diff options
Diffstat (limited to 'arch/powerpc')
73 files changed, 3099 insertions, 2361 deletions
diff --git a/arch/powerpc/Kconfig b/arch/powerpc/Kconfig index 25493a0b174..957bf344c0f 100644 --- a/arch/powerpc/Kconfig +++ b/arch/powerpc/Kconfig @@ -342,6 +342,8 @@ config PPC_TRANSACTIONAL_MEM bool "Transactional Memory support for POWERPC" depends on PPC_BOOK3S_64 depends on SMP + select ALTIVEC + select VSX default n ---help--- Support user-mode Transactional Memory on POWERPC. @@ -532,6 +534,7 @@ config PPC_16K_PAGES config PPC_64K_PAGES bool "64k page size" if 44x || PPC_STD_MMU_64 || PPC_BOOK3E_64 + depends on !PPC_FSL_BOOK3E select PPC_HAS_HASH_64K if PPC_STD_MMU_64 config PPC_256K_PAGES @@ -1045,11 +1048,6 @@ config KEYS_COMPAT source "crypto/Kconfig" -config PPC_CLOCK - bool - default n - select HAVE_CLK - config PPC_LIB_RHEAP bool diff --git a/arch/powerpc/boot/dts/ac14xx.dts b/arch/powerpc/boot/dts/ac14xx.dts index a543c4088cb..a1b883730b3 100644 --- a/arch/powerpc/boot/dts/ac14xx.dts +++ b/arch/powerpc/boot/dts/ac14xx.dts @@ -139,7 +139,14 @@ }; }; + clocks { + osc { + clock-frequency = <25000000>; + }; + }; + soc@80000000 { + bus-frequency = <80000000>; /* 80 MHz ips bus */ clock@f00 { compatible = "fsl,mpc5121rev2-clock", "fsl,mpc5121-clock"; diff --git a/arch/powerpc/boot/dts/mpc5121.dtsi b/arch/powerpc/boot/dts/mpc5121.dtsi index 2d7cb04ac96..2c0e1552d20 100644 --- a/arch/powerpc/boot/dts/mpc5121.dtsi +++ b/arch/powerpc/boot/dts/mpc5121.dtsi @@ -9,6 +9,8 @@ * option) any later version. */ +#include <dt-bindings/clock/mpc512x-clock.h> + /dts-v1/; / { @@ -49,6 +51,10 @@ compatible = "fsl,mpc5121-mbx"; reg = <0x20000000 0x4000>; interrupts = <66 0x8>; + clocks = <&clks MPC512x_CLK_MBX_BUS>, + <&clks MPC512x_CLK_MBX_3D>, + <&clks MPC512x_CLK_MBX>; + clock-names = "mbx-bus", "mbx-3d", "mbx"; }; sram@30000000 { @@ -62,6 +68,8 @@ interrupts = <6 8>; #address-cells = <1>; #size-cells = <1>; + clocks = <&clks MPC512x_CLK_NFC>; + clock-names = "ipg"; }; localbus@80000020 { @@ -73,6 +81,17 @@ ranges = <0x0 0x0 0xfc000000 0x04000000>; }; + clocks { + #address-cells = <1>; + #size-cells = <0>; + + osc: osc { + compatible = "fixed-clock"; + #clock-cells = <0>; + clock-frequency = <33000000>; + }; + }; + soc@80000000 { compatible = "fsl,mpc5121-immr"; #address-cells = <1>; @@ -117,9 +136,12 @@ }; /* Clock control */ - clock@f00 { + clks: clock@f00 { compatible = "fsl,mpc5121-clock"; reg = <0xf00 0x100>; + #clock-cells = <1>; + clocks = <&osc>; + clock-names = "osc"; }; /* Power Management Controller */ @@ -139,12 +161,24 @@ compatible = "fsl,mpc5121-mscan"; reg = <0x1300 0x80>; interrupts = <12 0x8>; + clocks = <&clks MPC512x_CLK_BDLC>, + <&clks MPC512x_CLK_IPS>, + <&clks MPC512x_CLK_SYS>, + <&clks MPC512x_CLK_REF>, + <&clks MPC512x_CLK_MSCAN0_MCLK>; + clock-names = "ipg", "ips", "sys", "ref", "mclk"; }; can@1380 { compatible = "fsl,mpc5121-mscan"; reg = <0x1380 0x80>; interrupts = <13 0x8>; + clocks = <&clks MPC512x_CLK_BDLC>, + <&clks MPC512x_CLK_IPS>, + <&clks MPC512x_CLK_SYS>, + <&clks MPC512x_CLK_REF>, + <&clks MPC512x_CLK_MSCAN1_MCLK>; + clock-names = "ipg", "ips", "sys", "ref", "mclk"; }; sdhc@1500 { @@ -153,6 +187,9 @@ interrupts = <8 0x8>; dmas = <&dma0 30>; dma-names = "rx-tx"; + clocks = <&clks MPC512x_CLK_IPS>, + <&clks MPC512x_CLK_SDHC>; + clock-names = "ipg", "per"; }; i2c@1700 { @@ -161,6 +198,8 @@ compatible = "fsl,mpc5121-i2c", "fsl-i2c"; reg = <0x1700 0x20>; interrupts = <9 0x8>; + clocks = <&clks MPC512x_CLK_I2C>; + clock-names = "ipg"; }; i2c@1720 { @@ -169,6 +208,8 @@ compatible = "fsl,mpc5121-i2c", "fsl-i2c"; reg = <0x1720 0x20>; interrupts = <10 0x8>; + clocks = <&clks MPC512x_CLK_I2C>; + clock-names = "ipg"; }; i2c@1740 { @@ -177,6 +218,8 @@ compatible = "fsl,mpc5121-i2c", "fsl-i2c"; reg = <0x1740 0x20>; interrupts = <11 0x8>; + clocks = <&clks MPC512x_CLK_I2C>; + clock-names = "ipg"; }; i2ccontrol@1760 { @@ -188,30 +231,48 @@ compatible = "fsl,mpc5121-axe"; reg = <0x2000 0x100>; interrupts = <42 0x8>; + clocks = <&clks MPC512x_CLK_AXE>; + clock-names = "ipg"; }; display@2100 { compatible = "fsl,mpc5121-diu"; reg = <0x2100 0x100>; interrupts = <64 0x8>; + clocks = <&clks MPC512x_CLK_DIU>; + clock-names = "ipg"; }; can@2300 { compatible = "fsl,mpc5121-mscan"; reg = <0x2300 0x80>; interrupts = <90 0x8>; + clocks = <&clks MPC512x_CLK_BDLC>, + <&clks MPC512x_CLK_IPS>, + <&clks MPC512x_CLK_SYS>, + <&clks MPC512x_CLK_REF>, + <&clks MPC512x_CLK_MSCAN2_MCLK>; + clock-names = "ipg", "ips", "sys", "ref", "mclk"; }; can@2380 { compatible = "fsl,mpc5121-mscan"; reg = <0x2380 0x80>; interrupts = <91 0x8>; + clocks = <&clks MPC512x_CLK_BDLC>, + <&clks MPC512x_CLK_IPS>, + <&clks MPC512x_CLK_SYS>, + <&clks MPC512x_CLK_REF>, + <&clks MPC512x_CLK_MSCAN3_MCLK>; + clock-names = "ipg", "ips", "sys", "ref", "mclk"; }; viu@2400 { compatible = "fsl,mpc5121-viu"; reg = <0x2400 0x400>; interrupts = <67 0x8>; + clocks = <&clks MPC512x_CLK_VIU>; + clock-names = "ipg"; }; mdio@2800 { @@ -219,6 +280,8 @@ reg = <0x2800 0x800>; #address-cells = <1>; #size-cells = <0>; + clocks = <&clks MPC512x_CLK_FEC>; + clock-names = "per"; }; eth0: ethernet@2800 { @@ -227,6 +290,8 @@ reg = <0x2800 0x800>; local-mac-address = [ 00 00 00 00 00 00 ]; interrupts = <4 0x8>; + clocks = <&clks MPC512x_CLK_FEC>; + clock-names = "per"; }; /* USB1 using external ULPI PHY */ @@ -238,6 +303,8 @@ interrupts = <43 0x8>; dr_mode = "otg"; phy_type = "ulpi"; + clocks = <&clks MPC512x_CLK_USB1>; + clock-names = "ipg"; }; /* USB0 using internal UTMI PHY */ @@ -249,6 +316,8 @@ interrupts = <44 0x8>; dr_mode = "otg"; phy_type = "utmi_wide"; + clocks = <&clks MPC512x_CLK_USB2>; + clock-names = "ipg"; }; /* IO control */ @@ -267,6 +336,8 @@ compatible = "fsl,mpc5121-pata"; reg = <0x10200 0x100>; interrupts = <5 0x8>; + clocks = <&clks MPC512x_CLK_PATA>; + clock-names = "ipg"; }; /* 512x PSCs are not 52xx PSC compatible */ @@ -278,6 +349,9 @@ interrupts = <40 0x8>; fsl,rx-fifo-size = <16>; fsl,tx-fifo-size = <16>; + clocks = <&clks MPC512x_CLK_PSC0>, + <&clks MPC512x_CLK_PSC0_MCLK>; + clock-names = "ipg", "mclk"; }; /* PSC1 */ @@ -287,6 +361,9 @@ interrupts = <40 0x8>; fsl,rx-fifo-size = <16>; fsl,tx-fifo-size = <16>; + clocks = <&clks MPC512x_CLK_PSC1>, + <&clks MPC512x_CLK_PSC1_MCLK>; + clock-names = "ipg", "mclk"; }; /* PSC2 */ @@ -296,6 +373,9 @@ interrupts = <40 0x8>; fsl,rx-fifo-size = <16>; fsl,tx-fifo-size = <16>; + clocks = <&clks MPC512x_CLK_PSC2>, + <&clks MPC512x_CLK_PSC2_MCLK>; + clock-names = "ipg", "mclk"; }; /* PSC3 */ @@ -305,6 +385,9 @@ interrupts = <40 0x8>; fsl,rx-fifo-size = <16>; fsl,tx-fifo-size = <16>; + clocks = <&clks MPC512x_CLK_PSC3>, + <&clks MPC512x_CLK_PSC3_MCLK>; + clock-names = "ipg", "mclk"; }; /* PSC4 */ @@ -314,6 +397,9 @@ interrupts = <40 0x8>; fsl,rx-fifo-size = <16>; fsl,tx-fifo-size = <16>; + clocks = <&clks MPC512x_CLK_PSC4>, + <&clks MPC512x_CLK_PSC4_MCLK>; + clock-names = "ipg", "mclk"; }; /* PSC5 */ @@ -323,6 +409,9 @@ interrupts = <40 0x8>; fsl,rx-fifo-size = <16>; fsl,tx-fifo-size = <16>; + clocks = <&clks MPC512x_CLK_PSC5>, + <&clks MPC512x_CLK_PSC5_MCLK>; + clock-names = "ipg", "mclk"; }; /* PSC6 */ @@ -332,6 +421,9 @@ interrupts = <40 0x8>; fsl,rx-fifo-size = <16>; fsl,tx-fifo-size = <16>; + clocks = <&clks MPC512x_CLK_PSC6>, + <&clks MPC512x_CLK_PSC6_MCLK>; + clock-names = "ipg", "mclk"; }; /* PSC7 */ @@ -341,6 +433,9 @@ interrupts = <40 0x8>; fsl,rx-fifo-size = <16>; fsl,tx-fifo-size = <16>; + clocks = <&clks MPC512x_CLK_PSC7>, + <&clks MPC512x_CLK_PSC7_MCLK>; + clock-names = "ipg", "mclk"; }; /* PSC8 */ @@ -350,6 +445,9 @@ interrupts = <40 0x8>; fsl,rx-fifo-size = <16>; fsl,tx-fifo-size = <16>; + clocks = <&clks MPC512x_CLK_PSC8>, + <&clks MPC512x_CLK_PSC8_MCLK>; + clock-names = "ipg", "mclk"; }; /* PSC9 */ @@ -359,6 +457,9 @@ interrupts = <40 0x8>; fsl,rx-fifo-size = <16>; fsl,tx-fifo-size = <16>; + clocks = <&clks MPC512x_CLK_PSC9>, + <&clks MPC512x_CLK_PSC9_MCLK>; + clock-names = "ipg", "mclk"; }; /* PSC10 */ @@ -368,6 +469,9 @@ interrupts = <40 0x8>; fsl,rx-fifo-size = <16>; fsl,tx-fifo-size = <16>; + clocks = <&clks MPC512x_CLK_PSC10>, + <&clks MPC512x_CLK_PSC10_MCLK>; + clock-names = "ipg", "mclk"; }; /* PSC11 */ @@ -377,12 +481,17 @@ interrupts = <40 0x8>; fsl,rx-fifo-size = <16>; fsl,tx-fifo-size = <16>; + clocks = <&clks MPC512x_CLK_PSC11>, + <&clks MPC512x_CLK_PSC11_MCLK>; + clock-names = "ipg", "mclk"; }; pscfifo@11f00 { compatible = "fsl,mpc5121-psc-fifo"; reg = <0x11f00 0x100>; interrupts = <40 0x8>; + clocks = <&clks MPC512x_CLK_PSC_FIFO>; + clock-names = "ipg"; }; dma0: dma@14000 { @@ -400,6 +509,8 @@ #address-cells = <3>; #size-cells = <2>; #interrupt-cells = <1>; + clocks = <&clks MPC512x_CLK_PCI>; + clock-names = "ipg"; reg = <0x80008500 0x100 /* internal registers */ 0x80008300 0x8>; /* config space access registers */ diff --git a/arch/powerpc/boot/dts/mpc5125twr.dts b/arch/powerpc/boot/dts/mpc5125twr.dts index a618dfc13e4..e4f29747174 100644 --- a/arch/powerpc/boot/dts/mpc5125twr.dts +++ b/arch/powerpc/boot/dts/mpc5125twr.dts @@ -12,6 +12,8 @@ * option) any later version. */ +#include <dt-bindings/clock/mpc512x-clock.h> + /dts-v1/; / { @@ -54,6 +56,17 @@ reg = <0x30000000 0x08000>; // 32K at 0x30000000 }; + clocks { + #address-cells = <1>; + #size-cells = <0>; + + osc: osc { + compatible = "fixed-clock"; + #clock-cells = <0>; + clock-frequency = <33000000>; + }; + }; + soc@80000000 { compatible = "fsl,mpc5121-immr"; #address-cells = <1>; @@ -87,9 +100,12 @@ reg = <0xe00 0x100>; }; - clock@f00 { // Clock control + clks: clock@f00 { // Clock control compatible = "fsl,mpc5121-clock"; reg = <0xf00 0x100>; + #clock-cells = <1>; + clocks = <&osc>; + clock-names = "osc"; }; pmc@1000{ // Power Management Controller @@ -114,18 +130,33 @@ compatible = "fsl,mpc5121-mscan"; interrupts = <12 0x8>; reg = <0x1300 0x80>; + clocks = <&clks MPC512x_CLK_BDLC>, + <&clks MPC512x_CLK_IPS>, + <&clks MPC512x_CLK_SYS>, + <&clks MPC512x_CLK_REF>, + <&clks MPC512x_CLK_MSCAN0_MCLK>; + clock-names = "ipg", "ips", "sys", "ref", "mclk"; }; can@1380 { compatible = "fsl,mpc5121-mscan"; interrupts = <13 0x8>; reg = <0x1380 0x80>; + clocks = <&clks MPC512x_CLK_BDLC>, + <&clks MPC512x_CLK_IPS>, + <&clks MPC512x_CLK_SYS>, + <&clks MPC512x_CLK_REF>, + <&clks MPC512x_CLK_MSCAN1_MCLK>; + clock-names = "ipg", "ips", "sys", "ref", "mclk"; }; sdhc@1500 { compatible = "fsl,mpc5121-sdhc"; interrupts = <8 0x8>; reg = <0x1500 0x100>; + clocks = <&clks MPC512x_CLK_IPS>, + <&clks MPC512x_CLK_SDHC>; + clock-names = "ipg", "per"; }; i2c@1700 { @@ -134,6 +165,8 @@ compatible = "fsl,mpc5121-i2c", "fsl-i2c"; reg = <0x1700 0x20>; interrupts = <0x9 0x8>; + clocks = <&clks MPC512x_CLK_I2C>; + clock-names = "ipg"; }; i2c@1720 { @@ -142,6 +175,8 @@ compatible = "fsl,mpc5121-i2c", "fsl-i2c"; reg = <0x1720 0x20>; interrupts = <0xa 0x8>; + clocks = <&clks MPC512x_CLK_I2C>; + clock-names = "ipg"; }; i2c@1740 { @@ -150,6 +185,8 @@ compatible = "fsl,mpc5121-i2c", "fsl-i2c"; reg = <0x1740 0x20>; interrupts = <0xb 0x8>; + clocks = <&clks MPC512x_CLK_I2C>; + clock-names = "ipg"; }; i2ccontrol@1760 { @@ -161,6 +198,8 @@ compatible = "fsl,mpc5121-diu"; reg = <0x2100 0x100>; interrupts = <64 0x8>; + clocks = <&clks MPC512x_CLK_DIU>; + clock-names = "ipg"; }; mdio@2800 { @@ -180,6 +219,8 @@ interrupts = <4 0x8>; phy-handle = < &phy0 >; phy-connection-type = "rmii"; + clocks = <&clks MPC512x_CLK_FEC>; + clock-names = "per"; }; // IO control @@ -200,6 +241,8 @@ interrupts = <43 0x8>; dr_mode = "host"; phy_type = "ulpi"; + clocks = <&clks MPC512x_CLK_USB1>; + clock-names = "ipg"; status = "disabled"; }; @@ -211,6 +254,9 @@ interrupts = <40 0x8>; fsl,rx-fifo-size = <16>; fsl,tx-fifo-size = <16>; + clocks = <&clks MPC512x_CLK_PSC1>, + <&clks MPC512x_CLK_PSC1_MCLK>; + clock-names = "ipg", "mclk"; }; // PSC9 uart1 aka ttyPSC1 @@ -220,12 +266,17 @@ interrupts = <40 0x8>; fsl,rx-fifo-size = <16>; fsl,tx-fifo-size = <16>; + clocks = <&clks MPC512x_CLK_PSC9>, + <&clks MPC512x_CLK_PSC9_MCLK>; + clock-names = "ipg", "mclk"; }; pscfifo@11f00 { compatible = "fsl,mpc5121-psc-fifo"; reg = <0x11f00 0x100>; interrupts = <40 0x8>; + clocks = <&clks MPC512x_CLK_PSC_FIFO>; + clock-names = "ipg"; }; dma@14000 { diff --git a/arch/powerpc/include/asm/clk_interface.h b/arch/powerpc/include/asm/clk_interface.h deleted file mode 100644 index ab1882c1e17..00000000000 --- a/arch/powerpc/include/asm/clk_interface.h +++ /dev/null @@ -1,20 +0,0 @@ -#ifndef __ASM_POWERPC_CLK_INTERFACE_H -#define __ASM_POWERPC_CLK_INTERFACE_H - -#include <linux/clk.h> - -struct clk_interface { - struct clk* (*clk_get) (struct device *dev, const char *id); - int (*clk_enable) (struct clk *clk); - void (*clk_disable) (struct clk *clk); - unsigned long (*clk_get_rate) (struct clk *clk); - void (*clk_put) (struct clk *clk); - long (*clk_round_rate) (struct clk *clk, unsigned long rate); - int (*clk_set_rate) (struct clk *clk, unsigned long rate); - int (*clk_set_parent) (struct clk *clk, struct clk *parent); - struct clk* (*clk_get_parent) (struct clk *clk); -}; - -extern struct clk_interface clk_functions; - -#endif /* __ASM_POWERPC_CLK_INTERFACE_H */ diff --git a/arch/powerpc/include/asm/epapr_hcalls.h b/arch/powerpc/include/asm/epapr_hcalls.h index 86b0ac79990..334459ad145 100644 --- a/arch/powerpc/include/asm/epapr_hcalls.h +++ b/arch/powerpc/include/asm/epapr_hcalls.h @@ -460,5 +460,116 @@ static inline unsigned int ev_idle(void) return r3; } + +#ifdef CONFIG_EPAPR_PARAVIRT +static inline unsigned long epapr_hypercall(unsigned long *in, + unsigned long *out, + unsigned long nr) +{ + unsigned long register r0 asm("r0"); + unsigned long register r3 asm("r3") = in[0]; + unsigned long register r4 asm("r4") = in[1]; + unsigned long register r5 asm("r5") = in[2]; + unsigned long register r6 asm("r6") = in[3]; + unsigned long register r7 asm("r7") = in[4]; + unsigned long register r8 asm("r8") = in[5]; + unsigned long register r9 asm("r9") = in[6]; + unsigned long register r10 asm("r10") = in[7]; + unsigned long register r11 asm("r11") = nr; + unsigned long register r12 asm("r12"); + + asm volatile("bl epapr_hypercall_start" + : "=r"(r0), "=r"(r3), "=r"(r4), "=r"(r5), "=r"(r6), + "=r"(r7), "=r"(r8), "=r"(r9), "=r"(r10), "=r"(r11), + "=r"(r12) + : "r"(r3), "r"(r4), "r"(r5), "r"(r6), "r"(r7), "r"(r8), + "r"(r9), "r"(r10), "r"(r11) + : "memory", "cc", "xer", "ctr", "lr"); + + out[0] = r4; + out[1] = r5; + out[2] = r6; + out[3] = r7; + out[4] = r8; + out[5] = r9; + out[6] = r10; + out[7] = r11; + + return r3; +} +#else +static unsigned long epapr_hypercall(unsigned long *in, + unsigned long *out, + unsigned long nr) +{ + return EV_UNIMPLEMENTED; +} +#endif + +static inline long epapr_hypercall0_1(unsigned int nr, unsigned long *r2) +{ + unsigned long in[8]; + unsigned long out[8]; + unsigned long r; + + r = epapr_hypercall(in, out, nr); + *r2 = out[0]; + + return r; +} + +static inline long epapr_hypercall0(unsigned int nr) +{ + unsigned long in[8]; + unsigned long out[8]; + + return epapr_hypercall(in, out, nr); +} + +static inline long epapr_hypercall1(unsigned int nr, unsigned long p1) +{ + unsigned long in[8]; + unsigned long out[8]; + + in[0] = p1; + return epapr_hypercall(in, out, nr); +} + +static inline long epapr_hypercall2(unsigned int nr, unsigned long p1, + unsigned long p2) +{ + unsigned long in[8]; + unsigned long out[8]; + + in[0] = p1; + in[1] = p2; + return epapr_hypercall(in, out, nr); +} + +static inline long epapr_hypercall3(unsigned int nr, unsigned long p1, + unsigned long p2, unsigned long p3) +{ + unsigned long in[8]; + unsigned long out[8]; + + in[0] = p1; + in[1] = p2; + in[2] = p3; + return epapr_hypercall(in, out, nr); +} + +static inline long epapr_hypercall4(unsigned int nr, unsigned long p1, + unsigned long p2, unsigned long p3, + unsigned long p4) +{ + unsigned long in[8]; + unsigned long out[8]; + + in[0] = p1; + in[1] = p2; + in[2] = p3; + in[3] = p4; + return epapr_hypercall(in, out, nr); +} #endif /* !__ASSEMBLY__ */ #endif /* _EPAPR_HCALLS_H */ diff --git a/arch/powerpc/include/asm/kvm_asm.h b/arch/powerpc/include/asm/kvm_asm.h index 1503d8c7c41..19eb74a95b5 100644 --- a/arch/powerpc/include/asm/kvm_asm.h +++ b/arch/powerpc/include/asm/kvm_asm.h @@ -92,14 +92,17 @@ #define BOOK3S_INTERRUPT_FP_UNAVAIL 0x800 #define BOOK3S_INTERRUPT_DECREMENTER 0x900 #define BOOK3S_INTERRUPT_HV_DECREMENTER 0x980 +#define BOOK3S_INTERRUPT_DOORBELL 0xa00 #define BOOK3S_INTERRUPT_SYSCALL 0xc00 #define BOOK3S_INTERRUPT_TRACE 0xd00 #define BOOK3S_INTERRUPT_H_DATA_STORAGE 0xe00 #define BOOK3S_INTERRUPT_H_INST_STORAGE 0xe20 #define BOOK3S_INTERRUPT_H_EMUL_ASSIST 0xe40 +#define BOOK3S_INTERRUPT_H_DOORBELL 0xe80 #define BOOK3S_INTERRUPT_PERFMON 0xf00 #define BOOK3S_INTERRUPT_ALTIVEC 0xf20 #define BOOK3S_INTERRUPT_VSX 0xf40 +#define BOOK3S_INTERRUPT_H_FAC_UNAVAIL 0xf80 #define BOOK3S_IRQPRIO_SYSTEM_RESET 0 #define BOOK3S_IRQPRIO_DATA_SEGMENT 1 diff --git a/arch/powerpc/include/asm/kvm_book3s.h b/arch/powerpc/include/asm/kvm_book3s.h index bc23b1ba798..83851aabfdc 100644 --- a/arch/powerpc/include/asm/kvm_book3s.h +++ b/arch/powerpc/include/asm/kvm_book3s.h @@ -186,9 +186,6 @@ extern void kvmppc_update_lpcr(struct kvm *kvm, unsigned long lpcr, extern void kvmppc_entry_trampoline(void); extern void kvmppc_hv_entry_trampoline(void); -extern void kvmppc_load_up_fpu(void); -extern void kvmppc_load_up_altivec(void); -extern void kvmppc_load_up_vsx(void); extern u32 kvmppc_alignment_dsisr(struct kvm_vcpu *vcpu, unsigned int inst); extern ulong kvmppc_alignment_dar(struct kvm_vcpu *vcpu, unsigned int inst); extern int kvmppc_h_pr(struct kvm_vcpu *vcpu, unsigned long cmd); @@ -271,16 +268,25 @@ static inline ulong kvmppc_get_pc(struct kvm_vcpu *vcpu) return vcpu->arch.pc; } -static inline u32 kvmppc_get_last_inst(struct kvm_vcpu *vcpu) +static inline bool kvmppc_need_byteswap(struct kvm_vcpu *vcpu) { - ulong pc = kvmppc_get_pc(vcpu); + return (vcpu->arch.shared->msr & MSR_LE) != (MSR_KERNEL & MSR_LE); +} +static inline u32 kvmppc_get_last_inst_internal(struct kvm_vcpu *vcpu, ulong pc) +{ /* Load the instruction manually if it failed to do so in the * exit path */ if (vcpu->arch.last_inst == KVM_INST_FETCH_FAILED) kvmppc_ld(vcpu, &pc, sizeof(u32), &vcpu->arch.last_inst, false); - return vcpu->arch.last_inst; + return kvmppc_need_byteswap(vcpu) ? swab32(vcpu->arch.last_inst) : + vcpu->arch.last_inst; +} + +static inline u32 kvmppc_get_last_inst(struct kvm_vcpu *vcpu) +{ + return kvmppc_get_last_inst_internal(vcpu, kvmppc_get_pc(vcpu)); } /* @@ -290,14 +296,7 @@ static inline u32 kvmppc_get_last_inst(struct kvm_vcpu *vcpu) */ static inline u32 kvmppc_get_last_sc(struct kvm_vcpu *vcpu) { - ulong pc = kvmppc_get_pc(vcpu) - 4; - - /* Load the instruction manually if it failed to do so in the - * exit path */ - if (vcpu->arch.last_inst == KVM_INST_FETCH_FAILED) - kvmppc_ld(vcpu, &pc, sizeof(u32), &vcpu->arch.last_inst, false); - - return vcpu->arch.last_inst; + return kvmppc_get_last_inst_internal(vcpu, kvmppc_get_pc(vcpu) - 4); } static inline ulong kvmppc_get_fault_dar(struct kvm_vcpu *vcpu) diff --git a/arch/powerpc/include/asm/kvm_book3s_asm.h b/arch/powerpc/include/asm/kvm_book3s_asm.h index 192917d2239..f3a91dc02c9 100644 --- a/arch/powerpc/include/asm/kvm_book3s_asm.h +++ b/arch/powerpc/include/asm/kvm_book3s_asm.h @@ -88,6 +88,7 @@ struct kvmppc_host_state { u8 hwthread_req; u8 hwthread_state; u8 host_ipi; + u8 ptid; struct kvm_vcpu *kvm_vcpu; struct kvmppc_vcore *kvm_vcore; unsigned long xics_phys; diff --git a/arch/powerpc/include/asm/kvm_booke.h b/arch/powerpc/include/asm/kvm_booke.h index dd8f61510df..80d46b5a7ef 100644 --- a/arch/powerpc/include/asm/kvm_booke.h +++ b/arch/powerpc/include/asm/kvm_booke.h @@ -63,6 +63,12 @@ static inline u32 kvmppc_get_xer(struct kvm_vcpu *vcpu) return vcpu->arch.xer; } +static inline bool kvmppc_need_byteswap(struct kvm_vcpu *vcpu) +{ + /* XXX Would need to check TLB entry */ + return false; +} + static inline u32 kvmppc_get_last_inst(struct kvm_vcpu *vcpu) { return vcpu->arch.last_inst; diff --git a/arch/powerpc/include/asm/kvm_host.h b/arch/powerpc/include/asm/kvm_host.h index 237d1d25b44..1eaea2dea17 100644 --- a/arch/powerpc/include/asm/kvm_host.h +++ b/arch/powerpc/include/asm/kvm_host.h @@ -288,6 +288,7 @@ struct kvmppc_vcore { int n_woken; int nap_count; int napping_threads; + int first_vcpuid; u16 pcpu; u16 last_cpu; u8 vcore_state; @@ -298,10 +299,12 @@ struct kvmppc_vcore { u64 stolen_tb; u64 preempt_tb; struct kvm_vcpu *runner; + struct kvm *kvm; u64 tb_offset; /* guest timebase - host timebase */ ulong lpcr; u32 arch_compat; ulong pcr; + ulong dpdes; /* doorbell state (POWER8) */ }; #define VCORE_ENTRY_COUNT(vc) ((vc)->entry_exit_count & 0xff) @@ -410,8 +413,7 @@ struct kvm_vcpu_arch { ulong gpr[32]; - u64 fpr[32]; - u64 fpscr; + struct thread_fp_state fp; #ifdef CONFIG_SPE ulong evr[32]; @@ -420,12 +422,7 @@ struct kvm_vcpu_arch { u64 acc; #endif #ifdef CONFIG_ALTIVEC - vector128 vr[32]; - vector128 vscr; -#endif - -#ifdef CONFIG_VSX - u64 vsr[64]; + struct thread_vr_state vr; #endif #ifdef CONFIG_KVM_BOOKE_HV @@ -452,6 +449,7 @@ struct kvm_vcpu_arch { ulong pc; ulong ctr; ulong lr; + ulong tar; ulong xer; u32 cr; @@ -461,13 +459,30 @@ struct kvm_vcpu_arch { ulong guest_owned_ext; ulong purr; ulong spurr; + ulong ic; + ulong vtb; ulong dscr; ulong amr; ulong uamor; + ulong iamr; u32 ctrl; + u32 dabrx; ulong dabr; + ulong dawr; + ulong dawrx; + ulong ciabr; ulong cfar; ulong ppr; + ulong pspb; + ulong fscr; + ulong ebbhr; + ulong ebbrr; + ulong bescr; + ulong csigr; + ulong tacr; + ulong tcscr; + ulong acop; + ulong wort; ulong shadow_srr1; #endif u32 vrsave; /* also USPRG0 */ @@ -502,10 +517,33 @@ struct kvm_vcpu_arch { u32 ccr1; u32 dbsr; - u64 mmcr[3]; + u64 mmcr[5]; u32 pmc[8]; + u32 spmc[2]; u64 siar; u64 sdar; + u64 sier; +#ifdef CONFIG_PPC_TRANSACTIONAL_MEM + u64 tfhar; + u64 texasr; + u64 tfiar; + + u32 cr_tm; + u64 lr_tm; + u64 ctr_tm; + u64 amr_tm; + u64 ppr_tm; + u64 dscr_tm; + u64 tar_tm; + + ulong gpr_tm[32]; + + struct thread_fp_state fp_tm; + + struct thread_vr_state vr_tm; + u32 vrsave_tm; /* also USPRG0 */ + +#endif #ifdef CONFIG_KVM_EXIT_TIMING struct mutex exit_timing_lock; @@ -546,6 +584,7 @@ struct kvm_vcpu_arch { #endif gpa_t paddr_accessed; gva_t vaddr_accessed; + pgd_t *pgdir; u8 io_gpr; /* GPR used as IO source/target */ u8 mmio_is_bigendian; @@ -603,7 +642,6 @@ struct kvm_vcpu_arch { struct list_head run_list; struct task_struct *run_task; struct kvm_run *kvm_run; - pgd_t *pgdir; spinlock_t vpa_update_lock; struct kvmppc_vpa vpa; @@ -616,9 +654,12 @@ struct kvm_vcpu_arch { spinlock_t tbacct_lock; u64 busy_stolen; u64 busy_preempt; + unsigned long intr_msr; #endif }; +#define VCPU_FPR(vcpu, i) (vcpu)->arch.fp.fpr[i][TS_FPROFFSET] + /* Values for vcpu->arch.state */ #define KVMPPC_VCPU_NOTREADY 0 #define KVMPPC_VCPU_RUNNABLE 1 diff --git a/arch/powerpc/include/asm/kvm_para.h b/arch/powerpc/include/asm/kvm_para.h index 2b119654b4c..336a91acb8b 100644 --- a/arch/powerpc/include/asm/kvm_para.h +++ b/arch/powerpc/include/asm/kvm_para.h @@ -39,10 +39,6 @@ static inline int kvm_para_available(void) return 1; } -extern unsigned long kvm_hypercall(unsigned long *in, - unsigned long *out, - unsigned long nr); - #else static inline int kvm_para_available(void) @@ -50,82 +46,8 @@ static inline int kvm_para_available(void) return 0; } -static unsigned long kvm_hypercall(unsigned long *in, - unsigned long *out, - unsigned long nr) -{ - return EV_UNIMPLEMENTED; -} - #endif -static inline long kvm_hypercall0_1(unsigned int nr, unsigned long *r2) -{ - unsigned long in[8]; - unsigned long out[8]; - unsigned long r; - - r = kvm_hypercall(in, out, KVM_HCALL_TOKEN(nr)); - *r2 = out[0]; - - return r; -} - -static inline long kvm_hypercall0(unsigned int nr) -{ - unsigned long in[8]; - unsigned long out[8]; - - return kvm_hypercall(in, out, KVM_HCALL_TOKEN(nr)); -} - -static inline long kvm_hypercall1(unsigned int nr, unsigned long p1) -{ - unsigned long in[8]; - unsigned long out[8]; - - in[0] = p1; - return kvm_hypercall(in, out, KVM_HCALL_TOKEN(nr)); -} - -static inline long kvm_hypercall2(unsigned int nr, unsigned long p1, - unsigned long p2) -{ - unsigned long in[8]; - unsigned long out[8]; - - in[0] = p1; - in[1] = p2; - return kvm_hypercall(in, out, KVM_HCALL_TOKEN(nr)); -} - -static inline long kvm_hypercall3(unsigned int nr, unsigned long p1, - unsigned long p2, unsigned long p3) -{ - unsigned long in[8]; - unsigned long out[8]; - - in[0] = p1; - in[1] = p2; - in[2] = p3; - return kvm_hypercall(in, out, KVM_HCALL_TOKEN(nr)); -} - -static inline long kvm_hypercall4(unsigned int nr, unsigned long p1, - unsigned long p2, unsigned long p3, - unsigned long p4) -{ - unsigned long in[8]; - unsigned long out[8]; - - in[0] = p1; - in[1] = p2; - in[2] = p3; - in[3] = p4; - return kvm_hypercall(in, out, KVM_HCALL_TOKEN(nr)); -} - - static inline unsigned int kvm_arch_para_features(void) { unsigned long r; @@ -133,7 +55,7 @@ static inline unsigned int kvm_arch_para_features(void) if (!kvm_para_available()) return 0; - if(kvm_hypercall0_1(KVM_HC_FEATURES, &r)) + if(epapr_hypercall0_1(KVM_HCALL_TOKEN(KVM_HC_FEATURES), &r)) return 0; return r; diff --git a/arch/powerpc/include/asm/kvm_ppc.h b/arch/powerpc/include/asm/kvm_ppc.h index c8317fbf92c..fcd53f0d34b 100644 --- a/arch/powerpc/include/asm/kvm_ppc.h +++ b/arch/powerpc/include/asm/kvm_ppc.h @@ -54,12 +54,13 @@ extern void kvmppc_handler_highmem(void); extern void kvmppc_dump_vcpu(struct kvm_vcpu *vcpu); extern int kvmppc_handle_load(struct kvm_run *run, struct kvm_vcpu *vcpu, unsigned int rt, unsigned int bytes, - int is_bigendian); + int is_default_endian); extern int kvmppc_handle_loads(struct kvm_run *run, struct kvm_vcpu *vcpu, unsigned int rt, unsigned int bytes, - int is_bigendian); + int is_default_endian); extern int kvmppc_handle_store(struct kvm_run *run, struct kvm_vcpu *vcpu, - u64 val, unsigned int bytes, int is_bigendian); + u64 val, unsigned int bytes, + int is_default_endian); extern int kvmppc_emulate_instruction(struct kvm_run *run, struct kvm_vcpu *vcpu); @@ -455,6 +456,12 @@ static inline void kvmppc_fix_ee_before_entry(void) trace_hardirqs_on(); #ifdef CONFIG_PPC64 + /* + * To avoid races, the caller must have gone directly from having + * interrupts fully-enabled to hard-disabled. + */ + WARN_ON(local_paca->irq_happened != PACA_IRQ_HARD_DIS); + /* Only need to enable IRQs by hard enabling them after this */ local_paca->irq_happened = 0; local_paca->soft_enabled = 1; diff --git a/arch/powerpc/include/asm/mpc5121.h b/arch/powerpc/include/asm/mpc5121.h index 887d3d6133e..4a69cd1d504 100644 --- a/arch/powerpc/include/asm/mpc5121.h +++ b/arch/powerpc/include/asm/mpc5121.h @@ -37,7 +37,12 @@ struct mpc512x_ccm { u32 cccr; /* CFM Clock Control Register */ u32 dccr; /* DIU Clock Control Register */ u32 mscan_ccr[4]; /* MSCAN Clock Control Registers */ - u8 res[0x98]; /* Reserved */ + u32 out_ccr[4]; /* OUT CLK Configure Registers */ + u32 rsv0[2]; /* Reserved */ + u32 scfr3; /* System Clock Frequency Register 3 */ + u32 rsv1[3]; /* Reserved */ + u32 spll_lock_cnt; /* System PLL Lock Counter */ + u8 res[0x6c]; /* Reserved */ }; /* diff --git a/arch/powerpc/include/asm/pgtable-ppc64.h b/arch/powerpc/include/asm/pgtable-ppc64.h index d27960c89a7..bc141c950b1 100644 --- a/arch/powerpc/include/asm/pgtable-ppc64.h +++ b/arch/powerpc/include/asm/pgtable-ppc64.h @@ -560,9 +560,9 @@ extern void pmdp_invalidate(struct vm_area_struct *vma, unsigned long address, pmd_t *pmdp); #define pmd_move_must_withdraw pmd_move_must_withdraw -typedef struct spinlock spinlock_t; -static inline int pmd_move_must_withdraw(spinlock_t *new_pmd_ptl, - spinlock_t *old_pmd_ptl) +struct spinlock; +static inline int pmd_move_must_withdraw(struct spinlock *new_pmd_ptl, + struct spinlock *old_pmd_ptl) { /* * Archs like ppc64 use pgtable to store per pmd diff --git a/arch/powerpc/include/asm/pgtable.h b/arch/powerpc/include/asm/pgtable.h index b999ca31898..f83b6f3e1b3 100644 --- a/arch/powerpc/include/asm/pgtable.h +++ b/arch/powerpc/include/asm/pgtable.h @@ -287,6 +287,27 @@ extern int gup_hugepte(pte_t *ptep, unsigned long sz, unsigned long addr, #endif pte_t *find_linux_pte_or_hugepte(pgd_t *pgdir, unsigned long ea, unsigned *shift); + +static inline pte_t *lookup_linux_ptep(pgd_t *pgdir, unsigned long hva, + unsigned long *pte_sizep) +{ + pte_t *ptep; + unsigned long ps = *pte_sizep; + unsigned int shift; + + ptep = find_linux_pte_or_hugepte(pgdir, hva, &shift); + if (!ptep) + return NULL; + if (shift) + *pte_sizep = 1ul << shift; + else + *pte_sizep = PAGE_SIZE; + + if (ps > *pte_sizep) + return NULL; + + return ptep; +} #endif /* __ASSEMBLY__ */ #endif /* __KERNEL__ */ diff --git a/arch/powerpc/include/asm/processor.h b/arch/powerpc/include/asm/processor.h index 8ca20ac28dc..b62de43ae5f 100644 --- a/arch/powerpc/include/asm/processor.h +++ b/arch/powerpc/include/asm/processor.h @@ -450,13 +450,6 @@ enum idle_boot_override {IDLE_NO_OVERRIDE = 0, IDLE_POWERSAVE_OFF}; extern int powersave_nap; /* set if nap mode can be used in idle loop */ extern void power7_nap(void); - -#ifdef CONFIG_PSERIES_IDLE -extern void update_smt_snooze_delay(int cpu, int residency); -#else -static inline void update_smt_snooze_delay(int cpu, int residency) {} -#endif - extern void flush_instruction_cache(void); extern void hard_reset_now(void); extern void poweroff_now(void); diff --git a/arch/powerpc/include/asm/reg.h b/arch/powerpc/include/asm/reg.h index 62b114e079c..90c06ec6eff 100644 --- a/arch/powerpc/include/asm/reg.h +++ b/arch/powerpc/include/asm/reg.h @@ -223,17 +223,26 @@ #define CTRL_TE 0x00c00000 /* thread enable */ #define CTRL_RUNLATCH 0x1 #define SPRN_DAWR 0xB4 +#define SPRN_CIABR 0xBB +#define CIABR_PRIV 0x3 +#define CIABR_PRIV_USER 1 +#define CIABR_PRIV_SUPER 2 +#define CIABR_PRIV_HYPER 3 #define SPRN_DAWRX 0xBC -#define DAWRX_USER (1UL << 0) -#define DAWRX_KERNEL (1UL << 1) -#define DAWRX_HYP (1UL << 2) +#define DAWRX_USER __MASK(0) +#define DAWRX_KERNEL __MASK(1) +#define DAWRX_HYP __MASK(2) +#define DAWRX_WTI __MASK(3) +#define DAWRX_WT __MASK(4) +#define DAWRX_DR __MASK(5) +#define DAWRX_DW __MASK(6) #define SPRN_DABR 0x3F5 /* Data Address Breakpoint Register */ #define SPRN_DABR2 0x13D /* e300 */ #define SPRN_DABRX 0x3F7 /* Data Address Breakpoint Register Extension */ -#define DABRX_USER (1UL << 0) -#define DABRX_KERNEL (1UL << 1) -#define DABRX_HYP (1UL << 2) -#define DABRX_BTI (1UL << 3) +#define DABRX_USER __MASK(0) +#define DABRX_KERNEL __MASK(1) +#define DABRX_HYP __MASK(2) +#define DABRX_BTI __MASK(3) #define DABRX_ALL (DABRX_BTI | DABRX_HYP | DABRX_KERNEL | DABRX_USER) #define SPRN_DAR 0x013 /* Data Address Register */ #define SPRN_DBCR 0x136 /* e300 Data Breakpoint Control Reg */ @@ -260,6 +269,8 @@ #define SPRN_HRMOR 0x139 /* Real mode offset register */ #define SPRN_HSRR0 0x13A /* Hypervisor Save/Restore 0 */ #define SPRN_HSRR1 0x13B /* Hypervisor Save/Restore 1 */ +#define SPRN_IC 0x350 /* Virtual Instruction Count */ +#define SPRN_VTB 0x351 /* Virtual Time Base */ /* HFSCR and FSCR bit numbers are the same */ #define FSCR_TAR_LG 8 /* Enable Target Address Register */ #define FSCR_EBB_LG 7 /* Enable Event Based Branching */ @@ -298,9 +309,13 @@ #define LPCR_RMLS 0x1C000000 /* impl dependent rmo limit sel */ #define LPCR_RMLS_SH (63-37) #define LPCR_ILE 0x02000000 /* !HV irqs set MSR:LE */ +#define LPCR_AIL 0x01800000 /* Alternate interrupt location */ #define LPCR_AIL_0 0x00000000 /* MMU off exception offset 0x0 */ #define LPCR_AIL_3 0x01800000 /* MMU on exception offset 0xc00...4xxx */ -#define LPCR_PECE 0x00007000 /* powersave exit cause enable */ +#define LPCR_ONL 0x00040000 /* online - PURR/SPURR count */ +#define LPCR_PECE 0x0001f000 /* powersave exit cause enable */ +#define LPCR_PECEDP 0x00010000 /* directed priv dbells cause exit */ +#define LPCR_PECEDH 0x00008000 /* directed hyp dbells cause exit */ #define LPCR_PECE0 0x00004000 /* ext. exceptions can cause exit */ #define LPCR_PECE1 0x00002000 /* decrementer can cause exit */ #define LPCR_PECE2 0x00001000 /* machine check etc can cause exit */ @@ -322,6 +337,8 @@ #define SPRN_PCR 0x152 /* Processor compatibility register */ #define PCR_VEC_DIS (1ul << (63-0)) /* Vec. disable (bit NA since POWER8) */ #define PCR_VSX_DIS (1ul << (63-1)) /* VSX disable (bit NA since POWER8) */ +#define PCR_TM_DIS (1ul << (63-2)) /* Trans. memory disable (POWER8) */ +#define PCR_ARCH_206 0x4 /* Architecture 2.06 */ #define PCR_ARCH_205 0x2 /* Architecture 2.05 */ #define SPRN_HEIR 0x153 /* Hypervisor Emulated Instruction Register */ #define SPRN_TLBINDEXR 0x154 /* P7 TLB control register */ @@ -368,6 +385,8 @@ #define DER_EBRKE 0x00000002 /* External Breakpoint Interrupt */ #define DER_DPIE 0x00000001 /* Dev. Port Nonmaskable Request */ #define SPRN_DMISS 0x3D0 /* Data TLB Miss Register */ +#define SPRN_DHDES 0x0B1 /* Directed Hyp. Doorbell Exc. State */ +#define SPRN_DPDES 0x0B0 /* Directed Priv. Doorbell Exc. State */ #define SPRN_EAR 0x11A /* External Address Register */ #define SPRN_HASH1 0x3D2 /* Primary Hash Address Register */ #define SPRN_HASH2 0x3D3 /* Secondary Hash Address Resgister */ @@ -427,6 +446,7 @@ #define SPRN_IABR 0x3F2 /* Instruction Address Breakpoint Register */ #define SPRN_IABR2 0x3FA /* 83xx */ #define SPRN_IBCR 0x135 /* 83xx Insn Breakpoint Control Reg */ +#define SPRN_IAMR 0x03D /* Instr. Authority Mask Reg */ #define SPRN_HID4 0x3F4 /* 970 HID4 */ #define HID4_LPES0 (1ul << (63-0)) /* LPAR env. sel. bit 0 */ #define HID4_RMLS2_SH (63 - 2) /* Real mode limit bottom 2 bits */ @@ -541,6 +561,7 @@ #define SPRN_PIR 0x3FF /* Processor Identification Register */ #endif #define SPRN_TIR 0x1BE /* Thread Identification Register */ +#define SPRN_PSPB 0x09F /* Problem State Priority Boost reg */ #define SPRN_PTEHI 0x3D5 /* 981 7450 PTE HI word (S/W TLB load) */ #define SPRN_PTELO 0x3D6 /* 982 7450 PTE LO word (S/W TLB load) */ #define SPRN_PURR 0x135 /* Processor Utilization of Resources Reg */ @@ -682,6 +703,7 @@ #define SPRN_EBBHR 804 /* Event based branch handler register */ #define SPRN_EBBRR 805 /* Event based branch return register */ #define SPRN_BESCR 806 /* Branch event status and control register */ +#define SPRN_WORT 895 /* Workload optimization register - thread */ #define SPRN_PMC1 787 #define SPRN_PMC2 788 @@ -698,6 +720,11 @@ #define SIER_SIHV 0x1000000 /* Sampled MSR_HV */ #define SIER_SIAR_VALID 0x0400000 /* SIAR contents valid */ #define SIER_SDAR_VALID 0x0200000 /* SDAR contents valid */ +#define SPRN_TACR 888 +#define SPRN_TCSCR 889 +#define SPRN_CSIGR 890 +#define SPRN_SPMC1 892 +#define SPRN_SPMC2 893 /* When EBB is enabled, some of MMCR0/MMCR2/SIER are user accessible */ #define MMCR0_USER_MASK (MMCR0_FC | MMCR0_PMXE | MMCR0_PMAO) diff --git a/arch/powerpc/include/asm/switch_to.h b/arch/powerpc/include/asm/switch_to.h index aace9054761..0e83e7d8c73 100644 --- a/arch/powerpc/include/asm/switch_to.h +++ b/arch/powerpc/include/asm/switch_to.h @@ -25,10 +25,8 @@ static inline void save_tar(struct thread_struct *prev) static inline void save_tar(struct thread_struct *prev) {} #endif -extern void load_up_fpu(void); extern void enable_kernel_fp(void); extern void enable_kernel_altivec(void); -extern void load_up_altivec(struct task_struct *); extern int emulate_altivec(struct pt_regs *); extern void __giveup_vsx(struct task_struct *); extern void giveup_vsx(struct task_struct *); diff --git a/arch/powerpc/include/asm/systbl.h b/arch/powerpc/include/asm/systbl.h index 43523fe0d8b..3ddf7027670 100644 --- a/arch/powerpc/include/asm/systbl.h +++ b/arch/powerpc/include/asm/systbl.h @@ -359,3 +359,5 @@ COMPAT_SYS(process_vm_readv) COMPAT_SYS(process_vm_writev) SYSCALL(finit_module) SYSCALL(ni_syscall) /* sys_kcmp */ +SYSCALL_SPU(sched_setattr) +SYSCALL_SPU(sched_getattr) diff --git a/arch/powerpc/include/asm/unistd.h b/arch/powerpc/include/asm/unistd.h index 3ca819f541b..4494f029b63 100644 --- a/arch/powerpc/include/asm/unistd.h +++ b/arch/powerpc/include/asm/unistd.h @@ -12,7 +12,7 @@ #include <uapi/asm/unistd.h> -#define __NR_syscalls 355 +#define __NR_syscalls 357 #define __NR__exit __NR_exit #define NR_syscalls __NR_syscalls diff --git a/arch/powerpc/include/uapi/asm/kvm.h b/arch/powerpc/include/uapi/asm/kvm.h index 6836ec79a83..a6665be4f3a 100644 --- a/arch/powerpc/include/uapi/asm/kvm.h +++ b/arch/powerpc/include/uapi/asm/kvm.h @@ -545,6 +545,7 @@ struct kvm_get_htab_header { #define KVM_REG_PPC_TCSCR (KVM_REG_PPC | KVM_REG_SIZE_U64 | 0xb1) #define KVM_REG_PPC_PID (KVM_REG_PPC | KVM_REG_SIZE_U64 | 0xb2) #define KVM_REG_PPC_ACOP (KVM_REG_PPC | KVM_REG_SIZE_U64 | 0xb3) +#define KVM_REG_PPC_WORT (KVM_REG_PPC | KVM_REG_SIZE_U64 | 0xb4) #define KVM_REG_PPC_VRSAVE (KVM_REG_PPC | KVM_REG_SIZE_U32 | 0xb4) #define KVM_REG_PPC_LPCR (KVM_REG_PPC | KVM_REG_SIZE_U32 | 0xb5) @@ -553,6 +554,8 @@ struct kvm_get_htab_header { /* Architecture compatibility level */ #define KVM_REG_PPC_ARCH_COMPAT (KVM_REG_PPC | KVM_REG_SIZE_U32 | 0xb7) +#define KVM_REG_PPC_DABRX (KVM_REG_PPC | KVM_REG_SIZE_U32 | 0xb8) + /* Transactional Memory checkpointed state: * This is all GPRs, all VSX regs and a subset of SPRs */ diff --git a/arch/powerpc/include/uapi/asm/tm.h b/arch/powerpc/include/uapi/asm/tm.h index 85059a00f56..5d836b7c117 100644 --- a/arch/powerpc/include/uapi/asm/tm.h +++ b/arch/powerpc/include/uapi/asm/tm.h @@ -6,6 +6,8 @@ * the failure is persistent. PAPR saves 0xff-0xe0 for the hypervisor. */ #define TM_CAUSE_PERSISTENT 0x01 +#define TM_CAUSE_KVM_RESCHED 0xe0 /* From PAPR */ +#define TM_CAUSE_KVM_FAC_UNAV 0xe2 /* From PAPR */ #define TM_CAUSE_RESCHED 0xde #define TM_CAUSE_TLBI 0xdc #define TM_CAUSE_FAC_UNAV 0xda diff --git a/arch/powerpc/include/uapi/asm/unistd.h b/arch/powerpc/include/uapi/asm/unistd.h index 74cb4d72d67..881bf2e2560 100644 --- a/arch/powerpc/include/uapi/asm/unistd.h +++ b/arch/powerpc/include/uapi/asm/unistd.h @@ -377,6 +377,7 @@ #define __NR_process_vm_writev 352 #define __NR_finit_module 353 #define __NR_kcmp 354 - +#define __NR_sched_setattr 355 +#define __NR_sched_getattr 356 #endif /* _UAPI_ASM_POWERPC_UNISTD_H_ */ diff --git a/arch/powerpc/kernel/Makefile b/arch/powerpc/kernel/Makefile index 904d713366f..fcc9a89a469 100644 --- a/arch/powerpc/kernel/Makefile +++ b/arch/powerpc/kernel/Makefile @@ -48,7 +48,6 @@ obj-$(CONFIG_ALTIVEC) += vecemu.o obj-$(CONFIG_PPC_970_NAP) += idle_power4.o obj-$(CONFIG_PPC_P7_NAP) += idle_power7.o obj-$(CONFIG_PPC_OF) += of_platform.o prom_parse.o -obj-$(CONFIG_PPC_CLOCK) += clock.o procfs-y := proc_powerpc.o obj-$(CONFIG_PROC_FS) += $(procfs-y) rtaspci-$(CONFIG_PPC64)-$(CONFIG_PCI) := rtas_pci.o diff --git a/arch/powerpc/kernel/asm-offsets.c b/arch/powerpc/kernel/asm-offsets.c index 8d1d94d9c64..b5aacf72ae6 100644 --- a/arch/powerpc/kernel/asm-offsets.c +++ b/arch/powerpc/kernel/asm-offsets.c @@ -438,18 +438,14 @@ int main(void) DEFINE(VCPU_GUEST_PID, offsetof(struct kvm_vcpu, arch.pid)); DEFINE(VCPU_GPRS, offsetof(struct kvm_vcpu, arch.gpr)); DEFINE(VCPU_VRSAVE, offsetof(struct kvm_vcpu, arch.vrsave)); - DEFINE(VCPU_FPRS, offsetof(struct kvm_vcpu, arch.fpr)); - DEFINE(VCPU_FPSCR, offsetof(struct kvm_vcpu, arch.fpscr)); + DEFINE(VCPU_FPRS, offsetof(struct kvm_vcpu, arch.fp.fpr)); #ifdef CONFIG_ALTIVEC - DEFINE(VCPU_VRS, offsetof(struct kvm_vcpu, arch.vr)); - DEFINE(VCPU_VSCR, offsetof(struct kvm_vcpu, arch.vscr)); -#endif -#ifdef CONFIG_VSX - DEFINE(VCPU_VSRS, offsetof(struct kvm_vcpu, arch.vsr)); + DEFINE(VCPU_VRS, offsetof(struct kvm_vcpu, arch.vr.vr)); #endif DEFINE(VCPU_XER, offsetof(struct kvm_vcpu, arch.xer)); DEFINE(VCPU_CTR, offsetof(struct kvm_vcpu, arch.ctr)); DEFINE(VCPU_LR, offsetof(struct kvm_vcpu, arch.lr)); + DEFINE(VCPU_TAR, offsetof(struct kvm_vcpu, arch.tar)); DEFINE(VCPU_CR, offsetof(struct kvm_vcpu, arch.cr)); DEFINE(VCPU_PC, offsetof(struct kvm_vcpu, arch.pc)); #ifdef CONFIG_KVM_BOOK3S_HV_POSSIBLE @@ -497,16 +493,24 @@ int main(void) DEFINE(VCPU_DAR, offsetof(struct kvm_vcpu, arch.shregs.dar)); DEFINE(VCPU_VPA, offsetof(struct kvm_vcpu, arch.vpa.pinned_addr)); DEFINE(VCPU_VPA_DIRTY, offsetof(struct kvm_vcpu, arch.vpa.dirty)); + DEFINE(VCPU_INTR_MSR, offsetof(struct kvm_vcpu, arch.intr_msr)); #endif #ifdef CONFIG_PPC_BOOK3S DEFINE(VCPU_VCPUID, offsetof(struct kvm_vcpu, vcpu_id)); DEFINE(VCPU_PURR, offsetof(struct kvm_vcpu, arch.purr)); DEFINE(VCPU_SPURR, offsetof(struct kvm_vcpu, arch.spurr)); + DEFINE(VCPU_IC, offsetof(struct kvm_vcpu, arch.ic)); + DEFINE(VCPU_VTB, offsetof(struct kvm_vcpu, arch.vtb)); DEFINE(VCPU_DSCR, offsetof(struct kvm_vcpu, arch.dscr)); DEFINE(VCPU_AMR, offsetof(struct kvm_vcpu, arch.amr)); DEFINE(VCPU_UAMOR, offsetof(struct kvm_vcpu, arch.uamor)); + DEFINE(VCPU_IAMR, offsetof(struct kvm_vcpu, arch.iamr)); DEFINE(VCPU_CTRL, offsetof(struct kvm_vcpu, arch.ctrl)); DEFINE(VCPU_DABR, offsetof(struct kvm_vcpu, arch.dabr)); + DEFINE(VCPU_DABRX, offsetof(struct kvm_vcpu, arch.dabrx)); + DEFINE(VCPU_DAWR, offsetof(struct kvm_vcpu, arch.dawr)); + DEFINE(VCPU_DAWRX, offsetof(struct kvm_vcpu, arch.dawrx)); + DEFINE(VCPU_CIABR, offsetof(struct kvm_vcpu, arch.ciabr)); DEFINE(VCPU_HFLAGS, offsetof(struct kvm_vcpu, arch.hflags)); DEFINE(VCPU_DEC, offsetof(struct kvm_vcpu, arch.dec)); DEFINE(VCPU_DEC_EXPIRES, offsetof(struct kvm_vcpu, arch.dec_expires)); @@ -515,8 +519,10 @@ int main(void) DEFINE(VCPU_PRODDED, offsetof(struct kvm_vcpu, arch.prodded)); DEFINE(VCPU_MMCR, offsetof(struct kvm_vcpu, arch.mmcr)); DEFINE(VCPU_PMC, offsetof(struct kvm_vcpu, arch.pmc)); + DEFINE(VCPU_SPMC, offsetof(struct kvm_vcpu, arch.spmc)); DEFINE(VCPU_SIAR, offsetof(struct kvm_vcpu, arch.siar)); DEFINE(VCPU_SDAR, offsetof(struct kvm_vcpu, arch.sdar)); + DEFINE(VCPU_SIER, offsetof(struct kvm_vcpu, arch.sier)); DEFINE(VCPU_SLB, offsetof(struct kvm_vcpu, arch.slb)); DEFINE(VCPU_SLB_MAX, offsetof(struct kvm_vcpu, arch.slb_max)); DEFINE(VCPU_SLB_NR, offsetof(struct kvm_vcpu, arch.slb_nr)); @@ -524,20 +530,47 @@ int main(void) DEFINE(VCPU_FAULT_DAR, offsetof(struct kvm_vcpu, arch.fault_dar)); DEFINE(VCPU_LAST_INST, offsetof(struct kvm_vcpu, arch.last_inst)); DEFINE(VCPU_TRAP, offsetof(struct kvm_vcpu, arch.trap)); - DEFINE(VCPU_PTID, offsetof(struct kvm_vcpu, arch.ptid)); DEFINE(VCPU_CFAR, offsetof(struct kvm_vcpu, arch.cfar)); DEFINE(VCPU_PPR, offsetof(struct kvm_vcpu, arch.ppr)); + DEFINE(VCPU_FSCR, offsetof(struct kvm_vcpu, arch.fscr)); + DEFINE(VCPU_PSPB, offsetof(struct kvm_vcpu, arch.pspb)); + DEFINE(VCPU_EBBHR, offsetof(struct kvm_vcpu, arch.ebbhr)); + DEFINE(VCPU_EBBRR, offsetof(struct kvm_vcpu, arch.ebbrr)); + DEFINE(VCPU_BESCR, offsetof(struct kvm_vcpu, arch.bescr)); + DEFINE(VCPU_CSIGR, offsetof(struct kvm_vcpu, arch.csigr)); + DEFINE(VCPU_TACR, offsetof(struct kvm_vcpu, arch.tacr)); + DEFINE(VCPU_TCSCR, offsetof(struct kvm_vcpu, arch.tcscr)); + DEFINE(VCPU_ACOP, offsetof(struct kvm_vcpu, arch.acop)); + DEFINE(VCPU_WORT, offsetof(struct kvm_vcpu, arch.wort)); DEFINE(VCPU_SHADOW_SRR1, offsetof(struct kvm_vcpu, arch.shadow_srr1)); DEFINE(VCORE_ENTRY_EXIT, offsetof(struct kvmppc_vcore, entry_exit_count)); DEFINE(VCORE_NAP_COUNT, offsetof(struct kvmppc_vcore, nap_count)); DEFINE(VCORE_IN_GUEST, offsetof(struct kvmppc_vcore, in_guest)); DEFINE(VCORE_NAPPING_THREADS, offsetof(struct kvmppc_vcore, napping_threads)); + DEFINE(VCORE_KVM, offsetof(struct kvmppc_vcore, kvm)); DEFINE(VCORE_TB_OFFSET, offsetof(struct kvmppc_vcore, tb_offset)); DEFINE(VCORE_LPCR, offsetof(struct kvmppc_vcore, lpcr)); DEFINE(VCORE_PCR, offsetof(struct kvmppc_vcore, pcr)); + DEFINE(VCORE_DPDES, offsetof(struct kvmppc_vcore, dpdes)); DEFINE(VCPU_SLB_E, offsetof(struct kvmppc_slb, orige)); DEFINE(VCPU_SLB_V, offsetof(struct kvmppc_slb, origv)); DEFINE(VCPU_SLB_SIZE, sizeof(struct kvmppc_slb)); +#ifdef CONFIG_PPC_TRANSACTIONAL_MEM + DEFINE(VCPU_TFHAR, offsetof(struct kvm_vcpu, arch.tfhar)); + DEFINE(VCPU_TFIAR, offsetof(struct kvm_vcpu, arch.tfiar)); + DEFINE(VCPU_TEXASR, offsetof(struct kvm_vcpu, arch.texasr)); + DEFINE(VCPU_GPR_TM, offsetof(struct kvm_vcpu, arch.gpr_tm)); + DEFINE(VCPU_FPRS_TM, offsetof(struct kvm_vcpu, arch.fp_tm.fpr)); + DEFINE(VCPU_VRS_TM, offsetof(struct kvm_vcpu, arch.vr_tm.vr)); + DEFINE(VCPU_VRSAVE_TM, offsetof(struct kvm_vcpu, arch.vrsave_tm)); + DEFINE(VCPU_CR_TM, offsetof(struct kvm_vcpu, arch.cr_tm)); + DEFINE(VCPU_LR_TM, offsetof(struct kvm_vcpu, arch.lr_tm)); + DEFINE(VCPU_CTR_TM, offsetof(struct kvm_vcpu, arch.ctr_tm)); + DEFINE(VCPU_AMR_TM, offsetof(struct kvm_vcpu, arch.amr_tm)); + DEFINE(VCPU_PPR_TM, offsetof(struct kvm_vcpu, arch.ppr_tm)); + DEFINE(VCPU_DSCR_TM, offsetof(struct kvm_vcpu, arch.dscr_tm)); + DEFINE(VCPU_TAR_TM, offsetof(struct kvm_vcpu, arch.tar_tm)); +#endif #ifdef CONFIG_PPC_BOOK3S_64 #ifdef CONFIG_KVM_BOOK3S_PR_POSSIBLE @@ -602,6 +635,7 @@ int main(void) HSTATE_FIELD(HSTATE_XICS_PHYS, xics_phys); HSTATE_FIELD(HSTATE_SAVED_XIRR, saved_xirr); HSTATE_FIELD(HSTATE_HOST_IPI, host_ipi); + HSTATE_FIELD(HSTATE_PTID, ptid); HSTATE_FIELD(HSTATE_MMCR, host_mmcr); HSTATE_FIELD(HSTATE_PMC, host_pmc); HSTATE_FIELD(HSTATE_PURR, host_purr); diff --git a/arch/powerpc/kernel/cacheinfo.c b/arch/powerpc/kernel/cacheinfo.c index abfa011344d..2912b8787aa 100644 --- a/arch/powerpc/kernel/cacheinfo.c +++ b/arch/powerpc/kernel/cacheinfo.c @@ -793,6 +793,9 @@ static void remove_cache_dir(struct cache_dir *cache_dir) { remove_index_dirs(cache_dir); + /* Remove cache dir from sysfs */ + kobject_del(cache_dir->kobj); + kobject_put(cache_dir->kobj); kfree(cache_dir); diff --git a/arch/powerpc/kernel/clock.c b/arch/powerpc/kernel/clock.c deleted file mode 100644 index a764b47791e..00000000000 --- a/arch/powerpc/kernel/clock.c +++ /dev/null @@ -1,82 +0,0 @@ -/* - * Dummy clk implementations for powerpc. - * These need to be overridden in platform code. - */ - -#include <linux/clk.h> -#include <linux/err.h> -#include <linux/errno.h> -#include <linux/export.h> -#include <asm/clk_interface.h> - -struct clk_interface clk_functions; - -struct clk *clk_get(struct device *dev, const char *id) -{ - if (clk_functions.clk_get) - return clk_functions.clk_get(dev, id); - return ERR_PTR(-ENOSYS); -} -EXPORT_SYMBOL(clk_get); - -void clk_put(struct clk *clk) -{ - if (clk_functions.clk_put) - clk_functions.clk_put(clk); -} -EXPORT_SYMBOL(clk_put); - -int clk_enable(struct clk *clk) -{ - if (clk_functions.clk_enable) - return clk_functions.clk_enable(clk); - return -ENOSYS; -} -EXPORT_SYMBOL(clk_enable); - -void clk_disable(struct clk *clk) -{ - if (clk_functions.clk_disable) - clk_functions.clk_disable(clk); -} -EXPORT_SYMBOL(clk_disable); - -unsigned long clk_get_rate(struct clk *clk) -{ - if (clk_functions.clk_get_rate) - return clk_functions.clk_get_rate(clk); - return 0; -} -EXPORT_SYMBOL(clk_get_rate); - -long clk_round_rate(struct clk *clk, unsigned long rate) -{ - if (clk_functions.clk_round_rate) - return clk_functions.clk_round_rate(clk, rate); - return -ENOSYS; -} -EXPORT_SYMBOL(clk_round_rate); - -int clk_set_rate(struct clk *clk, unsigned long rate) -{ - if (clk_functions.clk_set_rate) - return clk_functions.clk_set_rate(clk, rate); - return -ENOSYS; -} -EXPORT_SYMBOL(clk_set_rate); - -struct clk *clk_get_parent(struct clk *clk) -{ - if (clk_functions.clk_get_parent) - return clk_functions.clk_get_parent(clk); - return ERR_PTR(-ENOSYS); -} -EXPORT_SYMBOL(clk_get_parent); - -int clk_set_parent(struct clk *clk, struct clk *parent) -{ - if (clk_functions.clk_set_parent) - return clk_functions.clk_set_parent(clk, parent); - return -ENOSYS; -} -EXPORT_SYMBOL(clk_set_parent); diff --git a/arch/powerpc/kernel/kvm.c b/arch/powerpc/kernel/kvm.c index db28032e320..6a0175297b0 100644 --- a/arch/powerpc/kernel/kvm.c +++ b/arch/powerpc/kernel/kvm.c @@ -413,13 +413,13 @@ static void kvm_map_magic_page(void *data) { u32 *features = data; - ulong in[8]; + ulong in[8] = {0}; ulong out[8]; in[0] = KVM_MAGIC_PAGE; in[1] = KVM_MAGIC_PAGE; - kvm_hypercall(in, out, KVM_HCALL_TOKEN(KVM_HC_PPC_MAP_MAGIC_PAGE)); + epapr_hypercall(in, out, KVM_HCALL_TOKEN(KVM_HC_PPC_MAP_MAGIC_PAGE)); *features = out[0]; } @@ -711,43 +711,6 @@ static void kvm_use_magic_page(void) kvm_patching_worked ? "worked" : "failed"); } -unsigned long kvm_hypercall(unsigned long *in, - unsigned long *out, - unsigned long nr) -{ - unsigned long register r0 asm("r0"); - unsigned long register r3 asm("r3") = in[0]; - unsigned long register r4 asm("r4") = in[1]; - unsigned long register r5 asm("r5") = in[2]; - unsigned long register r6 asm("r6") = in[3]; - unsigned long register r7 asm("r7") = in[4]; - unsigned long register r8 asm("r8") = in[5]; - unsigned long register r9 asm("r9") = in[6]; - unsigned long register r10 asm("r10") = in[7]; - unsigned long register r11 asm("r11") = nr; - unsigned long register r12 asm("r12"); - - asm volatile("bl epapr_hypercall_start" - : "=r"(r0), "=r"(r3), "=r"(r4), "=r"(r5), "=r"(r6), - "=r"(r7), "=r"(r8), "=r"(r9), "=r"(r10), "=r"(r11), - "=r"(r12) - : "r"(r3), "r"(r4), "r"(r5), "r"(r6), "r"(r7), "r"(r8), - "r"(r9), "r"(r10), "r"(r11) - : "memory", "cc", "xer", "ctr", "lr"); - - out[0] = r4; - out[1] = r5; - out[2] = r6; - out[3] = r7; - out[4] = r8; - out[5] = r9; - out[6] = r10; - out[7] = r11; - - return r3; -} -EXPORT_SYMBOL_GPL(kvm_hypercall); - static __init void kvm_free_tmp(void) { free_reserved_area(&kvm_tmp[kvm_tmp_index], diff --git a/arch/powerpc/kernel/process.c b/arch/powerpc/kernel/process.c index 64b7a6e61dd..8d4c247f173 100644 --- a/arch/powerpc/kernel/process.c +++ b/arch/powerpc/kernel/process.c @@ -811,7 +811,7 @@ struct task_struct *__switch_to(struct task_struct *prev, * schedule DABR */ #ifndef CONFIG_HAVE_HW_BREAKPOINT - if (unlikely(hw_brk_match(&__get_cpu_var(current_brk), &new->thread.hw_brk))) + if (unlikely(!hw_brk_match(&__get_cpu_var(current_brk), &new->thread.hw_brk))) set_breakpoint(&new->thread.hw_brk); #endif /* CONFIG_HAVE_HW_BREAKPOINT */ #endif diff --git a/arch/powerpc/kernel/signal_32.c b/arch/powerpc/kernel/signal_32.c index 6ce69e6f1fc..a67e00aa3ca 100644 --- a/arch/powerpc/kernel/signal_32.c +++ b/arch/powerpc/kernel/signal_32.c @@ -1022,29 +1022,24 @@ int handle_rt_signal32(unsigned long sig, struct k_sigaction *ka, #ifdef CONFIG_PPC_TRANSACTIONAL_MEM tm_frame = &rt_sf->uc_transact.uc_mcontext; if (MSR_TM_ACTIVE(regs->msr)) { + if (__put_user((unsigned long)&rt_sf->uc_transact, + &rt_sf->uc.uc_link) || + __put_user((unsigned long)tm_frame, + &rt_sf->uc_transact.uc_regs)) + goto badframe; if (save_tm_user_regs(regs, frame, tm_frame, sigret)) goto badframe; } else #endif { + if (__put_user(0, &rt_sf->uc.uc_link)) + goto badframe; if (save_user_regs(regs, frame, tm_frame, sigret, 1)) goto badframe; } regs->link = tramp; -#ifdef CONFIG_PPC_TRANSACTIONAL_MEM - if (MSR_TM_ACTIVE(regs->msr)) { - if (__put_user((unsigned long)&rt_sf->uc_transact, - &rt_sf->uc.uc_link) - || __put_user((unsigned long)tm_frame, &rt_sf->uc_transact.uc_regs)) - goto badframe; - } - else -#endif - if (__put_user(0, &rt_sf->uc.uc_link)) - goto badframe; - current->thread.fp_state.fpscr = 0; /* turn off all fp exceptions */ /* create a stack frame for the caller of the handler */ diff --git a/arch/powerpc/kernel/sysfs.c b/arch/powerpc/kernel/sysfs.c index d4a43e64a6a..97e1dc91768 100644 --- a/arch/powerpc/kernel/sysfs.c +++ b/arch/powerpc/kernel/sysfs.c @@ -51,8 +51,6 @@ static ssize_t store_smt_snooze_delay(struct device *dev, return -EINVAL; per_cpu(smt_snooze_delay, cpu->dev.id) = snooze; - update_smt_snooze_delay(cpu->dev.id, snooze); - return count; } diff --git a/arch/powerpc/kvm/44x.c b/arch/powerpc/kvm/44x.c index 93221e87b91..9cb4b0a3603 100644 --- a/arch/powerpc/kvm/44x.c +++ b/arch/powerpc/kvm/44x.c @@ -21,6 +21,8 @@ #include <linux/slab.h> #include <linux/err.h> #include <linux/export.h> +#include <linux/module.h> +#include <linux/miscdevice.h> #include <asm/reg.h> #include <asm/cputable.h> @@ -231,3 +233,5 @@ static void __exit kvmppc_44x_exit(void) module_init(kvmppc_44x_init); module_exit(kvmppc_44x_exit); +MODULE_ALIAS_MISCDEV(KVM_MINOR); +MODULE_ALIAS("devname:kvm"); diff --git a/arch/powerpc/kvm/book3s.c b/arch/powerpc/kvm/book3s.c index 8912608b7e1..94e597e6f15 100644 --- a/arch/powerpc/kvm/book3s.c +++ b/arch/powerpc/kvm/book3s.c @@ -18,6 +18,8 @@ #include <linux/err.h> #include <linux/export.h> #include <linux/slab.h> +#include <linux/module.h> +#include <linux/miscdevice.h> #include <asm/reg.h> #include <asm/cputable.h> @@ -575,10 +577,10 @@ int kvm_vcpu_ioctl_get_one_reg(struct kvm_vcpu *vcpu, struct kvm_one_reg *reg) break; case KVM_REG_PPC_FPR0 ... KVM_REG_PPC_FPR31: i = reg->id - KVM_REG_PPC_FPR0; - val = get_reg_val(reg->id, vcpu->arch.fpr[i]); + val = get_reg_val(reg->id, VCPU_FPR(vcpu, i)); break; case KVM_REG_PPC_FPSCR: - val = get_reg_val(reg->id, vcpu->arch.fpscr); + val = get_reg_val(reg->id, vcpu->arch.fp.fpscr); break; #ifdef CONFIG_ALTIVEC case KVM_REG_PPC_VR0 ... KVM_REG_PPC_VR31: @@ -586,19 +588,30 @@ int kvm_vcpu_ioctl_get_one_reg(struct kvm_vcpu *vcpu, struct kvm_one_reg *reg) r = -ENXIO; break; } - val.vval = vcpu->arch.vr[reg->id - KVM_REG_PPC_VR0]; + val.vval = vcpu->arch.vr.vr[reg->id - KVM_REG_PPC_VR0]; break; case KVM_REG_PPC_VSCR: if (!cpu_has_feature(CPU_FTR_ALTIVEC)) { r = -ENXIO; break; } - val = get_reg_val(reg->id, vcpu->arch.vscr.u[3]); + val = get_reg_val(reg->id, vcpu->arch.vr.vscr.u[3]); break; case KVM_REG_PPC_VRSAVE: val = get_reg_val(reg->id, vcpu->arch.vrsave); break; #endif /* CONFIG_ALTIVEC */ +#ifdef CONFIG_VSX + case KVM_REG_PPC_VSR0 ... KVM_REG_PPC_VSR31: + if (cpu_has_feature(CPU_FTR_VSX)) { + long int i = reg->id - KVM_REG_PPC_VSR0; + val.vsxval[0] = vcpu->arch.fp.fpr[i][0]; + val.vsxval[1] = vcpu->arch.fp.fpr[i][1]; + } else { + r = -ENXIO; + } + break; +#endif /* CONFIG_VSX */ case KVM_REG_PPC_DEBUG_INST: { u32 opcode = INS_TW; r = copy_to_user((u32 __user *)(long)reg->addr, @@ -654,10 +667,10 @@ int kvm_vcpu_ioctl_set_one_reg(struct kvm_vcpu *vcpu, struct kvm_one_reg *reg) break; case KVM_REG_PPC_FPR0 ... KVM_REG_PPC_FPR31: i = reg->id - KVM_REG_PPC_FPR0; - vcpu->arch.fpr[i] = set_reg_val(reg->id, val); + VCPU_FPR(vcpu, i) = set_reg_val(reg->id, val); break; case KVM_REG_PPC_FPSCR: - vcpu->arch.fpscr = set_reg_val(reg->id, val); + vcpu->arch.fp.fpscr = set_reg_val(reg->id, val); break; #ifdef CONFIG_ALTIVEC case KVM_REG_PPC_VR0 ... KVM_REG_PPC_VR31: @@ -665,14 +678,14 @@ int kvm_vcpu_ioctl_set_one_reg(struct kvm_vcpu *vcpu, struct kvm_one_reg *reg) r = -ENXIO; break; } - vcpu->arch.vr[reg->id - KVM_REG_PPC_VR0] = val.vval; + vcpu->arch.vr.vr[reg->id - KVM_REG_PPC_VR0] = val.vval; break; case KVM_REG_PPC_VSCR: if (!cpu_has_feature(CPU_FTR_ALTIVEC)) { r = -ENXIO; break; } - vcpu->arch.vscr.u[3] = set_reg_val(reg->id, val); + vcpu->arch.vr.vscr.u[3] = set_reg_val(reg->id, val); break; case KVM_REG_PPC_VRSAVE: if (!cpu_has_feature(CPU_FTR_ALTIVEC)) { @@ -682,6 +695,17 @@ int kvm_vcpu_ioctl_set_one_reg(struct kvm_vcpu *vcpu, struct kvm_one_reg *reg) vcpu->arch.vrsave = set_reg_val(reg->id, val); break; #endif /* CONFIG_ALTIVEC */ +#ifdef CONFIG_VSX + case KVM_REG_PPC_VSR0 ... KVM_REG_PPC_VSR31: + if (cpu_has_feature(CPU_FTR_VSX)) { + long int i = reg->id - KVM_REG_PPC_VSR0; + vcpu->arch.fp.fpr[i][0] = val.vsxval[0]; + vcpu->arch.fp.fpr[i][1] = val.vsxval[1]; + } else { + r = -ENXIO; + } + break; +#endif /* CONFIG_VSX */ #ifdef CONFIG_KVM_XICS case KVM_REG_PPC_ICP_STATE: if (!vcpu->arch.icp) { @@ -879,3 +903,9 @@ static void kvmppc_book3s_exit(void) module_init(kvmppc_book3s_init); module_exit(kvmppc_book3s_exit); + +/* On 32bit this is our one and only kernel module */ +#ifdef CONFIG_KVM_BOOK3S_32 +MODULE_ALIAS_MISCDEV(KVM_MINOR); +MODULE_ALIAS("devname:kvm"); +#endif diff --git a/arch/powerpc/kvm/book3s_32_mmu_host.c b/arch/powerpc/kvm/book3s_32_mmu_host.c index 3a0abd2e5a1..5fac89dfe4c 100644 --- a/arch/powerpc/kvm/book3s_32_mmu_host.c +++ b/arch/powerpc/kvm/book3s_32_mmu_host.c @@ -243,6 +243,11 @@ next_pteg: /* Now tell our Shadow PTE code about the new page */ pte = kvmppc_mmu_hpte_cache_next(vcpu); + if (!pte) { + kvm_release_pfn_clean(hpaddr >> PAGE_SHIFT); + r = -EAGAIN; + goto out; + } dprintk_mmu("KVM: %c%c Map 0x%llx: [%lx] 0x%llx (0x%llx) -> %lx\n", orig_pte->may_write ? 'w' : '-', diff --git a/arch/powerpc/kvm/book3s_64_mmu_hv.c b/arch/powerpc/kvm/book3s_64_mmu_hv.c index c5d148434c0..303ece75b8e 100644 --- a/arch/powerpc/kvm/book3s_64_mmu_hv.c +++ b/arch/powerpc/kvm/book3s_64_mmu_hv.c @@ -262,7 +262,7 @@ int kvmppc_mmu_hv_init(void) static void kvmppc_mmu_book3s_64_hv_reset_msr(struct kvm_vcpu *vcpu) { - kvmppc_set_msr(vcpu, MSR_SF | MSR_ME); + kvmppc_set_msr(vcpu, vcpu->arch.intr_msr); } /* @@ -562,7 +562,7 @@ static int kvmppc_hv_emulate_mmio(struct kvm_run *run, struct kvm_vcpu *vcpu, * we just return and retry the instruction. */ - if (instruction_is_store(vcpu->arch.last_inst) != !!is_store) + if (instruction_is_store(kvmppc_get_last_inst(vcpu)) != !!is_store) return RESUME_GUEST; /* diff --git a/arch/powerpc/kvm/book3s_exports.c b/arch/powerpc/kvm/book3s_exports.c index 852989a9bad..20d4ea8e656 100644 --- a/arch/powerpc/kvm/book3s_exports.c +++ b/arch/powerpc/kvm/book3s_exports.c @@ -25,9 +25,5 @@ EXPORT_SYMBOL_GPL(kvmppc_hv_entry_trampoline); #endif #ifdef CONFIG_KVM_BOOK3S_PR_POSSIBLE EXPORT_SYMBOL_GPL(kvmppc_entry_trampoline); -EXPORT_SYMBOL_GPL(kvmppc_load_up_fpu); -#ifdef CONFIG_ALTIVEC -EXPORT_SYMBOL_GPL(kvmppc_load_up_altivec); -#endif #endif diff --git a/arch/powerpc/kvm/book3s_hv.c b/arch/powerpc/kvm/book3s_hv.c index 3818bd95327..17fc9496b6a 100644 --- a/arch/powerpc/kvm/book3s_hv.c +++ b/arch/powerpc/kvm/book3s_hv.c @@ -31,6 +31,7 @@ #include <linux/spinlock.h> #include <linux/page-flags.h> #include <linux/srcu.h> +#include <linux/miscdevice.h> #include <asm/reg.h> #include <asm/cputable.h> @@ -85,10 +86,13 @@ static void kvmppc_fast_vcpu_kick_hv(struct kvm_vcpu *vcpu) /* CPU points to the first thread of the core */ if (cpu != me && cpu >= 0 && cpu < nr_cpu_ids) { +#ifdef CONFIG_KVM_XICS int real_cpu = cpu + vcpu->arch.ptid; if (paca[real_cpu].kvm_hstate.xics_phys) xics_wake_cpu(real_cpu); - else if (cpu_online(cpu)) + else +#endif + if (cpu_online(cpu)) smp_send_reschedule(cpu); } put_cpu(); @@ -182,14 +186,28 @@ int kvmppc_set_arch_compat(struct kvm_vcpu *vcpu, u32 arch_compat) switch (arch_compat) { case PVR_ARCH_205: - pcr = PCR_ARCH_205; + /* + * If an arch bit is set in PCR, all the defined + * higher-order arch bits also have to be set. + */ + pcr = PCR_ARCH_206 | PCR_ARCH_205; break; case PVR_ARCH_206: case PVR_ARCH_206p: + pcr = PCR_ARCH_206; + break; + case PVR_ARCH_207: break; default: return -EINVAL; } + + if (!cpu_has_feature(CPU_FTR_ARCH_207S)) { + /* POWER7 can't emulate POWER8 */ + if (!(pcr & PCR_ARCH_206)) + return -EINVAL; + pcr &= ~PCR_ARCH_206; + } } spin_lock(&vc->lock); @@ -637,6 +655,7 @@ static int kvmppc_handle_exit_hv(struct kvm_run *run, struct kvm_vcpu *vcpu, r = RESUME_GUEST; break; case BOOK3S_INTERRUPT_EXTERNAL: + case BOOK3S_INTERRUPT_H_DOORBELL: vcpu->stat.ext_intr_exits++; r = RESUME_GUEST; break; @@ -673,12 +692,10 @@ static int kvmppc_handle_exit_hv(struct kvm_run *run, struct kvm_vcpu *vcpu, /* hcall - punt to userspace */ int i; - if (vcpu->arch.shregs.msr & MSR_PR) { - /* sc 1 from userspace - reflect to guest syscall */ - kvmppc_book3s_queue_irqprio(vcpu, BOOK3S_INTERRUPT_SYSCALL); - r = RESUME_GUEST; - break; - } + /* hypercall with MSR_PR has already been handled in rmode, + * and never reaches here. + */ + run->papr_hcall.nr = kvmppc_get_gpr(vcpu, 3); for (i = 0; i < 9; ++i) run->papr_hcall.args[i] = kvmppc_get_gpr(vcpu, 4 + i); @@ -708,7 +725,16 @@ static int kvmppc_handle_exit_hv(struct kvm_run *run, struct kvm_vcpu *vcpu, * we don't emulate any guest instructions at this stage. */ case BOOK3S_INTERRUPT_H_EMUL_ASSIST: - kvmppc_core_queue_program(vcpu, 0x80000); + kvmppc_core_queue_program(vcpu, SRR1_PROGILL); + r = RESUME_GUEST; + break; + /* + * This occurs if the guest (kernel or userspace), does something that + * is prohibited by HFSCR. We just generate a program interrupt to + * the guest. + */ + case BOOK3S_INTERRUPT_H_FAC_UNAVAIL: + kvmppc_core_queue_program(vcpu, SRR1_PROGILL); r = RESUME_GUEST; break; default: @@ -766,10 +792,34 @@ static void kvmppc_set_lpcr(struct kvm_vcpu *vcpu, u64 new_lpcr) spin_lock(&vc->lock); /* + * If ILE (interrupt little-endian) has changed, update the + * MSR_LE bit in the intr_msr for each vcpu in this vcore. + */ + if ((new_lpcr & LPCR_ILE) != (vc->lpcr & LPCR_ILE)) { + struct kvm *kvm = vcpu->kvm; + struct kvm_vcpu *vcpu; + int i; + + mutex_lock(&kvm->lock); + kvm_for_each_vcpu(i, vcpu, kvm) { + if (vcpu->arch.vcore != vc) + continue; + if (new_lpcr & LPCR_ILE) + vcpu->arch.intr_msr |= MSR_LE; + else + vcpu->arch.intr_msr &= ~MSR_LE; + } + mutex_unlock(&kvm->lock); + } + + /* * Userspace can only modify DPFD (default prefetch depth), * ILE (interrupt little-endian) and TC (translation control). + * On POWER8 userspace can also modify AIL (alt. interrupt loc.) */ mask = LPCR_DPFD | LPCR_ILE | LPCR_TC; + if (cpu_has_feature(CPU_FTR_ARCH_207S)) + mask |= LPCR_AIL; vc->lpcr = (vc->lpcr & ~mask) | (new_lpcr & mask); spin_unlock(&vc->lock); } @@ -787,6 +837,9 @@ static int kvmppc_get_one_reg_hv(struct kvm_vcpu *vcpu, u64 id, case KVM_REG_PPC_DABR: *val = get_reg_val(id, vcpu->arch.dabr); break; + case KVM_REG_PPC_DABRX: + *val = get_reg_val(id, vcpu->arch.dabrx); + break; case KVM_REG_PPC_DSCR: *val = get_reg_val(id, vcpu->arch.dscr); break; @@ -802,7 +855,7 @@ static int kvmppc_get_one_reg_hv(struct kvm_vcpu *vcpu, u64 id, case KVM_REG_PPC_UAMOR: *val = get_reg_val(id, vcpu->arch.uamor); break; - case KVM_REG_PPC_MMCR0 ... KVM_REG_PPC_MMCRA: + case KVM_REG_PPC_MMCR0 ... KVM_REG_PPC_MMCRS: i = id - KVM_REG_PPC_MMCR0; *val = get_reg_val(id, vcpu->arch.mmcr[i]); break; @@ -810,33 +863,87 @@ static int kvmppc_get_one_reg_hv(struct kvm_vcpu *vcpu, u64 id, i = id - KVM_REG_PPC_PMC1; *val = get_reg_val(id, vcpu->arch.pmc[i]); break; + case KVM_REG_PPC_SPMC1 ... KVM_REG_PPC_SPMC2: + i = id - KVM_REG_PPC_SPMC1; + *val = get_reg_val(id, vcpu->arch.spmc[i]); + break; case KVM_REG_PPC_SIAR: *val = get_reg_val(id, vcpu->arch.siar); break; case KVM_REG_PPC_SDAR: *val = get_reg_val(id, vcpu->arch.sdar); break; -#ifdef CONFIG_VSX - case KVM_REG_PPC_FPR0 ... KVM_REG_PPC_FPR31: - if (cpu_has_feature(CPU_FTR_VSX)) { - /* VSX => FP reg i is stored in arch.vsr[2*i] */ - long int i = id - KVM_REG_PPC_FPR0; - *val = get_reg_val(id, vcpu->arch.vsr[2 * i]); - } else { - /* let generic code handle it */ - r = -EINVAL; - } + case KVM_REG_PPC_SIER: + *val = get_reg_val(id, vcpu->arch.sier); break; - case KVM_REG_PPC_VSR0 ... KVM_REG_PPC_VSR31: - if (cpu_has_feature(CPU_FTR_VSX)) { - long int i = id - KVM_REG_PPC_VSR0; - val->vsxval[0] = vcpu->arch.vsr[2 * i]; - val->vsxval[1] = vcpu->arch.vsr[2 * i + 1]; - } else { - r = -ENXIO; - } + case KVM_REG_PPC_IAMR: + *val = get_reg_val(id, vcpu->arch.iamr); + break; +#ifdef CONFIG_PPC_TRANSACTIONAL_MEM + case KVM_REG_PPC_TFHAR: + *val = get_reg_val(id, vcpu->arch.tfhar); + break; + case KVM_REG_PPC_TFIAR: + *val = get_reg_val(id, vcpu->arch.tfiar); + break; + case KVM_REG_PPC_TEXASR: + *val = get_reg_val(id, vcpu->arch.texasr); + break; +#endif + case KVM_REG_PPC_FSCR: + *val = get_reg_val(id, vcpu->arch.fscr); + break; + case KVM_REG_PPC_PSPB: + *val = get_reg_val(id, vcpu->arch.pspb); + break; + case KVM_REG_PPC_EBBHR: + *val = get_reg_val(id, vcpu->arch.ebbhr); + break; + case KVM_REG_PPC_EBBRR: + *val = get_reg_val(id, vcpu->arch.ebbrr); + break; + case KVM_REG_PPC_BESCR: + *val = get_reg_val(id, vcpu->arch.bescr); + break; + case KVM_REG_PPC_TAR: + *val = get_reg_val(id, vcpu->arch.tar); + break; + case KVM_REG_PPC_DPDES: + *val = get_reg_val(id, vcpu->arch.vcore->dpdes); + break; + case KVM_REG_PPC_DAWR: + *val = get_reg_val(id, vcpu->arch.dawr); + break; + case KVM_REG_PPC_DAWRX: + *val = get_reg_val(id, vcpu->arch.dawrx); + break; + case KVM_REG_PPC_CIABR: + *val = get_reg_val(id, vcpu->arch.ciabr); + break; + case KVM_REG_PPC_IC: + *val = get_reg_val(id, vcpu->arch.ic); + break; + case KVM_REG_PPC_VTB: + *val = get_reg_val(id, vcpu->arch.vtb); + break; + case KVM_REG_PPC_CSIGR: + *val = get_reg_val(id, vcpu->arch.csigr); + break; + case KVM_REG_PPC_TACR: + *val = get_reg_val(id, vcpu->arch.tacr); + break; + case KVM_REG_PPC_TCSCR: + *val = get_reg_val(id, vcpu->arch.tcscr); + break; + case KVM_REG_PPC_PID: + *val = get_reg_val(id, vcpu->arch.pid); + break; + case KVM_REG_PPC_ACOP: + *val = get_reg_val(id, vcpu->arch.acop); + break; + case KVM_REG_PPC_WORT: + *val = get_reg_val(id, vcpu->arch.wort); break; -#endif /* CONFIG_VSX */ case KVM_REG_PPC_VPA_ADDR: spin_lock(&vcpu->arch.vpa_update_lock); *val = get_reg_val(id, vcpu->arch.vpa.next_gpa); @@ -890,6 +997,9 @@ static int kvmppc_set_one_reg_hv(struct kvm_vcpu *vcpu, u64 id, case KVM_REG_PPC_DABR: vcpu->arch.dabr = set_reg_val(id, *val); break; + case KVM_REG_PPC_DABRX: + vcpu->arch.dabrx = set_reg_val(id, *val) & ~DABRX_HYP; + break; case KVM_REG_PPC_DSCR: vcpu->arch.dscr = set_reg_val(id, *val); break; @@ -905,7 +1015,7 @@ static int kvmppc_set_one_reg_hv(struct kvm_vcpu *vcpu, u64 id, case KVM_REG_PPC_UAMOR: vcpu->arch.uamor = set_reg_val(id, *val); break; - case KVM_REG_PPC_MMCR0 ... KVM_REG_PPC_MMCRA: + case KVM_REG_PPC_MMCR0 ... KVM_REG_PPC_MMCRS: i = id - KVM_REG_PPC_MMCR0; vcpu->arch.mmcr[i] = set_reg_val(id, *val); break; @@ -913,33 +1023,90 @@ static int kvmppc_set_one_reg_hv(struct kvm_vcpu *vcpu, u64 id, i = id - KVM_REG_PPC_PMC1; vcpu->arch.pmc[i] = set_reg_val(id, *val); break; + case KVM_REG_PPC_SPMC1 ... KVM_REG_PPC_SPMC2: + i = id - KVM_REG_PPC_SPMC1; + vcpu->arch.spmc[i] = set_reg_val(id, *val); + break; case KVM_REG_PPC_SIAR: vcpu->arch.siar = set_reg_val(id, *val); break; case KVM_REG_PPC_SDAR: vcpu->arch.sdar = set_reg_val(id, *val); break; -#ifdef CONFIG_VSX - case KVM_REG_PPC_FPR0 ... KVM_REG_PPC_FPR31: - if (cpu_has_feature(CPU_FTR_VSX)) { - /* VSX => FP reg i is stored in arch.vsr[2*i] */ - long int i = id - KVM_REG_PPC_FPR0; - vcpu->arch.vsr[2 * i] = set_reg_val(id, *val); - } else { - /* let generic code handle it */ - r = -EINVAL; - } + case KVM_REG_PPC_SIER: + vcpu->arch.sier = set_reg_val(id, *val); break; - case KVM_REG_PPC_VSR0 ... KVM_REG_PPC_VSR31: - if (cpu_has_feature(CPU_FTR_VSX)) { - long int i = id - KVM_REG_PPC_VSR0; - vcpu->arch.vsr[2 * i] = val->vsxval[0]; - vcpu->arch.vsr[2 * i + 1] = val->vsxval[1]; - } else { - r = -ENXIO; - } + case KVM_REG_PPC_IAMR: + vcpu->arch.iamr = set_reg_val(id, *val); + break; +#ifdef CONFIG_PPC_TRANSACTIONAL_MEM + case KVM_REG_PPC_TFHAR: + vcpu->arch.tfhar = set_reg_val(id, *val); + break; + case KVM_REG_PPC_TFIAR: + vcpu->arch.tfiar = set_reg_val(id, *val); + break; + case KVM_REG_PPC_TEXASR: + vcpu->arch.texasr = set_reg_val(id, *val); + break; +#endif + case KVM_REG_PPC_FSCR: + vcpu->arch.fscr = set_reg_val(id, *val); + break; + case KVM_REG_PPC_PSPB: + vcpu->arch.pspb = set_reg_val(id, *val); + break; + case KVM_REG_PPC_EBBHR: + vcpu->arch.ebbhr = set_reg_val(id, *val); + break; + case KVM_REG_PPC_EBBRR: + vcpu->arch.ebbrr = set_reg_val(id, *val); + break; + case KVM_REG_PPC_BESCR: + vcpu->arch.bescr = set_reg_val(id, *val); + break; + case KVM_REG_PPC_TAR: + vcpu->arch.tar = set_reg_val(id, *val); + break; + case KVM_REG_PPC_DPDES: + vcpu->arch.vcore->dpdes = set_reg_val(id, *val); + break; + case KVM_REG_PPC_DAWR: + vcpu->arch.dawr = set_reg_val(id, *val); + break; + case KVM_REG_PPC_DAWRX: + vcpu->arch.dawrx = set_reg_val(id, *val) & ~DAWRX_HYP; + break; + case KVM_REG_PPC_CIABR: + vcpu->arch.ciabr = set_reg_val(id, *val); + /* Don't allow setting breakpoints in hypervisor code */ + if ((vcpu->arch.ciabr & CIABR_PRIV) == CIABR_PRIV_HYPER) + vcpu->arch.ciabr &= ~CIABR_PRIV; /* disable */ + break; + case KVM_REG_PPC_IC: + vcpu->arch.ic = set_reg_val(id, *val); + break; + case KVM_REG_PPC_VTB: + vcpu->arch.vtb = set_reg_val(id, *val); + break; + case KVM_REG_PPC_CSIGR: + vcpu->arch.csigr = set_reg_val(id, *val); + break; + case KVM_REG_PPC_TACR: + vcpu->arch.tacr = set_reg_val(id, *val); + break; + case KVM_REG_PPC_TCSCR: + vcpu->arch.tcscr = set_reg_val(id, *val); + break; + case KVM_REG_PPC_PID: + vcpu->arch.pid = set_reg_val(id, *val); + break; + case KVM_REG_PPC_ACOP: + vcpu->arch.acop = set_reg_val(id, *val); + break; + case KVM_REG_PPC_WORT: + vcpu->arch.wort = set_reg_val(id, *val); break; -#endif /* CONFIG_VSX */ case KVM_REG_PPC_VPA_ADDR: addr = set_reg_val(id, *val); r = -EINVAL; @@ -1017,6 +1184,7 @@ static struct kvm_vcpu *kvmppc_core_vcpu_create_hv(struct kvm *kvm, spin_lock_init(&vcpu->arch.vpa_update_lock); spin_lock_init(&vcpu->arch.tbacct_lock); vcpu->arch.busy_preempt = TB_NIL; + vcpu->arch.intr_msr = MSR_SF | MSR_ME; kvmppc_mmu_book3s_hv_init(vcpu); @@ -1034,6 +1202,8 @@ static struct kvm_vcpu *kvmppc_core_vcpu_create_hv(struct kvm *kvm, init_waitqueue_head(&vcore->wq); vcore->preempt_tb = TB_NIL; vcore->lpcr = kvm->arch.lpcr; + vcore->first_vcpuid = core * threads_per_core; + vcore->kvm = kvm; } kvm->arch.vcores[core] = vcore; kvm->arch.online_vcores++; @@ -1047,6 +1217,7 @@ static struct kvm_vcpu *kvmppc_core_vcpu_create_hv(struct kvm *kvm, ++vcore->num_threads; spin_unlock(&vcore->lock); vcpu->arch.vcore = vcore; + vcpu->arch.ptid = vcpu->vcpu_id - vcore->first_vcpuid; vcpu->arch.cpu_type = KVM_CPU_3S_64; kvmppc_sanity_check(vcpu); @@ -1110,7 +1281,7 @@ static void kvmppc_end_cede(struct kvm_vcpu *vcpu) } } -extern int __kvmppc_vcore_entry(struct kvm_run *kvm_run, struct kvm_vcpu *vcpu); +extern void __kvmppc_vcore_entry(void); static void kvmppc_remove_runnable(struct kvmppc_vcore *vc, struct kvm_vcpu *vcpu) @@ -1184,13 +1355,16 @@ static void kvmppc_start_thread(struct kvm_vcpu *vcpu) tpaca = &paca[cpu]; tpaca->kvm_hstate.kvm_vcpu = vcpu; tpaca->kvm_hstate.kvm_vcore = vc; - tpaca->kvm_hstate.napping = 0; + tpaca->kvm_hstate.ptid = vcpu->arch.ptid; vcpu->cpu = vc->pcpu; smp_wmb(); #if defined(CONFIG_PPC_ICP_NATIVE) && defined(CONFIG_SMP) - if (vcpu->arch.ptid) { + if (cpu != smp_processor_id()) { +#ifdef CONFIG_KVM_XICS xics_wake_cpu(cpu); - ++vc->n_woken; +#endif + if (vcpu->arch.ptid) + ++vc->n_woken; } #endif } @@ -1247,10 +1421,10 @@ static int on_primary_thread(void) */ static void kvmppc_run_core(struct kvmppc_vcore *vc) { - struct kvm_vcpu *vcpu, *vcpu0, *vnext; + struct kvm_vcpu *vcpu, *vnext; long ret; u64 now; - int ptid, i, need_vpa_update; + int i, need_vpa_update; int srcu_idx; struct kvm_vcpu *vcpus_to_update[threads_per_core]; @@ -1288,25 +1462,6 @@ static void kvmppc_run_core(struct kvmppc_vcore *vc) } /* - * Assign physical thread IDs, first to non-ceded vcpus - * and then to ceded ones. - */ - ptid = 0; - vcpu0 = NULL; - list_for_each_entry(vcpu, &vc->runnable_threads, arch.run_list) { - if (!vcpu->arch.ceded) { - if (!ptid) - vcpu0 = vcpu; - vcpu->arch.ptid = ptid++; - } - } - if (!vcpu0) - goto out; /* nothing to run; should never happen */ - list_for_each_entry(vcpu, &vc->runnable_threads, arch.run_list) - if (vcpu->arch.ceded) - vcpu->arch.ptid = ptid++; - - /* * Make sure we are running on thread 0, and that * secondary threads are offline. */ @@ -1322,15 +1477,19 @@ static void kvmppc_run_core(struct kvmppc_vcore *vc) kvmppc_create_dtl_entry(vcpu, vc); } + /* Set this explicitly in case thread 0 doesn't have a vcpu */ + get_paca()->kvm_hstate.kvm_vcore = vc; + get_paca()->kvm_hstate.ptid = 0; + vc->vcore_state = VCORE_RUNNING; preempt_disable(); spin_unlock(&vc->lock); kvm_guest_enter(); - srcu_idx = srcu_read_lock(&vcpu0->kvm->srcu); + srcu_idx = srcu_read_lock(&vc->kvm->srcu); - __kvmppc_vcore_entry(NULL, vcpu0); + __kvmppc_vcore_entry(); spin_lock(&vc->lock); /* disable sending of IPIs on virtual external irqs */ @@ -1345,7 +1504,7 @@ static void kvmppc_run_core(struct kvmppc_vcore *vc) vc->vcore_state = VCORE_EXITING; spin_unlock(&vc->lock); - srcu_read_unlock(&vcpu0->kvm->srcu, srcu_idx); + srcu_read_unlock(&vc->kvm->srcu, srcu_idx); /* make sure updates to secondary vcpu structs are visible now */ smp_mb(); @@ -1453,7 +1612,6 @@ static int kvmppc_run_vcpu(struct kvm_run *kvm_run, struct kvm_vcpu *vcpu) if (!signal_pending(current)) { if (vc->vcore_state == VCORE_RUNNING && VCORE_EXIT_COUNT(vc) == 0) { - vcpu->arch.ptid = vc->n_runnable - 1; kvmppc_create_dtl_entry(vcpu, vc); kvmppc_start_thread(vcpu); } else if (vc->vcore_state == VCORE_SLEEPING) { @@ -2048,6 +2206,9 @@ static int kvmppc_core_init_vm_hv(struct kvm *kvm) LPCR_VPM0 | LPCR_VPM1; kvm->arch.vrma_slb_v = SLB_VSID_B_1T | (VRMA_VSID << SLB_VSID_SHIFT_1T); + /* On POWER8 turn on online bit to enable PURR/SPURR */ + if (cpu_has_feature(CPU_FTR_ARCH_207S)) + lpcr |= LPCR_ONL; } kvm->arch.lpcr = lpcr; @@ -2222,3 +2383,5 @@ static void kvmppc_book3s_exit_hv(void) module_init(kvmppc_book3s_init_hv); module_exit(kvmppc_book3s_exit_hv); MODULE_LICENSE("GPL"); +MODULE_ALIAS_MISCDEV(KVM_MINOR); +MODULE_ALIAS("devname:kvm"); diff --git a/arch/powerpc/kvm/book3s_hv_interrupts.S b/arch/powerpc/kvm/book3s_hv_interrupts.S index 928142c64cb..e873796b1a2 100644 --- a/arch/powerpc/kvm/book3s_hv_interrupts.S +++ b/arch/powerpc/kvm/book3s_hv_interrupts.S @@ -35,7 +35,7 @@ ****************************************************************************/ /* Registers: - * r4: vcpu pointer + * none */ _GLOBAL(__kvmppc_vcore_entry) @@ -57,9 +57,11 @@ BEGIN_FTR_SECTION std r3, HSTATE_DSCR(r13) END_FTR_SECTION_IFSET(CPU_FTR_ARCH_206) +BEGIN_FTR_SECTION /* Save host DABR */ mfspr r3, SPRN_DABR std r3, HSTATE_DABR(r13) +END_FTR_SECTION_IFCLR(CPU_FTR_ARCH_207S) /* Hard-disable interrupts */ mfmsr r10 @@ -69,7 +71,6 @@ END_FTR_SECTION_IFSET(CPU_FTR_ARCH_206) mtmsrd r10,1 /* Save host PMU registers */ - /* R4 is live here (vcpu pointer) but not r3 or r5 */ li r3, 1 sldi r3, r3, 31 /* MMCR0_FC (freeze counters) bit */ mfspr r7, SPRN_MMCR0 /* save MMCR0 */ @@ -134,16 +135,15 @@ END_FTR_SECTION_IFSET(CPU_FTR_ARCH_201) * enters the guest with interrupts enabled. */ BEGIN_FTR_SECTION + ld r4, HSTATE_KVM_VCPU(r13) ld r0, VCPU_PENDING_EXC(r4) li r7, (1 << BOOK3S_IRQPRIO_EXTERNAL) oris r7, r7, (1 << BOOK3S_IRQPRIO_EXTERNAL_LEVEL)@h and. r0, r0, r7 beq 32f - mr r31, r4 lhz r3, PACAPACAINDEX(r13) bl smp_send_reschedule nop - mr r4, r31 32: END_FTR_SECTION_IFSET(CPU_FTR_ARCH_201) #endif /* CONFIG_SMP */ diff --git a/arch/powerpc/kvm/book3s_hv_rm_mmu.c b/arch/powerpc/kvm/book3s_hv_rm_mmu.c index 8689e2e3085..37fb3caa4c8 100644 --- a/arch/powerpc/kvm/book3s_hv_rm_mmu.c +++ b/arch/powerpc/kvm/book3s_hv_rm_mmu.c @@ -134,7 +134,7 @@ static void remove_revmap_chain(struct kvm *kvm, long pte_index, unlock_rmap(rmap); } -static pte_t lookup_linux_pte(pgd_t *pgdir, unsigned long hva, +static pte_t lookup_linux_pte_and_update(pgd_t *pgdir, unsigned long hva, int writing, unsigned long *pte_sizep) { pte_t *ptep; @@ -232,7 +232,8 @@ long kvmppc_do_h_enter(struct kvm *kvm, unsigned long flags, /* Look up the Linux PTE for the backing page */ pte_size = psize; - pte = lookup_linux_pte(pgdir, hva, writing, &pte_size); + pte = lookup_linux_pte_and_update(pgdir, hva, writing, + &pte_size); if (pte_present(pte)) { if (writing && !pte_write(pte)) /* make the actual HPTE be read-only */ @@ -672,7 +673,8 @@ long kvmppc_h_protect(struct kvm_vcpu *vcpu, unsigned long flags, memslot = __gfn_to_memslot(kvm_memslots(kvm), gfn); if (memslot) { hva = __gfn_to_hva_memslot(memslot, gfn); - pte = lookup_linux_pte(pgdir, hva, 1, &psize); + pte = lookup_linux_pte_and_update(pgdir, hva, + 1, &psize); if (pte_present(pte) && !pte_write(pte)) r = hpte_make_readonly(r); } diff --git a/arch/powerpc/kvm/book3s_hv_rmhandlers.S b/arch/powerpc/kvm/book3s_hv_rmhandlers.S index be4fa04a37c..e66d4ec04d9 100644 --- a/arch/powerpc/kvm/book3s_hv_rmhandlers.S +++ b/arch/powerpc/kvm/book3s_hv_rmhandlers.S @@ -33,6 +33,10 @@ #error Need to fix lppaca and SLB shadow accesses in little endian mode #endif +/* Values in HSTATE_NAPPING(r13) */ +#define NAPPING_CEDE 1 +#define NAPPING_NOVCPU 2 + /* * Call kvmppc_hv_entry in real mode. * Must be called with interrupts hard-disabled. @@ -57,29 +61,23 @@ _GLOBAL(kvmppc_hv_entry_trampoline) RFI kvmppc_call_hv_entry: + ld r4, HSTATE_KVM_VCPU(r13) bl kvmppc_hv_entry /* Back from guest - restore host state and return to caller */ +BEGIN_FTR_SECTION /* Restore host DABR and DABRX */ ld r5,HSTATE_DABR(r13) li r6,7 mtspr SPRN_DABR,r5 mtspr SPRN_DABRX,r6 +END_FTR_SECTION_IFCLR(CPU_FTR_ARCH_207S) /* Restore SPRG3 */ ld r3,PACA_SPRG3(r13) mtspr SPRN_SPRG3,r3 - /* - * Reload DEC. HDEC interrupts were disabled when - * we reloaded the host's LPCR value. - */ - ld r3, HSTATE_DECEXP(r13) - mftb r4 - subf r4, r4, r3 - mtspr SPRN_DEC, r4 - /* Reload the host's PMU registers */ ld r3, PACALPPACAPTR(r13) /* is the host using the PMU? */ lbz r4, LPPACA_PMCINUSE(r3) @@ -115,6 +113,15 @@ END_FTR_SECTION_IFSET(CPU_FTR_ARCH_201) 23: /* + * Reload DEC. HDEC interrupts were disabled when + * we reloaded the host's LPCR value. + */ + ld r3, HSTATE_DECEXP(r13) + mftb r4 + subf r4, r4, r3 + mtspr SPRN_DEC, r4 + + /* * For external and machine check interrupts, we need * to call the Linux handler to process the interrupt. * We do that by jumping to absolute address 0x500 for @@ -153,15 +160,75 @@ END_FTR_SECTION_IFSET(CPU_FTR_ARCH_206) 13: b machine_check_fwnmi +kvmppc_primary_no_guest: + /* We handle this much like a ceded vcpu */ + /* set our bit in napping_threads */ + ld r5, HSTATE_KVM_VCORE(r13) + lbz r7, HSTATE_PTID(r13) + li r0, 1 + sld r0, r0, r7 + addi r6, r5, VCORE_NAPPING_THREADS +1: lwarx r3, 0, r6 + or r3, r3, r0 + stwcx. r3, 0, r6 + bne 1b + /* order napping_threads update vs testing entry_exit_count */ + isync + li r12, 0 + lwz r7, VCORE_ENTRY_EXIT(r5) + cmpwi r7, 0x100 + bge kvm_novcpu_exit /* another thread already exiting */ + li r3, NAPPING_NOVCPU + stb r3, HSTATE_NAPPING(r13) + li r3, 1 + stb r3, HSTATE_HWTHREAD_REQ(r13) + + b kvm_do_nap + +kvm_novcpu_wakeup: + ld r1, HSTATE_HOST_R1(r13) + ld r5, HSTATE_KVM_VCORE(r13) + li r0, 0 + stb r0, HSTATE_NAPPING(r13) + stb r0, HSTATE_HWTHREAD_REQ(r13) + + /* check the wake reason */ + bl kvmppc_check_wake_reason + + /* see if any other thread is already exiting */ + lwz r0, VCORE_ENTRY_EXIT(r5) + cmpwi r0, 0x100 + bge kvm_novcpu_exit + + /* clear our bit in napping_threads */ + lbz r7, HSTATE_PTID(r13) + li r0, 1 + sld r0, r0, r7 + addi r6, r5, VCORE_NAPPING_THREADS +4: lwarx r7, 0, r6 + andc r7, r7, r0 + stwcx. r7, 0, r6 + bne 4b + + /* See if the wake reason means we need to exit */ + cmpdi r3, 0 + bge kvm_novcpu_exit + + /* Got an IPI but other vcpus aren't yet exiting, must be a latecomer */ + ld r4, HSTATE_KVM_VCPU(r13) + cmpdi r4, 0 + bne kvmppc_got_guest + +kvm_novcpu_exit: + b hdec_soon + /* - * We come in here when wakened from nap mode on a secondary hw thread. + * We come in here when wakened from nap mode. * Relocation is off and most register values are lost. * r13 points to the PACA. */ .globl kvm_start_guest kvm_start_guest: - ld r1,PACAEMERGSP(r13) - subi r1,r1,STACK_FRAME_OVERHEAD ld r2,PACATOC(r13) li r0,KVM_HWTHREAD_IN_KVM @@ -173,8 +240,13 @@ kvm_start_guest: /* were we napping due to cede? */ lbz r0,HSTATE_NAPPING(r13) - cmpwi r0,0 - bne kvm_end_cede + cmpwi r0,NAPPING_CEDE + beq kvm_end_cede + cmpwi r0,NAPPING_NOVCPU + beq kvm_novcpu_wakeup + + ld r1,PACAEMERGSP(r13) + subi r1,r1,STACK_FRAME_OVERHEAD /* * We weren't napping due to cede, so this must be a secondary @@ -184,40 +256,22 @@ kvm_start_guest: */ /* Check the wake reason in SRR1 to see why we got here */ - mfspr r3,SPRN_SRR1 - rlwinm r3,r3,44-31,0x7 /* extract wake reason field */ - cmpwi r3,4 /* was it an external interrupt? */ - bne 27f /* if not */ - ld r5,HSTATE_XICS_PHYS(r13) - li r7,XICS_XIRR /* if it was an external interrupt, */ - lwzcix r8,r5,r7 /* get and ack the interrupt */ - sync - clrldi. r9,r8,40 /* get interrupt source ID. */ - beq 28f /* none there? */ - cmpwi r9,XICS_IPI /* was it an IPI? */ - bne 29f - li r0,0xff - li r6,XICS_MFRR - stbcix r0,r5,r6 /* clear IPI */ - stwcix r8,r5,r7 /* EOI the interrupt */ - sync /* order loading of vcpu after that */ + bl kvmppc_check_wake_reason + cmpdi r3, 0 + bge kvm_no_guest /* get vcpu pointer, NULL if we have no vcpu to run */ ld r4,HSTATE_KVM_VCPU(r13) cmpdi r4,0 /* if we have no vcpu to run, go back to sleep */ beq kvm_no_guest - b 30f -27: /* XXX should handle hypervisor maintenance interrupts etc. here */ - b kvm_no_guest -28: /* SRR1 said external but ICP said nope?? */ - b kvm_no_guest -29: /* External non-IPI interrupt to offline secondary thread? help?? */ - stw r8,HSTATE_SAVED_XIRR(r13) - b kvm_no_guest + /* Set HSTATE_DSCR(r13) to something sensible */ + LOAD_REG_ADDR(r6, dscr_default) + ld r6, 0(r6) + std r6, HSTATE_DSCR(r13) -30: bl kvmppc_hv_entry + bl kvmppc_hv_entry /* Back from the guest, go back to nap */ /* Clear our vcpu pointer so we don't come back in early */ @@ -229,18 +283,6 @@ kvm_start_guest: * visible we could be given another vcpu. */ lwsync - /* Clear any pending IPI - we're an offline thread */ - ld r5, HSTATE_XICS_PHYS(r13) - li r7, XICS_XIRR - lwzcix r3, r5, r7 /* ack any pending interrupt */ - rlwinm. r0, r3, 0, 0xffffff /* any pending? */ - beq 37f - sync - li r0, 0xff - li r6, XICS_MFRR - stbcix r0, r5, r6 /* clear the IPI */ - stwcix r3, r5, r7 /* EOI it */ -37: sync /* increment the nap count and then go to nap mode */ ld r4, HSTATE_KVM_VCORE(r13) @@ -253,6 +295,7 @@ kvm_start_guest: kvm_no_guest: li r0, KVM_HWTHREAD_IN_NAP stb r0, HSTATE_HWTHREAD_STATE(r13) +kvm_do_nap: li r3, LPCR_PECE0 mfspr r4, SPRN_LPCR rlwimi r4, r3, 0, LPCR_PECE0 | LPCR_PECE1 @@ -277,7 +320,7 @@ kvmppc_hv_entry: /* Required state: * - * R4 = vcpu pointer + * R4 = vcpu pointer (or NULL) * MSR = ~IR|DR * R13 = PACA * R1 = host R1 @@ -287,122 +330,12 @@ kvmppc_hv_entry: std r0, PPC_LR_STKOFF(r1) stdu r1, -112(r1) - /* Set partition DABR */ - /* Do this before re-enabling PMU to avoid P7 DABR corruption bug */ - li r5,3 - ld r6,VCPU_DABR(r4) - mtspr SPRN_DABRX,r5 - mtspr SPRN_DABR,r6 -BEGIN_FTR_SECTION - isync -END_FTR_SECTION_IFSET(CPU_FTR_ARCH_206) - - /* Load guest PMU registers */ - /* R4 is live here (vcpu pointer) */ - li r3, 1 - sldi r3, r3, 31 /* MMCR0_FC (freeze counters) bit */ - mtspr SPRN_MMCR0, r3 /* freeze all counters, disable ints */ - isync - lwz r3, VCPU_PMC(r4) /* always load up guest PMU registers */ - lwz r5, VCPU_PMC + 4(r4) /* to prevent information leak */ - lwz r6, VCPU_PMC + 8(r4) - lwz r7, VCPU_PMC + 12(r4) - lwz r8, VCPU_PMC + 16(r4) - lwz r9, VCPU_PMC + 20(r4) -BEGIN_FTR_SECTION - lwz r10, VCPU_PMC + 24(r4) - lwz r11, VCPU_PMC + 28(r4) -END_FTR_SECTION_IFSET(CPU_FTR_ARCH_201) - mtspr SPRN_PMC1, r3 - mtspr SPRN_PMC2, r5 - mtspr SPRN_PMC3, r6 - mtspr SPRN_PMC4, r7 - mtspr SPRN_PMC5, r8 - mtspr SPRN_PMC6, r9 -BEGIN_FTR_SECTION - mtspr SPRN_PMC7, r10 - mtspr SPRN_PMC8, r11 -END_FTR_SECTION_IFSET(CPU_FTR_ARCH_201) - ld r3, VCPU_MMCR(r4) - ld r5, VCPU_MMCR + 8(r4) - ld r6, VCPU_MMCR + 16(r4) - ld r7, VCPU_SIAR(r4) - ld r8, VCPU_SDAR(r4) - mtspr SPRN_MMCR1, r5 - mtspr SPRN_MMCRA, r6 - mtspr SPRN_SIAR, r7 - mtspr SPRN_SDAR, r8 - mtspr SPRN_MMCR0, r3 - isync - - /* Load up FP, VMX and VSX registers */ - bl kvmppc_load_fp - - ld r14, VCPU_GPR(R14)(r4) - ld r15, VCPU_GPR(R15)(r4) - ld r16, VCPU_GPR(R16)(r4) - ld r17, VCPU_GPR(R17)(r4) - ld r18, VCPU_GPR(R18)(r4) - ld r19, VCPU_GPR(R19)(r4) - ld r20, VCPU_GPR(R20)(r4) - ld r21, VCPU_GPR(R21)(r4) - ld r22, VCPU_GPR(R22)(r4) - ld r23, VCPU_GPR(R23)(r4) - ld r24, VCPU_GPR(R24)(r4) - ld r25, VCPU_GPR(R25)(r4) - ld r26, VCPU_GPR(R26)(r4) - ld r27, VCPU_GPR(R27)(r4) - ld r28, VCPU_GPR(R28)(r4) - ld r29, VCPU_GPR(R29)(r4) - ld r30, VCPU_GPR(R30)(r4) - ld r31, VCPU_GPR(R31)(r4) - -BEGIN_FTR_SECTION - /* Switch DSCR to guest value */ - ld r5, VCPU_DSCR(r4) - mtspr SPRN_DSCR, r5 -END_FTR_SECTION_IFSET(CPU_FTR_ARCH_206) - - /* - * Set the decrementer to the guest decrementer. - */ - ld r8,VCPU_DEC_EXPIRES(r4) - mftb r7 - subf r3,r7,r8 - mtspr SPRN_DEC,r3 - stw r3,VCPU_DEC(r4) - - ld r5, VCPU_SPRG0(r4) - ld r6, VCPU_SPRG1(r4) - ld r7, VCPU_SPRG2(r4) - ld r8, VCPU_SPRG3(r4) - mtspr SPRN_SPRG0, r5 - mtspr SPRN_SPRG1, r6 - mtspr SPRN_SPRG2, r7 - mtspr SPRN_SPRG3, r8 - /* Save R1 in the PACA */ std r1, HSTATE_HOST_R1(r13) - /* Load up DAR and DSISR */ - ld r5, VCPU_DAR(r4) - lwz r6, VCPU_DSISR(r4) - mtspr SPRN_DAR, r5 - mtspr SPRN_DSISR, r6 - li r6, KVM_GUEST_MODE_HOST_HV stb r6, HSTATE_IN_GUEST(r13) -BEGIN_FTR_SECTION - /* Restore AMR and UAMOR, set AMOR to all 1s */ - ld r5,VCPU_AMR(r4) - ld r6,VCPU_UAMOR(r4) - li r7,-1 - mtspr SPRN_AMR,r5 - mtspr SPRN_UAMOR,r6 - mtspr SPRN_AMOR,r7 -END_FTR_SECTION_IFSET(CPU_FTR_ARCH_206) - /* Clear out SLB */ li r6,0 slbmte r6,r6 @@ -428,8 +361,8 @@ END_FTR_SECTION_IFSET(CPU_FTR_ARCH_201) bne 21b /* Primary thread switches to guest partition. */ - ld r9,VCPU_KVM(r4) /* pointer to struct kvm */ - lwz r6,VCPU_PTID(r4) + ld r9,VCORE_KVM(r5) /* pointer to struct kvm */ + lbz r6,HSTATE_PTID(r13) cmpwi r6,0 bne 20f ld r6,KVM_SDR1(r9) @@ -457,7 +390,13 @@ END_FTR_SECTION_IFSET(CPU_FTR_ARCH_201) andc r7,r7,r0 stdcx. r7,0,r6 bne 23b - li r6,128 /* and flush the TLB */ + /* Flush the TLB of any entries for this LPID */ + /* use arch 2.07S as a proxy for POWER8 */ +BEGIN_FTR_SECTION + li r6,512 /* POWER8 has 512 sets */ +FTR_SECTION_ELSE + li r6,128 /* POWER7 has 128 sets */ +ALT_FTR_SECTION_END_IFSET(CPU_FTR_ARCH_207S) mtctr r6 li r7,0x800 /* IS field = 0b10 */ ptesync @@ -487,6 +426,13 @@ END_FTR_SECTION_IFSET(CPU_FTR_ARCH_201) beq 38f mtspr SPRN_PCR, r7 38: + +BEGIN_FTR_SECTION + /* DPDES is shared between threads */ + ld r8, VCORE_DPDES(r5) + mtspr SPRN_DPDES, r8 +END_FTR_SECTION_IFSET(CPU_FTR_ARCH_207S) + li r0,1 stb r0,VCORE_IN_GUEST(r5) /* signal secondaries to continue */ b 10f @@ -503,32 +449,11 @@ END_FTR_SECTION_IFSET(CPU_FTR_ARCH_201) mtspr SPRN_RMOR,r8 isync - /* Increment yield count if they have a VPA */ - ld r3, VCPU_VPA(r4) - cmpdi r3, 0 - beq 25f - lwz r5, LPPACA_YIELDCOUNT(r3) - addi r5, r5, 1 - stw r5, LPPACA_YIELDCOUNT(r3) - li r6, 1 - stb r6, VCPU_VPA_DIRTY(r4) -25: /* Check if HDEC expires soon */ mfspr r3,SPRN_HDEC - cmpwi r3,10 + cmpwi r3,512 /* 1 microsecond */ li r12,BOOK3S_INTERRUPT_HV_DECREMENTER - mr r9,r4 blt hdec_soon - - /* Save purr/spurr */ - mfspr r5,SPRN_PURR - mfspr r6,SPRN_SPURR - std r5,HSTATE_PURR(r13) - std r6,HSTATE_SPURR(r13) - ld r7,VCPU_PURR(r4) - ld r8,VCPU_SPURR(r4) - mtspr SPRN_PURR,r7 - mtspr SPRN_SPURR,r8 b 31f /* @@ -539,7 +464,8 @@ END_FTR_SECTION_IFSET(CPU_FTR_ARCH_201) * We also have to invalidate the TLB since its * entries aren't tagged with the LPID. */ -30: ld r9,VCPU_KVM(r4) /* pointer to struct kvm */ +30: ld r5,HSTATE_KVM_VCORE(r13) + ld r9,VCORE_KVM(r5) /* pointer to struct kvm */ /* first take native_tlbie_lock */ .section ".toc","aw" @@ -604,7 +530,6 @@ toc_tlbie_lock: mfspr r3,SPRN_HDEC cmpwi r3,10 li r12,BOOK3S_INTERRUPT_HV_DECREMENTER - mr r9,r4 blt hdec_soon /* Enable HDEC interrupts */ @@ -619,9 +544,14 @@ toc_tlbie_lock: mfspr r0,SPRN_HID0 mfspr r0,SPRN_HID0 mfspr r0,SPRN_HID0 +31: + /* Do we have a guest vcpu to run? */ + cmpdi r4, 0 + beq kvmppc_primary_no_guest +kvmppc_got_guest: /* Load up guest SLB entries */ -31: lwz r5,VCPU_SLB_MAX(r4) + lwz r5,VCPU_SLB_MAX(r4) cmpwi r5,0 beq 9f mtctr r5 @@ -632,6 +562,209 @@ toc_tlbie_lock: addi r6,r6,VCPU_SLB_SIZE bdnz 1b 9: + /* Increment yield count if they have a VPA */ + ld r3, VCPU_VPA(r4) + cmpdi r3, 0 + beq 25f + lwz r5, LPPACA_YIELDCOUNT(r3) + addi r5, r5, 1 + stw r5, LPPACA_YIELDCOUNT(r3) + li r6, 1 + stb r6, VCPU_VPA_DIRTY(r4) +25: + +BEGIN_FTR_SECTION + /* Save purr/spurr */ + mfspr r5,SPRN_PURR + mfspr r6,SPRN_SPURR + std r5,HSTATE_PURR(r13) + std r6,HSTATE_SPURR(r13) + ld r7,VCPU_PURR(r4) + ld r8,VCPU_SPURR(r4) + mtspr SPRN_PURR,r7 + mtspr SPRN_SPURR,r8 +END_FTR_SECTION_IFSET(CPU_FTR_ARCH_206) + +BEGIN_FTR_SECTION + /* Set partition DABR */ + /* Do this before re-enabling PMU to avoid P7 DABR corruption bug */ + lwz r5,VCPU_DABRX(r4) + ld r6,VCPU_DABR(r4) + mtspr SPRN_DABRX,r5 + mtspr SPRN_DABR,r6 + BEGIN_FTR_SECTION_NESTED(89) + isync + END_FTR_SECTION_NESTED(CPU_FTR_ARCH_206, CPU_FTR_ARCH_206, 89) +END_FTR_SECTION_IFCLR(CPU_FTR_ARCH_207S) + + /* Load guest PMU registers */ + /* R4 is live here (vcpu pointer) */ + li r3, 1 + sldi r3, r3, 31 /* MMCR0_FC (freeze counters) bit */ + mtspr SPRN_MMCR0, r3 /* freeze all counters, disable ints */ + isync + lwz r3, VCPU_PMC(r4) /* always load up guest PMU registers */ + lwz r5, VCPU_PMC + 4(r4) /* to prevent information leak */ + lwz r6, VCPU_PMC + 8(r4) + lwz r7, VCPU_PMC + 12(r4) + lwz r8, VCPU_PMC + 16(r4) + lwz r9, VCPU_PMC + 20(r4) +BEGIN_FTR_SECTION + lwz r10, VCPU_PMC + 24(r4) + lwz r11, VCPU_PMC + 28(r4) +END_FTR_SECTION_IFSET(CPU_FTR_ARCH_201) + mtspr SPRN_PMC1, r3 + mtspr SPRN_PMC2, r5 + mtspr SPRN_PMC3, r6 + mtspr SPRN_PMC4, r7 + mtspr SPRN_PMC5, r8 + mtspr SPRN_PMC6, r9 +BEGIN_FTR_SECTION + mtspr SPRN_PMC7, r10 + mtspr SPRN_PMC8, r11 +END_FTR_SECTION_IFSET(CPU_FTR_ARCH_201) + ld r3, VCPU_MMCR(r4) + ld r5, VCPU_MMCR + 8(r4) + ld r6, VCPU_MMCR + 16(r4) + ld r7, VCPU_SIAR(r4) + ld r8, VCPU_SDAR(r4) + mtspr SPRN_MMCR1, r5 + mtspr SPRN_MMCRA, r6 + mtspr SPRN_SIAR, r7 + mtspr SPRN_SDAR, r8 +BEGIN_FTR_SECTION + ld r5, VCPU_MMCR + 24(r4) + ld r6, VCPU_SIER(r4) + lwz r7, VCPU_PMC + 24(r4) + lwz r8, VCPU_PMC + 28(r4) + ld r9, VCPU_MMCR + 32(r4) + mtspr SPRN_MMCR2, r5 + mtspr SPRN_SIER, r6 + mtspr SPRN_SPMC1, r7 + mtspr SPRN_SPMC2, r8 + mtspr SPRN_MMCRS, r9 +END_FTR_SECTION_IFSET(CPU_FTR_ARCH_207S) + mtspr SPRN_MMCR0, r3 + isync + + /* Load up FP, VMX and VSX registers */ + bl kvmppc_load_fp + + ld r14, VCPU_GPR(R14)(r4) + ld r15, VCPU_GPR(R15)(r4) + ld r16, VCPU_GPR(R16)(r4) + ld r17, VCPU_GPR(R17)(r4) + ld r18, VCPU_GPR(R18)(r4) + ld r19, VCPU_GPR(R19)(r4) + ld r20, VCPU_GPR(R20)(r4) + ld r21, VCPU_GPR(R21)(r4) + ld r22, VCPU_GPR(R22)(r4) + ld r23, VCPU_GPR(R23)(r4) + ld r24, VCPU_GPR(R24)(r4) + ld r25, VCPU_GPR(R25)(r4) + ld r26, VCPU_GPR(R26)(r4) + ld r27, VCPU_GPR(R27)(r4) + ld r28, VCPU_GPR(R28)(r4) + ld r29, VCPU_GPR(R29)(r4) + ld r30, VCPU_GPR(R30)(r4) + ld r31, VCPU_GPR(R31)(r4) + +BEGIN_FTR_SECTION + /* Switch DSCR to guest value */ + ld r5, VCPU_DSCR(r4) + mtspr SPRN_DSCR, r5 +END_FTR_SECTION_IFSET(CPU_FTR_ARCH_206) + +BEGIN_FTR_SECTION + /* Skip next section on POWER7 or PPC970 */ + b 8f +END_FTR_SECTION_IFCLR(CPU_FTR_ARCH_207S) + /* Turn on TM so we can access TFHAR/TFIAR/TEXASR */ + mfmsr r8 + li r0, 1 + rldimi r8, r0, MSR_TM_LG, 63-MSR_TM_LG + mtmsrd r8 + + /* Load up POWER8-specific registers */ + ld r5, VCPU_IAMR(r4) + lwz r6, VCPU_PSPB(r4) + ld r7, VCPU_FSCR(r4) + mtspr SPRN_IAMR, r5 + mtspr SPRN_PSPB, r6 + mtspr SPRN_FSCR, r7 + ld r5, VCPU_DAWR(r4) + ld r6, VCPU_DAWRX(r4) + ld r7, VCPU_CIABR(r4) + ld r8, VCPU_TAR(r4) + mtspr SPRN_DAWR, r5 + mtspr SPRN_DAWRX, r6 + mtspr SPRN_CIABR, r7 + mtspr SPRN_TAR, r8 + ld r5, VCPU_IC(r4) + ld r6, VCPU_VTB(r4) + mtspr SPRN_IC, r5 + mtspr SPRN_VTB, r6 +#ifdef CONFIG_PPC_TRANSACTIONAL_MEM + ld r5, VCPU_TFHAR(r4) + ld r6, VCPU_TFIAR(r4) + ld r7, VCPU_TEXASR(r4) + mtspr SPRN_TFHAR, r5 + mtspr SPRN_TFIAR, r6 + mtspr SPRN_TEXASR, r7 +#endif + ld r8, VCPU_EBBHR(r4) + mtspr SPRN_EBBHR, r8 + ld r5, VCPU_EBBRR(r4) + ld r6, VCPU_BESCR(r4) + ld r7, VCPU_CSIGR(r4) + ld r8, VCPU_TACR(r4) + mtspr SPRN_EBBRR, r5 + mtspr SPRN_BESCR, r6 + mtspr SPRN_CSIGR, r7 + mtspr SPRN_TACR, r8 + ld r5, VCPU_TCSCR(r4) + ld r6, VCPU_ACOP(r4) + lwz r7, VCPU_GUEST_PID(r4) + ld r8, VCPU_WORT(r4) + mtspr SPRN_TCSCR, r5 + mtspr SPRN_ACOP, r6 + mtspr SPRN_PID, r7 + mtspr SPRN_WORT, r8 +8: + + /* + * Set the decrementer to the guest decrementer. + */ + ld r8,VCPU_DEC_EXPIRES(r4) + mftb r7 + subf r3,r7,r8 + mtspr SPRN_DEC,r3 + stw r3,VCPU_DEC(r4) + + ld r5, VCPU_SPRG0(r4) + ld r6, VCPU_SPRG1(r4) + ld r7, VCPU_SPRG2(r4) + ld r8, VCPU_SPRG3(r4) + mtspr SPRN_SPRG0, r5 + mtspr SPRN_SPRG1, r6 + mtspr SPRN_SPRG2, r7 + mtspr SPRN_SPRG3, r8 + + /* Load up DAR and DSISR */ + ld r5, VCPU_DAR(r4) + lwz r6, VCPU_DSISR(r4) + mtspr SPRN_DAR, r5 + mtspr SPRN_DSISR, r6 + +BEGIN_FTR_SECTION + /* Restore AMR and UAMOR, set AMOR to all 1s */ + ld r5,VCPU_AMR(r4) + ld r6,VCPU_UAMOR(r4) + li r7,-1 + mtspr SPRN_AMR,r5 + mtspr SPRN_UAMOR,r6 + mtspr SPRN_AMOR,r7 +END_FTR_SECTION_IFSET(CPU_FTR_ARCH_206) /* Restore state of CTRL run bit; assume 1 on entry */ lwz r5,VCPU_CTRL(r4) @@ -647,48 +780,53 @@ toc_tlbie_lock: mtctr r6 mtxer r7 +kvmppc_cede_reentry: /* r4 = vcpu, r13 = paca */ ld r10, VCPU_PC(r4) ld r11, VCPU_MSR(r4) -kvmppc_cede_reentry: /* r4 = vcpu, r13 = paca */ ld r6, VCPU_SRR0(r4) ld r7, VCPU_SRR1(r4) + mtspr SPRN_SRR0, r6 + mtspr SPRN_SRR1, r7 +deliver_guest_interrupt: /* r11 = vcpu->arch.msr & ~MSR_HV */ rldicl r11, r11, 63 - MSR_HV_LG, 1 rotldi r11, r11, 1 + MSR_HV_LG ori r11, r11, MSR_ME /* Check if we can deliver an external or decrementer interrupt now */ - ld r0,VCPU_PENDING_EXC(r4) - lis r8,(1 << BOOK3S_IRQPRIO_EXTERNAL_LEVEL)@h - and r0,r0,r8 - cmpdi cr1,r0,0 - andi. r0,r11,MSR_EE - beq cr1,11f + ld r0, VCPU_PENDING_EXC(r4) + rldicl r0, r0, 64 - BOOK3S_IRQPRIO_EXTERNAL_LEVEL, 63 + cmpdi cr1, r0, 0 + andi. r8, r11, MSR_EE BEGIN_FTR_SECTION - mfspr r8,SPRN_LPCR - ori r8,r8,LPCR_MER - mtspr SPRN_LPCR,r8 + mfspr r8, SPRN_LPCR + /* Insert EXTERNAL_LEVEL bit into LPCR at the MER bit position */ + rldimi r8, r0, LPCR_MER_SH, 63 - LPCR_MER_SH + mtspr SPRN_LPCR, r8 isync END_FTR_SECTION_IFSET(CPU_FTR_ARCH_206) beq 5f - li r0,BOOK3S_INTERRUPT_EXTERNAL -12: mr r6,r10 - mr r10,r0 - mr r7,r11 - li r11,(MSR_ME << 1) | 1 /* synthesize MSR_SF | MSR_ME */ - rotldi r11,r11,63 - b 5f -11: beq 5f - mfspr r0,SPRN_DEC - cmpwi r0,0 - li r0,BOOK3S_INTERRUPT_DECREMENTER - blt 12b + li r0, BOOK3S_INTERRUPT_EXTERNAL + bne cr1, 12f + mfspr r0, SPRN_DEC + cmpwi r0, 0 + li r0, BOOK3S_INTERRUPT_DECREMENTER + bge 5f - /* Move SRR0 and SRR1 into the respective regs */ -5: mtspr SPRN_SRR0, r6 - mtspr SPRN_SRR1, r7 +12: mtspr SPRN_SRR0, r10 + mr r10,r0 + mtspr SPRN_SRR1, r11 + ld r11, VCPU_INTR_MSR(r4) +5: +/* + * Required state: + * R4 = vcpu + * R10: value for HSRR0 + * R11: value for HSRR1 + * R13 = PACA + */ fast_guest_return: li r0,0 stb r0,VCPU_CEDED(r4) /* cancel cede */ @@ -868,39 +1006,19 @@ END_FTR_SECTION_IFCLR(CPU_FTR_ARCH_206) /* External interrupt, first check for host_ipi. If this is * set, we know the host wants us out so let's do it now */ -do_ext_interrupt: bl kvmppc_read_intr cmpdi r3, 0 bgt ext_interrupt_to_host - /* Allright, looks like an IPI for the guest, we need to set MER */ /* Check if any CPU is heading out to the host, if so head out too */ ld r5, HSTATE_KVM_VCORE(r13) lwz r0, VCORE_ENTRY_EXIT(r5) cmpwi r0, 0x100 bge ext_interrupt_to_host - /* See if there is a pending interrupt for the guest */ - mfspr r8, SPRN_LPCR - ld r0, VCPU_PENDING_EXC(r9) - /* Insert EXTERNAL_LEVEL bit into LPCR at the MER bit position */ - rldicl. r0, r0, 64 - BOOK3S_IRQPRIO_EXTERNAL_LEVEL, 63 - rldimi r8, r0, LPCR_MER_SH, 63 - LPCR_MER_SH - beq 2f - - /* And if the guest EE is set, we can deliver immediately, else - * we return to the guest with MER set - */ - andi. r0, r11, MSR_EE - beq 2f - mtspr SPRN_SRR0, r10 - mtspr SPRN_SRR1, r11 - li r10, BOOK3S_INTERRUPT_EXTERNAL - li r11, (MSR_ME << 1) | 1 /* synthesize MSR_SF | MSR_ME */ - rotldi r11, r11, 63 -2: mr r4, r9 - mtspr SPRN_LPCR, r8 - b fast_guest_return + /* Return to guest after delivering any pending interrupt */ + mr r4, r9 + b deliver_guest_interrupt ext_interrupt_to_host: @@ -975,13 +1093,194 @@ BEGIN_FTR_SECTION mtspr SPRN_SPURR,r4 END_FTR_SECTION_IFCLR(CPU_FTR_ARCH_201) + /* Save DEC */ + mfspr r5,SPRN_DEC + mftb r6 + extsw r5,r5 + add r5,r5,r6 + std r5,VCPU_DEC_EXPIRES(r9) + +BEGIN_FTR_SECTION + b 8f +END_FTR_SECTION_IFCLR(CPU_FTR_ARCH_207S) + /* Turn on TM so we can access TFHAR/TFIAR/TEXASR */ + mfmsr r8 + li r0, 1 + rldimi r8, r0, MSR_TM_LG, 63-MSR_TM_LG + mtmsrd r8 + + /* Save POWER8-specific registers */ + mfspr r5, SPRN_IAMR + mfspr r6, SPRN_PSPB + mfspr r7, SPRN_FSCR + std r5, VCPU_IAMR(r9) + stw r6, VCPU_PSPB(r9) + std r7, VCPU_FSCR(r9) + mfspr r5, SPRN_IC + mfspr r6, SPRN_VTB + mfspr r7, SPRN_TAR + std r5, VCPU_IC(r9) + std r6, VCPU_VTB(r9) + std r7, VCPU_TAR(r9) +#ifdef CONFIG_PPC_TRANSACTIONAL_MEM + mfspr r5, SPRN_TFHAR + mfspr r6, SPRN_TFIAR + mfspr r7, SPRN_TEXASR + std r5, VCPU_TFHAR(r9) + std r6, VCPU_TFIAR(r9) + std r7, VCPU_TEXASR(r9) +#endif + mfspr r8, SPRN_EBBHR + std r8, VCPU_EBBHR(r9) + mfspr r5, SPRN_EBBRR + mfspr r6, SPRN_BESCR + mfspr r7, SPRN_CSIGR + mfspr r8, SPRN_TACR + std r5, VCPU_EBBRR(r9) + std r6, VCPU_BESCR(r9) + std r7, VCPU_CSIGR(r9) + std r8, VCPU_TACR(r9) + mfspr r5, SPRN_TCSCR + mfspr r6, SPRN_ACOP + mfspr r7, SPRN_PID + mfspr r8, SPRN_WORT + std r5, VCPU_TCSCR(r9) + std r6, VCPU_ACOP(r9) + stw r7, VCPU_GUEST_PID(r9) + std r8, VCPU_WORT(r9) +8: + + /* Save and reset AMR and UAMOR before turning on the MMU */ +BEGIN_FTR_SECTION + mfspr r5,SPRN_AMR + mfspr r6,SPRN_UAMOR + std r5,VCPU_AMR(r9) + std r6,VCPU_UAMOR(r9) + li r6,0 + mtspr SPRN_AMR,r6 +END_FTR_SECTION_IFSET(CPU_FTR_ARCH_206) + + /* Switch DSCR back to host value */ +BEGIN_FTR_SECTION + mfspr r8, SPRN_DSCR + ld r7, HSTATE_DSCR(r13) + std r8, VCPU_DSCR(r9) + mtspr SPRN_DSCR, r7 +END_FTR_SECTION_IFSET(CPU_FTR_ARCH_206) + + /* Save non-volatile GPRs */ + std r14, VCPU_GPR(R14)(r9) + std r15, VCPU_GPR(R15)(r9) + std r16, VCPU_GPR(R16)(r9) + std r17, VCPU_GPR(R17)(r9) + std r18, VCPU_GPR(R18)(r9) + std r19, VCPU_GPR(R19)(r9) + std r20, VCPU_GPR(R20)(r9) + std r21, VCPU_GPR(R21)(r9) + std r22, VCPU_GPR(R22)(r9) + std r23, VCPU_GPR(R23)(r9) + std r24, VCPU_GPR(R24)(r9) + std r25, VCPU_GPR(R25)(r9) + std r26, VCPU_GPR(R26)(r9) + std r27, VCPU_GPR(R27)(r9) + std r28, VCPU_GPR(R28)(r9) + std r29, VCPU_GPR(R29)(r9) + std r30, VCPU_GPR(R30)(r9) + std r31, VCPU_GPR(R31)(r9) + + /* Save SPRGs */ + mfspr r3, SPRN_SPRG0 + mfspr r4, SPRN_SPRG1 + mfspr r5, SPRN_SPRG2 + mfspr r6, SPRN_SPRG3 + std r3, VCPU_SPRG0(r9) + std r4, VCPU_SPRG1(r9) + std r5, VCPU_SPRG2(r9) + std r6, VCPU_SPRG3(r9) + + /* save FP state */ + mr r3, r9 + bl kvmppc_save_fp + + /* Increment yield count if they have a VPA */ + ld r8, VCPU_VPA(r9) /* do they have a VPA? */ + cmpdi r8, 0 + beq 25f + lwz r3, LPPACA_YIELDCOUNT(r8) + addi r3, r3, 1 + stw r3, LPPACA_YIELDCOUNT(r8) + li r3, 1 + stb r3, VCPU_VPA_DIRTY(r9) +25: + /* Save PMU registers if requested */ + /* r8 and cr0.eq are live here */ + li r3, 1 + sldi r3, r3, 31 /* MMCR0_FC (freeze counters) bit */ + mfspr r4, SPRN_MMCR0 /* save MMCR0 */ + mtspr SPRN_MMCR0, r3 /* freeze all counters, disable ints */ + mfspr r6, SPRN_MMCRA +BEGIN_FTR_SECTION + /* On P7, clear MMCRA in order to disable SDAR updates */ + li r7, 0 + mtspr SPRN_MMCRA, r7 +END_FTR_SECTION_IFSET(CPU_FTR_ARCH_206) + isync + beq 21f /* if no VPA, save PMU stuff anyway */ + lbz r7, LPPACA_PMCINUSE(r8) + cmpwi r7, 0 /* did they ask for PMU stuff to be saved? */ + bne 21f + std r3, VCPU_MMCR(r9) /* if not, set saved MMCR0 to FC */ + b 22f +21: mfspr r5, SPRN_MMCR1 + mfspr r7, SPRN_SIAR + mfspr r8, SPRN_SDAR + std r4, VCPU_MMCR(r9) + std r5, VCPU_MMCR + 8(r9) + std r6, VCPU_MMCR + 16(r9) + std r7, VCPU_SIAR(r9) + std r8, VCPU_SDAR(r9) + mfspr r3, SPRN_PMC1 + mfspr r4, SPRN_PMC2 + mfspr r5, SPRN_PMC3 + mfspr r6, SPRN_PMC4 + mfspr r7, SPRN_PMC5 + mfspr r8, SPRN_PMC6 +BEGIN_FTR_SECTION + mfspr r10, SPRN_PMC7 + mfspr r11, SPRN_PMC8 +END_FTR_SECTION_IFSET(CPU_FTR_ARCH_201) + stw r3, VCPU_PMC(r9) + stw r4, VCPU_PMC + 4(r9) + stw r5, VCPU_PMC + 8(r9) + stw r6, VCPU_PMC + 12(r9) + stw r7, VCPU_PMC + 16(r9) + stw r8, VCPU_PMC + 20(r9) +BEGIN_FTR_SECTION + stw r10, VCPU_PMC + 24(r9) + stw r11, VCPU_PMC + 28(r9) +END_FTR_SECTION_IFSET(CPU_FTR_ARCH_201) +BEGIN_FTR_SECTION + mfspr r4, SPRN_MMCR2 + mfspr r5, SPRN_SIER + mfspr r6, SPRN_SPMC1 + mfspr r7, SPRN_SPMC2 + mfspr r8, SPRN_MMCRS + std r4, VCPU_MMCR + 24(r9) + std r5, VCPU_SIER(r9) + stw r6, VCPU_PMC + 24(r9) + stw r7, VCPU_PMC + 28(r9) + std r8, VCPU_MMCR + 32(r9) + lis r4, 0x8000 + mtspr SPRN_MMCRS, r4 +END_FTR_SECTION_IFSET(CPU_FTR_ARCH_207S) +22: /* Clear out SLB */ li r5,0 slbmte r5,r5 slbia ptesync -hdec_soon: /* r9 = vcpu, r12 = trap, r13 = paca */ +hdec_soon: /* r12 = trap, r13 = paca */ BEGIN_FTR_SECTION b 32f END_FTR_SECTION_IFSET(CPU_FTR_ARCH_201) @@ -1014,8 +1313,6 @@ END_FTR_SECTION_IFSET(CPU_FTR_ARCH_201) */ cmpwi r3,0x100 /* Are we the first here? */ bge 43f - cmpwi r3,1 /* Are any other threads in the guest? */ - ble 43f cmpwi r12,BOOK3S_INTERRUPT_HV_DECREMENTER beq 40f li r0,0 @@ -1026,7 +1323,7 @@ END_FTR_SECTION_IFSET(CPU_FTR_ARCH_201) * doesn't wake CPUs up from nap. */ lwz r3,VCORE_NAPPING_THREADS(r5) - lwz r4,VCPU_PTID(r9) + lbz r4,HSTATE_PTID(r13) li r0,1 sld r0,r0,r4 andc. r3,r3,r0 /* no sense IPI'ing ourselves */ @@ -1045,10 +1342,11 @@ END_FTR_SECTION_IFSET(CPU_FTR_ARCH_201) addi r6,r6,PACA_SIZE bne 42b +secondary_too_late: /* Secondary threads wait for primary to do partition switch */ -43: ld r4,VCPU_KVM(r9) /* pointer to struct kvm */ - ld r5,HSTATE_KVM_VCORE(r13) - lwz r3,VCPU_PTID(r9) +43: ld r5,HSTATE_KVM_VCORE(r13) + ld r4,VCORE_KVM(r5) /* pointer to struct kvm */ + lbz r3,HSTATE_PTID(r13) cmpwi r3,0 beq 15f HMT_LOW @@ -1076,6 +1374,15 @@ END_FTR_SECTION_IFSET(CPU_FTR_ARCH_201) mtspr SPRN_LPID,r7 isync +BEGIN_FTR_SECTION + /* DPDES is shared between threads */ + mfspr r7, SPRN_DPDES + std r7, VCORE_DPDES(r5) + /* clear DPDES so we don't get guest doorbells in the host */ + li r8, 0 + mtspr SPRN_DPDES, r8 +END_FTR_SECTION_IFSET(CPU_FTR_ARCH_207S) + /* Subtract timebase offset from timebase */ ld r8,VCORE_TB_OFFSET(r5) cmpdi r8,0 @@ -1113,7 +1420,8 @@ END_FTR_SECTION_IFSET(CPU_FTR_ARCH_201) * We have to lock against concurrent tlbies, and * we have to flush the whole TLB. */ -32: ld r4,VCPU_KVM(r9) /* pointer to struct kvm */ +32: ld r5,HSTATE_KVM_VCORE(r13) + ld r4,VCORE_KVM(r5) /* pointer to struct kvm */ /* Take the guest's tlbie_lock */ #ifdef __BIG_ENDIAN__ @@ -1203,6 +1511,56 @@ END_FTR_SECTION_IFSET(CPU_FTR_ARCH_201) add r5,r5,r6 std r5,VCPU_DEC_EXPIRES(r9) +BEGIN_FTR_SECTION + b 8f +END_FTR_SECTION_IFCLR(CPU_FTR_ARCH_207S) + /* Turn on TM so we can access TFHAR/TFIAR/TEXASR */ + mfmsr r8 + li r0, 1 + rldimi r8, r0, MSR_TM_LG, 63-MSR_TM_LG + mtmsrd r8 + + /* Save POWER8-specific registers */ + mfspr r5, SPRN_IAMR + mfspr r6, SPRN_PSPB + mfspr r7, SPRN_FSCR + std r5, VCPU_IAMR(r9) + stw r6, VCPU_PSPB(r9) + std r7, VCPU_FSCR(r9) + mfspr r5, SPRN_IC + mfspr r6, SPRN_VTB + mfspr r7, SPRN_TAR + std r5, VCPU_IC(r9) + std r6, VCPU_VTB(r9) + std r7, VCPU_TAR(r9) +#ifdef CONFIG_PPC_TRANSACTIONAL_MEM + mfspr r5, SPRN_TFHAR + mfspr r6, SPRN_TFIAR + mfspr r7, SPRN_TEXASR + std r5, VCPU_TFHAR(r9) + std r6, VCPU_TFIAR(r9) + std r7, VCPU_TEXASR(r9) +#endif + mfspr r8, SPRN_EBBHR + std r8, VCPU_EBBHR(r9) + mfspr r5, SPRN_EBBRR + mfspr r6, SPRN_BESCR + mfspr r7, SPRN_CSIGR + mfspr r8, SPRN_TACR + std r5, VCPU_EBBRR(r9) + std r6, VCPU_BESCR(r9) + std r7, VCPU_CSIGR(r9) + std r8, VCPU_TACR(r9) + mfspr r5, SPRN_TCSCR + mfspr r6, SPRN_ACOP + mfspr r7, SPRN_PID + mfspr r8, SPRN_WORT + std r5, VCPU_TCSCR(r9) + std r6, VCPU_ACOP(r9) + stw r7, VCPU_GUEST_PID(r9) + std r8, VCPU_WORT(r9) +8: + /* Save and reset AMR and UAMOR before turning on the MMU */ BEGIN_FTR_SECTION mfspr r5,SPRN_AMR @@ -1217,130 +1575,10 @@ END_FTR_SECTION_IFSET(CPU_FTR_ARCH_206) li r0, KVM_GUEST_MODE_NONE stb r0, HSTATE_IN_GUEST(r13) - /* Switch DSCR back to host value */ -BEGIN_FTR_SECTION - mfspr r8, SPRN_DSCR - ld r7, HSTATE_DSCR(r13) - std r8, VCPU_DSCR(r9) - mtspr SPRN_DSCR, r7 -END_FTR_SECTION_IFSET(CPU_FTR_ARCH_206) - - /* Save non-volatile GPRs */ - std r14, VCPU_GPR(R14)(r9) - std r15, VCPU_GPR(R15)(r9) - std r16, VCPU_GPR(R16)(r9) - std r17, VCPU_GPR(R17)(r9) - std r18, VCPU_GPR(R18)(r9) - std r19, VCPU_GPR(R19)(r9) - std r20, VCPU_GPR(R20)(r9) - std r21, VCPU_GPR(R21)(r9) - std r22, VCPU_GPR(R22)(r9) - std r23, VCPU_GPR(R23)(r9) - std r24, VCPU_GPR(R24)(r9) - std r25, VCPU_GPR(R25)(r9) - std r26, VCPU_GPR(R26)(r9) - std r27, VCPU_GPR(R27)(r9) - std r28, VCPU_GPR(R28)(r9) - std r29, VCPU_GPR(R29)(r9) - std r30, VCPU_GPR(R30)(r9) - std r31, VCPU_GPR(R31)(r9) - - /* Save SPRGs */ - mfspr r3, SPRN_SPRG0 - mfspr r4, SPRN_SPRG1 - mfspr r5, SPRN_SPRG2 - mfspr r6, SPRN_SPRG3 - std r3, VCPU_SPRG0(r9) - std r4, VCPU_SPRG1(r9) - std r5, VCPU_SPRG2(r9) - std r6, VCPU_SPRG3(r9) - - /* save FP state */ - mr r3, r9 - bl .kvmppc_save_fp - - /* Increment yield count if they have a VPA */ - ld r8, VCPU_VPA(r9) /* do they have a VPA? */ - cmpdi r8, 0 - beq 25f - lwz r3, LPPACA_YIELDCOUNT(r8) - addi r3, r3, 1 - stw r3, LPPACA_YIELDCOUNT(r8) - li r3, 1 - stb r3, VCPU_VPA_DIRTY(r9) -25: - /* Save PMU registers if requested */ - /* r8 and cr0.eq are live here */ - li r3, 1 - sldi r3, r3, 31 /* MMCR0_FC (freeze counters) bit */ - mfspr r4, SPRN_MMCR0 /* save MMCR0 */ - mtspr SPRN_MMCR0, r3 /* freeze all counters, disable ints */ - mfspr r6, SPRN_MMCRA -BEGIN_FTR_SECTION - /* On P7, clear MMCRA in order to disable SDAR updates */ - li r7, 0 - mtspr SPRN_MMCRA, r7 -END_FTR_SECTION_IFSET(CPU_FTR_ARCH_206) - isync - beq 21f /* if no VPA, save PMU stuff anyway */ - lbz r7, LPPACA_PMCINUSE(r8) - cmpwi r7, 0 /* did they ask for PMU stuff to be saved? */ - bne 21f - std r3, VCPU_MMCR(r9) /* if not, set saved MMCR0 to FC */ - b 22f -21: mfspr r5, SPRN_MMCR1 - mfspr r7, SPRN_SIAR - mfspr r8, SPRN_SDAR - std r4, VCPU_MMCR(r9) - std r5, VCPU_MMCR + 8(r9) - std r6, VCPU_MMCR + 16(r9) - std r7, VCPU_SIAR(r9) - std r8, VCPU_SDAR(r9) - mfspr r3, SPRN_PMC1 - mfspr r4, SPRN_PMC2 - mfspr r5, SPRN_PMC3 - mfspr r6, SPRN_PMC4 - mfspr r7, SPRN_PMC5 - mfspr r8, SPRN_PMC6 -BEGIN_FTR_SECTION - mfspr r10, SPRN_PMC7 - mfspr r11, SPRN_PMC8 -END_FTR_SECTION_IFSET(CPU_FTR_ARCH_201) - stw r3, VCPU_PMC(r9) - stw r4, VCPU_PMC + 4(r9) - stw r5, VCPU_PMC + 8(r9) - stw r6, VCPU_PMC + 12(r9) - stw r7, VCPU_PMC + 16(r9) - stw r8, VCPU_PMC + 20(r9) -BEGIN_FTR_SECTION - stw r10, VCPU_PMC + 24(r9) - stw r11, VCPU_PMC + 28(r9) -END_FTR_SECTION_IFSET(CPU_FTR_ARCH_201) -22: ld r0, 112+PPC_LR_STKOFF(r1) addi r1, r1, 112 mtlr r0 blr -secondary_too_late: - ld r5,HSTATE_KVM_VCORE(r13) - HMT_LOW -13: lbz r3,VCORE_IN_GUEST(r5) - cmpwi r3,0 - bne 13b - HMT_MEDIUM - li r0, KVM_GUEST_MODE_NONE - stb r0, HSTATE_IN_GUEST(r13) - ld r11,PACA_SLBSHADOWPTR(r13) - - .rept SLB_NUM_BOLTED - ld r5,SLBSHADOW_SAVEAREA(r11) - ld r6,SLBSHADOW_SAVEAREA+8(r11) - andis. r7,r5,SLB_ESID_V@h - beq 1f - slbmte r6,r5 -1: addi r11,r11,16 - .endr - b 22b /* * Check whether an HDSI is an HPTE not found fault or something else. @@ -1386,8 +1624,7 @@ kvmppc_hdsi: mtspr SPRN_SRR0, r10 mtspr SPRN_SRR1, r11 li r10, BOOK3S_INTERRUPT_DATA_STORAGE - li r11, (MSR_ME << 1) | 1 /* synthesize MSR_SF | MSR_ME */ - rotldi r11, r11, 63 + ld r11, VCPU_INTR_MSR(r9) fast_interrupt_c_return: 6: ld r7, VCPU_CTR(r9) lwz r8, VCPU_XER(r9) @@ -1456,8 +1693,7 @@ kvmppc_hisi: 1: mtspr SPRN_SRR0, r10 mtspr SPRN_SRR1, r11 li r10, BOOK3S_INTERRUPT_INST_STORAGE - li r11, (MSR_ME << 1) | 1 /* synthesize MSR_SF | MSR_ME */ - rotldi r11, r11, 63 + ld r11, VCPU_INTR_MSR(r9) b fast_interrupt_c_return 3: ld r6, VCPU_KVM(r9) /* not relocated, use VRMA */ @@ -1474,7 +1710,8 @@ kvmppc_hisi: hcall_try_real_mode: ld r3,VCPU_GPR(R3)(r9) andi. r0,r11,MSR_PR - bne guest_exit_cont + /* sc 1 from userspace - reflect to guest syscall */ + bne sc_1_fast_return clrrdi r3,r3,2 cmpldi r3,hcall_real_table_end - hcall_real_table bge guest_exit_cont @@ -1495,6 +1732,14 @@ hcall_try_real_mode: ld r11,VCPU_MSR(r4) b fast_guest_return +sc_1_fast_return: + mtspr SPRN_SRR0,r10 + mtspr SPRN_SRR1,r11 + li r10, BOOK3S_INTERRUPT_SYSCALL + ld r11, VCPU_INTR_MSR(r9) + mr r4,r9 + b fast_guest_return + /* We've attempted a real mode hcall, but it's punted it back * to userspace. We need to restore some clobbered volatiles * before resuming the pass-it-to-qemu path */ @@ -1588,14 +1833,34 @@ hcall_real_table: .long 0 /* 0x11c */ .long 0 /* 0x120 */ .long .kvmppc_h_bulk_remove - hcall_real_table + .long 0 /* 0x128 */ + .long 0 /* 0x12c */ + .long 0 /* 0x130 */ + .long .kvmppc_h_set_xdabr - hcall_real_table hcall_real_table_end: ignore_hdec: mr r4,r9 b fast_guest_return +_GLOBAL(kvmppc_h_set_xdabr) + andi. r0, r5, DABRX_USER | DABRX_KERNEL + beq 6f + li r0, DABRX_USER | DABRX_KERNEL | DABRX_BTI + andc. r0, r5, r0 + beq 3f +6: li r3, H_PARAMETER + blr + _GLOBAL(kvmppc_h_set_dabr) + li r5, DABRX_USER | DABRX_KERNEL +3: +BEGIN_FTR_SECTION + b 2f +END_FTR_SECTION_IFSET(CPU_FTR_ARCH_207S) std r4,VCPU_DABR(r3) + stw r5, VCPU_DABRX(r3) + mtspr SPRN_DABRX, r5 /* Work around P7 bug where DABR can get corrupted on mtspr */ 1: mtspr SPRN_DABR,r4 mfspr r5, SPRN_DABR @@ -1605,6 +1870,17 @@ _GLOBAL(kvmppc_h_set_dabr) li r3,0 blr + /* Emulate H_SET_DABR/X on P8 for the sake of compat mode guests */ +2: rlwimi r5, r4, 5, DAWRX_DR | DAWRX_DW + rlwimi r5, r4, 1, DAWRX_WT + clrrdi r4, r4, 3 + std r4, VCPU_DAWR(r3) + std r5, VCPU_DAWRX(r3) + mtspr SPRN_DAWR, r4 + mtspr SPRN_DAWRX, r5 + li r3, 0 + blr + _GLOBAL(kvmppc_h_cede) ori r11,r11,MSR_EE std r11,VCPU_MSR(r3) @@ -1628,7 +1904,7 @@ END_FTR_SECTION_IFCLR(CPU_FTR_ARCH_206) * up to the host. */ ld r5,HSTATE_KVM_VCORE(r13) - lwz r6,VCPU_PTID(r3) + lbz r6,HSTATE_PTID(r13) lwz r8,VCORE_ENTRY_EXIT(r5) clrldi r8,r8,56 li r0,1 @@ -1643,9 +1919,8 @@ END_FTR_SECTION_IFCLR(CPU_FTR_ARCH_206) bne 31b /* order napping_threads update vs testing entry_exit_count */ isync - li r0,1 + li r0,NAPPING_CEDE stb r0,HSTATE_NAPPING(r13) - mr r4,r3 lwz r7,VCORE_ENTRY_EXIT(r5) cmpwi r7,0x100 bge 33f /* another thread already exiting */ @@ -1677,16 +1952,19 @@ END_FTR_SECTION_IFCLR(CPU_FTR_ARCH_206) std r31, VCPU_GPR(R31)(r3) /* save FP state */ - bl .kvmppc_save_fp + bl kvmppc_save_fp /* - * Take a nap until a decrementer or external interrupt occurs, - * with PECE1 (wake on decr) and PECE0 (wake on external) set in LPCR + * Take a nap until a decrementer or external or doobell interrupt + * occurs, with PECE1, PECE0 and PECEDP set in LPCR */ li r0,1 stb r0,HSTATE_HWTHREAD_REQ(r13) mfspr r5,SPRN_LPCR ori r5,r5,LPCR_PECE0 | LPCR_PECE1 +BEGIN_FTR_SECTION + oris r5,r5,LPCR_PECEDP@h +END_FTR_SECTION_IFSET(CPU_FTR_ARCH_207S) mtspr SPRN_LPCR,r5 isync li r0, 0 @@ -1698,6 +1976,11 @@ END_FTR_SECTION_IFCLR(CPU_FTR_ARCH_206) nap b . +33: mr r4, r3 + li r3, 0 + li r12, 0 + b 34f + kvm_end_cede: /* get vcpu pointer */ ld r4, HSTATE_KVM_VCPU(r13) @@ -1727,12 +2010,15 @@ kvm_end_cede: ld r29, VCPU_GPR(R29)(r4) ld r30, VCPU_GPR(R30)(r4) ld r31, VCPU_GPR(R31)(r4) + + /* Check the wake reason in SRR1 to see why we got here */ + bl kvmppc_check_wake_reason /* clear our bit in vcore->napping_threads */ -33: ld r5,HSTATE_KVM_VCORE(r13) - lwz r3,VCPU_PTID(r4) +34: ld r5,HSTATE_KVM_VCORE(r13) + lbz r7,HSTATE_PTID(r13) li r0,1 - sld r0,r0,r3 + sld r0,r0,r7 addi r6,r5,VCORE_NAPPING_THREADS 32: lwarx r7,0,r6 andc r7,r7,r0 @@ -1741,23 +2027,18 @@ kvm_end_cede: li r0,0 stb r0,HSTATE_NAPPING(r13) - /* Check the wake reason in SRR1 to see why we got here */ - mfspr r3, SPRN_SRR1 - rlwinm r3, r3, 44-31, 0x7 /* extract wake reason field */ - cmpwi r3, 4 /* was it an external interrupt? */ - li r12, BOOK3S_INTERRUPT_EXTERNAL + /* See if the wake reason means we need to exit */ + stw r12, VCPU_TRAP(r4) mr r9, r4 - ld r10, VCPU_PC(r9) - ld r11, VCPU_MSR(r9) - beq do_ext_interrupt /* if so */ + cmpdi r3, 0 + bgt guest_exit_cont /* see if any other thread is already exiting */ lwz r0,VCORE_ENTRY_EXIT(r5) cmpwi r0,0x100 - blt kvmppc_cede_reentry /* if not go back to guest */ + bge guest_exit_cont - /* some threads are exiting, so go to the guest exit path */ - b hcall_real_fallback + b kvmppc_cede_reentry /* if not go back to guest */ /* cede when already previously prodded case */ kvm_cede_prodded: @@ -1783,11 +2064,48 @@ machine_check_realmode: beq mc_cont /* If not, deliver a machine check. SRR0/1 are already set */ li r10, BOOK3S_INTERRUPT_MACHINE_CHECK - li r11, (MSR_ME << 1) | 1 /* synthesize MSR_SF | MSR_ME */ - rotldi r11, r11, 63 + ld r11, VCPU_INTR_MSR(r9) b fast_interrupt_c_return /* + * Check the reason we woke from nap, and take appropriate action. + * Returns: + * 0 if nothing needs to be done + * 1 if something happened that needs to be handled by the host + * -1 if there was a guest wakeup (IPI) + * + * Also sets r12 to the interrupt vector for any interrupt that needs + * to be handled now by the host (0x500 for external interrupt), or zero. + */ +kvmppc_check_wake_reason: + mfspr r6, SPRN_SRR1 +BEGIN_FTR_SECTION + rlwinm r6, r6, 45-31, 0xf /* extract wake reason field (P8) */ +FTR_SECTION_ELSE + rlwinm r6, r6, 45-31, 0xe /* P7 wake reason field is 3 bits */ +ALT_FTR_SECTION_END_IFSET(CPU_FTR_ARCH_207S) + cmpwi r6, 8 /* was it an external interrupt? */ + li r12, BOOK3S_INTERRUPT_EXTERNAL + beq kvmppc_read_intr /* if so, see what it was */ + li r3, 0 + li r12, 0 + cmpwi r6, 6 /* was it the decrementer? */ + beq 0f +BEGIN_FTR_SECTION + cmpwi r6, 5 /* privileged doorbell? */ + beq 0f + cmpwi r6, 3 /* hypervisor doorbell? */ + beq 3f +END_FTR_SECTION_IFSET(CPU_FTR_ARCH_207S) + li r3, 1 /* anything else, return 1 */ +0: blr + + /* hypervisor doorbell */ +3: li r12, BOOK3S_INTERRUPT_H_DOORBELL + li r3, 1 + blr + +/* * Determine what sort of external interrupt is pending (if any). * Returns: * 0 if no interrupt is pending @@ -1818,7 +2136,6 @@ kvmppc_read_intr: * interrupts directly to the guest */ cmpwi r3, XICS_IPI /* if there is, is it an IPI? */ - li r3, 1 bne 42f /* It's an IPI, clear the MFRR and EOI it */ @@ -1844,19 +2161,25 @@ kvmppc_read_intr: * before exit, it will be picked up by the host ICP driver */ stw r0, HSTATE_SAVED_XIRR(r13) + li r3, 1 b 1b 43: /* We raced with the host, we need to resend that IPI, bummer */ li r0, IPI_PRIORITY stbcix r0, r6, r8 /* set the IPI */ sync + li r3, 1 b 1b /* * Save away FP, VMX and VSX registers. * r3 = vcpu pointer + * N.B. r30 and r31 are volatile across this function, + * thus it is not callable from C. */ -_GLOBAL(kvmppc_save_fp) +kvmppc_save_fp: + mflr r30 + mr r31,r3 mfmsr r5 ori r8,r5,MSR_FP #ifdef CONFIG_ALTIVEC @@ -1871,42 +2194,17 @@ END_FTR_SECTION_IFSET(CPU_FTR_VSX) #endif mtmsrd r8 isync -#ifdef CONFIG_VSX -BEGIN_FTR_SECTION - reg = 0 - .rept 32 - li r6,reg*16+VCPU_VSRS - STXVD2X(reg,R6,R3) - reg = reg + 1 - .endr -FTR_SECTION_ELSE -#endif - reg = 0 - .rept 32 - stfd reg,reg*8+VCPU_FPRS(r3) - reg = reg + 1 - .endr -#ifdef CONFIG_VSX -ALT_FTR_SECTION_END_IFSET(CPU_FTR_VSX) -#endif - mffs fr0 - stfd fr0,VCPU_FPSCR(r3) - + addi r3,r3,VCPU_FPRS + bl .store_fp_state #ifdef CONFIG_ALTIVEC BEGIN_FTR_SECTION - reg = 0 - .rept 32 - li r6,reg*16+VCPU_VRS - stvx reg,r6,r3 - reg = reg + 1 - .endr - mfvscr vr0 - li r6,VCPU_VSCR - stvx vr0,r6,r3 + addi r3,r31,VCPU_VRS + bl .store_vr_state END_FTR_SECTION_IFSET(CPU_FTR_ALTIVEC) #endif mfspr r6,SPRN_VRSAVE stw r6,VCPU_VRSAVE(r3) + mtlr r30 mtmsrd r5 isync blr @@ -1914,9 +2212,12 @@ END_FTR_SECTION_IFSET(CPU_FTR_ALTIVEC) /* * Load up FP, VMX and VSX registers * r4 = vcpu pointer + * N.B. r30 and r31 are volatile across this function, + * thus it is not callable from C. */ - .globl kvmppc_load_fp kvmppc_load_fp: + mflr r30 + mr r31,r4 mfmsr r9 ori r8,r9,MSR_FP #ifdef CONFIG_ALTIVEC @@ -1931,42 +2232,18 @@ END_FTR_SECTION_IFSET(CPU_FTR_VSX) #endif mtmsrd r8 isync - lfd fr0,VCPU_FPSCR(r4) - MTFSF_L(fr0) -#ifdef CONFIG_VSX -BEGIN_FTR_SECTION - reg = 0 - .rept 32 - li r7,reg*16+VCPU_VSRS - LXVD2X(reg,R7,R4) - reg = reg + 1 - .endr -FTR_SECTION_ELSE -#endif - reg = 0 - .rept 32 - lfd reg,reg*8+VCPU_FPRS(r4) - reg = reg + 1 - .endr -#ifdef CONFIG_VSX -ALT_FTR_SECTION_END_IFSET(CPU_FTR_VSX) -#endif - + addi r3,r4,VCPU_FPRS + bl .load_fp_state #ifdef CONFIG_ALTIVEC BEGIN_FTR_SECTION - li r7,VCPU_VSCR - lvx vr0,r7,r4 - mtvscr vr0 - reg = 0 - .rept 32 - li r7,reg*16+VCPU_VRS - lvx reg,r7,r4 - reg = reg + 1 - .endr + addi r3,r31,VCPU_VRS + bl .load_vr_state END_FTR_SECTION_IFSET(CPU_FTR_ALTIVEC) #endif lwz r7,VCPU_VRSAVE(r4) mtspr SPRN_VRSAVE,r7 + mtlr r30 + mr r4,r31 blr /* diff --git a/arch/powerpc/kvm/book3s_paired_singles.c b/arch/powerpc/kvm/book3s_paired_singles.c index a59a25a1321..c1abd95063f 100644 --- a/arch/powerpc/kvm/book3s_paired_singles.c +++ b/arch/powerpc/kvm/book3s_paired_singles.c @@ -160,7 +160,7 @@ static inline void kvmppc_sync_qpr(struct kvm_vcpu *vcpu, int rt) { - kvm_cvt_df(&vcpu->arch.fpr[rt], &vcpu->arch.qpr[rt]); + kvm_cvt_df(&VCPU_FPR(vcpu, rt), &vcpu->arch.qpr[rt]); } static void kvmppc_inject_pf(struct kvm_vcpu *vcpu, ulong eaddr, bool is_store) @@ -207,11 +207,11 @@ static int kvmppc_emulate_fpr_load(struct kvm_run *run, struct kvm_vcpu *vcpu, /* put in registers */ switch (ls_type) { case FPU_LS_SINGLE: - kvm_cvt_fd((u32*)tmp, &vcpu->arch.fpr[rs]); + kvm_cvt_fd((u32*)tmp, &VCPU_FPR(vcpu, rs)); vcpu->arch.qpr[rs] = *((u32*)tmp); break; case FPU_LS_DOUBLE: - vcpu->arch.fpr[rs] = *((u64*)tmp); + VCPU_FPR(vcpu, rs) = *((u64*)tmp); break; } @@ -233,18 +233,18 @@ static int kvmppc_emulate_fpr_store(struct kvm_run *run, struct kvm_vcpu *vcpu, switch (ls_type) { case FPU_LS_SINGLE: - kvm_cvt_df(&vcpu->arch.fpr[rs], (u32*)tmp); + kvm_cvt_df(&VCPU_FPR(vcpu, rs), (u32*)tmp); val = *((u32*)tmp); len = sizeof(u32); break; case FPU_LS_SINGLE_LOW: - *((u32*)tmp) = vcpu->arch.fpr[rs]; - val = vcpu->arch.fpr[rs] & 0xffffffff; + *((u32*)tmp) = VCPU_FPR(vcpu, rs); + val = VCPU_FPR(vcpu, rs) & 0xffffffff; len = sizeof(u32); break; case FPU_LS_DOUBLE: - *((u64*)tmp) = vcpu->arch.fpr[rs]; - val = vcpu->arch.fpr[rs]; + *((u64*)tmp) = VCPU_FPR(vcpu, rs); + val = VCPU_FPR(vcpu, rs); len = sizeof(u64); break; default: @@ -301,7 +301,7 @@ static int kvmppc_emulate_psq_load(struct kvm_run *run, struct kvm_vcpu *vcpu, emulated = EMULATE_DONE; /* put in registers */ - kvm_cvt_fd(&tmp[0], &vcpu->arch.fpr[rs]); + kvm_cvt_fd(&tmp[0], &VCPU_FPR(vcpu, rs)); vcpu->arch.qpr[rs] = tmp[1]; dprintk(KERN_INFO "KVM: PSQ_LD [0x%x, 0x%x] at 0x%lx (%d)\n", tmp[0], @@ -319,7 +319,7 @@ static int kvmppc_emulate_psq_store(struct kvm_run *run, struct kvm_vcpu *vcpu, u32 tmp[2]; int len = w ? sizeof(u32) : sizeof(u64); - kvm_cvt_df(&vcpu->arch.fpr[rs], &tmp[0]); + kvm_cvt_df(&VCPU_FPR(vcpu, rs), &tmp[0]); tmp[1] = vcpu->arch.qpr[rs]; r = kvmppc_st(vcpu, &addr, len, tmp, true); @@ -512,7 +512,6 @@ static int kvmppc_ps_three_in(struct kvm_vcpu *vcpu, bool rc, u32 *src2, u32 *src3)) { u32 *qpr = vcpu->arch.qpr; - u64 *fpr = vcpu->arch.fpr; u32 ps0_out; u32 ps0_in1, ps0_in2, ps0_in3; u32 ps1_in1, ps1_in2, ps1_in3; @@ -521,20 +520,20 @@ static int kvmppc_ps_three_in(struct kvm_vcpu *vcpu, bool rc, WARN_ON(rc); /* PS0 */ - kvm_cvt_df(&fpr[reg_in1], &ps0_in1); - kvm_cvt_df(&fpr[reg_in2], &ps0_in2); - kvm_cvt_df(&fpr[reg_in3], &ps0_in3); + kvm_cvt_df(&VCPU_FPR(vcpu, reg_in1), &ps0_in1); + kvm_cvt_df(&VCPU_FPR(vcpu, reg_in2), &ps0_in2); + kvm_cvt_df(&VCPU_FPR(vcpu, reg_in3), &ps0_in3); if (scalar & SCALAR_LOW) ps0_in2 = qpr[reg_in2]; - func(&vcpu->arch.fpscr, &ps0_out, &ps0_in1, &ps0_in2, &ps0_in3); + func(&vcpu->arch.fp.fpscr, &ps0_out, &ps0_in1, &ps0_in2, &ps0_in3); dprintk(KERN_INFO "PS3 ps0 -> f(0x%x, 0x%x, 0x%x) = 0x%x\n", ps0_in1, ps0_in2, ps0_in3, ps0_out); if (!(scalar & SCALAR_NO_PS0)) - kvm_cvt_fd(&ps0_out, &fpr[reg_out]); + kvm_cvt_fd(&ps0_out, &VCPU_FPR(vcpu, reg_out)); /* PS1 */ ps1_in1 = qpr[reg_in1]; @@ -545,7 +544,7 @@ static int kvmppc_ps_three_in(struct kvm_vcpu *vcpu, bool rc, ps1_in2 = ps0_in2; if (!(scalar & SCALAR_NO_PS1)) - func(&vcpu->arch.fpscr, &qpr[reg_out], &ps1_in1, &ps1_in2, &ps1_in3); + func(&vcpu->arch.fp.fpscr, &qpr[reg_out], &ps1_in1, &ps1_in2, &ps1_in3); dprintk(KERN_INFO "PS3 ps1 -> f(0x%x, 0x%x, 0x%x) = 0x%x\n", ps1_in1, ps1_in2, ps1_in3, qpr[reg_out]); @@ -561,7 +560,6 @@ static int kvmppc_ps_two_in(struct kvm_vcpu *vcpu, bool rc, u32 *src2)) { u32 *qpr = vcpu->arch.qpr; - u64 *fpr = vcpu->arch.fpr; u32 ps0_out; u32 ps0_in1, ps0_in2; u32 ps1_out; @@ -571,20 +569,20 @@ static int kvmppc_ps_two_in(struct kvm_vcpu *vcpu, bool rc, WARN_ON(rc); /* PS0 */ - kvm_cvt_df(&fpr[reg_in1], &ps0_in1); + kvm_cvt_df(&VCPU_FPR(vcpu, reg_in1), &ps0_in1); if (scalar & SCALAR_LOW) ps0_in2 = qpr[reg_in2]; else - kvm_cvt_df(&fpr[reg_in2], &ps0_in2); + kvm_cvt_df(&VCPU_FPR(vcpu, reg_in2), &ps0_in2); - func(&vcpu->arch.fpscr, &ps0_out, &ps0_in1, &ps0_in2); + func(&vcpu->arch.fp.fpscr, &ps0_out, &ps0_in1, &ps0_in2); if (!(scalar & SCALAR_NO_PS0)) { dprintk(KERN_INFO "PS2 ps0 -> f(0x%x, 0x%x) = 0x%x\n", ps0_in1, ps0_in2, ps0_out); - kvm_cvt_fd(&ps0_out, &fpr[reg_out]); + kvm_cvt_fd(&ps0_out, &VCPU_FPR(vcpu, reg_out)); } /* PS1 */ @@ -594,7 +592,7 @@ static int kvmppc_ps_two_in(struct kvm_vcpu *vcpu, bool rc, if (scalar & SCALAR_HIGH) ps1_in2 = ps0_in2; - func(&vcpu->arch.fpscr, &ps1_out, &ps1_in1, &ps1_in2); + func(&vcpu->arch.fp.fpscr, &ps1_out, &ps1_in1, &ps1_in2); if (!(scalar & SCALAR_NO_PS1)) { qpr[reg_out] = ps1_out; @@ -612,7 +610,6 @@ static int kvmppc_ps_one_in(struct kvm_vcpu *vcpu, bool rc, u32 *dst, u32 *src1)) { u32 *qpr = vcpu->arch.qpr; - u64 *fpr = vcpu->arch.fpr; u32 ps0_out, ps0_in; u32 ps1_in; @@ -620,17 +617,17 @@ static int kvmppc_ps_one_in(struct kvm_vcpu *vcpu, bool rc, WARN_ON(rc); /* PS0 */ - kvm_cvt_df(&fpr[reg_in], &ps0_in); - func(&vcpu->arch.fpscr, &ps0_out, &ps0_in); + kvm_cvt_df(&VCPU_FPR(vcpu, reg_in), &ps0_in); + func(&vcpu->arch.fp.fpscr, &ps0_out, &ps0_in); dprintk(KERN_INFO "PS1 ps0 -> f(0x%x) = 0x%x\n", ps0_in, ps0_out); - kvm_cvt_fd(&ps0_out, &fpr[reg_out]); + kvm_cvt_fd(&ps0_out, &VCPU_FPR(vcpu, reg_out)); /* PS1 */ ps1_in = qpr[reg_in]; - func(&vcpu->arch.fpscr, &qpr[reg_out], &ps1_in); + func(&vcpu->arch.fp.fpscr, &qpr[reg_out], &ps1_in); dprintk(KERN_INFO "PS1 ps1 -> f(0x%x) = 0x%x\n", ps1_in, qpr[reg_out]); @@ -649,10 +646,10 @@ int kvmppc_emulate_paired_single(struct kvm_run *run, struct kvm_vcpu *vcpu) int ax_rc = inst_get_field(inst, 21, 25); short full_d = inst_get_field(inst, 16, 31); - u64 *fpr_d = &vcpu->arch.fpr[ax_rd]; - u64 *fpr_a = &vcpu->arch.fpr[ax_ra]; - u64 *fpr_b = &vcpu->arch.fpr[ax_rb]; - u64 *fpr_c = &vcpu->arch.fpr[ax_rc]; + u64 *fpr_d = &VCPU_FPR(vcpu, ax_rd); + u64 *fpr_a = &VCPU_FPR(vcpu, ax_ra); + u64 *fpr_b = &VCPU_FPR(vcpu, ax_rb); + u64 *fpr_c = &VCPU_FPR(vcpu, ax_rc); bool rcomp = (inst & 1) ? true : false; u32 cr = kvmppc_get_cr(vcpu); @@ -674,11 +671,11 @@ int kvmppc_emulate_paired_single(struct kvm_run *run, struct kvm_vcpu *vcpu) /* Do we need to clear FE0 / FE1 here? Don't think so. */ #ifdef DEBUG - for (i = 0; i < ARRAY_SIZE(vcpu->arch.fpr); i++) { + for (i = 0; i < ARRAY_SIZE(vcpu->arch.fp.fpr); i++) { u32 f; - kvm_cvt_df(&vcpu->arch.fpr[i], &f); + kvm_cvt_df(&VCPU_FPR(vcpu, i), &f); dprintk(KERN_INFO "FPR[%d] = 0x%x / 0x%llx QPR[%d] = 0x%x\n", - i, f, vcpu->arch.fpr[i], i, vcpu->arch.qpr[i]); + i, f, VCPU_FPR(vcpu, i), i, vcpu->arch.qpr[i]); } #endif @@ -764,8 +761,8 @@ int kvmppc_emulate_paired_single(struct kvm_run *run, struct kvm_vcpu *vcpu) break; } case OP_4X_PS_NEG: - vcpu->arch.fpr[ax_rd] = vcpu->arch.fpr[ax_rb]; - vcpu->arch.fpr[ax_rd] ^= 0x8000000000000000ULL; + VCPU_FPR(vcpu, ax_rd) = VCPU_FPR(vcpu, ax_rb); + VCPU_FPR(vcpu, ax_rd) ^= 0x8000000000000000ULL; vcpu->arch.qpr[ax_rd] = vcpu->arch.qpr[ax_rb]; vcpu->arch.qpr[ax_rd] ^= 0x80000000; break; @@ -775,7 +772,7 @@ int kvmppc_emulate_paired_single(struct kvm_run *run, struct kvm_vcpu *vcpu) break; case OP_4X_PS_MR: WARN_ON(rcomp); - vcpu->arch.fpr[ax_rd] = vcpu->arch.fpr[ax_rb]; + VCPU_FPR(vcpu, ax_rd) = VCPU_FPR(vcpu, ax_rb); vcpu->arch.qpr[ax_rd] = vcpu->arch.qpr[ax_rb]; break; case OP_4X_PS_CMPO1: @@ -784,44 +781,44 @@ int kvmppc_emulate_paired_single(struct kvm_run *run, struct kvm_vcpu *vcpu) break; case OP_4X_PS_NABS: WARN_ON(rcomp); - vcpu->arch.fpr[ax_rd] = vcpu->arch.fpr[ax_rb]; - vcpu->arch.fpr[ax_rd] |= 0x8000000000000000ULL; + VCPU_FPR(vcpu, ax_rd) = VCPU_FPR(vcpu, ax_rb); + VCPU_FPR(vcpu, ax_rd) |= 0x8000000000000000ULL; vcpu->arch.qpr[ax_rd] = vcpu->arch.qpr[ax_rb]; vcpu->arch.qpr[ax_rd] |= 0x80000000; break; case OP_4X_PS_ABS: WARN_ON(rcomp); - vcpu->arch.fpr[ax_rd] = vcpu->arch.fpr[ax_rb]; - vcpu->arch.fpr[ax_rd] &= ~0x8000000000000000ULL; + VCPU_FPR(vcpu, ax_rd) = VCPU_FPR(vcpu, ax_rb); + VCPU_FPR(vcpu, ax_rd) &= ~0x8000000000000000ULL; vcpu->arch.qpr[ax_rd] = vcpu->arch.qpr[ax_rb]; vcpu->arch.qpr[ax_rd] &= ~0x80000000; break; case OP_4X_PS_MERGE00: WARN_ON(rcomp); - vcpu->arch.fpr[ax_rd] = vcpu->arch.fpr[ax_ra]; - /* vcpu->arch.qpr[ax_rd] = vcpu->arch.fpr[ax_rb]; */ - kvm_cvt_df(&vcpu->arch.fpr[ax_rb], + VCPU_FPR(vcpu, ax_rd) = VCPU_FPR(vcpu, ax_ra); + /* vcpu->arch.qpr[ax_rd] = VCPU_FPR(vcpu, ax_rb); */ + kvm_cvt_df(&VCPU_FPR(vcpu, ax_rb), &vcpu->arch.qpr[ax_rd]); break; case OP_4X_PS_MERGE01: WARN_ON(rcomp); - vcpu->arch.fpr[ax_rd] = vcpu->arch.fpr[ax_ra]; + VCPU_FPR(vcpu, ax_rd) = VCPU_FPR(vcpu, ax_ra); vcpu->arch.qpr[ax_rd] = vcpu->arch.qpr[ax_rb]; break; case OP_4X_PS_MERGE10: WARN_ON(rcomp); - /* vcpu->arch.fpr[ax_rd] = vcpu->arch.qpr[ax_ra]; */ + /* VCPU_FPR(vcpu, ax_rd) = vcpu->arch.qpr[ax_ra]; */ kvm_cvt_fd(&vcpu->arch.qpr[ax_ra], - &vcpu->arch.fpr[ax_rd]); - /* vcpu->arch.qpr[ax_rd] = vcpu->arch.fpr[ax_rb]; */ - kvm_cvt_df(&vcpu->arch.fpr[ax_rb], + &VCPU_FPR(vcpu, ax_rd)); + /* vcpu->arch.qpr[ax_rd] = VCPU_FPR(vcpu, ax_rb); */ + kvm_cvt_df(&VCPU_FPR(vcpu, ax_rb), &vcpu->arch.qpr[ax_rd]); break; case OP_4X_PS_MERGE11: WARN_ON(rcomp); - /* vcpu->arch.fpr[ax_rd] = vcpu->arch.qpr[ax_ra]; */ + /* VCPU_FPR(vcpu, ax_rd) = vcpu->arch.qpr[ax_ra]; */ kvm_cvt_fd(&vcpu->arch.qpr[ax_ra], - &vcpu->arch.fpr[ax_rd]); + &VCPU_FPR(vcpu, ax_rd)); vcpu->arch.qpr[ax_rd] = vcpu->arch.qpr[ax_rb]; break; } @@ -856,7 +853,7 @@ int kvmppc_emulate_paired_single(struct kvm_run *run, struct kvm_vcpu *vcpu) case OP_4A_PS_SUM1: emulated = kvmppc_ps_two_in(vcpu, rcomp, ax_rd, ax_rb, ax_ra, SCALAR_NO_PS0 | SCALAR_HIGH, fps_fadds); - vcpu->arch.fpr[ax_rd] = vcpu->arch.fpr[ax_rc]; + VCPU_FPR(vcpu, ax_rd) = VCPU_FPR(vcpu, ax_rc); break; case OP_4A_PS_SUM0: emulated = kvmppc_ps_two_in(vcpu, rcomp, ax_rd, @@ -1106,45 +1103,45 @@ int kvmppc_emulate_paired_single(struct kvm_run *run, struct kvm_vcpu *vcpu) case 59: switch (inst_get_field(inst, 21, 30)) { case OP_59_FADDS: - fpd_fadds(&vcpu->arch.fpscr, &cr, fpr_d, fpr_a, fpr_b); + fpd_fadds(&vcpu->arch.fp.fpscr, &cr, fpr_d, fpr_a, fpr_b); kvmppc_sync_qpr(vcpu, ax_rd); break; case OP_59_FSUBS: - fpd_fsubs(&vcpu->arch.fpscr, &cr, fpr_d, fpr_a, fpr_b); + fpd_fsubs(&vcpu->arch.fp.fpscr, &cr, fpr_d, fpr_a, fpr_b); kvmppc_sync_qpr(vcpu, ax_rd); break; case OP_59_FDIVS: - fpd_fdivs(&vcpu->arch.fpscr, &cr, fpr_d, fpr_a, fpr_b); + fpd_fdivs(&vcpu->arch.fp.fpscr, &cr, fpr_d, fpr_a, fpr_b); kvmppc_sync_qpr(vcpu, ax_rd); break; case OP_59_FRES: - fpd_fres(&vcpu->arch.fpscr, &cr, fpr_d, fpr_b); + fpd_fres(&vcpu->arch.fp.fpscr, &cr, fpr_d, fpr_b); kvmppc_sync_qpr(vcpu, ax_rd); break; case OP_59_FRSQRTES: - fpd_frsqrtes(&vcpu->arch.fpscr, &cr, fpr_d, fpr_b); + fpd_frsqrtes(&vcpu->arch.fp.fpscr, &cr, fpr_d, fpr_b); kvmppc_sync_qpr(vcpu, ax_rd); break; } switch (inst_get_field(inst, 26, 30)) { case OP_59_FMULS: - fpd_fmuls(&vcpu->arch.fpscr, &cr, fpr_d, fpr_a, fpr_c); + fpd_fmuls(&vcpu->arch.fp.fpscr, &cr, fpr_d, fpr_a, fpr_c); kvmppc_sync_qpr(vcpu, ax_rd); break; case OP_59_FMSUBS: - fpd_fmsubs(&vcpu->arch.fpscr, &cr, fpr_d, fpr_a, fpr_c, fpr_b); + fpd_fmsubs(&vcpu->arch.fp.fpscr, &cr, fpr_d, fpr_a, fpr_c, fpr_b); kvmppc_sync_qpr(vcpu, ax_rd); break; case OP_59_FMADDS: - fpd_fmadds(&vcpu->arch.fpscr, &cr, fpr_d, fpr_a, fpr_c, fpr_b); + fpd_fmadds(&vcpu->arch.fp.fpscr, &cr, fpr_d, fpr_a, fpr_c, fpr_b); kvmppc_sync_qpr(vcpu, ax_rd); break; case OP_59_FNMSUBS: - fpd_fnmsubs(&vcpu->arch.fpscr, &cr, fpr_d, fpr_a, fpr_c, fpr_b); + fpd_fnmsubs(&vcpu->arch.fp.fpscr, &cr, fpr_d, fpr_a, fpr_c, fpr_b); kvmppc_sync_qpr(vcpu, ax_rd); break; case OP_59_FNMADDS: - fpd_fnmadds(&vcpu->arch.fpscr, &cr, fpr_d, fpr_a, fpr_c, fpr_b); + fpd_fnmadds(&vcpu->arch.fp.fpscr, &cr, fpr_d, fpr_a, fpr_c, fpr_b); kvmppc_sync_qpr(vcpu, ax_rd); break; } @@ -1159,12 +1156,12 @@ int kvmppc_emulate_paired_single(struct kvm_run *run, struct kvm_vcpu *vcpu) break; case OP_63_MFFS: /* XXX missing CR */ - *fpr_d = vcpu->arch.fpscr; + *fpr_d = vcpu->arch.fp.fpscr; break; case OP_63_MTFSF: /* XXX missing fm bits */ /* XXX missing CR */ - vcpu->arch.fpscr = *fpr_b; + vcpu->arch.fp.fpscr = *fpr_b; break; case OP_63_FCMPU: { @@ -1172,7 +1169,7 @@ int kvmppc_emulate_paired_single(struct kvm_run *run, struct kvm_vcpu *vcpu) u32 cr0_mask = 0xf0000000; u32 cr_shift = inst_get_field(inst, 6, 8) * 4; - fpd_fcmpu(&vcpu->arch.fpscr, &tmp_cr, fpr_a, fpr_b); + fpd_fcmpu(&vcpu->arch.fp.fpscr, &tmp_cr, fpr_a, fpr_b); cr &= ~(cr0_mask >> cr_shift); cr |= (cr & cr0_mask) >> cr_shift; break; @@ -1183,40 +1180,40 @@ int kvmppc_emulate_paired_single(struct kvm_run *run, struct kvm_vcpu *vcpu) u32 cr0_mask = 0xf0000000; u32 cr_shift = inst_get_field(inst, 6, 8) * 4; - fpd_fcmpo(&vcpu->arch.fpscr, &tmp_cr, fpr_a, fpr_b); + fpd_fcmpo(&vcpu->arch.fp.fpscr, &tmp_cr, fpr_a, fpr_b); cr &= ~(cr0_mask >> cr_shift); cr |= (cr & cr0_mask) >> cr_shift; break; } case OP_63_FNEG: - fpd_fneg(&vcpu->arch.fpscr, &cr, fpr_d, fpr_b); + fpd_fneg(&vcpu->arch.fp.fpscr, &cr, fpr_d, fpr_b); break; case OP_63_FMR: *fpr_d = *fpr_b; break; case OP_63_FABS: - fpd_fabs(&vcpu->arch.fpscr, &cr, fpr_d, fpr_b); + fpd_fabs(&vcpu->arch.fp.fpscr, &cr, fpr_d, fpr_b); break; case OP_63_FCPSGN: - fpd_fcpsgn(&vcpu->arch.fpscr, &cr, fpr_d, fpr_a, fpr_b); + fpd_fcpsgn(&vcpu->arch.fp.fpscr, &cr, fpr_d, fpr_a, fpr_b); break; case OP_63_FDIV: - fpd_fdiv(&vcpu->arch.fpscr, &cr, fpr_d, fpr_a, fpr_b); + fpd_fdiv(&vcpu->arch.fp.fpscr, &cr, fpr_d, fpr_a, fpr_b); break; case OP_63_FADD: - fpd_fadd(&vcpu->arch.fpscr, &cr, fpr_d, fpr_a, fpr_b); + fpd_fadd(&vcpu->arch.fp.fpscr, &cr, fpr_d, fpr_a, fpr_b); break; case OP_63_FSUB: - fpd_fsub(&vcpu->arch.fpscr, &cr, fpr_d, fpr_a, fpr_b); + fpd_fsub(&vcpu->arch.fp.fpscr, &cr, fpr_d, fpr_a, fpr_b); break; case OP_63_FCTIW: - fpd_fctiw(&vcpu->arch.fpscr, &cr, fpr_d, fpr_b); + fpd_fctiw(&vcpu->arch.fp.fpscr, &cr, fpr_d, fpr_b); break; case OP_63_FCTIWZ: - fpd_fctiwz(&vcpu->arch.fpscr, &cr, fpr_d, fpr_b); + fpd_fctiwz(&vcpu->arch.fp.fpscr, &cr, fpr_d, fpr_b); break; case OP_63_FRSP: - fpd_frsp(&vcpu->arch.fpscr, &cr, fpr_d, fpr_b); + fpd_frsp(&vcpu->arch.fp.fpscr, &cr, fpr_d, fpr_b); kvmppc_sync_qpr(vcpu, ax_rd); break; case OP_63_FRSQRTE: @@ -1224,39 +1221,39 @@ int kvmppc_emulate_paired_single(struct kvm_run *run, struct kvm_vcpu *vcpu) double one = 1.0f; /* fD = sqrt(fB) */ - fpd_fsqrt(&vcpu->arch.fpscr, &cr, fpr_d, fpr_b); + fpd_fsqrt(&vcpu->arch.fp.fpscr, &cr, fpr_d, fpr_b); /* fD = 1.0f / fD */ - fpd_fdiv(&vcpu->arch.fpscr, &cr, fpr_d, (u64*)&one, fpr_d); + fpd_fdiv(&vcpu->arch.fp.fpscr, &cr, fpr_d, (u64*)&one, fpr_d); break; } } switch (inst_get_field(inst, 26, 30)) { case OP_63_FMUL: - fpd_fmul(&vcpu->arch.fpscr, &cr, fpr_d, fpr_a, fpr_c); + fpd_fmul(&vcpu->arch.fp.fpscr, &cr, fpr_d, fpr_a, fpr_c); break; case OP_63_FSEL: - fpd_fsel(&vcpu->arch.fpscr, &cr, fpr_d, fpr_a, fpr_c, fpr_b); + fpd_fsel(&vcpu->arch.fp.fpscr, &cr, fpr_d, fpr_a, fpr_c, fpr_b); break; case OP_63_FMSUB: - fpd_fmsub(&vcpu->arch.fpscr, &cr, fpr_d, fpr_a, fpr_c, fpr_b); + fpd_fmsub(&vcpu->arch.fp.fpscr, &cr, fpr_d, fpr_a, fpr_c, fpr_b); break; case OP_63_FMADD: - fpd_fmadd(&vcpu->arch.fpscr, &cr, fpr_d, fpr_a, fpr_c, fpr_b); + fpd_fmadd(&vcpu->arch.fp.fpscr, &cr, fpr_d, fpr_a, fpr_c, fpr_b); break; case OP_63_FNMSUB: - fpd_fnmsub(&vcpu->arch.fpscr, &cr, fpr_d, fpr_a, fpr_c, fpr_b); + fpd_fnmsub(&vcpu->arch.fp.fpscr, &cr, fpr_d, fpr_a, fpr_c, fpr_b); break; case OP_63_FNMADD: - fpd_fnmadd(&vcpu->arch.fpscr, &cr, fpr_d, fpr_a, fpr_c, fpr_b); + fpd_fnmadd(&vcpu->arch.fp.fpscr, &cr, fpr_d, fpr_a, fpr_c, fpr_b); break; } break; } #ifdef DEBUG - for (i = 0; i < ARRAY_SIZE(vcpu->arch.fpr); i++) { + for (i = 0; i < ARRAY_SIZE(vcpu->arch.fp.fpr); i++) { u32 f; - kvm_cvt_df(&vcpu->arch.fpr[i], &f); + kvm_cvt_df(&VCPU_FPR(vcpu, i), &f); dprintk(KERN_INFO "FPR[%d] = 0x%x\n", i, f); } #endif diff --git a/arch/powerpc/kvm/book3s_pr.c b/arch/powerpc/kvm/book3s_pr.c index 5b9e9063cfa..c5c052a9729 100644 --- a/arch/powerpc/kvm/book3s_pr.c +++ b/arch/powerpc/kvm/book3s_pr.c @@ -41,6 +41,7 @@ #include <linux/vmalloc.h> #include <linux/highmem.h> #include <linux/module.h> +#include <linux/miscdevice.h> #include "book3s.h" @@ -566,12 +567,6 @@ static inline int get_fpr_index(int i) void kvmppc_giveup_ext(struct kvm_vcpu *vcpu, ulong msr) { struct thread_struct *t = ¤t->thread; - u64 *vcpu_fpr = vcpu->arch.fpr; -#ifdef CONFIG_VSX - u64 *vcpu_vsx = vcpu->arch.vsr; -#endif - u64 *thread_fpr = &t->fp_state.fpr[0][0]; - int i; /* * VSX instructions can access FP and vector registers, so if @@ -594,26 +589,16 @@ void kvmppc_giveup_ext(struct kvm_vcpu *vcpu, ulong msr) * both the traditional FP registers and the added VSX * registers into thread.fp_state.fpr[]. */ - if (current->thread.regs->msr & MSR_FP) + if (t->regs->msr & MSR_FP) giveup_fpu(current); - for (i = 0; i < ARRAY_SIZE(vcpu->arch.fpr); i++) - vcpu_fpr[i] = thread_fpr[get_fpr_index(i)]; - - vcpu->arch.fpscr = t->fp_state.fpscr; - -#ifdef CONFIG_VSX - if (cpu_has_feature(CPU_FTR_VSX)) - for (i = 0; i < ARRAY_SIZE(vcpu->arch.vsr) / 2; i++) - vcpu_vsx[i] = thread_fpr[get_fpr_index(i) + 1]; -#endif + t->fp_save_area = NULL; } #ifdef CONFIG_ALTIVEC if (msr & MSR_VEC) { if (current->thread.regs->msr & MSR_VEC) giveup_altivec(current); - memcpy(vcpu->arch.vr, t->vr_state.vr, sizeof(vcpu->arch.vr)); - vcpu->arch.vscr = t->vr_state.vscr; + t->vr_save_area = NULL; } #endif @@ -661,12 +646,6 @@ static int kvmppc_handle_ext(struct kvm_vcpu *vcpu, unsigned int exit_nr, ulong msr) { struct thread_struct *t = ¤t->thread; - u64 *vcpu_fpr = vcpu->arch.fpr; -#ifdef CONFIG_VSX - u64 *vcpu_vsx = vcpu->arch.vsr; -#endif - u64 *thread_fpr = &t->fp_state.fpr[0][0]; - int i; /* When we have paired singles, we emulate in software */ if (vcpu->arch.hflags & BOOK3S_HFLAG_PAIRED_SINGLE) @@ -704,27 +683,20 @@ static int kvmppc_handle_ext(struct kvm_vcpu *vcpu, unsigned int exit_nr, #endif if (msr & MSR_FP) { - for (i = 0; i < ARRAY_SIZE(vcpu->arch.fpr); i++) - thread_fpr[get_fpr_index(i)] = vcpu_fpr[i]; -#ifdef CONFIG_VSX - for (i = 0; i < ARRAY_SIZE(vcpu->arch.vsr) / 2; i++) - thread_fpr[get_fpr_index(i) + 1] = vcpu_vsx[i]; -#endif - t->fp_state.fpscr = vcpu->arch.fpscr; - t->fpexc_mode = 0; - kvmppc_load_up_fpu(); + enable_kernel_fp(); + load_fp_state(&vcpu->arch.fp); + t->fp_save_area = &vcpu->arch.fp; } if (msr & MSR_VEC) { #ifdef CONFIG_ALTIVEC - memcpy(t->vr_state.vr, vcpu->arch.vr, sizeof(vcpu->arch.vr)); - t->vr_state.vscr = vcpu->arch.vscr; - t->vrsave = -1; - kvmppc_load_up_altivec(); + enable_kernel_altivec(); + load_vr_state(&vcpu->arch.vr); + t->vr_save_area = &vcpu->arch.vr; #endif } - current->thread.regs->msr |= msr; + t->regs->msr |= msr; vcpu->arch.guest_owned_ext |= msr; kvmppc_recalc_shadow_msr(vcpu); @@ -743,11 +715,15 @@ static void kvmppc_handle_lost_ext(struct kvm_vcpu *vcpu) if (!lost_ext) return; - if (lost_ext & MSR_FP) - kvmppc_load_up_fpu(); + if (lost_ext & MSR_FP) { + enable_kernel_fp(); + load_fp_state(&vcpu->arch.fp); + } #ifdef CONFIG_ALTIVEC - if (lost_ext & MSR_VEC) - kvmppc_load_up_altivec(); + if (lost_ext & MSR_VEC) { + enable_kernel_altivec(); + load_vr_state(&vcpu->arch.vr); + } #endif current->thread.regs->msr |= lost_ext; } @@ -873,6 +849,7 @@ int kvmppc_handle_exit_pr(struct kvm_run *run, struct kvm_vcpu *vcpu, /* We're good on these - the host merely wanted to get our attention */ case BOOK3S_INTERRUPT_DECREMENTER: case BOOK3S_INTERRUPT_HV_DECREMENTER: + case BOOK3S_INTERRUPT_DOORBELL: vcpu->stat.dec_exits++; r = RESUME_GUEST; break; @@ -1045,14 +1022,14 @@ program_interrupt: * and if we really did time things so badly, then we just exit * again due to a host external interrupt. */ - local_irq_disable(); s = kvmppc_prepare_to_enter(vcpu); - if (s <= 0) { - local_irq_enable(); + if (s <= 0) r = s; - } else { + else { + /* interrupts now hard-disabled */ kvmppc_fix_ee_before_entry(); } + kvmppc_handle_lost_ext(vcpu); } @@ -1133,19 +1110,6 @@ static int kvmppc_get_one_reg_pr(struct kvm_vcpu *vcpu, u64 id, case KVM_REG_PPC_HIOR: *val = get_reg_val(id, to_book3s(vcpu)->hior); break; -#ifdef CONFIG_VSX - case KVM_REG_PPC_VSR0 ... KVM_REG_PPC_VSR31: { - long int i = id - KVM_REG_PPC_VSR0; - - if (!cpu_has_feature(CPU_FTR_VSX)) { - r = -ENXIO; - break; - } - val->vsxval[0] = vcpu->arch.fpr[i]; - val->vsxval[1] = vcpu->arch.vsr[i]; - break; - } -#endif /* CONFIG_VSX */ default: r = -EINVAL; break; @@ -1164,19 +1128,6 @@ static int kvmppc_set_one_reg_pr(struct kvm_vcpu *vcpu, u64 id, to_book3s(vcpu)->hior = set_reg_val(id, *val); to_book3s(vcpu)->hior_explicit = true; break; -#ifdef CONFIG_VSX - case KVM_REG_PPC_VSR0 ... KVM_REG_PPC_VSR31: { - long int i = id - KVM_REG_PPC_VSR0; - - if (!cpu_has_feature(CPU_FTR_VSX)) { - r = -ENXIO; - break; - } - vcpu->arch.fpr[i] = val->vsxval[0]; - vcpu->arch.vsr[i] = val->vsxval[1]; - break; - } -#endif /* CONFIG_VSX */ default: r = -EINVAL; break; @@ -1274,17 +1225,9 @@ static void kvmppc_core_vcpu_free_pr(struct kvm_vcpu *vcpu) static int kvmppc_vcpu_run_pr(struct kvm_run *kvm_run, struct kvm_vcpu *vcpu) { int ret; - struct thread_fp_state fp; - int fpexc_mode; #ifdef CONFIG_ALTIVEC - struct thread_vr_state vr; unsigned long uninitialized_var(vrsave); - int used_vr; #endif -#ifdef CONFIG_VSX - int used_vsr; -#endif - ulong ext_msr; /* Check if we can run the vcpu at all */ if (!vcpu->arch.sane) { @@ -1299,40 +1242,27 @@ static int kvmppc_vcpu_run_pr(struct kvm_run *kvm_run, struct kvm_vcpu *vcpu) * really did time things so badly, then we just exit again due to * a host external interrupt. */ - local_irq_disable(); ret = kvmppc_prepare_to_enter(vcpu); - if (ret <= 0) { - local_irq_enable(); + if (ret <= 0) goto out; - } + /* interrupts now hard-disabled */ - /* Save FPU state in stack */ + /* Save FPU state in thread_struct */ if (current->thread.regs->msr & MSR_FP) giveup_fpu(current); - fp = current->thread.fp_state; - fpexc_mode = current->thread.fpexc_mode; #ifdef CONFIG_ALTIVEC - /* Save Altivec state in stack */ - used_vr = current->thread.used_vr; - if (used_vr) { - if (current->thread.regs->msr & MSR_VEC) - giveup_altivec(current); - vr = current->thread.vr_state; - vrsave = current->thread.vrsave; - } + /* Save Altivec state in thread_struct */ + if (current->thread.regs->msr & MSR_VEC) + giveup_altivec(current); #endif #ifdef CONFIG_VSX - /* Save VSX state in stack */ - used_vsr = current->thread.used_vsr; - if (used_vsr && (current->thread.regs->msr & MSR_VSX)) + /* Save VSX state in thread_struct */ + if (current->thread.regs->msr & MSR_VSX) __giveup_vsx(current); #endif - /* Remember the MSR with disabled extensions */ - ext_msr = current->thread.regs->msr; - /* Preload FPU if it's enabled */ if (vcpu->arch.shared->msr & MSR_FP) kvmppc_handle_ext(vcpu, BOOK3S_INTERRUPT_FP_UNAVAIL, MSR_FP); @@ -1347,25 +1277,6 @@ static int kvmppc_vcpu_run_pr(struct kvm_run *kvm_run, struct kvm_vcpu *vcpu) /* Make sure we save the guest FPU/Altivec/VSX state */ kvmppc_giveup_ext(vcpu, MSR_FP | MSR_VEC | MSR_VSX); - current->thread.regs->msr = ext_msr; - - /* Restore FPU/VSX state from stack */ - current->thread.fp_state = fp; - current->thread.fpexc_mode = fpexc_mode; - -#ifdef CONFIG_ALTIVEC - /* Restore Altivec state from stack */ - if (used_vr && current->thread.used_vr) { - current->thread.vr_state = vr; - current->thread.vrsave = vrsave; - } - current->thread.used_vr = used_vr; -#endif - -#ifdef CONFIG_VSX - current->thread.used_vsr = used_vsr; -#endif - out: vcpu->mode = OUTSIDE_GUEST_MODE; return ret; @@ -1606,4 +1517,6 @@ module_init(kvmppc_book3s_init_pr); module_exit(kvmppc_book3s_exit_pr); MODULE_LICENSE("GPL"); +MODULE_ALIAS_MISCDEV(KVM_MINOR); +MODULE_ALIAS("devname:kvm"); #endif diff --git a/arch/powerpc/kvm/book3s_rmhandlers.S b/arch/powerpc/kvm/book3s_rmhandlers.S index c3c5231adad..9eec675220e 100644 --- a/arch/powerpc/kvm/book3s_rmhandlers.S +++ b/arch/powerpc/kvm/book3s_rmhandlers.S @@ -162,51 +162,4 @@ _GLOBAL(kvmppc_entry_trampoline) mtsrr1 r6 RFI -#if defined(CONFIG_PPC_BOOK3S_32) -#define STACK_LR INT_FRAME_SIZE+4 - -/* load_up_xxx have to run with MSR_DR=0 on Book3S_32 */ -#define MSR_EXT_START \ - PPC_STL r20, _NIP(r1); \ - mfmsr r20; \ - LOAD_REG_IMMEDIATE(r3, MSR_DR|MSR_EE); \ - andc r3,r20,r3; /* Disable DR,EE */ \ - mtmsr r3; \ - sync - -#define MSR_EXT_END \ - mtmsr r20; /* Enable DR,EE */ \ - sync; \ - PPC_LL r20, _NIP(r1) - -#elif defined(CONFIG_PPC_BOOK3S_64) -#define STACK_LR _LINK -#define MSR_EXT_START -#define MSR_EXT_END -#endif - -/* - * Activate current's external feature (FPU/Altivec/VSX) - */ -#define define_load_up(what) \ - \ -_GLOBAL(kvmppc_load_up_ ## what); \ - PPC_STLU r1, -INT_FRAME_SIZE(r1); \ - mflr r3; \ - PPC_STL r3, STACK_LR(r1); \ - MSR_EXT_START; \ - \ - bl FUNC(load_up_ ## what); \ - \ - MSR_EXT_END; \ - PPC_LL r3, STACK_LR(r1); \ - mtlr r3; \ - addi r1, r1, INT_FRAME_SIZE; \ - blr - -define_load_up(fpu) -#ifdef CONFIG_ALTIVEC -define_load_up(altivec) -#endif - #include "book3s_segment.S" diff --git a/arch/powerpc/kvm/book3s_segment.S b/arch/powerpc/kvm/book3s_segment.S index bc50c97751d..1e0cc2adfd4 100644 --- a/arch/powerpc/kvm/book3s_segment.S +++ b/arch/powerpc/kvm/book3s_segment.S @@ -361,6 +361,8 @@ END_FTR_SECTION_IFSET(CPU_FTR_HVMODE) beqa BOOK3S_INTERRUPT_DECREMENTER cmpwi r12, BOOK3S_INTERRUPT_PERFMON beqa BOOK3S_INTERRUPT_PERFMON + cmpwi r12, BOOK3S_INTERRUPT_DOORBELL + beqa BOOK3S_INTERRUPT_DOORBELL RFI kvmppc_handler_trampoline_exit_end: diff --git a/arch/powerpc/kvm/book3s_xics.c b/arch/powerpc/kvm/book3s_xics.c index 02a17dcf161..d1acd32a64c 100644 --- a/arch/powerpc/kvm/book3s_xics.c +++ b/arch/powerpc/kvm/book3s_xics.c @@ -1246,8 +1246,10 @@ static int kvmppc_xics_create(struct kvm_device *dev, u32 type) kvm->arch.xics = xics; mutex_unlock(&kvm->lock); - if (ret) + if (ret) { + kfree(xics); return ret; + } xics_debugfs_init(xics); diff --git a/arch/powerpc/kvm/booke.c b/arch/powerpc/kvm/booke.c index 0591e05db74..ab62109fdfa 100644 --- a/arch/powerpc/kvm/booke.c +++ b/arch/powerpc/kvm/booke.c @@ -643,7 +643,7 @@ int kvmppc_core_prepare_to_enter(struct kvm_vcpu *vcpu) local_irq_enable(); kvm_vcpu_block(vcpu); clear_bit(KVM_REQ_UNHALT, &vcpu->requests); - local_irq_disable(); + hard_irq_disable(); kvmppc_set_exit_type(vcpu, EMULATED_MTMSRWE_EXITS); r = 1; @@ -682,34 +682,22 @@ int kvmppc_vcpu_run(struct kvm_run *kvm_run, struct kvm_vcpu *vcpu) { int ret, s; struct debug_reg debug; -#ifdef CONFIG_PPC_FPU - struct thread_fp_state fp; - int fpexc_mode; -#endif if (!vcpu->arch.sane) { kvm_run->exit_reason = KVM_EXIT_INTERNAL_ERROR; return -EINVAL; } - local_irq_disable(); s = kvmppc_prepare_to_enter(vcpu); if (s <= 0) { - local_irq_enable(); ret = s; goto out; } + /* interrupts now hard-disabled */ #ifdef CONFIG_PPC_FPU /* Save userspace FPU state in stack */ enable_kernel_fp(); - fp = current->thread.fp_state; - fpexc_mode = current->thread.fpexc_mode; - - /* Restore guest FPU state to thread */ - memcpy(current->thread.fp_state.fpr, vcpu->arch.fpr, - sizeof(vcpu->arch.fpr)); - current->thread.fp_state.fpscr = vcpu->arch.fpscr; /* * Since we can't trap on MSR_FP in GS-mode, we consider the guest @@ -728,6 +716,7 @@ int kvmppc_vcpu_run(struct kvm_run *kvm_run, struct kvm_vcpu *vcpu) debug = current->thread.debug; current->thread.debug = vcpu->arch.shadow_dbg_reg; + vcpu->arch.pgdir = current->mm->pgd; kvmppc_fix_ee_before_entry(); ret = __kvmppc_vcpu_run(kvm_run, vcpu); @@ -743,15 +732,6 @@ int kvmppc_vcpu_run(struct kvm_run *kvm_run, struct kvm_vcpu *vcpu) kvmppc_save_guest_fp(vcpu); vcpu->fpu_active = 0; - - /* Save guest FPU state from thread */ - memcpy(vcpu->arch.fpr, current->thread.fp_state.fpr, - sizeof(vcpu->arch.fpr)); - vcpu->arch.fpscr = current->thread.fp_state.fpscr; - - /* Restore userspace FPU state from stack */ - current->thread.fp_state = fp; - current->thread.fpexc_mode = fpexc_mode; #endif out: @@ -898,17 +878,6 @@ int kvmppc_handle_exit(struct kvm_run *run, struct kvm_vcpu *vcpu, int s; int idx; -#ifdef CONFIG_PPC64 - WARN_ON(local_paca->irq_happened != 0); -#endif - - /* - * We enter with interrupts disabled in hardware, but - * we need to call hard_irq_disable anyway to ensure that - * the software state is kept in sync. - */ - hard_irq_disable(); - /* update before a new last_exit_type is rewritten */ kvmppc_update_timing_stats(vcpu); @@ -1217,12 +1186,11 @@ int kvmppc_handle_exit(struct kvm_run *run, struct kvm_vcpu *vcpu, * aren't already exiting to userspace for some other reason. */ if (!(r & RESUME_HOST)) { - local_irq_disable(); s = kvmppc_prepare_to_enter(vcpu); - if (s <= 0) { - local_irq_enable(); + if (s <= 0) r = (s << 2) | RESUME_HOST | (r & RESUME_FLAG_NV); - } else { + else { + /* interrupts now hard-disabled */ kvmppc_fix_ee_before_entry(); } } diff --git a/arch/powerpc/kvm/booke.h b/arch/powerpc/kvm/booke.h index 09bfd9bc7cf..b632cd35919 100644 --- a/arch/powerpc/kvm/booke.h +++ b/arch/powerpc/kvm/booke.h @@ -136,7 +136,9 @@ static inline void kvmppc_load_guest_fp(struct kvm_vcpu *vcpu) { #ifdef CONFIG_PPC_FPU if (vcpu->fpu_active && !(current->thread.regs->msr & MSR_FP)) { - load_up_fpu(); + enable_kernel_fp(); + load_fp_state(&vcpu->arch.fp); + current->thread.fp_save_area = &vcpu->arch.fp; current->thread.regs->msr |= MSR_FP; } #endif @@ -151,6 +153,7 @@ static inline void kvmppc_save_guest_fp(struct kvm_vcpu *vcpu) #ifdef CONFIG_PPC_FPU if (vcpu->fpu_active && (current->thread.regs->msr & MSR_FP)) giveup_fpu(current); + current->thread.fp_save_area = NULL; #endif } diff --git a/arch/powerpc/kvm/bookehv_interrupts.S b/arch/powerpc/kvm/bookehv_interrupts.S index a0d6929d867..e4185f6b330 100644 --- a/arch/powerpc/kvm/bookehv_interrupts.S +++ b/arch/powerpc/kvm/bookehv_interrupts.S @@ -33,6 +33,8 @@ #ifdef CONFIG_64BIT #include <asm/exception-64e.h> +#include <asm/hw_irq.h> +#include <asm/irqflags.h> #else #include "../kernel/head_booke.h" /* for THREAD_NORMSAVE() */ #endif @@ -467,6 +469,15 @@ _GLOBAL(kvmppc_resume_host) mtspr SPRN_EPCR, r3 isync +#ifdef CONFIG_64BIT + /* + * We enter with interrupts disabled in hardware, but + * we need to call RECONCILE_IRQ_STATE to ensure + * that the software state is kept in sync. + */ + RECONCILE_IRQ_STATE(r3,r5) +#endif + /* Switch to kernel stack and jump to handler. */ PPC_LL r3, HOST_RUN(r1) mr r5, r14 /* intno */ diff --git a/arch/powerpc/kvm/e500.c b/arch/powerpc/kvm/e500.c index 497b142f651..2e02ed849f3 100644 --- a/arch/powerpc/kvm/e500.c +++ b/arch/powerpc/kvm/e500.c @@ -16,6 +16,8 @@ #include <linux/slab.h> #include <linux/err.h> #include <linux/export.h> +#include <linux/module.h> +#include <linux/miscdevice.h> #include <asm/reg.h> #include <asm/cputable.h> @@ -573,3 +575,5 @@ static void __exit kvmppc_e500_exit(void) module_init(kvmppc_e500_init); module_exit(kvmppc_e500_exit); +MODULE_ALIAS_MISCDEV(KVM_MINOR); +MODULE_ALIAS("devname:kvm"); diff --git a/arch/powerpc/kvm/e500.h b/arch/powerpc/kvm/e500.h index 4fd9650eb01..a326178bdea 100644 --- a/arch/powerpc/kvm/e500.h +++ b/arch/powerpc/kvm/e500.h @@ -31,11 +31,13 @@ enum vcpu_ftr { #define E500_TLB_NUM 2 /* entry is mapped somewhere in host TLB */ -#define E500_TLB_VALID (1 << 0) +#define E500_TLB_VALID (1 << 31) /* TLB1 entry is mapped by host TLB1, tracked by bitmaps */ -#define E500_TLB_BITMAP (1 << 1) +#define E500_TLB_BITMAP (1 << 30) /* TLB1 entry is mapped by host TLB0 */ -#define E500_TLB_TLB0 (1 << 2) +#define E500_TLB_TLB0 (1 << 29) +/* bits [6-5] MAS2_X1 and MAS2_X0 and [4-0] bits for WIMGE */ +#define E500_TLB_MAS2_ATTR (0x7f) struct tlbe_ref { pfn_t pfn; /* valid only for TLB0, except briefly */ diff --git a/arch/powerpc/kvm/e500_mmu.c b/arch/powerpc/kvm/e500_mmu.c index ebca6b88ea5..50860e919cb 100644 --- a/arch/powerpc/kvm/e500_mmu.c +++ b/arch/powerpc/kvm/e500_mmu.c @@ -127,7 +127,7 @@ static int kvmppc_e500_tlb_index(struct kvmppc_vcpu_e500 *vcpu_e500, } static inline void kvmppc_e500_deliver_tlb_miss(struct kvm_vcpu *vcpu, - unsigned int eaddr, int as) + gva_t eaddr, int as) { struct kvmppc_vcpu_e500 *vcpu_e500 = to_e500(vcpu); unsigned int victim, tsized; diff --git a/arch/powerpc/kvm/e500_mmu_host.c b/arch/powerpc/kvm/e500_mmu_host.c index ecf2247b13b..dd2cc03f406 100644 --- a/arch/powerpc/kvm/e500_mmu_host.c +++ b/arch/powerpc/kvm/e500_mmu_host.c @@ -65,15 +65,6 @@ static inline u32 e500_shadow_mas3_attrib(u32 mas3, int usermode) return mas3; } -static inline u32 e500_shadow_mas2_attrib(u32 mas2, int usermode) -{ -#ifdef CONFIG_SMP - return (mas2 & MAS2_ATTRIB_MASK) | MAS2_M; -#else - return mas2 & MAS2_ATTRIB_MASK; -#endif -} - /* * writing shadow tlb entry to host TLB */ @@ -231,15 +222,15 @@ void inval_gtlbe_on_host(struct kvmppc_vcpu_e500 *vcpu_e500, int tlbsel, ref->flags &= ~(E500_TLB_TLB0 | E500_TLB_VALID); } - /* Already invalidated in between */ - if (!(ref->flags & E500_TLB_VALID)) - return; - - /* Guest tlbe is backed by at most one host tlbe per shadow pid. */ - kvmppc_e500_tlbil_one(vcpu_e500, gtlbe); + /* + * If TLB entry is still valid then it's a TLB0 entry, and thus + * backed by at most one host tlbe per shadow pid + */ + if (ref->flags & E500_TLB_VALID) + kvmppc_e500_tlbil_one(vcpu_e500, gtlbe); /* Mark the TLB as not backed by the host anymore */ - ref->flags &= ~E500_TLB_VALID; + ref->flags = 0; } static inline int tlbe_is_writable(struct kvm_book3e_206_tlb_entry *tlbe) @@ -249,10 +240,13 @@ static inline int tlbe_is_writable(struct kvm_book3e_206_tlb_entry *tlbe) static inline void kvmppc_e500_ref_setup(struct tlbe_ref *ref, struct kvm_book3e_206_tlb_entry *gtlbe, - pfn_t pfn) + pfn_t pfn, unsigned int wimg) { ref->pfn = pfn; - ref->flags |= E500_TLB_VALID; + ref->flags = E500_TLB_VALID; + + /* Use guest supplied MAS2_G and MAS2_E */ + ref->flags |= (gtlbe->mas2 & MAS2_ATTRIB_MASK) | wimg; /* Mark the page accessed */ kvm_set_pfn_accessed(pfn); @@ -316,8 +310,7 @@ static void kvmppc_e500_setup_stlbe( /* Force IPROT=0 for all guest mappings. */ stlbe->mas1 = MAS1_TSIZE(tsize) | get_tlb_sts(gtlbe) | MAS1_VALID; - stlbe->mas2 = (gvaddr & MAS2_EPN) | - e500_shadow_mas2_attrib(gtlbe->mas2, pr); + stlbe->mas2 = (gvaddr & MAS2_EPN) | (ref->flags & E500_TLB_MAS2_ATTR); stlbe->mas7_3 = ((u64)pfn << PAGE_SHIFT) | e500_shadow_mas3_attrib(gtlbe->mas7_3, pr); @@ -339,6 +332,10 @@ static inline int kvmppc_e500_shadow_map(struct kvmppc_vcpu_e500 *vcpu_e500, int ret = 0; unsigned long mmu_seq; struct kvm *kvm = vcpu_e500->vcpu.kvm; + unsigned long tsize_pages = 0; + pte_t *ptep; + unsigned int wimg = 0; + pgd_t *pgdir; /* used to check for invalidations in progress */ mmu_seq = kvm->mmu_notifier_seq; @@ -405,7 +402,7 @@ static inline int kvmppc_e500_shadow_map(struct kvmppc_vcpu_e500 *vcpu_e500, */ for (; tsize > BOOK3E_PAGESZ_4K; tsize -= 2) { - unsigned long gfn_start, gfn_end, tsize_pages; + unsigned long gfn_start, gfn_end; tsize_pages = 1 << (tsize - 2); gfn_start = gfn & ~(tsize_pages - 1); @@ -447,11 +444,12 @@ static inline int kvmppc_e500_shadow_map(struct kvmppc_vcpu_e500 *vcpu_e500, } if (likely(!pfnmap)) { - unsigned long tsize_pages = 1 << (tsize + 10 - PAGE_SHIFT); + tsize_pages = 1 << (tsize + 10 - PAGE_SHIFT); pfn = gfn_to_pfn_memslot(slot, gfn); if (is_error_noslot_pfn(pfn)) { - printk(KERN_ERR "Couldn't get real page for gfn %lx!\n", - (long)gfn); + if (printk_ratelimit()) + pr_err("%s: real page not found for gfn %lx\n", + __func__, (long)gfn); return -EINVAL; } @@ -466,7 +464,18 @@ static inline int kvmppc_e500_shadow_map(struct kvmppc_vcpu_e500 *vcpu_e500, goto out; } - kvmppc_e500_ref_setup(ref, gtlbe, pfn); + + pgdir = vcpu_e500->vcpu.arch.pgdir; + ptep = lookup_linux_ptep(pgdir, hva, &tsize_pages); + if (pte_present(*ptep)) + wimg = (*ptep >> PTE_WIMGE_SHIFT) & MAS2_WIMGE_MASK; + else { + if (printk_ratelimit()) + pr_err("%s: pte not present: gfn %lx, pfn %lx\n", + __func__, (long)gfn, pfn); + return -EINVAL; + } + kvmppc_e500_ref_setup(ref, gtlbe, pfn, wimg); kvmppc_e500_setup_stlbe(&vcpu_e500->vcpu, gtlbe, tsize, ref, gvaddr, stlbe); diff --git a/arch/powerpc/kvm/e500mc.c b/arch/powerpc/kvm/e500mc.c index 4132cd2fc17..17e45627922 100644 --- a/arch/powerpc/kvm/e500mc.c +++ b/arch/powerpc/kvm/e500mc.c @@ -16,6 +16,8 @@ #include <linux/slab.h> #include <linux/err.h> #include <linux/export.h> +#include <linux/miscdevice.h> +#include <linux/module.h> #include <asm/reg.h> #include <asm/cputable.h> @@ -391,3 +393,5 @@ static void __exit kvmppc_e500mc_exit(void) module_init(kvmppc_e500mc_init); module_exit(kvmppc_e500mc_exit); +MODULE_ALIAS_MISCDEV(KVM_MINOR); +MODULE_ALIAS("devname:kvm"); diff --git a/arch/powerpc/kvm/emulate.c b/arch/powerpc/kvm/emulate.c index 2f9a0873b44..c2b887be2c2 100644 --- a/arch/powerpc/kvm/emulate.c +++ b/arch/powerpc/kvm/emulate.c @@ -219,7 +219,6 @@ static int kvmppc_emulate_mfspr(struct kvm_vcpu *vcpu, int sprn, int rt) * lmw * stmw * - * XXX is_bigendian should depend on MMU mapping or MSR[LE] */ /* XXX Should probably auto-generate instruction decoding for a particular core * from opcode tables in the future. */ diff --git a/arch/powerpc/kvm/mpic.c b/arch/powerpc/kvm/mpic.c index 2861ae9eaae..efbd9962a20 100644 --- a/arch/powerpc/kvm/mpic.c +++ b/arch/powerpc/kvm/mpic.c @@ -1635,6 +1635,7 @@ static void mpic_destroy(struct kvm_device *dev) dev->kvm->arch.mpic = NULL; kfree(opp); + kfree(dev); } static int mpic_set_default_irq_routing(struct openpic *opp) diff --git a/arch/powerpc/kvm/powerpc.c b/arch/powerpc/kvm/powerpc.c index 9ae97686e9f..3cf541a53e2 100644 --- a/arch/powerpc/kvm/powerpc.c +++ b/arch/powerpc/kvm/powerpc.c @@ -68,14 +68,16 @@ int kvm_arch_vcpu_should_kick(struct kvm_vcpu *vcpu) */ int kvmppc_prepare_to_enter(struct kvm_vcpu *vcpu) { - int r = 1; + int r; + + WARN_ON(irqs_disabled()); + hard_irq_disable(); - WARN_ON_ONCE(!irqs_disabled()); while (true) { if (need_resched()) { local_irq_enable(); cond_resched(); - local_irq_disable(); + hard_irq_disable(); continue; } @@ -101,7 +103,7 @@ int kvmppc_prepare_to_enter(struct kvm_vcpu *vcpu) local_irq_enable(); trace_kvm_check_requests(vcpu); r = kvmppc_core_check_requests(vcpu); - local_irq_disable(); + hard_irq_disable(); if (r > 0) continue; break; @@ -113,22 +115,12 @@ int kvmppc_prepare_to_enter(struct kvm_vcpu *vcpu) continue; } -#ifdef CONFIG_PPC64 - /* lazy EE magic */ - hard_irq_disable(); - if (lazy_irq_pending()) { - /* Got an interrupt in between, try again */ - local_irq_enable(); - local_irq_disable(); - kvm_guest_exit(); - continue; - } -#endif - kvm_guest_enter(); - break; + return 1; } + /* return to host */ + local_irq_enable(); return r; } EXPORT_SYMBOL_GPL(kvmppc_prepare_to_enter); @@ -656,14 +648,14 @@ static void kvmppc_complete_mmio_load(struct kvm_vcpu *vcpu, kvmppc_set_gpr(vcpu, vcpu->arch.io_gpr, gpr); break; case KVM_MMIO_REG_FPR: - vcpu->arch.fpr[vcpu->arch.io_gpr & KVM_MMIO_REG_MASK] = gpr; + VCPU_FPR(vcpu, vcpu->arch.io_gpr & KVM_MMIO_REG_MASK) = gpr; break; #ifdef CONFIG_PPC_BOOK3S case KVM_MMIO_REG_QPR: vcpu->arch.qpr[vcpu->arch.io_gpr & KVM_MMIO_REG_MASK] = gpr; break; case KVM_MMIO_REG_FQPR: - vcpu->arch.fpr[vcpu->arch.io_gpr & KVM_MMIO_REG_MASK] = gpr; + VCPU_FPR(vcpu, vcpu->arch.io_gpr & KVM_MMIO_REG_MASK) = gpr; vcpu->arch.qpr[vcpu->arch.io_gpr & KVM_MMIO_REG_MASK] = gpr; break; #endif @@ -673,9 +665,19 @@ static void kvmppc_complete_mmio_load(struct kvm_vcpu *vcpu, } int kvmppc_handle_load(struct kvm_run *run, struct kvm_vcpu *vcpu, - unsigned int rt, unsigned int bytes, int is_bigendian) + unsigned int rt, unsigned int bytes, + int is_default_endian) { int idx, ret; + int is_bigendian; + + if (kvmppc_need_byteswap(vcpu)) { + /* Default endianness is "little endian". */ + is_bigendian = !is_default_endian; + } else { + /* Default endianness is "big endian". */ + is_bigendian = is_default_endian; + } if (bytes > sizeof(run->mmio.data)) { printk(KERN_ERR "%s: bad MMIO length: %d\n", __func__, @@ -711,21 +713,31 @@ EXPORT_SYMBOL_GPL(kvmppc_handle_load); /* Same as above, but sign extends */ int kvmppc_handle_loads(struct kvm_run *run, struct kvm_vcpu *vcpu, - unsigned int rt, unsigned int bytes, int is_bigendian) + unsigned int rt, unsigned int bytes, + int is_default_endian) { int r; vcpu->arch.mmio_sign_extend = 1; - r = kvmppc_handle_load(run, vcpu, rt, bytes, is_bigendian); + r = kvmppc_handle_load(run, vcpu, rt, bytes, is_default_endian); return r; } int kvmppc_handle_store(struct kvm_run *run, struct kvm_vcpu *vcpu, - u64 val, unsigned int bytes, int is_bigendian) + u64 val, unsigned int bytes, int is_default_endian) { void *data = run->mmio.data; int idx, ret; + int is_bigendian; + + if (kvmppc_need_byteswap(vcpu)) { + /* Default endianness is "little endian". */ + is_bigendian = !is_default_endian; + } else { + /* Default endianness is "big endian". */ + is_bigendian = is_default_endian; + } if (bytes > sizeof(run->mmio.data)) { printk(KERN_ERR "%s: bad MMIO length: %d\n", __func__, diff --git a/arch/powerpc/mm/hugetlbpage.c b/arch/powerpc/mm/hugetlbpage.c index 90bb6d9409b..eb923654ba8 100644 --- a/arch/powerpc/mm/hugetlbpage.c +++ b/arch/powerpc/mm/hugetlbpage.c @@ -472,12 +472,13 @@ static void hugepd_free(struct mmu_gather *tlb, void *hugepte) { struct hugepd_freelist **batchp; - batchp = &__get_cpu_var(hugepd_freelist_cur); + batchp = &get_cpu_var(hugepd_freelist_cur); if (atomic_read(&tlb->mm->mm_users) < 2 || cpumask_equal(mm_cpumask(tlb->mm), cpumask_of(smp_processor_id()))) { kmem_cache_free(hugepte_cache, hugepte); + put_cpu_var(hugepd_freelist_cur); return; } @@ -491,6 +492,7 @@ static void hugepd_free(struct mmu_gather *tlb, void *hugepte) call_rcu_sched(&(*batchp)->rcu, hugepd_free_rcu_callback); *batchp = NULL; } + put_cpu_var(hugepd_freelist_cur); } #endif diff --git a/arch/powerpc/mm/numa.c b/arch/powerpc/mm/numa.c index 86a63de072c..30a42e24bf1 100644 --- a/arch/powerpc/mm/numa.c +++ b/arch/powerpc/mm/numa.c @@ -1785,7 +1785,7 @@ static const struct file_operations topology_ops = { static int topology_update_init(void) { start_topology_update(); - proc_create("powerpc/topology_updates", 644, NULL, &topology_ops); + proc_create("powerpc/topology_updates", 0644, NULL, &topology_ops); return 0; } diff --git a/arch/powerpc/mm/slice.c b/arch/powerpc/mm/slice.c index 7ce9cf3b698..b0c75cc15ef 100644 --- a/arch/powerpc/mm/slice.c +++ b/arch/powerpc/mm/slice.c @@ -408,7 +408,7 @@ unsigned long slice_get_unmapped_area(unsigned long addr, unsigned long len, if (fixed && (addr & ((1ul << pshift) - 1))) return -EINVAL; if (fixed && addr > (mm->task_size - len)) - return -EINVAL; + return -ENOMEM; /* If hint, make sure it matches our alignment restrictions */ if (!fixed && addr) { diff --git a/arch/powerpc/mm/tlb_low_64e.S b/arch/powerpc/mm/tlb_low_64e.S index 16250b16237..c95eb323e9a 100644 --- a/arch/powerpc/mm/tlb_low_64e.S +++ b/arch/powerpc/mm/tlb_low_64e.S @@ -240,6 +240,7 @@ itlb_miss_fault_bolted: beq tlb_miss_common_bolted b itlb_miss_kernel_bolted +#ifdef CONFIG_PPC_FSL_BOOK3E /* * TLB miss handling for e6500 and derivatives, using hardware tablewalk. * @@ -409,7 +410,7 @@ itlb_miss_fault_e6500: TLB_MISS_STATS_I(MMSTAT_TLB_MISS_NORM_FAULT) tlb_epilog_bolted b exc_instruction_storage_book3e - +#endif /* CONFIG_PPC_FSL_BOOK3E */ /********************************************************************** * * diff --git a/arch/powerpc/mm/tlb_nohash.c b/arch/powerpc/mm/tlb_nohash.c index 735839b74dc..b37a58e1c92 100644 --- a/arch/powerpc/mm/tlb_nohash.c +++ b/arch/powerpc/mm/tlb_nohash.c @@ -557,10 +557,12 @@ static void setup_mmu_htw(void) patch_exception(0x1c0, exc_data_tlb_miss_htw_book3e); patch_exception(0x1e0, exc_instruction_tlb_miss_htw_book3e); break; +#ifdef CONFIG_PPC_FSL_BOOK3E case PPC_HTW_E6500: patch_exception(0x1c0, exc_data_tlb_miss_e6500_book3e); patch_exception(0x1e0, exc_instruction_tlb_miss_e6500_book3e); break; +#endif } pr_info("MMU: Book3E HW tablewalk %s\n", book3e_htw_mode != PPC_HTW_NONE ? "enabled" : "not supported"); diff --git a/arch/powerpc/platforms/512x/Kconfig b/arch/powerpc/platforms/512x/Kconfig index fc9c1cbfcb1..5aa3f4b5332 100644 --- a/arch/powerpc/platforms/512x/Kconfig +++ b/arch/powerpc/platforms/512x/Kconfig @@ -1,9 +1,9 @@ config PPC_MPC512x bool "512x-based boards" depends on 6xx + select COMMON_CLK select FSL_SOC select IPIC - select PPC_CLOCK select PPC_PCI_CHOICE select FSL_PCI if PCI select ARCH_WANT_OPTIONAL_GPIOLIB diff --git a/arch/powerpc/platforms/512x/Makefile b/arch/powerpc/platforms/512x/Makefile index 72fb9340e09..01693121a2b 100644 --- a/arch/powerpc/platforms/512x/Makefile +++ b/arch/powerpc/platforms/512x/Makefile @@ -1,7 +1,8 @@ # # Makefile for the Freescale PowerPC 512x linux kernel. # -obj-y += clock.o mpc512x_shared.o +obj-$(CONFIG_COMMON_CLK) += clock-commonclk.o +obj-y += mpc512x_shared.o obj-$(CONFIG_MPC5121_ADS) += mpc5121_ads.o mpc5121_ads_cpld.o obj-$(CONFIG_MPC512x_GENERIC) += mpc512x_generic.o obj-$(CONFIG_PDM360NG) += pdm360ng.o diff --git a/arch/powerpc/platforms/512x/clock-commonclk.c b/arch/powerpc/platforms/512x/clock-commonclk.c new file mode 100644 index 00000000000..6eb614a271f --- /dev/null +++ b/arch/powerpc/platforms/512x/clock-commonclk.c @@ -0,0 +1,1221 @@ +/* + * Copyright (C) 2013 DENX Software Engineering + * + * Gerhard Sittig, <gsi@denx.de> + * + * common clock driver support for the MPC512x platform + * + * This is free software; you can redistribute it and/or modify it + * under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + */ + +#include <linux/bitops.h> +#include <linux/clk-provider.h> +#include <linux/clkdev.h> +#include <linux/device.h> +#include <linux/errno.h> +#include <linux/io.h> +#include <linux/of.h> +#include <linux/of_address.h> + +#include <asm/mpc5121.h> +#include <dt-bindings/clock/mpc512x-clock.h> + +#include "mpc512x.h" /* our public mpc5121_clk_init() API */ + +/* helpers to keep the MCLK intermediates "somewhere" in our table */ +enum { + MCLK_IDX_MUX0, + MCLK_IDX_EN0, + MCLK_IDX_DIV0, + MCLK_MAX_IDX, +}; + +#define NR_PSCS 12 +#define NR_MSCANS 4 +#define NR_SPDIFS 1 +#define NR_OUTCLK 4 +#define NR_MCLKS (NR_PSCS + NR_MSCANS + NR_SPDIFS + NR_OUTCLK) + +/* extend the public set of clocks by adding internal slots for management */ +enum { + /* arrange for adjacent numbers after the public set */ + MPC512x_CLK_START_PRIVATE = MPC512x_CLK_LAST_PUBLIC, + /* clocks which aren't announced to the public */ + MPC512x_CLK_DDR, + MPC512x_CLK_MEM, + MPC512x_CLK_IIM, + /* intermediates in div+gate combos or fractional dividers */ + MPC512x_CLK_DDR_UG, + MPC512x_CLK_SDHC_x4, + MPC512x_CLK_SDHC_UG, + MPC512x_CLK_SDHC2_UG, + MPC512x_CLK_DIU_x4, + MPC512x_CLK_DIU_UG, + MPC512x_CLK_MBX_BUS_UG, + MPC512x_CLK_MBX_UG, + MPC512x_CLK_MBX_3D_UG, + MPC512x_CLK_PCI_UG, + MPC512x_CLK_NFC_UG, + MPC512x_CLK_LPC_UG, + MPC512x_CLK_SPDIF_TX_IN, + /* intermediates for the mux+gate+div+mux MCLK generation */ + MPC512x_CLK_MCLKS_FIRST, + MPC512x_CLK_MCLKS_LAST = MPC512x_CLK_MCLKS_FIRST + + NR_MCLKS * MCLK_MAX_IDX, + /* internal, symbolic spec for the number of slots */ + MPC512x_CLK_LAST_PRIVATE, +}; + +/* data required for the OF clock provider registration */ +static struct clk *clks[MPC512x_CLK_LAST_PRIVATE]; +static struct clk_onecell_data clk_data; + +/* CCM register access */ +static struct mpc512x_ccm __iomem *clkregs; +static DEFINE_SPINLOCK(clklock); + +/* SoC variants {{{ */ + +/* + * tell SoC variants apart as they are rather similar yet not identical, + * cache the result in an enum to not repeatedly run the expensive OF test + * + * MPC5123 is an MPC5121 without the MBX graphics accelerator + * + * MPC5125 has many more differences: no MBX, no AXE, no VIU, no SPDIF, + * no PATA, no SATA, no PCI, two FECs (of different compatibility name), + * only 10 PSCs (of different compatibility name), two SDHCs, different + * NFC IP block, output clocks, system PLL status query, different CPMF + * interpretation, no CFM, different fourth PSC/CAN mux0 input -- yet + * those differences can get folded into this clock provider support + * code and don't warrant a separate highly redundant implementation + */ + +static enum soc_type { + MPC512x_SOC_MPC5121, + MPC512x_SOC_MPC5123, + MPC512x_SOC_MPC5125, +} soc; + +static void mpc512x_clk_determine_soc(void) +{ + if (of_machine_is_compatible("fsl,mpc5121")) { + soc = MPC512x_SOC_MPC5121; + return; + } + if (of_machine_is_compatible("fsl,mpc5123")) { + soc = MPC512x_SOC_MPC5123; + return; + } + if (of_machine_is_compatible("fsl,mpc5125")) { + soc = MPC512x_SOC_MPC5125; + return; + } +} + +static bool soc_has_mbx(void) +{ + if (soc == MPC512x_SOC_MPC5121) + return true; + return false; +} + +static bool soc_has_axe(void) +{ + if (soc == MPC512x_SOC_MPC5125) + return false; + return true; +} + +static bool soc_has_viu(void) +{ + if (soc == MPC512x_SOC_MPC5125) + return false; + return true; +} + +static bool soc_has_spdif(void) +{ + if (soc == MPC512x_SOC_MPC5125) + return false; + return true; +} + +static bool soc_has_pata(void) +{ + if (soc == MPC512x_SOC_MPC5125) + return false; + return true; +} + +static bool soc_has_sata(void) +{ + if (soc == MPC512x_SOC_MPC5125) + return false; + return true; +} + +static bool soc_has_pci(void) +{ + if (soc == MPC512x_SOC_MPC5125) + return false; + return true; +} + +static bool soc_has_fec2(void) +{ + if (soc == MPC512x_SOC_MPC5125) + return true; + return false; +} + +static int soc_max_pscnum(void) +{ + if (soc == MPC512x_SOC_MPC5125) + return 10; + return 12; +} + +static bool soc_has_sdhc2(void) +{ + if (soc == MPC512x_SOC_MPC5125) + return true; + return false; +} + +static bool soc_has_nfc_5125(void) +{ + if (soc == MPC512x_SOC_MPC5125) + return true; + return false; +} + +static bool soc_has_outclk(void) +{ + if (soc == MPC512x_SOC_MPC5125) + return true; + return false; +} + +static bool soc_has_cpmf_0_bypass(void) +{ + if (soc == MPC512x_SOC_MPC5125) + return true; + return false; +} + +static bool soc_has_mclk_mux0_canin(void) +{ + if (soc == MPC512x_SOC_MPC5125) + return true; + return false; +} + +/* }}} SoC variants */ +/* common clk API wrappers {{{ */ + +/* convenience wrappers around the common clk API */ +static inline struct clk *mpc512x_clk_fixed(const char *name, int rate) +{ + return clk_register_fixed_rate(NULL, name, NULL, CLK_IS_ROOT, rate); +} + +static inline struct clk *mpc512x_clk_factor( + const char *name, const char *parent_name, + int mul, int div) +{ + int clkflags; + + clkflags = CLK_SET_RATE_PARENT; + return clk_register_fixed_factor(NULL, name, parent_name, clkflags, + mul, div); +} + +static inline struct clk *mpc512x_clk_divider( + const char *name, const char *parent_name, u8 clkflags, + u32 __iomem *reg, u8 pos, u8 len, int divflags) +{ + return clk_register_divider(NULL, name, parent_name, clkflags, + reg, pos, len, divflags, &clklock); +} + +static inline struct clk *mpc512x_clk_divtable( + const char *name, const char *parent_name, + u32 __iomem *reg, u8 pos, u8 len, + const struct clk_div_table *divtab) +{ + u8 divflags; + + divflags = 0; + return clk_register_divider_table(NULL, name, parent_name, 0, + reg, pos, len, divflags, + divtab, &clklock); +} + +static inline struct clk *mpc512x_clk_gated( + const char *name, const char *parent_name, + u32 __iomem *reg, u8 pos) +{ + int clkflags; + + clkflags = CLK_SET_RATE_PARENT; + return clk_register_gate(NULL, name, parent_name, clkflags, + reg, pos, 0, &clklock); +} + +static inline struct clk *mpc512x_clk_muxed(const char *name, + const char **parent_names, int parent_count, + u32 __iomem *reg, u8 pos, u8 len) +{ + int clkflags; + u8 muxflags; + + clkflags = CLK_SET_RATE_PARENT; + muxflags = 0; + return clk_register_mux(NULL, name, + parent_names, parent_count, clkflags, + reg, pos, len, muxflags, &clklock); +} + +/* }}} common clk API wrappers */ + +/* helper to isolate a bit field from a register */ +static inline int get_bit_field(uint32_t __iomem *reg, uint8_t pos, uint8_t len) +{ + uint32_t val; + + val = in_be32(reg); + val >>= pos; + val &= (1 << len) - 1; + return val; +} + +/* get the SPMF and translate it into the "sys pll" multiplier */ +static int get_spmf_mult(void) +{ + static int spmf_to_mult[] = { + 68, 1, 12, 16, 20, 24, 28, 32, + 36, 40, 44, 48, 52, 56, 60, 64, + }; + int spmf; + + spmf = get_bit_field(&clkregs->spmr, 24, 4); + return spmf_to_mult[spmf]; +} + +/* + * get the SYS_DIV value and translate it into a divide factor + * + * values returned from here are a multiple of the real factor since the + * divide ratio is fractional + */ +static int get_sys_div_x2(void) +{ + static int sysdiv_code_to_x2[] = { + 4, 5, 6, 7, 8, 9, 10, 14, + 12, 16, 18, 22, 20, 24, 26, 30, + 28, 32, 34, 38, 36, 40, 42, 46, + 44, 48, 50, 54, 52, 56, 58, 62, + 60, 64, 66, + }; + int divcode; + + divcode = get_bit_field(&clkregs->scfr2, 26, 6); + return sysdiv_code_to_x2[divcode]; +} + +/* + * get the CPMF value and translate it into a multiplier factor + * + * values returned from here are a multiple of the real factor since the + * multiplier ratio is fractional + */ +static int get_cpmf_mult_x2(void) +{ + static int cpmf_to_mult_x36[] = { + /* 0b000 is "times 36" */ + 72, 2, 2, 3, 4, 5, 6, 7, + }; + static int cpmf_to_mult_0by[] = { + /* 0b000 is "bypass" */ + 2, 2, 2, 3, 4, 5, 6, 7, + }; + + int *cpmf_to_mult; + int cpmf; + + cpmf = get_bit_field(&clkregs->spmr, 16, 4); + if (soc_has_cpmf_0_bypass()) + cpmf_to_mult = cpmf_to_mult_0by; + else + cpmf_to_mult = cpmf_to_mult_x36; + return cpmf_to_mult[cpmf]; +} + +/* + * some of the clock dividers do scale in a linear way, yet not all of + * their bit combinations are legal; use a divider table to get a + * resulting set of applicable divider values + */ + +/* applies to the IPS_DIV, and PCI_DIV values */ +static struct clk_div_table divtab_2346[] = { + { .val = 2, .div = 2, }, + { .val = 3, .div = 3, }, + { .val = 4, .div = 4, }, + { .val = 6, .div = 6, }, + { .div = 0, }, +}; + +/* applies to the MBX_DIV, LPC_DIV, and NFC_DIV values */ +static struct clk_div_table divtab_1234[] = { + { .val = 1, .div = 1, }, + { .val = 2, .div = 2, }, + { .val = 3, .div = 3, }, + { .val = 4, .div = 4, }, + { .div = 0, }, +}; + +static int get_freq_from_dt(char *propname) +{ + struct device_node *np; + const unsigned int *prop; + int val; + + val = 0; + np = of_find_compatible_node(NULL, NULL, "fsl,mpc5121-immr"); + if (np) { + prop = of_get_property(np, propname, NULL); + if (prop) + val = *prop; + of_node_put(np); + } + return val; +} + +static void mpc512x_clk_preset_data(void) +{ + size_t i; + + for (i = 0; i < ARRAY_SIZE(clks); i++) + clks[i] = ERR_PTR(-ENODEV); +} + +/* + * - receives the "bus frequency" from the caller (that's the IPS clock + * rate, the historical source of clock information) + * - fetches the system PLL multiplier and divider values as well as the + * IPS divider value from hardware + * - determines the REF clock rate either from the XTAL/OSC spec (if + * there is a device tree node describing the oscillator) or from the + * IPS bus clock (supported for backwards compatibility, such that + * setups without XTAL/OSC specs keep working) + * - creates the "ref" clock item in the clock tree, such that + * subsequent code can create the remainder of the hierarchy (REF -> + * SYS -> CSB -> IPS) from the REF clock rate and the returned mul/div + * values + */ +static void mpc512x_clk_setup_ref_clock(struct device_node *np, int bus_freq, + int *sys_mul, int *sys_div, + int *ips_div) +{ + struct clk *osc_clk; + int calc_freq; + + /* fetch mul/div factors from the hardware */ + *sys_mul = get_spmf_mult(); + *sys_mul *= 2; /* compensate for the fractional divider */ + *sys_div = get_sys_div_x2(); + *ips_div = get_bit_field(&clkregs->scfr1, 23, 3); + + /* lookup the oscillator clock for its rate */ + osc_clk = of_clk_get_by_name(np, "osc"); + + /* + * either descend from OSC to REF (and in bypassing verify the + * IPS rate), or backtrack from IPS and multiplier values that + * were fetched from hardware to REF and thus to the OSC value + * + * in either case the REF clock gets created here and the + * remainder of the clock tree can get spanned from there + */ + if (!IS_ERR(osc_clk)) { + clks[MPC512x_CLK_REF] = mpc512x_clk_factor("ref", "osc", 1, 1); + calc_freq = clk_get_rate(clks[MPC512x_CLK_REF]); + calc_freq *= *sys_mul; + calc_freq /= *sys_div; + calc_freq /= 2; + calc_freq /= *ips_div; + if (bus_freq && calc_freq != bus_freq) + pr_warn("calc rate %d != OF spec %d\n", + calc_freq, bus_freq); + } else { + calc_freq = bus_freq; /* start with IPS */ + calc_freq *= *ips_div; /* IPS -> CSB */ + calc_freq *= 2; /* CSB -> SYS */ + calc_freq *= *sys_div; /* SYS -> PLL out */ + calc_freq /= *sys_mul; /* PLL out -> REF == OSC */ + clks[MPC512x_CLK_REF] = mpc512x_clk_fixed("ref", calc_freq); + } +} + +/* MCLK helpers {{{ */ + +/* + * helper code for the MCLK subtree setup + * + * the overview in section 5.2.4 of the MPC5121e Reference Manual rev4 + * suggests that all instances of the "PSC clock generation" are equal, + * and that one might re-use the PSC setup for MSCAN clock generation + * (section 5.2.5) as well, at least the logic if not the data for + * description + * + * the details (starting at page 5-20) show differences in the specific + * inputs of the first mux stage ("can clk in", "spdif tx"), and the + * factual non-availability of the second mux stage (it's present yet + * only one input is valid) + * + * the MSCAN clock related registers (starting at page 5-35) all + * reference "spdif clk" at the first mux stage and don't mention any + * "can clk" at all, which somehow is unexpected + * + * TODO re-check the document, and clarify whether the RM is correct in + * the overview or in the details, and whether the difference is a + * clipboard induced error or results from chip revisions + * + * it turns out that the RM rev4 as of 2012-06 talks about "can" for the + * PSCs while RM rev3 as of 2008-10 talks about "spdif", so I guess that + * first a doc update is required which better reflects reality in the + * SoC before the implementation should follow while no questions remain + */ + +/* + * note that this declaration raises a checkpatch warning, but + * it's the very data type dictated by <linux/clk-provider.h>, + * "fixing" this warning will break compilation + */ +static const char *parent_names_mux0_spdif[] = { + "sys", "ref", "psc-mclk-in", "spdif-tx", +}; + +static const char *parent_names_mux0_canin[] = { + "sys", "ref", "psc-mclk-in", "can-clk-in", +}; + +enum mclk_type { + MCLK_TYPE_PSC, + MCLK_TYPE_MSCAN, + MCLK_TYPE_SPDIF, + MCLK_TYPE_OUTCLK, +}; + +struct mclk_setup_data { + enum mclk_type type; + bool has_mclk1; + const char *name_mux0; + const char *name_en0; + const char *name_div0; + const char *parent_names_mux1[2]; + const char *name_mclk; +}; + +#define MCLK_SETUP_DATA_PSC(id) { \ + MCLK_TYPE_PSC, 0, \ + "psc" #id "-mux0", \ + "psc" #id "-en0", \ + "psc" #id "_mclk_div", \ + { "psc" #id "_mclk_div", "dummy", }, \ + "psc" #id "_mclk", \ +} + +#define MCLK_SETUP_DATA_MSCAN(id) { \ + MCLK_TYPE_MSCAN, 0, \ + "mscan" #id "-mux0", \ + "mscan" #id "-en0", \ + "mscan" #id "_mclk_div", \ + { "mscan" #id "_mclk_div", "dummy", }, \ + "mscan" #id "_mclk", \ +} + +#define MCLK_SETUP_DATA_SPDIF { \ + MCLK_TYPE_SPDIF, 1, \ + "spdif-mux0", \ + "spdif-en0", \ + "spdif_mclk_div", \ + { "spdif_mclk_div", "spdif-rx", }, \ + "spdif_mclk", \ +} + +#define MCLK_SETUP_DATA_OUTCLK(id) { \ + MCLK_TYPE_OUTCLK, 0, \ + "out" #id "-mux0", \ + "out" #id "-en0", \ + "out" #id "_mclk_div", \ + { "out" #id "_mclk_div", "dummy", }, \ + "out" #id "_clk", \ +} + +static struct mclk_setup_data mclk_psc_data[] = { + MCLK_SETUP_DATA_PSC(0), + MCLK_SETUP_DATA_PSC(1), + MCLK_SETUP_DATA_PSC(2), + MCLK_SETUP_DATA_PSC(3), + MCLK_SETUP_DATA_PSC(4), + MCLK_SETUP_DATA_PSC(5), + MCLK_SETUP_DATA_PSC(6), + MCLK_SETUP_DATA_PSC(7), + MCLK_SETUP_DATA_PSC(8), + MCLK_SETUP_DATA_PSC(9), + MCLK_SETUP_DATA_PSC(10), + MCLK_SETUP_DATA_PSC(11), +}; + +static struct mclk_setup_data mclk_mscan_data[] = { + MCLK_SETUP_DATA_MSCAN(0), + MCLK_SETUP_DATA_MSCAN(1), + MCLK_SETUP_DATA_MSCAN(2), + MCLK_SETUP_DATA_MSCAN(3), +}; + +static struct mclk_setup_data mclk_spdif_data[] = { + MCLK_SETUP_DATA_SPDIF, +}; + +static struct mclk_setup_data mclk_outclk_data[] = { + MCLK_SETUP_DATA_OUTCLK(0), + MCLK_SETUP_DATA_OUTCLK(1), + MCLK_SETUP_DATA_OUTCLK(2), + MCLK_SETUP_DATA_OUTCLK(3), +}; + +/* setup the MCLK clock subtree of an individual PSC/MSCAN/SPDIF */ +static void mpc512x_clk_setup_mclk(struct mclk_setup_data *entry, size_t idx) +{ + size_t clks_idx_pub, clks_idx_int; + u32 __iomem *mccr_reg; /* MCLK control register (mux, en, div) */ + int div; + + /* derive a few parameters from the component type and index */ + switch (entry->type) { + case MCLK_TYPE_PSC: + clks_idx_pub = MPC512x_CLK_PSC0_MCLK + idx; + clks_idx_int = MPC512x_CLK_MCLKS_FIRST + + (idx) * MCLK_MAX_IDX; + mccr_reg = &clkregs->psc_ccr[idx]; + break; + case MCLK_TYPE_MSCAN: + clks_idx_pub = MPC512x_CLK_MSCAN0_MCLK + idx; + clks_idx_int = MPC512x_CLK_MCLKS_FIRST + + (NR_PSCS + idx) * MCLK_MAX_IDX; + mccr_reg = &clkregs->mscan_ccr[idx]; + break; + case MCLK_TYPE_SPDIF: + clks_idx_pub = MPC512x_CLK_SPDIF_MCLK; + clks_idx_int = MPC512x_CLK_MCLKS_FIRST + + (NR_PSCS + NR_MSCANS) * MCLK_MAX_IDX; + mccr_reg = &clkregs->spccr; + break; + case MCLK_TYPE_OUTCLK: + clks_idx_pub = MPC512x_CLK_OUT0_CLK + idx; + clks_idx_int = MPC512x_CLK_MCLKS_FIRST + + (NR_PSCS + NR_MSCANS + NR_SPDIFS + idx) + * MCLK_MAX_IDX; + mccr_reg = &clkregs->out_ccr[idx]; + break; + default: + return; + } + + /* + * this was grabbed from the PPC_CLOCK implementation, which + * enforced a specific MCLK divider while the clock was gated + * during setup (that's a documented hardware requirement) + * + * the PPC_CLOCK implementation might even have violated the + * "MCLK <= IPS" constraint, the fixed divider value of 1 + * results in a divider of 2 and thus MCLK = SYS/2 which equals + * CSB which is greater than IPS; the serial port setup may have + * adjusted the divider which the clock setup might have left in + * an undesirable state + * + * initial setup is: + * - MCLK 0 from SYS + * - MCLK DIV such to not exceed the IPS clock + * - MCLK 0 enabled + * - MCLK 1 from MCLK DIV + */ + div = clk_get_rate(clks[MPC512x_CLK_SYS]); + div /= clk_get_rate(clks[MPC512x_CLK_IPS]); + out_be32(mccr_reg, (0 << 16)); + out_be32(mccr_reg, (0 << 16) | ((div - 1) << 17)); + out_be32(mccr_reg, (1 << 16) | ((div - 1) << 17)); + + /* + * create the 'struct clk' items of the MCLK's clock subtree + * + * note that by design we always create all nodes and won't take + * shortcuts here, because + * - the "internal" MCLK_DIV and MCLK_OUT signal in turn are + * selectable inputs to the CFM while those who "actually use" + * the PSC/MSCAN/SPDIF (serial drivers et al) need the MCLK + * for their bitrate + * - in the absence of "aliases" for clocks we need to create + * individial 'struct clk' items for whatever might get + * referenced or looked up, even if several of those items are + * identical from the logical POV (their rate value) + * - for easier future maintenance and for better reflection of + * the SoC's documentation, it appears appropriate to generate + * clock items even for those muxers which actually are NOPs + * (those with two inputs of which one is reserved) + */ + clks[clks_idx_int + MCLK_IDX_MUX0] = mpc512x_clk_muxed( + entry->name_mux0, + soc_has_mclk_mux0_canin() + ? &parent_names_mux0_canin[0] + : &parent_names_mux0_spdif[0], + ARRAY_SIZE(parent_names_mux0_spdif), + mccr_reg, 14, 2); + clks[clks_idx_int + MCLK_IDX_EN0] = mpc512x_clk_gated( + entry->name_en0, entry->name_mux0, + mccr_reg, 16); + clks[clks_idx_int + MCLK_IDX_DIV0] = mpc512x_clk_divider( + entry->name_div0, + entry->name_en0, CLK_SET_RATE_GATE, + mccr_reg, 17, 15, 0); + if (entry->has_mclk1) { + clks[clks_idx_pub] = mpc512x_clk_muxed( + entry->name_mclk, + &entry->parent_names_mux1[0], + ARRAY_SIZE(entry->parent_names_mux1), + mccr_reg, 7, 1); + } else { + clks[clks_idx_pub] = mpc512x_clk_factor( + entry->name_mclk, + entry->parent_names_mux1[0], + 1, 1); + } +} + +/* }}} MCLK helpers */ + +static void mpc512x_clk_setup_clock_tree(struct device_node *np, int busfreq) +{ + int sys_mul, sys_div, ips_div; + int mul, div; + size_t mclk_idx; + int freq; + + /* + * developer's notes: + * - consider whether to handle clocks which have both gates and + * dividers via intermediates or by means of composites + * - fractional dividers appear to not map well to composites + * since they can be seen as a fixed multiplier and an + * adjustable divider, while composites can only combine at + * most one of a mux, div, and gate each into one 'struct clk' + * item + * - PSC/MSCAN/SPDIF clock generation OTOH already is very + * specific and cannot get mapped to componsites (at least not + * a single one, maybe two of them, but then some of these + * intermediate clock signals get referenced elsewhere (e.g. + * in the clock frequency measurement, CFM) and thus need + * publicly available names + * - the current source layout appropriately reflects the + * hardware setup, and it works, so it's questionable whether + * further changes will result in big enough a benefit + */ + + /* regardless of whether XTAL/OSC exists, have REF created */ + mpc512x_clk_setup_ref_clock(np, busfreq, &sys_mul, &sys_div, &ips_div); + + /* now setup the REF -> SYS -> CSB -> IPS hierarchy */ + clks[MPC512x_CLK_SYS] = mpc512x_clk_factor("sys", "ref", + sys_mul, sys_div); + clks[MPC512x_CLK_CSB] = mpc512x_clk_factor("csb", "sys", 1, 2); + clks[MPC512x_CLK_IPS] = mpc512x_clk_divtable("ips", "csb", + &clkregs->scfr1, 23, 3, + divtab_2346); + /* now setup anything below SYS and CSB and IPS */ + + clks[MPC512x_CLK_DDR_UG] = mpc512x_clk_factor("ddr-ug", "sys", 1, 2); + + /* + * the Reference Manual discusses that for SDHC only even divide + * ratios are supported because clock domain synchronization + * between 'per' and 'ipg' is broken; + * keep the divider's bit 0 cleared (per reset value), and only + * allow to setup the divider's bits 7:1, which results in that + * only even divide ratios can get configured upon rate changes; + * keep the "x4" name because this bit shift hack is an internal + * implementation detail, the "fractional divider with quarters" + * semantics remains + */ + clks[MPC512x_CLK_SDHC_x4] = mpc512x_clk_factor("sdhc-x4", "csb", 2, 1); + clks[MPC512x_CLK_SDHC_UG] = mpc512x_clk_divider("sdhc-ug", "sdhc-x4", 0, + &clkregs->scfr2, 1, 7, + CLK_DIVIDER_ONE_BASED); + if (soc_has_sdhc2()) { + clks[MPC512x_CLK_SDHC2_UG] = mpc512x_clk_divider( + "sdhc2-ug", "sdhc-x4", 0, &clkregs->scfr2, + 9, 7, CLK_DIVIDER_ONE_BASED); + } + + clks[MPC512x_CLK_DIU_x4] = mpc512x_clk_factor("diu-x4", "csb", 4, 1); + clks[MPC512x_CLK_DIU_UG] = mpc512x_clk_divider("diu-ug", "diu-x4", 0, + &clkregs->scfr1, 0, 8, + CLK_DIVIDER_ONE_BASED); + + /* + * the "power architecture PLL" was setup from data which was + * sampled from the reset config word, at this point in time the + * configuration can be considered fixed and read only (i.e. no + * longer adjustable, or no longer in need of adjustment), which + * is why we don't register a PLL here but assume fixed factors + */ + mul = get_cpmf_mult_x2(); + div = 2; /* compensate for the fractional factor */ + clks[MPC512x_CLK_E300] = mpc512x_clk_factor("e300", "csb", mul, div); + + if (soc_has_mbx()) { + clks[MPC512x_CLK_MBX_BUS_UG] = mpc512x_clk_factor( + "mbx-bus-ug", "csb", 1, 2); + clks[MPC512x_CLK_MBX_UG] = mpc512x_clk_divtable( + "mbx-ug", "mbx-bus-ug", &clkregs->scfr1, + 14, 3, divtab_1234); + clks[MPC512x_CLK_MBX_3D_UG] = mpc512x_clk_factor( + "mbx-3d-ug", "mbx-ug", 1, 1); + } + if (soc_has_pci()) { + clks[MPC512x_CLK_PCI_UG] = mpc512x_clk_divtable( + "pci-ug", "csb", &clkregs->scfr1, + 20, 3, divtab_2346); + } + if (soc_has_nfc_5125()) { + /* + * XXX TODO implement 5125 NFC clock setup logic, + * with high/low period counters in clkregs->scfr3, + * currently there are no users so it's ENOIMPL + */ + clks[MPC512x_CLK_NFC_UG] = ERR_PTR(-ENOTSUPP); + } else { + clks[MPC512x_CLK_NFC_UG] = mpc512x_clk_divtable( + "nfc-ug", "ips", &clkregs->scfr1, + 8, 3, divtab_1234); + } + clks[MPC512x_CLK_LPC_UG] = mpc512x_clk_divtable("lpc-ug", "ips", + &clkregs->scfr1, 11, 3, + divtab_1234); + + clks[MPC512x_CLK_LPC] = mpc512x_clk_gated("lpc", "lpc-ug", + &clkregs->sccr1, 30); + clks[MPC512x_CLK_NFC] = mpc512x_clk_gated("nfc", "nfc-ug", + &clkregs->sccr1, 29); + if (soc_has_pata()) { + clks[MPC512x_CLK_PATA] = mpc512x_clk_gated( + "pata", "ips", &clkregs->sccr1, 28); + } + /* for PSCs there is a "registers" gate and a bitrate MCLK subtree */ + for (mclk_idx = 0; mclk_idx < soc_max_pscnum(); mclk_idx++) { + char name[12]; + snprintf(name, sizeof(name), "psc%d", mclk_idx); + clks[MPC512x_CLK_PSC0 + mclk_idx] = mpc512x_clk_gated( + name, "ips", &clkregs->sccr1, 27 - mclk_idx); + mpc512x_clk_setup_mclk(&mclk_psc_data[mclk_idx], mclk_idx); + } + clks[MPC512x_CLK_PSC_FIFO] = mpc512x_clk_gated("psc-fifo", "ips", + &clkregs->sccr1, 15); + if (soc_has_sata()) { + clks[MPC512x_CLK_SATA] = mpc512x_clk_gated( + "sata", "ips", &clkregs->sccr1, 14); + } + clks[MPC512x_CLK_FEC] = mpc512x_clk_gated("fec", "ips", + &clkregs->sccr1, 13); + if (soc_has_pci()) { + clks[MPC512x_CLK_PCI] = mpc512x_clk_gated( + "pci", "pci-ug", &clkregs->sccr1, 11); + } + clks[MPC512x_CLK_DDR] = mpc512x_clk_gated("ddr", "ddr-ug", + &clkregs->sccr1, 10); + if (soc_has_fec2()) { + clks[MPC512x_CLK_FEC2] = mpc512x_clk_gated( + "fec2", "ips", &clkregs->sccr1, 9); + } + + clks[MPC512x_CLK_DIU] = mpc512x_clk_gated("diu", "diu-ug", + &clkregs->sccr2, 31); + if (soc_has_axe()) { + clks[MPC512x_CLK_AXE] = mpc512x_clk_gated( + "axe", "csb", &clkregs->sccr2, 30); + } + clks[MPC512x_CLK_MEM] = mpc512x_clk_gated("mem", "ips", + &clkregs->sccr2, 29); + clks[MPC512x_CLK_USB1] = mpc512x_clk_gated("usb1", "csb", + &clkregs->sccr2, 28); + clks[MPC512x_CLK_USB2] = mpc512x_clk_gated("usb2", "csb", + &clkregs->sccr2, 27); + clks[MPC512x_CLK_I2C] = mpc512x_clk_gated("i2c", "ips", + &clkregs->sccr2, 26); + /* MSCAN differs from PSC with just one gate for multiple components */ + clks[MPC512x_CLK_BDLC] = mpc512x_clk_gated("bdlc", "ips", + &clkregs->sccr2, 25); + for (mclk_idx = 0; mclk_idx < ARRAY_SIZE(mclk_mscan_data); mclk_idx++) + mpc512x_clk_setup_mclk(&mclk_mscan_data[mclk_idx], mclk_idx); + clks[MPC512x_CLK_SDHC] = mpc512x_clk_gated("sdhc", "sdhc-ug", + &clkregs->sccr2, 24); + /* there is only one SPDIF component, which shares MCLK support code */ + if (soc_has_spdif()) { + clks[MPC512x_CLK_SPDIF] = mpc512x_clk_gated( + "spdif", "ips", &clkregs->sccr2, 23); + mpc512x_clk_setup_mclk(&mclk_spdif_data[0], 0); + } + if (soc_has_mbx()) { + clks[MPC512x_CLK_MBX_BUS] = mpc512x_clk_gated( + "mbx-bus", "mbx-bus-ug", &clkregs->sccr2, 22); + clks[MPC512x_CLK_MBX] = mpc512x_clk_gated( + "mbx", "mbx-ug", &clkregs->sccr2, 21); + clks[MPC512x_CLK_MBX_3D] = mpc512x_clk_gated( + "mbx-3d", "mbx-3d-ug", &clkregs->sccr2, 20); + } + clks[MPC512x_CLK_IIM] = mpc512x_clk_gated("iim", "csb", + &clkregs->sccr2, 19); + if (soc_has_viu()) { + clks[MPC512x_CLK_VIU] = mpc512x_clk_gated( + "viu", "csb", &clkregs->sccr2, 18); + } + if (soc_has_sdhc2()) { + clks[MPC512x_CLK_SDHC2] = mpc512x_clk_gated( + "sdhc-2", "sdhc2-ug", &clkregs->sccr2, 17); + } + + if (soc_has_outclk()) { + size_t idx; /* used as mclk_idx, just to trim line length */ + for (idx = 0; idx < ARRAY_SIZE(mclk_outclk_data); idx++) + mpc512x_clk_setup_mclk(&mclk_outclk_data[idx], idx); + } + + /* + * externally provided clocks (when implemented in hardware, + * device tree may specify values which otherwise were unknown) + */ + freq = get_freq_from_dt("psc_mclk_in"); + if (!freq) + freq = 25000000; + clks[MPC512x_CLK_PSC_MCLK_IN] = mpc512x_clk_fixed("psc_mclk_in", freq); + if (soc_has_mclk_mux0_canin()) { + freq = get_freq_from_dt("can_clk_in"); + clks[MPC512x_CLK_CAN_CLK_IN] = mpc512x_clk_fixed( + "can_clk_in", freq); + } else { + freq = get_freq_from_dt("spdif_tx_in"); + clks[MPC512x_CLK_SPDIF_TX_IN] = mpc512x_clk_fixed( + "spdif_tx_in", freq); + freq = get_freq_from_dt("spdif_rx_in"); + clks[MPC512x_CLK_SPDIF_TX_IN] = mpc512x_clk_fixed( + "spdif_rx_in", freq); + } + + /* fixed frequency for AC97, always 24.567MHz */ + clks[MPC512x_CLK_AC97] = mpc512x_clk_fixed("ac97", 24567000); + + /* + * pre-enable those "internal" clock items which never get + * claimed by any peripheral driver, to not have the clock + * subsystem disable them late at startup + */ + clk_prepare_enable(clks[MPC512x_CLK_DUMMY]); + clk_prepare_enable(clks[MPC512x_CLK_E300]); /* PowerPC CPU */ + clk_prepare_enable(clks[MPC512x_CLK_DDR]); /* DRAM */ + clk_prepare_enable(clks[MPC512x_CLK_MEM]); /* SRAM */ + clk_prepare_enable(clks[MPC512x_CLK_IPS]); /* SoC periph */ + clk_prepare_enable(clks[MPC512x_CLK_LPC]); /* boot media */ +} + +/* + * registers the set of public clocks (those listed in the dt-bindings/ + * header file) for OF lookups, keeps the intermediates private to us + */ +static void mpc5121_clk_register_of_provider(struct device_node *np) +{ + clk_data.clks = clks; + clk_data.clk_num = MPC512x_CLK_LAST_PUBLIC + 1; /* _not_ ARRAY_SIZE() */ + of_clk_add_provider(np, of_clk_src_onecell_get, &clk_data); +} + +/* + * temporary support for the period of time between introduction of CCF + * support and the adjustment of peripheral drivers to OF based lookups + */ +static void mpc5121_clk_provide_migration_support(void) +{ + + /* + * pre-enable those clock items which are not yet appropriately + * acquired by their peripheral driver + * + * the PCI clock cannot get acquired by its peripheral driver, + * because for this platform the driver won't probe(), instead + * initialization is done from within the .setup_arch() routine + * at a point in time where the clock provider has not been + * setup yet and thus isn't available yet + * + * so we "pre-enable" the clock here, to not have the clock + * subsystem automatically disable this item in a late init call + * + * this PCI clock pre-enable workaround only applies when there + * are device tree nodes for PCI and thus the peripheral driver + * has attached to bridges, otherwise the PCI clock remains + * unused and so it gets disabled + */ + clk_prepare_enable(clks[MPC512x_CLK_PSC3_MCLK]);/* serial console */ + if (of_find_compatible_node(NULL, "pci", "fsl,mpc5121-pci")) + clk_prepare_enable(clks[MPC512x_CLK_PCI]); +} + +/* + * those macros are not exactly pretty, but they encapsulate a lot + * of copy'n'paste heavy code which is even more ugly, and reduce + * the potential for inconsistencies in those many code copies + */ +#define FOR_NODES(compatname) \ + for_each_compatible_node(np, NULL, compatname) + +#define NODE_PREP do { \ + of_address_to_resource(np, 0, &res); \ + snprintf(devname, sizeof(devname), "%08x.%s", res.start, np->name); \ +} while (0) + +#define NODE_CHK(clkname, clkitem, regnode, regflag) do { \ + struct clk *clk; \ + clk = of_clk_get_by_name(np, clkname); \ + if (IS_ERR(clk)) { \ + clk = clkitem; \ + clk_register_clkdev(clk, clkname, devname); \ + if (regnode) \ + clk_register_clkdev(clk, clkname, np->name); \ + did_register |= DID_REG_ ## regflag; \ + pr_debug("clock alias name '%s' for dev '%s' pointer %p\n", \ + clkname, devname, clk); \ + } else { \ + clk_put(clk); \ + } \ +} while (0) + +/* + * register source code provided fallback results for clock lookups, + * these get consulted when OF based clock lookup fails (that is in the + * case of not yet adjusted device tree data, where clock related specs + * are missing) + */ +static void mpc5121_clk_provide_backwards_compat(void) +{ + enum did_reg_flags { + DID_REG_PSC = BIT(0), + DID_REG_PSCFIFO = BIT(1), + DID_REG_NFC = BIT(2), + DID_REG_CAN = BIT(3), + DID_REG_I2C = BIT(4), + DID_REG_DIU = BIT(5), + DID_REG_VIU = BIT(6), + DID_REG_FEC = BIT(7), + DID_REG_USB = BIT(8), + DID_REG_PATA = BIT(9), + }; + + int did_register; + struct device_node *np; + struct resource res; + int idx; + char devname[32]; + + did_register = 0; + + FOR_NODES(mpc512x_select_psc_compat()) { + NODE_PREP; + idx = (res.start >> 8) & 0xf; + NODE_CHK("ipg", clks[MPC512x_CLK_PSC0 + idx], 0, PSC); + NODE_CHK("mclk", clks[MPC512x_CLK_PSC0_MCLK + idx], 0, PSC); + } + + FOR_NODES("fsl,mpc5121-psc-fifo") { + NODE_PREP; + NODE_CHK("ipg", clks[MPC512x_CLK_PSC_FIFO], 1, PSCFIFO); + } + + FOR_NODES("fsl,mpc5121-nfc") { + NODE_PREP; + NODE_CHK("ipg", clks[MPC512x_CLK_NFC], 0, NFC); + } + + FOR_NODES("fsl,mpc5121-mscan") { + NODE_PREP; + idx = 0; + idx += (res.start & 0x2000) ? 2 : 0; + idx += (res.start & 0x0080) ? 1 : 0; + NODE_CHK("ipg", clks[MPC512x_CLK_BDLC], 0, CAN); + NODE_CHK("mclk", clks[MPC512x_CLK_MSCAN0_MCLK + idx], 0, CAN); + } + + /* + * do register the 'ips', 'sys', and 'ref' names globally + * instead of inside each individual CAN node, as there is no + * potential for a name conflict (in contrast to 'ipg' and 'mclk') + */ + if (did_register & DID_REG_CAN) { + clk_register_clkdev(clks[MPC512x_CLK_IPS], "ips", NULL); + clk_register_clkdev(clks[MPC512x_CLK_SYS], "sys", NULL); + clk_register_clkdev(clks[MPC512x_CLK_REF], "ref", NULL); + } + + FOR_NODES("fsl,mpc5121-i2c") { + NODE_PREP; + NODE_CHK("ipg", clks[MPC512x_CLK_I2C], 0, I2C); + } + + /* + * workaround for the fact that the I2C driver does an "anonymous" + * lookup (NULL name spec, which yields the first clock spec) for + * which we cannot register an alias -- a _global_ 'ipg' alias that + * is not bound to any device name and returns the I2C clock item + * is not a good idea + * + * so we have the lookup in the peripheral driver fail, which is + * silent and non-fatal, and pre-enable the clock item here such + * that register access is possible + * + * see commit b3bfce2b "i2c: mpc: cleanup clock API use" for + * details, adjusting s/NULL/"ipg"/ in i2c-mpc.c would make this + * workaround obsolete + */ + if (did_register & DID_REG_I2C) + clk_prepare_enable(clks[MPC512x_CLK_I2C]); + + FOR_NODES("fsl,mpc5121-diu") { + NODE_PREP; + NODE_CHK("ipg", clks[MPC512x_CLK_DIU], 1, DIU); + } + + FOR_NODES("fsl,mpc5121-viu") { + NODE_PREP; + NODE_CHK("ipg", clks[MPC512x_CLK_VIU], 0, VIU); + } + + /* + * note that 2771399a "fs_enet: cleanup clock API use" did use the + * "per" string for the clock lookup in contrast to the "ipg" name + * which most other nodes are using -- this is not a fatal thing + * but just something to keep in mind when doing compatibility + * registration, it's a non-issue with up-to-date device tree data + */ + FOR_NODES("fsl,mpc5121-fec") { + NODE_PREP; + NODE_CHK("per", clks[MPC512x_CLK_FEC], 0, FEC); + } + FOR_NODES("fsl,mpc5121-fec-mdio") { + NODE_PREP; + NODE_CHK("per", clks[MPC512x_CLK_FEC], 0, FEC); + } + /* + * MPC5125 has two FECs: FEC1 at 0x2800, FEC2 at 0x4800; + * the clock items don't "form an array" since FEC2 was + * added only later and was not allowed to shift all other + * clock item indices, so the numbers aren't adjacent + */ + FOR_NODES("fsl,mpc5125-fec") { + NODE_PREP; + if (res.start & 0x4000) + idx = MPC512x_CLK_FEC2; + else + idx = MPC512x_CLK_FEC; + NODE_CHK("per", clks[idx], 0, FEC); + } + + FOR_NODES("fsl,mpc5121-usb2-dr") { + NODE_PREP; + idx = (res.start & 0x4000) ? 1 : 0; + NODE_CHK("ipg", clks[MPC512x_CLK_USB1 + idx], 0, USB); + } + + FOR_NODES("fsl,mpc5121-pata") { + NODE_PREP; + NODE_CHK("ipg", clks[MPC512x_CLK_PATA], 0, PATA); + } + + /* + * try to collapse diagnostics into a single line of output yet + * provide a full list of what is missing, to avoid noise in the + * absence of up-to-date device tree data -- backwards + * compatibility to old DTBs is a requirement, updates may be + * desirable or preferrable but are not at all mandatory + */ + if (did_register) { + pr_notice("device tree lacks clock specs, adding fallbacks (0x%x,%s%s%s%s%s%s%s%s%s%s)\n", + did_register, + (did_register & DID_REG_PSC) ? " PSC" : "", + (did_register & DID_REG_PSCFIFO) ? " PSCFIFO" : "", + (did_register & DID_REG_NFC) ? " NFC" : "", + (did_register & DID_REG_CAN) ? " CAN" : "", + (did_register & DID_REG_I2C) ? " I2C" : "", + (did_register & DID_REG_DIU) ? " DIU" : "", + (did_register & DID_REG_VIU) ? " VIU" : "", + (did_register & DID_REG_FEC) ? " FEC" : "", + (did_register & DID_REG_USB) ? " USB" : "", + (did_register & DID_REG_PATA) ? " PATA" : ""); + } else { + pr_debug("device tree has clock specs, no fallbacks added\n"); + } +} + +int __init mpc5121_clk_init(void) +{ + struct device_node *clk_np; + int busfreq; + + /* map the clock control registers */ + clk_np = of_find_compatible_node(NULL, NULL, "fsl,mpc5121-clock"); + if (!clk_np) + return -ENODEV; + clkregs = of_iomap(clk_np, 0); + WARN_ON(!clkregs); + + /* determine the SoC variant we run on */ + mpc512x_clk_determine_soc(); + + /* invalidate all not yet registered clock slots */ + mpc512x_clk_preset_data(); + + /* + * have the device tree scanned for "fixed-clock" nodes (which + * includes the oscillator node if the board's DT provides one) + */ + of_clk_init(NULL); + + /* + * add a dummy clock for those situations where a clock spec is + * required yet no real clock is involved + */ + clks[MPC512x_CLK_DUMMY] = mpc512x_clk_fixed("dummy", 0); + + /* + * have all the real nodes in the clock tree populated from REF + * down to all leaves, either starting from the OSC node or from + * a REF root that was created from the IPS bus clock input + */ + busfreq = get_freq_from_dt("bus-frequency"); + mpc512x_clk_setup_clock_tree(clk_np, busfreq); + + /* register as an OF clock provider */ + mpc5121_clk_register_of_provider(clk_np); + + /* + * unbreak not yet adjusted peripheral drivers during migration + * towards fully operational common clock support, and allow + * operation in the absence of clock related device tree specs + */ + mpc5121_clk_provide_migration_support(); + mpc5121_clk_provide_backwards_compat(); + + return 0; +} diff --git a/arch/powerpc/platforms/512x/clock.c b/arch/powerpc/platforms/512x/clock.c deleted file mode 100644 index fd8a3765341..00000000000 --- a/arch/powerpc/platforms/512x/clock.c +++ /dev/null @@ -1,754 +0,0 @@ -/* - * Copyright (C) 2007,2008 Freescale Semiconductor, Inc. All rights reserved. - * - * Author: John Rigby <jrigby@freescale.com> - * - * Implements the clk api defined in include/linux/clk.h - * - * Original based on linux/arch/arm/mach-integrator/clock.c - * - * Copyright (C) 2004 ARM Limited. - * Written by Deep Blue Solutions Limited. - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License version 2 as - * published by the Free Software Foundation. - */ -#include <linux/kernel.h> -#include <linux/list.h> -#include <linux/errno.h> -#include <linux/err.h> -#include <linux/module.h> -#include <linux/string.h> -#include <linux/clk.h> -#include <linux/mutex.h> -#include <linux/io.h> - -#include <linux/of_address.h> -#include <linux/of_platform.h> -#include <asm/mpc5xxx.h> -#include <asm/mpc5121.h> -#include <asm/clk_interface.h> - -#include "mpc512x.h" - -#undef CLK_DEBUG - -static int clocks_initialized; - -#define CLK_HAS_RATE 0x1 /* has rate in MHz */ -#define CLK_HAS_CTRL 0x2 /* has control reg and bit */ - -struct clk { - struct list_head node; - char name[32]; - int flags; - struct device *dev; - unsigned long rate; - struct module *owner; - void (*calc) (struct clk *); - struct clk *parent; - int reg, bit; /* CLK_HAS_CTRL */ - int div_shift; /* only used by generic_div_clk_calc */ -}; - -static LIST_HEAD(clocks); -static DEFINE_MUTEX(clocks_mutex); - -static struct clk *mpc5121_clk_get(struct device *dev, const char *id) -{ - struct clk *p, *clk = ERR_PTR(-ENOENT); - int dev_match; - int id_match; - - if (dev == NULL || id == NULL) - return clk; - - mutex_lock(&clocks_mutex); - list_for_each_entry(p, &clocks, node) { - dev_match = id_match = 0; - - if (dev == p->dev) - dev_match++; - if (strcmp(id, p->name) == 0) - id_match++; - if ((dev_match || id_match) && try_module_get(p->owner)) { - clk = p; - break; - } - } - mutex_unlock(&clocks_mutex); - - return clk; -} - -#ifdef CLK_DEBUG -static void dump_clocks(void) -{ - struct clk *p; - - mutex_lock(&clocks_mutex); - printk(KERN_INFO "CLOCKS:\n"); - list_for_each_entry(p, &clocks, node) { - pr_info(" %s=%ld", p->name, p->rate); - if (p->parent) - pr_cont(" %s=%ld", p->parent->name, - p->parent->rate); - if (p->flags & CLK_HAS_CTRL) - pr_cont(" reg/bit=%d/%d", p->reg, p->bit); - pr_cont("\n"); - } - mutex_unlock(&clocks_mutex); -} -#define DEBUG_CLK_DUMP() dump_clocks() -#else -#define DEBUG_CLK_DUMP() -#endif - - -static void mpc5121_clk_put(struct clk *clk) -{ - module_put(clk->owner); -} - -#define NRPSC 12 - -struct mpc512x_clockctl { - u32 spmr; /* System PLL Mode Reg */ - u32 sccr[2]; /* System Clk Ctrl Reg 1 & 2 */ - u32 scfr1; /* System Clk Freq Reg 1 */ - u32 scfr2; /* System Clk Freq Reg 2 */ - u32 reserved; - u32 bcr; /* Bread Crumb Reg */ - u32 pccr[NRPSC]; /* PSC Clk Ctrl Reg 0-11 */ - u32 spccr; /* SPDIF Clk Ctrl Reg */ - u32 cccr; /* CFM Clk Ctrl Reg */ - u32 dccr; /* DIU Clk Cnfg Reg */ -}; - -static struct mpc512x_clockctl __iomem *clockctl; - -static int mpc5121_clk_enable(struct clk *clk) -{ - unsigned int mask; - - if (clk->flags & CLK_HAS_CTRL) { - mask = in_be32(&clockctl->sccr[clk->reg]); - mask |= 1 << clk->bit; - out_be32(&clockctl->sccr[clk->reg], mask); - } - return 0; -} - -static void mpc5121_clk_disable(struct clk *clk) -{ - unsigned int mask; - - if (clk->flags & CLK_HAS_CTRL) { - mask = in_be32(&clockctl->sccr[clk->reg]); - mask &= ~(1 << clk->bit); - out_be32(&clockctl->sccr[clk->reg], mask); - } -} - -static unsigned long mpc5121_clk_get_rate(struct clk *clk) -{ - if (clk->flags & CLK_HAS_RATE) - return clk->rate; - else - return 0; -} - -static long mpc5121_clk_round_rate(struct clk *clk, unsigned long rate) -{ - return rate; -} - -static int mpc5121_clk_set_rate(struct clk *clk, unsigned long rate) -{ - return 0; -} - -static int clk_register(struct clk *clk) -{ - mutex_lock(&clocks_mutex); - list_add(&clk->node, &clocks); - mutex_unlock(&clocks_mutex); - return 0; -} - -static unsigned long spmf_mult(void) -{ - /* - * Convert spmf to multiplier - */ - static int spmf_to_mult[] = { - 68, 1, 12, 16, - 20, 24, 28, 32, - 36, 40, 44, 48, - 52, 56, 60, 64 - }; - int spmf = (in_be32(&clockctl->spmr) >> 24) & 0xf; - return spmf_to_mult[spmf]; -} - -static unsigned long sysdiv_div_x_2(void) -{ - /* - * Convert sysdiv to divisor x 2 - * Some divisors have fractional parts so - * multiply by 2 then divide by this value - */ - static int sysdiv_to_div_x_2[] = { - 4, 5, 6, 7, - 8, 9, 10, 14, - 12, 16, 18, 22, - 20, 24, 26, 30, - 28, 32, 34, 38, - 36, 40, 42, 46, - 44, 48, 50, 54, - 52, 56, 58, 62, - 60, 64, 66, - }; - int sysdiv = (in_be32(&clockctl->scfr2) >> 26) & 0x3f; - return sysdiv_to_div_x_2[sysdiv]; -} - -static unsigned long ref_to_sys(unsigned long rate) -{ - rate *= spmf_mult(); - rate *= 2; - rate /= sysdiv_div_x_2(); - - return rate; -} - -static unsigned long sys_to_ref(unsigned long rate) -{ - rate *= sysdiv_div_x_2(); - rate /= 2; - rate /= spmf_mult(); - - return rate; -} - -static long ips_to_ref(unsigned long rate) -{ - int ips_div = (in_be32(&clockctl->scfr1) >> 23) & 0x7; - - rate *= ips_div; /* csb_clk = ips_clk * ips_div */ - rate *= 2; /* sys_clk = csb_clk * 2 */ - return sys_to_ref(rate); -} - -static unsigned long devtree_getfreq(char *clockname) -{ - struct device_node *np; - const unsigned int *prop; - unsigned int val = 0; - - np = of_find_compatible_node(NULL, NULL, "fsl,mpc5121-immr"); - if (np) { - prop = of_get_property(np, clockname, NULL); - if (prop) - val = *prop; - of_node_put(np); - } - return val; -} - -static void ref_clk_calc(struct clk *clk) -{ - unsigned long rate; - - rate = devtree_getfreq("bus-frequency"); - if (rate == 0) { - printk(KERN_ERR "No bus-frequency in dev tree\n"); - clk->rate = 0; - return; - } - clk->rate = ips_to_ref(rate); -} - -static struct clk ref_clk = { - .name = "ref_clk", - .calc = ref_clk_calc, -}; - - -static void sys_clk_calc(struct clk *clk) -{ - clk->rate = ref_to_sys(ref_clk.rate); -} - -static struct clk sys_clk = { - .name = "sys_clk", - .calc = sys_clk_calc, -}; - -static void diu_clk_calc(struct clk *clk) -{ - int diudiv_x_2 = in_be32(&clockctl->scfr1) & 0xff; - unsigned long rate; - - rate = sys_clk.rate; - - rate *= 2; - rate /= diudiv_x_2; - - clk->rate = rate; -} - -static void viu_clk_calc(struct clk *clk) -{ - unsigned long rate; - - rate = sys_clk.rate; - rate /= 2; - clk->rate = rate; -} - -static void half_clk_calc(struct clk *clk) -{ - clk->rate = clk->parent->rate / 2; -} - -static void generic_div_clk_calc(struct clk *clk) -{ - int div = (in_be32(&clockctl->scfr1) >> clk->div_shift) & 0x7; - - clk->rate = clk->parent->rate / div; -} - -static void unity_clk_calc(struct clk *clk) -{ - clk->rate = clk->parent->rate; -} - -static struct clk csb_clk = { - .name = "csb_clk", - .calc = half_clk_calc, - .parent = &sys_clk, -}; - -static void e300_clk_calc(struct clk *clk) -{ - int spmf = (in_be32(&clockctl->spmr) >> 16) & 0xf; - int ratex2 = clk->parent->rate * spmf; - - clk->rate = ratex2 / 2; -} - -static struct clk e300_clk = { - .name = "e300_clk", - .calc = e300_clk_calc, - .parent = &csb_clk, -}; - -static struct clk ips_clk = { - .name = "ips_clk", - .calc = generic_div_clk_calc, - .parent = &csb_clk, - .div_shift = 23, -}; - -/* - * Clocks controlled by SCCR1 (.reg = 0) - */ -static struct clk lpc_clk = { - .name = "lpc_clk", - .flags = CLK_HAS_CTRL, - .reg = 0, - .bit = 30, - .calc = generic_div_clk_calc, - .parent = &ips_clk, - .div_shift = 11, -}; - -static struct clk nfc_clk = { - .name = "nfc_clk", - .flags = CLK_HAS_CTRL, - .reg = 0, - .bit = 29, - .calc = generic_div_clk_calc, - .parent = &ips_clk, - .div_shift = 8, -}; - -static struct clk pata_clk = { - .name = "pata_clk", - .flags = CLK_HAS_CTRL, - .reg = 0, - .bit = 28, - .calc = unity_clk_calc, - .parent = &ips_clk, -}; - -/* - * PSC clocks (bits 27 - 16) - * are setup elsewhere - */ - -static struct clk sata_clk = { - .name = "sata_clk", - .flags = CLK_HAS_CTRL, - .reg = 0, - .bit = 14, - .calc = unity_clk_calc, - .parent = &ips_clk, -}; - -static struct clk fec_clk = { - .name = "fec_clk", - .flags = CLK_HAS_CTRL, - .reg = 0, - .bit = 13, - .calc = unity_clk_calc, - .parent = &ips_clk, -}; - -static struct clk pci_clk = { - .name = "pci_clk", - .flags = CLK_HAS_CTRL, - .reg = 0, - .bit = 11, - .calc = generic_div_clk_calc, - .parent = &csb_clk, - .div_shift = 20, -}; - -/* - * Clocks controlled by SCCR2 (.reg = 1) - */ -static struct clk diu_clk = { - .name = "diu_clk", - .flags = CLK_HAS_CTRL, - .reg = 1, - .bit = 31, - .calc = diu_clk_calc, -}; - -static struct clk viu_clk = { - .name = "viu_clk", - .flags = CLK_HAS_CTRL, - .reg = 1, - .bit = 18, - .calc = viu_clk_calc, -}; - -static struct clk axe_clk = { - .name = "axe_clk", - .flags = CLK_HAS_CTRL, - .reg = 1, - .bit = 30, - .calc = unity_clk_calc, - .parent = &csb_clk, -}; - -static struct clk usb1_clk = { - .name = "usb1_clk", - .flags = CLK_HAS_CTRL, - .reg = 1, - .bit = 28, - .calc = unity_clk_calc, - .parent = &csb_clk, -}; - -static struct clk usb2_clk = { - .name = "usb2_clk", - .flags = CLK_HAS_CTRL, - .reg = 1, - .bit = 27, - .calc = unity_clk_calc, - .parent = &csb_clk, -}; - -static struct clk i2c_clk = { - .name = "i2c_clk", - .flags = CLK_HAS_CTRL, - .reg = 1, - .bit = 26, - .calc = unity_clk_calc, - .parent = &ips_clk, -}; - -static struct clk mscan_clk = { - .name = "mscan_clk", - .flags = CLK_HAS_CTRL, - .reg = 1, - .bit = 25, - .calc = unity_clk_calc, - .parent = &ips_clk, -}; - -static struct clk sdhc_clk = { - .name = "sdhc_clk", - .flags = CLK_HAS_CTRL, - .reg = 1, - .bit = 24, - .calc = unity_clk_calc, - .parent = &ips_clk, -}; - -static struct clk mbx_bus_clk = { - .name = "mbx_bus_clk", - .flags = CLK_HAS_CTRL, - .reg = 1, - .bit = 22, - .calc = half_clk_calc, - .parent = &csb_clk, -}; - -static struct clk mbx_clk = { - .name = "mbx_clk", - .flags = CLK_HAS_CTRL, - .reg = 1, - .bit = 21, - .calc = unity_clk_calc, - .parent = &csb_clk, -}; - -static struct clk mbx_3d_clk = { - .name = "mbx_3d_clk", - .flags = CLK_HAS_CTRL, - .reg = 1, - .bit = 20, - .calc = generic_div_clk_calc, - .parent = &mbx_bus_clk, - .div_shift = 14, -}; - -static void psc_mclk_in_calc(struct clk *clk) -{ - clk->rate = devtree_getfreq("psc_mclk_in"); - if (!clk->rate) - clk->rate = 25000000; -} - -static struct clk psc_mclk_in = { - .name = "psc_mclk_in", - .calc = psc_mclk_in_calc, -}; - -static struct clk spdif_txclk = { - .name = "spdif_txclk", - .flags = CLK_HAS_CTRL, - .reg = 1, - .bit = 23, -}; - -static struct clk spdif_rxclk = { - .name = "spdif_rxclk", - .flags = CLK_HAS_CTRL, - .reg = 1, - .bit = 23, -}; - -static void ac97_clk_calc(struct clk *clk) -{ - /* ac97 bit clock is always 24.567 MHz */ - clk->rate = 24567000; -} - -static struct clk ac97_clk = { - .name = "ac97_clk_in", - .calc = ac97_clk_calc, -}; - -static struct clk *rate_clks[] = { - &ref_clk, - &sys_clk, - &diu_clk, - &viu_clk, - &csb_clk, - &e300_clk, - &ips_clk, - &fec_clk, - &sata_clk, - &pata_clk, - &nfc_clk, - &lpc_clk, - &mbx_bus_clk, - &mbx_clk, - &mbx_3d_clk, - &axe_clk, - &usb1_clk, - &usb2_clk, - &i2c_clk, - &mscan_clk, - &sdhc_clk, - &pci_clk, - &psc_mclk_in, - &spdif_txclk, - &spdif_rxclk, - &ac97_clk, - NULL -}; - -static void rate_clk_init(struct clk *clk) -{ - if (clk->calc) { - clk->calc(clk); - clk->flags |= CLK_HAS_RATE; - clk_register(clk); - } else { - printk(KERN_WARNING - "Could not initialize clk %s without a calc routine\n", - clk->name); - } -} - -static void rate_clks_init(void) -{ - struct clk **cpp, *clk; - - cpp = rate_clks; - while ((clk = *cpp++)) - rate_clk_init(clk); -} - -/* - * There are two clk enable registers with 32 enable bits each - * psc clocks and device clocks are all stored in dev_clks - */ -static struct clk dev_clks[2][32]; - -/* - * Given a psc number return the dev_clk - * associated with it - */ -static struct clk *psc_dev_clk(int pscnum) -{ - int reg, bit; - struct clk *clk; - - reg = 0; - bit = 27 - pscnum; - - clk = &dev_clks[reg][bit]; - clk->reg = 0; - clk->bit = bit; - return clk; -} - -/* - * PSC clock rate calculation - */ -static void psc_calc_rate(struct clk *clk, int pscnum, struct device_node *np) -{ - unsigned long mclk_src = sys_clk.rate; - unsigned long mclk_div; - - /* - * Can only change value of mclk divider - * when the divider is disabled. - * - * Zero is not a valid divider so minimum - * divider is 1 - * - * disable/set divider/enable - */ - out_be32(&clockctl->pccr[pscnum], 0); - out_be32(&clockctl->pccr[pscnum], 0x00020000); - out_be32(&clockctl->pccr[pscnum], 0x00030000); - - if (in_be32(&clockctl->pccr[pscnum]) & 0x80) { - clk->rate = spdif_rxclk.rate; - return; - } - - switch ((in_be32(&clockctl->pccr[pscnum]) >> 14) & 0x3) { - case 0: - mclk_src = sys_clk.rate; - break; - case 1: - mclk_src = ref_clk.rate; - break; - case 2: - mclk_src = psc_mclk_in.rate; - break; - case 3: - mclk_src = spdif_txclk.rate; - break; - } - - mclk_div = ((in_be32(&clockctl->pccr[pscnum]) >> 17) & 0x7fff) + 1; - clk->rate = mclk_src / mclk_div; -} - -/* - * Find all psc nodes in device tree and assign a clock - * with name "psc%d_mclk" and dev pointing at the device - * returned from of_find_device_by_node - */ -static void psc_clks_init(void) -{ - struct device_node *np; - struct platform_device *ofdev; - u32 reg; - const char *psc_compat; - - psc_compat = mpc512x_select_psc_compat(); - if (!psc_compat) - return; - - for_each_compatible_node(np, NULL, psc_compat) { - if (!of_property_read_u32(np, "reg", ®)) { - int pscnum = (reg & 0xf00) >> 8; - struct clk *clk = psc_dev_clk(pscnum); - - clk->flags = CLK_HAS_RATE | CLK_HAS_CTRL; - ofdev = of_find_device_by_node(np); - clk->dev = &ofdev->dev; - /* - * AC97 is special rate clock does - * not go through normal path - */ - if (of_device_is_compatible(np, "fsl,mpc5121-psc-ac97")) - clk->rate = ac97_clk.rate; - else - psc_calc_rate(clk, pscnum, np); - sprintf(clk->name, "psc%d_mclk", pscnum); - clk_register(clk); - clk_enable(clk); - } - } -} - -static struct clk_interface mpc5121_clk_functions = { - .clk_get = mpc5121_clk_get, - .clk_enable = mpc5121_clk_enable, - .clk_disable = mpc5121_clk_disable, - .clk_get_rate = mpc5121_clk_get_rate, - .clk_put = mpc5121_clk_put, - .clk_round_rate = mpc5121_clk_round_rate, - .clk_set_rate = mpc5121_clk_set_rate, - .clk_set_parent = NULL, - .clk_get_parent = NULL, -}; - -int __init mpc5121_clk_init(void) -{ - struct device_node *np; - - np = of_find_compatible_node(NULL, NULL, "fsl,mpc5121-clock"); - if (np) { - clockctl = of_iomap(np, 0); - of_node_put(np); - } - - if (!clockctl) { - printk(KERN_ERR "Could not map clock control registers\n"); - return 0; - } - - rate_clks_init(); - psc_clks_init(); - - /* leave clockctl mapped forever */ - /*iounmap(clockctl); */ - DEBUG_CLK_DUMP(); - clocks_initialized++; - clk_functions = mpc5121_clk_functions; - return 0; -} diff --git a/arch/powerpc/platforms/512x/mpc512x_shared.c b/arch/powerpc/platforms/512x/mpc512x_shared.c index 36b5652aada..adb95f03d4d 100644 --- a/arch/powerpc/platforms/512x/mpc512x_shared.c +++ b/arch/powerpc/platforms/512x/mpc512x_shared.c @@ -12,6 +12,7 @@ * (at your option) any later version. */ +#include <linux/clk.h> #include <linux/kernel.h> #include <linux/io.h> #include <linux/irq.h> @@ -68,98 +69,112 @@ struct fsl_diu_shared_fb { bool in_use; }; -#define DIU_DIV_MASK 0x000000ff +/* receives a pixel clock spec in pico seconds, adjusts the DIU clock rate */ static void mpc512x_set_pixel_clock(unsigned int pixclock) { - unsigned long bestval, bestfreq, speed, busfreq; - unsigned long minpixclock, maxpixclock, pixval; - struct mpc512x_ccm __iomem *ccm; struct device_node *np; - u32 temp; - long err; - int i; + struct clk *clk_diu; + unsigned long epsilon, minpixclock, maxpixclock; + unsigned long offset, want, got, delta; - np = of_find_compatible_node(NULL, NULL, "fsl,mpc5121-clock"); + /* lookup and enable the DIU clock */ + np = of_find_compatible_node(NULL, NULL, "fsl,mpc5121-diu"); if (!np) { - pr_err("Can't find clock control module.\n"); + pr_err("Could not find DIU device tree node.\n"); return; } - - ccm = of_iomap(np, 0); + clk_diu = of_clk_get(np, 0); + if (IS_ERR(clk_diu)) { + /* backwards compat with device trees that lack clock specs */ + clk_diu = clk_get_sys(np->name, "ipg"); + } of_node_put(np); - if (!ccm) { - pr_err("Can't map clock control module reg.\n"); + if (IS_ERR(clk_diu)) { + pr_err("Could not lookup DIU clock.\n"); return; } - - np = of_find_node_by_type(NULL, "cpu"); - if (np) { - const unsigned int *prop = - of_get_property(np, "bus-frequency", NULL); - - of_node_put(np); - if (prop) { - busfreq = *prop; - } else { - pr_err("Can't get bus-frequency property\n"); - return; - } - } else { - pr_err("Can't find 'cpu' node.\n"); + if (clk_prepare_enable(clk_diu)) { + pr_err("Could not enable DIU clock.\n"); return; } - /* Pixel Clock configuration */ - pr_debug("DIU: Bus Frequency = %lu\n", busfreq); - speed = busfreq * 4; /* DIU_DIV ratio is 4 * CSB_CLK / DIU_CLK */ - - /* Calculate the pixel clock with the smallest error */ - /* calculate the following in steps to avoid overflow */ - pr_debug("DIU pixclock in ps - %d\n", pixclock); - temp = (1000000000 / pixclock) * 1000; - pixclock = temp; - pr_debug("DIU pixclock freq - %u\n", pixclock); - - temp = temp / 20; /* pixclock * 0.05 */ - pr_debug("deviation = %d\n", temp); - minpixclock = pixclock - temp; - maxpixclock = pixclock + temp; - pr_debug("DIU minpixclock - %lu\n", minpixclock); - pr_debug("DIU maxpixclock - %lu\n", maxpixclock); - pixval = speed/pixclock; - pr_debug("DIU pixval = %lu\n", pixval); - - err = LONG_MAX; - bestval = pixval; - pr_debug("DIU bestval = %lu\n", bestval); - - bestfreq = 0; - for (i = -1; i <= 1; i++) { - temp = speed / (pixval+i); - pr_debug("DIU test pixval i=%d, pixval=%lu, temp freq. = %u\n", - i, pixval, temp); - if ((temp < minpixclock) || (temp > maxpixclock)) - pr_debug("DIU exceeds monitor range (%lu to %lu)\n", - minpixclock, maxpixclock); - else if (abs(temp - pixclock) < err) { - pr_debug("Entered the else if block %d\n", i); - err = abs(temp - pixclock); - bestval = pixval + i; - bestfreq = temp; - } + /* + * convert the picoseconds spec into the desired clock rate, + * determine the acceptable clock range for the monitor (+/- 5%), + * do the calculation in steps to avoid integer overflow + */ + pr_debug("DIU pixclock in ps - %u\n", pixclock); + pixclock = (1000000000 / pixclock) * 1000; + pr_debug("DIU pixclock freq - %u\n", pixclock); + epsilon = pixclock / 20; /* pixclock * 0.05 */ + pr_debug("DIU deviation - %lu\n", epsilon); + minpixclock = pixclock - epsilon; + maxpixclock = pixclock + epsilon; + pr_debug("DIU minpixclock - %lu\n", minpixclock); + pr_debug("DIU maxpixclock - %lu\n", maxpixclock); + + /* + * check whether the DIU supports the desired pixel clock + * + * - simply request the desired clock and see what the + * platform's clock driver will make of it, assuming that it + * will setup the best approximation of the requested value + * - try other candidate frequencies in the order of decreasing + * preference (i.e. with increasing distance from the desired + * pixel clock, and checking the lower frequency before the + * higher frequency to not overload the hardware) until the + * first match is found -- any potential subsequent match + * would only be as good as the former match or typically + * would be less preferrable + * + * the offset increment of pixelclock divided by 64 is an + * arbitrary choice -- it's simple to calculate, in the typical + * case we expect the first check to succeed already, in the + * worst case seven frequencies get tested (the exact center and + * three more values each to the left and to the right) before + * the 5% tolerance window is exceeded, resulting in fast enough + * execution yet high enough probability of finding a suitable + * value, while the error rate will be in the order of single + * percents + */ + for (offset = 0; offset <= epsilon; offset += pixclock / 64) { + want = pixclock - offset; + pr_debug("DIU checking clock - %lu\n", want); + clk_set_rate(clk_diu, want); + got = clk_get_rate(clk_diu); + delta = abs(pixclock - got); + if (delta < epsilon) + break; + if (!offset) + continue; + want = pixclock + offset; + pr_debug("DIU checking clock - %lu\n", want); + clk_set_rate(clk_diu, want); + got = clk_get_rate(clk_diu); + delta = abs(pixclock - got); + if (delta < epsilon) + break; } + if (offset <= epsilon) { + pr_debug("DIU clock accepted - %lu\n", want); + pr_debug("DIU pixclock want %u, got %lu, delta %lu, eps %lu\n", + pixclock, got, delta, epsilon); + return; + } + pr_warn("DIU pixclock auto search unsuccessful\n"); - pr_debug("DIU chose = %lx\n", bestval); - pr_debug("DIU error = %ld\n NomPixClk ", err); - pr_debug("DIU: Best Freq = %lx\n", bestfreq); - /* Modify DIU_DIV in CCM SCFR1 */ - temp = in_be32(&ccm->scfr1); - pr_debug("DIU: Current value of SCFR1: 0x%08x\n", temp); - temp &= ~DIU_DIV_MASK; - temp |= (bestval & DIU_DIV_MASK); - out_be32(&ccm->scfr1, temp); - pr_debug("DIU: Modified value of SCFR1: 0x%08x\n", temp); - iounmap(ccm); + /* + * what is the most appropriate action to take when the search + * for an available pixel clock which is acceptable to the + * monitor has failed? disable the DIU (clock) or just provide + * a "best effort"? we go with the latter + */ + pr_warn("DIU pixclock best effort fallback (backend's choice)\n"); + clk_set_rate(clk_diu, pixclock); + got = clk_get_rate(clk_diu); + delta = abs(pixclock - got); + pr_debug("DIU pixclock want %u, got %lu, delta %lu, eps %lu\n", + pixclock, got, delta, epsilon); } static enum fsl_diu_monitor_port diff --git a/arch/powerpc/platforms/52xx/Kconfig b/arch/powerpc/platforms/52xx/Kconfig index af54174801f..b625a2c6f4f 100644 --- a/arch/powerpc/platforms/52xx/Kconfig +++ b/arch/powerpc/platforms/52xx/Kconfig @@ -1,7 +1,7 @@ config PPC_MPC52xx bool "52xx-based boards" depends on 6xx - select PPC_CLOCK + select COMMON_CLK select PPC_PCI_CHOICE config PPC_MPC5200_SIMPLE diff --git a/arch/powerpc/platforms/powernv/setup.c b/arch/powerpc/platforms/powernv/setup.c index a932feb2901..21166f65c97 100644 --- a/arch/powerpc/platforms/powernv/setup.c +++ b/arch/powerpc/platforms/powernv/setup.c @@ -26,6 +26,7 @@ #include <linux/of_fdt.h> #include <linux/interrupt.h> #include <linux/bug.h> +#include <linux/cpuidle.h> #include <asm/machdep.h> #include <asm/firmware.h> @@ -216,6 +217,16 @@ static int __init pnv_probe(void) return 1; } +void powernv_idle(void) +{ + /* Hook to cpuidle framework if available, else + * call on default platform idle code + */ + if (cpuidle_idle_call()) { + power7_idle(); + } +} + define_machine(powernv) { .name = "PowerNV", .probe = pnv_probe, @@ -225,7 +236,7 @@ define_machine(powernv) { .show_cpuinfo = pnv_show_cpuinfo, .progress = pnv_progress, .machine_shutdown = pnv_shutdown, - .power_save = power7_idle, + .power_save = powernv_idle, .calibrate_decr = generic_calibrate_decr, #ifdef CONFIG_KEXEC .kexec_cpu_down = pnv_kexec_cpu_down, diff --git a/arch/powerpc/platforms/pseries/Kconfig b/arch/powerpc/platforms/pseries/Kconfig index e66643250fe..37300f6ee24 100644 --- a/arch/powerpc/platforms/pseries/Kconfig +++ b/arch/powerpc/platforms/pseries/Kconfig @@ -119,12 +119,3 @@ config DTL which are accessible through a debugfs file. Say N if you are unsure. - -config PSERIES_IDLE - bool "Cpuidle driver for pSeries platforms" - depends on CPU_IDLE - depends on PPC_PSERIES - default y - help - Select this option to enable processor idle state management - through cpuidle subsystem. diff --git a/arch/powerpc/platforms/pseries/Makefile b/arch/powerpc/platforms/pseries/Makefile index fbccac9cd2d..03480796af9 100644 --- a/arch/powerpc/platforms/pseries/Makefile +++ b/arch/powerpc/platforms/pseries/Makefile @@ -21,7 +21,6 @@ obj-$(CONFIG_HCALL_STATS) += hvCall_inst.o obj-$(CONFIG_CMM) += cmm.o obj-$(CONFIG_DTL) += dtl.o obj-$(CONFIG_IO_EVENT_IRQ) += io_event_irq.o -obj-$(CONFIG_PSERIES_IDLE) += processor_idle.o obj-$(CONFIG_LPARCFG) += lparcfg.o ifeq ($(CONFIG_PPC_PSERIES),y) diff --git a/arch/powerpc/platforms/pseries/processor_idle.c b/arch/powerpc/platforms/pseries/processor_idle.c deleted file mode 100644 index 002d5b4112f..00000000000 --- a/arch/powerpc/platforms/pseries/processor_idle.c +++ /dev/null @@ -1,308 +0,0 @@ -/* - * processor_idle - idle state cpuidle driver. - * Adapted from drivers/idle/intel_idle.c and - * drivers/acpi/processor_idle.c - * - */ - -#include <linux/kernel.h> -#include <linux/module.h> -#include <linux/init.h> -#include <linux/moduleparam.h> -#include <linux/cpuidle.h> -#include <linux/cpu.h> -#include <linux/notifier.h> - -#include <asm/paca.h> -#include <asm/reg.h> -#include <asm/machdep.h> -#include <asm/firmware.h> -#include <asm/plpar_wrappers.h> - -struct cpuidle_driver pseries_idle_driver = { - .name = "pseries_idle", - .owner = THIS_MODULE, -}; - -#define MAX_IDLE_STATE_COUNT 2 - -static int max_idle_state = MAX_IDLE_STATE_COUNT - 1; -static struct cpuidle_state *cpuidle_state_table; - -static inline void idle_loop_prolog(unsigned long *in_purr) -{ - *in_purr = mfspr(SPRN_PURR); - /* - * Indicate to the HV that we are idle. Now would be - * a good time to find other work to dispatch. - */ - get_lppaca()->idle = 1; -} - -static inline void idle_loop_epilog(unsigned long in_purr) -{ - u64 wait_cycles; - - wait_cycles = be64_to_cpu(get_lppaca()->wait_state_cycles); - wait_cycles += mfspr(SPRN_PURR) - in_purr; - get_lppaca()->wait_state_cycles = cpu_to_be64(wait_cycles); - get_lppaca()->idle = 0; -} - -static int snooze_loop(struct cpuidle_device *dev, - struct cpuidle_driver *drv, - int index) -{ - unsigned long in_purr; - int cpu = dev->cpu; - - idle_loop_prolog(&in_purr); - local_irq_enable(); - set_thread_flag(TIF_POLLING_NRFLAG); - - while ((!need_resched()) && cpu_online(cpu)) { - HMT_low(); - HMT_very_low(); - } - - HMT_medium(); - clear_thread_flag(TIF_POLLING_NRFLAG); - smp_mb(); - - idle_loop_epilog(in_purr); - - return index; -} - -static void check_and_cede_processor(void) -{ - /* - * Ensure our interrupt state is properly tracked, - * also checks if no interrupt has occurred while we - * were soft-disabled - */ - if (prep_irq_for_idle()) { - cede_processor(); -#ifdef CONFIG_TRACE_IRQFLAGS - /* Ensure that H_CEDE returns with IRQs on */ - if (WARN_ON(!(mfmsr() & MSR_EE))) - __hard_irq_enable(); -#endif - } -} - -static int dedicated_cede_loop(struct cpuidle_device *dev, - struct cpuidle_driver *drv, - int index) -{ - unsigned long in_purr; - - idle_loop_prolog(&in_purr); - get_lppaca()->donate_dedicated_cpu = 1; - - HMT_medium(); - check_and_cede_processor(); - - get_lppaca()->donate_dedicated_cpu = 0; - - idle_loop_epilog(in_purr); - - return index; -} - -static int shared_cede_loop(struct cpuidle_device *dev, - struct cpuidle_driver *drv, - int index) -{ - unsigned long in_purr; - - idle_loop_prolog(&in_purr); - - /* - * Yield the processor to the hypervisor. We return if - * an external interrupt occurs (which are driven prior - * to returning here) or if a prod occurs from another - * processor. When returning here, external interrupts - * are enabled. - */ - check_and_cede_processor(); - - idle_loop_epilog(in_purr); - - return index; -} - -/* - * States for dedicated partition case. - */ -static struct cpuidle_state dedicated_states[MAX_IDLE_STATE_COUNT] = { - { /* Snooze */ - .name = "snooze", - .desc = "snooze", - .flags = CPUIDLE_FLAG_TIME_VALID, - .exit_latency = 0, - .target_residency = 0, - .enter = &snooze_loop }, - { /* CEDE */ - .name = "CEDE", - .desc = "CEDE", - .flags = CPUIDLE_FLAG_TIME_VALID, - .exit_latency = 10, - .target_residency = 100, - .enter = &dedicated_cede_loop }, -}; - -/* - * States for shared partition case. - */ -static struct cpuidle_state shared_states[MAX_IDLE_STATE_COUNT] = { - { /* Shared Cede */ - .name = "Shared Cede", - .desc = "Shared Cede", - .flags = CPUIDLE_FLAG_TIME_VALID, - .exit_latency = 0, - .target_residency = 0, - .enter = &shared_cede_loop }, -}; - -void update_smt_snooze_delay(int cpu, int residency) -{ - struct cpuidle_driver *drv = cpuidle_get_driver(); - struct cpuidle_device *dev = per_cpu(cpuidle_devices, cpu); - - if (cpuidle_state_table != dedicated_states) - return; - - if (residency < 0) { - /* Disable the Nap state on that cpu */ - if (dev) - dev->states_usage[1].disable = 1; - } else - if (drv) - drv->states[1].target_residency = residency; -} - -static int pseries_cpuidle_add_cpu_notifier(struct notifier_block *n, - unsigned long action, void *hcpu) -{ - int hotcpu = (unsigned long)hcpu; - struct cpuidle_device *dev = - per_cpu_ptr(cpuidle_devices, hotcpu); - - if (dev && cpuidle_get_driver()) { - switch (action) { - case CPU_ONLINE: - case CPU_ONLINE_FROZEN: - cpuidle_pause_and_lock(); - cpuidle_enable_device(dev); - cpuidle_resume_and_unlock(); - break; - - case CPU_DEAD: - case CPU_DEAD_FROZEN: - cpuidle_pause_and_lock(); - cpuidle_disable_device(dev); - cpuidle_resume_and_unlock(); - break; - - default: - return NOTIFY_DONE; - } - } - return NOTIFY_OK; -} - -static struct notifier_block setup_hotplug_notifier = { - .notifier_call = pseries_cpuidle_add_cpu_notifier, -}; - -/* - * pseries_cpuidle_driver_init() - */ -static int pseries_cpuidle_driver_init(void) -{ - int idle_state; - struct cpuidle_driver *drv = &pseries_idle_driver; - - drv->state_count = 0; - - for (idle_state = 0; idle_state < MAX_IDLE_STATE_COUNT; ++idle_state) { - - if (idle_state > max_idle_state) - break; - - /* is the state not enabled? */ - if (cpuidle_state_table[idle_state].enter == NULL) - continue; - - drv->states[drv->state_count] = /* structure copy */ - cpuidle_state_table[idle_state]; - - drv->state_count += 1; - } - - return 0; -} - -/* - * pseries_idle_probe() - * Choose state table for shared versus dedicated partition - */ -static int pseries_idle_probe(void) -{ - - if (!firmware_has_feature(FW_FEATURE_SPLPAR)) - return -ENODEV; - - if (cpuidle_disable != IDLE_NO_OVERRIDE) - return -ENODEV; - - if (max_idle_state == 0) { - printk(KERN_DEBUG "pseries processor idle disabled.\n"); - return -EPERM; - } - - if (lppaca_shared_proc(get_lppaca())) - cpuidle_state_table = shared_states; - else - cpuidle_state_table = dedicated_states; - - return 0; -} - -static int __init pseries_processor_idle_init(void) -{ - int retval; - - retval = pseries_idle_probe(); - if (retval) - return retval; - - pseries_cpuidle_driver_init(); - retval = cpuidle_register(&pseries_idle_driver, NULL); - if (retval) { - printk(KERN_DEBUG "Registration of pseries driver failed.\n"); - return retval; - } - - register_cpu_notifier(&setup_hotplug_notifier); - printk(KERN_DEBUG "pseries_idle_driver registered\n"); - - return 0; -} - -static void __exit pseries_processor_idle_exit(void) -{ - - unregister_cpu_notifier(&setup_hotplug_notifier); - cpuidle_unregister(&pseries_idle_driver); - - return; -} - -module_init(pseries_processor_idle_init); -module_exit(pseries_processor_idle_exit); - -MODULE_AUTHOR("Deepthi Dharwar <deepthi@linux.vnet.ibm.com>"); -MODULE_DESCRIPTION("Cpuidle driver for POWER"); -MODULE_LICENSE("GPL"); diff --git a/arch/powerpc/sysdev/dart_iommu.c b/arch/powerpc/sysdev/dart_iommu.c index bd968a43a48..62c47bb7651 100644 --- a/arch/powerpc/sysdev/dart_iommu.c +++ b/arch/powerpc/sysdev/dart_iommu.c @@ -292,6 +292,7 @@ static void iommu_table_dart_setup(void) iommu_table_dart.it_offset = 0; /* it_size is in number of entries */ iommu_table_dart.it_size = dart_tablesize / sizeof(u32); + iommu_table_dart.it_page_shift = IOMMU_PAGE_SHIFT_4K; /* Initialize the common IOMMU code */ iommu_table_dart.it_base = (unsigned long)dart_vbase; |