HwPfPcieLnCdrcfg1Ctrl1 = 0x00D8007C,
- HwPfPcieLnCdrcfg1Ctrl2 = 0x00D80080,
- HwPfPcieLnCdrcfg2Ctrl0 = 0x00D80084,
- HwPfPcieLnCdrcfg2Ctrl1 = 0x00D80088,
- HwPfPcieLnCdrcfg2Ctrl2 = 0x00D8008C,
- HwPfPcieLnCdrcfg3Ctrl0 = 0x00D80090,
- HwPfPcieLnCdrcfg3Ctrl1 = 0x00D80094,
- HwPfPcieLnCdrcfg3Ctrl2 = 0x00D80098,
- HwPfPcieLnCdrphase = 0x00D8009C,
- HwPfPcieLnCdrfreq = 0x00D800A0,
- HwPfPcieLnCdrstatusPhase = 0x00D800A4,
- HwPfPcieLnCdrstatusFreq = 0x00D800A8,
- HwPfPcieLnCdroffset = 0x00D800AC,
- HwPfPcieLnRxvosctl = 0x00D800B0,
- HwPfPcieLnRxvosctl2 = 0x00D800B4,
- HwPfPcieLnRxlosctl = 0x00D800B8,
- HwPfPcieLnRxlos = 0x00D800BC,
- HwPfPcieLnRxlosvval = 0x00D800C0,
- HwPfPcieLnRxvosd0 = 0x00D800C4,
- HwPfPcieLnRxvosd1 = 0x00D800C8,
- HwPfPcieLnRxvosep0 = 0x00D800CC,
- HwPfPcieLnRxvosep1 = 0x00D800D0,
- HwPfPcieLnRxvosen0 = 0x00D800D4,
- HwPfPcieLnRxvosen1 = 0x00D800D8,
- HwPfPcieLnRxvosafe = 0x00D800DC,
- HwPfPcieLnRxvosa0 = 0x00D800E0,
- HwPfPcieLnRxvosa0Out = 0x00D800E4,
- HwPfPcieLnRxvosa1 = 0x00D800E8,
- HwPfPcieLnRxvosa1Out = 0x00D800EC,
- HwPfPcieLnRxmisc = 0x00D800F0,
- HwPfPcieLnRxbeacon = 0x00D800F4,
- HwPfPcieLnRxdssout = 0x00D800F8,
- HwPfPcieLnRxdssout2 = 0x00D800FC,
- HwPfPcieLnAlphapctrl = 0x00D80100,
- HwPfPcieLnAlphanctrl = 0x00D80104,
HwPfPcieLnAdaptctrl = 0x00D80108,
- HwPfPcieLnAdaptctrl1 = 0x00D8010C,
- HwPfPcieLnAdaptstatus = 0x00D80110,
- HwPfPcieLnAdaptvga1 = 0x00D80114,
- HwPfPcieLnAdaptvga2 = 0x00D80118,
- HwPfPcieLnAdaptvga3 = 0x00D8011C,
- HwPfPcieLnAdaptvga4 = 0x00D80120,
- HwPfPcieLnAdaptboost1 = 0x00D80124,
- HwPfPcieLnAdaptboost2 = 0x00D80128,
- HwPfPcieLnAdaptboost3 = 0x00D8012C,
- HwPfPcieLnAdaptboost4 = 0x00D80130,
- HwPfPcieLnAdaptsslms1 = 0x00D80134,
- HwPfPcieLnAdaptsslms2 = 0x00D80138,
- HwPfPcieLnAdaptvgaStatus = 0x00D8013C,
- HwPfPcieLnAdaptboostStatus = 0x00D80140,
- HwPfPcieLnAdaptsslmsStatus1 = 0x00D80144,
- HwPfPcieLnAdaptsslmsStatus2 = 0x00D80148,
- HwPfPcieLnAfectrl1 = 0x00D8014C,
- HwPfPcieLnAfectrl2 = 0x00D80150,
- HwPfPcieLnAfectrl3 = 0x00D80154,
- HwPfPcieLnAfedefault1 = 0x00D80158,
- HwPfPcieLnAfedefault2 = 0x00D8015C,
- HwPfPcieLnDfectrl1 = 0x00D80160,
- HwPfPcieLnDfectrl2 = 0x00D80164,
- HwPfPcieLnDfectrl3 = 0x00D80168,
- HwPfPcieLnDfectrl4 = 0x00D8016C,
- HwPfPcieLnDfectrl5 = 0x00D80170,
- HwPfPcieLnDfectrl6 = 0x00D80174,
- HwPfPcieLnAfestatus1 = 0x00D80178,
- HwPfPcieLnAfestatus2 = 0x00D8017C,
- HwPfPcieLnDfestatus1 = 0x00D80180,
- HwPfPcieLnDfestatus2 = 0x00D80184,
- HwPfPcieLnDfestatus3 = 0x00D80188,
- HwPfPcieLnDfestatus4 = 0x00D8018C,
- HwPfPcieLnDfestatus5 = 0x00D80190,
- HwPfPcieLnAlphastatus = 0x00D80194,
- HwPfPcieLnFomctrl1 = 0x00D80198,
- HwPfPcieLnFomctrl2 = 0x00D8019C,
- HwPfPcieLnFomctrl3 = 0x00D801A0,
- HwPfPcieLnAclkcalStatus = 0x00D801A4,
- HwPfPcieLnOffscorrStatus = 0x00D801A8,
- HwPfPcieLnEyewidthStatus = 0x00D801AC,
- HwPfPcieLnEyeheightStatus = 0x00D801B0,
- HwPfPcieLnAsicTxovr1 = 0x00D801B4,
- HwPfPcieLnAsicTxovr2 = 0x00D801B8,
- HwPfPcieLnAsicTxovr3 = 0x00D801BC,
- HwPfPcieLnTxbiasadjOvr = 0x00D801C0,
- HwPfPcieLnTxcsr = 0x00D801C4,
- HwPfPcieLnTxtest = 0x00D801C8,
- HwPfPcieLnTxtestword = 0x00D801CC,
- HwPfPcieLnTxtestwordHigh = 0x00D801D0,
- HwPfPcieLnTxdrive = 0x00D801D4,
- HwPfPcieLnMtcsLn = 0x00D801D8,
- HwPfPcieLnStatsumLn = 0x00D801DC,
- HwPfPcieLnRcbusScratch = 0x00D801E0,
- HwPfPcieLnRcbusMinorrev = 0x00D801F0,
- HwPfPcieLnRcbusMajorrev = 0x00D801F4,
- HwPfPcieLnRcbusBlocktype = 0x00D801F8,
- HwPfPcieSupPllcsr = 0x00D80800,
- HwPfPcieSupPlldiv = 0x00D80804,
- HwPfPcieSupPllcal = 0x00D80808,
- HwPfPcieSupPllcalsts = 0x00D8080C,
- HwPfPcieSupPllmeas = 0x00D80810,
- HwPfPcieSupPlldactrim = 0x00D80814,
- HwPfPcieSupPllbiastrim = 0x00D80818,
- HwPfPcieSupPllbwtrim = 0x00D8081C,
- HwPfPcieSupPllcaldly = 0x00D80820,
- HwPfPcieSupRefclkonpclkctrl = 0x00D80824,
- HwPfPcieSupPclkdelay = 0x00D80828,
- HwPfPcieSupPhyconfig = 0x00D8082C,
- HwPfPcieSupRcalIntf = 0x00D80830,
- HwPfPcieSupAuxcsr = 0x00D80834,
- HwPfPcieSupVref = 0x00D80838,
- HwPfPcieSupLinkmode = 0x00D8083C,
- HwPfPcieSupRrefcalctl = 0x00D80840,
- HwPfPcieSupRrefcal = 0x00D80844,
- HwPfPcieSupRrefcaldly = 0x00D80848,
- HwPfPcieSupTximpcalctl = 0x00D8084C,
- HwPfPcieSupTximpcal = 0x00D80850,
- HwPfPcieSupTximpoffset = 0x00D80854,
- HwPfPcieSupTximpcaldly = 0x00D80858,
- HwPfPcieSupRximpcalctl = 0x00D8085C,
- HwPfPcieSupRximpcal = 0x00D80860,
- HwPfPcieSupRximpoffset = 0x00D80864,
- HwPfPcieSupRximpcaldly = 0x00D80868,
- HwPfPcieSupFence = 0x00D8086C,
- HwPfPcieSupMtcs = 0x00D80870,
- HwPfPcieSupStatsum = 0x00D809B8,
- HwPfPciePcsDpStatus0 = 0x00D81000,
- HwPfPciePcsDpControl0 = 0x00D81004,
- HwPfPciePcsPmaStatusLane0 = 0x00D81008,
- HwPfPciePcsPipeStatusLane0 = 0x00D8100C,
- HwPfPciePcsTxdeemph0Lane0 = 0x00D81010,
- HwPfPciePcsTxdeemph1Lane0 = 0x00D81014,
- HwPfPciePcsInternalStatusLane0 = 0x00D81018,
- HwPfPciePcsDpStatus1 = 0x00D8101C,
- HwPfPciePcsDpControl1 = 0x00D81020,
- HwPfPciePcsPmaStatusLane1 = 0x00D81024,
- HwPfPciePcsPipeStatusLane1 = 0x00D81028,
- HwPfPciePcsTxdeemph0Lane1 = 0x00D8102C,
- HwPfPciePcsTxdeemph1Lane1 = 0x00D81030,
- HwPfPciePcsInternalStatusLane1 = 0x00D81034,
- HwPfPciePcsDpStatus2 = 0x00D81038,
- HwPfPciePcsDpControl2 = 0x00D8103C,
- HwPfPciePcsPmaStatusLane2 = 0x00D81040,
- HwPfPciePcsPipeStatusLane2 = 0x00D81044,
- HwPfPciePcsTxdeemph0Lane2 = 0x00D81048,
- HwPfPciePcsTxdeemph1Lane2 = 0x00D8104C,
- HwPfPciePcsInternalStatusLane2 = 0x00D81050,
- HwPfPciePcsDpStatus3 = 0x00D81054,
- HwPfPciePcsDpControl3 = 0x00D81058,
- HwPfPciePcsPmaStatusLane3 = 0x00D8105C,
- HwPfPciePcsPipeStatusLane3 = 0x00D81060,
- HwPfPciePcsTxdeemph0Lane3 = 0x00D81064,
- HwPfPciePcsTxdeemph1Lane3 = 0x00D81068,
- HwPfPciePcsInternalStatusLane3 = 0x00D8106C,
- HwPfPciePcsEbStatus0 = 0x00D81070,
- HwPfPciePcsEbStatus1 = 0x00D81074,
- HwPfPciePcsEbStatus2 = 0x00D81078,
- HwPfPciePcsEbStatus3 = 0x00D8107C,
- HwPfPciePcsPllSettingPcieG1 = 0x00D81088,
- HwPfPciePcsPllSettingPcieG2 = 0x00D8108C,
- HwPfPciePcsPllSettingPcieG3 = 0x00D81090,
- HwPfPciePcsControl = 0x00D81094,
HwPfPciePcsEqControl = 0x00D81098,
- HwPfPciePcsEqTimer = 0x00D8109C,
- HwPfPciePcsEqErrStatus = 0x00D810A0,
- HwPfPciePcsEqErrCount = 0x00D810A4,
- HwPfPciePcsStatus = 0x00D810A8,
- HwPfPciePcsMiscRegister = 0x00D810AC,
- HwPfPciePcsObsControl = 0x00D810B0,
- HwPfPciePcsPrbsCount0 = 0x00D81200,
- HwPfPciePcsBistControl0 = 0x00D81204,
- HwPfPciePcsBistStaticWord00 = 0x00D81208,
- HwPfPciePcsBistStaticWord10 = 0x00D8120C,
- HwPfPciePcsBistStaticWord20 = 0x00D81210,
- HwPfPciePcsBistStaticWord30 = 0x00D81214,
- HwPfPciePcsPrbsCount1 = 0x00D81220,
- HwPfPciePcsBistControl1 = 0x00D81224,
- HwPfPciePcsBistStaticWord01 = 0x00D81228,
- HwPfPciePcsBistStaticWord11 = 0x00D8122C,
- HwPfPciePcsBistStaticWord21 = 0x00D81230,
- HwPfPciePcsBistStaticWord31 = 0x00D81234,
- HwPfPciePcsPrbsCount2 = 0x00D81240,
- HwPfPciePcsBistControl2 = 0x00D81244,
- HwPfPciePcsBistStaticWord02 = 0x00D81248,
- HwPfPciePcsBistStaticWord12 = 0x00D8124C,
- HwPfPciePcsBistStaticWord22 = 0x00D81250,
- HwPfPciePcsBistStaticWord32 = 0x00D81254,
- HwPfPciePcsPrbsCount3 = 0x00D81260,
- HwPfPciePcsBistControl3 = 0x00D81264,
- HwPfPciePcsBistStaticWord03 = 0x00D81268,
- HwPfPciePcsBistStaticWord13 = 0x00D8126C,
- HwPfPciePcsBistStaticWord23 = 0x00D81270,
- HwPfPciePcsBistStaticWord33 = 0x00D81274,
- HwPfPcieGpexLtssmStateCntrl = 0x00D90400,
- HwPfPcieGpexLtssmStateStatus = 0x00D90404,
- HwPfPcieGpexSkipFreqTimer = 0x00D90408,
- HwPfPcieGpexLaneSelect = 0x00D9040C,
- HwPfPcieGpexLaneDeskew = 0x00D90410,
- HwPfPcieGpexRxErrorStatus = 0x00D90414,
- HwPfPcieGpexLaneNumControl = 0x00D90418,
- HwPfPcieGpexNFstControl = 0x00D9041C,
- HwPfPcieGpexLinkStatus = 0x00D90420,
- HwPfPcieGpexAckReplayTimeout = 0x00D90438,
- HwPfPcieGpexSeqNumberStatus = 0x00D9043C,
- HwPfPcieGpexCoreClkRatio = 0x00D90440,
- HwPfPcieGpexDllTholdControl = 0x00D90448,
- HwPfPcieGpexPmTimer = 0x00D90450,
- HwPfPcieGpexPmeTimeout = 0x00D90454,
- HwPfPcieGpexAspmL1Timer = 0x00D90458,
- HwPfPcieGpexAspmReqTimer = 0x00D9045C,
- HwPfPcieGpexAspmL1Dis = 0x00D90460,
- HwPfPcieGpexAdvisoryErrorControl = 0x00D90468,
- HwPfPcieGpexId = 0x00D90470,
- HwPfPcieGpexClasscode = 0x00D90474,
- HwPfPcieGpexSubsystemId = 0x00D90478,
- HwPfPcieGpexDeviceCapabilities = 0x00D9047C,
- HwPfPcieGpexLinkCapabilities = 0x00D90480,
- HwPfPcieGpexFunctionNumber = 0x00D90484,
- HwPfPcieGpexPmCapabilities = 0x00D90488,
- HwPfPcieGpexFunctionSelect = 0x00D9048C,
- HwPfPcieGpexErrorCounter = 0x00D904AC,
- HwPfPcieGpexConfigReady = 0x00D904B0,
- HwPfPcieGpexFcUpdateTimeout = 0x00D904B8,
- HwPfPcieGpexFcUpdateTimer = 0x00D904BC,
- HwPfPcieGpexVcBufferLoad = 0x00D904C8,
- HwPfPcieGpexVcBufferSizeThold = 0x00D904CC,
- HwPfPcieGpexVcBufferSelect = 0x00D904D0,
- HwPfPcieGpexBarEnable = 0x00D904D4,
- HwPfPcieGpexBarDwordLower = 0x00D904D8,
- HwPfPcieGpexBarDwordUpper = 0x00D904DC,
- HwPfPcieGpexBarSelect = 0x00D904E0,
- HwPfPcieGpexCreditCounterSelect = 0x00D904E4,
- HwPfPcieGpexCreditCounterStatus = 0x00D904E8,
- HwPfPcieGpexTlpHeaderSelect = 0x00D904EC,
- HwPfPcieGpexTlpHeaderDword0 = 0x00D904F0,
- HwPfPcieGpexTlpHeaderDword1 = 0x00D904F4,
- HwPfPcieGpexTlpHeaderDword2 = 0x00D904F8,
- HwPfPcieGpexTlpHeaderDword3 = 0x00D904FC,
- HwPfPcieGpexRelaxOrderControl = 0x00D90500,
- HwPfPcieGpexBarPrefetch = 0x00D90504,
- HwPfPcieGpexFcCheckControl = 0x00D90508,
- HwPfPcieGpexFcUpdateTimerTraffic = 0x00D90518,
- HwPfPcieGpexPhyControl0 = 0x00D9053C,
- HwPfPcieGpexPhyControl1 = 0x00D90544,
- HwPfPcieGpexPhyControl2 = 0x00D9054C,
- HwPfPcieGpexUserControl0 = 0x00D9055C,
- HwPfPcieGpexUncorrErrorStatus = 0x00D905F0,
- HwPfPcieGpexRxCplError = 0x00D90620,
- HwPfPcieGpexRxCplErrorDword0 = 0x00D90624,
- HwPfPcieGpexRxCplErrorDword1 = 0x00D90628,
- HwPfPcieGpexRxCplErrorDword2 = 0x00D9062C,
- HwPfPcieGpexPabSwResetEn = 0x00D90630,
- HwPfPcieGpexGen3Control0 = 0x00D90634,
- HwPfPcieGpexGen3Control1 = 0x00D90638,
- HwPfPcieGpexGen3Control2 = 0x00D9063C,
- HwPfPcieGpexGen2ControlCsr = 0x00D90640,
- HwPfPcieGpexTotalVfInitialVf0 = 0x00D90644,
- HwPfPcieGpexTotalVfInitialVf1 = 0x00D90648,
- HwPfPcieGpexSriovLinkDevId0 = 0x00D90684,
- HwPfPcieGpexSriovLinkDevId1 = 0x00D90688,
- HwPfPcieGpexSriovPageSize0 = 0x00D906C4,
- HwPfPcieGpexSriovPageSize1 = 0x00D906C8,
- HwPfPcieGpexIdVersion = 0x00D906FC,
- HwPfPcieGpexSriovVfOffsetStride0 = 0x00D90704,
- HwPfPcieGpexSriovVfOffsetStride1 = 0x00D90708,
- HwPfPcieGpexGen3DeskewControl = 0x00D907B4,
- HwPfPcieGpexGen3EqControl = 0x00D907B8,
- HwPfPcieGpexBridgeVersion = 0x00D90800,
- HwPfPcieGpexBridgeCapability = 0x00D90804,
HwPfPcieGpexBridgeControl = 0x00D90808,
- HwPfPcieGpexBridgeStatus = 0x00D9080C,
- HwPfPcieGpexEngineActivityStatus = 0x00D9081C,
- HwPfPcieGpexEngineResetControl = 0x00D90820,
HwPfPcieGpexAxiPioControl = 0x00D90840,
- HwPfPcieGpexAxiPioStatus = 0x00D90844,
- HwPfPcieGpexAmbaSlaveCmdStatus = 0x00D90848,
- HwPfPcieGpexPexPioControl = 0x00D908C0,
- HwPfPcieGpexPexPioStatus = 0x00D908C4,
- HwPfPcieGpexAmbaMasterStatus = 0x00D908C8,
- HwPfPcieGpexCsrSlaveCmdStatus = 0x00D90920,
- HwPfPcieGpexMailboxAxiControl = 0x00D90A50,
- HwPfPcieGpexMailboxAxiData = 0x00D90A54,
- HwPfPcieGpexMailboxPexControl = 0x00D90A90,
- HwPfPcieGpexMailboxPexData = 0x00D90A94,
- HwPfPcieGpexPexInterruptEnable = 0x00D90AD0,
- HwPfPcieGpexPexInterruptStatus = 0x00D90AD4,
- HwPfPcieGpexPexInterruptAxiPioVector = 0x00D90AD8,
- HwPfPcieGpexPexInterruptPexPioVector = 0x00D90AE0,
- HwPfPcieGpexPexInterruptMiscVector = 0x00D90AF8,
- HwPfPcieGpexAmbaInterruptPioEnable = 0x00D90B00,
- HwPfPcieGpexAmbaInterruptMiscEnable = 0x00D90B0C,
- HwPfPcieGpexAmbaInterruptPioStatus = 0x00D90B10,
- HwPfPcieGpexAmbaInterruptMiscStatus = 0x00D90B1C,
- HwPfPcieGpexPexPmControl = 0x00D90B80,
- HwPfPcieGpexSlotMisc = 0x00D90B88,
- HwPfPcieGpexAxiAddrMappingControl = 0x00D90BA0,
- HwPfPcieGpexAxiAddrMappingWindowAxiBase = 0x00D90BA4,
- HwPfPcieGpexAxiAddrMappingWindowPexBaseLow = 0x00D90BA8,
HwPfPcieGpexAxiAddrMappingWindowPexBaseHigh = 0x00D90BAC,
- HwPfPcieGpexPexBarAddrFunc0Bar0 = 0x00D91BA0,
- HwPfPcieGpexPexBarAddrFunc0Bar1 = 0x00D91BA4,
- HwPfPcieGpexAxiAddrMappingPcieHdrParam = 0x00D95BA0,
- HwPfPcieGpexExtAxiAddrMappingAxiBase = 0x00D980A0,
- HwPfPcieGpexPexExtBarAddrFunc0Bar0 = 0x00D984A0,
- HwPfPcieGpexPexExtBarAddrFunc0Bar1 = 0x00D984A4,
- HwPfPcieGpexAmbaInterruptFlrEnable = 0x00D9B960,
- HwPfPcieGpexAmbaInterruptFlrStatus = 0x00D9B9A0,
- HwPfPcieGpexExtAxiAddrMappingSize = 0x00D9BAF0,
- HwPfPcieGpexPexPioAwcacheControl = 0x00D9C300,
- HwPfPcieGpexPexPioArcacheControl = 0x00D9C304,
- HwPfPcieGpexPabObSizeControlVc0 = 0x00D9C310
};
/* TIP PF Interrupt numbers */
--
2.37.1
^ permalink raw reply [flat|nested] 28+ messages in thread* [PATCH v6 02/14] baseband/acc100: refactor to segregate common code
2022-09-24 0:50 From: Nicolas Chautru <nicolas.chautru@intel.com> Nicolas Chautru
2022-09-24 0:50 ` [PATCH v6 01/14] baseband/acc100: remove unused registers Nicolas Chautru
@ 2022-09-24 0:50 ` Nicolas Chautru
2022-09-24 0:50 ` [PATCH v6 03/14] baseband/acc: rename directory from acc100 to acc Nicolas Chautru
` (11 subsequent siblings)
13 siblings, 0 replies; 28+ messages in thread
From: Nicolas Chautru @ 2022-09-24 0:50 UTC (permalink / raw)
To: dev, thomas
Cc: maxime.coquelin, trix, mdr, bruce.richardson, hemant.agrawal,
david.marchand, stephen, hernan.vargas, Nic Chautru
From: Nic Chautru <nicolas.chautru@intel.com>
Refactoring all shareable common code to be used by future PMD
(including ACC200 in this patchset as well as taking into account
following PMDs in roadmap) by gathering such structures or inline methods.
No functionality change.
Signed-off-by: Nic Chautru <nicolas.chautru@intel.com>
Acked-by: Bruce Richardson <bruce.richardson@intel.com>
Reviewed-by: Maxime Coquelin <maxime.coquelin@redhat.com>
---
app/test-bbdev/test_bbdev_perf.c | 6 +-
drivers/baseband/acc100/acc100_pmd.h | 449 +----
drivers/baseband/acc100/acc101_pmd.h | 10 -
drivers/baseband/acc100/acc_common.h | 1303 +++++++++++++
drivers/baseband/acc100/rte_acc100_cfg.h | 70 +-
drivers/baseband/acc100/rte_acc100_pmd.c | 1773 ++++++------------
drivers/baseband/acc100/rte_acc_common_cfg.h | 101 +
7 files changed, 1981 insertions(+), 1731 deletions(-)
create mode 100644 drivers/baseband/acc100/acc_common.h
create mode 100644 drivers/baseband/acc100/rte_acc_common_cfg.h
diff --git a/app/test-bbdev/test_bbdev_perf.c b/app/test-bbdev/test_bbdev_perf.c
index 5d07670ed3..af9ceca67b 100644
--- a/app/test-bbdev/test_bbdev_perf.c
+++ b/app/test-bbdev/test_bbdev_perf.c
@@ -708,18 +708,18 @@ add_bbdev_dev(uint8_t dev_id, struct rte_bbdev_info *info,
#ifdef RTE_BASEBAND_ACC100
if ((get_init_device() == true) &&
(!strcmp(info->drv.driver_name, ACC100PF_DRIVER_NAME))) {
- struct rte_acc100_conf conf;
+ struct rte_acc_conf conf;
unsigned int i;
printf("Configure ACC100/ACC101 FEC Driver %s with default values\n",
info->drv.driver_name);
/* clear default configuration before initialization */
- memset(&conf, 0, sizeof(struct rte_acc100_conf));
+ memset(&conf, 0, sizeof(struct rte_acc_conf));
/* Always set in PF mode for built-in configuration */
conf.pf_mode_en = true;
- for (i = 0; i < RTE_ACC100_NUM_VFS; ++i) {
+ for (i = 0; i < RTE_ACC_NUM_VFS; ++i) {
conf.arb_dl_4g[i].gbr_threshold1 = ACC100_QOS_GBR;
conf.arb_dl_4g[i].gbr_threshold1 = ACC100_QOS_GBR;
conf.arb_dl_4g[i].round_robin_weight = ACC100_QMGR_RR;
diff --git a/drivers/baseband/acc100/acc100_pmd.h b/drivers/baseband/acc100/acc100_pmd.h
index 0c9810ca56..b325948904 100644
--- a/drivers/baseband/acc100/acc100_pmd.h
+++ b/drivers/baseband/acc100/acc100_pmd.h
@@ -8,6 +8,7 @@
#include "acc100_pf_enum.h"
#include "acc100_vf_enum.h"
#include "rte_acc100_cfg.h"
+#include "acc_common.h"
/* Helper macro for logging */
#define rte_bbdev_log(level, fmt, ...) \
@@ -34,64 +35,18 @@
#define ACC100_PF_DEVICE_ID (0x0d5c)
#define ACC100_VF_DEVICE_ID (0x0d5d)
-/* Values used in filling in descriptors */
-#define ACC100_DMA_DESC_TYPE 2
-#define ACC100_DMA_CODE_BLK_MODE 0
-#define ACC100_DMA_BLKID_FCW 1
-#define ACC100_DMA_BLKID_IN 2
-#define ACC100_DMA_BLKID_OUT_ENC 1
-#define ACC100_DMA_BLKID_OUT_HARD 1
-#define ACC100_DMA_BLKID_OUT_SOFT 2
-#define ACC100_DMA_BLKID_OUT_HARQ 3
-#define ACC100_DMA_BLKID_IN_HARQ 3
-
-/* Values used in filling in decode FCWs */
-#define ACC100_FCW_TD_VER 1
-#define ACC100_FCW_TD_EXT_COLD_REG_EN 1
-#define ACC100_FCW_TD_AUTOMAP 0x0f
-#define ACC100_FCW_TD_RVIDX_0 2
-#define ACC100_FCW_TD_RVIDX_1 26
-#define ACC100_FCW_TD_RVIDX_2 50
-#define ACC100_FCW_TD_RVIDX_3 74
-
/* Values used in writing to the registers */
#define ACC100_REG_IRQ_EN_ALL 0x1FF83FF /* Enable all interrupts */
-/* ACC100 Specific Dimensioning */
-#define ACC100_SIZE_64MBYTE (64*1024*1024)
-/* Number of elements in an Info Ring */
-#define ACC100_INFO_RING_NUM_ENTRIES 1024
-/* Number of elements in HARQ layout memory */
-#define ACC100_HARQ_LAYOUT (64*1024*1024)
-/* Assume offset for HARQ in memory */
-#define ACC100_HARQ_OFFSET (32*1024)
-#define ACC100_HARQ_OFFSET_SHIFT 15
-#define ACC100_HARQ_OFFSET_MASK 0x7ffffff
-/* Mask used to calculate an index in an Info Ring array (not a byte offset) */
-#define ACC100_INFO_RING_MASK (ACC100_INFO_RING_NUM_ENTRIES-1)
/* Number of Virtual Functions ACC100 supports */
#define ACC100_NUM_VFS 16
#define ACC100_NUM_QGRPS 8
-#define ACC100_NUM_QGRPS_PER_WORD 8
#define ACC100_NUM_AQS 16
-#define MAX_ENQ_BATCH_SIZE 255
-/* All ACC100 Registers alignment are 32bits = 4B */
-#define ACC100_BYTES_IN_WORD 4
-#define ACC100_MAX_E_MBUF 64000
#define ACC100_GRP_ID_SHIFT 10 /* Queue Index Hierarchy */
#define ACC100_VF_ID_SHIFT 4 /* Queue Index Hierarchy */
-#define ACC100_VF_OFFSET_QOS 16 /* offset in Memory specific to QoS Mon */
-#define ACC100_TMPL_PRI_0 0x03020100
-#define ACC100_TMPL_PRI_1 0x07060504
-#define ACC100_TMPL_PRI_2 0x0b0a0908
-#define ACC100_TMPL_PRI_3 0x0f0e0d0c
-#define ACC100_QUEUE_ENABLE 0x80000000 /* Bit to mark Queue as Enabled */
#define ACC100_WORDS_IN_ARAM_SIZE (128 * 1024 / 4)
-#define ACC100_FDONE 0x80000000
-#define ACC100_SDONE 0x40000000
-#define ACC100_NUM_TMPL 32
/* Mapping of signals for the available engines */
#define ACC100_SIG_UL_5G 0
#define ACC100_SIG_UL_5G_LAST 7
@@ -102,50 +57,10 @@
#define ACC100_SIG_DL_4G 27
#define ACC100_SIG_DL_4G_LAST 31
#define ACC100_NUM_ACCS 5
-#define ACC100_ACCMAP_0 0
-#define ACC100_ACCMAP_1 2
-#define ACC100_ACCMAP_2 1
-#define ACC100_ACCMAP_3 3
-#define ACC100_ACCMAP_4 4
-#define ACC100_PF_VAL 2
-
-/* max number of iterations to allocate memory block for all rings */
-#define ACC100_SW_RING_MEM_ALLOC_ATTEMPTS 5
-#define ACC100_MAX_QUEUE_DEPTH 1024
-#define ACC100_DMA_MAX_NUM_POINTERS 14
-#define ACC100_DMA_MAX_NUM_POINTERS_IN 7
-#define ACC100_DMA_DESC_PADDING 8
-#define ACC100_FCW_PADDING 12
-#define ACC100_DESC_FCW_OFFSET 192
-#define ACC100_DESC_SIZE 256
-#define ACC100_DESC_OFFSET (ACC100_DESC_SIZE / 64)
-#define ACC100_FCW_TE_BLEN 32
-#define ACC100_FCW_TD_BLEN 24
-#define ACC100_FCW_LE_BLEN 32
-#define ACC100_FCW_LD_BLEN 36
-#define ACC100_5GUL_SIZE_0 16
-#define ACC100_5GUL_SIZE_1 40
-#define ACC100_5GUL_OFFSET_0 36
-#define ACC100_FCW_VER 2
-#define ACC100_MUX_5GDL_DESC 6
-#define ACC100_CMP_ENC_SIZE 20
-#define ACC100_CMP_DEC_SIZE 24
-#define ACC100_ENC_OFFSET (32)
-#define ACC100_DEC_OFFSET (80)
#define ACC100_EXT_MEM /* Default option with memory external to CPU */
#define ACC100_HARQ_OFFSET_THRESHOLD 1024
-/* Constants from K0 computation from 3GPP 38.212 Table 5.4.2.1-2 */
-#define ACC100_N_ZC_1 66 /* N = 66 Zc for BG 1 */
-#define ACC100_N_ZC_2 50 /* N = 50 Zc for BG 2 */
-#define ACC100_K0_1_1 17 /* K0 fraction numerator for rv 1 and BG 1 */
-#define ACC100_K0_1_2 13 /* K0 fraction numerator for rv 1 and BG 2 */
-#define ACC100_K0_2_1 33 /* K0 fraction numerator for rv 2 and BG 1 */
-#define ACC100_K0_2_2 25 /* K0 fraction numerator for rv 2 and BG 2 */
-#define ACC100_K0_3_1 56 /* K0 fraction numerator for rv 3 and BG 1 */
-#define ACC100_K0_3_2 43 /* K0 fraction numerator for rv 3 and BG 2 */
-
/* ACC100 Configuration */
#define ACC100_DDR_ECC_ENABLE
#define ACC100_CFG_DMA_ERROR 0x3D7
@@ -159,12 +74,10 @@
#define ACC100_PCIE_QUAD_OFFSET 0x2000
#define ACC100_PCS_EQ 0x6007
#define ACC100_ADAPT 0x8400
-#define ACC100_ENGINE_OFFSET 0x1000
#define ACC100_RESET_HI 0x20100
#define ACC100_RESET_LO 0x20000
#define ACC100_RESET_HARD 0x1FF
#define ACC100_ENGINES_MAX 9
-#define ACC100_LONG_WAIT 1000
#define ACC100_GPEX_AXIMAP_NUM 17
#define ACC100_CLOCK_GATING_EN 0x30000
#define ACC100_FABRIC_MODE 0xB
@@ -173,292 +86,8 @@
*/
#define ACC100_HARQ_DDR (512 * 1)
#define ACC100_PRQ_DDR_VER 0x10092020
-#define ACC100_MS_IN_US (1000)
#define ACC100_DDR_TRAINING_MAX (5000)
-/* ACC100 DMA Descriptor triplet */
-struct acc100_dma_triplet {
- uint64_t address;
- uint32_t blen:20,
- res0:4,
- last:1,
- dma_ext:1,
- res1:2,
- blkid:4;
-} __rte_packed;
-
-/* ACC100 DMA Response Descriptor */
-union acc100_dma_rsp_desc {
- uint32_t val;
- struct {
- uint32_t crc_status:1,
- synd_ok:1,
- dma_err:1,
- neg_stop:1,
- fcw_err:1,
- output_err:1,
- input_err:1,
- timestampEn:1,
- iterCountFrac:8,
- iter_cnt:8,
- rsrvd3:6,
- sdone:1,
- fdone:1;
- uint32_t add_info_0;
- uint32_t add_info_1;
- };
-};
-
-
-/* ACC100 Queue Manager Enqueue PCI Register */
-union acc100_enqueue_reg_fmt {
- uint32_t val;
- struct {
- uint32_t num_elem:8,
- addr_offset:3,
- rsrvd:1,
- req_elem_addr:20;
- };
-};
-
-/* FEC 4G Uplink Frame Control Word */
-struct __rte_packed acc100_fcw_td {
- uint8_t fcw_ver:4,
- num_maps:4; /* Unused */
- uint8_t filler:6, /* Unused */
- rsrvd0:1,
- bypass_sb_deint:1;
- uint16_t k_pos;
- uint16_t k_neg; /* Unused */
- uint8_t c_neg; /* Unused */
- uint8_t c; /* Unused */
- uint32_t ea; /* Unused */
- uint32_t eb; /* Unused */
- uint8_t cab; /* Unused */
- uint8_t k0_start_col; /* Unused */
- uint8_t rsrvd1;
- uint8_t code_block_mode:1, /* Unused */
- turbo_crc_type:1,
- rsrvd2:3,
- bypass_teq:1, /* Unused */
- soft_output_en:1, /* Unused */
- ext_td_cold_reg_en:1;
- union { /* External Cold register */
- uint32_t ext_td_cold_reg;
- struct {
- uint32_t min_iter:4, /* Unused */
- max_iter:4,
- ext_scale:5, /* Unused */
- rsrvd3:3,
- early_stop_en:1, /* Unused */
- sw_soft_out_dis:1, /* Unused */
- sw_et_cont:1, /* Unused */
- sw_soft_out_saturation:1, /* Unused */
- half_iter_on:1, /* Unused */
- raw_decoder_input_on:1, /* Unused */
- rsrvd4:10;
- };
- };
-};
-
-/* FEC 5GNR Uplink Frame Control Word */
-struct __rte_packed acc100_fcw_ld {
- uint32_t FCWversion:4,
- qm:4,
- nfiller:11,
- BG:1,
- Zc:9,
- res0:1,
- synd_precoder:1,
- synd_post:1;
- uint32_t ncb:16,
- k0:16;
- uint32_t rm_e:24,
- hcin_en:1,
- hcout_en:1,
- crc_select:1,
- bypass_dec:1,
- bypass_intlv:1,
- so_en:1,
- so_bypass_rm:1,
- so_bypass_intlv:1;
- uint32_t hcin_offset:16,
- hcin_size0:16;
- uint32_t hcin_size1:16,
- hcin_decomp_mode:3,
- llr_pack_mode:1,
- hcout_comp_mode:3,
- res2:1,
- dec_convllr:4,
- hcout_convllr:4;
- uint32_t itmax:7,
- itstop:1,
- so_it:7,
- res3:1,
- hcout_offset:16;
- uint32_t hcout_size0:16,
- hcout_size1:16;
- uint32_t gain_i:8,
- gain_h:8,
- negstop_th:16;
- uint32_t negstop_it:7,
- negstop_en:1,
- res4:24;
-};
-
-/* FEC 4G Downlink Frame Control Word */
-struct __rte_packed acc100_fcw_te {
- uint16_t k_neg;
- uint16_t k_pos;
- uint8_t c_neg;
- uint8_t c;
- uint8_t filler;
- uint8_t cab;
- uint32_t ea:17,
- rsrvd0:15;
- uint32_t eb:17,
- rsrvd1:15;
- uint16_t ncb_neg;
- uint16_t ncb_pos;
- uint8_t rv_idx0:2,
- rsrvd2:2,
- rv_idx1:2,
- rsrvd3:2;
- uint8_t bypass_rv_idx0:1,
- bypass_rv_idx1:1,
- bypass_rm:1,
- rsrvd4:5;
- uint8_t rsrvd5:1,
- rsrvd6:3,
- code_block_crc:1,
- rsrvd7:3;
- uint8_t code_block_mode:1,
- rsrvd8:7;
- uint64_t rsrvd9;
-};
-
-/* FEC 5GNR Downlink Frame Control Word */
-struct __rte_packed acc100_fcw_le {
- uint32_t FCWversion:4,
- qm:4,
- nfiller:11,
- BG:1,
- Zc:9,
- res0:3;
- uint32_t ncb:16,
- k0:16;
- uint32_t rm_e:24,
- res1:2,
- crc_select:1,
- res2:1,
- bypass_intlv:1,
- res3:3;
- uint32_t res4_a:12,
- mcb_count:3,
- res4_b:17;
- uint32_t res5;
- uint32_t res6;
- uint32_t res7;
- uint32_t res8;
-};
-
-/* ACC100 DMA Request Descriptor */
-struct __rte_packed acc100_dma_req_desc {
- union {
- struct{
- uint32_t type:4,
- rsrvd0:26,
- sdone:1,
- fdone:1;
- uint32_t rsrvd1;
- uint32_t rsrvd2;
- uint32_t pass_param:8,
- sdone_enable:1,
- irq_enable:1,
- timeStampEn:1,
- res0:5,
- numCBs:4,
- res1:4,
- m2dlen:4,
- d2mlen:4;
- };
- struct{
- uint32_t word0;
- uint32_t word1;
- uint32_t word2;
- uint32_t word3;
- };
- };
- struct acc100_dma_triplet data_ptrs[ACC100_DMA_MAX_NUM_POINTERS];
-
- /* Virtual addresses used to retrieve SW context info */
- union {
- void *op_addr;
- uint64_t pad1; /* pad to 64 bits */
- };
- /*
- * Stores additional information needed for driver processing:
- * - last_desc_in_batch - flag used to mark last descriptor (CB)
- * in batch
- * - cbs_in_tb - stores information about total number of Code Blocks
- * in currently processed Transport Block
- */
- union {
- struct {
- union {
- struct acc100_fcw_ld fcw_ld;
- struct acc100_fcw_td fcw_td;
- struct acc100_fcw_le fcw_le;
- struct acc100_fcw_te fcw_te;
- uint32_t pad2[ACC100_FCW_PADDING];
- };
- uint32_t last_desc_in_batch :8,
- cbs_in_tb:8,
- pad4 : 16;
- };
- uint64_t pad3[ACC100_DMA_DESC_PADDING]; /* pad to 64 bits */
- };
-};
-
-/* ACC100 DMA Descriptor */
-union acc100_dma_desc {
- struct acc100_dma_req_desc req;
- union acc100_dma_rsp_desc rsp;
- uint64_t atom_hdr;
-};
-
-
-/* Union describing Info Ring entry */
-union acc100_harq_layout_data {
- uint32_t val;
- struct {
- uint16_t offset;
- uint16_t size0;
- };
-} __rte_packed;
-
-
-/* Union describing Info Ring entry */
-union acc100_info_ring_data {
- uint32_t val;
- struct {
- union {
- uint16_t detailed_info;
- struct {
- uint16_t aq_id: 4;
- uint16_t qg_id: 4;
- uint16_t vf_id: 6;
- uint16_t reserved: 2;
- };
- };
- uint16_t int_nb: 7;
- uint16_t msi_0: 1;
- uint16_t vf2pf: 6;
- uint16_t loop: 1;
- uint16_t valid: 1;
- };
-} __rte_packed;
-
struct acc100_registry_addr {
unsigned int dma_ring_dl5g_hi;
unsigned int dma_ring_dl5g_lo;
@@ -545,80 +174,4 @@ static const struct acc100_registry_addr vf_reg_addr = {
.ddr_range = HWVfDmaDdrBaseRangeRoVf,
};
-/* Structure associated with each queue. */
-struct __rte_cache_aligned acc100_queue {
- union acc100_dma_desc *ring_addr; /* Virtual address of sw ring */
- rte_iova_t ring_addr_iova; /* IOVA address of software ring */
- uint32_t sw_ring_head; /* software ring head */
- uint32_t sw_ring_tail; /* software ring tail */
- /* software ring size (descriptors, not bytes) */
- uint32_t sw_ring_depth;
- /* mask used to wrap enqueued descriptors on the sw ring */
- uint32_t sw_ring_wrap_mask;
- /* MMIO register used to enqueue descriptors */
- void *mmio_reg_enqueue;
- uint8_t vf_id; /* VF ID (max = 63) */
- uint8_t qgrp_id; /* Queue Group ID */
- uint16_t aq_id; /* Atomic Queue ID */
- uint16_t aq_depth; /* Depth of atomic queue */
- uint32_t aq_enqueued; /* Count how many "batches" have been enqueued */
- uint32_t aq_dequeued; /* Count how many "batches" have been dequeued */
- uint32_t irq_enable; /* Enable ops dequeue interrupts if set to 1 */
- struct rte_mempool *fcw_mempool; /* FCW mempool */
- enum rte_bbdev_op_type op_type; /* Type of this Queue: TE or TD */
- /* Internal Buffers for loopback input */
- uint8_t *lb_in;
- uint8_t *lb_out;
- rte_iova_t lb_in_addr_iova;
- rte_iova_t lb_out_addr_iova;
- struct acc100_device *d;
-};
-
-typedef void (*acc10x_fcw_ld_fill_fun_t)(struct rte_bbdev_dec_op *op,
- struct acc100_fcw_ld *fcw,
- union acc100_harq_layout_data *harq_layout);
-
-/* Private data structure for each ACC100 device */
-struct acc100_device {
- void *mmio_base; /**< Base address of MMIO registers (BAR0) */
- void *sw_rings_base; /* Base addr of un-aligned memory for sw rings */
- void *sw_rings; /* 64MBs of 64MB aligned memory for sw rings */
- rte_iova_t sw_rings_iova; /* IOVA address of sw_rings */
- /* Virtual address of the info memory routed to the this function under
- * operation, whether it is PF or VF.
- * HW may DMA information data at this location asynchronously
- */
- union acc100_info_ring_data *info_ring;
-
- union acc100_harq_layout_data *harq_layout;
- /* Virtual Info Ring head */
- uint16_t info_ring_head;
- /* Number of bytes available for each queue in device, depending on
- * how many queues are enabled with configure()
- */
- uint32_t sw_ring_size;
- uint32_t ddr_size; /* Size in kB */
- uint32_t *tail_ptrs; /* Base address of response tail pointer buffer */
- rte_iova_t tail_ptr_iova; /* IOVA address of tail pointers */
- /* Max number of entries available for each queue in device, depending
- * on how many queues are enabled with configure()
- */
- uint32_t sw_ring_max_depth;
- struct rte_acc100_conf acc100_conf; /* ACC100 Initial configuration */
- /* Bitmap capturing which Queues have already been assigned */
- uint16_t q_assigned_bit_map[ACC100_NUM_QGRPS];
- bool pf_device; /**< True if this is a PF ACC100 device */
- bool configured; /**< True if this ACC100 device is configured */
- uint16_t device_variant; /**< Device variant */
- acc10x_fcw_ld_fill_fun_t fcw_ld_fill; /**< 5GUL FCW generation function */
-};
-
-/**
- * Structure with details about RTE_BBDEV_EVENT_DEQUEUE event. It's passed to
- * the callback function.
- */
-struct acc100_deq_intr_details {
- uint16_t queue_id;
-};
-
#endif /* _RTE_ACC100_PMD_H_ */
diff --git a/drivers/baseband/acc100/acc101_pmd.h b/drivers/baseband/acc100/acc101_pmd.h
index 9d8862ce36..37df008330 100644
--- a/drivers/baseband/acc100/acc101_pmd.h
+++ b/drivers/baseband/acc100/acc101_pmd.h
@@ -11,16 +11,9 @@
#define ACC101_NUM_VFS 16
#define ACC101_NUM_QGRPS 8
#define ACC101_NUM_AQS 16
-/* All ACC101 Registers alignment are 32bits = 4B */
-#define ACC101_BYTES_IN_WORD 4
-#define ACC101_TMPL_PRI_0 0x03020100
-#define ACC101_TMPL_PRI_1 0x07060504
-#define ACC101_TMPL_PRI_2 0x0b0a0908
-#define ACC101_TMPL_PRI_3 0x0f0e0d0c
#define ACC101_WORDS_IN_ARAM_SIZE (128 * 1024 / 4)
-#define ACC101_NUM_TMPL 32
/* Mapping of signals for the available engines */
#define ACC101_SIG_UL_5G 0
#define ACC101_SIG_UL_5G_LAST 8
@@ -31,7 +24,6 @@
#define ACC101_SIG_DL_4G 27
#define ACC101_SIG_DL_4G_LAST 31
#define ACC101_NUM_ACCS 5
-#define ACC101_PF_VAL 2
/* ACC101 Configuration */
#define ACC101_CFG_DMA_ERROR 0x3D7
@@ -39,8 +31,6 @@
#define ACC101_CFG_QMGR_HI_P 0x0F0F
#define ACC101_CFG_PCI_AXI 0xC003
#define ACC101_CFG_PCI_BRIDGE 0x40006033
-#define ACC101_ENGINE_OFFSET 0x1000
-#define ACC101_LONG_WAIT 1000
#define ACC101_GPEX_AXIMAP_NUM 17
#define ACC101_CLOCK_GATING_EN 0x30000
#define ACC101_DMA_INBOUND 0x104
diff --git a/drivers/baseband/acc100/acc_common.h b/drivers/baseband/acc100/acc_common.h
new file mode 100644
index 0000000000..ae8de9ed89
--- /dev/null
+++ b/drivers/baseband/acc100/acc_common.h
@@ -0,0 +1,1303 @@
+/* SPDX-License-Identifier: BSD-3-Clause
+ * Copyright(c) 2022 Intel Corporation
+ */
+
+#ifndef _ACC_COMMON_H_
+#define _ACC_COMMON_H_
+
+#include "rte_acc_common_cfg.h"
+
+/* Values used in filling in descriptors */
+#define ACC_DMA_DESC_TYPE 2
+#define ACC_DMA_BLKID_FCW 1
+#define ACC_DMA_BLKID_IN 2
+#define ACC_DMA_BLKID_OUT_ENC 1
+#define ACC_DMA_BLKID_OUT_HARD 1
+#define ACC_DMA_BLKID_OUT_SOFT 2
+#define ACC_DMA_BLKID_OUT_HARQ 3
+#define ACC_DMA_BLKID_IN_HARQ 3
+#define ACC_DMA_BLKID_IN_MLD_R 3
+
+/* Values used in filling in decode FCWs */
+#define ACC_FCW_TD_VER 1
+#define ACC_FCW_TD_EXT_COLD_REG_EN 1
+#define ACC_FCW_TD_AUTOMAP 0x0f
+#define ACC_FCW_TD_RVIDX_0 2
+#define ACC_FCW_TD_RVIDX_1 26
+#define ACC_FCW_TD_RVIDX_2 50
+#define ACC_FCW_TD_RVIDX_3 74
+
+#define ACC_SIZE_64MBYTE (64*1024*1024)
+/* Number of elements in an Info Ring */
+#define ACC_INFO_RING_NUM_ENTRIES 1024
+/* Number of elements in HARQ layout memory
+ * 128M x 32kB = 4GB addressable memory
+ */
+#define ACC_HARQ_LAYOUT (128 * 1024 * 1024)
+/* Assume offset for HARQ in memory */
+#define ACC_HARQ_OFFSET (32 * 1024)
+#define ACC_HARQ_OFFSET_SHIFT 15
+#define ACC_HARQ_OFFSET_MASK 0x7ffffff
+#define ACC_HARQ_OFFSET_THRESHOLD 1024
+/* Mask used to calculate an index in an Info Ring array (not a byte offset) */
+#define ACC_INFO_RING_MASK (ACC_INFO_RING_NUM_ENTRIES-1)
+
+#define MAX_ENQ_BATCH_SIZE 255
+
+/* All ACC100 Registers alignment are 32bits = 4B */
+#define ACC_BYTES_IN_WORD 4
+#define ACC_MAX_E_MBUF 64000
+
+#define ACC_VF_OFFSET_QOS 16 /* offset in Memory specific to QoS Mon */
+#define ACC_TMPL_PRI_0 0x03020100
+#define ACC_TMPL_PRI_1 0x07060504
+#define ACC_TMPL_PRI_2 0x0b0a0908
+#define ACC_TMPL_PRI_3 0x0f0e0d0c
+#define ACC_TMPL_PRI_4 0x13121110
+#define ACC_TMPL_PRI_5 0x17161514
+#define ACC_TMPL_PRI_6 0x1b1a1918
+#define ACC_TMPL_PRI_7 0x1f1e1d1c
+#define ACC_QUEUE_ENABLE 0x80000000 /* Bit to mark Queue as Enabled */
+#define ACC_FDONE 0x80000000
+#define ACC_SDONE 0x40000000
+
+#define ACC_NUM_TMPL 32
+
+#define ACC_ACCMAP_0 0
+#define ACC_ACCMAP_1 2
+#define ACC_ACCMAP_2 1
+#define ACC_ACCMAP_3 3
+#define ACC_ACCMAP_4 4
+#define ACC_ACCMAP_5 5
+#define ACC_PF_VAL 2
+
+/* max number of iterations to allocate memory block for all rings */
+#define ACC_SW_RING_MEM_ALLOC_ATTEMPTS 5
+#define ACC_MAX_QUEUE_DEPTH 1024
+#define ACC_DMA_MAX_NUM_POINTERS 14
+#define ACC_DMA_MAX_NUM_POINTERS_IN 7
+#define ACC_DMA_DESC_PADDINGS 8
+#define ACC_FCW_PADDING 12
+#define ACC_DESC_FCW_OFFSET 192
+#define ACC_DESC_SIZE 256
+#define ACC_DESC_OFFSET (ACC_DESC_SIZE / 64)
+#define ACC_FCW_TE_BLEN 32
+#define ACC_FCW_TD_BLEN 24
+#define ACC_FCW_LE_BLEN 32
+#define ACC_FCW_LD_BLEN 36
+#define ACC_FCW_FFT_BLEN 28
+#define ACC_5GUL_SIZE_0 16
+#define ACC_5GUL_SIZE_1 40
+#define ACC_5GUL_OFFSET_0 36
+#define ACC_COMPANION_PTRS 8
+#define ACC_FCW_VER 2
+#define ACC_MUX_5GDL_DESC 6
+#define ACC_CMP_ENC_SIZE 20
+#define ACC_CMP_DEC_SIZE 24
+#define ACC_ENC_OFFSET (32)
+#define ACC_DEC_OFFSET (80)
+#define ACC_LIMIT_DL_MUX_BITS 534
+#define ACC_NUM_QGRPS_PER_WORD 8
+#define ACC_MAX_NUM_QGRPS 32
+
+/* Constants from K0 computation from 3GPP 38.212 Table 5.4.2.1-2 */
+#define ACC_N_ZC_1 66 /* N = 66 Zc for BG 1 */
+#define ACC_N_ZC_2 50 /* N = 50 Zc for BG 2 */
+#define ACC_K_ZC_1 22 /* K = 22 Zc for BG 1 */
+#define ACC_K_ZC_2 10 /* K = 10 Zc for BG 2 */
+#define ACC_K0_1_1 17 /* K0 fraction numerator for rv 1 and BG 1 */
+#define ACC_K0_1_2 13 /* K0 fraction numerator for rv 1 and BG 2 */
+#define ACC_K0_2_1 33 /* K0 fraction numerator for rv 2 and BG 1 */
+#define ACC_K0_2_2 25 /* K0 fraction numerator for rv 2 and BG 2 */
+#define ACC_K0_3_1 56 /* K0 fraction numerator for rv 3 and BG 1 */
+#define ACC_K0_3_2 43 /* K0 fraction numerator for rv 3 and BG 2 */
+
+#define ACC_ENGINE_OFFSET 0x1000
+#define ACC_LONG_WAIT 1000
+#define ACC_MS_IN_US (1000)
+
+#define ACC_ALGO_SPA 0
+#define ACC_ALGO_MSA 1
+
+/* Helper macro for logging */
+#define rte_acc_log(level, fmt, ...) \
+ rte_log(RTE_LOG_ ## level, RTE_LOG_NOTICE, fmt "\n", \
+ ##__VA_ARGS__)
+
+/* ACC100 DMA Descriptor triplet */
+struct acc_dma_triplet {
+ uint64_t address;
+ uint32_t blen:20,
+ res0:4,
+ last:1,
+ dma_ext:1,
+ res1:2,
+ blkid:4;
+} __rte_packed;
+
+
+/* ACC100 Queue Manager Enqueue PCI Register */
+union acc_enqueue_reg_fmt {
+ uint32_t val;
+ struct {
+ uint32_t num_elem:8,
+ addr_offset:3,
+ rsrvd:1,
+ req_elem_addr:20;
+ };
+};
+
+/* FEC 4G Uplink Frame Control Word */
+struct __rte_packed acc_fcw_td {
+ uint8_t fcw_ver:4,
+ num_maps:4; /* Unused in ACC100 */
+ uint8_t filler:6, /* Unused in ACC100 */
+ rsrvd0:1,
+ bypass_sb_deint:1;
+ uint16_t k_pos;
+ uint16_t k_neg; /* Unused in ACC100 */
+ uint8_t c_neg; /* Unused in ACC100 */
+ uint8_t c; /* Unused in ACC100 */
+ uint32_t ea; /* Unused in ACC100 */
+ uint32_t eb; /* Unused in ACC100 */
+ uint8_t cab; /* Unused in ACC100 */
+ uint8_t k0_start_col; /* Unused in ACC100 */
+ uint8_t rsrvd1;
+ uint8_t code_block_mode:1, /* Unused in ACC100 */
+ turbo_crc_type:1,
+ rsrvd2:3,
+ bypass_teq:1, /* Unused in ACC100 */
+ soft_output_en:1, /* Unused in ACC100 */
+ ext_td_cold_reg_en:1;
+ union { /* External Cold register */
+ uint32_t ext_td_cold_reg;
+ struct {
+ uint32_t min_iter:4, /* Unused in ACC100 */
+ max_iter:4,
+ ext_scale:5, /* Unused in ACC100 */
+ rsrvd3:3,
+ early_stop_en:1, /* Unused in ACC100 */
+ sw_soft_out_dis:1, /* Unused in ACC100 */
+ sw_et_cont:1, /* Unused in ACC100 */
+ sw_soft_out_saturation:1, /* Unused in ACC100 */
+ half_iter_on:1, /* Unused in ACC100 */
+ raw_decoder_input_on:1, /* Unused in ACC100 */
+ rsrvd4:10;
+ };
+ };
+};
+
+/* FEC 4G Downlink Frame Control Word */
+struct __rte_packed acc_fcw_te {
+ uint16_t k_neg;
+ uint16_t k_pos;
+ uint8_t c_neg;
+ uint8_t c;
+ uint8_t filler;
+ uint8_t cab;
+ uint32_t ea:17,
+ rsrvd0:15;
+ uint32_t eb:17,
+ rsrvd1:15;
+ uint16_t ncb_neg;
+ uint16_t ncb_pos;
+ uint8_t rv_idx0:2,
+ rsrvd2:2,
+ rv_idx1:2,
+ rsrvd3:2;
+ uint8_t bypass_rv_idx0:1,
+ bypass_rv_idx1:1,
+ bypass_rm:1,
+ rsrvd4:5;
+ uint8_t rsrvd5:1,
+ rsrvd6:3,
+ code_block_crc:1,
+ rsrvd7:3;
+ uint8_t code_block_mode:1,
+ rsrvd8:7;
+ uint64_t rsrvd9;
+};
+
+/* FEC 5GNR Downlink Frame Control Word */
+struct __rte_packed acc_fcw_le {
+ uint32_t FCWversion:4,
+ qm:4,
+ nfiller:11,
+ BG:1,
+ Zc:9,
+ res0:3;
+ uint32_t ncb:16,
+ k0:16;
+ uint32_t rm_e:22,
+ res1:4,
+ crc_select:1,
+ res2:1,
+ bypass_intlv:1,
+ res3:3;
+ uint32_t res4_a:12,
+ mcb_count:3,
+ res4_b:1,
+ C:8,
+ Cab:8;
+ uint32_t rm_e_b:22,
+ res5:10;
+ uint32_t res6;
+ uint32_t res7;
+ uint32_t res8;
+};
+
+/* FEC 5GNR Uplink Frame Control Word */
+struct __rte_packed acc_fcw_ld {
+ uint32_t FCWversion:4,
+ qm:4,
+ nfiller:11,
+ BG:1,
+ Zc:9,
+ cnu_algo:1, /* Not supported in ACC100 */
+ synd_precoder:1,
+ synd_post:1;
+ uint32_t ncb:16,
+ k0:16;
+ uint32_t rm_e:24,
+ hcin_en:1,
+ hcout_en:1,
+ crc_select:1,
+ bypass_dec:1,
+ bypass_intlv:1,
+ so_en:1,
+ so_bypass_rm:1,
+ so_bypass_intlv:1;
+ uint32_t hcin_offset:16,
+ hcin_size0:16;
+ uint32_t hcin_size1:16,
+ hcin_decomp_mode:3,
+ llr_pack_mode:1,
+ hcout_comp_mode:3,
+ saturate_input:1, /* Not supported in ACC200 */
+ dec_convllr:4,
+ hcout_convllr:4;
+ uint32_t itmax:7,
+ itstop:1,
+ so_it:7,
+ minsum_offset:1, /* Not supported in ACC200 */
+ hcout_offset:16;
+ uint32_t hcout_size0:16,
+ hcout_size1:16;
+ uint32_t gain_i:8,
+ gain_h:8,
+ negstop_th:16;
+ uint32_t negstop_it:7,
+ negstop_en:1,
+ tb_crc_select:2, /* Not supported in ACC100 */
+ dec_llrclip:2, /* Not supported in ACC200 */
+ tb_trailer_size:20; /* Not supported in ACC100 */
+};
+
+/* FFT Frame Control Word */
+struct __rte_packed acc_fcw_fft {
+ uint32_t in_frame_size:16,
+ leading_pad_size:16;
+ uint32_t out_frame_size:16,
+ leading_depad_size:16;
+ uint32_t cs_window_sel;
+ uint32_t cs_window_sel2:16,
+ cs_enable_bmap:16;
+ uint32_t num_antennas:8,
+ idft_size:8,
+ dft_size:8,
+ cs_offset:8;
+ uint32_t idft_shift:8,
+ dft_shift:8,
+ cs_multiplier:16;
+ uint32_t bypass:2,
+ fp16_in:1, /* Not supported in ACC200 */
+ fp16_out:1,
+ exp_adj:4,
+ power_shift:4,
+ power_en:1,
+ res:19;
+};
+
+/* MLD-TS Frame Control Word */
+struct __rte_packed acc_fcw_mldts {
+ uint32_t fcw_version:4,
+ res0:12,
+ nrb:13, /* 1 to 1925 */
+ res1:3;
+ uint32_t NLayers:2, /* 1: 2L... 3: 4L */
+ res2:14,
+ Qmod0:2, /* 0: 2...3: 8 */
+ res3_0:2,
+ Qmod1:2,
+ res3_1:2,
+ Qmod2:2,
+ res3_2:2,
+ Qmod3:2,
+ res3_3:2;
+ uint32_t Rrep:3, /* 0 to 5 */
+ res4:1,
+ Crep:3, /* 0 to 6 */
+ res5:25;
+ uint32_t pad0;
+ uint32_t pad1;
+ uint32_t pad2;
+ uint32_t pad3;
+ uint32_t pad4;
+};
+
+/* DMA Response Descriptor */
+union acc_dma_rsp_desc {
+ uint32_t val;
+ struct {
+ uint32_t crc_status:1,
+ synd_ok:1,
+ dma_err:1,
+ neg_stop:1,
+ fcw_err:1,
+ output_truncate:1,
+ input_err:1,
+ tsen_pagefault:1,
+ iterCountFrac:8,
+ iter_cnt:8,
+ engine_hung:1,
+ core_reset:5,
+ sdone:1,
+ fdone:1;
+ uint32_t add_info_0;
+ uint32_t add_info_1;
+ };
+};
+
+/* DMA Request Descriptor */
+struct __rte_packed acc_dma_req_desc {
+ union {
+ struct{
+ uint32_t type:4,
+ rsrvd0:26,
+ sdone:1,
+ fdone:1;
+ uint32_t ib_ant_offset:16, /* Not supported in ACC100 */
+ res2:12,
+ num_ant:4;
+ uint32_t ob_ant_offset:16,
+ ob_cyc_offset:12,
+ num_cs:4;
+ uint32_t pass_param:8,
+ sdone_enable:1,
+ irq_enable:1,
+ timeStampEn:1,
+ dltb:1, /* Not supported in ACC200 */
+ res0:4,
+ numCBs:8,
+ m2dlen:4,
+ d2mlen:4;
+ };
+ struct{
+ uint32_t word0;
+ uint32_t word1;
+ uint32_t word2;
+ uint32_t word3;
+ };
+ };
+ struct acc_dma_triplet data_ptrs[ACC_DMA_MAX_NUM_POINTERS];
+
+ /* Virtual addresses used to retrieve SW context info */
+ union {
+ void *op_addr;
+ uint64_t pad1; /* pad to 64 bits */
+ };
+ /*
+ * Stores additional information needed for driver processing:
+ * - last_desc_in_batch - flag used to mark last descriptor (CB)
+ * in batch
+ * - cbs_in_tb - stores information about total number of Code Blocks
+ * in currently processed Transport Block
+ */
+ union {
+ struct {
+ union {
+ struct acc_fcw_ld fcw_ld;
+ struct acc_fcw_td fcw_td;
+ struct acc_fcw_le fcw_le;
+ struct acc_fcw_te fcw_te;
+ struct acc_fcw_fft fcw_fft;
+ struct acc_fcw_mldts fcw_mldts;
+ uint32_t pad2[ACC_FCW_PADDING];
+ };
+ uint32_t last_desc_in_batch :8,
+ cbs_in_tb:8,
+ pad4 : 16;
+ };
+ uint64_t pad3[ACC_DMA_DESC_PADDINGS]; /* pad to 64 bits */
+ };
+};
+
+/* ACC100 DMA Descriptor */
+union acc_dma_desc {
+ struct acc_dma_req_desc req;
+ union acc_dma_rsp_desc rsp;
+ uint64_t atom_hdr;
+};
+
+/* Union describing Info Ring entry */
+union acc_info_ring_data {
+ uint32_t val;
+ struct {
+ union {
+ uint16_t detailed_info;
+ struct {
+ uint16_t aq_id: 4;
+ uint16_t qg_id: 4;
+ uint16_t vf_id: 6;
+ uint16_t reserved: 2;
+ };
+ };
+ uint16_t int_nb: 7;
+ uint16_t msi_0: 1;
+ uint16_t vf2pf: 6;
+ uint16_t loop: 1;
+ uint16_t valid: 1;
+ };
+ struct {
+ uint32_t aq_id_3: 6;
+ uint32_t qg_id_3: 5;
+ uint32_t vf_id_3: 6;
+ uint32_t int_nb_3: 6;
+ uint32_t msi_0_3: 1;
+ uint32_t vf2pf_3: 6;
+ uint32_t loop_3: 1;
+ uint32_t valid_3: 1;
+ };
+} __rte_packed;
+
+struct __rte_packed acc_pad_ptr {
+ void *op_addr;
+ uint64_t pad1; /* pad to 64 bits */
+};
+
+struct __rte_packed acc_ptrs {
+ struct acc_pad_ptr ptr[ACC_COMPANION_PTRS];
+};
+
+/* Union describing Info Ring entry */
+union acc_harq_layout_data {
+ uint32_t val;
+ struct {
+ uint16_t offset;
+ uint16_t size0;
+ };
+} __rte_packed;
+
+/**
+ * Structure with details about RTE_BBDEV_EVENT_DEQUEUE event. It's passed to
+ * the callback function.
+ */
+struct acc_deq_intr_details {
+ uint16_t queue_id;
+};
+
+/* TIP VF2PF Comms */
+enum {
+ ACC_VF2PF_STATUS_REQUEST = 0,
+ ACC_VF2PF_USING_VF = 1,
+};
+
+
+typedef void (*acc10x_fcw_ld_fill_fun_t)(struct rte_bbdev_dec_op *op,
+ struct acc_fcw_ld *fcw,
+ union acc_harq_layout_data *harq_layout);
+
+/* Private data structure for each ACC100 device */
+struct acc_device {
+ void *mmio_base; /**< Base address of MMIO registers (BAR0) */
+ void *sw_rings_base; /* Base addr of un-aligned memory for sw rings */
+ void *sw_rings; /* 64MBs of 64MB aligned memory for sw rings */
+ rte_iova_t sw_rings_iova; /* IOVA address of sw_rings */
+ /* Virtual address of the info memory routed to the this function under
+ * operation, whether it is PF or VF.
+ * HW may DMA information data at this location asynchronously
+ */
+ union acc_info_ring_data *info_ring;
+
+ union acc_harq_layout_data *harq_layout;
+ /* Virtual Info Ring head */
+ uint16_t info_ring_head;
+ /* Number of bytes available for each queue in device, depending on
+ * how many queues are enabled with configure()
+ */
+ uint32_t sw_ring_size;
+ uint32_t ddr_size; /* Size in kB */
+ uint32_t *tail_ptrs; /* Base address of response tail pointer buffer */
+ rte_iova_t tail_ptr_iova; /* IOVA address of tail pointers */
+ /* Max number of entries available for each queue in device, depending
+ * on how many queues are enabled with configure()
+ */
+ uint32_t sw_ring_max_depth;
+ struct rte_acc_conf acc_conf; /* ACC100 Initial configuration */
+ /* Bitmap capturing which Queues have already been assigned */
+ uint64_t q_assigned_bit_map[ACC_MAX_NUM_QGRPS];
+ bool pf_device; /**< True if this is a PF ACC100 device */
+ bool configured; /**< True if this ACC100 device is configured */
+ uint16_t device_variant; /**< Device variant */
+ acc10x_fcw_ld_fill_fun_t fcw_ld_fill; /**< 5GUL FCW generation function */
+};
+
+/* Structure associated with each queue. */
+struct __rte_cache_aligned acc_queue {
+ union acc_dma_desc *ring_addr; /* Virtual address of sw ring */
+ rte_iova_t ring_addr_iova; /* IOVA address of software ring */
+ uint32_t sw_ring_head; /* software ring head */
+ uint32_t sw_ring_tail; /* software ring tail */
+ /* software ring size (descriptors, not bytes) */
+ uint32_t sw_ring_depth;
+ /* mask used to wrap enqueued descriptors on the sw ring */
+ uint32_t sw_ring_wrap_mask;
+ /* Virtual address of companion ring */
+ struct acc_ptrs *companion_ring_addr;
+ /* MMIO register used to enqueue descriptors */
+ void *mmio_reg_enqueue;
+ uint8_t vf_id; /* VF ID (max = 63) */
+ uint8_t qgrp_id; /* Queue Group ID */
+ uint16_t aq_id; /* Atomic Queue ID */
+ uint16_t aq_depth; /* Depth of atomic queue */
+ uint32_t aq_enqueued; /* Count how many "batches" have been enqueued */
+ uint32_t aq_dequeued; /* Count how many "batches" have been dequeued */
+ uint32_t irq_enable; /* Enable ops dequeue interrupts if set to 1 */
+ struct rte_mempool *fcw_mempool; /* FCW mempool */
+ enum rte_bbdev_op_type op_type; /* Type of this Queue: TE or TD */
+ /* Internal Buffers for loopback input */
+ uint8_t *lb_in;
+ uint8_t *lb_out;
+ rte_iova_t lb_in_addr_iova;
+ rte_iova_t lb_out_addr_iova;
+ int8_t *derm_buffer; /* interim buffer for de-rm in SDK */
+ struct acc_device *d;
+};
+
+/* Write to MMIO register address */
+static inline void
+mmio_write(void *addr, uint32_t value)
+{
+ *((volatile uint32_t *)(addr)) = rte_cpu_to_le_32(value);
+}
+
+/* Write a register of a ACC100 device */
+static inline void
+acc_reg_write(struct acc_device *d, uint32_t offset, uint32_t value)
+{
+ void *reg_addr = RTE_PTR_ADD(d->mmio_base, offset);
+ mmio_write(reg_addr, value);
+ usleep(ACC_LONG_WAIT);
+}
+
+/* Read a register of a ACC100 device */
+static inline uint32_t
+acc_reg_read(struct acc_device *d, uint32_t offset)
+{
+
+ void *reg_addr = RTE_PTR_ADD(d->mmio_base, offset);
+ uint32_t ret = *((volatile uint32_t *)(reg_addr));
+ return rte_le_to_cpu_32(ret);
+}
+
+/* Basic Implementation of Log2 for exact 2^N */
+static inline uint32_t
+log2_basic(uint32_t value)
+{
+ return (value == 0) ? 0 : rte_bsf32(value);
+}
+
+/* Calculate memory alignment offset assuming alignment is 2^N */
+static inline uint32_t
+calc_mem_alignment_offset(void *unaligned_virt_mem, uint32_t alignment)
+{
+ rte_iova_t unaligned_phy_mem = rte_malloc_virt2iova(unaligned_virt_mem);
+ return (uint32_t)(alignment -
+ (unaligned_phy_mem & (alignment-1)));
+}
+
+static void
+free_base_addresses(void **base_addrs, int size)
+{
+ int i;
+ for (i = 0; i < size; i++)
+ rte_free(base_addrs[i]);
+}
+
+/* Read flag value 0/1 from bitmap */
+static inline bool
+check_bit(uint32_t bitmap, uint32_t bitmask)
+{
+ return bitmap & bitmask;
+}
+
+static inline char *
+mbuf_append(struct rte_mbuf *m_head, struct rte_mbuf *m, uint16_t len)
+{
+ if (unlikely(len > rte_pktmbuf_tailroom(m)))
+ return NULL;
+
+ char *tail = (char *)m->buf_addr + m->data_off + m->data_len;
+ m->data_len = (uint16_t)(m->data_len + len);
+ m_head->pkt_len = (m_head->pkt_len + len);
+ return tail;
+}
+
+
+static inline uint32_t
+get_desc_len(void)
+{
+ return sizeof(union acc_dma_desc);
+}
+
+/* Allocate the 2 * 64MB block for the sw rings */
+static inline int
+alloc_2x64mb_sw_rings_mem(struct rte_bbdev *dev, struct acc_device *d,
+ int socket)
+{
+ uint32_t sw_ring_size = ACC_SIZE_64MBYTE;
+ d->sw_rings_base = rte_zmalloc_socket(dev->device->driver->name,
+ 2 * sw_ring_size, RTE_CACHE_LINE_SIZE, socket);
+ if (d->sw_rings_base == NULL) {
+ rte_acc_log(ERR, "Failed to allocate memory for %s:%u",
+ dev->device->driver->name,
+ dev->data->dev_id);
+ return -ENOMEM;
+ }
+ uint32_t next_64mb_align_offset = calc_mem_alignment_offset(
+ d->sw_rings_base, ACC_SIZE_64MBYTE);
+ d->sw_rings = RTE_PTR_ADD(d->sw_rings_base, next_64mb_align_offset);
+ d->sw_rings_iova = rte_malloc_virt2iova(d->sw_rings_base) +
+ next_64mb_align_offset;
+ d->sw_ring_size = ACC_MAX_QUEUE_DEPTH * get_desc_len();
+ d->sw_ring_max_depth = ACC_MAX_QUEUE_DEPTH;
+
+ return 0;
+}
+
+/* Attempt to allocate minimised memory space for sw rings */
+static inline void
+alloc_sw_rings_min_mem(struct rte_bbdev *dev, struct acc_device *d,
+ uint16_t num_queues, int socket)
+{
+ rte_iova_t sw_rings_base_iova, next_64mb_align_addr_iova;
+ uint32_t next_64mb_align_offset;
+ rte_iova_t sw_ring_iova_end_addr;
+ void *base_addrs[ACC_SW_RING_MEM_ALLOC_ATTEMPTS];
+ void *sw_rings_base;
+ int i = 0;
+ uint32_t q_sw_ring_size = ACC_MAX_QUEUE_DEPTH * get_desc_len();
+ uint32_t dev_sw_ring_size = q_sw_ring_size * num_queues;
+ /* Free first in case this is a reconfiguration */
+ rte_free(d->sw_rings_base);
+
+ /* Find an aligned block of memory to store sw rings */
+ while (i < ACC_SW_RING_MEM_ALLOC_ATTEMPTS) {
+ /*
+ * sw_ring allocated memory is guaranteed to be aligned to
+ * q_sw_ring_size at the condition that the requested size is
+ * less than the page size
+ */
+ sw_rings_base = rte_zmalloc_socket(
+ dev->device->driver->name,
+ dev_sw_ring_size, q_sw_ring_size, socket);
+
+ if (sw_rings_base == NULL) {
+ rte_acc_log(ERR,
+ "Failed to allocate memory for %s:%u",
+ dev->device->driver->name,
+ dev->data->dev_id);
+ break;
+ }
+
+ sw_rings_base_iova = rte_malloc_virt2iova(sw_rings_base);
+ next_64mb_align_offset = calc_mem_alignment_offset(
+ sw_rings_base, ACC_SIZE_64MBYTE);
+ next_64mb_align_addr_iova = sw_rings_base_iova +
+ next_64mb_align_offset;
+ sw_ring_iova_end_addr = sw_rings_base_iova + dev_sw_ring_size;
+
+ /* Check if the end of the sw ring memory block is before the
+ * start of next 64MB aligned mem address
+ */
+ if (sw_ring_iova_end_addr < next_64mb_align_addr_iova) {
+ d->sw_rings_iova = sw_rings_base_iova;
+ d->sw_rings = sw_rings_base;
+ d->sw_rings_base = sw_rings_base;
+ d->sw_ring_size = q_sw_ring_size;
+ d->sw_ring_max_depth = ACC_MAX_QUEUE_DEPTH;
+ break;
+ }
+ /* Store the address of the unaligned mem block */
+ base_addrs[i] = sw_rings_base;
+ i++;
+ }
+
+ /* Free all unaligned blocks of mem allocated in the loop */
+ free_base_addresses(base_addrs, i);
+}
+
+/*
+ * Find queue_id of a device queue based on details from the Info Ring.
+ * If a queue isn't found UINT16_MAX is returned.
+ */
+static inline uint16_t
+get_queue_id_from_ring_info(struct rte_bbdev_data *data,
+ const union acc_info_ring_data ring_data)
+{
+ uint16_t queue_id;
+
+ for (queue_id = 0; queue_id < data->num_queues; ++queue_id) {
+ struct acc_queue *acc_q =
+ data->queues[queue_id].queue_private;
+ if (acc_q != NULL && acc_q->aq_id == ring_data.aq_id &&
+ acc_q->qgrp_id == ring_data.qg_id &&
+ acc_q->vf_id == ring_data.vf_id)
+ return queue_id;
+ }
+
+ return UINT16_MAX;
+}
+
+/* Fill in a frame control word for turbo encoding. */
+static inline void
+acc_fcw_te_fill(const struct rte_bbdev_enc_op *op, struct acc_fcw_te *fcw)
+{
+ fcw->code_block_mode = op->turbo_enc.code_block_mode;
+ if (fcw->code_block_mode == RTE_BBDEV_TRANSPORT_BLOCK) {
+ fcw->k_neg = op->turbo_enc.tb_params.k_neg;
+ fcw->k_pos = op->turbo_enc.tb_params.k_pos;
+ fcw->c_neg = op->turbo_enc.tb_params.c_neg;
+ fcw->c = op->turbo_enc.tb_params.c;
+ fcw->ncb_neg = op->turbo_enc.tb_params.ncb_neg;
+ fcw->ncb_pos = op->turbo_enc.tb_params.ncb_pos;
+
+ if (check_bit(op->turbo_enc.op_flags,
+ RTE_BBDEV_TURBO_RATE_MATCH)) {
+ fcw->bypass_rm = 0;
+ fcw->cab = op->turbo_enc.tb_params.cab;
+ fcw->ea = op->turbo_enc.tb_params.ea;
+ fcw->eb = op->turbo_enc.tb_params.eb;
+ } else {
+ /* E is set to the encoding output size when RM is
+ * bypassed.
+ */
+ fcw->bypass_rm = 1;
+ fcw->cab = fcw->c_neg;
+ fcw->ea = 3 * fcw->k_neg + 12;
+ fcw->eb = 3 * fcw->k_pos + 12;
+ }
+ } else { /* For CB mode */
+ fcw->k_pos = op->turbo_enc.cb_params.k;
+ fcw->ncb_pos = op->turbo_enc.cb_params.ncb;
+
+ if (check_bit(op->turbo_enc.op_flags,
+ RTE_BBDEV_TURBO_RATE_MATCH)) {
+ fcw->bypass_rm = 0;
+ fcw->eb = op->turbo_enc.cb_params.e;
+ } else {
+ /* E is set to the encoding output size when RM is
+ * bypassed.
+ */
+ fcw->bypass_rm = 1;
+ fcw->eb = 3 * fcw->k_pos + 12;
+ }
+ }
+
+ fcw->bypass_rv_idx1 = check_bit(op->turbo_enc.op_flags,
+ RTE_BBDEV_TURBO_RV_INDEX_BYPASS);
+ fcw->code_block_crc = check_bit(op->turbo_enc.op_flags,
+ RTE_BBDEV_TURBO_CRC_24B_ATTACH);
+ fcw->rv_idx1 = op->turbo_enc.rv_index;
+}
+
+/* Compute value of k0.
+ * Based on 3GPP 38.212 Table 5.4.2.1-2
+ * Starting position of different redundancy versions, k0
+ */
+static inline uint16_t
+get_k0(uint16_t n_cb, uint16_t z_c, uint8_t bg, uint8_t rv_index)
+{
+ if (rv_index == 0)
+ return 0;
+ uint16_t n = (bg == 1 ? ACC_N_ZC_1 : ACC_N_ZC_2) * z_c;
+ if (n_cb == n) {
+ if (rv_index == 1)
+ return (bg == 1 ? ACC_K0_1_1 : ACC_K0_1_2) * z_c;
+ else if (rv_index == 2)
+ return (bg == 1 ? ACC_K0_2_1 : ACC_K0_2_2) * z_c;
+ else
+ return (bg == 1 ? ACC_K0_3_1 : ACC_K0_3_2) * z_c;
+ }
+ /* LBRM case - includes a division by N */
+ if (unlikely(z_c == 0))
+ return 0;
+ if (rv_index == 1)
+ return (((bg == 1 ? ACC_K0_1_1 : ACC_K0_1_2) * n_cb)
+ / n) * z_c;
+ else if (rv_index == 2)
+ return (((bg == 1 ? ACC_K0_2_1 : ACC_K0_2_2) * n_cb)
+ / n) * z_c;
+ else
+ return (((bg == 1 ? ACC_K0_3_1 : ACC_K0_3_2) * n_cb)
+ / n) * z_c;
+}
+
+/* Fill in a frame control word for LDPC encoding. */
+static inline void
+acc_fcw_le_fill(const struct rte_bbdev_enc_op *op,
+ struct acc_fcw_le *fcw, int num_cb, uint32_t default_e)
+{
+ fcw->qm = op->ldpc_enc.q_m;
+ fcw->nfiller = op->ldpc_enc.n_filler;
+ fcw->BG = (op->ldpc_enc.basegraph - 1);
+ fcw->Zc = op->ldpc_enc.z_c;
+ fcw->ncb = op->ldpc_enc.n_cb;
+ fcw->k0 = get_k0(fcw->ncb, fcw->Zc, op->ldpc_enc.basegraph,
+ op->ldpc_enc.rv_index);
+ fcw->rm_e = (default_e == 0) ? op->ldpc_enc.cb_params.e : default_e;
+ fcw->crc_select = check_bit(op->ldpc_enc.op_flags,
+ RTE_BBDEV_LDPC_CRC_24B_ATTACH);
+ fcw->bypass_intlv = check_bit(op->ldpc_enc.op_flags,
+ RTE_BBDEV_LDPC_INTERLEAVER_BYPASS);
+ fcw->mcb_count = num_cb;
+}
+
+/* Enqueue a number of operations to HW and update software rings */
+static inline void
+acc_dma_enqueue(struct acc_queue *q, uint16_t n,
+ struct rte_bbdev_stats *queue_stats)
+{
+ union acc_enqueue_reg_fmt enq_req;
+#ifdef RTE_BBDEV_OFFLOAD_COST
+ uint64_t start_time = 0;
+ queue_stats->acc_offload_cycles = 0;
+#else
+ RTE_SET_USED(queue_stats);
+#endif
+
+ enq_req.val = 0;
+ /* Setting offset, 100b for 256 DMA Desc */
+ enq_req.addr_offset = ACC_DESC_OFFSET;
+
+ /* Split ops into batches */
+ do {
+ union acc_dma_desc *desc;
+ uint16_t enq_batch_size;
+ uint64_t offset;
+ rte_iova_t req_elem_addr;
+
+ enq_batch_size = RTE_MIN(n, MAX_ENQ_BATCH_SIZE);
+
+ /* Set flag on last descriptor in a batch */
+ desc = q->ring_addr + ((q->sw_ring_head + enq_batch_size - 1) &
+ q->sw_ring_wrap_mask);
+ desc->req.last_desc_in_batch = 1;
+
+ /* Calculate the 1st descriptor's address */
+ offset = ((q->sw_ring_head & q->sw_ring_wrap_mask) *
+ sizeof(union acc_dma_desc));
+ req_elem_addr = q->ring_addr_iova + offset;
+
+ /* Fill enqueue struct */
+ enq_req.num_elem = enq_batch_size;
+ /* low 6 bits are not needed */
+ enq_req.req_elem_addr = (uint32_t)(req_elem_addr >> 6);
+
+#ifdef RTE_LIBRTE_BBDEV_DEBUG
+ rte_memdump(stderr, "Req sdone", desc, sizeof(*desc));
+#endif
+ rte_acc_log(DEBUG, "Enqueue %u reqs (phys %#"PRIx64") to reg %p",
+ enq_batch_size,
+ req_elem_addr,
+ (void *)q->mmio_reg_enqueue);
+
+ rte_wmb();
+
+#ifdef RTE_BBDEV_OFFLOAD_COST
+ /* Start time measurement for enqueue function offload. */
+ start_time = rte_rdtsc_precise();
+#endif
+ rte_acc_log(DEBUG, "Debug : MMIO Enqueue");
+ mmio_write(q->mmio_reg_enqueue, enq_req.val);
+
+#ifdef RTE_BBDEV_OFFLOAD_COST
+ queue_stats->acc_offload_cycles +=
+ rte_rdtsc_precise() - start_time;
+#endif
+
+ q->aq_enqueued++;
+ q->sw_ring_head += enq_batch_size;
+ n -= enq_batch_size;
+
+ } while (n);
+
+
+}
+
+/* Convert offset to harq index for harq_layout structure */
+static inline uint32_t hq_index(uint32_t offset)
+{
+ return (offset >> ACC_HARQ_OFFSET_SHIFT) & ACC_HARQ_OFFSET_MASK;
+}
+
+/* Calculates number of CBs in processed encoder TB based on 'r' and input
+ * length.
+ */
+static inline uint8_t
+get_num_cbs_in_tb_enc(struct rte_bbdev_op_turbo_enc *turbo_enc)
+{
+ uint8_t c, c_neg, r, crc24_bits = 0;
+ uint16_t k, k_neg, k_pos;
+ uint8_t cbs_in_tb = 0;
+ int32_t length;
+
+ length = turbo_enc->input.length;
+ r = turbo_enc->tb_params.r;
+ c = turbo_enc->tb_params.c;
+ c_neg = turbo_enc->tb_params.c_neg;
+ k_neg = turbo_enc->tb_params.k_neg;
+ k_pos = turbo_enc->tb_params.k_pos;
+ crc24_bits = 0;
+ if (check_bit(turbo_enc->op_flags, RTE_BBDEV_TURBO_CRC_24B_ATTACH))
+ crc24_bits = 24;
+ while (length > 0 && r < c) {
+ k = (r < c_neg) ? k_neg : k_pos;
+ length -= (k - crc24_bits) >> 3;
+ r++;
+ cbs_in_tb++;
+ }
+
+ return cbs_in_tb;
+}
+
+/* Calculates number of CBs in processed decoder TB based on 'r' and input
+ * length.
+ */
+static inline uint16_t
+get_num_cbs_in_tb_dec(struct rte_bbdev_op_turbo_dec *turbo_dec)
+{
+ uint8_t c, c_neg, r = 0;
+ uint16_t kw, k, k_neg, k_pos, cbs_in_tb = 0;
+ int32_t length;
+
+ length = turbo_dec->input.length;
+ r = turbo_dec->tb_params.r;
+ c = turbo_dec->tb_params.c;
+ c_neg = turbo_dec->tb_params.c_neg;
+ k_neg = turbo_dec->tb_params.k_neg;
+ k_pos = turbo_dec->tb_params.k_pos;
+ while (length > 0 && r < c) {
+ k = (r < c_neg) ? k_neg : k_pos;
+ kw = RTE_ALIGN_CEIL(k + 4, 32) * 3;
+ length -= kw;
+ r++;
+ cbs_in_tb++;
+ }
+
+ return cbs_in_tb;
+}
+
+/* Calculates number of CBs in processed decoder TB based on 'r' and input
+ * length.
+ */
+static inline uint16_t
+get_num_cbs_in_tb_ldpc_dec(struct rte_bbdev_op_ldpc_dec *ldpc_dec)
+{
+ uint16_t r, cbs_in_tb = 0;
+ int32_t length = ldpc_dec->input.length;
+ r = ldpc_dec->tb_params.r;
+ while (length > 0 && r < ldpc_dec->tb_params.c) {
+ length -= (r < ldpc_dec->tb_params.cab) ?
+ ldpc_dec->tb_params.ea :
+ ldpc_dec->tb_params.eb;
+ r++;
+ cbs_in_tb++;
+ }
+ return cbs_in_tb;
+}
+
+/* Check we can mux encode operations with common FCW */
+static inline int16_t
+check_mux(struct rte_bbdev_enc_op **ops, uint16_t num) {
+ uint16_t i;
+ if (num <= 1)
+ return 1;
+ for (i = 1; i < num; ++i) {
+ /* Only mux compatible code blocks */
+ if (memcmp((uint8_t *)(&ops[i]->ldpc_enc) + ACC_ENC_OFFSET,
+ (uint8_t *)(&ops[0]->ldpc_enc) +
+ ACC_ENC_OFFSET,
+ ACC_CMP_ENC_SIZE) != 0)
+ return i;
+ }
+ /* Avoid multiplexing small inbound size frames */
+ int Kp = (ops[0]->ldpc_enc.basegraph == 1 ? 22 : 10) *
+ ops[0]->ldpc_enc.z_c - ops[0]->ldpc_enc.n_filler;
+ if (Kp <= ACC_LIMIT_DL_MUX_BITS)
+ return 1;
+ return num;
+}
+
+/* Check we can mux encode operations with common FCW */
+static inline bool
+cmp_ldpc_dec_op(struct rte_bbdev_dec_op **ops) {
+ /* Only mux compatible code blocks */
+ if (memcmp((uint8_t *)(&ops[0]->ldpc_dec) + ACC_DEC_OFFSET,
+ (uint8_t *)(&ops[1]->ldpc_dec) +
+ ACC_DEC_OFFSET, ACC_CMP_DEC_SIZE) != 0) {
+ return false;
+ } else
+ return true;
+}
+
+/**
+ * Fills descriptor with data pointers of one block type.
+ *
+ * @param desc
+ * Pointer to DMA descriptor.
+ * @param input
+ * Pointer to pointer to input data which will be encoded. It can be changed
+ * and points to next segment in scatter-gather case.
+ * @param offset
+ * Input offset in rte_mbuf structure. It is used for calculating the point
+ * where data is starting.
+ * @param cb_len
+ * Length of currently processed Code Block
+ * @param seg_total_left
+ * It indicates how many bytes still left in segment (mbuf) for further
+ * processing.
+ * @param op_flags
+ * Store information about device capabilities
+ * @param next_triplet
+ * Index for ACC200 DMA Descriptor triplet
+ * @param scattergather
+ * Flag to support scatter-gather for the mbuf
+ *
+ * @return
+ * Returns index of next triplet on success, other value if lengths of
+ * pkt and processed cb do not match.
+ *
+ */
+static inline int
+acc_dma_fill_blk_type_in(struct acc_dma_req_desc *desc,
+ struct rte_mbuf **input, uint32_t *offset, uint32_t cb_len,
+ uint32_t *seg_total_left, int next_triplet,
+ bool scattergather)
+{
+ uint32_t part_len;
+ struct rte_mbuf *m = *input;
+ if (scattergather)
+ part_len = (*seg_total_left < cb_len) ?
+ *seg_total_left : cb_len;
+ else
+ part_len = cb_len;
+ cb_len -= part_len;
+ *seg_total_left -= part_len;
+
+ desc->data_ptrs[next_triplet].address =
+ rte_pktmbuf_iova_offset(m, *offset);
+ desc->data_ptrs[next_triplet].blen = part_len;
+ desc->data_ptrs[next_triplet].blkid = ACC_DMA_BLKID_IN;
+ desc->data_ptrs[next_triplet].last = 0;
+ desc->data_ptrs[next_triplet].dma_ext = 0;
+ *offset += part_len;
+ next_triplet++;
+
+ while (cb_len > 0) {
+ if (next_triplet < ACC_DMA_MAX_NUM_POINTERS_IN && m->next != NULL) {
+
+ m = m->next;
+ *seg_total_left = rte_pktmbuf_data_len(m);
+ part_len = (*seg_total_left < cb_len) ?
+ *seg_total_left :
+ cb_len;
+ desc->data_ptrs[next_triplet].address =
+ rte_pktmbuf_iova_offset(m, 0);
+ desc->data_ptrs[next_triplet].blen = part_len;
+ desc->data_ptrs[next_triplet].blkid =
+ ACC_DMA_BLKID_IN;
+ desc->data_ptrs[next_triplet].last = 0;
+ desc->data_ptrs[next_triplet].dma_ext = 0;
+ cb_len -= part_len;
+ *seg_total_left -= part_len;
+ /* Initializing offset for next segment (mbuf) */
+ *offset = part_len;
+ next_triplet++;
+ } else {
+ rte_acc_log(ERR,
+ "Some data still left for processing: "
+ "data_left: %u, next_triplet: %u, next_mbuf: %p",
+ cb_len, next_triplet, m->next);
+ return -EINVAL;
+ }
+ }
+ /* Storing new mbuf as it could be changed in scatter-gather case*/
+ *input = m;
+
+ return next_triplet;
+}
+
+/* Fills descriptor with data pointers of one block type.
+ * Returns index of next triplet
+ */
+static inline int
+acc_dma_fill_blk_type(struct acc_dma_req_desc *desc,
+ struct rte_mbuf *mbuf, uint32_t offset,
+ uint32_t len, int next_triplet, int blk_id)
+{
+ desc->data_ptrs[next_triplet].address =
+ rte_pktmbuf_iova_offset(mbuf, offset);
+ desc->data_ptrs[next_triplet].blen = len;
+ desc->data_ptrs[next_triplet].blkid = blk_id;
+ desc->data_ptrs[next_triplet].last = 0;
+ desc->data_ptrs[next_triplet].dma_ext = 0;
+ next_triplet++;
+
+ return next_triplet;
+}
+
+static inline void
+acc_header_init(struct acc_dma_req_desc *desc)
+{
+ desc->word0 = ACC_DMA_DESC_TYPE;
+ desc->word1 = 0; /**< Timestamp could be disabled */
+ desc->word2 = 0;
+ desc->word3 = 0;
+ desc->numCBs = 1;
+}
+
+#ifdef RTE_LIBRTE_BBDEV_DEBUG
+/* Check if any input data is unexpectedly left for processing */
+static inline int
+check_mbuf_total_left(uint32_t mbuf_total_left)
+{
+ if (mbuf_total_left == 0)
+ return 0;
+ rte_acc_log(ERR,
+ "Some date still left for processing: mbuf_total_left = %u",
+ mbuf_total_left);
+ return -EINVAL;
+}
+#endif
+
+static inline int
+acc_dma_desc_te_fill(struct rte_bbdev_enc_op *op,
+ struct acc_dma_req_desc *desc, struct rte_mbuf **input,
+ struct rte_mbuf *output, uint32_t *in_offset,
+ uint32_t *out_offset, uint32_t *out_length,
+ uint32_t *mbuf_total_left, uint32_t *seg_total_left, uint8_t r)
+{
+ int next_triplet = 1; /* FCW already done */
+ uint32_t e, ea, eb, length;
+ uint16_t k, k_neg, k_pos;
+ uint8_t cab, c_neg;
+
+ desc->word0 = ACC_DMA_DESC_TYPE;
+ desc->word1 = 0; /**< Timestamp could be disabled */
+ desc->word2 = 0;
+ desc->word3 = 0;
+ desc->numCBs = 1;
+
+ if (op->turbo_enc.code_block_mode == RTE_BBDEV_TRANSPORT_BLOCK) {
+ ea = op->turbo_enc.tb_params.ea;
+ eb = op->turbo_enc.tb_params.eb;
+ cab = op->turbo_enc.tb_params.cab;
+ k_neg = op->turbo_enc.tb_params.k_neg;
+ k_pos = op->turbo_enc.tb_params.k_pos;
+ c_neg = op->turbo_enc.tb_params.c_neg;
+ e = (r < cab) ? ea : eb;
+ k = (r < c_neg) ? k_neg : k_pos;
+ } else {
+ e = op->turbo_enc.cb_params.e;
+ k = op->turbo_enc.cb_params.k;
+ }
+
+ if (check_bit(op->turbo_enc.op_flags, RTE_BBDEV_TURBO_CRC_24B_ATTACH))
+ length = (k - 24) >> 3;
+ else
+ length = k >> 3;
+
+ if (unlikely((*mbuf_total_left == 0) || (*mbuf_total_left < length))) {
+ rte_acc_log(ERR,
+ "Mismatch between mbuf length and included CB sizes: mbuf len %u, cb len %u",
+ *mbuf_total_left, length);
+ return -1;
+ }
+
+ next_triplet = acc_dma_fill_blk_type_in(desc, input, in_offset,
+ length, seg_total_left, next_triplet,
+ check_bit(op->turbo_enc.op_flags,
+ RTE_BBDEV_TURBO_ENC_SCATTER_GATHER));
+ if (unlikely(next_triplet < 0)) {
+ rte_acc_log(ERR,
+ "Mismatch between data to process and mbuf data length in bbdev_op: %p",
+ op);
+ return -1;
+ }
+ desc->data_ptrs[next_triplet - 1].last = 1;
+ desc->m2dlen = next_triplet;
+ *mbuf_total_left -= length;
+
+ /* Set output length */
+ if (check_bit(op->turbo_enc.op_flags, RTE_BBDEV_TURBO_RATE_MATCH))
+ /* Integer round up division by 8 */
+ *out_length = (e + 7) >> 3;
+ else
+ *out_length = (k >> 3) * 3 + 2;
+
+ next_triplet = acc_dma_fill_blk_type(desc, output, *out_offset,
+ *out_length, next_triplet, ACC_DMA_BLKID_OUT_ENC);
+ if (unlikely(next_triplet < 0)) {
+ rte_acc_log(ERR,
+ "Mismatch between data to process and mbuf data length in bbdev_op: %p",
+ op);
+ return -1;
+ }
+ op->turbo_enc.output.length += *out_length;
+ *out_offset += *out_length;
+ desc->data_ptrs[next_triplet - 1].last = 1;
+ desc->d2mlen = next_triplet - desc->m2dlen;
+
+ desc->op_addr = op;
+
+ return 0;
+}
+
+static inline int
+acc_pci_remove(struct rte_pci_device *pci_dev)
+{
+ struct rte_bbdev *bbdev;
+ int ret;
+ uint8_t dev_id;
+
+ if (pci_dev == NULL)
+ return -EINVAL;
+
+ /* Find device */
+ bbdev = rte_bbdev_get_named_dev(pci_dev->device.name);
+ if (bbdev == NULL) {
+ rte_acc_log(CRIT,
+ "Couldn't find HW dev \"%s\" to uninitialise it",
+ pci_dev->device.name);
+ return -ENODEV;
+ }
+ dev_id = bbdev->data->dev_id;
+
+ /* free device private memory before close */
+ rte_free(bbdev->data->dev_private);
+
+ /* Close device */
+ ret = rte_bbdev_close(dev_id);
+ if (ret < 0)
+ rte_acc_log(ERR,
+ "Device %i failed to close during uninit: %i",
+ dev_id, ret);
+
+ /* release bbdev from library */
+ rte_bbdev_release(bbdev);
+
+ return 0;
+}
+
+#endif /* _ACC_COMMON_H_ */
diff --git a/drivers/baseband/acc100/rte_acc100_cfg.h b/drivers/baseband/acc100/rte_acc100_cfg.h
index b70803d96d..732c03be24 100644
--- a/drivers/baseband/acc100/rte_acc100_cfg.h
+++ b/drivers/baseband/acc100/rte_acc100_cfg.h
@@ -1,5 +1,5 @@
/* SPDX-License-Identifier: BSD-3-Clause
- * Copyright(c) 2020 Intel Corporation
+ * Copyright(c) 2022 Intel Corporation
*/
#ifndef _RTE_ACC100_CFG_H_
@@ -18,76 +18,12 @@
#include <stdint.h>
#include <stdbool.h>
+#include "rte_acc_common_cfg.h"
#ifdef __cplusplus
extern "C" {
#endif
-/**< Number of Virtual Functions ACC100 supports */
-#define RTE_ACC100_NUM_VFS 16
-/**
- * Definition of Queue Topology for ACC100 Configuration
- * Some level of details is abstracted out to expose a clean interface
- * given that comprehensive flexibility is not required
- */
-struct rte_acc100_queue_topology {
- /** Number of QGroups in incremental order of priority */
- uint16_t num_qgroups;
- /**
- * All QGroups have the same number of AQs here.
- * Note : Could be made a 16-array if more flexibility is really
- * required
- */
- uint16_t num_aqs_per_groups;
- /**
- * Depth of the AQs is the same of all QGroups here. Log2 Enum : 2^N
- * Note : Could be made a 16-array if more flexibility is really
- * required
- */
- uint16_t aq_depth_log2;
- /**
- * Index of the first Queue Group Index - assuming contiguity
- * Initialized as -1
- */
- int8_t first_qgroup_index;
-};
-
-/**
- * Definition of Arbitration related parameters for ACC100 Configuration
- */
-struct rte_acc100_arbitration {
- /** Default Weight for VF Fairness Arbitration */
- uint16_t round_robin_weight;
- uint32_t gbr_threshold1; /**< Guaranteed Bitrate Threshold 1 */
- uint32_t gbr_threshold2; /**< Guaranteed Bitrate Threshold 2 */
-};
-
-/**
- * Structure to pass ACC100 configuration.
- * Note: all VF Bundles will have the same configuration.
- */
-struct rte_acc100_conf {
- bool pf_mode_en; /**< 1 if PF is used for dataplane, 0 for VFs */
- /** 1 if input '1' bit is represented by a positive LLR value, 0 if '1'
- * bit is represented by a negative value.
- */
- bool input_pos_llr_1_bit;
- /** 1 if output '1' bit is represented by a positive value, 0 if '1'
- * bit is represented by a negative value.
- */
- bool output_pos_llr_1_bit;
- uint16_t num_vf_bundles; /**< Number of VF bundles to setup */
- /** Queue topology for each operation type */
- struct rte_acc100_queue_topology q_ul_4g;
- struct rte_acc100_queue_topology q_dl_4g;
- struct rte_acc100_queue_topology q_ul_5g;
- struct rte_acc100_queue_topology q_dl_5g;
- /** Arbitration configuration for each operation type */
- struct rte_acc100_arbitration arb_ul_4g[RTE_ACC100_NUM_VFS];
- struct rte_acc100_arbitration arb_dl_4g[RTE_ACC100_NUM_VFS];
- struct rte_acc100_arbitration arb_ul_5g[RTE_ACC100_NUM_VFS];
- struct rte_acc100_arbitration arb_dl_5g[RTE_ACC100_NUM_VFS];
-};
/**
* Configure a ACC100/ACC101 device in PF mode notably for bbdev-test
@@ -104,7 +40,7 @@ struct rte_acc100_conf {
*/
__rte_experimental
int
-rte_acc10x_configure(const char *dev_name, struct rte_acc100_conf *conf);
+rte_acc10x_configure(const char *dev_name, struct rte_acc_conf *conf);
#ifdef __cplusplus
}
diff --git a/drivers/baseband/acc100/rte_acc100_pmd.c b/drivers/baseband/acc100/rte_acc100_pmd.c
index 18ec04a7b8..e84d9f2511 100644
--- a/drivers/baseband/acc100/rte_acc100_pmd.c
+++ b/drivers/baseband/acc100/rte_acc100_pmd.c
@@ -30,48 +30,6 @@ RTE_LOG_REGISTER_DEFAULT(acc100_logtype, DEBUG);
RTE_LOG_REGISTER_DEFAULT(acc100_logtype, NOTICE);
#endif
-/* Write to MMIO register address */
-static inline void
-mmio_write(void *addr, uint32_t value)
-{
- *((volatile uint32_t *)(addr)) = rte_cpu_to_le_32(value);
-}
-
-/* Write a register of a ACC100 device */
-static inline void
-acc100_reg_write(struct acc100_device *d, uint32_t offset, uint32_t value)
-{
- void *reg_addr = RTE_PTR_ADD(d->mmio_base, offset);
- mmio_write(reg_addr, value);
- usleep(ACC100_LONG_WAIT);
-}
-
-/* Read a register of a ACC100 device */
-static inline uint32_t
-acc100_reg_read(struct acc100_device *d, uint32_t offset)
-{
-
- void *reg_addr = RTE_PTR_ADD(d->mmio_base, offset);
- uint32_t ret = *((volatile uint32_t *)(reg_addr));
- return rte_le_to_cpu_32(ret);
-}
-
-/* Basic Implementation of Log2 for exact 2^N */
-static inline uint32_t
-log2_basic(uint32_t value)
-{
- return (value == 0) ? 0 : rte_bsf32(value);
-}
-
-/* Calculate memory alignment offset assuming alignment is 2^N */
-static inline uint32_t
-calc_mem_alignment_offset(void *unaligned_virt_mem, uint32_t alignment)
-{
- rte_iova_t unaligned_phy_mem = rte_malloc_virt2iova(unaligned_virt_mem);
- return (uint32_t)(alignment -
- (unaligned_phy_mem & (alignment-1)));
-}
-
/* Calculate the offset of the enqueue register */
static inline uint32_t
queue_offset(bool pf_device, uint8_t vf_id, uint8_t qgrp_id, uint16_t aq_id)
@@ -88,17 +46,17 @@ enum {UL_4G = 0, UL_5G, DL_4G, DL_5G, NUM_ACC};
/* Return the accelerator enum for a Queue Group Index */
static inline int
-accFromQgid(int qg_idx, const struct rte_acc100_conf *acc100_conf)
+accFromQgid(int qg_idx, const struct rte_acc_conf *acc_conf)
{
int accQg[ACC100_NUM_QGRPS];
int NumQGroupsPerFn[NUM_ACC];
int acc, qgIdx, qgIndex = 0;
for (qgIdx = 0; qgIdx < ACC100_NUM_QGRPS; qgIdx++)
accQg[qgIdx] = 0;
- NumQGroupsPerFn[UL_4G] = acc100_conf->q_ul_4g.num_qgroups;
- NumQGroupsPerFn[UL_5G] = acc100_conf->q_ul_5g.num_qgroups;
- NumQGroupsPerFn[DL_4G] = acc100_conf->q_dl_4g.num_qgroups;
- NumQGroupsPerFn[DL_5G] = acc100_conf->q_dl_5g.num_qgroups;
+ NumQGroupsPerFn[UL_4G] = acc_conf->q_ul_4g.num_qgroups;
+ NumQGroupsPerFn[UL_5G] = acc_conf->q_ul_5g.num_qgroups;
+ NumQGroupsPerFn[DL_4G] = acc_conf->q_dl_4g.num_qgroups;
+ NumQGroupsPerFn[DL_5G] = acc_conf->q_dl_5g.num_qgroups;
for (acc = UL_4G; acc < NUM_ACC; acc++)
for (qgIdx = 0; qgIdx < NumQGroupsPerFn[acc]; qgIdx++)
accQg[qgIndex++] = acc;
@@ -108,23 +66,23 @@ accFromQgid(int qg_idx, const struct rte_acc100_conf *acc100_conf)
/* Return the queue topology for a Queue Group Index */
static inline void
-qtopFromAcc(struct rte_acc100_queue_topology **qtop, int acc_enum,
- struct rte_acc100_conf *acc100_conf)
+qtopFromAcc(struct rte_acc_queue_topology **qtop, int acc_enum,
+ struct rte_acc_conf *acc_conf)
{
- struct rte_acc100_queue_topology *p_qtop;
+ struct rte_acc_queue_topology *p_qtop;
p_qtop = NULL;
switch (acc_enum) {
case UL_4G:
- p_qtop = &(acc100_conf->q_ul_4g);
+ p_qtop = &(acc_conf->q_ul_4g);
break;
case UL_5G:
- p_qtop = &(acc100_conf->q_ul_5g);
+ p_qtop = &(acc_conf->q_ul_5g);
break;
case DL_4G:
- p_qtop = &(acc100_conf->q_dl_4g);
+ p_qtop = &(acc_conf->q_dl_4g);
break;
case DL_5G:
- p_qtop = &(acc100_conf->q_dl_5g);
+ p_qtop = &(acc_conf->q_dl_5g);
break;
default:
/* NOTREACHED */
@@ -136,11 +94,11 @@ qtopFromAcc(struct rte_acc100_queue_topology **qtop, int acc_enum,
/* Return the AQ depth for a Queue Group Index */
static inline int
-aqDepth(int qg_idx, struct rte_acc100_conf *acc100_conf)
+aqDepth(int qg_idx, struct rte_acc_conf *acc_conf)
{
- struct rte_acc100_queue_topology *q_top = NULL;
- int acc_enum = accFromQgid(qg_idx, acc100_conf);
- qtopFromAcc(&q_top, acc_enum, acc100_conf);
+ struct rte_acc_queue_topology *q_top = NULL;
+ int acc_enum = accFromQgid(qg_idx, acc_conf);
+ qtopFromAcc(&q_top, acc_enum, acc_conf);
if (unlikely(q_top == NULL))
return 1;
return RTE_MAX(1, q_top->aq_depth_log2);
@@ -148,39 +106,39 @@ aqDepth(int qg_idx, struct rte_acc100_conf *acc100_conf)
/* Return the AQ depth for a Queue Group Index */
static inline int
-aqNum(int qg_idx, struct rte_acc100_conf *acc100_conf)
+aqNum(int qg_idx, struct rte_acc_conf *acc_conf)
{
- struct rte_acc100_queue_topology *q_top = NULL;
- int acc_enum = accFromQgid(qg_idx, acc100_conf);
- qtopFromAcc(&q_top, acc_enum, acc100_conf);
+ struct rte_acc_queue_topology *q_top = NULL;
+ int acc_enum = accFromQgid(qg_idx, acc_conf);
+ qtopFromAcc(&q_top, acc_enum, acc_conf);
if (unlikely(q_top == NULL))
return 0;
return q_top->num_aqs_per_groups;
}
static void
-initQTop(struct rte_acc100_conf *acc100_conf)
+initQTop(struct rte_acc_conf *acc_conf)
{
- acc100_conf->q_ul_4g.num_aqs_per_groups = 0;
- acc100_conf->q_ul_4g.num_qgroups = 0;
- acc100_conf->q_ul_4g.first_qgroup_index = -1;
- acc100_conf->q_ul_5g.num_aqs_per_groups = 0;
- acc100_conf->q_ul_5g.num_qgroups = 0;
- acc100_conf->q_ul_5g.first_qgroup_index = -1;
- acc100_conf->q_dl_4g.num_aqs_per_groups = 0;
- acc100_conf->q_dl_4g.num_qgroups = 0;
- acc100_conf->q_dl_4g.first_qgroup_index = -1;
- acc100_conf->q_dl_5g.num_aqs_per_groups = 0;
- acc100_conf->q_dl_5g.num_qgroups = 0;
- acc100_conf->q_dl_5g.first_qgroup_index = -1;
+ acc_conf->q_ul_4g.num_aqs_per_groups = 0;
+ acc_conf->q_ul_4g.num_qgroups = 0;
+ acc_conf->q_ul_4g.first_qgroup_index = -1;
+ acc_conf->q_ul_5g.num_aqs_per_groups = 0;
+ acc_conf->q_ul_5g.num_qgroups = 0;
+ acc_conf->q_ul_5g.first_qgroup_index = -1;
+ acc_conf->q_dl_4g.num_aqs_per_groups = 0;
+ acc_conf->q_dl_4g.num_qgroups = 0;
+ acc_conf->q_dl_4g.first_qgroup_index = -1;
+ acc_conf->q_dl_5g.num_aqs_per_groups = 0;
+ acc_conf->q_dl_5g.num_qgroups = 0;
+ acc_conf->q_dl_5g.first_qgroup_index = -1;
}
static inline void
-updateQtop(uint8_t acc, uint8_t qg, struct rte_acc100_conf *acc100_conf,
- struct acc100_device *d) {
+updateQtop(uint8_t acc, uint8_t qg, struct rte_acc_conf *acc_conf,
+ struct acc_device *d) {
uint32_t reg;
- struct rte_acc100_queue_topology *q_top = NULL;
- qtopFromAcc(&q_top, acc, acc100_conf);
+ struct rte_acc_queue_topology *q_top = NULL;
+ qtopFromAcc(&q_top, acc, acc_conf);
if (unlikely(q_top == NULL))
return;
uint16_t aq;
@@ -188,17 +146,17 @@ updateQtop(uint8_t acc, uint8_t qg, struct rte_acc100_conf *acc100_conf,
if (q_top->first_qgroup_index == -1) {
q_top->first_qgroup_index = qg;
/* Can be optimized to assume all are enabled by default */
- reg = acc100_reg_read(d, queue_offset(d->pf_device,
+ reg = acc_reg_read(d, queue_offset(d->pf_device,
0, qg, ACC100_NUM_AQS - 1));
- if (reg & ACC100_QUEUE_ENABLE) {
+ if (reg & ACC_QUEUE_ENABLE) {
q_top->num_aqs_per_groups = ACC100_NUM_AQS;
return;
}
q_top->num_aqs_per_groups = 0;
for (aq = 0; aq < ACC100_NUM_AQS; aq++) {
- reg = acc100_reg_read(d, queue_offset(d->pf_device,
+ reg = acc_reg_read(d, queue_offset(d->pf_device,
0, qg, aq));
- if (reg & ACC100_QUEUE_ENABLE)
+ if (reg & ACC_QUEUE_ENABLE)
q_top->num_aqs_per_groups++;
}
}
@@ -208,8 +166,8 @@ updateQtop(uint8_t acc, uint8_t qg, struct rte_acc100_conf *acc100_conf,
static inline void
fetch_acc100_config(struct rte_bbdev *dev)
{
- struct acc100_device *d = dev->data->dev_private;
- struct rte_acc100_conf *acc100_conf = &d->acc100_conf;
+ struct acc_device *d = dev->data->dev_private;
+ struct rte_acc_conf *acc_conf = &d->acc_conf;
const struct acc100_registry_addr *reg_addr;
uint8_t acc, qg;
uint32_t reg, reg_aq, reg_len0, reg_len1;
@@ -225,201 +183,80 @@ fetch_acc100_config(struct rte_bbdev *dev)
else
reg_addr = &vf_reg_addr;
- d->ddr_size = (1 + acc100_reg_read(d, reg_addr->ddr_range)) << 10;
+ d->ddr_size = (1 + acc_reg_read(d, reg_addr->ddr_range)) << 10;
/* Single VF Bundle by VF */
- acc100_conf->num_vf_bundles = 1;
- initQTop(acc100_conf);
-
- struct rte_acc100_queue_topology *q_top = NULL;
- int qman_func_id[ACC100_NUM_ACCS] = {ACC100_ACCMAP_0, ACC100_ACCMAP_1,
- ACC100_ACCMAP_2, ACC100_ACCMAP_3, ACC100_ACCMAP_4};
- reg = acc100_reg_read(d, reg_addr->qman_group_func);
- for (qg = 0; qg < ACC100_NUM_QGRPS_PER_WORD; qg++) {
- reg_aq = acc100_reg_read(d,
+ acc_conf->num_vf_bundles = 1;
+ initQTop(acc_conf);
+
+ struct rte_acc_queue_topology *q_top = NULL;
+ int qman_func_id[ACC100_NUM_ACCS] = {ACC_ACCMAP_0, ACC_ACCMAP_1,
+ ACC_ACCMAP_2, ACC_ACCMAP_3, ACC_ACCMAP_4};
+ reg = acc_reg_read(d, reg_addr->qman_group_func);
+ for (qg = 0; qg < ACC_NUM_QGRPS_PER_WORD; qg++) {
+ reg_aq = acc_reg_read(d,
queue_offset(d->pf_device, 0, qg, 0));
- if (reg_aq & ACC100_QUEUE_ENABLE) {
+ if (reg_aq & ACC_QUEUE_ENABLE) {
uint32_t idx = (reg >> (qg * 4)) & 0x7;
if (idx < ACC100_NUM_ACCS) {
acc = qman_func_id[idx];
- updateQtop(acc, qg, acc100_conf, d);
+ updateQtop(acc, qg, acc_conf, d);
}
}
}
/* Check the depth of the AQs*/
- reg_len0 = acc100_reg_read(d, reg_addr->depth_log0_offset);
- reg_len1 = acc100_reg_read(d, reg_addr->depth_log1_offset);
+ reg_len0 = acc_reg_read(d, reg_addr->depth_log0_offset);
+ reg_len1 = acc_reg_read(d, reg_addr->depth_log1_offset);
for (acc = 0; acc < NUM_ACC; acc++) {
- qtopFromAcc(&q_top, acc, acc100_conf);
- if (q_top->first_qgroup_index < ACC100_NUM_QGRPS_PER_WORD)
+ qtopFromAcc(&q_top, acc, acc_conf);
+ if (q_top->first_qgroup_index < ACC_NUM_QGRPS_PER_WORD)
q_top->aq_depth_log2 = (reg_len0 >>
(q_top->first_qgroup_index * 4))
& 0xF;
else
q_top->aq_depth_log2 = (reg_len1 >>
((q_top->first_qgroup_index -
- ACC100_NUM_QGRPS_PER_WORD) * 4))
+ ACC_NUM_QGRPS_PER_WORD) * 4))
& 0xF;
}
/* Read PF mode */
if (d->pf_device) {
- reg_mode = acc100_reg_read(d, HWPfHiPfMode);
- acc100_conf->pf_mode_en = (reg_mode == ACC100_PF_VAL) ? 1 : 0;
+ reg_mode = acc_reg_read(d, HWPfHiPfMode);
+ acc_conf->pf_mode_en = (reg_mode == ACC_PF_VAL) ? 1 : 0;
}
rte_bbdev_log_debug(
"%s Config LLR SIGN IN/OUT %s %s QG %u %u %u %u AQ %u %u %u %u Len %u %u %u %u\n",
(d->pf_device) ? "PF" : "VF",
- (acc100_conf->input_pos_llr_1_bit) ? "POS" : "NEG",
- (acc100_conf->output_pos_llr_1_bit) ? "POS" : "NEG",
- acc100_conf->q_ul_4g.num_qgroups,
- acc100_conf->q_dl_4g.num_qgroups,
- acc100_conf->q_ul_5g.num_qgroups,
- acc100_conf->q_dl_5g.num_qgroups,
- acc100_conf->q_ul_4g.num_aqs_per_groups,
- acc100_conf->q_dl_4g.num_aqs_per_groups,
- acc100_conf->q_ul_5g.num_aqs_per_groups,
- acc100_conf->q_dl_5g.num_aqs_per_groups,
- acc100_conf->q_ul_4g.aq_depth_log2,
- acc100_conf->q_dl_4g.aq_depth_log2,
- acc100_conf->q_ul_5g.aq_depth_log2,
- acc100_conf->q_dl_5g.aq_depth_log2);
-}
-
-static void
-free_base_addresses(void **base_addrs, int size)
-{
- int i;
- for (i = 0; i < size; i++)
- rte_free(base_addrs[i]);
-}
-
-static inline uint32_t
-get_desc_len(void)
-{
- return sizeof(union acc100_dma_desc);
-}
-
-/* Allocate the 2 * 64MB block for the sw rings */
-static int
-alloc_2x64mb_sw_rings_mem(struct rte_bbdev *dev, struct acc100_device *d,
- int socket)
-{
- uint32_t sw_ring_size = ACC100_SIZE_64MBYTE;
- d->sw_rings_base = rte_zmalloc_socket(dev->device->driver->name,
- 2 * sw_ring_size, RTE_CACHE_LINE_SIZE, socket);
- if (d->sw_rings_base == NULL) {
- rte_bbdev_log(ERR, "Failed to allocate memory for %s:%u",
- dev->device->driver->name,
- dev->data->dev_id);
- return -ENOMEM;
- }
- uint32_t next_64mb_align_offset = calc_mem_alignment_offset(
- d->sw_rings_base, ACC100_SIZE_64MBYTE);
- d->sw_rings = RTE_PTR_ADD(d->sw_rings_base, next_64mb_align_offset);
- d->sw_rings_iova = rte_malloc_virt2iova(d->sw_rings_base) +
- next_64mb_align_offset;
- d->sw_ring_size = ACC100_MAX_QUEUE_DEPTH * get_desc_len();
- d->sw_ring_max_depth = ACC100_MAX_QUEUE_DEPTH;
-
- return 0;
-}
-
-/* Attempt to allocate minimised memory space for sw rings */
-static void
-alloc_sw_rings_min_mem(struct rte_bbdev *dev, struct acc100_device *d,
- uint16_t num_queues, int socket)
-{
- rte_iova_t sw_rings_base_iova, next_64mb_align_addr_iova;
- uint32_t next_64mb_align_offset;
- rte_iova_t sw_ring_iova_end_addr;
- void *base_addrs[ACC100_SW_RING_MEM_ALLOC_ATTEMPTS];
- void *sw_rings_base;
- int i = 0;
- uint32_t q_sw_ring_size = ACC100_MAX_QUEUE_DEPTH * get_desc_len();
- uint32_t dev_sw_ring_size = q_sw_ring_size * num_queues;
-
- /* Find an aligned block of memory to store sw rings */
- while (i < ACC100_SW_RING_MEM_ALLOC_ATTEMPTS) {
- /*
- * sw_ring allocated memory is guaranteed to be aligned to
- * q_sw_ring_size at the condition that the requested size is
- * less than the page size
- */
- sw_rings_base = rte_zmalloc_socket(
- dev->device->driver->name,
- dev_sw_ring_size, q_sw_ring_size, socket);
-
- if (sw_rings_base == NULL) {
- rte_bbdev_log(ERR,
- "Failed to allocate memory for %s:%u",
- dev->device->driver->name,
- dev->data->dev_id);
- break;
- }
-
- sw_rings_base_iova = rte_malloc_virt2iova(sw_rings_base);
- next_64mb_align_offset = calc_mem_alignment_offset(
- sw_rings_base, ACC100_SIZE_64MBYTE);
- next_64mb_align_addr_iova = sw_rings_base_iova +
- next_64mb_align_offset;
- sw_ring_iova_end_addr = sw_rings_base_iova + dev_sw_ring_size;
-
- /* Check if the end of the sw ring memory block is before the
- * start of next 64MB aligned mem address
- */
- if (sw_ring_iova_end_addr < next_64mb_align_addr_iova) {
- d->sw_rings_iova = sw_rings_base_iova;
- d->sw_rings = sw_rings_base;
- d->sw_rings_base = sw_rings_base;
- d->sw_ring_size = q_sw_ring_size;
- d->sw_ring_max_depth = ACC100_MAX_QUEUE_DEPTH;
- break;
- }
- /* Store the address of the unaligned mem block */
- base_addrs[i] = sw_rings_base;
- i++;
- }
-
- /* Free all unaligned blocks of mem allocated in the loop */
- free_base_addresses(base_addrs, i);
-}
-
-/*
- * Find queue_id of a device queue based on details from the Info Ring.
- * If a queue isn't found UINT16_MAX is returned.
- */
-static inline uint16_t
-get_queue_id_from_ring_info(struct rte_bbdev_data *data,
- const union acc100_info_ring_data ring_data)
-{
- uint16_t queue_id;
-
- for (queue_id = 0; queue_id < data->num_queues; ++queue_id) {
- struct acc100_queue *acc100_q =
- data->queues[queue_id].queue_private;
- if (acc100_q != NULL && acc100_q->aq_id == ring_data.aq_id &&
- acc100_q->qgrp_id == ring_data.qg_id &&
- acc100_q->vf_id == ring_data.vf_id)
- return queue_id;
- }
-
- return UINT16_MAX;
+ (acc_conf->input_pos_llr_1_bit) ? "POS" : "NEG",
+ (acc_conf->output_pos_llr_1_bit) ? "POS" : "NEG",
+ acc_conf->q_ul_4g.num_qgroups,
+ acc_conf->q_dl_4g.num_qgroups,
+ acc_conf->q_ul_5g.num_qgroups,
+ acc_conf->q_dl_5g.num_qgroups,
+ acc_conf->q_ul_4g.num_aqs_per_groups,
+ acc_conf->q_dl_4g.num_aqs_per_groups,
+ acc_conf->q_ul_5g.num_aqs_per_groups,
+ acc_conf->q_dl_5g.num_aqs_per_groups,
+ acc_conf->q_ul_4g.aq_depth_log2,
+ acc_conf->q_dl_4g.aq_depth_log2,
+ acc_conf->q_ul_5g.aq_depth_log2,
+ acc_conf->q_dl_5g.aq_depth_log2);
}
/* Checks PF Info Ring to find the interrupt cause and handles it accordingly */
static inline void
-acc100_check_ir(struct acc100_device *acc100_dev)
+acc100_check_ir(struct acc_device *acc100_dev)
{
- volatile union acc100_info_ring_data *ring_data;
+ volatile union acc_info_ring_data *ring_data;
uint16_t info_ring_head = acc100_dev->info_ring_head;
if (acc100_dev->info_ring == NULL)
return;
ring_data = acc100_dev->info_ring + (acc100_dev->info_ring_head &
- ACC100_INFO_RING_MASK);
+ ACC_INFO_RING_MASK);
while (ring_data->valid) {
if ((ring_data->int_nb < ACC100_PF_INT_DMA_DL_DESC_IRQ) || (
@@ -431,7 +268,7 @@ acc100_check_ir(struct acc100_device *acc100_dev)
ring_data->val = 0;
info_ring_head++;
ring_data = acc100_dev->info_ring +
- (info_ring_head & ACC100_INFO_RING_MASK);
+ (info_ring_head & ACC_INFO_RING_MASK);
}
}
@@ -439,12 +276,12 @@ acc100_check_ir(struct acc100_device *acc100_dev)
static inline void
acc100_pf_interrupt_handler(struct rte_bbdev *dev)
{
- struct acc100_device *acc100_dev = dev->data->dev_private;
- volatile union acc100_info_ring_data *ring_data;
- struct acc100_deq_intr_details deq_intr_det;
+ struct acc_device *acc100_dev = dev->data->dev_private;
+ volatile union acc_info_ring_data *ring_data;
+ struct acc_deq_intr_details deq_intr_det;
ring_data = acc100_dev->info_ring + (acc100_dev->info_ring_head &
- ACC100_INFO_RING_MASK);
+ ACC_INFO_RING_MASK);
while (ring_data->valid) {
@@ -481,7 +318,7 @@ acc100_pf_interrupt_handler(struct rte_bbdev *dev)
++acc100_dev->info_ring_head;
ring_data = acc100_dev->info_ring +
(acc100_dev->info_ring_head &
- ACC100_INFO_RING_MASK);
+ ACC_INFO_RING_MASK);
}
}
@@ -489,12 +326,12 @@ acc100_pf_interrupt_handler(struct rte_bbdev *dev)
static inline void
acc100_vf_interrupt_handler(struct rte_bbdev *dev)
{
- struct acc100_device *acc100_dev = dev->data->dev_private;
- volatile union acc100_info_ring_data *ring_data;
- struct acc100_deq_intr_details deq_intr_det;
+ struct acc_device *acc100_dev = dev->data->dev_private;
+ volatile union acc_info_ring_data *ring_data;
+ struct acc_deq_intr_details deq_intr_det;
ring_data = acc100_dev->info_ring + (acc100_dev->info_ring_head &
- ACC100_INFO_RING_MASK);
+ ACC_INFO_RING_MASK);
while (ring_data->valid) {
@@ -533,7 +370,7 @@ acc100_vf_interrupt_handler(struct rte_bbdev *dev)
ring_data->valid = 0;
++acc100_dev->info_ring_head;
ring_data = acc100_dev->info_ring + (acc100_dev->info_ring_head
- & ACC100_INFO_RING_MASK);
+ & ACC_INFO_RING_MASK);
}
}
@@ -542,7 +379,7 @@ static void
acc100_dev_interrupt_handler(void *cb_arg)
{
struct rte_bbdev *dev = cb_arg;
- struct acc100_device *acc100_dev = dev->data->dev_private;
+ struct acc_device *acc100_dev = dev->data->dev_private;
/* Read info ring */
if (acc100_dev->pf_device)
@@ -555,7 +392,7 @@ acc100_dev_interrupt_handler(void *cb_arg)
static int
allocate_info_ring(struct rte_bbdev *dev)
{
- struct acc100_device *d = dev->data->dev_private;
+ struct acc_device *d = dev->data->dev_private;
const struct acc100_registry_addr *reg_addr;
rte_iova_t info_ring_iova;
uint32_t phys_low, phys_high;
@@ -570,7 +407,7 @@ allocate_info_ring(struct rte_bbdev *dev)
reg_addr = &vf_reg_addr;
/* Allocate InfoRing */
d->info_ring = rte_zmalloc_socket("Info Ring",
- ACC100_INFO_RING_NUM_ENTRIES *
+ ACC_INFO_RING_NUM_ENTRIES *
sizeof(*d->info_ring), RTE_CACHE_LINE_SIZE,
dev->data->socket_id);
if (d->info_ring == NULL) {
@@ -585,11 +422,11 @@ allocate_info_ring(struct rte_bbdev *dev)
/* Setup Info Ring */
phys_high = (uint32_t)(info_ring_iova >> 32);
phys_low = (uint32_t)(info_ring_iova);
- acc100_reg_write(d, reg_addr->info_ring_hi, phys_high);
- acc100_reg_write(d, reg_addr->info_ring_lo, phys_low);
- acc100_reg_write(d, reg_addr->info_ring_en, ACC100_REG_IRQ_EN_ALL);
- d->info_ring_head = (acc100_reg_read(d, reg_addr->info_ring_ptr) &
- 0xFFF) / sizeof(union acc100_info_ring_data);
+ acc_reg_write(d, reg_addr->info_ring_hi, phys_high);
+ acc_reg_write(d, reg_addr->info_ring_lo, phys_low);
+ acc_reg_write(d, reg_addr->info_ring_en, ACC100_REG_IRQ_EN_ALL);
+ d->info_ring_head = (acc_reg_read(d, reg_addr->info_ring_ptr) &
+ 0xFFF) / sizeof(union acc_info_ring_data);
return 0;
}
@@ -599,11 +436,11 @@ static int
acc100_setup_queues(struct rte_bbdev *dev, uint16_t num_queues, int socket_id)
{
uint32_t phys_low, phys_high, value;
- struct acc100_device *d = dev->data->dev_private;
+ struct acc_device *d = dev->data->dev_private;
const struct acc100_registry_addr *reg_addr;
int ret;
- if (d->pf_device && !d->acc100_conf.pf_mode_en) {
+ if (d->pf_device && !d->acc_conf.pf_mode_en) {
rte_bbdev_log(NOTICE,
"%s has PF mode disabled. This PF can't be used.",
dev->data->name);
@@ -629,7 +466,7 @@ acc100_setup_queues(struct rte_bbdev *dev, uint16_t num_queues, int socket_id)
* Note : Assuming only VF0 bundle is used for PF mode
*/
phys_high = (uint32_t)(d->sw_rings_iova >> 32);
- phys_low = (uint32_t)(d->sw_rings_iova & ~(ACC100_SIZE_64MBYTE-1));
+ phys_low = (uint32_t)(d->sw_rings_iova & ~(ACC_SIZE_64MBYTE-1));
/* Choose correct registry addresses for the device type */
if (d->pf_device)
@@ -642,23 +479,23 @@ acc100_setup_queues(struct rte_bbdev *dev, uint16_t num_queues, int socket_id)
/* Release AXI from PF */
if (d->pf_device)
- acc100_reg_write(d, HWPfDmaAxiControl, 1);
+ acc_reg_write(d, HWPfDmaAxiControl, 1);
- acc100_reg_write(d, reg_addr->dma_ring_ul5g_hi, phys_high);
- acc100_reg_write(d, reg_addr->dma_ring_ul5g_lo, phys_low);
- acc100_reg_write(d, reg_addr->dma_ring_dl5g_hi, phys_high);
- acc100_reg_write(d, reg_addr->dma_ring_dl5g_lo, phys_low);
- acc100_reg_write(d, reg_addr->dma_ring_ul4g_hi, phys_high);
- acc100_reg_write(d, reg_addr->dma_ring_ul4g_lo, phys_low);
- acc100_reg_write(d, reg_addr->dma_ring_dl4g_hi, phys_high);
- acc100_reg_write(d, reg_addr->dma_ring_dl4g_lo, phys_low);
+ acc_reg_write(d, reg_addr->dma_ring_ul5g_hi, phys_high);
+ acc_reg_write(d, reg_addr->dma_ring_ul5g_lo, phys_low);
+ acc_reg_write(d, reg_addr->dma_ring_dl5g_hi, phys_high);
+ acc_reg_write(d, reg_addr->dma_ring_dl5g_lo, phys_low);
+ acc_reg_write(d, reg_addr->dma_ring_ul4g_hi, phys_high);
+ acc_reg_write(d, reg_addr->dma_ring_ul4g_lo, phys_low);
+ acc_reg_write(d, reg_addr->dma_ring_dl4g_hi, phys_high);
+ acc_reg_write(d, reg_addr->dma_ring_dl4g_lo, phys_low);
/*
* Configure Ring Size to the max queue ring size
* (used for wrapping purpose)
*/
value = log2_basic(d->sw_ring_size / 64);
- acc100_reg_write(d, reg_addr->ring_size, value);
+ acc_reg_write(d, reg_addr->ring_size, value);
/* Configure tail pointer for use when SDONE enabled */
d->tail_ptrs = rte_zmalloc_socket(
@@ -676,14 +513,14 @@ acc100_setup_queues(struct rte_bbdev *dev, uint16_t num_queues, int socket_id)
phys_high = (uint32_t)(d->tail_ptr_iova >> 32);
phys_low = (uint32_t)(d->tail_ptr_iova);
- acc100_reg_write(d, reg_addr->tail_ptrs_ul5g_hi, phys_high);
- acc100_reg_write(d, reg_addr->tail_ptrs_ul5g_lo, phys_low);
- acc100_reg_write(d, reg_addr->tail_ptrs_dl5g_hi, phys_high);
- acc100_reg_write(d, reg_addr->tail_ptrs_dl5g_lo, phys_low);
- acc100_reg_write(d, reg_addr->tail_ptrs_ul4g_hi, phys_high);
- acc100_reg_write(d, reg_addr->tail_ptrs_ul4g_lo, phys_low);
- acc100_reg_write(d, reg_addr->tail_ptrs_dl4g_hi, phys_high);
- acc100_reg_write(d, reg_addr->tail_ptrs_dl4g_lo, phys_low);
+ acc_reg_write(d, reg_addr->tail_ptrs_ul5g_hi, phys_high);
+ acc_reg_write(d, reg_addr->tail_ptrs_ul5g_lo, phys_low);
+ acc_reg_write(d, reg_addr->tail_ptrs_dl5g_hi, phys_high);
+ acc_reg_write(d, reg_addr->tail_ptrs_dl5g_lo, phys_low);
+ acc_reg_write(d, reg_addr->tail_ptrs_ul4g_hi, phys_high);
+ acc_reg_write(d, reg_addr->tail_ptrs_ul4g_lo, phys_low);
+ acc_reg_write(d, reg_addr->tail_ptrs_dl4g_hi, phys_high);
+ acc_reg_write(d, reg_addr->tail_ptrs_dl4g_lo, phys_low);
ret = allocate_info_ring(dev);
if (ret < 0) {
@@ -694,7 +531,7 @@ acc100_setup_queues(struct rte_bbdev *dev, uint16_t num_queues, int socket_id)
}
d->harq_layout = rte_zmalloc_socket("HARQ Layout",
- ACC100_HARQ_LAYOUT * sizeof(*d->harq_layout),
+ ACC_HARQ_LAYOUT * sizeof(*d->harq_layout),
RTE_CACHE_LINE_SIZE, dev->data->socket_id);
if (d->harq_layout == NULL) {
rte_bbdev_log(ERR, "Failed to allocate harq_layout for %s:%u",
@@ -718,7 +555,7 @@ static int
acc100_intr_enable(struct rte_bbdev *dev)
{
int ret;
- struct acc100_device *d = dev->data->dev_private;
+ struct acc_device *d = dev->data->dev_private;
/* Only MSI are currently supported */
if (rte_intr_type_get(dev->intr_handle) == RTE_INTR_HANDLE_VFIO_MSI ||
@@ -762,7 +599,7 @@ acc100_intr_enable(struct rte_bbdev *dev)
static int
acc100_dev_close(struct rte_bbdev *dev)
{
- struct acc100_device *d = dev->data->dev_private;
+ struct acc_device *d = dev->data->dev_private;
acc100_check_ir(d);
if (d->sw_rings_base != NULL) {
rte_free(d->tail_ptrs);
@@ -771,7 +608,7 @@ acc100_dev_close(struct rte_bbdev *dev)
d->sw_rings_base = NULL;
}
/* Ensure all in flight HW transactions are completed */
- usleep(ACC100_LONG_WAIT);
+ usleep(ACC_LONG_WAIT);
return 0;
}
@@ -784,12 +621,12 @@ static int
acc100_find_free_queue_idx(struct rte_bbdev *dev,
const struct rte_bbdev_queue_conf *conf)
{
- struct acc100_device *d = dev->data->dev_private;
+ struct acc_device *d = dev->data->dev_private;
int op_2_acc[5] = {0, UL_4G, DL_4G, UL_5G, DL_5G};
int acc = op_2_acc[conf->op_type];
- struct rte_acc100_queue_topology *qtop = NULL;
+ struct rte_acc_queue_topology *qtop = NULL;
- qtopFromAcc(&qtop, acc, &(d->acc100_conf));
+ qtopFromAcc(&qtop, acc, &(d->acc_conf));
if (qtop == NULL)
return -1;
/* Identify matching QGroup Index which are sorted in priority order */
@@ -802,7 +639,7 @@ acc100_find_free_queue_idx(struct rte_bbdev *dev,
return -1;
}
/* Find a free AQ_idx */
- uint16_t aq_idx;
+ uint64_t aq_idx;
for (aq_idx = 0; aq_idx < qtop->num_aqs_per_groups; aq_idx++) {
if (((d->q_assigned_bit_map[group_idx] >> aq_idx) & 0x1) == 0) {
/* Mark the Queue as assigned */
@@ -821,8 +658,8 @@ static int
acc100_queue_setup(struct rte_bbdev *dev, uint16_t queue_id,
const struct rte_bbdev_queue_conf *conf)
{
- struct acc100_device *d = dev->data->dev_private;
- struct acc100_queue *q;
+ struct acc_device *d = dev->data->dev_private;
+ struct acc_queue *q;
int16_t q_idx;
/* Allocate the queue data structure. */
@@ -842,37 +679,37 @@ acc100_queue_setup(struct rte_bbdev *dev, uint16_t queue_id,
q->ring_addr_iova = d->sw_rings_iova + (d->sw_ring_size * queue_id);
/* Prepare the Ring with default descriptor format */
- union acc100_dma_desc *desc = NULL;
+ union acc_dma_desc *desc = NULL;
unsigned int desc_idx, b_idx;
int fcw_len = (conf->op_type == RTE_BBDEV_OP_LDPC_ENC ?
- ACC100_FCW_LE_BLEN : (conf->op_type == RTE_BBDEV_OP_TURBO_DEC ?
- ACC100_FCW_TD_BLEN : ACC100_FCW_LD_BLEN));
+ ACC_FCW_LE_BLEN : (conf->op_type == RTE_BBDEV_OP_TURBO_DEC ?
+ ACC_FCW_TD_BLEN : ACC_FCW_LD_BLEN));
for (desc_idx = 0; desc_idx < d->sw_ring_max_depth; desc_idx++) {
desc = q->ring_addr + desc_idx;
- desc->req.word0 = ACC100_DMA_DESC_TYPE;
+ desc->req.word0 = ACC_DMA_DESC_TYPE;
desc->req.word1 = 0; /**< Timestamp */
desc->req.word2 = 0;
desc->req.word3 = 0;
- uint64_t fcw_offset = (desc_idx << 8) + ACC100_DESC_FCW_OFFSET;
+ uint64_t fcw_offset = (desc_idx << 8) + ACC_DESC_FCW_OFFSET;
desc->req.data_ptrs[0].address = q->ring_addr_iova + fcw_offset;
desc->req.data_ptrs[0].blen = fcw_len;
- desc->req.data_ptrs[0].blkid = ACC100_DMA_BLKID_FCW;
+ desc->req.data_ptrs[0].blkid = ACC_DMA_BLKID_FCW;
desc->req.data_ptrs[0].last = 0;
desc->req.data_ptrs[0].dma_ext = 0;
- for (b_idx = 1; b_idx < ACC100_DMA_MAX_NUM_POINTERS - 1;
+ for (b_idx = 1; b_idx < ACC_DMA_MAX_NUM_POINTERS - 1;
b_idx++) {
- desc->req.data_ptrs[b_idx].blkid = ACC100_DMA_BLKID_IN;
+ desc->req.data_ptrs[b_idx].blkid = ACC_DMA_BLKID_IN;
desc->req.data_ptrs[b_idx].last = 1;
desc->req.data_ptrs[b_idx].dma_ext = 0;
b_idx++;
desc->req.data_ptrs[b_idx].blkid =
- ACC100_DMA_BLKID_OUT_ENC;
+ ACC_DMA_BLKID_OUT_ENC;
desc->req.data_ptrs[b_idx].last = 1;
desc->req.data_ptrs[b_idx].dma_ext = 0;
}
/* Preset some fields of LDPC FCW */
- desc->req.fcw_ld.FCWversion = ACC100_FCW_VER;
+ desc->req.fcw_ld.FCWversion = ACC_FCW_VER;
desc->req.fcw_ld.gain_i = 1;
desc->req.fcw_ld.gain_h = 1;
}
@@ -925,8 +762,8 @@ acc100_queue_setup(struct rte_bbdev *dev, uint16_t queue_id,
q->vf_id = (q_idx >> ACC100_VF_ID_SHIFT) & 0x3F;
q->aq_id = q_idx & 0xF;
q->aq_depth = (conf->op_type == RTE_BBDEV_OP_TURBO_DEC) ?
- (1 << d->acc100_conf.q_ul_4g.aq_depth_log2) :
- (1 << d->acc100_conf.q_dl_4g.aq_depth_log2);
+ (1 << d->acc_conf.q_ul_4g.aq_depth_log2) :
+ (1 << d->acc_conf.q_dl_4g.aq_depth_log2);
q->mmio_reg_enqueue = RTE_PTR_ADD(d->mmio_base,
queue_offset(d->pf_device,
@@ -945,13 +782,13 @@ acc100_queue_setup(struct rte_bbdev *dev, uint16_t queue_id,
static int
acc100_queue_release(struct rte_bbdev *dev, uint16_t q_id)
{
- struct acc100_device *d = dev->data->dev_private;
- struct acc100_queue *q = dev->data->queues[q_id].queue_private;
+ struct acc_device *d = dev->data->dev_private;
+ struct acc_queue *q = dev->data->queues[q_id].queue_private;
if (q != NULL) {
/* Mark the Queue as un-assigned */
- d->q_assigned_bit_map[q->qgrp_id] &= (0xFFFFFFFF -
- (1 << q->aq_id));
+ d->q_assigned_bit_map[q->qgrp_id] &= (0xFFFFFFFFFFFFFFFF -
+ (uint64_t) (1 << q->aq_id));
rte_free(q->lb_in);
rte_free(q->lb_out);
rte_free(q);
@@ -966,7 +803,7 @@ static void
acc100_dev_info_get(struct rte_bbdev *dev,
struct rte_bbdev_driver_info *dev_info)
{
- struct acc100_device *d = dev->data->dev_private;
+ struct acc_device *d = dev->data->dev_private;
int i;
static const struct rte_bbdev_op_cap bbdev_capabilities[] = {
@@ -1056,7 +893,7 @@ acc100_dev_info_get(struct rte_bbdev *dev,
static struct rte_bbdev_queue_conf default_queue_conf;
default_queue_conf.socket = dev->data->socket_id;
- default_queue_conf.queue_size = ACC100_MAX_QUEUE_DEPTH;
+ default_queue_conf.queue_size = ACC_MAX_QUEUE_DEPTH;
dev_info->driver_name = dev->device->driver->name;
@@ -1066,27 +903,27 @@ acc100_dev_info_get(struct rte_bbdev *dev,
/* Expose number of queues */
dev_info->num_queues[RTE_BBDEV_OP_NONE] = 0;
- dev_info->num_queues[RTE_BBDEV_OP_TURBO_DEC] = d->acc100_conf.q_ul_4g.num_aqs_per_groups *
- d->acc100_conf.q_ul_4g.num_qgroups;
- dev_info->num_queues[RTE_BBDEV_OP_TURBO_ENC] = d->acc100_conf.q_dl_4g.num_aqs_per_groups *
- d->acc100_conf.q_dl_4g.num_qgroups;
- dev_info->num_queues[RTE_BBDEV_OP_LDPC_DEC] = d->acc100_conf.q_ul_5g.num_aqs_per_groups *
- d->acc100_conf.q_ul_5g.num_qgroups;
- dev_info->num_queues[RTE_BBDEV_OP_LDPC_ENC] = d->acc100_conf.q_dl_5g.num_aqs_per_groups *
- d->acc100_conf.q_dl_5g.num_qgroups;
- dev_info->queue_priority[RTE_BBDEV_OP_TURBO_DEC] = d->acc100_conf.q_ul_4g.num_qgroups;
- dev_info->queue_priority[RTE_BBDEV_OP_TURBO_ENC] = d->acc100_conf.q_dl_4g.num_qgroups;
- dev_info->queue_priority[RTE_BBDEV_OP_LDPC_DEC] = d->acc100_conf.q_ul_5g.num_qgroups;
- dev_info->queue_priority[RTE_BBDEV_OP_LDPC_ENC] = d->acc100_conf.q_dl_5g.num_qgroups;
+ dev_info->num_queues[RTE_BBDEV_OP_TURBO_DEC] = d->acc_conf.q_ul_4g.num_aqs_per_groups *
+ d->acc_conf.q_ul_4g.num_qgroups;
+ dev_info->num_queues[RTE_BBDEV_OP_TURBO_ENC] = d->acc_conf.q_dl_4g.num_aqs_per_groups *
+ d->acc_conf.q_dl_4g.num_qgroups;
+ dev_info->num_queues[RTE_BBDEV_OP_LDPC_DEC] = d->acc_conf.q_ul_5g.num_aqs_per_groups *
+ d->acc_conf.q_ul_5g.num_qgroups;
+ dev_info->num_queues[RTE_BBDEV_OP_LDPC_ENC] = d->acc_conf.q_dl_5g.num_aqs_per_groups *
+ d->acc_conf.q_dl_5g.num_qgroups;
+ dev_info->queue_priority[RTE_BBDEV_OP_TURBO_DEC] = d->acc_conf.q_ul_4g.num_qgroups;
+ dev_info->queue_priority[RTE_BBDEV_OP_TURBO_ENC] = d->acc_conf.q_dl_4g.num_qgroups;
+ dev_info->queue_priority[RTE_BBDEV_OP_LDPC_DEC] = d->acc_conf.q_ul_5g.num_qgroups;
+ dev_info->queue_priority[RTE_BBDEV_OP_LDPC_ENC] = d->acc_conf.q_dl_5g.num_qgroups;
dev_info->max_num_queues = 0;
for (i = RTE_BBDEV_OP_TURBO_DEC; i <= RTE_BBDEV_OP_LDPC_ENC; i++)
dev_info->max_num_queues += dev_info->num_queues[i];
- dev_info->queue_size_lim = ACC100_MAX_QUEUE_DEPTH;
+ dev_info->queue_size_lim = ACC_MAX_QUEUE_DEPTH;
dev_info->hardware_accelerated = true;
dev_info->max_dl_queue_priority =
- d->acc100_conf.q_dl_4g.num_qgroups - 1;
+ d->acc_conf.q_dl_4g.num_qgroups - 1;
dev_info->max_ul_queue_priority =
- d->acc100_conf.q_ul_4g.num_qgroups - 1;
+ d->acc_conf.q_ul_4g.num_qgroups - 1;
dev_info->default_queue_conf = default_queue_conf;
dev_info->cpu_flag_reqs = NULL;
dev_info->min_alignment = 64;
@@ -1103,7 +940,7 @@ acc100_dev_info_get(struct rte_bbdev *dev,
static int
acc100_queue_intr_enable(struct rte_bbdev *dev, uint16_t queue_id)
{
- struct acc100_queue *q = dev->data->queues[queue_id].queue_private;
+ struct acc_queue *q = dev->data->queues[queue_id].queue_private;
if (rte_intr_type_get(dev->intr_handle) != RTE_INTR_HANDLE_VFIO_MSI &&
rte_intr_type_get(dev->intr_handle) != RTE_INTR_HANDLE_UIO)
@@ -1116,7 +953,7 @@ acc100_queue_intr_enable(struct rte_bbdev *dev, uint16_t queue_id)
static int
acc100_queue_intr_disable(struct rte_bbdev *dev, uint16_t queue_id)
{
- struct acc100_queue *q = dev->data->queues[queue_id].queue_private;
+ struct acc_queue *q = dev->data->queues[queue_id].queue_private;
if (rte_intr_type_get(dev->intr_handle) != RTE_INTR_HANDLE_VFIO_MSI &&
rte_intr_type_get(dev->intr_handle) != RTE_INTR_HANDLE_UIO)
@@ -1159,132 +996,10 @@ static struct rte_pci_id pci_id_acc100_vf_map[] = {
{.device_id = 0},
};
-/* Read flag value 0/1 from bitmap */
-static inline bool
-check_bit(uint32_t bitmap, uint32_t bitmask)
-{
- return bitmap & bitmask;
-}
-
-static inline char *
-mbuf_append(struct rte_mbuf *m_head, struct rte_mbuf *m, uint16_t len)
-{
- if (unlikely(len > rte_pktmbuf_tailroom(m)))
- return NULL;
-
- char *tail = (char *)m->buf_addr + m->data_off + m->data_len;
- m->data_len = (uint16_t)(m->data_len + len);
- m_head->pkt_len = (m_head->pkt_len + len);
- return tail;
-}
-
-/* Fill in a frame control word for turbo encoding. */
-static inline void
-acc100_fcw_te_fill(const struct rte_bbdev_enc_op *op, struct acc100_fcw_te *fcw)
-{
- fcw->code_block_mode = op->turbo_enc.code_block_mode;
- if (fcw->code_block_mode == RTE_BBDEV_TRANSPORT_BLOCK) {
- fcw->k_neg = op->turbo_enc.tb_params.k_neg;
- fcw->k_pos = op->turbo_enc.tb_params.k_pos;
- fcw->c_neg = op->turbo_enc.tb_params.c_neg;
- fcw->c = op->turbo_enc.tb_params.c;
- fcw->ncb_neg = op->turbo_enc.tb_params.ncb_neg;
- fcw->ncb_pos = op->turbo_enc.tb_params.ncb_pos;
-
- if (check_bit(op->turbo_enc.op_flags,
- RTE_BBDEV_TURBO_RATE_MATCH)) {
- fcw->bypass_rm = 0;
- fcw->cab = op->turbo_enc.tb_params.cab;
- fcw->ea = op->turbo_enc.tb_params.ea;
- fcw->eb = op->turbo_enc.tb_params.eb;
- } else {
- /* E is set to the encoding output size when RM is
- * bypassed.
- */
- fcw->bypass_rm = 1;
- fcw->cab = fcw->c_neg;
- fcw->ea = 3 * fcw->k_neg + 12;
- fcw->eb = 3 * fcw->k_pos + 12;
- }
- } else { /* For CB mode */
- fcw->k_pos = op->turbo_enc.cb_params.k;
- fcw->ncb_pos = op->turbo_enc.cb_params.ncb;
-
- if (check_bit(op->turbo_enc.op_flags,
- RTE_BBDEV_TURBO_RATE_MATCH)) {
- fcw->bypass_rm = 0;
- fcw->eb = op->turbo_enc.cb_params.e;
- } else {
- /* E is set to the encoding output size when RM is
- * bypassed.
- */
- fcw->bypass_rm = 1;
- fcw->eb = 3 * fcw->k_pos + 12;
- }
- }
-
- fcw->bypass_rv_idx1 = check_bit(op->turbo_enc.op_flags,
- RTE_BBDEV_TURBO_RV_INDEX_BYPASS);
- fcw->code_block_crc = check_bit(op->turbo_enc.op_flags,
- RTE_BBDEV_TURBO_CRC_24B_ATTACH);
- fcw->rv_idx1 = op->turbo_enc.rv_index;
-}
-
-/* Compute value of k0.
- * Based on 3GPP 38.212 Table 5.4.2.1-2
- * Starting position of different redundancy versions, k0
- */
-static inline uint16_t
-get_k0(uint16_t n_cb, uint16_t z_c, uint8_t bg, uint8_t rv_index)
-{
- if (rv_index == 0)
- return 0;
- uint16_t n = (bg == 1 ? ACC100_N_ZC_1 : ACC100_N_ZC_2) * z_c;
- if (n_cb == n) {
- if (rv_index == 1)
- return (bg == 1 ? ACC100_K0_1_1 : ACC100_K0_1_2) * z_c;
- else if (rv_index == 2)
- return (bg == 1 ? ACC100_K0_2_1 : ACC100_K0_2_2) * z_c;
- else
- return (bg == 1 ? ACC100_K0_3_1 : ACC100_K0_3_2) * z_c;
- }
- /* LBRM case - includes a division by N */
- if (unlikely(z_c == 0))
- return 0;
- if (rv_index == 1)
- return (((bg == 1 ? ACC100_K0_1_1 : ACC100_K0_1_2) * n_cb)
- / n) * z_c;
- else if (rv_index == 2)
- return (((bg == 1 ? ACC100_K0_2_1 : ACC100_K0_2_2) * n_cb)
- / n) * z_c;
- else
- return (((bg == 1 ? ACC100_K0_3_1 : ACC100_K0_3_2) * n_cb)
- / n) * z_c;
-}
-
-/* Fill in a frame control word for LDPC encoding. */
-static inline void
-acc100_fcw_le_fill(const struct rte_bbdev_enc_op *op,
- struct acc100_fcw_le *fcw, int num_cb)
-{
- fcw->qm = op->ldpc_enc.q_m;
- fcw->nfiller = op->ldpc_enc.n_filler;
- fcw->BG = (op->ldpc_enc.basegraph - 1);
- fcw->Zc = op->ldpc_enc.z_c;
- fcw->ncb = op->ldpc_enc.n_cb;
- fcw->k0 = get_k0(fcw->ncb, fcw->Zc, op->ldpc_enc.basegraph,
- op->ldpc_enc.rv_index);
- fcw->rm_e = op->ldpc_enc.cb_params.e;
- fcw->crc_select = check_bit(op->ldpc_enc.op_flags,
- RTE_BBDEV_LDPC_CRC_24B_ATTACH);
- fcw->bypass_intlv = check_bit(op->ldpc_enc.op_flags,
- RTE_BBDEV_LDPC_INTERLEAVER_BYPASS);
- fcw->mcb_count = num_cb;
-}
/* Fill in a frame control word for turbo decoding. */
static inline void
-acc100_fcw_td_fill(const struct rte_bbdev_dec_op *op, struct acc100_fcw_td *fcw)
+acc100_fcw_td_fill(const struct rte_bbdev_dec_op *op, struct acc_fcw_td *fcw)
{
/* Note : Early termination is always enabled for 4GUL */
fcw->fcw_ver = 1;
@@ -1304,13 +1019,13 @@ acc100_fcw_td_fill(const struct rte_bbdev_dec_op *op, struct acc100_fcw_td *fcw)
#ifdef RTE_LIBRTE_BBDEV_DEBUG
static inline bool
-is_acc100(struct acc100_queue *q)
+is_acc100(struct acc_queue *q)
{
return (q->d->device_variant == ACC100_VARIANT);
}
static inline bool
-validate_op_required(struct acc100_queue *q)
+validate_op_required(struct acc_queue *q)
{
return is_acc100(q);
}
@@ -1318,8 +1033,8 @@ validate_op_required(struct acc100_queue *q)
/* Fill in a frame control word for LDPC decoding. */
static inline void
-acc100_fcw_ld_fill(struct rte_bbdev_dec_op *op, struct acc100_fcw_ld *fcw,
- union acc100_harq_layout_data *harq_layout)
+acc100_fcw_ld_fill(struct rte_bbdev_dec_op *op, struct acc_fcw_ld *fcw,
+ union acc_harq_layout_data *harq_layout)
{
uint16_t harq_out_length, harq_in_length, ncb_p, k0_p, parity_offset;
uint16_t harq_index;
@@ -1362,13 +1077,13 @@ acc100_fcw_ld_fill(struct rte_bbdev_dec_op *op, struct acc100_fcw_ld *fcw,
fcw->llr_pack_mode = check_bit(op->ldpc_dec.op_flags,
RTE_BBDEV_LDPC_LLR_COMPRESSION);
harq_index = op->ldpc_dec.harq_combined_output.offset /
- ACC100_HARQ_OFFSET;
+ ACC_HARQ_OFFSET;
#ifdef ACC100_EXT_MEM
/* Limit cases when HARQ pruning is valid */
harq_prun = ((op->ldpc_dec.harq_combined_output.offset %
- ACC100_HARQ_OFFSET) == 0) &&
+ ACC_HARQ_OFFSET) == 0) &&
(op->ldpc_dec.harq_combined_output.offset <= UINT16_MAX
- * ACC100_HARQ_OFFSET);
+ * ACC_HARQ_OFFSET);
#endif
if (fcw->hcin_en > 0) {
harq_in_length = op->ldpc_dec.harq_combined_input.length;
@@ -1423,7 +1138,7 @@ acc100_fcw_ld_fill(struct rte_bbdev_dec_op *op, struct acc100_fcw_ld *fcw,
harq_out_length = (uint16_t) fcw->hcin_size0;
harq_out_length = RTE_MIN(RTE_MAX(harq_out_length, l), ncb_p);
harq_out_length = (harq_out_length + 0x3F) & 0xFFC0;
- if ((k0_p > fcw->hcin_size0 + ACC100_HARQ_OFFSET_THRESHOLD) &&
+ if ((k0_p > fcw->hcin_size0 + ACC_HARQ_OFFSET_THRESHOLD) &&
harq_prun) {
fcw->hcout_size0 = (uint16_t) fcw->hcin_size0;
fcw->hcout_offset = k0_p & 0xFFC0;
@@ -1442,16 +1157,10 @@ acc100_fcw_ld_fill(struct rte_bbdev_dec_op *op, struct acc100_fcw_ld *fcw,
}
}
-/* Convert offset to harq index for harq_layout structure */
-static inline uint32_t hq_index(uint32_t offset)
-{
- return (offset >> ACC100_HARQ_OFFSET_SHIFT) & ACC100_HARQ_OFFSET_MASK;
-}
-
/* Fill in a frame control word for LDPC decoding for ACC101 */
static inline void
-acc101_fcw_ld_fill(struct rte_bbdev_dec_op *op, struct acc100_fcw_ld *fcw,
- union acc100_harq_layout_data *harq_layout)
+acc101_fcw_ld_fill(struct rte_bbdev_dec_op *op, struct acc_fcw_ld *fcw,
+ union acc_harq_layout_data *harq_layout)
{
uint16_t harq_out_length, harq_in_length, ncb_p, k0_p, parity_offset;
uint32_t harq_index;
@@ -1591,7 +1300,7 @@ acc101_fcw_ld_fill(struct rte_bbdev_dec_op *op, struct acc100_fcw_ld *fcw,
*
*/
static inline int
-acc100_dma_fill_blk_type_in(struct acc100_dma_req_desc *desc,
+acc100_dma_fill_blk_type_in(struct acc_dma_req_desc *desc,
struct rte_mbuf **input, uint32_t *offset, uint32_t cb_len,
uint32_t *seg_total_left, int next_triplet)
{
@@ -1605,14 +1314,14 @@ acc100_dma_fill_blk_type_in(struct acc100_dma_req_desc *desc,
desc->data_ptrs[next_triplet].address =
rte_pktmbuf_iova_offset(m, *offset);
desc->data_ptrs[next_triplet].blen = part_len;
- desc->data_ptrs[next_triplet].blkid = ACC100_DMA_BLKID_IN;
+ desc->data_ptrs[next_triplet].blkid = ACC_DMA_BLKID_IN;
desc->data_ptrs[next_triplet].last = 0;
desc->data_ptrs[next_triplet].dma_ext = 0;
*offset += part_len;
next_triplet++;
while (cb_len > 0) {
- if (next_triplet < ACC100_DMA_MAX_NUM_POINTERS_IN && m->next != NULL) {
+ if (next_triplet < ACC_DMA_MAX_NUM_POINTERS_IN && m->next != NULL) {
m = m->next;
*seg_total_left = rte_pktmbuf_data_len(m);
@@ -1623,7 +1332,7 @@ acc100_dma_fill_blk_type_in(struct acc100_dma_req_desc *desc,
rte_pktmbuf_iova_offset(m, 0);
desc->data_ptrs[next_triplet].blen = part_len;
desc->data_ptrs[next_triplet].blkid =
- ACC100_DMA_BLKID_IN;
+ ACC_DMA_BLKID_IN;
desc->data_ptrs[next_triplet].last = 0;
desc->data_ptrs[next_triplet].dma_ext = 0;
cb_len -= part_len;
@@ -1645,134 +1354,9 @@ acc100_dma_fill_blk_type_in(struct acc100_dma_req_desc *desc,
return next_triplet;
}
-/* Fills descriptor with data pointers of one block type.
- * Returns index of next triplet on success, other value if lengths of
- * output data and processed mbuf do not match.
- */
-static inline int
-acc100_dma_fill_blk_type_out(struct acc100_dma_req_desc *desc,
- struct rte_mbuf *output, uint32_t out_offset,
- uint32_t output_len, int next_triplet, int blk_id)
-{
- desc->data_ptrs[next_triplet].address =
- rte_pktmbuf_iova_offset(output, out_offset);
- desc->data_ptrs[next_triplet].blen = output_len;
- desc->data_ptrs[next_triplet].blkid = blk_id;
- desc->data_ptrs[next_triplet].last = 0;
- desc->data_ptrs[next_triplet].dma_ext = 0;
- next_triplet++;
-
- return next_triplet;
-}
-
-static inline void
-acc100_header_init(struct acc100_dma_req_desc *desc)
-{
- desc->word0 = ACC100_DMA_DESC_TYPE;
- desc->word1 = 0; /**< Timestamp could be disabled */
- desc->word2 = 0;
- desc->word3 = 0;
- desc->numCBs = 1;
-}
-
-#ifdef RTE_LIBRTE_BBDEV_DEBUG
-/* Check if any input data is unexpectedly left for processing */
-static inline int
-check_mbuf_total_left(uint32_t mbuf_total_left)
-{
- if (mbuf_total_left == 0)
- return 0;
- rte_bbdev_log(ERR,
- "Some date still left for processing: mbuf_total_left = %u",
- mbuf_total_left);
- return -EINVAL;
-}
-#endif
-
-static inline int
-acc100_dma_desc_te_fill(struct rte_bbdev_enc_op *op,
- struct acc100_dma_req_desc *desc, struct rte_mbuf **input,
- struct rte_mbuf *output, uint32_t *in_offset,
- uint32_t *out_offset, uint32_t *out_length,
- uint32_t *mbuf_total_left, uint32_t *seg_total_left, uint8_t r)
-{
- int next_triplet = 1; /* FCW already done */
- uint32_t e, ea, eb, length;
- uint16_t k, k_neg, k_pos;
- uint8_t cab, c_neg;
-
- desc->word0 = ACC100_DMA_DESC_TYPE;
- desc->word1 = 0; /**< Timestamp could be disabled */
- desc->word2 = 0;
- desc->word3 = 0;
- desc->numCBs = 1;
-
- if (op->turbo_enc.code_block_mode == RTE_BBDEV_TRANSPORT_BLOCK) {
- ea = op->turbo_enc.tb_params.ea;
- eb = op->turbo_enc.tb_params.eb;
- cab = op->turbo_enc.tb_params.cab;
- k_neg = op->turbo_enc.tb_params.k_neg;
- k_pos = op->turbo_enc.tb_params.k_pos;
- c_neg = op->turbo_enc.tb_params.c_neg;
- e = (r < cab) ? ea : eb;
- k = (r < c_neg) ? k_neg : k_pos;
- } else {
- e = op->turbo_enc.cb_params.e;
- k = op->turbo_enc.cb_params.k;
- }
-
- if (check_bit(op->turbo_enc.op_flags, RTE_BBDEV_TURBO_CRC_24B_ATTACH))
- length = (k - 24) >> 3;
- else
- length = k >> 3;
-
- if (unlikely((*mbuf_total_left == 0) || (*mbuf_total_left < length))) {
- rte_bbdev_log(ERR,
- "Mismatch between mbuf length and included CB sizes: mbuf len %u, cb len %u",
- *mbuf_total_left, length);
- return -1;
- }
-
- next_triplet = acc100_dma_fill_blk_type_in(desc, input, in_offset,
- length, seg_total_left, next_triplet);
- if (unlikely(next_triplet < 0)) {
- rte_bbdev_log(ERR,
- "Mismatch between data to process and mbuf data length in bbdev_op: %p",
- op);
- return -1;
- }
- desc->data_ptrs[next_triplet - 1].last = 1;
- desc->m2dlen = next_triplet;
- *mbuf_total_left -= length;
-
- /* Set output length */
- if (check_bit(op->turbo_enc.op_flags, RTE_BBDEV_TURBO_RATE_MATCH))
- /* Integer round up division by 8 */
- *out_length = (e + 7) >> 3;
- else
- *out_length = (k >> 3) * 3 + 2;
-
- next_triplet = acc100_dma_fill_blk_type_out(desc, output, *out_offset,
- *out_length, next_triplet, ACC100_DMA_BLKID_OUT_ENC);
- if (unlikely(next_triplet < 0)) {
- rte_bbdev_log(ERR,
- "Mismatch between data to process and mbuf data length in bbdev_op: %p",
- op);
- return -1;
- }
- op->turbo_enc.output.length += *out_length;
- *out_offset += *out_length;
- desc->data_ptrs[next_triplet - 1].last = 1;
- desc->d2mlen = next_triplet - desc->m2dlen;
-
- desc->op_addr = op;
-
- return 0;
-}
-
static inline int
acc100_dma_desc_le_fill(struct rte_bbdev_enc_op *op,
- struct acc100_dma_req_desc *desc, struct rte_mbuf **input,
+ struct acc_dma_req_desc *desc, struct rte_mbuf **input,
struct rte_mbuf *output, uint32_t *in_offset,
uint32_t *out_offset, uint32_t *out_length,
uint32_t *mbuf_total_left, uint32_t *seg_total_left)
@@ -1781,7 +1365,7 @@ acc100_dma_desc_le_fill(struct rte_bbdev_enc_op *op,
uint16_t K, in_length_in_bits, in_length_in_bytes;
struct rte_bbdev_op_ldpc_enc *enc = &op->ldpc_enc;
- acc100_header_init(desc);
+ acc_header_init(desc);
K = (enc->basegraph == 1 ? 22 : 10) * enc->z_c;
in_length_in_bits = K - enc->n_filler;
@@ -1815,8 +1399,8 @@ acc100_dma_desc_le_fill(struct rte_bbdev_enc_op *op,
/* Integer round up division by 8 */
*out_length = (enc->cb_params.e + 7) >> 3;
- next_triplet = acc100_dma_fill_blk_type_out(desc, output, *out_offset,
- *out_length, next_triplet, ACC100_DMA_BLKID_OUT_ENC);
+ next_triplet = acc_dma_fill_blk_type(desc, output, *out_offset,
+ *out_length, next_triplet, ACC_DMA_BLKID_OUT_ENC);
op->ldpc_enc.output.length += *out_length;
*out_offset += *out_length;
desc->data_ptrs[next_triplet - 1].last = 1;
@@ -1830,7 +1414,7 @@ acc100_dma_desc_le_fill(struct rte_bbdev_enc_op *op,
static inline int
acc100_dma_desc_td_fill(struct rte_bbdev_dec_op *op,
- struct acc100_dma_req_desc *desc, struct rte_mbuf **input,
+ struct acc_dma_req_desc *desc, struct rte_mbuf **input,
struct rte_mbuf *h_output, struct rte_mbuf *s_output,
uint32_t *in_offset, uint32_t *h_out_offset,
uint32_t *s_out_offset, uint32_t *h_out_length,
@@ -1842,7 +1426,7 @@ acc100_dma_desc_td_fill(struct rte_bbdev_dec_op *op,
uint16_t crc24_overlap = 0;
uint32_t e, kw;
- desc->word0 = ACC100_DMA_DESC_TYPE;
+ desc->word0 = ACC_DMA_DESC_TYPE;
desc->word1 = 0; /**< Timestamp could be disabled */
desc->word2 = 0;
desc->word3 = 0;
@@ -1899,10 +1483,10 @@ acc100_dma_desc_td_fill(struct rte_bbdev_dec_op *op,
desc->m2dlen = next_triplet;
*mbuf_total_left -= kw;
- next_triplet = acc100_dma_fill_blk_type_out(
+ next_triplet = acc_dma_fill_blk_type(
desc, h_output, *h_out_offset,
(k - crc24_overlap) >> 3, next_triplet,
- ACC100_DMA_BLKID_OUT_HARD);
+ ACC_DMA_BLKID_OUT_HARD);
if (unlikely(next_triplet < 0)) {
rte_bbdev_log(ERR,
"Mismatch between data to process and mbuf data length in bbdev_op: %p",
@@ -1926,9 +1510,9 @@ acc100_dma_desc_td_fill(struct rte_bbdev_dec_op *op,
else
*s_out_length = (k * 3) + 12;
- next_triplet = acc100_dma_fill_blk_type_out(desc, s_output,
+ next_triplet = acc_dma_fill_blk_type(desc, s_output,
*s_out_offset, *s_out_length, next_triplet,
- ACC100_DMA_BLKID_OUT_SOFT);
+ ACC_DMA_BLKID_OUT_SOFT);
if (unlikely(next_triplet < 0)) {
rte_bbdev_log(ERR,
"Mismatch between data to process and mbuf data length in bbdev_op: %p",
@@ -1950,12 +1534,12 @@ acc100_dma_desc_td_fill(struct rte_bbdev_dec_op *op,
static inline int
acc100_dma_desc_ld_fill(struct rte_bbdev_dec_op *op,
- struct acc100_dma_req_desc *desc,
+ struct acc_dma_req_desc *desc,
struct rte_mbuf **input, struct rte_mbuf *h_output,
uint32_t *in_offset, uint32_t *h_out_offset,
uint32_t *h_out_length, uint32_t *mbuf_total_left,
uint32_t *seg_total_left,
- struct acc100_fcw_ld *fcw)
+ struct acc_fcw_ld *fcw)
{
struct rte_bbdev_op_ldpc_dec *dec = &op->ldpc_dec;
int next_triplet = 1; /* FCW already done */
@@ -1965,7 +1549,7 @@ acc100_dma_desc_ld_fill(struct rte_bbdev_dec_op *op,
bool h_comp = check_bit(dec->op_flags,
RTE_BBDEV_LDPC_HARQ_6BIT_COMPRESSION);
- acc100_header_init(desc);
+ acc_header_init(desc);
if (check_bit(op->ldpc_dec.op_flags,
RTE_BBDEV_LDPC_CRC_TYPE_24B_DROP))
@@ -2007,16 +1591,16 @@ acc100_dma_desc_ld_fill(struct rte_bbdev_dec_op *op,
desc->data_ptrs[next_triplet].address =
dec->harq_combined_input.offset;
desc->data_ptrs[next_triplet].blen = h_p_size;
- desc->data_ptrs[next_triplet].blkid = ACC100_DMA_BLKID_IN_HARQ;
+ desc->data_ptrs[next_triplet].blkid = ACC_DMA_BLKID_IN_HARQ;
desc->data_ptrs[next_triplet].dma_ext = 1;
#ifndef ACC100_EXT_MEM
- acc100_dma_fill_blk_type_out(
+ acc_dma_fill_blk_type(
desc,
op->ldpc_dec.harq_combined_input.data,
op->ldpc_dec.harq_combined_input.offset,
h_p_size,
next_triplet,
- ACC100_DMA_BLKID_IN_HARQ);
+ ACC_DMA_BLKID_IN_HARQ);
#endif
next_triplet++;
}
@@ -2025,9 +1609,9 @@ acc100_dma_desc_ld_fill(struct rte_bbdev_dec_op *op,
desc->m2dlen = next_triplet;
*mbuf_total_left -= input_length;
- next_triplet = acc100_dma_fill_blk_type_out(desc, h_output,
+ next_triplet = acc_dma_fill_blk_type(desc, h_output,
*h_out_offset, output_length >> 3, next_triplet,
- ACC100_DMA_BLKID_OUT_HARD);
+ ACC_DMA_BLKID_OUT_HARD);
if (check_bit(op->ldpc_dec.op_flags,
RTE_BBDEV_LDPC_HQ_COMBINE_OUT_ENABLE)) {
@@ -2045,16 +1629,16 @@ acc100_dma_desc_ld_fill(struct rte_bbdev_dec_op *op,
desc->data_ptrs[next_triplet].address =
dec->harq_combined_output.offset;
desc->data_ptrs[next_triplet].blen = h_p_size;
- desc->data_ptrs[next_triplet].blkid = ACC100_DMA_BLKID_OUT_HARQ;
+ desc->data_ptrs[next_triplet].blkid = ACC_DMA_BLKID_OUT_HARQ;
desc->data_ptrs[next_triplet].dma_ext = 1;
#ifndef ACC100_EXT_MEM
- acc100_dma_fill_blk_type_out(
+ acc_dma_fill_blk_type(
desc,
dec->harq_combined_output.data,
dec->harq_combined_output.offset,
h_p_size,
next_triplet,
- ACC100_DMA_BLKID_OUT_HARQ);
+ ACC_DMA_BLKID_OUT_HARQ);
#endif
next_triplet++;
}
@@ -2072,11 +1656,11 @@ acc100_dma_desc_ld_fill(struct rte_bbdev_dec_op *op,
static inline void
acc100_dma_desc_ld_update(struct rte_bbdev_dec_op *op,
- struct acc100_dma_req_desc *desc,
+ struct acc_dma_req_desc *desc,
struct rte_mbuf *input, struct rte_mbuf *h_output,
uint32_t *in_offset, uint32_t *h_out_offset,
uint32_t *h_out_length,
- union acc100_harq_layout_data *harq_layout)
+ union acc_harq_layout_data *harq_layout)
{
int next_triplet = 1; /* FCW already done */
desc->data_ptrs[next_triplet].address =
@@ -2108,10 +1692,10 @@ acc100_dma_desc_ld_update(struct rte_bbdev_dec_op *op,
op->ldpc_dec.harq_combined_output.length =
prev_op->ldpc_dec.harq_combined_output.length;
int16_t hq_idx = op->ldpc_dec.harq_combined_output.offset /
- ACC100_HARQ_OFFSET;
+ ACC_HARQ_OFFSET;
int16_t prev_hq_idx =
prev_op->ldpc_dec.harq_combined_output.offset
- / ACC100_HARQ_OFFSET;
+ / ACC_HARQ_OFFSET;
harq_layout[hq_idx].val = harq_layout[prev_hq_idx].val;
#ifndef ACC100_EXT_MEM
struct rte_bbdev_op_data ho =
@@ -2126,84 +1710,10 @@ acc100_dma_desc_ld_update(struct rte_bbdev_dec_op *op,
desc->op_addr = op;
}
-
-/* Enqueue a number of operations to HW and update software rings */
-static inline void
-acc100_dma_enqueue(struct acc100_queue *q, uint16_t n,
- struct rte_bbdev_stats *queue_stats)
-{
- union acc100_enqueue_reg_fmt enq_req;
-#ifdef RTE_BBDEV_OFFLOAD_COST
- uint64_t start_time = 0;
- queue_stats->acc_offload_cycles = 0;
-#else
- RTE_SET_USED(queue_stats);
-#endif
-
- enq_req.val = 0;
- /* Setting offset, 100b for 256 DMA Desc */
- enq_req.addr_offset = ACC100_DESC_OFFSET;
-
- /* Split ops into batches */
- do {
- union acc100_dma_desc *desc;
- uint16_t enq_batch_size;
- uint64_t offset;
- rte_iova_t req_elem_addr;
-
- enq_batch_size = RTE_MIN(n, MAX_ENQ_BATCH_SIZE);
-
- /* Set flag on last descriptor in a batch */
- desc = q->ring_addr + ((q->sw_ring_head + enq_batch_size - 1) &
- q->sw_ring_wrap_mask);
- desc->req.last_desc_in_batch = 1;
-
- /* Calculate the 1st descriptor's address */
- offset = ((q->sw_ring_head & q->sw_ring_wrap_mask) *
- sizeof(union acc100_dma_desc));
- req_elem_addr = q->ring_addr_iova + offset;
-
- /* Fill enqueue struct */
- enq_req.num_elem = enq_batch_size;
- /* low 6 bits are not needed */
- enq_req.req_elem_addr = (uint32_t)(req_elem_addr >> 6);
-
-#ifdef RTE_LIBRTE_BBDEV_DEBUG
- rte_memdump(stderr, "Req sdone", desc, sizeof(*desc));
-#endif
- rte_bbdev_log_debug(
- "Enqueue %u reqs (phys %#"PRIx64") to reg %p",
- enq_batch_size,
- req_elem_addr,
- (void *)q->mmio_reg_enqueue);
-
- rte_wmb();
-
-#ifdef RTE_BBDEV_OFFLOAD_COST
- /* Start time measurement for enqueue function offload. */
- start_time = rte_rdtsc_precise();
-#endif
- rte_bbdev_log(DEBUG, "Debug : MMIO Enqueue");
- mmio_write(q->mmio_reg_enqueue, enq_req.val);
-
-#ifdef RTE_BBDEV_OFFLOAD_COST
- queue_stats->acc_offload_cycles +=
- rte_rdtsc_precise() - start_time;
-#endif
-
- q->aq_enqueued++;
- q->sw_ring_head += enq_batch_size;
- n -= enq_batch_size;
-
- } while (n);
-
-
-}
-
#ifdef RTE_LIBRTE_BBDEV_DEBUG
/* Validates turbo encoder parameters */
static inline int
-validate_enc_op(struct rte_bbdev_enc_op *op, struct acc100_queue *q)
+validate_enc_op(struct rte_bbdev_enc_op *op, struct acc_queue *q)
{
struct rte_bbdev_op_turbo_enc *turbo_enc = &op->turbo_enc;
struct rte_bbdev_op_enc_turbo_cb_params *cb = NULL;
@@ -2344,7 +1854,7 @@ validate_enc_op(struct rte_bbdev_enc_op *op, struct acc100_queue *q)
}
/* Validates LDPC encoder parameters */
static inline int
-validate_ldpc_enc_op(struct rte_bbdev_enc_op *op, struct acc100_queue *q)
+validate_ldpc_enc_op(struct rte_bbdev_enc_op *op, struct acc_queue *q)
{
struct rte_bbdev_op_ldpc_enc *ldpc_enc = &op->ldpc_enc;
@@ -2400,7 +1910,7 @@ validate_ldpc_enc_op(struct rte_bbdev_enc_op *op, struct acc100_queue *q)
/* Validates LDPC decoder parameters */
static inline int
-validate_ldpc_dec_op(struct rte_bbdev_dec_op *op, struct acc100_queue *q)
+validate_ldpc_dec_op(struct rte_bbdev_dec_op *op, struct acc_queue *q)
{
struct rte_bbdev_op_ldpc_dec *ldpc_dec = &op->ldpc_dec;
@@ -2448,10 +1958,10 @@ validate_ldpc_dec_op(struct rte_bbdev_dec_op *op, struct acc100_queue *q)
/* Enqueue one encode operations for ACC100 device in CB mode */
static inline int
-enqueue_enc_one_op_cb(struct acc100_queue *q, struct rte_bbdev_enc_op *op,
+enqueue_enc_one_op_cb(struct acc_queue *q, struct rte_bbdev_enc_op *op,
uint16_t total_enqueued_cbs)
{
- union acc100_dma_desc *desc = NULL;
+ union acc_dma_desc *desc = NULL;
int ret;
uint32_t in_offset, out_offset, out_length, mbuf_total_left,
seg_total_left;
@@ -2468,7 +1978,7 @@ enqueue_enc_one_op_cb(struct acc100_queue *q, struct rte_bbdev_enc_op *op,
uint16_t desc_idx = ((q->sw_ring_head + total_enqueued_cbs)
& q->sw_ring_wrap_mask);
desc = q->ring_addr + desc_idx;
- acc100_fcw_te_fill(op, &desc->req.fcw_te);
+ acc_fcw_te_fill(op, &desc->req.fcw_te);
input = op->turbo_enc.input.data;
output_head = output = op->turbo_enc.output.data;
@@ -2479,7 +1989,7 @@ enqueue_enc_one_op_cb(struct acc100_queue *q, struct rte_bbdev_enc_op *op,
seg_total_left = rte_pktmbuf_data_len(op->turbo_enc.input.data)
- in_offset;
- ret = acc100_dma_desc_te_fill(op, &desc->req, &input, output,
+ ret = acc_dma_desc_te_fill(op, &desc->req, &input, output,
&in_offset, &out_offset, &out_length, &mbuf_total_left,
&seg_total_left, 0);
@@ -2501,10 +2011,10 @@ enqueue_enc_one_op_cb(struct acc100_queue *q, struct rte_bbdev_enc_op *op,
/* Enqueue one encode operations for ACC100 device in CB mode */
static inline int
-enqueue_ldpc_enc_n_op_cb(struct acc100_queue *q, struct rte_bbdev_enc_op **ops,
+enqueue_ldpc_enc_n_op_cb(struct acc_queue *q, struct rte_bbdev_enc_op **ops,
uint16_t total_enqueued_cbs, int16_t num)
{
- union acc100_dma_desc *desc = NULL;
+ union acc_dma_desc *desc = NULL;
uint32_t out_length;
struct rte_mbuf *output_head, *output;
int i, next_triplet;
@@ -2522,10 +2032,10 @@ enqueue_ldpc_enc_n_op_cb(struct acc100_queue *q, struct rte_bbdev_enc_op **ops,
uint16_t desc_idx = ((q->sw_ring_head + total_enqueued_cbs)
& q->sw_ring_wrap_mask);
desc = q->ring_addr + desc_idx;
- acc100_fcw_le_fill(ops[0], &desc->req.fcw_le, num);
+ acc_fcw_le_fill(ops[0], &desc->req.fcw_le, num, 0);
/** This could be done at polling */
- acc100_header_init(&desc->req);
+ acc_header_init(&desc->req);
desc->req.numCBs = num;
in_length_in_bytes = ops[0]->ldpc_enc.input.data->data_len;
@@ -2564,10 +2074,10 @@ enqueue_ldpc_enc_n_op_cb(struct acc100_queue *q, struct rte_bbdev_enc_op **ops,
/* Enqueue one encode operations for ACC100 device in CB mode */
static inline int
-enqueue_ldpc_enc_one_op_cb(struct acc100_queue *q, struct rte_bbdev_enc_op *op,
+enqueue_ldpc_enc_one_op_cb(struct acc_queue *q, struct rte_bbdev_enc_op *op,
uint16_t total_enqueued_cbs)
{
- union acc100_dma_desc *desc = NULL;
+ union acc_dma_desc *desc = NULL;
int ret;
uint32_t in_offset, out_offset, out_length, mbuf_total_left,
seg_total_left;
@@ -2584,7 +2094,7 @@ enqueue_ldpc_enc_one_op_cb(struct acc100_queue *q, struct rte_bbdev_enc_op *op,
uint16_t desc_idx = ((q->sw_ring_head + total_enqueued_cbs)
& q->sw_ring_wrap_mask);
desc = q->ring_addr + desc_idx;
- acc100_fcw_le_fill(op, &desc->req.fcw_le, 1);
+ acc_fcw_le_fill(op, &desc->req.fcw_le, 1, 0);
input = op->ldpc_enc.input.data;
output_head = output = op->ldpc_enc.output.data;
@@ -2619,10 +2129,10 @@ enqueue_ldpc_enc_one_op_cb(struct acc100_queue *q, struct rte_bbdev_enc_op *op,
/* Enqueue one encode operations for ACC100 device in TB mode. */
static inline int
-enqueue_enc_one_op_tb(struct acc100_queue *q, struct rte_bbdev_enc_op *op,
+enqueue_enc_one_op_tb(struct acc_queue *q, struct rte_bbdev_enc_op *op,
uint16_t total_enqueued_cbs, uint8_t cbs_in_tb)
{
- union acc100_dma_desc *desc = NULL;
+ union acc_dma_desc *desc = NULL;
int ret;
uint8_t r, c;
uint32_t in_offset, out_offset, out_length, mbuf_total_left,
@@ -2641,8 +2151,8 @@ enqueue_enc_one_op_tb(struct acc100_queue *q, struct rte_bbdev_enc_op *op,
uint16_t desc_idx = ((q->sw_ring_head + total_enqueued_cbs)
& q->sw_ring_wrap_mask);
desc = q->ring_addr + desc_idx;
- uint64_t fcw_offset = (desc_idx << 8) + ACC100_DESC_FCW_OFFSET;
- acc100_fcw_te_fill(op, &desc->req.fcw_te);
+ uint64_t fcw_offset = (desc_idx << 8) + ACC_DESC_FCW_OFFSET;
+ acc_fcw_te_fill(op, &desc->req.fcw_te);
input = op->turbo_enc.input.data;
output_head = output = op->turbo_enc.output.data;
@@ -2660,9 +2170,9 @@ enqueue_enc_one_op_tb(struct acc100_queue *q, struct rte_bbdev_enc_op *op,
desc = q->ring_addr + ((q->sw_ring_head + total_enqueued_cbs)
& q->sw_ring_wrap_mask);
desc->req.data_ptrs[0].address = q->ring_addr_iova + fcw_offset;
- desc->req.data_ptrs[0].blen = ACC100_FCW_TE_BLEN;
+ desc->req.data_ptrs[0].blen = ACC_FCW_TE_BLEN;
- ret = acc100_dma_desc_te_fill(op, &desc->req, &input, output,
+ ret = acc_dma_desc_te_fill(op, &desc->req, &input, output,
&in_offset, &out_offset, &out_length,
&mbuf_total_left, &seg_total_left, r);
if (unlikely(ret < 0))
@@ -2705,7 +2215,7 @@ enqueue_enc_one_op_tb(struct acc100_queue *q, struct rte_bbdev_enc_op *op,
#ifdef RTE_LIBRTE_BBDEV_DEBUG
/* Validates turbo decoder parameters */
static inline int
-validate_dec_op(struct rte_bbdev_dec_op *op, struct acc100_queue *q)
+validate_dec_op(struct rte_bbdev_dec_op *op, struct acc_queue *q)
{
struct rte_bbdev_op_turbo_dec *turbo_dec = &op->turbo_dec;
struct rte_bbdev_op_dec_turbo_cb_params *cb = NULL;
@@ -2843,10 +2353,10 @@ validate_dec_op(struct rte_bbdev_dec_op *op, struct acc100_queue *q)
/** Enqueue one decode operations for ACC100 device in CB mode */
static inline int
-enqueue_dec_one_op_cb(struct acc100_queue *q, struct rte_bbdev_dec_op *op,
+enqueue_dec_one_op_cb(struct acc_queue *q, struct rte_bbdev_dec_op *op,
uint16_t total_enqueued_cbs)
{
- union acc100_dma_desc *desc = NULL;
+ union acc_dma_desc *desc = NULL;
int ret;
uint32_t in_offset, h_out_offset, s_out_offset, s_out_length,
h_out_length, mbuf_total_left, seg_total_left;
@@ -2915,10 +2425,10 @@ enqueue_dec_one_op_cb(struct acc100_queue *q, struct rte_bbdev_dec_op *op,
}
static inline int
-harq_loopback(struct acc100_queue *q, struct rte_bbdev_dec_op *op,
+harq_loopback(struct acc_queue *q, struct rte_bbdev_dec_op *op,
uint16_t total_enqueued_cbs) {
- struct acc100_fcw_ld *fcw;
- union acc100_dma_desc *desc;
+ struct acc_fcw_ld *fcw;
+ union acc_dma_desc *desc;
int next_triplet = 1;
struct rte_mbuf *hq_output_head, *hq_output;
uint16_t harq_dma_length_in, harq_dma_length_out;
@@ -2943,24 +2453,24 @@ harq_loopback(struct acc100_queue *q, struct rte_bbdev_dec_op *op,
bool ddr_mem_in = check_bit(op->ldpc_dec.op_flags,
RTE_BBDEV_LDPC_INTERNAL_HARQ_MEMORY_IN_ENABLE);
- union acc100_harq_layout_data *harq_layout = q->d->harq_layout;
+ union acc_harq_layout_data *harq_layout = q->d->harq_layout;
uint16_t harq_index = (ddr_mem_in ?
op->ldpc_dec.harq_combined_input.offset :
op->ldpc_dec.harq_combined_output.offset)
- / ACC100_HARQ_OFFSET;
+ / ACC_HARQ_OFFSET;
uint16_t desc_idx = ((q->sw_ring_head + total_enqueued_cbs)
& q->sw_ring_wrap_mask);
desc = q->ring_addr + desc_idx;
fcw = &desc->req.fcw_ld;
/* Set the FCW from loopback into DDR */
- memset(fcw, 0, sizeof(struct acc100_fcw_ld));
- fcw->FCWversion = ACC100_FCW_VER;
+ memset(fcw, 0, sizeof(struct acc_fcw_ld));
+ fcw->FCWversion = ACC_FCW_VER;
fcw->qm = 2;
fcw->Zc = 384;
- if (harq_in_length < 16 * ACC100_N_ZC_1)
+ if (harq_in_length < 16 * ACC_N_ZC_1)
fcw->Zc = 16;
- fcw->ncb = fcw->Zc * ACC100_N_ZC_1;
+ fcw->ncb = fcw->Zc * ACC_N_ZC_1;
fcw->rm_e = 2;
fcw->hcin_en = 1;
fcw->hcout_en = 1;
@@ -2990,32 +2500,32 @@ harq_loopback(struct acc100_queue *q, struct rte_bbdev_dec_op *op,
fcw->gain_h = 1;
/* Set the prefix of descriptor. This could be done at polling */
- acc100_header_init(&desc->req);
+ acc_header_init(&desc->req);
/* Null LLR input for Decoder */
desc->req.data_ptrs[next_triplet].address =
q->lb_in_addr_iova;
desc->req.data_ptrs[next_triplet].blen = 2;
- desc->req.data_ptrs[next_triplet].blkid = ACC100_DMA_BLKID_IN;
+ desc->req.data_ptrs[next_triplet].blkid = ACC_DMA_BLKID_IN;
desc->req.data_ptrs[next_triplet].last = 0;
desc->req.data_ptrs[next_triplet].dma_ext = 0;
next_triplet++;
/* HARQ Combine input from either Memory interface */
if (!ddr_mem_in) {
- next_triplet = acc100_dma_fill_blk_type_out(&desc->req,
+ next_triplet = acc_dma_fill_blk_type(&desc->req,
op->ldpc_dec.harq_combined_input.data,
op->ldpc_dec.harq_combined_input.offset,
harq_dma_length_in,
next_triplet,
- ACC100_DMA_BLKID_IN_HARQ);
+ ACC_DMA_BLKID_IN_HARQ);
} else {
desc->req.data_ptrs[next_triplet].address =
op->ldpc_dec.harq_combined_input.offset;
desc->req.data_ptrs[next_triplet].blen =
harq_dma_length_in;
desc->req.data_ptrs[next_triplet].blkid =
- ACC100_DMA_BLKID_IN_HARQ;
+ ACC_DMA_BLKID_IN_HARQ;
desc->req.data_ptrs[next_triplet].dma_ext = 1;
next_triplet++;
}
@@ -3025,8 +2535,8 @@ harq_loopback(struct acc100_queue *q, struct rte_bbdev_dec_op *op,
/* Dropped decoder hard output */
desc->req.data_ptrs[next_triplet].address =
q->lb_out_addr_iova;
- desc->req.data_ptrs[next_triplet].blen = ACC100_BYTES_IN_WORD;
- desc->req.data_ptrs[next_triplet].blkid = ACC100_DMA_BLKID_OUT_HARD;
+ desc->req.data_ptrs[next_triplet].blen = ACC_BYTES_IN_WORD;
+ desc->req.data_ptrs[next_triplet].blkid = ACC_DMA_BLKID_OUT_HARD;
desc->req.data_ptrs[next_triplet].last = 0;
desc->req.data_ptrs[next_triplet].dma_ext = 0;
next_triplet++;
@@ -3040,19 +2550,19 @@ harq_loopback(struct acc100_queue *q, struct rte_bbdev_dec_op *op,
desc->req.data_ptrs[next_triplet].blen =
harq_dma_length_out;
desc->req.data_ptrs[next_triplet].blkid =
- ACC100_DMA_BLKID_OUT_HARQ;
+ ACC_DMA_BLKID_OUT_HARQ;
desc->req.data_ptrs[next_triplet].dma_ext = 1;
next_triplet++;
} else {
hq_output_head = op->ldpc_dec.harq_combined_output.data;
hq_output = op->ldpc_dec.harq_combined_output.data;
- next_triplet = acc100_dma_fill_blk_type_out(
+ next_triplet = acc_dma_fill_blk_type(
&desc->req,
op->ldpc_dec.harq_combined_output.data,
op->ldpc_dec.harq_combined_output.offset,
harq_dma_length_out,
next_triplet,
- ACC100_DMA_BLKID_OUT_HARQ);
+ ACC_DMA_BLKID_OUT_HARQ);
/* HARQ output */
mbuf_append(hq_output_head, hq_output, harq_dma_length_out);
op->ldpc_dec.harq_combined_output.length =
@@ -3068,7 +2578,7 @@ harq_loopback(struct acc100_queue *q, struct rte_bbdev_dec_op *op,
/** Enqueue one decode operations for ACC100 device in CB mode */
static inline int
-enqueue_ldpc_dec_one_op_cb(struct acc100_queue *q, struct rte_bbdev_dec_op *op,
+enqueue_ldpc_dec_one_op_cb(struct acc_queue *q, struct rte_bbdev_dec_op *op,
uint16_t total_enqueued_cbs, bool same_op)
{
int ret;
@@ -3085,7 +2595,7 @@ enqueue_ldpc_dec_one_op_cb(struct acc100_queue *q, struct rte_bbdev_dec_op *op,
return -EINVAL;
}
#endif
- union acc100_dma_desc *desc;
+ union acc_dma_desc *desc;
uint16_t desc_idx = ((q->sw_ring_head + total_enqueued_cbs)
& q->sw_ring_wrap_mask);
desc = q->ring_addr + desc_idx;
@@ -3102,36 +2612,36 @@ enqueue_ldpc_dec_one_op_cb(struct acc100_queue *q, struct rte_bbdev_dec_op *op,
return -EFAULT;
}
#endif
- union acc100_harq_layout_data *harq_layout = q->d->harq_layout;
+ union acc_harq_layout_data *harq_layout = q->d->harq_layout;
if (same_op) {
- union acc100_dma_desc *prev_desc;
+ union acc_dma_desc *prev_desc;
desc_idx = ((q->sw_ring_head + total_enqueued_cbs - 1)
& q->sw_ring_wrap_mask);
prev_desc = q->ring_addr + desc_idx;
uint8_t *prev_ptr = (uint8_t *) prev_desc;
uint8_t *new_ptr = (uint8_t *) desc;
/* Copy first 4 words and BDESCs */
- rte_memcpy(new_ptr, prev_ptr, ACC100_5GUL_SIZE_0);
- rte_memcpy(new_ptr + ACC100_5GUL_OFFSET_0,
- prev_ptr + ACC100_5GUL_OFFSET_0,
- ACC100_5GUL_SIZE_1);
+ rte_memcpy(new_ptr, prev_ptr, ACC_5GUL_SIZE_0);
+ rte_memcpy(new_ptr + ACC_5GUL_OFFSET_0,
+ prev_ptr + ACC_5GUL_OFFSET_0,
+ ACC_5GUL_SIZE_1);
desc->req.op_addr = prev_desc->req.op_addr;
/* Copy FCW */
- rte_memcpy(new_ptr + ACC100_DESC_FCW_OFFSET,
- prev_ptr + ACC100_DESC_FCW_OFFSET,
- ACC100_FCW_LD_BLEN);
+ rte_memcpy(new_ptr + ACC_DESC_FCW_OFFSET,
+ prev_ptr + ACC_DESC_FCW_OFFSET,
+ ACC_FCW_LD_BLEN);
acc100_dma_desc_ld_update(op, &desc->req, input, h_output,
&in_offset, &h_out_offset,
&h_out_length, harq_layout);
} else {
- struct acc100_fcw_ld *fcw;
+ struct acc_fcw_ld *fcw;
uint32_t seg_total_left;
fcw = &desc->req.fcw_ld;
q->d->fcw_ld_fill(op, fcw, harq_layout);
/* Special handling when overusing mbuf */
- if (fcw->rm_e < ACC100_MAX_E_MBUF)
+ if (fcw->rm_e < ACC_MAX_E_MBUF)
seg_total_left = rte_pktmbuf_data_len(input)
- in_offset;
else
@@ -3171,10 +2681,10 @@ enqueue_ldpc_dec_one_op_cb(struct acc100_queue *q, struct rte_bbdev_dec_op *op,
/* Enqueue one decode operations for ACC100 device in TB mode */
static inline int
-enqueue_ldpc_dec_one_op_tb(struct acc100_queue *q, struct rte_bbdev_dec_op *op,
+enqueue_ldpc_dec_one_op_tb(struct acc_queue *q, struct rte_bbdev_dec_op *op,
uint16_t total_enqueued_cbs, uint8_t cbs_in_tb)
{
- union acc100_dma_desc *desc = NULL;
+ union acc_dma_desc *desc = NULL;
int ret;
uint8_t r, c;
uint32_t in_offset, h_out_offset,
@@ -3193,8 +2703,8 @@ enqueue_ldpc_dec_one_op_tb(struct acc100_queue *q, struct rte_bbdev_dec_op *op,
uint16_t desc_idx = ((q->sw_ring_head + total_enqueued_cbs)
& q->sw_ring_wrap_mask);
desc = q->ring_addr + desc_idx;
- uint64_t fcw_offset = (desc_idx << 8) + ACC100_DESC_FCW_OFFSET;
- union acc100_harq_layout_data *harq_layout = q->d->harq_layout;
+ uint64_t fcw_offset = (desc_idx << 8) + ACC_DESC_FCW_OFFSET;
+ union acc_harq_layout_data *harq_layout = q->d->harq_layout;
q->d->fcw_ld_fill(op, &desc->req.fcw_ld, harq_layout);
input = op->ldpc_dec.input.data;
@@ -3214,7 +2724,7 @@ enqueue_ldpc_dec_one_op_tb(struct acc100_queue *q, struct rte_bbdev_dec_op *op,
desc = q->ring_addr + ((q->sw_ring_head + total_enqueued_cbs)
& q->sw_ring_wrap_mask);
desc->req.data_ptrs[0].address = q->ring_addr_iova + fcw_offset;
- desc->req.data_ptrs[0].blen = ACC100_FCW_LD_BLEN;
+ desc->req.data_ptrs[0].blen = ACC_FCW_LD_BLEN;
ret = acc100_dma_desc_ld_fill(op, &desc->req, &input,
h_output, &in_offset, &h_out_offset,
&h_out_length,
@@ -3260,10 +2770,10 @@ enqueue_ldpc_dec_one_op_tb(struct acc100_queue *q, struct rte_bbdev_dec_op *op,
/* Enqueue one decode operations for ACC100 device in TB mode */
static inline int
-enqueue_dec_one_op_tb(struct acc100_queue *q, struct rte_bbdev_dec_op *op,
+enqueue_dec_one_op_tb(struct acc_queue *q, struct rte_bbdev_dec_op *op,
uint16_t total_enqueued_cbs, uint8_t cbs_in_tb)
{
- union acc100_dma_desc *desc = NULL;
+ union acc_dma_desc *desc = NULL;
int ret;
uint8_t r, c;
uint32_t in_offset, h_out_offset, s_out_offset, s_out_length,
@@ -3283,7 +2793,7 @@ enqueue_dec_one_op_tb(struct acc100_queue *q, struct rte_bbdev_dec_op *op,
uint16_t desc_idx = ((q->sw_ring_head + total_enqueued_cbs)
& q->sw_ring_wrap_mask);
desc = q->ring_addr + desc_idx;
- uint64_t fcw_offset = (desc_idx << 8) + ACC100_DESC_FCW_OFFSET;
+ uint64_t fcw_offset = (desc_idx << 8) + ACC_DESC_FCW_OFFSET;
acc100_fcw_td_fill(op, &desc->req.fcw_td);
input = op->turbo_dec.input.data;
@@ -3305,7 +2815,7 @@ enqueue_dec_one_op_tb(struct acc100_queue *q, struct rte_bbdev_dec_op *op,
desc = q->ring_addr + ((q->sw_ring_head + total_enqueued_cbs)
& q->sw_ring_wrap_mask);
desc->req.data_ptrs[0].address = q->ring_addr_iova + fcw_offset;
- desc->req.data_ptrs[0].blen = ACC100_FCW_TD_BLEN;
+ desc->req.data_ptrs[0].blen = ACC_FCW_TD_BLEN;
ret = acc100_dma_desc_td_fill(op, &desc->req, &input,
h_output, s_output, &in_offset, &h_out_offset,
&s_out_offset, &h_out_length, &s_out_length,
@@ -3360,91 +2870,15 @@ enqueue_dec_one_op_tb(struct acc100_queue *q, struct rte_bbdev_dec_op *op,
return current_enqueued_cbs;
}
-/* Calculates number of CBs in processed encoder TB based on 'r' and input
- * length.
- */
-static inline uint8_t
-get_num_cbs_in_tb_enc(struct rte_bbdev_op_turbo_enc *turbo_enc)
-{
- uint8_t c, c_neg, r, crc24_bits = 0;
- uint16_t k, k_neg, k_pos;
- uint8_t cbs_in_tb = 0;
- int32_t length;
-
- length = turbo_enc->input.length;
- r = turbo_enc->tb_params.r;
- c = turbo_enc->tb_params.c;
- c_neg = turbo_enc->tb_params.c_neg;
- k_neg = turbo_enc->tb_params.k_neg;
- k_pos = turbo_enc->tb_params.k_pos;
- crc24_bits = 0;
- if (check_bit(turbo_enc->op_flags, RTE_BBDEV_TURBO_CRC_24B_ATTACH))
- crc24_bits = 24;
- while (length > 0 && r < c) {
- k = (r < c_neg) ? k_neg : k_pos;
- length -= (k - crc24_bits) >> 3;
- r++;
- cbs_in_tb++;
- }
-
- return cbs_in_tb;
-}
-
-/* Calculates number of CBs in processed decoder TB based on 'r' and input
- * length.
- */
-static inline uint16_t
-get_num_cbs_in_tb_dec(struct rte_bbdev_op_turbo_dec *turbo_dec)
-{
- uint8_t c, c_neg, r = 0;
- uint16_t kw, k, k_neg, k_pos, cbs_in_tb = 0;
- int32_t length;
-
- length = turbo_dec->input.length;
- r = turbo_dec->tb_params.r;
- c = turbo_dec->tb_params.c;
- c_neg = turbo_dec->tb_params.c_neg;
- k_neg = turbo_dec->tb_params.k_neg;
- k_pos = turbo_dec->tb_params.k_pos;
- while (length > 0 && r < c) {
- k = (r < c_neg) ? k_neg : k_pos;
- kw = RTE_ALIGN_CEIL(k + 4, 32) * 3;
- length -= kw;
- r++;
- cbs_in_tb++;
- }
-
- return cbs_in_tb;
-}
-
-/* Calculates number of CBs in processed decoder TB based on 'r' and input
- * length.
- */
-static inline uint16_t
-get_num_cbs_in_tb_ldpc_dec(struct rte_bbdev_op_ldpc_dec *ldpc_dec)
-{
- uint16_t r, cbs_in_tb = 0;
- int32_t length = ldpc_dec->input.length;
- r = ldpc_dec->tb_params.r;
- while (length > 0 && r < ldpc_dec->tb_params.c) {
- length -= (r < ldpc_dec->tb_params.cab) ?
- ldpc_dec->tb_params.ea :
- ldpc_dec->tb_params.eb;
- r++;
- cbs_in_tb++;
- }
- return cbs_in_tb;
-}
-
/* Enqueue encode operations for ACC100 device in CB mode. */
static uint16_t
acc100_enqueue_enc_cb(struct rte_bbdev_queue_data *q_data,
struct rte_bbdev_enc_op **ops, uint16_t num)
{
- struct acc100_queue *q = q_data->queue_private;
+ struct acc_queue *q = q_data->queue_private;
int32_t avail = q->sw_ring_depth + q->sw_ring_tail - q->sw_ring_head;
uint16_t i;
- union acc100_dma_desc *desc;
+ union acc_dma_desc *desc;
int ret;
for (i = 0; i < num; ++i) {
@@ -3467,7 +2901,7 @@ acc100_enqueue_enc_cb(struct rte_bbdev_queue_data *q_data,
desc->req.sdone_enable = 1;
desc->req.irq_enable = q->irq_enable;
- acc100_dma_enqueue(q, i, &q_data->queue_stats);
+ acc_dma_enqueue(q, i, &q_data->queue_stats);
/* Update stats */
q_data->queue_stats.enqueued_count += i;
@@ -3475,32 +2909,15 @@ acc100_enqueue_enc_cb(struct rte_bbdev_queue_data *q_data,
return i;
}
-/* Check we can mux encode operations with common FCW */
-static inline bool
-check_mux(struct rte_bbdev_enc_op **ops, uint16_t num) {
- uint16_t i;
- if (num <= 1)
- return false;
- for (i = 1; i < num; ++i) {
- /* Only mux compatible code blocks */
- if (memcmp((uint8_t *)(&ops[i]->ldpc_enc) + ACC100_ENC_OFFSET,
- (uint8_t *)(&ops[0]->ldpc_enc) +
- ACC100_ENC_OFFSET,
- ACC100_CMP_ENC_SIZE) != 0)
- return false;
- }
- return true;
-}
-
/** Enqueue encode operations for ACC100 device in CB mode. */
static inline uint16_t
acc100_enqueue_ldpc_enc_cb(struct rte_bbdev_queue_data *q_data,
struct rte_bbdev_enc_op **ops, uint16_t num)
{
- struct acc100_queue *q = q_data->queue_private;
+ struct acc_queue *q = q_data->queue_private;
int32_t avail = q->sw_ring_depth + q->sw_ring_tail - q->sw_ring_head;
uint16_t i = 0;
- union acc100_dma_desc *desc;
+ union acc_dma_desc *desc;
int ret, desc_idx = 0;
int16_t enq, left = num;
@@ -3508,7 +2925,7 @@ acc100_enqueue_ldpc_enc_cb(struct rte_bbdev_queue_data *q_data,
if (unlikely(avail < 1))
break;
avail--;
- enq = RTE_MIN(left, ACC100_MUX_5GDL_DESC);
+ enq = RTE_MIN(left, ACC_MUX_5GDL_DESC);
if (check_mux(&ops[i], enq)) {
ret = enqueue_ldpc_enc_n_op_cb(q, &ops[i],
desc_idx, enq);
@@ -3534,7 +2951,7 @@ acc100_enqueue_ldpc_enc_cb(struct rte_bbdev_queue_data *q_data,
desc->req.sdone_enable = 1;
desc->req.irq_enable = q->irq_enable;
- acc100_dma_enqueue(q, desc_idx, &q_data->queue_stats);
+ acc_dma_enqueue(q, desc_idx, &q_data->queue_stats);
/* Update stats */
q_data->queue_stats.enqueued_count += i;
@@ -3548,7 +2965,7 @@ static uint16_t
acc100_enqueue_enc_tb(struct rte_bbdev_queue_data *q_data,
struct rte_bbdev_enc_op **ops, uint16_t num)
{
- struct acc100_queue *q = q_data->queue_private;
+ struct acc_queue *q = q_data->queue_private;
int32_t avail = q->sw_ring_depth + q->sw_ring_tail - q->sw_ring_head;
uint16_t i, enqueued_cbs = 0;
uint8_t cbs_in_tb;
@@ -3569,7 +2986,7 @@ acc100_enqueue_enc_tb(struct rte_bbdev_queue_data *q_data,
if (unlikely(enqueued_cbs == 0))
return 0; /* Nothing to enqueue */
- acc100_dma_enqueue(q, enqueued_cbs, &q_data->queue_stats);
+ acc_dma_enqueue(q, enqueued_cbs, &q_data->queue_stats);
/* Update stats */
q_data->queue_stats.enqueued_count += i;
@@ -3610,10 +3027,10 @@ static uint16_t
acc100_enqueue_dec_cb(struct rte_bbdev_queue_data *q_data,
struct rte_bbdev_dec_op **ops, uint16_t num)
{
- struct acc100_queue *q = q_data->queue_private;
+ struct acc_queue *q = q_data->queue_private;
int32_t avail = q->sw_ring_depth + q->sw_ring_tail - q->sw_ring_head;
uint16_t i;
- union acc100_dma_desc *desc;
+ union acc_dma_desc *desc;
int ret;
for (i = 0; i < num; ++i) {
@@ -3636,7 +3053,7 @@ acc100_enqueue_dec_cb(struct rte_bbdev_queue_data *q_data,
desc->req.sdone_enable = 1;
desc->req.irq_enable = q->irq_enable;
- acc100_dma_enqueue(q, i, &q_data->queue_stats);
+ acc_dma_enqueue(q, i, &q_data->queue_stats);
/* Update stats */
q_data->queue_stats.enqueued_count += i;
@@ -3645,25 +3062,12 @@ acc100_enqueue_dec_cb(struct rte_bbdev_queue_data *q_data,
return i;
}
-/* Check we can mux encode operations with common FCW */
-static inline bool
-cmp_ldpc_dec_op(struct rte_bbdev_dec_op **ops) {
- /* Only mux compatible code blocks */
- if (memcmp((uint8_t *)(&ops[0]->ldpc_dec) + ACC100_DEC_OFFSET,
- (uint8_t *)(&ops[1]->ldpc_dec) +
- ACC100_DEC_OFFSET, ACC100_CMP_DEC_SIZE) != 0) {
- return false;
- } else
- return true;
-}
-
-
/* Enqueue decode operations for ACC100 device in TB mode */
static uint16_t
acc100_enqueue_ldpc_dec_tb(struct rte_bbdev_queue_data *q_data,
struct rte_bbdev_dec_op **ops, uint16_t num)
{
- struct acc100_queue *q = q_data->queue_private;
+ struct acc_queue *q = q_data->queue_private;
int32_t avail = q->sw_ring_depth + q->sw_ring_tail - q->sw_ring_head;
uint16_t i, enqueued_cbs = 0;
uint8_t cbs_in_tb;
@@ -3683,7 +3087,7 @@ acc100_enqueue_ldpc_dec_tb(struct rte_bbdev_queue_data *q_data,
enqueued_cbs += ret;
}
- acc100_dma_enqueue(q, enqueued_cbs, &q_data->queue_stats);
+ acc_dma_enqueue(q, enqueued_cbs, &q_data->queue_stats);
/* Update stats */
q_data->queue_stats.enqueued_count += i;
@@ -3696,10 +3100,10 @@ static uint16_t
acc100_enqueue_ldpc_dec_cb(struct rte_bbdev_queue_data *q_data,
struct rte_bbdev_dec_op **ops, uint16_t num)
{
- struct acc100_queue *q = q_data->queue_private;
+ struct acc_queue *q = q_data->queue_private;
int32_t avail = q->sw_ring_depth + q->sw_ring_tail - q->sw_ring_head;
uint16_t i;
- union acc100_dma_desc *desc;
+ union acc_dma_desc *desc;
int ret;
bool same_op = false;
for (i = 0; i < num; ++i) {
@@ -3732,7 +3136,7 @@ acc100_enqueue_ldpc_dec_cb(struct rte_bbdev_queue_data *q_data,
desc->req.sdone_enable = 1;
desc->req.irq_enable = q->irq_enable;
- acc100_dma_enqueue(q, i, &q_data->queue_stats);
+ acc_dma_enqueue(q, i, &q_data->queue_stats);
/* Update stats */
q_data->queue_stats.enqueued_count += i;
@@ -3746,7 +3150,7 @@ static uint16_t
acc100_enqueue_dec_tb(struct rte_bbdev_queue_data *q_data,
struct rte_bbdev_dec_op **ops, uint16_t num)
{
- struct acc100_queue *q = q_data->queue_private;
+ struct acc_queue *q = q_data->queue_private;
int32_t avail = q->sw_ring_depth + q->sw_ring_tail - q->sw_ring_head;
uint16_t i, enqueued_cbs = 0;
uint8_t cbs_in_tb;
@@ -3765,7 +3169,7 @@ acc100_enqueue_dec_tb(struct rte_bbdev_queue_data *q_data,
enqueued_cbs += ret;
}
- acc100_dma_enqueue(q, enqueued_cbs, &q_data->queue_stats);
+ acc_dma_enqueue(q, enqueued_cbs, &q_data->queue_stats);
/* Update stats */
q_data->queue_stats.enqueued_count += i;
@@ -3792,7 +3196,7 @@ static uint16_t
acc100_enqueue_ldpc_dec(struct rte_bbdev_queue_data *q_data,
struct rte_bbdev_dec_op **ops, uint16_t num)
{
- struct acc100_queue *q = q_data->queue_private;
+ struct acc_queue *q = q_data->queue_private;
int32_t aq_avail = q->aq_depth +
(q->aq_dequeued - q->aq_enqueued) / 128;
@@ -3808,11 +3212,11 @@ acc100_enqueue_ldpc_dec(struct rte_bbdev_queue_data *q_data,
/* Dequeue one encode operations from ACC100 device in CB mode */
static inline int
-dequeue_enc_one_op_cb(struct acc100_queue *q, struct rte_bbdev_enc_op **ref_op,
+dequeue_enc_one_op_cb(struct acc_queue *q, struct rte_bbdev_enc_op **ref_op,
uint16_t total_dequeued_cbs, uint32_t *aq_dequeued)
{
- union acc100_dma_desc *desc, atom_desc;
- union acc100_dma_rsp_desc rsp;
+ union acc_dma_desc *desc, atom_desc;
+ union acc_dma_rsp_desc rsp;
struct rte_bbdev_enc_op *op;
int i;
@@ -3822,7 +3226,7 @@ dequeue_enc_one_op_cb(struct acc100_queue *q, struct rte_bbdev_enc_op **ref_op,
__ATOMIC_RELAXED);
/* Check fdone bit */
- if (!(atom_desc.rsp.val & ACC100_FDONE))
+ if (!(atom_desc.rsp.val & ACC_FDONE))
return -1;
rsp.val = atom_desc.rsp.val;
@@ -3843,7 +3247,7 @@ dequeue_enc_one_op_cb(struct acc100_queue *q, struct rte_bbdev_enc_op **ref_op,
(*aq_dequeued)++;
desc->req.last_desc_in_batch = 0;
}
- desc->rsp.val = ACC100_DMA_DESC_TYPE;
+ desc->rsp.val = ACC_DMA_DESC_TYPE;
desc->rsp.add_info_0 = 0; /*Reserved bits */
desc->rsp.add_info_1 = 0; /*Reserved bits */
@@ -3858,11 +3262,11 @@ dequeue_enc_one_op_cb(struct acc100_queue *q, struct rte_bbdev_enc_op **ref_op,
/* Dequeue one encode operations from ACC100 device in TB mode */
static inline int
-dequeue_enc_one_op_tb(struct acc100_queue *q, struct rte_bbdev_enc_op **ref_op,
+dequeue_enc_one_op_tb(struct acc_queue *q, struct rte_bbdev_enc_op **ref_op,
uint16_t total_dequeued_cbs, uint32_t *aq_dequeued)
{
- union acc100_dma_desc *desc, *last_desc, atom_desc;
- union acc100_dma_rsp_desc rsp;
+ union acc_dma_desc *desc, *last_desc, atom_desc;
+ union acc_dma_rsp_desc rsp;
struct rte_bbdev_enc_op *op;
uint8_t i = 0;
uint16_t current_dequeued_cbs = 0, cbs_in_tb;
@@ -3873,7 +3277,7 @@ dequeue_enc_one_op_tb(struct acc100_queue *q, struct rte_bbdev_enc_op **ref_op,
__ATOMIC_RELAXED);
/* Check fdone bit */
- if (!(atom_desc.rsp.val & ACC100_FDONE))
+ if (!(atom_desc.rsp.val & ACC_FDONE))
return -1;
/* Get number of CBs in dequeued TB */
@@ -3887,7 +3291,7 @@ dequeue_enc_one_op_tb(struct acc100_queue *q, struct rte_bbdev_enc_op **ref_op,
*/
atom_desc.atom_hdr = __atomic_load_n((uint64_t *)last_desc,
__ATOMIC_RELAXED);
- if (!(atom_desc.rsp.val & ACC100_SDONE))
+ if (!(atom_desc.rsp.val & ACC_SDONE))
return -1;
/* Dequeue */
@@ -3915,7 +3319,7 @@ dequeue_enc_one_op_tb(struct acc100_queue *q, struct rte_bbdev_enc_op **ref_op,
(*aq_dequeued)++;
desc->req.last_desc_in_batch = 0;
}
- desc->rsp.val = ACC100_DMA_DESC_TYPE;
+ desc->rsp.val = ACC_DMA_DESC_TYPE;
desc->rsp.add_info_0 = 0;
desc->rsp.add_info_1 = 0;
total_dequeued_cbs++;
@@ -3931,11 +3335,11 @@ dequeue_enc_one_op_tb(struct acc100_queue *q, struct rte_bbdev_enc_op **ref_op,
/* Dequeue one decode operation from ACC100 device in CB mode */
static inline int
dequeue_dec_one_op_cb(struct rte_bbdev_queue_data *q_data,
- struct acc100_queue *q, struct rte_bbdev_dec_op **ref_op,
+ struct acc_queue *q, struct rte_bbdev_dec_op **ref_op,
uint16_t dequeued_cbs, uint32_t *aq_dequeued)
{
- union acc100_dma_desc *desc, atom_desc;
- union acc100_dma_rsp_desc rsp;
+ union acc_dma_desc *desc, atom_desc;
+ union acc_dma_rsp_desc rsp;
struct rte_bbdev_dec_op *op;
desc = q->ring_addr + ((q->sw_ring_tail + dequeued_cbs)
@@ -3944,7 +3348,7 @@ dequeue_dec_one_op_cb(struct rte_bbdev_queue_data *q_data,
__ATOMIC_RELAXED);
/* Check fdone bit */
- if (!(atom_desc.rsp.val & ACC100_FDONE))
+ if (!(atom_desc.rsp.val & ACC_FDONE))
return -1;
rsp.val = atom_desc.rsp.val;
@@ -3973,7 +3377,7 @@ dequeue_dec_one_op_cb(struct rte_bbdev_queue_data *q_data,
(*aq_dequeued)++;
desc->req.last_desc_in_batch = 0;
}
- desc->rsp.val = ACC100_DMA_DESC_TYPE;
+ desc->rsp.val = ACC_DMA_DESC_TYPE;
desc->rsp.add_info_0 = 0;
desc->rsp.add_info_1 = 0;
*ref_op = op;
@@ -3985,11 +3389,11 @@ dequeue_dec_one_op_cb(struct rte_bbdev_queue_data *q_data,
/* Dequeue one decode operations from ACC100 device in CB mode */
static inline int
dequeue_ldpc_dec_one_op_cb(struct rte_bbdev_queue_data *q_data,
- struct acc100_queue *q, struct rte_bbdev_dec_op **ref_op,
+ struct acc_queue *q, struct rte_bbdev_dec_op **ref_op,
uint16_t dequeued_cbs, uint32_t *aq_dequeued)
{
- union acc100_dma_desc *desc, atom_desc;
- union acc100_dma_rsp_desc rsp;
+ union acc_dma_desc *desc, atom_desc;
+ union acc_dma_rsp_desc rsp;
struct rte_bbdev_dec_op *op;
desc = q->ring_addr + ((q->sw_ring_tail + dequeued_cbs)
@@ -3998,7 +3402,7 @@ dequeue_ldpc_dec_one_op_cb(struct rte_bbdev_queue_data *q_data,
__ATOMIC_RELAXED);
/* Check fdone bit */
- if (!(atom_desc.rsp.val & ACC100_FDONE))
+ if (!(atom_desc.rsp.val & ACC_FDONE))
return -1;
rsp.val = atom_desc.rsp.val;
@@ -4028,7 +3432,7 @@ dequeue_ldpc_dec_one_op_cb(struct rte_bbdev_queue_data *q_data,
desc->req.last_desc_in_batch = 0;
}
- desc->rsp.val = ACC100_DMA_DESC_TYPE;
+ desc->rsp.val = ACC_DMA_DESC_TYPE;
desc->rsp.add_info_0 = 0;
desc->rsp.add_info_1 = 0;
@@ -4040,11 +3444,11 @@ dequeue_ldpc_dec_one_op_cb(struct rte_bbdev_queue_data *q_data,
/* Dequeue one decode operations from ACC100 device in TB mode. */
static inline int
-dequeue_dec_one_op_tb(struct acc100_queue *q, struct rte_bbdev_dec_op **ref_op,
+dequeue_dec_one_op_tb(struct acc_queue *q, struct rte_bbdev_dec_op **ref_op,
uint16_t dequeued_cbs, uint32_t *aq_dequeued)
{
- union acc100_dma_desc *desc, *last_desc, atom_desc;
- union acc100_dma_rsp_desc rsp;
+ union acc_dma_desc *desc, *last_desc, atom_desc;
+ union acc_dma_rsp_desc rsp;
struct rte_bbdev_dec_op *op;
uint8_t cbs_in_tb = 1, cb_idx = 0;
@@ -4054,7 +3458,7 @@ dequeue_dec_one_op_tb(struct acc100_queue *q, struct rte_bbdev_dec_op **ref_op,
__ATOMIC_RELAXED);
/* Check fdone bit */
- if (!(atom_desc.rsp.val & ACC100_FDONE))
+ if (!(atom_desc.rsp.val & ACC_FDONE))
return -1;
/* Dequeue */
@@ -4071,7 +3475,7 @@ dequeue_dec_one_op_tb(struct acc100_queue *q, struct rte_bbdev_dec_op **ref_op,
*/
atom_desc.atom_hdr = __atomic_load_n((uint64_t *)last_desc,
__ATOMIC_RELAXED);
- if (!(atom_desc.rsp.val & ACC100_SDONE))
+ if (!(atom_desc.rsp.val & ACC_SDONE))
return -1;
/* Clearing status, it will be set based on response */
@@ -4103,7 +3507,7 @@ dequeue_dec_one_op_tb(struct acc100_queue *q, struct rte_bbdev_dec_op **ref_op,
(*aq_dequeued)++;
desc->req.last_desc_in_batch = 0;
}
- desc->rsp.val = ACC100_DMA_DESC_TYPE;
+ desc->rsp.val = ACC_DMA_DESC_TYPE;
desc->rsp.add_info_0 = 0;
desc->rsp.add_info_1 = 0;
dequeued_cbs++;
@@ -4120,7 +3524,7 @@ static uint16_t
acc100_dequeue_enc(struct rte_bbdev_queue_data *q_data,
struct rte_bbdev_enc_op **ops, uint16_t num)
{
- struct acc100_queue *q = q_data->queue_private;
+ struct acc_queue *q = q_data->queue_private;
uint16_t dequeue_num;
uint32_t avail = q->sw_ring_head - q->sw_ring_tail;
uint32_t aq_dequeued = 0;
@@ -4166,7 +3570,7 @@ static uint16_t
acc100_dequeue_ldpc_enc(struct rte_bbdev_queue_data *q_data,
struct rte_bbdev_enc_op **ops, uint16_t num)
{
- struct acc100_queue *q = q_data->queue_private;
+ struct acc_queue *q = q_data->queue_private;
uint32_t avail = q->sw_ring_head - q->sw_ring_tail;
uint32_t aq_dequeued = 0;
uint16_t dequeue_num, i, dequeued_cbs = 0, dequeued_descs = 0;
@@ -4205,7 +3609,7 @@ static uint16_t
acc100_dequeue_dec(struct rte_bbdev_queue_data *q_data,
struct rte_bbdev_dec_op **ops, uint16_t num)
{
- struct acc100_queue *q = q_data->queue_private;
+ struct acc_queue *q = q_data->queue_private;
uint16_t dequeue_num;
uint32_t avail = q->sw_ring_head - q->sw_ring_tail;
uint32_t aq_dequeued = 0;
@@ -4250,7 +3654,7 @@ static uint16_t
acc100_dequeue_ldpc_dec(struct rte_bbdev_queue_data *q_data,
struct rte_bbdev_dec_op **ops, uint16_t num)
{
- struct acc100_queue *q = q_data->queue_private;
+ struct acc_queue *q = q_data->queue_private;
uint16_t dequeue_num;
uint32_t avail = q->sw_ring_head - q->sw_ring_tail;
uint32_t aq_dequeued = 0;
@@ -4310,17 +3714,17 @@ acc100_bbdev_init(struct rte_bbdev *dev, struct rte_pci_driver *drv)
/* Device variant specific handling */
if ((pci_dev->id.device_id == ACC100_PF_DEVICE_ID) ||
(pci_dev->id.device_id == ACC100_VF_DEVICE_ID)) {
- ((struct acc100_device *) dev->data->dev_private)->device_variant = ACC100_VARIANT;
- ((struct acc100_device *) dev->data->dev_private)->fcw_ld_fill = acc100_fcw_ld_fill;
+ ((struct acc_device *) dev->data->dev_private)->device_variant = ACC100_VARIANT;
+ ((struct acc_device *) dev->data->dev_private)->fcw_ld_fill = acc100_fcw_ld_fill;
} else {
- ((struct acc100_device *) dev->data->dev_private)->device_variant = ACC101_VARIANT;
- ((struct acc100_device *) dev->data->dev_private)->fcw_ld_fill = acc101_fcw_ld_fill;
+ ((struct acc_device *) dev->data->dev_private)->device_variant = ACC101_VARIANT;
+ ((struct acc_device *) dev->data->dev_private)->fcw_ld_fill = acc101_fcw_ld_fill;
}
- ((struct acc100_device *) dev->data->dev_private)->pf_device =
+ ((struct acc_device *) dev->data->dev_private)->pf_device =
!strcmp(drv->driver.name, RTE_STR(ACC100PF_DRIVER_NAME));
- ((struct acc100_device *) dev->data->dev_private)->mmio_base =
+ ((struct acc_device *) dev->data->dev_private)->mmio_base =
pci_dev->mem_resource[0].addr;
rte_bbdev_log_debug("Init device %s [%s] @ vaddr %p paddr %#"PRIx64"",
@@ -4349,13 +3753,13 @@ static int acc100_pci_probe(struct rte_pci_driver *pci_drv,
/* allocate device private memory */
bbdev->data->dev_private = rte_zmalloc_socket(dev_name,
- sizeof(struct acc100_device), RTE_CACHE_LINE_SIZE,
+ sizeof(struct acc_device), RTE_CACHE_LINE_SIZE,
pci_dev->device.numa_node);
if (bbdev->data->dev_private == NULL) {
rte_bbdev_log(CRIT,
"Allocate of %zu bytes for device \"%s\" failed",
- sizeof(struct acc100_device), dev_name);
+ sizeof(struct acc_device), dev_name);
rte_bbdev_release(bbdev);
return -ENOMEM;
}
@@ -4373,53 +3777,16 @@ static int acc100_pci_probe(struct rte_pci_driver *pci_drv,
return 0;
}
-static int acc100_pci_remove(struct rte_pci_device *pci_dev)
-{
- struct rte_bbdev *bbdev;
- int ret;
- uint8_t dev_id;
-
- if (pci_dev == NULL)
- return -EINVAL;
-
- /* Find device */
- bbdev = rte_bbdev_get_named_dev(pci_dev->device.name);
- if (bbdev == NULL) {
- rte_bbdev_log(CRIT,
- "Couldn't find HW dev \"%s\" to uninitialise it",
- pci_dev->device.name);
- return -ENODEV;
- }
- dev_id = bbdev->data->dev_id;
-
- /* free device private memory before close */
- rte_free(bbdev->data->dev_private);
-
- /* Close device */
- ret = rte_bbdev_close(dev_id);
- if (ret < 0)
- rte_bbdev_log(ERR,
- "Device %i failed to close during uninit: %i",
- dev_id, ret);
-
- /* release bbdev from library */
- rte_bbdev_release(bbdev);
-
- rte_bbdev_log_debug("Destroyed bbdev = %u", dev_id);
-
- return 0;
-}
-
static struct rte_pci_driver acc100_pci_pf_driver = {
.probe = acc100_pci_probe,
- .remove = acc100_pci_remove,
+ .remove = acc_pci_remove,
.id_table = pci_id_acc100_pf_map,
.drv_flags = RTE_PCI_DRV_NEED_MAPPING
};
static struct rte_pci_driver acc100_pci_vf_driver = {
.probe = acc100_pci_probe,
- .remove = acc100_pci_remove,
+ .remove = acc_pci_remove,
.id_table = pci_id_acc100_vf_map,
.drv_flags = RTE_PCI_DRV_NEED_MAPPING
};
@@ -4437,51 +3804,51 @@ RTE_PMD_REGISTER_PCI_TABLE(ACC100VF_DRIVER_NAME, pci_id_acc100_vf_map);
* defined.
*/
static void
-poweron_cleanup(struct rte_bbdev *bbdev, struct acc100_device *d,
- struct rte_acc100_conf *conf)
+poweron_cleanup(struct rte_bbdev *bbdev, struct acc_device *d,
+ struct rte_acc_conf *conf)
{
int i, template_idx, qg_idx;
uint32_t address, status, value;
printf("Need to clear power-on 5GUL status in internal memory\n");
/* Reset LDPC Cores */
for (i = 0; i < ACC100_ENGINES_MAX; i++)
- acc100_reg_write(d, HWPfFecUl5gCntrlReg +
- ACC100_ENGINE_OFFSET * i, ACC100_RESET_HI);
- usleep(ACC100_LONG_WAIT);
+ acc_reg_write(d, HWPfFecUl5gCntrlReg +
+ ACC_ENGINE_OFFSET * i, ACC100_RESET_HI);
+ usleep(ACC_LONG_WAIT);
for (i = 0; i < ACC100_ENGINES_MAX; i++)
- acc100_reg_write(d, HWPfFecUl5gCntrlReg +
- ACC100_ENGINE_OFFSET * i, ACC100_RESET_LO);
- usleep(ACC100_LONG_WAIT);
+ acc_reg_write(d, HWPfFecUl5gCntrlReg +
+ ACC_ENGINE_OFFSET * i, ACC100_RESET_LO);
+ usleep(ACC_LONG_WAIT);
/* Prepare dummy workload */
alloc_2x64mb_sw_rings_mem(bbdev, d, 0);
/* Set base addresses */
uint32_t phys_high = (uint32_t)(d->sw_rings_iova >> 32);
uint32_t phys_low = (uint32_t)(d->sw_rings_iova &
- ~(ACC100_SIZE_64MBYTE-1));
- acc100_reg_write(d, HWPfDmaFec5GulDescBaseHiRegVf, phys_high);
- acc100_reg_write(d, HWPfDmaFec5GulDescBaseLoRegVf, phys_low);
+ ~(ACC_SIZE_64MBYTE-1));
+ acc_reg_write(d, HWPfDmaFec5GulDescBaseHiRegVf, phys_high);
+ acc_reg_write(d, HWPfDmaFec5GulDescBaseLoRegVf, phys_low);
/* Descriptor for a dummy 5GUL code block processing*/
- union acc100_dma_desc *desc = NULL;
+ union acc_dma_desc *desc = NULL;
desc = d->sw_rings;
desc->req.data_ptrs[0].address = d->sw_rings_iova +
- ACC100_DESC_FCW_OFFSET;
- desc->req.data_ptrs[0].blen = ACC100_FCW_LD_BLEN;
- desc->req.data_ptrs[0].blkid = ACC100_DMA_BLKID_FCW;
+ ACC_DESC_FCW_OFFSET;
+ desc->req.data_ptrs[0].blen = ACC_FCW_LD_BLEN;
+ desc->req.data_ptrs[0].blkid = ACC_DMA_BLKID_FCW;
desc->req.data_ptrs[0].last = 0;
desc->req.data_ptrs[0].dma_ext = 0;
desc->req.data_ptrs[1].address = d->sw_rings_iova + 512;
- desc->req.data_ptrs[1].blkid = ACC100_DMA_BLKID_IN;
+ desc->req.data_ptrs[1].blkid = ACC_DMA_BLKID_IN;
desc->req.data_ptrs[1].last = 1;
desc->req.data_ptrs[1].dma_ext = 0;
desc->req.data_ptrs[1].blen = 44;
desc->req.data_ptrs[2].address = d->sw_rings_iova + 1024;
- desc->req.data_ptrs[2].blkid = ACC100_DMA_BLKID_OUT_ENC;
+ desc->req.data_ptrs[2].blkid = ACC_DMA_BLKID_OUT_ENC;
desc->req.data_ptrs[2].last = 1;
desc->req.data_ptrs[2].dma_ext = 0;
desc->req.data_ptrs[2].blen = 5;
/* Dummy FCW */
- desc->req.fcw_ld.FCWversion = ACC100_FCW_VER;
+ desc->req.fcw_ld.FCWversion = ACC_FCW_VER;
desc->req.fcw_ld.qm = 1;
desc->req.fcw_ld.nfiller = 30;
desc->req.fcw_ld.BG = 2 - 1;
@@ -4500,8 +3867,8 @@ poweron_cleanup(struct rte_bbdev *bbdev, struct acc100_device *d,
template_idx++) {
/* Check engine power-on status */
address = HwPfFecUl5gIbDebugReg +
- ACC100_ENGINE_OFFSET * template_idx;
- status = (acc100_reg_read(d, address) >> 4) & 0xF;
+ ACC_ENGINE_OFFSET * template_idx;
+ status = (acc_reg_read(d, address) >> 4) & 0xF;
if (status == 0) {
engines_to_restart[num_failed_engine] = template_idx;
num_failed_engine++;
@@ -4521,14 +3888,14 @@ poweron_cleanup(struct rte_bbdev *bbdev, struct acc100_device *d,
template_idx <= ACC100_SIG_UL_5G_LAST;
template_idx++) {
address = HWPfQmgrGrpTmplateReg4Indx
- + ACC100_BYTES_IN_WORD * template_idx;
+ + ACC_BYTES_IN_WORD * template_idx;
if (template_idx == failed_engine)
- acc100_reg_write(d, address, value);
+ acc_reg_write(d, address, value);
else
- acc100_reg_write(d, address, 0);
+ acc_reg_write(d, address, 0);
}
/* Reset descriptor header */
- desc->req.word0 = ACC100_DMA_DESC_TYPE;
+ desc->req.word0 = ACC_DMA_DESC_TYPE;
desc->req.word1 = 0;
desc->req.word2 = 0;
desc->req.word3 = 0;
@@ -4536,56 +3903,56 @@ poweron_cleanup(struct rte_bbdev *bbdev, struct acc100_device *d,
desc->req.m2dlen = 2;
desc->req.d2mlen = 1;
/* Enqueue the code block for processing */
- union acc100_enqueue_reg_fmt enq_req;
+ union acc_enqueue_reg_fmt enq_req;
enq_req.val = 0;
- enq_req.addr_offset = ACC100_DESC_OFFSET;
+ enq_req.addr_offset = ACC_DESC_OFFSET;
enq_req.num_elem = 1;
enq_req.req_elem_addr = 0;
rte_wmb();
- acc100_reg_write(d, HWPfQmgrIngressAq + 0x100, enq_req.val);
- usleep(ACC100_LONG_WAIT * 100);
+ acc_reg_write(d, HWPfQmgrIngressAq + 0x100, enq_req.val);
+ usleep(ACC_LONG_WAIT * 100);
if (desc->req.word0 != 2)
printf("DMA Response %#"PRIx32"\n", desc->req.word0);
}
/* Reset LDPC Cores */
for (i = 0; i < ACC100_ENGINES_MAX; i++)
- acc100_reg_write(d, HWPfFecUl5gCntrlReg +
- ACC100_ENGINE_OFFSET * i,
+ acc_reg_write(d, HWPfFecUl5gCntrlReg +
+ ACC_ENGINE_OFFSET * i,
ACC100_RESET_HI);
- usleep(ACC100_LONG_WAIT);
+ usleep(ACC_LONG_WAIT);
for (i = 0; i < ACC100_ENGINES_MAX; i++)
- acc100_reg_write(d, HWPfFecUl5gCntrlReg +
- ACC100_ENGINE_OFFSET * i,
+ acc_reg_write(d, HWPfFecUl5gCntrlReg +
+ ACC_ENGINE_OFFSET * i,
ACC100_RESET_LO);
- usleep(ACC100_LONG_WAIT);
- acc100_reg_write(d, HWPfHi5GHardResetReg, ACC100_RESET_HARD);
- usleep(ACC100_LONG_WAIT);
+ usleep(ACC_LONG_WAIT);
+ acc_reg_write(d, HWPfHi5GHardResetReg, ACC100_RESET_HARD);
+ usleep(ACC_LONG_WAIT);
int numEngines = 0;
/* Check engine power-on status again */
for (template_idx = ACC100_SIG_UL_5G;
template_idx <= ACC100_SIG_UL_5G_LAST;
template_idx++) {
address = HwPfFecUl5gIbDebugReg +
- ACC100_ENGINE_OFFSET * template_idx;
- status = (acc100_reg_read(d, address) >> 4) & 0xF;
+ ACC_ENGINE_OFFSET * template_idx;
+ status = (acc_reg_read(d, address) >> 4) & 0xF;
address = HWPfQmgrGrpTmplateReg4Indx
- + ACC100_BYTES_IN_WORD * template_idx;
+ + ACC_BYTES_IN_WORD * template_idx;
if (status == 1) {
- acc100_reg_write(d, address, value);
+ acc_reg_write(d, address, value);
numEngines++;
} else
- acc100_reg_write(d, address, 0);
+ acc_reg_write(d, address, 0);
}
printf("Number of 5GUL engines %d\n", numEngines);
rte_free(d->sw_rings_base);
- usleep(ACC100_LONG_WAIT);
+ usleep(ACC_LONG_WAIT);
}
/* Initial configuration of a ACC100 device prior to running configure() */
static int
-acc100_configure(const char *dev_name, struct rte_acc100_conf *conf)
+acc100_configure(const char *dev_name, struct rte_acc_conf *conf)
{
rte_bbdev_log(INFO, "rte_acc100_configure");
uint32_t value, address, status;
@@ -4593,10 +3960,10 @@ acc100_configure(const char *dev_name, struct rte_acc100_conf *conf)
struct rte_bbdev *bbdev = rte_bbdev_get_named_dev(dev_name);
/* Compile time checks */
- RTE_BUILD_BUG_ON(sizeof(struct acc100_dma_req_desc) != 256);
- RTE_BUILD_BUG_ON(sizeof(union acc100_dma_desc) != 256);
- RTE_BUILD_BUG_ON(sizeof(struct acc100_fcw_td) != 24);
- RTE_BUILD_BUG_ON(sizeof(struct acc100_fcw_te) != 32);
+ RTE_BUILD_BUG_ON(sizeof(struct acc_dma_req_desc) != 256);
+ RTE_BUILD_BUG_ON(sizeof(union acc_dma_desc) != 256);
+ RTE_BUILD_BUG_ON(sizeof(struct acc_fcw_td) != 24);
+ RTE_BUILD_BUG_ON(sizeof(struct acc_fcw_te) != 32);
if (bbdev == NULL) {
rte_bbdev_log(ERR,
@@ -4604,87 +3971,87 @@ acc100_configure(const char *dev_name, struct rte_acc100_conf *conf)
dev_name);
return -ENODEV;
}
- struct acc100_device *d = bbdev->data->dev_private;
+ struct acc_device *d = bbdev->data->dev_private;
/* Store configuration */
- rte_memcpy(&d->acc100_conf, conf, sizeof(d->acc100_conf));
+ rte_memcpy(&d->acc_conf, conf, sizeof(d->acc_conf));
- value = acc100_reg_read(d, HwPfPcieGpexBridgeControl);
+ value = acc_reg_read(d, HwPfPcieGpexBridgeControl);
bool firstCfg = (value != ACC100_CFG_PCI_BRIDGE);
/* PCIe Bridge configuration */
- acc100_reg_write(d, HwPfPcieGpexBridgeControl, ACC100_CFG_PCI_BRIDGE);
+ acc_reg_write(d, HwPfPcieGpexBridgeControl, ACC100_CFG_PCI_BRIDGE);
for (i = 1; i < ACC100_GPEX_AXIMAP_NUM; i++)
- acc100_reg_write(d,
+ acc_reg_write(d,
HwPfPcieGpexAxiAddrMappingWindowPexBaseHigh
+ i * 16, 0);
/* Prevent blocking AXI read on BRESP for AXI Write */
address = HwPfPcieGpexAxiPioControl;
value = ACC100_CFG_PCI_AXI;
- acc100_reg_write(d, address, value);
+ acc_reg_write(d, address, value);
/* 5GDL PLL phase shift */
- acc100_reg_write(d, HWPfChaDl5gPllPhshft0, 0x1);
+ acc_reg_write(d, HWPfChaDl5gPllPhshft0, 0x1);
/* Explicitly releasing AXI as this may be stopped after PF FLR/BME */
address = HWPfDmaAxiControl;
value = 1;
- acc100_reg_write(d, address, value);
+ acc_reg_write(d, address, value);
/* Enable granular dynamic clock gating */
address = HWPfHiClkGateHystReg;
value = ACC100_CLOCK_GATING_EN;
- acc100_reg_write(d, address, value);
+ acc_reg_write(d, address, value);
/* Set default descriptor signature */
address = HWPfDmaDescriptorSignatuture;
value = 0;
- acc100_reg_write(d, address, value);
+ acc_reg_write(d, address, value);
/* Enable the Error Detection in DMA */
value = ACC100_CFG_DMA_ERROR;
address = HWPfDmaErrorDetectionEn;
- acc100_reg_write(d, address, value);
+ acc_reg_write(d, address, value);
/* AXI Cache configuration */
value = ACC100_CFG_AXI_CACHE;
address = HWPfDmaAxcacheReg;
- acc100_reg_write(d, address, value);
+ acc_reg_write(d, address, value);
/* Adjust PCIe Lane adaptation */
for (i = 0; i < ACC100_QUAD_NUMS; i++)
for (j = 0; j < ACC100_LANES_PER_QUAD; j++)
- acc100_reg_write(d, HwPfPcieLnAdaptctrl + i * ACC100_PCIE_QUAD_OFFSET
+ acc_reg_write(d, HwPfPcieLnAdaptctrl + i * ACC100_PCIE_QUAD_OFFSET
+ j * ACC100_PCIE_LANE_OFFSET, ACC100_ADAPT);
/* Enable PCIe live adaptation */
for (i = 0; i < ACC100_QUAD_NUMS; i++)
- acc100_reg_write(d, HwPfPciePcsEqControl +
+ acc_reg_write(d, HwPfPciePcsEqControl +
i * ACC100_PCIE_QUAD_OFFSET, ACC100_PCS_EQ);
/* Default DMA Configuration (Qmgr Enabled) */
address = HWPfDmaConfig0Reg;
value = 0;
- acc100_reg_write(d, address, value);
+ acc_reg_write(d, address, value);
address = HWPfDmaQmanen;
value = 0;
- acc100_reg_write(d, address, value);
+ acc_reg_write(d, address, value);
/* Default RLIM/ALEN configuration */
address = HWPfDmaConfig1Reg;
value = (1 << 31) + (23 << 8) + (1 << 6) + 7;
- acc100_reg_write(d, address, value);
+ acc_reg_write(d, address, value);
/* Configure DMA Qmanager addresses */
address = HWPfDmaQmgrAddrReg;
value = HWPfQmgrEgressQueuesTemplate;
- acc100_reg_write(d, address, value);
+ acc_reg_write(d, address, value);
/* Default Fabric Mode */
address = HWPfFabricMode;
value = ACC100_FABRIC_MODE;
- acc100_reg_write(d, address, value);
+ acc_reg_write(d, address, value);
/* ===== Qmgr Configuration ===== */
/* Configuration of the AQueue Depth QMGR_GRP_0_DEPTH_LOG2 for UL */
@@ -4694,42 +4061,42 @@ acc100_configure(const char *dev_name, struct rte_acc100_conf *conf)
conf->q_dl_5g.num_qgroups;
for (qg_idx = 0; qg_idx < totalQgs; qg_idx++) {
address = HWPfQmgrDepthLog2Grp +
- ACC100_BYTES_IN_WORD * qg_idx;
+ ACC_BYTES_IN_WORD * qg_idx;
value = aqDepth(qg_idx, conf);
- acc100_reg_write(d, address, value);
+ acc_reg_write(d, address, value);
address = HWPfQmgrTholdGrp +
- ACC100_BYTES_IN_WORD * qg_idx;
+ ACC_BYTES_IN_WORD * qg_idx;
value = (1 << 16) + (1 << (aqDepth(qg_idx, conf) - 1));
- acc100_reg_write(d, address, value);
+ acc_reg_write(d, address, value);
}
/* Template Priority in incremental order */
- for (template_idx = 0; template_idx < ACC100_NUM_TMPL; template_idx++) {
- address = HWPfQmgrGrpTmplateReg0Indx + ACC100_BYTES_IN_WORD * template_idx;
- value = ACC100_TMPL_PRI_0;
- acc100_reg_write(d, address, value);
- address = HWPfQmgrGrpTmplateReg1Indx + ACC100_BYTES_IN_WORD * template_idx;
- value = ACC100_TMPL_PRI_1;
- acc100_reg_write(d, address, value);
- address = HWPfQmgrGrpTmplateReg2indx + ACC100_BYTES_IN_WORD * template_idx;
- value = ACC100_TMPL_PRI_2;
- acc100_reg_write(d, address, value);
- address = HWPfQmgrGrpTmplateReg3Indx + ACC100_BYTES_IN_WORD * template_idx;
- value = ACC100_TMPL_PRI_3;
- acc100_reg_write(d, address, value);
+ for (template_idx = 0; template_idx < ACC_NUM_TMPL; template_idx++) {
+ address = HWPfQmgrGrpTmplateReg0Indx + ACC_BYTES_IN_WORD * template_idx;
+ value = ACC_TMPL_PRI_0;
+ acc_reg_write(d, address, value);
+ address = HWPfQmgrGrpTmplateReg1Indx + ACC_BYTES_IN_WORD * template_idx;
+ value = ACC_TMPL_PRI_1;
+ acc_reg_write(d, address, value);
+ address = HWPfQmgrGrpTmplateReg2indx + ACC_BYTES_IN_WORD * template_idx;
+ value = ACC_TMPL_PRI_2;
+ acc_reg_write(d, address, value);
+ address = HWPfQmgrGrpTmplateReg3Indx + ACC_BYTES_IN_WORD * template_idx;
+ value = ACC_TMPL_PRI_3;
+ acc_reg_write(d, address, value);
}
address = HWPfQmgrGrpPriority;
value = ACC100_CFG_QMGR_HI_P;
- acc100_reg_write(d, address, value);
+ acc_reg_write(d, address, value);
/* Template Configuration */
- for (template_idx = 0; template_idx < ACC100_NUM_TMPL;
+ for (template_idx = 0; template_idx < ACC_NUM_TMPL;
template_idx++) {
value = 0;
address = HWPfQmgrGrpTmplateReg4Indx
- + ACC100_BYTES_IN_WORD * template_idx;
- acc100_reg_write(d, address, value);
+ + ACC_BYTES_IN_WORD * template_idx;
+ acc_reg_write(d, address, value);
}
/* 4GUL */
int numQgs = conf->q_ul_4g.num_qgroups;
@@ -4741,8 +4108,8 @@ acc100_configure(const char *dev_name, struct rte_acc100_conf *conf)
template_idx <= ACC100_SIG_UL_4G_LAST;
template_idx++) {
address = HWPfQmgrGrpTmplateReg4Indx
- + ACC100_BYTES_IN_WORD * template_idx;
- acc100_reg_write(d, address, value);
+ + ACC_BYTES_IN_WORD * template_idx;
+ acc_reg_write(d, address, value);
}
/* 5GUL */
numQqsAcc += numQgs;
@@ -4756,15 +4123,15 @@ acc100_configure(const char *dev_name, struct rte_acc100_conf *conf)
template_idx++) {
/* Check engine power-on status */
address = HwPfFecUl5gIbDebugReg +
- ACC100_ENGINE_OFFSET * template_idx;
- status = (acc100_reg_read(d, address) >> 4) & 0xF;
+ ACC_ENGINE_OFFSET * template_idx;
+ status = (acc_reg_read(d, address) >> 4) & 0xF;
address = HWPfQmgrGrpTmplateReg4Indx
- + ACC100_BYTES_IN_WORD * template_idx;
+ + ACC_BYTES_IN_WORD * template_idx;
if (status == 1) {
- acc100_reg_write(d, address, value);
+ acc_reg_write(d, address, value);
numEngines++;
} else
- acc100_reg_write(d, address, 0);
+ acc_reg_write(d, address, 0);
}
printf("Number of 5GUL engines %d\n", numEngines);
/* 4GDL */
@@ -4777,8 +4144,8 @@ acc100_configure(const char *dev_name, struct rte_acc100_conf *conf)
template_idx <= ACC100_SIG_DL_4G_LAST;
template_idx++) {
address = HWPfQmgrGrpTmplateReg4Indx
- + ACC100_BYTES_IN_WORD * template_idx;
- acc100_reg_write(d, address, value);
+ + ACC_BYTES_IN_WORD * template_idx;
+ acc_reg_write(d, address, value);
}
/* 5GDL */
numQqsAcc += numQgs;
@@ -4790,8 +4157,8 @@ acc100_configure(const char *dev_name, struct rte_acc100_conf *conf)
template_idx <= ACC100_SIG_DL_5G_LAST;
template_idx++) {
address = HWPfQmgrGrpTmplateReg4Indx
- + ACC100_BYTES_IN_WORD * template_idx;
- acc100_reg_write(d, address, value);
+ + ACC_BYTES_IN_WORD * template_idx;
+ acc_reg_write(d, address, value);
}
/* Queue Group Function mapping */
@@ -4802,14 +4169,14 @@ acc100_configure(const char *dev_name, struct rte_acc100_conf *conf)
acc = accFromQgid(qg_idx, conf);
value |= qman_func_id[acc]<<(qg_idx * 4);
}
- acc100_reg_write(d, address, value);
+ acc_reg_write(d, address, value);
/* Configuration of the Arbitration QGroup depth to 1 */
for (qg_idx = 0; qg_idx < totalQgs; qg_idx++) {
address = HWPfQmgrArbQDepthGrp +
- ACC100_BYTES_IN_WORD * qg_idx;
+ ACC_BYTES_IN_WORD * qg_idx;
value = 0;
- acc100_reg_write(d, address, value);
+ acc_reg_write(d, address, value);
}
/* Enabling AQueues through the Queue hierarchy*/
@@ -4820,9 +4187,9 @@ acc100_configure(const char *dev_name, struct rte_acc100_conf *conf)
qg_idx < totalQgs)
value = (1 << aqNum(qg_idx, conf)) - 1;
address = HWPfQmgrAqEnableVf
- + vf_idx * ACC100_BYTES_IN_WORD;
+ + vf_idx * ACC_BYTES_IN_WORD;
value += (qg_idx << 16);
- acc100_reg_write(d, address, value);
+ acc_reg_write(d, address, value);
}
}
@@ -4831,10 +4198,10 @@ acc100_configure(const char *dev_name, struct rte_acc100_conf *conf)
for (qg_idx = 0; qg_idx < totalQgs; qg_idx++) {
for (vf_idx = 0; vf_idx < conf->num_vf_bundles; vf_idx++) {
address = HWPfQmgrVfBaseAddr + vf_idx
- * ACC100_BYTES_IN_WORD + qg_idx
- * ACC100_BYTES_IN_WORD * 64;
+ * ACC_BYTES_IN_WORD + qg_idx
+ * ACC_BYTES_IN_WORD * 64;
value = aram_address;
- acc100_reg_write(d, address, value);
+ acc_reg_write(d, address, value);
/* Offset ARAM Address for next memory bank
* - increment of 4B
*/
@@ -4852,29 +4219,29 @@ acc100_configure(const char *dev_name, struct rte_acc100_conf *conf)
/* ==== HI Configuration ==== */
/* No Info Ring/MSI by default */
- acc100_reg_write(d, HWPfHiInfoRingIntWrEnRegPf, 0);
- acc100_reg_write(d, HWPfHiInfoRingVf2pfLoWrEnReg, 0);
- acc100_reg_write(d, HWPfHiCfgMsiIntWrEnRegPf, 0xFFFFFFFF);
- acc100_reg_write(d, HWPfHiCfgMsiVf2pfLoWrEnReg, 0xFFFFFFFF);
+ acc_reg_write(d, HWPfHiInfoRingIntWrEnRegPf, 0);
+ acc_reg_write(d, HWPfHiInfoRingVf2pfLoWrEnReg, 0);
+ acc_reg_write(d, HWPfHiCfgMsiIntWrEnRegPf, 0xFFFFFFFF);
+ acc_reg_write(d, HWPfHiCfgMsiVf2pfLoWrEnReg, 0xFFFFFFFF);
/* Prevent Block on Transmit Error */
address = HWPfHiBlockTransmitOnErrorEn;
value = 0;
- acc100_reg_write(d, address, value);
+ acc_reg_write(d, address, value);
/* Prevents to drop MSI */
address = HWPfHiMsiDropEnableReg;
value = 0;
- acc100_reg_write(d, address, value);
+ acc_reg_write(d, address, value);
/* Set the PF Mode register */
address = HWPfHiPfMode;
- value = (conf->pf_mode_en) ? ACC100_PF_VAL : 0;
- acc100_reg_write(d, address, value);
+ value = (conf->pf_mode_en) ? ACC_PF_VAL : 0;
+ acc_reg_write(d, address, value);
/* QoS overflow init */
value = 1;
address = HWPfQosmonAEvalOverflow0;
- acc100_reg_write(d, address, value);
+ acc_reg_write(d, address, value);
address = HWPfQosmonBEvalOverflow0;
- acc100_reg_write(d, address, value);
+ acc_reg_write(d, address, value);
/* HARQ DDR Configuration */
unsigned int ddrSizeInMb = ACC100_HARQ_DDR;
@@ -4883,9 +4250,9 @@ acc100_configure(const char *dev_name, struct rte_acc100_conf *conf)
* 0x10;
value = ((vf_idx * (ddrSizeInMb / 64)) << 16) +
(ddrSizeInMb - 1);
- acc100_reg_write(d, address, value);
+ acc_reg_write(d, address, value);
}
- usleep(ACC100_LONG_WAIT);
+ usleep(ACC_LONG_WAIT);
/* Workaround in case some 5GUL engines are in an unexpected state */
if (numEngines < (ACC100_SIG_UL_5G_LAST + 1))
@@ -4893,7 +4260,7 @@ acc100_configure(const char *dev_name, struct rte_acc100_conf *conf)
uint32_t version = 0;
for (i = 0; i < 4; i++)
- version += acc100_reg_read(d,
+ version += acc_reg_read(d,
HWPfDdrPhyIdtmFwVersion + 4 * i) << (8 * i);
if (version != ACC100_PRQ_DDR_VER) {
printf("* Note: Not on DDR PRQ version %8x != %08x\n",
@@ -4901,76 +4268,76 @@ acc100_configure(const char *dev_name, struct rte_acc100_conf *conf)
} else if (firstCfg) {
/* ---- DDR configuration at boot up --- */
/* Read Clear Ddr training status */
- acc100_reg_read(d, HWPfChaDdrStDoneStatus);
+ acc_reg_read(d, HWPfChaDdrStDoneStatus);
/* Reset PHY/IDTM/UMMC */
- acc100_reg_write(d, HWPfChaDdrWbRstCfg, 3);
- acc100_reg_write(d, HWPfChaDdrApbRstCfg, 2);
- acc100_reg_write(d, HWPfChaDdrPhyRstCfg, 2);
- acc100_reg_write(d, HWPfChaDdrCpuRstCfg, 3);
- acc100_reg_write(d, HWPfChaDdrSifRstCfg, 2);
- usleep(ACC100_MS_IN_US);
+ acc_reg_write(d, HWPfChaDdrWbRstCfg, 3);
+ acc_reg_write(d, HWPfChaDdrApbRstCfg, 2);
+ acc_reg_write(d, HWPfChaDdrPhyRstCfg, 2);
+ acc_reg_write(d, HWPfChaDdrCpuRstCfg, 3);
+ acc_reg_write(d, HWPfChaDdrSifRstCfg, 2);
+ usleep(ACC_MS_IN_US);
/* Reset WB and APB resets */
- acc100_reg_write(d, HWPfChaDdrWbRstCfg, 2);
- acc100_reg_write(d, HWPfChaDdrApbRstCfg, 3);
+ acc_reg_write(d, HWPfChaDdrWbRstCfg, 2);
+ acc_reg_write(d, HWPfChaDdrApbRstCfg, 3);
/* Configure PHY-IDTM */
- acc100_reg_write(d, HWPfDdrPhyIdletimeout, 0x3e8);
+ acc_reg_write(d, HWPfDdrPhyIdletimeout, 0x3e8);
/* IDTM timing registers */
- acc100_reg_write(d, HWPfDdrPhyRdLatency, 0x13);
- acc100_reg_write(d, HWPfDdrPhyRdLatencyDbi, 0x15);
- acc100_reg_write(d, HWPfDdrPhyWrLatency, 0x10011);
+ acc_reg_write(d, HWPfDdrPhyRdLatency, 0x13);
+ acc_reg_write(d, HWPfDdrPhyRdLatencyDbi, 0x15);
+ acc_reg_write(d, HWPfDdrPhyWrLatency, 0x10011);
/* Configure SDRAM MRS registers */
- acc100_reg_write(d, HWPfDdrPhyMr01Dimm, 0x3030b70);
- acc100_reg_write(d, HWPfDdrPhyMr01DimmDbi, 0x3030b50);
- acc100_reg_write(d, HWPfDdrPhyMr23Dimm, 0x30);
- acc100_reg_write(d, HWPfDdrPhyMr67Dimm, 0xc00);
- acc100_reg_write(d, HWPfDdrPhyMr45Dimm, 0x4000000);
+ acc_reg_write(d, HWPfDdrPhyMr01Dimm, 0x3030b70);
+ acc_reg_write(d, HWPfDdrPhyMr01DimmDbi, 0x3030b50);
+ acc_reg_write(d, HWPfDdrPhyMr23Dimm, 0x30);
+ acc_reg_write(d, HWPfDdrPhyMr67Dimm, 0xc00);
+ acc_reg_write(d, HWPfDdrPhyMr45Dimm, 0x4000000);
/* Configure active lanes */
- acc100_reg_write(d, HWPfDdrPhyDqsCountMax, 0x9);
- acc100_reg_write(d, HWPfDdrPhyDqsCountNum, 0x9);
+ acc_reg_write(d, HWPfDdrPhyDqsCountMax, 0x9);
+ acc_reg_write(d, HWPfDdrPhyDqsCountNum, 0x9);
/* Configure WR/RD leveling timing registers */
- acc100_reg_write(d, HWPfDdrPhyWrlvlWwRdlvlRr, 0x101212);
+ acc_reg_write(d, HWPfDdrPhyWrlvlWwRdlvlRr, 0x101212);
/* Configure what trainings to execute */
- acc100_reg_write(d, HWPfDdrPhyTrngType, 0x2d3c);
+ acc_reg_write(d, HWPfDdrPhyTrngType, 0x2d3c);
/* Releasing PHY reset */
- acc100_reg_write(d, HWPfChaDdrPhyRstCfg, 3);
+ acc_reg_write(d, HWPfChaDdrPhyRstCfg, 3);
/* Configure Memory Controller registers */
- acc100_reg_write(d, HWPfDdrMemInitPhyTrng0, 0x3);
- acc100_reg_write(d, HWPfDdrBcDram, 0x3c232003);
- acc100_reg_write(d, HWPfDdrBcAddrMap, 0x31);
+ acc_reg_write(d, HWPfDdrMemInitPhyTrng0, 0x3);
+ acc_reg_write(d, HWPfDdrBcDram, 0x3c232003);
+ acc_reg_write(d, HWPfDdrBcAddrMap, 0x31);
/* Configure UMMC BC timing registers */
- acc100_reg_write(d, HWPfDdrBcRef, 0xa22);
- acc100_reg_write(d, HWPfDdrBcTim0, 0x4050501);
- acc100_reg_write(d, HWPfDdrBcTim1, 0xf0b0476);
- acc100_reg_write(d, HWPfDdrBcTim2, 0x103);
- acc100_reg_write(d, HWPfDdrBcTim3, 0x144050a1);
- acc100_reg_write(d, HWPfDdrBcTim4, 0x23300);
- acc100_reg_write(d, HWPfDdrBcTim5, 0x4230276);
- acc100_reg_write(d, HWPfDdrBcTim6, 0x857914);
- acc100_reg_write(d, HWPfDdrBcTim7, 0x79100232);
- acc100_reg_write(d, HWPfDdrBcTim8, 0x100007ce);
- acc100_reg_write(d, HWPfDdrBcTim9, 0x50020);
- acc100_reg_write(d, HWPfDdrBcTim10, 0x40ee);
+ acc_reg_write(d, HWPfDdrBcRef, 0xa22);
+ acc_reg_write(d, HWPfDdrBcTim0, 0x4050501);
+ acc_reg_write(d, HWPfDdrBcTim1, 0xf0b0476);
+ acc_reg_write(d, HWPfDdrBcTim2, 0x103);
+ acc_reg_write(d, HWPfDdrBcTim3, 0x144050a1);
+ acc_reg_write(d, HWPfDdrBcTim4, 0x23300);
+ acc_reg_write(d, HWPfDdrBcTim5, 0x4230276);
+ acc_reg_write(d, HWPfDdrBcTim6, 0x857914);
+ acc_reg_write(d, HWPfDdrBcTim7, 0x79100232);
+ acc_reg_write(d, HWPfDdrBcTim8, 0x100007ce);
+ acc_reg_write(d, HWPfDdrBcTim9, 0x50020);
+ acc_reg_write(d, HWPfDdrBcTim10, 0x40ee);
/* Configure UMMC DFI timing registers */
- acc100_reg_write(d, HWPfDdrDfiInit, 0x5000);
- acc100_reg_write(d, HWPfDdrDfiTim0, 0x15030006);
- acc100_reg_write(d, HWPfDdrDfiTim1, 0x11305);
- acc100_reg_write(d, HWPfDdrDfiPhyUpdEn, 0x1);
- acc100_reg_write(d, HWPfDdrUmmcIntEn, 0x1f);
+ acc_reg_write(d, HWPfDdrDfiInit, 0x5000);
+ acc_reg_write(d, HWPfDdrDfiTim0, 0x15030006);
+ acc_reg_write(d, HWPfDdrDfiTim1, 0x11305);
+ acc_reg_write(d, HWPfDdrDfiPhyUpdEn, 0x1);
+ acc_reg_write(d, HWPfDdrUmmcIntEn, 0x1f);
/* Release IDTM CPU out of reset */
- acc100_reg_write(d, HWPfChaDdrCpuRstCfg, 0x2);
+ acc_reg_write(d, HWPfChaDdrCpuRstCfg, 0x2);
/* Wait PHY-IDTM to finish static training */
for (i = 0; i < ACC100_DDR_TRAINING_MAX; i++) {
- usleep(ACC100_MS_IN_US);
- value = acc100_reg_read(d,
+ usleep(ACC_MS_IN_US);
+ value = acc_reg_read(d,
HWPfChaDdrStDoneStatus);
if (value & 1)
break;
}
printf("DDR Training completed in %d ms", i);
/* Enable Memory Controller */
- acc100_reg_write(d, HWPfDdrUmmcCtrl, 0x401);
+ acc_reg_write(d, HWPfDdrUmmcCtrl, 0x401);
/* Release AXI interface reset */
- acc100_reg_write(d, HWPfChaDdrSifRstCfg, 3);
+ acc_reg_write(d, HWPfChaDdrSifRstCfg, 3);
}
rte_bbdev_log_debug("PF Tip configuration complete for %s", dev_name);
@@ -4980,7 +4347,7 @@ acc100_configure(const char *dev_name, struct rte_acc100_conf *conf)
/* Initial configuration of a ACC101 device prior to running configure() */
static int
-acc101_configure(const char *dev_name, struct rte_acc100_conf *conf)
+acc101_configure(const char *dev_name, struct rte_acc_conf *conf)
{
rte_bbdev_log(INFO, "rte_acc101_configure");
uint32_t value, address, status;
@@ -4988,10 +4355,10 @@ acc101_configure(const char *dev_name, struct rte_acc100_conf *conf)
struct rte_bbdev *bbdev = rte_bbdev_get_named_dev(dev_name);
/* Compile time checks */
- RTE_BUILD_BUG_ON(sizeof(struct acc100_dma_req_desc) != 256);
- RTE_BUILD_BUG_ON(sizeof(union acc100_dma_desc) != 256);
- RTE_BUILD_BUG_ON(sizeof(struct acc100_fcw_td) != 24);
- RTE_BUILD_BUG_ON(sizeof(struct acc100_fcw_te) != 32);
+ RTE_BUILD_BUG_ON(sizeof(struct acc_dma_req_desc) != 256);
+ RTE_BUILD_BUG_ON(sizeof(union acc_dma_desc) != 256);
+ RTE_BUILD_BUG_ON(sizeof(struct acc_fcw_td) != 24);
+ RTE_BUILD_BUG_ON(sizeof(struct acc_fcw_te) != 32);
if (bbdev == NULL) {
rte_bbdev_log(ERR,
@@ -4999,67 +4366,67 @@ acc101_configure(const char *dev_name, struct rte_acc100_conf *conf)
dev_name);
return -ENODEV;
}
- struct acc100_device *d = bbdev->data->dev_private;
+ struct acc_device *d = bbdev->data->dev_private;
/* Store configuration */
- rte_memcpy(&d->acc100_conf, conf, sizeof(d->acc100_conf));
+ rte_memcpy(&d->acc_conf, conf, sizeof(d->acc_conf));
/* PCIe Bridge configuration */
- acc100_reg_write(d, HwPfPcieGpexBridgeControl, ACC101_CFG_PCI_BRIDGE);
+ acc_reg_write(d, HwPfPcieGpexBridgeControl, ACC101_CFG_PCI_BRIDGE);
for (i = 1; i < ACC101_GPEX_AXIMAP_NUM; i++)
- acc100_reg_write(d, HwPfPcieGpexAxiAddrMappingWindowPexBaseHigh + i * 16, 0);
+ acc_reg_write(d, HwPfPcieGpexAxiAddrMappingWindowPexBaseHigh + i * 16, 0);
/* Prevent blocking AXI read on BRESP for AXI Write */
address = HwPfPcieGpexAxiPioControl;
value = ACC101_CFG_PCI_AXI;
- acc100_reg_write(d, address, value);
+ acc_reg_write(d, address, value);
/* Explicitly releasing AXI including a 2ms delay on ACC101 */
usleep(2000);
- acc100_reg_write(d, HWPfDmaAxiControl, 1);
+ acc_reg_write(d, HWPfDmaAxiControl, 1);
/* Set the default 5GDL DMA configuration */
- acc100_reg_write(d, HWPfDmaInboundDrainDataSize, ACC101_DMA_INBOUND);
+ acc_reg_write(d, HWPfDmaInboundDrainDataSize, ACC101_DMA_INBOUND);
/* Enable granular dynamic clock gating */
address = HWPfHiClkGateHystReg;
value = ACC101_CLOCK_GATING_EN;
- acc100_reg_write(d, address, value);
+ acc_reg_write(d, address, value);
/* Set default descriptor signature */
address = HWPfDmaDescriptorSignatuture;
value = 0;
- acc100_reg_write(d, address, value);
+ acc_reg_write(d, address, value);
/* Enable the Error Detection in DMA */
value = ACC101_CFG_DMA_ERROR;
address = HWPfDmaErrorDetectionEn;
- acc100_reg_write(d, address, value);
+ acc_reg_write(d, address, value);
/* AXI Cache configuration */
value = ACC101_CFG_AXI_CACHE;
address = HWPfDmaAxcacheReg;
- acc100_reg_write(d, address, value);
+ acc_reg_write(d, address, value);
/* Default DMA Configuration (Qmgr Enabled) */
address = HWPfDmaConfig0Reg;
value = 0;
- acc100_reg_write(d, address, value);
+ acc_reg_write(d, address, value);
address = HWPfDmaQmanen;
value = 0;
- acc100_reg_write(d, address, value);
+ acc_reg_write(d, address, value);
/* Default RLIM/ALEN configuration */
address = HWPfDmaConfig1Reg;
int alen_r = 0xF;
int alen_w = 0x7;
value = (1 << 31) + (alen_w << 20) + (1 << 6) + alen_r;
- acc100_reg_write(d, address, value);
+ acc_reg_write(d, address, value);
/* Configure DMA Qmanager addresses */
address = HWPfDmaQmgrAddrReg;
value = HWPfQmgrEgressQueuesTemplate;
- acc100_reg_write(d, address, value);
+ acc_reg_write(d, address, value);
/* ===== Qmgr Configuration ===== */
/* Configuration of the AQueue Depth QMGR_GRP_0_DEPTH_LOG2 for UL */
@@ -5069,43 +4436,43 @@ acc101_configure(const char *dev_name, struct rte_acc100_conf *conf)
conf->q_dl_5g.num_qgroups;
for (qg_idx = 0; qg_idx < totalQgs; qg_idx++) {
address = HWPfQmgrDepthLog2Grp +
- ACC101_BYTES_IN_WORD * qg_idx;
+ ACC_BYTES_IN_WORD * qg_idx;
value = aqDepth(qg_idx, conf);
- acc100_reg_write(d, address, value);
+ acc_reg_write(d, address, value);
address = HWPfQmgrTholdGrp +
- ACC101_BYTES_IN_WORD * qg_idx;
+ ACC_BYTES_IN_WORD * qg_idx;
value = (1 << 16) + (1 << (aqDepth(qg_idx, conf) - 1));
- acc100_reg_write(d, address, value);
+ acc_reg_write(d, address, value);
}
/* Template Priority in incremental order */
- for (template_idx = 0; template_idx < ACC101_NUM_TMPL;
+ for (template_idx = 0; template_idx < ACC_NUM_TMPL;
template_idx++) {
- address = HWPfQmgrGrpTmplateReg0Indx + ACC101_BYTES_IN_WORD * template_idx;
- value = ACC101_TMPL_PRI_0;
- acc100_reg_write(d, address, value);
- address = HWPfQmgrGrpTmplateReg1Indx + ACC101_BYTES_IN_WORD * template_idx;
- value = ACC101_TMPL_PRI_1;
- acc100_reg_write(d, address, value);
- address = HWPfQmgrGrpTmplateReg2indx + ACC101_BYTES_IN_WORD * template_idx;
- value = ACC101_TMPL_PRI_2;
- acc100_reg_write(d, address, value);
- address = HWPfQmgrGrpTmplateReg3Indx + ACC101_BYTES_IN_WORD * template_idx;
- value = ACC101_TMPL_PRI_3;
- acc100_reg_write(d, address, value);
+ address = HWPfQmgrGrpTmplateReg0Indx + ACC_BYTES_IN_WORD * template_idx;
+ value = ACC_TMPL_PRI_0;
+ acc_reg_write(d, address, value);
+ address = HWPfQmgrGrpTmplateReg1Indx + ACC_BYTES_IN_WORD * template_idx;
+ value = ACC_TMPL_PRI_1;
+ acc_reg_write(d, address, value);
+ address = HWPfQmgrGrpTmplateReg2indx + ACC_BYTES_IN_WORD * template_idx;
+ value = ACC_TMPL_PRI_2;
+ acc_reg_write(d, address, value);
+ address = HWPfQmgrGrpTmplateReg3Indx + ACC_BYTES_IN_WORD * template_idx;
+ value = ACC_TMPL_PRI_3;
+ acc_reg_write(d, address, value);
}
address = HWPfQmgrGrpPriority;
value = ACC101_CFG_QMGR_HI_P;
- acc100_reg_write(d, address, value);
+ acc_reg_write(d, address, value);
/* Template Configuration */
- for (template_idx = 0; template_idx < ACC101_NUM_TMPL;
+ for (template_idx = 0; template_idx < ACC_NUM_TMPL;
template_idx++) {
value = 0;
address = HWPfQmgrGrpTmplateReg4Indx
- + ACC101_BYTES_IN_WORD * template_idx;
- acc100_reg_write(d, address, value);
+ + ACC_BYTES_IN_WORD * template_idx;
+ acc_reg_write(d, address, value);
}
/* 4GUL */
int numQgs = conf->q_ul_4g.num_qgroups;
@@ -5117,8 +4484,8 @@ acc101_configure(const char *dev_name, struct rte_acc100_conf *conf)
template_idx <= ACC101_SIG_UL_4G_LAST;
template_idx++) {
address = HWPfQmgrGrpTmplateReg4Indx
- + ACC101_BYTES_IN_WORD * template_idx;
- acc100_reg_write(d, address, value);
+ + ACC_BYTES_IN_WORD * template_idx;
+ acc_reg_write(d, address, value);
}
/* 5GUL */
numQqsAcc += numQgs;
@@ -5132,15 +4499,15 @@ acc101_configure(const char *dev_name, struct rte_acc100_conf *conf)
template_idx++) {
/* Check engine power-on status */
address = HwPfFecUl5gIbDebugReg +
- ACC101_ENGINE_OFFSET * template_idx;
- status = (acc100_reg_read(d, address) >> 4) & 0xF;
+ ACC_ENGINE_OFFSET * template_idx;
+ status = (acc_reg_read(d, address) >> 4) & 0xF;
address = HWPfQmgrGrpTmplateReg4Indx
- + ACC101_BYTES_IN_WORD * template_idx;
+ + ACC_BYTES_IN_WORD * template_idx;
if (status == 1) {
- acc100_reg_write(d, address, value);
+ acc_reg_write(d, address, value);
numEngines++;
} else
- acc100_reg_write(d, address, 0);
+ acc_reg_write(d, address, 0);
}
printf("Number of 5GUL engines %d\n", numEngines);
/* 4GDL */
@@ -5153,8 +4520,8 @@ acc101_configure(const char *dev_name, struct rte_acc100_conf *conf)
template_idx <= ACC101_SIG_DL_4G_LAST;
template_idx++) {
address = HWPfQmgrGrpTmplateReg4Indx
- + ACC101_BYTES_IN_WORD * template_idx;
- acc100_reg_write(d, address, value);
+ + ACC_BYTES_IN_WORD * template_idx;
+ acc_reg_write(d, address, value);
}
/* 5GDL */
numQqsAcc += numQgs;
@@ -5166,8 +4533,8 @@ acc101_configure(const char *dev_name, struct rte_acc100_conf *conf)
template_idx <= ACC101_SIG_DL_5G_LAST;
template_idx++) {
address = HWPfQmgrGrpTmplateReg4Indx
- + ACC101_BYTES_IN_WORD * template_idx;
- acc100_reg_write(d, address, value);
+ + ACC_BYTES_IN_WORD * template_idx;
+ acc_reg_write(d, address, value);
}
/* Queue Group Function mapping */
@@ -5178,14 +4545,14 @@ acc101_configure(const char *dev_name, struct rte_acc100_conf *conf)
acc = accFromQgid(qg_idx, conf);
value |= qman_func_id[acc]<<(qg_idx * 4);
}
- acc100_reg_write(d, address, value);
+ acc_reg_write(d, address, value);
/* Configuration of the Arbitration QGroup depth to 1 */
for (qg_idx = 0; qg_idx < totalQgs; qg_idx++) {
address = HWPfQmgrArbQDepthGrp +
- ACC101_BYTES_IN_WORD * qg_idx;
+ ACC_BYTES_IN_WORD * qg_idx;
value = 0;
- acc100_reg_write(d, address, value);
+ acc_reg_write(d, address, value);
}
/* Enabling AQueues through the Queue hierarchy*/
@@ -5196,9 +4563,9 @@ acc101_configure(const char *dev_name, struct rte_acc100_conf *conf)
qg_idx < totalQgs)
value = (1 << aqNum(qg_idx, conf)) - 1;
address = HWPfQmgrAqEnableVf
- + vf_idx * ACC101_BYTES_IN_WORD;
+ + vf_idx * ACC_BYTES_IN_WORD;
value += (qg_idx << 16);
- acc100_reg_write(d, address, value);
+ acc_reg_write(d, address, value);
}
}
@@ -5207,10 +4574,10 @@ acc101_configure(const char *dev_name, struct rte_acc100_conf *conf)
for (qg_idx = 0; qg_idx < totalQgs; qg_idx++) {
for (vf_idx = 0; vf_idx < conf->num_vf_bundles; vf_idx++) {
address = HWPfQmgrVfBaseAddr + vf_idx
- * ACC101_BYTES_IN_WORD + qg_idx
- * ACC101_BYTES_IN_WORD * 64;
+ * ACC_BYTES_IN_WORD + qg_idx
+ * ACC_BYTES_IN_WORD * 64;
value = aram_address;
- acc100_reg_write(d, address, value);
+ acc_reg_write(d, address, value);
/* Offset ARAM Address for next memory bank
* - increment of 4B
*/
@@ -5228,32 +4595,32 @@ acc101_configure(const char *dev_name, struct rte_acc100_conf *conf)
/* ==== HI Configuration ==== */
/* No Info Ring/MSI by default */
- acc100_reg_write(d, HWPfHiInfoRingIntWrEnRegPf, 0);
- acc100_reg_write(d, HWPfHiInfoRingVf2pfLoWrEnReg, 0);
- acc100_reg_write(d, HWPfHiCfgMsiIntWrEnRegPf, 0xFFFFFFFF);
- acc100_reg_write(d, HWPfHiCfgMsiVf2pfLoWrEnReg, 0xFFFFFFFF);
+ acc_reg_write(d, HWPfHiInfoRingIntWrEnRegPf, 0);
+ acc_reg_write(d, HWPfHiInfoRingVf2pfLoWrEnReg, 0);
+ acc_reg_write(d, HWPfHiCfgMsiIntWrEnRegPf, 0xFFFFFFFF);
+ acc_reg_write(d, HWPfHiCfgMsiVf2pfLoWrEnReg, 0xFFFFFFFF);
/* Prevent Block on Transmit Error */
address = HWPfHiBlockTransmitOnErrorEn;
value = 0;
- acc100_reg_write(d, address, value);
+ acc_reg_write(d, address, value);
/* Prevents to drop MSI */
address = HWPfHiMsiDropEnableReg;
value = 0;
- acc100_reg_write(d, address, value);
+ acc_reg_write(d, address, value);
/* Set the PF Mode register */
address = HWPfHiPfMode;
- value = (conf->pf_mode_en) ? ACC101_PF_VAL : 0;
- acc100_reg_write(d, address, value);
+ value = (conf->pf_mode_en) ? ACC_PF_VAL : 0;
+ acc_reg_write(d, address, value);
/* Explicitly releasing AXI after PF Mode and 2 ms */
usleep(2000);
- acc100_reg_write(d, HWPfDmaAxiControl, 1);
+ acc_reg_write(d, HWPfDmaAxiControl, 1);
/* QoS overflow init */
value = 1;
address = HWPfQosmonAEvalOverflow0;
- acc100_reg_write(d, address, value);
+ acc_reg_write(d, address, value);
address = HWPfQosmonBEvalOverflow0;
- acc100_reg_write(d, address, value);
+ acc_reg_write(d, address, value);
/* HARQ DDR Configuration */
unsigned int ddrSizeInMb = ACC101_HARQ_DDR;
@@ -5262,16 +4629,16 @@ acc101_configure(const char *dev_name, struct rte_acc100_conf *conf)
* 0x10;
value = ((vf_idx * (ddrSizeInMb / 64)) << 16) +
(ddrSizeInMb - 1);
- acc100_reg_write(d, address, value);
+ acc_reg_write(d, address, value);
}
- usleep(ACC101_LONG_WAIT);
+ usleep(ACC_LONG_WAIT);
rte_bbdev_log_debug("PF TIP configuration complete for %s", dev_name);
return 0;
}
int
-rte_acc10x_configure(const char *dev_name, struct rte_acc100_conf *conf)
+rte_acc10x_configure(const char *dev_name, struct rte_acc_conf *conf)
{
struct rte_bbdev *bbdev = rte_bbdev_get_named_dev(dev_name);
if (bbdev == NULL) {
diff --git a/drivers/baseband/acc100/rte_acc_common_cfg.h b/drivers/baseband/acc100/rte_acc_common_cfg.h
new file mode 100644
index 0000000000..8292ef44da
--- /dev/null
+++ b/drivers/baseband/acc100/rte_acc_common_cfg.h
@@ -0,0 +1,101 @@
+/* SPDX-License-Identifier: BSD-3-Clause
+ * Copyright(c) 2022 Intel Corporation
+ */
+
+#ifndef _RTE_ACC_COMMON_CFG_H_
+#define _RTE_ACC_COMMON_CFG_H_
+
+/**
+ * @file rte_acc100_cfg.h
+ *
+ * Functions for configuring ACC100 HW, exposed directly to applications.
+ * Configuration related to encoding/decoding is done through the
+ * librte_bbdev library.
+ *
+ * @warning
+ * @b EXPERIMENTAL: this API may change without prior notice
+ */
+
+#include <stdint.h>
+#include <stdbool.h>
+
+#ifdef __cplusplus
+extern "C" {
+#endif
+
+/**< Number of Virtual Functions ACC300 supports */
+#define RTE_ACC_NUM_VFS 64
+
+/**
+ * Definition of Queue Topology for ACC300 Configuration
+ * Some level of details is abstracted out to expose a clean interface
+ * given that comprehensive flexibility is not required
+ */
+struct rte_acc_queue_topology {
+ /** Number of QGroups in incremental order of priority */
+ uint16_t num_qgroups;
+ /**
+ * All QGroups have the same number of AQs here.
+ * Note : Could be made a 16-array if more flexibility is really
+ * required
+ */
+ uint16_t num_aqs_per_groups;
+ /**
+ * Depth of the AQs is the same of all QGroups here. Log2 Enum : 2^N
+ * Note : Could be made a 16-array if more flexibility is really
+ * required
+ */
+ uint16_t aq_depth_log2;
+ /**
+ * Index of the first Queue Group Index - assuming contiguity
+ * Initialized as -1
+ */
+ int8_t first_qgroup_index;
+};
+
+/**
+ * Definition of Arbitration related parameters for ACC300 Configuration
+ */
+struct rte_acc_arbitration {
+ /** Default Weight for VF Fairness Arbitration */
+ uint16_t round_robin_weight;
+ uint32_t gbr_threshold1; /**< Guaranteed Bitrate Threshold 1 */
+ uint32_t gbr_threshold2; /**< Guaranteed Bitrate Threshold 2 */
+};
+
+/**
+ * Structure to pass ACC300 configuration.
+ * Note: all VF Bundles will have the same configuration.
+ */
+struct rte_acc_conf {
+ bool pf_mode_en; /**< 1 if PF is used for dataplane, 0 for VFs */
+ /** 1 if input '1' bit is represented by a positive LLR value, 0 if '1'
+ * bit is represented by a negative value.
+ */
+ bool input_pos_llr_1_bit;
+ /** 1 if output '1' bit is represented by a positive value, 0 if '1'
+ * bit is represented by a negative value.
+ */
+ bool output_pos_llr_1_bit;
+ uint16_t num_vf_bundles; /**< Number of VF bundles to setup */
+ /** Queue topology for each operation type */
+ struct rte_acc_queue_topology q_ul_4g;
+ struct rte_acc_queue_topology q_dl_4g;
+ struct rte_acc_queue_topology q_ul_5g;
+ struct rte_acc_queue_topology q_dl_5g;
+ struct rte_acc_queue_topology q_fft;
+ struct rte_acc_queue_topology q_mld;
+ /** Arbitration configuration for each operation type */
+ struct rte_acc_arbitration arb_ul_4g[RTE_ACC_NUM_VFS];
+ struct rte_acc_arbitration arb_dl_4g[RTE_ACC_NUM_VFS];
+ struct rte_acc_arbitration arb_ul_5g[RTE_ACC_NUM_VFS];
+ struct rte_acc_arbitration arb_dl_5g[RTE_ACC_NUM_VFS];
+ struct rte_acc_arbitration arb_fft[RTE_ACC_NUM_VFS];
+ struct rte_acc_arbitration arb_mld[RTE_ACC_NUM_VFS];
+};
+
+#ifdef __cplusplus
+}
+#endif
+
+#endif /* _RTE_ACC_COMMON_CFG_H_ */
--
2.37.1
^ permalink raw reply [flat|nested] 28+ messages in thread* [PATCH v6 03/14] baseband/acc: rename directory from acc100 to acc
2022-09-24 0:50 From: Nicolas Chautru <nicolas.chautru@intel.com> Nicolas Chautru
2022-09-24 0:50 ` [PATCH v6 01/14] baseband/acc100: remove unused registers Nicolas Chautru
2022-09-24 0:50 ` [PATCH v6 02/14] baseband/acc100: refactor to segregate common code Nicolas Chautru
@ 2022-09-24 0:50 ` Nicolas Chautru
2022-09-27 13:01 ` Maxime Coquelin
2022-09-24 0:50 ` [PATCH v6 04/14] baseband/acc: introduce PMD for ACC200 Nicolas Chautru
` (10 subsequent siblings)
13 siblings, 1 reply; 28+ messages in thread
From: Nicolas Chautru @ 2022-09-24 0:50 UTC (permalink / raw)
To: dev, thomas
Cc: maxime.coquelin, trix, mdr, bruce.richardson, hemant.agrawal,
david.marchand, stephen, hernan.vargas, Nic Chautru
From: Nic Chautru <nicolas.chautru@intel.com>
Using a common directory for the ACC PMDs
Signed-off-by: Nic Chautru <nicolas.chautru@intel.com>
---
MAINTAINERS | 2 +-
app/test-bbdev/meson.build | 4 ++--
app/test-bbdev/test_bbdev_perf.c | 4 ++--
drivers/baseband/{acc100 => acc}/acc100_pf_enum.h | 0
drivers/baseband/{acc100 => acc}/acc100_pmd.h | 0
drivers/baseband/{acc100 => acc}/acc100_vf_enum.h | 0
drivers/baseband/{acc100 => acc}/acc101_pmd.h | 0
drivers/baseband/{acc100 => acc}/acc_common.h | 0
drivers/baseband/{acc100 => acc}/meson.build | 0
drivers/baseband/{acc100 => acc}/rte_acc100_cfg.h | 0
drivers/baseband/{acc100 => acc}/rte_acc100_pmd.c | 0
drivers/baseband/{acc100 => acc}/rte_acc_common_cfg.h | 0
drivers/baseband/{acc100 => acc}/version.map | 0
drivers/baseband/meson.build | 2 +-
14 files changed, 6 insertions(+), 6 deletions(-)
rename drivers/baseband/{acc100 => acc}/acc100_pf_enum.h (100%)
rename drivers/baseband/{acc100 => acc}/acc100_pmd.h (100%)
rename drivers/baseband/{acc100 => acc}/acc100_vf_enum.h (100%)
rename drivers/baseband/{acc100 => acc}/acc101_pmd.h (100%)
rename drivers/baseband/{acc100 => acc}/acc_common.h (100%)
rename drivers/baseband/{acc100 => acc}/meson.build (100%)
rename drivers/baseband/{acc100 => acc}/rte_acc100_cfg.h (100%)
rename drivers/baseband/{acc100 => acc}/rte_acc100_pmd.c (100%)
rename drivers/baseband/{acc100 => acc}/rte_acc_common_cfg.h (100%)
rename drivers/baseband/{acc100 => acc}/version.map (100%)
diff --git a/MAINTAINERS b/MAINTAINERS
index 32ffdd1a61..52afd5d2e0 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -1336,7 +1336,7 @@ F: doc/guides/bbdevs/features/fpga_lte_fec.ini
F: drivers/baseband/fpga_5gnr_fec/
F: doc/guides/bbdevs/fpga_5gnr_fec.rst
F: doc/guides/bbdevs/features/fpga_5gnr_fec.ini
-F: drivers/baseband/acc100/
+F: drivers/baseband/acc/
F: doc/guides/bbdevs/acc100.rst
F: doc/guides/bbdevs/features/acc100.ini
F: doc/guides/bbdevs/features/acc101.ini
diff --git a/app/test-bbdev/meson.build b/app/test-bbdev/meson.build
index 76d4c26999..cd6a5089d5 100644
--- a/app/test-bbdev/meson.build
+++ b/app/test-bbdev/meson.build
@@ -20,8 +20,8 @@ endif
if dpdk_conf.has('RTE_BASEBAND_FPGA_5GNR_FEC')
deps += ['baseband_fpga_5gnr_fec']
endif
-if dpdk_conf.has('RTE_BASEBAND_ACC100')
- deps += ['baseband_acc100']
+if dpdk_conf.has('RTE_BASEBAND_ACC')
+ deps += ['baseband_acc']
endif
if dpdk_conf.has('RTE_LIBRTE_PMD_BBDEV_LA12XX')
deps += ['baseband_la12xx']
diff --git a/app/test-bbdev/test_bbdev_perf.c b/app/test-bbdev/test_bbdev_perf.c
index af9ceca67b..41c78ded7d 100644
--- a/app/test-bbdev/test_bbdev_perf.c
+++ b/app/test-bbdev/test_bbdev_perf.c
@@ -52,7 +52,7 @@
#define DL_5G_LOAD_BALANCE 128
#endif
-#ifdef RTE_BASEBAND_ACC100
+#ifdef RTE_BASEBAND_ACC
#include <rte_acc100_cfg.h>
#define ACC100PF_DRIVER_NAME ("intel_acc100_pf")
#define ACC100VF_DRIVER_NAME ("intel_acc100_vf")
@@ -705,7 +705,7 @@ add_bbdev_dev(uint8_t dev_id, struct rte_bbdev_info *info,
info->dev_name);
}
#endif
-#ifdef RTE_BASEBAND_ACC100
+#ifdef RTE_BASEBAND_ACC
if ((get_init_device() == true) &&
(!strcmp(info->drv.driver_name, ACC100PF_DRIVER_NAME))) {
struct rte_acc_conf conf;
diff --git a/drivers/baseband/acc100/acc100_pf_enum.h b/drivers/baseband/acc/acc100_pf_enum.h
similarity index 100%
rename from drivers/baseband/acc100/acc100_pf_enum.h
rename to drivers/baseband/acc/acc100_pf_enum.h
diff --git a/drivers/baseband/acc100/acc100_pmd.h b/drivers/baseband/acc/acc100_pmd.h
similarity index 100%
rename from drivers/baseband/acc100/acc100_pmd.h
rename to drivers/baseband/acc/acc100_pmd.h
diff --git a/drivers/baseband/acc100/acc100_vf_enum.h b/drivers/baseband/acc/acc100_vf_enum.h
similarity index 100%
rename from drivers/baseband/acc100/acc100_vf_enum.h
rename to drivers/baseband/acc/acc100_vf_enum.h
diff --git a/drivers/baseband/acc100/acc101_pmd.h b/drivers/baseband/acc/acc101_pmd.h
similarity index 100%
rename from drivers/baseband/acc100/acc101_pmd.h
rename to drivers/baseband/acc/acc101_pmd.h
diff --git a/drivers/baseband/acc100/acc_common.h b/drivers/baseband/acc/acc_common.h
similarity index 100%
rename from drivers/baseband/acc100/acc_common.h
rename to drivers/baseband/acc/acc_common.h
diff --git a/drivers/baseband/acc100/meson.build b/drivers/baseband/acc/meson.build
similarity index 100%
rename from drivers/baseband/acc100/meson.build
rename to drivers/baseband/acc/meson.build
diff --git a/drivers/baseband/acc100/rte_acc100_cfg.h b/drivers/baseband/acc/rte_acc100_cfg.h
similarity index 100%
rename from drivers/baseband/acc100/rte_acc100_cfg.h
rename to drivers/baseband/acc/rte_acc100_cfg.h
diff --git a/drivers/baseband/acc100/rte_acc100_pmd.c b/drivers/baseband/acc/rte_acc100_pmd.c
similarity index 100%
rename from drivers/baseband/acc100/rte_acc100_pmd.c
rename to drivers/baseband/acc/rte_acc100_pmd.c
diff --git a/drivers/baseband/acc100/rte_acc_common_cfg.h b/drivers/baseband/acc/rte_acc_common_cfg.h
similarity index 100%
rename from drivers/baseband/acc100/rte_acc_common_cfg.h
rename to drivers/baseband/acc/rte_acc_common_cfg.h
diff --git a/drivers/baseband/acc100/version.map b/drivers/baseband/acc/version.map
similarity index 100%
rename from drivers/baseband/acc100/version.map
rename to drivers/baseband/acc/version.map
diff --git a/drivers/baseband/meson.build b/drivers/baseband/meson.build
index 686e98b2ed..1d732da882 100644
--- a/drivers/baseband/meson.build
+++ b/drivers/baseband/meson.build
@@ -6,7 +6,7 @@ if is_windows
endif
drivers = [
- 'acc100',
+ 'acc',
'fpga_5gnr_fec',
'fpga_lte_fec',
'la12xx',
--
2.37.1
^ permalink raw reply [flat|nested] 28+ messages in thread* Re: [PATCH v6 03/14] baseband/acc: rename directory from acc100 to acc
2022-09-24 0:50 ` [PATCH v6 03/14] baseband/acc: rename directory from acc100 to acc Nicolas Chautru
@ 2022-09-27 13:01 ` Maxime Coquelin
0 siblings, 0 replies; 28+ messages in thread
From: Maxime Coquelin @ 2022-09-27 13:01 UTC (permalink / raw)
To: Nicolas Chautru, dev, thomas
Cc: trix, mdr, bruce.richardson, hemant.agrawal, david.marchand,
stephen, hernan.vargas
On 9/24/22 02:50, Nicolas Chautru wrote:
> From: Nic Chautru <nicolas.chautru@intel.com>
>
> Using a common directory for the ACC PMDs
>
> Signed-off-by: Nic Chautru <nicolas.chautru@intel.com>
> ---
> MAINTAINERS | 2 +-
> app/test-bbdev/meson.build | 4 ++--
> app/test-bbdev/test_bbdev_perf.c | 4 ++--
> drivers/baseband/{acc100 => acc}/acc100_pf_enum.h | 0
> drivers/baseband/{acc100 => acc}/acc100_pmd.h | 0
> drivers/baseband/{acc100 => acc}/acc100_vf_enum.h | 0
> drivers/baseband/{acc100 => acc}/acc101_pmd.h | 0
> drivers/baseband/{acc100 => acc}/acc_common.h | 0
> drivers/baseband/{acc100 => acc}/meson.build | 0
> drivers/baseband/{acc100 => acc}/rte_acc100_cfg.h | 0
> drivers/baseband/{acc100 => acc}/rte_acc100_pmd.c | 0
> drivers/baseband/{acc100 => acc}/rte_acc_common_cfg.h | 0
> drivers/baseband/{acc100 => acc}/version.map | 0
> drivers/baseband/meson.build | 2 +-
> 14 files changed, 6 insertions(+), 6 deletions(-)
> rename drivers/baseband/{acc100 => acc}/acc100_pf_enum.h (100%)
> rename drivers/baseband/{acc100 => acc}/acc100_pmd.h (100%)
> rename drivers/baseband/{acc100 => acc}/acc100_vf_enum.h (100%)
> rename drivers/baseband/{acc100 => acc}/acc101_pmd.h (100%)
> rename drivers/baseband/{acc100 => acc}/acc_common.h (100%)
> rename drivers/baseband/{acc100 => acc}/meson.build (100%)
> rename drivers/baseband/{acc100 => acc}/rte_acc100_cfg.h (100%)
> rename drivers/baseband/{acc100 => acc}/rte_acc100_pmd.c (100%)
> rename drivers/baseband/{acc100 => acc}/rte_acc_common_cfg.h (100%)
> rename drivers/baseband/{acc100 => acc}/version.map (100%)
>
> diff --git a/MAINTAINERS b/MAINTAINERS
> index 32ffdd1a61..52afd5d2e0 100644
> --- a/MAINTAINERS
> +++ b/MAINTAINERS
> @@ -1336,7 +1336,7 @@ F: doc/guides/bbdevs/features/fpga_lte_fec.ini
> F: drivers/baseband/fpga_5gnr_fec/
> F: doc/guides/bbdevs/fpga_5gnr_fec.rst
> F: doc/guides/bbdevs/features/fpga_5gnr_fec.ini
> -F: drivers/baseband/acc100/
> +F: drivers/baseband/acc/
> F: doc/guides/bbdevs/acc100.rst
> F: doc/guides/bbdevs/features/acc100.ini
> F: doc/guides/bbdevs/features/acc101.ini
> diff --git a/app/test-bbdev/meson.build b/app/test-bbdev/meson.build
> index 76d4c26999..cd6a5089d5 100644
> --- a/app/test-bbdev/meson.build
> +++ b/app/test-bbdev/meson.build
> @@ -20,8 +20,8 @@ endif
> if dpdk_conf.has('RTE_BASEBAND_FPGA_5GNR_FEC')
> deps += ['baseband_fpga_5gnr_fec']
> endif
> -if dpdk_conf.has('RTE_BASEBAND_ACC100')
> - deps += ['baseband_acc100']
> +if dpdk_conf.has('RTE_BASEBAND_ACC')
> + deps += ['baseband_acc']
> endif
> if dpdk_conf.has('RTE_LIBRTE_PMD_BBDEV_LA12XX')
> deps += ['baseband_la12xx']
> diff --git a/app/test-bbdev/test_bbdev_perf.c b/app/test-bbdev/test_bbdev_perf.c
> index af9ceca67b..41c78ded7d 100644
> --- a/app/test-bbdev/test_bbdev_perf.c
> +++ b/app/test-bbdev/test_bbdev_perf.c
> @@ -52,7 +52,7 @@
> #define DL_5G_LOAD_BALANCE 128
> #endif
>
> -#ifdef RTE_BASEBAND_ACC100
> +#ifdef RTE_BASEBAND_ACC
> #include <rte_acc100_cfg.h>
> #define ACC100PF_DRIVER_NAME ("intel_acc100_pf")
> #define ACC100VF_DRIVER_NAME ("intel_acc100_vf")
> @@ -705,7 +705,7 @@ add_bbdev_dev(uint8_t dev_id, struct rte_bbdev_info *info,
> info->dev_name);
> }
> #endif
> -#ifdef RTE_BASEBAND_ACC100
> +#ifdef RTE_BASEBAND_ACC
> if ((get_init_device() == true) &&
> (!strcmp(info->drv.driver_name, ACC100PF_DRIVER_NAME))) {
> struct rte_acc_conf conf;
> diff --git a/drivers/baseband/acc100/acc100_pf_enum.h b/drivers/baseband/acc/acc100_pf_enum.h
> similarity index 100%
> rename from drivers/baseband/acc100/acc100_pf_enum.h
> rename to drivers/baseband/acc/acc100_pf_enum.h
> diff --git a/drivers/baseband/acc100/acc100_pmd.h b/drivers/baseband/acc/acc100_pmd.h
> similarity index 100%
> rename from drivers/baseband/acc100/acc100_pmd.h
> rename to drivers/baseband/acc/acc100_pmd.h
> diff --git a/drivers/baseband/acc100/acc100_vf_enum.h b/drivers/baseband/acc/acc100_vf_enum.h
> similarity index 100%
> rename from drivers/baseband/acc100/acc100_vf_enum.h
> rename to drivers/baseband/acc/acc100_vf_enum.h
> diff --git a/drivers/baseband/acc100/acc101_pmd.h b/drivers/baseband/acc/acc101_pmd.h
> similarity index 100%
> rename from drivers/baseband/acc100/acc101_pmd.h
> rename to drivers/baseband/acc/acc101_pmd.h
> diff --git a/drivers/baseband/acc100/acc_common.h b/drivers/baseband/acc/acc_common.h
> similarity index 100%
> rename from drivers/baseband/acc100/acc_common.h
> rename to drivers/baseband/acc/acc_common.h
> diff --git a/drivers/baseband/acc100/meson.build b/drivers/baseband/acc/meson.build
> similarity index 100%
> rename from drivers/baseband/acc100/meson.build
> rename to drivers/baseband/acc/meson.build
> diff --git a/drivers/baseband/acc100/rte_acc100_cfg.h b/drivers/baseband/acc/rte_acc100_cfg.h
> similarity index 100%
> rename from drivers/baseband/acc100/rte_acc100_cfg.h
> rename to drivers/baseband/acc/rte_acc100_cfg.h
> diff --git a/drivers/baseband/acc100/rte_acc100_pmd.c b/drivers/baseband/acc/rte_acc100_pmd.c
> similarity index 100%
> rename from drivers/baseband/acc100/rte_acc100_pmd.c
> rename to drivers/baseband/acc/rte_acc100_pmd.c
> diff --git a/drivers/baseband/acc100/rte_acc_common_cfg.h b/drivers/baseband/acc/rte_acc_common_cfg.h
> similarity index 100%
> rename from drivers/baseband/acc100/rte_acc_common_cfg.h
> rename to drivers/baseband/acc/rte_acc_common_cfg.h
> diff --git a/drivers/baseband/acc100/version.map b/drivers/baseband/acc/version.map
> similarity index 100%
> rename from drivers/baseband/acc100/version.map
> rename to drivers/baseband/acc/version.map
> diff --git a/drivers/baseband/meson.build b/drivers/baseband/meson.build
> index 686e98b2ed..1d732da882 100644
> --- a/drivers/baseband/meson.build
> +++ b/drivers/baseband/meson.build
> @@ -6,7 +6,7 @@ if is_windows
> endif
>
> drivers = [
> - 'acc100',
> + 'acc',
> 'fpga_5gnr_fec',
> 'fpga_lte_fec',
> 'la12xx',
Reviewed-by: Maxime Coquelin <maxime.coquelin@redhat.com>
Thanks,
Maxime
^ permalink raw reply [flat|nested] 28+ messages in thread
* [PATCH v6 04/14] baseband/acc: introduce PMD for ACC200
2022-09-24 0:50 From: Nicolas Chautru <nicolas.chautru@intel.com> Nicolas Chautru
` (2 preceding siblings ...)
2022-09-24 0:50 ` [PATCH v6 03/14] baseband/acc: rename directory from acc100 to acc Nicolas Chautru
@ 2022-09-24 0:50 ` Nicolas Chautru
2022-09-24 0:50 ` [PATCH v6 05/14] baseband/acc: add HW register definitions " Nicolas Chautru
` (9 subsequent siblings)
13 siblings, 0 replies; 28+ messages in thread
From: Nicolas Chautru @ 2022-09-24 0:50 UTC (permalink / raw)
To: dev, thomas
Cc: maxime.coquelin, trix, mdr, bruce.richardson, hemant.agrawal,
david.marchand, stephen, hernan.vargas, Nicolas Chautru
This patch introduces stubs for device driver for the ACC200
integrated VRAN accelerator on SPR-EEC
Signed-off-by: Nicolas Chautru <nicolas.chautru@intel.com>
Reviewed-by: Maxime Coquelin <maxime.coquelin@redhat.com>
---
MAINTAINERS | 3 +
doc/guides/bbdevs/acc200.rst | 244 ++++++++++++++++++++++++++
doc/guides/bbdevs/index.rst | 1 +
drivers/baseband/acc/acc200_pmd.h | 32 ++++
drivers/baseband/acc/meson.build | 2 +-
drivers/baseband/acc/rte_acc200_pmd.c | 144 +++++++++++++++
6 files changed, 425 insertions(+), 1 deletion(-)
create mode 100644 doc/guides/bbdevs/acc200.rst
create mode 100644 drivers/baseband/acc/acc200_pmd.h
create mode 100644 drivers/baseband/acc/rte_acc200_pmd.c
diff --git a/MAINTAINERS b/MAINTAINERS
index 52afd5d2e0..909c855048 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -1340,6 +1340,9 @@ F: drivers/baseband/acc/
F: doc/guides/bbdevs/acc100.rst
F: doc/guides/bbdevs/features/acc100.ini
F: doc/guides/bbdevs/features/acc101.ini
+F: drivers/baseband/acc200/
+F: doc/guides/bbdevs/acc200.rst
+F: doc/guides/bbdevs/features/acc200.ini
Null baseband
M: Nicolas Chautru <nicolas.chautru@intel.com>
diff --git a/doc/guides/bbdevs/acc200.rst b/doc/guides/bbdevs/acc200.rst
new file mode 100644
index 0000000000..c5e1bd7890
--- /dev/null
+++ b/doc/guides/bbdevs/acc200.rst
@@ -0,0 +1,244 @@
+.. SPDX-License-Identifier: BSD-3-Clause
+ Copyright(c) 2022 Intel Corporation
+
+Intel(R) ACC200 vRAN Dedicated Accelerator Poll Mode Driver
+===========================================================
+
+The Intel® vRAN Dedicated Accelerator ACC200 peripheral enables cost-effective 4G
+and 5G next-generation virtualized Radio Access Network (vRAN) solutions integrated on
+Sapphire Rapids EEC Intel(R)7 based Xeon(R) multi-core Serverprocessor.
+
+Features
+--------
+
+The ACC200 includes a 5G Low Density Parity Check (LDPC) encoder/decoder, rate match/dematch,
+Hybrid Automatic Repeat Request (HARQ) with access to DDR memory for buffer management, a 4G
+Turbo encoder/decoder, a Fast Fourier Transform (FFT) block providing DFT/iDFT processing offload
+for the 5G Sounding Reference Signal (SRS), a Queue Manager (QMGR), and a DMA subsystem.
+There is no dedicated on-card memory for HARQ, this is using coherent memory on the CPU side.
+
+These correspond to the following features exposed by the PMD:
+
+- LDPC Encode in the Downlink (5GNR)
+- LDPC Decode in the Uplink (5GNR)
+- Turbo Encode in the Downlink (4G)
+- Turbo Decode in the Uplink (4G)
+- FFT processing
+- SR-IOV with 16 VFs per PF
+- Maximum of 256 queues per VF
+- MSI
+
+ACC200 PMD supports the following BBDEV capabilities:
+
+* For the LDPC encode operation:
+ - ``RTE_BBDEV_LDPC_CRC_24B_ATTACH`` : set to attach CRC24B to CB(s)
+ - ``RTE_BBDEV_LDPC_RATE_MATCH`` : if set then do not do Rate Match bypass
+ - ``RTE_BBDEV_LDPC_INTERLEAVER_BYPASS`` : if set then bypass interleaver
+
+* For the LDPC decode operation:
+ - ``RTE_BBDEV_LDPC_CRC_TYPE_24B_CHECK`` : check CRC24B from CB(s)
+ - ``RTE_BBDEV_LDPC_CRC_TYPE_24B_DROP`` : drops CRC24B bits appended while decoding
+ - ``RTE_BBDEV_LDPC_CRC_TYPE_24A_CHECK`` : check CRC24A from CB(s)
+ - ``RTE_BBDEV_LDPC_CRC_TYPE_16_CHECK`` : check CRC16 from CB(s)
+ - ``RTE_BBDEV_LDPC_HQ_COMBINE_IN_ENABLE`` : provides an input for HARQ combining
+ - ``RTE_BBDEV_LDPC_HQ_COMBINE_OUT_ENABLE`` : provides an input for HARQ combining
+ - ``RTE_BBDEV_LDPC_ITERATION_STOP_ENABLE`` : disable early termination
+ - ``RTE_BBDEV_LDPC_DEC_SCATTER_GATHER`` : supports scatter-gather for input/output data
+ - ``RTE_BBDEV_LDPC_HARQ_6BIT_COMPRESSION`` : supports compression of the HARQ input/output
+ - ``RTE_BBDEV_LDPC_LLR_COMPRESSION`` : supports LLR input compression
+
+* For the turbo encode operation:
+ - ``RTE_BBDEV_TURBO_CRC_24B_ATTACH`` : set to attach CRC24B to CB(s)
+ - ``RTE_BBDEV_TURBO_RATE_MATCH`` : if set then do not do Rate Match bypass
+ - ``RTE_BBDEV_TURBO_ENC_INTERRUPTS`` : set for encoder dequeue interrupts
+ - ``RTE_BBDEV_TURBO_RV_INDEX_BYPASS`` : set to bypass RV index
+ - ``RTE_BBDEV_TURBO_ENC_SCATTER_GATHER`` : supports scatter-gather for input/output data
+
+* For the turbo decode operation:
+ - ``RTE_BBDEV_TURBO_CRC_TYPE_24B`` : check CRC24B from CB(s)
+ - ``RTE_BBDEV_TURBO_SUBBLOCK_DEINTERLEAVE`` : perform subblock de-interleave
+ - ``RTE_BBDEV_TURBO_DEC_INTERRUPTS`` : set for decoder dequeue interrupts
+ - ``RTE_BBDEV_TURBO_NEG_LLR_1_BIT_IN`` : set if negative LLR input is supported
+ - ``RTE_BBDEV_TURBO_DEC_TB_CRC_24B_KEEP`` : keep CRC24B bits appended while decoding
+ - ``RTE_BBDEV_TURBO_DEC_CRC_24B_DROP`` : option to drop the code block CRC after decoding
+ - ``RTE_BBDEV_TURBO_EARLY_TERMINATION`` : set early termination feature
+ - ``RTE_BBDEV_TURBO_DEC_SCATTER_GATHER`` : supports scatter-gather for input/output data
+ - ``RTE_BBDEV_TURBO_HALF_ITERATION_EVEN`` : set half iteration granularity
+ - ``RTE_BBDEV_TURBO_SOFT_OUTPUT`` : set the APP LLR soft output
+ - ``RTE_BBDEV_TURBO_EQUALIZER`` : set the turbo equalizer feature
+ - ``RTE_BBDEV_TURBO_SOFT_OUT_SATURATE`` : set the soft output saturation
+ - ``RTE_BBDEV_TURBO_CONTINUE_CRC_MATCH`` : set to run an extra odd iteration after CRC match
+ - ``RTE_BBDEV_TURBO_NEG_LLR_1_BIT_SOFT_OUT`` : set if negative APP LLR output supported
+ - ``RTE_BBDEV_TURBO_MAP_DEC`` : supports flexible parallel MAP engine decoding
+
+Installation
+------------
+
+Section 3 of the DPDK manual provides instructions on installing and compiling DPDK.
+
+DPDK requires hugepages to be configured as detailed in section 2 of the DPDK manual.
+The bbdev test application has been tested with a configuration 40 x 1GB hugepages. The
+hugepage configuration of a server may be examined using:
+
+.. code-block:: console
+
+ grep Huge* /proc/meminfo
+
+
+Initialization
+--------------
+
+When the device first powers up, its PCI Physical Functions (PF) can be listed through these
+commands for ACC200:
+
+.. code-block:: console
+
+ sudo lspci -vd8086:57c0
+
+The physical and virtual functions are compatible with Linux UIO drivers:
+``vfio`` and ``igb_uio``. However, in order to work the 5G/4G
+FEC device first needs to be bound to one of these linux drivers through DPDK.
+
+
+Bind PF UIO driver(s)
+~~~~~~~~~~~~~~~~~~~~~
+
+Install the DPDK igb_uio driver, bind it with the PF PCI device ID and use
+``lspci`` to confirm the PF device is under use by ``igb_uio`` DPDK UIO driver.
+
+The igb_uio driver may be bound to the PF PCI device using one of two methods for ACC200:
+
+
+1. PCI functions (physical or virtual, depending on the use case) can be bound to
+the UIO driver by repeating this command for every function.
+
+.. code-block:: console
+
+ cd <dpdk-top-level-directory>
+ insmod ./build/kmod/igb_uio.ko
+ echo "8086 57c0" > /sys/bus/pci/drivers/igb_uio/new_id
+ lspci -vd8086:57c0
+
+
+2. Another way to bind PF with DPDK UIO driver is by using the ``dpdk-devbind.py`` tool
+
+.. code-block:: console
+
+ cd <dpdk-top-level-directory>
+ ./usertools/dpdk-devbind.py -b igb_uio 0000:f7:00.0
+
+where the PCI device ID (example: 0000:f7:00.0) is obtained using lspci -vd8086:57c0
+
+
+In a similar way the PF may be bound with vfio-pci as any PCIe device.
+
+
+Enable Virtual Functions
+~~~~~~~~~~~~~~~~~~~~~~~~
+
+Now, it should be visible in the printouts that PCI PF is under igb_uio control
+"``Kernel driver in use: igb_uio``"
+
+To show the number of available VFs on the device, read ``sriov_totalvfs`` file..
+
+.. code-block:: console
+
+ cat /sys/bus/pci/devices/0000\:<b>\:<d>.<f>/sriov_totalvfs
+
+ where 0000\:<b>\:<d>.<f> is the PCI device ID
+
+
+To enable VFs via igb_uio, echo the number of virtual functions intended to
+enable to ``max_vfs`` file..
+
+.. code-block:: console
+
+ echo <num-of-vfs> > /sys/bus/pci/devices/0000\:<b>\:<d>.<f>/max_vfs
+
+
+Afterwards, all VFs must be bound to appropriate UIO drivers as required, same
+way it was done with the physical function previously.
+
+Enabling SR-IOV via vfio driver is pretty much the same, except that the file
+name is different:
+
+.. code-block:: console
+
+ echo <num-of-vfs> > /sys/bus/pci/devices/0000\:<b>\:<d>.<f>/sriov_numvfs
+
+
+Configure the VFs through PF
+~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+
+The PCI virtual functions must be configured before working or getting assigned
+to VMs/Containers. The configuration involves allocating the number of hardware
+queues, priorities, load balance, bandwidth and other settings necessary for the
+device to perform FEC functions.
+
+This configuration needs to be executed at least once after reboot or PCI FLR and can
+be achieved by using the functions ``rte_acc200_configure()``,
+which sets up the parameters defined in the compatible ``acc200_conf`` structure.
+
+Test Application
+----------------
+
+BBDEV provides a test application, ``test-bbdev.py`` and range of test data for testing
+the functionality of the device, depending on the device's
+capabilities. The test application is located under app->test-bbdev folder and has the
+following options:
+
+.. code-block:: console
+
+ "-p", "--testapp-path": specifies path to the bbdev test app.
+ "-e", "--eal-params" : EAL arguments which are passed to the test app.
+ "-t", "--timeout" : Timeout in seconds (default=300).
+ "-c", "--test-cases" : Defines test cases to run. Run all if not specified.
+ "-v", "--test-vector" : Test vector path (default=dpdk_path+/app/test-bbdev/test_vectors/bbdev_null.data).
+ "-n", "--num-ops" : Number of operations to process on device (default=32).
+ "-b", "--burst-size" : Operations enqueue/dequeue burst size (default=32).
+ "-s", "--snr" : SNR in dB used when generating LLRs for bler tests.
+ "-s", "--iter_max" : Number of iterations for LDPC decoder.
+ "-l", "--num-lcores" : Number of lcores to run (default=16).
+ "-i", "--init-device" : Initialise PF device with default values.
+
+
+To execute the test application tool using simple decode or encode data,
+type one of the following:
+
+.. code-block:: console
+
+ ./test-bbdev.py -c validation -n 64 -b 1 -v ./ldpc_dec_default.data
+ ./test-bbdev.py -c validation -n 64 -b 1 -v ./ldpc_enc_default.data
+
+
+The test application ``test-bbdev.py``, supports the ability to configure the PF device with
+a default set of values, if the "-i" or "- -init-device" option is included. The default values
+are defined in test_bbdev_perf.c.
+
+
+Test Vectors
+~~~~~~~~~~~~
+
+In addition to the simple LDPC decoder and LDPC encoder tests, bbdev also provides
+a range of additional tests under the test_vectors folder, which may be useful. The results
+of these tests will depend on the device capabilities which may cause some
+testcases to be skipped, but no failure should be reported.
+
+
+Alternate Baseband Device configuration tool
+~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+
+On top of the embedded configuration feature supported in test-bbdev using "- -init-device"
+option mentioned above, there is also a tool available to perform that device configuration
+using a companion application.
+The ``pf_bb_config`` application notably enables then to run bbdev-test from the VF
+and not only limited to the PF as captured above.
+
+See for more details: https://github.com/intel/pf-bb-config
+
+Specifically for the BBDEV ACC200 PMD, the command below can be used:
+
+.. code-block:: console
+
+ ./pf_bb_config ACC200 -c ./acc200/acc200_config_vf_5g.cfg
+ ./test-bbdev.py -e="-c 0xff0 -a${VF_PCI_ADDR}" -c validation -n 64 -b 64 -l 1 -v ./ldpc_dec_default.data
diff --git a/doc/guides/bbdevs/index.rst b/doc/guides/bbdevs/index.rst
index cedd706fa6..4e9dea8e4c 100644
--- a/doc/guides/bbdevs/index.rst
+++ b/doc/guides/bbdevs/index.rst
@@ -14,4 +14,5 @@ Baseband Device Drivers
fpga_lte_fec
fpga_5gnr_fec
acc100
+ acc200
la12xx
diff --git a/drivers/baseband/acc/acc200_pmd.h b/drivers/baseband/acc/acc200_pmd.h
new file mode 100644
index 0000000000..aaa6b7753c
--- /dev/null
+++ b/drivers/baseband/acc/acc200_pmd.h
@@ -0,0 +1,32 @@
+/* SPDX-License-Identifier: BSD-3-Clause
+ * Copyright(c) 2022 Intel Corporation
+ */
+
+#ifndef _RTE_ACC200_PMD_H_
+#define _RTE_ACC200_PMD_H_
+
+#include "acc_common.h"
+
+/* Helper macro for logging */
+#define rte_bbdev_log(level, fmt, ...) \
+ rte_log(RTE_LOG_ ## level, acc200_logtype, fmt "\n", \
+ ##__VA_ARGS__)
+
+#ifdef RTE_LIBRTE_BBDEV_DEBUG
+#define rte_bbdev_log_debug(fmt, ...) \
+ rte_bbdev_log(DEBUG, "acc200_pmd: " fmt, \
+ ##__VA_ARGS__)
+#else
+#define rte_bbdev_log_debug(fmt, ...)
+#endif
+
+/* ACC200 PF and VF driver names */
+#define ACC200PF_DRIVER_NAME intel_acc200_pf
+#define ACC200VF_DRIVER_NAME intel_acc200_vf
+
+/* ACC200 PCI vendor & device IDs */
+#define RTE_ACC200_VENDOR_ID (0x8086)
+#define RTE_ACC200_PF_DEVICE_ID (0x57C0)
+#define RTE_ACC200_VF_DEVICE_ID (0x57C1)
+
+#endif /* _RTE_ACC200_PMD_H_ */
diff --git a/drivers/baseband/acc/meson.build b/drivers/baseband/acc/meson.build
index 9a1a3b8b07..63912f0621 100644
--- a/drivers/baseband/acc/meson.build
+++ b/drivers/baseband/acc/meson.build
@@ -3,6 +3,6 @@
deps += ['bbdev', 'bus_vdev', 'ring', 'pci', 'bus_pci']
-sources = files('rte_acc100_pmd.c')
+sources = files('rte_acc100_pmd.c', 'rte_acc200_pmd.c')
headers = files('rte_acc100_cfg.h')
diff --git a/drivers/baseband/acc/rte_acc200_pmd.c b/drivers/baseband/acc/rte_acc200_pmd.c
new file mode 100644
index 0000000000..5554488280
--- /dev/null
+++ b/drivers/baseband/acc/rte_acc200_pmd.c
@@ -0,0 +1,144 @@
+/* SPDX-License-Identifier: BSD-3-Clause
+ * Copyright(c) 2022 Intel Corporation
+ */
+
+#include <unistd.h>
+
+#include <rte_common.h>
+#include <rte_log.h>
+#include <rte_dev.h>
+#include <rte_malloc.h>
+#include <rte_mempool.h>
+#include <rte_byteorder.h>
+#include <rte_errno.h>
+#include <rte_branch_prediction.h>
+#include <rte_hexdump.h>
+#include <rte_pci.h>
+#include <rte_bus_pci.h>
+#ifdef RTE_BBDEV_OFFLOAD_COST
+#include <rte_cycles.h>
+#endif
+
+#include <rte_bbdev.h>
+#include <rte_bbdev_pmd.h>
+#include "acc200_pmd.h"
+
+#ifdef RTE_LIBRTE_BBDEV_DEBUG
+RTE_LOG_REGISTER_DEFAULT(acc200_logtype, DEBUG);
+#else
+RTE_LOG_REGISTER_DEFAULT(acc200_logtype, NOTICE);
+#endif
+
+/* Free memory used for software rings */
+static int
+acc200_dev_close(struct rte_bbdev *dev)
+{
+ RTE_SET_USED(dev);
+ /* Ensure all in flight HW transactions are completed */
+ usleep(ACC_LONG_WAIT);
+ return 0;
+}
+
+
+static const struct rte_bbdev_ops acc200_bbdev_ops = {
+ .close = acc200_dev_close,
+};
+
+/* ACC200 PCI PF address map */
+static struct rte_pci_id pci_id_acc200_pf_map[] = {
+ {
+ RTE_PCI_DEVICE(RTE_ACC200_VENDOR_ID, RTE_ACC200_PF_DEVICE_ID)
+ },
+ {.device_id = 0},
+};
+
+/* ACC200 PCI VF address map */
+static struct rte_pci_id pci_id_acc200_vf_map[] = {
+ {
+ RTE_PCI_DEVICE(RTE_ACC200_VENDOR_ID, RTE_ACC200_VF_DEVICE_ID)
+ },
+ {.device_id = 0},
+};
+
+/* Initialization Function */
+static void
+acc200_bbdev_init(struct rte_bbdev *dev, struct rte_pci_driver *drv)
+{
+ struct rte_pci_device *pci_dev = RTE_DEV_TO_PCI(dev->device);
+
+ dev->dev_ops = &acc200_bbdev_ops;
+
+ ((struct acc_device *) dev->data->dev_private)->pf_device =
+ !strcmp(drv->driver.name,
+ RTE_STR(ACC200PF_DRIVER_NAME));
+ ((struct acc_device *) dev->data->dev_private)->mmio_base =
+ pci_dev->mem_resource[0].addr;
+
+ rte_bbdev_log_debug("Init device %s [%s] @ vaddr %p paddr %#"PRIx64"",
+ drv->driver.name, dev->data->name,
+ (void *)pci_dev->mem_resource[0].addr,
+ pci_dev->mem_resource[0].phys_addr);
+}
+
+static int acc200_pci_probe(struct rte_pci_driver *pci_drv,
+ struct rte_pci_device *pci_dev)
+{
+ struct rte_bbdev *bbdev = NULL;
+ char dev_name[RTE_BBDEV_NAME_MAX_LEN];
+
+ if (pci_dev == NULL) {
+ rte_bbdev_log(ERR, "NULL PCI device");
+ return -EINVAL;
+ }
+
+ rte_pci_device_name(&pci_dev->addr, dev_name, sizeof(dev_name));
+
+ /* Allocate memory to be used privately by drivers */
+ bbdev = rte_bbdev_allocate(pci_dev->device.name);
+ if (bbdev == NULL)
+ return -ENODEV;
+
+ /* allocate device private memory */
+ bbdev->data->dev_private = rte_zmalloc_socket(dev_name,
+ sizeof(struct acc_device), RTE_CACHE_LINE_SIZE,
+ pci_dev->device.numa_node);
+
+ if (bbdev->data->dev_private == NULL) {
+ rte_bbdev_log(CRIT,
+ "Allocate of %zu bytes for device \"%s\" failed",
+ sizeof(struct acc_device), dev_name);
+ rte_bbdev_release(bbdev);
+ return -ENOMEM;
+ }
+
+ /* Fill HW specific part of device structure */
+ bbdev->device = &pci_dev->device;
+ bbdev->intr_handle = pci_dev->intr_handle;
+ bbdev->data->socket_id = pci_dev->device.numa_node;
+
+ /* Invoke ACC200 device initialization function */
+ acc200_bbdev_init(bbdev, pci_drv);
+
+ rte_bbdev_log_debug("Initialised bbdev %s (id = %u)",
+ dev_name, bbdev->data->dev_id);
+ return 0;
+}
+
+static struct rte_pci_driver acc200_pci_pf_driver = {
+ .probe = acc200_pci_probe,
+ .remove = acc_pci_remove,
+ .id_table = pci_id_acc200_pf_map,
+ .drv_flags = RTE_PCI_DRV_NEED_MAPPING
+};
+
+static struct rte_pci_driver acc200_pci_vf_driver = {
+ .probe = acc200_pci_probe,
+ .remove = acc_pci_remove,
+ .id_table = pci_id_acc200_vf_map,
+ .drv_flags = RTE_PCI_DRV_NEED_MAPPING
+};
+
+RTE_PMD_REGISTER_PCI(ACC200PF_DRIVER_NAME, acc200_pci_pf_driver);
+RTE_PMD_REGISTER_PCI_TABLE(ACC200PF_DRIVER_NAME, pci_id_acc200_pf_map);
+RTE_PMD_REGISTER_PCI(ACC200VF_DRIVER_NAME, acc200_pci_vf_driver);
+RTE_PMD_REGISTER_PCI_TABLE(ACC200VF_DRIVER_NAME, pci_id_acc200_vf_map);
--
2.37.1
^ permalink raw reply [flat|nested] 28+ messages in thread* [PATCH v6 05/14] baseband/acc: add HW register definitions for ACC200
2022-09-24 0:50 From: Nicolas Chautru <nicolas.chautru@intel.com> Nicolas Chautru
` (3 preceding siblings ...)
2022-09-24 0:50 ` [PATCH v6 04/14] baseband/acc: introduce PMD for ACC200 Nicolas Chautru
@ 2022-09-24 0:50 ` Nicolas Chautru
2022-09-24 0:50 ` [PATCH v6 06/14] baseband/acc: add info get function " Nicolas Chautru
` (8 subsequent siblings)
13 siblings, 0 replies; 28+ messages in thread
From: Nicolas Chautru @ 2022-09-24 0:50 UTC (permalink / raw)
To: dev, thomas
Cc: maxime.coquelin, trix, mdr, bruce.richardson, hemant.agrawal,
david.marchand, stephen, hernan.vargas, Nic Chautru
From: Nic Chautru <nicolas.chautru@intel.com>
Add registers list and structure to access the device.
Signed-off-by: Nic Chautru <nicolas.chautru@intel.com>
Reviewed-by: Maxime Coquelin <maxime.coquelin@redhat.com>
---
drivers/baseband/acc/acc200_pf_enum.h | 108 +++++++++++++++++
drivers/baseband/acc/acc200_pmd.h | 163 ++++++++++++++++++++++++++
drivers/baseband/acc/acc200_vf_enum.h | 83 +++++++++++++
3 files changed, 354 insertions(+)
create mode 100644 drivers/baseband/acc/acc200_pf_enum.h
create mode 100644 drivers/baseband/acc/acc200_vf_enum.h
diff --git a/drivers/baseband/acc/acc200_pf_enum.h b/drivers/baseband/acc/acc200_pf_enum.h
new file mode 100644
index 0000000000..e52d8f5b19
--- /dev/null
+++ b/drivers/baseband/acc/acc200_pf_enum.h
@@ -0,0 +1,108 @@
+/* SPDX-License-Identifier: BSD-3-Clause
+ * Copyright(c) 2021 Intel Corporation
+ */
+
+#ifndef ACC200_PF_ENUM_H
+#define ACC200_PF_ENUM_H
+
+/*
+ * ACC200 Register mapping on PF BAR0
+ * This is automatically generated from RDL, format may change with new RDL
+ * Release.
+ * Variable names are as is
+ */
+enum {
+ HWPfQmgrEgressQueuesTemplate = 0x0007FC00,
+ HWPfQmgrIngressAq = 0x00080000,
+ HWPfQmgrDepthLog2Grp = 0x00A00200,
+ HWPfQmgrTholdGrp = 0x00A00300,
+ HWPfQmgrGrpTmplateReg0Indx = 0x00A00600,
+ HWPfQmgrGrpTmplateReg1Indx = 0x00A00700,
+ HWPfQmgrGrpTmplateReg2indx = 0x00A00800,
+ HWPfQmgrGrpTmplateReg3Indx = 0x00A00900,
+ HWPfQmgrGrpTmplateReg4Indx = 0x00A00A00,
+ HWPfQmgrVfBaseAddr = 0x00A01000,
+ HWPfQmgrArbQDepthGrp = 0x00A02F00,
+ HWPfQmgrGrpFunction0 = 0x00A02F40,
+ HWPfQmgrGrpFunction1 = 0x00A02F44,
+ HWPfQmgrGrpPriority = 0x00A02F48,
+ HWPfQmgrAqEnableVf = 0x00A10000,
+ HWPfQmgrRingSizeVf = 0x00A20004,
+ HWPfQmgrGrpDepthLog20Vf = 0x00A20008,
+ HWPfQmgrGrpDepthLog21Vf = 0x00A2000C,
+ HWPfFabricM2iBufferReg = 0x00B30000,
+ HWPfFabricI2Mdma_weight = 0x00B31044,
+ HwPfFecUl5gIbDebugReg = 0x00B40200,
+ HWPfFftConfig0 = 0x00B58004,
+ HWPfFftRamPageAccess = 0x00B5800C,
+ HWPfFftRamOff = 0x00B58800,
+ HWPfDmaConfig0Reg = 0x00B80000,
+ HWPfDmaConfig1Reg = 0x00B80004,
+ HWPfDmaQmgrAddrReg = 0x00B80008,
+ HWPfDmaAxcacheReg = 0x00B80010,
+ HWPfDmaAxiControl = 0x00B8002C,
+ HWPfDmaQmanen = 0x00B80040,
+ HWPfDma4gdlIbThld = 0x00B800CC,
+ HWPfDmaCfgRrespBresp = 0x00B80814,
+ HWPfDmaDescriptorSignatuture = 0x00B80868,
+ HWPfDmaErrorDetectionEn = 0x00B80870,
+ HWPfDmaFec5GulDescBaseLoRegVf = 0x00B88020,
+ HWPfDmaFec5GulDescBaseHiRegVf = 0x00B88024,
+ HWPfDmaFec5GulRespPtrLoRegVf = 0x00B88028,
+ HWPfDmaFec5GulRespPtrHiRegVf = 0x00B8802C,
+ HWPfDmaFec5GdlDescBaseLoRegVf = 0x00B88040,
+ HWPfDmaFec5GdlDescBaseHiRegVf = 0x00B88044,
+ HWPfDmaFec5GdlRespPtrLoRegVf = 0x00B88048,
+ HWPfDmaFec5GdlRespPtrHiRegVf = 0x00B8804C,
+ HWPfDmaFec4GulDescBaseLoRegVf = 0x00B88060,
+ HWPfDmaFec4GulDescBaseHiRegVf = 0x00B88064,
+ HWPfDmaFec4GulRespPtrLoRegVf = 0x00B88068,
+ HWPfDmaFec4GulRespPtrHiRegVf = 0x00B8806C,
+ HWPfDmaFec4GdlDescBaseLoRegVf = 0x00B88080,
+ HWPfDmaFec4GdlDescBaseHiRegVf = 0x00B88084,
+ HWPfDmaFec4GdlRespPtrLoRegVf = 0x00B88088,
+ HWPfDmaFec4GdlRespPtrHiRegVf = 0x00B8808C,
+ HWPDmaFftDescBaseLoRegVf = 0x00B880A0,
+ HWPDmaFftDescBaseHiRegVf = 0x00B880A4,
+ HWPDmaFftRespPtrLoRegVf = 0x00B880A8,
+ HWPDmaFftRespPtrHiRegVf = 0x00B880AC,
+ HWPfQosmonAEvalOverflow0 = 0x00B90008,
+ HWPfPermonACntrlRegVf = 0x00B98000,
+ HWPfQosmonBEvalOverflow0 = 0x00BA0008,
+ HWPfPermonBCntrlRegVf = 0x00BA8000,
+ HWPfPermonCCntrlRegVf = 0x00BB8000,
+ HWPfHiInfoRingBaseLoRegPf = 0x00C84014,
+ HWPfHiInfoRingBaseHiRegPf = 0x00C84018,
+ HWPfHiInfoRingPointerRegPf = 0x00C8401C,
+ HWPfHiInfoRingIntWrEnRegPf = 0x00C84020,
+ HWPfHiBlockTransmitOnErrorEn = 0x00C84038,
+ HWPfHiCfgMsiIntWrEnRegPf = 0x00C84040,
+ HWPfHiMsixVectorMapperPf = 0x00C84060,
+ HWPfHiPfMode = 0x00C84108,
+ HWPfHiClkGateHystReg = 0x00C8410C,
+ HWPfHiMsiDropEnableReg = 0x00C84114,
+ HWPfHiSectionPowerGatingReq = 0x00C84128,
+ HWPfHiSectionPowerGatingAck = 0x00C8412C,
+};
+
+/* TIP PF Interrupt numbers */
+enum {
+ ACC200_PF_INT_QMGR_AQ_OVERFLOW = 0,
+ ACC200_PF_INT_DOORBELL_VF_2_PF = 1,
+ ACC200_PF_INT_ILLEGAL_FORMAT = 2,
+ ACC200_PF_INT_QMGR_DISABLED_ACCESS = 3,
+ ACC200_PF_INT_QMGR_AQ_OVERTHRESHOLD = 4,
+ ACC200_PF_INT_DMA_DL_DESC_IRQ = 5,
+ ACC200_PF_INT_DMA_UL_DESC_IRQ = 6,
+ ACC200_PF_INT_DMA_FFT_DESC_IRQ = 7,
+ ACC200_PF_INT_DMA_UL5G_DESC_IRQ = 8,
+ ACC200_PF_INT_DMA_DL5G_DESC_IRQ = 9,
+ ACC200_PF_INT_DMA_MLD_DESC_IRQ = 10,
+ ACC200_PF_INT_ARAM_ECC_1BIT_ERR = 11,
+ ACC200_PF_INT_PARITY_ERR = 12,
+ ACC200_PF_INT_QMGR_ERR = 13,
+ ACC200_PF_INT_INT_REQ_OVERFLOW = 14,
+ ACC200_PF_INT_APB_TIMEOUT = 15,
+};
+
+#endif /* ACC200_PF_ENUM_H */
diff --git a/drivers/baseband/acc/acc200_pmd.h b/drivers/baseband/acc/acc200_pmd.h
index aaa6b7753c..9df1f506ad 100644
--- a/drivers/baseband/acc/acc200_pmd.h
+++ b/drivers/baseband/acc/acc200_pmd.h
@@ -6,6 +6,8 @@
#define _RTE_ACC200_PMD_H_
#include "acc_common.h"
+#include "acc200_pf_enum.h"
+#include "acc200_vf_enum.h"
/* Helper macro for logging */
#define rte_bbdev_log(level, fmt, ...) \
@@ -29,4 +31,165 @@
#define RTE_ACC200_PF_DEVICE_ID (0x57C0)
#define RTE_ACC200_VF_DEVICE_ID (0x57C1)
+#define ACC200_MAX_PF_MSIX (256+32)
+#define ACC200_MAX_VF_MSIX (256+7)
+
+/* Values used in writing to the registers */
+#define ACC200_REG_IRQ_EN_ALL 0x1FF83FF /* Enable all interrupts */
+
+/* Number of Virtual Functions ACC200 supports */
+#define ACC200_NUM_VFS 16
+#define ACC200_NUM_QGRPS 16
+#define ACC200_NUM_AQS 16
+
+#define ACC200_GRP_ID_SHIFT 10 /* Queue Index Hierarchy */
+#define ACC200_VF_ID_SHIFT 4 /* Queue Index Hierarchy */
+#define ACC200_WORDS_IN_ARAM_SIZE (256 * 1024 / 4)
+
+/* Mapping of signals for the available engines */
+#define ACC200_SIG_UL_5G 0
+#define ACC200_SIG_UL_5G_LAST 4
+#define ACC200_SIG_DL_5G 10
+#define ACC200_SIG_DL_5G_LAST 11
+#define ACC200_SIG_UL_4G 12
+#define ACC200_SIG_UL_4G_LAST 16
+#define ACC200_SIG_DL_4G 21
+#define ACC200_SIG_DL_4G_LAST 23
+#define ACC200_SIG_FFT 24
+#define ACC200_SIG_FFT_LAST 24
+
+#define ACC200_NUM_ACCS 5 /* FIXMEFFT */
+
+/* ACC200 Configuration */
+#define ACC200_FABRIC_MODE 0x8000103
+#define ACC200_CFG_DMA_ERROR 0x3DF
+#define ACC200_CFG_AXI_CACHE 0x11
+#define ACC200_CFG_QMGR_HI_P 0x0F0F
+#define ACC200_RESET_HARD 0x1FF
+#define ACC200_ENGINES_MAX 9
+#define ACC200_GPEX_AXIMAP_NUM 17
+#define ACC200_CLOCK_GATING_EN 0x30000
+#define ACC200_FFT_CFG_0 0x2001
+#define ACC200_FFT_RAM_EN 0x80008000
+#define ACC200_FFT_RAM_DIS 0x0
+#define ACC200_FFT_RAM_SIZE 512
+#define ACC200_CLK_EN 0x00010A01
+#define ACC200_CLK_DIS 0x01F10A01
+#define ACC200_PG_MASK_0 0x1F
+#define ACC200_PG_MASK_1 0xF
+#define ACC200_PG_MASK_2 0x1
+#define ACC200_PG_MASK_3 0x0
+#define ACC200_PG_MASK_FFT 1
+#define ACC200_PG_MASK_4GUL 4
+#define ACC200_PG_MASK_5GUL 8
+#define ACC200_STATUS_WAIT 10
+#define ACC200_STATUS_TO 100
+
+struct acc200_registry_addr {
+ unsigned int dma_ring_dl5g_hi;
+ unsigned int dma_ring_dl5g_lo;
+ unsigned int dma_ring_ul5g_hi;
+ unsigned int dma_ring_ul5g_lo;
+ unsigned int dma_ring_dl4g_hi;
+ unsigned int dma_ring_dl4g_lo;
+ unsigned int dma_ring_ul4g_hi;
+ unsigned int dma_ring_ul4g_lo;
+ unsigned int dma_ring_fft_hi;
+ unsigned int dma_ring_fft_lo;
+ unsigned int ring_size;
+ unsigned int info_ring_hi;
+ unsigned int info_ring_lo;
+ unsigned int info_ring_en;
+ unsigned int info_ring_ptr;
+ unsigned int tail_ptrs_dl5g_hi;
+ unsigned int tail_ptrs_dl5g_lo;
+ unsigned int tail_ptrs_ul5g_hi;
+ unsigned int tail_ptrs_ul5g_lo;
+ unsigned int tail_ptrs_dl4g_hi;
+ unsigned int tail_ptrs_dl4g_lo;
+ unsigned int tail_ptrs_ul4g_hi;
+ unsigned int tail_ptrs_ul4g_lo;
+ unsigned int tail_ptrs_fft_hi;
+ unsigned int tail_ptrs_fft_lo;
+ unsigned int depth_log0_offset;
+ unsigned int depth_log1_offset;
+ unsigned int qman_group_func;
+ unsigned int hi_mode;
+ unsigned int pmon_ctrl_a;
+ unsigned int pmon_ctrl_b;
+ unsigned int pmon_ctrl_c;
+};
+
+/* Structure holding registry addresses for PF */
+static const struct acc200_registry_addr pf_reg_addr = {
+ .dma_ring_dl5g_hi = HWPfDmaFec5GdlDescBaseHiRegVf,
+ .dma_ring_dl5g_lo = HWPfDmaFec5GdlDescBaseLoRegVf,
+ .dma_ring_ul5g_hi = HWPfDmaFec5GulDescBaseHiRegVf,
+ .dma_ring_ul5g_lo = HWPfDmaFec5GulDescBaseLoRegVf,
+ .dma_ring_dl4g_hi = HWPfDmaFec4GdlDescBaseHiRegVf,
+ .dma_ring_dl4g_lo = HWPfDmaFec4GdlDescBaseLoRegVf,
+ .dma_ring_ul4g_hi = HWPfDmaFec4GulDescBaseHiRegVf,
+ .dma_ring_ul4g_lo = HWPfDmaFec4GulDescBaseLoRegVf,
+ .dma_ring_fft_hi = HWPDmaFftDescBaseHiRegVf,
+ .dma_ring_fft_lo = HWPDmaFftDescBaseLoRegVf,
+ .ring_size = HWPfQmgrRingSizeVf,
+ .info_ring_hi = HWPfHiInfoRingBaseHiRegPf,
+ .info_ring_lo = HWPfHiInfoRingBaseLoRegPf,
+ .info_ring_en = HWPfHiInfoRingIntWrEnRegPf,
+ .info_ring_ptr = HWPfHiInfoRingPointerRegPf,
+ .tail_ptrs_dl5g_hi = HWPfDmaFec5GdlRespPtrHiRegVf,
+ .tail_ptrs_dl5g_lo = HWPfDmaFec5GdlRespPtrLoRegVf,
+ .tail_ptrs_ul5g_hi = HWPfDmaFec5GulRespPtrHiRegVf,
+ .tail_ptrs_ul5g_lo = HWPfDmaFec5GulRespPtrLoRegVf,
+ .tail_ptrs_dl4g_hi = HWPfDmaFec4GdlRespPtrHiRegVf,
+ .tail_ptrs_dl4g_lo = HWPfDmaFec4GdlRespPtrLoRegVf,
+ .tail_ptrs_ul4g_hi = HWPfDmaFec4GulRespPtrHiRegVf,
+ .tail_ptrs_ul4g_lo = HWPfDmaFec4GulRespPtrLoRegVf,
+ .tail_ptrs_fft_hi = HWPDmaFftRespPtrHiRegVf,
+ .tail_ptrs_fft_lo = HWPDmaFftRespPtrLoRegVf,
+ .depth_log0_offset = HWPfQmgrGrpDepthLog20Vf,
+ .depth_log1_offset = HWPfQmgrGrpDepthLog21Vf,
+ .qman_group_func = HWPfQmgrGrpFunction0,
+ .hi_mode = HWPfHiMsixVectorMapperPf,
+ .pmon_ctrl_a = HWPfPermonACntrlRegVf,
+ .pmon_ctrl_b = HWPfPermonBCntrlRegVf,
+ .pmon_ctrl_c = HWPfPermonCCntrlRegVf,
+};
+
+/* Structure holding registry addresses for VF */
+static const struct acc200_registry_addr vf_reg_addr = {
+ .dma_ring_dl5g_hi = HWVfDmaFec5GdlDescBaseHiRegVf,
+ .dma_ring_dl5g_lo = HWVfDmaFec5GdlDescBaseLoRegVf,
+ .dma_ring_ul5g_hi = HWVfDmaFec5GulDescBaseHiRegVf,
+ .dma_ring_ul5g_lo = HWVfDmaFec5GulDescBaseLoRegVf,
+ .dma_ring_dl4g_hi = HWVfDmaFec4GdlDescBaseHiRegVf,
+ .dma_ring_dl4g_lo = HWVfDmaFec4GdlDescBaseLoRegVf,
+ .dma_ring_ul4g_hi = HWVfDmaFec4GulDescBaseHiRegVf,
+ .dma_ring_ul4g_lo = HWVfDmaFec4GulDescBaseLoRegVf,
+ .dma_ring_fft_hi = HWVfDmaFftDescBaseHiRegVf,
+ .dma_ring_fft_lo = HWVfDmaFftDescBaseLoRegVf,
+ .ring_size = HWVfQmgrRingSizeVf,
+ .info_ring_hi = HWVfHiInfoRingBaseHiVf,
+ .info_ring_lo = HWVfHiInfoRingBaseLoVf,
+ .info_ring_en = HWVfHiInfoRingIntWrEnVf,
+ .info_ring_ptr = HWVfHiInfoRingPointerVf,
+ .tail_ptrs_dl5g_hi = HWVfDmaFec5GdlRespPtrHiRegVf,
+ .tail_ptrs_dl5g_lo = HWVfDmaFec5GdlRespPtrLoRegVf,
+ .tail_ptrs_ul5g_hi = HWVfDmaFec5GulRespPtrHiRegVf,
+ .tail_ptrs_ul5g_lo = HWVfDmaFec5GulRespPtrLoRegVf,
+ .tail_ptrs_dl4g_hi = HWVfDmaFec4GdlRespPtrHiRegVf,
+ .tail_ptrs_dl4g_lo = HWVfDmaFec4GdlRespPtrLoRegVf,
+ .tail_ptrs_ul4g_hi = HWVfDmaFec4GulRespPtrHiRegVf,
+ .tail_ptrs_ul4g_lo = HWVfDmaFec4GulRespPtrLoRegVf,
+ .tail_ptrs_fft_hi = HWVfDmaFftRespPtrHiRegVf,
+ .tail_ptrs_fft_lo = HWVfDmaFftRespPtrLoRegVf,
+ .depth_log0_offset = HWVfQmgrGrpDepthLog20Vf,
+ .depth_log1_offset = HWVfQmgrGrpDepthLog21Vf,
+ .qman_group_func = HWVfQmgrGrpFunction0Vf,
+ .hi_mode = HWVfHiMsixVectorMapperVf,
+ .pmon_ctrl_a = HWVfPmACntrlRegVf,
+ .pmon_ctrl_b = HWVfPmBCntrlRegVf,
+ .pmon_ctrl_c = HWVfPmCCntrlRegVf,
+};
+
#endif /* _RTE_ACC200_PMD_H_ */
diff --git a/drivers/baseband/acc/acc200_vf_enum.h b/drivers/baseband/acc/acc200_vf_enum.h
new file mode 100644
index 0000000000..0d354208ab
--- /dev/null
+++ b/drivers/baseband/acc/acc200_vf_enum.h
@@ -0,0 +1,83 @@
+/* SPDX-License-Identifier: BSD-3-Clause
+ * Copyright(c) 2021 Intel Corporation
+ */
+
+#ifndef ACC200_VF_ENUM_H
+#define ACC200_VF_ENUM_H
+
+/*
+ * ACC200 Register mapping on VF BAR0
+ * This is automatically generated from RDL, format may change with new RDL
+ */
+enum {
+ HWVfQmgrIngressAq = 0x00000000,
+ HWVfHiVfToPfDbellVf = 0x00000800,
+ HWVfHiPfToVfDbellVf = 0x00000808,
+ HWVfHiInfoRingBaseLoVf = 0x00000810,
+ HWVfHiInfoRingBaseHiVf = 0x00000814,
+ HWVfHiInfoRingPointerVf = 0x00000818,
+ HWVfHiInfoRingIntWrEnVf = 0x00000820,
+ HWVfHiInfoRingPf2VfWrEnVf = 0x00000824,
+ HWVfHiMsixVectorMapperVf = 0x00000860,
+ HWVfDmaFec5GulDescBaseLoRegVf = 0x00000920,
+ HWVfDmaFec5GulDescBaseHiRegVf = 0x00000924,
+ HWVfDmaFec5GulRespPtrLoRegVf = 0x00000928,
+ HWVfDmaFec5GulRespPtrHiRegVf = 0x0000092C,
+ HWVfDmaFec5GdlDescBaseLoRegVf = 0x00000940,
+ HWVfDmaFec5GdlDescBaseHiRegVf = 0x00000944,
+ HWVfDmaFec5GdlRespPtrLoRegVf = 0x00000948,
+ HWVfDmaFec5GdlRespPtrHiRegVf = 0x0000094C,
+ HWVfDmaFec4GulDescBaseLoRegVf = 0x00000960,
+ HWVfDmaFec4GulDescBaseHiRegVf = 0x00000964,
+ HWVfDmaFec4GulRespPtrLoRegVf = 0x00000968,
+ HWVfDmaFec4GulRespPtrHiRegVf = 0x0000096C,
+ HWVfDmaFec4GdlDescBaseLoRegVf = 0x00000980,
+ HWVfDmaFec4GdlDescBaseHiRegVf = 0x00000984,
+ HWVfDmaFec4GdlRespPtrLoRegVf = 0x00000988,
+ HWVfDmaFec4GdlRespPtrHiRegVf = 0x0000098C,
+ HWVfDmaFftDescBaseLoRegVf = 0x000009A0,
+ HWVfDmaFftDescBaseHiRegVf = 0x000009A4,
+ HWVfDmaFftRespPtrLoRegVf = 0x000009A8,
+ HWVfDmaFftRespPtrHiRegVf = 0x000009AC,
+ HWVfQmgrAqResetVf = 0x00000E00,
+ HWVfQmgrRingSizeVf = 0x00000E04,
+ HWVfQmgrGrpDepthLog20Vf = 0x00000E08,
+ HWVfQmgrGrpDepthLog21Vf = 0x00000E0C,
+ HWVfQmgrGrpFunction0Vf = 0x00000E10,
+ HWVfQmgrGrpFunction1Vf = 0x00000E14,
+ HWVfPmACntrlRegVf = 0x00000F40,
+ HWVfPmACountVf = 0x00000F48,
+ HWVfPmAKCntLoVf = 0x00000F50,
+ HWVfPmAKCntHiVf = 0x00000F54,
+ HWVfPmADeltaCntLoVf = 0x00000F60,
+ HWVfPmADeltaCntHiVf = 0x00000F64,
+ HWVfPmBCntrlRegVf = 0x00000F80,
+ HWVfPmBCountVf = 0x00000F88,
+ HWVfPmBKCntLoVf = 0x00000F90,
+ HWVfPmBKCntHiVf = 0x00000F94,
+ HWVfPmBDeltaCntLoVf = 0x00000FA0,
+ HWVfPmBDeltaCntHiVf = 0x00000FA4,
+ HWVfPmCCntrlRegVf = 0x00000FC0,
+ HWVfPmCCountVf = 0x00000FC8,
+ HWVfPmCKCntLoVf = 0x00000FD0,
+ HWVfPmCKCntHiVf = 0x00000FD4,
+ HWVfPmCDeltaCntLoVf = 0x00000FE0,
+ HWVfPmCDeltaCntHiVf = 0x00000FE4
+};
+
+/* TIP VF Interrupt numbers */
+enum {
+ ACC200_VF_INT_QMGR_AQ_OVERFLOW = 0,
+ ACC200_VF_INT_DOORBELL_PF_2_VF = 1,
+ ACC200_VF_INT_ILLEGAL_FORMAT = 2,
+ ACC200_VF_INT_QMGR_DISABLED_ACCESS = 3,
+ ACC200_VF_INT_QMGR_AQ_OVERTHRESHOLD = 4,
+ ACC200_VF_INT_DMA_DL_DESC_IRQ = 5,
+ ACC200_VF_INT_DMA_UL_DESC_IRQ = 6,
+ ACC200_VF_INT_DMA_FFT_DESC_IRQ = 7,
+ ACC200_VF_INT_DMA_UL5G_DESC_IRQ = 8,
+ ACC200_VF_INT_DMA_DL5G_DESC_IRQ = 9,
+ ACC200_VF_INT_DMA_MLD_DESC_IRQ = 10,
+};
+
+#endif /* ACC200_VF_ENUM_H */
--
2.37.1
^ permalink raw reply [flat|nested] 28+ messages in thread* [PATCH v6 06/14] baseband/acc: add info get function for ACC200
2022-09-24 0:50 From: Nicolas Chautru <nicolas.chautru@intel.com> Nicolas Chautru
` (4 preceding siblings ...)
2022-09-24 0:50 ` [PATCH v6 05/14] baseband/acc: add HW register definitions " Nicolas Chautru
@ 2022-09-24 0:50 ` Nicolas Chautru
2022-09-27 13:03 ` Maxime Coquelin
2022-09-24 0:50 ` [PATCH v6 07/14] baseband/acc: add queue configuration " Nicolas Chautru
` (7 subsequent siblings)
13 siblings, 1 reply; 28+ messages in thread
From: Nicolas Chautru @ 2022-09-24 0:50 UTC (permalink / raw)
To: dev, thomas
Cc: maxime.coquelin, trix, mdr, bruce.richardson, hemant.agrawal,
david.marchand, stephen, hernan.vargas, Nic Chautru
From: Nic Chautru <nicolas.chautru@intel.com>
Add support for info_get to allow to query the device.
Null capability exposed.
Signed-off-by: Nic Chautru <nicolas.chautru@intel.com>
---
drivers/baseband/acc/acc200_pmd.h | 1 +
drivers/baseband/acc/rte_acc200_pmd.c | 239 ++++++++++++++++++++++++++
2 files changed, 240 insertions(+)
diff --git a/drivers/baseband/acc/acc200_pmd.h b/drivers/baseband/acc/acc200_pmd.h
index 9df1f506ad..0a0f6dc4fe 100644
--- a/drivers/baseband/acc/acc200_pmd.h
+++ b/drivers/baseband/acc/acc200_pmd.h
@@ -8,6 +8,7 @@
#include "acc_common.h"
#include "acc200_pf_enum.h"
#include "acc200_vf_enum.h"
+#include "rte_acc200_cfg.h"
/* Helper macro for logging */
#define rte_bbdev_log(level, fmt, ...) \
diff --git a/drivers/baseband/acc/rte_acc200_pmd.c b/drivers/baseband/acc/rte_acc200_pmd.c
index 5554488280..f666667801 100644
--- a/drivers/baseband/acc/rte_acc200_pmd.c
+++ b/drivers/baseband/acc/rte_acc200_pmd.c
@@ -29,6 +29,197 @@ RTE_LOG_REGISTER_DEFAULT(acc200_logtype, DEBUG);
RTE_LOG_REGISTER_DEFAULT(acc200_logtype, NOTICE);
#endif
+/* Calculate the offset of the enqueue register */
+static inline uint32_t
+queue_offset(bool pf_device, uint8_t vf_id, uint8_t qgrp_id, uint16_t aq_id)
+{
+ if (pf_device)
+ return ((vf_id << 12) + (qgrp_id << 7) + (aq_id << 3) +
+ HWPfQmgrIngressAq);
+ else
+ return ((qgrp_id << 7) + (aq_id << 3) +
+ HWVfQmgrIngressAq);
+}
+
+enum {UL_4G = 0, UL_5G, DL_4G, DL_5G, FFT, NUM_ACC};
+
+/* Return the queue topology for a Queue Group Index */
+static inline void
+qtopFromAcc(struct rte_acc_queue_topology **qtop, int acc_enum,
+ struct rte_acc_conf *acc_conf)
+{
+ struct rte_acc_queue_topology *p_qtop;
+ p_qtop = NULL;
+ switch (acc_enum) {
+ case UL_4G:
+ p_qtop = &(acc_conf->q_ul_4g);
+ break;
+ case UL_5G:
+ p_qtop = &(acc_conf->q_ul_5g);
+ break;
+ case DL_4G:
+ p_qtop = &(acc_conf->q_dl_4g);
+ break;
+ case DL_5G:
+ p_qtop = &(acc_conf->q_dl_5g);
+ break;
+ case FFT:
+ p_qtop = &(acc_conf->q_fft);
+ break;
+ default:
+ /* NOTREACHED */
+ rte_bbdev_log(ERR, "Unexpected error evaluating qtopFromAcc %d",
+ acc_enum);
+ break;
+ }
+ *qtop = p_qtop;
+}
+
+static void
+initQTop(struct rte_acc_conf *acc_conf)
+{
+ acc_conf->q_ul_4g.num_aqs_per_groups = 0;
+ acc_conf->q_ul_4g.num_qgroups = 0;
+ acc_conf->q_ul_4g.first_qgroup_index = -1;
+ acc_conf->q_ul_5g.num_aqs_per_groups = 0;
+ acc_conf->q_ul_5g.num_qgroups = 0;
+ acc_conf->q_ul_5g.first_qgroup_index = -1;
+ acc_conf->q_dl_4g.num_aqs_per_groups = 0;
+ acc_conf->q_dl_4g.num_qgroups = 0;
+ acc_conf->q_dl_4g.first_qgroup_index = -1;
+ acc_conf->q_dl_5g.num_aqs_per_groups = 0;
+ acc_conf->q_dl_5g.num_qgroups = 0;
+ acc_conf->q_dl_5g.first_qgroup_index = -1;
+ acc_conf->q_fft.num_aqs_per_groups = 0;
+ acc_conf->q_fft.num_qgroups = 0;
+ acc_conf->q_fft.first_qgroup_index = -1;
+}
+
+static inline void
+updateQtop(uint8_t acc, uint8_t qg, struct rte_acc_conf *acc_conf, struct acc_device *d) {
+ uint32_t reg;
+ struct rte_acc_queue_topology *q_top = NULL;
+ uint16_t aq;
+
+ qtopFromAcc(&q_top, acc, acc_conf);
+ if (unlikely(q_top == NULL))
+ return;
+ q_top->num_qgroups++;
+ if (q_top->first_qgroup_index == -1) {
+ q_top->first_qgroup_index = qg;
+ /* Can be optimized to assume all are enabled by default */
+ reg = acc_reg_read(d, queue_offset(d->pf_device,
+ 0, qg, ACC200_NUM_AQS - 1));
+ if (reg & ACC_QUEUE_ENABLE) {
+ q_top->num_aqs_per_groups = ACC200_NUM_AQS;
+ return;
+ }
+ q_top->num_aqs_per_groups = 0;
+ for (aq = 0; aq < ACC200_NUM_AQS; aq++) {
+ reg = acc_reg_read(d, queue_offset(d->pf_device,
+ 0, qg, aq));
+ if (reg & ACC_QUEUE_ENABLE)
+ q_top->num_aqs_per_groups++;
+ }
+ }
+}
+
+/* Fetch configuration enabled for the PF/VF using MMIO Read (slow) */
+static inline void
+fetch_acc200_config(struct rte_bbdev *dev)
+{
+ struct acc_device *d = dev->data->dev_private;
+ struct rte_acc_conf *acc_conf = &d->acc_conf;
+ const struct acc200_registry_addr *reg_addr;
+ uint8_t acc, qg;
+ uint32_t reg_aq, reg_len0, reg_len1, reg0, reg1;
+ uint32_t reg_mode, idx;
+ struct rte_acc_queue_topology *q_top = NULL;
+ int qman_func_id[ACC200_NUM_ACCS] = {ACC_ACCMAP_0, ACC_ACCMAP_1,
+ ACC_ACCMAP_2, ACC_ACCMAP_3, ACC_ACCMAP_4};
+
+ /* No need to retrieve the configuration is already done */
+ if (d->configured)
+ return;
+
+ /* Choose correct registry addresses for the device type */
+ if (d->pf_device)
+ reg_addr = &pf_reg_addr;
+ else
+ reg_addr = &vf_reg_addr;
+
+ d->ddr_size = 0;
+
+ /* Single VF Bundle by VF */
+ acc_conf->num_vf_bundles = 1;
+ initQTop(acc_conf);
+
+ reg0 = acc_reg_read(d, reg_addr->qman_group_func);
+ reg1 = acc_reg_read(d, reg_addr->qman_group_func + 4);
+ for (qg = 0; qg < ACC200_NUM_QGRPS; qg++) {
+ reg_aq = acc_reg_read(d,
+ queue_offset(d->pf_device, 0, qg, 0));
+ if (reg_aq & ACC_QUEUE_ENABLE) {
+ /* printf("Qg enabled %d %x\n", qg, reg_aq); */
+ if (qg < ACC_NUM_QGRPS_PER_WORD)
+ idx = (reg0 >> (qg * 4)) & 0x7;
+ else
+ idx = (reg1 >> ((qg -
+ ACC_NUM_QGRPS_PER_WORD) * 4)) & 0x7;
+ if (idx < ACC200_NUM_ACCS) {
+ acc = qman_func_id[idx];
+ updateQtop(acc, qg, acc_conf, d);
+ }
+ }
+ }
+
+ /* Check the depth of the AQs*/
+ reg_len0 = acc_reg_read(d, reg_addr->depth_log0_offset);
+ reg_len1 = acc_reg_read(d, reg_addr->depth_log1_offset);
+ for (acc = 0; acc < NUM_ACC; acc++) {
+ qtopFromAcc(&q_top, acc, acc_conf);
+ if (q_top->first_qgroup_index < ACC_NUM_QGRPS_PER_WORD)
+ q_top->aq_depth_log2 = (reg_len0 >>
+ (q_top->first_qgroup_index * 4))
+ & 0xF;
+ else
+ q_top->aq_depth_log2 = (reg_len1 >>
+ ((q_top->first_qgroup_index -
+ ACC_NUM_QGRPS_PER_WORD) * 4))
+ & 0xF;
+ }
+
+ /* Read PF mode */
+ if (d->pf_device) {
+ reg_mode = acc_reg_read(d, HWPfHiPfMode);
+ acc_conf->pf_mode_en = (reg_mode == ACC_PF_VAL) ? 1 : 0;
+ } else {
+ reg_mode = acc_reg_read(d, reg_addr->hi_mode);
+ acc_conf->pf_mode_en = reg_mode & 1;
+ }
+
+ rte_bbdev_log_debug(
+ "%s Config LLR SIGN IN/OUT %s %s QG %u %u %u %u %u AQ %u %u %u %u %u Len %u %u %u %u %u\n",
+ (d->pf_device) ? "PF" : "VF",
+ (acc_conf->input_pos_llr_1_bit) ? "POS" : "NEG",
+ (acc_conf->output_pos_llr_1_bit) ? "POS" : "NEG",
+ acc_conf->q_ul_4g.num_qgroups,
+ acc_conf->q_dl_4g.num_qgroups,
+ acc_conf->q_ul_5g.num_qgroups,
+ acc_conf->q_dl_5g.num_qgroups,
+ acc_conf->q_fft.num_qgroups,
+ acc_conf->q_ul_4g.num_aqs_per_groups,
+ acc_conf->q_dl_4g.num_aqs_per_groups,
+ acc_conf->q_ul_5g.num_aqs_per_groups,
+ acc_conf->q_dl_5g.num_aqs_per_groups,
+ acc_conf->q_fft.num_aqs_per_groups,
+ acc_conf->q_ul_4g.aq_depth_log2,
+ acc_conf->q_dl_4g.aq_depth_log2,
+ acc_conf->q_ul_5g.aq_depth_log2,
+ acc_conf->q_dl_5g.aq_depth_log2,
+ acc_conf->q_fft.aq_depth_log2);
+}
+
/* Free memory used for software rings */
static int
acc200_dev_close(struct rte_bbdev *dev)
@@ -39,9 +230,57 @@ acc200_dev_close(struct rte_bbdev *dev)
return 0;
}
+/* Get ACC200 device info */
+static void
+acc200_dev_info_get(struct rte_bbdev *dev,
+ struct rte_bbdev_driver_info *dev_info)
+{
+ struct acc_device *d = dev->data->dev_private;
+ int i;
+ static const struct rte_bbdev_op_cap bbdev_capabilities[] = {
+ RTE_BBDEV_END_OF_CAPABILITIES_LIST()
+ };
+
+ static struct rte_bbdev_queue_conf default_queue_conf;
+ default_queue_conf.socket = dev->data->socket_id;
+ default_queue_conf.queue_size = ACC_MAX_QUEUE_DEPTH;
+
+ dev_info->driver_name = dev->device->driver->name;
+
+ /* Read and save the populated config from ACC200 registers */
+ fetch_acc200_config(dev);
+
+ /* Exposed number of queues */
+ dev_info->num_queues[RTE_BBDEV_OP_NONE] = 0;
+ dev_info->num_queues[RTE_BBDEV_OP_TURBO_DEC] = 0;
+ dev_info->num_queues[RTE_BBDEV_OP_TURBO_ENC] = 0;
+ dev_info->num_queues[RTE_BBDEV_OP_LDPC_DEC] = 0;
+ dev_info->num_queues[RTE_BBDEV_OP_LDPC_ENC] = 0;
+ dev_info->num_queues[RTE_BBDEV_OP_FFT] = 0;
+ dev_info->queue_priority[RTE_BBDEV_OP_TURBO_DEC] = 0;
+ dev_info->queue_priority[RTE_BBDEV_OP_TURBO_ENC] = 0;
+ dev_info->queue_priority[RTE_BBDEV_OP_LDPC_DEC] = 0;
+ dev_info->queue_priority[RTE_BBDEV_OP_LDPC_ENC] = 0;
+ dev_info->queue_priority[RTE_BBDEV_OP_FFT] = 0;
+ dev_info->max_num_queues = 0;
+ for (i = RTE_BBDEV_OP_NONE; i <= RTE_BBDEV_OP_FFT; i++)
+ dev_info->max_num_queues += dev_info->num_queues[i];
+ dev_info->queue_size_lim = ACC_MAX_QUEUE_DEPTH;
+ dev_info->hardware_accelerated = true;
+ dev_info->max_dl_queue_priority =
+ d->acc_conf.q_dl_4g.num_qgroups - 1;
+ dev_info->max_ul_queue_priority =
+ d->acc_conf.q_ul_4g.num_qgroups - 1;
+ dev_info->default_queue_conf = default_queue_conf;
+ dev_info->cpu_flag_reqs = NULL;
+ dev_info->min_alignment = 1;
+ dev_info->capabilities = bbdev_capabilities;
+ dev_info->harq_buffer_size = 0;
+}
static const struct rte_bbdev_ops acc200_bbdev_ops = {
.close = acc200_dev_close,
+ .info_get = acc200_dev_info_get,
};
/* ACC200 PCI PF address map */
--
2.37.1
^ permalink raw reply [flat|nested] 28+ messages in thread* Re: [PATCH v6 06/14] baseband/acc: add info get function for ACC200
2022-09-24 0:50 ` [PATCH v6 06/14] baseband/acc: add info get function " Nicolas Chautru
@ 2022-09-27 13:03 ` Maxime Coquelin
0 siblings, 0 replies; 28+ messages in thread
From: Maxime Coquelin @ 2022-09-27 13:03 UTC (permalink / raw)
To: Nicolas Chautru, dev, thomas
Cc: trix, mdr, bruce.richardson, hemant.agrawal, david.marchand,
stephen, hernan.vargas
On 9/24/22 02:50, Nicolas Chautru wrote:
> From: Nic Chautru <nicolas.chautru@intel.com>
>
> Add support for info_get to allow to query the device.
> Null capability exposed.
>
> Signed-off-by: Nic Chautru <nicolas.chautru@intel.com>
> ---
> drivers/baseband/acc/acc200_pmd.h | 1 +
> drivers/baseband/acc/rte_acc200_pmd.c | 239 ++++++++++++++++++++++++++
> 2 files changed, 240 insertions(+)
>
> diff --git a/drivers/baseband/acc/acc200_pmd.h b/drivers/baseband/acc/acc200_pmd.h
> index 9df1f506ad..0a0f6dc4fe 100644
> --- a/drivers/baseband/acc/acc200_pmd.h
> +++ b/drivers/baseband/acc/acc200_pmd.h
> @@ -8,6 +8,7 @@
> #include "acc_common.h"
> #include "acc200_pf_enum.h"
> #include "acc200_vf_enum.h"
> +#include "rte_acc200_cfg.h"
>
> /* Helper macro for logging */
> #define rte_bbdev_log(level, fmt, ...) \
> diff --git a/drivers/baseband/acc/rte_acc200_pmd.c b/drivers/baseband/acc/rte_acc200_pmd.c
> index 5554488280..f666667801 100644
> --- a/drivers/baseband/acc/rte_acc200_pmd.c
> +++ b/drivers/baseband/acc/rte_acc200_pmd.c
> @@ -29,6 +29,197 @@ RTE_LOG_REGISTER_DEFAULT(acc200_logtype, DEBUG);
> RTE_LOG_REGISTER_DEFAULT(acc200_logtype, NOTICE);
> #endif
>
> +/* Calculate the offset of the enqueue register */
> +static inline uint32_t
> +queue_offset(bool pf_device, uint8_t vf_id, uint8_t qgrp_id, uint16_t aq_id)
> +{
> + if (pf_device)
> + return ((vf_id << 12) + (qgrp_id << 7) + (aq_id << 3) +
> + HWPfQmgrIngressAq);
> + else
> + return ((qgrp_id << 7) + (aq_id << 3) +
> + HWVfQmgrIngressAq);
> +}
> +
> +enum {UL_4G = 0, UL_5G, DL_4G, DL_5G, FFT, NUM_ACC};
> +
> +/* Return the queue topology for a Queue Group Index */
> +static inline void
> +qtopFromAcc(struct rte_acc_queue_topology **qtop, int acc_enum,
> + struct rte_acc_conf *acc_conf)
> +{
> + struct rte_acc_queue_topology *p_qtop;
> + p_qtop = NULL;
> + switch (acc_enum) {
> + case UL_4G:
> + p_qtop = &(acc_conf->q_ul_4g);
> + break;
> + case UL_5G:
> + p_qtop = &(acc_conf->q_ul_5g);
> + break;
> + case DL_4G:
> + p_qtop = &(acc_conf->q_dl_4g);
> + break;
> + case DL_5G:
> + p_qtop = &(acc_conf->q_dl_5g);
> + break;
> + case FFT:
> + p_qtop = &(acc_conf->q_fft);
> + break;
> + default:
> + /* NOTREACHED */
> + rte_bbdev_log(ERR, "Unexpected error evaluating qtopFromAcc %d",
> + acc_enum);
> + break;
> + }
> + *qtop = p_qtop;
> +}
> +
> +static void
> +initQTop(struct rte_acc_conf *acc_conf)
> +{
> + acc_conf->q_ul_4g.num_aqs_per_groups = 0;
> + acc_conf->q_ul_4g.num_qgroups = 0;
> + acc_conf->q_ul_4g.first_qgroup_index = -1;
> + acc_conf->q_ul_5g.num_aqs_per_groups = 0;
> + acc_conf->q_ul_5g.num_qgroups = 0;
> + acc_conf->q_ul_5g.first_qgroup_index = -1;
> + acc_conf->q_dl_4g.num_aqs_per_groups = 0;
> + acc_conf->q_dl_4g.num_qgroups = 0;
> + acc_conf->q_dl_4g.first_qgroup_index = -1;
> + acc_conf->q_dl_5g.num_aqs_per_groups = 0;
> + acc_conf->q_dl_5g.num_qgroups = 0;
> + acc_conf->q_dl_5g.first_qgroup_index = -1;
> + acc_conf->q_fft.num_aqs_per_groups = 0;
> + acc_conf->q_fft.num_qgroups = 0;
> + acc_conf->q_fft.first_qgroup_index = -1;
> +}
> +
> +static inline void
> +updateQtop(uint8_t acc, uint8_t qg, struct rte_acc_conf *acc_conf, struct acc_device *d) {
> + uint32_t reg;
> + struct rte_acc_queue_topology *q_top = NULL;
> + uint16_t aq;
> +
> + qtopFromAcc(&q_top, acc, acc_conf);
> + if (unlikely(q_top == NULL))
> + return;
> + q_top->num_qgroups++;
> + if (q_top->first_qgroup_index == -1) {
> + q_top->first_qgroup_index = qg;
> + /* Can be optimized to assume all are enabled by default */
> + reg = acc_reg_read(d, queue_offset(d->pf_device,
> + 0, qg, ACC200_NUM_AQS - 1));
> + if (reg & ACC_QUEUE_ENABLE) {
> + q_top->num_aqs_per_groups = ACC200_NUM_AQS;
> + return;
> + }
> + q_top->num_aqs_per_groups = 0;
> + for (aq = 0; aq < ACC200_NUM_AQS; aq++) {
> + reg = acc_reg_read(d, queue_offset(d->pf_device,
> + 0, qg, aq));
> + if (reg & ACC_QUEUE_ENABLE)
> + q_top->num_aqs_per_groups++;
> + }
> + }
> +}
> +
> +/* Fetch configuration enabled for the PF/VF using MMIO Read (slow) */
> +static inline void
> +fetch_acc200_config(struct rte_bbdev *dev)
> +{
> + struct acc_device *d = dev->data->dev_private;
> + struct rte_acc_conf *acc_conf = &d->acc_conf;
> + const struct acc200_registry_addr *reg_addr;
> + uint8_t acc, qg;
> + uint32_t reg_aq, reg_len0, reg_len1, reg0, reg1;
> + uint32_t reg_mode, idx;
> + struct rte_acc_queue_topology *q_top = NULL;
> + int qman_func_id[ACC200_NUM_ACCS] = {ACC_ACCMAP_0, ACC_ACCMAP_1,
> + ACC_ACCMAP_2, ACC_ACCMAP_3, ACC_ACCMAP_4};
> +
> + /* No need to retrieve the configuration is already done */
> + if (d->configured)
> + return;
> +
> + /* Choose correct registry addresses for the device type */
> + if (d->pf_device)
> + reg_addr = &pf_reg_addr;
> + else
> + reg_addr = &vf_reg_addr;
> +
> + d->ddr_size = 0;
> +
> + /* Single VF Bundle by VF */
> + acc_conf->num_vf_bundles = 1;
> + initQTop(acc_conf);
> +
> + reg0 = acc_reg_read(d, reg_addr->qman_group_func);
> + reg1 = acc_reg_read(d, reg_addr->qman_group_func + 4);
> + for (qg = 0; qg < ACC200_NUM_QGRPS; qg++) {
> + reg_aq = acc_reg_read(d,
> + queue_offset(d->pf_device, 0, qg, 0));
> + if (reg_aq & ACC_QUEUE_ENABLE) {
> + /* printf("Qg enabled %d %x\n", qg, reg_aq); */
> + if (qg < ACC_NUM_QGRPS_PER_WORD)
> + idx = (reg0 >> (qg * 4)) & 0x7;
> + else
> + idx = (reg1 >> ((qg -
> + ACC_NUM_QGRPS_PER_WORD) * 4)) & 0x7;
> + if (idx < ACC200_NUM_ACCS) {
> + acc = qman_func_id[idx];
> + updateQtop(acc, qg, acc_conf, d);
> + }
> + }
> + }
> +
> + /* Check the depth of the AQs*/
> + reg_len0 = acc_reg_read(d, reg_addr->depth_log0_offset);
> + reg_len1 = acc_reg_read(d, reg_addr->depth_log1_offset);
> + for (acc = 0; acc < NUM_ACC; acc++) {
> + qtopFromAcc(&q_top, acc, acc_conf);
> + if (q_top->first_qgroup_index < ACC_NUM_QGRPS_PER_WORD)
> + q_top->aq_depth_log2 = (reg_len0 >>
> + (q_top->first_qgroup_index * 4))
> + & 0xF;
> + else
> + q_top->aq_depth_log2 = (reg_len1 >>
> + ((q_top->first_qgroup_index -
> + ACC_NUM_QGRPS_PER_WORD) * 4))
> + & 0xF;
> + }
> +
> + /* Read PF mode */
> + if (d->pf_device) {
> + reg_mode = acc_reg_read(d, HWPfHiPfMode);
> + acc_conf->pf_mode_en = (reg_mode == ACC_PF_VAL) ? 1 : 0;
> + } else {
> + reg_mode = acc_reg_read(d, reg_addr->hi_mode);
> + acc_conf->pf_mode_en = reg_mode & 1;
> + }
> +
> + rte_bbdev_log_debug(
> + "%s Config LLR SIGN IN/OUT %s %s QG %u %u %u %u %u AQ %u %u %u %u %u Len %u %u %u %u %u\n",
> + (d->pf_device) ? "PF" : "VF",
> + (acc_conf->input_pos_llr_1_bit) ? "POS" : "NEG",
> + (acc_conf->output_pos_llr_1_bit) ? "POS" : "NEG",
> + acc_conf->q_ul_4g.num_qgroups,
> + acc_conf->q_dl_4g.num_qgroups,
> + acc_conf->q_ul_5g.num_qgroups,
> + acc_conf->q_dl_5g.num_qgroups,
> + acc_conf->q_fft.num_qgroups,
> + acc_conf->q_ul_4g.num_aqs_per_groups,
> + acc_conf->q_dl_4g.num_aqs_per_groups,
> + acc_conf->q_ul_5g.num_aqs_per_groups,
> + acc_conf->q_dl_5g.num_aqs_per_groups,
> + acc_conf->q_fft.num_aqs_per_groups,
> + acc_conf->q_ul_4g.aq_depth_log2,
> + acc_conf->q_dl_4g.aq_depth_log2,
> + acc_conf->q_ul_5g.aq_depth_log2,
> + acc_conf->q_dl_5g.aq_depth_log2,
> + acc_conf->q_fft.aq_depth_log2);
> +}
> +
> /* Free memory used for software rings */
> static int
> acc200_dev_close(struct rte_bbdev *dev)
> @@ -39,9 +230,57 @@ acc200_dev_close(struct rte_bbdev *dev)
> return 0;
> }
>
> +/* Get ACC200 device info */
> +static void
> +acc200_dev_info_get(struct rte_bbdev *dev,
> + struct rte_bbdev_driver_info *dev_info)
> +{
> + struct acc_device *d = dev->data->dev_private;
> + int i;
> + static const struct rte_bbdev_op_cap bbdev_capabilities[] = {
> + RTE_BBDEV_END_OF_CAPABILITIES_LIST()
> + };
> +
> + static struct rte_bbdev_queue_conf default_queue_conf;
> + default_queue_conf.socket = dev->data->socket_id;
> + default_queue_conf.queue_size = ACC_MAX_QUEUE_DEPTH;
> +
> + dev_info->driver_name = dev->device->driver->name;
> +
> + /* Read and save the populated config from ACC200 registers */
> + fetch_acc200_config(dev);
> +
> + /* Exposed number of queues */
> + dev_info->num_queues[RTE_BBDEV_OP_NONE] = 0;
> + dev_info->num_queues[RTE_BBDEV_OP_TURBO_DEC] = 0;
> + dev_info->num_queues[RTE_BBDEV_OP_TURBO_ENC] = 0;
> + dev_info->num_queues[RTE_BBDEV_OP_LDPC_DEC] = 0;
> + dev_info->num_queues[RTE_BBDEV_OP_LDPC_ENC] = 0;
> + dev_info->num_queues[RTE_BBDEV_OP_FFT] = 0;
> + dev_info->queue_priority[RTE_BBDEV_OP_TURBO_DEC] = 0;
> + dev_info->queue_priority[RTE_BBDEV_OP_TURBO_ENC] = 0;
> + dev_info->queue_priority[RTE_BBDEV_OP_LDPC_DEC] = 0;
> + dev_info->queue_priority[RTE_BBDEV_OP_LDPC_ENC] = 0;
> + dev_info->queue_priority[RTE_BBDEV_OP_FFT] = 0;
> + dev_info->max_num_queues = 0;
> + for (i = RTE_BBDEV_OP_NONE; i <= RTE_BBDEV_OP_FFT; i++)
> + dev_info->max_num_queues += dev_info->num_queues[i];
> + dev_info->queue_size_lim = ACC_MAX_QUEUE_DEPTH;
> + dev_info->hardware_accelerated = true;
> + dev_info->max_dl_queue_priority =
> + d->acc_conf.q_dl_4g.num_qgroups - 1;
> + dev_info->max_ul_queue_priority =
> + d->acc_conf.q_ul_4g.num_qgroups - 1;
> + dev_info->default_queue_conf = default_queue_conf;
> + dev_info->cpu_flag_reqs = NULL;
> + dev_info->min_alignment = 1;
> + dev_info->capabilities = bbdev_capabilities;
> + dev_info->harq_buffer_size = 0;
> +}
>
> static const struct rte_bbdev_ops acc200_bbdev_ops = {
> .close = acc200_dev_close,
> + .info_get = acc200_dev_info_get,
> };
>
> /* ACC200 PCI PF address map */
Reviewed-by: Maxime Coquelin <maxime.coquelin@redhat.com>
Thanks,
Maxime
^ permalink raw reply [flat|nested] 28+ messages in thread
* [PATCH v6 07/14] baseband/acc: add queue configuration for ACC200
2022-09-24 0:50 From: Nicolas Chautru <nicolas.chautru@intel.com> Nicolas Chautru
` (5 preceding siblings ...)
2022-09-24 0:50 ` [PATCH v6 06/14] baseband/acc: add info get function " Nicolas Chautru
@ 2022-09-24 0:50 ` Nicolas Chautru
2022-09-27 13:06 ` Maxime Coquelin
2022-09-24 0:50 ` [PATCH v6 08/14] baseband/acc: add LDPC processing functions Nicolas Chautru
` (6 subsequent siblings)
13 siblings, 1 reply; 28+ messages in thread
From: Nicolas Chautru @ 2022-09-24 0:50 UTC (permalink / raw)
To: dev, thomas
Cc: maxime.coquelin, trix, mdr, bruce.richardson, hemant.agrawal,
david.marchand, stephen, hernan.vargas, Nic Chautru
From: Nic Chautru <nicolas.chautru@intel.com>
Adding function to create and configure queues for the
device.
Signed-off-by: Nic Chautru <nicolas.chautru@intel.com>
---
drivers/baseband/acc/acc_common.h | 1 +
drivers/baseband/acc/rte_acc200_pmd.c | 391 +++++++++++++++++++++++++-
2 files changed, 391 insertions(+), 1 deletion(-)
diff --git a/drivers/baseband/acc/acc_common.h b/drivers/baseband/acc/acc_common.h
index ae8de9ed89..92da41d896 100644
--- a/drivers/baseband/acc/acc_common.h
+++ b/drivers/baseband/acc/acc_common.h
@@ -99,6 +99,7 @@
#define ACC_LIMIT_DL_MUX_BITS 534
#define ACC_NUM_QGRPS_PER_WORD 8
#define ACC_MAX_NUM_QGRPS 32
+#define ACC_RING_SIZE_GRANULARITY 64
/* Constants from K0 computation from 3GPP 38.212 Table 5.4.2.1-2 */
#define ACC_N_ZC_1 66 /* N = 66 Zc for BG 1 */
diff --git a/drivers/baseband/acc/rte_acc200_pmd.c b/drivers/baseband/acc/rte_acc200_pmd.c
index f666667801..2bbb9700ad 100644
--- a/drivers/baseband/acc/rte_acc200_pmd.c
+++ b/drivers/baseband/acc/rte_acc200_pmd.c
@@ -220,16 +220,401 @@ fetch_acc200_config(struct rte_bbdev *dev)
acc_conf->q_fft.aq_depth_log2);
}
+/* Allocate 64MB memory used for all software rings */
+static int
+acc200_setup_queues(struct rte_bbdev *dev, uint16_t num_queues, int socket_id)
+{
+ uint32_t phys_low, phys_high, value;
+ struct acc_device *d = dev->data->dev_private;
+ const struct acc200_registry_addr *reg_addr;
+ int ret;
+
+ if (d->pf_device && !d->acc_conf.pf_mode_en) {
+ rte_bbdev_log(NOTICE,
+ "%s has PF mode disabled. This PF can't be used.",
+ dev->data->name);
+ return -ENODEV;
+ }
+ if (!d->pf_device && d->acc_conf.pf_mode_en) {
+ rte_bbdev_log(NOTICE,
+ "%s has PF mode enabled. This VF can't be used.",
+ dev->data->name);
+ return -ENODEV;
+ }
+
+ alloc_sw_rings_min_mem(dev, d, num_queues, socket_id);
+
+ /* If minimal memory space approach failed, then allocate
+ * the 2 * 64MB block for the sw rings
+ */
+ if (d->sw_rings == NULL)
+ alloc_2x64mb_sw_rings_mem(dev, d, socket_id);
+
+ if (d->sw_rings == NULL) {
+ rte_bbdev_log(NOTICE,
+ "Failure allocating sw_rings memory");
+ return -ENOMEM;
+ }
+
+ /* Configure ACC200 with the base address for DMA descriptor rings
+ * Same descriptor rings used for UL and DL DMA Engines
+ * Note : Assuming only VF0 bundle is used for PF mode
+ */
+ phys_high = (uint32_t)(d->sw_rings_iova >> 32);
+ phys_low = (uint32_t)(d->sw_rings_iova & ~(ACC_SIZE_64MBYTE-1));
+
+ /* Choose correct registry addresses for the device type */
+ if (d->pf_device)
+ reg_addr = &pf_reg_addr;
+ else
+ reg_addr = &vf_reg_addr;
+
+ /* Read the populated cfg from ACC200 registers */
+ fetch_acc200_config(dev);
+
+ /* Start Pmon */
+ for (value = 0; value <= 2; value++) {
+ acc_reg_write(d, reg_addr->pmon_ctrl_a, value);
+ acc_reg_write(d, reg_addr->pmon_ctrl_b, value);
+ acc_reg_write(d, reg_addr->pmon_ctrl_c, value);
+ }
+
+ /* Release AXI from PF */
+ if (d->pf_device)
+ acc_reg_write(d, HWPfDmaAxiControl, 1);
+
+ acc_reg_write(d, reg_addr->dma_ring_ul5g_hi, phys_high);
+ acc_reg_write(d, reg_addr->dma_ring_ul5g_lo, phys_low);
+ acc_reg_write(d, reg_addr->dma_ring_dl5g_hi, phys_high);
+ acc_reg_write(d, reg_addr->dma_ring_dl5g_lo, phys_low);
+ acc_reg_write(d, reg_addr->dma_ring_ul4g_hi, phys_high);
+ acc_reg_write(d, reg_addr->dma_ring_ul4g_lo, phys_low);
+ acc_reg_write(d, reg_addr->dma_ring_dl4g_hi, phys_high);
+ acc_reg_write(d, reg_addr->dma_ring_dl4g_lo, phys_low);
+ acc_reg_write(d, reg_addr->dma_ring_fft_hi, phys_high);
+ acc_reg_write(d, reg_addr->dma_ring_fft_lo, phys_low);
+ /*
+ * Configure Ring Size to the max queue ring size
+ * (used for wrapping purpose)
+ */
+ value = log2_basic(d->sw_ring_size / ACC_RING_SIZE_GRANULARITY);
+ acc_reg_write(d, reg_addr->ring_size, value);
+
+ /* Configure tail pointer for use when SDONE enabled */
+ if (d->tail_ptrs == NULL)
+ d->tail_ptrs = rte_zmalloc_socket(
+ dev->device->driver->name,
+ ACC200_NUM_QGRPS * ACC200_NUM_AQS * sizeof(uint32_t),
+ RTE_CACHE_LINE_SIZE, socket_id);
+ if (d->tail_ptrs == NULL) {
+ rte_bbdev_log(ERR, "Failed to allocate tail ptr for %s:%u",
+ dev->device->driver->name,
+ dev->data->dev_id);
+ ret = -ENOMEM;
+ goto free_sw_rings;
+ }
+ d->tail_ptr_iova = rte_malloc_virt2iova(d->tail_ptrs);
+
+ phys_high = (uint32_t)(d->tail_ptr_iova >> 32);
+ phys_low = (uint32_t)(d->tail_ptr_iova);
+ acc_reg_write(d, reg_addr->tail_ptrs_ul5g_hi, phys_high);
+ acc_reg_write(d, reg_addr->tail_ptrs_ul5g_lo, phys_low);
+ acc_reg_write(d, reg_addr->tail_ptrs_dl5g_hi, phys_high);
+ acc_reg_write(d, reg_addr->tail_ptrs_dl5g_lo, phys_low);
+ acc_reg_write(d, reg_addr->tail_ptrs_ul4g_hi, phys_high);
+ acc_reg_write(d, reg_addr->tail_ptrs_ul4g_lo, phys_low);
+ acc_reg_write(d, reg_addr->tail_ptrs_dl4g_hi, phys_high);
+ acc_reg_write(d, reg_addr->tail_ptrs_dl4g_lo, phys_low);
+ acc_reg_write(d, reg_addr->tail_ptrs_fft_hi, phys_high);
+ acc_reg_write(d, reg_addr->tail_ptrs_fft_lo, phys_low);
+
+ if (d->harq_layout == NULL)
+ d->harq_layout = rte_zmalloc_socket("HARQ Layout",
+ ACC_HARQ_LAYOUT * sizeof(*d->harq_layout),
+ RTE_CACHE_LINE_SIZE, dev->data->socket_id);
+ if (d->harq_layout == NULL) {
+ rte_bbdev_log(ERR, "Failed to allocate harq_layout for %s:%u",
+ dev->device->driver->name,
+ dev->data->dev_id);
+ ret = -ENOMEM;
+ goto free_tail_ptrs;
+ }
+
+ /* Mark as configured properly */
+ d->configured = true;
+
+ rte_bbdev_log_debug(
+ "ACC200 (%s) configured sw_rings = %p, sw_rings_iova = %#"
+ PRIx64, dev->data->name, d->sw_rings, d->sw_rings_iova);
+ return 0;
+
+free_tail_ptrs:
+ rte_free(d->tail_ptrs);
+ d->tail_ptrs = NULL;
+free_sw_rings:
+ rte_free(d->sw_rings_base);
+ d->sw_rings = NULL;
+
+ return ret;
+}
+
/* Free memory used for software rings */
static int
acc200_dev_close(struct rte_bbdev *dev)
{
- RTE_SET_USED(dev);
+ struct acc_device *d = dev->data->dev_private;
+ if (d->sw_rings_base != NULL) {
+ rte_free(d->tail_ptrs);
+ rte_free(d->sw_rings_base);
+ rte_free(d->harq_layout);
+ d->sw_rings_base = NULL;
+ d->tail_ptrs = NULL;
+ d->harq_layout = NULL;
+ }
/* Ensure all in flight HW transactions are completed */
usleep(ACC_LONG_WAIT);
return 0;
}
+/**
+ * Report a ACC200 queue index which is free
+ * Return 0 to 16k for a valid queue_idx or -1 when no queue is available
+ * Note : Only supporting VF0 Bundle for PF mode
+ */
+static int
+acc200_find_free_queue_idx(struct rte_bbdev *dev,
+ const struct rte_bbdev_queue_conf *conf)
+{
+ struct acc_device *d = dev->data->dev_private;
+ int op_2_acc[6] = {0, UL_4G, DL_4G, UL_5G, DL_5G, FFT};
+ int acc = op_2_acc[conf->op_type];
+ struct rte_acc_queue_topology *qtop = NULL;
+ uint16_t group_idx;
+ uint64_t aq_idx;
+
+ qtopFromAcc(&qtop, acc, &(d->acc_conf));
+ if (qtop == NULL)
+ return -1;
+ /* Identify matching QGroup Index which are sorted in priority order */
+ group_idx = qtop->first_qgroup_index + conf->priority;
+ if (group_idx >= ACC200_NUM_QGRPS ||
+ conf->priority >= qtop->num_qgroups) {
+ rte_bbdev_log(INFO, "Invalid Priority on %s, priority %u",
+ dev->data->name, conf->priority);
+ return -1;
+ }
+ /* Find a free AQ_idx */
+ for (aq_idx = 0; aq_idx < qtop->num_aqs_per_groups; aq_idx++) {
+ if (((d->q_assigned_bit_map[group_idx] >> aq_idx) & 0x1) == 0) {
+ /* Mark the Queue as assigned */
+ d->q_assigned_bit_map[group_idx] |= (1 << aq_idx);
+ /* Report the AQ Index */
+ return (group_idx << ACC200_GRP_ID_SHIFT) + aq_idx;
+ }
+ }
+ rte_bbdev_log(INFO, "Failed to find free queue on %s, priority %u",
+ dev->data->name, conf->priority);
+ return -1;
+}
+
+/* Setup ACC200 queue */
+static int
+acc200_queue_setup(struct rte_bbdev *dev, uint16_t queue_id,
+ const struct rte_bbdev_queue_conf *conf)
+{
+ struct acc_device *d = dev->data->dev_private;
+ struct acc_queue *q;
+ int16_t q_idx;
+ int ret;
+
+ if (d == NULL) {
+ rte_bbdev_log(ERR, "Undefined device");
+ return -ENODEV;
+ }
+ /* Allocate the queue data structure. */
+ q = rte_zmalloc_socket(dev->device->driver->name, sizeof(*q),
+ RTE_CACHE_LINE_SIZE, conf->socket);
+ if (q == NULL) {
+ rte_bbdev_log(ERR, "Failed to allocate queue memory");
+ return -ENOMEM;
+ }
+
+ q->d = d;
+ q->ring_addr = RTE_PTR_ADD(d->sw_rings, (d->sw_ring_size * queue_id));
+ q->ring_addr_iova = d->sw_rings_iova + (d->sw_ring_size * queue_id);
+
+ /* Prepare the Ring with default descriptor format */
+ union acc_dma_desc *desc = NULL;
+ unsigned int desc_idx, b_idx;
+ int fcw_len = (conf->op_type == RTE_BBDEV_OP_LDPC_ENC ?
+ ACC_FCW_LE_BLEN : (conf->op_type == RTE_BBDEV_OP_TURBO_DEC ?
+ ACC_FCW_TD_BLEN : (conf->op_type == RTE_BBDEV_OP_LDPC_DEC ?
+ ACC_FCW_LD_BLEN : ACC_FCW_FFT_BLEN)));
+
+ for (desc_idx = 0; desc_idx < d->sw_ring_max_depth; desc_idx++) {
+ desc = q->ring_addr + desc_idx;
+ desc->req.word0 = ACC_DMA_DESC_TYPE;
+ desc->req.word1 = 0; /**< Timestamp */
+ desc->req.word2 = 0;
+ desc->req.word3 = 0;
+ uint64_t fcw_offset = (desc_idx << 8) + ACC_DESC_FCW_OFFSET;
+ desc->req.data_ptrs[0].address = q->ring_addr_iova + fcw_offset;
+ desc->req.data_ptrs[0].blen = fcw_len;
+ desc->req.data_ptrs[0].blkid = ACC_DMA_BLKID_FCW;
+ desc->req.data_ptrs[0].last = 0;
+ desc->req.data_ptrs[0].dma_ext = 0;
+ for (b_idx = 1; b_idx < ACC_DMA_MAX_NUM_POINTERS - 1;
+ b_idx++) {
+ desc->req.data_ptrs[b_idx].blkid = ACC_DMA_BLKID_IN;
+ desc->req.data_ptrs[b_idx].last = 1;
+ desc->req.data_ptrs[b_idx].dma_ext = 0;
+ b_idx++;
+ desc->req.data_ptrs[b_idx].blkid =
+ ACC_DMA_BLKID_OUT_ENC;
+ desc->req.data_ptrs[b_idx].last = 1;
+ desc->req.data_ptrs[b_idx].dma_ext = 0;
+ }
+ /* Preset some fields of LDPC FCW */
+ desc->req.fcw_ld.FCWversion = ACC_FCW_VER;
+ desc->req.fcw_ld.gain_i = 1;
+ desc->req.fcw_ld.gain_h = 1;
+ }
+
+ q->lb_in = rte_zmalloc_socket(dev->device->driver->name,
+ RTE_CACHE_LINE_SIZE,
+ RTE_CACHE_LINE_SIZE, conf->socket);
+ if (q->lb_in == NULL) {
+ rte_bbdev_log(ERR, "Failed to allocate lb_in memory");
+ ret = -ENOMEM;
+ goto free_q;
+ }
+ q->lb_in_addr_iova = rte_malloc_virt2iova(q->lb_in);
+ q->lb_out = rte_zmalloc_socket(dev->device->driver->name,
+ RTE_CACHE_LINE_SIZE,
+ RTE_CACHE_LINE_SIZE, conf->socket);
+ if (q->lb_out == NULL) {
+ rte_bbdev_log(ERR, "Failed to allocate lb_out memory");
+ ret = -ENOMEM;
+ goto free_lb_in;
+ }
+ q->lb_out_addr_iova = rte_malloc_virt2iova(q->lb_out);
+ q->companion_ring_addr = rte_zmalloc_socket(dev->device->driver->name,
+ d->sw_ring_max_depth * sizeof(*q->companion_ring_addr),
+ RTE_CACHE_LINE_SIZE, conf->socket);
+ if (q->companion_ring_addr == NULL) {
+ rte_bbdev_log(ERR, "Failed to allocate companion_ring memory");
+ ret = -ENOMEM;
+ goto free_lb_out;
+ }
+
+ /*
+ * Software queue ring wraps synchronously with the HW when it reaches
+ * the boundary of the maximum allocated queue size, no matter what the
+ * sw queue size is. This wrapping is guarded by setting the wrap_mask
+ * to represent the maximum queue size as allocated at the time when
+ * the device has been setup (in configure()).
+ *
+ * The queue depth is set to the queue size value (conf->queue_size).
+ * This limits the occupancy of the queue at any point of time, so that
+ * the queue does not get swamped with enqueue requests.
+ */
+ q->sw_ring_depth = conf->queue_size;
+ q->sw_ring_wrap_mask = d->sw_ring_max_depth - 1;
+
+ q->op_type = conf->op_type;
+
+ q_idx = acc200_find_free_queue_idx(dev, conf);
+ if (q_idx == -1) {
+ ret = -EINVAL;
+ goto free_companion_ring_addr;
+ }
+
+ q->qgrp_id = (q_idx >> ACC200_GRP_ID_SHIFT) & 0xF;
+ q->vf_id = (q_idx >> ACC200_VF_ID_SHIFT) & 0x3F;
+ q->aq_id = q_idx & 0xF;
+ q->aq_depth = 0;
+ if (conf->op_type == RTE_BBDEV_OP_TURBO_DEC)
+ q->aq_depth = (1 << d->acc_conf.q_ul_4g.aq_depth_log2);
+ else if (conf->op_type == RTE_BBDEV_OP_TURBO_ENC)
+ q->aq_depth = (1 << d->acc_conf.q_dl_4g.aq_depth_log2);
+ else if (conf->op_type == RTE_BBDEV_OP_LDPC_DEC)
+ q->aq_depth = (1 << d->acc_conf.q_ul_5g.aq_depth_log2);
+ else if (conf->op_type == RTE_BBDEV_OP_LDPC_ENC)
+ q->aq_depth = (1 << d->acc_conf.q_dl_5g.aq_depth_log2);
+ else if (conf->op_type == RTE_BBDEV_OP_FFT)
+ q->aq_depth = (1 << d->acc_conf.q_fft.aq_depth_log2);
+
+ q->mmio_reg_enqueue = RTE_PTR_ADD(d->mmio_base,
+ queue_offset(d->pf_device,
+ q->vf_id, q->qgrp_id, q->aq_id));
+
+ rte_bbdev_log_debug(
+ "Setup dev%u q%u: qgrp_id=%u, vf_id=%u, aq_id=%u, aq_depth=%u, mmio_reg_enqueue=%p base %p\n",
+ dev->data->dev_id, queue_id, q->qgrp_id, q->vf_id,
+ q->aq_id, q->aq_depth, q->mmio_reg_enqueue,
+ d->mmio_base);
+
+ dev->data->queues[queue_id].queue_private = q;
+ return 0;
+
+free_companion_ring_addr:
+ rte_free(q->companion_ring_addr);
+ q->companion_ring_addr = NULL;
+free_lb_out:
+ rte_free(q->lb_out);
+ q->lb_out = NULL;
+free_lb_in:
+ rte_free(q->lb_in);
+ q->lb_in = NULL;
+free_q:
+ rte_free(q);
+ q = NULL;
+
+ return ret;
+}
+
+
+static int
+acc_queue_stop(struct rte_bbdev *dev, uint16_t queue_id)
+{
+ struct acc_queue *q;
+ q = dev->data->queues[queue_id].queue_private;
+ rte_bbdev_log(INFO, "Queue Stop %d H/T/D %d %d %x OpType %d",
+ queue_id, q->sw_ring_head, q->sw_ring_tail,
+ q->sw_ring_depth, q->op_type);
+ /* ignore all operations in flight and clear counters */
+ q->sw_ring_tail = q->sw_ring_head;
+ q->aq_enqueued = 0;
+ q->aq_dequeued = 0;
+ dev->data->queues[queue_id].queue_stats.enqueued_count = 0;
+ dev->data->queues[queue_id].queue_stats.dequeued_count = 0;
+ dev->data->queues[queue_id].queue_stats.enqueue_err_count = 0;
+ dev->data->queues[queue_id].queue_stats.dequeue_err_count = 0;
+ dev->data->queues[queue_id].queue_stats.enqueue_warn_count = 0;
+ dev->data->queues[queue_id].queue_stats.dequeue_warn_count = 0;
+ return 0;
+}
+
+/* Release ACC200 queue */
+static int
+acc200_queue_release(struct rte_bbdev *dev, uint16_t q_id)
+{
+ struct acc_device *d = dev->data->dev_private;
+ struct acc_queue *q = dev->data->queues[q_id].queue_private;
+
+ if (q != NULL) {
+ /* Mark the Queue as un-assigned */
+ d->q_assigned_bit_map[q->qgrp_id] &= (~0ULL - (uint64_t) (1 << q->aq_id));
+ rte_free(q->companion_ring_addr);
+ rte_free(q->lb_in);
+ rte_free(q->lb_out);
+ rte_free(q);
+ dev->data->queues[q_id].queue_private = NULL;
+ }
+
+ return 0;
+}
+
/* Get ACC200 device info */
static void
acc200_dev_info_get(struct rte_bbdev *dev,
@@ -279,8 +664,12 @@ acc200_dev_info_get(struct rte_bbdev *dev,
}
static const struct rte_bbdev_ops acc200_bbdev_ops = {
+ .setup_queues = acc200_setup_queues,
.close = acc200_dev_close,
.info_get = acc200_dev_info_get,
+ .queue_setup = acc200_queue_setup,
+ .queue_release = acc200_queue_release,
+ .queue_stop = acc_queue_stop,
};
/* ACC200 PCI PF address map */
--
2.37.1
^ permalink raw reply [flat|nested] 28+ messages in thread* Re: [PATCH v6 07/14] baseband/acc: add queue configuration for ACC200
2022-09-24 0:50 ` [PATCH v6 07/14] baseband/acc: add queue configuration " Nicolas Chautru
@ 2022-09-27 13:06 ` Maxime Coquelin
0 siblings, 0 replies; 28+ messages in thread
From: Maxime Coquelin @ 2022-09-27 13:06 UTC (permalink / raw)
To: Nicolas Chautru, dev, thomas
Cc: trix, mdr, bruce.richardson, hemant.agrawal, david.marchand,
stephen, hernan.vargas
On 9/24/22 02:50, Nicolas Chautru wrote:
> From: Nic Chautru <nicolas.chautru@intel.com>
>
> Adding function to create and configure queues for the
> device.
>
> Signed-off-by: Nic Chautru <nicolas.chautru@intel.com>
> ---
> drivers/baseband/acc/acc_common.h | 1 +
> drivers/baseband/acc/rte_acc200_pmd.c | 391 +++++++++++++++++++++++++-
> 2 files changed, 391 insertions(+), 1 deletion(-)
>
> diff --git a/drivers/baseband/acc/acc_common.h b/drivers/baseband/acc/acc_common.h
> index ae8de9ed89..92da41d896 100644
> --- a/drivers/baseband/acc/acc_common.h
> +++ b/drivers/baseband/acc/acc_common.h
> @@ -99,6 +99,7 @@
> #define ACC_LIMIT_DL_MUX_BITS 534
> #define ACC_NUM_QGRPS_PER_WORD 8
> #define ACC_MAX_NUM_QGRPS 32
> +#define ACC_RING_SIZE_GRANULARITY 64
>
> /* Constants from K0 computation from 3GPP 38.212 Table 5.4.2.1-2 */
> #define ACC_N_ZC_1 66 /* N = 66 Zc for BG 1 */
> diff --git a/drivers/baseband/acc/rte_acc200_pmd.c b/drivers/baseband/acc/rte_acc200_pmd.c
> index f666667801..2bbb9700ad 100644
> --- a/drivers/baseband/acc/rte_acc200_pmd.c
> +++ b/drivers/baseband/acc/rte_acc200_pmd.c
> @@ -220,16 +220,401 @@ fetch_acc200_config(struct rte_bbdev *dev)
> acc_conf->q_fft.aq_depth_log2);
> }
>
> +/* Allocate 64MB memory used for all software rings */
> +static int
> +acc200_setup_queues(struct rte_bbdev *dev, uint16_t num_queues, int socket_id)
> +{
> + uint32_t phys_low, phys_high, value;
> + struct acc_device *d = dev->data->dev_private;
> + const struct acc200_registry_addr *reg_addr;
> + int ret;
> +
> + if (d->pf_device && !d->acc_conf.pf_mode_en) {
> + rte_bbdev_log(NOTICE,
> + "%s has PF mode disabled. This PF can't be used.",
> + dev->data->name);
> + return -ENODEV;
> + }
> + if (!d->pf_device && d->acc_conf.pf_mode_en) {
> + rte_bbdev_log(NOTICE,
> + "%s has PF mode enabled. This VF can't be used.",
> + dev->data->name);
> + return -ENODEV;
> + }
> +
> + alloc_sw_rings_min_mem(dev, d, num_queues, socket_id);
> +
> + /* If minimal memory space approach failed, then allocate
> + * the 2 * 64MB block for the sw rings
> + */
> + if (d->sw_rings == NULL)
> + alloc_2x64mb_sw_rings_mem(dev, d, socket_id);
> +
> + if (d->sw_rings == NULL) {
> + rte_bbdev_log(NOTICE,
> + "Failure allocating sw_rings memory");
> + return -ENOMEM;
> + }
> +
> + /* Configure ACC200 with the base address for DMA descriptor rings
> + * Same descriptor rings used for UL and DL DMA Engines
> + * Note : Assuming only VF0 bundle is used for PF mode
> + */
> + phys_high = (uint32_t)(d->sw_rings_iova >> 32);
> + phys_low = (uint32_t)(d->sw_rings_iova & ~(ACC_SIZE_64MBYTE-1));
> +
> + /* Choose correct registry addresses for the device type */
> + if (d->pf_device)
> + reg_addr = &pf_reg_addr;
> + else
> + reg_addr = &vf_reg_addr;
> +
> + /* Read the populated cfg from ACC200 registers */
> + fetch_acc200_config(dev);
> +
> + /* Start Pmon */
> + for (value = 0; value <= 2; value++) {
> + acc_reg_write(d, reg_addr->pmon_ctrl_a, value);
> + acc_reg_write(d, reg_addr->pmon_ctrl_b, value);
> + acc_reg_write(d, reg_addr->pmon_ctrl_c, value);
> + }
> +
> + /* Release AXI from PF */
> + if (d->pf_device)
> + acc_reg_write(d, HWPfDmaAxiControl, 1);
> +
> + acc_reg_write(d, reg_addr->dma_ring_ul5g_hi, phys_high);
> + acc_reg_write(d, reg_addr->dma_ring_ul5g_lo, phys_low);
> + acc_reg_write(d, reg_addr->dma_ring_dl5g_hi, phys_high);
> + acc_reg_write(d, reg_addr->dma_ring_dl5g_lo, phys_low);
> + acc_reg_write(d, reg_addr->dma_ring_ul4g_hi, phys_high);
> + acc_reg_write(d, reg_addr->dma_ring_ul4g_lo, phys_low);
> + acc_reg_write(d, reg_addr->dma_ring_dl4g_hi, phys_high);
> + acc_reg_write(d, reg_addr->dma_ring_dl4g_lo, phys_low);
> + acc_reg_write(d, reg_addr->dma_ring_fft_hi, phys_high);
> + acc_reg_write(d, reg_addr->dma_ring_fft_lo, phys_low);
> + /*
> + * Configure Ring Size to the max queue ring size
> + * (used for wrapping purpose)
> + */
> + value = log2_basic(d->sw_ring_size / ACC_RING_SIZE_GRANULARITY);
> + acc_reg_write(d, reg_addr->ring_size, value);
> +
> + /* Configure tail pointer for use when SDONE enabled */
> + if (d->tail_ptrs == NULL)
> + d->tail_ptrs = rte_zmalloc_socket(
> + dev->device->driver->name,
> + ACC200_NUM_QGRPS * ACC200_NUM_AQS * sizeof(uint32_t),
> + RTE_CACHE_LINE_SIZE, socket_id);
> + if (d->tail_ptrs == NULL) {
> + rte_bbdev_log(ERR, "Failed to allocate tail ptr for %s:%u",
> + dev->device->driver->name,
> + dev->data->dev_id);
> + ret = -ENOMEM;
> + goto free_sw_rings;
> + }
> + d->tail_ptr_iova = rte_malloc_virt2iova(d->tail_ptrs);
> +
> + phys_high = (uint32_t)(d->tail_ptr_iova >> 32);
> + phys_low = (uint32_t)(d->tail_ptr_iova);
> + acc_reg_write(d, reg_addr->tail_ptrs_ul5g_hi, phys_high);
> + acc_reg_write(d, reg_addr->tail_ptrs_ul5g_lo, phys_low);
> + acc_reg_write(d, reg_addr->tail_ptrs_dl5g_hi, phys_high);
> + acc_reg_write(d, reg_addr->tail_ptrs_dl5g_lo, phys_low);
> + acc_reg_write(d, reg_addr->tail_ptrs_ul4g_hi, phys_high);
> + acc_reg_write(d, reg_addr->tail_ptrs_ul4g_lo, phys_low);
> + acc_reg_write(d, reg_addr->tail_ptrs_dl4g_hi, phys_high);
> + acc_reg_write(d, reg_addr->tail_ptrs_dl4g_lo, phys_low);
> + acc_reg_write(d, reg_addr->tail_ptrs_fft_hi, phys_high);
> + acc_reg_write(d, reg_addr->tail_ptrs_fft_lo, phys_low);
> +
> + if (d->harq_layout == NULL)
> + d->harq_layout = rte_zmalloc_socket("HARQ Layout",
> + ACC_HARQ_LAYOUT * sizeof(*d->harq_layout),
> + RTE_CACHE_LINE_SIZE, dev->data->socket_id);
> + if (d->harq_layout == NULL) {
> + rte_bbdev_log(ERR, "Failed to allocate harq_layout for %s:%u",
> + dev->device->driver->name,
> + dev->data->dev_id);
> + ret = -ENOMEM;
> + goto free_tail_ptrs;
> + }
> +
> + /* Mark as configured properly */
> + d->configured = true;
> +
> + rte_bbdev_log_debug(
> + "ACC200 (%s) configured sw_rings = %p, sw_rings_iova = %#"
> + PRIx64, dev->data->name, d->sw_rings, d->sw_rings_iova);
> + return 0;
> +
> +free_tail_ptrs:
> + rte_free(d->tail_ptrs);
> + d->tail_ptrs = NULL;
> +free_sw_rings:
> + rte_free(d->sw_rings_base);
> + d->sw_rings = NULL;
> +
> + return ret;
> +}
> +
> /* Free memory used for software rings */
> static int
> acc200_dev_close(struct rte_bbdev *dev)
> {
> - RTE_SET_USED(dev);
> + struct acc_device *d = dev->data->dev_private;
> + if (d->sw_rings_base != NULL) {
> + rte_free(d->tail_ptrs);
> + rte_free(d->sw_rings_base);
> + rte_free(d->harq_layout);
> + d->sw_rings_base = NULL;
> + d->tail_ptrs = NULL;
> + d->harq_layout = NULL;
> + }
> /* Ensure all in flight HW transactions are completed */
> usleep(ACC_LONG_WAIT);
> return 0;
> }
>
> +/**
> + * Report a ACC200 queue index which is free
> + * Return 0 to 16k for a valid queue_idx or -1 when no queue is available
> + * Note : Only supporting VF0 Bundle for PF mode
> + */
> +static int
> +acc200_find_free_queue_idx(struct rte_bbdev *dev,
> + const struct rte_bbdev_queue_conf *conf)
> +{
> + struct acc_device *d = dev->data->dev_private;
> + int op_2_acc[6] = {0, UL_4G, DL_4G, UL_5G, DL_5G, FFT};
> + int acc = op_2_acc[conf->op_type];
> + struct rte_acc_queue_topology *qtop = NULL;
> + uint16_t group_idx;
> + uint64_t aq_idx;
> +
> + qtopFromAcc(&qtop, acc, &(d->acc_conf));
> + if (qtop == NULL)
> + return -1;
> + /* Identify matching QGroup Index which are sorted in priority order */
> + group_idx = qtop->first_qgroup_index + conf->priority;
> + if (group_idx >= ACC200_NUM_QGRPS ||
> + conf->priority >= qtop->num_qgroups) {
> + rte_bbdev_log(INFO, "Invalid Priority on %s, priority %u",
> + dev->data->name, conf->priority);
> + return -1;
> + }
> + /* Find a free AQ_idx */
> + for (aq_idx = 0; aq_idx < qtop->num_aqs_per_groups; aq_idx++) {
> + if (((d->q_assigned_bit_map[group_idx] >> aq_idx) & 0x1) == 0) {
> + /* Mark the Queue as assigned */
> + d->q_assigned_bit_map[group_idx] |= (1 << aq_idx);
> + /* Report the AQ Index */
> + return (group_idx << ACC200_GRP_ID_SHIFT) + aq_idx;
> + }
> + }
> + rte_bbdev_log(INFO, "Failed to find free queue on %s, priority %u",
> + dev->data->name, conf->priority);
> + return -1;
> +}
> +
> +/* Setup ACC200 queue */
> +static int
> +acc200_queue_setup(struct rte_bbdev *dev, uint16_t queue_id,
> + const struct rte_bbdev_queue_conf *conf)
> +{
> + struct acc_device *d = dev->data->dev_private;
> + struct acc_queue *q;
> + int16_t q_idx;
> + int ret;
> +
> + if (d == NULL) {
> + rte_bbdev_log(ERR, "Undefined device");
> + return -ENODEV;
> + }
> + /* Allocate the queue data structure. */
> + q = rte_zmalloc_socket(dev->device->driver->name, sizeof(*q),
> + RTE_CACHE_LINE_SIZE, conf->socket);
> + if (q == NULL) {
> + rte_bbdev_log(ERR, "Failed to allocate queue memory");
> + return -ENOMEM;
> + }
> +
> + q->d = d;
> + q->ring_addr = RTE_PTR_ADD(d->sw_rings, (d->sw_ring_size * queue_id));
> + q->ring_addr_iova = d->sw_rings_iova + (d->sw_ring_size * queue_id);
> +
> + /* Prepare the Ring with default descriptor format */
> + union acc_dma_desc *desc = NULL;
> + unsigned int desc_idx, b_idx;
> + int fcw_len = (conf->op_type == RTE_BBDEV_OP_LDPC_ENC ?
> + ACC_FCW_LE_BLEN : (conf->op_type == RTE_BBDEV_OP_TURBO_DEC ?
> + ACC_FCW_TD_BLEN : (conf->op_type == RTE_BBDEV_OP_LDPC_DEC ?
> + ACC_FCW_LD_BLEN : ACC_FCW_FFT_BLEN)));
> +
> + for (desc_idx = 0; desc_idx < d->sw_ring_max_depth; desc_idx++) {
> + desc = q->ring_addr + desc_idx;
> + desc->req.word0 = ACC_DMA_DESC_TYPE;
> + desc->req.word1 = 0; /**< Timestamp */
> + desc->req.word2 = 0;
> + desc->req.word3 = 0;
> + uint64_t fcw_offset = (desc_idx << 8) + ACC_DESC_FCW_OFFSET;
> + desc->req.data_ptrs[0].address = q->ring_addr_iova + fcw_offset;
> + desc->req.data_ptrs[0].blen = fcw_len;
> + desc->req.data_ptrs[0].blkid = ACC_DMA_BLKID_FCW;
> + desc->req.data_ptrs[0].last = 0;
> + desc->req.data_ptrs[0].dma_ext = 0;
> + for (b_idx = 1; b_idx < ACC_DMA_MAX_NUM_POINTERS - 1;
> + b_idx++) {
> + desc->req.data_ptrs[b_idx].blkid = ACC_DMA_BLKID_IN;
> + desc->req.data_ptrs[b_idx].last = 1;
> + desc->req.data_ptrs[b_idx].dma_ext = 0;
> + b_idx++;
> + desc->req.data_ptrs[b_idx].blkid =
> + ACC_DMA_BLKID_OUT_ENC;
> + desc->req.data_ptrs[b_idx].last = 1;
> + desc->req.data_ptrs[b_idx].dma_ext = 0;
> + }
> + /* Preset some fields of LDPC FCW */
> + desc->req.fcw_ld.FCWversion = ACC_FCW_VER;
> + desc->req.fcw_ld.gain_i = 1;
> + desc->req.fcw_ld.gain_h = 1;
> + }
> +
> + q->lb_in = rte_zmalloc_socket(dev->device->driver->name,
> + RTE_CACHE_LINE_SIZE,
> + RTE_CACHE_LINE_SIZE, conf->socket);
> + if (q->lb_in == NULL) {
> + rte_bbdev_log(ERR, "Failed to allocate lb_in memory");
> + ret = -ENOMEM;
> + goto free_q;
> + }
> + q->lb_in_addr_iova = rte_malloc_virt2iova(q->lb_in);
> + q->lb_out = rte_zmalloc_socket(dev->device->driver->name,
> + RTE_CACHE_LINE_SIZE,
> + RTE_CACHE_LINE_SIZE, conf->socket);
> + if (q->lb_out == NULL) {
> + rte_bbdev_log(ERR, "Failed to allocate lb_out memory");
> + ret = -ENOMEM;
> + goto free_lb_in;
> + }
> + q->lb_out_addr_iova = rte_malloc_virt2iova(q->lb_out);
> + q->companion_ring_addr = rte_zmalloc_socket(dev->device->driver->name,
> + d->sw_ring_max_depth * sizeof(*q->companion_ring_addr),
> + RTE_CACHE_LINE_SIZE, conf->socket);
> + if (q->companion_ring_addr == NULL) {
> + rte_bbdev_log(ERR, "Failed to allocate companion_ring memory");
> + ret = -ENOMEM;
> + goto free_lb_out;
> + }
> +
> + /*
> + * Software queue ring wraps synchronously with the HW when it reaches
> + * the boundary of the maximum allocated queue size, no matter what the
> + * sw queue size is. This wrapping is guarded by setting the wrap_mask
> + * to represent the maximum queue size as allocated at the time when
> + * the device has been setup (in configure()).
> + *
> + * The queue depth is set to the queue size value (conf->queue_size).
> + * This limits the occupancy of the queue at any point of time, so that
> + * the queue does not get swamped with enqueue requests.
> + */
> + q->sw_ring_depth = conf->queue_size;
> + q->sw_ring_wrap_mask = d->sw_ring_max_depth - 1;
> +
> + q->op_type = conf->op_type;
> +
> + q_idx = acc200_find_free_queue_idx(dev, conf);
> + if (q_idx == -1) {
> + ret = -EINVAL;
> + goto free_companion_ring_addr;
> + }
> +
> + q->qgrp_id = (q_idx >> ACC200_GRP_ID_SHIFT) & 0xF;
> + q->vf_id = (q_idx >> ACC200_VF_ID_SHIFT) & 0x3F;
> + q->aq_id = q_idx & 0xF;
> + q->aq_depth = 0;
> + if (conf->op_type == RTE_BBDEV_OP_TURBO_DEC)
> + q->aq_depth = (1 << d->acc_conf.q_ul_4g.aq_depth_log2);
> + else if (conf->op_type == RTE_BBDEV_OP_TURBO_ENC)
> + q->aq_depth = (1 << d->acc_conf.q_dl_4g.aq_depth_log2);
> + else if (conf->op_type == RTE_BBDEV_OP_LDPC_DEC)
> + q->aq_depth = (1 << d->acc_conf.q_ul_5g.aq_depth_log2);
> + else if (conf->op_type == RTE_BBDEV_OP_LDPC_ENC)
> + q->aq_depth = (1 << d->acc_conf.q_dl_5g.aq_depth_log2);
> + else if (conf->op_type == RTE_BBDEV_OP_FFT)
> + q->aq_depth = (1 << d->acc_conf.q_fft.aq_depth_log2);
> +
> + q->mmio_reg_enqueue = RTE_PTR_ADD(d->mmio_base,
> + queue_offset(d->pf_device,
> + q->vf_id, q->qgrp_id, q->aq_id));
> +
> + rte_bbdev_log_debug(
> + "Setup dev%u q%u: qgrp_id=%u, vf_id=%u, aq_id=%u, aq_depth=%u, mmio_reg_enqueue=%p base %p\n",
> + dev->data->dev_id, queue_id, q->qgrp_id, q->vf_id,
> + q->aq_id, q->aq_depth, q->mmio_reg_enqueue,
> + d->mmio_base);
> +
> + dev->data->queues[queue_id].queue_private = q;
> + return 0;
> +
> +free_companion_ring_addr:
> + rte_free(q->companion_ring_addr);
> + q->companion_ring_addr = NULL;
> +free_lb_out:
> + rte_free(q->lb_out);
> + q->lb_out = NULL;
> +free_lb_in:
> + rte_free(q->lb_in);
> + q->lb_in = NULL;
> +free_q:
> + rte_free(q);
> + q = NULL;
> +
> + return ret;
> +}
> +
> +
> +static int
> +acc_queue_stop(struct rte_bbdev *dev, uint16_t queue_id)
> +{
> + struct acc_queue *q;
> + q = dev->data->queues[queue_id].queue_private;
> + rte_bbdev_log(INFO, "Queue Stop %d H/T/D %d %d %x OpType %d",
> + queue_id, q->sw_ring_head, q->sw_ring_tail,
> + q->sw_ring_depth, q->op_type);
> + /* ignore all operations in flight and clear counters */
> + q->sw_ring_tail = q->sw_ring_head;
> + q->aq_enqueued = 0;
> + q->aq_dequeued = 0;
> + dev->data->queues[queue_id].queue_stats.enqueued_count = 0;
> + dev->data->queues[queue_id].queue_stats.dequeued_count = 0;
> + dev->data->queues[queue_id].queue_stats.enqueue_err_count = 0;
> + dev->data->queues[queue_id].queue_stats.dequeue_err_count = 0;
> + dev->data->queues[queue_id].queue_stats.enqueue_warn_count = 0;
> + dev->data->queues[queue_id].queue_stats.dequeue_warn_count = 0;
> + return 0;
> +}
> +
> +/* Release ACC200 queue */
> +static int
> +acc200_queue_release(struct rte_bbdev *dev, uint16_t q_id)
> +{
> + struct acc_device *d = dev->data->dev_private;
> + struct acc_queue *q = dev->data->queues[q_id].queue_private;
> +
> + if (q != NULL) {
> + /* Mark the Queue as un-assigned */
> + d->q_assigned_bit_map[q->qgrp_id] &= (~0ULL - (uint64_t) (1 << q->aq_id));
> + rte_free(q->companion_ring_addr);
> + rte_free(q->lb_in);
> + rte_free(q->lb_out);
> + rte_free(q);
> + dev->data->queues[q_id].queue_private = NULL;
> + }
> +
> + return 0;
> +}
> +
> /* Get ACC200 device info */
> static void
> acc200_dev_info_get(struct rte_bbdev *dev,
> @@ -279,8 +664,12 @@ acc200_dev_info_get(struct rte_bbdev *dev,
> }
>
> static const struct rte_bbdev_ops acc200_bbdev_ops = {
> + .setup_queues = acc200_setup_queues,
> .close = acc200_dev_close,
> .info_get = acc200_dev_info_get,
> + .queue_setup = acc200_queue_setup,
> + .queue_release = acc200_queue_release,
> + .queue_stop = acc_queue_stop,
> };
>
> /* ACC200 PCI PF address map */
Thanks for adding proper error paths.
Reviewed-by: Maxime Coquelin <maxime.coquelin@redhat.com>
Thanks,
Maxime
^ permalink raw reply [flat|nested] 28+ messages in thread
* [PATCH v6 08/14] baseband/acc: add LDPC processing functions
2022-09-24 0:50 From: Nicolas Chautru <nicolas.chautru@intel.com> Nicolas Chautru
` (6 preceding siblings ...)
2022-09-24 0:50 ` [PATCH v6 07/14] baseband/acc: add queue configuration " Nicolas Chautru
@ 2022-09-24 0:50 ` Nicolas Chautru
2022-09-27 13:21 ` Maxime Coquelin
2022-09-24 0:50 ` [PATCH v6 09/14] baseband/acc: add LTE " Nicolas Chautru
` (5 subsequent siblings)
13 siblings, 1 reply; 28+ messages in thread
From: Nicolas Chautru @ 2022-09-24 0:50 UTC (permalink / raw)
To: dev, thomas
Cc: maxime.coquelin, trix, mdr, bruce.richardson, hemant.agrawal,
david.marchand, stephen, hernan.vargas, Nic Chautru
From: Nic Chautru <nicolas.chautru@intel.com>
Adding LDPC encode and decode processing functions.
Signed-off-by: Nic Chautru <nicolas.chautru@intel.com>
---
drivers/baseband/acc/acc_common.h | 84 ++
drivers/baseband/acc/rte_acc200_pmd.c | 1384 ++++++++++++++++++++++++-
2 files changed, 1464 insertions(+), 4 deletions(-)
diff --git a/drivers/baseband/acc/acc_common.h b/drivers/baseband/acc/acc_common.h
index 92da41d896..b3ac9800d1 100644
--- a/drivers/baseband/acc/acc_common.h
+++ b/drivers/baseband/acc/acc_common.h
@@ -1301,4 +1301,88 @@ acc_pci_remove(struct rte_pci_device *pci_dev)
return 0;
}
+static inline void
+acc_enqueue_status(struct rte_bbdev_queue_data *q_data,
+ enum rte_bbdev_enqueue_status status)
+{
+ q_data->enqueue_status = status;
+ q_data->queue_stats.enqueue_status_count[status]++;
+
+ rte_acc_log(WARNING, "Enqueue Status: %s %#"PRIx64"",
+ rte_bbdev_enqueue_status_str(status),
+ q_data->queue_stats.enqueue_status_count[status]);
+}
+
+static inline void
+acc_enqueue_invalid(struct rte_bbdev_queue_data *q_data)
+{
+ acc_enqueue_status(q_data, RTE_BBDEV_ENQ_STATUS_INVALID_OP);
+}
+
+static inline void
+acc_enqueue_ring_full(struct rte_bbdev_queue_data *q_data)
+{
+ acc_enqueue_status(q_data, RTE_BBDEV_ENQ_STATUS_RING_FULL);
+}
+
+static inline void
+acc_enqueue_queue_full(struct rte_bbdev_queue_data *q_data)
+{
+ acc_enqueue_status(q_data, RTE_BBDEV_ENQ_STATUS_QUEUE_FULL);
+}
+
+/* Number of available descriptor in ring to enqueue */
+static inline uint32_t
+acc_ring_avail_enq(struct acc_queue *q)
+{
+ return (q->sw_ring_depth - 1 + q->sw_ring_tail - q->sw_ring_head) & q->sw_ring_wrap_mask;
+}
+
+/* Number of available descriptor in ring to dequeue */
+static inline uint32_t
+acc_ring_avail_deq(struct acc_queue *q)
+{
+ return (q->sw_ring_depth + q->sw_ring_head - q->sw_ring_tail) & q->sw_ring_wrap_mask;
+}
+
+/* Check room in AQ for the enqueues batches into Qmgr */
+static inline int32_t
+acc_aq_avail(struct rte_bbdev_queue_data *q_data, uint16_t num_ops)
+{
+ struct acc_queue *q = q_data->queue_private;
+ int32_t aq_avail = q->aq_depth -
+ ((q->aq_enqueued - q->aq_dequeued +
+ ACC_MAX_QUEUE_DEPTH) % ACC_MAX_QUEUE_DEPTH)
+ - (num_ops >> 7);
+ if (aq_avail <= 0)
+ acc_enqueue_queue_full(q_data);
+ return aq_avail;
+}
+
+/* Calculates number of CBs in processed encoder TB based on 'r' and input
+ * length.
+ */
+static inline uint8_t
+get_num_cbs_in_tb_ldpc_enc(struct rte_bbdev_op_ldpc_enc *ldpc_enc)
+{
+ uint8_t c, r, crc24_bits = 0;
+ uint16_t k = (ldpc_enc->basegraph == 1 ? 22 : 10) * ldpc_enc->z_c
+ - ldpc_enc->n_filler;
+ uint8_t cbs_in_tb = 0;
+ int32_t length;
+
+ length = ldpc_enc->input.length;
+ r = ldpc_enc->tb_params.r;
+ c = ldpc_enc->tb_params.c;
+ crc24_bits = 0;
+ if (check_bit(ldpc_enc->op_flags, RTE_BBDEV_LDPC_CRC_24B_ATTACH))
+ crc24_bits = 24;
+ while (length > 0 && r < c) {
+ length -= (k - crc24_bits) >> 3;
+ r++;
+ cbs_in_tb++;
+ }
+ return cbs_in_tb;
+}
+
#endif /* _ACC_COMMON_H_ */
diff --git a/drivers/baseband/acc/rte_acc200_pmd.c b/drivers/baseband/acc/rte_acc200_pmd.c
index 2bbb9700ad..229e5fba86 100644
--- a/drivers/baseband/acc/rte_acc200_pmd.c
+++ b/drivers/baseband/acc/rte_acc200_pmd.c
@@ -573,15 +573,50 @@ acc200_queue_setup(struct rte_bbdev *dev, uint16_t queue_id,
return ret;
}
+static inline void
+acc200_print_op(struct rte_bbdev_dec_op *op, enum rte_bbdev_op_type op_type,
+ uint16_t index)
+{
+ if (op == NULL)
+ return;
+ if (op_type == RTE_BBDEV_OP_LDPC_DEC)
+ rte_bbdev_log(INFO,
+ " Op 5GUL %d %d %d %d %d %d %d %d %d %d %d %d",
+ index,
+ op->ldpc_dec.basegraph, op->ldpc_dec.z_c,
+ op->ldpc_dec.n_cb, op->ldpc_dec.q_m,
+ op->ldpc_dec.n_filler, op->ldpc_dec.cb_params.e,
+ op->ldpc_dec.op_flags, op->ldpc_dec.rv_index,
+ op->ldpc_dec.iter_max, op->ldpc_dec.iter_count,
+ op->ldpc_dec.harq_combined_input.length
+ );
+ else if (op_type == RTE_BBDEV_OP_LDPC_ENC) {
+ struct rte_bbdev_enc_op *op_dl = (struct rte_bbdev_enc_op *) op;
+ rte_bbdev_log(INFO,
+ " Op 5GDL %d %d %d %d %d %d %d %d %d",
+ index,
+ op_dl->ldpc_enc.basegraph, op_dl->ldpc_enc.z_c,
+ op_dl->ldpc_enc.n_cb, op_dl->ldpc_enc.q_m,
+ op_dl->ldpc_enc.n_filler, op_dl->ldpc_enc.cb_params.e,
+ op_dl->ldpc_enc.op_flags, op_dl->ldpc_enc.rv_index
+ );
+ }
+}
static int
acc_queue_stop(struct rte_bbdev *dev, uint16_t queue_id)
{
struct acc_queue *q;
+ struct rte_bbdev_dec_op *op;
+ uint16_t i;
q = dev->data->queues[queue_id].queue_private;
rte_bbdev_log(INFO, "Queue Stop %d H/T/D %d %d %x OpType %d",
queue_id, q->sw_ring_head, q->sw_ring_tail,
q->sw_ring_depth, q->op_type);
+ for (i = 0; i < q->sw_ring_depth; ++i) {
+ op = (q->ring_addr + i)->req.op_addr;
+ acc200_print_op(op, q->op_type, i);
+ }
/* ignore all operations in flight and clear counters */
q->sw_ring_tail = q->sw_ring_head;
q->aq_enqueued = 0;
@@ -623,6 +658,43 @@ acc200_dev_info_get(struct rte_bbdev *dev,
struct acc_device *d = dev->data->dev_private;
int i;
static const struct rte_bbdev_op_cap bbdev_capabilities[] = {
+ {
+ .type = RTE_BBDEV_OP_LDPC_ENC,
+ .cap.ldpc_enc = {
+ .capability_flags =
+ RTE_BBDEV_LDPC_RATE_MATCH |
+ RTE_BBDEV_LDPC_CRC_24B_ATTACH |
+ RTE_BBDEV_LDPC_INTERLEAVER_BYPASS,
+ .num_buffers_src =
+ RTE_BBDEV_LDPC_MAX_CODE_BLOCKS,
+ .num_buffers_dst =
+ RTE_BBDEV_LDPC_MAX_CODE_BLOCKS,
+ }
+ },
+ {
+ .type = RTE_BBDEV_OP_LDPC_DEC,
+ .cap.ldpc_dec = {
+ .capability_flags =
+ RTE_BBDEV_LDPC_CRC_TYPE_24B_CHECK |
+ RTE_BBDEV_LDPC_CRC_TYPE_24B_DROP |
+ RTE_BBDEV_LDPC_CRC_TYPE_24A_CHECK |
+ RTE_BBDEV_LDPC_CRC_TYPE_16_CHECK |
+ RTE_BBDEV_LDPC_HQ_COMBINE_IN_ENABLE |
+ RTE_BBDEV_LDPC_HQ_COMBINE_OUT_ENABLE |
+ RTE_BBDEV_LDPC_ITERATION_STOP_ENABLE |
+ RTE_BBDEV_LDPC_DEINTERLEAVER_BYPASS |
+ RTE_BBDEV_LDPC_DEC_SCATTER_GATHER |
+ RTE_BBDEV_LDPC_HARQ_6BIT_COMPRESSION |
+ RTE_BBDEV_LDPC_LLR_COMPRESSION,
+ .llr_size = 8,
+ .llr_decimals = 1,
+ .num_buffers_src =
+ RTE_BBDEV_LDPC_MAX_CODE_BLOCKS,
+ .num_buffers_hard_out =
+ RTE_BBDEV_LDPC_MAX_CODE_BLOCKS,
+ .num_buffers_soft_out = 0,
+ }
+ },
RTE_BBDEV_END_OF_CAPABILITIES_LIST()
};
@@ -639,13 +711,15 @@ acc200_dev_info_get(struct rte_bbdev *dev,
dev_info->num_queues[RTE_BBDEV_OP_NONE] = 0;
dev_info->num_queues[RTE_BBDEV_OP_TURBO_DEC] = 0;
dev_info->num_queues[RTE_BBDEV_OP_TURBO_ENC] = 0;
- dev_info->num_queues[RTE_BBDEV_OP_LDPC_DEC] = 0;
- dev_info->num_queues[RTE_BBDEV_OP_LDPC_ENC] = 0;
+ dev_info->num_queues[RTE_BBDEV_OP_LDPC_DEC] = d->acc_conf.q_ul_5g.num_aqs_per_groups *
+ d->acc_conf.q_ul_5g.num_qgroups;
+ dev_info->num_queues[RTE_BBDEV_OP_LDPC_ENC] = d->acc_conf.q_dl_5g.num_aqs_per_groups *
+ d->acc_conf.q_dl_5g.num_qgroups;
dev_info->num_queues[RTE_BBDEV_OP_FFT] = 0;
dev_info->queue_priority[RTE_BBDEV_OP_TURBO_DEC] = 0;
dev_info->queue_priority[RTE_BBDEV_OP_TURBO_ENC] = 0;
- dev_info->queue_priority[RTE_BBDEV_OP_LDPC_DEC] = 0;
- dev_info->queue_priority[RTE_BBDEV_OP_LDPC_ENC] = 0;
+ dev_info->queue_priority[RTE_BBDEV_OP_LDPC_DEC] = d->acc_conf.q_ul_5g.num_qgroups;
+ dev_info->queue_priority[RTE_BBDEV_OP_LDPC_ENC] = d->acc_conf.q_dl_5g.num_qgroups;
dev_info->queue_priority[RTE_BBDEV_OP_FFT] = 0;
dev_info->max_num_queues = 0;
for (i = RTE_BBDEV_OP_NONE; i <= RTE_BBDEV_OP_FFT; i++)
@@ -688,6 +762,1304 @@ static struct rte_pci_id pci_id_acc200_vf_map[] = {
{.device_id = 0},
};
+/* Fill in a frame control word for LDPC decoding. */
+static inline void
+acc200_fcw_ld_fill(struct rte_bbdev_dec_op *op, struct acc_fcw_ld *fcw,
+ union acc_harq_layout_data *harq_layout)
+{
+ uint16_t harq_out_length, harq_in_length, ncb_p, k0_p, parity_offset;
+ uint32_t harq_index;
+ uint32_t l;
+
+ fcw->qm = op->ldpc_dec.q_m;
+ fcw->nfiller = op->ldpc_dec.n_filler;
+ fcw->BG = (op->ldpc_dec.basegraph - 1);
+ fcw->Zc = op->ldpc_dec.z_c;
+ fcw->ncb = op->ldpc_dec.n_cb;
+ fcw->k0 = get_k0(fcw->ncb, fcw->Zc, op->ldpc_dec.basegraph,
+ op->ldpc_dec.rv_index);
+ if (op->ldpc_dec.code_block_mode == RTE_BBDEV_CODE_BLOCK)
+ fcw->rm_e = op->ldpc_dec.cb_params.e;
+ else
+ fcw->rm_e = (op->ldpc_dec.tb_params.r <
+ op->ldpc_dec.tb_params.cab) ?
+ op->ldpc_dec.tb_params.ea :
+ op->ldpc_dec.tb_params.eb;
+
+ if (unlikely(check_bit(op->ldpc_dec.op_flags,
+ RTE_BBDEV_LDPC_HQ_COMBINE_IN_ENABLE) &&
+ (op->ldpc_dec.harq_combined_input.length == 0))) {
+ rte_bbdev_log(WARNING, "Null HARQ input size provided");
+ /* Disable HARQ input in that case to carry forward */
+ op->ldpc_dec.op_flags ^= RTE_BBDEV_LDPC_HQ_COMBINE_IN_ENABLE;
+ }
+ if (unlikely(fcw->rm_e == 0)) {
+ rte_bbdev_log(WARNING, "Null E input provided");
+ fcw->rm_e = 2;
+ }
+
+ fcw->hcin_en = check_bit(op->ldpc_dec.op_flags,
+ RTE_BBDEV_LDPC_HQ_COMBINE_IN_ENABLE);
+ fcw->hcout_en = check_bit(op->ldpc_dec.op_flags,
+ RTE_BBDEV_LDPC_HQ_COMBINE_OUT_ENABLE);
+ fcw->crc_select = check_bit(op->ldpc_dec.op_flags,
+ RTE_BBDEV_LDPC_CRC_TYPE_24B_CHECK);
+ fcw->bypass_dec = 0;
+ fcw->bypass_intlv = check_bit(op->ldpc_dec.op_flags,
+ RTE_BBDEV_LDPC_DEINTERLEAVER_BYPASS);
+ if (op->ldpc_dec.q_m == 1) {
+ fcw->bypass_intlv = 1;
+ fcw->qm = 2;
+ }
+ fcw->hcin_decomp_mode = check_bit(op->ldpc_dec.op_flags,
+ RTE_BBDEV_LDPC_HARQ_6BIT_COMPRESSION);
+ fcw->hcout_comp_mode = check_bit(op->ldpc_dec.op_flags,
+ RTE_BBDEV_LDPC_HARQ_6BIT_COMPRESSION);
+ fcw->llr_pack_mode = check_bit(op->ldpc_dec.op_flags,
+ RTE_BBDEV_LDPC_LLR_COMPRESSION);
+ harq_index = hq_index(op->ldpc_dec.harq_combined_output.offset);
+
+ if (fcw->hcin_en > 0) {
+ harq_in_length = op->ldpc_dec.harq_combined_input.length;
+ if (fcw->hcin_decomp_mode > 0)
+ harq_in_length = harq_in_length * 8 / 6;
+ harq_in_length = RTE_MIN(harq_in_length, op->ldpc_dec.n_cb
+ - op->ldpc_dec.n_filler);
+ harq_in_length = RTE_ALIGN_CEIL(harq_in_length, 64);
+ fcw->hcin_size0 = harq_in_length;
+ fcw->hcin_offset = 0;
+ fcw->hcin_size1 = 0;
+ } else {
+ fcw->hcin_size0 = 0;
+ fcw->hcin_offset = 0;
+ fcw->hcin_size1 = 0;
+ }
+
+ fcw->itmax = op->ldpc_dec.iter_max;
+ fcw->itstop = check_bit(op->ldpc_dec.op_flags,
+ RTE_BBDEV_LDPC_ITERATION_STOP_ENABLE);
+ fcw->cnu_algo = ACC_ALGO_MSA;
+ fcw->synd_precoder = fcw->itstop;
+ /*
+ * These are all implicitly set
+ * fcw->synd_post = 0;
+ * fcw->so_en = 0;
+ * fcw->so_bypass_rm = 0;
+ * fcw->so_bypass_intlv = 0;
+ * fcw->dec_convllr = 0;
+ * fcw->hcout_convllr = 0;
+ * fcw->hcout_size1 = 0;
+ * fcw->so_it = 0;
+ * fcw->hcout_offset = 0;
+ * fcw->negstop_th = 0;
+ * fcw->negstop_it = 0;
+ * fcw->negstop_en = 0;
+ * fcw->gain_i = 1;
+ * fcw->gain_h = 1;
+ */
+ if (fcw->hcout_en > 0) {
+ parity_offset = (op->ldpc_dec.basegraph == 1 ? 20 : 8)
+ * op->ldpc_dec.z_c - op->ldpc_dec.n_filler;
+ k0_p = (fcw->k0 > parity_offset) ?
+ fcw->k0 - op->ldpc_dec.n_filler : fcw->k0;
+ ncb_p = fcw->ncb - op->ldpc_dec.n_filler;
+ l = k0_p + fcw->rm_e;
+ harq_out_length = (uint16_t) fcw->hcin_size0;
+ harq_out_length = RTE_MIN(RTE_MAX(harq_out_length, l), ncb_p);
+ harq_out_length = RTE_ALIGN_CEIL(harq_out_length, 64);
+ fcw->hcout_size0 = harq_out_length;
+ fcw->hcout_size1 = 0;
+ fcw->hcout_offset = 0;
+ harq_layout[harq_index].offset = fcw->hcout_offset;
+ harq_layout[harq_index].size0 = fcw->hcout_size0;
+ } else {
+ fcw->hcout_size0 = 0;
+ fcw->hcout_size1 = 0;
+ fcw->hcout_offset = 0;
+ }
+
+ fcw->tb_crc_select = 0;
+ if (check_bit(op->ldpc_dec.op_flags,
+ RTE_BBDEV_LDPC_CRC_TYPE_24A_CHECK))
+ fcw->tb_crc_select = 2;
+ if (check_bit(op->ldpc_dec.op_flags,
+ RTE_BBDEV_LDPC_CRC_TYPE_16_CHECK))
+ fcw->tb_crc_select = 1;
+}
+
+static inline int
+acc200_dma_desc_ld_fill(struct rte_bbdev_dec_op *op,
+ struct acc_dma_req_desc *desc,
+ struct rte_mbuf **input, struct rte_mbuf *h_output,
+ uint32_t *in_offset, uint32_t *h_out_offset,
+ uint32_t *h_out_length, uint32_t *mbuf_total_left,
+ uint32_t *seg_total_left,
+ struct acc_fcw_ld *fcw)
+{
+ struct rte_bbdev_op_ldpc_dec *dec = &op->ldpc_dec;
+ int next_triplet = 1; /* FCW already done */
+ uint32_t input_length;
+ uint16_t output_length, crc24_overlap = 0;
+ uint16_t sys_cols, K, h_p_size, h_np_size;
+ bool h_comp = check_bit(dec->op_flags,
+ RTE_BBDEV_LDPC_HARQ_6BIT_COMPRESSION);
+
+ acc_header_init(desc);
+
+ if (check_bit(op->ldpc_dec.op_flags,
+ RTE_BBDEV_LDPC_CRC_TYPE_24B_DROP))
+ crc24_overlap = 24;
+
+ /* Compute some LDPC BG lengths */
+ input_length = fcw->rm_e;
+ if (check_bit(op->ldpc_dec.op_flags,
+ RTE_BBDEV_LDPC_LLR_COMPRESSION))
+ input_length = (input_length * 3 + 3) / 4;
+ sys_cols = (dec->basegraph == 1) ? 22 : 10;
+ K = sys_cols * dec->z_c;
+ output_length = K - dec->n_filler - crc24_overlap;
+
+ if (unlikely((*mbuf_total_left == 0) ||
+ (*mbuf_total_left < input_length))) {
+ rte_bbdev_log(ERR,
+ "Mismatch between mbuf length and included CB sizes: mbuf len %u, cb len %u",
+ *mbuf_total_left, input_length);
+ return -1;
+ }
+
+ next_triplet = acc_dma_fill_blk_type_in(desc, input,
+ in_offset, input_length,
+ seg_total_left, next_triplet,
+ check_bit(op->ldpc_dec.op_flags,
+ RTE_BBDEV_LDPC_DEC_SCATTER_GATHER));
+
+ if (unlikely(next_triplet < 0)) {
+ rte_bbdev_log(ERR,
+ "Mismatch between data to process and mbuf data length in bbdev_op: %p",
+ op);
+ return -1;
+ }
+
+ if (check_bit(op->ldpc_dec.op_flags,
+ RTE_BBDEV_LDPC_HQ_COMBINE_IN_ENABLE)) {
+ if (op->ldpc_dec.harq_combined_input.data == 0) {
+ rte_bbdev_log(ERR, "HARQ input is not defined");
+ return -1;
+ }
+ h_p_size = fcw->hcin_size0 + fcw->hcin_size1;
+ if (h_comp)
+ h_p_size = (h_p_size * 3 + 3) / 4;
+ if (op->ldpc_dec.harq_combined_input.data == 0) {
+ rte_bbdev_log(ERR, "HARQ input is not defined");
+ return -1;
+ }
+ acc_dma_fill_blk_type(
+ desc,
+ op->ldpc_dec.harq_combined_input.data,
+ op->ldpc_dec.harq_combined_input.offset,
+ h_p_size,
+ next_triplet,
+ ACC_DMA_BLKID_IN_HARQ);
+ next_triplet++;
+ }
+
+ desc->data_ptrs[next_triplet - 1].last = 1;
+ desc->m2dlen = next_triplet;
+ *mbuf_total_left -= input_length;
+
+ next_triplet = acc_dma_fill_blk_type(desc, h_output,
+ *h_out_offset, output_length >> 3, next_triplet,
+ ACC_DMA_BLKID_OUT_HARD);
+
+ if (check_bit(op->ldpc_dec.op_flags,
+ RTE_BBDEV_LDPC_HQ_COMBINE_OUT_ENABLE)) {
+ if (op->ldpc_dec.harq_combined_output.data == 0) {
+ rte_bbdev_log(ERR, "HARQ output is not defined");
+ return -1;
+ }
+
+ /* Pruned size of the HARQ */
+ h_p_size = fcw->hcout_size0 + fcw->hcout_size1;
+ /* Non-Pruned size of the HARQ */
+ h_np_size = fcw->hcout_offset > 0 ?
+ fcw->hcout_offset + fcw->hcout_size1 :
+ h_p_size;
+ if (h_comp) {
+ h_np_size = (h_np_size * 3 + 3) / 4;
+ h_p_size = (h_p_size * 3 + 3) / 4;
+ }
+ dec->harq_combined_output.length = h_np_size;
+ acc_dma_fill_blk_type(
+ desc,
+ dec->harq_combined_output.data,
+ dec->harq_combined_output.offset,
+ h_p_size,
+ next_triplet,
+ ACC_DMA_BLKID_OUT_HARQ);
+
+ next_triplet++;
+ }
+
+ *h_out_length = output_length >> 3;
+ dec->hard_output.length += *h_out_length;
+ *h_out_offset += *h_out_length;
+ desc->data_ptrs[next_triplet - 1].last = 1;
+ desc->d2mlen = next_triplet - desc->m2dlen;
+
+ desc->op_addr = op;
+
+ return 0;
+}
+
+static inline void
+acc200_dma_desc_ld_update(struct rte_bbdev_dec_op *op,
+ struct acc_dma_req_desc *desc,
+ struct rte_mbuf *input, struct rte_mbuf *h_output,
+ uint32_t *in_offset, uint32_t *h_out_offset,
+ uint32_t *h_out_length,
+ union acc_harq_layout_data *harq_layout)
+{
+ int next_triplet = 1; /* FCW already done */
+ desc->data_ptrs[next_triplet].address =
+ rte_pktmbuf_iova_offset(input, *in_offset);
+ next_triplet++;
+
+ if (check_bit(op->ldpc_dec.op_flags,
+ RTE_BBDEV_LDPC_HQ_COMBINE_IN_ENABLE)) {
+ struct rte_bbdev_op_data hi = op->ldpc_dec.harq_combined_input;
+ desc->data_ptrs[next_triplet].address =
+ rte_pktmbuf_iova_offset(hi.data, hi.offset);
+ next_triplet++;
+ }
+
+ desc->data_ptrs[next_triplet].address =
+ rte_pktmbuf_iova_offset(h_output, *h_out_offset);
+ *h_out_length = desc->data_ptrs[next_triplet].blen;
+ next_triplet++;
+
+ if (check_bit(op->ldpc_dec.op_flags,
+ RTE_BBDEV_LDPC_HQ_COMBINE_OUT_ENABLE)) {
+ /* Adjust based on previous operation */
+ struct rte_bbdev_dec_op *prev_op = desc->op_addr;
+ op->ldpc_dec.harq_combined_output.length =
+ prev_op->ldpc_dec.harq_combined_output.length;
+ uint32_t harq_idx = hq_index(
+ op->ldpc_dec.harq_combined_output.offset);
+ uint32_t prev_harq_idx = hq_index(
+ prev_op->ldpc_dec.harq_combined_output.offset);
+ harq_layout[harq_idx].val = harq_layout[prev_harq_idx].val;
+ struct rte_bbdev_op_data ho =
+ op->ldpc_dec.harq_combined_output;
+ desc->data_ptrs[next_triplet].address =
+ rte_pktmbuf_iova_offset(ho.data, ho.offset);
+ next_triplet++;
+ }
+
+ op->ldpc_dec.hard_output.length += *h_out_length;
+ desc->op_addr = op;
+}
+
+/* Enqueue one encode operations for ACC200 device in CB mode
+ * multiplexed on the same descriptor
+ */
+static inline int
+enqueue_ldpc_enc_n_op_cb(struct acc_queue *q, struct rte_bbdev_enc_op **ops,
+ uint16_t total_enqueued_descs, int16_t num)
+{
+ union acc_dma_desc *desc = NULL;
+ uint32_t out_length;
+ struct rte_mbuf *output_head, *output;
+ int i, next_triplet;
+ uint16_t in_length_in_bytes;
+ struct rte_bbdev_op_ldpc_enc *enc = &ops[0]->ldpc_enc;
+
+ uint16_t desc_idx = ((q->sw_ring_head + total_enqueued_descs)
+ & q->sw_ring_wrap_mask);
+ desc = q->ring_addr + desc_idx;
+ acc_fcw_le_fill(ops[0], &desc->req.fcw_le, num, 0);
+
+ /** This could be done at polling */
+ acc_header_init(&desc->req);
+ desc->req.numCBs = num;
+
+ in_length_in_bytes = ops[0]->ldpc_enc.input.data->data_len;
+ out_length = (enc->cb_params.e + 7) >> 3;
+ desc->req.m2dlen = 1 + num;
+ desc->req.d2mlen = num;
+ next_triplet = 1;
+
+ for (i = 0; i < num; i++) {
+ desc->req.data_ptrs[next_triplet].address =
+ rte_pktmbuf_iova_offset(ops[i]->ldpc_enc.input.data, 0);
+ desc->req.data_ptrs[next_triplet].blen = in_length_in_bytes;
+ next_triplet++;
+ desc->req.data_ptrs[next_triplet].address =
+ rte_pktmbuf_iova_offset(
+ ops[i]->ldpc_enc.output.data, 0);
+ desc->req.data_ptrs[next_triplet].blen = out_length;
+ next_triplet++;
+ ops[i]->ldpc_enc.output.length = out_length;
+ output_head = output = ops[i]->ldpc_enc.output.data;
+ mbuf_append(output_head, output, out_length);
+ output->data_len = out_length;
+ }
+
+ desc->req.op_addr = ops[0];
+ /* Keep track of pointers even when multiplexed in single descriptor */
+ struct acc_ptrs *context_ptrs = q->companion_ring_addr + desc_idx;
+ for (i = 0; i < num; i++)
+ context_ptrs->ptr[i].op_addr = ops[i];
+
+#ifdef RTE_LIBRTE_BBDEV_DEBUG
+ rte_memdump(stderr, "FCW", &desc->req.fcw_le,
+ sizeof(desc->req.fcw_le) - 8);
+ rte_memdump(stderr, "Req Desc.", desc, sizeof(*desc));
+#endif
+
+ /* Number of compatible CBs/ops successfully prepared to enqueue */
+ return num;
+}
+
+/* Enqueue one encode operations for ACC200 device for a partial TB
+ * all codes blocks have same configuration multiplexed on the same descriptor
+ */
+static inline void
+enqueue_ldpc_enc_part_tb(struct acc_queue *q, struct rte_bbdev_enc_op *op,
+ uint16_t total_enqueued_descs, int16_t num_cbs, uint32_t e,
+ uint16_t in_len_B, uint32_t out_len_B, uint32_t *in_offset,
+ uint32_t *out_offset)
+{
+
+ union acc_dma_desc *desc = NULL;
+ struct rte_mbuf *output_head, *output;
+ int i, next_triplet;
+ struct rte_bbdev_op_ldpc_enc *enc = &op->ldpc_enc;
+
+
+ uint16_t desc_idx = ((q->sw_ring_head + total_enqueued_descs)
+ & q->sw_ring_wrap_mask);
+ desc = q->ring_addr + desc_idx;
+ acc_fcw_le_fill(op, &desc->req.fcw_le, num_cbs, e);
+
+ /** This could be done at polling */
+ acc_header_init(&desc->req);
+ desc->req.numCBs = num_cbs;
+
+ desc->req.m2dlen = 1 + num_cbs;
+ desc->req.d2mlen = num_cbs;
+ next_triplet = 1;
+
+ for (i = 0; i < num_cbs; i++) {
+ desc->req.data_ptrs[next_triplet].address =
+ rte_pktmbuf_iova_offset(enc->input.data,
+ *in_offset);
+ *in_offset += in_len_B;
+ desc->req.data_ptrs[next_triplet].blen = in_len_B;
+ next_triplet++;
+ desc->req.data_ptrs[next_triplet].address =
+ rte_pktmbuf_iova_offset(
+ enc->output.data, *out_offset);
+ *out_offset += out_len_B;
+ desc->req.data_ptrs[next_triplet].blen = out_len_B;
+ next_triplet++;
+ enc->output.length += out_len_B;
+ output_head = output = enc->output.data;
+ mbuf_append(output_head, output, out_len_B);
+ }
+
+#ifdef RTE_LIBRTE_BBDEV_DEBUG
+ rte_memdump(stderr, "FCW", &desc->req.fcw_le,
+ sizeof(desc->req.fcw_le) - 8);
+ rte_memdump(stderr, "Req Desc.", desc, sizeof(*desc));
+#endif
+
+}
+
+/* Enqueue one encode operations for ACC200 device in TB mode.
+ * returns the number of descs used
+ */
+static inline int
+enqueue_ldpc_enc_one_op_tb(struct acc_queue *q, struct rte_bbdev_enc_op *op,
+ uint16_t enq_descs, uint8_t cbs_in_tb)
+{
+ uint8_t num_a, num_b;
+ uint16_t desc_idx, input_len_B, return_descs;
+ uint8_t r = op->ldpc_enc.tb_params.r;
+ uint8_t cab = op->ldpc_enc.tb_params.cab;
+ union acc_dma_desc *desc;
+ uint16_t init_enq_descs = enq_descs;
+ uint32_t in_offset = 0, out_offset = 0;
+
+ input_len_B = ((op->ldpc_enc.basegraph == 1 ? 22 : 10) * op->ldpc_enc.z_c) >> 3;
+
+ if (check_bit(op->ldpc_enc.op_flags, RTE_BBDEV_LDPC_CRC_24B_ATTACH))
+ input_len_B -= 3;
+
+ if (r < cab) {
+ num_a = cab - r;
+ num_b = cbs_in_tb - cab;
+ } else {
+ num_a = 0;
+ num_b = cbs_in_tb - r;
+ }
+
+ while (num_a > 0) {
+ uint32_t e = op->ldpc_enc.tb_params.ea;
+ uint32_t out_len_B = (e + 7) >> 3;
+ uint8_t enq = RTE_MIN(num_a, ACC_MUX_5GDL_DESC);
+ num_a -= enq;
+ enqueue_ldpc_enc_part_tb(q, op, enq_descs, enq, e, input_len_B,
+ out_len_B, &in_offset, &out_offset);
+ enq_descs++;
+ }
+ while (num_b > 0) {
+ uint32_t e = op->ldpc_enc.tb_params.eb;
+ uint32_t out_len_B = (e + 7) >> 3;
+ uint8_t enq = RTE_MIN(num_b, ACC_MUX_5GDL_DESC);
+ num_b -= enq;
+ enqueue_ldpc_enc_part_tb(q, op, enq_descs, enq, e, input_len_B,
+ out_len_B, &in_offset, &out_offset);
+ enq_descs++;
+ }
+
+ return_descs = enq_descs - init_enq_descs;
+ /* Keep total number of CBs in first TB */
+ desc_idx = ((q->sw_ring_head + init_enq_descs)
+ & q->sw_ring_wrap_mask);
+ desc = q->ring_addr + desc_idx;
+ desc->req.cbs_in_tb = return_descs; /** Actual number of descriptors */
+ desc->req.op_addr = op;
+
+ /* Set SDone on last CB descriptor for TB mode. */
+ desc_idx = ((q->sw_ring_head + enq_descs - 1)
+ & q->sw_ring_wrap_mask);
+ desc = q->ring_addr + desc_idx;
+ desc->req.sdone_enable = 1;
+ desc->req.irq_enable = q->irq_enable;
+ desc->req.op_addr = op;
+ return return_descs;
+}
+
+/** Enqueue one decode operations for ACC200 device in CB mode */
+static inline int
+enqueue_ldpc_dec_one_op_cb(struct acc_queue *q, struct rte_bbdev_dec_op *op,
+ uint16_t total_enqueued_cbs, bool same_op)
+{
+ int ret, hq_len;
+ union acc_dma_desc *desc;
+ uint16_t desc_idx;
+ struct rte_mbuf *input, *h_output_head, *h_output;
+ uint32_t in_offset, h_out_offset, mbuf_total_left, h_out_length = 0;
+ union acc_harq_layout_data *harq_layout;
+
+ if (op->ldpc_dec.cb_params.e == 0)
+ return -EINVAL;
+
+ desc_idx = ((q->sw_ring_head + total_enqueued_cbs)
+ & q->sw_ring_wrap_mask);
+ desc = q->ring_addr + desc_idx;
+
+ input = op->ldpc_dec.input.data;
+ h_output_head = h_output = op->ldpc_dec.hard_output.data;
+ in_offset = op->ldpc_dec.input.offset;
+ h_out_offset = op->ldpc_dec.hard_output.offset;
+ mbuf_total_left = op->ldpc_dec.input.length;
+ harq_layout = q->d->harq_layout;
+
+ if (same_op) {
+ union acc_dma_desc *prev_desc;
+ desc_idx = ((q->sw_ring_head + total_enqueued_cbs - 1)
+ & q->sw_ring_wrap_mask);
+ prev_desc = q->ring_addr + desc_idx;
+ uint8_t *prev_ptr = (uint8_t *) prev_desc;
+ uint8_t *new_ptr = (uint8_t *) desc;
+ /* Copy first 4 words and BDESCs */
+ rte_memcpy(new_ptr, prev_ptr, ACC_5GUL_SIZE_0);
+ rte_memcpy(new_ptr + ACC_5GUL_OFFSET_0,
+ prev_ptr + ACC_5GUL_OFFSET_0,
+ ACC_5GUL_SIZE_1);
+ desc->req.op_addr = prev_desc->req.op_addr;
+ /* Copy FCW */
+ rte_memcpy(new_ptr + ACC_DESC_FCW_OFFSET,
+ prev_ptr + ACC_DESC_FCW_OFFSET,
+ ACC_FCW_LD_BLEN);
+ acc200_dma_desc_ld_update(op, &desc->req, input, h_output,
+ &in_offset, &h_out_offset,
+ &h_out_length, harq_layout);
+ } else {
+ struct acc_fcw_ld *fcw;
+ uint32_t seg_total_left;
+ fcw = &desc->req.fcw_ld;
+ acc200_fcw_ld_fill(op, fcw, harq_layout);
+
+ /* Special handling when using mbuf or not */
+ if (check_bit(op->ldpc_dec.op_flags,
+ RTE_BBDEV_LDPC_DEC_SCATTER_GATHER))
+ seg_total_left = rte_pktmbuf_data_len(input)
+ - in_offset;
+ else
+ seg_total_left = fcw->rm_e;
+
+ ret = acc200_dma_desc_ld_fill(op, &desc->req, &input, h_output,
+ &in_offset, &h_out_offset,
+ &h_out_length, &mbuf_total_left,
+ &seg_total_left, fcw);
+ if (unlikely(ret < 0))
+ return ret;
+ }
+
+ /* Hard output */
+ mbuf_append(h_output_head, h_output, h_out_length);
+ if (op->ldpc_dec.harq_combined_output.length > 0) {
+ /* Push the HARQ output into host memory */
+ struct rte_mbuf *hq_output_head, *hq_output;
+ hq_output_head = op->ldpc_dec.harq_combined_output.data;
+ hq_output = op->ldpc_dec.harq_combined_output.data;
+ hq_len = op->ldpc_dec.harq_combined_output.length;
+ if (unlikely(!mbuf_append(hq_output_head, hq_output,
+ hq_len))) {
+ rte_bbdev_log(ERR, "HARQ output mbuf issue %d %d\n",
+ hq_output->buf_len,
+ hq_len);
+ return -1;
+ }
+ }
+
+#ifdef RTE_LIBRTE_BBDEV_DEBUG
+ rte_memdump(stderr, "FCW", &desc->req.fcw_ld,
+ sizeof(desc->req.fcw_ld) - 8);
+ rte_memdump(stderr, "Req Desc.", desc, sizeof(*desc));
+#endif
+
+ /* One CB (one op) was successfully prepared to enqueue */
+ return 1;
+}
+
+
+/* Enqueue one decode operations for ACC200 device in TB mode */
+static inline int
+enqueue_ldpc_dec_one_op_tb(struct acc_queue *q, struct rte_bbdev_dec_op *op,
+ uint16_t total_enqueued_cbs, uint8_t cbs_in_tb)
+{
+ union acc_dma_desc *desc = NULL;
+ union acc_dma_desc *desc_first = NULL;
+ int ret;
+ uint8_t r, c;
+ uint32_t in_offset, h_out_offset,
+ h_out_length, mbuf_total_left, seg_total_left;
+ struct rte_mbuf *input, *h_output_head, *h_output;
+ uint16_t current_enqueued_cbs = 0;
+ uint16_t sys_cols, trail_len = 0;
+
+ uint16_t desc_idx = ((q->sw_ring_head + total_enqueued_cbs)
+ & q->sw_ring_wrap_mask);
+ desc = q->ring_addr + desc_idx;
+ desc_first = desc;
+ uint64_t fcw_offset = (desc_idx << 8) + ACC_DESC_FCW_OFFSET;
+ union acc_harq_layout_data *harq_layout = q->d->harq_layout;
+ acc200_fcw_ld_fill(op, &desc->req.fcw_ld, harq_layout);
+
+ input = op->ldpc_dec.input.data;
+ h_output_head = h_output = op->ldpc_dec.hard_output.data;
+ in_offset = op->ldpc_dec.input.offset;
+ h_out_offset = op->ldpc_dec.hard_output.offset;
+ h_out_length = 0;
+ mbuf_total_left = op->ldpc_dec.input.length;
+ c = op->ldpc_dec.tb_params.c;
+ r = op->ldpc_dec.tb_params.r;
+ if (check_bit(op->ldpc_dec.op_flags,
+ RTE_BBDEV_LDPC_CRC_TYPE_24A_CHECK)) {
+ sys_cols = (op->ldpc_dec.basegraph == 1) ? 22 : 10;
+ trail_len = sys_cols * op->ldpc_dec.z_c -
+ op->ldpc_dec.n_filler - 24;
+ }
+
+ while (mbuf_total_left > 0 && r < c) {
+ if (check_bit(op->ldpc_dec.op_flags,
+ RTE_BBDEV_LDPC_DEC_SCATTER_GATHER))
+ seg_total_left = rte_pktmbuf_data_len(input)
+ - in_offset;
+ else
+ seg_total_left = op->ldpc_dec.input.length;
+ /* Set up DMA descriptor */
+ desc_idx = ((q->sw_ring_head + total_enqueued_cbs)
+ & q->sw_ring_wrap_mask);
+ desc = q->ring_addr + desc_idx;
+ fcw_offset = (desc_idx << 8) + ACC_DESC_FCW_OFFSET;
+ desc->req.data_ptrs[0].address = q->ring_addr_iova +
+ fcw_offset;
+ desc->req.data_ptrs[0].blen = ACC_FCW_LD_BLEN;
+ rte_memcpy(&desc->req.fcw_ld, &desc_first->req.fcw_ld,
+ ACC_FCW_LD_BLEN);
+ desc->req.fcw_ld.tb_trailer_size = (c - r - 1) * trail_len;
+
+ ret = acc200_dma_desc_ld_fill(op, &desc->req, &input,
+ h_output, &in_offset, &h_out_offset,
+ &h_out_length,
+ &mbuf_total_left, &seg_total_left,
+ &desc->req.fcw_ld);
+
+ if (unlikely(ret < 0))
+ return ret;
+
+ /* Hard output */
+ mbuf_append(h_output_head, h_output, h_out_length);
+
+ /* Set total number of CBs in TB */
+ desc->req.cbs_in_tb = cbs_in_tb;
+#ifdef RTE_LIBRTE_BBDEV_DEBUG
+ rte_memdump(stderr, "FCW", &desc->req.fcw_td,
+ sizeof(desc->req.fcw_td) - 8);
+ rte_memdump(stderr, "Req Desc.", desc, sizeof(*desc));
+#endif
+ if (check_bit(op->ldpc_dec.op_flags,
+ RTE_BBDEV_LDPC_DEC_SCATTER_GATHER)
+ && (seg_total_left == 0)) {
+ /* Go to the next mbuf */
+ input = input->next;
+ in_offset = 0;
+ h_output = h_output->next;
+ h_out_offset = 0;
+ }
+ total_enqueued_cbs++;
+ current_enqueued_cbs++;
+ r++;
+ }
+
+#ifdef RTE_LIBRTE_BBDEV_DEBUG
+ if (check_mbuf_total_left(mbuf_total_left) != 0)
+ return -EINVAL;
+#endif
+ /* Set SDone on last CB descriptor for TB mode */
+ desc->req.sdone_enable = 1;
+ desc->req.irq_enable = q->irq_enable;
+
+ return current_enqueued_cbs;
+}
+
+/** Enqueue encode operations for ACC200 device in CB mode. */
+static inline uint16_t
+acc200_enqueue_ldpc_enc_cb(struct rte_bbdev_queue_data *q_data,
+ struct rte_bbdev_enc_op **ops, uint16_t num)
+{
+ struct acc_queue *q = q_data->queue_private;
+ int32_t avail = acc_ring_avail_enq(q);
+ uint16_t i = 0;
+ union acc_dma_desc *desc;
+ int ret, desc_idx = 0;
+ int16_t enq, left = num;
+
+ while (left > 0) {
+ if (unlikely(avail < 1)) {
+ acc_enqueue_ring_full(q_data);
+ break;
+ }
+ avail--;
+ enq = RTE_MIN(left, ACC_MUX_5GDL_DESC);
+ enq = check_mux(&ops[i], enq);
+ ret = enqueue_ldpc_enc_n_op_cb(q, &ops[i], desc_idx, enq);
+ if (ret < 0) {
+ acc_enqueue_invalid(q_data);
+ break;
+ }
+ i += enq;
+ desc_idx++;
+ left = num - i;
+ }
+
+ if (unlikely(i == 0))
+ return 0; /* Nothing to enqueue */
+
+ /* Set SDone in last CB in enqueued ops for CB mode*/
+ desc = q->ring_addr + ((q->sw_ring_head + desc_idx - 1)
+ & q->sw_ring_wrap_mask);
+ desc->req.sdone_enable = 1;
+ desc->req.irq_enable = q->irq_enable;
+
+ acc_dma_enqueue(q, desc_idx, &q_data->queue_stats);
+
+ /* Update stats */
+ q_data->queue_stats.enqueued_count += i;
+ q_data->queue_stats.enqueue_err_count += num - i;
+
+ return i;
+}
+
+/* Enqueue LDPC encode operations for ACC200 device in TB mode. */
+static uint16_t
+acc200_enqueue_ldpc_enc_tb(struct rte_bbdev_queue_data *q_data,
+ struct rte_bbdev_enc_op **ops, uint16_t num)
+{
+ struct acc_queue *q = q_data->queue_private;
+ int32_t avail = acc_ring_avail_enq(q);
+ uint16_t i, enqueued_descs = 0;
+ uint8_t cbs_in_tb;
+ int descs_used;
+
+ for (i = 0; i < num; ++i) {
+ cbs_in_tb = get_num_cbs_in_tb_ldpc_enc(&ops[i]->ldpc_enc);
+ /* Check if there are available space for further processing */
+ if (unlikely((avail - cbs_in_tb < 0) || (cbs_in_tb == 0))) {
+ acc_enqueue_ring_full(q_data);
+ break;
+ }
+
+ descs_used = enqueue_ldpc_enc_one_op_tb(q, ops[i],
+ enqueued_descs, cbs_in_tb);
+ if (descs_used < 0) {
+ acc_enqueue_invalid(q_data);
+ break;
+ }
+ enqueued_descs += descs_used;
+ avail -= descs_used;
+ }
+ if (unlikely(enqueued_descs == 0))
+ return 0; /* Nothing to enqueue */
+
+ acc_dma_enqueue(q, enqueued_descs, &q_data->queue_stats);
+
+ /* Update stats */
+ q_data->queue_stats.enqueued_count += i;
+ q_data->queue_stats.enqueue_err_count += num - i;
+
+ return i;
+}
+
+/* Enqueue encode operations for ACC200 device. */
+static uint16_t
+acc200_enqueue_ldpc_enc(struct rte_bbdev_queue_data *q_data,
+ struct rte_bbdev_enc_op **ops, uint16_t num)
+{
+ int32_t aq_avail = acc_aq_avail(q_data, num);
+ if (unlikely((aq_avail <= 0) || (num == 0)))
+ return 0;
+ if (ops[0]->ldpc_enc.code_block_mode == RTE_BBDEV_TRANSPORT_BLOCK)
+ return acc200_enqueue_ldpc_enc_tb(q_data, ops, num);
+ else
+ return acc200_enqueue_ldpc_enc_cb(q_data, ops, num);
+}
+
+/* Enqueue decode operations for ACC200 device in TB mode */
+static uint16_t
+acc200_enqueue_ldpc_dec_tb(struct rte_bbdev_queue_data *q_data,
+ struct rte_bbdev_dec_op **ops, uint16_t num)
+{
+ struct acc_queue *q = q_data->queue_private;
+ int32_t avail = acc_ring_avail_enq(q);
+ uint16_t i, enqueued_cbs = 0;
+ uint8_t cbs_in_tb;
+ int ret;
+
+ for (i = 0; i < num; ++i) {
+ cbs_in_tb = get_num_cbs_in_tb_ldpc_dec(&ops[i]->ldpc_dec);
+ /* Check if there are available space for further processing */
+ if (unlikely((avail - cbs_in_tb < 0) ||
+ (cbs_in_tb == 0)))
+ break;
+ avail -= cbs_in_tb;
+
+ ret = enqueue_ldpc_dec_one_op_tb(q, ops[i],
+ enqueued_cbs, cbs_in_tb);
+ if (ret <= 0)
+ break;
+ enqueued_cbs += ret;
+ }
+
+ acc_dma_enqueue(q, enqueued_cbs, &q_data->queue_stats);
+
+ /* Update stats */
+ q_data->queue_stats.enqueued_count += i;
+ q_data->queue_stats.enqueue_err_count += num - i;
+ return i;
+}
+
+/* Enqueue decode operations for ACC200 device in CB mode */
+static uint16_t
+acc200_enqueue_ldpc_dec_cb(struct rte_bbdev_queue_data *q_data,
+ struct rte_bbdev_dec_op **ops, uint16_t num)
+{
+ struct acc_queue *q = q_data->queue_private;
+ int32_t avail = acc_ring_avail_enq(q);
+ uint16_t i;
+ union acc_dma_desc *desc;
+ int ret;
+ bool same_op = false;
+
+ for (i = 0; i < num; ++i) {
+ /* Check if there are available space for further processing */
+ if (unlikely(avail < 1)) {
+ acc_enqueue_ring_full(q_data);
+ break;
+ }
+ avail -= 1;
+
+ rte_bbdev_log(INFO, "Op %d %d %d %d %d %d %d %d %d %d %d %d\n",
+ i, ops[i]->ldpc_dec.op_flags, ops[i]->ldpc_dec.rv_index,
+ ops[i]->ldpc_dec.iter_max, ops[i]->ldpc_dec.iter_count,
+ ops[i]->ldpc_dec.basegraph, ops[i]->ldpc_dec.z_c,
+ ops[i]->ldpc_dec.n_cb, ops[i]->ldpc_dec.q_m,
+ ops[i]->ldpc_dec.n_filler, ops[i]->ldpc_dec.cb_params.e,
+ same_op);
+ ret = enqueue_ldpc_dec_one_op_cb(q, ops[i], i, same_op);
+ if (ret < 0) {
+ acc_enqueue_invalid(q_data);
+ break;
+ }
+ }
+
+ if (unlikely(i == 0))
+ return 0; /* Nothing to enqueue */
+
+ /* Set SDone in last CB in enqueued ops for CB mode*/
+ desc = q->ring_addr + ((q->sw_ring_head + i - 1) & q->sw_ring_wrap_mask);
+ desc->req.sdone_enable = 1;
+ desc->req.irq_enable = q->irq_enable;
+
+ acc_dma_enqueue(q, i, &q_data->queue_stats);
+
+ /* Update stats */
+ q_data->queue_stats.enqueued_count += i;
+ q_data->queue_stats.enqueue_err_count += num - i;
+ return i;
+}
+
+/* Enqueue decode operations for ACC200 device. */
+static uint16_t
+acc200_enqueue_ldpc_dec(struct rte_bbdev_queue_data *q_data,
+ struct rte_bbdev_dec_op **ops, uint16_t num)
+{
+ int32_t aq_avail = acc_aq_avail(q_data, num);
+ if (unlikely((aq_avail <= 0) || (num == 0)))
+ return 0;
+ if (ops[0]->ldpc_dec.code_block_mode == RTE_BBDEV_TRANSPORT_BLOCK)
+ return acc200_enqueue_ldpc_dec_tb(q_data, ops, num);
+ else
+ return acc200_enqueue_ldpc_dec_cb(q_data, ops, num);
+}
+
+
+/* Dequeue one encode operations from ACC200 device in CB mode
+ */
+static inline int
+dequeue_enc_one_op_cb(struct acc_queue *q, struct rte_bbdev_enc_op **ref_op,
+ uint16_t *dequeued_ops, uint32_t *aq_dequeued,
+ uint16_t *dequeued_descs)
+{
+ union acc_dma_desc *desc, atom_desc;
+ union acc_dma_rsp_desc rsp;
+ struct rte_bbdev_enc_op *op;
+ int i;
+ struct acc_ptrs *context_ptrs;
+ int desc_idx = ((q->sw_ring_tail + *dequeued_descs)
+ & q->sw_ring_wrap_mask);
+
+ desc = q->ring_addr + desc_idx;
+ atom_desc.atom_hdr = __atomic_load_n((uint64_t *)desc,
+ __ATOMIC_RELAXED);
+
+ /* Check fdone bit */
+ if (!(atom_desc.rsp.val & ACC_FDONE))
+ return -1;
+
+ rsp.val = atom_desc.rsp.val;
+ rte_bbdev_log_debug("Resp. desc %p: %x", desc, rsp.val);
+
+ /* Dequeue */
+ op = desc->req.op_addr;
+
+ /* Clearing status, it will be set based on response */
+ op->status = 0;
+
+ op->status |= ((rsp.input_err)
+ ? (1 << RTE_BBDEV_DATA_ERROR) : 0);
+ op->status |= ((rsp.dma_err) ? (1 << RTE_BBDEV_DRV_ERROR) : 0);
+ op->status |= ((rsp.fcw_err) ? (1 << RTE_BBDEV_DRV_ERROR) : 0);
+
+ if (desc->req.last_desc_in_batch) {
+ (*aq_dequeued)++;
+ desc->req.last_desc_in_batch = 0;
+ }
+ desc->rsp.val = ACC_DMA_DESC_TYPE;
+ desc->rsp.add_info_0 = 0; /*Reserved bits */
+ desc->rsp.add_info_1 = 0; /*Reserved bits */
+
+ ref_op[0] = op;
+ context_ptrs = q->companion_ring_addr + desc_idx;
+ for (i = 1 ; i < desc->req.numCBs; i++)
+ ref_op[i] = context_ptrs->ptr[i].op_addr;
+
+ /* One op was successfully dequeued */
+ (*dequeued_descs)++;
+ *dequeued_ops += desc->req.numCBs;
+ return desc->req.numCBs;
+}
+
+/* Dequeue one LDPC encode operations from ACC200 device in TB mode
+ * That operation may cover multiple descriptors
+ */
+static inline int
+dequeue_enc_one_op_tb(struct acc_queue *q, struct rte_bbdev_enc_op **ref_op,
+ uint16_t *dequeued_ops, uint32_t *aq_dequeued,
+ uint16_t *dequeued_descs)
+{
+ union acc_dma_desc *desc, *last_desc, atom_desc;
+ union acc_dma_rsp_desc rsp;
+ struct rte_bbdev_enc_op *op;
+ uint8_t i = 0;
+ uint16_t current_dequeued_descs = 0, descs_in_tb;
+
+ desc = q->ring_addr + ((q->sw_ring_tail + *dequeued_descs)
+ & q->sw_ring_wrap_mask);
+ atom_desc.atom_hdr = __atomic_load_n((uint64_t *)desc,
+ __ATOMIC_RELAXED);
+
+ /* Check fdone bit */
+ if (!(atom_desc.rsp.val & ACC_FDONE))
+ return -1;
+
+ /* Get number of CBs in dequeued TB */
+ descs_in_tb = desc->req.cbs_in_tb;
+ /* Get last CB */
+ last_desc = q->ring_addr + ((q->sw_ring_tail
+ + *dequeued_descs + descs_in_tb - 1)
+ & q->sw_ring_wrap_mask);
+ /* Check if last CB in TB is ready to dequeue (and thus
+ * the whole TB) - checking sdone bit. If not return.
+ */
+ atom_desc.atom_hdr = __atomic_load_n((uint64_t *)last_desc,
+ __ATOMIC_RELAXED);
+ if (!(atom_desc.rsp.val & ACC_SDONE))
+ return -1;
+
+ /* Dequeue */
+ op = desc->req.op_addr;
+
+ /* Clearing status, it will be set based on response */
+ op->status = 0;
+
+ while (i < descs_in_tb) {
+ desc = q->ring_addr + ((q->sw_ring_tail
+ + *dequeued_descs)
+ & q->sw_ring_wrap_mask);
+ atom_desc.atom_hdr = __atomic_load_n((uint64_t *)desc,
+ __ATOMIC_RELAXED);
+ rsp.val = atom_desc.rsp.val;
+ rte_bbdev_log_debug("Resp. desc %p: %x", desc,
+ rsp.val);
+
+ op->status |= ((rsp.input_err)
+ ? (1 << RTE_BBDEV_DATA_ERROR) : 0);
+ op->status |= ((rsp.dma_err) ? (1 << RTE_BBDEV_DRV_ERROR) : 0);
+ op->status |= ((rsp.fcw_err) ? (1 << RTE_BBDEV_DRV_ERROR) : 0);
+
+ if (desc->req.last_desc_in_batch) {
+ (*aq_dequeued)++;
+ desc->req.last_desc_in_batch = 0;
+ }
+ desc->rsp.val = ACC_DMA_DESC_TYPE;
+ desc->rsp.add_info_0 = 0;
+ desc->rsp.add_info_1 = 0;
+ (*dequeued_descs)++;
+ current_dequeued_descs++;
+ i++;
+ }
+
+ *ref_op = op;
+ (*dequeued_ops)++;
+ return current_dequeued_descs;
+}
+
+/* Dequeue one decode operation from ACC200 device in CB mode */
+static inline int
+dequeue_dec_one_op_cb(struct rte_bbdev_queue_data *q_data,
+ struct acc_queue *q, struct rte_bbdev_dec_op **ref_op,
+ uint16_t dequeued_cbs, uint32_t *aq_dequeued)
+{
+ union acc_dma_desc *desc, atom_desc;
+ union acc_dma_rsp_desc rsp;
+ struct rte_bbdev_dec_op *op;
+
+ desc = q->ring_addr + ((q->sw_ring_tail + dequeued_cbs)
+ & q->sw_ring_wrap_mask);
+ atom_desc.atom_hdr = __atomic_load_n((uint64_t *)desc,
+ __ATOMIC_RELAXED);
+
+ /* Check fdone bit */
+ if (!(atom_desc.rsp.val & ACC_FDONE))
+ return -1;
+
+ rsp.val = atom_desc.rsp.val;
+ rte_bbdev_log_debug("Resp. desc %p: %x\n", desc, rsp.val);
+
+ /* Dequeue */
+ op = desc->req.op_addr;
+
+ /* Clearing status, it will be set based on response */
+ op->status = 0;
+ op->status |= ((rsp.input_err)
+ ? (1 << RTE_BBDEV_DATA_ERROR) : 0);
+ op->status |= ((rsp.dma_err) ? (1 << RTE_BBDEV_DRV_ERROR) : 0);
+ op->status |= ((rsp.fcw_err) ? (1 << RTE_BBDEV_DRV_ERROR) : 0);
+ if (op->status != 0) {
+ /* These errors are not expected */
+ q_data->queue_stats.dequeue_err_count++;
+ }
+
+ /* CRC invalid if error exists */
+ if (!op->status)
+ op->status |= rsp.crc_status << RTE_BBDEV_CRC_ERROR;
+ op->turbo_dec.iter_count = (uint8_t) rsp.iter_cnt;
+ /* Check if this is the last desc in batch (Atomic Queue) */
+ if (desc->req.last_desc_in_batch) {
+ (*aq_dequeued)++;
+ desc->req.last_desc_in_batch = 0;
+ }
+ desc->rsp.val = ACC_DMA_DESC_TYPE;
+ desc->rsp.add_info_0 = 0;
+ desc->rsp.add_info_1 = 0;
+ *ref_op = op;
+
+ /* One CB (op) was successfully dequeued */
+ return 1;
+}
+
+/* Dequeue one decode operations from ACC200 device in CB mode */
+static inline int
+dequeue_ldpc_dec_one_op_cb(struct rte_bbdev_queue_data *q_data,
+ struct acc_queue *q, struct rte_bbdev_dec_op **ref_op,
+ uint16_t dequeued_cbs, uint32_t *aq_dequeued)
+{
+ union acc_dma_desc *desc, atom_desc;
+ union acc_dma_rsp_desc rsp;
+ struct rte_bbdev_dec_op *op;
+
+ desc = q->ring_addr + ((q->sw_ring_tail + dequeued_cbs)
+ & q->sw_ring_wrap_mask);
+ atom_desc.atom_hdr = __atomic_load_n((uint64_t *)desc,
+ __ATOMIC_RELAXED);
+
+ /* Check fdone bit */
+ if (!(atom_desc.rsp.val & ACC_FDONE))
+ return -1;
+
+ rsp.val = atom_desc.rsp.val;
+ rte_bbdev_log_debug("Resp. desc %p: %x %x %x\n", desc,
+ rsp.val, desc->rsp.add_info_0,
+ desc->rsp.add_info_1);
+
+ /* Dequeue */
+ op = desc->req.op_addr;
+
+ /* Clearing status, it will be set based on response */
+ op->status = 0;
+ op->status |= rsp.input_err << RTE_BBDEV_DATA_ERROR;
+ op->status |= rsp.dma_err << RTE_BBDEV_DRV_ERROR;
+ op->status |= rsp.fcw_err << RTE_BBDEV_DRV_ERROR;
+ if (op->status != 0)
+ q_data->queue_stats.dequeue_err_count++;
+
+ op->status |= rsp.crc_status << RTE_BBDEV_CRC_ERROR;
+ if (op->ldpc_dec.hard_output.length > 0 && !rsp.synd_ok)
+ op->status |= 1 << RTE_BBDEV_SYNDROME_ERROR;
+
+ if (check_bit(op->ldpc_dec.op_flags,
+ RTE_BBDEV_LDPC_CRC_TYPE_24A_CHECK) ||
+ check_bit(op->ldpc_dec.op_flags,
+ RTE_BBDEV_LDPC_CRC_TYPE_16_CHECK)) {
+ if (desc->rsp.add_info_1 != 0)
+ op->status |= 1 << RTE_BBDEV_CRC_ERROR;
+ }
+
+ op->ldpc_dec.iter_count = (uint8_t) rsp.iter_cnt;
+
+ /* Check if this is the last desc in batch (Atomic Queue) */
+ if (desc->req.last_desc_in_batch) {
+ (*aq_dequeued)++;
+ desc->req.last_desc_in_batch = 0;
+ }
+
+ desc->rsp.val = ACC_DMA_DESC_TYPE;
+ desc->rsp.add_info_0 = 0;
+ desc->rsp.add_info_1 = 0;
+
+ *ref_op = op;
+
+ /* One CB (op) was successfully dequeued */
+ return 1;
+}
+
+/* Dequeue one decode operations from ACC200 device in TB mode. */
+static inline int
+dequeue_dec_one_op_tb(struct acc_queue *q, struct rte_bbdev_dec_op **ref_op,
+ uint16_t dequeued_cbs, uint32_t *aq_dequeued)
+{
+ union acc_dma_desc *desc, *last_desc, atom_desc;
+ union acc_dma_rsp_desc rsp;
+ struct rte_bbdev_dec_op *op;
+ uint8_t cbs_in_tb = 1, cb_idx = 0;
+ uint32_t tb_crc_check = 0;
+
+ desc = q->ring_addr + ((q->sw_ring_tail + dequeued_cbs)
+ & q->sw_ring_wrap_mask);
+ atom_desc.atom_hdr = __atomic_load_n((uint64_t *)desc,
+ __ATOMIC_RELAXED);
+
+ /* Check fdone bit */
+ if (!(atom_desc.rsp.val & ACC_FDONE))
+ return -1;
+
+ /* Dequeue */
+ op = desc->req.op_addr;
+
+ /* Get number of CBs in dequeued TB */
+ cbs_in_tb = desc->req.cbs_in_tb;
+ /* Get last CB */
+ last_desc = q->ring_addr + ((q->sw_ring_tail
+ + dequeued_cbs + cbs_in_tb - 1)
+ & q->sw_ring_wrap_mask);
+ /* Check if last CB in TB is ready to dequeue (and thus
+ * the whole TB) - checking sdone bit. If not return.
+ */
+ atom_desc.atom_hdr = __atomic_load_n((uint64_t *)last_desc,
+ __ATOMIC_RELAXED);
+ if (!(atom_desc.rsp.val & ACC_SDONE))
+ return -1;
+
+ /* Clearing status, it will be set based on response */
+ op->status = 0;
+
+ /* Read remaining CBs if exists */
+ while (cb_idx < cbs_in_tb) {
+ desc = q->ring_addr + ((q->sw_ring_tail + dequeued_cbs)
+ & q->sw_ring_wrap_mask);
+ atom_desc.atom_hdr = __atomic_load_n((uint64_t *)desc,
+ __ATOMIC_RELAXED);
+ rsp.val = atom_desc.rsp.val;
+ rte_bbdev_log_debug("Resp. desc %p: %x %x %x", desc,
+ rsp.val, desc->rsp.add_info_0,
+ desc->rsp.add_info_1);
+
+ op->status |= ((rsp.input_err)
+ ? (1 << RTE_BBDEV_DATA_ERROR) : 0);
+ op->status |= ((rsp.dma_err) ? (1 << RTE_BBDEV_DRV_ERROR) : 0);
+ op->status |= ((rsp.fcw_err) ? (1 << RTE_BBDEV_DRV_ERROR) : 0);
+
+ if (check_bit(op->ldpc_dec.op_flags,
+ RTE_BBDEV_LDPC_CRC_TYPE_24A_CHECK))
+ tb_crc_check ^= desc->rsp.add_info_1;
+
+ /* CRC invalid if error exists */
+ if (!op->status)
+ op->status |= rsp.crc_status << RTE_BBDEV_CRC_ERROR;
+ op->turbo_dec.iter_count = RTE_MAX((uint8_t) rsp.iter_cnt,
+ op->turbo_dec.iter_count);
+
+ /* Check if this is the last desc in batch (Atomic Queue) */
+ if (desc->req.last_desc_in_batch) {
+ (*aq_dequeued)++;
+ desc->req.last_desc_in_batch = 0;
+ }
+ desc->rsp.val = ACC_DMA_DESC_TYPE;
+ desc->rsp.add_info_0 = 0;
+ desc->rsp.add_info_1 = 0;
+ dequeued_cbs++;
+ cb_idx++;
+ }
+
+ if (check_bit(op->ldpc_dec.op_flags,
+ RTE_BBDEV_LDPC_CRC_TYPE_24A_CHECK)) {
+ rte_bbdev_log_debug("TB-CRC Check %x\n", tb_crc_check);
+ if (tb_crc_check > 0)
+ op->status |= 1 << RTE_BBDEV_CRC_ERROR;
+ }
+
+ *ref_op = op;
+
+ return cb_idx;
+}
+
+/* Dequeue LDPC encode operations from ACC200 device. */
+static uint16_t
+acc200_dequeue_ldpc_enc(struct rte_bbdev_queue_data *q_data,
+ struct rte_bbdev_enc_op **ops, uint16_t num)
+{
+ struct acc_queue *q = q_data->queue_private;
+ uint32_t avail = acc_ring_avail_deq(q);
+ uint32_t aq_dequeued = 0;
+ uint16_t i, dequeued_ops = 0, dequeued_descs = 0;
+ int ret, cbm;
+ struct rte_bbdev_enc_op *op;
+ if (avail == 0)
+ return 0;
+ op = (q->ring_addr + (q->sw_ring_tail &
+ q->sw_ring_wrap_mask))->req.op_addr;
+ cbm = op->ldpc_enc.code_block_mode;
+
+ for (i = 0; i < avail; i++) {
+ if (cbm == RTE_BBDEV_TRANSPORT_BLOCK)
+ ret = dequeue_enc_one_op_tb(q, &ops[dequeued_ops],
+ &dequeued_ops, &aq_dequeued,
+ &dequeued_descs);
+ else
+ ret = dequeue_enc_one_op_cb(q, &ops[dequeued_ops],
+ &dequeued_ops, &aq_dequeued,
+ &dequeued_descs);
+ if (ret < 0)
+ break;
+ if (dequeued_ops >= num)
+ break;
+ }
+
+ q->aq_dequeued += aq_dequeued;
+ q->sw_ring_tail += dequeued_descs;
+
+ /* Update enqueue stats */
+ q_data->queue_stats.dequeued_count += dequeued_ops;
+
+ return dequeued_ops;
+}
+
+/* Dequeue decode operations from ACC200 device. */
+static uint16_t
+acc200_dequeue_ldpc_dec(struct rte_bbdev_queue_data *q_data,
+ struct rte_bbdev_dec_op **ops, uint16_t num)
+{
+ struct acc_queue *q = q_data->queue_private;
+ uint16_t dequeue_num;
+ uint32_t avail = acc_ring_avail_deq(q);
+ uint32_t aq_dequeued = 0;
+ uint16_t i;
+ uint16_t dequeued_cbs = 0;
+ struct rte_bbdev_dec_op *op;
+ int ret;
+
+ dequeue_num = RTE_MIN(avail, num);
+
+ for (i = 0; i < dequeue_num; ++i) {
+ op = (q->ring_addr + ((q->sw_ring_tail + dequeued_cbs)
+ & q->sw_ring_wrap_mask))->req.op_addr;
+ if (op->ldpc_dec.code_block_mode == RTE_BBDEV_TRANSPORT_BLOCK)
+ ret = dequeue_dec_one_op_tb(q, &ops[i], dequeued_cbs,
+ &aq_dequeued);
+ else
+ ret = dequeue_ldpc_dec_one_op_cb(
+ q_data, q, &ops[i], dequeued_cbs,
+ &aq_dequeued);
+
+ if (ret <= 0)
+ break;
+ dequeued_cbs += ret;
+ }
+
+ q->aq_dequeued += aq_dequeued;
+ q->sw_ring_tail += dequeued_cbs;
+
+ /* Update enqueue stats */
+ q_data->queue_stats.dequeued_count += i;
+
+ return i;
+}
+
/* Initialization Function */
static void
acc200_bbdev_init(struct rte_bbdev *dev, struct rte_pci_driver *drv)
@@ -695,6 +2067,10 @@ acc200_bbdev_init(struct rte_bbdev *dev, struct rte_pci_driver *drv)
struct rte_pci_device *pci_dev = RTE_DEV_TO_PCI(dev->device);
dev->dev_ops = &acc200_bbdev_ops;
+ dev->enqueue_ldpc_enc_ops = acc200_enqueue_ldpc_enc;
+ dev->enqueue_ldpc_dec_ops = acc200_enqueue_ldpc_dec;
+ dev->dequeue_ldpc_enc_ops = acc200_dequeue_ldpc_enc;
+ dev->dequeue_ldpc_dec_ops = acc200_dequeue_ldpc_dec;
((struct acc_device *) dev->data->dev_private)->pf_device =
!strcmp(drv->driver.name,
--
2.37.1
^ permalink raw reply [flat|nested] 28+ messages in thread* Re: [PATCH v6 08/14] baseband/acc: add LDPC processing functions
2022-09-24 0:50 ` [PATCH v6 08/14] baseband/acc: add LDPC processing functions Nicolas Chautru
@ 2022-09-27 13:21 ` Maxime Coquelin
0 siblings, 0 replies; 28+ messages in thread
From: Maxime Coquelin @ 2022-09-27 13:21 UTC (permalink / raw)
To: Nicolas Chautru, dev, thomas
Cc: trix, mdr, bruce.richardson, hemant.agrawal, david.marchand,
stephen, hernan.vargas
On 9/24/22 02:50, Nicolas Chautru wrote:
> From: Nic Chautru <nicolas.chautru@intel.com>
>
> Adding LDPC encode and decode processing functions.
>
> Signed-off-by: Nic Chautru <nicolas.chautru@intel.com>
> ---
> drivers/baseband/acc/acc_common.h | 84 ++
> drivers/baseband/acc/rte_acc200_pmd.c | 1384 ++++++++++++++++++++++++-
> 2 files changed, 1464 insertions(+), 4 deletions(-)
>
> diff --git a/drivers/baseband/acc/acc_common.h b/drivers/baseband/acc/acc_common.h
> index 92da41d896..b3ac9800d1 100644
> --- a/drivers/baseband/acc/acc_common.h
> +++ b/drivers/baseband/acc/acc_common.h
> @@ -1301,4 +1301,88 @@ acc_pci_remove(struct rte_pci_device *pci_dev)
> return 0;
> }
>
> +static inline void
> +acc_enqueue_status(struct rte_bbdev_queue_data *q_data,
> + enum rte_bbdev_enqueue_status status)
> +{
> + q_data->enqueue_status = status;
> + q_data->queue_stats.enqueue_status_count[status]++;
> +
> + rte_acc_log(WARNING, "Enqueue Status: %s %#"PRIx64"",
> + rte_bbdev_enqueue_status_str(status),
> + q_data->queue_stats.enqueue_status_count[status]);
> +}
> +
> +static inline void
> +acc_enqueue_invalid(struct rte_bbdev_queue_data *q_data)
> +{
> + acc_enqueue_status(q_data, RTE_BBDEV_ENQ_STATUS_INVALID_OP);
> +}
> +
> +static inline void
> +acc_enqueue_ring_full(struct rte_bbdev_queue_data *q_data)
> +{
> + acc_enqueue_status(q_data, RTE_BBDEV_ENQ_STATUS_RING_FULL);
> +}
> +
> +static inline void
> +acc_enqueue_queue_full(struct rte_bbdev_queue_data *q_data)
> +{
> + acc_enqueue_status(q_data, RTE_BBDEV_ENQ_STATUS_QUEUE_FULL);
> +}
> +
> +/* Number of available descriptor in ring to enqueue */
> +static inline uint32_t
> +acc_ring_avail_enq(struct acc_queue *q)
> +{
> + return (q->sw_ring_depth - 1 + q->sw_ring_tail - q->sw_ring_head) & q->sw_ring_wrap_mask;
> +}
> +
> +/* Number of available descriptor in ring to dequeue */
> +static inline uint32_t
> +acc_ring_avail_deq(struct acc_queue *q)
> +{
> + return (q->sw_ring_depth + q->sw_ring_head - q->sw_ring_tail) & q->sw_ring_wrap_mask;
> +}
> +
> +/* Check room in AQ for the enqueues batches into Qmgr */
> +static inline int32_t
> +acc_aq_avail(struct rte_bbdev_queue_data *q_data, uint16_t num_ops)
> +{
> + struct acc_queue *q = q_data->queue_private;
> + int32_t aq_avail = q->aq_depth -
> + ((q->aq_enqueued - q->aq_dequeued +
> + ACC_MAX_QUEUE_DEPTH) % ACC_MAX_QUEUE_DEPTH)
> + - (num_ops >> 7);
> + if (aq_avail <= 0)
> + acc_enqueue_queue_full(q_data);
> + return aq_avail;
> +}
> +
> +/* Calculates number of CBs in processed encoder TB based on 'r' and input
> + * length.
> + */
> +static inline uint8_t
> +get_num_cbs_in_tb_ldpc_enc(struct rte_bbdev_op_ldpc_enc *ldpc_enc)
> +{
> + uint8_t c, r, crc24_bits = 0;
> + uint16_t k = (ldpc_enc->basegraph == 1 ? 22 : 10) * ldpc_enc->z_c
> + - ldpc_enc->n_filler;
> + uint8_t cbs_in_tb = 0;
> + int32_t length;
> +
> + length = ldpc_enc->input.length;
> + r = ldpc_enc->tb_params.r;
> + c = ldpc_enc->tb_params.c;
> + crc24_bits = 0;
> + if (check_bit(ldpc_enc->op_flags, RTE_BBDEV_LDPC_CRC_24B_ATTACH))
> + crc24_bits = 24;
> + while (length > 0 && r < c) {
> + length -= (k - crc24_bits) >> 3;
> + r++;
> + cbs_in_tb++;
> + }
> + return cbs_in_tb;
> +}
> +
> #endif /* _ACC_COMMON_H_ */
> diff --git a/drivers/baseband/acc/rte_acc200_pmd.c b/drivers/baseband/acc/rte_acc200_pmd.c
> index 2bbb9700ad..229e5fba86 100644
> --- a/drivers/baseband/acc/rte_acc200_pmd.c
> +++ b/drivers/baseband/acc/rte_acc200_pmd.c
> @@ -573,15 +573,50 @@ acc200_queue_setup(struct rte_bbdev *dev, uint16_t queue_id,
> return ret;
> }
>
> +static inline void
> +acc200_print_op(struct rte_bbdev_dec_op *op, enum rte_bbdev_op_type op_type,
> + uint16_t index)
> +{
> + if (op == NULL)
> + return;
> + if (op_type == RTE_BBDEV_OP_LDPC_DEC)
> + rte_bbdev_log(INFO,
> + " Op 5GUL %d %d %d %d %d %d %d %d %d %d %d %d",
> + index,
> + op->ldpc_dec.basegraph, op->ldpc_dec.z_c,
> + op->ldpc_dec.n_cb, op->ldpc_dec.q_m,
> + op->ldpc_dec.n_filler, op->ldpc_dec.cb_params.e,
> + op->ldpc_dec.op_flags, op->ldpc_dec.rv_index,
> + op->ldpc_dec.iter_max, op->ldpc_dec.iter_count,
> + op->ldpc_dec.harq_combined_input.length
> + );
> + else if (op_type == RTE_BBDEV_OP_LDPC_ENC) {
> + struct rte_bbdev_enc_op *op_dl = (struct rte_bbdev_enc_op *) op;
> + rte_bbdev_log(INFO,
> + " Op 5GDL %d %d %d %d %d %d %d %d %d",
> + index,
> + op_dl->ldpc_enc.basegraph, op_dl->ldpc_enc.z_c,
> + op_dl->ldpc_enc.n_cb, op_dl->ldpc_enc.q_m,
> + op_dl->ldpc_enc.n_filler, op_dl->ldpc_enc.cb_params.e,
> + op_dl->ldpc_enc.op_flags, op_dl->ldpc_enc.rv_index
> + );
> + }
> +}
>
> static int
> acc_queue_stop(struct rte_bbdev *dev, uint16_t queue_id)
> {
> struct acc_queue *q;
> + struct rte_bbdev_dec_op *op;
> + uint16_t i;
> q = dev->data->queues[queue_id].queue_private;
> rte_bbdev_log(INFO, "Queue Stop %d H/T/D %d %d %x OpType %d",
> queue_id, q->sw_ring_head, q->sw_ring_tail,
> q->sw_ring_depth, q->op_type);
> + for (i = 0; i < q->sw_ring_depth; ++i) {
> + op = (q->ring_addr + i)->req.op_addr;
> + acc200_print_op(op, q->op_type, i);
> + }
> /* ignore all operations in flight and clear counters */
> q->sw_ring_tail = q->sw_ring_head;
> q->aq_enqueued = 0;
> @@ -623,6 +658,43 @@ acc200_dev_info_get(struct rte_bbdev *dev,
> struct acc_device *d = dev->data->dev_private;
> int i;
> static const struct rte_bbdev_op_cap bbdev_capabilities[] = {
> + {
> + .type = RTE_BBDEV_OP_LDPC_ENC,
> + .cap.ldpc_enc = {
> + .capability_flags =
> + RTE_BBDEV_LDPC_RATE_MATCH |
> + RTE_BBDEV_LDPC_CRC_24B_ATTACH |
> + RTE_BBDEV_LDPC_INTERLEAVER_BYPASS,
> + .num_buffers_src =
> + RTE_BBDEV_LDPC_MAX_CODE_BLOCKS,
> + .num_buffers_dst =
> + RTE_BBDEV_LDPC_MAX_CODE_BLOCKS,
> + }
> + },
> + {
> + .type = RTE_BBDEV_OP_LDPC_DEC,
> + .cap.ldpc_dec = {
> + .capability_flags =
> + RTE_BBDEV_LDPC_CRC_TYPE_24B_CHECK |
> + RTE_BBDEV_LDPC_CRC_TYPE_24B_DROP |
> + RTE_BBDEV_LDPC_CRC_TYPE_24A_CHECK |
> + RTE_BBDEV_LDPC_CRC_TYPE_16_CHECK |
> + RTE_BBDEV_LDPC_HQ_COMBINE_IN_ENABLE |
> + RTE_BBDEV_LDPC_HQ_COMBINE_OUT_ENABLE |
> + RTE_BBDEV_LDPC_ITERATION_STOP_ENABLE |
> + RTE_BBDEV_LDPC_DEINTERLEAVER_BYPASS |
> + RTE_BBDEV_LDPC_DEC_SCATTER_GATHER |
> + RTE_BBDEV_LDPC_HARQ_6BIT_COMPRESSION |
> + RTE_BBDEV_LDPC_LLR_COMPRESSION,
> + .llr_size = 8,
> + .llr_decimals = 1,
> + .num_buffers_src =
> + RTE_BBDEV_LDPC_MAX_CODE_BLOCKS,
> + .num_buffers_hard_out =
> + RTE_BBDEV_LDPC_MAX_CODE_BLOCKS,
> + .num_buffers_soft_out = 0,
> + }
> + },
> RTE_BBDEV_END_OF_CAPABILITIES_LIST()
> };
>
> @@ -639,13 +711,15 @@ acc200_dev_info_get(struct rte_bbdev *dev,
> dev_info->num_queues[RTE_BBDEV_OP_NONE] = 0;
> dev_info->num_queues[RTE_BBDEV_OP_TURBO_DEC] = 0;
> dev_info->num_queues[RTE_BBDEV_OP_TURBO_ENC] = 0;
> - dev_info->num_queues[RTE_BBDEV_OP_LDPC_DEC] = 0;
> - dev_info->num_queues[RTE_BBDEV_OP_LDPC_ENC] = 0;
> + dev_info->num_queues[RTE_BBDEV_OP_LDPC_DEC] = d->acc_conf.q_ul_5g.num_aqs_per_groups *
> + d->acc_conf.q_ul_5g.num_qgroups;
> + dev_info->num_queues[RTE_BBDEV_OP_LDPC_ENC] = d->acc_conf.q_dl_5g.num_aqs_per_groups *
> + d->acc_conf.q_dl_5g.num_qgroups;
> dev_info->num_queues[RTE_BBDEV_OP_FFT] = 0;
> dev_info->queue_priority[RTE_BBDEV_OP_TURBO_DEC] = 0;
> dev_info->queue_priority[RTE_BBDEV_OP_TURBO_ENC] = 0;
> - dev_info->queue_priority[RTE_BBDEV_OP_LDPC_DEC] = 0;
> - dev_info->queue_priority[RTE_BBDEV_OP_LDPC_ENC] = 0;
> + dev_info->queue_priority[RTE_BBDEV_OP_LDPC_DEC] = d->acc_conf.q_ul_5g.num_qgroups;
> + dev_info->queue_priority[RTE_BBDEV_OP_LDPC_ENC] = d->acc_conf.q_dl_5g.num_qgroups;
> dev_info->queue_priority[RTE_BBDEV_OP_FFT] = 0;
> dev_info->max_num_queues = 0;
> for (i = RTE_BBDEV_OP_NONE; i <= RTE_BBDEV_OP_FFT; i++)
> @@ -688,6 +762,1304 @@ static struct rte_pci_id pci_id_acc200_vf_map[] = {
> {.device_id = 0},
> };
>
> +/* Fill in a frame control word for LDPC decoding. */
> +static inline void
> +acc200_fcw_ld_fill(struct rte_bbdev_dec_op *op, struct acc_fcw_ld *fcw,
> + union acc_harq_layout_data *harq_layout)
> +{
> + uint16_t harq_out_length, harq_in_length, ncb_p, k0_p, parity_offset;
> + uint32_t harq_index;
> + uint32_t l;
> +
> + fcw->qm = op->ldpc_dec.q_m;
> + fcw->nfiller = op->ldpc_dec.n_filler;
> + fcw->BG = (op->ldpc_dec.basegraph - 1);
> + fcw->Zc = op->ldpc_dec.z_c;
> + fcw->ncb = op->ldpc_dec.n_cb;
> + fcw->k0 = get_k0(fcw->ncb, fcw->Zc, op->ldpc_dec.basegraph,
> + op->ldpc_dec.rv_index);
> + if (op->ldpc_dec.code_block_mode == RTE_BBDEV_CODE_BLOCK)
> + fcw->rm_e = op->ldpc_dec.cb_params.e;
> + else
> + fcw->rm_e = (op->ldpc_dec.tb_params.r <
> + op->ldpc_dec.tb_params.cab) ?
> + op->ldpc_dec.tb_params.ea :
> + op->ldpc_dec.tb_params.eb;
> +
> + if (unlikely(check_bit(op->ldpc_dec.op_flags,
> + RTE_BBDEV_LDPC_HQ_COMBINE_IN_ENABLE) &&
> + (op->ldpc_dec.harq_combined_input.length == 0))) {
> + rte_bbdev_log(WARNING, "Null HARQ input size provided");
> + /* Disable HARQ input in that case to carry forward */
> + op->ldpc_dec.op_flags ^= RTE_BBDEV_LDPC_HQ_COMBINE_IN_ENABLE;
> + }
> + if (unlikely(fcw->rm_e == 0)) {
> + rte_bbdev_log(WARNING, "Null E input provided");
> + fcw->rm_e = 2;
> + }
> +
> + fcw->hcin_en = check_bit(op->ldpc_dec.op_flags,
> + RTE_BBDEV_LDPC_HQ_COMBINE_IN_ENABLE);
> + fcw->hcout_en = check_bit(op->ldpc_dec.op_flags,
> + RTE_BBDEV_LDPC_HQ_COMBINE_OUT_ENABLE);
> + fcw->crc_select = check_bit(op->ldpc_dec.op_flags,
> + RTE_BBDEV_LDPC_CRC_TYPE_24B_CHECK);
> + fcw->bypass_dec = 0;
> + fcw->bypass_intlv = check_bit(op->ldpc_dec.op_flags,
> + RTE_BBDEV_LDPC_DEINTERLEAVER_BYPASS);
> + if (op->ldpc_dec.q_m == 1) {
> + fcw->bypass_intlv = 1;
> + fcw->qm = 2;
> + }
> + fcw->hcin_decomp_mode = check_bit(op->ldpc_dec.op_flags,
> + RTE_BBDEV_LDPC_HARQ_6BIT_COMPRESSION);
> + fcw->hcout_comp_mode = check_bit(op->ldpc_dec.op_flags,
> + RTE_BBDEV_LDPC_HARQ_6BIT_COMPRESSION);
> + fcw->llr_pack_mode = check_bit(op->ldpc_dec.op_flags,
> + RTE_BBDEV_LDPC_LLR_COMPRESSION);
> + harq_index = hq_index(op->ldpc_dec.harq_combined_output.offset);
> +
> + if (fcw->hcin_en > 0) {
> + harq_in_length = op->ldpc_dec.harq_combined_input.length;
> + if (fcw->hcin_decomp_mode > 0)
> + harq_in_length = harq_in_length * 8 / 6;
> + harq_in_length = RTE_MIN(harq_in_length, op->ldpc_dec.n_cb
> + - op->ldpc_dec.n_filler);
> + harq_in_length = RTE_ALIGN_CEIL(harq_in_length, 64);
> + fcw->hcin_size0 = harq_in_length;
> + fcw->hcin_offset = 0;
> + fcw->hcin_size1 = 0;
> + } else {
> + fcw->hcin_size0 = 0;
> + fcw->hcin_offset = 0;
> + fcw->hcin_size1 = 0;
> + }
> +
> + fcw->itmax = op->ldpc_dec.iter_max;
> + fcw->itstop = check_bit(op->ldpc_dec.op_flags,
> + RTE_BBDEV_LDPC_ITERATION_STOP_ENABLE);
> + fcw->cnu_algo = ACC_ALGO_MSA;
> + fcw->synd_precoder = fcw->itstop;
> + /*
> + * These are all implicitly set
> + * fcw->synd_post = 0;
> + * fcw->so_en = 0;
> + * fcw->so_bypass_rm = 0;
> + * fcw->so_bypass_intlv = 0;
> + * fcw->dec_convllr = 0;
> + * fcw->hcout_convllr = 0;
> + * fcw->hcout_size1 = 0;
> + * fcw->so_it = 0;
> + * fcw->hcout_offset = 0;
> + * fcw->negstop_th = 0;
> + * fcw->negstop_it = 0;
> + * fcw->negstop_en = 0;
> + * fcw->gain_i = 1;
> + * fcw->gain_h = 1;
> + */
> + if (fcw->hcout_en > 0) {
> + parity_offset = (op->ldpc_dec.basegraph == 1 ? 20 : 8)
> + * op->ldpc_dec.z_c - op->ldpc_dec.n_filler;
> + k0_p = (fcw->k0 > parity_offset) ?
> + fcw->k0 - op->ldpc_dec.n_filler : fcw->k0;
> + ncb_p = fcw->ncb - op->ldpc_dec.n_filler;
> + l = k0_p + fcw->rm_e;
> + harq_out_length = (uint16_t) fcw->hcin_size0;
> + harq_out_length = RTE_MIN(RTE_MAX(harq_out_length, l), ncb_p);
> + harq_out_length = RTE_ALIGN_CEIL(harq_out_length, 64);
> + fcw->hcout_size0 = harq_out_length;
> + fcw->hcout_size1 = 0;
> + fcw->hcout_offset = 0;
> + harq_layout[harq_index].offset = fcw->hcout_offset;
> + harq_layout[harq_index].size0 = fcw->hcout_size0;
> + } else {
> + fcw->hcout_size0 = 0;
> + fcw->hcout_size1 = 0;
> + fcw->hcout_offset = 0;
> + }
> +
> + fcw->tb_crc_select = 0;
> + if (check_bit(op->ldpc_dec.op_flags,
> + RTE_BBDEV_LDPC_CRC_TYPE_24A_CHECK))
> + fcw->tb_crc_select = 2;
> + if (check_bit(op->ldpc_dec.op_flags,
> + RTE_BBDEV_LDPC_CRC_TYPE_16_CHECK))
> + fcw->tb_crc_select = 1;
> +}
> +
> +static inline int
> +acc200_dma_desc_ld_fill(struct rte_bbdev_dec_op *op,
> + struct acc_dma_req_desc *desc,
> + struct rte_mbuf **input, struct rte_mbuf *h_output,
> + uint32_t *in_offset, uint32_t *h_out_offset,
> + uint32_t *h_out_length, uint32_t *mbuf_total_left,
> + uint32_t *seg_total_left,
> + struct acc_fcw_ld *fcw)
> +{
> + struct rte_bbdev_op_ldpc_dec *dec = &op->ldpc_dec;
> + int next_triplet = 1; /* FCW already done */
> + uint32_t input_length;
> + uint16_t output_length, crc24_overlap = 0;
> + uint16_t sys_cols, K, h_p_size, h_np_size;
> + bool h_comp = check_bit(dec->op_flags,
> + RTE_BBDEV_LDPC_HARQ_6BIT_COMPRESSION);
> +
> + acc_header_init(desc);
> +
> + if (check_bit(op->ldpc_dec.op_flags,
> + RTE_BBDEV_LDPC_CRC_TYPE_24B_DROP))
> + crc24_overlap = 24;
> +
> + /* Compute some LDPC BG lengths */
> + input_length = fcw->rm_e;
> + if (check_bit(op->ldpc_dec.op_flags,
> + RTE_BBDEV_LDPC_LLR_COMPRESSION))
> + input_length = (input_length * 3 + 3) / 4;
> + sys_cols = (dec->basegraph == 1) ? 22 : 10;
> + K = sys_cols * dec->z_c;
> + output_length = K - dec->n_filler - crc24_overlap;
> +
> + if (unlikely((*mbuf_total_left == 0) ||
> + (*mbuf_total_left < input_length))) {
> + rte_bbdev_log(ERR,
> + "Mismatch between mbuf length and included CB sizes: mbuf len %u, cb len %u",
> + *mbuf_total_left, input_length);
> + return -1;
> + }
> +
> + next_triplet = acc_dma_fill_blk_type_in(desc, input,
> + in_offset, input_length,
> + seg_total_left, next_triplet,
> + check_bit(op->ldpc_dec.op_flags,
> + RTE_BBDEV_LDPC_DEC_SCATTER_GATHER));
> +
> + if (unlikely(next_triplet < 0)) {
> + rte_bbdev_log(ERR,
> + "Mismatch between data to process and mbuf data length in bbdev_op: %p",
> + op);
> + return -1;
> + }
> +
> + if (check_bit(op->ldpc_dec.op_flags,
> + RTE_BBDEV_LDPC_HQ_COMBINE_IN_ENABLE)) {
> + if (op->ldpc_dec.harq_combined_input.data == 0) {
> + rte_bbdev_log(ERR, "HARQ input is not defined");
> + return -1;
> + }
> + h_p_size = fcw->hcin_size0 + fcw->hcin_size1;
> + if (h_comp)
> + h_p_size = (h_p_size * 3 + 3) / 4;
> + if (op->ldpc_dec.harq_combined_input.data == 0) {
> + rte_bbdev_log(ERR, "HARQ input is not defined");
> + return -1;
> + }
> + acc_dma_fill_blk_type(
> + desc,
> + op->ldpc_dec.harq_combined_input.data,
> + op->ldpc_dec.harq_combined_input.offset,
> + h_p_size,
> + next_triplet,
> + ACC_DMA_BLKID_IN_HARQ);
> + next_triplet++;
> + }
> +
> + desc->data_ptrs[next_triplet - 1].last = 1;
> + desc->m2dlen = next_triplet;
> + *mbuf_total_left -= input_length;
> +
> + next_triplet = acc_dma_fill_blk_type(desc, h_output,
> + *h_out_offset, output_length >> 3, next_triplet,
> + ACC_DMA_BLKID_OUT_HARD);
> +
> + if (check_bit(op->ldpc_dec.op_flags,
> + RTE_BBDEV_LDPC_HQ_COMBINE_OUT_ENABLE)) {
> + if (op->ldpc_dec.harq_combined_output.data == 0) {
> + rte_bbdev_log(ERR, "HARQ output is not defined");
> + return -1;
> + }
> +
> + /* Pruned size of the HARQ */
> + h_p_size = fcw->hcout_size0 + fcw->hcout_size1;
> + /* Non-Pruned size of the HARQ */
> + h_np_size = fcw->hcout_offset > 0 ?
> + fcw->hcout_offset + fcw->hcout_size1 :
> + h_p_size;
> + if (h_comp) {
> + h_np_size = (h_np_size * 3 + 3) / 4;
> + h_p_size = (h_p_size * 3 + 3) / 4;
> + }
> + dec->harq_combined_output.length = h_np_size;
> + acc_dma_fill_blk_type(
> + desc,
> + dec->harq_combined_output.data,
> + dec->harq_combined_output.offset,
> + h_p_size,
> + next_triplet,
> + ACC_DMA_BLKID_OUT_HARQ);
> +
> + next_triplet++;
> + }
> +
> + *h_out_length = output_length >> 3;
> + dec->hard_output.length += *h_out_length;
> + *h_out_offset += *h_out_length;
> + desc->data_ptrs[next_triplet - 1].last = 1;
> + desc->d2mlen = next_triplet - desc->m2dlen;
> +
> + desc->op_addr = op;
> +
> + return 0;
> +}
> +
> +static inline void
> +acc200_dma_desc_ld_update(struct rte_bbdev_dec_op *op,
> + struct acc_dma_req_desc *desc,
> + struct rte_mbuf *input, struct rte_mbuf *h_output,
> + uint32_t *in_offset, uint32_t *h_out_offset,
> + uint32_t *h_out_length,
> + union acc_harq_layout_data *harq_layout)
> +{
> + int next_triplet = 1; /* FCW already done */
> + desc->data_ptrs[next_triplet].address =
> + rte_pktmbuf_iova_offset(input, *in_offset);
> + next_triplet++;
> +
> + if (check_bit(op->ldpc_dec.op_flags,
> + RTE_BBDEV_LDPC_HQ_COMBINE_IN_ENABLE)) {
> + struct rte_bbdev_op_data hi = op->ldpc_dec.harq_combined_input;
> + desc->data_ptrs[next_triplet].address =
> + rte_pktmbuf_iova_offset(hi.data, hi.offset);
> + next_triplet++;
> + }
> +
> + desc->data_ptrs[next_triplet].address =
> + rte_pktmbuf_iova_offset(h_output, *h_out_offset);
> + *h_out_length = desc->data_ptrs[next_triplet].blen;
> + next_triplet++;
> +
> + if (check_bit(op->ldpc_dec.op_flags,
> + RTE_BBDEV_LDPC_HQ_COMBINE_OUT_ENABLE)) {
> + /* Adjust based on previous operation */
> + struct rte_bbdev_dec_op *prev_op = desc->op_addr;
> + op->ldpc_dec.harq_combined_output.length =
> + prev_op->ldpc_dec.harq_combined_output.length;
> + uint32_t harq_idx = hq_index(
> + op->ldpc_dec.harq_combined_output.offset);
> + uint32_t prev_harq_idx = hq_index(
> + prev_op->ldpc_dec.harq_combined_output.offset);
> + harq_layout[harq_idx].val = harq_layout[prev_harq_idx].val;
> + struct rte_bbdev_op_data ho =
> + op->ldpc_dec.harq_combined_output;
> + desc->data_ptrs[next_triplet].address =
> + rte_pktmbuf_iova_offset(ho.data, ho.offset);
> + next_triplet++;
> + }
> +
> + op->ldpc_dec.hard_output.length += *h_out_length;
> + desc->op_addr = op;
> +}
> +
> +/* Enqueue one encode operations for ACC200 device in CB mode
> + * multiplexed on the same descriptor
> + */
> +static inline int
> +enqueue_ldpc_enc_n_op_cb(struct acc_queue *q, struct rte_bbdev_enc_op **ops,
> + uint16_t total_enqueued_descs, int16_t num)
> +{
> + union acc_dma_desc *desc = NULL;
> + uint32_t out_length;
> + struct rte_mbuf *output_head, *output;
> + int i, next_triplet;
> + uint16_t in_length_in_bytes;
> + struct rte_bbdev_op_ldpc_enc *enc = &ops[0]->ldpc_enc;
> +
> + uint16_t desc_idx = ((q->sw_ring_head + total_enqueued_descs)
> + & q->sw_ring_wrap_mask);
> + desc = q->ring_addr + desc_idx;
> + acc_fcw_le_fill(ops[0], &desc->req.fcw_le, num, 0);
> +
> + /** This could be done at polling */
> + acc_header_init(&desc->req);
> + desc->req.numCBs = num;
> +
> + in_length_in_bytes = ops[0]->ldpc_enc.input.data->data_len;
> + out_length = (enc->cb_params.e + 7) >> 3;
> + desc->req.m2dlen = 1 + num;
> + desc->req.d2mlen = num;
> + next_triplet = 1;
> +
> + for (i = 0; i < num; i++) {
> + desc->req.data_ptrs[next_triplet].address =
> + rte_pktmbuf_iova_offset(ops[i]->ldpc_enc.input.data, 0);
> + desc->req.data_ptrs[next_triplet].blen = in_length_in_bytes;
> + next_triplet++;
> + desc->req.data_ptrs[next_triplet].address =
> + rte_pktmbuf_iova_offset(
> + ops[i]->ldpc_enc.output.data, 0);
> + desc->req.data_ptrs[next_triplet].blen = out_length;
> + next_triplet++;
> + ops[i]->ldpc_enc.output.length = out_length;
> + output_head = output = ops[i]->ldpc_enc.output.data;
> + mbuf_append(output_head, output, out_length);
> + output->data_len = out_length;
> + }
> +
> + desc->req.op_addr = ops[0];
> + /* Keep track of pointers even when multiplexed in single descriptor */
> + struct acc_ptrs *context_ptrs = q->companion_ring_addr + desc_idx;
> + for (i = 0; i < num; i++)
> + context_ptrs->ptr[i].op_addr = ops[i];
> +
> +#ifdef RTE_LIBRTE_BBDEV_DEBUG
> + rte_memdump(stderr, "FCW", &desc->req.fcw_le,
> + sizeof(desc->req.fcw_le) - 8);
> + rte_memdump(stderr, "Req Desc.", desc, sizeof(*desc));
> +#endif
> +
> + /* Number of compatible CBs/ops successfully prepared to enqueue */
> + return num;
> +}
> +
> +/* Enqueue one encode operations for ACC200 device for a partial TB
> + * all codes blocks have same configuration multiplexed on the same descriptor
> + */
> +static inline void
> +enqueue_ldpc_enc_part_tb(struct acc_queue *q, struct rte_bbdev_enc_op *op,
> + uint16_t total_enqueued_descs, int16_t num_cbs, uint32_t e,
> + uint16_t in_len_B, uint32_t out_len_B, uint32_t *in_offset,
> + uint32_t *out_offset)
> +{
> +
> + union acc_dma_desc *desc = NULL;
> + struct rte_mbuf *output_head, *output;
> + int i, next_triplet;
> + struct rte_bbdev_op_ldpc_enc *enc = &op->ldpc_enc;
> +
> +
> + uint16_t desc_idx = ((q->sw_ring_head + total_enqueued_descs)
> + & q->sw_ring_wrap_mask);
> + desc = q->ring_addr + desc_idx;
> + acc_fcw_le_fill(op, &desc->req.fcw_le, num_cbs, e);
> +
> + /** This could be done at polling */
> + acc_header_init(&desc->req);
> + desc->req.numCBs = num_cbs;
> +
> + desc->req.m2dlen = 1 + num_cbs;
> + desc->req.d2mlen = num_cbs;
> + next_triplet = 1;
> +
> + for (i = 0; i < num_cbs; i++) {
> + desc->req.data_ptrs[next_triplet].address =
> + rte_pktmbuf_iova_offset(enc->input.data,
> + *in_offset);
> + *in_offset += in_len_B;
> + desc->req.data_ptrs[next_triplet].blen = in_len_B;
> + next_triplet++;
> + desc->req.data_ptrs[next_triplet].address =
> + rte_pktmbuf_iova_offset(
> + enc->output.data, *out_offset);
> + *out_offset += out_len_B;
> + desc->req.data_ptrs[next_triplet].blen = out_len_B;
> + next_triplet++;
> + enc->output.length += out_len_B;
> + output_head = output = enc->output.data;
> + mbuf_append(output_head, output, out_len_B);
> + }
> +
> +#ifdef RTE_LIBRTE_BBDEV_DEBUG
> + rte_memdump(stderr, "FCW", &desc->req.fcw_le,
> + sizeof(desc->req.fcw_le) - 8);
> + rte_memdump(stderr, "Req Desc.", desc, sizeof(*desc));
> +#endif
> +
> +}
> +
> +/* Enqueue one encode operations for ACC200 device in TB mode.
> + * returns the number of descs used
> + */
> +static inline int
> +enqueue_ldpc_enc_one_op_tb(struct acc_queue *q, struct rte_bbdev_enc_op *op,
> + uint16_t enq_descs, uint8_t cbs_in_tb)
> +{
> + uint8_t num_a, num_b;
> + uint16_t desc_idx, input_len_B, return_descs;
> + uint8_t r = op->ldpc_enc.tb_params.r;
> + uint8_t cab = op->ldpc_enc.tb_params.cab;
> + union acc_dma_desc *desc;
> + uint16_t init_enq_descs = enq_descs;
> + uint32_t in_offset = 0, out_offset = 0;
> +
> + input_len_B = ((op->ldpc_enc.basegraph == 1 ? 22 : 10) * op->ldpc_enc.z_c) >> 3;
> +
> + if (check_bit(op->ldpc_enc.op_flags, RTE_BBDEV_LDPC_CRC_24B_ATTACH))
> + input_len_B -= 3;
> +
> + if (r < cab) {
> + num_a = cab - r;
> + num_b = cbs_in_tb - cab;
> + } else {
> + num_a = 0;
> + num_b = cbs_in_tb - r;
> + }
> +
> + while (num_a > 0) {
> + uint32_t e = op->ldpc_enc.tb_params.ea;
> + uint32_t out_len_B = (e + 7) >> 3;
> + uint8_t enq = RTE_MIN(num_a, ACC_MUX_5GDL_DESC);
> + num_a -= enq;
> + enqueue_ldpc_enc_part_tb(q, op, enq_descs, enq, e, input_len_B,
> + out_len_B, &in_offset, &out_offset);
> + enq_descs++;
> + }
> + while (num_b > 0) {
> + uint32_t e = op->ldpc_enc.tb_params.eb;
> + uint32_t out_len_B = (e + 7) >> 3;
> + uint8_t enq = RTE_MIN(num_b, ACC_MUX_5GDL_DESC);
> + num_b -= enq;
> + enqueue_ldpc_enc_part_tb(q, op, enq_descs, enq, e, input_len_B,
> + out_len_B, &in_offset, &out_offset);
> + enq_descs++;
> + }
> +
> + return_descs = enq_descs - init_enq_descs;
> + /* Keep total number of CBs in first TB */
> + desc_idx = ((q->sw_ring_head + init_enq_descs)
> + & q->sw_ring_wrap_mask);
> + desc = q->ring_addr + desc_idx;
> + desc->req.cbs_in_tb = return_descs; /** Actual number of descriptors */
> + desc->req.op_addr = op;
> +
> + /* Set SDone on last CB descriptor for TB mode. */
> + desc_idx = ((q->sw_ring_head + enq_descs - 1)
> + & q->sw_ring_wrap_mask);
> + desc = q->ring_addr + desc_idx;
> + desc->req.sdone_enable = 1;
> + desc->req.irq_enable = q->irq_enable;
> + desc->req.op_addr = op;
> + return return_descs;
> +}
> +
> +/** Enqueue one decode operations for ACC200 device in CB mode */
> +static inline int
> +enqueue_ldpc_dec_one_op_cb(struct acc_queue *q, struct rte_bbdev_dec_op *op,
> + uint16_t total_enqueued_cbs, bool same_op)
> +{
> + int ret, hq_len;
> + union acc_dma_desc *desc;
> + uint16_t desc_idx;
> + struct rte_mbuf *input, *h_output_head, *h_output;
> + uint32_t in_offset, h_out_offset, mbuf_total_left, h_out_length = 0;
> + union acc_harq_layout_data *harq_layout;
> +
> + if (op->ldpc_dec.cb_params.e == 0)
> + return -EINVAL;
> +
> + desc_idx = ((q->sw_ring_head + total_enqueued_cbs)
> + & q->sw_ring_wrap_mask);
> + desc = q->ring_addr + desc_idx;
> +
> + input = op->ldpc_dec.input.data;
> + h_output_head = h_output = op->ldpc_dec.hard_output.data;
> + in_offset = op->ldpc_dec.input.offset;
> + h_out_offset = op->ldpc_dec.hard_output.offset;
> + mbuf_total_left = op->ldpc_dec.input.length;
> + harq_layout = q->d->harq_layout;
> +
> + if (same_op) {
> + union acc_dma_desc *prev_desc;
> + desc_idx = ((q->sw_ring_head + total_enqueued_cbs - 1)
> + & q->sw_ring_wrap_mask);
> + prev_desc = q->ring_addr + desc_idx;
> + uint8_t *prev_ptr = (uint8_t *) prev_desc;
> + uint8_t *new_ptr = (uint8_t *) desc;
> + /* Copy first 4 words and BDESCs */
> + rte_memcpy(new_ptr, prev_ptr, ACC_5GUL_SIZE_0);
> + rte_memcpy(new_ptr + ACC_5GUL_OFFSET_0,
> + prev_ptr + ACC_5GUL_OFFSET_0,
> + ACC_5GUL_SIZE_1);
> + desc->req.op_addr = prev_desc->req.op_addr;
> + /* Copy FCW */
> + rte_memcpy(new_ptr + ACC_DESC_FCW_OFFSET,
> + prev_ptr + ACC_DESC_FCW_OFFSET,
> + ACC_FCW_LD_BLEN);
> + acc200_dma_desc_ld_update(op, &desc->req, input, h_output,
> + &in_offset, &h_out_offset,
> + &h_out_length, harq_layout);
> + } else {
> + struct acc_fcw_ld *fcw;
> + uint32_t seg_total_left;
> + fcw = &desc->req.fcw_ld;
> + acc200_fcw_ld_fill(op, fcw, harq_layout);
> +
> + /* Special handling when using mbuf or not */
> + if (check_bit(op->ldpc_dec.op_flags,
> + RTE_BBDEV_LDPC_DEC_SCATTER_GATHER))
> + seg_total_left = rte_pktmbuf_data_len(input)
> + - in_offset;
> + else
> + seg_total_left = fcw->rm_e;
> +
> + ret = acc200_dma_desc_ld_fill(op, &desc->req, &input, h_output,
> + &in_offset, &h_out_offset,
> + &h_out_length, &mbuf_total_left,
> + &seg_total_left, fcw);
> + if (unlikely(ret < 0))
> + return ret;
> + }
> +
> + /* Hard output */
> + mbuf_append(h_output_head, h_output, h_out_length);
> + if (op->ldpc_dec.harq_combined_output.length > 0) {
> + /* Push the HARQ output into host memory */
> + struct rte_mbuf *hq_output_head, *hq_output;
> + hq_output_head = op->ldpc_dec.harq_combined_output.data;
> + hq_output = op->ldpc_dec.harq_combined_output.data;
> + hq_len = op->ldpc_dec.harq_combined_output.length;
> + if (unlikely(!mbuf_append(hq_output_head, hq_output,
> + hq_len))) {
> + rte_bbdev_log(ERR, "HARQ output mbuf issue %d %d\n",
> + hq_output->buf_len,
> + hq_len);
> + return -1;
> + }
> + }
> +
> +#ifdef RTE_LIBRTE_BBDEV_DEBUG
> + rte_memdump(stderr, "FCW", &desc->req.fcw_ld,
> + sizeof(desc->req.fcw_ld) - 8);
> + rte_memdump(stderr, "Req Desc.", desc, sizeof(*desc));
> +#endif
> +
> + /* One CB (one op) was successfully prepared to enqueue */
> + return 1;
> +}
> +
> +
> +/* Enqueue one decode operations for ACC200 device in TB mode */
> +static inline int
> +enqueue_ldpc_dec_one_op_tb(struct acc_queue *q, struct rte_bbdev_dec_op *op,
> + uint16_t total_enqueued_cbs, uint8_t cbs_in_tb)
> +{
> + union acc_dma_desc *desc = NULL;
> + union acc_dma_desc *desc_first = NULL;
> + int ret;
> + uint8_t r, c;
> + uint32_t in_offset, h_out_offset,
> + h_out_length, mbuf_total_left, seg_total_left;
> + struct rte_mbuf *input, *h_output_head, *h_output;
> + uint16_t current_enqueued_cbs = 0;
> + uint16_t sys_cols, trail_len = 0;
> +
> + uint16_t desc_idx = ((q->sw_ring_head + total_enqueued_cbs)
> + & q->sw_ring_wrap_mask);
> + desc = q->ring_addr + desc_idx;
> + desc_first = desc;
> + uint64_t fcw_offset = (desc_idx << 8) + ACC_DESC_FCW_OFFSET;
> + union acc_harq_layout_data *harq_layout = q->d->harq_layout;
> + acc200_fcw_ld_fill(op, &desc->req.fcw_ld, harq_layout);
> +
> + input = op->ldpc_dec.input.data;
> + h_output_head = h_output = op->ldpc_dec.hard_output.data;
> + in_offset = op->ldpc_dec.input.offset;
> + h_out_offset = op->ldpc_dec.hard_output.offset;
> + h_out_length = 0;
> + mbuf_total_left = op->ldpc_dec.input.length;
> + c = op->ldpc_dec.tb_params.c;
> + r = op->ldpc_dec.tb_params.r;
> + if (check_bit(op->ldpc_dec.op_flags,
> + RTE_BBDEV_LDPC_CRC_TYPE_24A_CHECK)) {
> + sys_cols = (op->ldpc_dec.basegraph == 1) ? 22 : 10;
> + trail_len = sys_cols * op->ldpc_dec.z_c -
> + op->ldpc_dec.n_filler - 24;
> + }
> +
> + while (mbuf_total_left > 0 && r < c) {
> + if (check_bit(op->ldpc_dec.op_flags,
> + RTE_BBDEV_LDPC_DEC_SCATTER_GATHER))
> + seg_total_left = rte_pktmbuf_data_len(input)
> + - in_offset;
> + else
> + seg_total_left = op->ldpc_dec.input.length;
> + /* Set up DMA descriptor */
> + desc_idx = ((q->sw_ring_head + total_enqueued_cbs)
> + & q->sw_ring_wrap_mask);
> + desc = q->ring_addr + desc_idx;
> + fcw_offset = (desc_idx << 8) + ACC_DESC_FCW_OFFSET;
> + desc->req.data_ptrs[0].address = q->ring_addr_iova +
> + fcw_offset;
> + desc->req.data_ptrs[0].blen = ACC_FCW_LD_BLEN;
> + rte_memcpy(&desc->req.fcw_ld, &desc_first->req.fcw_ld,
> + ACC_FCW_LD_BLEN);
> + desc->req.fcw_ld.tb_trailer_size = (c - r - 1) * trail_len;
> +
> + ret = acc200_dma_desc_ld_fill(op, &desc->req, &input,
> + h_output, &in_offset, &h_out_offset,
> + &h_out_length,
> + &mbuf_total_left, &seg_total_left,
> + &desc->req.fcw_ld);
> +
> + if (unlikely(ret < 0))
> + return ret;
> +
> + /* Hard output */
> + mbuf_append(h_output_head, h_output, h_out_length);
> +
> + /* Set total number of CBs in TB */
> + desc->req.cbs_in_tb = cbs_in_tb;
> +#ifdef RTE_LIBRTE_BBDEV_DEBUG
> + rte_memdump(stderr, "FCW", &desc->req.fcw_td,
> + sizeof(desc->req.fcw_td) - 8);
> + rte_memdump(stderr, "Req Desc.", desc, sizeof(*desc));
> +#endif
> + if (check_bit(op->ldpc_dec.op_flags,
> + RTE_BBDEV_LDPC_DEC_SCATTER_GATHER)
> + && (seg_total_left == 0)) {
> + /* Go to the next mbuf */
> + input = input->next;
> + in_offset = 0;
> + h_output = h_output->next;
> + h_out_offset = 0;
> + }
> + total_enqueued_cbs++;
> + current_enqueued_cbs++;
> + r++;
> + }
> +
> +#ifdef RTE_LIBRTE_BBDEV_DEBUG
> + if (check_mbuf_total_left(mbuf_total_left) != 0)
> + return -EINVAL;
> +#endif
> + /* Set SDone on last CB descriptor for TB mode */
> + desc->req.sdone_enable = 1;
> + desc->req.irq_enable = q->irq_enable;
> +
> + return current_enqueued_cbs;
> +}
> +
> +/** Enqueue encode operations for ACC200 device in CB mode. */
> +static inline uint16_t
> +acc200_enqueue_ldpc_enc_cb(struct rte_bbdev_queue_data *q_data,
> + struct rte_bbdev_enc_op **ops, uint16_t num)
> +{
> + struct acc_queue *q = q_data->queue_private;
> + int32_t avail = acc_ring_avail_enq(q);
> + uint16_t i = 0;
> + union acc_dma_desc *desc;
> + int ret, desc_idx = 0;
> + int16_t enq, left = num;
> +
> + while (left > 0) {
> + if (unlikely(avail < 1)) {
> + acc_enqueue_ring_full(q_data);
> + break;
> + }
> + avail--;
> + enq = RTE_MIN(left, ACC_MUX_5GDL_DESC);
> + enq = check_mux(&ops[i], enq);
> + ret = enqueue_ldpc_enc_n_op_cb(q, &ops[i], desc_idx, enq);
> + if (ret < 0) {
> + acc_enqueue_invalid(q_data);
> + break;
> + }
> + i += enq;
> + desc_idx++;
> + left = num - i;
> + }
> +
> + if (unlikely(i == 0))
> + return 0; /* Nothing to enqueue */
> +
> + /* Set SDone in last CB in enqueued ops for CB mode*/
> + desc = q->ring_addr + ((q->sw_ring_head + desc_idx - 1)
> + & q->sw_ring_wrap_mask);
> + desc->req.sdone_enable = 1;
> + desc->req.irq_enable = q->irq_enable;
> +
> + acc_dma_enqueue(q, desc_idx, &q_data->queue_stats);
> +
> + /* Update stats */
> + q_data->queue_stats.enqueued_count += i;
> + q_data->queue_stats.enqueue_err_count += num - i;
> +
> + return i;
> +}
> +
> +/* Enqueue LDPC encode operations for ACC200 device in TB mode. */
> +static uint16_t
> +acc200_enqueue_ldpc_enc_tb(struct rte_bbdev_queue_data *q_data,
> + struct rte_bbdev_enc_op **ops, uint16_t num)
> +{
> + struct acc_queue *q = q_data->queue_private;
> + int32_t avail = acc_ring_avail_enq(q);
> + uint16_t i, enqueued_descs = 0;
> + uint8_t cbs_in_tb;
> + int descs_used;
> +
> + for (i = 0; i < num; ++i) {
> + cbs_in_tb = get_num_cbs_in_tb_ldpc_enc(&ops[i]->ldpc_enc);
> + /* Check if there are available space for further processing */
> + if (unlikely((avail - cbs_in_tb < 0) || (cbs_in_tb == 0))) {
> + acc_enqueue_ring_full(q_data);
> + break;
> + }
> +
> + descs_used = enqueue_ldpc_enc_one_op_tb(q, ops[i],
> + enqueued_descs, cbs_in_tb);
> + if (descs_used < 0) {
> + acc_enqueue_invalid(q_data);
> + break;
> + }
> + enqueued_descs += descs_used;
> + avail -= descs_used;
> + }
> + if (unlikely(enqueued_descs == 0))
> + return 0; /* Nothing to enqueue */
> +
> + acc_dma_enqueue(q, enqueued_descs, &q_data->queue_stats);
> +
> + /* Update stats */
> + q_data->queue_stats.enqueued_count += i;
> + q_data->queue_stats.enqueue_err_count += num - i;
> +
> + return i;
> +}
> +
> +/* Enqueue encode operations for ACC200 device. */
> +static uint16_t
> +acc200_enqueue_ldpc_enc(struct rte_bbdev_queue_data *q_data,
> + struct rte_bbdev_enc_op **ops, uint16_t num)
> +{
> + int32_t aq_avail = acc_aq_avail(q_data, num);
> + if (unlikely((aq_avail <= 0) || (num == 0)))
> + return 0;
> + if (ops[0]->ldpc_enc.code_block_mode == RTE_BBDEV_TRANSPORT_BLOCK)
> + return acc200_enqueue_ldpc_enc_tb(q_data, ops, num);
> + else
> + return acc200_enqueue_ldpc_enc_cb(q_data, ops, num);
> +}
> +
> +/* Enqueue decode operations for ACC200 device in TB mode */
> +static uint16_t
> +acc200_enqueue_ldpc_dec_tb(struct rte_bbdev_queue_data *q_data,
> + struct rte_bbdev_dec_op **ops, uint16_t num)
> +{
> + struct acc_queue *q = q_data->queue_private;
> + int32_t avail = acc_ring_avail_enq(q);
> + uint16_t i, enqueued_cbs = 0;
> + uint8_t cbs_in_tb;
> + int ret;
> +
> + for (i = 0; i < num; ++i) {
> + cbs_in_tb = get_num_cbs_in_tb_ldpc_dec(&ops[i]->ldpc_dec);
> + /* Check if there are available space for further processing */
> + if (unlikely((avail - cbs_in_tb < 0) ||
> + (cbs_in_tb == 0)))
> + break;
> + avail -= cbs_in_tb;
> +
> + ret = enqueue_ldpc_dec_one_op_tb(q, ops[i],
> + enqueued_cbs, cbs_in_tb);
> + if (ret <= 0)
> + break;
> + enqueued_cbs += ret;
> + }
> +
> + acc_dma_enqueue(q, enqueued_cbs, &q_data->queue_stats);
> +
> + /* Update stats */
> + q_data->queue_stats.enqueued_count += i;
> + q_data->queue_stats.enqueue_err_count += num - i;
> + return i;
> +}
> +
> +/* Enqueue decode operations for ACC200 device in CB mode */
> +static uint16_t
> +acc200_enqueue_ldpc_dec_cb(struct rte_bbdev_queue_data *q_data,
> + struct rte_bbdev_dec_op **ops, uint16_t num)
> +{
> + struct acc_queue *q = q_data->queue_private;
> + int32_t avail = acc_ring_avail_enq(q);
> + uint16_t i;
> + union acc_dma_desc *desc;
> + int ret;
> + bool same_op = false;
> +
> + for (i = 0; i < num; ++i) {
> + /* Check if there are available space for further processing */
> + if (unlikely(avail < 1)) {
> + acc_enqueue_ring_full(q_data);
> + break;
> + }
> + avail -= 1;
> +
> + rte_bbdev_log(INFO, "Op %d %d %d %d %d %d %d %d %d %d %d %d\n",
> + i, ops[i]->ldpc_dec.op_flags, ops[i]->ldpc_dec.rv_index,
> + ops[i]->ldpc_dec.iter_max, ops[i]->ldpc_dec.iter_count,
> + ops[i]->ldpc_dec.basegraph, ops[i]->ldpc_dec.z_c,
> + ops[i]->ldpc_dec.n_cb, ops[i]->ldpc_dec.q_m,
> + ops[i]->ldpc_dec.n_filler, ops[i]->ldpc_dec.cb_params.e,
> + same_op);
> + ret = enqueue_ldpc_dec_one_op_cb(q, ops[i], i, same_op);
> + if (ret < 0) {
> + acc_enqueue_invalid(q_data);
> + break;
> + }
> + }
> +
> + if (unlikely(i == 0))
> + return 0; /* Nothing to enqueue */
> +
> + /* Set SDone in last CB in enqueued ops for CB mode*/
> + desc = q->ring_addr + ((q->sw_ring_head + i - 1) & q->sw_ring_wrap_mask);
> + desc->req.sdone_enable = 1;
> + desc->req.irq_enable = q->irq_enable;
> +
> + acc_dma_enqueue(q, i, &q_data->queue_stats);
> +
> + /* Update stats */
> + q_data->queue_stats.enqueued_count += i;
> + q_data->queue_stats.enqueue_err_count += num - i;
> + return i;
> +}
> +
> +/* Enqueue decode operations for ACC200 device. */
> +static uint16_t
> +acc200_enqueue_ldpc_dec(struct rte_bbdev_queue_data *q_data,
> + struct rte_bbdev_dec_op **ops, uint16_t num)
> +{
> + int32_t aq_avail = acc_aq_avail(q_data, num);
> + if (unlikely((aq_avail <= 0) || (num == 0)))
> + return 0;
> + if (ops[0]->ldpc_dec.code_block_mode == RTE_BBDEV_TRANSPORT_BLOCK)
> + return acc200_enqueue_ldpc_dec_tb(q_data, ops, num);
> + else
> + return acc200_enqueue_ldpc_dec_cb(q_data, ops, num);
> +}
> +
> +
> +/* Dequeue one encode operations from ACC200 device in CB mode
> + */
> +static inline int
> +dequeue_enc_one_op_cb(struct acc_queue *q, struct rte_bbdev_enc_op **ref_op,
> + uint16_t *dequeued_ops, uint32_t *aq_dequeued,
> + uint16_t *dequeued_descs)
> +{
> + union acc_dma_desc *desc, atom_desc;
> + union acc_dma_rsp_desc rsp;
> + struct rte_bbdev_enc_op *op;
> + int i;
> + struct acc_ptrs *context_ptrs;
> + int desc_idx = ((q->sw_ring_tail + *dequeued_descs)
> + & q->sw_ring_wrap_mask);
> +
> + desc = q->ring_addr + desc_idx;
> + atom_desc.atom_hdr = __atomic_load_n((uint64_t *)desc,
> + __ATOMIC_RELAXED);
> +
> + /* Check fdone bit */
> + if (!(atom_desc.rsp.val & ACC_FDONE))
> + return -1;
> +
> + rsp.val = atom_desc.rsp.val;
> + rte_bbdev_log_debug("Resp. desc %p: %x", desc, rsp.val);
> +
> + /* Dequeue */
> + op = desc->req.op_addr;
> +
> + /* Clearing status, it will be set based on response */
> + op->status = 0;
> +
> + op->status |= ((rsp.input_err)
> + ? (1 << RTE_BBDEV_DATA_ERROR) : 0);
> + op->status |= ((rsp.dma_err) ? (1 << RTE_BBDEV_DRV_ERROR) : 0);
> + op->status |= ((rsp.fcw_err) ? (1 << RTE_BBDEV_DRV_ERROR) : 0);
> +
> + if (desc->req.last_desc_in_batch) {
> + (*aq_dequeued)++;
> + desc->req.last_desc_in_batch = 0;
> + }
> + desc->rsp.val = ACC_DMA_DESC_TYPE;
> + desc->rsp.add_info_0 = 0; /*Reserved bits */
> + desc->rsp.add_info_1 = 0; /*Reserved bits */
> +
> + ref_op[0] = op;
> + context_ptrs = q->companion_ring_addr + desc_idx;
> + for (i = 1 ; i < desc->req.numCBs; i++)
> + ref_op[i] = context_ptrs->ptr[i].op_addr;
> +
> + /* One op was successfully dequeued */
> + (*dequeued_descs)++;
> + *dequeued_ops += desc->req.numCBs;
> + return desc->req.numCBs;
> +}
> +
> +/* Dequeue one LDPC encode operations from ACC200 device in TB mode
> + * That operation may cover multiple descriptors
> + */
> +static inline int
> +dequeue_enc_one_op_tb(struct acc_queue *q, struct rte_bbdev_enc_op **ref_op,
> + uint16_t *dequeued_ops, uint32_t *aq_dequeued,
> + uint16_t *dequeued_descs)
> +{
> + union acc_dma_desc *desc, *last_desc, atom_desc;
> + union acc_dma_rsp_desc rsp;
> + struct rte_bbdev_enc_op *op;
> + uint8_t i = 0;
> + uint16_t current_dequeued_descs = 0, descs_in_tb;
> +
> + desc = q->ring_addr + ((q->sw_ring_tail + *dequeued_descs)
> + & q->sw_ring_wrap_mask);
> + atom_desc.atom_hdr = __atomic_load_n((uint64_t *)desc,
> + __ATOMIC_RELAXED);
> +
> + /* Check fdone bit */
> + if (!(atom_desc.rsp.val & ACC_FDONE))
> + return -1;
> +
> + /* Get number of CBs in dequeued TB */
> + descs_in_tb = desc->req.cbs_in_tb;
> + /* Get last CB */
> + last_desc = q->ring_addr + ((q->sw_ring_tail
> + + *dequeued_descs + descs_in_tb - 1)
> + & q->sw_ring_wrap_mask);
> + /* Check if last CB in TB is ready to dequeue (and thus
> + * the whole TB) - checking sdone bit. If not return.
> + */
> + atom_desc.atom_hdr = __atomic_load_n((uint64_t *)last_desc,
> + __ATOMIC_RELAXED);
> + if (!(atom_desc.rsp.val & ACC_SDONE))
> + return -1;
> +
> + /* Dequeue */
> + op = desc->req.op_addr;
> +
> + /* Clearing status, it will be set based on response */
> + op->status = 0;
> +
> + while (i < descs_in_tb) {
> + desc = q->ring_addr + ((q->sw_ring_tail
> + + *dequeued_descs)
> + & q->sw_ring_wrap_mask);
> + atom_desc.atom_hdr = __atomic_load_n((uint64_t *)desc,
> + __ATOMIC_RELAXED);
> + rsp.val = atom_desc.rsp.val;
> + rte_bbdev_log_debug("Resp. desc %p: %x", desc,
> + rsp.val);
> +
> + op->status |= ((rsp.input_err)
> + ? (1 << RTE_BBDEV_DATA_ERROR) : 0);
> + op->status |= ((rsp.dma_err) ? (1 << RTE_BBDEV_DRV_ERROR) : 0);
> + op->status |= ((rsp.fcw_err) ? (1 << RTE_BBDEV_DRV_ERROR) : 0);
> +
> + if (desc->req.last_desc_in_batch) {
> + (*aq_dequeued)++;
> + desc->req.last_desc_in_batch = 0;
> + }
> + desc->rsp.val = ACC_DMA_DESC_TYPE;
> + desc->rsp.add_info_0 = 0;
> + desc->rsp.add_info_1 = 0;
> + (*dequeued_descs)++;
> + current_dequeued_descs++;
> + i++;
> + }
> +
> + *ref_op = op;
> + (*dequeued_ops)++;
> + return current_dequeued_descs;
> +}
> +
> +/* Dequeue one decode operation from ACC200 device in CB mode */
> +static inline int
> +dequeue_dec_one_op_cb(struct rte_bbdev_queue_data *q_data,
> + struct acc_queue *q, struct rte_bbdev_dec_op **ref_op,
> + uint16_t dequeued_cbs, uint32_t *aq_dequeued)
> +{
> + union acc_dma_desc *desc, atom_desc;
> + union acc_dma_rsp_desc rsp;
> + struct rte_bbdev_dec_op *op;
> +
> + desc = q->ring_addr + ((q->sw_ring_tail + dequeued_cbs)
> + & q->sw_ring_wrap_mask);
> + atom_desc.atom_hdr = __atomic_load_n((uint64_t *)desc,
> + __ATOMIC_RELAXED);
> +
> + /* Check fdone bit */
> + if (!(atom_desc.rsp.val & ACC_FDONE))
> + return -1;
> +
> + rsp.val = atom_desc.rsp.val;
> + rte_bbdev_log_debug("Resp. desc %p: %x\n", desc, rsp.val);
> +
> + /* Dequeue */
> + op = desc->req.op_addr;
> +
> + /* Clearing status, it will be set based on response */
> + op->status = 0;
> + op->status |= ((rsp.input_err)
> + ? (1 << RTE_BBDEV_DATA_ERROR) : 0);
> + op->status |= ((rsp.dma_err) ? (1 << RTE_BBDEV_DRV_ERROR) : 0);
> + op->status |= ((rsp.fcw_err) ? (1 << RTE_BBDEV_DRV_ERROR) : 0);
> + if (op->status != 0) {
> + /* These errors are not expected */
> + q_data->queue_stats.dequeue_err_count++;
> + }
> +
> + /* CRC invalid if error exists */
> + if (!op->status)
> + op->status |= rsp.crc_status << RTE_BBDEV_CRC_ERROR;
> + op->turbo_dec.iter_count = (uint8_t) rsp.iter_cnt;
> + /* Check if this is the last desc in batch (Atomic Queue) */
> + if (desc->req.last_desc_in_batch) {
> + (*aq_dequeued)++;
> + desc->req.last_desc_in_batch = 0;
> + }
> + desc->rsp.val = ACC_DMA_DESC_TYPE;
> + desc->rsp.add_info_0 = 0;
> + desc->rsp.add_info_1 = 0;
> + *ref_op = op;
> +
> + /* One CB (op) was successfully dequeued */
> + return 1;
> +}
> +
> +/* Dequeue one decode operations from ACC200 device in CB mode */
> +static inline int
> +dequeue_ldpc_dec_one_op_cb(struct rte_bbdev_queue_data *q_data,
> + struct acc_queue *q, struct rte_bbdev_dec_op **ref_op,
> + uint16_t dequeued_cbs, uint32_t *aq_dequeued)
> +{
> + union acc_dma_desc *desc, atom_desc;
> + union acc_dma_rsp_desc rsp;
> + struct rte_bbdev_dec_op *op;
> +
> + desc = q->ring_addr + ((q->sw_ring_tail + dequeued_cbs)
> + & q->sw_ring_wrap_mask);
> + atom_desc.atom_hdr = __atomic_load_n((uint64_t *)desc,
> + __ATOMIC_RELAXED);
> +
> + /* Check fdone bit */
> + if (!(atom_desc.rsp.val & ACC_FDONE))
> + return -1;
> +
> + rsp.val = atom_desc.rsp.val;
> + rte_bbdev_log_debug("Resp. desc %p: %x %x %x\n", desc,
> + rsp.val, desc->rsp.add_info_0,
> + desc->rsp.add_info_1);
> +
> + /* Dequeue */
> + op = desc->req.op_addr;
> +
> + /* Clearing status, it will be set based on response */
> + op->status = 0;
> + op->status |= rsp.input_err << RTE_BBDEV_DATA_ERROR;
> + op->status |= rsp.dma_err << RTE_BBDEV_DRV_ERROR;
> + op->status |= rsp.fcw_err << RTE_BBDEV_DRV_ERROR;
> + if (op->status != 0)
> + q_data->queue_stats.dequeue_err_count++;
> +
> + op->status |= rsp.crc_status << RTE_BBDEV_CRC_ERROR;
> + if (op->ldpc_dec.hard_output.length > 0 && !rsp.synd_ok)
> + op->status |= 1 << RTE_BBDEV_SYNDROME_ERROR;
> +
> + if (check_bit(op->ldpc_dec.op_flags,
> + RTE_BBDEV_LDPC_CRC_TYPE_24A_CHECK) ||
> + check_bit(op->ldpc_dec.op_flags,
> + RTE_BBDEV_LDPC_CRC_TYPE_16_CHECK)) {
> + if (desc->rsp.add_info_1 != 0)
> + op->status |= 1 << RTE_BBDEV_CRC_ERROR;
> + }
> +
> + op->ldpc_dec.iter_count = (uint8_t) rsp.iter_cnt;
> +
> + /* Check if this is the last desc in batch (Atomic Queue) */
> + if (desc->req.last_desc_in_batch) {
> + (*aq_dequeued)++;
> + desc->req.last_desc_in_batch = 0;
> + }
> +
> + desc->rsp.val = ACC_DMA_DESC_TYPE;
> + desc->rsp.add_info_0 = 0;
> + desc->rsp.add_info_1 = 0;
> +
> + *ref_op = op;
> +
> + /* One CB (op) was successfully dequeued */
> + return 1;
> +}
> +
> +/* Dequeue one decode operations from ACC200 device in TB mode. */
> +static inline int
> +dequeue_dec_one_op_tb(struct acc_queue *q, struct rte_bbdev_dec_op **ref_op,
> + uint16_t dequeued_cbs, uint32_t *aq_dequeued)
> +{
> + union acc_dma_desc *desc, *last_desc, atom_desc;
> + union acc_dma_rsp_desc rsp;
> + struct rte_bbdev_dec_op *op;
> + uint8_t cbs_in_tb = 1, cb_idx = 0;
> + uint32_t tb_crc_check = 0;
> +
> + desc = q->ring_addr + ((q->sw_ring_tail + dequeued_cbs)
> + & q->sw_ring_wrap_mask);
> + atom_desc.atom_hdr = __atomic_load_n((uint64_t *)desc,
> + __ATOMIC_RELAXED);
> +
> + /* Check fdone bit */
> + if (!(atom_desc.rsp.val & ACC_FDONE))
> + return -1;
> +
> + /* Dequeue */
> + op = desc->req.op_addr;
> +
> + /* Get number of CBs in dequeued TB */
> + cbs_in_tb = desc->req.cbs_in_tb;
> + /* Get last CB */
> + last_desc = q->ring_addr + ((q->sw_ring_tail
> + + dequeued_cbs + cbs_in_tb - 1)
> + & q->sw_ring_wrap_mask);
> + /* Check if last CB in TB is ready to dequeue (and thus
> + * the whole TB) - checking sdone bit. If not return.
> + */
> + atom_desc.atom_hdr = __atomic_load_n((uint64_t *)last_desc,
> + __ATOMIC_RELAXED);
> + if (!(atom_desc.rsp.val & ACC_SDONE))
> + return -1;
> +
> + /* Clearing status, it will be set based on response */
> + op->status = 0;
> +
> + /* Read remaining CBs if exists */
> + while (cb_idx < cbs_in_tb) {
> + desc = q->ring_addr + ((q->sw_ring_tail + dequeued_cbs)
> + & q->sw_ring_wrap_mask);
> + atom_desc.atom_hdr = __atomic_load_n((uint64_t *)desc,
> + __ATOMIC_RELAXED);
> + rsp.val = atom_desc.rsp.val;
> + rte_bbdev_log_debug("Resp. desc %p: %x %x %x", desc,
> + rsp.val, desc->rsp.add_info_0,
> + desc->rsp.add_info_1);
> +
> + op->status |= ((rsp.input_err)
> + ? (1 << RTE_BBDEV_DATA_ERROR) : 0);
> + op->status |= ((rsp.dma_err) ? (1 << RTE_BBDEV_DRV_ERROR) : 0);
> + op->status |= ((rsp.fcw_err) ? (1 << RTE_BBDEV_DRV_ERROR) : 0);
> +
> + if (check_bit(op->ldpc_dec.op_flags,
> + RTE_BBDEV_LDPC_CRC_TYPE_24A_CHECK))
> + tb_crc_check ^= desc->rsp.add_info_1;
> +
> + /* CRC invalid if error exists */
> + if (!op->status)
> + op->status |= rsp.crc_status << RTE_BBDEV_CRC_ERROR;
> + op->turbo_dec.iter_count = RTE_MAX((uint8_t) rsp.iter_cnt,
> + op->turbo_dec.iter_count);
> +
> + /* Check if this is the last desc in batch (Atomic Queue) */
> + if (desc->req.last_desc_in_batch) {
> + (*aq_dequeued)++;
> + desc->req.last_desc_in_batch = 0;
> + }
> + desc->rsp.val = ACC_DMA_DESC_TYPE;
> + desc->rsp.add_info_0 = 0;
> + desc->rsp.add_info_1 = 0;
> + dequeued_cbs++;
> + cb_idx++;
> + }
> +
> + if (check_bit(op->ldpc_dec.op_flags,
> + RTE_BBDEV_LDPC_CRC_TYPE_24A_CHECK)) {
> + rte_bbdev_log_debug("TB-CRC Check %x\n", tb_crc_check);
> + if (tb_crc_check > 0)
> + op->status |= 1 << RTE_BBDEV_CRC_ERROR;
> + }
> +
> + *ref_op = op;
> +
> + return cb_idx;
> +}
> +
> +/* Dequeue LDPC encode operations from ACC200 device. */
> +static uint16_t
> +acc200_dequeue_ldpc_enc(struct rte_bbdev_queue_data *q_data,
> + struct rte_bbdev_enc_op **ops, uint16_t num)
> +{
> + struct acc_queue *q = q_data->queue_private;
> + uint32_t avail = acc_ring_avail_deq(q);
> + uint32_t aq_dequeued = 0;
> + uint16_t i, dequeued_ops = 0, dequeued_descs = 0;
> + int ret, cbm;
> + struct rte_bbdev_enc_op *op;
> + if (avail == 0)
> + return 0;
> + op = (q->ring_addr + (q->sw_ring_tail &
> + q->sw_ring_wrap_mask))->req.op_addr;
> + cbm = op->ldpc_enc.code_block_mode;
> +
> + for (i = 0; i < avail; i++) {
> + if (cbm == RTE_BBDEV_TRANSPORT_BLOCK)
> + ret = dequeue_enc_one_op_tb(q, &ops[dequeued_ops],
> + &dequeued_ops, &aq_dequeued,
> + &dequeued_descs);
> + else
> + ret = dequeue_enc_one_op_cb(q, &ops[dequeued_ops],
> + &dequeued_ops, &aq_dequeued,
> + &dequeued_descs);
> + if (ret < 0)
> + break;
> + if (dequeued_ops >= num)
> + break;
> + }
> +
> + q->aq_dequeued += aq_dequeued;
> + q->sw_ring_tail += dequeued_descs;
> +
> + /* Update enqueue stats */
> + q_data->queue_stats.dequeued_count += dequeued_ops;
> +
> + return dequeued_ops;
> +}
> +
> +/* Dequeue decode operations from ACC200 device. */
> +static uint16_t
> +acc200_dequeue_ldpc_dec(struct rte_bbdev_queue_data *q_data,
> + struct rte_bbdev_dec_op **ops, uint16_t num)
> +{
> + struct acc_queue *q = q_data->queue_private;
> + uint16_t dequeue_num;
> + uint32_t avail = acc_ring_avail_deq(q);
> + uint32_t aq_dequeued = 0;
> + uint16_t i;
> + uint16_t dequeued_cbs = 0;
> + struct rte_bbdev_dec_op *op;
> + int ret;
> +
> + dequeue_num = RTE_MIN(avail, num);
> +
> + for (i = 0; i < dequeue_num; ++i) {
> + op = (q->ring_addr + ((q->sw_ring_tail + dequeued_cbs)
> + & q->sw_ring_wrap_mask))->req.op_addr;
> + if (op->ldpc_dec.code_block_mode == RTE_BBDEV_TRANSPORT_BLOCK)
> + ret = dequeue_dec_one_op_tb(q, &ops[i], dequeued_cbs,
> + &aq_dequeued);
> + else
> + ret = dequeue_ldpc_dec_one_op_cb(
> + q_data, q, &ops[i], dequeued_cbs,
> + &aq_dequeued);
> +
> + if (ret <= 0)
> + break;
> + dequeued_cbs += ret;
> + }
> +
> + q->aq_dequeued += aq_dequeued;
> + q->sw_ring_tail += dequeued_cbs;
> +
> + /* Update enqueue stats */
> + q_data->queue_stats.dequeued_count += i;
> +
> + return i;
> +}
> +
> /* Initialization Function */
> static void
> acc200_bbdev_init(struct rte_bbdev *dev, struct rte_pci_driver *drv)
> @@ -695,6 +2067,10 @@ acc200_bbdev_init(struct rte_bbdev *dev, struct rte_pci_driver *drv)
> struct rte_pci_device *pci_dev = RTE_DEV_TO_PCI(dev->device);
>
> dev->dev_ops = &acc200_bbdev_ops;
> + dev->enqueue_ldpc_enc_ops = acc200_enqueue_ldpc_enc;
> + dev->enqueue_ldpc_dec_ops = acc200_enqueue_ldpc_dec;
> + dev->dequeue_ldpc_enc_ops = acc200_dequeue_ldpc_enc;
> + dev->dequeue_ldpc_dec_ops = acc200_dequeue_ldpc_dec;
>
> ((struct acc_device *) dev->data->dev_private)->pf_device =
> !strcmp(drv->driver.name,
Reviewed-by: Maxime Coquelin <maxime.coquelin@redhat.com>
Thanks,
Maxime
^ permalink raw reply [flat|nested] 28+ messages in thread
* [PATCH v6 09/14] baseband/acc: add LTE processing functions
2022-09-24 0:50 From: Nicolas Chautru <nicolas.chautru@intel.com> Nicolas Chautru
` (7 preceding siblings ...)
2022-09-24 0:50 ` [PATCH v6 08/14] baseband/acc: add LDPC processing functions Nicolas Chautru
@ 2022-09-24 0:50 ` Nicolas Chautru
2022-09-27 13:43 ` Maxime Coquelin
2022-09-24 0:50 ` [PATCH v6 10/14] baseband/acc: add support for FFT operations Nicolas Chautru
` (4 subsequent siblings)
13 siblings, 1 reply; 28+ messages in thread
From: Nicolas Chautru @ 2022-09-24 0:50 UTC (permalink / raw)
To: dev, thomas
Cc: maxime.coquelin, trix, mdr, bruce.richardson, hemant.agrawal,
david.marchand, stephen, hernan.vargas, Nic Chautru
From: Nic Chautru <nicolas.chautru@intel.com>
Add functions and capability for 4G FEC
Signed-off-by: Nic Chautru <nicolas.chautru@intel.com>
---
drivers/baseband/acc/rte_acc200_pmd.c | 854 +++++++++++++++++++++++++-
1 file changed, 850 insertions(+), 4 deletions(-)
diff --git a/drivers/baseband/acc/rte_acc200_pmd.c b/drivers/baseband/acc/rte_acc200_pmd.c
index 229e5fba86..e8901c60d6 100644
--- a/drivers/baseband/acc/rte_acc200_pmd.c
+++ b/drivers/baseband/acc/rte_acc200_pmd.c
@@ -658,6 +658,46 @@ acc200_dev_info_get(struct rte_bbdev *dev,
struct acc_device *d = dev->data->dev_private;
int i;
static const struct rte_bbdev_op_cap bbdev_capabilities[] = {
+ {
+ .type = RTE_BBDEV_OP_TURBO_DEC,
+ .cap.turbo_dec = {
+ .capability_flags =
+ RTE_BBDEV_TURBO_SUBBLOCK_DEINTERLEAVE |
+ RTE_BBDEV_TURBO_CRC_TYPE_24B |
+ RTE_BBDEV_TURBO_EQUALIZER |
+ RTE_BBDEV_TURBO_SOFT_OUT_SATURATE |
+ RTE_BBDEV_TURBO_HALF_ITERATION_EVEN |
+ RTE_BBDEV_TURBO_CONTINUE_CRC_MATCH |
+ RTE_BBDEV_TURBO_SOFT_OUTPUT |
+ RTE_BBDEV_TURBO_EARLY_TERMINATION |
+ RTE_BBDEV_TURBO_NEG_LLR_1_BIT_IN |
+ RTE_BBDEV_TURBO_NEG_LLR_1_BIT_SOFT_OUT |
+ RTE_BBDEV_TURBO_MAP_DEC |
+ RTE_BBDEV_TURBO_DEC_TB_CRC_24B_KEEP |
+ RTE_BBDEV_TURBO_DEC_SCATTER_GATHER,
+ .max_llr_modulus = INT8_MAX,
+ .num_buffers_src =
+ RTE_BBDEV_TURBO_MAX_CODE_BLOCKS,
+ .num_buffers_hard_out =
+ RTE_BBDEV_TURBO_MAX_CODE_BLOCKS,
+ .num_buffers_soft_out =
+ RTE_BBDEV_TURBO_MAX_CODE_BLOCKS,
+ }
+ },
+ {
+ .type = RTE_BBDEV_OP_TURBO_ENC,
+ .cap.turbo_enc = {
+ .capability_flags =
+ RTE_BBDEV_TURBO_CRC_24B_ATTACH |
+ RTE_BBDEV_TURBO_RV_INDEX_BYPASS |
+ RTE_BBDEV_TURBO_RATE_MATCH |
+ RTE_BBDEV_TURBO_ENC_SCATTER_GATHER,
+ .num_buffers_src =
+ RTE_BBDEV_TURBO_MAX_CODE_BLOCKS,
+ .num_buffers_dst =
+ RTE_BBDEV_TURBO_MAX_CODE_BLOCKS,
+ }
+ },
{
.type = RTE_BBDEV_OP_LDPC_ENC,
.cap.ldpc_enc = {
@@ -709,15 +749,17 @@ acc200_dev_info_get(struct rte_bbdev *dev,
/* Exposed number of queues */
dev_info->num_queues[RTE_BBDEV_OP_NONE] = 0;
- dev_info->num_queues[RTE_BBDEV_OP_TURBO_DEC] = 0;
- dev_info->num_queues[RTE_BBDEV_OP_TURBO_ENC] = 0;
+ dev_info->num_queues[RTE_BBDEV_OP_TURBO_DEC] = d->acc_conf.q_ul_4g.num_aqs_per_groups *
+ d->acc_conf.q_ul_4g.num_qgroups;
+ dev_info->num_queues[RTE_BBDEV_OP_TURBO_ENC] = d->acc_conf.q_dl_4g.num_aqs_per_groups *
+ d->acc_conf.q_dl_4g.num_qgroups;
dev_info->num_queues[RTE_BBDEV_OP_LDPC_DEC] = d->acc_conf.q_ul_5g.num_aqs_per_groups *
d->acc_conf.q_ul_5g.num_qgroups;
dev_info->num_queues[RTE_BBDEV_OP_LDPC_ENC] = d->acc_conf.q_dl_5g.num_aqs_per_groups *
d->acc_conf.q_dl_5g.num_qgroups;
dev_info->num_queues[RTE_BBDEV_OP_FFT] = 0;
- dev_info->queue_priority[RTE_BBDEV_OP_TURBO_DEC] = 0;
- dev_info->queue_priority[RTE_BBDEV_OP_TURBO_ENC] = 0;
+ dev_info->queue_priority[RTE_BBDEV_OP_TURBO_DEC] = d->acc_conf.q_ul_4g.num_qgroups;
+ dev_info->queue_priority[RTE_BBDEV_OP_TURBO_ENC] = d->acc_conf.q_dl_4g.num_qgroups;
dev_info->queue_priority[RTE_BBDEV_OP_LDPC_DEC] = d->acc_conf.q_ul_5g.num_qgroups;
dev_info->queue_priority[RTE_BBDEV_OP_LDPC_ENC] = d->acc_conf.q_dl_5g.num_qgroups;
dev_info->queue_priority[RTE_BBDEV_OP_FFT] = 0;
@@ -762,6 +804,70 @@ static struct rte_pci_id pci_id_acc200_vf_map[] = {
{.device_id = 0},
};
+/* Fill in a frame control word for turbo decoding. */
+static inline void
+acc200_fcw_td_fill(const struct rte_bbdev_dec_op *op, struct acc_fcw_td *fcw)
+{
+ fcw->fcw_ver = 1;
+ fcw->num_maps = ACC_FCW_TD_AUTOMAP;
+ fcw->bypass_sb_deint = !check_bit(op->turbo_dec.op_flags,
+ RTE_BBDEV_TURBO_SUBBLOCK_DEINTERLEAVE);
+ if (op->turbo_dec.code_block_mode == RTE_BBDEV_TRANSPORT_BLOCK) {
+ /* FIXME for TB block */
+ fcw->k_pos = op->turbo_dec.tb_params.k_pos;
+ fcw->k_neg = op->turbo_dec.tb_params.k_neg;
+ } else {
+ fcw->k_pos = op->turbo_dec.cb_params.k;
+ fcw->k_neg = op->turbo_dec.cb_params.k;
+ }
+ fcw->c = 1;
+ fcw->c_neg = 1;
+ if (check_bit(op->turbo_dec.op_flags, RTE_BBDEV_TURBO_SOFT_OUTPUT)) {
+ fcw->soft_output_en = 1;
+ fcw->sw_soft_out_dis = 0;
+ fcw->sw_et_cont = check_bit(op->turbo_dec.op_flags,
+ RTE_BBDEV_TURBO_CONTINUE_CRC_MATCH);
+ fcw->sw_soft_out_saturation = check_bit(op->turbo_dec.op_flags,
+ RTE_BBDEV_TURBO_SOFT_OUT_SATURATE);
+ if (check_bit(op->turbo_dec.op_flags,
+ RTE_BBDEV_TURBO_EQUALIZER)) {
+ fcw->bypass_teq = 0;
+ fcw->ea = op->turbo_dec.cb_params.e;
+ fcw->eb = op->turbo_dec.cb_params.e;
+ if (op->turbo_dec.rv_index == 0)
+ fcw->k0_start_col = ACC_FCW_TD_RVIDX_0;
+ else if (op->turbo_dec.rv_index == 1)
+ fcw->k0_start_col = ACC_FCW_TD_RVIDX_1;
+ else if (op->turbo_dec.rv_index == 2)
+ fcw->k0_start_col = ACC_FCW_TD_RVIDX_2;
+ else
+ fcw->k0_start_col = ACC_FCW_TD_RVIDX_3;
+ } else {
+ fcw->bypass_teq = 1;
+ fcw->eb = 64; /* avoid undefined value */
+ }
+ } else {
+ fcw->soft_output_en = 0;
+ fcw->sw_soft_out_dis = 1;
+ fcw->bypass_teq = 0;
+ }
+
+ fcw->code_block_mode = 1; /* FIXME */
+ fcw->turbo_crc_type = check_bit(op->turbo_dec.op_flags,
+ RTE_BBDEV_TURBO_CRC_TYPE_24B);
+
+ fcw->ext_td_cold_reg_en = 1;
+ fcw->raw_decoder_input_on = 0;
+ fcw->max_iter = RTE_MAX((uint8_t) op->turbo_dec.iter_max, 2);
+ fcw->min_iter = 2;
+ fcw->half_iter_on = !check_bit(op->turbo_dec.op_flags,
+ RTE_BBDEV_TURBO_HALF_ITERATION_EVEN);
+
+ fcw->early_stop_en = check_bit(op->turbo_dec.op_flags,
+ RTE_BBDEV_TURBO_EARLY_TERMINATION) & !fcw->soft_output_en;
+ fcw->ext_scale = 0xF;
+}
+
/* Fill in a frame control word for LDPC decoding. */
static inline void
acc200_fcw_ld_fill(struct rte_bbdev_dec_op *op, struct acc_fcw_ld *fcw,
@@ -887,6 +993,205 @@ acc200_fcw_ld_fill(struct rte_bbdev_dec_op *op, struct acc_fcw_ld *fcw,
fcw->tb_crc_select = 1;
}
+static inline int
+acc200_dma_desc_te_fill(struct rte_bbdev_enc_op *op,
+ struct acc_dma_req_desc *desc, struct rte_mbuf **input,
+ struct rte_mbuf *output, uint32_t *in_offset,
+ uint32_t *out_offset, uint32_t *out_length,
+ uint32_t *mbuf_total_left, uint32_t *seg_total_left, uint8_t r)
+{
+ int next_triplet = 1; /* FCW already done */
+ uint32_t e, ea, eb, length;
+ uint16_t k, k_neg, k_pos;
+ uint8_t cab, c_neg;
+
+ desc->word0 = ACC_DMA_DESC_TYPE;
+ desc->word1 = 0; /**< Timestamp could be disabled */
+ desc->word2 = 0;
+ desc->word3 = 0;
+ desc->numCBs = 1;
+
+ if (op->turbo_enc.code_block_mode == RTE_BBDEV_TRANSPORT_BLOCK) {
+ ea = op->turbo_enc.tb_params.ea;
+ eb = op->turbo_enc.tb_params.eb;
+ cab = op->turbo_enc.tb_params.cab;
+ k_neg = op->turbo_enc.tb_params.k_neg;
+ k_pos = op->turbo_enc.tb_params.k_pos;
+ c_neg = op->turbo_enc.tb_params.c_neg;
+ e = (r < cab) ? ea : eb;
+ k = (r < c_neg) ? k_neg : k_pos;
+ } else {
+ e = op->turbo_enc.cb_params.e;
+ k = op->turbo_enc.cb_params.k;
+ }
+
+ if (check_bit(op->turbo_enc.op_flags, RTE_BBDEV_TURBO_CRC_24B_ATTACH))
+ length = (k - 24) >> 3;
+ else
+ length = k >> 3;
+
+ if (unlikely((*mbuf_total_left == 0) || (*mbuf_total_left < length))) {
+ rte_bbdev_log(ERR,
+ "Mismatch between mbuf length and included CB sizes: mbuf len %u, cb len %u",
+ *mbuf_total_left, length);
+ return -1;
+ }
+
+ next_triplet = acc_dma_fill_blk_type_in(desc, input, in_offset,
+ length, seg_total_left, next_triplet,
+ check_bit(op->turbo_enc.op_flags,
+ RTE_BBDEV_TURBO_ENC_SCATTER_GATHER));
+ if (unlikely(next_triplet < 0)) {
+ rte_bbdev_log(ERR,
+ "Mismatch between data to process and mbuf data length in bbdev_op: %p",
+ op);
+ return -1;
+ }
+ desc->data_ptrs[next_triplet - 1].last = 1;
+ desc->m2dlen = next_triplet;
+ *mbuf_total_left -= length;
+
+ /* Set output length */
+ if (check_bit(op->turbo_enc.op_flags, RTE_BBDEV_TURBO_RATE_MATCH))
+ /* Integer round up division by 8 */
+ *out_length = (e + 7) >> 3;
+ else
+ *out_length = (k >> 3) * 3 + 2;
+
+ next_triplet = acc_dma_fill_blk_type(desc, output, *out_offset,
+ *out_length, next_triplet, ACC_DMA_BLKID_OUT_ENC);
+ if (unlikely(next_triplet < 0)) {
+ rte_bbdev_log(ERR,
+ "Mismatch between data to process and mbuf data length in bbdev_op: %p",
+ op);
+ return -1;
+ }
+ op->turbo_enc.output.length += *out_length;
+ *out_offset += *out_length;
+ desc->data_ptrs[next_triplet - 1].last = 1;
+ desc->d2mlen = next_triplet - desc->m2dlen;
+
+ desc->op_addr = op;
+
+ return 0;
+}
+
+static inline int
+acc200_dma_desc_td_fill(struct rte_bbdev_dec_op *op,
+ struct acc_dma_req_desc *desc, struct rte_mbuf **input,
+ struct rte_mbuf *h_output, struct rte_mbuf *s_output,
+ uint32_t *in_offset, uint32_t *h_out_offset,
+ uint32_t *s_out_offset, uint32_t *h_out_length,
+ uint32_t *s_out_length, uint32_t *mbuf_total_left,
+ uint32_t *seg_total_left, uint8_t r)
+{
+ int next_triplet = 1; /* FCW already done */
+ uint16_t k;
+ uint16_t crc24_overlap = 0;
+ uint32_t e, kw;
+
+ desc->word0 = ACC_DMA_DESC_TYPE;
+ desc->word1 = 0; /**< Timestamp could be disabled */
+ desc->word2 = 0;
+ desc->word3 = 0;
+ desc->numCBs = 1;
+
+ if (op->turbo_dec.code_block_mode == RTE_BBDEV_TRANSPORT_BLOCK) {
+ k = (r < op->turbo_dec.tb_params.c_neg)
+ ? op->turbo_dec.tb_params.k_neg
+ : op->turbo_dec.tb_params.k_pos;
+ e = (r < op->turbo_dec.tb_params.cab)
+ ? op->turbo_dec.tb_params.ea
+ : op->turbo_dec.tb_params.eb;
+ } else {
+ k = op->turbo_dec.cb_params.k;
+ e = op->turbo_dec.cb_params.e;
+ }
+
+ if ((op->turbo_dec.code_block_mode == RTE_BBDEV_TRANSPORT_BLOCK)
+ && !check_bit(op->turbo_dec.op_flags,
+ RTE_BBDEV_TURBO_DEC_TB_CRC_24B_KEEP))
+ crc24_overlap = 24;
+
+ /* Calculates circular buffer size.
+ * According to 3gpp 36.212 section 5.1.4.2
+ * Kw = 3 * Kpi,
+ * where:
+ * Kpi = nCol * nRow
+ * where nCol is 32 and nRow can be calculated from:
+ * D =< nCol * nRow
+ * where D is the size of each output from turbo encoder block (k + 4).
+ */
+ kw = RTE_ALIGN_CEIL(k + 4, 32) * 3;
+
+ if (unlikely((*mbuf_total_left == 0) || (*mbuf_total_left < kw))) {
+ rte_bbdev_log(ERR,
+ "Mismatch between mbuf length and included CB sizes: mbuf len %u, cb len %u",
+ *mbuf_total_left, kw);
+ return -1;
+ }
+
+ next_triplet = acc_dma_fill_blk_type_in(desc, input, in_offset, kw,
+ seg_total_left, next_triplet,
+ check_bit(op->turbo_dec.op_flags,
+ RTE_BBDEV_TURBO_DEC_SCATTER_GATHER));
+ if (unlikely(next_triplet < 0)) {
+ rte_bbdev_log(ERR,
+ "Mismatch between data to process and mbuf data length in bbdev_op: %p",
+ op);
+ return -1;
+ }
+ desc->data_ptrs[next_triplet - 1].last = 1;
+ desc->m2dlen = next_triplet;
+ *mbuf_total_left -= kw;
+ *h_out_length = ((k - crc24_overlap) >> 3);
+ next_triplet = acc_dma_fill_blk_type(
+ desc, h_output, *h_out_offset,
+ *h_out_length, next_triplet, ACC_DMA_BLKID_OUT_HARD);
+ if (unlikely(next_triplet < 0)) {
+ rte_bbdev_log(ERR,
+ "Mismatch between data to process and mbuf data length in bbdev_op: %p",
+ op);
+ return -1;
+ }
+
+ op->turbo_dec.hard_output.length += *h_out_length;
+ *h_out_offset += *h_out_length;
+
+ /* Soft output */
+ if (check_bit(op->turbo_dec.op_flags, RTE_BBDEV_TURBO_SOFT_OUTPUT)) {
+ if (op->turbo_dec.soft_output.data == 0) {
+ rte_bbdev_log(ERR, "Soft output is not defined");
+ return -1;
+ }
+ if (check_bit(op->turbo_dec.op_flags,
+ RTE_BBDEV_TURBO_EQUALIZER))
+ *s_out_length = e;
+ else
+ *s_out_length = (k * 3) + 12;
+
+ next_triplet = acc_dma_fill_blk_type(desc, s_output,
+ *s_out_offset, *s_out_length, next_triplet,
+ ACC_DMA_BLKID_OUT_SOFT);
+ if (unlikely(next_triplet < 0)) {
+ rte_bbdev_log(ERR,
+ "Mismatch between data to process and mbuf data length in bbdev_op: %p",
+ op);
+ return -1;
+ }
+
+ op->turbo_dec.soft_output.length += *s_out_length;
+ *s_out_offset += *s_out_length;
+ }
+
+ desc->data_ptrs[next_triplet - 1].last = 1;
+ desc->d2mlen = next_triplet - desc->m2dlen;
+
+ desc->op_addr = op;
+
+ return 0;
+}
+
static inline int
acc200_dma_desc_ld_fill(struct rte_bbdev_dec_op *op,
struct acc_dma_req_desc *desc,
@@ -1059,6 +1364,49 @@ acc200_dma_desc_ld_update(struct rte_bbdev_dec_op *op,
desc->op_addr = op;
}
+/* Enqueue one encode operations for ACC200 device in CB mode */
+static inline int
+enqueue_enc_one_op_cb(struct acc_queue *q, struct rte_bbdev_enc_op *op,
+ uint16_t total_enqueued_cbs)
+{
+ union acc_dma_desc *desc = NULL;
+ int ret;
+ uint32_t in_offset, out_offset, out_length, mbuf_total_left,
+ seg_total_left;
+ struct rte_mbuf *input, *output_head, *output;
+
+ uint16_t desc_idx = ((q->sw_ring_head + total_enqueued_cbs)
+ & q->sw_ring_wrap_mask);
+ desc = q->ring_addr + desc_idx;
+ acc_fcw_te_fill(op, &desc->req.fcw_te);
+
+ input = op->turbo_enc.input.data;
+ output_head = output = op->turbo_enc.output.data;
+ in_offset = op->turbo_enc.input.offset;
+ out_offset = op->turbo_enc.output.offset;
+ out_length = 0;
+ mbuf_total_left = op->turbo_enc.input.length;
+ seg_total_left = rte_pktmbuf_data_len(op->turbo_enc.input.data)
+ - in_offset;
+
+ ret = acc200_dma_desc_te_fill(op, &desc->req, &input, output,
+ &in_offset, &out_offset, &out_length, &mbuf_total_left,
+ &seg_total_left, 0);
+
+ if (unlikely(ret < 0))
+ return ret;
+
+ mbuf_append(output_head, output, out_length);
+
+#ifdef RTE_LIBRTE_BBDEV_DEBUG
+ rte_memdump(stderr, "FCW", &desc->req.fcw_te,
+ sizeof(desc->req.fcw_te) - 8);
+ rte_memdump(stderr, "Req Desc.", desc, sizeof(*desc));
+#endif
+ /* One CB (one op) was successfully prepared to enqueue */
+ return 1;
+}
+
/* Enqueue one encode operations for ACC200 device in CB mode
* multiplexed on the same descriptor
*/
@@ -1175,6 +1523,78 @@ enqueue_ldpc_enc_part_tb(struct acc_queue *q, struct rte_bbdev_enc_op *op,
}
+/* Enqueue one encode operations for ACC200 device in TB mode. */
+static inline int
+enqueue_enc_one_op_tb(struct acc_queue *q, struct rte_bbdev_enc_op *op,
+ uint16_t total_enqueued_cbs, uint8_t cbs_in_tb)
+{
+ union acc_dma_desc *desc = NULL;
+ int ret;
+ uint8_t r, c;
+ uint32_t in_offset, out_offset, out_length, mbuf_total_left,
+ seg_total_left;
+ struct rte_mbuf *input, *output_head, *output;
+ uint16_t current_enqueued_cbs = 0;
+
+ uint16_t desc_idx = ((q->sw_ring_head + total_enqueued_cbs)
+ & q->sw_ring_wrap_mask);
+ desc = q->ring_addr + desc_idx;
+ uint64_t fcw_offset = (desc_idx << 8) + ACC_DESC_FCW_OFFSET;
+ acc_fcw_te_fill(op, &desc->req.fcw_te);
+
+ input = op->turbo_enc.input.data;
+ output_head = output = op->turbo_enc.output.data;
+ in_offset = op->turbo_enc.input.offset;
+ out_offset = op->turbo_enc.output.offset;
+ out_length = 0;
+ mbuf_total_left = op->turbo_enc.input.length;
+
+ c = op->turbo_enc.tb_params.c;
+ r = op->turbo_enc.tb_params.r;
+
+ while (mbuf_total_left > 0 && r < c) {
+ seg_total_left = rte_pktmbuf_data_len(input) - in_offset;
+ /* Set up DMA descriptor */
+ desc = q->ring_addr + ((q->sw_ring_head + total_enqueued_cbs)
+ & q->sw_ring_wrap_mask);
+ desc->req.data_ptrs[0].address = q->ring_addr_iova + fcw_offset;
+ desc->req.data_ptrs[0].blen = ACC_FCW_TE_BLEN;
+
+ ret = acc200_dma_desc_te_fill(op, &desc->req, &input, output,
+ &in_offset, &out_offset, &out_length,
+ &mbuf_total_left, &seg_total_left, r);
+ if (unlikely(ret < 0))
+ return ret;
+ mbuf_append(output_head, output, out_length);
+
+ /* Set total number of CBs in TB */
+ desc->req.cbs_in_tb = cbs_in_tb;
+#ifdef RTE_LIBRTE_BBDEV_DEBUG
+ rte_memdump(stderr, "FCW", &desc->req.fcw_te,
+ sizeof(desc->req.fcw_te) - 8);
+ rte_memdump(stderr, "Req Desc.", desc, sizeof(*desc));
+#endif
+
+ if (seg_total_left == 0) {
+ /* Go to the next mbuf */
+ input = input->next;
+ in_offset = 0;
+ output = output->next;
+ out_offset = 0;
+ }
+
+ total_enqueued_cbs++;
+ current_enqueued_cbs++;
+ r++;
+ }
+
+ /* Set SDone on last CB descriptor for TB mode. */
+ desc->req.sdone_enable = 1;
+ desc->req.irq_enable = q->irq_enable;
+
+ return current_enqueued_cbs;
+}
+
/* Enqueue one encode operations for ACC200 device in TB mode.
* returns the number of descs used
*/
@@ -1240,6 +1660,62 @@ enqueue_ldpc_enc_one_op_tb(struct acc_queue *q, struct rte_bbdev_enc_op *op,
return return_descs;
}
+/** Enqueue one decode operations for ACC200 device in CB mode */
+static inline int
+enqueue_dec_one_op_cb(struct acc_queue *q, struct rte_bbdev_dec_op *op,
+ uint16_t total_enqueued_cbs)
+{
+ union acc_dma_desc *desc = NULL;
+ int ret;
+ uint32_t in_offset, h_out_offset, s_out_offset, s_out_length,
+ h_out_length, mbuf_total_left, seg_total_left;
+ struct rte_mbuf *input, *h_output_head, *h_output,
+ *s_output_head, *s_output;
+
+ uint16_t desc_idx = ((q->sw_ring_head + total_enqueued_cbs)
+ & q->sw_ring_wrap_mask);
+ desc = q->ring_addr + desc_idx;
+ acc200_fcw_td_fill(op, &desc->req.fcw_td);
+
+ input = op->turbo_dec.input.data;
+ h_output_head = h_output = op->turbo_dec.hard_output.data;
+ s_output_head = s_output = op->turbo_dec.soft_output.data;
+ in_offset = op->turbo_dec.input.offset;
+ h_out_offset = op->turbo_dec.hard_output.offset;
+ s_out_offset = op->turbo_dec.soft_output.offset;
+ h_out_length = s_out_length = 0;
+ mbuf_total_left = op->turbo_dec.input.length;
+ seg_total_left = rte_pktmbuf_data_len(input) - in_offset;
+
+ /* Set up DMA descriptor */
+ desc = q->ring_addr + ((q->sw_ring_head + total_enqueued_cbs)
+ & q->sw_ring_wrap_mask);
+
+ ret = acc200_dma_desc_td_fill(op, &desc->req, &input, h_output,
+ s_output, &in_offset, &h_out_offset, &s_out_offset,
+ &h_out_length, &s_out_length, &mbuf_total_left,
+ &seg_total_left, 0);
+
+ if (unlikely(ret < 0))
+ return ret;
+
+ /* Hard output */
+ mbuf_append(h_output_head, h_output, h_out_length);
+
+ /* Soft output */
+ if (check_bit(op->turbo_dec.op_flags, RTE_BBDEV_TURBO_SOFT_OUTPUT))
+ mbuf_append(s_output_head, s_output, s_out_length);
+
+#ifdef RTE_LIBRTE_BBDEV_DEBUG
+ rte_memdump(stderr, "FCW", &desc->req.fcw_td,
+ sizeof(desc->req.fcw_td));
+ rte_memdump(stderr, "Req Desc.", desc, sizeof(*desc));
+#endif
+
+ /* One CB (one op) was successfully prepared to enqueue */
+ return 1;
+}
+
/** Enqueue one decode operations for ACC200 device in CB mode */
static inline int
enqueue_ldpc_dec_one_op_cb(struct acc_queue *q, struct rte_bbdev_dec_op *op,
@@ -1437,6 +1913,139 @@ enqueue_ldpc_dec_one_op_tb(struct acc_queue *q, struct rte_bbdev_dec_op *op,
return current_enqueued_cbs;
}
+/* Enqueue one decode operations for ACC200 device in TB mode */
+static inline int
+enqueue_dec_one_op_tb(struct acc_queue *q, struct rte_bbdev_dec_op *op,
+ uint16_t total_enqueued_cbs, uint8_t cbs_in_tb)
+{
+ union acc_dma_desc *desc = NULL;
+ int ret;
+ uint8_t r, c;
+ uint32_t in_offset, h_out_offset, s_out_offset, s_out_length,
+ h_out_length, mbuf_total_left, seg_total_left;
+ struct rte_mbuf *input, *h_output_head, *h_output,
+ *s_output_head, *s_output;
+ uint16_t current_enqueued_cbs = 0;
+
+ uint16_t desc_idx = ((q->sw_ring_head + total_enqueued_cbs)
+ & q->sw_ring_wrap_mask);
+ desc = q->ring_addr + desc_idx;
+ uint64_t fcw_offset = (desc_idx << 8) + ACC_DESC_FCW_OFFSET;
+ acc200_fcw_td_fill(op, &desc->req.fcw_td);
+
+ input = op->turbo_dec.input.data;
+ h_output_head = h_output = op->turbo_dec.hard_output.data;
+ s_output_head = s_output = op->turbo_dec.soft_output.data;
+ in_offset = op->turbo_dec.input.offset;
+ h_out_offset = op->turbo_dec.hard_output.offset;
+ s_out_offset = op->turbo_dec.soft_output.offset;
+ h_out_length = s_out_length = 0;
+ mbuf_total_left = op->turbo_dec.input.length;
+ c = op->turbo_dec.tb_params.c;
+ r = op->turbo_dec.tb_params.r;
+
+ while (mbuf_total_left > 0 && r < c) {
+
+ seg_total_left = rte_pktmbuf_data_len(input) - in_offset;
+
+ /* Set up DMA descriptor */
+ desc = q->ring_addr + ((q->sw_ring_head + total_enqueued_cbs)
+ & q->sw_ring_wrap_mask);
+ desc->req.data_ptrs[0].address = q->ring_addr_iova + fcw_offset;
+ desc->req.data_ptrs[0].blen = ACC_FCW_TD_BLEN;
+ ret = acc200_dma_desc_td_fill(op, &desc->req, &input,
+ h_output, s_output, &in_offset, &h_out_offset,
+ &s_out_offset, &h_out_length, &s_out_length,
+ &mbuf_total_left, &seg_total_left, r);
+
+ if (unlikely(ret < 0))
+ return ret;
+
+ /* Hard output */
+ mbuf_append(h_output_head, h_output, h_out_length);
+
+ /* Soft output */
+ if (check_bit(op->turbo_dec.op_flags,
+ RTE_BBDEV_TURBO_SOFT_OUTPUT))
+ mbuf_append(s_output_head, s_output, s_out_length);
+
+ /* Set total number of CBs in TB */
+ desc->req.cbs_in_tb = cbs_in_tb;
+#ifdef RTE_LIBRTE_BBDEV_DEBUG
+ rte_memdump(stderr, "FCW", &desc->req.fcw_td,
+ sizeof(desc->req.fcw_td) - 8);
+ rte_memdump(stderr, "Req Desc.", desc, sizeof(*desc));
+#endif
+
+ if (seg_total_left == 0) {
+ /* Go to the next mbuf */
+ input = input->next;
+ in_offset = 0;
+ h_output = h_output->next;
+ h_out_offset = 0;
+
+ if (check_bit(op->turbo_dec.op_flags,
+ RTE_BBDEV_TURBO_SOFT_OUTPUT)) {
+ s_output = s_output->next;
+ s_out_offset = 0;
+ }
+ }
+
+ total_enqueued_cbs++;
+ current_enqueued_cbs++;
+ r++;
+ }
+
+ /* Set SDone on last CB descriptor for TB mode */
+ desc->req.sdone_enable = 1;
+ desc->req.irq_enable = q->irq_enable;
+
+ return current_enqueued_cbs;
+}
+
+/* Enqueue encode operations for ACC200 device in CB mode. */
+static uint16_t
+acc200_enqueue_enc_cb(struct rte_bbdev_queue_data *q_data,
+ struct rte_bbdev_enc_op **ops, uint16_t num)
+{
+ struct acc_queue *q = q_data->queue_private;
+ int32_t avail = acc_ring_avail_enq(q);
+ uint16_t i;
+ union acc_dma_desc *desc;
+ int ret;
+
+ for (i = 0; i < num; ++i) {
+ /* Check if there are available space for further processing */
+ if (unlikely(avail - 1 < 0)) {
+ acc_enqueue_ring_full(q_data);
+ break;
+ }
+ avail -= 1;
+
+ ret = enqueue_enc_one_op_cb(q, ops[i], i);
+ if (ret < 0) {
+ acc_enqueue_invalid(q_data);
+ break;
+ }
+ }
+
+ if (unlikely(i == 0))
+ return 0; /* Nothing to enqueue */
+
+ /* Set SDone in last CB in enqueued ops for CB mode*/
+ desc = q->ring_addr + ((q->sw_ring_head + i - 1)
+ & q->sw_ring_wrap_mask);
+ desc->req.sdone_enable = 1;
+ desc->req.irq_enable = q->irq_enable;
+
+ acc_dma_enqueue(q, i, &q_data->queue_stats);
+
+ /* Update stats */
+ q_data->queue_stats.enqueued_count += i;
+ q_data->queue_stats.enqueue_err_count += num - i;
+ return i;
+}
+
/** Enqueue encode operations for ACC200 device in CB mode. */
static inline uint16_t
acc200_enqueue_ldpc_enc_cb(struct rte_bbdev_queue_data *q_data,
@@ -1485,6 +2094,45 @@ acc200_enqueue_ldpc_enc_cb(struct rte_bbdev_queue_data *q_data,
return i;
}
+/* Enqueue encode operations for ACC200 device in TB mode. */
+static uint16_t
+acc200_enqueue_enc_tb(struct rte_bbdev_queue_data *q_data,
+ struct rte_bbdev_enc_op **ops, uint16_t num)
+{
+ struct acc_queue *q = q_data->queue_private;
+ int32_t avail = acc_ring_avail_enq(q);
+ uint16_t i, enqueued_cbs = 0;
+ uint8_t cbs_in_tb;
+ int ret;
+
+ for (i = 0; i < num; ++i) {
+ cbs_in_tb = get_num_cbs_in_tb_enc(&ops[i]->turbo_enc);
+ /* Check if there are available space for further processing */
+ if (unlikely((avail - cbs_in_tb < 0) || (cbs_in_tb == 0))) {
+ acc_enqueue_ring_full(q_data);
+ break;
+ }
+ avail -= cbs_in_tb;
+
+ ret = enqueue_enc_one_op_tb(q, ops[i], enqueued_cbs, cbs_in_tb);
+ if (ret <= 0) {
+ acc_enqueue_invalid(q_data);
+ break;
+ }
+ enqueued_cbs += ret;
+ }
+ if (unlikely(enqueued_cbs == 0))
+ return 0; /* Nothing to enqueue */
+
+ acc_dma_enqueue(q, enqueued_cbs, &q_data->queue_stats);
+
+ /* Update stats */
+ q_data->queue_stats.enqueued_count += i;
+ q_data->queue_stats.enqueue_err_count += num - i;
+
+ return i;
+}
+
/* Enqueue LDPC encode operations for ACC200 device in TB mode. */
static uint16_t
acc200_enqueue_ldpc_enc_tb(struct rte_bbdev_queue_data *q_data,
@@ -1525,6 +2173,20 @@ acc200_enqueue_ldpc_enc_tb(struct rte_bbdev_queue_data *q_data,
return i;
}
+/* Enqueue encode operations for ACC200 device. */
+static uint16_t
+acc200_enqueue_enc(struct rte_bbdev_queue_data *q_data,
+ struct rte_bbdev_enc_op **ops, uint16_t num)
+{
+ int32_t aq_avail = acc_aq_avail(q_data, num);
+ if (unlikely((aq_avail <= 0) || (num == 0)))
+ return 0;
+ if (ops[0]->turbo_enc.code_block_mode == RTE_BBDEV_TRANSPORT_BLOCK)
+ return acc200_enqueue_enc_tb(q_data, ops, num);
+ else
+ return acc200_enqueue_enc_cb(q_data, ops, num);
+}
+
/* Enqueue encode operations for ACC200 device. */
static uint16_t
acc200_enqueue_ldpc_enc(struct rte_bbdev_queue_data *q_data,
@@ -1539,6 +2201,47 @@ acc200_enqueue_ldpc_enc(struct rte_bbdev_queue_data *q_data,
return acc200_enqueue_ldpc_enc_cb(q_data, ops, num);
}
+
+/* Enqueue decode operations for ACC200 device in CB mode */
+static uint16_t
+acc200_enqueue_dec_cb(struct rte_bbdev_queue_data *q_data,
+ struct rte_bbdev_dec_op **ops, uint16_t num)
+{
+ struct acc_queue *q = q_data->queue_private;
+ int32_t avail = acc_ring_avail_enq(q);
+ uint16_t i;
+ union acc_dma_desc *desc;
+ int ret;
+
+ for (i = 0; i < num; ++i) {
+ /* Check if there are available space for further processing */
+ if (unlikely(avail - 1 < 0))
+ break;
+ avail -= 1;
+
+ ret = enqueue_dec_one_op_cb(q, ops[i], i);
+ if (ret < 0)
+ break;
+ }
+
+ if (unlikely(i == 0))
+ return 0; /* Nothing to enqueue */
+
+ /* Set SDone in last CB in enqueued ops for CB mode*/
+ desc = q->ring_addr + ((q->sw_ring_head + i - 1)
+ & q->sw_ring_wrap_mask);
+ desc->req.sdone_enable = 1;
+ desc->req.irq_enable = q->irq_enable;
+
+ acc_dma_enqueue(q, i, &q_data->queue_stats);
+
+ /* Update stats */
+ q_data->queue_stats.enqueued_count += i;
+ q_data->queue_stats.enqueue_err_count += num - i;
+
+ return i;
+}
+
/* Enqueue decode operations for ACC200 device in TB mode */
static uint16_t
acc200_enqueue_ldpc_dec_tb(struct rte_bbdev_queue_data *q_data,
@@ -1623,6 +2326,58 @@ acc200_enqueue_ldpc_dec_cb(struct rte_bbdev_queue_data *q_data,
return i;
}
+
+/* Enqueue decode operations for ACC200 device in TB mode */
+static uint16_t
+acc200_enqueue_dec_tb(struct rte_bbdev_queue_data *q_data,
+ struct rte_bbdev_dec_op **ops, uint16_t num)
+{
+ struct acc_queue *q = q_data->queue_private;
+ int32_t avail = acc_ring_avail_enq(q);
+ uint16_t i, enqueued_cbs = 0;
+ uint8_t cbs_in_tb;
+ int ret;
+
+ for (i = 0; i < num; ++i) {
+ cbs_in_tb = get_num_cbs_in_tb_dec(&ops[i]->turbo_dec);
+ /* Check if there are available space for further processing */
+ if (unlikely((avail - cbs_in_tb < 0) || (cbs_in_tb == 0))) {
+ acc_enqueue_ring_full(q_data);
+ break;
+ }
+ avail -= cbs_in_tb;
+
+ ret = enqueue_dec_one_op_tb(q, ops[i], enqueued_cbs, cbs_in_tb);
+ if (ret <= 0) {
+ acc_enqueue_invalid(q_data);
+ break;
+ }
+ enqueued_cbs += ret;
+ }
+
+ acc_dma_enqueue(q, enqueued_cbs, &q_data->queue_stats);
+
+ /* Update stats */
+ q_data->queue_stats.enqueued_count += i;
+ q_data->queue_stats.enqueue_err_count += num - i;
+
+ return i;
+}
+
+/* Enqueue decode operations for ACC200 device. */
+static uint16_t
+acc200_enqueue_dec(struct rte_bbdev_queue_data *q_data,
+ struct rte_bbdev_dec_op **ops, uint16_t num)
+{
+ int32_t aq_avail = acc_aq_avail(q_data, num);
+ if (unlikely((aq_avail <= 0) || (num == 0)))
+ return 0;
+ if (ops[0]->turbo_dec.code_block_mode == RTE_BBDEV_TRANSPORT_BLOCK)
+ return acc200_enqueue_dec_tb(q_data, ops, num);
+ else
+ return acc200_enqueue_dec_cb(q_data, ops, num);
+}
+
/* Enqueue decode operations for ACC200 device. */
static uint16_t
acc200_enqueue_ldpc_dec(struct rte_bbdev_queue_data *q_data,
@@ -1978,6 +2733,48 @@ dequeue_dec_one_op_tb(struct acc_queue *q, struct rte_bbdev_dec_op **ref_op,
return cb_idx;
}
+/* Dequeue encode operations from ACC200 device. */
+static uint16_t
+acc200_dequeue_enc(struct rte_bbdev_queue_data *q_data,
+ struct rte_bbdev_enc_op **ops, uint16_t num)
+{
+ struct acc_queue *q = q_data->queue_private;
+ uint32_t avail = acc_ring_avail_deq(q);
+ uint32_t aq_dequeued = 0;
+ uint16_t i, dequeued_ops = 0, dequeued_descs = 0;
+ int ret, cbm;
+ struct rte_bbdev_enc_op *op;
+ if (avail == 0)
+ return 0;
+ op = (q->ring_addr + (q->sw_ring_tail &
+ q->sw_ring_wrap_mask))->req.op_addr;
+
+ cbm = op->turbo_enc.code_block_mode;
+
+ for (i = 0; i < num; i++) {
+ if (cbm == RTE_BBDEV_TRANSPORT_BLOCK)
+ ret = dequeue_enc_one_op_tb(q, &ops[dequeued_ops],
+ &dequeued_ops, &aq_dequeued,
+ &dequeued_descs);
+ else
+ ret = dequeue_enc_one_op_cb(q, &ops[dequeued_ops],
+ &dequeued_ops, &aq_dequeued,
+ &dequeued_descs);
+ if (ret < 0)
+ break;
+ if (dequeued_ops >= num)
+ break;
+ }
+
+ q->aq_dequeued += aq_dequeued;
+ q->sw_ring_tail += dequeued_descs;
+
+ /* Update enqueue stats */
+ q_data->queue_stats.dequeued_count += dequeued_ops;
+
+ return dequeued_ops;
+}
+
/* Dequeue LDPC encode operations from ACC200 device. */
static uint16_t
acc200_dequeue_ldpc_enc(struct rte_bbdev_queue_data *q_data,
@@ -2019,6 +2816,51 @@ acc200_dequeue_ldpc_enc(struct rte_bbdev_queue_data *q_data,
return dequeued_ops;
}
+/* Dequeue decode operations from ACC200 device. */
+static uint16_t
+acc200_dequeue_dec(struct rte_bbdev_queue_data *q_data,
+ struct rte_bbdev_dec_op **ops, uint16_t num)
+{
+ struct acc_queue *q = q_data->queue_private;
+ uint16_t dequeue_num;
+ uint32_t avail = acc_ring_avail_deq(q);
+ uint32_t aq_dequeued = 0;
+ uint16_t i;
+ uint16_t dequeued_cbs = 0;
+ struct rte_bbdev_dec_op *op;
+ int ret;
+
+#ifdef RTE_LIBRTE_BBDEV_DEBUG
+ if (unlikely(ops == 0 && q == NULL))
+ return 0;
+#endif
+
+ dequeue_num = (avail < num) ? avail : num;
+
+ for (i = 0; i < dequeue_num; ++i) {
+ op = (q->ring_addr + ((q->sw_ring_tail + dequeued_cbs)
+ & q->sw_ring_wrap_mask))->req.op_addr;
+ if (op->turbo_dec.code_block_mode == RTE_BBDEV_TRANSPORT_BLOCK)
+ ret = dequeue_dec_one_op_tb(q, &ops[i], dequeued_cbs,
+ &aq_dequeued);
+ else
+ ret = dequeue_dec_one_op_cb(q_data, q, &ops[i],
+ dequeued_cbs, &aq_dequeued);
+
+ if (ret <= 0)
+ break;
+ dequeued_cbs += ret;
+ }
+
+ q->aq_dequeued += aq_dequeued;
+ q->sw_ring_tail += dequeued_cbs;
+
+ /* Update enqueue stats */
+ q_data->queue_stats.dequeued_count += i;
+
+ return i;
+}
+
/* Dequeue decode operations from ACC200 device. */
static uint16_t
acc200_dequeue_ldpc_dec(struct rte_bbdev_queue_data *q_data,
@@ -2067,6 +2909,10 @@ acc200_bbdev_init(struct rte_bbdev *dev, struct rte_pci_driver *drv)
struct rte_pci_device *pci_dev = RTE_DEV_TO_PCI(dev->device);
dev->dev_ops = &acc200_bbdev_ops;
+ dev->enqueue_enc_ops = acc200_enqueue_enc;
+ dev->enqueue_dec_ops = acc200_enqueue_dec;
+ dev->dequeue_enc_ops = acc200_dequeue_enc;
+ dev->dequeue_dec_ops = acc200_dequeue_dec;
dev->enqueue_ldpc_enc_ops = acc200_enqueue_ldpc_enc;
dev->enqueue_ldpc_dec_ops = acc200_enqueue_ldpc_dec;
dev->dequeue_ldpc_enc_ops = acc200_dequeue_ldpc_enc;
--
2.37.1
^ permalink raw reply [flat|nested] 28+ messages in thread* Re: [PATCH v6 09/14] baseband/acc: add LTE processing functions
2022-09-24 0:50 ` [PATCH v6 09/14] baseband/acc: add LTE " Nicolas Chautru
@ 2022-09-27 13:43 ` Maxime Coquelin
2022-09-29 21:13 ` Chautru, Nicolas
0 siblings, 1 reply; 28+ messages in thread
From: Maxime Coquelin @ 2022-09-27 13:43 UTC (permalink / raw)
To: Nicolas Chautru, dev, thomas
Cc: trix, mdr, bruce.richardson, hemant.agrawal, david.marchand,
stephen, hernan.vargas
On 9/24/22 02:50, Nicolas Chautru wrote:
> From: Nic Chautru <nicolas.chautru@intel.com>
>
> Add functions and capability for 4G FEC
>
> Signed-off-by: Nic Chautru <nicolas.chautru@intel.com>
> ---
> drivers/baseband/acc/rte_acc200_pmd.c | 854 +++++++++++++++++++++++++-
> 1 file changed, 850 insertions(+), 4 deletions(-)
>
> diff --git a/drivers/baseband/acc/rte_acc200_pmd.c b/drivers/baseband/acc/rte_acc200_pmd.c
> index 229e5fba86..e8901c60d6 100644
> --- a/drivers/baseband/acc/rte_acc200_pmd.c
> +++ b/drivers/baseband/acc/rte_acc200_pmd.c
> @@ -658,6 +658,46 @@ acc200_dev_info_get(struct rte_bbdev *dev,
> struct acc_device *d = dev->data->dev_private;
> int i;
> static const struct rte_bbdev_op_cap bbdev_capabilities[] = {
> + {
> + .type = RTE_BBDEV_OP_TURBO_DEC,
> + .cap.turbo_dec = {
> + .capability_flags =
> + RTE_BBDEV_TURBO_SUBBLOCK_DEINTERLEAVE |
> + RTE_BBDEV_TURBO_CRC_TYPE_24B |
> + RTE_BBDEV_TURBO_EQUALIZER |
> + RTE_BBDEV_TURBO_SOFT_OUT_SATURATE |
> + RTE_BBDEV_TURBO_HALF_ITERATION_EVEN |
> + RTE_BBDEV_TURBO_CONTINUE_CRC_MATCH |
> + RTE_BBDEV_TURBO_SOFT_OUTPUT |
> + RTE_BBDEV_TURBO_EARLY_TERMINATION |
> + RTE_BBDEV_TURBO_NEG_LLR_1_BIT_IN |
> + RTE_BBDEV_TURBO_NEG_LLR_1_BIT_SOFT_OUT |
> + RTE_BBDEV_TURBO_MAP_DEC |
> + RTE_BBDEV_TURBO_DEC_TB_CRC_24B_KEEP |
> + RTE_BBDEV_TURBO_DEC_SCATTER_GATHER,
> + .max_llr_modulus = INT8_MAX,
> + .num_buffers_src =
> + RTE_BBDEV_TURBO_MAX_CODE_BLOCKS,
> + .num_buffers_hard_out =
> + RTE_BBDEV_TURBO_MAX_CODE_BLOCKS,
> + .num_buffers_soft_out =
> + RTE_BBDEV_TURBO_MAX_CODE_BLOCKS,
> + }
> + },
> + {
> + .type = RTE_BBDEV_OP_TURBO_ENC,
> + .cap.turbo_enc = {
> + .capability_flags =
> + RTE_BBDEV_TURBO_CRC_24B_ATTACH |
> + RTE_BBDEV_TURBO_RV_INDEX_BYPASS |
> + RTE_BBDEV_TURBO_RATE_MATCH |
> + RTE_BBDEV_TURBO_ENC_SCATTER_GATHER,
> + .num_buffers_src =
> + RTE_BBDEV_TURBO_MAX_CODE_BLOCKS,
> + .num_buffers_dst =
> + RTE_BBDEV_TURBO_MAX_CODE_BLOCKS,
> + }
> + },
> {
> .type = RTE_BBDEV_OP_LDPC_ENC,
> .cap.ldpc_enc = {
> @@ -709,15 +749,17 @@ acc200_dev_info_get(struct rte_bbdev *dev,
>
> /* Exposed number of queues */
> dev_info->num_queues[RTE_BBDEV_OP_NONE] = 0;
> - dev_info->num_queues[RTE_BBDEV_OP_TURBO_DEC] = 0;
> - dev_info->num_queues[RTE_BBDEV_OP_TURBO_ENC] = 0;
> + dev_info->num_queues[RTE_BBDEV_OP_TURBO_DEC] = d->acc_conf.q_ul_4g.num_aqs_per_groups *
> + d->acc_conf.q_ul_4g.num_qgroups;
> + dev_info->num_queues[RTE_BBDEV_OP_TURBO_ENC] = d->acc_conf.q_dl_4g.num_aqs_per_groups *
> + d->acc_conf.q_dl_4g.num_qgroups;
> dev_info->num_queues[RTE_BBDEV_OP_LDPC_DEC] = d->acc_conf.q_ul_5g.num_aqs_per_groups *
> d->acc_conf.q_ul_5g.num_qgroups;
> dev_info->num_queues[RTE_BBDEV_OP_LDPC_ENC] = d->acc_conf.q_dl_5g.num_aqs_per_groups *
> d->acc_conf.q_dl_5g.num_qgroups;
> dev_info->num_queues[RTE_BBDEV_OP_FFT] = 0;
> - dev_info->queue_priority[RTE_BBDEV_OP_TURBO_DEC] = 0;
> - dev_info->queue_priority[RTE_BBDEV_OP_TURBO_ENC] = 0;
> + dev_info->queue_priority[RTE_BBDEV_OP_TURBO_DEC] = d->acc_conf.q_ul_4g.num_qgroups;
> + dev_info->queue_priority[RTE_BBDEV_OP_TURBO_ENC] = d->acc_conf.q_dl_4g.num_qgroups;
> dev_info->queue_priority[RTE_BBDEV_OP_LDPC_DEC] = d->acc_conf.q_ul_5g.num_qgroups;
> dev_info->queue_priority[RTE_BBDEV_OP_LDPC_ENC] = d->acc_conf.q_dl_5g.num_qgroups;
> dev_info->queue_priority[RTE_BBDEV_OP_FFT] = 0;
> @@ -762,6 +804,70 @@ static struct rte_pci_id pci_id_acc200_vf_map[] = {
> {.device_id = 0},
> };
>
> +/* Fill in a frame control word for turbo decoding. */
> +static inline void
> +acc200_fcw_td_fill(const struct rte_bbdev_dec_op *op, struct acc_fcw_td *fcw)
> +{
> + fcw->fcw_ver = 1;
> + fcw->num_maps = ACC_FCW_TD_AUTOMAP;
> + fcw->bypass_sb_deint = !check_bit(op->turbo_dec.op_flags,
> + RTE_BBDEV_TURBO_SUBBLOCK_DEINTERLEAVE);
> + if (op->turbo_dec.code_block_mode == RTE_BBDEV_TRANSPORT_BLOCK) {
> + /* FIXME for TB block */
> + fcw->k_pos = op->turbo_dec.tb_params.k_pos;
> + fcw->k_neg = op->turbo_dec.tb_params.k_neg;
> + } else {
> + fcw->k_pos = op->turbo_dec.cb_params.k;
> + fcw->k_neg = op->turbo_dec.cb_params.k;
> + }
> + fcw->c = 1;
> + fcw->c_neg = 1;
> + if (check_bit(op->turbo_dec.op_flags, RTE_BBDEV_TURBO_SOFT_OUTPUT)) {
> + fcw->soft_output_en = 1;
> + fcw->sw_soft_out_dis = 0;
> + fcw->sw_et_cont = check_bit(op->turbo_dec.op_flags,
> + RTE_BBDEV_TURBO_CONTINUE_CRC_MATCH);
> + fcw->sw_soft_out_saturation = check_bit(op->turbo_dec.op_flags,
> + RTE_BBDEV_TURBO_SOFT_OUT_SATURATE);
> + if (check_bit(op->turbo_dec.op_flags,
> + RTE_BBDEV_TURBO_EQUALIZER)) {
> + fcw->bypass_teq = 0;
> + fcw->ea = op->turbo_dec.cb_params.e;
> + fcw->eb = op->turbo_dec.cb_params.e;
> + if (op->turbo_dec.rv_index == 0)
> + fcw->k0_start_col = ACC_FCW_TD_RVIDX_0;
> + else if (op->turbo_dec.rv_index == 1)
> + fcw->k0_start_col = ACC_FCW_TD_RVIDX_1;
> + else if (op->turbo_dec.rv_index == 2)
> + fcw->k0_start_col = ACC_FCW_TD_RVIDX_2;
> + else
> + fcw->k0_start_col = ACC_FCW_TD_RVIDX_3;
> + } else {
> + fcw->bypass_teq = 1;
> + fcw->eb = 64; /* avoid undefined value */
> + }
> + } else {
> + fcw->soft_output_en = 0;
> + fcw->sw_soft_out_dis = 1;
> + fcw->bypass_teq = 0;
> + }
> +
> + fcw->code_block_mode = 1; /* FIXME */
> + fcw->turbo_crc_type = check_bit(op->turbo_dec.op_flags,
> + RTE_BBDEV_TURBO_CRC_TYPE_24B);
> +
> + fcw->ext_td_cold_reg_en = 1;
> + fcw->raw_decoder_input_on = 0;
> + fcw->max_iter = RTE_MAX((uint8_t) op->turbo_dec.iter_max, 2);
> + fcw->min_iter = 2;
> + fcw->half_iter_on = !check_bit(op->turbo_dec.op_flags,
> + RTE_BBDEV_TURBO_HALF_ITERATION_EVEN);
> +
> + fcw->early_stop_en = check_bit(op->turbo_dec.op_flags,
> + RTE_BBDEV_TURBO_EARLY_TERMINATION) & !fcw->soft_output_en;
> + fcw->ext_scale = 0xF;
> +}
> +
> /* Fill in a frame control word for LDPC decoding. */
> static inline void
> acc200_fcw_ld_fill(struct rte_bbdev_dec_op *op, struct acc_fcw_ld *fcw,
> @@ -887,6 +993,205 @@ acc200_fcw_ld_fill(struct rte_bbdev_dec_op *op, struct acc_fcw_ld *fcw,
> fcw->tb_crc_select = 1;
> }
>
> +static inline int
> +acc200_dma_desc_te_fill(struct rte_bbdev_enc_op *op,
> + struct acc_dma_req_desc *desc, struct rte_mbuf **input,
> + struct rte_mbuf *output, uint32_t *in_offset,
> + uint32_t *out_offset, uint32_t *out_length,
> + uint32_t *mbuf_total_left, uint32_t *seg_total_left, uint8_t r)
> +{
> + int next_triplet = 1; /* FCW already done */
> + uint32_t e, ea, eb, length;
> + uint16_t k, k_neg, k_pos;
> + uint8_t cab, c_neg;
> +
> + desc->word0 = ACC_DMA_DESC_TYPE;
> + desc->word1 = 0; /**< Timestamp could be disabled */
> + desc->word2 = 0;
> + desc->word3 = 0;
> + desc->numCBs = 1;
> +
> + if (op->turbo_enc.code_block_mode == RTE_BBDEV_TRANSPORT_BLOCK) {
> + ea = op->turbo_enc.tb_params.ea;
> + eb = op->turbo_enc.tb_params.eb;
> + cab = op->turbo_enc.tb_params.cab;
> + k_neg = op->turbo_enc.tb_params.k_neg;
> + k_pos = op->turbo_enc.tb_params.k_pos;
> + c_neg = op->turbo_enc.tb_params.c_neg;
> + e = (r < cab) ? ea : eb;
> + k = (r < c_neg) ? k_neg : k_pos;
> + } else {
> + e = op->turbo_enc.cb_params.e;
> + k = op->turbo_enc.cb_params.k;
> + }
> +
> + if (check_bit(op->turbo_enc.op_flags, RTE_BBDEV_TURBO_CRC_24B_ATTACH))
> + length = (k - 24) >> 3;
> + else
> + length = k >> 3;
> +
> + if (unlikely((*mbuf_total_left == 0) || (*mbuf_total_left < length))) {
> + rte_bbdev_log(ERR,
> + "Mismatch between mbuf length and included CB sizes: mbuf len %u, cb len %u",
> + *mbuf_total_left, length);
> + return -1;
> + }
> +
> + next_triplet = acc_dma_fill_blk_type_in(desc, input, in_offset,
> + length, seg_total_left, next_triplet,
> + check_bit(op->turbo_enc.op_flags,
> + RTE_BBDEV_TURBO_ENC_SCATTER_GATHER));
> + if (unlikely(next_triplet < 0)) {
> + rte_bbdev_log(ERR,
> + "Mismatch between data to process and mbuf data length in bbdev_op: %p",
> + op);
> + return -1;
> + }
> + desc->data_ptrs[next_triplet - 1].last = 1;
> + desc->m2dlen = next_triplet;
> + *mbuf_total_left -= length;
> +
> + /* Set output length */
> + if (check_bit(op->turbo_enc.op_flags, RTE_BBDEV_TURBO_RATE_MATCH))
> + /* Integer round up division by 8 */
> + *out_length = (e + 7) >> 3;
> + else
> + *out_length = (k >> 3) * 3 + 2;
> +
> + next_triplet = acc_dma_fill_blk_type(desc, output, *out_offset,
> + *out_length, next_triplet, ACC_DMA_BLKID_OUT_ENC);
> + if (unlikely(next_triplet < 0)) {
> + rte_bbdev_log(ERR,
> + "Mismatch between data to process and mbuf data length in bbdev_op: %p",
> + op);
> + return -1;
> + }
> + op->turbo_enc.output.length += *out_length;
> + *out_offset += *out_length;
> + desc->data_ptrs[next_triplet - 1].last = 1;
> + desc->d2mlen = next_triplet - desc->m2dlen;
> +
> + desc->op_addr = op;
> +
> + return 0;
> +}
> +
> +static inline int
> +acc200_dma_desc_td_fill(struct rte_bbdev_dec_op *op,
> + struct acc_dma_req_desc *desc, struct rte_mbuf **input,
> + struct rte_mbuf *h_output, struct rte_mbuf *s_output,
> + uint32_t *in_offset, uint32_t *h_out_offset,
> + uint32_t *s_out_offset, uint32_t *h_out_length,
> + uint32_t *s_out_length, uint32_t *mbuf_total_left,
> + uint32_t *seg_total_left, uint8_t r)
> +{
> + int next_triplet = 1; /* FCW already done */
> + uint16_t k;
> + uint16_t crc24_overlap = 0;
> + uint32_t e, kw;
> +
> + desc->word0 = ACC_DMA_DESC_TYPE;
> + desc->word1 = 0; /**< Timestamp could be disabled */
> + desc->word2 = 0;
> + desc->word3 = 0;
> + desc->numCBs = 1;
> +
> + if (op->turbo_dec.code_block_mode == RTE_BBDEV_TRANSPORT_BLOCK) {
> + k = (r < op->turbo_dec.tb_params.c_neg)
> + ? op->turbo_dec.tb_params.k_neg
> + : op->turbo_dec.tb_params.k_pos;
> + e = (r < op->turbo_dec.tb_params.cab)
> + ? op->turbo_dec.tb_params.ea
> + : op->turbo_dec.tb_params.eb;
> + } else {
> + k = op->turbo_dec.cb_params.k;
> + e = op->turbo_dec.cb_params.e;
> + }
> +
> + if ((op->turbo_dec.code_block_mode == RTE_BBDEV_TRANSPORT_BLOCK)
> + && !check_bit(op->turbo_dec.op_flags,
> + RTE_BBDEV_TURBO_DEC_TB_CRC_24B_KEEP))
> + crc24_overlap = 24;
> +
> + /* Calculates circular buffer size.
> + * According to 3gpp 36.212 section 5.1.4.2
> + * Kw = 3 * Kpi,
> + * where:
> + * Kpi = nCol * nRow
> + * where nCol is 32 and nRow can be calculated from:
> + * D =< nCol * nRow
> + * where D is the size of each output from turbo encoder block (k + 4).
> + */
> + kw = RTE_ALIGN_CEIL(k + 4, 32) * 3;
> +
> + if (unlikely((*mbuf_total_left == 0) || (*mbuf_total_left < kw))) {
> + rte_bbdev_log(ERR,
> + "Mismatch between mbuf length and included CB sizes: mbuf len %u, cb len %u",
> + *mbuf_total_left, kw);
> + return -1;
> + }
> +
> + next_triplet = acc_dma_fill_blk_type_in(desc, input, in_offset, kw,
> + seg_total_left, next_triplet,
> + check_bit(op->turbo_dec.op_flags,
> + RTE_BBDEV_TURBO_DEC_SCATTER_GATHER));
> + if (unlikely(next_triplet < 0)) {
> + rte_bbdev_log(ERR,
> + "Mismatch between data to process and mbuf data length in bbdev_op: %p",
> + op);
> + return -1;
> + }
> + desc->data_ptrs[next_triplet - 1].last = 1;
> + desc->m2dlen = next_triplet;
> + *mbuf_total_left -= kw;
> + *h_out_length = ((k - crc24_overlap) >> 3);
> + next_triplet = acc_dma_fill_blk_type(
> + desc, h_output, *h_out_offset,
> + *h_out_length, next_triplet, ACC_DMA_BLKID_OUT_HARD);
> + if (unlikely(next_triplet < 0)) {
> + rte_bbdev_log(ERR,
> + "Mismatch between data to process and mbuf data length in bbdev_op: %p",
> + op);
> + return -1;
> + }
> +
> + op->turbo_dec.hard_output.length += *h_out_length;
> + *h_out_offset += *h_out_length;
> +
> + /* Soft output */
> + if (check_bit(op->turbo_dec.op_flags, RTE_BBDEV_TURBO_SOFT_OUTPUT)) {
> + if (op->turbo_dec.soft_output.data == 0) {
> + rte_bbdev_log(ERR, "Soft output is not defined");
> + return -1;
> + }
> + if (check_bit(op->turbo_dec.op_flags,
> + RTE_BBDEV_TURBO_EQUALIZER))
> + *s_out_length = e;
> + else
> + *s_out_length = (k * 3) + 12;
> +
> + next_triplet = acc_dma_fill_blk_type(desc, s_output,
> + *s_out_offset, *s_out_length, next_triplet,
> + ACC_DMA_BLKID_OUT_SOFT);
> + if (unlikely(next_triplet < 0)) {
> + rte_bbdev_log(ERR,
> + "Mismatch between data to process and mbuf data length in bbdev_op: %p",
> + op);
> + return -1;
> + }
> +
> + op->turbo_dec.soft_output.length += *s_out_length;
> + *s_out_offset += *s_out_length;
> + }
> +
> + desc->data_ptrs[next_triplet - 1].last = 1;
> + desc->d2mlen = next_triplet - desc->m2dlen;
> +
> + desc->op_addr = op;
> +
> + return 0;
> +}
> +
> static inline int
> acc200_dma_desc_ld_fill(struct rte_bbdev_dec_op *op,
> struct acc_dma_req_desc *desc,
> @@ -1059,6 +1364,49 @@ acc200_dma_desc_ld_update(struct rte_bbdev_dec_op *op,
> desc->op_addr = op;
> }
>
> +/* Enqueue one encode operations for ACC200 device in CB mode */
> +static inline int
> +enqueue_enc_one_op_cb(struct acc_queue *q, struct rte_bbdev_enc_op *op,
> + uint16_t total_enqueued_cbs)
> +{
> + union acc_dma_desc *desc = NULL;
> + int ret;
> + uint32_t in_offset, out_offset, out_length, mbuf_total_left,
> + seg_total_left;
> + struct rte_mbuf *input, *output_head, *output;
> +
> + uint16_t desc_idx = ((q->sw_ring_head + total_enqueued_cbs)
> + & q->sw_ring_wrap_mask);
> + desc = q->ring_addr + desc_idx;
> + acc_fcw_te_fill(op, &desc->req.fcw_te);
> +
> + input = op->turbo_enc.input.data;
> + output_head = output = op->turbo_enc.output.data;
> + in_offset = op->turbo_enc.input.offset;
> + out_offset = op->turbo_enc.output.offset;
> + out_length = 0;
> + mbuf_total_left = op->turbo_enc.input.length;
> + seg_total_left = rte_pktmbuf_data_len(op->turbo_enc.input.data)
> + - in_offset;
> +
> + ret = acc200_dma_desc_te_fill(op, &desc->req, &input, output,
> + &in_offset, &out_offset, &out_length, &mbuf_total_left,
> + &seg_total_left, 0);
> +
> + if (unlikely(ret < 0))
> + return ret;
> +
> + mbuf_append(output_head, output, out_length);
> +
> +#ifdef RTE_LIBRTE_BBDEV_DEBUG
> + rte_memdump(stderr, "FCW", &desc->req.fcw_te,
> + sizeof(desc->req.fcw_te) - 8);
> + rte_memdump(stderr, "Req Desc.", desc, sizeof(*desc));
> +#endif
> + /* One CB (one op) was successfully prepared to enqueue */
> + return 1;
> +}
> +
> /* Enqueue one encode operations for ACC200 device in CB mode
> * multiplexed on the same descriptor
> */
> @@ -1175,6 +1523,78 @@ enqueue_ldpc_enc_part_tb(struct acc_queue *q, struct rte_bbdev_enc_op *op,
>
> }
>
> +/* Enqueue one encode operations for ACC200 device in TB mode. */
> +static inline int
> +enqueue_enc_one_op_tb(struct acc_queue *q, struct rte_bbdev_enc_op *op,
> + uint16_t total_enqueued_cbs, uint8_t cbs_in_tb)
> +{
> + union acc_dma_desc *desc = NULL;
> + int ret;
> + uint8_t r, c;
> + uint32_t in_offset, out_offset, out_length, mbuf_total_left,
> + seg_total_left;
> + struct rte_mbuf *input, *output_head, *output;
> + uint16_t current_enqueued_cbs = 0;
> +
> + uint16_t desc_idx = ((q->sw_ring_head + total_enqueued_cbs)
> + & q->sw_ring_wrap_mask);
> + desc = q->ring_addr + desc_idx;
> + uint64_t fcw_offset = (desc_idx << 8) + ACC_DESC_FCW_OFFSET;
> + acc_fcw_te_fill(op, &desc->req.fcw_te);
> +
> + input = op->turbo_enc.input.data;
> + output_head = output = op->turbo_enc.output.data;
> + in_offset = op->turbo_enc.input.offset;
> + out_offset = op->turbo_enc.output.offset;
> + out_length = 0;
> + mbuf_total_left = op->turbo_enc.input.length;
> +
> + c = op->turbo_enc.tb_params.c;
> + r = op->turbo_enc.tb_params.r;
> +
> + while (mbuf_total_left > 0 && r < c) {
> + seg_total_left = rte_pktmbuf_data_len(input) - in_offset;
> + /* Set up DMA descriptor */
> + desc = q->ring_addr + ((q->sw_ring_head + total_enqueued_cbs)
> + & q->sw_ring_wrap_mask);
> + desc->req.data_ptrs[0].address = q->ring_addr_iova + fcw_offset;
> + desc->req.data_ptrs[0].blen = ACC_FCW_TE_BLEN;
> +
> + ret = acc200_dma_desc_te_fill(op, &desc->req, &input, output,
> + &in_offset, &out_offset, &out_length,
> + &mbuf_total_left, &seg_total_left, r);
> + if (unlikely(ret < 0))
> + return ret;
> + mbuf_append(output_head, output, out_length);
> +
> + /* Set total number of CBs in TB */
> + desc->req.cbs_in_tb = cbs_in_tb;
> +#ifdef RTE_LIBRTE_BBDEV_DEBUG
> + rte_memdump(stderr, "FCW", &desc->req.fcw_te,
> + sizeof(desc->req.fcw_te) - 8);
> + rte_memdump(stderr, "Req Desc.", desc, sizeof(*desc));
> +#endif
> +
> + if (seg_total_left == 0) {
> + /* Go to the next mbuf */
> + input = input->next;
> + in_offset = 0;
> + output = output->next;
> + out_offset = 0;
> + }
> +
> + total_enqueued_cbs++;
> + current_enqueued_cbs++;
> + r++;
> + }
> +
> + /* Set SDone on last CB descriptor for TB mode. */
> + desc->req.sdone_enable = 1;
> + desc->req.irq_enable = q->irq_enable;
> +
> + return current_enqueued_cbs;
> +}
> +
> /* Enqueue one encode operations for ACC200 device in TB mode.
> * returns the number of descs used
> */
> @@ -1240,6 +1660,62 @@ enqueue_ldpc_enc_one_op_tb(struct acc_queue *q, struct rte_bbdev_enc_op *op,
> return return_descs;
> }
>
> +/** Enqueue one decode operations for ACC200 device in CB mode */
> +static inline int
> +enqueue_dec_one_op_cb(struct acc_queue *q, struct rte_bbdev_dec_op *op,
> + uint16_t total_enqueued_cbs)
> +{
> + union acc_dma_desc *desc = NULL;
> + int ret;
> + uint32_t in_offset, h_out_offset, s_out_offset, s_out_length,
> + h_out_length, mbuf_total_left, seg_total_left;
> + struct rte_mbuf *input, *h_output_head, *h_output,
> + *s_output_head, *s_output;
> +
> + uint16_t desc_idx = ((q->sw_ring_head + total_enqueued_cbs)
> + & q->sw_ring_wrap_mask);
> + desc = q->ring_addr + desc_idx;
> + acc200_fcw_td_fill(op, &desc->req.fcw_td);
> +
> + input = op->turbo_dec.input.data;
> + h_output_head = h_output = op->turbo_dec.hard_output.data;
> + s_output_head = s_output = op->turbo_dec.soft_output.data;
> + in_offset = op->turbo_dec.input.offset;
> + h_out_offset = op->turbo_dec.hard_output.offset;
> + s_out_offset = op->turbo_dec.soft_output.offset;
> + h_out_length = s_out_length = 0;
> + mbuf_total_left = op->turbo_dec.input.length;
> + seg_total_left = rte_pktmbuf_data_len(input) - in_offset;
> +
> + /* Set up DMA descriptor */
> + desc = q->ring_addr + ((q->sw_ring_head + total_enqueued_cbs)
> + & q->sw_ring_wrap_mask);
> +
> + ret = acc200_dma_desc_td_fill(op, &desc->req, &input, h_output,
> + s_output, &in_offset, &h_out_offset, &s_out_offset,
> + &h_out_length, &s_out_length, &mbuf_total_left,
> + &seg_total_left, 0);
> +
> + if (unlikely(ret < 0))
> + return ret;
> +
> + /* Hard output */
> + mbuf_append(h_output_head, h_output, h_out_length);
> +
> + /* Soft output */
> + if (check_bit(op->turbo_dec.op_flags, RTE_BBDEV_TURBO_SOFT_OUTPUT))
> + mbuf_append(s_output_head, s_output, s_out_length);
> +
> +#ifdef RTE_LIBRTE_BBDEV_DEBUG
> + rte_memdump(stderr, "FCW", &desc->req.fcw_td,
> + sizeof(desc->req.fcw_td));
> + rte_memdump(stderr, "Req Desc.", desc, sizeof(*desc));
> +#endif
> +
> + /* One CB (one op) was successfully prepared to enqueue */
> + return 1;
> +}
> +
> /** Enqueue one decode operations for ACC200 device in CB mode */
> static inline int
> enqueue_ldpc_dec_one_op_cb(struct acc_queue *q, struct rte_bbdev_dec_op *op,
> @@ -1437,6 +1913,139 @@ enqueue_ldpc_dec_one_op_tb(struct acc_queue *q, struct rte_bbdev_dec_op *op,
> return current_enqueued_cbs;
> }
>
> +/* Enqueue one decode operations for ACC200 device in TB mode */
> +static inline int
> +enqueue_dec_one_op_tb(struct acc_queue *q, struct rte_bbdev_dec_op *op,
> + uint16_t total_enqueued_cbs, uint8_t cbs_in_tb)
> +{
> + union acc_dma_desc *desc = NULL;
> + int ret;
> + uint8_t r, c;
> + uint32_t in_offset, h_out_offset, s_out_offset, s_out_length,
> + h_out_length, mbuf_total_left, seg_total_left;
> + struct rte_mbuf *input, *h_output_head, *h_output,
> + *s_output_head, *s_output;
> + uint16_t current_enqueued_cbs = 0;
> +
> + uint16_t desc_idx = ((q->sw_ring_head + total_enqueued_cbs)
> + & q->sw_ring_wrap_mask);
> + desc = q->ring_addr + desc_idx;
> + uint64_t fcw_offset = (desc_idx << 8) + ACC_DESC_FCW_OFFSET;
> + acc200_fcw_td_fill(op, &desc->req.fcw_td);
> +
> + input = op->turbo_dec.input.data;
> + h_output_head = h_output = op->turbo_dec.hard_output.data;
> + s_output_head = s_output = op->turbo_dec.soft_output.data;
> + in_offset = op->turbo_dec.input.offset;
> + h_out_offset = op->turbo_dec.hard_output.offset;
> + s_out_offset = op->turbo_dec.soft_output.offset;
> + h_out_length = s_out_length = 0;
> + mbuf_total_left = op->turbo_dec.input.length;
> + c = op->turbo_dec.tb_params.c;
> + r = op->turbo_dec.tb_params.r;
> +
> + while (mbuf_total_left > 0 && r < c) {
> +
> + seg_total_left = rte_pktmbuf_data_len(input) - in_offset;
> +
> + /* Set up DMA descriptor */
> + desc = q->ring_addr + ((q->sw_ring_head + total_enqueued_cbs)
> + & q->sw_ring_wrap_mask);
> + desc->req.data_ptrs[0].address = q->ring_addr_iova + fcw_offset;
> + desc->req.data_ptrs[0].blen = ACC_FCW_TD_BLEN;
> + ret = acc200_dma_desc_td_fill(op, &desc->req, &input,
> + h_output, s_output, &in_offset, &h_out_offset,
> + &s_out_offset, &h_out_length, &s_out_length,
> + &mbuf_total_left, &seg_total_left, r);
> +
> + if (unlikely(ret < 0))
> + return ret;
> +
> + /* Hard output */
> + mbuf_append(h_output_head, h_output, h_out_length);
> +
> + /* Soft output */
> + if (check_bit(op->turbo_dec.op_flags,
> + RTE_BBDEV_TURBO_SOFT_OUTPUT))
> + mbuf_append(s_output_head, s_output, s_out_length);
> +
> + /* Set total number of CBs in TB */
> + desc->req.cbs_in_tb = cbs_in_tb;
> +#ifdef RTE_LIBRTE_BBDEV_DEBUG
> + rte_memdump(stderr, "FCW", &desc->req.fcw_td,
> + sizeof(desc->req.fcw_td) - 8);
> + rte_memdump(stderr, "Req Desc.", desc, sizeof(*desc));
> +#endif
> +
> + if (seg_total_left == 0) {
> + /* Go to the next mbuf */
> + input = input->next;
> + in_offset = 0;
> + h_output = h_output->next;
> + h_out_offset = 0;
> +
> + if (check_bit(op->turbo_dec.op_flags,
> + RTE_BBDEV_TURBO_SOFT_OUTPUT)) {
> + s_output = s_output->next;
> + s_out_offset = 0;
> + }
> + }
> +
> + total_enqueued_cbs++;
> + current_enqueued_cbs++;
> + r++;
> + }
> +
> + /* Set SDone on last CB descriptor for TB mode */
> + desc->req.sdone_enable = 1;
> + desc->req.irq_enable = q->irq_enable;
> +
> + return current_enqueued_cbs;
> +}
> +
> +/* Enqueue encode operations for ACC200 device in CB mode. */
> +static uint16_t
> +acc200_enqueue_enc_cb(struct rte_bbdev_queue_data *q_data,
> + struct rte_bbdev_enc_op **ops, uint16_t num)
> +{
> + struct acc_queue *q = q_data->queue_private;
> + int32_t avail = acc_ring_avail_enq(q);
> + uint16_t i;
> + union acc_dma_desc *desc;
> + int ret;
> +
> + for (i = 0; i < num; ++i) {
> + /* Check if there are available space for further processing */
> + if (unlikely(avail - 1 < 0)) {
> + acc_enqueue_ring_full(q_data);
> + break;
> + }
> + avail -= 1;
> +
> + ret = enqueue_enc_one_op_cb(q, ops[i], i);
> + if (ret < 0) {
> + acc_enqueue_invalid(q_data);
> + break;
> + }
> + }
> +
> + if (unlikely(i == 0))
> + return 0; /* Nothing to enqueue */
> +
> + /* Set SDone in last CB in enqueued ops for CB mode*/
> + desc = q->ring_addr + ((q->sw_ring_head + i - 1)
> + & q->sw_ring_wrap_mask);
> + desc->req.sdone_enable = 1;
> + desc->req.irq_enable = q->irq_enable;
> +
> + acc_dma_enqueue(q, i, &q_data->queue_stats);
> +
> + /* Update stats */
> + q_data->queue_stats.enqueued_count += i;
> + q_data->queue_stats.enqueue_err_count += num - i;
> + return i;
> +}
> +
> /** Enqueue encode operations for ACC200 device in CB mode. */
> static inline uint16_t
> acc200_enqueue_ldpc_enc_cb(struct rte_bbdev_queue_data *q_data,
> @@ -1485,6 +2094,45 @@ acc200_enqueue_ldpc_enc_cb(struct rte_bbdev_queue_data *q_data,
> return i;
> }
>
> +/* Enqueue encode operations for ACC200 device in TB mode. */
> +static uint16_t
> +acc200_enqueue_enc_tb(struct rte_bbdev_queue_data *q_data,
> + struct rte_bbdev_enc_op **ops, uint16_t num)
> +{
> + struct acc_queue *q = q_data->queue_private;
> + int32_t avail = acc_ring_avail_enq(q);
> + uint16_t i, enqueued_cbs = 0;
> + uint8_t cbs_in_tb;
> + int ret;
> +
> + for (i = 0; i < num; ++i) {
> + cbs_in_tb = get_num_cbs_in_tb_enc(&ops[i]->turbo_enc);
> + /* Check if there are available space for further processing */
> + if (unlikely((avail - cbs_in_tb < 0) || (cbs_in_tb == 0))) {
> + acc_enqueue_ring_full(q_data);
> + break;
> + }
> + avail -= cbs_in_tb;
> +
> + ret = enqueue_enc_one_op_tb(q, ops[i], enqueued_cbs, cbs_in_tb);
> + if (ret <= 0) {
> + acc_enqueue_invalid(q_data);
> + break;
> + }
> + enqueued_cbs += ret;
> + }
> + if (unlikely(enqueued_cbs == 0))
> + return 0; /* Nothing to enqueue */
> +
> + acc_dma_enqueue(q, enqueued_cbs, &q_data->queue_stats);
> +
> + /* Update stats */
> + q_data->queue_stats.enqueued_count += i;
> + q_data->queue_stats.enqueue_err_count += num - i;
> +
> + return i;
> +}
> +
> /* Enqueue LDPC encode operations for ACC200 device in TB mode. */
> static uint16_t
> acc200_enqueue_ldpc_enc_tb(struct rte_bbdev_queue_data *q_data,
> @@ -1525,6 +2173,20 @@ acc200_enqueue_ldpc_enc_tb(struct rte_bbdev_queue_data *q_data,
> return i;
> }
>
> +/* Enqueue encode operations for ACC200 device. */
> +static uint16_t
> +acc200_enqueue_enc(struct rte_bbdev_queue_data *q_data,
> + struct rte_bbdev_enc_op **ops, uint16_t num)
> +{
> + int32_t aq_avail = acc_aq_avail(q_data, num);
> + if (unlikely((aq_avail <= 0) || (num == 0)))
> + return 0;
> + if (ops[0]->turbo_enc.code_block_mode == RTE_BBDEV_TRANSPORT_BLOCK)
> + return acc200_enqueue_enc_tb(q_data, ops, num);
> + else
> + return acc200_enqueue_enc_cb(q_data, ops, num);
> +}
> +
> /* Enqueue encode operations for ACC200 device. */
> static uint16_t
> acc200_enqueue_ldpc_enc(struct rte_bbdev_queue_data *q_data,
> @@ -1539,6 +2201,47 @@ acc200_enqueue_ldpc_enc(struct rte_bbdev_queue_data *q_data,
> return acc200_enqueue_ldpc_enc_cb(q_data, ops, num);
> }
>
> +
> +/* Enqueue decode operations for ACC200 device in CB mode */
> +static uint16_t
> +acc200_enqueue_dec_cb(struct rte_bbdev_queue_data *q_data,
> + struct rte_bbdev_dec_op **ops, uint16_t num)
> +{
> + struct acc_queue *q = q_data->queue_private;
> + int32_t avail = acc_ring_avail_enq(q);
> + uint16_t i;
> + union acc_dma_desc *desc;
> + int ret;
> +
> + for (i = 0; i < num; ++i) {
> + /* Check if there are available space for further processing */
> + if (unlikely(avail - 1 < 0))
> + break;
> + avail -= 1;
> +
> + ret = enqueue_dec_one_op_cb(q, ops[i], i);
> + if (ret < 0)
> + break;
> + }
> +
> + if (unlikely(i == 0))
> + return 0; /* Nothing to enqueue */
> +
> + /* Set SDone in last CB in enqueued ops for CB mode*/
> + desc = q->ring_addr + ((q->sw_ring_head + i - 1)
> + & q->sw_ring_wrap_mask);
> + desc->req.sdone_enable = 1;
> + desc->req.irq_enable = q->irq_enable;
> +
> + acc_dma_enqueue(q, i, &q_data->queue_stats);
> +
> + /* Update stats */
> + q_data->queue_stats.enqueued_count += i;
> + q_data->queue_stats.enqueue_err_count += num - i;
> +
> + return i;
> +}
> +
> /* Enqueue decode operations for ACC200 device in TB mode */
> static uint16_t
> acc200_enqueue_ldpc_dec_tb(struct rte_bbdev_queue_data *q_data,
> @@ -1623,6 +2326,58 @@ acc200_enqueue_ldpc_dec_cb(struct rte_bbdev_queue_data *q_data,
> return i;
> }
>
> +
> +/* Enqueue decode operations for ACC200 device in TB mode */
> +static uint16_t
> +acc200_enqueue_dec_tb(struct rte_bbdev_queue_data *q_data,
> + struct rte_bbdev_dec_op **ops, uint16_t num)
> +{
> + struct acc_queue *q = q_data->queue_private;
> + int32_t avail = acc_ring_avail_enq(q);
> + uint16_t i, enqueued_cbs = 0;
> + uint8_t cbs_in_tb;
> + int ret;
> +
> + for (i = 0; i < num; ++i) {
> + cbs_in_tb = get_num_cbs_in_tb_dec(&ops[i]->turbo_dec);
> + /* Check if there are available space for further processing */
> + if (unlikely((avail - cbs_in_tb < 0) || (cbs_in_tb == 0))) {
> + acc_enqueue_ring_full(q_data);
> + break;
> + }
> + avail -= cbs_in_tb;
> +
> + ret = enqueue_dec_one_op_tb(q, ops[i], enqueued_cbs, cbs_in_tb);
> + if (ret <= 0) {
> + acc_enqueue_invalid(q_data);
> + break;
> + }
> + enqueued_cbs += ret;
> + }
> +
> + acc_dma_enqueue(q, enqueued_cbs, &q_data->queue_stats);
> +
> + /* Update stats */
> + q_data->queue_stats.enqueued_count += i;
> + q_data->queue_stats.enqueue_err_count += num - i;
> +
> + return i;
> +}
> +
> +/* Enqueue decode operations for ACC200 device. */
> +static uint16_t
> +acc200_enqueue_dec(struct rte_bbdev_queue_data *q_data,
> + struct rte_bbdev_dec_op **ops, uint16_t num)
> +{
> + int32_t aq_avail = acc_aq_avail(q_data, num);
> + if (unlikely((aq_avail <= 0) || (num == 0)))
> + return 0;
> + if (ops[0]->turbo_dec.code_block_mode == RTE_BBDEV_TRANSPORT_BLOCK)
> + return acc200_enqueue_dec_tb(q_data, ops, num);
> + else
> + return acc200_enqueue_dec_cb(q_data, ops, num);
> +}
> +
> /* Enqueue decode operations for ACC200 device. */
> static uint16_t
> acc200_enqueue_ldpc_dec(struct rte_bbdev_queue_data *q_data,
> @@ -1978,6 +2733,48 @@ dequeue_dec_one_op_tb(struct acc_queue *q, struct rte_bbdev_dec_op **ref_op,
> return cb_idx;
> }
>
> +/* Dequeue encode operations from ACC200 device. */
> +static uint16_t
> +acc200_dequeue_enc(struct rte_bbdev_queue_data *q_data,
> + struct rte_bbdev_enc_op **ops, uint16_t num)
> +{
> + struct acc_queue *q = q_data->queue_private;
> + uint32_t avail = acc_ring_avail_deq(q);
> + uint32_t aq_dequeued = 0;
> + uint16_t i, dequeued_ops = 0, dequeued_descs = 0;
> + int ret, cbm;
> + struct rte_bbdev_enc_op *op;
Why isn't there "debug checks" here while there are in
acc200_dequeue_dec? Are we sure that here ops and q are non-null while
we cannot know in acc200_dequeue_dec?
> + if (avail == 0)
> + return 0;
> + op = (q->ring_addr + (q->sw_ring_tail &
> + q->sw_ring_wrap_mask))->req.op_addr;
> +
> + cbm = op->turbo_enc.code_block_mode;
> +
> + for (i = 0; i < num; i++) {
> + if (cbm == RTE_BBDEV_TRANSPORT_BLOCK)
> + ret = dequeue_enc_one_op_tb(q, &ops[dequeued_ops],
> + &dequeued_ops, &aq_dequeued,
> + &dequeued_descs);
> + else
> + ret = dequeue_enc_one_op_cb(q, &ops[dequeued_ops],
> + &dequeued_ops, &aq_dequeued,
> + &dequeued_descs);
> + if (ret < 0)
> + break;
> + if (dequeued_ops >= num)
> + break;
> + }
> +
> + q->aq_dequeued += aq_dequeued;
> + q->sw_ring_tail += dequeued_descs;
> +
> + /* Update enqueue stats */
> + q_data->queue_stats.dequeued_count += dequeued_ops;
> +
> + return dequeued_ops;
> +}
> +
> /* Dequeue LDPC encode operations from ACC200 device. */
> static uint16_t
> acc200_dequeue_ldpc_enc(struct rte_bbdev_queue_data *q_data,
> @@ -2019,6 +2816,51 @@ acc200_dequeue_ldpc_enc(struct rte_bbdev_queue_data *q_data,
> return dequeued_ops;
> }
>
> +/* Dequeue decode operations from ACC200 device. */
> +static uint16_t
> +acc200_dequeue_dec(struct rte_bbdev_queue_data *q_data,
> + struct rte_bbdev_dec_op **ops, uint16_t num)
> +{
> + struct acc_queue *q = q_data->queue_private;
> + uint16_t dequeue_num;
> + uint32_t avail = acc_ring_avail_deq(q);
> + uint32_t aq_dequeued = 0;
> + uint16_t i;
> + uint16_t dequeued_cbs = 0;
> + struct rte_bbdev_dec_op *op;
> + int ret;
> +
> +#ifdef RTE_LIBRTE_BBDEV_DEBUG
> + if (unlikely(ops == 0 && q == NULL))
> + return 0;
It makes the debug build to fail silently. Checking for pointers
validity is fine, but you want to emit a warning if it happens.
> +#endif
q is already dereferenced to get avail. acc_ring_avail_deq(q) should be
called after the check.
> +
> + dequeue_num = (avail < num) ? avail : num;
> +
> + for (i = 0; i < dequeue_num; ++i) {
> + op = (q->ring_addr + ((q->sw_ring_tail + dequeued_cbs)
> + & q->sw_ring_wrap_mask))->req.op_addr;
> + if (op->turbo_dec.code_block_mode == RTE_BBDEV_TRANSPORT_BLOCK)
> + ret = dequeue_dec_one_op_tb(q, &ops[i], dequeued_cbs,
> + &aq_dequeued);
> + else
> + ret = dequeue_dec_one_op_cb(q_data, q, &ops[i],
> + dequeued_cbs, &aq_dequeued);
> +
> + if (ret <= 0)
> + break;
> + dequeued_cbs += ret;
> + }
> +
> + q->aq_dequeued += aq_dequeued;
> + q->sw_ring_tail += dequeued_cbs;
> +
> + /* Update enqueue stats */
> + q_data->queue_stats.dequeued_count += i;
> +
> + return i;
> +}
> +
> /* Dequeue decode operations from ACC200 device. */
> static uint16_t
> acc200_dequeue_ldpc_dec(struct rte_bbdev_queue_data *q_data,
> @@ -2067,6 +2909,10 @@ acc200_bbdev_init(struct rte_bbdev *dev, struct rte_pci_driver *drv)
> struct rte_pci_device *pci_dev = RTE_DEV_TO_PCI(dev->device);
>
> dev->dev_ops = &acc200_bbdev_ops;
> + dev->enqueue_enc_ops = acc200_enqueue_enc;
> + dev->enqueue_dec_ops = acc200_enqueue_dec;
> + dev->dequeue_enc_ops = acc200_dequeue_enc;
> + dev->dequeue_dec_ops = acc200_dequeue_dec;
> dev->enqueue_ldpc_enc_ops = acc200_enqueue_ldpc_enc;
> dev->enqueue_ldpc_dec_ops = acc200_enqueue_ldpc_dec;
> dev->dequeue_ldpc_enc_ops = acc200_dequeue_ldpc_enc;
^ permalink raw reply [flat|nested] 28+ messages in thread* RE: [PATCH v6 09/14] baseband/acc: add LTE processing functions
2022-09-27 13:43 ` Maxime Coquelin
@ 2022-09-29 21:13 ` Chautru, Nicolas
0 siblings, 0 replies; 28+ messages in thread
From: Chautru, Nicolas @ 2022-09-29 21:13 UTC (permalink / raw)
To: Maxime Coquelin, dev, thomas
Cc: trix, mdr, Richardson, Bruce, hemant.agrawal, david.marchand,
stephen, Vargas, Hernan
Thanks Maxime,
> -----Original Message-----
> From: Maxime Coquelin <maxime.coquelin@redhat.com>
> Sent: Tuesday, September 27, 2022 6:43 AM
> To: Chautru, Nicolas <nicolas.chautru@intel.com>; dev@dpdk.org;
> thomas@monjalon.net
> Cc: trix@redhat.com; mdr@ashroe.eu; Richardson, Bruce
> <bruce.richardson@intel.com>; hemant.agrawal@nxp.com;
> david.marchand@redhat.com; stephen@networkplumber.org; Vargas, Hernan
> <hernan.vargas@intel.com>
> Subject: Re: [PATCH v6 09/14] baseband/acc: add LTE processing functions
>
>
>
> On 9/24/22 02:50, Nicolas Chautru wrote:
> > From: Nic Chautru <nicolas.chautru@intel.com>
> >
> > Add functions and capability for 4G FEC
> >
> > Signed-off-by: Nic Chautru <nicolas.chautru@intel.com>
> > ---
> > drivers/baseband/acc/rte_acc200_pmd.c | 854
> +++++++++++++++++++++++++-
> > 1 file changed, 850 insertions(+), 4 deletions(-)
> >
> > diff --git a/drivers/baseband/acc/rte_acc200_pmd.c
> > b/drivers/baseband/acc/rte_acc200_pmd.c
> > index 229e5fba86..e8901c60d6 100644
> > --- a/drivers/baseband/acc/rte_acc200_pmd.c
> > +++ b/drivers/baseband/acc/rte_acc200_pmd.c
> > @@ -658,6 +658,46 @@ acc200_dev_info_get(struct rte_bbdev *dev,
> > struct acc_device *d = dev->data->dev_private;
> > int i;
> > static const struct rte_bbdev_op_cap bbdev_capabilities[] = {
> > + {
> > + .type = RTE_BBDEV_OP_TURBO_DEC,
> > + .cap.turbo_dec = {
> > + .capability_flags =
> > +
> RTE_BBDEV_TURBO_SUBBLOCK_DEINTERLEAVE |
> > + RTE_BBDEV_TURBO_CRC_TYPE_24B |
> > + RTE_BBDEV_TURBO_EQUALIZER |
> > +
> RTE_BBDEV_TURBO_SOFT_OUT_SATURATE |
> > +
> RTE_BBDEV_TURBO_HALF_ITERATION_EVEN |
> > +
> RTE_BBDEV_TURBO_CONTINUE_CRC_MATCH |
> > + RTE_BBDEV_TURBO_SOFT_OUTPUT |
> > +
> RTE_BBDEV_TURBO_EARLY_TERMINATION |
> > +
> RTE_BBDEV_TURBO_NEG_LLR_1_BIT_IN |
> > +
> RTE_BBDEV_TURBO_NEG_LLR_1_BIT_SOFT_OUT |
> > + RTE_BBDEV_TURBO_MAP_DEC |
> > +
> RTE_BBDEV_TURBO_DEC_TB_CRC_24B_KEEP |
> > +
> RTE_BBDEV_TURBO_DEC_SCATTER_GATHER,
> > + .max_llr_modulus = INT8_MAX,
> > + .num_buffers_src =
> > +
> RTE_BBDEV_TURBO_MAX_CODE_BLOCKS,
> > + .num_buffers_hard_out =
> > +
> RTE_BBDEV_TURBO_MAX_CODE_BLOCKS,
> > + .num_buffers_soft_out =
> > +
> RTE_BBDEV_TURBO_MAX_CODE_BLOCKS,
> > + }
> > + },
> > + {
> > + .type = RTE_BBDEV_OP_TURBO_ENC,
> > + .cap.turbo_enc = {
> > + .capability_flags =
> > +
> RTE_BBDEV_TURBO_CRC_24B_ATTACH |
> > +
> RTE_BBDEV_TURBO_RV_INDEX_BYPASS |
> > + RTE_BBDEV_TURBO_RATE_MATCH |
> > +
> RTE_BBDEV_TURBO_ENC_SCATTER_GATHER,
> > + .num_buffers_src =
> > +
> RTE_BBDEV_TURBO_MAX_CODE_BLOCKS,
> > + .num_buffers_dst =
> > +
> RTE_BBDEV_TURBO_MAX_CODE_BLOCKS,
> > + }
> > + },
> > {
> > .type = RTE_BBDEV_OP_LDPC_ENC,
> > .cap.ldpc_enc = {
> > @@ -709,15 +749,17 @@ acc200_dev_info_get(struct rte_bbdev *dev,
> >
> > /* Exposed number of queues */
> > dev_info->num_queues[RTE_BBDEV_OP_NONE] = 0;
> > - dev_info->num_queues[RTE_BBDEV_OP_TURBO_DEC] = 0;
> > - dev_info->num_queues[RTE_BBDEV_OP_TURBO_ENC] = 0;
> > + dev_info->num_queues[RTE_BBDEV_OP_TURBO_DEC] = d-
> >acc_conf.q_ul_4g.num_aqs_per_groups *
> > + d->acc_conf.q_ul_4g.num_qgroups;
> > + dev_info->num_queues[RTE_BBDEV_OP_TURBO_ENC] = d-
> >acc_conf.q_dl_4g.num_aqs_per_groups *
> > + d->acc_conf.q_dl_4g.num_qgroups;
> > dev_info->num_queues[RTE_BBDEV_OP_LDPC_DEC] = d-
> >acc_conf.q_ul_5g.num_aqs_per_groups *
> > d->acc_conf.q_ul_5g.num_qgroups;
> > dev_info->num_queues[RTE_BBDEV_OP_LDPC_ENC] = d-
> >acc_conf.q_dl_5g.num_aqs_per_groups *
> > d->acc_conf.q_dl_5g.num_qgroups;
> > dev_info->num_queues[RTE_BBDEV_OP_FFT] = 0;
> > - dev_info->queue_priority[RTE_BBDEV_OP_TURBO_DEC] = 0;
> > - dev_info->queue_priority[RTE_BBDEV_OP_TURBO_ENC] = 0;
> > + dev_info->queue_priority[RTE_BBDEV_OP_TURBO_DEC] = d-
> >acc_conf.q_ul_4g.num_qgroups;
> > + dev_info->queue_priority[RTE_BBDEV_OP_TURBO_ENC] =
> > +d->acc_conf.q_dl_4g.num_qgroups;
> > dev_info->queue_priority[RTE_BBDEV_OP_LDPC_DEC] = d-
> >acc_conf.q_ul_5g.num_qgroups;
> > dev_info->queue_priority[RTE_BBDEV_OP_LDPC_ENC] = d-
> >acc_conf.q_dl_5g.num_qgroups;
> > dev_info->queue_priority[RTE_BBDEV_OP_FFT] = 0; @@ -762,6
> +804,70
> > @@ static struct rte_pci_id pci_id_acc200_vf_map[] = {
> > {.device_id = 0},
> > };
> >
> > +/* Fill in a frame control word for turbo decoding. */ static inline
> > +void acc200_fcw_td_fill(const struct rte_bbdev_dec_op *op, struct
> > +acc_fcw_td *fcw) {
> > + fcw->fcw_ver = 1;
> > + fcw->num_maps = ACC_FCW_TD_AUTOMAP;
> > + fcw->bypass_sb_deint = !check_bit(op->turbo_dec.op_flags,
> > + RTE_BBDEV_TURBO_SUBBLOCK_DEINTERLEAVE);
> > + if (op->turbo_dec.code_block_mode ==
> RTE_BBDEV_TRANSPORT_BLOCK) {
> > + /* FIXME for TB block */
> > + fcw->k_pos = op->turbo_dec.tb_params.k_pos;
> > + fcw->k_neg = op->turbo_dec.tb_params.k_neg;
> > + } else {
> > + fcw->k_pos = op->turbo_dec.cb_params.k;
> > + fcw->k_neg = op->turbo_dec.cb_params.k;
> > + }
> > + fcw->c = 1;
> > + fcw->c_neg = 1;
> > + if (check_bit(op->turbo_dec.op_flags,
> RTE_BBDEV_TURBO_SOFT_OUTPUT)) {
> > + fcw->soft_output_en = 1;
> > + fcw->sw_soft_out_dis = 0;
> > + fcw->sw_et_cont = check_bit(op->turbo_dec.op_flags,
> > +
> RTE_BBDEV_TURBO_CONTINUE_CRC_MATCH);
> > + fcw->sw_soft_out_saturation = check_bit(op-
> >turbo_dec.op_flags,
> > + RTE_BBDEV_TURBO_SOFT_OUT_SATURATE);
> > + if (check_bit(op->turbo_dec.op_flags,
> > + RTE_BBDEV_TURBO_EQUALIZER)) {
> > + fcw->bypass_teq = 0;
> > + fcw->ea = op->turbo_dec.cb_params.e;
> > + fcw->eb = op->turbo_dec.cb_params.e;
> > + if (op->turbo_dec.rv_index == 0)
> > + fcw->k0_start_col = ACC_FCW_TD_RVIDX_0;
> > + else if (op->turbo_dec.rv_index == 1)
> > + fcw->k0_start_col = ACC_FCW_TD_RVIDX_1;
> > + else if (op->turbo_dec.rv_index == 2)
> > + fcw->k0_start_col = ACC_FCW_TD_RVIDX_2;
> > + else
> > + fcw->k0_start_col = ACC_FCW_TD_RVIDX_3;
> > + } else {
> > + fcw->bypass_teq = 1;
> > + fcw->eb = 64; /* avoid undefined value */
> > + }
> > + } else {
> > + fcw->soft_output_en = 0;
> > + fcw->sw_soft_out_dis = 1;
> > + fcw->bypass_teq = 0;
> > + }
> > +
> > + fcw->code_block_mode = 1; /* FIXME */
> > + fcw->turbo_crc_type = check_bit(op->turbo_dec.op_flags,
> > + RTE_BBDEV_TURBO_CRC_TYPE_24B);
> > +
> > + fcw->ext_td_cold_reg_en = 1;
> > + fcw->raw_decoder_input_on = 0;
> > + fcw->max_iter = RTE_MAX((uint8_t) op->turbo_dec.iter_max, 2);
> > + fcw->min_iter = 2;
> > + fcw->half_iter_on = !check_bit(op->turbo_dec.op_flags,
> > + RTE_BBDEV_TURBO_HALF_ITERATION_EVEN);
> > +
> > + fcw->early_stop_en = check_bit(op->turbo_dec.op_flags,
> > + RTE_BBDEV_TURBO_EARLY_TERMINATION) & !fcw-
> >soft_output_en;
> > + fcw->ext_scale = 0xF;
> > +}
> > +
> > /* Fill in a frame control word for LDPC decoding. */
> > static inline void
> > acc200_fcw_ld_fill(struct rte_bbdev_dec_op *op, struct acc_fcw_ld
> > *fcw, @@ -887,6 +993,205 @@ acc200_fcw_ld_fill(struct rte_bbdev_dec_op
> *op, struct acc_fcw_ld *fcw,
> > fcw->tb_crc_select = 1;
> > }
> >
> > +static inline int
> > +acc200_dma_desc_te_fill(struct rte_bbdev_enc_op *op,
> > + struct acc_dma_req_desc *desc, struct rte_mbuf **input,
> > + struct rte_mbuf *output, uint32_t *in_offset,
> > + uint32_t *out_offset, uint32_t *out_length,
> > + uint32_t *mbuf_total_left, uint32_t *seg_total_left, uint8_t r)
> {
> > + int next_triplet = 1; /* FCW already done */
> > + uint32_t e, ea, eb, length;
> > + uint16_t k, k_neg, k_pos;
> > + uint8_t cab, c_neg;
> > +
> > + desc->word0 = ACC_DMA_DESC_TYPE;
> > + desc->word1 = 0; /**< Timestamp could be disabled */
> > + desc->word2 = 0;
> > + desc->word3 = 0;
> > + desc->numCBs = 1;
> > +
> > + if (op->turbo_enc.code_block_mode ==
> RTE_BBDEV_TRANSPORT_BLOCK) {
> > + ea = op->turbo_enc.tb_params.ea;
> > + eb = op->turbo_enc.tb_params.eb;
> > + cab = op->turbo_enc.tb_params.cab;
> > + k_neg = op->turbo_enc.tb_params.k_neg;
> > + k_pos = op->turbo_enc.tb_params.k_pos;
> > + c_neg = op->turbo_enc.tb_params.c_neg;
> > + e = (r < cab) ? ea : eb;
> > + k = (r < c_neg) ? k_neg : k_pos;
> > + } else {
> > + e = op->turbo_enc.cb_params.e;
> > + k = op->turbo_enc.cb_params.k;
> > + }
> > +
> > + if (check_bit(op->turbo_enc.op_flags,
> RTE_BBDEV_TURBO_CRC_24B_ATTACH))
> > + length = (k - 24) >> 3;
> > + else
> > + length = k >> 3;
> > +
> > + if (unlikely((*mbuf_total_left == 0) || (*mbuf_total_left < length))) {
> > + rte_bbdev_log(ERR,
> > + "Mismatch between mbuf length and included
> CB sizes: mbuf len %u, cb len %u",
> > + *mbuf_total_left, length);
> > + return -1;
> > + }
> > +
> > + next_triplet = acc_dma_fill_blk_type_in(desc, input, in_offset,
> > + length, seg_total_left, next_triplet,
> > + check_bit(op->turbo_enc.op_flags,
> > + RTE_BBDEV_TURBO_ENC_SCATTER_GATHER));
> > + if (unlikely(next_triplet < 0)) {
> > + rte_bbdev_log(ERR,
> > + "Mismatch between data to process and mbuf
> data length in bbdev_op: %p",
> > + op);
> > + return -1;
> > + }
> > + desc->data_ptrs[next_triplet - 1].last = 1;
> > + desc->m2dlen = next_triplet;
> > + *mbuf_total_left -= length;
> > +
> > + /* Set output length */
> > + if (check_bit(op->turbo_enc.op_flags,
> RTE_BBDEV_TURBO_RATE_MATCH))
> > + /* Integer round up division by 8 */
> > + *out_length = (e + 7) >> 3;
> > + else
> > + *out_length = (k >> 3) * 3 + 2;
> > +
> > + next_triplet = acc_dma_fill_blk_type(desc, output, *out_offset,
> > + *out_length, next_triplet,
> ACC_DMA_BLKID_OUT_ENC);
> > + if (unlikely(next_triplet < 0)) {
> > + rte_bbdev_log(ERR,
> > + "Mismatch between data to process and mbuf
> data length in bbdev_op: %p",
> > + op);
> > + return -1;
> > + }
> > + op->turbo_enc.output.length += *out_length;
> > + *out_offset += *out_length;
> > + desc->data_ptrs[next_triplet - 1].last = 1;
> > + desc->d2mlen = next_triplet - desc->m2dlen;
> > +
> > + desc->op_addr = op;
> > +
> > + return 0;
> > +}
> > +
> > +static inline int
> > +acc200_dma_desc_td_fill(struct rte_bbdev_dec_op *op,
> > + struct acc_dma_req_desc *desc, struct rte_mbuf **input,
> > + struct rte_mbuf *h_output, struct rte_mbuf *s_output,
> > + uint32_t *in_offset, uint32_t *h_out_offset,
> > + uint32_t *s_out_offset, uint32_t *h_out_length,
> > + uint32_t *s_out_length, uint32_t *mbuf_total_left,
> > + uint32_t *seg_total_left, uint8_t r) {
> > + int next_triplet = 1; /* FCW already done */
> > + uint16_t k;
> > + uint16_t crc24_overlap = 0;
> > + uint32_t e, kw;
> > +
> > + desc->word0 = ACC_DMA_DESC_TYPE;
> > + desc->word1 = 0; /**< Timestamp could be disabled */
> > + desc->word2 = 0;
> > + desc->word3 = 0;
> > + desc->numCBs = 1;
> > +
> > + if (op->turbo_dec.code_block_mode ==
> RTE_BBDEV_TRANSPORT_BLOCK) {
> > + k = (r < op->turbo_dec.tb_params.c_neg)
> > + ? op->turbo_dec.tb_params.k_neg
> > + : op->turbo_dec.tb_params.k_pos;
> > + e = (r < op->turbo_dec.tb_params.cab)
> > + ? op->turbo_dec.tb_params.ea
> > + : op->turbo_dec.tb_params.eb;
> > + } else {
> > + k = op->turbo_dec.cb_params.k;
> > + e = op->turbo_dec.cb_params.e;
> > + }
> > +
> > + if ((op->turbo_dec.code_block_mode ==
> RTE_BBDEV_TRANSPORT_BLOCK)
> > + && !check_bit(op->turbo_dec.op_flags,
> > + RTE_BBDEV_TURBO_DEC_TB_CRC_24B_KEEP))
> > + crc24_overlap = 24;
> > +
> > + /* Calculates circular buffer size.
> > + * According to 3gpp 36.212 section 5.1.4.2
> > + * Kw = 3 * Kpi,
> > + * where:
> > + * Kpi = nCol * nRow
> > + * where nCol is 32 and nRow can be calculated from:
> > + * D =< nCol * nRow
> > + * where D is the size of each output from turbo encoder block (k + 4).
> > + */
> > + kw = RTE_ALIGN_CEIL(k + 4, 32) * 3;
> > +
> > + if (unlikely((*mbuf_total_left == 0) || (*mbuf_total_left < kw))) {
> > + rte_bbdev_log(ERR,
> > + "Mismatch between mbuf length and included
> CB sizes: mbuf len %u, cb len %u",
> > + *mbuf_total_left, kw);
> > + return -1;
> > + }
> > +
> > + next_triplet = acc_dma_fill_blk_type_in(desc, input, in_offset, kw,
> > + seg_total_left, next_triplet,
> > + check_bit(op->turbo_dec.op_flags,
> > + RTE_BBDEV_TURBO_DEC_SCATTER_GATHER));
> > + if (unlikely(next_triplet < 0)) {
> > + rte_bbdev_log(ERR,
> > + "Mismatch between data to process and mbuf
> data length in bbdev_op: %p",
> > + op);
> > + return -1;
> > + }
> > + desc->data_ptrs[next_triplet - 1].last = 1;
> > + desc->m2dlen = next_triplet;
> > + *mbuf_total_left -= kw;
> > + *h_out_length = ((k - crc24_overlap) >> 3);
> > + next_triplet = acc_dma_fill_blk_type(
> > + desc, h_output, *h_out_offset,
> > + *h_out_length, next_triplet,
> ACC_DMA_BLKID_OUT_HARD);
> > + if (unlikely(next_triplet < 0)) {
> > + rte_bbdev_log(ERR,
> > + "Mismatch between data to process and mbuf
> data length in bbdev_op: %p",
> > + op);
> > + return -1;
> > + }
> > +
> > + op->turbo_dec.hard_output.length += *h_out_length;
> > + *h_out_offset += *h_out_length;
> > +
> > + /* Soft output */
> > + if (check_bit(op->turbo_dec.op_flags,
> RTE_BBDEV_TURBO_SOFT_OUTPUT)) {
> > + if (op->turbo_dec.soft_output.data == 0) {
> > + rte_bbdev_log(ERR, "Soft output is not defined");
> > + return -1;
> > + }
> > + if (check_bit(op->turbo_dec.op_flags,
> > + RTE_BBDEV_TURBO_EQUALIZER))
> > + *s_out_length = e;
> > + else
> > + *s_out_length = (k * 3) + 12;
> > +
> > + next_triplet = acc_dma_fill_blk_type(desc, s_output,
> > + *s_out_offset, *s_out_length, next_triplet,
> > + ACC_DMA_BLKID_OUT_SOFT);
> > + if (unlikely(next_triplet < 0)) {
> > + rte_bbdev_log(ERR,
> > + "Mismatch between data to process
> and mbuf data length in bbdev_op: %p",
> > + op);
> > + return -1;
> > + }
> > +
> > + op->turbo_dec.soft_output.length += *s_out_length;
> > + *s_out_offset += *s_out_length;
> > + }
> > +
> > + desc->data_ptrs[next_triplet - 1].last = 1;
> > + desc->d2mlen = next_triplet - desc->m2dlen;
> > +
> > + desc->op_addr = op;
> > +
> > + return 0;
> > +}
> > +
> > static inline int
> > acc200_dma_desc_ld_fill(struct rte_bbdev_dec_op *op,
> > struct acc_dma_req_desc *desc,
> > @@ -1059,6 +1364,49 @@ acc200_dma_desc_ld_update(struct
> rte_bbdev_dec_op *op,
> > desc->op_addr = op;
> > }
> >
> > +/* Enqueue one encode operations for ACC200 device in CB mode */
> > +static inline int enqueue_enc_one_op_cb(struct acc_queue *q, struct
> > +rte_bbdev_enc_op *op,
> > + uint16_t total_enqueued_cbs)
> > +{
> > + union acc_dma_desc *desc = NULL;
> > + int ret;
> > + uint32_t in_offset, out_offset, out_length, mbuf_total_left,
> > + seg_total_left;
> > + struct rte_mbuf *input, *output_head, *output;
> > +
> > + uint16_t desc_idx = ((q->sw_ring_head + total_enqueued_cbs)
> > + & q->sw_ring_wrap_mask);
> > + desc = q->ring_addr + desc_idx;
> > + acc_fcw_te_fill(op, &desc->req.fcw_te);
> > +
> > + input = op->turbo_enc.input.data;
> > + output_head = output = op->turbo_enc.output.data;
> > + in_offset = op->turbo_enc.input.offset;
> > + out_offset = op->turbo_enc.output.offset;
> > + out_length = 0;
> > + mbuf_total_left = op->turbo_enc.input.length;
> > + seg_total_left = rte_pktmbuf_data_len(op->turbo_enc.input.data)
> > + - in_offset;
> > +
> > + ret = acc200_dma_desc_te_fill(op, &desc->req, &input, output,
> > + &in_offset, &out_offset, &out_length,
> &mbuf_total_left,
> > + &seg_total_left, 0);
> > +
> > + if (unlikely(ret < 0))
> > + return ret;
> > +
> > + mbuf_append(output_head, output, out_length);
> > +
> > +#ifdef RTE_LIBRTE_BBDEV_DEBUG
> > + rte_memdump(stderr, "FCW", &desc->req.fcw_te,
> > + sizeof(desc->req.fcw_te) - 8);
> > + rte_memdump(stderr, "Req Desc.", desc, sizeof(*desc)); #endif
> > + /* One CB (one op) was successfully prepared to enqueue */
> > + return 1;
> > +}
> > +
> > /* Enqueue one encode operations for ACC200 device in CB mode
> > * multiplexed on the same descriptor
> > */
> > @@ -1175,6 +1523,78 @@ enqueue_ldpc_enc_part_tb(struct acc_queue *q,
> > struct rte_bbdev_enc_op *op,
> >
> > }
> >
> > +/* Enqueue one encode operations for ACC200 device in TB mode. */
> > +static inline int enqueue_enc_one_op_tb(struct acc_queue *q, struct
> > +rte_bbdev_enc_op *op,
> > + uint16_t total_enqueued_cbs, uint8_t cbs_in_tb) {
> > + union acc_dma_desc *desc = NULL;
> > + int ret;
> > + uint8_t r, c;
> > + uint32_t in_offset, out_offset, out_length, mbuf_total_left,
> > + seg_total_left;
> > + struct rte_mbuf *input, *output_head, *output;
> > + uint16_t current_enqueued_cbs = 0;
> > +
> > + uint16_t desc_idx = ((q->sw_ring_head + total_enqueued_cbs)
> > + & q->sw_ring_wrap_mask);
> > + desc = q->ring_addr + desc_idx;
> > + uint64_t fcw_offset = (desc_idx << 8) + ACC_DESC_FCW_OFFSET;
> > + acc_fcw_te_fill(op, &desc->req.fcw_te);
> > +
> > + input = op->turbo_enc.input.data;
> > + output_head = output = op->turbo_enc.output.data;
> > + in_offset = op->turbo_enc.input.offset;
> > + out_offset = op->turbo_enc.output.offset;
> > + out_length = 0;
> > + mbuf_total_left = op->turbo_enc.input.length;
> > +
> > + c = op->turbo_enc.tb_params.c;
> > + r = op->turbo_enc.tb_params.r;
> > +
> > + while (mbuf_total_left > 0 && r < c) {
> > + seg_total_left = rte_pktmbuf_data_len(input) - in_offset;
> > + /* Set up DMA descriptor */
> > + desc = q->ring_addr + ((q->sw_ring_head +
> total_enqueued_cbs)
> > + & q->sw_ring_wrap_mask);
> > + desc->req.data_ptrs[0].address = q->ring_addr_iova +
> fcw_offset;
> > + desc->req.data_ptrs[0].blen = ACC_FCW_TE_BLEN;
> > +
> > + ret = acc200_dma_desc_te_fill(op, &desc->req, &input,
> output,
> > + &in_offset, &out_offset, &out_length,
> > + &mbuf_total_left, &seg_total_left, r);
> > + if (unlikely(ret < 0))
> > + return ret;
> > + mbuf_append(output_head, output, out_length);
> > +
> > + /* Set total number of CBs in TB */
> > + desc->req.cbs_in_tb = cbs_in_tb;
> > +#ifdef RTE_LIBRTE_BBDEV_DEBUG
> > + rte_memdump(stderr, "FCW", &desc->req.fcw_te,
> > + sizeof(desc->req.fcw_te) - 8);
> > + rte_memdump(stderr, "Req Desc.", desc, sizeof(*desc)); #endif
> > +
> > + if (seg_total_left == 0) {
> > + /* Go to the next mbuf */
> > + input = input->next;
> > + in_offset = 0;
> > + output = output->next;
> > + out_offset = 0;
> > + }
> > +
> > + total_enqueued_cbs++;
> > + current_enqueued_cbs++;
> > + r++;
> > + }
> > +
> > + /* Set SDone on last CB descriptor for TB mode. */
> > + desc->req.sdone_enable = 1;
> > + desc->req.irq_enable = q->irq_enable;
> > +
> > + return current_enqueued_cbs;
> > +}
> > +
> > /* Enqueue one encode operations for ACC200 device in TB mode.
> > * returns the number of descs used
> > */
> > @@ -1240,6 +1660,62 @@ enqueue_ldpc_enc_one_op_tb(struct acc_queue
> *q, struct rte_bbdev_enc_op *op,
> > return return_descs;
> > }
> >
> > +/** Enqueue one decode operations for ACC200 device in CB mode */
> > +static inline int enqueue_dec_one_op_cb(struct acc_queue *q, struct
> > +rte_bbdev_dec_op *op,
> > + uint16_t total_enqueued_cbs)
> > +{
> > + union acc_dma_desc *desc = NULL;
> > + int ret;
> > + uint32_t in_offset, h_out_offset, s_out_offset, s_out_length,
> > + h_out_length, mbuf_total_left, seg_total_left;
> > + struct rte_mbuf *input, *h_output_head, *h_output,
> > + *s_output_head, *s_output;
> > +
> > + uint16_t desc_idx = ((q->sw_ring_head + total_enqueued_cbs)
> > + & q->sw_ring_wrap_mask);
> > + desc = q->ring_addr + desc_idx;
> > + acc200_fcw_td_fill(op, &desc->req.fcw_td);
> > +
> > + input = op->turbo_dec.input.data;
> > + h_output_head = h_output = op->turbo_dec.hard_output.data;
> > + s_output_head = s_output = op->turbo_dec.soft_output.data;
> > + in_offset = op->turbo_dec.input.offset;
> > + h_out_offset = op->turbo_dec.hard_output.offset;
> > + s_out_offset = op->turbo_dec.soft_output.offset;
> > + h_out_length = s_out_length = 0;
> > + mbuf_total_left = op->turbo_dec.input.length;
> > + seg_total_left = rte_pktmbuf_data_len(input) - in_offset;
> > +
> > + /* Set up DMA descriptor */
> > + desc = q->ring_addr + ((q->sw_ring_head + total_enqueued_cbs)
> > + & q->sw_ring_wrap_mask);
> > +
> > + ret = acc200_dma_desc_td_fill(op, &desc->req, &input, h_output,
> > + s_output, &in_offset, &h_out_offset, &s_out_offset,
> > + &h_out_length, &s_out_length, &mbuf_total_left,
> > + &seg_total_left, 0);
> > +
> > + if (unlikely(ret < 0))
> > + return ret;
> > +
> > + /* Hard output */
> > + mbuf_append(h_output_head, h_output, h_out_length);
> > +
> > + /* Soft output */
> > + if (check_bit(op->turbo_dec.op_flags,
> RTE_BBDEV_TURBO_SOFT_OUTPUT))
> > + mbuf_append(s_output_head, s_output, s_out_length);
> > +
> > +#ifdef RTE_LIBRTE_BBDEV_DEBUG
> > + rte_memdump(stderr, "FCW", &desc->req.fcw_td,
> > + sizeof(desc->req.fcw_td));
> > + rte_memdump(stderr, "Req Desc.", desc, sizeof(*desc)); #endif
> > +
> > + /* One CB (one op) was successfully prepared to enqueue */
> > + return 1;
> > +}
> > +
> > /** Enqueue one decode operations for ACC200 device in CB mode */
> > static inline int
> > enqueue_ldpc_dec_one_op_cb(struct acc_queue *q, struct
> > rte_bbdev_dec_op *op, @@ -1437,6 +1913,139 @@
> enqueue_ldpc_dec_one_op_tb(struct acc_queue *q, struct rte_bbdev_dec_op
> *op,
> > return current_enqueued_cbs;
> > }
> >
> > +/* Enqueue one decode operations for ACC200 device in TB mode */
> > +static inline int enqueue_dec_one_op_tb(struct acc_queue *q, struct
> > +rte_bbdev_dec_op *op,
> > + uint16_t total_enqueued_cbs, uint8_t cbs_in_tb) {
> > + union acc_dma_desc *desc = NULL;
> > + int ret;
> > + uint8_t r, c;
> > + uint32_t in_offset, h_out_offset, s_out_offset, s_out_length,
> > + h_out_length, mbuf_total_left, seg_total_left;
> > + struct rte_mbuf *input, *h_output_head, *h_output,
> > + *s_output_head, *s_output;
> > + uint16_t current_enqueued_cbs = 0;
> > +
> > + uint16_t desc_idx = ((q->sw_ring_head + total_enqueued_cbs)
> > + & q->sw_ring_wrap_mask);
> > + desc = q->ring_addr + desc_idx;
> > + uint64_t fcw_offset = (desc_idx << 8) + ACC_DESC_FCW_OFFSET;
> > + acc200_fcw_td_fill(op, &desc->req.fcw_td);
> > +
> > + input = op->turbo_dec.input.data;
> > + h_output_head = h_output = op->turbo_dec.hard_output.data;
> > + s_output_head = s_output = op->turbo_dec.soft_output.data;
> > + in_offset = op->turbo_dec.input.offset;
> > + h_out_offset = op->turbo_dec.hard_output.offset;
> > + s_out_offset = op->turbo_dec.soft_output.offset;
> > + h_out_length = s_out_length = 0;
> > + mbuf_total_left = op->turbo_dec.input.length;
> > + c = op->turbo_dec.tb_params.c;
> > + r = op->turbo_dec.tb_params.r;
> > +
> > + while (mbuf_total_left > 0 && r < c) {
> > +
> > + seg_total_left = rte_pktmbuf_data_len(input) - in_offset;
> > +
> > + /* Set up DMA descriptor */
> > + desc = q->ring_addr + ((q->sw_ring_head +
> total_enqueued_cbs)
> > + & q->sw_ring_wrap_mask);
> > + desc->req.data_ptrs[0].address = q->ring_addr_iova +
> fcw_offset;
> > + desc->req.data_ptrs[0].blen = ACC_FCW_TD_BLEN;
> > + ret = acc200_dma_desc_td_fill(op, &desc->req, &input,
> > + h_output, s_output, &in_offset,
> &h_out_offset,
> > + &s_out_offset, &h_out_length,
> &s_out_length,
> > + &mbuf_total_left, &seg_total_left, r);
> > +
> > + if (unlikely(ret < 0))
> > + return ret;
> > +
> > + /* Hard output */
> > + mbuf_append(h_output_head, h_output, h_out_length);
> > +
> > + /* Soft output */
> > + if (check_bit(op->turbo_dec.op_flags,
> > + RTE_BBDEV_TURBO_SOFT_OUTPUT))
> > + mbuf_append(s_output_head, s_output,
> s_out_length);
> > +
> > + /* Set total number of CBs in TB */
> > + desc->req.cbs_in_tb = cbs_in_tb;
> > +#ifdef RTE_LIBRTE_BBDEV_DEBUG
> > + rte_memdump(stderr, "FCW", &desc->req.fcw_td,
> > + sizeof(desc->req.fcw_td) - 8);
> > + rte_memdump(stderr, "Req Desc.", desc, sizeof(*desc)); #endif
> > +
> > + if (seg_total_left == 0) {
> > + /* Go to the next mbuf */
> > + input = input->next;
> > + in_offset = 0;
> > + h_output = h_output->next;
> > + h_out_offset = 0;
> > +
> > + if (check_bit(op->turbo_dec.op_flags,
> > + RTE_BBDEV_TURBO_SOFT_OUTPUT))
> {
> > + s_output = s_output->next;
> > + s_out_offset = 0;
> > + }
> > + }
> > +
> > + total_enqueued_cbs++;
> > + current_enqueued_cbs++;
> > + r++;
> > + }
> > +
> > + /* Set SDone on last CB descriptor for TB mode */
> > + desc->req.sdone_enable = 1;
> > + desc->req.irq_enable = q->irq_enable;
> > +
> > + return current_enqueued_cbs;
> > +}
> > +
> > +/* Enqueue encode operations for ACC200 device in CB mode. */ static
> > +uint16_t acc200_enqueue_enc_cb(struct rte_bbdev_queue_data *q_data,
> > + struct rte_bbdev_enc_op **ops, uint16_t num) {
> > + struct acc_queue *q = q_data->queue_private;
> > + int32_t avail = acc_ring_avail_enq(q);
> > + uint16_t i;
> > + union acc_dma_desc *desc;
> > + int ret;
> > +
> > + for (i = 0; i < num; ++i) {
> > + /* Check if there are available space for further processing */
> > + if (unlikely(avail - 1 < 0)) {
> > + acc_enqueue_ring_full(q_data);
> > + break;
> > + }
> > + avail -= 1;
> > +
> > + ret = enqueue_enc_one_op_cb(q, ops[i], i);
> > + if (ret < 0) {
> > + acc_enqueue_invalid(q_data);
> > + break;
> > + }
> > + }
> > +
> > + if (unlikely(i == 0))
> > + return 0; /* Nothing to enqueue */
> > +
> > + /* Set SDone in last CB in enqueued ops for CB mode*/
> > + desc = q->ring_addr + ((q->sw_ring_head + i - 1)
> > + & q->sw_ring_wrap_mask);
> > + desc->req.sdone_enable = 1;
> > + desc->req.irq_enable = q->irq_enable;
> > +
> > + acc_dma_enqueue(q, i, &q_data->queue_stats);
> > +
> > + /* Update stats */
> > + q_data->queue_stats.enqueued_count += i;
> > + q_data->queue_stats.enqueue_err_count += num - i;
> > + return i;
> > +}
> > +
> > /** Enqueue encode operations for ACC200 device in CB mode. */
> > static inline uint16_t
> > acc200_enqueue_ldpc_enc_cb(struct rte_bbdev_queue_data *q_data, @@
> > -1485,6 +2094,45 @@ acc200_enqueue_ldpc_enc_cb(struct
> rte_bbdev_queue_data *q_data,
> > return i;
> > }
> >
> > +/* Enqueue encode operations for ACC200 device in TB mode. */ static
> > +uint16_t acc200_enqueue_enc_tb(struct rte_bbdev_queue_data *q_data,
> > + struct rte_bbdev_enc_op **ops, uint16_t num) {
> > + struct acc_queue *q = q_data->queue_private;
> > + int32_t avail = acc_ring_avail_enq(q);
> > + uint16_t i, enqueued_cbs = 0;
> > + uint8_t cbs_in_tb;
> > + int ret;
> > +
> > + for (i = 0; i < num; ++i) {
> > + cbs_in_tb = get_num_cbs_in_tb_enc(&ops[i]->turbo_enc);
> > + /* Check if there are available space for further processing */
> > + if (unlikely((avail - cbs_in_tb < 0) || (cbs_in_tb == 0))) {
> > + acc_enqueue_ring_full(q_data);
> > + break;
> > + }
> > + avail -= cbs_in_tb;
> > +
> > + ret = enqueue_enc_one_op_tb(q, ops[i], enqueued_cbs,
> cbs_in_tb);
> > + if (ret <= 0) {
> > + acc_enqueue_invalid(q_data);
> > + break;
> > + }
> > + enqueued_cbs += ret;
> > + }
> > + if (unlikely(enqueued_cbs == 0))
> > + return 0; /* Nothing to enqueue */
> > +
> > + acc_dma_enqueue(q, enqueued_cbs, &q_data->queue_stats);
> > +
> > + /* Update stats */
> > + q_data->queue_stats.enqueued_count += i;
> > + q_data->queue_stats.enqueue_err_count += num - i;
> > +
> > + return i;
> > +}
> > +
> > /* Enqueue LDPC encode operations for ACC200 device in TB mode. */
> > static uint16_t
> > acc200_enqueue_ldpc_enc_tb(struct rte_bbdev_queue_data *q_data, @@
> > -1525,6 +2173,20 @@ acc200_enqueue_ldpc_enc_tb(struct
> rte_bbdev_queue_data *q_data,
> > return i;
> > }
> >
> > +/* Enqueue encode operations for ACC200 device. */ static uint16_t
> > +acc200_enqueue_enc(struct rte_bbdev_queue_data *q_data,
> > + struct rte_bbdev_enc_op **ops, uint16_t num) {
> > + int32_t aq_avail = acc_aq_avail(q_data, num);
> > + if (unlikely((aq_avail <= 0) || (num == 0)))
> > + return 0;
> > + if (ops[0]->turbo_enc.code_block_mode ==
> RTE_BBDEV_TRANSPORT_BLOCK)
> > + return acc200_enqueue_enc_tb(q_data, ops, num);
> > + else
> > + return acc200_enqueue_enc_cb(q_data, ops, num); }
> > +
> > /* Enqueue encode operations for ACC200 device. */
> > static uint16_t
> > acc200_enqueue_ldpc_enc(struct rte_bbdev_queue_data *q_data, @@
> > -1539,6 +2201,47 @@ acc200_enqueue_ldpc_enc(struct
> rte_bbdev_queue_data *q_data,
> > return acc200_enqueue_ldpc_enc_cb(q_data, ops, num);
> > }
> >
> > +
> > +/* Enqueue decode operations for ACC200 device in CB mode */ static
> > +uint16_t acc200_enqueue_dec_cb(struct rte_bbdev_queue_data *q_data,
> > + struct rte_bbdev_dec_op **ops, uint16_t num) {
> > + struct acc_queue *q = q_data->queue_private;
> > + int32_t avail = acc_ring_avail_enq(q);
> > + uint16_t i;
> > + union acc_dma_desc *desc;
> > + int ret;
> > +
> > + for (i = 0; i < num; ++i) {
> > + /* Check if there are available space for further processing */
> > + if (unlikely(avail - 1 < 0))
> > + break;
> > + avail -= 1;
> > +
> > + ret = enqueue_dec_one_op_cb(q, ops[i], i);
> > + if (ret < 0)
> > + break;
> > + }
> > +
> > + if (unlikely(i == 0))
> > + return 0; /* Nothing to enqueue */
> > +
> > + /* Set SDone in last CB in enqueued ops for CB mode*/
> > + desc = q->ring_addr + ((q->sw_ring_head + i - 1)
> > + & q->sw_ring_wrap_mask);
> > + desc->req.sdone_enable = 1;
> > + desc->req.irq_enable = q->irq_enable;
> > +
> > + acc_dma_enqueue(q, i, &q_data->queue_stats);
> > +
> > + /* Update stats */
> > + q_data->queue_stats.enqueued_count += i;
> > + q_data->queue_stats.enqueue_err_count += num - i;
> > +
> > + return i;
> > +}
> > +
> > /* Enqueue decode operations for ACC200 device in TB mode */
> > static uint16_t
> > acc200_enqueue_ldpc_dec_tb(struct rte_bbdev_queue_data *q_data, @@
> > -1623,6 +2326,58 @@ acc200_enqueue_ldpc_dec_cb(struct
> rte_bbdev_queue_data *q_data,
> > return i;
> > }
> >
> > +
> > +/* Enqueue decode operations for ACC200 device in TB mode */ static
> > +uint16_t acc200_enqueue_dec_tb(struct rte_bbdev_queue_data *q_data,
> > + struct rte_bbdev_dec_op **ops, uint16_t num) {
> > + struct acc_queue *q = q_data->queue_private;
> > + int32_t avail = acc_ring_avail_enq(q);
> > + uint16_t i, enqueued_cbs = 0;
> > + uint8_t cbs_in_tb;
> > + int ret;
> > +
> > + for (i = 0; i < num; ++i) {
> > + cbs_in_tb = get_num_cbs_in_tb_dec(&ops[i]->turbo_dec);
> > + /* Check if there are available space for further processing */
> > + if (unlikely((avail - cbs_in_tb < 0) || (cbs_in_tb == 0))) {
> > + acc_enqueue_ring_full(q_data);
> > + break;
> > + }
> > + avail -= cbs_in_tb;
> > +
> > + ret = enqueue_dec_one_op_tb(q, ops[i], enqueued_cbs,
> cbs_in_tb);
> > + if (ret <= 0) {
> > + acc_enqueue_invalid(q_data);
> > + break;
> > + }
> > + enqueued_cbs += ret;
> > + }
> > +
> > + acc_dma_enqueue(q, enqueued_cbs, &q_data->queue_stats);
> > +
> > + /* Update stats */
> > + q_data->queue_stats.enqueued_count += i;
> > + q_data->queue_stats.enqueue_err_count += num - i;
> > +
> > + return i;
> > +}
> > +
> > +/* Enqueue decode operations for ACC200 device. */ static uint16_t
> > +acc200_enqueue_dec(struct rte_bbdev_queue_data *q_data,
> > + struct rte_bbdev_dec_op **ops, uint16_t num) {
> > + int32_t aq_avail = acc_aq_avail(q_data, num);
> > + if (unlikely((aq_avail <= 0) || (num == 0)))
> > + return 0;
> > + if (ops[0]->turbo_dec.code_block_mode ==
> RTE_BBDEV_TRANSPORT_BLOCK)
> > + return acc200_enqueue_dec_tb(q_data, ops, num);
> > + else
> > + return acc200_enqueue_dec_cb(q_data, ops, num); }
> > +
> > /* Enqueue decode operations for ACC200 device. */
> > static uint16_t
> > acc200_enqueue_ldpc_dec(struct rte_bbdev_queue_data *q_data, @@
> > -1978,6 +2733,48 @@ dequeue_dec_one_op_tb(struct acc_queue *q, struct
> rte_bbdev_dec_op **ref_op,
> > return cb_idx;
> > }
> >
> > +/* Dequeue encode operations from ACC200 device. */ static uint16_t
> > +acc200_dequeue_enc(struct rte_bbdev_queue_data *q_data,
> > + struct rte_bbdev_enc_op **ops, uint16_t num) {
> > + struct acc_queue *q = q_data->queue_private;
> > + uint32_t avail = acc_ring_avail_deq(q);
> > + uint32_t aq_dequeued = 0;
> > + uint16_t i, dequeued_ops = 0, dequeued_descs = 0;
> > + int ret, cbm;
> > + struct rte_bbdev_enc_op *op;
>
> Why isn't there "debug checks" here while there are in acc200_dequeue_dec?
> Are we sure that here ops and q are non-null while we cannot know in
> acc200_dequeue_dec?
Removing the other debug checks as discussed on other commits, not doing anything
different for debug build in that commit.
Really it should never happen (or it would be caught by static code analysis) regardless of debug build or not
>
> > + if (avail == 0)
> > + return 0;
> > + op = (q->ring_addr + (q->sw_ring_tail &
> > + q->sw_ring_wrap_mask))->req.op_addr;
> > +
> > + cbm = op->turbo_enc.code_block_mode;
> > +
> > + for (i = 0; i < num; i++) {
> > + if (cbm == RTE_BBDEV_TRANSPORT_BLOCK)
> > + ret = dequeue_enc_one_op_tb(q,
> &ops[dequeued_ops],
> > + &dequeued_ops, &aq_dequeued,
> > + &dequeued_descs);
> > + else
> > + ret = dequeue_enc_one_op_cb(q,
> &ops[dequeued_ops],
> > + &dequeued_ops, &aq_dequeued,
> > + &dequeued_descs);
> > + if (ret < 0)
> > + break;
> > + if (dequeued_ops >= num)
> > + break;
> > + }
> > +
> > + q->aq_dequeued += aq_dequeued;
> > + q->sw_ring_tail += dequeued_descs;
> > +
> > + /* Update enqueue stats */
> > + q_data->queue_stats.dequeued_count += dequeued_ops;
> > +
> > + return dequeued_ops;
> > +}
> > +
> > /* Dequeue LDPC encode operations from ACC200 device. */
> > static uint16_t
> > acc200_dequeue_ldpc_enc(struct rte_bbdev_queue_data *q_data, @@
> > -2019,6 +2816,51 @@ acc200_dequeue_ldpc_enc(struct
> rte_bbdev_queue_data *q_data,
> > return dequeued_ops;
> > }
> >
> > +/* Dequeue decode operations from ACC200 device. */ static uint16_t
> > +acc200_dequeue_dec(struct rte_bbdev_queue_data *q_data,
> > + struct rte_bbdev_dec_op **ops, uint16_t num) {
> > + struct acc_queue *q = q_data->queue_private;
> > + uint16_t dequeue_num;
> > + uint32_t avail = acc_ring_avail_deq(q);
> > + uint32_t aq_dequeued = 0;
> > + uint16_t i;
> > + uint16_t dequeued_cbs = 0;
> > + struct rte_bbdev_dec_op *op;
> > + int ret;
> > +
> > +#ifdef RTE_LIBRTE_BBDEV_DEBUG
> > + if (unlikely(ops == 0 && q == NULL))
> > + return 0;
>
> It makes the debug build to fail silently. Checking for pointers validity is fine,
> but you want to emit a warning if it happens.
>
> > +#endif
>
> q is already dereferenced to get avail. acc_ring_avail_deq(q) should be called
> after the check.
Thanks taking out
>
> > +
> > + dequeue_num = (avail < num) ? avail : num;
> > +
> > + for (i = 0; i < dequeue_num; ++i) {
> > + op = (q->ring_addr + ((q->sw_ring_tail + dequeued_cbs)
> > + & q->sw_ring_wrap_mask))->req.op_addr;
> > + if (op->turbo_dec.code_block_mode ==
> RTE_BBDEV_TRANSPORT_BLOCK)
> > + ret = dequeue_dec_one_op_tb(q, &ops[i],
> dequeued_cbs,
> > + &aq_dequeued);
> > + else
> > + ret = dequeue_dec_one_op_cb(q_data, q, &ops[i],
> > + dequeued_cbs, &aq_dequeued);
> > +
> > + if (ret <= 0)
> > + break;
> > + dequeued_cbs += ret;
> > + }
> > +
> > + q->aq_dequeued += aq_dequeued;
> > + q->sw_ring_tail += dequeued_cbs;
> > +
> > + /* Update enqueue stats */
> > + q_data->queue_stats.dequeued_count += i;
> > +
> > + return i;
> > +}
> > +
> > /* Dequeue decode operations from ACC200 device. */
> > static uint16_t
> > acc200_dequeue_ldpc_dec(struct rte_bbdev_queue_data *q_data, @@
> > -2067,6 +2909,10 @@ acc200_bbdev_init(struct rte_bbdev *dev, struct
> rte_pci_driver *drv)
> > struct rte_pci_device *pci_dev = RTE_DEV_TO_PCI(dev->device);
> >
> > dev->dev_ops = &acc200_bbdev_ops;
> > + dev->enqueue_enc_ops = acc200_enqueue_enc;
> > + dev->enqueue_dec_ops = acc200_enqueue_dec;
> > + dev->dequeue_enc_ops = acc200_dequeue_enc;
> > + dev->dequeue_dec_ops = acc200_dequeue_dec;
> > dev->enqueue_ldpc_enc_ops = acc200_enqueue_ldpc_enc;
> > dev->enqueue_ldpc_dec_ops = acc200_enqueue_ldpc_dec;
> > dev->dequeue_ldpc_enc_ops = acc200_dequeue_ldpc_enc;
^ permalink raw reply [flat|nested] 28+ messages in thread
* [PATCH v6 10/14] baseband/acc: add support for FFT operations
2022-09-24 0:50 From: Nicolas Chautru <nicolas.chautru@intel.com> Nicolas Chautru
` (8 preceding siblings ...)
2022-09-24 0:50 ` [PATCH v6 09/14] baseband/acc: add LTE " Nicolas Chautru
@ 2022-09-24 0:50 ` Nicolas Chautru
2022-09-27 13:45 ` Maxime Coquelin
2022-09-24 0:50 ` [PATCH v6 11/14] baseband/acc: support interrupt Nicolas Chautru
` (3 subsequent siblings)
13 siblings, 1 reply; 28+ messages in thread
From: Nicolas Chautru @ 2022-09-24 0:50 UTC (permalink / raw)
To: dev, thomas
Cc: maxime.coquelin, trix, mdr, bruce.richardson, hemant.agrawal,
david.marchand, stephen, hernan.vargas, Nic Chautru
From: Nic Chautru <nicolas.chautru@intel.com>
Add functions and capability for FFT processing
Signed-off-by: Nic Chautru <nicolas.chautru@intel.com>
---
drivers/baseband/acc/rte_acc200_pmd.c | 242 +++++++++++++++++++++++++-
1 file changed, 240 insertions(+), 2 deletions(-)
diff --git a/drivers/baseband/acc/rte_acc200_pmd.c b/drivers/baseband/acc/rte_acc200_pmd.c
index e8901c60d6..7f2cd71166 100644
--- a/drivers/baseband/acc/rte_acc200_pmd.c
+++ b/drivers/baseband/acc/rte_acc200_pmd.c
@@ -735,6 +735,21 @@ acc200_dev_info_get(struct rte_bbdev *dev,
.num_buffers_soft_out = 0,
}
},
+ {
+ .type = RTE_BBDEV_OP_FFT,
+ .cap.fft = {
+ .capability_flags =
+ RTE_BBDEV_FFT_WINDOWING |
+ RTE_BBDEV_FFT_CS_ADJUSTMENT |
+ RTE_BBDEV_FFT_DFT_BYPASS |
+ RTE_BBDEV_FFT_IDFT_BYPASS |
+ RTE_BBDEV_FFT_WINDOWING_BYPASS,
+ .num_buffers_src =
+ RTE_BBDEV_LDPC_MAX_CODE_BLOCKS,
+ .num_buffers_dst =
+ RTE_BBDEV_LDPC_MAX_CODE_BLOCKS,
+ }
+ },
RTE_BBDEV_END_OF_CAPABILITIES_LIST()
};
@@ -757,12 +772,13 @@ acc200_dev_info_get(struct rte_bbdev *dev,
d->acc_conf.q_ul_5g.num_qgroups;
dev_info->num_queues[RTE_BBDEV_OP_LDPC_ENC] = d->acc_conf.q_dl_5g.num_aqs_per_groups *
d->acc_conf.q_dl_5g.num_qgroups;
- dev_info->num_queues[RTE_BBDEV_OP_FFT] = 0;
+ dev_info->num_queues[RTE_BBDEV_OP_FFT] = d->acc_conf.q_fft.num_aqs_per_groups *
+ d->acc_conf.q_fft.num_qgroups;
dev_info->queue_priority[RTE_BBDEV_OP_TURBO_DEC] = d->acc_conf.q_ul_4g.num_qgroups;
dev_info->queue_priority[RTE_BBDEV_OP_TURBO_ENC] = d->acc_conf.q_dl_4g.num_qgroups;
dev_info->queue_priority[RTE_BBDEV_OP_LDPC_DEC] = d->acc_conf.q_ul_5g.num_qgroups;
dev_info->queue_priority[RTE_BBDEV_OP_LDPC_ENC] = d->acc_conf.q_dl_5g.num_qgroups;
- dev_info->queue_priority[RTE_BBDEV_OP_FFT] = 0;
+ dev_info->queue_priority[RTE_BBDEV_OP_FFT] = d->acc_conf.q_fft.num_qgroups;
dev_info->max_num_queues = 0;
for (i = RTE_BBDEV_OP_NONE; i <= RTE_BBDEV_OP_FFT; i++)
dev_info->max_num_queues += dev_info->num_queues[i];
@@ -2902,6 +2918,226 @@ acc200_dequeue_ldpc_dec(struct rte_bbdev_queue_data *q_data,
return i;
}
+/* Fill in a frame control word for FFT processing. */
+static inline void
+acc200_fcw_fft_fill(struct rte_bbdev_fft_op *op, struct acc_fcw_fft *fcw)
+{
+ fcw->in_frame_size = op->fft.input_sequence_size;
+ fcw->leading_pad_size = op->fft.input_leading_padding;
+ fcw->out_frame_size = op->fft.output_sequence_size;
+ fcw->leading_depad_size = op->fft.output_leading_depadding;
+ fcw->cs_window_sel = op->fft.window_index[0] +
+ (op->fft.window_index[1] << 8) +
+ (op->fft.window_index[2] << 16) +
+ (op->fft.window_index[3] << 24);
+ fcw->cs_window_sel2 = op->fft.window_index[4] +
+ (op->fft.window_index[5] << 8);
+ fcw->cs_enable_bmap = op->fft.cs_bitmap;
+ fcw->num_antennas = op->fft.num_antennas_log2;
+ fcw->idft_size = op->fft.idft_log2;
+ fcw->dft_size = op->fft.dft_log2;
+ fcw->cs_offset = op->fft.cs_time_adjustment;
+ fcw->idft_shift = op->fft.idft_shift;
+ fcw->dft_shift = op->fft.dft_shift;
+ fcw->cs_multiplier = op->fft.ncs_reciprocal;
+ if (check_bit(op->fft.op_flags,
+ RTE_BBDEV_FFT_IDFT_BYPASS)) {
+ if (check_bit(op->fft.op_flags,
+ RTE_BBDEV_FFT_WINDOWING_BYPASS))
+ fcw->bypass = 2;
+ else
+ fcw->bypass = 1;
+ } else if (check_bit(op->fft.op_flags,
+ RTE_BBDEV_FFT_DFT_BYPASS))
+ fcw->bypass = 3;
+ else
+ fcw->bypass = 0;
+}
+
+static inline int
+acc200_dma_desc_fft_fill(struct rte_bbdev_fft_op *op,
+ struct acc_dma_req_desc *desc,
+ struct rte_mbuf *input, struct rte_mbuf *output,
+ uint32_t *in_offset, uint32_t *out_offset)
+{
+ /* FCW already done */
+ acc_header_init(desc);
+ desc->data_ptrs[1].address =
+ rte_pktmbuf_iova_offset(input, *in_offset);
+ desc->data_ptrs[1].blen = op->fft.input_sequence_size * 4;
+ desc->data_ptrs[1].blkid = ACC_DMA_BLKID_IN;
+ desc->data_ptrs[1].last = 1;
+ desc->data_ptrs[1].dma_ext = 0;
+ desc->data_ptrs[2].address =
+ rte_pktmbuf_iova_offset(output, *out_offset);
+ desc->data_ptrs[2].blen = op->fft.output_sequence_size * 4;
+ desc->data_ptrs[2].blkid = ACC_DMA_BLKID_OUT_HARD;
+ desc->data_ptrs[2].last = 1;
+ desc->data_ptrs[2].dma_ext = 0;
+ desc->m2dlen = 2;
+ desc->d2mlen = 1;
+ desc->ib_ant_offset = op->fft.input_sequence_size;
+ desc->num_ant = op->fft.num_antennas_log2 - 3;
+ int num_cs = 0, i;
+ for (i = 0; i < 12; i++)
+ if (check_bit(op->fft.cs_bitmap, 1 << i))
+ num_cs++;
+ desc->num_cs = num_cs;
+ desc->ob_cyc_offset = op->fft.output_sequence_size;
+ desc->ob_ant_offset = op->fft.output_sequence_size * num_cs;
+ desc->op_addr = op;
+ return 0;
+}
+
+
+/** Enqueue one FFT operation for ACC200 device*/
+static inline int
+enqueue_fft_one_op(struct acc_queue *q, struct rte_bbdev_fft_op *op,
+ uint16_t total_enqueued_cbs)
+{
+ union acc_dma_desc *desc;
+ uint16_t desc_idx = ((q->sw_ring_head + total_enqueued_cbs) & q->sw_ring_wrap_mask);
+ desc = q->ring_addr + desc_idx;
+ struct rte_mbuf *input, *output;
+ uint32_t in_offset, out_offset;
+ struct acc_fcw_fft *fcw;
+
+ input = op->fft.base_input.data;
+ output = op->fft.base_output.data;
+ in_offset = op->fft.base_input.offset;
+ out_offset = op->fft.base_output.offset;
+ fcw = &desc->req.fcw_fft;
+
+ acc200_fcw_fft_fill(op, fcw);
+ acc200_dma_desc_fft_fill(op, &desc->req, input, output, &in_offset, &out_offset);
+#ifdef RTE_LIBRTE_BBDEV_DEBUG
+ rte_memdump(stderr, "FCW", &desc->req.fcw_fft,
+ sizeof(desc->req.fcw_fft));
+ rte_memdump(stderr, "Req Desc.", desc, sizeof(*desc));
+#endif
+ return 1;
+}
+
+/* Enqueue decode operations for ACC200 device. */
+static uint16_t
+acc200_enqueue_fft(struct rte_bbdev_queue_data *q_data,
+ struct rte_bbdev_fft_op **ops, uint16_t num)
+{
+ struct acc_queue *q;
+ int32_t aq_avail, avail;
+ uint16_t i;
+ union acc_dma_desc *desc;
+ int ret;
+
+ aq_avail = acc_aq_avail(q_data, num);
+ if (unlikely((aq_avail <= 0) || (num == 0)))
+ return 0;
+ q = q_data->queue_private;
+ avail = acc_ring_avail_enq(q);
+
+ for (i = 0; i < num; ++i) {
+ /* Check if there are available space for further processing */
+ if (unlikely(avail < 1))
+ break;
+ avail -= 1;
+ ret = enqueue_fft_one_op(q, ops[i], i);
+ if (ret < 0)
+ break;
+ }
+
+ if (unlikely(i == 0))
+ return 0; /* Nothing to enqueue */
+
+ /* Set SDone in last CB in enqueued ops for CB mode*/
+ desc = q->ring_addr + ((q->sw_ring_head + i - 1)
+ & q->sw_ring_wrap_mask);
+
+ desc->req.sdone_enable = 1;
+ desc->req.irq_enable = q->irq_enable;
+ acc_dma_enqueue(q, i, &q_data->queue_stats);
+
+ /* Update stats */
+ q_data->queue_stats.enqueued_count += i;
+ q_data->queue_stats.enqueue_err_count += num - i;
+ return i;
+}
+
+
+/* Dequeue one FFT operations from ACC200 device */
+static inline int
+dequeue_fft_one_op(struct rte_bbdev_queue_data *q_data,
+ struct acc_queue *q, struct rte_bbdev_fft_op **ref_op,
+ uint16_t dequeued_cbs, uint32_t *aq_dequeued)
+{
+ union acc_dma_desc *desc, atom_desc;
+ union acc_dma_rsp_desc rsp;
+ struct rte_bbdev_fft_op *op;
+
+ desc = q->ring_addr + ((q->sw_ring_tail + dequeued_cbs)
+ & q->sw_ring_wrap_mask);
+ atom_desc.atom_hdr = __atomic_load_n((uint64_t *)desc,
+ __ATOMIC_RELAXED);
+
+ /* Check fdone bit */
+ if (!(atom_desc.rsp.val & ACC_FDONE))
+ return -1;
+
+ rsp.val = atom_desc.rsp.val;
+#ifdef RTE_LIBRTE_BBDEV_DEBUG
+ rte_memdump(stderr, "Resp", &desc->rsp.val,
+ sizeof(desc->rsp.val));
+#endif
+ /* Dequeue */
+ op = desc->req.op_addr;
+
+ /* Clearing status, it will be set based on response */
+ op->status = 0;
+ op->status |= rsp.input_err << RTE_BBDEV_DATA_ERROR;
+ op->status |= rsp.dma_err << RTE_BBDEV_DRV_ERROR;
+ op->status |= rsp.fcw_err << RTE_BBDEV_DRV_ERROR;
+ if (op->status != 0)
+ q_data->queue_stats.dequeue_err_count++;
+
+ /* Check if this is the last desc in batch (Atomic Queue) */
+ if (desc->req.last_desc_in_batch) {
+ (*aq_dequeued)++;
+ desc->req.last_desc_in_batch = 0;
+ }
+ desc->rsp.val = ACC_DMA_DESC_TYPE;
+ desc->rsp.add_info_0 = 0;
+ *ref_op = op;
+ /* One CB (op) was successfully dequeued */
+ return 1;
+}
+
+
+/* Dequeue FFT operations from ACC200 device. */
+static uint16_t
+acc200_dequeue_fft(struct rte_bbdev_queue_data *q_data,
+ struct rte_bbdev_fft_op **ops, uint16_t num)
+{
+ struct acc_queue *q = q_data->queue_private;
+ uint16_t dequeue_num, i, dequeued_cbs = 0;
+ uint32_t avail = acc_ring_avail_deq(q);
+ uint32_t aq_dequeued = 0;
+ int ret;
+
+ dequeue_num = RTE_MIN(avail, num);
+
+ for (i = 0; i < dequeue_num; ++i) {
+ ret = dequeue_fft_one_op(q_data, q, &ops[i], dequeued_cbs, &aq_dequeued);
+ if (ret <= 0)
+ break;
+ dequeued_cbs += ret;
+ }
+
+ q->aq_dequeued += aq_dequeued;
+ q->sw_ring_tail += dequeued_cbs;
+ /* Update enqueue stats */
+ q_data->queue_stats.dequeued_count += i;
+ return i;
+}
+
/* Initialization Function */
static void
acc200_bbdev_init(struct rte_bbdev *dev, struct rte_pci_driver *drv)
@@ -2917,6 +3153,8 @@ acc200_bbdev_init(struct rte_bbdev *dev, struct rte_pci_driver *drv)
dev->enqueue_ldpc_dec_ops = acc200_enqueue_ldpc_dec;
dev->dequeue_ldpc_enc_ops = acc200_dequeue_ldpc_enc;
dev->dequeue_ldpc_dec_ops = acc200_dequeue_ldpc_dec;
+ dev->enqueue_fft_ops = acc200_enqueue_fft;
+ dev->dequeue_fft_ops = acc200_dequeue_fft;
((struct acc_device *) dev->data->dev_private)->pf_device =
!strcmp(drv->driver.name,
--
2.37.1
^ permalink raw reply [flat|nested] 28+ messages in thread* Re: [PATCH v6 10/14] baseband/acc: add support for FFT operations
2022-09-24 0:50 ` [PATCH v6 10/14] baseband/acc: add support for FFT operations Nicolas Chautru
@ 2022-09-27 13:45 ` Maxime Coquelin
2022-09-29 21:14 ` Chautru, Nicolas
0 siblings, 1 reply; 28+ messages in thread
From: Maxime Coquelin @ 2022-09-27 13:45 UTC (permalink / raw)
To: Nicolas Chautru, dev, thomas
Cc: trix, mdr, bruce.richardson, hemant.agrawal, david.marchand,
stephen, hernan.vargas
On 9/24/22 02:50, Nicolas Chautru wrote:
> From: Nic Chautru <nicolas.chautru@intel.com>
>
> Add functions and capability for FFT processing
>
> Signed-off-by: Nic Chautru <nicolas.chautru@intel.com>
> ---
> drivers/baseband/acc/rte_acc200_pmd.c | 242 +++++++++++++++++++++++++-
> 1 file changed, 240 insertions(+), 2 deletions(-)
>
> diff --git a/drivers/baseband/acc/rte_acc200_pmd.c b/drivers/baseband/acc/rte_acc200_pmd.c
> index e8901c60d6..7f2cd71166 100644
> --- a/drivers/baseband/acc/rte_acc200_pmd.c
> +++ b/drivers/baseband/acc/rte_acc200_pmd.c
> @@ -735,6 +735,21 @@ acc200_dev_info_get(struct rte_bbdev *dev,
> .num_buffers_soft_out = 0,
> }
> },
> + {
> + .type = RTE_BBDEV_OP_FFT,
> + .cap.fft = {
> + .capability_flags =
> + RTE_BBDEV_FFT_WINDOWING |
> + RTE_BBDEV_FFT_CS_ADJUSTMENT |
> + RTE_BBDEV_FFT_DFT_BYPASS |
> + RTE_BBDEV_FFT_IDFT_BYPASS |
> + RTE_BBDEV_FFT_WINDOWING_BYPASS,
> + .num_buffers_src =
> + RTE_BBDEV_LDPC_MAX_CODE_BLOCKS,
> + .num_buffers_dst =
> + RTE_BBDEV_LDPC_MAX_CODE_BLOCKS,
> + }
> + },
> RTE_BBDEV_END_OF_CAPABILITIES_LIST()
> };
>
> @@ -757,12 +772,13 @@ acc200_dev_info_get(struct rte_bbdev *dev,
> d->acc_conf.q_ul_5g.num_qgroups;
> dev_info->num_queues[RTE_BBDEV_OP_LDPC_ENC] = d->acc_conf.q_dl_5g.num_aqs_per_groups *
> d->acc_conf.q_dl_5g.num_qgroups;
> - dev_info->num_queues[RTE_BBDEV_OP_FFT] = 0;
> + dev_info->num_queues[RTE_BBDEV_OP_FFT] = d->acc_conf.q_fft.num_aqs_per_groups *
> + d->acc_conf.q_fft.num_qgroups;
> dev_info->queue_priority[RTE_BBDEV_OP_TURBO_DEC] = d->acc_conf.q_ul_4g.num_qgroups;
> dev_info->queue_priority[RTE_BBDEV_OP_TURBO_ENC] = d->acc_conf.q_dl_4g.num_qgroups;
> dev_info->queue_priority[RTE_BBDEV_OP_LDPC_DEC] = d->acc_conf.q_ul_5g.num_qgroups;
> dev_info->queue_priority[RTE_BBDEV_OP_LDPC_ENC] = d->acc_conf.q_dl_5g.num_qgroups;
> - dev_info->queue_priority[RTE_BBDEV_OP_FFT] = 0;
> + dev_info->queue_priority[RTE_BBDEV_OP_FFT] = d->acc_conf.q_fft.num_qgroups;
> dev_info->max_num_queues = 0;
> for (i = RTE_BBDEV_OP_NONE; i <= RTE_BBDEV_OP_FFT; i++)
> dev_info->max_num_queues += dev_info->num_queues[i];
> @@ -2902,6 +2918,226 @@ acc200_dequeue_ldpc_dec(struct rte_bbdev_queue_data *q_data,
> return i;
> }
>
> +/* Fill in a frame control word for FFT processing. */
> +static inline void
> +acc200_fcw_fft_fill(struct rte_bbdev_fft_op *op, struct acc_fcw_fft *fcw)
> +{
> + fcw->in_frame_size = op->fft.input_sequence_size;
> + fcw->leading_pad_size = op->fft.input_leading_padding;
> + fcw->out_frame_size = op->fft.output_sequence_size;
> + fcw->leading_depad_size = op->fft.output_leading_depadding;
> + fcw->cs_window_sel = op->fft.window_index[0] +
> + (op->fft.window_index[1] << 8) +
> + (op->fft.window_index[2] << 16) +
> + (op->fft.window_index[3] << 24);
> + fcw->cs_window_sel2 = op->fft.window_index[4] +
> + (op->fft.window_index[5] << 8);
> + fcw->cs_enable_bmap = op->fft.cs_bitmap;
> + fcw->num_antennas = op->fft.num_antennas_log2;
> + fcw->idft_size = op->fft.idft_log2;
> + fcw->dft_size = op->fft.dft_log2;
> + fcw->cs_offset = op->fft.cs_time_adjustment;
> + fcw->idft_shift = op->fft.idft_shift;
> + fcw->dft_shift = op->fft.dft_shift;
> + fcw->cs_multiplier = op->fft.ncs_reciprocal;
> + if (check_bit(op->fft.op_flags,
> + RTE_BBDEV_FFT_IDFT_BYPASS)) {
> + if (check_bit(op->fft.op_flags,
> + RTE_BBDEV_FFT_WINDOWING_BYPASS))
> + fcw->bypass = 2;
> + else
> + fcw->bypass = 1;
> + } else if (check_bit(op->fft.op_flags,
> + RTE_BBDEV_FFT_DFT_BYPASS))
> + fcw->bypass = 3;
> + else
> + fcw->bypass = 0;
> +}
> +
> +static inline int
> +acc200_dma_desc_fft_fill(struct rte_bbdev_fft_op *op,
> + struct acc_dma_req_desc *desc,
> + struct rte_mbuf *input, struct rte_mbuf *output,
> + uint32_t *in_offset, uint32_t *out_offset)
> +{
> + /* FCW already done */
> + acc_header_init(desc);
> + desc->data_ptrs[1].address =
> + rte_pktmbuf_iova_offset(input, *in_offset);
> + desc->data_ptrs[1].blen = op->fft.input_sequence_size * 4;
> + desc->data_ptrs[1].blkid = ACC_DMA_BLKID_IN;
> + desc->data_ptrs[1].last = 1;
> + desc->data_ptrs[1].dma_ext = 0;
> + desc->data_ptrs[2].address =
> + rte_pktmbuf_iova_offset(output, *out_offset);
> + desc->data_ptrs[2].blen = op->fft.output_sequence_size * 4;
> + desc->data_ptrs[2].blkid = ACC_DMA_BLKID_OUT_HARD;
> + desc->data_ptrs[2].last = 1;
> + desc->data_ptrs[2].dma_ext = 0;
> + desc->m2dlen = 2;
> + desc->d2mlen = 1;
> + desc->ib_ant_offset = op->fft.input_sequence_size;
> + desc->num_ant = op->fft.num_antennas_log2 - 3;
> + int num_cs = 0, i;
> + for (i = 0; i < 12; i++)
> + if (check_bit(op->fft.cs_bitmap, 1 << i))
> + num_cs++;
> + desc->num_cs = num_cs;
> + desc->ob_cyc_offset = op->fft.output_sequence_size;
> + desc->ob_ant_offset = op->fft.output_sequence_size * num_cs;
> + desc->op_addr = op;
> + return 0;
> +}
> +
> +
> +/** Enqueue one FFT operation for ACC200 device*/
> +static inline int
> +enqueue_fft_one_op(struct acc_queue *q, struct rte_bbdev_fft_op *op,
> + uint16_t total_enqueued_cbs)
> +{
> + union acc_dma_desc *desc;
> + uint16_t desc_idx = ((q->sw_ring_head + total_enqueued_cbs) & q->sw_ring_wrap_mask);
> + desc = q->ring_addr + desc_idx;
Don't mix declarations & code.
> + struct rte_mbuf *input, *output;
> + uint32_t in_offset, out_offset;
> + struct acc_fcw_fft *fcw;
> +
> + input = op->fft.base_input.data;
> + output = op->fft.base_output.data;
> + in_offset = op->fft.base_input.offset;
> + out_offset = op->fft.base_output.offset;
> + fcw = &desc->req.fcw_fft;
> +
> + acc200_fcw_fft_fill(op, fcw);
> + acc200_dma_desc_fft_fill(op, &desc->req, input, output, &in_offset, &out_offset);
> +#ifdef RTE_LIBRTE_BBDEV_DEBUG
> + rte_memdump(stderr, "FCW", &desc->req.fcw_fft,
> + sizeof(desc->req.fcw_fft));
> + rte_memdump(stderr, "Req Desc.", desc, sizeof(*desc));
> +#endif
> + return 1;
> +}
> +
> +/* Enqueue decode operations for ACC200 device. */
> +static uint16_t
> +acc200_enqueue_fft(struct rte_bbdev_queue_data *q_data,
> + struct rte_bbdev_fft_op **ops, uint16_t num)
> +{
> + struct acc_queue *q;
> + int32_t aq_avail, avail;
> + uint16_t i;
> + union acc_dma_desc *desc;
> + int ret;
> +
> + aq_avail = acc_aq_avail(q_data, num);
> + if (unlikely((aq_avail <= 0) || (num == 0)))
> + return 0;
> + q = q_data->queue_private;
> + avail = acc_ring_avail_enq(q);
> +
> + for (i = 0; i < num; ++i) {
> + /* Check if there are available space for further processing */
> + if (unlikely(avail < 1))
> + break;
> + avail -= 1;
> + ret = enqueue_fft_one_op(q, ops[i], i);
> + if (ret < 0)
> + break;
> + }
> +
> + if (unlikely(i == 0))
> + return 0; /* Nothing to enqueue */
> +
> + /* Set SDone in last CB in enqueued ops for CB mode*/
> + desc = q->ring_addr + ((q->sw_ring_head + i - 1)
> + & q->sw_ring_wrap_mask);
> +
> + desc->req.sdone_enable = 1;
> + desc->req.irq_enable = q->irq_enable;
> + acc_dma_enqueue(q, i, &q_data->queue_stats);
> +
> + /* Update stats */
> + q_data->queue_stats.enqueued_count += i;
> + q_data->queue_stats.enqueue_err_count += num - i;
> + return i;
> +}
> +
> +
> +/* Dequeue one FFT operations from ACC200 device */
> +static inline int
> +dequeue_fft_one_op(struct rte_bbdev_queue_data *q_data,
> + struct acc_queue *q, struct rte_bbdev_fft_op **ref_op,
> + uint16_t dequeued_cbs, uint32_t *aq_dequeued)
> +{
> + union acc_dma_desc *desc, atom_desc;
> + union acc_dma_rsp_desc rsp;
> + struct rte_bbdev_fft_op *op;
> +
> + desc = q->ring_addr + ((q->sw_ring_tail + dequeued_cbs)
> + & q->sw_ring_wrap_mask);
> + atom_desc.atom_hdr = __atomic_load_n((uint64_t *)desc,
> + __ATOMIC_RELAXED);
> +
> + /* Check fdone bit */
> + if (!(atom_desc.rsp.val & ACC_FDONE))
> + return -1;
> +
> + rsp.val = atom_desc.rsp.val;
> +#ifdef RTE_LIBRTE_BBDEV_DEBUG
> + rte_memdump(stderr, "Resp", &desc->rsp.val,
> + sizeof(desc->rsp.val));
> +#endif
> + /* Dequeue */
> + op = desc->req.op_addr;
> +
> + /* Clearing status, it will be set based on response */
> + op->status = 0;
> + op->status |= rsp.input_err << RTE_BBDEV_DATA_ERROR;
> + op->status |= rsp.dma_err << RTE_BBDEV_DRV_ERROR;
> + op->status |= rsp.fcw_err << RTE_BBDEV_DRV_ERROR;
> + if (op->status != 0)
> + q_data->queue_stats.dequeue_err_count++;
> +
> + /* Check if this is the last desc in batch (Atomic Queue) */
> + if (desc->req.last_desc_in_batch) {
> + (*aq_dequeued)++;
> + desc->req.last_desc_in_batch = 0;
> + }
> + desc->rsp.val = ACC_DMA_DESC_TYPE;
> + desc->rsp.add_info_0 = 0;
> + *ref_op = op;
> + /* One CB (op) was successfully dequeued */
> + return 1;
> +}
> +
> +
> +/* Dequeue FFT operations from ACC200 device. */
> +static uint16_t
> +acc200_dequeue_fft(struct rte_bbdev_queue_data *q_data,
> + struct rte_bbdev_fft_op **ops, uint16_t num)
> +{
> + struct acc_queue *q = q_data->queue_private;
> + uint16_t dequeue_num, i, dequeued_cbs = 0;
> + uint32_t avail = acc_ring_avail_deq(q);
> + uint32_t aq_dequeued = 0;
> + int ret;
> +
> + dequeue_num = RTE_MIN(avail, num);
> +
> + for (i = 0; i < dequeue_num; ++i) {
> + ret = dequeue_fft_one_op(q_data, q, &ops[i], dequeued_cbs, &aq_dequeued);
> + if (ret <= 0)
> + break;
> + dequeued_cbs += ret;
> + }
> +
> + q->aq_dequeued += aq_dequeued;
> + q->sw_ring_tail += dequeued_cbs;
> + /* Update enqueue stats */
> + q_data->queue_stats.dequeued_count += i;
> + return i;
> +}
> +
> /* Initialization Function */
> static void
> acc200_bbdev_init(struct rte_bbdev *dev, struct rte_pci_driver *drv)
> @@ -2917,6 +3153,8 @@ acc200_bbdev_init(struct rte_bbdev *dev, struct rte_pci_driver *drv)
> dev->enqueue_ldpc_dec_ops = acc200_enqueue_ldpc_dec;
> dev->dequeue_ldpc_enc_ops = acc200_dequeue_ldpc_enc;
> dev->dequeue_ldpc_dec_ops = acc200_dequeue_ldpc_dec;
> + dev->enqueue_fft_ops = acc200_enqueue_fft;
> + dev->dequeue_fft_ops = acc200_dequeue_fft;
>
> ((struct acc_device *) dev->data->dev_private)->pf_device =
> !strcmp(drv->driver.name,
^ permalink raw reply [flat|nested] 28+ messages in thread* RE: [PATCH v6 10/14] baseband/acc: add support for FFT operations
2022-09-27 13:45 ` Maxime Coquelin
@ 2022-09-29 21:14 ` Chautru, Nicolas
0 siblings, 0 replies; 28+ messages in thread
From: Chautru, Nicolas @ 2022-09-29 21:14 UTC (permalink / raw)
To: Maxime Coquelin, dev, thomas
Cc: trix, mdr, Richardson, Bruce, hemant.agrawal, david.marchand,
stephen, Vargas, Hernan
Hi Maxime,
> -----Original Message-----
> From: Maxime Coquelin <maxime.coquelin@redhat.com>
> Sent: Tuesday, September 27, 2022 6:45 AM
> To: Chautru, Nicolas <nicolas.chautru@intel.com>; dev@dpdk.org;
> thomas@monjalon.net
> Cc: trix@redhat.com; mdr@ashroe.eu; Richardson, Bruce
> <bruce.richardson@intel.com>; hemant.agrawal@nxp.com;
> david.marchand@redhat.com; stephen@networkplumber.org; Vargas,
> Hernan <hernan.vargas@intel.com>
> Subject: Re: [PATCH v6 10/14] baseband/acc: add support for FFT operations
>
>
>
> On 9/24/22 02:50, Nicolas Chautru wrote:
> > From: Nic Chautru <nicolas.chautru@intel.com>
> >
> > Add functions and capability for FFT processing
> >
> > Signed-off-by: Nic Chautru <nicolas.chautru@intel.com>
> > ---
> > drivers/baseband/acc/rte_acc200_pmd.c | 242
> +++++++++++++++++++++++++-
> > 1 file changed, 240 insertions(+), 2 deletions(-)
> >
> > diff --git a/drivers/baseband/acc/rte_acc200_pmd.c
> > b/drivers/baseband/acc/rte_acc200_pmd.c
> > index e8901c60d6..7f2cd71166 100644
> > --- a/drivers/baseband/acc/rte_acc200_pmd.c
> > +++ b/drivers/baseband/acc/rte_acc200_pmd.c
> > @@ -735,6 +735,21 @@ acc200_dev_info_get(struct rte_bbdev *dev,
> > .num_buffers_soft_out = 0,
> > }
> > },
> > + {
> > + .type = RTE_BBDEV_OP_FFT,
> > + .cap.fft = {
> > + .capability_flags =
> > +
> RTE_BBDEV_FFT_WINDOWING |
> > +
> RTE_BBDEV_FFT_CS_ADJUSTMENT |
> > +
> RTE_BBDEV_FFT_DFT_BYPASS |
> > +
> RTE_BBDEV_FFT_IDFT_BYPASS |
> > +
> RTE_BBDEV_FFT_WINDOWING_BYPASS,
> > + .num_buffers_src =
> > +
> RTE_BBDEV_LDPC_MAX_CODE_BLOCKS,
> > + .num_buffers_dst =
> > +
> RTE_BBDEV_LDPC_MAX_CODE_BLOCKS,
> > + }
> > + },
> > RTE_BBDEV_END_OF_CAPABILITIES_LIST()
> > };
> >
> > @@ -757,12 +772,13 @@ acc200_dev_info_get(struct rte_bbdev *dev,
> > d->acc_conf.q_ul_5g.num_qgroups;
> > dev_info->num_queues[RTE_BBDEV_OP_LDPC_ENC] = d-
> >acc_conf.q_dl_5g.num_aqs_per_groups *
> > d->acc_conf.q_dl_5g.num_qgroups;
> > - dev_info->num_queues[RTE_BBDEV_OP_FFT] = 0;
> > + dev_info->num_queues[RTE_BBDEV_OP_FFT] = d-
> >acc_conf.q_fft.num_aqs_per_groups *
> > + d->acc_conf.q_fft.num_qgroups;
> > dev_info->queue_priority[RTE_BBDEV_OP_TURBO_DEC] = d-
> >acc_conf.q_ul_4g.num_qgroups;
> > dev_info->queue_priority[RTE_BBDEV_OP_TURBO_ENC] = d-
> >acc_conf.q_dl_4g.num_qgroups;
> > dev_info->queue_priority[RTE_BBDEV_OP_LDPC_DEC] = d-
> >acc_conf.q_ul_5g.num_qgroups;
> > dev_info->queue_priority[RTE_BBDEV_OP_LDPC_ENC] = d-
> >acc_conf.q_dl_5g.num_qgroups;
> > - dev_info->queue_priority[RTE_BBDEV_OP_FFT] = 0;
> > + dev_info->queue_priority[RTE_BBDEV_OP_FFT] =
> > +d->acc_conf.q_fft.num_qgroups;
> > dev_info->max_num_queues = 0;
> > for (i = RTE_BBDEV_OP_NONE; i <= RTE_BBDEV_OP_FFT; i++)
> > dev_info->max_num_queues += dev_info->num_queues[i];
> @@ -2902,6
> > +2918,226 @@ acc200_dequeue_ldpc_dec(struct rte_bbdev_queue_data
> *q_data,
> > return i;
> > }
> >
> > +/* Fill in a frame control word for FFT processing. */ static inline
> > +void acc200_fcw_fft_fill(struct rte_bbdev_fft_op *op, struct
> > +acc_fcw_fft *fcw) {
> > + fcw->in_frame_size = op->fft.input_sequence_size;
> > + fcw->leading_pad_size = op->fft.input_leading_padding;
> > + fcw->out_frame_size = op->fft.output_sequence_size;
> > + fcw->leading_depad_size = op->fft.output_leading_depadding;
> > + fcw->cs_window_sel = op->fft.window_index[0] +
> > + (op->fft.window_index[1] << 8) +
> > + (op->fft.window_index[2] << 16) +
> > + (op->fft.window_index[3] << 24);
> > + fcw->cs_window_sel2 = op->fft.window_index[4] +
> > + (op->fft.window_index[5] << 8);
> > + fcw->cs_enable_bmap = op->fft.cs_bitmap;
> > + fcw->num_antennas = op->fft.num_antennas_log2;
> > + fcw->idft_size = op->fft.idft_log2;
> > + fcw->dft_size = op->fft.dft_log2;
> > + fcw->cs_offset = op->fft.cs_time_adjustment;
> > + fcw->idft_shift = op->fft.idft_shift;
> > + fcw->dft_shift = op->fft.dft_shift;
> > + fcw->cs_multiplier = op->fft.ncs_reciprocal;
> > + if (check_bit(op->fft.op_flags,
> > + RTE_BBDEV_FFT_IDFT_BYPASS)) {
> > + if (check_bit(op->fft.op_flags,
> > + RTE_BBDEV_FFT_WINDOWING_BYPASS))
> > + fcw->bypass = 2;
> > + else
> > + fcw->bypass = 1;
> > + } else if (check_bit(op->fft.op_flags,
> > + RTE_BBDEV_FFT_DFT_BYPASS))
> > + fcw->bypass = 3;
> > + else
> > + fcw->bypass = 0;
> > +}
> > +
> > +static inline int
> > +acc200_dma_desc_fft_fill(struct rte_bbdev_fft_op *op,
> > + struct acc_dma_req_desc *desc,
> > + struct rte_mbuf *input, struct rte_mbuf *output,
> > + uint32_t *in_offset, uint32_t *out_offset) {
> > + /* FCW already done */
> > + acc_header_init(desc);
> > + desc->data_ptrs[1].address =
> > + rte_pktmbuf_iova_offset(input, *in_offset);
> > + desc->data_ptrs[1].blen = op->fft.input_sequence_size * 4;
> > + desc->data_ptrs[1].blkid = ACC_DMA_BLKID_IN;
> > + desc->data_ptrs[1].last = 1;
> > + desc->data_ptrs[1].dma_ext = 0;
> > + desc->data_ptrs[2].address =
> > + rte_pktmbuf_iova_offset(output, *out_offset);
> > + desc->data_ptrs[2].blen = op->fft.output_sequence_size * 4;
> > + desc->data_ptrs[2].blkid = ACC_DMA_BLKID_OUT_HARD;
> > + desc->data_ptrs[2].last = 1;
> > + desc->data_ptrs[2].dma_ext = 0;
> > + desc->m2dlen = 2;
> > + desc->d2mlen = 1;
> > + desc->ib_ant_offset = op->fft.input_sequence_size;
> > + desc->num_ant = op->fft.num_antennas_log2 - 3;
> > + int num_cs = 0, i;
> > + for (i = 0; i < 12; i++)
> > + if (check_bit(op->fft.cs_bitmap, 1 << i))
> > + num_cs++;
> > + desc->num_cs = num_cs;
> > + desc->ob_cyc_offset = op->fft.output_sequence_size;
> > + desc->ob_ant_offset = op->fft.output_sequence_size * num_cs;
> > + desc->op_addr = op;
> > + return 0;
> > +}
> > +
> > +
> > +/** Enqueue one FFT operation for ACC200 device*/ static inline int
> > +enqueue_fft_one_op(struct acc_queue *q, struct rte_bbdev_fft_op *op,
> > + uint16_t total_enqueued_cbs)
> > +{
> > + union acc_dma_desc *desc;
> > + uint16_t desc_idx = ((q->sw_ring_head + total_enqueued_cbs) & q-
> >sw_ring_wrap_mask);
> > + desc = q->ring_addr + desc_idx;
>
> Don't mix declarations & code.
Thanks, updated in v7
>
> > + struct rte_mbuf *input, *output;
> > + uint32_t in_offset, out_offset;
> > + struct acc_fcw_fft *fcw;
> > +
> > + input = op->fft.base_input.data;
> > + output = op->fft.base_output.data;
> > + in_offset = op->fft.base_input.offset;
> > + out_offset = op->fft.base_output.offset;
> > + fcw = &desc->req.fcw_fft;
> > +
> > + acc200_fcw_fft_fill(op, fcw);
> > + acc200_dma_desc_fft_fill(op, &desc->req, input, output, &in_offset,
> > +&out_offset); #ifdef RTE_LIBRTE_BBDEV_DEBUG
> > + rte_memdump(stderr, "FCW", &desc->req.fcw_fft,
> > + sizeof(desc->req.fcw_fft));
> > + rte_memdump(stderr, "Req Desc.", desc, sizeof(*desc)); #endif
> > + return 1;
> > +}
> > +
> > +/* Enqueue decode operations for ACC200 device. */ static uint16_t
> > +acc200_enqueue_fft(struct rte_bbdev_queue_data *q_data,
> > + struct rte_bbdev_fft_op **ops, uint16_t num) {
> > + struct acc_queue *q;
> > + int32_t aq_avail, avail;
> > + uint16_t i;
> > + union acc_dma_desc *desc;
> > + int ret;
> > +
> > + aq_avail = acc_aq_avail(q_data, num);
> > + if (unlikely((aq_avail <= 0) || (num == 0)))
> > + return 0;
> > + q = q_data->queue_private;
> > + avail = acc_ring_avail_enq(q);
> > +
> > + for (i = 0; i < num; ++i) {
> > + /* Check if there are available space for further processing */
> > + if (unlikely(avail < 1))
> > + break;
> > + avail -= 1;
> > + ret = enqueue_fft_one_op(q, ops[i], i);
> > + if (ret < 0)
> > + break;
> > + }
> > +
> > + if (unlikely(i == 0))
> > + return 0; /* Nothing to enqueue */
> > +
> > + /* Set SDone in last CB in enqueued ops for CB mode*/
> > + desc = q->ring_addr + ((q->sw_ring_head + i - 1)
> > + & q->sw_ring_wrap_mask);
> > +
> > + desc->req.sdone_enable = 1;
> > + desc->req.irq_enable = q->irq_enable;
> > + acc_dma_enqueue(q, i, &q_data->queue_stats);
> > +
> > + /* Update stats */
> > + q_data->queue_stats.enqueued_count += i;
> > + q_data->queue_stats.enqueue_err_count += num - i;
> > + return i;
> > +}
> > +
> > +
> > +/* Dequeue one FFT operations from ACC200 device */ static inline int
> > +dequeue_fft_one_op(struct rte_bbdev_queue_data *q_data,
> > + struct acc_queue *q, struct rte_bbdev_fft_op **ref_op,
> > + uint16_t dequeued_cbs, uint32_t *aq_dequeued) {
> > + union acc_dma_desc *desc, atom_desc;
> > + union acc_dma_rsp_desc rsp;
> > + struct rte_bbdev_fft_op *op;
> > +
> > + desc = q->ring_addr + ((q->sw_ring_tail + dequeued_cbs)
> > + & q->sw_ring_wrap_mask);
> > + atom_desc.atom_hdr = __atomic_load_n((uint64_t *)desc,
> > + __ATOMIC_RELAXED);
> > +
> > + /* Check fdone bit */
> > + if (!(atom_desc.rsp.val & ACC_FDONE))
> > + return -1;
> > +
> > + rsp.val = atom_desc.rsp.val;
> > +#ifdef RTE_LIBRTE_BBDEV_DEBUG
> > + rte_memdump(stderr, "Resp", &desc->rsp.val,
> > + sizeof(desc->rsp.val));
> > +#endif
> > + /* Dequeue */
> > + op = desc->req.op_addr;
> > +
> > + /* Clearing status, it will be set based on response */
> > + op->status = 0;
> > + op->status |= rsp.input_err << RTE_BBDEV_DATA_ERROR;
> > + op->status |= rsp.dma_err << RTE_BBDEV_DRV_ERROR;
> > + op->status |= rsp.fcw_err << RTE_BBDEV_DRV_ERROR;
> > + if (op->status != 0)
> > + q_data->queue_stats.dequeue_err_count++;
> > +
> > + /* Check if this is the last desc in batch (Atomic Queue) */
> > + if (desc->req.last_desc_in_batch) {
> > + (*aq_dequeued)++;
> > + desc->req.last_desc_in_batch = 0;
> > + }
> > + desc->rsp.val = ACC_DMA_DESC_TYPE;
> > + desc->rsp.add_info_0 = 0;
> > + *ref_op = op;
> > + /* One CB (op) was successfully dequeued */
> > + return 1;
> > +}
> > +
> > +
> > +/* Dequeue FFT operations from ACC200 device. */ static uint16_t
> > +acc200_dequeue_fft(struct rte_bbdev_queue_data *q_data,
> > + struct rte_bbdev_fft_op **ops, uint16_t num) {
> > + struct acc_queue *q = q_data->queue_private;
> > + uint16_t dequeue_num, i, dequeued_cbs = 0;
> > + uint32_t avail = acc_ring_avail_deq(q);
> > + uint32_t aq_dequeued = 0;
> > + int ret;
> > +
> > + dequeue_num = RTE_MIN(avail, num);
> > +
> > + for (i = 0; i < dequeue_num; ++i) {
> > + ret = dequeue_fft_one_op(q_data, q, &ops[i],
> dequeued_cbs, &aq_dequeued);
> > + if (ret <= 0)
> > + break;
> > + dequeued_cbs += ret;
> > + }
> > +
> > + q->aq_dequeued += aq_dequeued;
> > + q->sw_ring_tail += dequeued_cbs;
> > + /* Update enqueue stats */
> > + q_data->queue_stats.dequeued_count += i;
> > + return i;
> > +}
> > +
> > /* Initialization Function */
> > static void
> > acc200_bbdev_init(struct rte_bbdev *dev, struct rte_pci_driver *drv)
> > @@ -2917,6 +3153,8 @@ acc200_bbdev_init(struct rte_bbdev *dev, struct
> rte_pci_driver *drv)
> > dev->enqueue_ldpc_dec_ops = acc200_enqueue_ldpc_dec;
> > dev->dequeue_ldpc_enc_ops = acc200_dequeue_ldpc_enc;
> > dev->dequeue_ldpc_dec_ops = acc200_dequeue_ldpc_dec;
> > + dev->enqueue_fft_ops = acc200_enqueue_fft;
> > + dev->dequeue_fft_ops = acc200_dequeue_fft;
> >
> > ((struct acc_device *) dev->data->dev_private)->pf_device =
> > !strcmp(drv->driver.name,
^ permalink raw reply [flat|nested] 28+ messages in thread
* [PATCH v6 11/14] baseband/acc: support interrupt
2022-09-24 0:50 From: Nicolas Chautru <nicolas.chautru@intel.com> Nicolas Chautru
` (9 preceding siblings ...)
2022-09-24 0:50 ` [PATCH v6 10/14] baseband/acc: add support for FFT operations Nicolas Chautru
@ 2022-09-24 0:50 ` Nicolas Chautru
2022-09-27 13:49 ` Maxime Coquelin
2022-09-24 0:50 ` [PATCH v6 12/14] baseband/acc: add device status and vf2pf comms Nicolas Chautru
` (2 subsequent siblings)
13 siblings, 1 reply; 28+ messages in thread
From: Nicolas Chautru @ 2022-09-24 0:50 UTC (permalink / raw)
To: dev, thomas
Cc: maxime.coquelin, trix, mdr, bruce.richardson, hemant.agrawal,
david.marchand, stephen, hernan.vargas, Nic Chautru
From: Nic Chautru <nicolas.chautru@intel.com>
Adding support for capability and functions for
MSI/MSI-X interrupt and underlying information ring.
Signed-off-by: Nic Chautru <nicolas.chautru@intel.com>
---
drivers/baseband/acc/rte_acc200_pmd.c | 303 +++++++++++++++++++++++++-
1 file changed, 301 insertions(+), 2 deletions(-)
diff --git a/drivers/baseband/acc/rte_acc200_pmd.c b/drivers/baseband/acc/rte_acc200_pmd.c
index 7f2cd71166..46027ff6af 100644
--- a/drivers/baseband/acc/rte_acc200_pmd.c
+++ b/drivers/baseband/acc/rte_acc200_pmd.c
@@ -220,6 +220,152 @@ fetch_acc200_config(struct rte_bbdev *dev)
acc_conf->q_fft.aq_depth_log2);
}
+/* Checks PF Info Ring to find the interrupt cause and handles it accordingly */
+static inline void
+acc200_check_ir(struct acc_device *acc200_dev)
+{
+ volatile union acc_info_ring_data *ring_data;
+ uint16_t info_ring_head = acc200_dev->info_ring_head;
+ if (acc200_dev->info_ring == NULL)
+ return;
+
+ ring_data = acc200_dev->info_ring + (acc200_dev->info_ring_head &
+ ACC_INFO_RING_MASK);
+
+ while (ring_data->valid) {
+ if ((ring_data->int_nb < ACC200_PF_INT_DMA_DL_DESC_IRQ) || (
+ ring_data->int_nb >
+ ACC200_PF_INT_DMA_DL5G_DESC_IRQ)) {
+ rte_bbdev_log(WARNING, "InfoRing: ITR:%d Info:0x%x",
+ ring_data->int_nb, ring_data->detailed_info);
+ /* Initialize Info Ring entry and move forward */
+ ring_data->val = 0;
+ }
+ info_ring_head++;
+ ring_data = acc200_dev->info_ring +
+ (info_ring_head & ACC_INFO_RING_MASK);
+ }
+}
+
+/* Interrupt handler triggered by ACC200 dev for handling specific interrupt */
+static void
+acc200_dev_interrupt_handler(void *cb_arg)
+{
+ struct rte_bbdev *dev = cb_arg;
+ struct acc_device *acc200_dev = dev->data->dev_private;
+ volatile union acc_info_ring_data *ring_data;
+ struct acc_deq_intr_details deq_intr_det;
+
+ ring_data = acc200_dev->info_ring + (acc200_dev->info_ring_head & ACC_INFO_RING_MASK);
+
+ while (ring_data->valid) {
+ if (acc200_dev->pf_device) {
+ rte_bbdev_log_debug(
+ "ACC200 PF Interrupt received, Info Ring data: 0x%x -> %d",
+ ring_data->val, ring_data->int_nb);
+
+ switch (ring_data->int_nb) {
+ case ACC200_PF_INT_DMA_DL_DESC_IRQ:
+ case ACC200_PF_INT_DMA_UL_DESC_IRQ:
+ case ACC200_PF_INT_DMA_FFT_DESC_IRQ:
+ case ACC200_PF_INT_DMA_UL5G_DESC_IRQ:
+ case ACC200_PF_INT_DMA_DL5G_DESC_IRQ:
+ deq_intr_det.queue_id = get_queue_id_from_ring_info(
+ dev->data, *ring_data);
+ if (deq_intr_det.queue_id == UINT16_MAX) {
+ rte_bbdev_log(ERR,
+ "Couldn't find queue: aq_id: %u, qg_id: %u, vf_id: %u",
+ ring_data->aq_id,
+ ring_data->qg_id,
+ ring_data->vf_id);
+ return;
+ }
+ rte_bbdev_pmd_callback_process(dev,
+ RTE_BBDEV_EVENT_DEQUEUE, &deq_intr_det);
+ break;
+ default:
+ rte_bbdev_pmd_callback_process(dev, RTE_BBDEV_EVENT_ERROR, NULL);
+ break;
+ }
+ } else {
+ rte_bbdev_log_debug(
+ "ACC200 VF Interrupt received, Info Ring data: 0x%x\n",
+ ring_data->val);
+ switch (ring_data->int_nb) {
+ case ACC200_VF_INT_DMA_DL_DESC_IRQ:
+ case ACC200_VF_INT_DMA_UL_DESC_IRQ:
+ case ACC200_VF_INT_DMA_FFT_DESC_IRQ:
+ case ACC200_VF_INT_DMA_UL5G_DESC_IRQ:
+ case ACC200_VF_INT_DMA_DL5G_DESC_IRQ:
+ /* VFs are not aware of their vf_id - it's set to 0 */
+ ring_data->vf_id = 0;
+ deq_intr_det.queue_id = get_queue_id_from_ring_info(
+ dev->data, *ring_data);
+ if (deq_intr_det.queue_id == UINT16_MAX) {
+ rte_bbdev_log(ERR,
+ "Couldn't find queue: aq_id: %u, qg_id: %u",
+ ring_data->aq_id,
+ ring_data->qg_id);
+ return;
+ }
+ rte_bbdev_pmd_callback_process(dev,
+ RTE_BBDEV_EVENT_DEQUEUE, &deq_intr_det);
+ break;
+ default:
+ rte_bbdev_pmd_callback_process(dev, RTE_BBDEV_EVENT_ERROR, NULL);
+ break;
+ }
+ }
+
+ /* Initialize Info Ring entry and move forward */
+ ring_data->val = 0;
+ ++acc200_dev->info_ring_head;
+ ring_data = acc200_dev->info_ring +
+ (acc200_dev->info_ring_head & ACC_INFO_RING_MASK);
+ }
+}
+
+/* Allocate and setup inforing */
+static int
+allocate_info_ring(struct rte_bbdev *dev)
+{
+ struct acc_device *d = dev->data->dev_private;
+ const struct acc200_registry_addr *reg_addr;
+ rte_iova_t info_ring_iova;
+ uint32_t phys_low, phys_high;
+
+ if (d->info_ring != NULL)
+ return 0; /* Already configured */
+
+ /* Choose correct registry addresses for the device type */
+ if (d->pf_device)
+ reg_addr = &pf_reg_addr;
+ else
+ reg_addr = &vf_reg_addr;
+ /* Allocate InfoRing */
+ d->info_ring = rte_zmalloc_socket("Info Ring", ACC_INFO_RING_NUM_ENTRIES *
+ sizeof(*d->info_ring), RTE_CACHE_LINE_SIZE, dev->data->socket_id);
+ if (d->info_ring == NULL) {
+ rte_bbdev_log(ERR,
+ "Failed to allocate Info Ring for %s:%u",
+ dev->device->driver->name,
+ dev->data->dev_id);
+ return -ENOMEM;
+ }
+ info_ring_iova = rte_malloc_virt2iova(d->info_ring);
+
+ /* Setup Info Ring */
+ phys_high = (uint32_t)(info_ring_iova >> 32);
+ phys_low = (uint32_t)(info_ring_iova);
+ acc_reg_write(d, reg_addr->info_ring_hi, phys_high);
+ acc_reg_write(d, reg_addr->info_ring_lo, phys_low);
+ acc_reg_write(d, reg_addr->info_ring_en, ACC200_REG_IRQ_EN_ALL);
+ d->info_ring_head = (acc_reg_read(d, reg_addr->info_ring_ptr) &
+ 0xFFF) / sizeof(union acc_info_ring_data);
+ return 0;
+}
+
+
/* Allocate 64MB memory used for all software rings */
static int
acc200_setup_queues(struct rte_bbdev *dev, uint16_t num_queues, int socket_id)
@@ -328,6 +474,14 @@ acc200_setup_queues(struct rte_bbdev *dev, uint16_t num_queues, int socket_id)
acc_reg_write(d, reg_addr->tail_ptrs_fft_hi, phys_high);
acc_reg_write(d, reg_addr->tail_ptrs_fft_lo, phys_low);
+ ret = allocate_info_ring(dev);
+ if (ret < 0) {
+ rte_bbdev_log(ERR, "Failed to allocate info_ring for %s:%u",
+ dev->device->driver->name,
+ dev->data->dev_id);
+ /* Continue */
+ }
+
if (d->harq_layout == NULL)
d->harq_layout = rte_zmalloc_socket("HARQ Layout",
ACC_HARQ_LAYOUT * sizeof(*d->harq_layout),
@@ -358,17 +512,120 @@ acc200_setup_queues(struct rte_bbdev *dev, uint16_t num_queues, int socket_id)
return ret;
}
+static int
+acc200_intr_enable(struct rte_bbdev *dev)
+{
+ int ret;
+ struct acc_device *d = dev->data->dev_private;
+ /*
+ * MSI/MSI-X are supported
+ * Option controlled by vfio-intr through EAL parameter
+ */
+ if (rte_intr_type_get(dev->intr_handle) == RTE_INTR_HANDLE_VFIO_MSI) {
+
+ ret = allocate_info_ring(dev);
+ if (ret < 0) {
+ rte_bbdev_log(ERR,
+ "Couldn't allocate info ring for device: %s",
+ dev->data->name);
+ return ret;
+ }
+ ret = rte_intr_enable(dev->intr_handle);
+ if (ret < 0) {
+ rte_bbdev_log(ERR,
+ "Couldn't enable interrupts for device: %s",
+ dev->data->name);
+ rte_free(d->info_ring);
+ return ret;
+ }
+ ret = rte_intr_callback_register(dev->intr_handle,
+ acc200_dev_interrupt_handler, dev);
+ if (ret < 0) {
+ rte_bbdev_log(ERR,
+ "Couldn't register interrupt callback for device: %s",
+ dev->data->name);
+ rte_free(d->info_ring);
+ return ret;
+ }
+
+ return 0;
+ } else if (rte_intr_type_get(dev->intr_handle) == RTE_INTR_HANDLE_VFIO_MSIX) {
+ int i, max_queues;
+ struct acc_device *acc200_dev = dev->data->dev_private;
+
+ ret = allocate_info_ring(dev);
+ if (ret < 0) {
+ rte_bbdev_log(ERR,
+ "Couldn't allocate info ring for device: %s",
+ dev->data->name);
+ return ret;
+ }
+
+ if (acc200_dev->pf_device)
+ max_queues = ACC200_MAX_PF_MSIX;
+ else
+ max_queues = ACC200_MAX_VF_MSIX;
+
+ if (rte_intr_efd_enable(dev->intr_handle, max_queues)) {
+ rte_bbdev_log(ERR, "Failed to create fds for %u queues",
+ dev->data->num_queues);
+ return -1;
+ }
+
+ for (i = 0; i < max_queues; ++i) {
+ if (rte_intr_efds_index_set(dev->intr_handle, i,
+ rte_intr_fd_get(dev->intr_handle)))
+ return -rte_errno;
+ }
+
+ if (rte_intr_vec_list_alloc(dev->intr_handle, "intr_vec",
+ dev->data->num_queues)) {
+ rte_bbdev_log(ERR, "Failed to allocate %u vectors",
+ dev->data->num_queues);
+ return -ENOMEM;
+ }
+
+ ret = rte_intr_enable(dev->intr_handle);
+
+ if (ret < 0) {
+ rte_bbdev_log(ERR,
+ "Couldn't enable interrupts for device: %s",
+ dev->data->name);
+ rte_free(d->info_ring);
+ return ret;
+ }
+ ret = rte_intr_callback_register(dev->intr_handle,
+ acc200_dev_interrupt_handler, dev);
+ if (ret < 0) {
+ rte_bbdev_log(ERR,
+ "Couldn't register interrupt callback for device: %s",
+ dev->data->name);
+ rte_free(d->info_ring);
+ return ret;
+ }
+
+ return 0;
+ }
+
+ rte_bbdev_log(ERR, "ACC200 (%s) supports only VFIO MSI/MSI-X interrupts\n",
+ dev->data->name);
+ return -ENOTSUP;
+}
+
/* Free memory used for software rings */
static int
acc200_dev_close(struct rte_bbdev *dev)
{
struct acc_device *d = dev->data->dev_private;
+ acc200_check_ir(d);
if (d->sw_rings_base != NULL) {
rte_free(d->tail_ptrs);
+ rte_free(d->info_ring);
rte_free(d->sw_rings_base);
rte_free(d->harq_layout);
d->sw_rings_base = NULL;
d->tail_ptrs = NULL;
+ d->info_ring = NULL;
d->harq_layout = NULL;
}
/* Ensure all in flight HW transactions are completed */
@@ -670,6 +927,7 @@ acc200_dev_info_get(struct rte_bbdev *dev,
RTE_BBDEV_TURBO_CONTINUE_CRC_MATCH |
RTE_BBDEV_TURBO_SOFT_OUTPUT |
RTE_BBDEV_TURBO_EARLY_TERMINATION |
+ RTE_BBDEV_TURBO_DEC_INTERRUPTS |
RTE_BBDEV_TURBO_NEG_LLR_1_BIT_IN |
RTE_BBDEV_TURBO_NEG_LLR_1_BIT_SOFT_OUT |
RTE_BBDEV_TURBO_MAP_DEC |
@@ -691,6 +949,7 @@ acc200_dev_info_get(struct rte_bbdev *dev,
RTE_BBDEV_TURBO_CRC_24B_ATTACH |
RTE_BBDEV_TURBO_RV_INDEX_BYPASS |
RTE_BBDEV_TURBO_RATE_MATCH |
+ RTE_BBDEV_TURBO_ENC_INTERRUPTS |
RTE_BBDEV_TURBO_ENC_SCATTER_GATHER,
.num_buffers_src =
RTE_BBDEV_TURBO_MAX_CODE_BLOCKS,
@@ -704,7 +963,8 @@ acc200_dev_info_get(struct rte_bbdev *dev,
.capability_flags =
RTE_BBDEV_LDPC_RATE_MATCH |
RTE_BBDEV_LDPC_CRC_24B_ATTACH |
- RTE_BBDEV_LDPC_INTERLEAVER_BYPASS,
+ RTE_BBDEV_LDPC_INTERLEAVER_BYPASS |
+ RTE_BBDEV_LDPC_ENC_INTERRUPTS,
.num_buffers_src =
RTE_BBDEV_LDPC_MAX_CODE_BLOCKS,
.num_buffers_dst =
@@ -725,7 +985,8 @@ acc200_dev_info_get(struct rte_bbdev *dev,
RTE_BBDEV_LDPC_DEINTERLEAVER_BYPASS |
RTE_BBDEV_LDPC_DEC_SCATTER_GATHER |
RTE_BBDEV_LDPC_HARQ_6BIT_COMPRESSION |
- RTE_BBDEV_LDPC_LLR_COMPRESSION,
+ RTE_BBDEV_LDPC_LLR_COMPRESSION |
+ RTE_BBDEV_LDPC_DEC_INTERRUPTS,
.llr_size = 8,
.llr_decimals = 1,
.num_buffers_src =
@@ -793,15 +1054,46 @@ acc200_dev_info_get(struct rte_bbdev *dev,
dev_info->min_alignment = 1;
dev_info->capabilities = bbdev_capabilities;
dev_info->harq_buffer_size = 0;
+
+ acc200_check_ir(d);
+}
+
+static int
+acc200_queue_intr_enable(struct rte_bbdev *dev, uint16_t queue_id)
+{
+ struct acc_queue *q = dev->data->queues[queue_id].queue_private;
+
+ if (rte_intr_type_get(dev->intr_handle) != RTE_INTR_HANDLE_VFIO_MSI &&
+ rte_intr_type_get(dev->intr_handle) != RTE_INTR_HANDLE_VFIO_MSIX)
+ return -ENOTSUP;
+
+ q->irq_enable = 1;
+ return 0;
+}
+
+static int
+acc200_queue_intr_disable(struct rte_bbdev *dev, uint16_t queue_id)
+{
+ struct acc_queue *q = dev->data->queues[queue_id].queue_private;
+
+ if (rte_intr_type_get(dev->intr_handle) != RTE_INTR_HANDLE_VFIO_MSI &&
+ rte_intr_type_get(dev->intr_handle) != RTE_INTR_HANDLE_VFIO_MSIX)
+ return -ENOTSUP;
+
+ q->irq_enable = 0;
+ return 0;
}
static const struct rte_bbdev_ops acc200_bbdev_ops = {
.setup_queues = acc200_setup_queues,
+ .intr_enable = acc200_intr_enable,
.close = acc200_dev_close,
.info_get = acc200_dev_info_get,
.queue_setup = acc200_queue_setup,
.queue_release = acc200_queue_release,
.queue_stop = acc_queue_stop,
+ .queue_intr_enable = acc200_queue_intr_enable,
+ .queue_intr_disable = acc200_queue_intr_disable
};
/* ACC200 PCI PF address map */
@@ -2574,6 +2866,7 @@ dequeue_dec_one_op_cb(struct rte_bbdev_queue_data *q_data,
if (op->status != 0) {
/* These errors are not expected */
q_data->queue_stats.dequeue_err_count++;
+ acc200_check_ir(q->d);
}
/* CRC invalid if error exists */
@@ -2643,6 +2936,9 @@ dequeue_ldpc_dec_one_op_cb(struct rte_bbdev_queue_data *q_data,
op->ldpc_dec.iter_count = (uint8_t) rsp.iter_cnt;
+ if (op->status & (1 << RTE_BBDEV_DRV_ERROR))
+ acc200_check_ir(q->d);
+
/* Check if this is the last desc in batch (Atomic Queue) */
if (desc->req.last_desc_in_batch) {
(*aq_dequeued)++;
@@ -3098,6 +3394,9 @@ dequeue_fft_one_op(struct rte_bbdev_queue_data *q_data,
if (op->status != 0)
q_data->queue_stats.dequeue_err_count++;
+ if (op->status & (1 << RTE_BBDEV_DRV_ERROR))
+ acc200_check_ir(q->d);
+
/* Check if this is the last desc in batch (Atomic Queue) */
if (desc->req.last_desc_in_batch) {
(*aq_dequeued)++;
--
2.37.1
^ permalink raw reply [flat|nested] 28+ messages in thread* Re: [PATCH v6 11/14] baseband/acc: support interrupt
2022-09-24 0:50 ` [PATCH v6 11/14] baseband/acc: support interrupt Nicolas Chautru
@ 2022-09-27 13:49 ` Maxime Coquelin
2022-09-29 21:15 ` Chautru, Nicolas
0 siblings, 1 reply; 28+ messages in thread
From: Maxime Coquelin @ 2022-09-27 13:49 UTC (permalink / raw)
To: Nicolas Chautru, dev, thomas
Cc: trix, mdr, bruce.richardson, hemant.agrawal, david.marchand,
stephen, hernan.vargas
On 9/24/22 02:50, Nicolas Chautru wrote:
> From: Nic Chautru <nicolas.chautru@intel.com>
>
> Adding support for capability and functions for
> MSI/MSI-X interrupt and underlying information ring.
>
> Signed-off-by: Nic Chautru <nicolas.chautru@intel.com>
> ---
> drivers/baseband/acc/rte_acc200_pmd.c | 303 +++++++++++++++++++++++++-
> 1 file changed, 301 insertions(+), 2 deletions(-)
>
> diff --git a/drivers/baseband/acc/rte_acc200_pmd.c b/drivers/baseband/acc/rte_acc200_pmd.c
> index 7f2cd71166..46027ff6af 100644
> --- a/drivers/baseband/acc/rte_acc200_pmd.c
> +++ b/drivers/baseband/acc/rte_acc200_pmd.c
> @@ -220,6 +220,152 @@ fetch_acc200_config(struct rte_bbdev *dev)
> acc_conf->q_fft.aq_depth_log2);
> }
>
> +/* Checks PF Info Ring to find the interrupt cause and handles it accordingly */
> +static inline void
> +acc200_check_ir(struct acc_device *acc200_dev)
> +{
> + volatile union acc_info_ring_data *ring_data;
> + uint16_t info_ring_head = acc200_dev->info_ring_head;
> + if (acc200_dev->info_ring == NULL)
> + return;
My understanding is this function is called in the hot path, and above
condition is not expected to be true in working conditions.
If so, it can be marked as unlikely.
> +
> + ring_data = acc200_dev->info_ring + (acc200_dev->info_ring_head &
> + ACC_INFO_RING_MASK);
> +
> + while (ring_data->valid) {
> + if ((ring_data->int_nb < ACC200_PF_INT_DMA_DL_DESC_IRQ) || (
> + ring_data->int_nb >
> + ACC200_PF_INT_DMA_DL5G_DESC_IRQ)) {
> + rte_bbdev_log(WARNING, "InfoRing: ITR:%d Info:0x%x",
> + ring_data->int_nb, ring_data->detailed_info);
> + /* Initialize Info Ring entry and move forward */
> + ring_data->val = 0;
> + }
> + info_ring_head++;
> + ring_data = acc200_dev->info_ring +
> + (info_ring_head & ACC_INFO_RING_MASK);
> + }
> +}
> +
> +/* Interrupt handler triggered by ACC200 dev for handling specific interrupt */
> +static void
> +acc200_dev_interrupt_handler(void *cb_arg)
> +{
> + struct rte_bbdev *dev = cb_arg;
> + struct acc_device *acc200_dev = dev->data->dev_private;
> + volatile union acc_info_ring_data *ring_data;
> + struct acc_deq_intr_details deq_intr_det;
> +
> + ring_data = acc200_dev->info_ring + (acc200_dev->info_ring_head & ACC_INFO_RING_MASK);
> +
> + while (ring_data->valid) {
> + if (acc200_dev->pf_device) {
> + rte_bbdev_log_debug(
> + "ACC200 PF Interrupt received, Info Ring data: 0x%x -> %d",
> + ring_data->val, ring_data->int_nb);
> +
> + switch (ring_data->int_nb) {
> + case ACC200_PF_INT_DMA_DL_DESC_IRQ:
> + case ACC200_PF_INT_DMA_UL_DESC_IRQ:
> + case ACC200_PF_INT_DMA_FFT_DESC_IRQ:
> + case ACC200_PF_INT_DMA_UL5G_DESC_IRQ:
> + case ACC200_PF_INT_DMA_DL5G_DESC_IRQ:
> + deq_intr_det.queue_id = get_queue_id_from_ring_info(
> + dev->data, *ring_data);
> + if (deq_intr_det.queue_id == UINT16_MAX) {
> + rte_bbdev_log(ERR,
> + "Couldn't find queue: aq_id: %u, qg_id: %u, vf_id: %u",
> + ring_data->aq_id,
> + ring_data->qg_id,
> + ring_data->vf_id);
> + return;
> + }
> + rte_bbdev_pmd_callback_process(dev,
> + RTE_BBDEV_EVENT_DEQUEUE, &deq_intr_det);
> + break;
> + default:
> + rte_bbdev_pmd_callback_process(dev, RTE_BBDEV_EVENT_ERROR, NULL);
> + break;
> + }
> + } else {
> + rte_bbdev_log_debug(
> + "ACC200 VF Interrupt received, Info Ring data: 0x%x\n",
> + ring_data->val);
> + switch (ring_data->int_nb) {
> + case ACC200_VF_INT_DMA_DL_DESC_IRQ:
> + case ACC200_VF_INT_DMA_UL_DESC_IRQ:
> + case ACC200_VF_INT_DMA_FFT_DESC_IRQ:
> + case ACC200_VF_INT_DMA_UL5G_DESC_IRQ:
> + case ACC200_VF_INT_DMA_DL5G_DESC_IRQ:
> + /* VFs are not aware of their vf_id - it's set to 0 */
> + ring_data->vf_id = 0;
> + deq_intr_det.queue_id = get_queue_id_from_ring_info(
> + dev->data, *ring_data);
> + if (deq_intr_det.queue_id == UINT16_MAX) {
> + rte_bbdev_log(ERR,
> + "Couldn't find queue: aq_id: %u, qg_id: %u",
> + ring_data->aq_id,
> + ring_data->qg_id);
> + return;
> + }
> + rte_bbdev_pmd_callback_process(dev,
> + RTE_BBDEV_EVENT_DEQUEUE, &deq_intr_det);
> + break;
> + default:
> + rte_bbdev_pmd_callback_process(dev, RTE_BBDEV_EVENT_ERROR, NULL);
> + break;
> + }
> + }
> +
> + /* Initialize Info Ring entry and move forward */
> + ring_data->val = 0;
> + ++acc200_dev->info_ring_head;
> + ring_data = acc200_dev->info_ring +
> + (acc200_dev->info_ring_head & ACC_INFO_RING_MASK);
> + }
> +}
> +
> +/* Allocate and setup inforing */
> +static int
> +allocate_info_ring(struct rte_bbdev *dev)
> +{
> + struct acc_device *d = dev->data->dev_private;
> + const struct acc200_registry_addr *reg_addr;
> + rte_iova_t info_ring_iova;
> + uint32_t phys_low, phys_high;
> +
> + if (d->info_ring != NULL)
> + return 0; /* Already configured */
> +
> + /* Choose correct registry addresses for the device type */
> + if (d->pf_device)
> + reg_addr = &pf_reg_addr;
> + else
> + reg_addr = &vf_reg_addr;
> + /* Allocate InfoRing */
> + d->info_ring = rte_zmalloc_socket("Info Ring", ACC_INFO_RING_NUM_ENTRIES *
> + sizeof(*d->info_ring), RTE_CACHE_LINE_SIZE, dev->data->socket_id);
> + if (d->info_ring == NULL) {
> + rte_bbdev_log(ERR,
> + "Failed to allocate Info Ring for %s:%u",
> + dev->device->driver->name,
> + dev->data->dev_id);
> + return -ENOMEM;
> + }
> + info_ring_iova = rte_malloc_virt2iova(d->info_ring);
> +
> + /* Setup Info Ring */
> + phys_high = (uint32_t)(info_ring_iova >> 32);
> + phys_low = (uint32_t)(info_ring_iova);
> + acc_reg_write(d, reg_addr->info_ring_hi, phys_high);
> + acc_reg_write(d, reg_addr->info_ring_lo, phys_low);
> + acc_reg_write(d, reg_addr->info_ring_en, ACC200_REG_IRQ_EN_ALL);
> + d->info_ring_head = (acc_reg_read(d, reg_addr->info_ring_ptr) &
> + 0xFFF) / sizeof(union acc_info_ring_data);
> + return 0;
> +}
> +
> +
> /* Allocate 64MB memory used for all software rings */
> static int
> acc200_setup_queues(struct rte_bbdev *dev, uint16_t num_queues, int socket_id)
> @@ -328,6 +474,14 @@ acc200_setup_queues(struct rte_bbdev *dev, uint16_t num_queues, int socket_id)
> acc_reg_write(d, reg_addr->tail_ptrs_fft_hi, phys_high);
> acc_reg_write(d, reg_addr->tail_ptrs_fft_lo, phys_low);
>
> + ret = allocate_info_ring(dev);
> + if (ret < 0) {
> + rte_bbdev_log(ERR, "Failed to allocate info_ring for %s:%u",
> + dev->device->driver->name,
> + dev->data->dev_id);
> + /* Continue */
> + }
> +
> if (d->harq_layout == NULL)
> d->harq_layout = rte_zmalloc_socket("HARQ Layout",
> ACC_HARQ_LAYOUT * sizeof(*d->harq_layout),
> @@ -358,17 +512,120 @@ acc200_setup_queues(struct rte_bbdev *dev, uint16_t num_queues, int socket_id)
> return ret;
> }
>
> +static int
> +acc200_intr_enable(struct rte_bbdev *dev)
> +{
> + int ret;
> + struct acc_device *d = dev->data->dev_private;
> + /*
> + * MSI/MSI-X are supported
> + * Option controlled by vfio-intr through EAL parameter
> + */
> + if (rte_intr_type_get(dev->intr_handle) == RTE_INTR_HANDLE_VFIO_MSI) {
> +
> + ret = allocate_info_ring(dev);
> + if (ret < 0) {
> + rte_bbdev_log(ERR,
> + "Couldn't allocate info ring for device: %s",
> + dev->data->name);
> + return ret;
> + }
> + ret = rte_intr_enable(dev->intr_handle);
> + if (ret < 0) {
> + rte_bbdev_log(ERR,
> + "Couldn't enable interrupts for device: %s",
> + dev->data->name);
> + rte_free(d->info_ring);
> + return ret;
> + }
> + ret = rte_intr_callback_register(dev->intr_handle,
> + acc200_dev_interrupt_handler, dev);
> + if (ret < 0) {
> + rte_bbdev_log(ERR,
> + "Couldn't register interrupt callback for device: %s",
> + dev->data->name);
> + rte_free(d->info_ring);
> + return ret;
> + }
> +
> + return 0;
> + } else if (rte_intr_type_get(dev->intr_handle) == RTE_INTR_HANDLE_VFIO_MSIX) {
> + int i, max_queues;
> + struct acc_device *acc200_dev = dev->data->dev_private;
> +
> + ret = allocate_info_ring(dev);
> + if (ret < 0) {
> + rte_bbdev_log(ERR,
> + "Couldn't allocate info ring for device: %s",
> + dev->data->name);
> + return ret;
> + }
> +
> + if (acc200_dev->pf_device)
> + max_queues = ACC200_MAX_PF_MSIX;
> + else
> + max_queues = ACC200_MAX_VF_MSIX;
> +
> + if (rte_intr_efd_enable(dev->intr_handle, max_queues)) {
> + rte_bbdev_log(ERR, "Failed to create fds for %u queues",
> + dev->data->num_queues);
> + return -1;
> + }
> +
> + for (i = 0; i < max_queues; ++i) {
> + if (rte_intr_efds_index_set(dev->intr_handle, i,
> + rte_intr_fd_get(dev->intr_handle)))
> + return -rte_errno;
> + }
> +
> + if (rte_intr_vec_list_alloc(dev->intr_handle, "intr_vec",
> + dev->data->num_queues)) {
> + rte_bbdev_log(ERR, "Failed to allocate %u vectors",
> + dev->data->num_queues);
> + return -ENOMEM;
> + }
> +
> + ret = rte_intr_enable(dev->intr_handle);
> +
> + if (ret < 0) {
> + rte_bbdev_log(ERR,
> + "Couldn't enable interrupts for device: %s",
> + dev->data->name);
> + rte_free(d->info_ring);
> + return ret;
> + }
> + ret = rte_intr_callback_register(dev->intr_handle,
> + acc200_dev_interrupt_handler, dev);
> + if (ret < 0) {
> + rte_bbdev_log(ERR,
> + "Couldn't register interrupt callback for device: %s",
> + dev->data->name);
> + rte_free(d->info_ring);
> + return ret;
> + }
> +
> + return 0;
> + }
> +
> + rte_bbdev_log(ERR, "ACC200 (%s) supports only VFIO MSI/MSI-X interrupts\n",
> + dev->data->name);
> + return -ENOTSUP;
> +}
> +
> /* Free memory used for software rings */
> static int
> acc200_dev_close(struct rte_bbdev *dev)
> {
> struct acc_device *d = dev->data->dev_private;
> + acc200_check_ir(d);
> if (d->sw_rings_base != NULL) {
> rte_free(d->tail_ptrs);
> + rte_free(d->info_ring);
> rte_free(d->sw_rings_base);
> rte_free(d->harq_layout);
> d->sw_rings_base = NULL;
> d->tail_ptrs = NULL;
> + d->info_ring = NULL;
> d->harq_layout = NULL;
Not a big deal, but rte_free() and NULL assignment are not done in the
same order.
> }
> /* Ensure all in flight HW transactions are completed */
> @@ -670,6 +927,7 @@ acc200_dev_info_get(struct rte_bbdev *dev,
> RTE_BBDEV_TURBO_CONTINUE_CRC_MATCH |
> RTE_BBDEV_TURBO_SOFT_OUTPUT |
> RTE_BBDEV_TURBO_EARLY_TERMINATION |
> + RTE_BBDEV_TURBO_DEC_INTERRUPTS |
> RTE_BBDEV_TURBO_NEG_LLR_1_BIT_IN |
> RTE_BBDEV_TURBO_NEG_LLR_1_BIT_SOFT_OUT |
> RTE_BBDEV_TURBO_MAP_DEC |
> @@ -691,6 +949,7 @@ acc200_dev_info_get(struct rte_bbdev *dev,
> RTE_BBDEV_TURBO_CRC_24B_ATTACH |
> RTE_BBDEV_TURBO_RV_INDEX_BYPASS |
> RTE_BBDEV_TURBO_RATE_MATCH |
> + RTE_BBDEV_TURBO_ENC_INTERRUPTS |
> RTE_BBDEV_TURBO_ENC_SCATTER_GATHER,
> .num_buffers_src =
> RTE_BBDEV_TURBO_MAX_CODE_BLOCKS,
> @@ -704,7 +963,8 @@ acc200_dev_info_get(struct rte_bbdev *dev,
> .capability_flags =
> RTE_BBDEV_LDPC_RATE_MATCH |
> RTE_BBDEV_LDPC_CRC_24B_ATTACH |
> - RTE_BBDEV_LDPC_INTERLEAVER_BYPASS,
> + RTE_BBDEV_LDPC_INTERLEAVER_BYPASS |
> + RTE_BBDEV_LDPC_ENC_INTERRUPTS,
> .num_buffers_src =
> RTE_BBDEV_LDPC_MAX_CODE_BLOCKS,
> .num_buffers_dst =
> @@ -725,7 +985,8 @@ acc200_dev_info_get(struct rte_bbdev *dev,
> RTE_BBDEV_LDPC_DEINTERLEAVER_BYPASS |
> RTE_BBDEV_LDPC_DEC_SCATTER_GATHER |
> RTE_BBDEV_LDPC_HARQ_6BIT_COMPRESSION |
> - RTE_BBDEV_LDPC_LLR_COMPRESSION,
> + RTE_BBDEV_LDPC_LLR_COMPRESSION |
> + RTE_BBDEV_LDPC_DEC_INTERRUPTS,
> .llr_size = 8,
> .llr_decimals = 1,
> .num_buffers_src =
> @@ -793,15 +1054,46 @@ acc200_dev_info_get(struct rte_bbdev *dev,
> dev_info->min_alignment = 1;
> dev_info->capabilities = bbdev_capabilities;
> dev_info->harq_buffer_size = 0;
> +
> + acc200_check_ir(d);
> +}
> +
> +static int
> +acc200_queue_intr_enable(struct rte_bbdev *dev, uint16_t queue_id)
> +{
> + struct acc_queue *q = dev->data->queues[queue_id].queue_private;
> +
> + if (rte_intr_type_get(dev->intr_handle) != RTE_INTR_HANDLE_VFIO_MSI &&
> + rte_intr_type_get(dev->intr_handle) != RTE_INTR_HANDLE_VFIO_MSIX)
> + return -ENOTSUP;
> +
> + q->irq_enable = 1;
> + return 0;
> +}
> +
> +static int
> +acc200_queue_intr_disable(struct rte_bbdev *dev, uint16_t queue_id)
> +{
> + struct acc_queue *q = dev->data->queues[queue_id].queue_private;
> +
> + if (rte_intr_type_get(dev->intr_handle) != RTE_INTR_HANDLE_VFIO_MSI &&
> + rte_intr_type_get(dev->intr_handle) != RTE_INTR_HANDLE_VFIO_MSIX)
> + return -ENOTSUP;
> +
> + q->irq_enable = 0;
> + return 0;
> }
>
> static const struct rte_bbdev_ops acc200_bbdev_ops = {
> .setup_queues = acc200_setup_queues,
> + .intr_enable = acc200_intr_enable,
> .close = acc200_dev_close,
> .info_get = acc200_dev_info_get,
> .queue_setup = acc200_queue_setup,
> .queue_release = acc200_queue_release,
> .queue_stop = acc_queue_stop,
> + .queue_intr_enable = acc200_queue_intr_enable,
> + .queue_intr_disable = acc200_queue_intr_disable
> };
>
> /* ACC200 PCI PF address map */
> @@ -2574,6 +2866,7 @@ dequeue_dec_one_op_cb(struct rte_bbdev_queue_data *q_data,
> if (op->status != 0) {
> /* These errors are not expected */
> q_data->queue_stats.dequeue_err_count++;
> + acc200_check_ir(q->d);
> }
>
> /* CRC invalid if error exists */
> @@ -2643,6 +2936,9 @@ dequeue_ldpc_dec_one_op_cb(struct rte_bbdev_queue_data *q_data,
>
> op->ldpc_dec.iter_count = (uint8_t) rsp.iter_cnt;
>
> + if (op->status & (1 << RTE_BBDEV_DRV_ERROR))
> + acc200_check_ir(q->d);
> +
> /* Check if this is the last desc in batch (Atomic Queue) */
> if (desc->req.last_desc_in_batch) {
> (*aq_dequeued)++;
> @@ -3098,6 +3394,9 @@ dequeue_fft_one_op(struct rte_bbdev_queue_data *q_data,
> if (op->status != 0)
> q_data->queue_stats.dequeue_err_count++;
>
> + if (op->status & (1 << RTE_BBDEV_DRV_ERROR))
> + acc200_check_ir(q->d);
> +
> /* Check if this is the last desc in batch (Atomic Queue) */
> if (desc->req.last_desc_in_batch) {
> (*aq_dequeued)++;
^ permalink raw reply [flat|nested] 28+ messages in thread* RE: [PATCH v6 11/14] baseband/acc: support interrupt
2022-09-27 13:49 ` Maxime Coquelin
@ 2022-09-29 21:15 ` Chautru, Nicolas
0 siblings, 0 replies; 28+ messages in thread
From: Chautru, Nicolas @ 2022-09-29 21:15 UTC (permalink / raw)
To: Maxime Coquelin, dev, thomas
Cc: trix, mdr, Richardson, Bruce, hemant.agrawal, david.marchand,
stephen, Vargas, Hernan
Hi Maxime,
> -----Original Message-----
> From: Maxime Coquelin <maxime.coquelin@redhat.com>
> Sent: Tuesday, September 27, 2022 6:50 AM
> To: Chautru, Nicolas <nicolas.chautru@intel.com>; dev@dpdk.org;
> thomas@monjalon.net
> Cc: trix@redhat.com; mdr@ashroe.eu; Richardson, Bruce
> <bruce.richardson@intel.com>; hemant.agrawal@nxp.com;
> david.marchand@redhat.com; stephen@networkplumber.org; Vargas, Hernan
> <hernan.vargas@intel.com>
> Subject: Re: [PATCH v6 11/14] baseband/acc: support interrupt
>
>
>
> On 9/24/22 02:50, Nicolas Chautru wrote:
> > From: Nic Chautru <nicolas.chautru@intel.com>
> >
> > Adding support for capability and functions for MSI/MSI-X interrupt
> > and underlying information ring.
> >
> > Signed-off-by: Nic Chautru <nicolas.chautru@intel.com>
> > ---
> > drivers/baseband/acc/rte_acc200_pmd.c | 303
> +++++++++++++++++++++++++-
> > 1 file changed, 301 insertions(+), 2 deletions(-)
> >
> > diff --git a/drivers/baseband/acc/rte_acc200_pmd.c
> > b/drivers/baseband/acc/rte_acc200_pmd.c
> > index 7f2cd71166..46027ff6af 100644
> > --- a/drivers/baseband/acc/rte_acc200_pmd.c
> > +++ b/drivers/baseband/acc/rte_acc200_pmd.c
> > @@ -220,6 +220,152 @@ fetch_acc200_config(struct rte_bbdev *dev)
> > acc_conf->q_fft.aq_depth_log2);
> > }
> >
> > +/* Checks PF Info Ring to find the interrupt cause and handles it
> > +accordingly */ static inline void acc200_check_ir(struct acc_device
> > +*acc200_dev) {
> > + volatile union acc_info_ring_data *ring_data;
> > + uint16_t info_ring_head = acc200_dev->info_ring_head;
> > + if (acc200_dev->info_ring == NULL)
> > + return;
>
> My understanding is this function is called in the hot path, and above condition
> is not expected to be true in working conditions.
> If so, it can be marked as unlikely.
Thanks, updated in v7
>
> > +
> > + ring_data = acc200_dev->info_ring + (acc200_dev->info_ring_head &
> > + ACC_INFO_RING_MASK);
> > +
> > + while (ring_data->valid) {
> > + if ((ring_data->int_nb < ACC200_PF_INT_DMA_DL_DESC_IRQ)
> || (
> > + ring_data->int_nb >
> > + ACC200_PF_INT_DMA_DL5G_DESC_IRQ)) {
> > + rte_bbdev_log(WARNING, "InfoRing: ITR:%d
> Info:0x%x",
> > + ring_data->int_nb, ring_data->detailed_info);
> > + /* Initialize Info Ring entry and move forward */
> > + ring_data->val = 0;
> > + }
> > + info_ring_head++;
> > + ring_data = acc200_dev->info_ring +
> > + (info_ring_head & ACC_INFO_RING_MASK);
> > + }
> > +}
> > +
> > +/* Interrupt handler triggered by ACC200 dev for handling specific
> > +interrupt */ static void acc200_dev_interrupt_handler(void *cb_arg) {
> > + struct rte_bbdev *dev = cb_arg;
> > + struct acc_device *acc200_dev = dev->data->dev_private;
> > + volatile union acc_info_ring_data *ring_data;
> > + struct acc_deq_intr_details deq_intr_det;
> > +
> > + ring_data = acc200_dev->info_ring + (acc200_dev->info_ring_head &
> > +ACC_INFO_RING_MASK);
> > +
> > + while (ring_data->valid) {
> > + if (acc200_dev->pf_device) {
> > + rte_bbdev_log_debug(
> > + "ACC200 PF Interrupt received, Info
> Ring data: 0x%x -> %d",
> > + ring_data->val, ring_data->int_nb);
> > +
> > + switch (ring_data->int_nb) {
> > + case ACC200_PF_INT_DMA_DL_DESC_IRQ:
> > + case ACC200_PF_INT_DMA_UL_DESC_IRQ:
> > + case ACC200_PF_INT_DMA_FFT_DESC_IRQ:
> > + case ACC200_PF_INT_DMA_UL5G_DESC_IRQ:
> > + case ACC200_PF_INT_DMA_DL5G_DESC_IRQ:
> > + deq_intr_det.queue_id =
> get_queue_id_from_ring_info(
> > + dev->data, *ring_data);
> > + if (deq_intr_det.queue_id == UINT16_MAX) {
> > + rte_bbdev_log(ERR,
> > + "Couldn't find queue:
> aq_id: %u, qg_id: %u, vf_id: %u",
> > + ring_data->aq_id,
> > + ring_data->qg_id,
> > + ring_data->vf_id);
> > + return;
> > + }
> > + rte_bbdev_pmd_callback_process(dev,
> > +
> RTE_BBDEV_EVENT_DEQUEUE, &deq_intr_det);
> > + break;
> > + default:
> > + rte_bbdev_pmd_callback_process(dev,
> RTE_BBDEV_EVENT_ERROR, NULL);
> > + break;
> > + }
> > + } else {
> > + rte_bbdev_log_debug(
> > + "ACC200 VF Interrupt received, Info
> Ring data: 0x%x\n",
> > + ring_data->val);
> > + switch (ring_data->int_nb) {
> > + case ACC200_VF_INT_DMA_DL_DESC_IRQ:
> > + case ACC200_VF_INT_DMA_UL_DESC_IRQ:
> > + case ACC200_VF_INT_DMA_FFT_DESC_IRQ:
> > + case ACC200_VF_INT_DMA_UL5G_DESC_IRQ:
> > + case ACC200_VF_INT_DMA_DL5G_DESC_IRQ:
> > + /* VFs are not aware of their vf_id - it's set to
> 0 */
> > + ring_data->vf_id = 0;
> > + deq_intr_det.queue_id =
> get_queue_id_from_ring_info(
> > + dev->data, *ring_data);
> > + if (deq_intr_det.queue_id == UINT16_MAX) {
> > + rte_bbdev_log(ERR,
> > + "Couldn't find queue:
> aq_id: %u, qg_id: %u",
> > + ring_data->aq_id,
> > + ring_data->qg_id);
> > + return;
> > + }
> > + rte_bbdev_pmd_callback_process(dev,
> > +
> RTE_BBDEV_EVENT_DEQUEUE, &deq_intr_det);
> > + break;
> > + default:
> > + rte_bbdev_pmd_callback_process(dev,
> RTE_BBDEV_EVENT_ERROR, NULL);
> > + break;
> > + }
> > + }
> > +
> > + /* Initialize Info Ring entry and move forward */
> > + ring_data->val = 0;
> > + ++acc200_dev->info_ring_head;
> > + ring_data = acc200_dev->info_ring +
> > + (acc200_dev->info_ring_head &
> ACC_INFO_RING_MASK);
> > + }
> > +}
> > +
> > +/* Allocate and setup inforing */
> > +static int
> > +allocate_info_ring(struct rte_bbdev *dev) {
> > + struct acc_device *d = dev->data->dev_private;
> > + const struct acc200_registry_addr *reg_addr;
> > + rte_iova_t info_ring_iova;
> > + uint32_t phys_low, phys_high;
> > +
> > + if (d->info_ring != NULL)
> > + return 0; /* Already configured */
> > +
> > + /* Choose correct registry addresses for the device type */
> > + if (d->pf_device)
> > + reg_addr = &pf_reg_addr;
> > + else
> > + reg_addr = &vf_reg_addr;
> > + /* Allocate InfoRing */
> > + d->info_ring = rte_zmalloc_socket("Info Ring",
> ACC_INFO_RING_NUM_ENTRIES *
> > + sizeof(*d->info_ring), RTE_CACHE_LINE_SIZE, dev-
> >data->socket_id);
> > + if (d->info_ring == NULL) {
> > + rte_bbdev_log(ERR,
> > + "Failed to allocate Info Ring for %s:%u",
> > + dev->device->driver->name,
> > + dev->data->dev_id);
> > + return -ENOMEM;
> > + }
> > + info_ring_iova = rte_malloc_virt2iova(d->info_ring);
> > +
> > + /* Setup Info Ring */
> > + phys_high = (uint32_t)(info_ring_iova >> 32);
> > + phys_low = (uint32_t)(info_ring_iova);
> > + acc_reg_write(d, reg_addr->info_ring_hi, phys_high);
> > + acc_reg_write(d, reg_addr->info_ring_lo, phys_low);
> > + acc_reg_write(d, reg_addr->info_ring_en, ACC200_REG_IRQ_EN_ALL);
> > + d->info_ring_head = (acc_reg_read(d, reg_addr->info_ring_ptr) &
> > + 0xFFF) / sizeof(union acc_info_ring_data);
> > + return 0;
> > +}
> > +
> > +
> > /* Allocate 64MB memory used for all software rings */
> > static int
> > acc200_setup_queues(struct rte_bbdev *dev, uint16_t num_queues, int
> > socket_id) @@ -328,6 +474,14 @@ acc200_setup_queues(struct rte_bbdev
> *dev, uint16_t num_queues, int socket_id)
> > acc_reg_write(d, reg_addr->tail_ptrs_fft_hi, phys_high);
> > acc_reg_write(d, reg_addr->tail_ptrs_fft_lo, phys_low);
> >
> > + ret = allocate_info_ring(dev);
> > + if (ret < 0) {
> > + rte_bbdev_log(ERR, "Failed to allocate info_ring for %s:%u",
> > + dev->device->driver->name,
> > + dev->data->dev_id);
> > + /* Continue */
> > + }
> > +
> > if (d->harq_layout == NULL)
> > d->harq_layout = rte_zmalloc_socket("HARQ Layout",
> > ACC_HARQ_LAYOUT * sizeof(*d-
> >harq_layout), @@ -358,17 +512,120
> > @@ acc200_setup_queues(struct rte_bbdev *dev, uint16_t num_queues, int
> socket_id)
> > return ret;
> > }
> >
> > +static int
> > +acc200_intr_enable(struct rte_bbdev *dev) {
> > + int ret;
> > + struct acc_device *d = dev->data->dev_private;
> > + /*
> > + * MSI/MSI-X are supported
> > + * Option controlled by vfio-intr through EAL parameter
> > + */
> > + if (rte_intr_type_get(dev->intr_handle) ==
> RTE_INTR_HANDLE_VFIO_MSI)
> > +{
> > +
> > + ret = allocate_info_ring(dev);
> > + if (ret < 0) {
> > + rte_bbdev_log(ERR,
> > + "Couldn't allocate info ring for device:
> %s",
> > + dev->data->name);
> > + return ret;
> > + }
> > + ret = rte_intr_enable(dev->intr_handle);
> > + if (ret < 0) {
> > + rte_bbdev_log(ERR,
> > + "Couldn't enable interrupts for device:
> %s",
> > + dev->data->name);
> > + rte_free(d->info_ring);
> > + return ret;
> > + }
> > + ret = rte_intr_callback_register(dev->intr_handle,
> > + acc200_dev_interrupt_handler, dev);
> > + if (ret < 0) {
> > + rte_bbdev_log(ERR,
> > + "Couldn't register interrupt callback
> for device: %s",
> > + dev->data->name);
> > + rte_free(d->info_ring);
> > + return ret;
> > + }
> > +
> > + return 0;
> > + } else if (rte_intr_type_get(dev->intr_handle) ==
> RTE_INTR_HANDLE_VFIO_MSIX) {
> > + int i, max_queues;
> > + struct acc_device *acc200_dev = dev->data->dev_private;
> > +
> > + ret = allocate_info_ring(dev);
> > + if (ret < 0) {
> > + rte_bbdev_log(ERR,
> > + "Couldn't allocate info ring for device:
> %s",
> > + dev->data->name);
> > + return ret;
> > + }
> > +
> > + if (acc200_dev->pf_device)
> > + max_queues = ACC200_MAX_PF_MSIX;
> > + else
> > + max_queues = ACC200_MAX_VF_MSIX;
> > +
> > + if (rte_intr_efd_enable(dev->intr_handle, max_queues)) {
> > + rte_bbdev_log(ERR, "Failed to create fds for %u
> queues",
> > + dev->data->num_queues);
> > + return -1;
> > + }
> > +
> > + for (i = 0; i < max_queues; ++i) {
> > + if (rte_intr_efds_index_set(dev->intr_handle, i,
> > + rte_intr_fd_get(dev->intr_handle)))
> > + return -rte_errno;
> > + }
> > +
> > + if (rte_intr_vec_list_alloc(dev->intr_handle, "intr_vec",
> > + dev->data->num_queues)) {
> > + rte_bbdev_log(ERR, "Failed to allocate %u vectors",
> > + dev->data->num_queues);
> > + return -ENOMEM;
> > + }
> > +
> > + ret = rte_intr_enable(dev->intr_handle);
> > +
> > + if (ret < 0) {
> > + rte_bbdev_log(ERR,
> > + "Couldn't enable interrupts for device:
> %s",
> > + dev->data->name);
> > + rte_free(d->info_ring);
> > + return ret;
> > + }
> > + ret = rte_intr_callback_register(dev->intr_handle,
> > + acc200_dev_interrupt_handler, dev);
> > + if (ret < 0) {
> > + rte_bbdev_log(ERR,
> > + "Couldn't register interrupt callback
> for device: %s",
> > + dev->data->name);
> > + rte_free(d->info_ring);
> > + return ret;
> > + }
> > +
> > + return 0;
> > + }
> > +
> > + rte_bbdev_log(ERR, "ACC200 (%s) supports only VFIO MSI/MSI-X
> interrupts\n",
> > + dev->data->name);
> > + return -ENOTSUP;
> > +}
> > +
> > /* Free memory used for software rings */
> > static int
> > acc200_dev_close(struct rte_bbdev *dev)
> > {
> > struct acc_device *d = dev->data->dev_private;
> > + acc200_check_ir(d);
> > if (d->sw_rings_base != NULL) {
> > rte_free(d->tail_ptrs);
> > + rte_free(d->info_ring);
> > rte_free(d->sw_rings_base);
> > rte_free(d->harq_layout);
> > d->sw_rings_base = NULL;
> > d->tail_ptrs = NULL;
> > + d->info_ring = NULL;
> > d->harq_layout = NULL;
>
> Not a big deal, but rte_free() and NULL assignment are not done in the same
> order.
Thanks, updated in v7
>
> > }
> > /* Ensure all in flight HW transactions are completed */ @@ -670,6
> > +927,7 @@ acc200_dev_info_get(struct rte_bbdev *dev,
> >
> RTE_BBDEV_TURBO_CONTINUE_CRC_MATCH |
> > RTE_BBDEV_TURBO_SOFT_OUTPUT |
> >
> RTE_BBDEV_TURBO_EARLY_TERMINATION |
> > +
> RTE_BBDEV_TURBO_DEC_INTERRUPTS |
> >
> RTE_BBDEV_TURBO_NEG_LLR_1_BIT_IN |
> >
> RTE_BBDEV_TURBO_NEG_LLR_1_BIT_SOFT_OUT |
> > RTE_BBDEV_TURBO_MAP_DEC |
> > @@ -691,6 +949,7 @@ acc200_dev_info_get(struct rte_bbdev *dev,
> >
> RTE_BBDEV_TURBO_CRC_24B_ATTACH |
> >
> RTE_BBDEV_TURBO_RV_INDEX_BYPASS |
> > RTE_BBDEV_TURBO_RATE_MATCH |
> > +
> RTE_BBDEV_TURBO_ENC_INTERRUPTS |
> >
> RTE_BBDEV_TURBO_ENC_SCATTER_GATHER,
> > .num_buffers_src =
> >
> RTE_BBDEV_TURBO_MAX_CODE_BLOCKS, @@ -704,7 +963,8 @@
> > acc200_dev_info_get(struct rte_bbdev *dev,
> > .capability_flags =
> > RTE_BBDEV_LDPC_RATE_MATCH |
> > RTE_BBDEV_LDPC_CRC_24B_ATTACH
> |
> > -
> RTE_BBDEV_LDPC_INTERLEAVER_BYPASS,
> > +
> RTE_BBDEV_LDPC_INTERLEAVER_BYPASS |
> > + RTE_BBDEV_LDPC_ENC_INTERRUPTS,
> > .num_buffers_src =
> >
> RTE_BBDEV_LDPC_MAX_CODE_BLOCKS,
> > .num_buffers_dst =
> > @@ -725,7 +985,8 @@ acc200_dev_info_get(struct rte_bbdev *dev,
> > RTE_BBDEV_LDPC_DEINTERLEAVER_BYPASS |
> > RTE_BBDEV_LDPC_DEC_SCATTER_GATHER |
> > RTE_BBDEV_LDPC_HARQ_6BIT_COMPRESSION
> |
> > - RTE_BBDEV_LDPC_LLR_COMPRESSION,
> > + RTE_BBDEV_LDPC_LLR_COMPRESSION |
> > + RTE_BBDEV_LDPC_DEC_INTERRUPTS,
> > .llr_size = 8,
> > .llr_decimals = 1,
> > .num_buffers_src =
> > @@ -793,15 +1054,46 @@ acc200_dev_info_get(struct rte_bbdev *dev,
> > dev_info->min_alignment = 1;
> > dev_info->capabilities = bbdev_capabilities;
> > dev_info->harq_buffer_size = 0;
> > +
> > + acc200_check_ir(d);
> > +}
> > +
> > +static int
> > +acc200_queue_intr_enable(struct rte_bbdev *dev, uint16_t queue_id) {
> > + struct acc_queue *q = dev->data->queues[queue_id].queue_private;
> > +
> > + if (rte_intr_type_get(dev->intr_handle) !=
> RTE_INTR_HANDLE_VFIO_MSI &&
> > + rte_intr_type_get(dev->intr_handle) !=
> RTE_INTR_HANDLE_VFIO_MSIX)
> > + return -ENOTSUP;
> > +
> > + q->irq_enable = 1;
> > + return 0;
> > +}
> > +
> > +static int
> > +acc200_queue_intr_disable(struct rte_bbdev *dev, uint16_t queue_id) {
> > + struct acc_queue *q = dev->data->queues[queue_id].queue_private;
> > +
> > + if (rte_intr_type_get(dev->intr_handle) !=
> RTE_INTR_HANDLE_VFIO_MSI &&
> > + rte_intr_type_get(dev->intr_handle) !=
> RTE_INTR_HANDLE_VFIO_MSIX)
> > + return -ENOTSUP;
> > +
> > + q->irq_enable = 0;
> > + return 0;
> > }
> >
> > static const struct rte_bbdev_ops acc200_bbdev_ops = {
> > .setup_queues = acc200_setup_queues,
> > + .intr_enable = acc200_intr_enable,
> > .close = acc200_dev_close,
> > .info_get = acc200_dev_info_get,
> > .queue_setup = acc200_queue_setup,
> > .queue_release = acc200_queue_release,
> > .queue_stop = acc_queue_stop,
> > + .queue_intr_enable = acc200_queue_intr_enable,
> > + .queue_intr_disable = acc200_queue_intr_disable
> > };
> >
> > /* ACC200 PCI PF address map */
> > @@ -2574,6 +2866,7 @@ dequeue_dec_one_op_cb(struct
> rte_bbdev_queue_data *q_data,
> > if (op->status != 0) {
> > /* These errors are not expected */
> > q_data->queue_stats.dequeue_err_count++;
> > + acc200_check_ir(q->d);
> > }
> >
> > /* CRC invalid if error exists */
> > @@ -2643,6 +2936,9 @@ dequeue_ldpc_dec_one_op_cb(struct
> > rte_bbdev_queue_data *q_data,
> >
> > op->ldpc_dec.iter_count = (uint8_t) rsp.iter_cnt;
> >
> > + if (op->status & (1 << RTE_BBDEV_DRV_ERROR))
> > + acc200_check_ir(q->d);
> > +
> > /* Check if this is the last desc in batch (Atomic Queue) */
> > if (desc->req.last_desc_in_batch) {
> > (*aq_dequeued)++;
> > @@ -3098,6 +3394,9 @@ dequeue_fft_one_op(struct
> rte_bbdev_queue_data *q_data,
> > if (op->status != 0)
> > q_data->queue_stats.dequeue_err_count++;
> >
> > + if (op->status & (1 << RTE_BBDEV_DRV_ERROR))
> > + acc200_check_ir(q->d);
> > +
> > /* Check if this is the last desc in batch (Atomic Queue) */
> > if (desc->req.last_desc_in_batch) {
> > (*aq_dequeued)++;
^ permalink raw reply [flat|nested] 28+ messages in thread
* [PATCH v6 12/14] baseband/acc: add device status and vf2pf comms
2022-09-24 0:50 From: Nicolas Chautru <nicolas.chautru@intel.com> Nicolas Chautru
` (10 preceding siblings ...)
2022-09-24 0:50 ` [PATCH v6 11/14] baseband/acc: support interrupt Nicolas Chautru
@ 2022-09-24 0:50 ` Nicolas Chautru
2022-09-24 0:50 ` [PATCH v6 13/14] baseband/acc: add PF configure companion function Nicolas Chautru
2022-09-24 0:50 ` [PATCH v6 14/14] baseband/acc: simplify meson dependency Nicolas Chautru
13 siblings, 0 replies; 28+ messages in thread
From: Nicolas Chautru @ 2022-09-24 0:50 UTC (permalink / raw)
To: dev, thomas
Cc: maxime.coquelin, trix, mdr, bruce.richardson, hemant.agrawal,
david.marchand, stephen, hernan.vargas, Nic Chautru
From: Nic Chautru <nicolas.chautru@intel.com>
Add support to expose the device status seen from the
host through v2pf mailbox communication.
Signed-off-by: Nic Chautru <nicolas.chautru@intel.com>
Reviewed-by: Maxime Coquelin <maxime.coquelin@redhat.com>
---
drivers/baseband/acc/rte_acc200_pmd.c | 64 ++++++++++++++++++++-------
1 file changed, 47 insertions(+), 17 deletions(-)
diff --git a/drivers/baseband/acc/rte_acc200_pmd.c b/drivers/baseband/acc/rte_acc200_pmd.c
index 46027ff6af..cd3214f6c9 100644
--- a/drivers/baseband/acc/rte_acc200_pmd.c
+++ b/drivers/baseband/acc/rte_acc200_pmd.c
@@ -201,23 +201,50 @@ fetch_acc200_config(struct rte_bbdev *dev)
rte_bbdev_log_debug(
"%s Config LLR SIGN IN/OUT %s %s QG %u %u %u %u %u AQ %u %u %u %u %u Len %u %u %u %u %u\n",
(d->pf_device) ? "PF" : "VF",
- (acc_conf->input_pos_llr_1_bit) ? "POS" : "NEG",
- (acc_conf->output_pos_llr_1_bit) ? "POS" : "NEG",
- acc_conf->q_ul_4g.num_qgroups,
- acc_conf->q_dl_4g.num_qgroups,
- acc_conf->q_ul_5g.num_qgroups,
- acc_conf->q_dl_5g.num_qgroups,
- acc_conf->q_fft.num_qgroups,
- acc_conf->q_ul_4g.num_aqs_per_groups,
- acc_conf->q_dl_4g.num_aqs_per_groups,
- acc_conf->q_ul_5g.num_aqs_per_groups,
- acc_conf->q_dl_5g.num_aqs_per_groups,
- acc_conf->q_fft.num_aqs_per_groups,
- acc_conf->q_ul_4g.aq_depth_log2,
- acc_conf->q_dl_4g.aq_depth_log2,
- acc_conf->q_ul_5g.aq_depth_log2,
- acc_conf->q_dl_5g.aq_depth_log2,
- acc_conf->q_fft.aq_depth_log2);
+ (acc200_conf->input_pos_llr_1_bit) ? "POS" : "NEG",
+ (acc200_conf->output_pos_llr_1_bit) ? "POS" : "NEG",
+ acc200_conf->q_ul_4g.num_qgroups,
+ acc200_conf->q_dl_4g.num_qgroups,
+ acc200_conf->q_ul_5g.num_qgroups,
+ acc200_conf->q_dl_5g.num_qgroups,
+ acc200_conf->q_fft.num_qgroups,
+ acc200_conf->q_ul_4g.num_aqs_per_groups,
+ acc200_conf->q_dl_4g.num_aqs_per_groups,
+ acc200_conf->q_ul_5g.num_aqs_per_groups,
+ acc200_conf->q_dl_5g.num_aqs_per_groups,
+ acc200_conf->q_fft.num_aqs_per_groups,
+ acc200_conf->q_ul_4g.aq_depth_log2,
+ acc200_conf->q_dl_4g.aq_depth_log2,
+ acc200_conf->q_ul_5g.aq_depth_log2,
+ acc200_conf->q_dl_5g.aq_depth_log2,
+ acc200_conf->q_fft.aq_depth_log2);
+}
+
+static inline void
+acc200_vf2pf(struct acc_device *d, unsigned int payload)
+{
+ acc_reg_write(d, HWVfHiVfToPfDbellVf, payload);
+}
+
+/* Request device status information */
+static inline uint32_t
+acc200_device_status(struct rte_bbdev *dev)
+{
+ struct acc_device *d = dev->data->dev_private;
+ uint32_t reg, time_out = 0;
+
+ if (d->pf_device)
+ return RTE_BBDEV_DEV_NOT_SUPPORTED;
+
+ acc200_vf2pf(d, ACC_VF2PF_STATUS_REQUEST);
+ reg = acc_reg_read(d, HWVfHiPfToVfDbellVf);
+ while ((time_out < ACC200_STATUS_TO) && (reg == RTE_BBDEV_DEV_NOSTATUS)) {
+ usleep(ACC200_STATUS_WAIT); /*< Wait or VF->PF->VF Comms */
+ reg = acc_reg_read(d, HWVfHiPfToVfDbellVf);
+ time_out++;
+ }
+
+ return reg;
}
/* Checks PF Info Ring to find the interrupt cause and handles it accordingly */
@@ -496,6 +523,7 @@ acc200_setup_queues(struct rte_bbdev *dev, uint16_t num_queues, int socket_id)
/* Mark as configured properly */
d->configured = true;
+ acc200_vf2pf(d, ACC_VF2PF_USING_VF);
rte_bbdev_log_debug(
"ACC200 (%s) configured sw_rings = %p, sw_rings_iova = %#"
@@ -1022,6 +1050,8 @@ acc200_dev_info_get(struct rte_bbdev *dev,
/* Read and save the populated config from ACC200 registers */
fetch_acc200_config(dev);
+ /* Check the status of device */
+ dev_info->device_status = acc200_device_status(dev);
/* Exposed number of queues */
dev_info->num_queues[RTE_BBDEV_OP_NONE] = 0;
--
2.37.1
^ permalink raw reply [flat|nested] 28+ messages in thread* [PATCH v6 13/14] baseband/acc: add PF configure companion function
2022-09-24 0:50 From: Nicolas Chautru <nicolas.chautru@intel.com> Nicolas Chautru
` (11 preceding siblings ...)
2022-09-24 0:50 ` [PATCH v6 12/14] baseband/acc: add device status and vf2pf comms Nicolas Chautru
@ 2022-09-24 0:50 ` Nicolas Chautru
2022-09-24 0:50 ` [PATCH v6 14/14] baseband/acc: simplify meson dependency Nicolas Chautru
13 siblings, 0 replies; 28+ messages in thread
From: Nicolas Chautru @ 2022-09-24 0:50 UTC (permalink / raw)
To: dev, thomas
Cc: maxime.coquelin, trix, mdr, bruce.richardson, hemant.agrawal,
david.marchand, stephen, hernan.vargas, Nic Chautru
From: Nic Chautru <nicolas.chautru@intel.com>
Add configure function notably to configure the device from
the PF within DPDK and bbdev-test (without external dependency).
Signed-off-by: Nic Chautru <nicolas.chautru@intel.com>
---
app/test-bbdev/test_bbdev_perf.c | 71 ++++
drivers/baseband/acc/meson.build | 2 +-
drivers/baseband/acc/rte_acc200_cfg.h | 48 +++
drivers/baseband/acc/rte_acc200_pmd.c | 462 ++++++++++++++++++++++++++
drivers/baseband/acc/version.map | 1 +
5 files changed, 583 insertions(+), 1 deletion(-)
create mode 100644 drivers/baseband/acc/rte_acc200_cfg.h
diff --git a/app/test-bbdev/test_bbdev_perf.c b/app/test-bbdev/test_bbdev_perf.c
index 41c78ded7d..ec6ee2a52c 100644
--- a/app/test-bbdev/test_bbdev_perf.c
+++ b/app/test-bbdev/test_bbdev_perf.c
@@ -62,6 +62,15 @@
#define ACC100_QMGR_INVALID_IDX -1
#define ACC100_QMGR_RR 1
#define ACC100_QOS_GBR 0
+#include <rte_acc200_cfg.h>
+#define ACC200PF_DRIVER_NAME ("intel_acc200_pf")
+#define ACC200VF_DRIVER_NAME ("intel_acc200_vf")
+#define ACC200_QMGR_NUM_AQS 16
+#define ACC200_QMGR_NUM_QGS 2
+#define ACC200_QMGR_AQ_DEPTH 5
+#define ACC200_QMGR_INVALID_IDX -1
+#define ACC200_QMGR_RR 1
+#define ACC200_QOS_GBR 0
#endif
#define OPS_CACHE_SIZE 256U
@@ -761,6 +770,68 @@ add_bbdev_dev(uint8_t dev_id, struct rte_bbdev_info *info,
"Failed to configure ACC100 PF for bbdev %s",
info->dev_name);
}
+ if ((get_init_device() == true) &&
+ (!strcmp(info->drv.driver_name, ACC200PF_DRIVER_NAME))) {
+ struct rte_acc_conf conf;
+ unsigned int i;
+
+ printf("Configure ACC200 FEC Driver %s with default values\n",
+ info->drv.driver_name);
+
+ /* clear default configuration before initialization */
+ memset(&conf, 0, sizeof(struct rte_acc_conf));
+
+ /* Always set in PF mode for built-in configuration */
+ conf.pf_mode_en = true;
+ for (i = 0; i < RTE_ACC_NUM_VFS; ++i) {
+ conf.arb_dl_4g[i].gbr_threshold1 = ACC200_QOS_GBR;
+ conf.arb_dl_4g[i].gbr_threshold1 = ACC200_QOS_GBR;
+ conf.arb_dl_4g[i].round_robin_weight = ACC200_QMGR_RR;
+ conf.arb_ul_4g[i].gbr_threshold1 = ACC200_QOS_GBR;
+ conf.arb_ul_4g[i].gbr_threshold1 = ACC200_QOS_GBR;
+ conf.arb_ul_4g[i].round_robin_weight = ACC200_QMGR_RR;
+ conf.arb_dl_5g[i].gbr_threshold1 = ACC200_QOS_GBR;
+ conf.arb_dl_5g[i].gbr_threshold1 = ACC200_QOS_GBR;
+ conf.arb_dl_5g[i].round_robin_weight = ACC200_QMGR_RR;
+ conf.arb_ul_5g[i].gbr_threshold1 = ACC200_QOS_GBR;
+ conf.arb_ul_5g[i].gbr_threshold1 = ACC200_QOS_GBR;
+ conf.arb_ul_5g[i].round_robin_weight = ACC200_QMGR_RR;
+ conf.arb_fft[i].gbr_threshold1 = ACC200_QOS_GBR;
+ conf.arb_fft[i].gbr_threshold1 = ACC200_QOS_GBR;
+ conf.arb_fft[i].round_robin_weight = ACC200_QMGR_RR;
+ }
+
+ conf.input_pos_llr_1_bit = true;
+ conf.output_pos_llr_1_bit = true;
+ conf.num_vf_bundles = 1; /**< Number of VF bundles to setup */
+
+ conf.q_ul_4g.num_qgroups = ACC200_QMGR_NUM_QGS;
+ conf.q_ul_4g.first_qgroup_index = ACC200_QMGR_INVALID_IDX;
+ conf.q_ul_4g.num_aqs_per_groups = ACC200_QMGR_NUM_AQS;
+ conf.q_ul_4g.aq_depth_log2 = ACC200_QMGR_AQ_DEPTH;
+ conf.q_dl_4g.num_qgroups = ACC200_QMGR_NUM_QGS;
+ conf.q_dl_4g.first_qgroup_index = ACC200_QMGR_INVALID_IDX;
+ conf.q_dl_4g.num_aqs_per_groups = ACC200_QMGR_NUM_AQS;
+ conf.q_dl_4g.aq_depth_log2 = ACC200_QMGR_AQ_DEPTH;
+ conf.q_ul_5g.num_qgroups = ACC200_QMGR_NUM_QGS;
+ conf.q_ul_5g.first_qgroup_index = ACC200_QMGR_INVALID_IDX;
+ conf.q_ul_5g.num_aqs_per_groups = ACC200_QMGR_NUM_AQS;
+ conf.q_ul_5g.aq_depth_log2 = ACC200_QMGR_AQ_DEPTH;
+ conf.q_dl_5g.num_qgroups = ACC200_QMGR_NUM_QGS;
+ conf.q_dl_5g.first_qgroup_index = ACC200_QMGR_INVALID_IDX;
+ conf.q_dl_5g.num_aqs_per_groups = ACC200_QMGR_NUM_AQS;
+ conf.q_dl_5g.aq_depth_log2 = ACC200_QMGR_AQ_DEPTH;
+ conf.q_fft.num_qgroups = ACC200_QMGR_NUM_QGS;
+ conf.q_fft.first_qgroup_index = ACC200_QMGR_INVALID_IDX;
+ conf.q_fft.num_aqs_per_groups = ACC200_QMGR_NUM_AQS;
+ conf.q_fft.aq_depth_log2 = ACC200_QMGR_AQ_DEPTH;
+
+ /* setup PF with configuration information */
+ ret = rte_acc200_configure(info->dev_name, &conf);
+ TEST_ASSERT_SUCCESS(ret,
+ "Failed to configure ACC200 PF for bbdev %s",
+ info->dev_name);
+ }
#endif
/* Let's refresh this now this is configured */
rte_bbdev_info_get(dev_id, info);
diff --git a/drivers/baseband/acc/meson.build b/drivers/baseband/acc/meson.build
index 63912f0621..7ae162aab8 100644
--- a/drivers/baseband/acc/meson.build
+++ b/drivers/baseband/acc/meson.build
@@ -5,4 +5,4 @@ deps += ['bbdev', 'bus_vdev', 'ring', 'pci', 'bus_pci']
sources = files('rte_acc100_pmd.c', 'rte_acc200_pmd.c')
-headers = files('rte_acc100_cfg.h')
+headers = files('rte_acc100_cfg.h', 'rte_acc200_cfg.h')
diff --git a/drivers/baseband/acc/rte_acc200_cfg.h b/drivers/baseband/acc/rte_acc200_cfg.h
new file mode 100644
index 0000000000..8bd9b20e79
--- /dev/null
+++ b/drivers/baseband/acc/rte_acc200_cfg.h
@@ -0,0 +1,48 @@
+/* SPDX-License-Identifier: BSD-3-Clause
+ * Copyright(c) 2022 Intel Corporation
+ */
+
+#ifndef _RTE_ACC200_CFG_H_
+#define _RTE_ACC200_CFG_H_
+
+/**
+ * @file rte_acc200_cfg.h
+ *
+ * Functions for configuring ACC200 HW, exposed directly to applications.
+ * Configuration related to encoding/decoding is done through the
+ * librte_bbdev library.
+ *
+ * @warning
+ * @b EXPERIMENTAL: this API may change without prior notice
+ */
+
+#include <stdint.h>
+#include <stdbool.h>
+#include "rte_acc_common_cfg.h"
+
+#ifdef __cplusplus
+extern "C" {
+#endif
+
+/**
+ * Configure a ACC200 device
+ *
+ * @param dev_name
+ * The name of the device. This is the short form of PCI BDF, e.g. 00:01.0.
+ * It can also be retrieved for a bbdev device from the dev_name field in the
+ * rte_bbdev_info structure returned by rte_bbdev_info_get().
+ * @param conf
+ * Configuration to apply to ACC200 HW.
+ *
+ * @return
+ * Zero on success, negative value on failure.
+ */
+__rte_experimental
+int
+rte_acc200_configure(const char *dev_name, struct rte_acc_conf *conf);
+
+#ifdef __cplusplus
+}
+#endif
+
+#endif /* _RTE_ACC200_CFG_H_ */
diff --git a/drivers/baseband/acc/rte_acc200_pmd.c b/drivers/baseband/acc/rte_acc200_pmd.c
index cd3214f6c9..bbb3976d34 100644
--- a/drivers/baseband/acc/rte_acc200_pmd.c
+++ b/drivers/baseband/acc/rte_acc200_pmd.c
@@ -43,13 +43,36 @@ queue_offset(bool pf_device, uint8_t vf_id, uint8_t qgrp_id, uint16_t aq_id)
enum {UL_4G = 0, UL_5G, DL_4G, DL_5G, FFT, NUM_ACC};
+/* Return the accelerator enum for a Queue Group Index */
+static inline int
+accFromQgid(int qg_idx, const struct rte_acc_conf *acc_conf)
+{
+ int accQg[ACC200_NUM_QGRPS];
+ int NumQGroupsPerFn[NUM_ACC];
+ int acc, qgIdx, qgIndex = 0;
+ for (qgIdx = 0; qgIdx < ACC200_NUM_QGRPS; qgIdx++)
+ accQg[qgIdx] = 0;
+ NumQGroupsPerFn[UL_4G] = acc_conf->q_ul_4g.num_qgroups;
+ NumQGroupsPerFn[UL_5G] = acc_conf->q_ul_5g.num_qgroups;
+ NumQGroupsPerFn[DL_4G] = acc_conf->q_dl_4g.num_qgroups;
+ NumQGroupsPerFn[DL_5G] = acc_conf->q_dl_5g.num_qgroups;
+ NumQGroupsPerFn[FFT] = acc_conf->q_fft.num_qgroups;
+ for (acc = UL_4G; acc < NUM_ACC; acc++)
+ for (qgIdx = 0; qgIdx < NumQGroupsPerFn[acc]; qgIdx++)
+ accQg[qgIndex++] = acc;
+ acc = accQg[qg_idx];
+ return acc;
+}
+
/* Return the queue topology for a Queue Group Index */
static inline void
qtopFromAcc(struct rte_acc_queue_topology **qtop, int acc_enum,
struct rte_acc_conf *acc_conf)
{
struct rte_acc_queue_topology *p_qtop;
+
p_qtop = NULL;
+
switch (acc_enum) {
case UL_4G:
p_qtop = &(acc_conf->q_ul_4g);
@@ -72,9 +95,40 @@ qtopFromAcc(struct rte_acc_queue_topology **qtop, int acc_enum,
acc_enum);
break;
}
+
*qtop = p_qtop;
}
+/* Return the AQ depth for a Queue Group Index */
+static inline int
+aqDepth(int qg_idx, struct rte_acc_conf *acc_conf)
+{
+ struct rte_acc_queue_topology *q_top = NULL;
+
+ int acc_enum = accFromQgid(qg_idx, acc_conf);
+ qtopFromAcc(&q_top, acc_enum, acc_conf);
+
+ if (unlikely(q_top == NULL))
+ return 0;
+
+ return q_top->aq_depth_log2;
+}
+
+/* Return the AQ depth for a Queue Group Index */
+static inline int
+aqNum(int qg_idx, struct rte_acc_conf *acc_conf)
+{
+ struct rte_acc_queue_topology *q_top = NULL;
+
+ int acc_enum = accFromQgid(qg_idx, acc_conf);
+ qtopFromAcc(&q_top, acc_enum, acc_conf);
+
+ if (unlikely(q_top == NULL))
+ return 0;
+
+ return q_top->num_aqs_per_groups;
+}
+
static void
initQTop(struct rte_acc_conf *acc_conf)
{
@@ -3559,3 +3613,411 @@ RTE_PMD_REGISTER_PCI(ACC200PF_DRIVER_NAME, acc200_pci_pf_driver);
RTE_PMD_REGISTER_PCI_TABLE(ACC200PF_DRIVER_NAME, pci_id_acc200_pf_map);
RTE_PMD_REGISTER_PCI(ACC200VF_DRIVER_NAME, acc200_pci_vf_driver);
RTE_PMD_REGISTER_PCI_TABLE(ACC200VF_DRIVER_NAME, pci_id_acc200_vf_map);
+
+/* Initial configuration of a ACC200 device prior to running configure() */
+int
+rte_acc200_configure(const char *dev_name, struct rte_acc_conf *conf)
+{
+ rte_bbdev_log(INFO, "rte_acc200_configure");
+ uint32_t value, address, status;
+ int qg_idx, template_idx, vf_idx, acc, i, rlim, alen, timestamp, totalQgs, numEngines;
+ int numQgs, numQqsAcc;
+ struct rte_bbdev *bbdev = rte_bbdev_get_named_dev(dev_name);
+
+ /* Compile time checks */
+ RTE_BUILD_BUG_ON(sizeof(struct acc_dma_req_desc) != 256);
+ RTE_BUILD_BUG_ON(sizeof(union acc_dma_desc) != 256);
+ RTE_BUILD_BUG_ON(sizeof(struct acc_fcw_td) != 24);
+ RTE_BUILD_BUG_ON(sizeof(struct acc_fcw_te) != 32);
+
+ if (bbdev == NULL) {
+ rte_bbdev_log(ERR,
+ "Invalid dev_name (%s), or device is not yet initialised",
+ dev_name);
+ return -ENODEV;
+ }
+ struct acc_device *d = bbdev->data->dev_private;
+
+ /* Store configuration */
+ rte_memcpy(&d->acc_conf, conf, sizeof(d->acc_conf));
+
+ /* Check we are already out of PG */
+ status = acc_reg_read(d, HWPfHiSectionPowerGatingAck);
+ if (status > 0) {
+ if (status != ACC200_PG_MASK_0) {
+ rte_bbdev_log(ERR, "Unexpected status %x %x",
+ status, ACC200_PG_MASK_0);
+ return -ENODEV;
+ }
+ /* Clock gate sections that will be un-PG */
+ acc_reg_write(d, HWPfHiClkGateHystReg, ACC200_CLK_DIS);
+ /* Un-PG required sections */
+ acc_reg_write(d, HWPfHiSectionPowerGatingReq,
+ ACC200_PG_MASK_1);
+ status = acc_reg_read(d, HWPfHiSectionPowerGatingAck);
+ if (status != ACC200_PG_MASK_1) {
+ rte_bbdev_log(ERR, "Unexpected status %x %x",
+ status, ACC200_PG_MASK_1);
+ return -ENODEV;
+ }
+ acc_reg_write(d, HWPfHiSectionPowerGatingReq,
+ ACC200_PG_MASK_2);
+ status = acc_reg_read(d, HWPfHiSectionPowerGatingAck);
+ if (status != ACC200_PG_MASK_2) {
+ rte_bbdev_log(ERR, "Unexpected status %x %x",
+ status, ACC200_PG_MASK_2);
+ return -ENODEV;
+ }
+ acc_reg_write(d, HWPfHiSectionPowerGatingReq,
+ ACC200_PG_MASK_3);
+ status = acc_reg_read(d, HWPfHiSectionPowerGatingAck);
+ if (status != ACC200_PG_MASK_3) {
+ rte_bbdev_log(ERR, "Unexpected status %x %x",
+ status, ACC200_PG_MASK_3);
+ return -ENODEV;
+ }
+ /* Enable clocks for all sections */
+ acc_reg_write(d, HWPfHiClkGateHystReg, ACC200_CLK_EN);
+ }
+
+ /* Explicitly releasing AXI as this may be stopped after PF FLR/BME */
+ address = HWPfDmaAxiControl;
+ value = 1;
+ acc_reg_write(d, address, value);
+
+ /* Set the fabric mode */
+ address = HWPfFabricM2iBufferReg;
+ value = ACC200_FABRIC_MODE;
+ acc_reg_write(d, address, value);
+
+ /* Set default descriptor signature */
+ address = HWPfDmaDescriptorSignatuture;
+ value = 0;
+ acc_reg_write(d, address, value);
+
+ /* Enable the Error Detection in DMA */
+ value = ACC200_CFG_DMA_ERROR;
+ address = HWPfDmaErrorDetectionEn;
+ acc_reg_write(d, address, value);
+
+ /* AXI Cache configuration */
+ value = ACC200_CFG_AXI_CACHE;
+ address = HWPfDmaAxcacheReg;
+ acc_reg_write(d, address, value);
+
+ /* Default DMA Configuration (Qmgr Enabled) */
+ address = HWPfDmaConfig0Reg;
+ value = 0;
+ acc_reg_write(d, address, value);
+ address = HWPfDmaQmanen;
+ value = 0;
+ acc_reg_write(d, address, value);
+
+ /* Default RLIM/ALEN configuration */
+ rlim = 0;
+ alen = 1;
+ timestamp = 0;
+ address = HWPfDmaConfig1Reg;
+ value = (1 << 31) + (rlim << 8) + (timestamp << 6) + alen;
+ acc_reg_write(d, address, value);
+
+ /* Default FFT configuration */
+ address = HWPfFftConfig0;
+ value = ACC200_FFT_CFG_0;
+ acc_reg_write(d, address, value);
+
+ /* Configure DMA Qmanager addresses */
+ address = HWPfDmaQmgrAddrReg;
+ value = HWPfQmgrEgressQueuesTemplate;
+ acc_reg_write(d, address, value);
+
+ /* ===== Qmgr Configuration ===== */
+ /* Configuration of the AQueue Depth QMGR_GRP_0_DEPTH_LOG2 for UL */
+ totalQgs = conf->q_ul_4g.num_qgroups +
+ conf->q_ul_5g.num_qgroups +
+ conf->q_dl_4g.num_qgroups +
+ conf->q_dl_5g.num_qgroups +
+ conf->q_fft.num_qgroups;
+ for (qg_idx = 0; qg_idx < ACC200_NUM_QGRPS; qg_idx++) {
+ address = HWPfQmgrDepthLog2Grp +
+ ACC_BYTES_IN_WORD * qg_idx;
+ value = aqDepth(qg_idx, conf);
+ acc_reg_write(d, address, value);
+ address = HWPfQmgrTholdGrp +
+ ACC_BYTES_IN_WORD * qg_idx;
+ value = (1 << 16) + (1 << (aqDepth(qg_idx, conf) - 1));
+ acc_reg_write(d, address, value);
+ }
+
+ /* Template Priority in incremental order */
+ for (template_idx = 0; template_idx < ACC_NUM_TMPL;
+ template_idx++) {
+ address = HWPfQmgrGrpTmplateReg0Indx + ACC_BYTES_IN_WORD * template_idx;
+ value = ACC_TMPL_PRI_0;
+ acc_reg_write(d, address, value);
+ address = HWPfQmgrGrpTmplateReg1Indx + ACC_BYTES_IN_WORD * template_idx;
+ value = ACC_TMPL_PRI_1;
+ acc_reg_write(d, address, value);
+ address = HWPfQmgrGrpTmplateReg2indx + ACC_BYTES_IN_WORD * template_idx;
+ value = ACC_TMPL_PRI_2;
+ acc_reg_write(d, address, value);
+ address = HWPfQmgrGrpTmplateReg3Indx + ACC_BYTES_IN_WORD * template_idx;
+ value = ACC_TMPL_PRI_3;
+ acc_reg_write(d, address, value);
+ }
+
+ address = HWPfQmgrGrpPriority;
+ value = ACC200_CFG_QMGR_HI_P;
+ acc_reg_write(d, address, value);
+
+ /* Template Configuration */
+ for (template_idx = 0; template_idx < ACC_NUM_TMPL;
+ template_idx++) {
+ value = 0;
+ address = HWPfQmgrGrpTmplateReg4Indx
+ + ACC_BYTES_IN_WORD * template_idx;
+ acc_reg_write(d, address, value);
+ }
+ /* 4GUL */
+ numQgs = conf->q_ul_4g.num_qgroups;
+ numQqsAcc = 0;
+ value = 0;
+ for (qg_idx = numQqsAcc; qg_idx < (numQgs + numQqsAcc); qg_idx++)
+ value |= (1 << qg_idx);
+ for (template_idx = ACC200_SIG_UL_4G;
+ template_idx <= ACC200_SIG_UL_4G_LAST;
+ template_idx++) {
+ address = HWPfQmgrGrpTmplateReg4Indx
+ + ACC_BYTES_IN_WORD * template_idx;
+ acc_reg_write(d, address, value);
+ }
+ /* 5GUL */
+ numQqsAcc += numQgs;
+ numQgs = conf->q_ul_5g.num_qgroups;
+ value = 0;
+ numEngines = 0;
+ for (qg_idx = numQqsAcc; qg_idx < (numQgs + numQqsAcc); qg_idx++)
+ value |= (1 << qg_idx);
+ for (template_idx = ACC200_SIG_UL_5G;
+ template_idx <= ACC200_SIG_UL_5G_LAST;
+ template_idx++) {
+ /* Check engine power-on status */
+ address = HwPfFecUl5gIbDebugReg + ACC_ENGINE_OFFSET * template_idx;
+ status = (acc_reg_read(d, address) >> 4) & 0x7;
+ address = HWPfQmgrGrpTmplateReg4Indx
+ + ACC_BYTES_IN_WORD * template_idx;
+ if (status == 1) {
+ acc_reg_write(d, address, value);
+ numEngines++;
+ } else
+ acc_reg_write(d, address, 0);
+ }
+ printf("Number of 5GUL engines %d\n", numEngines);
+ /* 4GDL */
+ numQqsAcc += numQgs;
+ numQgs = conf->q_dl_4g.num_qgroups;
+ value = 0;
+ for (qg_idx = numQqsAcc; qg_idx < (numQgs + numQqsAcc); qg_idx++)
+ value |= (1 << qg_idx);
+ for (template_idx = ACC200_SIG_DL_4G;
+ template_idx <= ACC200_SIG_DL_4G_LAST;
+ template_idx++) {
+ address = HWPfQmgrGrpTmplateReg4Indx
+ + ACC_BYTES_IN_WORD * template_idx;
+ acc_reg_write(d, address, value);
+ }
+ /* 5GDL */
+ numQqsAcc += numQgs;
+ numQgs = conf->q_dl_5g.num_qgroups;
+ value = 0;
+ for (qg_idx = numQqsAcc; qg_idx < (numQgs + numQqsAcc); qg_idx++)
+ value |= (1 << qg_idx);
+ for (template_idx = ACC200_SIG_DL_5G;
+ template_idx <= ACC200_SIG_DL_5G_LAST;
+ template_idx++) {
+ address = HWPfQmgrGrpTmplateReg4Indx
+ + ACC_BYTES_IN_WORD * template_idx;
+ acc_reg_write(d, address, value);
+ }
+ /* FFT */
+ numQqsAcc += numQgs;
+ numQgs = conf->q_fft.num_qgroups;
+ value = 0;
+ for (qg_idx = numQqsAcc; qg_idx < (numQgs + numQqsAcc); qg_idx++)
+ value |= (1 << qg_idx);
+ for (template_idx = ACC200_SIG_FFT;
+ template_idx <= ACC200_SIG_FFT_LAST;
+ template_idx++) {
+ address = HWPfQmgrGrpTmplateReg4Indx
+ + ACC_BYTES_IN_WORD * template_idx;
+ acc_reg_write(d, address, value);
+ }
+
+ /* Queue Group Function mapping */
+ int qman_func_id[8] = {0, 2, 1, 3, 4, 0, 0, 0};
+ value = 0;
+ for (qg_idx = 0; qg_idx < ACC_NUM_QGRPS_PER_WORD; qg_idx++) {
+ acc = accFromQgid(qg_idx, conf);
+ value |= qman_func_id[acc] << (qg_idx * 4);
+ }
+ acc_reg_write(d, HWPfQmgrGrpFunction0, value);
+ value = 0;
+ for (qg_idx = 0; qg_idx < ACC_NUM_QGRPS_PER_WORD; qg_idx++) {
+ acc = accFromQgid(qg_idx + ACC_NUM_QGRPS_PER_WORD, conf);
+ value |= qman_func_id[acc] << (qg_idx * 4);
+ }
+ acc_reg_write(d, HWPfQmgrGrpFunction1, value);
+
+ /* Configuration of the Arbitration QGroup depth to 1 */
+ for (qg_idx = 0; qg_idx < ACC200_NUM_QGRPS; qg_idx++) {
+ address = HWPfQmgrArbQDepthGrp +
+ ACC_BYTES_IN_WORD * qg_idx;
+ value = 0;
+ acc_reg_write(d, address, value);
+ }
+
+ /* This pointer to ARAM (256kB) is shifted by 2 (4B per register) */
+ uint32_t aram_address = 0;
+ for (qg_idx = 0; qg_idx < totalQgs; qg_idx++) {
+ for (vf_idx = 0; vf_idx < conf->num_vf_bundles; vf_idx++) {
+ address = HWPfQmgrVfBaseAddr + vf_idx
+ * ACC_BYTES_IN_WORD + qg_idx
+ * ACC_BYTES_IN_WORD * 64;
+ value = aram_address;
+ acc_reg_write(d, address, value);
+ /* Offset ARAM Address for next memory bank
+ * - increment of 4B
+ */
+ aram_address += aqNum(qg_idx, conf) *
+ (1 << aqDepth(qg_idx, conf));
+ }
+ }
+
+ if (aram_address > ACC200_WORDS_IN_ARAM_SIZE) {
+ rte_bbdev_log(ERR, "ARAM Configuration not fitting %d %d\n",
+ aram_address, ACC200_WORDS_IN_ARAM_SIZE);
+ return -EINVAL;
+ }
+
+ /* Performance tuning */
+ acc_reg_write(d, HWPfFabricI2Mdma_weight, 0x0FFF);
+ acc_reg_write(d, HWPfDma4gdlIbThld, 0x1f10);
+
+ /* ==== HI Configuration ==== */
+
+ /* No Info Ring/MSI by default */
+ address = HWPfHiInfoRingIntWrEnRegPf;
+ value = 0;
+ acc_reg_write(d, address, value);
+ address = HWPfHiCfgMsiIntWrEnRegPf;
+ value = 0xFFFFFFFF;
+ acc_reg_write(d, address, value);
+ /* Prevent Block on Transmit Error */
+ address = HWPfHiBlockTransmitOnErrorEn;
+ value = 0;
+ acc_reg_write(d, address, value);
+ /* Prevents to drop MSI */
+ address = HWPfHiMsiDropEnableReg;
+ value = 0;
+ acc_reg_write(d, address, value);
+ /* Set the PF Mode register */
+ address = HWPfHiPfMode;
+ value = (conf->pf_mode_en) ? ACC_PF_VAL : 0;
+ acc_reg_write(d, address, value);
+
+ /* QoS overflow init */
+ value = 1;
+ address = HWPfQosmonAEvalOverflow0;
+ acc_reg_write(d, address, value);
+ address = HWPfQosmonBEvalOverflow0;
+ acc_reg_write(d, address, value);
+
+ /* Configure the FFT RAM LUT */
+ uint32_t fft_lut[ACC200_FFT_RAM_SIZE] = {
+ 0x1FFFF, 0x1FFFF, 0x1FFFE, 0x1FFFA, 0x1FFF6, 0x1FFF1, 0x1FFEA, 0x1FFE2,
+ 0x1FFD9, 0x1FFCE, 0x1FFC2, 0x1FFB5, 0x1FFA7, 0x1FF98, 0x1FF87, 0x1FF75,
+ 0x1FF62, 0x1FF4E, 0x1FF38, 0x1FF21, 0x1FF09, 0x1FEF0, 0x1FED6, 0x1FEBA,
+ 0x1FE9D, 0x1FE7F, 0x1FE5F, 0x1FE3F, 0x1FE1D, 0x1FDFA, 0x1FDD5, 0x1FDB0,
+ 0x1FD89, 0x1FD61, 0x1FD38, 0x1FD0D, 0x1FCE1, 0x1FCB4, 0x1FC86, 0x1FC57,
+ 0x1FC26, 0x1FBF4, 0x1FBC1, 0x1FB8D, 0x1FB58, 0x1FB21, 0x1FAE9, 0x1FAB0,
+ 0x1FA75, 0x1FA3A, 0x1F9FD, 0x1F9BF, 0x1F980, 0x1F93F, 0x1F8FD, 0x1F8BA,
+ 0x1F876, 0x1F831, 0x1F7EA, 0x1F7A3, 0x1F75A, 0x1F70F, 0x1F6C4, 0x1F677,
+ 0x1F629, 0x1F5DA, 0x1F58A, 0x1F539, 0x1F4E6, 0x1F492, 0x1F43D, 0x1F3E7,
+ 0x1F38F, 0x1F337, 0x1F2DD, 0x1F281, 0x1F225, 0x1F1C8, 0x1F169, 0x1F109,
+ 0x1F0A8, 0x1F046, 0x1EFE2, 0x1EF7D, 0x1EF18, 0x1EEB0, 0x1EE48, 0x1EDDF,
+ 0x1ED74, 0x1ED08, 0x1EC9B, 0x1EC2D, 0x1EBBE, 0x1EB4D, 0x1EADB, 0x1EA68,
+ 0x1E9F4, 0x1E97F, 0x1E908, 0x1E891, 0x1E818, 0x1E79E, 0x1E722, 0x1E6A6,
+ 0x1E629, 0x1E5AA, 0x1E52A, 0x1E4A9, 0x1E427, 0x1E3A3, 0x1E31F, 0x1E299,
+ 0x1E212, 0x1E18A, 0x1E101, 0x1E076, 0x1DFEB, 0x1DF5E, 0x1dED0, 0x1DE41,
+ 0x1DDB1, 0x1DD20, 0x1DC8D, 0x1DBFA, 0x1DB65, 0x1DACF, 0x1DA38, 0x1D9A0,
+ 0x1D907, 0x1D86C, 0x1D7D1, 0x1D734, 0x1D696, 0x1D5F7, 0x1D557, 0x1D4B6,
+ 0x1D413, 0x1D370, 0x1D2CB, 0x1D225, 0x1D17E, 0x1D0D6, 0x1D02D, 0x1CF83,
+ 0x1CED8, 0x1CE2B, 0x1CD7E, 0x1CCCF, 0x1CC1F, 0x1CB6E, 0x1CABC, 0x1CA09,
+ 0x1C955, 0x1C89F, 0x1C7E9, 0x1C731, 0x1C679, 0x1C5BF, 0x1C504, 0x1C448,
+ 0x1C38B, 0x1C2CD, 0x1C20E, 0x1C14E, 0x1C08C, 0x1BFCA, 0x1BF06, 0x1BE42,
+ 0x1BD7C, 0x1BCB5, 0x1BBED, 0x1BB25, 0x1BA5B, 0x1B990, 0x1B8C4, 0x1B7F6,
+ 0x1B728, 0x1B659, 0x1B589, 0x1B4B7, 0x1B3E5, 0x1B311, 0x1B23D, 0x1B167,
+ 0x1B091, 0x1AFB9, 0x1AEE0, 0x1AE07, 0x1AD2C, 0x1AC50, 0x1AB73, 0x1AA95,
+ 0x1A9B6, 0x1A8D6, 0x1A7F6, 0x1A714, 0x1A631, 0x1A54D, 0x1A468, 0x1A382,
+ 0x1A29A, 0x1A1B2, 0x1A0C9, 0x19FDF, 0x19EF4, 0x19E08, 0x19D1B, 0x19C2D,
+ 0x19B3E, 0x19A4E, 0x1995D, 0x1986B, 0x19778, 0x19684, 0x1958F, 0x19499,
+ 0x193A2, 0x192AA, 0x191B1, 0x190B8, 0x18FBD, 0x18EC1, 0x18DC4, 0x18CC7,
+ 0x18BC8, 0x18AC8, 0x189C8, 0x188C6, 0x187C4, 0x186C1, 0x185BC, 0x184B7,
+ 0x183B1, 0x182AA, 0x181A2, 0x18099, 0x17F8F, 0x17E84, 0x17D78, 0x17C6C,
+ 0x17B5E, 0x17A4F, 0x17940, 0x17830, 0x1771E, 0x1760C, 0x174F9, 0x173E5,
+ 0x172D1, 0x171BB, 0x170A4, 0x16F8D, 0x16E74, 0x16D5B, 0x16C41, 0x16B26,
+ 0x16A0A, 0x168ED, 0x167CF, 0x166B1, 0x16592, 0x16471, 0x16350, 0x1622E,
+ 0x1610B, 0x15FE8, 0x15EC3, 0x15D9E, 0x15C78, 0x15B51, 0x15A29, 0x15900,
+ 0x157D7, 0x156AC, 0x15581, 0x15455, 0x15328, 0x151FB, 0x150CC, 0x14F9D,
+ 0x14E6D, 0x14D3C, 0x14C0A, 0x14AD8, 0x149A4, 0x14870, 0x1473B, 0x14606,
+ 0x144CF, 0x14398, 0x14260, 0x14127, 0x13FEE, 0x13EB3, 0x13D78, 0x13C3C,
+ 0x13B00, 0x139C2, 0x13884, 0x13745, 0x13606, 0x134C5, 0x13384, 0x13242,
+ 0x130FF, 0x12FBC, 0x12E78, 0x12D33, 0x12BEE, 0x12AA7, 0x12960, 0x12819,
+ 0x126D0, 0x12587, 0x1243D, 0x122F3, 0x121A8, 0x1205C, 0x11F0F, 0x11DC2,
+ 0x11C74, 0x11B25, 0x119D6, 0x11886, 0x11735, 0x115E3, 0x11491, 0x1133F,
+ 0x111EB, 0x11097, 0x10F42, 0x10dED, 0x10C97, 0x10B40, 0x109E9, 0x10891,
+ 0x10738, 0x105DF, 0x10485, 0x1032B, 0x101D0, 0x10074, 0x0FF18, 0x0FDBB,
+ 0x0FC5D, 0x0FAFF, 0x0F9A0, 0x0F841, 0x0F6E1, 0x0F580, 0x0F41F, 0x0F2BD,
+ 0x0F15B, 0x0EFF8, 0x0EE94, 0x0ED30, 0x0EBCC, 0x0EA67, 0x0E901, 0x0E79A,
+ 0x0E633, 0x0E4CC, 0x0E364, 0x0E1FB, 0x0E092, 0x0DF29, 0x0DDBE, 0x0DC54,
+ 0x0DAE9, 0x0D97D, 0x0D810, 0x0D6A4, 0x0D536, 0x0D3C8, 0x0D25A, 0x0D0EB,
+ 0x0CF7C, 0x0CE0C, 0x0CC9C, 0x0CB2B, 0x0C9B9, 0x0C847, 0x0C6D5, 0x0C562,
+ 0x0C3EF, 0x0C27B, 0x0C107, 0x0BF92, 0x0BE1D, 0x0BCA8, 0x0BB32, 0x0B9BB,
+ 0x0B844, 0x0B6CD, 0x0B555, 0x0B3DD, 0x0B264, 0x0B0EB, 0x0AF71, 0x0ADF7,
+ 0x0AC7D, 0x0AB02, 0x0A987, 0x0A80B, 0x0A68F, 0x0A513, 0x0A396, 0x0A219,
+ 0x0A09B, 0x09F1D, 0x09D9E, 0x09C20, 0x09AA1, 0x09921, 0x097A1, 0x09621,
+ 0x094A0, 0x0931F, 0x0919E, 0x0901C, 0x08E9A, 0x08D18, 0x08B95, 0x08A12,
+ 0x0888F, 0x0870B, 0x08587, 0x08402, 0x0827E, 0x080F9, 0x07F73, 0x07DEE,
+ 0x07C68, 0x07AE2, 0x0795B, 0x077D4, 0x0764D, 0x074C6, 0x0733E, 0x071B6,
+ 0x0702E, 0x06EA6, 0x06D1D, 0x06B94, 0x06A0B, 0x06881, 0x066F7, 0x0656D,
+ 0x063E3, 0x06258, 0x060CE, 0x05F43, 0x05DB7, 0x05C2C, 0x05AA0, 0x05914,
+ 0x05788, 0x055FC, 0x0546F, 0x052E3, 0x05156, 0x04FC9, 0x04E3B, 0x04CAE,
+ 0x04B20, 0x04992, 0x04804, 0x04676, 0x044E8, 0x04359, 0x041CB, 0x0403C,
+ 0x03EAD, 0x03D1D, 0x03B8E, 0x039FF, 0x0386F, 0x036DF, 0x0354F, 0x033BF,
+ 0x0322F, 0x0309F, 0x02F0F, 0x02D7E, 0x02BEE, 0x02A5D, 0x028CC, 0x0273B,
+ 0x025AA, 0x02419, 0x02288, 0x020F7, 0x01F65, 0x01DD4, 0x01C43, 0x01AB1,
+ 0x0191F, 0x0178E, 0x015FC, 0x0146A, 0x012D8, 0x01147, 0x00FB5, 0x00E23,
+ 0x00C91, 0x00AFF, 0x0096D, 0x007DB, 0x00648, 0x004B6, 0x00324, 0x00192};
+
+ acc_reg_write(d, HWPfFftRamPageAccess, ACC200_FFT_RAM_EN + 64);
+ for (i = 0; i < ACC200_FFT_RAM_SIZE; i++)
+ acc_reg_write(d, HWPfFftRamOff + i * 4, fft_lut[i]);
+ acc_reg_write(d, HWPfFftRamPageAccess, ACC200_FFT_RAM_DIS);
+
+ /* Enabling AQueues through the Queue hierarchy*/
+ for (vf_idx = 0; vf_idx < ACC200_NUM_VFS; vf_idx++) {
+ for (qg_idx = 0; qg_idx < ACC200_NUM_QGRPS; qg_idx++) {
+ value = 0;
+ if (vf_idx < conf->num_vf_bundles &&
+ qg_idx < totalQgs)
+ value = (1 << aqNum(qg_idx, conf)) - 1;
+ address = HWPfQmgrAqEnableVf
+ + vf_idx * ACC_BYTES_IN_WORD;
+ value += (qg_idx << 16);
+ acc_reg_write(d, address, value);
+ }
+ }
+
+ rte_bbdev_log_debug("PF Tip configuration complete for %s", dev_name);
+ return 0;
+}
diff --git a/drivers/baseband/acc/version.map b/drivers/baseband/acc/version.map
index b4ff13e38f..27fbbe3de5 100644
--- a/drivers/baseband/acc/version.map
+++ b/drivers/baseband/acc/version.map
@@ -6,4 +6,5 @@ EXPERIMENTAL {
global:
rte_acc10x_configure;
+ rte_acc200_configure;
};
--
2.37.1
^ permalink raw reply [flat|nested] 28+ messages in thread* [PATCH v6 14/14] baseband/acc: simplify meson dependency
2022-09-24 0:50 From: Nicolas Chautru <nicolas.chautru@intel.com> Nicolas Chautru
` (12 preceding siblings ...)
2022-09-24 0:50 ` [PATCH v6 13/14] baseband/acc: add PF configure companion function Nicolas Chautru
@ 2022-09-24 0:50 ` Nicolas Chautru
13 siblings, 0 replies; 28+ messages in thread
From: Nicolas Chautru @ 2022-09-24 0:50 UTC (permalink / raw)
To: dev, thomas
Cc: maxime.coquelin, trix, mdr, bruce.richardson, hemant.agrawal,
david.marchand, stephen, hernan.vargas, Nic Chautru
From: Nic Chautru <nicolas.chautru@intel.com>
Removing some of libraries from the external dependency captured in
meson build file.
Signed-off-by: Nic Chautru <nicolas.chautru@intel.com>
---
drivers/baseband/acc/meson.build | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/drivers/baseband/acc/meson.build b/drivers/baseband/acc/meson.build
index 7ae162aab8..bece3a6e48 100644
--- a/drivers/baseband/acc/meson.build
+++ b/drivers/baseband/acc/meson.build
@@ -1,7 +1,7 @@
# SPDX-License-Identifier: BSD-3-Clause
# Copyright(c) 2020 Intel Corporation
-deps += ['bbdev', 'bus_vdev', 'ring', 'pci', 'bus_pci']
+deps += ['bbdev', 'bus_pci']
sources = files('rte_acc100_pmd.c', 'rte_acc200_pmd.c')
--
2.37.1
^ permalink raw reply [flat|nested] 28+ messages in thread