diff options
Diffstat (limited to 'kernel/arch')
149 files changed, 1285 insertions, 1330 deletions
diff --git a/kernel/arch/arc/Makefile b/kernel/arch/arc/Makefile index db72fec0e..2f21e1e0e 100644 --- a/kernel/arch/arc/Makefile +++ b/kernel/arch/arc/Makefile @@ -43,7 +43,8 @@ endif ifndef CONFIG_CC_OPTIMIZE_FOR_SIZE # Generic build system uses -O2, we want -O3 -cflags-y += -O3 +# Note: No need to add to cflags-y as that happens anyways +ARCH_CFLAGS += -O3 endif # small data is default for elf32 tool-chain. If not usable, disable it diff --git a/kernel/arch/arc/include/asm/bitops.h b/kernel/arch/arc/include/asm/bitops.h index 624a9d048..dae03e66f 100644 --- a/kernel/arch/arc/include/asm/bitops.h +++ b/kernel/arch/arc/include/asm/bitops.h @@ -18,83 +18,49 @@ #include <linux/types.h> #include <linux/compiler.h> #include <asm/barrier.h> +#ifndef CONFIG_ARC_HAS_LLSC +#include <asm/smp.h> +#endif -/* - * Hardware assisted read-modify-write using ARC700 LLOCK/SCOND insns. - * The Kconfig glue ensures that in SMP, this is only set if the container - * SoC/platform has cross-core coherent LLOCK/SCOND - */ #if defined(CONFIG_ARC_HAS_LLSC) -static inline void set_bit(unsigned long nr, volatile unsigned long *m) -{ - unsigned int temp; - - m += nr >> 5; - - /* - * ARC ISA micro-optimization: - * - * Instructions dealing with bitpos only consider lower 5 bits (0-31) - * e.g (x << 33) is handled like (x << 1) by ASL instruction - * (mem pointer still needs adjustment to point to next word) - * - * Hence the masking to clamp @nr arg can be elided in general. - * - * However if @nr is a constant (above assumed it in a register), - * and greater than 31, gcc can optimize away (x << 33) to 0, - * as overflow, given the 32-bit ISA. Thus masking needs to be done - * for constant @nr, but no code is generated due to const prop. - */ - if (__builtin_constant_p(nr)) - nr &= 0x1f; - - __asm__ __volatile__( - "1: llock %0, [%1] \n" - " bset %0, %0, %2 \n" - " scond %0, [%1] \n" - " bnz 1b \n" - : "=&r"(temp) - : "r"(m), "ir"(nr) - : "cc"); -} - -static inline void clear_bit(unsigned long nr, volatile unsigned long *m) -{ - unsigned int temp; - - m += nr >> 5; - - if (__builtin_constant_p(nr)) - nr &= 0x1f; - - __asm__ __volatile__( - "1: llock %0, [%1] \n" - " bclr %0, %0, %2 \n" - " scond %0, [%1] \n" - " bnz 1b \n" - : "=&r"(temp) - : "r"(m), "ir"(nr) - : "cc"); -} - -static inline void change_bit(unsigned long nr, volatile unsigned long *m) -{ - unsigned int temp; - - m += nr >> 5; - - if (__builtin_constant_p(nr)) - nr &= 0x1f; +/* + * Hardware assisted Atomic-R-M-W + */ - __asm__ __volatile__( - "1: llock %0, [%1] \n" - " bxor %0, %0, %2 \n" - " scond %0, [%1] \n" - " bnz 1b \n" - : "=&r"(temp) - : "r"(m), "ir"(nr) - : "cc"); +#define BIT_OP(op, c_op, asm_op) \ +static inline void op##_bit(unsigned long nr, volatile unsigned long *m)\ +{ \ + unsigned int temp; \ + \ + m += nr >> 5; \ + \ + /* \ + * ARC ISA micro-optimization: \ + * \ + * Instructions dealing with bitpos only consider lower 5 bits \ + * e.g (x << 33) is handled like (x << 1) by ASL instruction \ + * (mem pointer still needs adjustment to point to next word) \ + * \ + * Hence the masking to clamp @nr arg can be elided in general. \ + * \ + * However if @nr is a constant (above assumed in a register), \ + * and greater than 31, gcc can optimize away (x << 33) to 0, \ + * as overflow, given the 32-bit ISA. Thus masking needs to be \ + * done for const @nr, but no code is generated due to gcc \ + * const prop. \ + */ \ + nr &= 0x1f; \ + \ + __asm__ __volatile__( \ + "1: llock %0, [%1] \n" \ + " " #asm_op " %0, %0, %2 \n" \ + " scond %0, [%1] \n" \ + " bnz 1b \n" \ + : "=&r"(temp) /* Early clobber, to prevent reg reuse */ \ + : "r"(m), /* Not "m": llock only supports reg direct addr mode */ \ + "ir"(nr) \ + : "cc"); \ } /* @@ -108,91 +74,37 @@ static inline void change_bit(unsigned long nr, volatile unsigned long *m) * Since ARC lacks a equivalent h/w primitive, the bit is set unconditionally * and the old value of bit is returned */ -static inline int test_and_set_bit(unsigned long nr, volatile unsigned long *m) -{ - unsigned long old, temp; - - m += nr >> 5; - - if (__builtin_constant_p(nr)) - nr &= 0x1f; - - /* - * Explicit full memory barrier needed before/after as - * LLOCK/SCOND themselves don't provide any such semantics - */ - smp_mb(); - - __asm__ __volatile__( - "1: llock %0, [%2] \n" - " bset %1, %0, %3 \n" - " scond %1, [%2] \n" - " bnz 1b \n" - : "=&r"(old), "=&r"(temp) - : "r"(m), "ir"(nr) - : "cc"); - - smp_mb(); - - return (old & (1 << nr)) != 0; -} - -static inline int -test_and_clear_bit(unsigned long nr, volatile unsigned long *m) -{ - unsigned int old, temp; - - m += nr >> 5; - - if (__builtin_constant_p(nr)) - nr &= 0x1f; - - smp_mb(); - - __asm__ __volatile__( - "1: llock %0, [%2] \n" - " bclr %1, %0, %3 \n" - " scond %1, [%2] \n" - " bnz 1b \n" - : "=&r"(old), "=&r"(temp) - : "r"(m), "ir"(nr) - : "cc"); - - smp_mb(); - - return (old & (1 << nr)) != 0; -} - -static inline int -test_and_change_bit(unsigned long nr, volatile unsigned long *m) -{ - unsigned int old, temp; - - m += nr >> 5; - - if (__builtin_constant_p(nr)) - nr &= 0x1f; - - smp_mb(); - - __asm__ __volatile__( - "1: llock %0, [%2] \n" - " bxor %1, %0, %3 \n" - " scond %1, [%2] \n" - " bnz 1b \n" - : "=&r"(old), "=&r"(temp) - : "r"(m), "ir"(nr) - : "cc"); - - smp_mb(); - - return (old & (1 << nr)) != 0; +#define TEST_N_BIT_OP(op, c_op, asm_op) \ +static inline int test_and_##op##_bit(unsigned long nr, volatile unsigned long *m)\ +{ \ + unsigned long old, temp; \ + \ + m += nr >> 5; \ + \ + nr &= 0x1f; \ + \ + /* \ + * Explicit full memory barrier needed before/after as \ + * LLOCK/SCOND themselves don't provide any such smenatic \ + */ \ + smp_mb(); \ + \ + __asm__ __volatile__( \ + "1: llock %0, [%2] \n" \ + " " #asm_op " %1, %0, %3 \n" \ + " scond %1, [%2] \n" \ + " bnz 1b \n" \ + : "=&r"(old), "=&r"(temp) \ + : "r"(m), "ir"(nr) \ + : "cc"); \ + \ + smp_mb(); \ + \ + return (old & (1 << nr)) != 0; \ } #else /* !CONFIG_ARC_HAS_LLSC */ -#include <asm/smp.h> - /* * Non hardware assisted Atomic-R-M-W * Locking would change to irq-disabling only (UP) and spinlocks (SMP) @@ -209,111 +121,37 @@ test_and_change_bit(unsigned long nr, volatile unsigned long *m) * at compile time) */ -static inline void set_bit(unsigned long nr, volatile unsigned long *m) -{ - unsigned long temp, flags; - m += nr >> 5; - - if (__builtin_constant_p(nr)) - nr &= 0x1f; - - bitops_lock(flags); - - temp = *m; - *m = temp | (1UL << nr); - - bitops_unlock(flags); +#define BIT_OP(op, c_op, asm_op) \ +static inline void op##_bit(unsigned long nr, volatile unsigned long *m)\ +{ \ + unsigned long temp, flags; \ + m += nr >> 5; \ + \ + /* \ + * spin lock/unlock provide the needed smp_mb() before/after \ + */ \ + bitops_lock(flags); \ + \ + temp = *m; \ + *m = temp c_op (1UL << (nr & 0x1f)); \ + \ + bitops_unlock(flags); \ } -static inline void clear_bit(unsigned long nr, volatile unsigned long *m) -{ - unsigned long temp, flags; - m += nr >> 5; - - if (__builtin_constant_p(nr)) - nr &= 0x1f; - - bitops_lock(flags); - - temp = *m; - *m = temp & ~(1UL << nr); - - bitops_unlock(flags); -} - -static inline void change_bit(unsigned long nr, volatile unsigned long *m) -{ - unsigned long temp, flags; - m += nr >> 5; - - if (__builtin_constant_p(nr)) - nr &= 0x1f; - - bitops_lock(flags); - - temp = *m; - *m = temp ^ (1UL << nr); - - bitops_unlock(flags); -} - -static inline int test_and_set_bit(unsigned long nr, volatile unsigned long *m) -{ - unsigned long old, flags; - m += nr >> 5; - - if (__builtin_constant_p(nr)) - nr &= 0x1f; - - /* - * spin lock/unlock provide the needed smp_mb() before/after - */ - bitops_lock(flags); - - old = *m; - *m = old | (1 << nr); - - bitops_unlock(flags); - - return (old & (1 << nr)) != 0; -} - -static inline int -test_and_clear_bit(unsigned long nr, volatile unsigned long *m) -{ - unsigned long old, flags; - m += nr >> 5; - - if (__builtin_constant_p(nr)) - nr &= 0x1f; - - bitops_lock(flags); - - old = *m; - *m = old & ~(1 << nr); - - bitops_unlock(flags); - - return (old & (1 << nr)) != 0; -} - -static inline int -test_and_change_bit(unsigned long nr, volatile unsigned long *m) -{ - unsigned long old, flags; - m += nr >> 5; - - if (__builtin_constant_p(nr)) - nr &= 0x1f; - - bitops_lock(flags); - - old = *m; - *m = old ^ (1 << nr); - - bitops_unlock(flags); - - return (old & (1 << nr)) != 0; +#define TEST_N_BIT_OP(op, c_op, asm_op) \ +static inline int test_and_##op##_bit(unsigned long nr, volatile unsigned long *m)\ +{ \ + unsigned long old, flags; \ + m += nr >> 5; \ + \ + bitops_lock(flags); \ + \ + old = *m; \ + *m = old c_op (1UL << (nr & 0x1f)); \ + \ + bitops_unlock(flags); \ + \ + return (old & (1UL << (nr & 0x1f))) != 0; \ } #endif /* CONFIG_ARC_HAS_LLSC */ @@ -322,86 +160,45 @@ test_and_change_bit(unsigned long nr, volatile unsigned long *m) * Non atomic variants **************************************/ -static inline void __set_bit(unsigned long nr, volatile unsigned long *m) -{ - unsigned long temp; - m += nr >> 5; - - if (__builtin_constant_p(nr)) - nr &= 0x1f; - - temp = *m; - *m = temp | (1UL << nr); +#define __BIT_OP(op, c_op, asm_op) \ +static inline void __##op##_bit(unsigned long nr, volatile unsigned long *m) \ +{ \ + unsigned long temp; \ + m += nr >> 5; \ + \ + temp = *m; \ + *m = temp c_op (1UL << (nr & 0x1f)); \ } -static inline void __clear_bit(unsigned long nr, volatile unsigned long *m) -{ - unsigned long temp; - m += nr >> 5; - - if (__builtin_constant_p(nr)) - nr &= 0x1f; - - temp = *m; - *m = temp & ~(1UL << nr); +#define __TEST_N_BIT_OP(op, c_op, asm_op) \ +static inline int __test_and_##op##_bit(unsigned long nr, volatile unsigned long *m)\ +{ \ + unsigned long old; \ + m += nr >> 5; \ + \ + old = *m; \ + *m = old c_op (1UL << (nr & 0x1f)); \ + \ + return (old & (1UL << (nr & 0x1f))) != 0; \ } -static inline void __change_bit(unsigned long nr, volatile unsigned long *m) -{ - unsigned long temp; - m += nr >> 5; - - if (__builtin_constant_p(nr)) - nr &= 0x1f; - - temp = *m; - *m = temp ^ (1UL << nr); -} - -static inline int -__test_and_set_bit(unsigned long nr, volatile unsigned long *m) -{ - unsigned long old; - m += nr >> 5; - - if (__builtin_constant_p(nr)) - nr &= 0x1f; - - old = *m; - *m = old | (1 << nr); - - return (old & (1 << nr)) != 0; -} - -static inline int -__test_and_clear_bit(unsigned long nr, volatile unsigned long *m) -{ - unsigned long old; - m += nr >> 5; - - if (__builtin_constant_p(nr)) - nr &= 0x1f; - - old = *m; - *m = old & ~(1 << nr); - - return (old & (1 << nr)) != 0; -} - -static inline int -__test_and_change_bit(unsigned long nr, volatile unsigned long *m) -{ - unsigned long old; - m += nr >> 5; - - if (__builtin_constant_p(nr)) - nr &= 0x1f; - - old = *m; - *m = old ^ (1 << nr); - - return (old & (1 << nr)) != 0; -} +#define BIT_OPS(op, c_op, asm_op) \ + \ + /* set_bit(), clear_bit(), change_bit() */ \ + BIT_OP(op, c_op, asm_op) \ + \ + /* test_and_set_bit(), test_and_clear_bit(), test_and_change_bit() */\ + TEST_N_BIT_OP(op, c_op, asm_op) \ + \ + /* __set_bit(), __clear_bit(), __change_bit() */ \ + __BIT_OP(op, c_op, asm_op) \ + \ + /* __test_and_set_bit(), __test_and_clear_bit(), __test_and_change_bit() */\ + __TEST_N_BIT_OP(op, c_op, asm_op) + +BIT_OPS(set, |, bset) +BIT_OPS(clear, & ~, bclr) +BIT_OPS(change, ^, bxor) /* * This routine doesn't need to be atomic. @@ -413,10 +210,7 @@ test_bit(unsigned int nr, const volatile unsigned long *addr) addr += nr >> 5; - if (__builtin_constant_p(nr)) - nr &= 0x1f; - - mask = 1 << nr; + mask = 1UL << (nr & 0x1f); return ((mask & *addr) != 0); } diff --git a/kernel/arch/arc/include/asm/ptrace.h b/kernel/arch/arc/include/asm/ptrace.h index 1bfeec2c0..2a58af7a2 100644 --- a/kernel/arch/arc/include/asm/ptrace.h +++ b/kernel/arch/arc/include/asm/ptrace.h @@ -63,7 +63,7 @@ struct callee_regs { long r25, r24, r23, r22, r21, r20, r19, r18, r17, r16, r15, r14, r13; }; -#define instruction_pointer(regs) ((regs)->ret) +#define instruction_pointer(regs) (unsigned long)((regs)->ret) #define profile_pc(regs) instruction_pointer(regs) /* return 1 if user mode or 0 if kernel mode */ diff --git a/kernel/arch/arm/boot/dts/am57xx-beagle-x15.dts b/kernel/arch/arm/boot/dts/am57xx-beagle-x15.dts index 7128fad99..c9df40e5c 100644 --- a/kernel/arch/arm/boot/dts/am57xx-beagle-x15.dts +++ b/kernel/arch/arm/boot/dts/am57xx-beagle-x15.dts @@ -544,6 +544,10 @@ phy-supply = <&ldousb_reg>; }; +&usb2_phy2 { + phy-supply = <&ldousb_reg>; +}; + &usb1 { dr_mode = "host"; pinctrl-names = "default"; diff --git a/kernel/arch/arm/boot/dts/at91-sama5d4ek.dts b/kernel/arch/arm/boot/dts/at91-sama5d4ek.dts index 89ef4a540..45e7761b7 100644 --- a/kernel/arch/arm/boot/dts/at91-sama5d4ek.dts +++ b/kernel/arch/arm/boot/dts/at91-sama5d4ek.dts @@ -108,8 +108,8 @@ mmc0: mmc@f8000000 { pinctrl-names = "default"; pinctrl-0 = <&pinctrl_mmc0_clk_cmd_dat0 &pinctrl_mmc0_dat1_3 &pinctrl_mmc0_cd>; - slot@1 { - reg = <1>; + slot@0 { + reg = <0>; bus-width = <4>; cd-gpios = <&pioE 5 0>; }; diff --git a/kernel/arch/arm/boot/dts/at91sam9g45.dtsi b/kernel/arch/arm/boot/dts/at91sam9g45.dtsi index 70e59c5ce..e54421176 100644 --- a/kernel/arch/arm/boot/dts/at91sam9g45.dtsi +++ b/kernel/arch/arm/boot/dts/at91sam9g45.dtsi @@ -1148,7 +1148,7 @@ usb2: gadget@fff78000 { #address-cells = <1>; #size-cells = <0>; - compatible = "atmel,at91sam9rl-udc"; + compatible = "atmel,at91sam9g45-udc"; reg = <0x00600000 0x80000 0xfff78000 0x400>; interrupts = <27 IRQ_TYPE_LEVEL_HIGH 0>; diff --git a/kernel/arch/arm/boot/dts/at91sam9x5.dtsi b/kernel/arch/arm/boot/dts/at91sam9x5.dtsi index 3aa56ae34..3314a7303 100644 --- a/kernel/arch/arm/boot/dts/at91sam9x5.dtsi +++ b/kernel/arch/arm/boot/dts/at91sam9x5.dtsi @@ -1062,7 +1062,7 @@ usb2: gadget@f803c000 { #address-cells = <1>; #size-cells = <0>; - compatible = "atmel,at91sam9rl-udc"; + compatible = "atmel,at91sam9g45-udc"; reg = <0x00500000 0x80000 0xf803c000 0x400>; interrupts = <23 IRQ_TYPE_LEVEL_HIGH 0>; diff --git a/kernel/arch/arm/boot/dts/dra7-evm.dts b/kernel/arch/arm/boot/dts/dra7-evm.dts index aa465904f..096f68be9 100644 --- a/kernel/arch/arm/boot/dts/dra7-evm.dts +++ b/kernel/arch/arm/boot/dts/dra7-evm.dts @@ -686,7 +686,8 @@ &dcan1 { status = "ok"; - pinctrl-names = "default", "sleep"; - pinctrl-0 = <&dcan1_pins_default>; + pinctrl-names = "default", "sleep", "active"; + pinctrl-0 = <&dcan1_pins_sleep>; pinctrl-1 = <&dcan1_pins_sleep>; + pinctrl-2 = <&dcan1_pins_default>; }; diff --git a/kernel/arch/arm/boot/dts/dra7.dtsi b/kernel/arch/arm/boot/dts/dra7.dtsi index f03a091cd..dfcc0dd63 100644 --- a/kernel/arch/arm/boot/dts/dra7.dtsi +++ b/kernel/arch/arm/boot/dts/dra7.dtsi @@ -116,7 +116,7 @@ ranges = <0 0x2000 0x2000>; scm_conf: scm_conf@0 { - compatible = "syscon"; + compatible = "syscon", "simple-bus"; reg = <0x0 0x1400>; #address-cells = <1>; #size-cells = <1>; diff --git a/kernel/arch/arm/boot/dts/dra72-evm.dts b/kernel/arch/arm/boot/dts/dra72-evm.dts index ce0390f08..6b05f6a0b 100644 --- a/kernel/arch/arm/boot/dts/dra72-evm.dts +++ b/kernel/arch/arm/boot/dts/dra72-evm.dts @@ -497,9 +497,10 @@ &dcan1 { status = "ok"; - pinctrl-names = "default", "sleep"; - pinctrl-0 = <&dcan1_pins_default>; + pinctrl-names = "default", "sleep", "active"; + pinctrl-0 = <&dcan1_pins_sleep>; pinctrl-1 = <&dcan1_pins_sleep>; + pinctrl-2 = <&dcan1_pins_default>; }; &qspi { diff --git a/kernel/arch/arm/boot/dts/imx23.dtsi b/kernel/arch/arm/boot/dts/imx23.dtsi index bbcfb5a19..0cb8b0b11 100644 --- a/kernel/arch/arm/boot/dts/imx23.dtsi +++ b/kernel/arch/arm/boot/dts/imx23.dtsi @@ -435,6 +435,7 @@ interrupts = <36 37 38 39 40 41 42 43 44>; status = "disabled"; clocks = <&clks 26>; + #io-channel-cells = <1>; }; spdif@80054000 { diff --git a/kernel/arch/arm/boot/dts/imx35.dtsi b/kernel/arch/arm/boot/dts/imx35.dtsi index b6478e97d..e6540b5cf 100644 --- a/kernel/arch/arm/boot/dts/imx35.dtsi +++ b/kernel/arch/arm/boot/dts/imx35.dtsi @@ -286,8 +286,8 @@ can1: can@53fe4000 { compatible = "fsl,imx35-flexcan", "fsl,p1010-flexcan"; reg = <0x53fe4000 0x1000>; - clocks = <&clks 33>; - clock-names = "ipg"; + clocks = <&clks 33>, <&clks 33>; + clock-names = "ipg", "per"; interrupts = <43>; status = "disabled"; }; @@ -295,8 +295,8 @@ can2: can@53fe8000 { compatible = "fsl,imx35-flexcan", "fsl,p1010-flexcan"; reg = <0x53fe8000 0x1000>; - clocks = <&clks 34>; - clock-names = "ipg"; + clocks = <&clks 34>, <&clks 34>; + clock-names = "ipg", "per"; interrupts = <44>; status = "disabled"; }; diff --git a/kernel/arch/arm/boot/dts/imx6qdl.dtsi b/kernel/arch/arm/boot/dts/imx6qdl.dtsi index f74a8ded5..38c786018 100644 --- a/kernel/arch/arm/boot/dts/imx6qdl.dtsi +++ b/kernel/arch/arm/boot/dts/imx6qdl.dtsi @@ -153,10 +153,10 @@ interrupt-names = "msi"; #interrupt-cells = <1>; interrupt-map-mask = <0 0 0 0x7>; - interrupt-map = <0 0 0 1 &intc GIC_SPI 123 IRQ_TYPE_LEVEL_HIGH>, - <0 0 0 2 &intc GIC_SPI 122 IRQ_TYPE_LEVEL_HIGH>, - <0 0 0 3 &intc GIC_SPI 121 IRQ_TYPE_LEVEL_HIGH>, - <0 0 0 4 &intc GIC_SPI 120 IRQ_TYPE_LEVEL_HIGH>; + interrupt-map = <0 0 0 1 &gpc GIC_SPI 123 IRQ_TYPE_LEVEL_HIGH>, + <0 0 0 2 &gpc GIC_SPI 122 IRQ_TYPE_LEVEL_HIGH>, + <0 0 0 3 &gpc GIC_SPI 121 IRQ_TYPE_LEVEL_HIGH>, + <0 0 0 4 &gpc GIC_SPI 120 IRQ_TYPE_LEVEL_HIGH>; clocks = <&clks IMX6QDL_CLK_PCIE_AXI>, <&clks IMX6QDL_CLK_LVDS1_GATE>, <&clks IMX6QDL_CLK_PCIE_REF_125M>; diff --git a/kernel/arch/arm/boot/dts/k2e-clocks.dtsi b/kernel/arch/arm/boot/dts/k2e-clocks.dtsi index 4773d6af6..d56d68fe7 100644 --- a/kernel/arch/arm/boot/dts/k2e-clocks.dtsi +++ b/kernel/arch/arm/boot/dts/k2e-clocks.dtsi @@ -13,9 +13,8 @@ clocks { #clock-cells = <0>; compatible = "ti,keystone,main-pll-clock"; clocks = <&refclksys>; - reg = <0x02620350 4>, <0x02310110 4>; - reg-names = "control", "multiplier"; - fixed-postdiv = <2>; + reg = <0x02620350 4>, <0x02310110 4>, <0x02310108 4>; + reg-names = "control", "multiplier", "post-divider"; }; papllclk: papllclk@2620358 { diff --git a/kernel/arch/arm/boot/dts/k2hk-clocks.dtsi b/kernel/arch/arm/boot/dts/k2hk-clocks.dtsi index d5adee3c0..af9b71905 100644 --- a/kernel/arch/arm/boot/dts/k2hk-clocks.dtsi +++ b/kernel/arch/arm/boot/dts/k2hk-clocks.dtsi @@ -22,9 +22,8 @@ clocks { #clock-cells = <0>; compatible = "ti,keystone,main-pll-clock"; clocks = <&refclksys>; - reg = <0x02620350 4>, <0x02310110 4>; - reg-names = "control", "multiplier"; - fixed-postdiv = <2>; + reg = <0x02620350 4>, <0x02310110 4>, <0x02310108 4>; + reg-names = "control", "multiplier", "post-divider"; }; papllclk: papllclk@2620358 { diff --git a/kernel/arch/arm/boot/dts/k2l-clocks.dtsi b/kernel/arch/arm/boot/dts/k2l-clocks.dtsi index eb1e3e29f..ef8464bb1 100644 --- a/kernel/arch/arm/boot/dts/k2l-clocks.dtsi +++ b/kernel/arch/arm/boot/dts/k2l-clocks.dtsi @@ -22,9 +22,8 @@ clocks { #clock-cells = <0>; compatible = "ti,keystone,main-pll-clock"; clocks = <&refclksys>; - reg = <0x02620350 4>, <0x02310110 4>; - reg-names = "control", "multiplier"; - fixed-postdiv = <2>; + reg = <0x02620350 4>, <0x02310110 4>, <0x02310108 4>; + reg-names = "control", "multiplier", "post-divider"; }; papllclk: papllclk@2620358 { diff --git a/kernel/arch/arm/boot/dts/omap2430.dtsi b/kernel/arch/arm/boot/dts/omap2430.dtsi index 11a7963be..2390f387c 100644 --- a/kernel/arch/arm/boot/dts/omap2430.dtsi +++ b/kernel/arch/arm/boot/dts/omap2430.dtsi @@ -51,7 +51,8 @@ }; scm_conf: scm_conf@270 { - compatible = "syscon"; + compatible = "syscon", + "simple-bus"; reg = <0x270 0x240>; #address-cells = <1>; #size-cells = <1>; diff --git a/kernel/arch/arm/boot/dts/omap4.dtsi b/kernel/arch/arm/boot/dts/omap4.dtsi index f884d6adb..84be9da74 100644 --- a/kernel/arch/arm/boot/dts/omap4.dtsi +++ b/kernel/arch/arm/boot/dts/omap4.dtsi @@ -191,7 +191,8 @@ }; omap4_padconf_global: omap4_padconf_global@5a0 { - compatible = "syscon"; + compatible = "syscon", + "simple-bus"; reg = <0x5a0 0x170>; #address-cells = <1>; #size-cells = <1>; diff --git a/kernel/arch/arm/boot/dts/omap5.dtsi b/kernel/arch/arm/boot/dts/omap5.dtsi index 7d24ae030..874a26f9d 100644 --- a/kernel/arch/arm/boot/dts/omap5.dtsi +++ b/kernel/arch/arm/boot/dts/omap5.dtsi @@ -180,7 +180,8 @@ }; omap5_padconf_global: omap5_padconf_global@5a0 { - compatible = "syscon"; + compatible = "syscon", + "simple-bus"; reg = <0x5a0 0xec>; #address-cells = <1>; #size-cells = <1>; diff --git a/kernel/arch/arm/boot/dts/sama5d3.dtsi b/kernel/arch/arm/boot/dts/sama5d3.dtsi index 57ab8587f..37e6182f1 100644 --- a/kernel/arch/arm/boot/dts/sama5d3.dtsi +++ b/kernel/arch/arm/boot/dts/sama5d3.dtsi @@ -1321,7 +1321,7 @@ usb0: gadget@00500000 { #address-cells = <1>; #size-cells = <0>; - compatible = "atmel,at91sam9rl-udc"; + compatible = "atmel,sama5d3-udc"; reg = <0x00500000 0x100000 0xf8030000 0x4000>; interrupts = <33 IRQ_TYPE_LEVEL_HIGH 2>; diff --git a/kernel/arch/arm/boot/dts/sama5d4.dtsi b/kernel/arch/arm/boot/dts/sama5d4.dtsi index 6b1bb58f9..a5f5f4090 100644 --- a/kernel/arch/arm/boot/dts/sama5d4.dtsi +++ b/kernel/arch/arm/boot/dts/sama5d4.dtsi @@ -123,7 +123,7 @@ usb0: gadget@00400000 { #address-cells = <1>; #size-cells = <0>; - compatible = "atmel,at91sam9rl-udc"; + compatible = "atmel,sama5d3-udc"; reg = <0x00400000 0x100000 0xfc02c000 0x4000>; interrupts = <47 IRQ_TYPE_LEVEL_HIGH 2>; @@ -1125,10 +1125,10 @@ compatible = "atmel,at91sam9g46-aes"; reg = <0xfc044000 0x100>; interrupts = <12 IRQ_TYPE_LEVEL_HIGH 0>; - dmas = <&dma0 (AT91_XDMAC_DT_MEM_IF(0) | AT91_XDMAC_DT_PER_IF(1)) - AT91_XDMAC_DT_PERID(41)>, - <&dma0 (AT91_XDMAC_DT_MEM_IF(0) | AT91_XDMAC_DT_PER_IF(1)) - AT91_XDMAC_DT_PERID(40)>; + dmas = <&dma0 (AT91_XDMAC_DT_MEM_IF(0) | AT91_XDMAC_DT_PER_IF(1) + | AT91_XDMAC_DT_PERID(41))>, + <&dma0 (AT91_XDMAC_DT_MEM_IF(0) | AT91_XDMAC_DT_PER_IF(1) + | AT91_XDMAC_DT_PERID(40))>; dma-names = "tx", "rx"; clocks = <&aes_clk>; clock-names = "aes_clk"; @@ -1139,10 +1139,10 @@ compatible = "atmel,at91sam9g46-tdes"; reg = <0xfc04c000 0x100>; interrupts = <14 IRQ_TYPE_LEVEL_HIGH 0>; - dmas = <&dma0 (AT91_XDMAC_DT_MEM_IF(0) | AT91_XDMAC_DT_PER_IF(1)) - AT91_XDMAC_DT_PERID(42)>, - <&dma0 (AT91_XDMAC_DT_MEM_IF(0) | AT91_XDMAC_DT_PER_IF(1)) - AT91_XDMAC_DT_PERID(43)>; + dmas = <&dma0 (AT91_XDMAC_DT_MEM_IF(0) | AT91_XDMAC_DT_PER_IF(1) + | AT91_XDMAC_DT_PERID(42))>, + <&dma0 (AT91_XDMAC_DT_MEM_IF(0) | AT91_XDMAC_DT_PER_IF(1) + | AT91_XDMAC_DT_PERID(43))>; dma-names = "tx", "rx"; clocks = <&tdes_clk>; clock-names = "tdes_clk"; @@ -1153,8 +1153,8 @@ compatible = "atmel,at91sam9g46-sha"; reg = <0xfc050000 0x100>; interrupts = <15 IRQ_TYPE_LEVEL_HIGH 0>; - dmas = <&dma0 (AT91_XDMAC_DT_MEM_IF(0) | AT91_XDMAC_DT_PER_IF(1)) - AT91_XDMAC_DT_PERID(44)>; + dmas = <&dma0 (AT91_XDMAC_DT_MEM_IF(0) | AT91_XDMAC_DT_PER_IF(1) + | AT91_XDMAC_DT_PERID(44))>; dma-names = "tx"; clocks = <&sha_clk>; clock-names = "sha_clk"; diff --git a/kernel/arch/arm/kernel/smp.c b/kernel/arch/arm/kernel/smp.c index cca5b8758..e561aef09 100644 --- a/kernel/arch/arm/kernel/smp.c +++ b/kernel/arch/arm/kernel/smp.c @@ -213,8 +213,6 @@ int __cpu_disable(void) flush_cache_louis(); local_flush_tlb_all(); - clear_tasks_mm_cpumask(cpu); - return 0; } @@ -230,6 +228,9 @@ void __cpu_die(unsigned int cpu) pr_err("CPU%u: cpu didn't die\n", cpu); return; } + + clear_tasks_mm_cpumask(cpu); + pr_notice("CPU%u: shutdown\n", cpu); /* @@ -576,7 +577,7 @@ void handle_IPI(int ipinr, struct pt_regs *regs) struct pt_regs *old_regs = set_irq_regs(regs); if ((unsigned)ipinr < NR_IPI) { - trace_ipi_entry(ipi_types[ipinr]); + trace_ipi_entry_rcuidle(ipi_types[ipinr]); __inc_irq_stat(cpu, ipi_irqs[ipinr]); } @@ -635,7 +636,7 @@ void handle_IPI(int ipinr, struct pt_regs *regs) } if ((unsigned)ipinr < NR_IPI) - trace_ipi_exit(ipi_types[ipinr]); + trace_ipi_exit_rcuidle(ipi_types[ipinr]); set_irq_regs(old_regs); } diff --git a/kernel/arch/arm/mach-bcm/Makefile b/kernel/arch/arm/mach-bcm/Makefile index 4c38674c7..54d274da7 100644 --- a/kernel/arch/arm/mach-bcm/Makefile +++ b/kernel/arch/arm/mach-bcm/Makefile @@ -43,5 +43,5 @@ obj-$(CONFIG_ARCH_BCM_63XX) := bcm63xx.o ifeq ($(CONFIG_ARCH_BRCMSTB),y) CFLAGS_platsmp-brcmstb.o += -march=armv7-a obj-y += brcmstb.o -obj-$(CONFIG_SMP) += headsmp-brcmstb.o platsmp-brcmstb.o +obj-$(CONFIG_SMP) += platsmp-brcmstb.o endif diff --git a/kernel/arch/arm/mach-bcm/brcmstb.h b/kernel/arch/arm/mach-bcm/brcmstb.h deleted file mode 100644 index ec0c3d112..000000000 --- a/kernel/arch/arm/mach-bcm/brcmstb.h +++ /dev/null @@ -1,19 +0,0 @@ -/* - * Copyright (C) 2013-2014 Broadcom Corporation - * - * This program 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 version 2. - * - * This program is distributed "as is" WITHOUT ANY WARRANTY of any - * kind, whether express or implied; without even the implied warranty - * of MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. - */ - -#ifndef __BRCMSTB_H__ -#define __BRCMSTB_H__ - -void brcmstb_secondary_startup(void); - -#endif /* __BRCMSTB_H__ */ diff --git a/kernel/arch/arm/mach-bcm/headsmp-brcmstb.S b/kernel/arch/arm/mach-bcm/headsmp-brcmstb.S deleted file mode 100644 index 199c1ea58..000000000 --- a/kernel/arch/arm/mach-bcm/headsmp-brcmstb.S +++ /dev/null @@ -1,33 +0,0 @@ -/* - * SMP boot code for secondary CPUs - * Based on arch/arm/mach-tegra/headsmp.S - * - * Copyright (C) 2010 NVIDIA, Inc. - * Copyright (C) 2013-2014 Broadcom Corporation - * - * This program 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 version 2. - * - * This program is distributed "as is" WITHOUT ANY WARRANTY of any - * kind, whether express or implied; without even the implied warranty - * of MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. - */ - -#include <asm/assembler.h> -#include <linux/linkage.h> -#include <linux/init.h> - - .section ".text.head", "ax" - -ENTRY(brcmstb_secondary_startup) - /* - * Ensure CPU is in a sane state by disabling all IRQs and switching - * into SVC mode. - */ - setmode PSR_I_BIT | PSR_F_BIT | SVC_MODE, r0 - - bl v7_invalidate_l1 - b secondary_startup -ENDPROC(brcmstb_secondary_startup) diff --git a/kernel/arch/arm/mach-bcm/platsmp-brcmstb.c b/kernel/arch/arm/mach-bcm/platsmp-brcmstb.c index e209e6fc7..44d6bddf7 100644 --- a/kernel/arch/arm/mach-bcm/platsmp-brcmstb.c +++ b/kernel/arch/arm/mach-bcm/platsmp-brcmstb.c @@ -30,8 +30,6 @@ #include <asm/mach-types.h> #include <asm/smp_plat.h> -#include "brcmstb.h" - enum { ZONE_MAN_CLKEN_MASK = BIT(0), ZONE_MAN_RESET_CNTL_MASK = BIT(1), @@ -153,7 +151,7 @@ static void brcmstb_cpu_boot(u32 cpu) * Set the reset vector to point to the secondary_startup * routine */ - cpu_set_boot_addr(cpu, virt_to_phys(brcmstb_secondary_startup)); + cpu_set_boot_addr(cpu, virt_to_phys(secondary_startup)); /* Unhalt the cpu */ cpu_rst_cfg_set(cpu, 0); diff --git a/kernel/arch/arm/mach-berlin/headsmp.S b/kernel/arch/arm/mach-berlin/headsmp.S index 4a4c56a58..dc82a3486 100644 --- a/kernel/arch/arm/mach-berlin/headsmp.S +++ b/kernel/arch/arm/mach-berlin/headsmp.S @@ -12,12 +12,6 @@ #include <linux/init.h> #include <asm/assembler.h> -ENTRY(berlin_secondary_startup) - ARM_BE8(setend be) - bl v7_invalidate_l1 - b secondary_startup -ENDPROC(berlin_secondary_startup) - /* * If the following instruction is set in the reset exception vector, CPUs * will fetch the value of the software reset address vector when being diff --git a/kernel/arch/arm/mach-berlin/platsmp.c b/kernel/arch/arm/mach-berlin/platsmp.c index 702e79820..34a3753e7 100644 --- a/kernel/arch/arm/mach-berlin/platsmp.c +++ b/kernel/arch/arm/mach-berlin/platsmp.c @@ -22,7 +22,6 @@ #define RESET_VECT 0x00 #define SW_RESET_ADDR 0x94 -extern void berlin_secondary_startup(void); extern u32 boot_inst; static void __iomem *cpu_ctrl; @@ -85,7 +84,7 @@ static void __init berlin_smp_prepare_cpus(unsigned int max_cpus) * Write the secondary startup address into the SW reset address * vector. This is used by boot_inst. */ - writel(virt_to_phys(berlin_secondary_startup), vectors_base + SW_RESET_ADDR); + writel(virt_to_phys(secondary_startup), vectors_base + SW_RESET_ADDR); iounmap(vectors_base); unmap_scu: diff --git a/kernel/arch/arm/mach-dove/include/mach/irqs.h b/kernel/arch/arm/mach-dove/include/mach/irqs.h index 03d401d20..3f29e6bca 100644 --- a/kernel/arch/arm/mach-dove/include/mach/irqs.h +++ b/kernel/arch/arm/mach-dove/include/mach/irqs.h @@ -14,73 +14,73 @@ /* * Dove Low Interrupt Controller */ -#define IRQ_DOVE_BRIDGE 0 -#define IRQ_DOVE_H2C 1 -#define IRQ_DOVE_C2H 2 -#define IRQ_DOVE_NAND 3 -#define IRQ_DOVE_PDMA 4 -#define IRQ_DOVE_SPI1 5 -#define IRQ_DOVE_SPI0 6 -#define IRQ_DOVE_UART_0 7 -#define IRQ_DOVE_UART_1 8 -#define IRQ_DOVE_UART_2 9 -#define IRQ_DOVE_UART_3 10 -#define IRQ_DOVE_I2C 11 -#define IRQ_DOVE_GPIO_0_7 12 -#define IRQ_DOVE_GPIO_8_15 13 -#define IRQ_DOVE_GPIO_16_23 14 -#define IRQ_DOVE_PCIE0_ERR 15 -#define IRQ_DOVE_PCIE0 16 -#define IRQ_DOVE_PCIE1_ERR 17 -#define IRQ_DOVE_PCIE1 18 -#define IRQ_DOVE_I2S0 19 -#define IRQ_DOVE_I2S0_ERR 20 -#define IRQ_DOVE_I2S1 21 -#define IRQ_DOVE_I2S1_ERR 22 -#define IRQ_DOVE_USB_ERR 23 -#define IRQ_DOVE_USB0 24 -#define IRQ_DOVE_USB1 25 -#define IRQ_DOVE_GE00_RX 26 -#define IRQ_DOVE_GE00_TX 27 -#define IRQ_DOVE_GE00_MISC 28 -#define IRQ_DOVE_GE00_SUM 29 -#define IRQ_DOVE_GE00_ERR 30 -#define IRQ_DOVE_CRYPTO 31 +#define IRQ_DOVE_BRIDGE (1 + 0) +#define IRQ_DOVE_H2C (1 + 1) +#define IRQ_DOVE_C2H (1 + 2) +#define IRQ_DOVE_NAND (1 + 3) +#define IRQ_DOVE_PDMA (1 + 4) +#define IRQ_DOVE_SPI1 (1 + 5) +#define IRQ_DOVE_SPI0 (1 + 6) +#define IRQ_DOVE_UART_0 (1 + 7) +#define IRQ_DOVE_UART_1 (1 + 8) +#define IRQ_DOVE_UART_2 (1 + 9) +#define IRQ_DOVE_UART_3 (1 + 10) +#define IRQ_DOVE_I2C (1 + 11) +#define IRQ_DOVE_GPIO_0_7 (1 + 12) +#define IRQ_DOVE_GPIO_8_15 (1 + 13) +#define IRQ_DOVE_GPIO_16_23 (1 + 14) +#define IRQ_DOVE_PCIE0_ERR (1 + 15) +#define IRQ_DOVE_PCIE0 (1 + 16) +#define IRQ_DOVE_PCIE1_ERR (1 + 17) +#define IRQ_DOVE_PCIE1 (1 + 18) +#define IRQ_DOVE_I2S0 (1 + 19) +#define IRQ_DOVE_I2S0_ERR (1 + 20) +#define IRQ_DOVE_I2S1 (1 + 21) +#define IRQ_DOVE_I2S1_ERR (1 + 22) +#define IRQ_DOVE_USB_ERR (1 + 23) +#define IRQ_DOVE_USB0 (1 + 24) +#define IRQ_DOVE_USB1 (1 + 25) +#define IRQ_DOVE_GE00_RX (1 + 26) +#define IRQ_DOVE_GE00_TX (1 + 27) +#define IRQ_DOVE_GE00_MISC (1 + 28) +#define IRQ_DOVE_GE00_SUM (1 + 29) +#define IRQ_DOVE_GE00_ERR (1 + 30) +#define IRQ_DOVE_CRYPTO (1 + 31) /* * Dove High Interrupt Controller */ -#define IRQ_DOVE_AC97 32 -#define IRQ_DOVE_PMU 33 -#define IRQ_DOVE_CAM 34 -#define IRQ_DOVE_SDIO0 35 -#define IRQ_DOVE_SDIO1 36 -#define IRQ_DOVE_SDIO0_WAKEUP 37 -#define IRQ_DOVE_SDIO1_WAKEUP 38 -#define IRQ_DOVE_XOR_00 39 -#define IRQ_DOVE_XOR_01 40 -#define IRQ_DOVE_XOR0_ERR 41 -#define IRQ_DOVE_XOR_10 42 -#define IRQ_DOVE_XOR_11 43 -#define IRQ_DOVE_XOR1_ERR 44 -#define IRQ_DOVE_LCD_DCON 45 -#define IRQ_DOVE_LCD1 46 -#define IRQ_DOVE_LCD0 47 -#define IRQ_DOVE_GPU 48 -#define IRQ_DOVE_PERFORM_MNTR 49 -#define IRQ_DOVE_VPRO_DMA1 51 -#define IRQ_DOVE_SSP_TIMER 54 -#define IRQ_DOVE_SSP 55 -#define IRQ_DOVE_MC_L2_ERR 56 -#define IRQ_DOVE_CRYPTO_ERR 59 -#define IRQ_DOVE_GPIO_24_31 60 -#define IRQ_DOVE_HIGH_GPIO 61 -#define IRQ_DOVE_SATA 62 +#define IRQ_DOVE_AC97 (1 + 32) +#define IRQ_DOVE_PMU (1 + 33) +#define IRQ_DOVE_CAM (1 + 34) +#define IRQ_DOVE_SDIO0 (1 + 35) +#define IRQ_DOVE_SDIO1 (1 + 36) +#define IRQ_DOVE_SDIO0_WAKEUP (1 + 37) +#define IRQ_DOVE_SDIO1_WAKEUP (1 + 38) +#define IRQ_DOVE_XOR_00 (1 + 39) +#define IRQ_DOVE_XOR_01 (1 + 40) +#define IRQ_DOVE_XOR0_ERR (1 + 41) +#define IRQ_DOVE_XOR_10 (1 + 42) +#define IRQ_DOVE_XOR_11 (1 + 43) +#define IRQ_DOVE_XOR1_ERR (1 + 44) +#define IRQ_DOVE_LCD_DCON (1 + 45) +#define IRQ_DOVE_LCD1 (1 + 46) +#define IRQ_DOVE_LCD0 (1 + 47) +#define IRQ_DOVE_GPU (1 + 48) +#define IRQ_DOVE_PERFORM_MNTR (1 + 49) +#define IRQ_DOVE_VPRO_DMA1 (1 + 51) +#define IRQ_DOVE_SSP_TIMER (1 + 54) +#define IRQ_DOVE_SSP (1 + 55) +#define IRQ_DOVE_MC_L2_ERR (1 + 56) +#define IRQ_DOVE_CRYPTO_ERR (1 + 59) +#define IRQ_DOVE_GPIO_24_31 (1 + 60) +#define IRQ_DOVE_HIGH_GPIO (1 + 61) +#define IRQ_DOVE_SATA (1 + 62) /* * DOVE General Purpose Pins */ -#define IRQ_DOVE_GPIO_START 64 +#define IRQ_DOVE_GPIO_START 65 #define NR_GPIO_IRQS 64 /* diff --git a/kernel/arch/arm/mach-dove/irq.c b/kernel/arch/arm/mach-dove/irq.c index 4a5a7aedc..df0223f76 100644 --- a/kernel/arch/arm/mach-dove/irq.c +++ b/kernel/arch/arm/mach-dove/irq.c @@ -126,14 +126,14 @@ __exception_irq_entry dove_legacy_handle_irq(struct pt_regs *regs) stat = readl_relaxed(dove_irq_base + IRQ_CAUSE_LOW_OFF); stat &= readl_relaxed(dove_irq_base + IRQ_MASK_LOW_OFF); if (stat) { - unsigned int hwirq = __fls(stat); + unsigned int hwirq = 1 + __fls(stat); handle_IRQ(hwirq, regs); return; } stat = readl_relaxed(dove_irq_base + IRQ_CAUSE_HIGH_OFF); stat &= readl_relaxed(dove_irq_base + IRQ_MASK_HIGH_OFF); if (stat) { - unsigned int hwirq = 32 + __fls(stat); + unsigned int hwirq = 33 + __fls(stat); handle_IRQ(hwirq, regs); return; } @@ -144,8 +144,8 @@ void __init dove_init_irq(void) { int i; - orion_irq_init(0, IRQ_VIRT_BASE + IRQ_MASK_LOW_OFF); - orion_irq_init(32, IRQ_VIRT_BASE + IRQ_MASK_HIGH_OFF); + orion_irq_init(1, IRQ_VIRT_BASE + IRQ_MASK_LOW_OFF); + orion_irq_init(33, IRQ_VIRT_BASE + IRQ_MASK_HIGH_OFF); #ifdef CONFIG_MULTI_IRQ_HANDLER set_handle_irq(dove_legacy_handle_irq); diff --git a/kernel/arch/arm/mach-hisi/Makefile b/kernel/arch/arm/mach-hisi/Makefile index 6b7b3033d..659db1933 100644 --- a/kernel/arch/arm/mach-hisi/Makefile +++ b/kernel/arch/arm/mach-hisi/Makefile @@ -6,4 +6,4 @@ CFLAGS_platmcpm.o := -march=armv7-a obj-y += hisilicon.o obj-$(CONFIG_MCPM) += platmcpm.o -obj-$(CONFIG_SMP) += platsmp.o hotplug.o headsmp.o +obj-$(CONFIG_SMP) += platsmp.o hotplug.o diff --git a/kernel/arch/arm/mach-hisi/core.h b/kernel/arch/arm/mach-hisi/core.h index 92a682d8e..c7648ef18 100644 --- a/kernel/arch/arm/mach-hisi/core.h +++ b/kernel/arch/arm/mach-hisi/core.h @@ -12,7 +12,6 @@ extern void hi3xxx_cpu_die(unsigned int cpu); extern int hi3xxx_cpu_kill(unsigned int cpu); extern void hi3xxx_set_cpu(int cpu, bool enable); -extern void hisi_secondary_startup(void); extern struct smp_operations hix5hd2_smp_ops; extern void hix5hd2_set_cpu(int cpu, bool enable); extern void hix5hd2_cpu_die(unsigned int cpu); diff --git a/kernel/arch/arm/mach-hisi/headsmp.S b/kernel/arch/arm/mach-hisi/headsmp.S deleted file mode 100644 index 81e35b159..000000000 --- a/kernel/arch/arm/mach-hisi/headsmp.S +++ /dev/null @@ -1,16 +0,0 @@ -/* - * Copyright (c) 2014 Hisilicon Limited. - * Copyright (c) 2014 Linaro Ltd. - * - * 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/linkage.h> -#include <linux/init.h> - - __CPUINIT - -ENTRY(hisi_secondary_startup) - bl v7_invalidate_l1 - b secondary_startup diff --git a/kernel/arch/arm/mach-hisi/platsmp.c b/kernel/arch/arm/mach-hisi/platsmp.c index 8880c8e8b..51744127d 100644 --- a/kernel/arch/arm/mach-hisi/platsmp.c +++ b/kernel/arch/arm/mach-hisi/platsmp.c @@ -118,7 +118,7 @@ static int hix5hd2_boot_secondary(unsigned int cpu, struct task_struct *idle) { phys_addr_t jumpaddr; - jumpaddr = virt_to_phys(hisi_secondary_startup); + jumpaddr = virt_to_phys(secondary_startup); hix5hd2_set_scu_boot_addr(HIX5HD2_BOOT_ADDRESS, jumpaddr); hix5hd2_set_cpu(cpu, true); arch_send_wakeup_ipi_mask(cpumask_of(cpu)); @@ -156,7 +156,7 @@ static int hip01_boot_secondary(unsigned int cpu, struct task_struct *idle) struct device_node *node; - jumpaddr = virt_to_phys(hisi_secondary_startup); + jumpaddr = virt_to_phys(secondary_startup); hip01_set_boot_addr(HIP01_BOOT_ADDRESS, jumpaddr); node = of_find_compatible_node(NULL, NULL, "hisilicon,hip01-sysctrl"); diff --git a/kernel/arch/arm/mach-imx/gpc.c b/kernel/arch/arm/mach-imx/gpc.c index 6d0893a38..78b6fd0b8 100644 --- a/kernel/arch/arm/mach-imx/gpc.c +++ b/kernel/arch/arm/mach-imx/gpc.c @@ -291,8 +291,6 @@ void __init imx_gpc_check_dt(void) } } -#ifdef CONFIG_PM_GENERIC_DOMAINS - static void _imx6q_pm_pu_power_off(struct generic_pm_domain *genpd) { int iso, iso2sw; @@ -399,7 +397,6 @@ static struct genpd_onecell_data imx_gpc_onecell_data = { static int imx_gpc_genpd_init(struct device *dev, struct regulator *pu_reg) { struct clk *clk; - bool is_off; int i; imx6q_pu_domain.reg = pu_reg; @@ -416,18 +413,13 @@ static int imx_gpc_genpd_init(struct device *dev, struct regulator *pu_reg) } imx6q_pu_domain.num_clks = i; - is_off = IS_ENABLED(CONFIG_PM); - if (is_off) { - _imx6q_pm_pu_power_off(&imx6q_pu_domain.base); - } else { - /* - * Enable power if compiled without CONFIG_PM in case the - * bootloader disabled it. - */ - imx6q_pm_pu_power_on(&imx6q_pu_domain.base); - } + /* Enable power always in case bootloader disabled it. */ + imx6q_pm_pu_power_on(&imx6q_pu_domain.base); + + if (!IS_ENABLED(CONFIG_PM_GENERIC_DOMAINS)) + return 0; - pm_genpd_init(&imx6q_pu_domain.base, NULL, is_off); + pm_genpd_init(&imx6q_pu_domain.base, NULL, false); return of_genpd_add_provider_onecell(dev->of_node, &imx_gpc_onecell_data); @@ -437,13 +429,6 @@ clk_err: return -EINVAL; } -#else -static inline int imx_gpc_genpd_init(struct device *dev, struct regulator *reg) -{ - return 0; -} -#endif /* CONFIG_PM_GENERIC_DOMAINS */ - static int imx_gpc_probe(struct platform_device *pdev) { struct regulator *pu_reg; diff --git a/kernel/arch/arm/mach-imx/headsmp.S b/kernel/arch/arm/mach-imx/headsmp.S index de5047c8a..b5e976816 100644 --- a/kernel/arch/arm/mach-imx/headsmp.S +++ b/kernel/arch/arm/mach-imx/headsmp.S @@ -25,7 +25,6 @@ diag_reg_offset: .endm ENTRY(v7_secondary_startup) - bl v7_invalidate_l1 set_diag_reg b secondary_startup ENDPROC(v7_secondary_startup) diff --git a/kernel/arch/arm/mach-mvebu/headsmp-a9.S b/kernel/arch/arm/mach-mvebu/headsmp-a9.S index 08d5ed46b..48e4c4b3c 100644 --- a/kernel/arch/arm/mach-mvebu/headsmp-a9.S +++ b/kernel/arch/arm/mach-mvebu/headsmp-a9.S @@ -21,7 +21,6 @@ ENTRY(mvebu_cortex_a9_secondary_startup) ARM_BE8(setend be) - bl v7_invalidate_l1 bl armada_38x_scu_power_up b secondary_startup ENDPROC(mvebu_cortex_a9_secondary_startup) diff --git a/kernel/arch/arm/mach-omap2/omap-wakeupgen.c b/kernel/arch/arm/mach-omap2/omap-wakeupgen.c index 3b56722df..6833df45d 100644 --- a/kernel/arch/arm/mach-omap2/omap-wakeupgen.c +++ b/kernel/arch/arm/mach-omap2/omap-wakeupgen.c @@ -392,6 +392,7 @@ static struct irq_chip wakeupgen_chip = { .irq_mask = wakeupgen_mask, .irq_unmask = wakeupgen_unmask, .irq_retrigger = irq_chip_retrigger_hierarchy, + .irq_set_type = irq_chip_set_type_parent, .flags = IRQCHIP_SKIP_SET_WAKE | IRQCHIP_MASK_ON_SUSPEND, #ifdef CONFIG_SMP .irq_set_affinity = irq_chip_set_affinity_parent, diff --git a/kernel/arch/arm/mach-omap2/omap_hwmod.c b/kernel/arch/arm/mach-omap2/omap_hwmod.c index 752969ff9..5286e7773 100644 --- a/kernel/arch/arm/mach-omap2/omap_hwmod.c +++ b/kernel/arch/arm/mach-omap2/omap_hwmod.c @@ -2373,6 +2373,9 @@ static int of_dev_hwmod_lookup(struct device_node *np, * registers. This address is needed early so the OCP registers that * are part of the device's address space can be ioremapped properly. * + * If SYSC access is not needed, the registers will not be remapped + * and non-availability of MPU access is not treated as an error. + * * Returns 0 on success, -EINVAL if an invalid hwmod is passed, and * -ENXIO on absent or invalid register target address space. */ @@ -2387,6 +2390,11 @@ static int __init _init_mpu_rt_base(struct omap_hwmod *oh, void *data, _save_mpu_port_index(oh); + /* if we don't need sysc access we don't need to ioremap */ + if (!oh->class->sysc) + return 0; + + /* we can't continue without MPU PORT if we need sysc access */ if (oh->_int_flags & _HWMOD_NO_MPU_PORT) return -ENXIO; @@ -2396,8 +2404,10 @@ static int __init _init_mpu_rt_base(struct omap_hwmod *oh, void *data, oh->name); /* Extract the IO space from device tree blob */ - if (!np) + if (!np) { + pr_err("omap_hwmod: %s: no dt node\n", oh->name); return -ENXIO; + } va_start = of_iomap(np, index + oh->mpu_rt_idx); } else { @@ -2456,13 +2466,11 @@ static int __init _init(struct omap_hwmod *oh, void *data) oh->name, np->name); } - if (oh->class->sysc) { - r = _init_mpu_rt_base(oh, NULL, index, np); - if (r < 0) { - WARN(1, "omap_hwmod: %s: doesn't have mpu register target base\n", - oh->name); - return 0; - } + r = _init_mpu_rt_base(oh, NULL, index, np); + if (r < 0) { + WARN(1, "omap_hwmod: %s: doesn't have mpu register target base\n", + oh->name); + return 0; } r = _init_clocks(oh, NULL); diff --git a/kernel/arch/arm/mach-prima2/headsmp.S b/kernel/arch/arm/mach-prima2/headsmp.S index d86fe33c5..209d9fc5c 100644 --- a/kernel/arch/arm/mach-prima2/headsmp.S +++ b/kernel/arch/arm/mach-prima2/headsmp.S @@ -15,7 +15,6 @@ * ready for them to initialise. */ ENTRY(sirfsoc_secondary_startup) - bl v7_invalidate_l1 mrc p15, 0, r0, c0, c0, 5 and r0, r0, #15 adr r4, 1f diff --git a/kernel/arch/arm/mach-pxa/capc7117.c b/kernel/arch/arm/mach-pxa/capc7117.c index c09273074..bf366b39f 100644 --- a/kernel/arch/arm/mach-pxa/capc7117.c +++ b/kernel/arch/arm/mach-pxa/capc7117.c @@ -24,6 +24,7 @@ #include <linux/ata_platform.h> #include <linux/serial_8250.h> #include <linux/gpio.h> +#include <linux/regulator/machine.h> #include <asm/mach-types.h> #include <asm/mach/arch.h> @@ -144,6 +145,8 @@ static void __init capc7117_init(void) capc7117_uarts_init(); capc7117_ide_init(); + + regulator_has_full_constraints(); } MACHINE_START(CAPC7117, diff --git a/kernel/arch/arm/mach-pxa/cm-x2xx.c b/kernel/arch/arm/mach-pxa/cm-x2xx.c index bb99f59a3..a17a91eb8 100644 --- a/kernel/arch/arm/mach-pxa/cm-x2xx.c +++ b/kernel/arch/arm/mach-pxa/cm-x2xx.c @@ -13,6 +13,7 @@ #include <linux/syscore_ops.h> #include <linux/irq.h> #include <linux/gpio.h> +#include <linux/regulator/machine.h> #include <linux/dm9000.h> #include <linux/leds.h> @@ -466,6 +467,8 @@ static void __init cmx2xx_init(void) cmx2xx_init_ac97(); cmx2xx_init_touchscreen(); cmx2xx_init_leds(); + + regulator_has_full_constraints(); } static void __init cmx2xx_init_irq(void) diff --git a/kernel/arch/arm/mach-pxa/cm-x300.c b/kernel/arch/arm/mach-pxa/cm-x300.c index 4d3588d26..5851f4c25 100644 --- a/kernel/arch/arm/mach-pxa/cm-x300.c +++ b/kernel/arch/arm/mach-pxa/cm-x300.c @@ -835,6 +835,8 @@ static void __init cm_x300_init(void) cm_x300_init_ac97(); cm_x300_init_wi2wi(); cm_x300_init_bl(); + + regulator_has_full_constraints(); } static void __init cm_x300_fixup(struct tag *tags, char **cmdline) diff --git a/kernel/arch/arm/mach-pxa/colibri-pxa270.c b/kernel/arch/arm/mach-pxa/colibri-pxa270.c index 5f9d9303b..350382633 100644 --- a/kernel/arch/arm/mach-pxa/colibri-pxa270.c +++ b/kernel/arch/arm/mach-pxa/colibri-pxa270.c @@ -18,6 +18,7 @@ #include <linux/mtd/partitions.h> #include <linux/mtd/physmap.h> #include <linux/platform_device.h> +#include <linux/regulator/machine.h> #include <linux/ucb1400.h> #include <asm/mach/arch.h> @@ -294,6 +295,8 @@ static void __init colibri_pxa270_init(void) printk(KERN_ERR "Illegal colibri_pxa270_baseboard type %d\n", colibri_pxa270_baseboard); } + + regulator_has_full_constraints(); } /* The "Income s.r.o. SH-Dmaster PXA270 SBC" board can be booted either diff --git a/kernel/arch/arm/mach-pxa/em-x270.c b/kernel/arch/arm/mach-pxa/em-x270.c index 51531ecff..9d7072b04 100644 --- a/kernel/arch/arm/mach-pxa/em-x270.c +++ b/kernel/arch/arm/mach-pxa/em-x270.c @@ -1306,6 +1306,8 @@ static void __init em_x270_init(void) em_x270_init_i2c(); em_x270_init_camera(); em_x270_userspace_consumers_init(); + + regulator_has_full_constraints(); } MACHINE_START(EM_X270, "Compulab EM-X270") diff --git a/kernel/arch/arm/mach-pxa/icontrol.c b/kernel/arch/arm/mach-pxa/icontrol.c index c98511c5a..9b0eb0252 100644 --- a/kernel/arch/arm/mach-pxa/icontrol.c +++ b/kernel/arch/arm/mach-pxa/icontrol.c @@ -26,6 +26,7 @@ #include <linux/spi/spi.h> #include <linux/spi/pxa2xx_spi.h> #include <linux/can/platform/mcp251x.h> +#include <linux/regulator/machine.h> #include "generic.h" @@ -185,6 +186,8 @@ static void __init icontrol_init(void) mxm_8x10_mmc_init(); icontrol_can_init(); + + regulator_has_full_constraints(); } MACHINE_START(ICONTROL, "iControl/SafeTcam boards using Embedian MXM-8x10 CoM") diff --git a/kernel/arch/arm/mach-pxa/trizeps4.c b/kernel/arch/arm/mach-pxa/trizeps4.c index 872dcb20e..066e3a250 100644 --- a/kernel/arch/arm/mach-pxa/trizeps4.c +++ b/kernel/arch/arm/mach-pxa/trizeps4.c @@ -26,6 +26,7 @@ #include <linux/dm9000.h> #include <linux/mtd/physmap.h> #include <linux/mtd/partitions.h> +#include <linux/regulator/machine.h> #include <linux/i2c/pxa-i2c.h> #include <asm/types.h> @@ -534,6 +535,8 @@ static void __init trizeps4_init(void) BCR_writew(trizeps_conxs_bcr); board_backlight_power(1); + + regulator_has_full_constraints(); } static void __init trizeps4_map_io(void) diff --git a/kernel/arch/arm/mach-pxa/vpac270.c b/kernel/arch/arm/mach-pxa/vpac270.c index aa89488f9..54122a983 100644 --- a/kernel/arch/arm/mach-pxa/vpac270.c +++ b/kernel/arch/arm/mach-pxa/vpac270.c @@ -24,6 +24,7 @@ #include <linux/dm9000.h> #include <linux/ucb1400.h> #include <linux/ata_platform.h> +#include <linux/regulator/machine.h> #include <linux/regulator/max1586.h> #include <linux/i2c/pxa-i2c.h> @@ -711,6 +712,8 @@ static void __init vpac270_init(void) vpac270_ts_init(); vpac270_rtc_init(); vpac270_ide_init(); + + regulator_has_full_constraints(); } MACHINE_START(VPAC270, "Voipac PXA270") diff --git a/kernel/arch/arm/mach-pxa/zeus.c b/kernel/arch/arm/mach-pxa/zeus.c index ac2ae5c71..6158566fa 100644 --- a/kernel/arch/arm/mach-pxa/zeus.c +++ b/kernel/arch/arm/mach-pxa/zeus.c @@ -868,6 +868,8 @@ static void __init zeus_init(void) i2c_register_board_info(0, ARRAY_AND_SIZE(zeus_i2c_devices)); pxa2xx_set_spi_info(3, &pxa2xx_spi_ssp3_master_info); spi_register_board_info(zeus_spi_board_info, ARRAY_SIZE(zeus_spi_board_info)); + + regulator_has_full_constraints(); } static struct map_desc zeus_io_desc[] __initdata = { diff --git a/kernel/arch/arm/mach-rockchip/core.h b/kernel/arch/arm/mach-rockchip/core.h index 39bca96b5..492c04881 100644 --- a/kernel/arch/arm/mach-rockchip/core.h +++ b/kernel/arch/arm/mach-rockchip/core.h @@ -17,4 +17,3 @@ extern char rockchip_secondary_trampoline; extern char rockchip_secondary_trampoline_end; extern unsigned long rockchip_boot_fn; -extern void rockchip_secondary_startup(void); diff --git a/kernel/arch/arm/mach-rockchip/headsmp.S b/kernel/arch/arm/mach-rockchip/headsmp.S index 46c22dedf..d69708b07 100644 --- a/kernel/arch/arm/mach-rockchip/headsmp.S +++ b/kernel/arch/arm/mach-rockchip/headsmp.S @@ -15,14 +15,6 @@ #include <linux/linkage.h> #include <linux/init.h> -ENTRY(rockchip_secondary_startup) - mrc p15, 0, r0, c0, c0, 0 @ read main ID register - ldr r1, =0x00000c09 @ Cortex-A9 primary part number - teq r0, r1 - beq v7_invalidate_l1 - b secondary_startup -ENDPROC(rockchip_secondary_startup) - ENTRY(rockchip_secondary_trampoline) ldr pc, 1f ENDPROC(rockchip_secondary_trampoline) diff --git a/kernel/arch/arm/mach-rockchip/platsmp.c b/kernel/arch/arm/mach-rockchip/platsmp.c index 5b4ca3c3c..2e6ab67e2 100644 --- a/kernel/arch/arm/mach-rockchip/platsmp.c +++ b/kernel/arch/arm/mach-rockchip/platsmp.c @@ -149,8 +149,7 @@ static int __cpuinit rockchip_boot_secondary(unsigned int cpu, * sram_base_addr + 8: start address for pc * */ udelay(10); - writel(virt_to_phys(rockchip_secondary_startup), - sram_base_addr + 8); + writel(virt_to_phys(secondary_startup), sram_base_addr + 8); writel(0xDEADBEAF, sram_base_addr + 4); dsb_sev(); } @@ -189,7 +188,7 @@ static int __init rockchip_smp_prepare_sram(struct device_node *node) } /* set the boot function for the sram code */ - rockchip_boot_fn = virt_to_phys(rockchip_secondary_startup); + rockchip_boot_fn = virt_to_phys(secondary_startup); /* copy the trampoline to sram, that runs during startup of the core */ memcpy(sram_base_addr, &rockchip_secondary_trampoline, trampoline_sz); diff --git a/kernel/arch/arm/mach-shmobile/common.h b/kernel/arch/arm/mach-shmobile/common.h index afc60bad6..476092b86 100644 --- a/kernel/arch/arm/mach-shmobile/common.h +++ b/kernel/arch/arm/mach-shmobile/common.h @@ -14,7 +14,6 @@ extern void shmobile_smp_sleep(void); extern void shmobile_smp_hook(unsigned int cpu, unsigned long fn, unsigned long arg); extern int shmobile_smp_cpu_disable(unsigned int cpu); -extern void shmobile_invalidate_start(void); extern void shmobile_boot_scu(void); extern void shmobile_smp_scu_prepare_cpus(unsigned int max_cpus); extern void shmobile_smp_scu_cpu_die(unsigned int cpu); diff --git a/kernel/arch/arm/mach-shmobile/headsmp-scu.S b/kernel/arch/arm/mach-shmobile/headsmp-scu.S index 69df8bfac..fa5248c52 100644 --- a/kernel/arch/arm/mach-shmobile/headsmp-scu.S +++ b/kernel/arch/arm/mach-shmobile/headsmp-scu.S @@ -22,7 +22,7 @@ * Boot code for secondary CPUs. * * First we turn on L1 cache coherency for our CPU. Then we jump to - * shmobile_invalidate_start that invalidates the cache and hands over control + * secondary_startup that invalidates the cache and hands over control * to the common ARM startup code. */ ENTRY(shmobile_boot_scu) @@ -36,7 +36,7 @@ ENTRY(shmobile_boot_scu) bic r2, r2, r3 @ Clear bits of our CPU (Run Mode) str r2, [r0, #8] @ write back - b shmobile_invalidate_start + b secondary_startup ENDPROC(shmobile_boot_scu) .text diff --git a/kernel/arch/arm/mach-shmobile/headsmp.S b/kernel/arch/arm/mach-shmobile/headsmp.S index 50c491567..330c1fc63 100644 --- a/kernel/arch/arm/mach-shmobile/headsmp.S +++ b/kernel/arch/arm/mach-shmobile/headsmp.S @@ -16,13 +16,6 @@ #include <asm/assembler.h> #include <asm/memory.h> -#ifdef CONFIG_SMP -ENTRY(shmobile_invalidate_start) - bl v7_invalidate_l1 - b secondary_startup -ENDPROC(shmobile_invalidate_start) -#endif - /* * Reset vector for secondary CPUs. * This will be mapped at address 0 by SBAR register. diff --git a/kernel/arch/arm/mach-shmobile/platsmp-apmu.c b/kernel/arch/arm/mach-shmobile/platsmp-apmu.c index f483b560b..b0790fc32 100644 --- a/kernel/arch/arm/mach-shmobile/platsmp-apmu.c +++ b/kernel/arch/arm/mach-shmobile/platsmp-apmu.c @@ -133,7 +133,7 @@ void __init shmobile_smp_apmu_prepare_cpus(unsigned int max_cpus, int shmobile_smp_apmu_boot_secondary(unsigned int cpu, struct task_struct *idle) { /* For this particular CPU register boot vector */ - shmobile_smp_hook(cpu, virt_to_phys(shmobile_invalidate_start), 0); + shmobile_smp_hook(cpu, virt_to_phys(secondary_startup), 0); return apmu_wrap(cpu, apmu_power_on); } diff --git a/kernel/arch/arm/mach-socfpga/core.h b/kernel/arch/arm/mach-socfpga/core.h index a0f3b1cd4..767c09e95 100644 --- a/kernel/arch/arm/mach-socfpga/core.h +++ b/kernel/arch/arm/mach-socfpga/core.h @@ -31,7 +31,6 @@ #define RSTMGR_MPUMODRST_CPU1 0x2 /* CPU1 Reset */ -extern void socfpga_secondary_startup(void); extern void __iomem *socfpga_scu_base_addr; extern void socfpga_init_clocks(void); diff --git a/kernel/arch/arm/mach-socfpga/headsmp.S b/kernel/arch/arm/mach-socfpga/headsmp.S index f65ea0af4..5bb016427 100644 --- a/kernel/arch/arm/mach-socfpga/headsmp.S +++ b/kernel/arch/arm/mach-socfpga/headsmp.S @@ -30,8 +30,3 @@ ENTRY(secondary_trampoline) 1: .long . .long socfpga_cpu1start_addr ENTRY(secondary_trampoline_end) - -ENTRY(socfpga_secondary_startup) - bl v7_invalidate_l1 - b secondary_startup -ENDPROC(socfpga_secondary_startup) diff --git a/kernel/arch/arm/mach-socfpga/platsmp.c b/kernel/arch/arm/mach-socfpga/platsmp.c index c64d89b7c..79c5336c5 100644 --- a/kernel/arch/arm/mach-socfpga/platsmp.c +++ b/kernel/arch/arm/mach-socfpga/platsmp.c @@ -40,7 +40,7 @@ static int socfpga_boot_secondary(unsigned int cpu, struct task_struct *idle) memcpy(phys_to_virt(0), &secondary_trampoline, trampoline_size); - writel(virt_to_phys(socfpga_secondary_startup), + writel(virt_to_phys(secondary_startup), sys_manager_base_addr + (socfpga_cpu1start_addr & 0x000000ff)); flush_cache_all(); diff --git a/kernel/arch/arm/mach-tegra/Makefile b/kernel/arch/arm/mach-tegra/Makefile index e48a74458..fffad2426 100644 --- a/kernel/arch/arm/mach-tegra/Makefile +++ b/kernel/arch/arm/mach-tegra/Makefile @@ -19,7 +19,7 @@ obj-$(CONFIG_ARCH_TEGRA_3x_SOC) += pm-tegra30.o ifeq ($(CONFIG_CPU_IDLE),y) obj-$(CONFIG_ARCH_TEGRA_3x_SOC) += cpuidle-tegra30.o endif -obj-$(CONFIG_SMP) += platsmp.o headsmp.o +obj-$(CONFIG_SMP) += platsmp.o obj-$(CONFIG_HOTPLUG_CPU) += hotplug.o obj-$(CONFIG_ARCH_TEGRA_114_SOC) += sleep-tegra30.o diff --git a/kernel/arch/arm/mach-tegra/headsmp.S b/kernel/arch/arm/mach-tegra/headsmp.S deleted file mode 100644 index 2072e7322..000000000 --- a/kernel/arch/arm/mach-tegra/headsmp.S +++ /dev/null @@ -1,12 +0,0 @@ -#include <linux/linkage.h> -#include <linux/init.h> - -#include "sleep.h" - - .section ".text.head", "ax" - -ENTRY(tegra_secondary_startup) - check_cpu_part_num 0xc09, r8, r9 - bleq v7_invalidate_l1 - b secondary_startup -ENDPROC(tegra_secondary_startup) diff --git a/kernel/arch/arm/mach-tegra/reset.c b/kernel/arch/arm/mach-tegra/reset.c index 894c5c472..6fd9db548 100644 --- a/kernel/arch/arm/mach-tegra/reset.c +++ b/kernel/arch/arm/mach-tegra/reset.c @@ -94,7 +94,7 @@ void __init tegra_cpu_reset_handler_init(void) __tegra_cpu_reset_handler_data[TEGRA_RESET_MASK_PRESENT] = *((u32 *)cpu_possible_mask); __tegra_cpu_reset_handler_data[TEGRA_RESET_STARTUP_SECONDARY] = - virt_to_phys((void *)tegra_secondary_startup); + virt_to_phys((void *)secondary_startup); #endif #ifdef CONFIG_PM_SLEEP diff --git a/kernel/arch/arm/mach-tegra/reset.h b/kernel/arch/arm/mach-tegra/reset.h index 29c3dec01..9c479c792 100644 --- a/kernel/arch/arm/mach-tegra/reset.h +++ b/kernel/arch/arm/mach-tegra/reset.h @@ -37,7 +37,6 @@ void __tegra_cpu_reset_handler_start(void); void __tegra_cpu_reset_handler(void); void __tegra20_cpu1_resettable_status_offset(void); void __tegra_cpu_reset_handler_end(void); -void tegra_secondary_startup(void); #ifdef CONFIG_PM_SLEEP #define tegra_cpu_lp1_mask \ diff --git a/kernel/arch/arm/mach-zynq/common.h b/kernel/arch/arm/mach-zynq/common.h index 382c60e9a..7038cae95 100644 --- a/kernel/arch/arm/mach-zynq/common.h +++ b/kernel/arch/arm/mach-zynq/common.h @@ -17,8 +17,6 @@ #ifndef __MACH_ZYNQ_COMMON_H__ #define __MACH_ZYNQ_COMMON_H__ -void zynq_secondary_startup(void); - extern int zynq_slcr_init(void); extern int zynq_early_slcr_init(void); extern void zynq_slcr_system_reset(void); diff --git a/kernel/arch/arm/mach-zynq/headsmp.S b/kernel/arch/arm/mach-zynq/headsmp.S index dd8c07194..045c72720 100644 --- a/kernel/arch/arm/mach-zynq/headsmp.S +++ b/kernel/arch/arm/mach-zynq/headsmp.S @@ -22,8 +22,3 @@ zynq_secondary_trampoline_jump: .globl zynq_secondary_trampoline_end zynq_secondary_trampoline_end: ENDPROC(zynq_secondary_trampoline) - -ENTRY(zynq_secondary_startup) - bl v7_invalidate_l1 - b secondary_startup -ENDPROC(zynq_secondary_startup) diff --git a/kernel/arch/arm/mach-zynq/platsmp.c b/kernel/arch/arm/mach-zynq/platsmp.c index 52d768ff7..f66816c49 100644 --- a/kernel/arch/arm/mach-zynq/platsmp.c +++ b/kernel/arch/arm/mach-zynq/platsmp.c @@ -87,10 +87,9 @@ int zynq_cpun_start(u32 address, int cpu) } EXPORT_SYMBOL(zynq_cpun_start); -static int zynq_boot_secondary(unsigned int cpu, - struct task_struct *idle) +static int zynq_boot_secondary(unsigned int cpu, struct task_struct *idle) { - return zynq_cpun_start(virt_to_phys(zynq_secondary_startup), cpu); + return zynq_cpun_start(virt_to_phys(secondary_startup), cpu); } /* diff --git a/kernel/arch/arm/mm/dma-mapping.c b/kernel/arch/arm/mm/dma-mapping.c index 7e7583ddd..6e4b9ff22 100644 --- a/kernel/arch/arm/mm/dma-mapping.c +++ b/kernel/arch/arm/mm/dma-mapping.c @@ -1953,7 +1953,7 @@ static int extend_iommu_mapping(struct dma_iommu_mapping *mapping) { int next_bitmap; - if (mapping->nr_bitmaps > mapping->extensions) + if (mapping->nr_bitmaps >= mapping->extensions) return -EINVAL; next_bitmap = mapping->nr_bitmaps; diff --git a/kernel/arch/arm/mm/proc-v7.S b/kernel/arch/arm/mm/proc-v7.S index 3d1054f11..7911f14c2 100644 --- a/kernel/arch/arm/mm/proc-v7.S +++ b/kernel/arch/arm/mm/proc-v7.S @@ -268,7 +268,10 @@ __v7_ca15mp_setup: __v7_b15mp_setup: __v7_ca17mp_setup: mov r10, #0 -1: +1: adr r12, __v7_setup_stack @ the local stack + stmia r12, {r0-r5, lr} @ v7_invalidate_l1 touches r0-r6 + bl v7_invalidate_l1 + ldmia r12, {r0-r5, lr} #ifdef CONFIG_SMP ALT_SMP(mrc p15, 0, r0, c1, c0, 1) ALT_UP(mov r0, #(1 << 6)) @ fake it for UP @@ -277,7 +280,7 @@ __v7_ca17mp_setup: orreq r0, r0, r10 @ Enable CPU-specific SMP bits mcreq p15, 0, r0, c1, c0, 1 #endif - b __v7_setup + b __v7_setup_cont __v7_pj4b_setup: #ifdef CONFIG_CPU_PJ4B @@ -335,10 +338,11 @@ __v7_pj4b_setup: __v7_setup: adr r12, __v7_setup_stack @ the local stack - stmia r12, {r0-r5, r7, r9, r11, lr} - bl v7_flush_dcache_louis - ldmia r12, {r0-r5, r7, r9, r11, lr} + stmia r12, {r0-r5, lr} @ v7_invalidate_l1 touches r0-r6 + bl v7_invalidate_l1 + ldmia r12, {r0-r5, lr} +__v7_setup_cont: mrc p15, 0, r0, c0, c0, 0 @ read main ID register and r10, r0, #0xff000000 @ ARM? teq r10, #0x41000000 @@ -460,7 +464,7 @@ ENDPROC(__v7_setup) .align 2 __v7_setup_stack: - .space 4 * 11 @ 11 registers + .space 4 * 7 @ 12 registers __INITDATA diff --git a/kernel/arch/arm/vdso/Makefile b/kernel/arch/arm/vdso/Makefile index 8aa791051..1160434ee 100644 --- a/kernel/arch/arm/vdso/Makefile +++ b/kernel/arch/arm/vdso/Makefile @@ -6,9 +6,15 @@ obj-vdso := vgettimeofday.o datapage.o targets := $(obj-vdso) vdso.so vdso.so.dbg vdso.so.raw vdso.lds obj-vdso := $(addprefix $(obj)/, $(obj-vdso)) -ccflags-y := -shared -fPIC -fno-common -fno-builtin -fno-stack-protector -ccflags-y += -nostdlib -Wl,-soname=linux-vdso.so.1 -DDISABLE_BRANCH_PROFILING -ccflags-y += -Wl,--no-undefined $(call cc-ldoption, -Wl$(comma)--hash-style=sysv) +ccflags-y := -fPIC -fno-common -fno-builtin -fno-stack-protector +ccflags-y += -DDISABLE_BRANCH_PROFILING + +VDSO_LDFLAGS := -Wl,-Bsymbolic -Wl,--no-undefined -Wl,-soname=linux-vdso.so.1 +VDSO_LDFLAGS += -Wl,-z,max-page-size=4096 -Wl,-z,common-page-size=4096 +VDSO_LDFLAGS += -nostdlib -shared +VDSO_LDFLAGS += $(call cc-ldoption, -Wl$(comma)--hash-style=sysv) +VDSO_LDFLAGS += $(call cc-ldoption, -Wl$(comma)--build-id) +VDSO_LDFLAGS += $(call cc-ldoption, -fuse-ld=bfd) obj-$(CONFIG_VDSO) += vdso.o extra-$(CONFIG_VDSO) += vdso.lds @@ -40,10 +46,8 @@ $(obj)/%.so: $(obj)/%.so.dbg FORCE # Actual build commands quiet_cmd_vdsold = VDSO $@ - cmd_vdsold = $(CC) $(c_flags) -Wl,-T $(filter %.lds,$^) $(filter %.o,$^) \ - $(call cc-ldoption, -Wl$(comma)--build-id) \ - -Wl,-Bsymbolic -Wl,-z,max-page-size=4096 \ - -Wl,-z,common-page-size=4096 -o $@ + cmd_vdsold = $(CC) $(c_flags) $(VDSO_LDFLAGS) \ + -Wl,-T $(filter %.lds,$^) $(filter %.o,$^) -o $@ quiet_cmd_vdsomunge = MUNGE $@ cmd_vdsomunge = $(objtree)/$(obj)/vdsomunge $< $@ diff --git a/kernel/arch/arm/vdso/vdsomunge.c b/kernel/arch/arm/vdso/vdsomunge.c index 9005b0729..aedec81d1 100644 --- a/kernel/arch/arm/vdso/vdsomunge.c +++ b/kernel/arch/arm/vdso/vdsomunge.c @@ -45,13 +45,11 @@ * it does. */ -#define _GNU_SOURCE - #include <byteswap.h> #include <elf.h> #include <errno.h> -#include <error.h> #include <fcntl.h> +#include <stdarg.h> #include <stdbool.h> #include <stdio.h> #include <stdlib.h> @@ -82,11 +80,25 @@ #define EF_ARM_ABI_FLOAT_HARD 0x400 #endif +static int failed; +static const char *argv0; static const char *outfile; +static void fail(const char *fmt, ...) +{ + va_list ap; + + failed = 1; + fprintf(stderr, "%s: ", argv0); + va_start(ap, fmt); + vfprintf(stderr, fmt, ap); + va_end(ap); + exit(EXIT_FAILURE); +} + static void cleanup(void) { - if (error_message_count > 0 && outfile != NULL) + if (failed && outfile != NULL) unlink(outfile); } @@ -119,68 +131,66 @@ int main(int argc, char **argv) int infd; atexit(cleanup); + argv0 = argv[0]; if (argc != 3) - error(EXIT_FAILURE, 0, "Usage: %s [infile] [outfile]", argv[0]); + fail("Usage: %s [infile] [outfile]\n", argv[0]); infile = argv[1]; outfile = argv[2]; infd = open(infile, O_RDONLY); if (infd < 0) - error(EXIT_FAILURE, errno, "Cannot open %s", infile); + fail("Cannot open %s: %s\n", infile, strerror(errno)); if (fstat(infd, &stat) != 0) - error(EXIT_FAILURE, errno, "Failed stat for %s", infile); + fail("Failed stat for %s: %s\n", infile, strerror(errno)); inbuf = mmap(NULL, stat.st_size, PROT_READ, MAP_PRIVATE, infd, 0); if (inbuf == MAP_FAILED) - error(EXIT_FAILURE, errno, "Failed to map %s", infile); + fail("Failed to map %s: %s\n", infile, strerror(errno)); close(infd); inhdr = inbuf; if (memcmp(&inhdr->e_ident, ELFMAG, SELFMAG) != 0) - error(EXIT_FAILURE, 0, "Not an ELF file"); + fail("Not an ELF file\n"); if (inhdr->e_ident[EI_CLASS] != ELFCLASS32) - error(EXIT_FAILURE, 0, "Unsupported ELF class"); + fail("Unsupported ELF class\n"); swap = inhdr->e_ident[EI_DATA] != HOST_ORDER; if (read_elf_half(inhdr->e_type, swap) != ET_DYN) - error(EXIT_FAILURE, 0, "Not a shared object"); + fail("Not a shared object\n"); - if (read_elf_half(inhdr->e_machine, swap) != EM_ARM) { - error(EXIT_FAILURE, 0, "Unsupported architecture %#x", - inhdr->e_machine); - } + if (read_elf_half(inhdr->e_machine, swap) != EM_ARM) + fail("Unsupported architecture %#x\n", inhdr->e_machine); e_flags = read_elf_word(inhdr->e_flags, swap); if (EF_ARM_EABI_VERSION(e_flags) != EF_ARM_EABI_VER5) { - error(EXIT_FAILURE, 0, "Unsupported EABI version %#x", - EF_ARM_EABI_VERSION(e_flags)); + fail("Unsupported EABI version %#x\n", + EF_ARM_EABI_VERSION(e_flags)); } if (e_flags & EF_ARM_ABI_FLOAT_HARD) - error(EXIT_FAILURE, 0, - "Unexpected hard-float flag set in e_flags"); + fail("Unexpected hard-float flag set in e_flags\n"); clear_soft_float = !!(e_flags & EF_ARM_ABI_FLOAT_SOFT); outfd = open(outfile, O_RDWR | O_CREAT | O_TRUNC, S_IRUSR | S_IWUSR); if (outfd < 0) - error(EXIT_FAILURE, errno, "Cannot open %s", outfile); + fail("Cannot open %s: %s\n", outfile, strerror(errno)); if (ftruncate(outfd, stat.st_size) != 0) - error(EXIT_FAILURE, errno, "Cannot truncate %s", outfile); + fail("Cannot truncate %s: %s\n", outfile, strerror(errno)); outbuf = mmap(NULL, stat.st_size, PROT_READ | PROT_WRITE, MAP_SHARED, outfd, 0); if (outbuf == MAP_FAILED) - error(EXIT_FAILURE, errno, "Failed to map %s", outfile); + fail("Failed to map %s: %s\n", outfile, strerror(errno)); close(outfd); @@ -195,7 +205,7 @@ int main(int argc, char **argv) } if (msync(outbuf, stat.st_size, MS_SYNC) != 0) - error(EXIT_FAILURE, errno, "Failed to sync %s", outfile); + fail("Failed to sync %s: %s\n", outfile, strerror(errno)); return EXIT_SUCCESS; } diff --git a/kernel/arch/arm64/kernel/efi.c b/kernel/arch/arm64/kernel/efi.c index ab21e0d58..352962bc2 100644 --- a/kernel/arch/arm64/kernel/efi.c +++ b/kernel/arch/arm64/kernel/efi.c @@ -122,12 +122,12 @@ static int __init uefi_init(void) /* Show what we know for posterity */ c16 = early_memremap(efi_to_phys(efi.systab->fw_vendor), - sizeof(vendor)); + sizeof(vendor) * sizeof(efi_char16_t)); if (c16) { for (i = 0; i < (int) sizeof(vendor) - 1 && *c16; ++i) vendor[i] = c16[i]; vendor[i] = '\0'; - early_memunmap(c16, sizeof(vendor)); + early_memunmap(c16, sizeof(vendor) * sizeof(efi_char16_t)); } pr_info("EFI v%u.%.02u by %s\n", diff --git a/kernel/arch/arm64/kernel/perf_event.c b/kernel/arch/arm64/kernel/perf_event.c index 702591f61..fd26e57e7 100644 --- a/kernel/arch/arm64/kernel/perf_event.c +++ b/kernel/arch/arm64/kernel/perf_event.c @@ -1318,7 +1318,7 @@ static int armpmu_device_probe(struct platform_device *pdev) /* Don't bother with PPIs; they're already affine */ irq = platform_get_irq(pdev, 0); if (irq >= 0 && irq_is_percpu(irq)) - return 0; + goto out; irqs = kcalloc(pdev->num_resources, sizeof(*irqs), GFP_KERNEL); if (!irqs) @@ -1355,6 +1355,7 @@ static int armpmu_device_probe(struct platform_device *pdev) else kfree(irqs); +out: cpu_pmu->plat_device = pdev; return 0; } diff --git a/kernel/arch/arm64/kernel/signal32.c b/kernel/arch/arm64/kernel/signal32.c index d26fcd4cd..c0cff3410 100644 --- a/kernel/arch/arm64/kernel/signal32.c +++ b/kernel/arch/arm64/kernel/signal32.c @@ -168,7 +168,8 @@ int copy_siginfo_to_user32(compat_siginfo_t __user *to, const siginfo_t *from) * Other callers might not initialize the si_lsb field, * so check explicitely for the right codes here. */ - if (from->si_code == BUS_MCEERR_AR || from->si_code == BUS_MCEERR_AO) + if (from->si_signo == SIGBUS && + (from->si_code == BUS_MCEERR_AR || from->si_code == BUS_MCEERR_AO)) err |= __put_user(from->si_addr_lsb, &to->si_addr_lsb); #endif break; @@ -201,8 +202,6 @@ int copy_siginfo_to_user32(compat_siginfo_t __user *to, const siginfo_t *from) int copy_siginfo_from_user32(siginfo_t *to, compat_siginfo_t __user *from) { - memset(to, 0, sizeof *to); - if (copy_from_user(to, from, __ARCH_SI_PREAMBLE_SIZE) || copy_from_user(to->_sifields._pad, from->_sifields._pad, SI_PAD_SIZE)) diff --git a/kernel/arch/arm64/kernel/smp.c b/kernel/arch/arm64/kernel/smp.c index 2cb008177..d3a202b85 100644 --- a/kernel/arch/arm64/kernel/smp.c +++ b/kernel/arch/arm64/kernel/smp.c @@ -569,7 +569,7 @@ void handle_IPI(int ipinr, struct pt_regs *regs) struct pt_regs *old_regs = set_irq_regs(regs); if ((unsigned)ipinr < NR_IPI) { - trace_ipi_entry(ipi_types[ipinr]); + trace_ipi_entry_rcuidle(ipi_types[ipinr]); __inc_irq_stat(cpu, ipi_irqs[ipinr]); } @@ -612,7 +612,7 @@ void handle_IPI(int ipinr, struct pt_regs *regs) } if ((unsigned)ipinr < NR_IPI) - trace_ipi_exit(ipi_types[ipinr]); + trace_ipi_exit_rcuidle(ipi_types[ipinr]); set_irq_regs(old_regs); } diff --git a/kernel/arch/arm64/kvm/inject_fault.c b/kernel/arch/arm64/kvm/inject_fault.c index f02530e72..85c57158d 100644 --- a/kernel/arch/arm64/kvm/inject_fault.c +++ b/kernel/arch/arm64/kvm/inject_fault.c @@ -168,8 +168,8 @@ void kvm_inject_dabt(struct kvm_vcpu *vcpu, unsigned long addr) { if (!(vcpu->arch.hcr_el2 & HCR_RW)) inject_abt32(vcpu, false, addr); - - inject_abt64(vcpu, false, addr); + else + inject_abt64(vcpu, false, addr); } /** @@ -184,8 +184,8 @@ void kvm_inject_pabt(struct kvm_vcpu *vcpu, unsigned long addr) { if (!(vcpu->arch.hcr_el2 & HCR_RW)) inject_abt32(vcpu, true, addr); - - inject_abt64(vcpu, true, addr); + else + inject_abt64(vcpu, true, addr); } /** @@ -198,6 +198,6 @@ void kvm_inject_undefined(struct kvm_vcpu *vcpu) { if (!(vcpu->arch.hcr_el2 & HCR_RW)) inject_undef32(vcpu); - - inject_undef64(vcpu); + else + inject_undef64(vcpu); } diff --git a/kernel/arch/arm64/mm/hugetlbpage.c b/kernel/arch/arm64/mm/hugetlbpage.c index 2de9d2e59..0eeb4f093 100644 --- a/kernel/arch/arm64/mm/hugetlbpage.c +++ b/kernel/arch/arm64/mm/hugetlbpage.c @@ -40,13 +40,13 @@ int huge_pmd_unshare(struct mm_struct *mm, unsigned long *addr, pte_t *ptep) int pmd_huge(pmd_t pmd) { - return !(pmd_val(pmd) & PMD_TABLE_BIT); + return pmd_val(pmd) && !(pmd_val(pmd) & PMD_TABLE_BIT); } int pud_huge(pud_t pud) { #ifndef __PAGETABLE_PMD_FOLDED - return !(pud_val(pud) & PUD_TABLE_BIT); + return pud_val(pud) && !(pud_val(pud) & PUD_TABLE_BIT); #else return 0; #endif diff --git a/kernel/arch/arm64/net/bpf_jit.h b/kernel/arch/arm64/net/bpf_jit.h index de0a81a53..98a26ce82 100644 --- a/kernel/arch/arm64/net/bpf_jit.h +++ b/kernel/arch/arm64/net/bpf_jit.h @@ -110,6 +110,10 @@ /* Rd = Rn >> shift; signed */ #define A64_ASR(sf, Rd, Rn, shift) A64_SBFM(sf, Rd, Rn, shift, (sf) ? 63 : 31) +/* Zero extend */ +#define A64_UXTH(sf, Rd, Rn) A64_UBFM(sf, Rd, Rn, 0, 15) +#define A64_UXTW(sf, Rd, Rn) A64_UBFM(sf, Rd, Rn, 0, 31) + /* Move wide (immediate) */ #define A64_MOVEW(sf, Rd, imm16, shift, type) \ aarch64_insn_gen_movewide(Rd, imm16, shift, \ diff --git a/kernel/arch/arm64/net/bpf_jit_comp.c b/kernel/arch/arm64/net/bpf_jit_comp.c index dc6a48426..c047598b0 100644 --- a/kernel/arch/arm64/net/bpf_jit_comp.c +++ b/kernel/arch/arm64/net/bpf_jit_comp.c @@ -113,9 +113,9 @@ static inline void emit_a64_mov_i(const int is64, const int reg, static inline int bpf2a64_offset(int bpf_to, int bpf_from, const struct jit_ctx *ctx) { - int to = ctx->offset[bpf_to + 1]; + int to = ctx->offset[bpf_to]; /* -1 to account for the Branch instruction */ - int from = ctx->offset[bpf_from + 1] - 1; + int from = ctx->offset[bpf_from] - 1; return to - from; } @@ -289,23 +289,41 @@ static int build_insn(const struct bpf_insn *insn, struct jit_ctx *ctx) case BPF_ALU | BPF_END | BPF_FROM_BE: #ifdef CONFIG_CPU_BIG_ENDIAN if (BPF_SRC(code) == BPF_FROM_BE) - break; + goto emit_bswap_uxt; #else /* !CONFIG_CPU_BIG_ENDIAN */ if (BPF_SRC(code) == BPF_FROM_LE) - break; + goto emit_bswap_uxt; #endif switch (imm) { case 16: emit(A64_REV16(is64, dst, dst), ctx); + /* zero-extend 16 bits into 64 bits */ + emit(A64_UXTH(is64, dst, dst), ctx); break; case 32: emit(A64_REV32(is64, dst, dst), ctx); + /* upper 32 bits already cleared */ break; case 64: emit(A64_REV64(dst, dst), ctx); break; } break; +emit_bswap_uxt: + switch (imm) { + case 16: + /* zero-extend 16 bits into 64 bits */ + emit(A64_UXTH(is64, dst, dst), ctx); + break; + case 32: + /* zero-extend 32 bits into 64 bits */ + emit(A64_UXTW(is64, dst, dst), ctx); + break; + case 64: + /* nop */ + break; + } + break; /* dst = imm */ case BPF_ALU | BPF_MOV | BPF_K: case BPF_ALU64 | BPF_MOV | BPF_K: @@ -640,10 +658,11 @@ static int build_body(struct jit_ctx *ctx) const struct bpf_insn *insn = &prog->insnsi[i]; int ret; + ret = build_insn(insn, ctx); + if (ctx->image == NULL) ctx->offset[i] = ctx->idx; - ret = build_insn(insn, ctx); if (ret > 0) { i++; continue; diff --git a/kernel/arch/avr32/mach-at32ap/clock.c b/kernel/arch/avr32/mach-at32ap/clock.c index 23b1a97fa..52c179bec 100644 --- a/kernel/arch/avr32/mach-at32ap/clock.c +++ b/kernel/arch/avr32/mach-at32ap/clock.c @@ -80,6 +80,9 @@ int clk_enable(struct clk *clk) { unsigned long flags; + if (!clk) + return 0; + spin_lock_irqsave(&clk_lock, flags); __clk_enable(clk); spin_unlock_irqrestore(&clk_lock, flags); @@ -106,6 +109,9 @@ void clk_disable(struct clk *clk) { unsigned long flags; + if (IS_ERR_OR_NULL(clk)) + return; + spin_lock_irqsave(&clk_lock, flags); __clk_disable(clk); spin_unlock_irqrestore(&clk_lock, flags); @@ -117,6 +123,9 @@ unsigned long clk_get_rate(struct clk *clk) unsigned long flags; unsigned long rate; + if (!clk) + return 0; + spin_lock_irqsave(&clk_lock, flags); rate = clk->get_rate(clk); spin_unlock_irqrestore(&clk_lock, flags); @@ -129,6 +138,9 @@ long clk_round_rate(struct clk *clk, unsigned long rate) { unsigned long flags, actual_rate; + if (!clk) + return 0; + if (!clk->set_rate) return -ENOSYS; @@ -145,6 +157,9 @@ int clk_set_rate(struct clk *clk, unsigned long rate) unsigned long flags; long ret; + if (!clk) + return 0; + if (!clk->set_rate) return -ENOSYS; @@ -161,6 +176,9 @@ int clk_set_parent(struct clk *clk, struct clk *parent) unsigned long flags; int ret; + if (!clk) + return 0; + if (!clk->set_parent) return -ENOSYS; @@ -174,7 +192,7 @@ EXPORT_SYMBOL(clk_set_parent); struct clk *clk_get_parent(struct clk *clk) { - return clk->parent; + return !clk ? NULL : clk->parent; } EXPORT_SYMBOL(clk_get_parent); diff --git a/kernel/arch/m68k/Kconfig.cpu b/kernel/arch/m68k/Kconfig.cpu index 33013dfcd..5c68c85d5 100644 --- a/kernel/arch/m68k/Kconfig.cpu +++ b/kernel/arch/m68k/Kconfig.cpu @@ -125,6 +125,13 @@ endif # M68KCLASSIC if COLDFIRE +choice + prompt "ColdFire SoC type" + default M520x + help + Select the type of ColdFire System-on-Chip (SoC) that you want + to build for. + config M5206 bool "MCF5206" depends on !MMU @@ -174,9 +181,6 @@ config M525x help Freescale (Motorola) Coldfire 5251/5253 processor support. -config M527x - bool - config M5271 bool "MCF5271" depends on !MMU @@ -223,9 +227,6 @@ config M5307 help Motorola ColdFire 5307 processor support. -config M53xx - bool - config M532x bool "MCF532x" depends on !MMU @@ -251,9 +252,6 @@ config M5407 help Motorola ColdFire 5407 processor support. -config M54xx - bool - config M547x bool "MCF547x" select M54xx @@ -280,6 +278,17 @@ config M5441x help Freescale Coldfire 54410/54415/54416/54417/54418 processor support. +endchoice + +config M527x + bool + +config M53xx + bool + +config M54xx + bool + endif # COLDFIRE @@ -416,22 +425,10 @@ config HAVE_MBAR config HAVE_IPSBAR bool -config CLOCK_SET - bool "Enable setting the CPU clock frequency" - depends on COLDFIRE - default n - help - On some CPU's you do not need to know what the core CPU clock - frequency is. On these you can disable clock setting. On some - traditional 68K parts, and on all ColdFire parts you need to set - the appropriate CPU clock frequency. On these devices many of the - onboard peripherals derive their timing from the master CPU clock - frequency. - config CLOCK_FREQ int "Set the core clock frequency" default "66666666" - depends on CLOCK_SET + depends on COLDFIRE help Define the CPU clock frequency in use. This is the core clock frequency, it may or may not be the same as the external clock diff --git a/kernel/arch/m68k/include/asm/coldfire.h b/kernel/arch/m68k/include/asm/coldfire.h index c94557b91..50aa4dac9 100644 --- a/kernel/arch/m68k/include/asm/coldfire.h +++ b/kernel/arch/m68k/include/asm/coldfire.h @@ -19,7 +19,7 @@ * in any case new boards come along from time to time that have yet * another different clocking frequency. */ -#ifdef CONFIG_CLOCK_SET +#ifdef CONFIG_CLOCK_FREQ #define MCF_CLK CONFIG_CLOCK_FREQ #else #error "Don't know what your ColdFire CPU clock frequency is??" diff --git a/kernel/arch/mips/Kconfig b/kernel/arch/mips/Kconfig index db1f41683..9b95c9b7e 100644 --- a/kernel/arch/mips/Kconfig +++ b/kernel/arch/mips/Kconfig @@ -1417,6 +1417,7 @@ config CPU_MIPS64_R6 select CPU_SUPPORTS_HIGHMEM select CPU_SUPPORTS_MSA select GENERIC_CSUM + select MIPS_O32_FP64_SUPPORT if MIPS32_O32 help Choose this option to build a kernel for release 6 or later of the MIPS64 architecture. New MIPS processors, starting with the Warrior diff --git a/kernel/arch/mips/ath79/setup.c b/kernel/arch/mips/ath79/setup.c index 7fc8397d1..fd2a36a79 100644 --- a/kernel/arch/mips/ath79/setup.c +++ b/kernel/arch/mips/ath79/setup.c @@ -186,6 +186,7 @@ int get_c0_perfcount_int(void) { return ATH79_MISC_IRQ(5); } +EXPORT_SYMBOL_GPL(get_c0_perfcount_int); unsigned int get_c0_compare_int(void) { diff --git a/kernel/arch/mips/include/asm/fpu.h b/kernel/arch/mips/include/asm/fpu.h index 084780b35..1b0625189 100644 --- a/kernel/arch/mips/include/asm/fpu.h +++ b/kernel/arch/mips/include/asm/fpu.h @@ -74,7 +74,7 @@ static inline int __enable_fpu(enum fpu_mode mode) goto fr_common; case FPU_64BIT: -#if !(defined(CONFIG_CPU_MIPS32_R2) || defined(CONFIG_CPU_MIPS32_R6) \ +#if !(defined(CONFIG_CPU_MIPSR2) || defined(CONFIG_CPU_MIPSR6) \ || defined(CONFIG_64BIT)) /* we only have a 32-bit FPU */ return SIGFPE; diff --git a/kernel/arch/mips/include/asm/mach-bcm63xx/dma-coherence.h b/kernel/arch/mips/include/asm/mach-bcm63xx/dma-coherence.h deleted file mode 100644 index 11d3b572b..000000000 --- a/kernel/arch/mips/include/asm/mach-bcm63xx/dma-coherence.h +++ /dev/null @@ -1,10 +0,0 @@ -#ifndef __ASM_MACH_BCM63XX_DMA_COHERENCE_H -#define __ASM_MACH_BCM63XX_DMA_COHERENCE_H - -#include <asm/bmips.h> - -#define plat_post_dma_flush bmips_post_dma_flush - -#include <asm/mach-generic/dma-coherence.h> - -#endif /* __ASM_MACH_BCM63XX_DMA_COHERENCE_H */ diff --git a/kernel/arch/mips/include/asm/pgtable.h b/kernel/arch/mips/include/asm/pgtable.h index 819af9d05..70f6e7f07 100644 --- a/kernel/arch/mips/include/asm/pgtable.h +++ b/kernel/arch/mips/include/asm/pgtable.h @@ -182,8 +182,39 @@ static inline void set_pte(pte_t *ptep, pte_t pteval) * Make sure the buddy is global too (if it's !none, * it better already be global) */ +#ifdef CONFIG_SMP + /* + * For SMP, multiple CPUs can race, so we need to do + * this atomically. + */ +#ifdef CONFIG_64BIT +#define LL_INSN "lld" +#define SC_INSN "scd" +#else /* CONFIG_32BIT */ +#define LL_INSN "ll" +#define SC_INSN "sc" +#endif + unsigned long page_global = _PAGE_GLOBAL; + unsigned long tmp; + + __asm__ __volatile__ ( + " .set push\n" + " .set noreorder\n" + "1: " LL_INSN " %[tmp], %[buddy]\n" + " bnez %[tmp], 2f\n" + " or %[tmp], %[tmp], %[global]\n" + " " SC_INSN " %[tmp], %[buddy]\n" + " beqz %[tmp], 1b\n" + " nop\n" + "2:\n" + " .set pop" + : [buddy] "+m" (buddy->pte), + [tmp] "=&r" (tmp) + : [global] "r" (page_global)); +#else /* !CONFIG_SMP */ if (pte_none(*buddy)) pte_val(*buddy) = pte_val(*buddy) | _PAGE_GLOBAL; +#endif /* CONFIG_SMP */ } #endif } diff --git a/kernel/arch/mips/include/asm/smp.h b/kernel/arch/mips/include/asm/smp.h index 2b25d1ba1..16f1ea9ab 100644 --- a/kernel/arch/mips/include/asm/smp.h +++ b/kernel/arch/mips/include/asm/smp.h @@ -23,6 +23,7 @@ extern int smp_num_siblings; extern cpumask_t cpu_sibling_map[]; extern cpumask_t cpu_core_map[]; +extern cpumask_t cpu_foreign_map; #define raw_smp_processor_id() (current_thread_info()->cpu) diff --git a/kernel/arch/mips/include/asm/stackframe.h b/kernel/arch/mips/include/asm/stackframe.h index 28d6d9364..a71da5768 100644 --- a/kernel/arch/mips/include/asm/stackframe.h +++ b/kernel/arch/mips/include/asm/stackframe.h @@ -152,6 +152,31 @@ .set noreorder bltz k0, 8f move k1, sp +#ifdef CONFIG_EVA + /* + * Flush interAptiv's Return Prediction Stack (RPS) by writing + * EntryHi. Toggling Config7.RPS is slower and less portable. + * + * The RPS isn't automatically flushed when exceptions are + * taken, which can result in kernel mode speculative accesses + * to user addresses if the RPS mispredicts. That's harmless + * when user and kernel share the same address space, but with + * EVA the same user segments may be unmapped to kernel mode, + * even containing sensitive MMIO regions or invalid memory. + * + * This can happen when the kernel sets the return address to + * ret_from_* and jr's to the exception handler, which looks + * more like a tail call than a function call. If nested calls + * don't evict the last user address in the RPS, it will + * mispredict the return and fetch from a user controlled + * address into the icache. + * + * More recent EVA-capable cores with MAAR to restrict + * speculative accesses aren't affected. + */ + MFC0 k0, CP0_ENTRYHI + MTC0 k0, CP0_ENTRYHI +#endif .set reorder /* Called from user mode, new stack. */ get_saved_sp diff --git a/kernel/arch/mips/kernel/mips-mt-fpaff.c b/kernel/arch/mips/kernel/mips-mt-fpaff.c index 3e4491aa6..789d7bf4f 100644 --- a/kernel/arch/mips/kernel/mips-mt-fpaff.c +++ b/kernel/arch/mips/kernel/mips-mt-fpaff.c @@ -154,7 +154,7 @@ asmlinkage long mipsmt_sys_sched_getaffinity(pid_t pid, unsigned int len, unsigned long __user *user_mask_ptr) { unsigned int real_len; - cpumask_t mask; + cpumask_t allowed, mask; int retval; struct task_struct *p; @@ -173,7 +173,8 @@ asmlinkage long mipsmt_sys_sched_getaffinity(pid_t pid, unsigned int len, if (retval) goto out_unlock; - cpumask_and(&mask, &p->thread.user_cpus_allowed, cpu_possible_mask); + cpumask_or(&allowed, &p->thread.user_cpus_allowed, &p->cpus_allowed); + cpumask_and(&mask, &allowed, cpu_active_mask); out_unlock: read_unlock(&tasklist_lock); diff --git a/kernel/arch/mips/kernel/relocate_kernel.S b/kernel/arch/mips/kernel/relocate_kernel.S index 74bab9ddd..c6bbf2165 100644 --- a/kernel/arch/mips/kernel/relocate_kernel.S +++ b/kernel/arch/mips/kernel/relocate_kernel.S @@ -24,7 +24,7 @@ LEAF(relocate_new_kernel) process_entry: PTR_L s2, (s0) - PTR_ADD s0, s0, SZREG + PTR_ADDIU s0, s0, SZREG /* * In case of a kdump/crash kernel, the indirection page is not @@ -61,9 +61,9 @@ copy_word: /* copy page word by word */ REG_L s5, (s2) REG_S s5, (s4) - PTR_ADD s4, s4, SZREG - PTR_ADD s2, s2, SZREG - LONG_SUB s6, s6, 1 + PTR_ADDIU s4, s4, SZREG + PTR_ADDIU s2, s2, SZREG + LONG_ADDIU s6, s6, -1 beq s6, zero, process_entry b copy_word b process_entry diff --git a/kernel/arch/mips/kernel/scall64-64.S b/kernel/arch/mips/kernel/scall64-64.S index ad4d44635..a6f6b762c 100644 --- a/kernel/arch/mips/kernel/scall64-64.S +++ b/kernel/arch/mips/kernel/scall64-64.S @@ -80,7 +80,7 @@ syscall_trace_entry: SAVE_STATIC move s0, t2 move a0, sp - daddiu a1, v0, __NR_64_Linux + move a1, v0 jal syscall_trace_enter bltz v0, 2f # seccomp failed? Skip syscall diff --git a/kernel/arch/mips/kernel/scall64-n32.S b/kernel/arch/mips/kernel/scall64-n32.S index 446cc654d..4b2010654 100644 --- a/kernel/arch/mips/kernel/scall64-n32.S +++ b/kernel/arch/mips/kernel/scall64-n32.S @@ -72,7 +72,7 @@ n32_syscall_trace_entry: SAVE_STATIC move s0, t2 move a0, sp - daddiu a1, v0, __NR_N32_Linux + move a1, v0 jal syscall_trace_enter bltz v0, 2f # seccomp failed? Skip syscall diff --git a/kernel/arch/mips/kernel/signal32.c b/kernel/arch/mips/kernel/signal32.c index 19a7705f2..5d7f26349 100644 --- a/kernel/arch/mips/kernel/signal32.c +++ b/kernel/arch/mips/kernel/signal32.c @@ -409,8 +409,6 @@ int copy_siginfo_to_user32(compat_siginfo_t __user *to, const siginfo_t *from) int copy_siginfo_from_user32(siginfo_t *to, compat_siginfo_t __user *from) { - memset(to, 0, sizeof *to); - if (copy_from_user(to, from, 3*sizeof(int)) || copy_from_user(to->_sifields._pad, from->_sifields._pad, SI_PAD_SIZE32)) diff --git a/kernel/arch/mips/kernel/smp.c b/kernel/arch/mips/kernel/smp.c index faa46ebd9..d0744cc77 100644 --- a/kernel/arch/mips/kernel/smp.c +++ b/kernel/arch/mips/kernel/smp.c @@ -63,6 +63,13 @@ EXPORT_SYMBOL(cpu_sibling_map); cpumask_t cpu_core_map[NR_CPUS] __read_mostly; EXPORT_SYMBOL(cpu_core_map); +/* + * A logcal cpu mask containing only one VPE per core to + * reduce the number of IPIs on large MT systems. + */ +cpumask_t cpu_foreign_map __read_mostly; +EXPORT_SYMBOL(cpu_foreign_map); + /* representing cpus for which sibling maps can be computed */ static cpumask_t cpu_sibling_setup_map; @@ -103,6 +110,29 @@ static inline void set_cpu_core_map(int cpu) } } +/* + * Calculate a new cpu_foreign_map mask whenever a + * new cpu appears or disappears. + */ +static inline void calculate_cpu_foreign_map(void) +{ + int i, k, core_present; + cpumask_t temp_foreign_map; + + /* Re-calculate the mask */ + for_each_online_cpu(i) { + core_present = 0; + for_each_cpu(k, &temp_foreign_map) + if (cpu_data[i].package == cpu_data[k].package && + cpu_data[i].core == cpu_data[k].core) + core_present = 1; + if (!core_present) + cpumask_set_cpu(i, &temp_foreign_map); + } + + cpumask_copy(&cpu_foreign_map, &temp_foreign_map); +} + struct plat_smp_ops *mp_ops; EXPORT_SYMBOL(mp_ops); @@ -146,6 +176,8 @@ asmlinkage void start_secondary(void) set_cpu_sibling_map(cpu); set_cpu_core_map(cpu); + calculate_cpu_foreign_map(); + cpumask_set_cpu(cpu, &cpu_callin_map); synchronise_count_slave(cpu); @@ -173,9 +205,18 @@ void __irq_entry smp_call_function_interrupt(void) static void stop_this_cpu(void *dummy) { /* - * Remove this CPU: + * Remove this CPU. Be a bit slow here and + * set the bits for every online CPU so we don't miss + * any IPI whilst taking this VPE down. */ + + cpumask_copy(&cpu_foreign_map, cpu_online_mask); + + /* Make it visible to every other CPU */ + smp_mb(); + set_cpu_online(smp_processor_id(), false); + calculate_cpu_foreign_map(); local_irq_disable(); while (1); } @@ -197,6 +238,7 @@ void __init smp_prepare_cpus(unsigned int max_cpus) mp_ops->prepare_cpus(max_cpus); set_cpu_sibling_map(0); set_cpu_core_map(0); + calculate_cpu_foreign_map(); #ifndef CONFIG_HOTPLUG_CPU init_cpu_present(cpu_possible_mask); #endif diff --git a/kernel/arch/mips/kernel/traps.c b/kernel/arch/mips/kernel/traps.c index d2d1c1933..5f5f44edc 100644 --- a/kernel/arch/mips/kernel/traps.c +++ b/kernel/arch/mips/kernel/traps.c @@ -192,6 +192,7 @@ static void show_stacktrace(struct task_struct *task, void show_stack(struct task_struct *task, unsigned long *sp) { struct pt_regs regs; + mm_segment_t old_fs = get_fs(); if (sp) { regs.regs[29] = (unsigned long)sp; regs.regs[31] = 0; @@ -210,7 +211,13 @@ void show_stack(struct task_struct *task, unsigned long *sp) prepare_frametrace(®s); } } + /* + * show_stack() deals exclusively with kernel mode, so be sure to access + * the stack in the kernel (not user) address space. + */ + set_fs(KERNEL_DS); show_stacktrace(task, ®s); + set_fs(old_fs); } static void show_code(unsigned int __user *pc) @@ -1518,6 +1525,7 @@ asmlinkage void do_mcheck(struct pt_regs *regs) const int field = 2 * sizeof(unsigned long); int multi_match = regs->cp0_status & ST0_TS; enum ctx_state prev_state; + mm_segment_t old_fs = get_fs(); prev_state = exception_enter(); show_regs(regs); @@ -1539,8 +1547,13 @@ asmlinkage void do_mcheck(struct pt_regs *regs) dump_tlb_all(); } + if (!user_mode(regs)) + set_fs(KERNEL_DS); + show_code((unsigned int __user *) regs->cp0_epc); + set_fs(old_fs); + /* * Some chips may have other causes of machine check (e.g. SB1 * graduation timer) diff --git a/kernel/arch/mips/kernel/unaligned.c b/kernel/arch/mips/kernel/unaligned.c index af84bef0c..eb3efd137 100644 --- a/kernel/arch/mips/kernel/unaligned.c +++ b/kernel/arch/mips/kernel/unaligned.c @@ -438,7 +438,7 @@ do { \ : "memory"); \ } while(0) -#define StoreDW(addr, value, res) \ +#define _StoreDW(addr, value, res) \ do { \ __asm__ __volatile__ ( \ ".set\tpush\n\t" \ diff --git a/kernel/arch/mips/lantiq/irq.c b/kernel/arch/mips/lantiq/irq.c index 6ab105734..d01ade634 100644 --- a/kernel/arch/mips/lantiq/irq.c +++ b/kernel/arch/mips/lantiq/irq.c @@ -466,6 +466,7 @@ int get_c0_perfcount_int(void) { return ltq_perfcount_irq; } +EXPORT_SYMBOL_GPL(get_c0_perfcount_int); unsigned int get_c0_compare_int(void) { diff --git a/kernel/arch/mips/math-emu/cp1emu.c b/kernel/arch/mips/math-emu/cp1emu.c index 22b9b2cb9..6983fcd48 100644 --- a/kernel/arch/mips/math-emu/cp1emu.c +++ b/kernel/arch/mips/math-emu/cp1emu.c @@ -451,7 +451,7 @@ static int isBranchInstr(struct pt_regs *regs, struct mm_decoded_insn dec_insn, /* Fall through */ case jr_op: /* For R6, JR already emulated in jalr_op */ - if (NO_R6EMU && insn.r_format.opcode == jr_op) + if (NO_R6EMU && insn.r_format.func == jr_op) break; *contpc = regs->regs[insn.r_format.rs]; return 1; diff --git a/kernel/arch/mips/mm/c-r4k.c b/kernel/arch/mips/mm/c-r4k.c index 2e03ab173..dca0efc07 100644 --- a/kernel/arch/mips/mm/c-r4k.c +++ b/kernel/arch/mips/mm/c-r4k.c @@ -37,6 +37,7 @@ #include <asm/cacheflush.h> /* for run_uncached() */ #include <asm/traps.h> #include <asm/dma-coherence.h> +#include <asm/mips-cm.h> /* * Special Variant of smp_call_function for use by cache functions: @@ -51,9 +52,16 @@ static inline void r4k_on_each_cpu(void (*func) (void *info), void *info) { preempt_disable(); -#ifndef CONFIG_MIPS_MT_SMP - smp_call_function(func, info, 1); -#endif + /* + * The Coherent Manager propagates address-based cache ops to other + * cores but not index-based ops. However, r4k_on_each_cpu is used + * in both cases so there is no easy way to tell what kind of op is + * executed to the other cores. The best we can probably do is + * to restrict that call when a CM is not present because both + * CM-based SMP protocols (CMP & CPS) restrict index-based cache ops. + */ + if (!mips_cm_present()) + smp_call_function_many(&cpu_foreign_map, func, info, 1); func(info); preempt_enable(); } diff --git a/kernel/arch/mips/mti-malta/malta-time.c b/kernel/arch/mips/mti-malta/malta-time.c index 185e68261..a7f7d9ffb 100644 --- a/kernel/arch/mips/mti-malta/malta-time.c +++ b/kernel/arch/mips/mti-malta/malta-time.c @@ -148,6 +148,7 @@ int get_c0_perfcount_int(void) return mips_cpu_perf_irq; } +EXPORT_SYMBOL_GPL(get_c0_perfcount_int); unsigned int get_c0_compare_int(void) { @@ -165,14 +166,17 @@ unsigned int get_c0_compare_int(void) static void __init init_rtc(void) { - /* stop the clock whilst setting it up */ - CMOS_WRITE(RTC_SET | RTC_24H, RTC_CONTROL); + unsigned char freq, ctrl; - /* 32KHz time base */ - CMOS_WRITE(RTC_REF_CLCK_32KHZ, RTC_FREQ_SELECT); + /* Set 32KHz time base if not already set */ + freq = CMOS_READ(RTC_FREQ_SELECT); + if ((freq & RTC_DIV_CTL) != RTC_REF_CLCK_32KHZ) + CMOS_WRITE(RTC_REF_CLCK_32KHZ, RTC_FREQ_SELECT); - /* start the clock */ - CMOS_WRITE(RTC_24H, RTC_CONTROL); + /* Ensure SET bit is clear so RTC can run */ + ctrl = CMOS_READ(RTC_CONTROL); + if (ctrl & RTC_SET) + CMOS_WRITE(ctrl & ~RTC_SET, RTC_CONTROL); } void __init plat_time_init(void) diff --git a/kernel/arch/mips/mti-sead3/sead3-time.c b/kernel/arch/mips/mti-sead3/sead3-time.c index e1d69895f..a120b7a5a 100644 --- a/kernel/arch/mips/mti-sead3/sead3-time.c +++ b/kernel/arch/mips/mti-sead3/sead3-time.c @@ -77,6 +77,7 @@ int get_c0_perfcount_int(void) return MIPS_CPU_IRQ_BASE + cp0_perfcount_irq; return -1; } +EXPORT_SYMBOL_GPL(get_c0_perfcount_int); unsigned int get_c0_compare_int(void) { diff --git a/kernel/arch/mips/pistachio/time.c b/kernel/arch/mips/pistachio/time.c index 67889fcea..ab73f6f40 100644 --- a/kernel/arch/mips/pistachio/time.c +++ b/kernel/arch/mips/pistachio/time.c @@ -26,6 +26,7 @@ int get_c0_perfcount_int(void) { return gic_get_c0_perfcount_int(); } +EXPORT_SYMBOL_GPL(get_c0_perfcount_int); void __init plat_time_init(void) { diff --git a/kernel/arch/mips/ralink/irq.c b/kernel/arch/mips/ralink/irq.c index 7cf91b92e..199ace4ca 100644 --- a/kernel/arch/mips/ralink/irq.c +++ b/kernel/arch/mips/ralink/irq.c @@ -89,6 +89,7 @@ int get_c0_perfcount_int(void) { return rt_perfcount_irq; } +EXPORT_SYMBOL_GPL(get_c0_perfcount_int); unsigned int get_c0_compare_int(void) { diff --git a/kernel/arch/openrisc/Kconfig b/kernel/arch/openrisc/Kconfig index e5a693b16..443f44de1 100644 --- a/kernel/arch/openrisc/Kconfig +++ b/kernel/arch/openrisc/Kconfig @@ -17,6 +17,7 @@ config OPENRISC select GENERIC_IRQ_SHOW select GENERIC_IOMAP select GENERIC_CPU_DEVICES + select HAVE_UID16 select GENERIC_ATOMIC64 select GENERIC_CLOCKEVENTS select GENERIC_STRNCPY_FROM_USER @@ -31,9 +32,6 @@ config MMU config HAVE_DMA_ATTRS def_bool y -config UID16 - def_bool y - config RWSEM_GENERIC_SPINLOCK def_bool y diff --git a/kernel/arch/parisc/include/asm/pgalloc.h b/kernel/arch/parisc/include/asm/pgalloc.h index 3a08eae33..3edbb9fc9 100644 --- a/kernel/arch/parisc/include/asm/pgalloc.h +++ b/kernel/arch/parisc/include/asm/pgalloc.h @@ -72,7 +72,7 @@ static inline pmd_t *pmd_alloc_one(struct mm_struct *mm, unsigned long address) static inline void pmd_free(struct mm_struct *mm, pmd_t *pmd) { - if(pmd_flag(*pmd) & PxD_FLAG_ATTACHED) + if (pmd_flag(*pmd) & PxD_FLAG_ATTACHED) { /* * This is the permanent pmd attached to the pgd; * cannot free it. @@ -81,6 +81,7 @@ static inline void pmd_free(struct mm_struct *mm, pmd_t *pmd) */ mm_inc_nr_pmds(mm); return; + } free_pages((unsigned long)pmd, PMD_ORDER); } diff --git a/kernel/arch/parisc/include/asm/pgtable.h b/kernel/arch/parisc/include/asm/pgtable.h index 0a183756d..f93c4a4e6 100644 --- a/kernel/arch/parisc/include/asm/pgtable.h +++ b/kernel/arch/parisc/include/asm/pgtable.h @@ -16,7 +16,7 @@ #include <asm/processor.h> #include <asm/cache.h> -extern spinlock_t pa_dbit_lock; +extern spinlock_t pa_tlb_lock; /* * kern_addr_valid(ADDR) tests if ADDR is pointing to valid kernel @@ -33,6 +33,19 @@ extern spinlock_t pa_dbit_lock; */ #define kern_addr_valid(addr) (1) +/* Purge data and instruction TLB entries. Must be called holding + * the pa_tlb_lock. The TLB purge instructions are slow on SMP + * machines since the purge must be broadcast to all CPUs. + */ + +static inline void purge_tlb_entries(struct mm_struct *mm, unsigned long addr) +{ + mtsp(mm->context, 1); + pdtlb(addr); + if (unlikely(split_tlb)) + pitlb(addr); +} + /* Certain architectures need to do special things when PTEs * within a page table are directly modified. Thus, the following * hook is made available. @@ -42,15 +55,20 @@ extern spinlock_t pa_dbit_lock; *(pteptr) = (pteval); \ } while(0) -extern void purge_tlb_entries(struct mm_struct *, unsigned long); +#define pte_inserted(x) \ + ((pte_val(x) & (_PAGE_PRESENT|_PAGE_ACCESSED)) \ + == (_PAGE_PRESENT|_PAGE_ACCESSED)) -#define set_pte_at(mm, addr, ptep, pteval) \ - do { \ +#define set_pte_at(mm, addr, ptep, pteval) \ + do { \ + pte_t old_pte; \ unsigned long flags; \ - spin_lock_irqsave(&pa_dbit_lock, flags); \ - set_pte(ptep, pteval); \ - purge_tlb_entries(mm, addr); \ - spin_unlock_irqrestore(&pa_dbit_lock, flags); \ + spin_lock_irqsave(&pa_tlb_lock, flags); \ + old_pte = *ptep; \ + set_pte(ptep, pteval); \ + if (pte_inserted(old_pte)) \ + purge_tlb_entries(mm, addr); \ + spin_unlock_irqrestore(&pa_tlb_lock, flags); \ } while (0) #endif /* !__ASSEMBLY__ */ @@ -268,7 +286,7 @@ extern unsigned long *empty_zero_page; #define pte_none(x) (pte_val(x) == 0) #define pte_present(x) (pte_val(x) & _PAGE_PRESENT) -#define pte_clear(mm,addr,xp) do { pte_val(*(xp)) = 0; } while (0) +#define pte_clear(mm, addr, xp) set_pte_at(mm, addr, xp, __pte(0)) #define pmd_flag(x) (pmd_val(x) & PxD_FLAG_MASK) #define pmd_address(x) ((unsigned long)(pmd_val(x) &~ PxD_FLAG_MASK) << PxD_VALUE_SHIFT) @@ -435,15 +453,15 @@ static inline int ptep_test_and_clear_young(struct vm_area_struct *vma, unsigned if (!pte_young(*ptep)) return 0; - spin_lock_irqsave(&pa_dbit_lock, flags); + spin_lock_irqsave(&pa_tlb_lock, flags); pte = *ptep; if (!pte_young(pte)) { - spin_unlock_irqrestore(&pa_dbit_lock, flags); + spin_unlock_irqrestore(&pa_tlb_lock, flags); return 0; } set_pte(ptep, pte_mkold(pte)); purge_tlb_entries(vma->vm_mm, addr); - spin_unlock_irqrestore(&pa_dbit_lock, flags); + spin_unlock_irqrestore(&pa_tlb_lock, flags); return 1; } @@ -453,11 +471,12 @@ static inline pte_t ptep_get_and_clear(struct mm_struct *mm, unsigned long addr, pte_t old_pte; unsigned long flags; - spin_lock_irqsave(&pa_dbit_lock, flags); + spin_lock_irqsave(&pa_tlb_lock, flags); old_pte = *ptep; - pte_clear(mm,addr,ptep); - purge_tlb_entries(mm, addr); - spin_unlock_irqrestore(&pa_dbit_lock, flags); + set_pte(ptep, __pte(0)); + if (pte_inserted(old_pte)) + purge_tlb_entries(mm, addr); + spin_unlock_irqrestore(&pa_tlb_lock, flags); return old_pte; } @@ -465,10 +484,10 @@ static inline pte_t ptep_get_and_clear(struct mm_struct *mm, unsigned long addr, static inline void ptep_set_wrprotect(struct mm_struct *mm, unsigned long addr, pte_t *ptep) { unsigned long flags; - spin_lock_irqsave(&pa_dbit_lock, flags); + spin_lock_irqsave(&pa_tlb_lock, flags); set_pte(ptep, pte_wrprotect(*ptep)); purge_tlb_entries(mm, addr); - spin_unlock_irqrestore(&pa_dbit_lock, flags); + spin_unlock_irqrestore(&pa_tlb_lock, flags); } #define pte_same(A,B) (pte_val(A) == pte_val(B)) diff --git a/kernel/arch/parisc/include/asm/tlbflush.h b/kernel/arch/parisc/include/asm/tlbflush.h index 9d086a599..e84b96478 100644 --- a/kernel/arch/parisc/include/asm/tlbflush.h +++ b/kernel/arch/parisc/include/asm/tlbflush.h @@ -13,6 +13,9 @@ * active at any one time on the Merced bus. This tlb purge * synchronisation is fairly lightweight and harmless so we activate * it on all systems not just the N class. + + * It is also used to ensure PTE updates are atomic and consistent + * with the TLB. */ extern spinlock_t pa_tlb_lock; @@ -24,20 +27,24 @@ extern void flush_tlb_all_local(void *); #define smp_flush_tlb_all() flush_tlb_all() +int __flush_tlb_range(unsigned long sid, + unsigned long start, unsigned long end); + +#define flush_tlb_range(vma, start, end) \ + __flush_tlb_range((vma)->vm_mm->context, start, end) + +#define flush_tlb_kernel_range(start, end) \ + __flush_tlb_range(0, start, end) + /* * flush_tlb_mm() * - * XXX This code is NOT valid for HP-UX compatibility processes, - * (although it will probably work 99% of the time). HP-UX - * processes are free to play with the space id's and save them - * over long periods of time, etc. so we have to preserve the - * space and just flush the entire tlb. We need to check the - * personality in order to do that, but the personality is not - * currently being set correctly. - * - * Of course, Linux processes could do the same thing, but - * we don't support that (and the compilers, dynamic linker, - * etc. do not do that). + * The code to switch to a new context is NOT valid for processes + * which play with the space id's. Thus, we have to preserve the + * space and just flush the entire tlb. However, the compilers, + * dynamic linker, etc, do not manipulate space id's, so there + * could be a significant performance benefit in switching contexts + * and not flushing the whole tlb. */ static inline void flush_tlb_mm(struct mm_struct *mm) @@ -45,10 +52,18 @@ static inline void flush_tlb_mm(struct mm_struct *mm) BUG_ON(mm == &init_mm); /* Should never happen */ #if 1 || defined(CONFIG_SMP) + /* Except for very small threads, flushing the whole TLB is + * faster than using __flush_tlb_range. The pdtlb and pitlb + * instructions are very slow because of the TLB broadcast. + * It might be faster to do local range flushes on all CPUs + * on PA 2.0 systems. + */ flush_tlb_all(); #else /* FIXME: currently broken, causing space id and protection ids - * to go out of sync, resulting in faults on userspace accesses. + * to go out of sync, resulting in faults on userspace accesses. + * This approach needs further investigation since running many + * small applications (e.g., GCC testsuite) is faster on HP-UX. */ if (mm) { if (mm->context != 0) @@ -65,22 +80,12 @@ static inline void flush_tlb_page(struct vm_area_struct *vma, { unsigned long flags, sid; - /* For one page, it's not worth testing the split_tlb variable */ - - mb(); sid = vma->vm_mm->context; purge_tlb_start(flags); mtsp(sid, 1); pdtlb(addr); - pitlb(addr); + if (unlikely(split_tlb)) + pitlb(addr); purge_tlb_end(flags); } - -void __flush_tlb_range(unsigned long sid, - unsigned long start, unsigned long end); - -#define flush_tlb_range(vma,start,end) __flush_tlb_range((vma)->vm_mm->context,start,end) - -#define flush_tlb_kernel_range(start, end) __flush_tlb_range(0,start,end) - #endif diff --git a/kernel/arch/parisc/kernel/cache.c b/kernel/arch/parisc/kernel/cache.c index f6448c7c6..cda6dbbe9 100644 --- a/kernel/arch/parisc/kernel/cache.c +++ b/kernel/arch/parisc/kernel/cache.c @@ -342,12 +342,15 @@ EXPORT_SYMBOL(flush_data_cache_local); EXPORT_SYMBOL(flush_kernel_icache_range_asm); #define FLUSH_THRESHOLD 0x80000 /* 0.5MB */ -int parisc_cache_flush_threshold __read_mostly = FLUSH_THRESHOLD; +static unsigned long parisc_cache_flush_threshold __read_mostly = FLUSH_THRESHOLD; + +#define FLUSH_TLB_THRESHOLD (2*1024*1024) /* 2MB initial TLB threshold */ +static unsigned long parisc_tlb_flush_threshold __read_mostly = FLUSH_TLB_THRESHOLD; void __init parisc_setup_cache_timing(void) { unsigned long rangetime, alltime; - unsigned long size; + unsigned long size, start; alltime = mfctl(16); flush_data_cache(); @@ -364,14 +367,43 @@ void __init parisc_setup_cache_timing(void) /* Racy, but if we see an intermediate value, it's ok too... */ parisc_cache_flush_threshold = size * alltime / rangetime; - parisc_cache_flush_threshold = (parisc_cache_flush_threshold + L1_CACHE_BYTES - 1) &~ (L1_CACHE_BYTES - 1); + parisc_cache_flush_threshold = L1_CACHE_ALIGN(parisc_cache_flush_threshold); if (!parisc_cache_flush_threshold) parisc_cache_flush_threshold = FLUSH_THRESHOLD; if (parisc_cache_flush_threshold > cache_info.dc_size) parisc_cache_flush_threshold = cache_info.dc_size; - printk(KERN_INFO "Setting cache flush threshold to %x (%d CPUs online)\n", parisc_cache_flush_threshold, num_online_cpus()); + printk(KERN_INFO "Setting cache flush threshold to %lu kB\n", + parisc_cache_flush_threshold/1024); + + /* calculate TLB flush threshold */ + + alltime = mfctl(16); + flush_tlb_all(); + alltime = mfctl(16) - alltime; + + size = PAGE_SIZE; + start = (unsigned long) _text; + rangetime = mfctl(16); + while (start < (unsigned long) _end) { + flush_tlb_kernel_range(start, start + PAGE_SIZE); + start += PAGE_SIZE; + size += PAGE_SIZE; + } + rangetime = mfctl(16) - rangetime; + + printk(KERN_DEBUG "Whole TLB flush %lu cycles, flushing %lu bytes %lu cycles\n", + alltime, size, rangetime); + + parisc_tlb_flush_threshold = size * alltime / rangetime; + parisc_tlb_flush_threshold *= num_online_cpus(); + parisc_tlb_flush_threshold = PAGE_ALIGN(parisc_tlb_flush_threshold); + if (!parisc_tlb_flush_threshold) + parisc_tlb_flush_threshold = FLUSH_TLB_THRESHOLD; + + printk(KERN_INFO "Setting TLB flush threshold to %lu kB\n", + parisc_tlb_flush_threshold/1024); } extern void purge_kernel_dcache_page_asm(unsigned long); @@ -403,48 +435,45 @@ void copy_user_page(void *vto, void *vfrom, unsigned long vaddr, } EXPORT_SYMBOL(copy_user_page); -void purge_tlb_entries(struct mm_struct *mm, unsigned long addr) -{ - unsigned long flags; - - /* Note: purge_tlb_entries can be called at startup with - no context. */ - - purge_tlb_start(flags); - mtsp(mm->context, 1); - pdtlb(addr); - pitlb(addr); - purge_tlb_end(flags); -} -EXPORT_SYMBOL(purge_tlb_entries); - -void __flush_tlb_range(unsigned long sid, unsigned long start, - unsigned long end) +/* __flush_tlb_range() + * + * returns 1 if all TLBs were flushed. + */ +int __flush_tlb_range(unsigned long sid, unsigned long start, + unsigned long end) { - unsigned long npages; + unsigned long flags, size; - npages = ((end - (start & PAGE_MASK)) + (PAGE_SIZE - 1)) >> PAGE_SHIFT; - if (npages >= 512) /* 2MB of space: arbitrary, should be tuned */ + size = (end - start); + if (size >= parisc_tlb_flush_threshold) { flush_tlb_all(); - else { - unsigned long flags; + return 1; + } + /* Purge TLB entries for small ranges using the pdtlb and + pitlb instructions. These instructions execute locally + but cause a purge request to be broadcast to other TLBs. */ + if (likely(!split_tlb)) { + while (start < end) { + purge_tlb_start(flags); + mtsp(sid, 1); + pdtlb(start); + purge_tlb_end(flags); + start += PAGE_SIZE; + } + return 0; + } + + /* split TLB case */ + while (start < end) { purge_tlb_start(flags); mtsp(sid, 1); - if (split_tlb) { - while (npages--) { - pdtlb(start); - pitlb(start); - start += PAGE_SIZE; - } - } else { - while (npages--) { - pdtlb(start); - start += PAGE_SIZE; - } - } + pdtlb(start); + pitlb(start); purge_tlb_end(flags); + start += PAGE_SIZE; } + return 0; } static void cacheflush_h_tmp_function(void *dummy) diff --git a/kernel/arch/parisc/kernel/entry.S b/kernel/arch/parisc/kernel/entry.S index 75819617f..c5ef4081b 100644 --- a/kernel/arch/parisc/kernel/entry.S +++ b/kernel/arch/parisc/kernel/entry.S @@ -45,7 +45,7 @@ .level 2.0 #endif - .import pa_dbit_lock,data + .import pa_tlb_lock,data /* space_to_prot macro creates a prot id from a space id */ @@ -420,8 +420,8 @@ SHLREG %r9,PxD_VALUE_SHIFT,\pmd extru \va,31-PAGE_SHIFT,ASM_BITS_PER_PTE,\index dep %r0,31,PAGE_SHIFT,\pmd /* clear offset */ - shladd \index,BITS_PER_PTE_ENTRY,\pmd,\pmd - LDREG %r0(\pmd),\pte /* pmd is now pte */ + shladd \index,BITS_PER_PTE_ENTRY,\pmd,\pmd /* pmd is now pte */ + LDREG %r0(\pmd),\pte bb,>=,n \pte,_PAGE_PRESENT_BIT,\fault .endm @@ -453,57 +453,53 @@ L2_ptep \pgd,\pte,\index,\va,\fault .endm - /* Acquire pa_dbit_lock lock. */ - .macro dbit_lock spc,tmp,tmp1 + /* Acquire pa_tlb_lock lock and recheck page is still present. */ + .macro tlb_lock spc,ptp,pte,tmp,tmp1,fault #ifdef CONFIG_SMP cmpib,COND(=),n 0,\spc,2f - load32 PA(pa_dbit_lock),\tmp + load32 PA(pa_tlb_lock),\tmp 1: LDCW 0(\tmp),\tmp1 cmpib,COND(=) 0,\tmp1,1b nop + LDREG 0(\ptp),\pte + bb,<,n \pte,_PAGE_PRESENT_BIT,2f + b \fault + stw \spc,0(\tmp) 2: #endif .endm - /* Release pa_dbit_lock lock without reloading lock address. */ - .macro dbit_unlock0 spc,tmp + /* Release pa_tlb_lock lock without reloading lock address. */ + .macro tlb_unlock0 spc,tmp #ifdef CONFIG_SMP or,COND(=) %r0,\spc,%r0 stw \spc,0(\tmp) #endif .endm - /* Release pa_dbit_lock lock. */ - .macro dbit_unlock1 spc,tmp + /* Release pa_tlb_lock lock. */ + .macro tlb_unlock1 spc,tmp #ifdef CONFIG_SMP - load32 PA(pa_dbit_lock),\tmp - dbit_unlock0 \spc,\tmp + load32 PA(pa_tlb_lock),\tmp + tlb_unlock0 \spc,\tmp #endif .endm /* Set the _PAGE_ACCESSED bit of the PTE. Be clever and * don't needlessly dirty the cache line if it was already set */ - .macro update_ptep spc,ptep,pte,tmp,tmp1 -#ifdef CONFIG_SMP - or,COND(=) %r0,\spc,%r0 - LDREG 0(\ptep),\pte -#endif + .macro update_accessed ptp,pte,tmp,tmp1 ldi _PAGE_ACCESSED,\tmp1 or \tmp1,\pte,\tmp and,COND(<>) \tmp1,\pte,%r0 - STREG \tmp,0(\ptep) + STREG \tmp,0(\ptp) .endm /* Set the dirty bit (and accessed bit). No need to be * clever, this is only used from the dirty fault */ - .macro update_dirty spc,ptep,pte,tmp -#ifdef CONFIG_SMP - or,COND(=) %r0,\spc,%r0 - LDREG 0(\ptep),\pte -#endif + .macro update_dirty ptp,pte,tmp ldi _PAGE_ACCESSED|_PAGE_DIRTY,\tmp or \tmp,\pte,\pte - STREG \pte,0(\ptep) + STREG \pte,0(\ptp) .endm /* bitshift difference between a PFN (based on kernel's PAGE_SIZE) @@ -1148,14 +1144,14 @@ dtlb_miss_20w: L3_ptep ptp,pte,t0,va,dtlb_check_alias_20w - dbit_lock spc,t0,t1 - update_ptep spc,ptp,pte,t0,t1 + tlb_lock spc,ptp,pte,t0,t1,dtlb_check_alias_20w + update_accessed ptp,pte,t0,t1 make_insert_tlb spc,pte,prot idtlbt pte,prot - dbit_unlock1 spc,t0 + tlb_unlock1 spc,t0 rfir nop @@ -1174,14 +1170,14 @@ nadtlb_miss_20w: L3_ptep ptp,pte,t0,va,nadtlb_check_alias_20w - dbit_lock spc,t0,t1 - update_ptep spc,ptp,pte,t0,t1 + tlb_lock spc,ptp,pte,t0,t1,nadtlb_check_alias_20w + update_accessed ptp,pte,t0,t1 make_insert_tlb spc,pte,prot idtlbt pte,prot - dbit_unlock1 spc,t0 + tlb_unlock1 spc,t0 rfir nop @@ -1202,20 +1198,20 @@ dtlb_miss_11: L2_ptep ptp,pte,t0,va,dtlb_check_alias_11 - dbit_lock spc,t0,t1 - update_ptep spc,ptp,pte,t0,t1 + tlb_lock spc,ptp,pte,t0,t1,dtlb_check_alias_11 + update_accessed ptp,pte,t0,t1 make_insert_tlb_11 spc,pte,prot - mfsp %sr1,t0 /* Save sr1 so we can use it in tlb inserts */ + mfsp %sr1,t1 /* Save sr1 so we can use it in tlb inserts */ mtsp spc,%sr1 idtlba pte,(%sr1,va) idtlbp prot,(%sr1,va) - mtsp t0, %sr1 /* Restore sr1 */ - dbit_unlock1 spc,t0 + mtsp t1, %sr1 /* Restore sr1 */ + tlb_unlock1 spc,t0 rfir nop @@ -1235,21 +1231,20 @@ nadtlb_miss_11: L2_ptep ptp,pte,t0,va,nadtlb_check_alias_11 - dbit_lock spc,t0,t1 - update_ptep spc,ptp,pte,t0,t1 + tlb_lock spc,ptp,pte,t0,t1,nadtlb_check_alias_11 + update_accessed ptp,pte,t0,t1 make_insert_tlb_11 spc,pte,prot - - mfsp %sr1,t0 /* Save sr1 so we can use it in tlb inserts */ + mfsp %sr1,t1 /* Save sr1 so we can use it in tlb inserts */ mtsp spc,%sr1 idtlba pte,(%sr1,va) idtlbp prot,(%sr1,va) - mtsp t0, %sr1 /* Restore sr1 */ - dbit_unlock1 spc,t0 + mtsp t1, %sr1 /* Restore sr1 */ + tlb_unlock1 spc,t0 rfir nop @@ -1269,16 +1264,16 @@ dtlb_miss_20: L2_ptep ptp,pte,t0,va,dtlb_check_alias_20 - dbit_lock spc,t0,t1 - update_ptep spc,ptp,pte,t0,t1 + tlb_lock spc,ptp,pte,t0,t1,dtlb_check_alias_20 + update_accessed ptp,pte,t0,t1 make_insert_tlb spc,pte,prot - f_extend pte,t0 + f_extend pte,t1 idtlbt pte,prot - dbit_unlock1 spc,t0 + tlb_unlock1 spc,t0 rfir nop @@ -1297,16 +1292,16 @@ nadtlb_miss_20: L2_ptep ptp,pte,t0,va,nadtlb_check_alias_20 - dbit_lock spc,t0,t1 - update_ptep spc,ptp,pte,t0,t1 + tlb_lock spc,ptp,pte,t0,t1,nadtlb_check_alias_20 + update_accessed ptp,pte,t0,t1 make_insert_tlb spc,pte,prot - f_extend pte,t0 + f_extend pte,t1 - idtlbt pte,prot - dbit_unlock1 spc,t0 + idtlbt pte,prot + tlb_unlock1 spc,t0 rfir nop @@ -1406,14 +1401,14 @@ itlb_miss_20w: L3_ptep ptp,pte,t0,va,itlb_fault - dbit_lock spc,t0,t1 - update_ptep spc,ptp,pte,t0,t1 + tlb_lock spc,ptp,pte,t0,t1,itlb_fault + update_accessed ptp,pte,t0,t1 make_insert_tlb spc,pte,prot iitlbt pte,prot - dbit_unlock1 spc,t0 + tlb_unlock1 spc,t0 rfir nop @@ -1430,14 +1425,14 @@ naitlb_miss_20w: L3_ptep ptp,pte,t0,va,naitlb_check_alias_20w - dbit_lock spc,t0,t1 - update_ptep spc,ptp,pte,t0,t1 + tlb_lock spc,ptp,pte,t0,t1,naitlb_check_alias_20w + update_accessed ptp,pte,t0,t1 make_insert_tlb spc,pte,prot iitlbt pte,prot - dbit_unlock1 spc,t0 + tlb_unlock1 spc,t0 rfir nop @@ -1458,20 +1453,20 @@ itlb_miss_11: L2_ptep ptp,pte,t0,va,itlb_fault - dbit_lock spc,t0,t1 - update_ptep spc,ptp,pte,t0,t1 + tlb_lock spc,ptp,pte,t0,t1,itlb_fault + update_accessed ptp,pte,t0,t1 make_insert_tlb_11 spc,pte,prot - mfsp %sr1,t0 /* Save sr1 so we can use it in tlb inserts */ + mfsp %sr1,t1 /* Save sr1 so we can use it in tlb inserts */ mtsp spc,%sr1 iitlba pte,(%sr1,va) iitlbp prot,(%sr1,va) - mtsp t0, %sr1 /* Restore sr1 */ - dbit_unlock1 spc,t0 + mtsp t1, %sr1 /* Restore sr1 */ + tlb_unlock1 spc,t0 rfir nop @@ -1482,20 +1477,20 @@ naitlb_miss_11: L2_ptep ptp,pte,t0,va,naitlb_check_alias_11 - dbit_lock spc,t0,t1 - update_ptep spc,ptp,pte,t0,t1 + tlb_lock spc,ptp,pte,t0,t1,naitlb_check_alias_11 + update_accessed ptp,pte,t0,t1 make_insert_tlb_11 spc,pte,prot - mfsp %sr1,t0 /* Save sr1 so we can use it in tlb inserts */ + mfsp %sr1,t1 /* Save sr1 so we can use it in tlb inserts */ mtsp spc,%sr1 iitlba pte,(%sr1,va) iitlbp prot,(%sr1,va) - mtsp t0, %sr1 /* Restore sr1 */ - dbit_unlock1 spc,t0 + mtsp t1, %sr1 /* Restore sr1 */ + tlb_unlock1 spc,t0 rfir nop @@ -1516,16 +1511,16 @@ itlb_miss_20: L2_ptep ptp,pte,t0,va,itlb_fault - dbit_lock spc,t0,t1 - update_ptep spc,ptp,pte,t0,t1 + tlb_lock spc,ptp,pte,t0,t1,itlb_fault + update_accessed ptp,pte,t0,t1 make_insert_tlb spc,pte,prot - f_extend pte,t0 + f_extend pte,t1 iitlbt pte,prot - dbit_unlock1 spc,t0 + tlb_unlock1 spc,t0 rfir nop @@ -1536,16 +1531,16 @@ naitlb_miss_20: L2_ptep ptp,pte,t0,va,naitlb_check_alias_20 - dbit_lock spc,t0,t1 - update_ptep spc,ptp,pte,t0,t1 + tlb_lock spc,ptp,pte,t0,t1,naitlb_check_alias_20 + update_accessed ptp,pte,t0,t1 make_insert_tlb spc,pte,prot - f_extend pte,t0 + f_extend pte,t1 iitlbt pte,prot - dbit_unlock1 spc,t0 + tlb_unlock1 spc,t0 rfir nop @@ -1568,14 +1563,14 @@ dbit_trap_20w: L3_ptep ptp,pte,t0,va,dbit_fault - dbit_lock spc,t0,t1 - update_dirty spc,ptp,pte,t1 + tlb_lock spc,ptp,pte,t0,t1,dbit_fault + update_dirty ptp,pte,t1 make_insert_tlb spc,pte,prot idtlbt pte,prot - dbit_unlock0 spc,t0 + tlb_unlock0 spc,t0 rfir nop #else @@ -1588,8 +1583,8 @@ dbit_trap_11: L2_ptep ptp,pte,t0,va,dbit_fault - dbit_lock spc,t0,t1 - update_dirty spc,ptp,pte,t1 + tlb_lock spc,ptp,pte,t0,t1,dbit_fault + update_dirty ptp,pte,t1 make_insert_tlb_11 spc,pte,prot @@ -1600,8 +1595,8 @@ dbit_trap_11: idtlbp prot,(%sr1,va) mtsp t1, %sr1 /* Restore sr1 */ - dbit_unlock0 spc,t0 + tlb_unlock0 spc,t0 rfir nop @@ -1612,16 +1607,16 @@ dbit_trap_20: L2_ptep ptp,pte,t0,va,dbit_fault - dbit_lock spc,t0,t1 - update_dirty spc,ptp,pte,t1 + tlb_lock spc,ptp,pte,t0,t1,dbit_fault + update_dirty ptp,pte,t1 make_insert_tlb spc,pte,prot f_extend pte,t1 - idtlbt pte,prot - dbit_unlock0 spc,t0 + idtlbt pte,prot + tlb_unlock0 spc,t0 rfir nop #endif diff --git a/kernel/arch/parisc/kernel/traps.c b/kernel/arch/parisc/kernel/traps.c index 6548fd1d2..b99b39f1d 100644 --- a/kernel/arch/parisc/kernel/traps.c +++ b/kernel/arch/parisc/kernel/traps.c @@ -43,10 +43,6 @@ #include "../math-emu/math-emu.h" /* for handle_fpe() */ -#if defined(CONFIG_SMP) || defined(CONFIG_DEBUG_SPINLOCK) -DEFINE_SPINLOCK(pa_dbit_lock); -#endif - static void parisc_show_stack(struct task_struct *task, unsigned long *sp, struct pt_regs *regs); diff --git a/kernel/arch/powerpc/kernel/idle_power7.S b/kernel/arch/powerpc/kernel/idle_power7.S index ccde8f084..112ccf497 100644 --- a/kernel/arch/powerpc/kernel/idle_power7.S +++ b/kernel/arch/powerpc/kernel/idle_power7.S @@ -52,6 +52,22 @@ .text /* + * Used by threads when the lock bit of core_idle_state is set. + * Threads will spin in HMT_LOW until the lock bit is cleared. + * r14 - pointer to core_idle_state + * r15 - used to load contents of core_idle_state + */ + +core_idle_lock_held: + HMT_LOW +3: lwz r15,0(r14) + andi. r15,r15,PNV_CORE_IDLE_LOCK_BIT + bne 3b + HMT_MEDIUM + lwarx r15,0,r14 + blr + +/* * Pass requested state in r3: * r3 - PNV_THREAD_NAP/SLEEP/WINKLE * @@ -150,6 +166,10 @@ power7_enter_nap_mode: ld r14,PACA_CORE_IDLE_STATE_PTR(r13) lwarx_loop1: lwarx r15,0,r14 + + andi. r9,r15,PNV_CORE_IDLE_LOCK_BIT + bnel core_idle_lock_held + andc r15,r15,r7 /* Clear thread bit */ andi. r15,r15,PNV_CORE_IDLE_THREAD_BITS @@ -294,7 +314,7 @@ lwarx_loop2: * workaround undo code or resyncing timebase or restoring context * In either case loop until the lock bit is cleared. */ - bne core_idle_lock_held + bnel core_idle_lock_held cmpwi cr2,r15,0 lbz r4,PACA_SUBCORE_SIBLING_MASK(r13) @@ -319,15 +339,6 @@ lwarx_loop2: isync b common_exit -core_idle_lock_held: - HMT_LOW -core_idle_lock_loop: - lwz r15,0(14) - andi. r9,r15,PNV_CORE_IDLE_LOCK_BIT - bne core_idle_lock_loop - HMT_MEDIUM - b lwarx_loop2 - first_thread_in_subcore: /* First thread in subcore to wakeup */ ori r15,r15,PNV_CORE_IDLE_LOCK_BIT diff --git a/kernel/arch/powerpc/kernel/signal_32.c b/kernel/arch/powerpc/kernel/signal_32.c index d3a831ac0..da50e0c9c 100644 --- a/kernel/arch/powerpc/kernel/signal_32.c +++ b/kernel/arch/powerpc/kernel/signal_32.c @@ -966,8 +966,6 @@ int copy_siginfo_to_user32(struct compat_siginfo __user *d, const siginfo_t *s) int copy_siginfo_from_user32(siginfo_t *to, struct compat_siginfo __user *from) { - memset(to, 0, sizeof *to); - if (copy_from_user(to, from, 3*sizeof(int)) || copy_from_user(to->_sifields._pad, from->_sifields._pad, SI_PAD_SIZE32)) diff --git a/kernel/arch/s390/include/asm/ctl_reg.h b/kernel/arch/s390/include/asm/ctl_reg.h index cfad7fca0..d7697ab80 100644 --- a/kernel/arch/s390/include/asm/ctl_reg.h +++ b/kernel/arch/s390/include/asm/ctl_reg.h @@ -57,7 +57,10 @@ union ctlreg0 { unsigned long lap : 1; /* Low-address-protection control */ unsigned long : 4; unsigned long edat : 1; /* Enhanced-DAT-enablement control */ - unsigned long : 23; + unsigned long : 4; + unsigned long afp : 1; /* AFP-register control */ + unsigned long vx : 1; /* Vector enablement control */ + unsigned long : 17; }; }; diff --git a/kernel/arch/s390/kernel/cache.c b/kernel/arch/s390/kernel/cache.c index bff5e3b6d..8ba32436e 100644 --- a/kernel/arch/s390/kernel/cache.c +++ b/kernel/arch/s390/kernel/cache.c @@ -138,6 +138,8 @@ int init_cache_level(unsigned int cpu) union cache_topology ct; enum cache_type ctype; + if (!test_facility(34)) + return -EOPNOTSUPP; if (!this_cpu_ci) return -EINVAL; ct.raw = ecag(EXTRACT_TOPOLOGY, 0, 0); diff --git a/kernel/arch/s390/kernel/nmi.c b/kernel/arch/s390/kernel/nmi.c index 505c17c0a..56b550893 100644 --- a/kernel/arch/s390/kernel/nmi.c +++ b/kernel/arch/s390/kernel/nmi.c @@ -21,6 +21,7 @@ #include <asm/nmi.h> #include <asm/crw.h> #include <asm/switch_to.h> +#include <asm/ctl_reg.h> struct mcck_struct { int kill_task; @@ -129,26 +130,30 @@ static int notrace s390_revalidate_registers(struct mci *mci) } else asm volatile("lfpc 0(%0)" : : "a" (fpt_creg_save_area)); - asm volatile( - " ld 0,0(%0)\n" - " ld 1,8(%0)\n" - " ld 2,16(%0)\n" - " ld 3,24(%0)\n" - " ld 4,32(%0)\n" - " ld 5,40(%0)\n" - " ld 6,48(%0)\n" - " ld 7,56(%0)\n" - " ld 8,64(%0)\n" - " ld 9,72(%0)\n" - " ld 10,80(%0)\n" - " ld 11,88(%0)\n" - " ld 12,96(%0)\n" - " ld 13,104(%0)\n" - " ld 14,112(%0)\n" - " ld 15,120(%0)\n" - : : "a" (fpt_save_area)); - /* Revalidate vector registers */ - if (MACHINE_HAS_VX && current->thread.vxrs) { + if (!MACHINE_HAS_VX) { + /* Revalidate floating point registers */ + asm volatile( + " ld 0,0(%0)\n" + " ld 1,8(%0)\n" + " ld 2,16(%0)\n" + " ld 3,24(%0)\n" + " ld 4,32(%0)\n" + " ld 5,40(%0)\n" + " ld 6,48(%0)\n" + " ld 7,56(%0)\n" + " ld 8,64(%0)\n" + " ld 9,72(%0)\n" + " ld 10,80(%0)\n" + " ld 11,88(%0)\n" + " ld 12,96(%0)\n" + " ld 13,104(%0)\n" + " ld 14,112(%0)\n" + " ld 15,120(%0)\n" + : : "a" (fpt_save_area)); + } else { + /* Revalidate vector registers */ + union ctlreg0 cr0; + if (!mci->vr) { /* * Vector registers can't be restored and therefore @@ -156,8 +161,12 @@ static int notrace s390_revalidate_registers(struct mci *mci) */ kill_task = 1; } + cr0.val = S390_lowcore.cregs_save_area[0]; + cr0.afp = cr0.vx = 1; + __ctl_load(cr0.val, 0, 0); restore_vx_regs((__vector128 *) - S390_lowcore.vector_save_area_addr); + &S390_lowcore.vector_save_area); + __ctl_load(S390_lowcore.cregs_save_area[0], 0, 0); } /* Revalidate access registers */ asm volatile( diff --git a/kernel/arch/s390/kernel/process.c b/kernel/arch/s390/kernel/process.c index dc5edc29b..8f587d871 100644 --- a/kernel/arch/s390/kernel/process.c +++ b/kernel/arch/s390/kernel/process.c @@ -163,7 +163,7 @@ int copy_thread(unsigned long clone_flags, unsigned long new_stackp, asmlinkage void execve_tail(void) { current->thread.fp_regs.fpc = 0; - asm volatile("sfpc %0,%0" : : "d" (0)); + asm volatile("sfpc %0" : : "d" (0)); } /* diff --git a/kernel/arch/s390/kernel/sclp.S b/kernel/arch/s390/kernel/sclp.S index 43c3169ea..ada0c07fe 100644 --- a/kernel/arch/s390/kernel/sclp.S +++ b/kernel/arch/s390/kernel/sclp.S @@ -270,6 +270,8 @@ ENTRY(_sclp_print_early) jno .Lesa2 ahi %r15,-80 stmh %r6,%r15,96(%r15) # store upper register halves + basr %r13,0 + lmh %r0,%r15,.Lzeroes-.(%r13) # clear upper register halves .Lesa2: lr %r10,%r2 # save string pointer lhi %r2,0 @@ -291,6 +293,8 @@ ENTRY(_sclp_print_early) .Lesa3: lm %r6,%r15,120(%r15) # restore registers br %r14 +.Lzeroes: + .fill 64,4,0 .LwritedataS4: .long 0x00760005 # SCLP command for write data diff --git a/kernel/arch/s390/net/bpf_jit_comp.c b/kernel/arch/s390/net/bpf_jit_comp.c index 9afb9d602..dc2d7aa56 100644 --- a/kernel/arch/s390/net/bpf_jit_comp.c +++ b/kernel/arch/s390/net/bpf_jit_comp.c @@ -415,13 +415,13 @@ static void bpf_jit_prologue(struct bpf_jit *jit) EMIT6_DISP_LH(0xe3000000, 0x0004, REG_SKB_DATA, REG_0, BPF_REG_1, offsetof(struct sk_buff, data)); } - /* BPF compatibility: clear A (%b7) and X (%b8) registers */ - if (REG_SEEN(BPF_REG_7)) - /* lghi %b7,0 */ - EMIT4_IMM(0xa7090000, BPF_REG_7, 0); - if (REG_SEEN(BPF_REG_8)) - /* lghi %b8,0 */ - EMIT4_IMM(0xa7090000, BPF_REG_8, 0); + /* BPF compatibility: clear A (%b0) and X (%b7) registers */ + if (REG_SEEN(BPF_REG_A)) + /* lghi %ba,0 */ + EMIT4_IMM(0xa7090000, BPF_REG_A, 0); + if (REG_SEEN(BPF_REG_X)) + /* lghi %bx,0 */ + EMIT4_IMM(0xa7090000, BPF_REG_X, 0); } /* diff --git a/kernel/arch/sparc/include/asm/visasm.h b/kernel/arch/sparc/include/asm/visasm.h index 1f0aa2024..6424249d5 100644 --- a/kernel/arch/sparc/include/asm/visasm.h +++ b/kernel/arch/sparc/include/asm/visasm.h @@ -28,16 +28,10 @@ * Must preserve %o5 between VISEntryHalf and VISExitHalf */ #define VISEntryHalf \ - rd %fprs, %o5; \ - andcc %o5, FPRS_FEF, %g0; \ - be,pt %icc, 297f; \ - sethi %hi(298f), %g7; \ - sethi %hi(VISenterhalf), %g1; \ - jmpl %g1 + %lo(VISenterhalf), %g0; \ - or %g7, %lo(298f), %g7; \ - clr %o5; \ -297: wr %o5, FPRS_FEF, %fprs; \ -298: + VISEntry + +#define VISExitHalf \ + VISExit #define VISEntryHalfFast(fail_label) \ rd %fprs, %o5; \ @@ -47,7 +41,7 @@ ba,a,pt %xcc, fail_label; \ 297: wr %o5, FPRS_FEF, %fprs; -#define VISExitHalf \ +#define VISExitHalfFast \ wr %o5, 0, %fprs; #ifndef __ASSEMBLY__ diff --git a/kernel/arch/sparc/lib/NG4memcpy.S b/kernel/arch/sparc/lib/NG4memcpy.S index 140527a20..83aeeb1df 100644 --- a/kernel/arch/sparc/lib/NG4memcpy.S +++ b/kernel/arch/sparc/lib/NG4memcpy.S @@ -240,8 +240,11 @@ FUNC_NAME: /* %o0=dst, %o1=src, %o2=len */ add %o0, 0x40, %o0 bne,pt %icc, 1b LOAD(prefetch, %g1 + 0x200, #n_reads_strong) +#ifdef NON_USER_COPY + VISExitHalfFast +#else VISExitHalf - +#endif brz,pn %o2, .Lexit cmp %o2, 19 ble,pn %icc, .Lsmall_unaligned diff --git a/kernel/arch/sparc/lib/VISsave.S b/kernel/arch/sparc/lib/VISsave.S index b320ae9e2..a063d8433 100644 --- a/kernel/arch/sparc/lib/VISsave.S +++ b/kernel/arch/sparc/lib/VISsave.S @@ -44,9 +44,8 @@ vis1: ldub [%g6 + TI_FPSAVED], %g3 stx %g3, [%g6 + TI_GSR] 2: add %g6, %g1, %g3 - cmp %o5, FPRS_DU - be,pn %icc, 6f - sll %g1, 3, %g1 + mov FPRS_DU | FPRS_DL | FPRS_FEF, %o5 + sll %g1, 3, %g1 stb %o5, [%g3 + TI_FPSAVED] rd %gsr, %g2 add %g6, %g1, %g3 @@ -80,65 +79,3 @@ vis1: ldub [%g6 + TI_FPSAVED], %g3 .align 32 80: jmpl %g7 + %g0, %g0 nop - -6: ldub [%g3 + TI_FPSAVED], %o5 - or %o5, FPRS_DU, %o5 - add %g6, TI_FPREGS+0x80, %g2 - stb %o5, [%g3 + TI_FPSAVED] - - sll %g1, 5, %g1 - add %g6, TI_FPREGS+0xc0, %g3 - wr %g0, FPRS_FEF, %fprs - membar #Sync - stda %f32, [%g2 + %g1] ASI_BLK_P - stda %f48, [%g3 + %g1] ASI_BLK_P - membar #Sync - ba,pt %xcc, 80f - nop - - .align 32 -80: jmpl %g7 + %g0, %g0 - nop - - .align 32 -VISenterhalf: - ldub [%g6 + TI_FPDEPTH], %g1 - brnz,a,pn %g1, 1f - cmp %g1, 1 - stb %g0, [%g6 + TI_FPSAVED] - stx %fsr, [%g6 + TI_XFSR] - clr %o5 - jmpl %g7 + %g0, %g0 - wr %g0, FPRS_FEF, %fprs - -1: bne,pn %icc, 2f - srl %g1, 1, %g1 - ba,pt %xcc, vis1 - sub %g7, 8, %g7 -2: addcc %g6, %g1, %g3 - sll %g1, 3, %g1 - andn %o5, FPRS_DU, %g2 - stb %g2, [%g3 + TI_FPSAVED] - - rd %gsr, %g2 - add %g6, %g1, %g3 - stx %g2, [%g3 + TI_GSR] - add %g6, %g1, %g2 - stx %fsr, [%g2 + TI_XFSR] - sll %g1, 5, %g1 -3: andcc %o5, FPRS_DL, %g0 - be,pn %icc, 4f - add %g6, TI_FPREGS, %g2 - - add %g6, TI_FPREGS+0x40, %g3 - membar #Sync - stda %f0, [%g2 + %g1] ASI_BLK_P - stda %f16, [%g3 + %g1] ASI_BLK_P - membar #Sync - ba,pt %xcc, 4f - nop - - .align 32 -4: and %o5, FPRS_DU, %o5 - jmpl %g7 + %g0, %g0 - wr %o5, FPRS_FEF, %fprs diff --git a/kernel/arch/sparc/lib/ksyms.c b/kernel/arch/sparc/lib/ksyms.c index 1d649a956..8069ce12f 100644 --- a/kernel/arch/sparc/lib/ksyms.c +++ b/kernel/arch/sparc/lib/ksyms.c @@ -135,10 +135,6 @@ EXPORT_SYMBOL(copy_user_page); void VISenter(void); EXPORT_SYMBOL(VISenter); -/* CRYPTO code needs this */ -void VISenterhalf(void); -EXPORT_SYMBOL(VISenterhalf); - extern void xor_vis_2(unsigned long, unsigned long *, unsigned long *); extern void xor_vis_3(unsigned long, unsigned long *, unsigned long *, unsigned long *); diff --git a/kernel/arch/tile/kernel/compat_signal.c b/kernel/arch/tile/kernel/compat_signal.c index e8c2c0414..c667e104a 100644 --- a/kernel/arch/tile/kernel/compat_signal.c +++ b/kernel/arch/tile/kernel/compat_signal.c @@ -113,8 +113,6 @@ int copy_siginfo_from_user32(siginfo_t *to, struct compat_siginfo __user *from) if (!access_ok(VERIFY_READ, from, sizeof(struct compat_siginfo))) return -EFAULT; - memset(to, 0, sizeof(*to)); - err = __get_user(to->si_signo, &from->si_signo); err |= __get_user(to->si_errno, &from->si_errno); err |= __get_user(to->si_code, &from->si_code); diff --git a/kernel/arch/tile/kernel/setup.c b/kernel/arch/tile/kernel/setup.c index d366675e4..396b5c96e 100644 --- a/kernel/arch/tile/kernel/setup.c +++ b/kernel/arch/tile/kernel/setup.c @@ -1139,7 +1139,7 @@ static void __init load_hv_initrd(void) void __init free_initrd_mem(unsigned long begin, unsigned long end) { - free_bootmem(__pa(begin), end - begin); + free_bootmem_late(__pa(begin), end - begin); } static int __init setup_initrd(char *str) diff --git a/kernel/arch/x86/boot/compressed/eboot.c b/kernel/arch/x86/boot/compressed/eboot.c index 48304b89b..0cdc154a2 100644 --- a/kernel/arch/x86/boot/compressed/eboot.c +++ b/kernel/arch/x86/boot/compressed/eboot.c @@ -1193,6 +1193,10 @@ static efi_status_t setup_e820(struct boot_params *params, unsigned int e820_type = 0; unsigned long m = efi->efi_memmap; +#ifdef CONFIG_X86_64 + m |= (u64)efi->efi_memmap_hi << 32; +#endif + d = (efi_memory_desc_t *)(m + (i * efi->efi_memdesc_size)); switch (d->type) { case EFI_RESERVED_TYPE: diff --git a/kernel/arch/x86/include/asm/kasan.h b/kernel/arch/x86/include/asm/kasan.h index 8b22422fb..74a2a8dc9 100644 --- a/kernel/arch/x86/include/asm/kasan.h +++ b/kernel/arch/x86/include/asm/kasan.h @@ -14,15 +14,11 @@ #ifndef __ASSEMBLY__ -extern pte_t kasan_zero_pte[]; -extern pte_t kasan_zero_pmd[]; -extern pte_t kasan_zero_pud[]; - #ifdef CONFIG_KASAN -void __init kasan_map_early_shadow(pgd_t *pgd); +void __init kasan_early_init(void); void __init kasan_init(void); #else -static inline void kasan_map_early_shadow(pgd_t *pgd) { } +static inline void kasan_early_init(void) { } static inline void kasan_init(void) { } #endif diff --git a/kernel/arch/x86/include/asm/mmu_context.h b/kernel/arch/x86/include/asm/mmu_context.h index 883f6b933..e997f70f8 100644 --- a/kernel/arch/x86/include/asm/mmu_context.h +++ b/kernel/arch/x86/include/asm/mmu_context.h @@ -23,7 +23,7 @@ extern struct static_key rdpmc_always_available; static inline void load_mm_cr4(struct mm_struct *mm) { - if (static_key_true(&rdpmc_always_available) || + if (static_key_false(&rdpmc_always_available) || atomic_read(&mm->context.perf_rdpmc_allowed)) cr4_set_bits(X86_CR4_PCE); else diff --git a/kernel/arch/x86/include/asm/sigcontext.h b/kernel/arch/x86/include/asm/sigcontext.h index 6fe6b182c..9dfce4e04 100644 --- a/kernel/arch/x86/include/asm/sigcontext.h +++ b/kernel/arch/x86/include/asm/sigcontext.h @@ -57,9 +57,9 @@ struct sigcontext { unsigned long ip; unsigned long flags; unsigned short cs; - unsigned short __pad2; /* Was called gs, but was always zero. */ - unsigned short __pad1; /* Was called fs, but was always zero. */ - unsigned short ss; + unsigned short gs; + unsigned short fs; + unsigned short __pad0; unsigned long err; unsigned long trapno; unsigned long oldmask; diff --git a/kernel/arch/x86/include/uapi/asm/sigcontext.h b/kernel/arch/x86/include/uapi/asm/sigcontext.h index 16dc4e8a2..d8b9f9081 100644 --- a/kernel/arch/x86/include/uapi/asm/sigcontext.h +++ b/kernel/arch/x86/include/uapi/asm/sigcontext.h @@ -177,24 +177,9 @@ struct sigcontext { __u64 rip; __u64 eflags; /* RFLAGS */ __u16 cs; - - /* - * Prior to 2.5.64 ("[PATCH] x86-64 updates for 2.5.64-bk3"), - * Linux saved and restored fs and gs in these slots. This - * was counterproductive, as fsbase and gsbase were never - * saved, so arch_prctl was presumably unreliable. - * - * If these slots are ever needed for any other purpose, there - * is some risk that very old 64-bit binaries could get - * confused. I doubt that many such binaries still work, - * though, since the same patch in 2.5.64 also removed the - * 64-bit set_thread_area syscall, so it appears that there is - * no TLS API that works in both pre- and post-2.5.64 kernels. - */ - __u16 __pad2; /* Was gs. */ - __u16 __pad1; /* Was fs. */ - - __u16 ss; + __u16 gs; + __u16 fs; + __u16 __pad0; __u64 err; __u64 trapno; __u64 oldmask; diff --git a/kernel/arch/x86/kernel/apic/apic.c b/kernel/arch/x86/kernel/apic/apic.c index dcb52850a..cde732c1b 100644 --- a/kernel/arch/x86/kernel/apic/apic.c +++ b/kernel/arch/x86/kernel/apic/apic.c @@ -1424,7 +1424,7 @@ static inline void __x2apic_disable(void) { u64 msr; - if (cpu_has_apic) + if (!cpu_has_apic) return; rdmsrl(MSR_IA32_APICBASE, msr); @@ -1483,10 +1483,13 @@ void x2apic_setup(void) static __init void x2apic_disable(void) { - u32 x2apic_id; + u32 x2apic_id, state = x2apic_state; - if (x2apic_state != X2APIC_ON) - goto out; + x2apic_mode = 0; + x2apic_state = X2APIC_DISABLED; + + if (state != X2APIC_ON) + return; x2apic_id = read_apic_id(); if (x2apic_id >= 255) @@ -1494,9 +1497,6 @@ static __init void x2apic_disable(void) __x2apic_disable(); register_lapic_address(mp_lapic_addr); -out: - x2apic_state = X2APIC_DISABLED; - x2apic_mode = 0; } static __init void x2apic_enable(void) diff --git a/kernel/arch/x86/kernel/cpu/perf_event_intel_cqm.c b/kernel/arch/x86/kernel/cpu/perf_event_intel_cqm.c index e4d1b8b73..cb77b11bc 100644 --- a/kernel/arch/x86/kernel/cpu/perf_event_intel_cqm.c +++ b/kernel/arch/x86/kernel/cpu/perf_event_intel_cqm.c @@ -934,6 +934,14 @@ static u64 intel_cqm_event_count(struct perf_event *event) return 0; /* + * Getting up-to-date values requires an SMP IPI which is not + * possible if we're being called in interrupt context. Return + * the cached values instead. + */ + if (unlikely(in_interrupt())) + goto out; + + /* * Notice that we don't perform the reading of an RMID * atomically, because we can't hold a spin lock across the * IPIs. diff --git a/kernel/arch/x86/kernel/dumpstack_32.c b/kernel/arch/x86/kernel/dumpstack_32.c index 464ffd69b..00db1aad1 100644 --- a/kernel/arch/x86/kernel/dumpstack_32.c +++ b/kernel/arch/x86/kernel/dumpstack_32.c @@ -42,7 +42,7 @@ void dump_trace(struct task_struct *task, struct pt_regs *regs, unsigned long *stack, unsigned long bp, const struct stacktrace_ops *ops, void *data) { - const unsigned cpu = get_cpu(); + const unsigned cpu = get_cpu_light(); int graph = 0; u32 *prev_esp; @@ -86,7 +86,7 @@ void dump_trace(struct task_struct *task, struct pt_regs *regs, break; touch_nmi_watchdog(); } - put_cpu(); + put_cpu_light(); } EXPORT_SYMBOL(dump_trace); diff --git a/kernel/arch/x86/kernel/dumpstack_64.c b/kernel/arch/x86/kernel/dumpstack_64.c index 5f1c6266e..c331e3fef 100644 --- a/kernel/arch/x86/kernel/dumpstack_64.c +++ b/kernel/arch/x86/kernel/dumpstack_64.c @@ -152,7 +152,7 @@ void dump_trace(struct task_struct *task, struct pt_regs *regs, unsigned long *stack, unsigned long bp, const struct stacktrace_ops *ops, void *data) { - const unsigned cpu = get_cpu(); + const unsigned cpu = get_cpu_light(); struct thread_info *tinfo; unsigned long *irq_stack = (unsigned long *)per_cpu(irq_stack_ptr, cpu); unsigned long dummy; @@ -241,7 +241,7 @@ void dump_trace(struct task_struct *task, struct pt_regs *regs, * This handles the process stack: */ bp = ops->walk_stack(tinfo, stack, bp, ops, data, NULL, &graph); - put_cpu(); + put_cpu_light(); } EXPORT_SYMBOL(dump_trace); @@ -255,7 +255,7 @@ show_stack_log_lvl(struct task_struct *task, struct pt_regs *regs, int cpu; int i; - preempt_disable(); + migrate_disable(); cpu = smp_processor_id(); irq_stack_end = (unsigned long *)(per_cpu(irq_stack_ptr, cpu)); @@ -291,7 +291,7 @@ show_stack_log_lvl(struct task_struct *task, struct pt_regs *regs, pr_cont(" %016lx", *stack++); touch_nmi_watchdog(); } - preempt_enable(); + migrate_enable(); pr_cont("\n"); show_trace_log_lvl(task, regs, sp, bp, log_lvl); diff --git a/kernel/arch/x86/kernel/entry_64.S b/kernel/arch/x86/kernel/entry_64.S index 9bf907020..8a3445bdf 100644 --- a/kernel/arch/x86/kernel/entry_64.S +++ b/kernel/arch/x86/kernel/entry_64.S @@ -809,8 +809,6 @@ do_preempt_schedule_irq: restore_c_regs_and_iret: RESTORE_C_REGS REMOVE_PT_GPREGS_FROM_STACK 8 - -irq_return: INTERRUPT_RETURN ENTRY(native_iret) @@ -1431,11 +1429,12 @@ ENTRY(nmi) * If the variable is not set and the stack is not the NMI * stack then: * o Set the special variable on the stack - * o Copy the interrupt frame into a "saved" location on the stack - * o Copy the interrupt frame into a "copy" location on the stack + * o Copy the interrupt frame into an "outermost" location on the + * stack + * o Copy the interrupt frame into an "iret" location on the stack * o Continue processing the NMI * If the variable is set or the previous stack is the NMI stack: - * o Modify the "copy" location to jump to the repeate_nmi + * o Modify the "iret" location to jump to the repeat_nmi * o return back to the first NMI * * Now on exit of the first NMI, we first clear the stack variable @@ -1444,32 +1443,151 @@ ENTRY(nmi) * a nested NMI that updated the copy interrupt stack frame, a * jump will be made to the repeat_nmi code that will handle the second * NMI. + * + * However, espfix prevents us from directly returning to userspace + * with a single IRET instruction. Similarly, IRET to user mode + * can fault. We therefore handle NMIs from user space like + * other IST entries. */ /* Use %rdx as our temp variable throughout */ pushq_cfi %rdx CFI_REL_OFFSET rdx, 0 + testb $3, CS-RIP+8(%rsp) + jz .Lnmi_from_kernel + /* - * If %cs was not the kernel segment, then the NMI triggered in user - * space, which means it is definitely not nested. + * NMI from user mode. We need to run on the thread stack, but we + * can't go through the normal entry paths: NMIs are masked, and + * we don't want to enable interrupts, because then we'll end + * up in an awkward situation in which IRQs are on but NMIs + * are off. */ - cmpl $__KERNEL_CS, 16(%rsp) - jne first_nmi + + SWAPGS + cld + movq %rsp, %rdx + movq PER_CPU_VAR(kernel_stack), %rsp + pushq 5*8(%rdx) /* pt_regs->ss */ + pushq 4*8(%rdx) /* pt_regs->rsp */ + pushq 3*8(%rdx) /* pt_regs->flags */ + pushq 2*8(%rdx) /* pt_regs->cs */ + pushq 1*8(%rdx) /* pt_regs->rip */ + pushq $-1 /* pt_regs->orig_ax */ + pushq %rdi /* pt_regs->di */ + pushq %rsi /* pt_regs->si */ + pushq (%rdx) /* pt_regs->dx */ + pushq %rcx /* pt_regs->cx */ + pushq %rax /* pt_regs->ax */ + pushq %r8 /* pt_regs->r8 */ + pushq %r9 /* pt_regs->r9 */ + pushq %r10 /* pt_regs->r10 */ + pushq %r11 /* pt_regs->r11 */ + pushq %rbx /* pt_regs->rbx */ + pushq %rbp /* pt_regs->rbp */ + pushq %r12 /* pt_regs->r12 */ + pushq %r13 /* pt_regs->r13 */ + pushq %r14 /* pt_regs->r14 */ + pushq %r15 /* pt_regs->r15 */ /* - * Check the special variable on the stack to see if NMIs are - * executing. + * At this point we no longer need to worry about stack damage + * due to nesting -- we're on the normal thread stack and we're + * done with the NMI stack. + */ + movq %rsp, %rdi + movq $-1, %rsi + call do_nmi + + /* + * Return back to user mode. We must *not* do the normal exit + * work, because we don't want to enable interrupts. Fortunately, + * do_nmi doesn't modify pt_regs. + */ + SWAPGS + jmp restore_c_regs_and_iret + +.Lnmi_from_kernel: + /* + * Here's what our stack frame will look like: + * +---------------------------------------------------------+ + * | original SS | + * | original Return RSP | + * | original RFLAGS | + * | original CS | + * | original RIP | + * +---------------------------------------------------------+ + * | temp storage for rdx | + * +---------------------------------------------------------+ + * | "NMI executing" variable | + * +---------------------------------------------------------+ + * | iret SS } Copied from "outermost" frame | + * | iret Return RSP } on each loop iteration; overwritten | + * | iret RFLAGS } by a nested NMI to force another | + * | iret CS } iteration if needed. | + * | iret RIP } | + * +---------------------------------------------------------+ + * | outermost SS } initialized in first_nmi; | + * | outermost Return RSP } will not be changed before | + * | outermost RFLAGS } NMI processing is done. | + * | outermost CS } Copied to "iret" frame on each | + * | outermost RIP } iteration. | + * +---------------------------------------------------------+ + * | pt_regs | + * +---------------------------------------------------------+ + * + * The "original" frame is used by hardware. Before re-enabling + * NMIs, we need to be done with it, and we need to leave enough + * space for the asm code here. + * + * We return by executing IRET while RSP points to the "iret" frame. + * That will either return for real or it will loop back into NMI + * processing. + * + * The "outermost" frame is copied to the "iret" frame on each + * iteration of the loop, so each iteration starts with the "iret" + * frame pointing to the final return target. + */ + + /* + * Determine whether we're a nested NMI. + * + * If we interrupted kernel code between repeat_nmi and + * end_repeat_nmi, then we are a nested NMI. We must not + * modify the "iret" frame because it's being written by + * the outer NMI. That's okay; the outer NMI handler is + * about to about to call do_nmi anyway, so we can just + * resume the outer NMI. + */ + + movq $repeat_nmi, %rdx + cmpq 8(%rsp), %rdx + ja 1f + movq $end_repeat_nmi, %rdx + cmpq 8(%rsp), %rdx + ja nested_nmi_out +1: + + /* + * Now check "NMI executing". If it's set, then we're nested. + * This will not detect if we interrupted an outer NMI just + * before IRET. */ cmpl $1, -8(%rsp) je nested_nmi /* - * Now test if the previous stack was an NMI stack. - * We need the double check. We check the NMI stack to satisfy the - * race when the first NMI clears the variable before returning. - * We check the variable because the first NMI could be in a - * breakpoint routine using a breakpoint stack. + * Now test if the previous stack was an NMI stack. This covers + * the case where we interrupt an outer NMI after it clears + * "NMI executing" but before IRET. We need to be careful, though: + * there is one case in which RSP could point to the NMI stack + * despite there being no NMI active: naughty userspace controls + * RSP at the very beginning of the SYSCALL targets. We can + * pull a fast one on naughty userspace, though: we program + * SYSCALL to mask DF, so userspace cannot cause DF to be set + * if it controls the kernel's RSP. We set DF before we clear + * "NMI executing". */ lea 6*8(%rsp), %rdx /* Compare the NMI stack (rdx) with the stack we came from (4*8(%rsp)) */ @@ -1480,25 +1598,21 @@ ENTRY(nmi) cmpq %rdx, 4*8(%rsp) /* If it is below the NMI stack, it is a normal NMI */ jb first_nmi - /* Ah, it is within the NMI stack, treat it as nested */ + + /* Ah, it is within the NMI stack. */ + + testb $(X86_EFLAGS_DF >> 8), (3*8 + 1)(%rsp) + jz first_nmi /* RSP was user controlled. */ + + /* This is a nested NMI. */ CFI_REMEMBER_STATE nested_nmi: /* - * Do nothing if we interrupted the fixup in repeat_nmi. - * It's about to repeat the NMI handler, so we are fine - * with ignoring this one. + * Modify the "iret" frame to point to repeat_nmi, forcing another + * iteration of NMI handling. */ - movq $repeat_nmi, %rdx - cmpq 8(%rsp), %rdx - ja 1f - movq $end_repeat_nmi, %rdx - cmpq 8(%rsp), %rdx - ja nested_nmi_out - -1: - /* Set up the interrupted NMIs stack to jump to repeat_nmi */ leaq -1*8(%rsp), %rdx movq %rdx, %rsp CFI_ADJUST_CFA_OFFSET 1*8 @@ -1517,60 +1631,23 @@ nested_nmi_out: popq_cfi %rdx CFI_RESTORE rdx - /* No need to check faults here */ + /* We are returning to kernel mode, so this cannot result in a fault. */ INTERRUPT_RETURN CFI_RESTORE_STATE first_nmi: - /* - * Because nested NMIs will use the pushed location that we - * stored in rdx, we must keep that space available. - * Here's what our stack frame will look like: - * +-------------------------+ - * | original SS | - * | original Return RSP | - * | original RFLAGS | - * | original CS | - * | original RIP | - * +-------------------------+ - * | temp storage for rdx | - * +-------------------------+ - * | NMI executing variable | - * +-------------------------+ - * | copied SS | - * | copied Return RSP | - * | copied RFLAGS | - * | copied CS | - * | copied RIP | - * +-------------------------+ - * | Saved SS | - * | Saved Return RSP | - * | Saved RFLAGS | - * | Saved CS | - * | Saved RIP | - * +-------------------------+ - * | pt_regs | - * +-------------------------+ - * - * The saved stack frame is used to fix up the copied stack frame - * that a nested NMI may change to make the interrupted NMI iret jump - * to the repeat_nmi. The original stack frame and the temp storage - * is also used by nested NMIs and can not be trusted on exit. - */ - /* Do not pop rdx, nested NMIs will corrupt that part of the stack */ + /* Restore rdx. */ movq (%rsp), %rdx CFI_RESTORE rdx - /* Set the NMI executing variable on the stack. */ + /* Set "NMI executing" on the stack. */ pushq_cfi $1 - /* - * Leave room for the "copied" frame - */ + /* Leave room for the "iret" frame */ subq $(5*8), %rsp CFI_ADJUST_CFA_OFFSET 5*8 - /* Copy the stack frame to the Saved frame */ + /* Copy the "original" frame to the "outermost" frame */ .rept 5 pushq_cfi 11*8(%rsp) .endr @@ -1578,6 +1655,7 @@ first_nmi: /* Everything up to here is safe from nested NMIs */ +repeat_nmi: /* * If there was a nested NMI, the first NMI's iret will return * here. But NMIs are still enabled and we can take another @@ -1586,16 +1664,21 @@ first_nmi: * it will just return, as we are about to repeat an NMI anyway. * This makes it safe to copy to the stack frame that a nested * NMI will update. - */ -repeat_nmi: - /* - * Update the stack variable to say we are still in NMI (the update - * is benign for the non-repeat case, where 1 was pushed just above - * to this very stack slot). + * + * RSP is pointing to "outermost RIP". gsbase is unknown, but, if + * we're repeating an NMI, gsbase has the same value that it had on + * the first iteration. paranoid_entry will load the kernel + * gsbase if needed before we call do_nmi. + * + * Set "NMI executing" in case we came back here via IRET. */ movq $1, 10*8(%rsp) - /* Make another copy, this one may be modified by nested NMIs */ + /* + * Copy the "outermost" frame to the "iret" frame. NMIs that nest + * here must not modify the "iret" frame while we're writing to + * it or it will end up containing garbage. + */ addq $(10*8), %rsp CFI_ADJUST_CFA_OFFSET -10*8 .rept 5 @@ -1606,9 +1689,9 @@ repeat_nmi: end_repeat_nmi: /* - * Everything below this point can be preempted by a nested - * NMI if the first NMI took an exception and reset our iret stack - * so that we repeat another NMI. + * Everything below this point can be preempted by a nested NMI. + * If this happens, then the inner NMI will change the "iret" + * frame to point back to repeat_nmi. */ pushq_cfi $-1 /* ORIG_RAX: no syscall to restart */ ALLOC_PT_GPREGS_ON_STACK @@ -1623,29 +1706,11 @@ end_repeat_nmi: call paranoid_entry DEFAULT_FRAME 0 - /* - * Save off the CR2 register. If we take a page fault in the NMI then - * it could corrupt the CR2 value. If the NMI preempts a page fault - * handler before it was able to read the CR2 register, and then the - * NMI itself takes a page fault, the page fault that was preempted - * will read the information from the NMI page fault and not the - * origin fault. Save it off and restore it if it changes. - * Use the r12 callee-saved register. - */ - movq %cr2, %r12 - /* paranoidentry do_nmi, 0; without TRACE_IRQS_OFF */ movq %rsp,%rdi movq $-1,%rsi call do_nmi - /* Did the NMI take a page fault? Restore cr2 if it did */ - movq %cr2, %rcx - cmpq %rcx, %r12 - je 1f - movq %r12, %cr2 -1: - testl %ebx,%ebx /* swapgs needed? */ jnz nmi_restore nmi_swapgs: @@ -1653,12 +1718,27 @@ nmi_swapgs: nmi_restore: RESTORE_EXTRA_REGS RESTORE_C_REGS - /* Pop the extra iret frame at once */ + + /* Point RSP at the "iret" frame. */ REMOVE_PT_GPREGS_FROM_STACK 6*8 - /* Clear the NMI executing stack variable */ - movq $0, 5*8(%rsp) - jmp irq_return + /* + * Clear "NMI executing". Set DF first so that we can easily + * distinguish the remaining code between here and IRET from + * the SYSCALL entry and exit paths. On a native kernel, we + * could just inspect RIP, but, on paravirt kernels, + * INTERRUPT_RETURN can translate into a jump into a + * hypercall page. + */ + std + movq $0, 5*8(%rsp) /* clear "NMI executing" */ + + /* + * INTERRUPT_RETURN reads the "iret" frame and exits the NMI + * stack in a single instruction. We are returning to kernel + * mode, so this cannot result in a fault. + */ + INTERRUPT_RETURN CFI_ENDPROC END(nmi) diff --git a/kernel/arch/x86/kernel/head64.c b/kernel/arch/x86/kernel/head64.c index 5a4668136..f129a9af6 100644 --- a/kernel/arch/x86/kernel/head64.c +++ b/kernel/arch/x86/kernel/head64.c @@ -161,11 +161,12 @@ asmlinkage __visible void __init x86_64_start_kernel(char * real_mode_data) /* Kill off the identity-map trampoline */ reset_early_page_tables(); - kasan_map_early_shadow(early_level4_pgt); - - /* clear bss before set_intr_gate with early_idt_handler */ clear_bss(); + clear_page(init_level4_pgt); + + kasan_early_init(); + for (i = 0; i < NUM_EXCEPTION_VECTORS; i++) set_intr_gate(i, early_idt_handler_array[i]); load_idt((const struct desc_ptr *)&idt_descr); @@ -177,12 +178,9 @@ asmlinkage __visible void __init x86_64_start_kernel(char * real_mode_data) */ load_ucode_bsp(); - clear_page(init_level4_pgt); /* set init_level4_pgt kernel high mapping*/ init_level4_pgt[511] = early_level4_pgt[511]; - kasan_map_early_shadow(init_level4_pgt); - x86_64_start_reservations(real_mode_data); } diff --git a/kernel/arch/x86/kernel/head_64.S b/kernel/arch/x86/kernel/head_64.S index df7e78057..7e5da2cbe 100644 --- a/kernel/arch/x86/kernel/head_64.S +++ b/kernel/arch/x86/kernel/head_64.S @@ -516,38 +516,9 @@ ENTRY(phys_base) /* This must match the first entry in level2_kernel_pgt */ .quad 0x0000000000000000 -#ifdef CONFIG_KASAN -#define FILL(VAL, COUNT) \ - .rept (COUNT) ; \ - .quad (VAL) ; \ - .endr - -NEXT_PAGE(kasan_zero_pte) - FILL(kasan_zero_page - __START_KERNEL_map + _KERNPG_TABLE, 512) -NEXT_PAGE(kasan_zero_pmd) - FILL(kasan_zero_pte - __START_KERNEL_map + _KERNPG_TABLE, 512) -NEXT_PAGE(kasan_zero_pud) - FILL(kasan_zero_pmd - __START_KERNEL_map + _KERNPG_TABLE, 512) - -#undef FILL -#endif - - #include "../../x86/xen/xen-head.S" __PAGE_ALIGNED_BSS NEXT_PAGE(empty_zero_page) .skip PAGE_SIZE -#ifdef CONFIG_KASAN -/* - * This page used as early shadow. We don't use empty_zero_page - * at early stages, stack instrumentation could write some garbage - * to this page. - * Latter we reuse it as zero shadow for large ranges of memory - * that allowed to access, but not instrumented by kasan - * (vmalloc/vmemmap ...). - */ -NEXT_PAGE(kasan_zero_page) - .skip PAGE_SIZE -#endif diff --git a/kernel/arch/x86/kernel/nmi.c b/kernel/arch/x86/kernel/nmi.c index c3e985d17..d05bd2e2e 100644 --- a/kernel/arch/x86/kernel/nmi.c +++ b/kernel/arch/x86/kernel/nmi.c @@ -408,15 +408,15 @@ static void default_do_nmi(struct pt_regs *regs) NOKPROBE_SYMBOL(default_do_nmi); /* - * NMIs can hit breakpoints which will cause it to lose its - * NMI context with the CPU when the breakpoint does an iret. - */ -#ifdef CONFIG_X86_32 -/* - * For i386, NMIs use the same stack as the kernel, and we can - * add a workaround to the iret problem in C (preventing nested - * NMIs if an NMI takes a trap). Simply have 3 states the NMI - * can be in: + * NMIs can page fault or hit breakpoints which will cause it to lose + * its NMI context with the CPU when the breakpoint or page fault does an IRET. + * + * As a result, NMIs can nest if NMIs get unmasked due an IRET during + * NMI processing. On x86_64, the asm glue protects us from nested NMIs + * if the outer NMI came from kernel mode, but we can still nest if the + * outer NMI came from user mode. + * + * To handle these nested NMIs, we have three states: * * 1) not running * 2) executing @@ -430,15 +430,14 @@ NOKPROBE_SYMBOL(default_do_nmi); * (Note, the latch is binary, thus multiple NMIs triggering, * when one is running, are ignored. Only one NMI is restarted.) * - * If an NMI hits a breakpoint that executes an iret, another - * NMI can preempt it. We do not want to allow this new NMI - * to run, but we want to execute it when the first one finishes. - * We set the state to "latched", and the exit of the first NMI will - * perform a dec_return, if the result is zero (NOT_RUNNING), then - * it will simply exit the NMI handler. If not, the dec_return - * would have set the state to NMI_EXECUTING (what we want it to - * be when we are running). In this case, we simply jump back - * to rerun the NMI handler again, and restart the 'latched' NMI. + * If an NMI executes an iret, another NMI can preempt it. We do not + * want to allow this new NMI to run, but we want to execute it when the + * first one finishes. We set the state to "latched", and the exit of + * the first NMI will perform a dec_return, if the result is zero + * (NOT_RUNNING), then it will simply exit the NMI handler. If not, the + * dec_return would have set the state to NMI_EXECUTING (what we want it + * to be when we are running). In this case, we simply jump back to + * rerun the NMI handler again, and restart the 'latched' NMI. * * No trap (breakpoint or page fault) should be hit before nmi_restart, * thus there is no race between the first check of state for NOT_RUNNING @@ -461,49 +460,36 @@ enum nmi_states { static DEFINE_PER_CPU(enum nmi_states, nmi_state); static DEFINE_PER_CPU(unsigned long, nmi_cr2); -#define nmi_nesting_preprocess(regs) \ - do { \ - if (this_cpu_read(nmi_state) != NMI_NOT_RUNNING) { \ - this_cpu_write(nmi_state, NMI_LATCHED); \ - return; \ - } \ - this_cpu_write(nmi_state, NMI_EXECUTING); \ - this_cpu_write(nmi_cr2, read_cr2()); \ - } while (0); \ - nmi_restart: - -#define nmi_nesting_postprocess() \ - do { \ - if (unlikely(this_cpu_read(nmi_cr2) != read_cr2())) \ - write_cr2(this_cpu_read(nmi_cr2)); \ - if (this_cpu_dec_return(nmi_state)) \ - goto nmi_restart; \ - } while (0) -#else /* x86_64 */ +#ifdef CONFIG_X86_64 /* - * In x86_64 things are a bit more difficult. This has the same problem - * where an NMI hitting a breakpoint that calls iret will remove the - * NMI context, allowing a nested NMI to enter. What makes this more - * difficult is that both NMIs and breakpoints have their own stack. - * When a new NMI or breakpoint is executed, the stack is set to a fixed - * point. If an NMI is nested, it will have its stack set at that same - * fixed address that the first NMI had, and will start corrupting the - * stack. This is handled in entry_64.S, but the same problem exists with - * the breakpoint stack. + * In x86_64, we need to handle breakpoint -> NMI -> breakpoint. Without + * some care, the inner breakpoint will clobber the outer breakpoint's + * stack. * - * If a breakpoint is being processed, and the debug stack is being used, - * if an NMI comes in and also hits a breakpoint, the stack pointer - * will be set to the same fixed address as the breakpoint that was - * interrupted, causing that stack to be corrupted. To handle this case, - * check if the stack that was interrupted is the debug stack, and if - * so, change the IDT so that new breakpoints will use the current stack - * and not switch to the fixed address. On return of the NMI, switch back - * to the original IDT. + * If a breakpoint is being processed, and the debug stack is being + * used, if an NMI comes in and also hits a breakpoint, the stack + * pointer will be set to the same fixed address as the breakpoint that + * was interrupted, causing that stack to be corrupted. To handle this + * case, check if the stack that was interrupted is the debug stack, and + * if so, change the IDT so that new breakpoints will use the current + * stack and not switch to the fixed address. On return of the NMI, + * switch back to the original IDT. */ static DEFINE_PER_CPU(int, update_debug_stack); +#endif -static inline void nmi_nesting_preprocess(struct pt_regs *regs) +dotraplinkage notrace void +do_nmi(struct pt_regs *regs, long error_code) { + if (this_cpu_read(nmi_state) != NMI_NOT_RUNNING) { + this_cpu_write(nmi_state, NMI_LATCHED); + return; + } + this_cpu_write(nmi_state, NMI_EXECUTING); + this_cpu_write(nmi_cr2, read_cr2()); +nmi_restart: + +#ifdef CONFIG_X86_64 /* * If we interrupted a breakpoint, it is possible that * the nmi handler will have breakpoints too. We need to @@ -514,22 +500,8 @@ static inline void nmi_nesting_preprocess(struct pt_regs *regs) debug_stack_set_zero(); this_cpu_write(update_debug_stack, 1); } -} - -static inline void nmi_nesting_postprocess(void) -{ - if (unlikely(this_cpu_read(update_debug_stack))) { - debug_stack_reset(); - this_cpu_write(update_debug_stack, 0); - } -} #endif -dotraplinkage notrace void -do_nmi(struct pt_regs *regs, long error_code) -{ - nmi_nesting_preprocess(regs); - nmi_enter(); inc_irq_stat(__nmi_count); @@ -539,8 +511,17 @@ do_nmi(struct pt_regs *regs, long error_code) nmi_exit(); - /* On i386, may loop back to preprocess */ - nmi_nesting_postprocess(); +#ifdef CONFIG_X86_64 + if (unlikely(this_cpu_read(update_debug_stack))) { + debug_stack_reset(); + this_cpu_write(update_debug_stack, 0); + } +#endif + + if (unlikely(this_cpu_read(nmi_cr2) != read_cr2())) + write_cr2(this_cpu_read(nmi_cr2)); + if (this_cpu_dec_return(nmi_state)) + goto nmi_restart; } NOKPROBE_SYMBOL(do_nmi); diff --git a/kernel/arch/x86/kernel/process.c b/kernel/arch/x86/kernel/process.c index 6e338e3b1..971743774 100644 --- a/kernel/arch/x86/kernel/process.c +++ b/kernel/arch/x86/kernel/process.c @@ -453,6 +453,7 @@ static int prefer_mwait_c1_over_halt(const struct cpuinfo_x86 *c) static void mwait_idle(void) { if (!current_set_polling_and_test()) { + trace_cpu_idle_rcuidle(1, smp_processor_id()); if (this_cpu_has(X86_BUG_CLFLUSH_MONITOR)) { smp_mb(); /* quirk */ clflush((void *)¤t_thread_info()->flags); @@ -464,6 +465,7 @@ static void mwait_idle(void) __sti_mwait(0, 0); else local_irq_enable(); + trace_cpu_idle_rcuidle(PWR_EVENT_EXIT, smp_processor_id()); } else { local_irq_enable(); } diff --git a/kernel/arch/x86/kernel/signal.c b/kernel/arch/x86/kernel/signal.c index 74c44c4f0..12c28f79e 100644 --- a/kernel/arch/x86/kernel/signal.c +++ b/kernel/arch/x86/kernel/signal.c @@ -93,8 +93,15 @@ int restore_sigcontext(struct pt_regs *regs, struct sigcontext __user *sc) COPY(r15); #endif /* CONFIG_X86_64 */ +#ifdef CONFIG_X86_32 COPY_SEG_CPL3(cs); COPY_SEG_CPL3(ss); +#else /* !CONFIG_X86_32 */ + /* Kernel saves and restores only the CS segment register on signals, + * which is the bare minimum needed to allow mixed 32/64-bit code. + * App's signal handler can save/restore other segments if needed. */ + COPY_SEG_CPL3(cs); +#endif /* CONFIG_X86_32 */ get_user_ex(tmpflags, &sc->flags); regs->flags = (regs->flags & ~FIX_EFLAGS) | (tmpflags & FIX_EFLAGS); @@ -154,9 +161,8 @@ int setup_sigcontext(struct sigcontext __user *sc, void __user *fpstate, #else /* !CONFIG_X86_32 */ put_user_ex(regs->flags, &sc->flags); put_user_ex(regs->cs, &sc->cs); - put_user_ex(0, &sc->__pad2); - put_user_ex(0, &sc->__pad1); - put_user_ex(regs->ss, &sc->ss); + put_user_ex(0, &sc->gs); + put_user_ex(0, &sc->fs); #endif /* CONFIG_X86_32 */ put_user_ex(fpstate, &sc->fpstate); @@ -450,19 +456,9 @@ static int __setup_rt_frame(int sig, struct ksignal *ksig, regs->sp = (unsigned long)frame; - /* - * Set up the CS and SS registers to run signal handlers in - * 64-bit mode, even if the handler happens to be interrupting - * 32-bit or 16-bit code. - * - * SS is subtle. In 64-bit mode, we don't need any particular - * SS descriptor, but we do need SS to be valid. It's possible - * that the old SS is entirely bogus -- this can happen if the - * signal we're trying to deliver is #GP or #SS caused by a bad - * SS value. - */ + /* Set up the CS register to run signal handlers in 64-bit mode, + even if the handler happens to be interrupting 32-bit code. */ regs->cs = __USER_CS; - regs->ss = __USER_DS; return 0; } diff --git a/kernel/arch/x86/kvm/lapic.h b/kernel/arch/x86/kvm/lapic.h index 9d28383fc..c4ea87eed 100644 --- a/kernel/arch/x86/kvm/lapic.h +++ b/kernel/arch/x86/kvm/lapic.h @@ -150,7 +150,7 @@ static inline bool kvm_apic_vid_enabled(struct kvm *kvm) static inline bool kvm_apic_has_events(struct kvm_vcpu *vcpu) { - return vcpu->arch.apic->pending_events; + return kvm_vcpu_has_lapic(vcpu) && vcpu->arch.apic->pending_events; } bool kvm_apic_pending_eoi(struct kvm_vcpu *vcpu, int vector); diff --git a/kernel/arch/x86/mm/kasan_init_64.c b/kernel/arch/x86/mm/kasan_init_64.c index 4860906c6..9a54dbe98 100644 --- a/kernel/arch/x86/mm/kasan_init_64.c +++ b/kernel/arch/x86/mm/kasan_init_64.c @@ -11,7 +11,19 @@ extern pgd_t early_level4_pgt[PTRS_PER_PGD]; extern struct range pfn_mapped[E820_X_MAX]; -extern unsigned char kasan_zero_page[PAGE_SIZE]; +static pud_t kasan_zero_pud[PTRS_PER_PUD] __page_aligned_bss; +static pmd_t kasan_zero_pmd[PTRS_PER_PMD] __page_aligned_bss; +static pte_t kasan_zero_pte[PTRS_PER_PTE] __page_aligned_bss; + +/* + * This page used as early shadow. We don't use empty_zero_page + * at early stages, stack instrumentation could write some garbage + * to this page. + * Latter we reuse it as zero shadow for large ranges of memory + * that allowed to access, but not instrumented by kasan + * (vmalloc/vmemmap ...). + */ +static unsigned char kasan_zero_page[PAGE_SIZE] __page_aligned_bss; static int __init map_range(struct range *range) { @@ -36,7 +48,7 @@ static void __init clear_pgds(unsigned long start, pgd_clear(pgd_offset_k(start)); } -void __init kasan_map_early_shadow(pgd_t *pgd) +static void __init kasan_map_early_shadow(pgd_t *pgd) { int i; unsigned long start = KASAN_SHADOW_START; @@ -73,7 +85,7 @@ static int __init zero_pmd_populate(pud_t *pud, unsigned long addr, while (IS_ALIGNED(addr, PMD_SIZE) && addr + PMD_SIZE <= end) { WARN_ON(!pmd_none(*pmd)); set_pmd(pmd, __pmd(__pa_nodebug(kasan_zero_pte) - | __PAGE_KERNEL_RO)); + | _KERNPG_TABLE)); addr += PMD_SIZE; pmd = pmd_offset(pud, addr); } @@ -99,7 +111,7 @@ static int __init zero_pud_populate(pgd_t *pgd, unsigned long addr, while (IS_ALIGNED(addr, PUD_SIZE) && addr + PUD_SIZE <= end) { WARN_ON(!pud_none(*pud)); set_pud(pud, __pud(__pa_nodebug(kasan_zero_pmd) - | __PAGE_KERNEL_RO)); + | _KERNPG_TABLE)); addr += PUD_SIZE; pud = pud_offset(pgd, addr); } @@ -124,7 +136,7 @@ static int __init zero_pgd_populate(unsigned long addr, unsigned long end) while (IS_ALIGNED(addr, PGDIR_SIZE) && addr + PGDIR_SIZE <= end) { WARN_ON(!pgd_none(*pgd)); set_pgd(pgd, __pgd(__pa_nodebug(kasan_zero_pud) - | __PAGE_KERNEL_RO)); + | _KERNPG_TABLE)); addr += PGDIR_SIZE; pgd = pgd_offset_k(addr); } @@ -166,6 +178,26 @@ static struct notifier_block kasan_die_notifier = { }; #endif +void __init kasan_early_init(void) +{ + int i; + pteval_t pte_val = __pa_nodebug(kasan_zero_page) | __PAGE_KERNEL; + pmdval_t pmd_val = __pa_nodebug(kasan_zero_pte) | _KERNPG_TABLE; + pudval_t pud_val = __pa_nodebug(kasan_zero_pmd) | _KERNPG_TABLE; + + for (i = 0; i < PTRS_PER_PTE; i++) + kasan_zero_pte[i] = __pte(pte_val); + + for (i = 0; i < PTRS_PER_PMD; i++) + kasan_zero_pmd[i] = __pmd(pmd_val); + + for (i = 0; i < PTRS_PER_PUD; i++) + kasan_zero_pud[i] = __pud(pud_val); + + kasan_map_early_shadow(early_level4_pgt); + kasan_map_early_shadow(init_level4_pgt); +} + void __init kasan_init(void) { int i; @@ -176,6 +208,7 @@ void __init kasan_init(void) memcpy(early_level4_pgt, init_level4_pgt, sizeof(early_level4_pgt)); load_cr3(early_level4_pgt); + __flush_tlb_all(); clear_pgds(KASAN_SHADOW_START, KASAN_SHADOW_END); @@ -202,5 +235,6 @@ void __init kasan_init(void) memset(kasan_zero_page, 0, PAGE_SIZE); load_cr3(init_level4_pgt); + __flush_tlb_all(); init_task.kasan_depth = 0; } diff --git a/kernel/arch/x86/mm/mmap.c b/kernel/arch/x86/mm/mmap.c index 9d518d693..844b06d67 100644 --- a/kernel/arch/x86/mm/mmap.c +++ b/kernel/arch/x86/mm/mmap.c @@ -126,3 +126,10 @@ void arch_pick_mmap_layout(struct mm_struct *mm) mm->get_unmapped_area = arch_get_unmapped_area_topdown; } } + +const char *arch_vma_name(struct vm_area_struct *vma) +{ + if (vma->vm_flags & VM_MPX) + return "[mpx]"; + return NULL; +} diff --git a/kernel/arch/x86/mm/mpx.c b/kernel/arch/x86/mm/mpx.c index c439ec478..4d1c11c07 100644 --- a/kernel/arch/x86/mm/mpx.c +++ b/kernel/arch/x86/mm/mpx.c @@ -18,26 +18,9 @@ #include <asm/processor.h> #include <asm/fpu-internal.h> -static const char *mpx_mapping_name(struct vm_area_struct *vma) -{ - return "[mpx]"; -} - -static struct vm_operations_struct mpx_vma_ops = { - .name = mpx_mapping_name, -}; - -static int is_mpx_vma(struct vm_area_struct *vma) -{ - return (vma->vm_ops == &mpx_vma_ops); -} - /* * This is really a simplified "vm_mmap". it only handles MPX * bounds tables (the bounds directory is user-allocated). - * - * Later on, we use the vma->vm_ops to uniquely identify these - * VMAs. */ static unsigned long mpx_mmap(unsigned long len) { @@ -83,7 +66,6 @@ static unsigned long mpx_mmap(unsigned long len) ret = -ENOMEM; goto out; } - vma->vm_ops = &mpx_vma_ops; if (vm_flags & VM_LOCKED) { up_write(&mm->mmap_sem); @@ -661,7 +643,7 @@ static int zap_bt_entries(struct mm_struct *mm, * so stop immediately and return an error. This * probably results in a SIGSEGV. */ - if (!is_mpx_vma(vma)) + if (!(vma->vm_flags & VM_MPX)) return -EINVAL; len = min(vma->vm_end, end) - addr; diff --git a/kernel/arch/x86/mm/tlb.c b/kernel/arch/x86/mm/tlb.c index 3250f2371..90b924acd 100644 --- a/kernel/arch/x86/mm/tlb.c +++ b/kernel/arch/x86/mm/tlb.c @@ -117,7 +117,7 @@ static void flush_tlb_func(void *info) } else { unsigned long addr; unsigned long nr_pages = - f->flush_end - f->flush_start / PAGE_SIZE; + (f->flush_end - f->flush_start) / PAGE_SIZE; addr = f->flush_start; while (addr < f->flush_end) { __flush_tlb_single(addr); diff --git a/kernel/arch/x86/platform/efi/efi.c b/kernel/arch/x86/platform/efi/efi.c index 02744df57..841ea05e1 100644 --- a/kernel/arch/x86/platform/efi/efi.c +++ b/kernel/arch/x86/platform/efi/efi.c @@ -946,6 +946,11 @@ u64 efi_mem_attributes(unsigned long phys_addr) static int __init arch_parse_efi_cmdline(char *str) { + if (!str) { + pr_warn("need at least one option\n"); + return -EINVAL; + } + if (parse_option_str(str, "old_map")) set_bit(EFI_OLD_MEMMAP, &efi.flags); if (parse_option_str(str, "debug")) diff --git a/kernel/arch/x86/xen/Kconfig b/kernel/arch/x86/xen/Kconfig index e88fda867..484145368 100644 --- a/kernel/arch/x86/xen/Kconfig +++ b/kernel/arch/x86/xen/Kconfig @@ -8,7 +8,7 @@ config XEN select PARAVIRT_CLOCK select XEN_HAVE_PVMMU depends on X86_64 || (X86_32 && X86_PAE) - depends on X86_TSC + depends on X86_LOCAL_APIC && X86_TSC help This is the Linux Xen port. Enabling this will allow the kernel to boot in a paravirtualized environment under the @@ -17,7 +17,7 @@ config XEN config XEN_DOM0 def_bool y depends on XEN && PCI_XEN && SWIOTLB_XEN - depends on X86_LOCAL_APIC && X86_IO_APIC && ACPI && PCI + depends on X86_IO_APIC && ACPI && PCI config XEN_PVHVM def_bool y diff --git a/kernel/arch/x86/xen/Makefile b/kernel/arch/x86/xen/Makefile index 7322755f3..4b6e29ac0 100644 --- a/kernel/arch/x86/xen/Makefile +++ b/kernel/arch/x86/xen/Makefile @@ -13,13 +13,13 @@ CFLAGS_mmu.o := $(nostackp) obj-y := enlighten.o setup.o multicalls.o mmu.o irq.o \ time.o xen-asm.o xen-asm_$(BITS).o \ grant-table.o suspend.o platform-pci-unplug.o \ - p2m.o + p2m.o apic.o obj-$(CONFIG_EVENT_TRACING) += trace.o obj-$(CONFIG_SMP) += smp.o obj-$(CONFIG_PARAVIRT_SPINLOCKS)+= spinlock.o obj-$(CONFIG_XEN_DEBUG_FS) += debugfs.o -obj-$(CONFIG_XEN_DOM0) += apic.o vga.o +obj-$(CONFIG_XEN_DOM0) += vga.o obj-$(CONFIG_SWIOTLB_XEN) += pci-swiotlb-xen.o obj-$(CONFIG_XEN_EFI) += efi.o diff --git a/kernel/arch/x86/xen/enlighten.c b/kernel/arch/x86/xen/enlighten.c index 46957ead3..a671e8372 100644 --- a/kernel/arch/x86/xen/enlighten.c +++ b/kernel/arch/x86/xen/enlighten.c @@ -483,6 +483,7 @@ static void set_aliased_prot(void *v, pgprot_t prot) pte_t pte; unsigned long pfn; struct page *page; + unsigned char dummy; ptep = lookup_address((unsigned long)v, &level); BUG_ON(ptep == NULL); @@ -492,6 +493,32 @@ static void set_aliased_prot(void *v, pgprot_t prot) pte = pfn_pte(pfn, prot); + /* + * Careful: update_va_mapping() will fail if the virtual address + * we're poking isn't populated in the page tables. We don't + * need to worry about the direct map (that's always in the page + * tables), but we need to be careful about vmap space. In + * particular, the top level page table can lazily propagate + * entries between processes, so if we've switched mms since we + * vmapped the target in the first place, we might not have the + * top-level page table entry populated. + * + * We disable preemption because we want the same mm active when + * we probe the target and when we issue the hypercall. We'll + * have the same nominal mm, but if we're a kernel thread, lazy + * mm dropping could change our pgd. + * + * Out of an abundance of caution, this uses __get_user() to fault + * in the target address just in case there's some obscure case + * in which the target address isn't readable. + */ + + preempt_disable(); + + pagefault_disable(); /* Avoid warnings due to being atomic. */ + __get_user(dummy, (unsigned char __user __force *)v); + pagefault_enable(); + if (HYPERVISOR_update_va_mapping((unsigned long)v, pte, 0)) BUG(); @@ -503,6 +530,8 @@ static void set_aliased_prot(void *v, pgprot_t prot) BUG(); } else kmap_flush_unused(); + + preempt_enable(); } static void xen_alloc_ldt(struct desc_struct *ldt, unsigned entries) @@ -510,6 +539,17 @@ static void xen_alloc_ldt(struct desc_struct *ldt, unsigned entries) const unsigned entries_per_page = PAGE_SIZE / LDT_ENTRY_SIZE; int i; + /* + * We need to mark the all aliases of the LDT pages RO. We + * don't need to call vm_flush_aliases(), though, since that's + * only responsible for flushing aliases out the TLBs, not the + * page tables, and Xen will flush the TLB for us if needed. + * + * To avoid confusing future readers: none of this is necessary + * to load the LDT. The hypervisor only checks this when the + * LDT is faulted in due to subsequent descriptor access. + */ + for(i = 0; i < entries; i += entries_per_page) set_aliased_prot(ldt + i, PAGE_KERNEL_RO); } diff --git a/kernel/arch/x86/xen/xen-ops.h b/kernel/arch/x86/xen/xen-ops.h index 9e195c683..bef30cbb5 100644 --- a/kernel/arch/x86/xen/xen-ops.h +++ b/kernel/arch/x86/xen/xen-ops.h @@ -101,17 +101,15 @@ struct dom0_vga_console_info; #ifdef CONFIG_XEN_DOM0 void __init xen_init_vga(const struct dom0_vga_console_info *, size_t size); -void __init xen_init_apic(void); #else static inline void __init xen_init_vga(const struct dom0_vga_console_info *info, size_t size) { } -static inline void __init xen_init_apic(void) -{ -} #endif +void __init xen_init_apic(void); + #ifdef CONFIG_XEN_EFI extern void xen_efi_init(void); #else |