| Message ID | 1476796207-94336-4-git-send-email-heyi.guo@linaro.org |
|---|---|
| State | Superseded |
| Headers | show |
On Tue, Oct 18, 2016 at 09:09:47PM +0800, Heyi Guo wrote: > Modify PCIe transaction memory attribute to improve performance, like > SMMU bypass, cache snoopy, etc. > > Contributed-under: TianoCore Contribution Agreement 1.0 > Signed-off-by: hensonwang <wanghuiqiang@huawei.com> > Signed-off-by: Heyi Guo <heyi.guo@linaro.org> > --- > .../Hi1610/Drivers/PcieInit1610/PcieInitDxe.inf | 3 ++ > .../Hi1610/Drivers/PcieInit1610/PcieInitLib.c | 47 ++++++++++++++++++++++ > Chips/Hisilicon/HisiPkg.dec | 1 + > Chips/Hisilicon/Include/Regs/HisiPcieV1RegOffset.h | 1 + > Platforms/Hisilicon/D03/D03.dsc | 1 + > 5 files changed, 53 insertions(+) > mode change 100755 => 100644 Chips/Hisilicon/Hi1610/Drivers/PcieInit1610/PcieInitLib.c > > diff --git a/Chips/Hisilicon/Hi1610/Drivers/PcieInit1610/PcieInitDxe.inf b/Chips/Hisilicon/Hi1610/Drivers/PcieInit1610/PcieInitDxe.inf > index 63d8bb1..8659e29 100644 > --- a/Chips/Hisilicon/Hi1610/Drivers/PcieInit1610/PcieInitDxe.inf > +++ b/Chips/Hisilicon/Hi1610/Drivers/PcieInit1610/PcieInitDxe.inf > @@ -53,6 +53,9 @@ > gHisiTokenSpaceGuid.Pcdsoctype > gHisiTokenSpaceGuid.PcdPcieMsiTargetAddress > > +[FeaturePcd] > + gHisiTokenSpaceGuid.PcdIsPciPerfTuningEnable > + > [depex] > TRUE > > diff --git a/Chips/Hisilicon/Hi1610/Drivers/PcieInit1610/PcieInitLib.c b/Chips/Hisilicon/Hi1610/Drivers/PcieInit1610/PcieInitLib.c > old mode 100755 > new mode 100644 > index 5c14907..3a2bee0 > --- a/Chips/Hisilicon/Hi1610/Drivers/PcieInit1610/PcieInitLib.c > +++ b/Chips/Hisilicon/Hi1610/Drivers/PcieInit1610/PcieInitLib.c > @@ -21,6 +21,8 @@ > #include <Library/IoLib.h> > #include <Library/TimerLib.h> > > +#define PCIE_SYS_REG_OFFSET 0x1000 > + > static PCIE_INIT_CFG mPcieIntCfg; > UINT64 pcie_subctrl_base[2] = {0xb0000000, BASE_4TB + 0xb0000000}; > UINT64 pcie_subctrl_base_1610[2] = {0xa0000000, 0xb0000000}; > @@ -185,6 +187,49 @@ EFI_STATUS PcieEnableItssm(UINT32 soctype, UINT32 HostBridgeNum, UINT32 Port) > > } > > +STATIC EFI_STATUS PciPerfTuning(UINT32 soctype, UINT32 HostBridgeNum, UINT32 Port) > +{ > + UINT32 Value; > + UINTN RegSegmentOffset; > + > + if(Port >= PCIE_MAX_PORT_NUM) > + { This should be if (Port >= PCIE_MAX_PORT_NUM) { (Space before parenthesis, brace on same line.) > + return EFI_INVALID_PARAMETER; > + } > + > + RegSegmentOffset = PCIE_APB_SLAVE_BASE_1610[HostBridgeNum][Port] + PCIE_SYS_REG_OFFSET; > + > + //Enable SMMU bypass for translation > + RegRead(RegSegmentOffset + PCIE_SYS_CTRL13_REG, Value); > + //BIT13: controller master read SMMU bypass > + //BIT12: controller master write SMMU bypass > + //BIT10: SMMU bypass enable These comments really help - thanks! > + Value |= (BIT13 | BIT12 | BIT10); > + RegWrite(RegSegmentOffset + PCIE_SYS_CTRL13_REG, Value); > + > + //Switch strongly order (SO) to relaxed order (RO) for write transaction > + RegRead(RegSegmentOffset + PCIE_CTRL_6_REG, Value); > + //BIT13 | BIT12: Enable write merge and SMMU streaming ordered write acknowledge > + //BIT17 | BIT19 | BIT21 | BIT23 | BIT25 | BIT27 | BIT29: Enable RO for all types of write transaction > + Value |= (BIT13 | BIT12 | BIT17 | BIT19 | BIT21 | BIT23 | BIT25 | BIT27 | BIT29); I think it would be worthwhile to split these up as: //BIT13 | BIT12: Enable write merge and SMMU streaming ordered write acknowledge Value |= (BIT13 | BIT12); //BIT17 | BIT19 | BIT21 | BIT23 | BIT25 | BIT27 | BIT29: Enable RO for all types of write transaction Value |= (BIT17 | BIT19 | BIT21 | BIT23 | BIT25 | BIT27 | BIT29); However, for the second part, can the bits be sorted in descending order please? > + RegWrite(RegSegmentOffset + PCIE_CTRL_6_REG, Value); > + > + //Force streamID for controller read operation > + RegRead(RegSegmentOffset + PCIE_SYS_CTRL54_REG, Value); > + //Force using streamID in PCIE_SYS_CTRL54_REG > + Value &= ~(BIT30); > + //Set streamID to 0, bit[0:15] is for request ID and should be kept > + Value &= ~(0xff<<16); Value &= ~(0xff << 16); (spaces around <<) > + RegWrite(RegSegmentOffset + PCIE_SYS_CTRL54_REG, Value); > + > + //Enable read and write snoopy > + RegRead(RegSegmentOffset + PCIE_SYS_CTRL19_REG, Value); > + Value |= (BIT28 | BIT30); Bits in descending order please. > + RegWrite(RegSegmentOffset + PCIE_SYS_CTRL19_REG, Value); > + > + return EFI_SUCCESS; > +} > + > EFI_STATUS PcieDisableItssm(UINT32 soctype, UINT32 HostBridgeNum, UINT32 Port) > { > PCIE_CTRL_7_U pcie_ctrl7; > @@ -940,6 +985,8 @@ PciePortInit ( > > /* assert LTSSM enable */ > (VOID)PcieEnableItssm(soctype, HostBridgeNum, PortIndex); > + if (FeaturePcdGet (PcdIsPciPerfTuningEnable)) > + (VOID)PciPerfTuning(soctype, HostBridgeNum, PortIndex); Here is a correct use of casting unused return value to (VOID). However, I am unsure why adding a function with a return value and then explicitly discarding it for the only caller. I would normally expect one of: - Check return value and print warning message. - VOID as return type of function, and ASSERT/return if invalid input. > > PcieConfigContextHi1610(soctype, HostBridgeNum, PortIndex); > /* > diff --git a/Chips/Hisilicon/HisiPkg.dec b/Chips/Hisilicon/HisiPkg.dec > index 8e46e0d..2ce60d9 100644 > --- a/Chips/Hisilicon/HisiPkg.dec > +++ b/Chips/Hisilicon/HisiPkg.dec > @@ -161,6 +161,7 @@ > gHisiTokenSpaceGuid.PcdSerDesFlowCtrlFlag|0|UINT32|0x40000056 > > [PcdsFeatureFlag] > + gHisiTokenSpaceGuid.PcdIsPciPerfTuningEnable|FALSE|BOOLEAN|0x00000066 > > > > diff --git a/Chips/Hisilicon/Include/Regs/HisiPcieV1RegOffset.h b/Chips/Hisilicon/Include/Regs/HisiPcieV1RegOffset.h > index bdd80f8..539d567 100644 > --- a/Chips/Hisilicon/Include/Regs/HisiPcieV1RegOffset.h > +++ b/Chips/Hisilicon/Include/Regs/HisiPcieV1RegOffset.h > @@ -8981,6 +8981,7 @@ typedef union tagIepMsiCtrlIntStatus > #define PCIE_SYS_CTRL24_REG (PCI_SYS_BASE + 0x1b4) > #define PCIE_SYS_CTRL28_REG (PCI_SYS_BASE + 0x1c4) > #define PCIE_SYS_CTRL29_REG (PCI_SYS_BASE + 0x1c8) > +#define PCIE_SYS_CTRL54_REG (PCI_SYS_BASE + 0x274) > #define PCIE_SYS_STATE5_REG (PCI_SYS_BASE + 0x30) > #define PCIE_SYS_STATE6_REG (PCI_SYS_BASE + 0x34) > #define PCIE_SYS_STATE7_REG (PCI_SYS_BASE + 0x38) > diff --git a/Platforms/Hisilicon/D03/D03.dsc b/Platforms/Hisilicon/D03/D03.dsc > index 6d82627..942b2b8 100644 > --- a/Platforms/Hisilicon/D03/D03.dsc > +++ b/Platforms/Hisilicon/D03/D03.dsc > @@ -111,6 +111,7 @@ > ## If TRUE, Graphics Output Protocol will be installed on virtual handle created by ConsplitterDxe. > # It could be set FALSE to save size. > gEfiMdeModulePkgTokenSpaceGuid.PcdConOutGopSupport|TRUE > + gHisiTokenSpaceGuid.PcdIsPciPerfTuningEnable|TRUE > > [PcdsFixedAtBuild.common] > gArmPlatformTokenSpaceGuid.PcdFirmwareVendor|"ARM Versatile Express" > -- > 1.9.1 >
diff --git a/Chips/Hisilicon/Hi1610/Drivers/PcieInit1610/PcieInitDxe.inf b/Chips/Hisilicon/Hi1610/Drivers/PcieInit1610/PcieInitDxe.inf index 63d8bb1..8659e29 100644 --- a/Chips/Hisilicon/Hi1610/Drivers/PcieInit1610/PcieInitDxe.inf +++ b/Chips/Hisilicon/Hi1610/Drivers/PcieInit1610/PcieInitDxe.inf @@ -53,6 +53,9 @@ gHisiTokenSpaceGuid.Pcdsoctype gHisiTokenSpaceGuid.PcdPcieMsiTargetAddress +[FeaturePcd] + gHisiTokenSpaceGuid.PcdIsPciPerfTuningEnable + [depex] TRUE diff --git a/Chips/Hisilicon/Hi1610/Drivers/PcieInit1610/PcieInitLib.c b/Chips/Hisilicon/Hi1610/Drivers/PcieInit1610/PcieInitLib.c old mode 100755 new mode 100644 index 5c14907..3a2bee0 --- a/Chips/Hisilicon/Hi1610/Drivers/PcieInit1610/PcieInitLib.c +++ b/Chips/Hisilicon/Hi1610/Drivers/PcieInit1610/PcieInitLib.c @@ -21,6 +21,8 @@ #include <Library/IoLib.h> #include <Library/TimerLib.h> +#define PCIE_SYS_REG_OFFSET 0x1000 + static PCIE_INIT_CFG mPcieIntCfg; UINT64 pcie_subctrl_base[2] = {0xb0000000, BASE_4TB + 0xb0000000}; UINT64 pcie_subctrl_base_1610[2] = {0xa0000000, 0xb0000000}; @@ -185,6 +187,49 @@ EFI_STATUS PcieEnableItssm(UINT32 soctype, UINT32 HostBridgeNum, UINT32 Port) } +STATIC EFI_STATUS PciPerfTuning(UINT32 soctype, UINT32 HostBridgeNum, UINT32 Port) +{ + UINT32 Value; + UINTN RegSegmentOffset; + + if(Port >= PCIE_MAX_PORT_NUM) + { + return EFI_INVALID_PARAMETER; + } + + RegSegmentOffset = PCIE_APB_SLAVE_BASE_1610[HostBridgeNum][Port] + PCIE_SYS_REG_OFFSET; + + //Enable SMMU bypass for translation + RegRead(RegSegmentOffset + PCIE_SYS_CTRL13_REG, Value); + //BIT13: controller master read SMMU bypass + //BIT12: controller master write SMMU bypass + //BIT10: SMMU bypass enable + Value |= (BIT13 | BIT12 | BIT10); + RegWrite(RegSegmentOffset + PCIE_SYS_CTRL13_REG, Value); + + //Switch strongly order (SO) to relaxed order (RO) for write transaction + RegRead(RegSegmentOffset + PCIE_CTRL_6_REG, Value); + //BIT13 | BIT12: Enable write merge and SMMU streaming ordered write acknowledge + //BIT17 | BIT19 | BIT21 | BIT23 | BIT25 | BIT27 | BIT29: Enable RO for all types of write transaction + Value |= (BIT13 | BIT12 | BIT17 | BIT19 | BIT21 | BIT23 | BIT25 | BIT27 | BIT29); + RegWrite(RegSegmentOffset + PCIE_CTRL_6_REG, Value); + + //Force streamID for controller read operation + RegRead(RegSegmentOffset + PCIE_SYS_CTRL54_REG, Value); + //Force using streamID in PCIE_SYS_CTRL54_REG + Value &= ~(BIT30); + //Set streamID to 0, bit[0:15] is for request ID and should be kept + Value &= ~(0xff<<16); + RegWrite(RegSegmentOffset + PCIE_SYS_CTRL54_REG, Value); + + //Enable read and write snoopy + RegRead(RegSegmentOffset + PCIE_SYS_CTRL19_REG, Value); + Value |= (BIT28 | BIT30); + RegWrite(RegSegmentOffset + PCIE_SYS_CTRL19_REG, Value); + + return EFI_SUCCESS; +} + EFI_STATUS PcieDisableItssm(UINT32 soctype, UINT32 HostBridgeNum, UINT32 Port) { PCIE_CTRL_7_U pcie_ctrl7; @@ -940,6 +985,8 @@ PciePortInit ( /* assert LTSSM enable */ (VOID)PcieEnableItssm(soctype, HostBridgeNum, PortIndex); + if (FeaturePcdGet (PcdIsPciPerfTuningEnable)) + (VOID)PciPerfTuning(soctype, HostBridgeNum, PortIndex); PcieConfigContextHi1610(soctype, HostBridgeNum, PortIndex); /* diff --git a/Chips/Hisilicon/HisiPkg.dec b/Chips/Hisilicon/HisiPkg.dec index 8e46e0d..2ce60d9 100644 --- a/Chips/Hisilicon/HisiPkg.dec +++ b/Chips/Hisilicon/HisiPkg.dec @@ -161,6 +161,7 @@ gHisiTokenSpaceGuid.PcdSerDesFlowCtrlFlag|0|UINT32|0x40000056 [PcdsFeatureFlag] + gHisiTokenSpaceGuid.PcdIsPciPerfTuningEnable|FALSE|BOOLEAN|0x00000066 diff --git a/Chips/Hisilicon/Include/Regs/HisiPcieV1RegOffset.h b/Chips/Hisilicon/Include/Regs/HisiPcieV1RegOffset.h index bdd80f8..539d567 100644 --- a/Chips/Hisilicon/Include/Regs/HisiPcieV1RegOffset.h +++ b/Chips/Hisilicon/Include/Regs/HisiPcieV1RegOffset.h @@ -8981,6 +8981,7 @@ typedef union tagIepMsiCtrlIntStatus #define PCIE_SYS_CTRL24_REG (PCI_SYS_BASE + 0x1b4) #define PCIE_SYS_CTRL28_REG (PCI_SYS_BASE + 0x1c4) #define PCIE_SYS_CTRL29_REG (PCI_SYS_BASE + 0x1c8) +#define PCIE_SYS_CTRL54_REG (PCI_SYS_BASE + 0x274) #define PCIE_SYS_STATE5_REG (PCI_SYS_BASE + 0x30) #define PCIE_SYS_STATE6_REG (PCI_SYS_BASE + 0x34) #define PCIE_SYS_STATE7_REG (PCI_SYS_BASE + 0x38) diff --git a/Platforms/Hisilicon/D03/D03.dsc b/Platforms/Hisilicon/D03/D03.dsc index 6d82627..942b2b8 100644 --- a/Platforms/Hisilicon/D03/D03.dsc +++ b/Platforms/Hisilicon/D03/D03.dsc @@ -111,6 +111,7 @@ ## If TRUE, Graphics Output Protocol will be installed on virtual handle created by ConsplitterDxe. # It could be set FALSE to save size. gEfiMdeModulePkgTokenSpaceGuid.PcdConOutGopSupport|TRUE + gHisiTokenSpaceGuid.PcdIsPciPerfTuningEnable|TRUE [PcdsFixedAtBuild.common] gArmPlatformTokenSpaceGuid.PcdFirmwareVendor|"ARM Versatile Express"