diff options
Diffstat (limited to 'arch')
255 files changed, 3627 insertions, 1559 deletions
diff --git a/arch/alpha/Makefile b/arch/alpha/Makefile index 4759fe7..2cc3cc5 100644 --- a/arch/alpha/Makefile +++ b/arch/alpha/Makefile @@ -12,7 +12,7 @@ NM := $(NM) -B LDFLAGS_vmlinux := -static -N #-relax CHECKFLAGS += -D__alpha__ -m64 -cflags-y := -pipe -mno-fp-regs -ffixed-8 -msmall-data +cflags-y := -pipe -mno-fp-regs -ffixed-8 cflags-y += $(call cc-option, -fno-jump-tables) cpuflags-$(CONFIG_ALPHA_EV4) := -mcpu=ev4 diff --git a/arch/alpha/include/asm/floppy.h b/arch/alpha/include/asm/floppy.h index 46cefbd..bae97eb 100644 --- a/arch/alpha/include/asm/floppy.h +++ b/arch/alpha/include/asm/floppy.h @@ -26,7 +26,7 @@ #define fd_disable_irq() disable_irq(FLOPPY_IRQ) #define fd_cacheflush(addr,size) /* nothing */ #define fd_request_irq() request_irq(FLOPPY_IRQ, floppy_interrupt,\ - IRQF_DISABLED, "floppy", NULL) + 0, "floppy", NULL) #define fd_free_irq() free_irq(FLOPPY_IRQ, NULL) #ifdef CONFIG_PCI diff --git a/arch/alpha/kernel/irq.c b/arch/alpha/kernel/irq.c index 2872acc..7b2be25 100644 --- a/arch/alpha/kernel/irq.c +++ b/arch/alpha/kernel/irq.c @@ -117,13 +117,6 @@ handle_irq(int irq) return; } - /* - * From here we must proceed with IPL_MAX. Note that we do not - * explicitly enable interrupts afterwards - some MILO PALcode - * (namely LX164 one) seems to have severe problems with RTI - * at IPL 0. - */ - local_irq_disable(); irq_enter(); generic_handle_irq_desc(irq, desc); irq_exit(); diff --git a/arch/alpha/kernel/irq_alpha.c b/arch/alpha/kernel/irq_alpha.c index 772ddfdb..f433fc1 100644 --- a/arch/alpha/kernel/irq_alpha.c +++ b/arch/alpha/kernel/irq_alpha.c @@ -45,6 +45,14 @@ do_entInt(unsigned long type, unsigned long vector, unsigned long la_ptr, struct pt_regs *regs) { struct pt_regs *old_regs; + + /* + * Disable interrupts during IRQ handling. + * Note that there is no matching local_irq_enable() due to + * severe problems with RTI at IPL0 and some MILO PALcode + * (namely LX164). + */ + local_irq_disable(); switch (type) { case 0: #ifdef CONFIG_SMP @@ -62,7 +70,6 @@ do_entInt(unsigned long type, unsigned long vector, { long cpu; - local_irq_disable(); smp_percpu_timer_interrupt(regs); cpu = smp_processor_id(); if (cpu != boot_cpuid) { @@ -222,7 +229,6 @@ process_mcheck_info(unsigned long vector, unsigned long la_ptr, struct irqaction timer_irqaction = { .handler = timer_interrupt, - .flags = IRQF_DISABLED, .name = "timer", }; diff --git a/arch/alpha/kernel/sys_nautilus.c b/arch/alpha/kernel/sys_nautilus.c index 4d4c046..1383f86 100644 --- a/arch/alpha/kernel/sys_nautilus.c +++ b/arch/alpha/kernel/sys_nautilus.c @@ -188,6 +188,10 @@ nautilus_machine_check(unsigned long vector, unsigned long la_ptr) extern void free_reserved_mem(void *, void *); extern void pcibios_claim_one_bus(struct pci_bus *); +static struct resource irongate_io = { + .name = "Irongate PCI IO", + .flags = IORESOURCE_IO, +}; static struct resource irongate_mem = { .name = "Irongate PCI MEM", .flags = IORESOURCE_MEM, @@ -209,6 +213,7 @@ nautilus_init_pci(void) irongate = pci_get_bus_and_slot(0, 0); bus->self = irongate; + bus->resource[0] = &irongate_io; bus->resource[1] = &irongate_mem; pci_bus_size_bridges(bus); diff --git a/arch/alpha/kernel/sys_titan.c b/arch/alpha/kernel/sys_titan.c index 5cf4a48..a53cf03 100644 --- a/arch/alpha/kernel/sys_titan.c +++ b/arch/alpha/kernel/sys_titan.c @@ -280,15 +280,15 @@ titan_late_init(void) * all reported to the kernel as machine checks, so the handler * is a nop so it can be called to count the individual events. */ - titan_request_irq(63+16, titan_intr_nop, IRQF_DISABLED, + titan_request_irq(63+16, titan_intr_nop, 0, "CChip Error", NULL); - titan_request_irq(62+16, titan_intr_nop, IRQF_DISABLED, + titan_request_irq(62+16, titan_intr_nop, 0, "PChip 0 H_Error", NULL); - titan_request_irq(61+16, titan_intr_nop, IRQF_DISABLED, + titan_request_irq(61+16, titan_intr_nop, 0, "PChip 1 H_Error", NULL); - titan_request_irq(60+16, titan_intr_nop, IRQF_DISABLED, + titan_request_irq(60+16, titan_intr_nop, 0, "PChip 0 C_Error", NULL); - titan_request_irq(59+16, titan_intr_nop, IRQF_DISABLED, + titan_request_irq(59+16, titan_intr_nop, 0, "PChip 1 C_Error", NULL); /* @@ -348,9 +348,9 @@ privateer_init_pci(void) * Hook a couple of extra err interrupts that the * common titan code won't. */ - titan_request_irq(53+16, titan_intr_nop, IRQF_DISABLED, + titan_request_irq(53+16, titan_intr_nop, 0, "NMI", NULL); - titan_request_irq(50+16, titan_intr_nop, IRQF_DISABLED, + titan_request_irq(50+16, titan_intr_nop, 0, "Temperature Warning", NULL); /* diff --git a/arch/arc/include/asm/irqflags.h b/arch/arc/include/asm/irqflags.h index ccd8480..eac0716 100644 --- a/arch/arc/include/asm/irqflags.h +++ b/arch/arc/include/asm/irqflags.h @@ -39,7 +39,7 @@ static inline long arch_local_irq_save(void) " flag.nz %0 \n" : "=r"(temp), "=r"(flags) : "n"((STATUS_E1_MASK | STATUS_E2_MASK)) - : "cc"); + : "memory", "cc"); return flags; } @@ -53,7 +53,8 @@ static inline void arch_local_irq_restore(unsigned long flags) __asm__ __volatile__( " flag %0 \n" : - : "r"(flags)); + : "r"(flags) + : "memory"); } /* @@ -73,7 +74,8 @@ static inline void arch_local_irq_disable(void) " and %0, %0, %1 \n" " flag %0 \n" : "=&r"(temp) - : "n"(~(STATUS_E1_MASK | STATUS_E2_MASK))); + : "n"(~(STATUS_E1_MASK | STATUS_E2_MASK)) + : "memory"); } /* @@ -85,7 +87,9 @@ static inline long arch_local_save_flags(void) __asm__ __volatile__( " lr %0, [status32] \n" - : "=&r"(temp)); + : "=&r"(temp) + : + : "memory"); return temp; } diff --git a/arch/arm/Kconfig b/arch/arm/Kconfig index 13b7394..1cacda4 100644 --- a/arch/arm/Kconfig +++ b/arch/arm/Kconfig @@ -1183,9 +1183,9 @@ config ARM_NR_BANKS default 8 config IWMMXT - bool "Enable iWMMXt support" + bool "Enable iWMMXt support" if !CPU_PJ4 depends on CPU_XSCALE || CPU_XSC3 || CPU_MOHAWK || CPU_PJ4 - default y if PXA27x || PXA3xx || ARCH_MMP + default y if PXA27x || PXA3xx || ARCH_MMP || CPU_PJ4 help Enable support for iWMMXt context switching at run time if running on a CPU that supports it. @@ -1439,6 +1439,16 @@ config ARM_ERRATA_775420 to deadlock. This workaround puts DSB before executing ISB if an abort may occur on cache maintenance. +config ARM_ERRATA_798181 + bool "ARM errata: TLBI/DSB failure on Cortex-A15" + depends on CPU_V7 && SMP + help + On Cortex-A15 (r0p0..r3p2) the TLBI*IS/DSB operations are not + adequately shooting down all use of the old entries. This + option enables the Linux kernel workaround for this erratum + which sends an IPI to the CPUs that are running the same ASID + as the one being invalidated. + endmenu source "arch/arm/common/Kconfig" diff --git a/arch/arm/boot/dts/armada-370-mirabox.dts b/arch/arm/boot/dts/armada-370-mirabox.dts index dd0c57d..3234875 100644 --- a/arch/arm/boot/dts/armada-370-mirabox.dts +++ b/arch/arm/boot/dts/armada-370-mirabox.dts @@ -54,7 +54,7 @@ }; mvsdio@d00d4000 { - pinctrl-0 = <&sdio_pins2>; + pinctrl-0 = <&sdio_pins3>; pinctrl-names = "default"; status = "okay"; /* diff --git a/arch/arm/boot/dts/armada-370.dtsi b/arch/arm/boot/dts/armada-370.dtsi index 8188d13..a195deb 100644 --- a/arch/arm/boot/dts/armada-370.dtsi +++ b/arch/arm/boot/dts/armada-370.dtsi @@ -59,6 +59,12 @@ "mpp50", "mpp51", "mpp52"; marvell,function = "sd0"; }; + + sdio_pins3: sdio-pins3 { + marvell,pins = "mpp48", "mpp49", "mpp50", + "mpp51", "mpp52", "mpp53"; + marvell,function = "sd0"; + }; }; gpio0: gpio@d0018100 { diff --git a/arch/arm/boot/dts/dbx5x0.dtsi b/arch/arm/boot/dts/dbx5x0.dtsi index 9de9309..aaa63d0 100644 --- a/arch/arm/boot/dts/dbx5x0.dtsi +++ b/arch/arm/boot/dts/dbx5x0.dtsi @@ -191,8 +191,8 @@ prcmu: prcmu@80157000 { compatible = "stericsson,db8500-prcmu"; - reg = <0x80157000 0x1000>; - reg-names = "prcmu"; + reg = <0x80157000 0x1000>, <0x801b0000 0x8000>, <0x801b8000 0x1000>; + reg-names = "prcmu", "prcmu-tcpm", "prcmu-tcdm"; interrupts = <0 47 0x4>; #address-cells = <1>; #size-cells = <1>; diff --git a/arch/arm/boot/dts/imx28-m28evk.dts b/arch/arm/boot/dts/imx28-m28evk.dts index 6ce3d17..fd36e1c 100644 --- a/arch/arm/boot/dts/imx28-m28evk.dts +++ b/arch/arm/boot/dts/imx28-m28evk.dts @@ -152,7 +152,6 @@ i2c0: i2c@80058000 { pinctrl-names = "default"; pinctrl-0 = <&i2c0_pins_a>; - clock-frequency = <400000>; status = "okay"; sgtl5000: codec@0a { diff --git a/arch/arm/boot/dts/imx28-sps1.dts b/arch/arm/boot/dts/imx28-sps1.dts index e6cde8a..6c6a544 100644 --- a/arch/arm/boot/dts/imx28-sps1.dts +++ b/arch/arm/boot/dts/imx28-sps1.dts @@ -70,7 +70,6 @@ i2c0: i2c@80058000 { pinctrl-names = "default"; pinctrl-0 = <&i2c0_pins_a>; - clock-frequency = <400000>; status = "okay"; rtc: rtc@51 { diff --git a/arch/arm/boot/dts/imx6qdl.dtsi b/arch/arm/boot/dts/imx6qdl.dtsi index 06ec460..281a223 100644 --- a/arch/arm/boot/dts/imx6qdl.dtsi +++ b/arch/arm/boot/dts/imx6qdl.dtsi @@ -91,6 +91,7 @@ compatible = "arm,cortex-a9-twd-timer"; reg = <0x00a00600 0x20>; interrupts = <1 13 0xf01>; + clocks = <&clks 15>; }; L2: l2-cache@00a02000 { diff --git a/arch/arm/boot/dts/kirkwood-goflexnet.dts b/arch/arm/boot/dts/kirkwood-goflexnet.dts index bd83b8f..c3573be 100644 --- a/arch/arm/boot/dts/kirkwood-goflexnet.dts +++ b/arch/arm/boot/dts/kirkwood-goflexnet.dts @@ -77,6 +77,7 @@ }; nand@3000000 { + chip-delay = <40>; status = "okay"; partition@0 { diff --git a/arch/arm/boot/dts/kirkwood-iomega_ix2_200.dts b/arch/arm/boot/dts/kirkwood-iomega_ix2_200.dts index 93c3afb..3694e94 100644 --- a/arch/arm/boot/dts/kirkwood-iomega_ix2_200.dts +++ b/arch/arm/boot/dts/kirkwood-iomega_ix2_200.dts @@ -96,11 +96,11 @@ marvell,function = "gpio"; }; pmx_led_rebuild_brt_ctrl_1: pmx-led-rebuild-brt-ctrl-1 { - marvell,pins = "mpp44"; + marvell,pins = "mpp46"; marvell,function = "gpio"; }; pmx_led_rebuild_brt_ctrl_2: pmx-led-rebuild-brt-ctrl-2 { - marvell,pins = "mpp45"; + marvell,pins = "mpp47"; marvell,function = "gpio"; }; @@ -157,14 +157,14 @@ gpios = <&gpio0 16 0>; linux,default-trigger = "default-on"; }; - health_led1 { + rebuild_led { + label = "status:white:rebuild_led"; + gpios = <&gpio1 4 0>; + }; + health_led { label = "status:red:health_led"; gpios = <&gpio1 5 0>; }; - health_led2 { - label = "status:white:health_led"; - gpios = <&gpio1 4 0>; - }; backup_led { label = "status:blue:backup_led"; gpios = <&gpio0 15 0>; diff --git a/arch/arm/boot/dts/orion5x.dtsi b/arch/arm/boot/dts/orion5x.dtsi index 8aad00f..f7bec3b 100644 --- a/arch/arm/boot/dts/orion5x.dtsi +++ b/arch/arm/boot/dts/orion5x.dtsi @@ -13,6 +13,9 @@ compatible = "marvell,orion5x"; interrupt-parent = <&intc>; + aliases { + gpio0 = &gpio0; + }; intc: interrupt-controller { compatible = "marvell,orion-intc", "marvell,intc"; interrupt-controller; @@ -32,7 +35,9 @@ #gpio-cells = <2>; gpio-controller; reg = <0x10100 0x40>; - ngpio = <32>; + ngpios = <32>; + interrupt-controller; + #interrupt-cells = <2>; interrupts = <6>, <7>, <8>, <9>; }; @@ -91,7 +96,7 @@ reg = <0x90000 0x10000>, <0xf2200000 0x800>; reg-names = "regs", "sram"; - interrupts = <22>; + interrupts = <28>; status = "okay"; }; }; diff --git a/arch/arm/include/asm/delay.h b/arch/arm/include/asm/delay.h index 720799f..dff714d 100644 --- a/arch/arm/include/asm/delay.h +++ b/arch/arm/include/asm/delay.h @@ -24,7 +24,7 @@ extern struct arm_delay_ops { void (*delay)(unsigned long); void (*const_udelay)(unsigned long); void (*udelay)(unsigned long); - bool const_clock; + unsigned long ticks_per_jiffy; } arm_delay_ops; #define __delay(n) arm_delay_ops.delay(n) diff --git a/arch/arm/include/asm/glue-cache.h b/arch/arm/include/asm/glue-cache.h index cca9f15..ea289e1 100644 --- a/arch/arm/include/asm/glue-cache.h +++ b/arch/arm/include/asm/glue-cache.h @@ -19,14 +19,6 @@ #undef _CACHE #undef MULTI_CACHE -#if defined(CONFIG_CPU_CACHE_V3) -# ifdef _CACHE -# define MULTI_CACHE 1 -# else -# define _CACHE v3 -# endif -#endif - #if defined(CONFIG_CPU_CACHE_V4) # ifdef _CACHE # define MULTI_CACHE 1 diff --git a/arch/arm/include/asm/hardware/iop3xx.h b/arch/arm/include/asm/hardware/iop3xx.h index 02fe2fb..ed94b1a 100644 --- a/arch/arm/include/asm/hardware/iop3xx.h +++ b/arch/arm/include/asm/hardware/iop3xx.h @@ -37,7 +37,7 @@ extern int iop3xx_get_init_atu(void); * IOP3XX processor registers */ #define IOP3XX_PERIPHERAL_PHYS_BASE 0xffffe000 -#define IOP3XX_PERIPHERAL_VIRT_BASE 0xfeffe000 +#define IOP3XX_PERIPHERAL_VIRT_BASE 0xfedfe000 #define IOP3XX_PERIPHERAL_SIZE 0x00002000 #define IOP3XX_PERIPHERAL_UPPER_PA (IOP3XX_PERIPHERAL_PHYS_BASE +\ IOP3XX_PERIPHERAL_SIZE - 1) diff --git a/arch/arm/include/asm/highmem.h b/arch/arm/include/asm/highmem.h index 8c5e828..91b99ab 100644 --- a/arch/arm/include/asm/highmem.h +++ b/arch/arm/include/asm/highmem.h @@ -41,6 +41,13 @@ extern void kunmap_high(struct page *page); #endif #endif +/* + * Needed to be able to broadcast the TLB invalidation for kmap. + */ +#ifdef CONFIG_ARM_ERRATA_798181 +#undef ARCH_NEEDS_KMAP_HIGH_GET +#endif + #ifdef ARCH_NEEDS_KMAP_HIGH_GET extern void *kmap_high_get(struct page *page); #else diff --git a/arch/arm/include/asm/mmu_context.h b/arch/arm/include/asm/mmu_context.h index 863a661..a7b85e0 100644 --- a/arch/arm/include/asm/mmu_context.h +++ b/arch/arm/include/asm/mmu_context.h @@ -27,6 +27,8 @@ void __check_vmalloc_seq(struct mm_struct *mm); void check_and_switch_context(struct mm_struct *mm, struct task_struct *tsk); #define init_new_context(tsk,mm) ({ atomic64_set(&mm->context.id, 0); 0; }) +DECLARE_PER_CPU(atomic64_t, active_asids); + #else /* !CONFIG_CPU_HAS_ASID */ #ifdef CONFIG_MMU diff --git a/arch/arm/include/asm/pgtable-3level.h b/arch/arm/include/asm/pgtable-3level.h index 6ef8afd..86b8fe3 100644 --- a/arch/arm/include/asm/pgtable-3level.h +++ b/arch/arm/include/asm/pgtable-3level.h @@ -111,7 +111,7 @@ #define L_PTE_S2_MT_WRITETHROUGH (_AT(pteval_t, 0xa) << 2) /* MemAttr[3:0] */ #define L_PTE_S2_MT_WRITEBACK (_AT(pteval_t, 0xf) << 2) /* MemAttr[3:0] */ #define L_PTE_S2_RDONLY (_AT(pteval_t, 1) << 6) /* HAP[1] */ -#define L_PTE_S2_RDWR (_AT(pteval_t, 2) << 6) /* HAP[2:1] */ +#define L_PTE_S2_RDWR (_AT(pteval_t, 3) << 6) /* HAP[2:1] */ /* * Hyp-mode PL2 PTE definitions for LPAE. diff --git a/arch/arm/include/asm/tlbflush.h b/arch/arm/include/asm/tlbflush.h index 4db8c88..ab865e6 100644 --- a/arch/arm/include/asm/tlbflush.h +++ b/arch/arm/include/asm/tlbflush.h @@ -14,7 +14,6 @@ #include <asm/glue.h> -#define TLB_V3_PAGE (1 << 0) #define TLB_V4_U_PAGE (1 << 1) #define TLB_V4_D_PAGE (1 << 2) #define TLB_V4_I_PAGE (1 << 3) @@ -22,7 +21,6 @@ #define TLB_V6_D_PAGE (1 << 5) #define TLB_V6_I_PAGE (1 << 6) -#define TLB_V3_FULL (1 << 8) #define TLB_V4_U_FULL (1 << 9) #define TLB_V4_D_FULL (1 << 10) #define TLB_V4_I_FULL (1 << 11) @@ -52,7 +50,6 @@ * ============= * * We have the following to choose from: - * v3 - ARMv3 * v4 - ARMv4 without write buffer * v4wb - ARMv4 with write buffer without I TLB flush entry instruction * v4wbi - ARMv4 with write buffer with I TLB flush entry instruction @@ -330,7 +327,6 @@ static inline void local_flush_tlb_all(void) if (tlb_flag(TLB_WB)) dsb(); - tlb_op(TLB_V3_FULL, "c6, c0, 0", zero); tlb_op(TLB_V4_U_FULL | TLB_V6_U_FULL, "c8, c7, 0", zero); tlb_op(TLB_V4_D_FULL | TLB_V6_D_FULL, "c8, c6, 0", zero); tlb_op(TLB_V4_I_FULL | TLB_V6_I_FULL, "c8, c5, 0", zero); @@ -351,9 +347,8 @@ static inline void local_flush_tlb_mm(struct mm_struct *mm) if (tlb_flag(TLB_WB)) dsb(); - if (possible_tlb_flags & (TLB_V3_FULL|TLB_V4_U_FULL|TLB_V4_D_FULL|TLB_V4_I_FULL)) { + if (possible_tlb_flags & (TLB_V4_U_FULL|TLB_V4_D_FULL|TLB_V4_I_FULL)) { if (cpumask_test_cpu(get_cpu(), mm_cpumask(mm))) { - tlb_op(TLB_V3_FULL, "c6, c0, 0", zero); tlb_op(TLB_V4_U_FULL, "c8, c7, 0", zero); tlb_op(TLB_V4_D_FULL, "c8, c6, 0", zero); tlb_op(TLB_V4_I_FULL, "c8, c5, 0", zero); @@ -385,9 +380,8 @@ local_flush_tlb_page(struct vm_area_struct *vma, unsigned long uaddr) if (tlb_flag(TLB_WB)) dsb(); - if (possible_tlb_flags & (TLB_V3_PAGE|TLB_V4_U_PAGE|TLB_V4_D_PAGE|TLB_V4_I_PAGE|TLB_V4_I_FULL) && + if (possible_tlb_flags & (TLB_V4_U_PAGE|TLB_V4_D_PAGE|TLB_V4_I_PAGE|TLB_V4_I_FULL) && cpumask_test_cpu(smp_processor_id(), mm_cpumask(vma->vm_mm))) { - tlb_op(TLB_V3_PAGE, "c6, c0, 0", uaddr); tlb_op(TLB_V4_U_PAGE, "c8, c7, 1", uaddr); tlb_op(TLB_V4_D_PAGE, "c8, c6, 1", uaddr); tlb_op(TLB_V4_I_PAGE, "c8, c5, 1", uaddr); @@ -418,7 +412,6 @@ static inline void local_flush_tlb_kernel_page(unsigned long kaddr) if (tlb_flag(TLB_WB)) dsb(); - tlb_op(TLB_V3_PAGE, "c6, c0, 0", kaddr); tlb_op(TLB_V4_U_PAGE, "c8, c7, 1", kaddr); tlb_op(TLB_V4_D_PAGE, "c8, c6, 1", kaddr); tlb_op(TLB_V4_I_PAGE, "c8, c5, 1", kaddr); @@ -450,6 +443,21 @@ static inline void local_flush_bp_all(void) isb(); } +#ifdef CONFIG_ARM_ERRATA_798181 +static inline void dummy_flush_tlb_a15_erratum(void) +{ + /* + * Dummy TLBIMVAIS. Using the unmapped address 0 and ASID 0. + */ + asm("mcr p15, 0, %0, c8, c3, 1" : : "r" (0)); + dsb(); +} +#else +static inline void dummy_flush_tlb_a15_erratum(void) +{ +} +#endif + /* * flush_pmd_entry * diff --git a/arch/arm/kernel/entry-common.S b/arch/arm/kernel/entry-common.S index 3248cde..fefd7f9 100644 --- a/arch/arm/kernel/entry-common.S +++ b/arch/arm/kernel/entry-common.S @@ -276,7 +276,13 @@ ENDPROC(ftrace_graph_caller_old) */ .macro mcount_enter +/* + * This pad compensates for the push {lr} at the call site. Note that we are + * unable to unwind through a function which does not otherwise save its lr. + */ + UNWIND(.pad #4) stmdb sp!, {r0-r3, lr} + UNWIND(.save {r0-r3, lr}) .endm .macro mcount_get_lr reg @@ -289,6 +295,7 @@ ENDPROC(ftrace_graph_caller_old) .endm ENTRY(__gnu_mcount_nc) +UNWIND(.fnstart) #ifdef CONFIG_DYNAMIC_FTRACE mov ip, lr ldmia sp!, {lr} @@ -296,17 +303,22 @@ ENTRY(__gnu_mcount_nc) #else __mcount #endif +UNWIND(.fnend) ENDPROC(__gnu_mcount_nc) #ifdef CONFIG_DYNAMIC_FTRACE ENTRY(ftrace_caller) +UNWIND(.fnstart) __ftrace_caller +UNWIND(.fnend) ENDPROC(ftrace_caller) #endif #ifdef CONFIG_FUNCTION_GRAPH_TRACER ENTRY(ftrace_graph_caller) +UNWIND(.fnstart) __ftrace_graph_caller +UNWIND(.fnend) ENDPROC(ftrace_graph_caller) #endif diff --git a/arch/arm/kernel/head.S b/arch/arm/kernel/head.S index e0eb9a1..8bac553 100644 --- a/arch/arm/kernel/head.S +++ b/arch/arm/kernel/head.S @@ -267,7 +267,7 @@ __create_page_tables: addne r6, r6, #1 << SECTION_SHIFT strne r6, [r3] -#if defined(CONFIG_LPAE) && defined(CONFIG_CPU_ENDIAN_BE8) +#if defined(CONFIG_ARM_LPAE) && defined(CONFIG_CPU_ENDIAN_BE8) sub r4, r4, #4 @ Fixup page table pointer @ for 64-bit descriptors #endif diff --git a/arch/arm/kernel/hw_breakpoint.c b/arch/arm/kernel/hw_breakpoint.c index 96093b7..1fd749e 100644 --- a/arch/arm/kernel/hw_breakpoint.c +++ b/arch/arm/kernel/hw_breakpoint.c @@ -966,7 +966,7 @@ static void reset_ctrl_regs(void *unused) } if (err) { - pr_warning("CPU %d debug is powered down!\n", cpu); + pr_warn_once("CPU %d debug is powered down!\n", cpu); cpumask_or(&debug_err_mask, &debug_err_mask, cpumask_of(cpu)); return; } @@ -987,7 +987,7 @@ clear_vcr: isb(); if (cpumask_intersects(&debug_err_mask, cpumask_of(cpu))) { - pr_warning("CPU %d failed to disable vector catch\n", cpu); + pr_warn_once("CPU %d failed to disable vector catch\n", cpu); return; } @@ -1007,7 +1007,7 @@ clear_vcr: } if (cpumask_intersects(&debug_err_mask, cpumask_of(cpu))) { - pr_warning("CPU %d failed to clear debug register pairs\n", cpu); + pr_warn_once("CPU %d failed to clear debug register pairs\n", cpu); return; } @@ -1043,7 +1043,7 @@ static int dbg_cpu_pm_notify(struct notifier_block *self, unsigned long action, return NOTIFY_OK; } -static struct notifier_block __cpuinitdata dbg_cpu_pm_nb = { +static struct notifier_block dbg_cpu_pm_nb = { .notifier_call = dbg_cpu_pm_notify, }; diff --git a/arch/arm/kernel/perf_event.c b/arch/arm/kernel/perf_event.c index 146157d..8c3094d 100644 --- a/arch/arm/kernel/perf_event.c +++ b/arch/arm/kernel/perf_event.c @@ -253,7 +253,10 @@ validate_event(struct pmu_hw_events *hw_events, struct arm_pmu *armpmu = to_arm_pmu(event->pmu); struct pmu *leader_pmu = event->group_leader->pmu; - if (event->pmu != leader_pmu || event->state <= PERF_EVENT_STATE_OFF) + if (event->pmu != leader_pmu || event->state < PERF_EVENT_STATE_OFF) + return 1; + + if (event->state == PERF_EVENT_STATE_OFF && !event->attr.enable_on_exec) return 1; return armpmu->get_event_idx(hw_events, event) >= 0; diff --git a/arch/arm/kernel/sched_clock.c b/arch/arm/kernel/sched_clock.c index bd6f56b..59d2adb 100644 --- a/arch/arm/kernel/sched_clock.c +++ b/arch/arm/kernel/sched_clock.c @@ -45,12 +45,12 @@ static u32 notrace jiffy_sched_clock_read(void) static u32 __read_mostly (*read_sched_clock)(void) = jiffy_sched_clock_read; -static inline u64 cyc_to_ns(u64 cyc, u32 mult, u32 shift) +static inline u64 notrace cyc_to_ns(u64 cyc, u32 mult, u32 shift) { return (cyc * mult) >> shift; } -static unsigned long long cyc_to_sched_clock(u32 cyc, u32 mask) +static unsigned long long notrace cyc_to_sched_clock(u32 cyc, u32 mask) { u64 epoch_ns; u32 epoch_cyc; diff --git a/arch/arm/kernel/setup.c b/arch/arm/kernel/setup.c index 3f6cbb2..234e339 100644 --- a/arch/arm/kernel/setup.c +++ b/arch/arm/kernel/setup.c @@ -56,7 +56,6 @@ #include <asm/virt.h> #include "atags.h" -#include "tcm.h" #if defined(CONFIG_FPE_NWFPE) || defined(CONFIG_FPE_FASTFPE) @@ -353,6 +352,23 @@ void __init early_print(const char *str, ...) printk("%s", buf); } +static void __init cpuid_init_hwcaps(void) +{ + unsigned int divide_instrs; + + if (cpu_architecture() < CPU_ARCH_ARMv7) + return; + + divide_instrs = (read_cpuid_ext(CPUID_EXT_ISAR0) & 0x0f000000) >> 24; + + switch (divide_instrs) { + case 2: + elf_hwcap |= HWCAP_IDIVA; + case 1: + elf_hwcap |= HWCAP_IDIVT; + } +} + static void __init feat_v6_fixup(void) { int id = read_cpuid_id(); @@ -483,8 +499,11 @@ static void __init setup_processor(void) snprintf(elf_platform, ELF_PLATFORM_SIZE, "%s%c", list->elf_name, ENDIANNESS); elf_hwcap = list->elf_hwcap; + + cpuid_init_hwcaps(); + #ifndef CONFIG_ARM_THUMB - elf_hwcap &= ~HWCAP_THUMB; + elf_hwcap &= ~(HWCAP_THUMB | HWCAP_IDIVT); #endif feat_v6_fixup(); @@ -524,7 +543,7 @@ int __init arm_add_memory(phys_addr_t start, phys_addr_t size) size -= start & ~PAGE_MASK; bank->start = PAGE_ALIGN(start); -#ifndef CONFIG_LPAE +#ifndef CONFIG_ARM_LPAE if (bank->start + size < bank->start) { printk(KERN_CRIT "Truncating memory at 0x%08llx to fit in " "32-bit physical address space\n", (long long)start); @@ -778,8 +797,6 @@ void __init setup_arch(char **cmdline_p) reserve_crashkernel(); - tcm_init(); - #ifdef CONFIG_MULTI_IRQ_HANDLER handle_arch_irq = mdesc->handle_irq; #endif diff --git a/arch/arm/kernel/smp.c b/arch/arm/kernel/smp.c index 79078ed..1f2cccc 100644 --- a/arch/arm/kernel/smp.c +++ b/arch/arm/kernel/smp.c @@ -673,9 +673,6 @@ static int cpufreq_callback(struct notifier_block *nb, if (freq->flags & CPUFREQ_CONST_LOOPS) return NOTIFY_OK; - if (arm_delay_ops.const_clock) - return NOTIFY_OK; - if (!per_cpu(l_p_j_ref, cpu)) { per_cpu(l_p_j_ref, cpu) = per_cpu(cpu_data, cpu).loops_per_jiffy; diff --git a/arch/arm/kernel/smp_tlb.c b/arch/arm/kernel/smp_tlb.c index bd03005..e82e1d2 100644 --- a/arch/arm/kernel/smp_tlb.c +++ b/arch/arm/kernel/smp_tlb.c @@ -12,6 +12,7 @@ #include <asm/smp_plat.h> #include <asm/tlbflush.h> +#include <asm/mmu_context.h> /**********************************************************************/ @@ -69,12 +70,72 @@ static inline void ipi_flush_bp_all(void *ignored) local_flush_bp_all(); } +#ifdef CONFIG_ARM_ERRATA_798181 +static int erratum_a15_798181(void) +{ + unsigned int midr = read_cpuid_id(); + + /* Cortex-A15 r0p0..r3p2 affected */ + if ((midr & 0xff0ffff0) != 0x410fc0f0 || midr > 0x413fc0f2) + return 0; + return 1; +} +#else +static int erratum_a15_798181(void) +{ + return 0; +} +#endif + +static void ipi_flush_tlb_a15_erratum(void *arg) +{ + dmb(); +} + +static void broadcast_tlb_a15_erratum(void) +{ + if (!erratum_a15_798181()) + return; + + dummy_flush_tlb_a15_erratum(); + smp_call_function_many(cpu_online_mask, ipi_flush_tlb_a15_erratum, + NULL, 1); +} + +static void broadcast_tlb_mm_a15_erratum(struct mm_struct *mm) +{ + int cpu; + cpumask_t mask = { CPU_BITS_NONE }; + + if (!erratum_a15_798181()) + return; + + dummy_flush_tlb_a15_erratum(); + for_each_online_cpu(cpu) { + if (cpu == smp_processor_id()) + continue; + /* + * We only need to send an IPI if the other CPUs are running + * the same ASID as the one being invalidated. There is no + * need for locking around the active_asids check since the + * switch_mm() function has at least one dmb() (as required by + * this workaround) in case a context switch happens on + * another CPU after the condition below. + */ + if (atomic64_read(&mm->context.id) == + atomic64_read(&per_cpu(active_asids, cpu))) + cpumask_set_cpu(cpu, &mask); + } + smp_call_function_many(&mask, ipi_flush_tlb_a15_erratum, NULL, 1); +} + void flush_tlb_all(void) { if (tlb_ops_need_broadcast()) on_each_cpu(ipi_flush_tlb_all, NULL, 1); else local_flush_tlb_all(); + broadcast_tlb_a15_erratum(); } void flush_tlb_mm(struct mm_struct *mm) @@ -83,6 +144,7 @@ void flush_tlb_mm(struct mm_struct *mm) on_each_cpu_mask(mm_cpumask(mm), ipi_flush_tlb_mm, mm, 1); else local_flush_tlb_mm(mm); + broadcast_tlb_mm_a15_erratum(mm); } void flush_tlb_page(struct vm_area_struct *vma, unsigned long uaddr) @@ -95,6 +157,7 @@ void flush_tlb_page(struct vm_area_struct *vma, unsigned long uaddr) &ta, 1); } else local_flush_tlb_page(vma, uaddr); + broadcast_tlb_mm_a15_erratum(vma->vm_mm); } void flush_tlb_kernel_page(unsigned long kaddr) @@ -105,6 +168,7 @@ void flush_tlb_kernel_page(unsigned long kaddr) on_each_cpu(ipi_flush_tlb_kernel_page, &ta, 1); } else local_flush_tlb_kernel_page(kaddr); + broadcast_tlb_a15_erratum(); } void flush_tlb_range(struct vm_area_struct *vma, @@ -119,6 +183,7 @@ void flush_tlb_range(struct vm_area_struct *vma, &ta, 1); } else local_flush_tlb_range(vma, start, end); + broadcast_tlb_mm_a15_erratum(vma->vm_mm); } void flush_tlb_kernel_range(unsigned long start, unsigned long end) @@ -130,6 +195,7 @@ void flush_tlb_kernel_range(unsigned long start, unsigned long end) on_each_cpu(ipi_flush_tlb_kernel_range, &ta, 1); } else local_flush_tlb_kernel_range(start, end); + broadcast_tlb_a15_erratum(); } void flush_bp_all(void) diff --git a/arch/arm/kernel/tcm.c b/arch/arm/kernel/tcm.c index 30ae6bb..f50f19e 100644 --- a/arch/arm/kernel/tcm.c +++ b/arch/arm/kernel/tcm.c @@ -17,7 +17,6 @@ #include <asm/mach/map.h> #include <asm/memory.h> #include <asm/system_info.h> -#include "tcm.h" static struct gen_pool *tcm_pool; static bool dtcm_present; diff --git a/arch/arm/kvm/arm.c b/arch/arm/kvm/arm.c index 5a93698..c1fe498 100644 --- a/arch/arm/kvm/arm.c +++ b/arch/arm/kvm/arm.c @@ -201,6 +201,7 @@ int kvm_dev_ioctl_check_extension(long ext) break; case KVM_CAP_ARM_SET_DEVICE_ADDR: r = 1; + break; case KVM_CAP_NR_VCPUS: r = num_online_cpus(); break; diff --git a/arch/arm/kvm/coproc.c b/arch/arm/kvm/coproc.c index 4ea9a98..7bed755 100644 --- a/arch/arm/kvm/coproc.c +++ b/arch/arm/kvm/coproc.c @@ -79,11 +79,11 @@ static bool access_dcsw(struct kvm_vcpu *vcpu, u32 val; int cpu; - cpu = get_cpu(); - if (!p->is_write) return read_from_write_only(vcpu, p); + cpu = get_cpu(); + cpumask_setall(&vcpu->arch.require_dcache_flush); cpumask_clear_cpu(cpu, &vcpu->arch.require_dcache_flush); diff --git a/arch/arm/kvm/vgic.c b/arch/arm/kvm/vgic.c index c9a1731..0e4cfe1 100644 --- a/arch/arm/kvm/vgic.c +++ b/arch/arm/kvm/vgic.c @@ -883,8 +883,7 @@ static bool vgic_queue_irq(struct kvm_vcpu *vcpu, u8 sgi_source_id, int irq) lr, irq, vgic_cpu->vgic_lr[lr]); BUG_ON(!test_bit(lr, vgic_cpu->lr_used)); vgic_cpu->vgic_lr[lr] |= GICH_LR_PENDING_BIT; - - goto out; + return true; } /* Try to use another LR for this interrupt */ @@ -898,7 +897,6 @@ static bool vgic_queue_irq(struct kvm_vcpu *vcpu, u8 sgi_source_id, int irq) vgic_cpu->vgic_irq_lr_map[irq] = lr; set_bit(lr, vgic_cpu->lr_used); -out: if (!vgic_irq_is_edge(vcpu, irq)) vgic_cpu->vgic_lr[lr] |= GICH_LR_EOI; @@ -1018,21 +1016,6 @@ static bool vgic_process_maintenance(struct kvm_vcpu *vcpu) kvm_debug("MISR = %08x\n", vgic_cpu->vgic_misr); - /* - * We do not need to take the distributor lock here, since the only - * action we perform is clearing the irq_active_bit for an EOIed - * level interrupt. There is a potential race with - * the queuing of an interrupt in __kvm_vgic_flush_hwstate(), where we - * check if the interrupt is already active. Two possibilities: - * - * - The queuing is occurring on the same vcpu: cannot happen, - * as we're already in the context of this vcpu, and - * executing the handler - * - The interrupt has been migrated to another vcpu, and we - * ignore this interrupt for this run. Big deal. It is still - * pending though, and will get considered when this vcpu - * exits. - */ if (vgic_cpu->vgic_misr & GICH_MISR_EOI) { /* * Some level interrupts have been EOIed. Clear their @@ -1054,6 +1037,13 @@ static bool vgic_process_maintenance(struct kvm_vcpu *vcpu) } else { vgic_cpu_irq_clear(vcpu, irq); } + + /* + * Despite being EOIed, the LR may not have + * been marked as empty. + */ + set_bit(lr, (unsigned long *)vgic_cpu->vgic_elrsr); + vgic_cpu->vgic_lr[lr] &= ~GICH_LR_ACTIVE_BIT; } } @@ -1064,9 +1054,8 @@ static bool vgic_process_maintenance(struct kvm_vcpu *vcpu) } /* - * Sync back the VGIC state after a guest run. We do not really touch - * the distributor here (the irq_pending_on_cpu bit is safe to set), - * so there is no need for taking its lock. + * Sync back the VGIC state after a guest run. The distributor lock is + * needed so we don't get preempted in the middle of the state processing. */ static void __kvm_vgic_sync_hwstate(struct kvm_vcpu *vcpu) { @@ -1112,10 +1101,14 @@ void kvm_vgic_flush_hwstate(struct kvm_vcpu *vcpu) void kvm_vgic_sync_hwstate(struct kvm_vcpu *vcpu) { + struct vgic_dist *dist = &vcpu->kvm->arch.vgic; + if (!irqchip_in_kernel(vcpu->kvm)) return; + spin_lock(&dist->lock); __kvm_vgic_sync_hwstate(vcpu); + spin_unlock(&dist->lock); } int kvm_vgic_vcpu_pending_irq(struct kvm_vcpu *vcpu) diff --git a/arch/arm/lib/delay.c b/arch/arm/lib/delay.c index 6b93f6a..64dbfa5 100644 --- a/arch/arm/lib/delay.c +++ b/arch/arm/lib/delay.c @@ -58,7 +58,7 @@ static void __timer_delay(unsigned long cycles) static void __timer_const_udelay(unsigned long xloops) { unsigned long long loops = xloops; - loops *= loops_per_jiffy; + loops *= arm_delay_ops.ticks_per_jiffy; __timer_delay(loops >> UDELAY_SHIFT); } @@ -73,11 +73,13 @@ void __init register_current_timer_delay(const struct delay_timer *timer) pr_info("Switching to timer-based delay loop\n"); delay_timer = timer; lpj_fine = timer->freq / HZ; - loops_per_jiffy = lpj_fine; + + /* cpufreq may scale loops_per_jiffy, so keep a private copy */ + arm_delay_ops.ticks_per_jiffy = lpj_fine; arm_delay_ops.delay = __timer_delay; arm_delay_ops.const_udelay = __timer_const_udelay; arm_delay_ops.udelay = __timer_udelay; - arm_delay_ops.const_clock = true; + delay_calibrated = true; } else { pr_info("Ignoring duplicate/late registration of read_current_timer delay\n"); diff --git a/arch/arm/mach-cns3xxx/core.c b/arch/arm/mach-cns3xxx/core.c index e698f26..52e4bb5 100644 --- a/arch/arm/mach-cns3xxx/core.c +++ b/arch/arm/mach-cns3xxx/core.c @@ -22,19 +22,9 @@ static struct map_desc cns3xxx_io_desc[] __initdata = { { - .virtual = CNS3XXX_TC11MP_TWD_BASE_VIRT, - .pfn = __phys_to_pfn(CNS3XXX_TC11MP_TWD_BASE), - .length = SZ_4K, - .type = MT_DEVICE, - }, { - .virtual = CNS3XXX_TC11MP_GIC_CPU_BASE_VIRT, - .pfn = __phys_to_pfn(CNS3XXX_TC11MP_GIC_CPU_BASE), - .length = SZ_4K, - .type = MT_DEVICE, - }, { - .virtual = CNS3XXX_TC11MP_GIC_DIST_BASE_VIRT, - .pfn = __phys_to_pfn(CNS3XXX_TC11MP_GIC_DIST_BASE), - .length = SZ_4K, + .virtual = CNS3XXX_TC11MP_SCU_BASE_VIRT, + .pfn = __phys_to_pfn(CNS3XXX_TC11MP_SCU_BASE), + .length = SZ_8K, .type = MT_DEVICE, }, { .virtual = CNS3XXX_TIMER1_2_3_BASE_VIRT, diff --git a/arch/arm/mach-cns3xxx/include/mach/cns3xxx.h b/arch/arm/mach-cns3xxx/include/mach/cns3xxx.h index 191c8e5..b1021aa 100644 --- a/arch/arm/mach-cns3xxx/include/mach/cns3xxx.h +++ b/arch/arm/mach-cns3xxx/include/mach/cns3xxx.h @@ -94,10 +94,10 @@ #define RTC_INTR_STS_OFFSET 0x34 #define CNS3XXX_MISC_BASE 0x76000000 /* Misc Control */ -#define CNS3XXX_MISC_BASE_VIRT 0xFFF07000 /* Misc Control */ +#define CNS3XXX_MISC_BASE_VIRT 0xFB000000 /* Misc Control */ #define CNS3XXX_PM_BASE 0x77000000 /* Power Management Control */ -#define CNS3XXX_PM_BASE_VIRT 0xFFF08000 +#define CNS3XXX_PM_BASE_VIRT 0xFB001000 #define PM_CLK_GATE_OFFSET 0x00 #define PM_SOFT_RST_OFFSET 0x04 @@ -109,7 +109,7 @@ #define PM_PLL_HM_PD_OFFSET 0x1C #define CNS3XXX_UART0_BASE 0x78000000 /* UART 0 */ -#define CNS3XXX_UART0_BASE_VIRT 0xFFF09000 +#define CNS3XXX_UART0_BASE_VIRT 0xFB002000 #define CNS3XXX_UART1_BASE 0x78400000 /* UART 1 */ #define CNS3XXX_UART1_BASE_VIRT 0xFFF0A000 @@ -130,7 +130,7 @@ #define CNS3XXX_I2S_BASE_VIRT 0xFFF10000 #define CNS3XXX_TIMER1_2_3_BASE 0x7C800000 /* Timer */ -#define CNS3XXX_TIMER1_2_3_BASE_VIRT 0xFFF10800 +#define CNS3XXX_TIMER1_2_3_BASE_VIRT 0xFB003000 #define TIMER1_COUNTER_OFFSET 0x00 #define TIMER1_AUTO_RELOAD_OFFSET 0x04 @@ -227,16 +227,16 @@ * Testchip peripheral and fpga gic regions */ #define CNS3XXX_TC11MP_SCU_BASE 0x90000000 /* IRQ, Test chip */ -#define CNS3XXX_TC11MP_SCU_BASE_VIRT 0xFF000000 +#define CNS3XXX_TC11MP_SCU_BASE_VIRT 0xFB004000 #define CNS3XXX_TC11MP_GIC_CPU_BASE 0x90000100 /* Test chip interrupt controller CPU interface */ -#define CNS3XXX_TC11MP_GIC_CPU_BASE_VIRT 0xFF000100 +#define CNS3XXX_TC11MP_GIC_CPU_BASE_VIRT (CNS3XXX_TC11MP_SCU_BASE_VIRT + 0x100) #define CNS3XXX_TC11MP_TWD_BASE 0x90000600 -#define CNS3XXX_TC11MP_TWD_BASE_VIRT 0xFF000600 +#define CNS3XXX_TC11MP_TWD_BASE_VIRT (CNS3XXX_TC11MP_SCU_BASE_VIRT + 0x600) #define CNS3XXX_TC11MP_GIC_DIST_BASE 0x90001000 /* Test chip interrupt controller distributor */ -#define CNS3XXX_TC11MP_GIC_DIST_BASE_VIRT 0xFF001000 +#define CNS3XXX_TC11MP_GIC_DIST_BASE_VIRT (CNS3XXX_TC11MP_SCU_BASE_VIRT + 0x1000) #define CNS3XXX_TC11MP_L220_BASE 0x92002000 /* L220 registers */ #define CNS3XXX_TC11MP_L220_BASE_VIRT 0xFF002000 diff --git a/arch/arm/mach-ep93xx/include/mach/uncompress.h b/arch/arm/mach-ep93xx/include/mach/uncompress.h index d2afb4d..b5cc77d 100644 --- a/arch/arm/mach-ep93xx/include/mach/uncompress.h +++ b/arch/arm/mach-ep93xx/include/mach/uncompress.h @@ -47,9 +47,13 @@ static void __raw_writel(unsigned int value, unsigned int ptr) static inline void putc(int c) { - /* Transmit fifo not full? */ - while (__raw_readb(PHYS_UART_FLAG) & UART_FLAG_TXFF) - ; + int i; + + for (i = 0; i < 10000; i++) { + /* Transmit fifo not full? */ + if (!(__raw_readb(PHYS_UART_FLAG) & UART_FLAG_TXFF)) + break; + } __raw_writeb(c, PHYS_UART_DATA); } diff --git a/arch/arm/mach-highbank/hotplug.c b/arch/arm/mach-highbank/hotplug.c index f30c528..890cae2 100644 --- a/arch/arm/mach-highbank/hotplug.c +++ b/arch/arm/mach-highbank/hotplug.c @@ -28,13 +28,11 @@ extern void secondary_startup(void); */ void __ref highbank_cpu_die(unsigned int cpu) { - flush_cache_all(); - highbank_set_cpu_jump(cpu, phys_to_virt(0)); - highbank_set_core_pwr(); - cpu_do_idle(); + flush_cache_louis(); + highbank_set_core_pwr(); - /* We should never return from idle */ - panic("highbank: cpu %d unexpectedly exit from shutdown\n", cpu); + while (1) + cpu_do_idle(); } diff --git a/arch/arm/mach-imx/clk-imx35.c b/arch/arm/mach-imx/clk-imx35.c index e13a8fa..2193c83 100644 --- a/arch/arm/mach-imx/clk-imx35.c +++ b/arch/arm/mach-imx/clk-imx35.c @@ -257,6 +257,7 @@ int __init mx35_clocks_init(void) clk_register_clkdev(clk[wdog_gate], NULL, "imx2-wdt.0"); clk_register_clkdev(clk[nfc_div], NULL, "imx25-nand.0"); clk_register_clkdev(clk[csi_gate], NULL, "mx3-camera.0"); + clk_register_clkdev(clk[admux_gate], "audmux", NULL); clk_prepare_enable(clk[spba_gate]); clk_prepare_enable(clk[gpio1_gate]); @@ -265,6 +266,7 @@ int __init mx35_clocks_init(void) clk_prepare_enable(clk[iim_gate]); clk_prepare_enable(clk[emi_gate]); clk_prepare_enable(clk[max_gate]); + clk_prepare_enable(clk[iomuxc_gate]); /* * SCC is needed to boot via mmc after a watchdog reset. The clock code diff --git a/arch/arm/mach-imx/clk-imx6q.c b/arch/arm/mach-imx/clk-imx6q.c index 2f9ff93..d38e54f 100644 --- a/arch/arm/mach-imx/clk-imx6q.c +++ b/arch/arm/mach-imx/clk-imx6q.c @@ -115,7 +115,7 @@ static const char *gpu2d_core_sels[] = { "axi", "pll3_usb_otg", "pll2_pfd0_352m" static const char *gpu3d_core_sels[] = { "mmdc_ch0_axi", "pll3_usb_otg", "pll2_pfd1_594m", "pll2_pfd2_396m", }; static const char *gpu3d_shader_sels[] = { "mmdc_ch0_axi", "pll3_usb_otg", "pll2_pfd1_594m", "pll2_pfd9_720m", }; static const char *ipu_sels[] = { "mmdc_ch0_axi", "pll2_pfd2_396m", "pll3_120m", "pll3_pfd1_540m", }; -static const char *ldb_di_sels[] = { "pll5_video", "pll2_pfd0_352m", "pll2_pfd2_396m", "mmdc_ch1_axi", "pll3_pfd1_540m", }; +static const char *ldb_di_sels[] = { "pll5_video", "pll2_pfd0_352m", "pll2_pfd2_396m", "mmdc_ch1_axi", "pll3_usb_otg", }; static const char *ipu_di_pre_sels[] = { "mmdc_ch0_axi", "pll3_usb_otg", "pll5_video", "pll2_pfd0_352m", "pll2_pfd2_396m", "pll3_pfd1_540m", }; static const char *ipu1_di0_sels[] = { "ipu1_di0_pre", "dummy", "dummy", "ldb_di0", "ldb_di1", }; static const char *ipu1_di1_sels[] = { "ipu1_di1_pre", "dummy", "dummy", "ldb_di0", "ldb_di1", }; @@ -443,7 +443,6 @@ int __init mx6q_clocks_init(void) clk_register_clkdev(clk[gpt_ipg], "ipg", "imx-gpt.0"); clk_register_clkdev(clk[gpt_ipg_per], "per", "imx-gpt.0"); - clk_register_clkdev(clk[twd], NULL, "smp_twd"); clk_register_clkdev(clk[cko1_sel], "cko1_sel", NULL); clk_register_clkdev(clk[ahb], "ahb", NULL); clk_register_clkdev(clk[cko1], "cko1", NULL); diff --git a/arch/arm/mach-imx/common.h b/arch/arm/mach-imx/common.h index 5a800bf..5bf4a97 100644 --- a/arch/arm/mach-imx/common.h +++ b/arch/arm/mach-imx/common.h @@ -110,6 +110,8 @@ void tzic_handle_irq(struct pt_regs *); extern void imx_enable_cpu(int cpu, bool enable); extern void imx_set_cpu_jump(int cpu, void *jump_addr); +extern u32 imx_get_cpu_arg(int cpu); +extern void imx_set_cpu_arg(int cpu, u32 arg); extern void v7_cpu_resume(void); extern u32 *pl310_get_save_ptr(void); #ifdef CONFIG_SMP diff --git a/arch/arm/mach-imx/hotplug.c b/arch/arm/mach-imx/hotplug.c index 7bc5fe1..361a253 100644 --- a/arch/arm/mach-imx/hotplug.c +++ b/arch/arm/mach-imx/hotplug.c @@ -46,11 +46,23 @@ static inline void cpu_enter_lowpower(void) void imx_cpu_die(unsigned int cpu) { cpu_enter_lowpower(); + /* + * We use the cpu jumping argument register to sync with + * imx_cpu_kill() which is running on cpu0 and waiting for + * the register being cleared to kill the cpu. + */ + imx_set_cpu_arg(cpu, ~0); cpu_do_idle(); } int imx_cpu_kill(unsigned int cpu) { + unsigned long timeout = jiffies + msecs_to_jiffies(50); + + while (imx_get_cpu_arg(cpu) == 0) + if (time_after(jiffies, timeout)) + return 0; imx_enable_cpu(cpu, false); + imx_set_cpu_arg(cpu, 0); return 1; } diff --git a/arch/arm/mach-imx/src.c b/arch/arm/mach-imx/src.c index e15f155..09a742f 100644 --- a/arch/arm/mach-imx/src.c +++ b/arch/arm/mach-imx/src.c @@ -43,6 +43,18 @@ void imx_set_cpu_jump(int cpu, void *jump_addr) src_base + SRC_GPR1 + cpu * 8); } +u32 imx_get_cpu_arg(int cpu) +{ + cpu = cpu_logical_map(cpu); + return readl_relaxed(src_base + SRC_GPR1 + cpu * 8 + 4); +} + +void imx_set_cpu_arg(int cpu, u32 arg) +{ + cpu = cpu_logical_map(cpu); + writel_relaxed(arg, src_base + SRC_GPR1 + cpu * 8 + 4); +} + void imx_src_prepare_restart(void) { u32 val; diff --git a/arch/arm/mach-kirkwood/board-iomega_ix2_200.c b/arch/arm/mach-kirkwood/board-iomega_ix2_200.c index f655b26..e5f7041 100644 --- a/arch/arm/mach-kirkwood/board-iomega_ix2_200.c +++ b/arch/arm/mach-kirkwood/board-iomega_ix2_200.c @@ -20,10 +20,15 @@ static struct mv643xx_eth_platform_data iomega_ix2_200_ge00_data = { .duplex = DUPLEX_FULL, }; +static struct mv643xx_eth_platform_data iomega_ix2_200_ge01_data = { + .phy_addr = MV643XX_ETH_PHY_ADDR(11), +}; + void __init iomega_ix2_200_init(void) { /* * Basic setup. Needs to be called early. */ - kirkwood_ge01_init(&iomega_ix2_200_ge00_data); + kirkwood_ge00_init(&iomega_ix2_200_ge00_data); + kirkwood_ge01_init(&iomega_ix2_200_ge01_data); } diff --git a/arch/arm/mach-kirkwood/guruplug-setup.c b/arch/arm/mach-kirkwood/guruplug-setup.c index 1c6e736..08dd739 100644 --- a/arch/arm/mach-kirkwood/guruplug-setup.c +++ b/arch/arm/mach-kirkwood/guruplug-setup.c @@ -53,6 +53,8 @@ static struct mv_sata_platform_data guruplug_sata_data = { static struct mvsdio_platform_data guruplug_mvsdio_data = { /* unfortunately the CD signal has not been connected */ + .gpio_card_detect = -1, + .gpio_write_protect = -1, }; static struct gpio_led guruplug_led_pins[] = { diff --git a/arch/arm/mach-kirkwood/openrd-setup.c b/arch/arm/mach-kirkwood/openrd-setup.c index 8ddd69f..6a6eb54 100644 --- a/arch/arm/mach-kirkwood/openrd-setup.c +++ b/arch/arm/mach-kirkwood/openrd-setup.c @@ -55,6 +55,7 @@ static struct mv_sata_platform_data openrd_sata_data = { static struct mvsdio_platform_data openrd_mvsdio_data = { .gpio_card_detect = 29, /* MPP29 used as SD card detect */ + .gpio_write_protect = -1, }; static unsigned int openrd_mpp_config[] __initdata = { diff --git a/arch/arm/mach-kirkwood/rd88f6281-setup.c b/arch/arm/mach-kirkwood/rd88f6281-setup.c index c7d93b4..d242231 100644 --- a/arch/arm/mach-kirkwood/rd88f6281-setup.c +++ b/arch/arm/mach-kirkwood/rd88f6281-setup.c @@ -69,6 +69,7 @@ static struct mv_sata_platform_data rd88f6281_sata_data = { static struct mvsdio_platform_data rd88f6281_mvsdio_data = { .gpio_card_detect = 28, + .gpio_write_protect = -1, }; static unsigned int rd88f6281_mpp_config[] __initdata = { diff --git a/arch/arm/mach-msm/timer.c b/arch/arm/mach-msm/timer.c index 2969027..f9fd77e 100644 --- a/arch/arm/mach-msm/timer.c +++ b/arch/arm/mach-msm/timer.c @@ -62,7 +62,10 @@ static int msm_timer_set_next_event(unsigned long cycles, { u32 ctrl = readl_relaxed(event_base + TIMER_ENABLE); - writel_relaxed(0, event_base + TIMER_CLEAR); + ctrl &= ~TIMER_ENABLE_EN; + writel_relaxed(ctrl, event_base + TIMER_ENABLE); + + writel_relaxed(ctrl, event_base + TIMER_CLEAR); writel_relaxed(cycles, event_base + TIMER_MATCH_VAL); writel_relaxed(ctrl | TIMER_ENABLE_EN, event_base + TIMER_ENABLE); return 0; diff --git a/arch/arm/mach-mvebu/irq-armada-370-xp.c b/arch/arm/mach-mvebu/irq-armada-370-xp.c index 274ff58..d5970f5 100644 --- a/arch/arm/mach-mvebu/irq-armada-370-xp.c +++ b/arch/arm/mach-mvebu/irq-armada-370-xp.c @@ -44,6 +44,8 @@ #define ARMADA_370_XP_MAX_PER_CPU_IRQS (28) +#define ARMADA_370_XP_TIMER0_PER_CPU_IRQ (5) + #define ACTIVE_DOORBELLS (8) static DEFINE_RAW_SPINLOCK(irq_controller_lock); @@ -59,36 +61,26 @@ static struct irq_domain *armada_370_xp_mpic_domain; */ static void armada_370_xp_irq_mask(struct irq_data *d) { -#ifdef CONFIG_SMP irq_hw_number_t hwirq = irqd_to_hwirq(d); - if (hwirq > ARMADA_370_XP_MAX_PER_CPU_IRQS) + if (hwirq != ARMADA_370_XP_TIMER0_PER_CPU_IRQ) writel(hwirq, main_int_base + ARMADA_370_XP_INT_CLEAR_ENABLE_OFFS); else writel(hwirq, per_cpu_int_base + ARMADA_370_XP_INT_SET_MASK_OFFS); -#else - writel(irqd_to_hwirq(d), - per_cpu_int_base + ARMADA_370_XP_INT_SET_MASK_OFFS); -#endif } static void armada_370_xp_irq_unmask(struct irq_data *d) { -#ifdef CONFIG_SMP irq_hw_number_t hwirq = irqd_to_hwirq(d); - if (hwirq > ARMADA_370_XP_MAX_PER_CPU_IRQS) + if (hwirq != ARMADA_370_XP_TIMER0_PER_CPU_IRQ) writel(hwirq, main_int_base + ARMADA_370_XP_INT_SET_ENABLE_OFFS); else writel(hwirq, per_cpu_int_base + ARMADA_370_XP_INT_CLEAR_MASK_OFFS); -#else - writel(irqd_to_hwirq(d), - per_cpu_int_base + ARMADA_370_XP_INT_CLEAR_MASK_OFFS); -#endif } #ifdef CONFIG_SMP @@ -144,10 +136,14 @@ static int armada_370_xp_mpic_irq_map(struct irq_domain *h, unsigned int virq, irq_hw_number_t hw) { armada_370_xp_irq_mask(irq_get_irq_data(virq)); - writel(hw, main_int_base + ARMADA_370_XP_INT_SET_ENABLE_OFFS); + if (hw != ARMADA_370_XP_TIMER0_PER_CPU_IRQ) + writel(hw, per_cpu_int_base + + ARMADA_370_XP_INT_CLEAR_MASK_OFFS); + else + writel(hw, main_int_base + ARMADA_370_XP_INT_SET_ENABLE_OFFS); irq_set_status_flags(virq, IRQ_LEVEL); - if (hw < ARMADA_370_XP_MAX_PER_CPU_IRQS) { + if (hw == ARMADA_370_XP_TIMER0_PER_CPU_IRQ) { irq_set_percpu_devid(virq); irq_set_chip_and_handler(virq, &armada_370_xp_irq_chip, handle_percpu_devid_irq); diff --git a/arch/arm/mach-omap1/clock_data.c b/arch/arm/mach-omap1/clock_data.c index cb7c6ae..6c4f766 100644 --- a/arch/arm/mach-omap1/clock_data.c +++ b/arch/arm/mach-omap1/clock_data.c @@ -543,15 +543,6 @@ static struct clk usb_dc_ck = { /* Direct from ULPD, no parent */ .rate = 48000000, .enable_reg = OMAP1_IO_ADDRESS(SOFT_REQ_REG), - .enable_bit = USB_REQ_EN_SHIFT, -}; - -static struct clk usb_dc_ck7xx = { - .name = "usb_dc_ck", - .ops = &clkops_generic, - /* Direct from ULPD, no parent */ - .rate = 48000000, - .enable_reg = OMAP1_IO_ADDRESS(SOFT_REQ_REG), .enable_bit = SOFT_USB_OTG_DPLL_REQ_SHIFT, }; @@ -727,8 +718,7 @@ static struct omap_clk omap_clks[] = { CLK(NULL, "usb_clko", &usb_clko, CK_16XX | CK_1510 | CK_310), CLK(NULL, "usb_hhc_ck", &usb_hhc_ck1510, CK_1510 | CK_310), CLK(NULL, "usb_hhc_ck", &usb_hhc_ck16xx, CK_16XX), - CLK(NULL, "usb_dc_ck", &usb_dc_ck, CK_16XX), - CLK(NULL, "usb_dc_ck", &usb_dc_ck7xx, CK_7XX), + CLK(NULL, "usb_dc_ck", &usb_dc_ck, CK_16XX | CK_7XX), CLK(NULL, "mclk", &mclk_1510, CK_1510 | CK_310), CLK(NULL, "mclk", &mclk_16xx, CK_16XX), CLK(NULL, "bclk", &bclk_1510, CK_1510 | CK_310), diff --git a/arch/arm/mach-omap2/cclock44xx_data.c b/arch/arm/mach-omap2/cclock44xx_data.c index 3d58f33..0c6834a 100644 --- a/arch/arm/mach-omap2/cclock44xx_data.c +++ b/arch/arm/mach-omap2/cclock44xx_data.c @@ -52,6 +52,13 @@ */ #define OMAP4_DPLL_ABE_DEFFREQ 98304000 +/* + * OMAP4 USB DPLL default frequency. In OMAP4430 TRM version V, section + * "3.6.3.9.5 DPLL_USB Preferred Settings" shows that the preferred + * locked frequency for the USB DPLL is 960MHz. + */ +#define OMAP4_DPLL_USB_DEFFREQ 960000000 + /* Root clocks */ DEFINE_CLK_FIXED_RATE(extalt_clkin_ck, CLK_IS_ROOT, 59000000, 0x0); @@ -1011,6 +1018,10 @@ DEFINE_CLK_OMAP_MUX(hsmmc2_fclk, "l3_init_clkdm", hsmmc1_fclk_sel, OMAP4430_CM_L3INIT_MMC2_CLKCTRL, OMAP4430_CLKSEL_MASK, hsmmc1_fclk_parents, func_dmic_abe_gfclk_ops); +DEFINE_CLK_GATE(ocp2scp_usb_phy_phy_48m, "func_48m_fclk", &func_48m_fclk, 0x0, + OMAP4430_CM_L3INIT_USBPHYOCP2SCP_CLKCTRL, + OMAP4430_OPTFCLKEN_PHY_48M_SHIFT, 0x0, NULL); + DEFINE_CLK_GATE(sha2md5_fck, "l3_div_ck", &l3_div_ck, 0x0, OMAP4430_CM_L4SEC_SHA2MD51_CLKCTRL, OMAP4430_MODULEMODE_SWCTRL_SHIFT, 0x0, NULL); @@ -1538,6 +1549,7 @@ static struct omap_clk omap44xx_clks[] = { CLK(NULL, "per_mcbsp4_gfclk", &per_mcbsp4_gfclk, CK_443X), CLK(NULL, "hsmmc1_fclk", &hsmmc1_fclk, CK_443X), CLK(NULL, "hsmmc2_fclk", &hsmmc2_fclk, CK_443X), + CLK(NULL, "ocp2scp_usb_phy_phy_48m", &ocp2scp_usb_phy_phy_48m, CK_443X), CLK(NULL, "sha2md5_fck", &sha2md5_fck, CK_443X), CLK(NULL, "slimbus1_fclk_1", &slimbus1_fclk_1, CK_443X), CLK(NULL, "slimbus1_fclk_0", &slimbus1_fclk_0, CK_443X), @@ -1705,5 +1717,13 @@ int __init omap4xxx_clk_init(void) if (rc) pr_err("%s: failed to configure ABE DPLL!\n", __func__); + /* + * Lock USB DPLL on OMAP4 devices so that the L3INIT power + * domain can transition to retention state when not in use. + */ + rc = clk_set_rate(&dpll_usb_ck, OMAP4_DPLL_USB_DEFFREQ); + if (rc) + pr_err("%s: failed to configure USB DPLL!\n", __func__); + return 0; } diff --git a/arch/arm/mach-omap2/common.h b/arch/arm/mach-omap2/common.h index 40f4a03..d6ba13e 100644 --- a/arch/arm/mach-omap2/common.h +++ b/arch/arm/mach-omap2/common.h @@ -293,5 +293,8 @@ extern void omap_reserve(void); struct omap_hwmod; extern int omap_dss_reset(struct omap_hwmod *); +/* SoC specific clock initializer */ +extern int (*omap_clk_init)(void); + #endif /* __ASSEMBLER__ */ #endif /* __ARCH_ARM_MACH_OMAP2PLUS_COMMON_H */ diff --git a/arch/arm/mach-omap2/io.c b/arch/arm/mach-omap2/io.c index 2c3fdd6..5c445ca 100644 --- a/arch/arm/mach-omap2/io.c +++ b/arch/arm/mach-omap2/io.c @@ -55,6 +55,12 @@ #include "prm44xx.h" /* + * omap_clk_init: points to a function that does the SoC-specific + * clock initializations + */ +int (*omap_clk_init)(void); + +/* * The machine specific code may provide the extra mapping besides the * default mapping provided here. */ @@ -397,7 +403,7 @@ void __init omap2420_init_early(void) omap242x_clockdomains_init(); omap2420_hwmod_init(); omap_hwmod_init_postsetup(); - omap2420_clk_init(); + omap_clk_init = omap2420_clk_init; } void __init omap2420_init_late(void) @@ -427,7 +433,7 @@ void __init omap2430_init_early(void) omap243x_clockdomains_init(); omap2430_hwmod_init(); omap_hwmod_init_postsetup(); - omap2430_clk_init(); + omap_clk_init = omap2430_clk_init; } void __init omap2430_init_late(void) @@ -462,7 +468,7 @@ void __init omap3_init_early(void) omap3xxx_clockdomains_init(); omap3xxx_hwmod_init(); omap_hwmod_init_postsetup(); - omap3xxx_clk_init(); + omap_clk_init = omap3xxx_clk_init; } void __init omap3430_init_early(void) @@ -500,7 +506,7 @@ void __init ti81xx_init_early(void) omap3xxx_clockdomains_init(); omap3xxx_hwmod_init(); omap_hwmod_init_postsetup(); - omap3xxx_clk_init(); + omap_clk_init = omap3xxx_clk_init; } void __init omap3_init_late(void) @@ -568,7 +574,7 @@ void __init am33xx_init_early(void) am33xx_clockdomains_init(); am33xx_hwmod_init(); omap_hwmod_init_postsetup(); - am33xx_clk_init(); + omap_clk_init = am33xx_clk_init; } #endif @@ -593,7 +599,7 @@ void __init omap4430_init_early(void) omap44xx_clockdomains_init(); omap44xx_hwmod_init(); omap_hwmod_init_postsetup(); - omap4xxx_clk_init(); + omap_clk_init = omap4xxx_clk_init; } void __init omap4430_init_late(void) diff --git a/arch/arm/mach-omap2/omap_hwmod.c b/arch/arm/mach-omap2/omap_hwmod.c index c2c798c..a202a47 100644 --- a/arch/arm/mach-omap2/omap_hwmod.c +++ b/arch/arm/mach-omap2/omap_hwmod.c @@ -1368,7 +1368,9 @@ static void _enable_sysc(struct omap_hwmod *oh) } if (sf & SYSC_HAS_MIDLEMODE) { - if (oh->flags & HWMOD_SWSUP_MSTANDBY) { + if (oh->flags & HWMOD_FORCE_MSTANDBY) { + idlemode = HWMOD_IDLEMODE_FORCE; + } else if (oh->flags & HWMOD_SWSUP_MSTANDBY) { idlemode = HWMOD_IDLEMODE_NO; } else { if (sf & SYSC_HAS_ENAWAKEUP) @@ -1440,7 +1442,8 @@ static void _idle_sysc(struct omap_hwmod *oh) } if (sf & SYSC_HAS_MIDLEMODE) { - if (oh->flags & HWMOD_SWSUP_MSTANDBY) { + if ((oh->flags & HWMOD_SWSUP_MSTANDBY) || + (oh->flags & HWMOD_FORCE_MSTANDBY)) { idlemode = HWMOD_IDLEMODE_FORCE; } else { if (sf & SYSC_HAS_ENAWAKEUP) diff --git a/arch/arm/mach-omap2/omap_hwmod.h b/arch/arm/mach-omap2/omap_hwmod.h index d43d9b6..d5dc935 100644 --- a/arch/arm/mach-omap2/omap_hwmod.h +++ b/arch/arm/mach-omap2/omap_hwmod.h @@ -427,8 +427,8 @@ struct omap_hwmod_omap4_prcm { * * HWMOD_SWSUP_SIDLE: omap_hwmod code should manually bring module in and out * of idle, rather than relying on module smart-idle - * HWMOD_SWSUP_MSTDBY: omap_hwmod code should manually bring module in and out - * of standby, rather than relying on module smart-standby + * HWMOD_SWSUP_MSTANDBY: omap_hwmod code should manually bring module in and + * out of standby, rather than relying on module smart-standby * HWMOD_INIT_NO_RESET: don't reset this module at boot - important for * SDRAM controller, etc. XXX probably belongs outside the main hwmod file * XXX Should be HWMOD_SETUP_NO_RESET @@ -459,6 +459,10 @@ struct omap_hwmod_omap4_prcm { * correctly, or this is being abused to deal with some PM latency * issues -- but we're currently suffering from a shortage of * folks who are able to track these issues down properly. + * HWMOD_FORCE_MSTANDBY: Always keep MIDLEMODE bits cleared so that device + * is kept in force-standby mode. Failing to do so causes PM problems + * with musb on OMAP3630 at least. Note that musb has a dedicated register + * to control MSTANDBY signal when MIDLEMODE is set to force-standby. */ #define HWMOD_SWSUP_SIDLE (1 << 0) #define HWMOD_SWSUP_MSTANDBY (1 << 1) @@ -471,6 +475,7 @@ struct omap_hwmod_omap4_prcm { #define HWMOD_16BIT_REG (1 << 8) #define HWMOD_EXT_OPT_MAIN_CLK (1 << 9) #define HWMOD_BLOCK_WFI (1 << 10) +#define HWMOD_FORCE_MSTANDBY (1 << 11) /* * omap_hwmod._int_flags definitions diff --git a/arch/arm/mach-omap2/omap_hwmod_3xxx_data.c b/arch/arm/mach-omap2/omap_hwmod_3xxx_data.c index ac7e03e..5112d04 100644 --- a/arch/arm/mach-omap2/omap_hwmod_3xxx_data.c +++ b/arch/arm/mach-omap2/omap_hwmod_3xxx_data.c @@ -1707,9 +1707,14 @@ static struct omap_hwmod omap3xxx_usbhsotg_hwmod = { * Erratum ID: i479 idle_req / idle_ack mechanism potentially * broken when autoidle is enabled * workaround is to disable the autoidle bit at module level. + * + * Enabling the device in any other MIDLEMODE setting but force-idle + * causes core_pwrdm not enter idle states at least on OMAP3630. + * Note that musb has OTG_FORCESTDBY register that controls MSTANDBY + * signal when MIDLEMODE is set to force-idle. */ .flags = HWMOD_NO_OCP_AUTOIDLE | HWMOD_SWSUP_SIDLE - | HWMOD_SWSUP_MSTANDBY, + | HWMOD_FORCE_MSTANDBY, }; /* usb_otg_hs */ diff --git a/arch/arm/mach-omap2/omap_hwmod_44xx_data.c b/arch/arm/mach-omap2/omap_hwmod_44xx_data.c index 0e47d2e..9e05765 100644 --- a/arch/arm/mach-omap2/omap_hwmod_44xx_data.c +++ b/arch/arm/mach-omap2/omap_hwmod_44xx_data.c @@ -2714,6 +2714,10 @@ static struct omap_ocp2scp_dev ocp2scp_dev_attr[] = { { } }; +static struct omap_hwmod_opt_clk ocp2scp_usb_phy_opt_clks[] = { + { .role = "48mhz", .clk = "ocp2scp_usb_phy_phy_48m" }, +}; + /* ocp2scp_usb_phy */ static struct omap_hwmod omap44xx_ocp2scp_usb_phy_hwmod = { .name = "ocp2scp_usb_phy", @@ -2728,6 +2732,8 @@ static struct omap_hwmod omap44xx_ocp2scp_usb_phy_hwmod = { }, }, .dev_attr = ocp2scp_dev_attr, + .opt_clks = ocp2scp_usb_phy_opt_clks, + .opt_clks_cnt = ARRAY_SIZE(ocp2scp_usb_phy_opt_clks), }; /* diff --git a/arch/arm/mach-omap2/timer.c b/arch/arm/mach-omap2/timer.c index 2bdd4cf..f62b509 100644 --- a/arch/arm/mach-omap2/timer.c +++ b/arch/arm/mach-omap2/timer.c @@ -547,6 +547,8 @@ static inline void __init realtime_counter_init(void) clksrc_nr, clksrc_src) \ void __init omap##name##_gptimer_timer_init(void) \ { \ + if (omap_clk_init) \ + omap_clk_init(); \ omap_dmtimer_init(); \ omap2_gp_clockevent_init((clkev_nr), clkev_src, clkev_prop); \ omap2_gptimer_clocksource_init((clksrc_nr), clksrc_src); \ @@ -556,6 +558,8 @@ void __init omap##name##_gptimer_timer_init(void) \ clksrc_nr, clksrc_src) \ void __init omap##name##_sync32k_timer_init(void) \ { \ + if (omap_clk_init) \ + omap_clk_init(); \ omap_dmtimer_init(); \ omap2_gp_clockevent_init((clkev_nr), clkev_src, clkev_prop); \ /* Enable the use of clocksource="gp_timer" kernel parameter */ \ diff --git a/arch/arm/mach-s3c24xx/include/mach/irqs.h b/arch/arm/mach-s3c24xx/include/mach/irqs.h index b7a9f4d..1e73f5f 100644 --- a/arch/arm/mach-s3c24xx/include/mach/irqs.h +++ b/arch/arm/mach-s3c24xx/include/mach/irqs.h @@ -188,10 +188,8 @@ #if defined(CONFIG_CPU_S3C2416) #define NR_IRQS (IRQ_S3C2416_I2S1 + 1) -#elif defined(CONFIG_CPU_S3C2443) -#define NR_IRQS (IRQ_S3C2443_AC97+1) #else -#define NR_IRQS (IRQ_S3C2440_AC97+1) +#define NR_IRQS (IRQ_S3C2443_AC97 + 1) #endif /* compatibility define. */ diff --git a/arch/arm/mach-s3c24xx/irq.c b/arch/arm/mach-s3c24xx/irq.c index cb9f5e0..d8ba9be 100644 --- a/arch/arm/mach-s3c24xx/irq.c +++ b/arch/arm/mach-s3c24xx/irq.c @@ -500,7 +500,7 @@ struct s3c_irq_intc *s3c24xx_init_intc(struct device_node *np, base = (void *)0xfd000000; intc->reg_mask = base + 0xa4; - intc->reg_pending = base + 0x08; + intc->reg_pending = base + 0xa8; irq_num = 20; irq_start = S3C2410_IRQ(32); irq_offset = 4; diff --git a/arch/arm/mach-ux500/board-mop500-sdi.c b/arch/arm/mach-ux500/board-mop500-sdi.c index 051b62c..7f2cb6c 100644 --- a/arch/arm/mach-ux500/board-mop500-sdi.c +++ b/arch/arm/mach-ux500/board-mop500-sdi.c @@ -81,7 +81,6 @@ static struct stedma40_chan_cfg mop500_sdi0_dma_cfg_tx = { #endif struct mmci_platform_data mop500_sdi0_data = { - .ios_handler = mop500_sdi0_ios_handler, .ocr_mask = MMC_VDD_29_30, .f_max = 50000000, .capabilities = MMC_CAP_4_BIT_DATA | diff --git a/arch/arm/mach-ux500/board-mop500.c b/arch/arm/mach-ux500/board-mop500.c index b034578..87d2d7b 100644 --- a/arch/arm/mach-ux500/board-mop500.c +++ b/arch/arm/mach-ux500/board-mop500.c @@ -12,6 +12,7 @@ #include <linux/init.h> #include <linux/interrupt.h> #include <linux/platform_device.h> +#include <linux/clk.h> #include <linux/io.h> #include <linux/i2c.h> #include <linux/platform_data/i2c-nomadik.h> @@ -439,6 +440,15 @@ static void mop500_prox_deactivate(struct device *dev) regulator_put(prox_regulator); } +void mop500_snowball_ethernet_clock_enable(void) +{ + struct clk *clk; + + clk = clk_get_sys("fsmc", NULL); + if (!IS_ERR(clk)) + clk_prepare_enable(clk); +} + static struct cryp_platform_data u8500_cryp1_platform_data = { .mem_to_engine = { .dir = STEDMA40_MEM_TO_PERIPH, @@ -683,6 +693,8 @@ static void __init snowball_init_machine(void) mop500_audio_init(parent); mop500_uart_init(parent); + mop500_snowball_ethernet_clock_enable(); + /* This board has full regulator constraints */ regulator_has_full_constraints(); } diff --git a/arch/arm/mach-ux500/board-mop500.h b/arch/arm/mach-ux500/board-mop500.h index eaa605f..d38951b 100644 --- a/arch/arm/mach-ux500/board-mop500.h +++ b/arch/arm/mach-ux500/board-mop500.h @@ -104,6 +104,7 @@ void __init mop500_pinmaps_init(void); void __init snowball_pinmaps_init(void); void __init hrefv60_pinmaps_init(void); void mop500_audio_init(struct device *parent); +void mop500_snowball_ethernet_clock_enable(void); int __init mop500_uib_init(void); void mop500_uib_i2c_add(int busnum, struct i2c_board_info *info, diff --git a/arch/arm/mach-ux500/cpu-db8500.c b/arch/arm/mach-ux500/cpu-db8500.c index 19235cf..f1a5818 100644 --- a/arch/arm/mach-ux500/cpu-db8500.c +++ b/arch/arm/mach-ux500/cpu-db8500.c @@ -312,9 +312,10 @@ static void __init u8500_init_machine(void) /* Pinmaps must be in place before devices register */ if (of_machine_is_compatible("st-ericsson,mop500")) mop500_pinmaps_init(); - else if (of_machine_is_compatible("calaosystems,snowball-a9500")) + else if (of_machine_is_compatible("calaosystems,snowball-a9500")) { snowball_pinmaps_init(); - else if (of_machine_is_compatible("st-ericsson,hrefv60+")) + mop500_snowball_ethernet_clock_enable(); + } else if (of_machine_is_compatible("st-ericsson,hrefv60+")) hrefv60_pinmaps_init(); else if (of_machine_is_compatible("st-ericsson,ccu9540")) {} /* TODO: Add pinmaps for ccu9540 board. */ diff --git a/arch/arm/mm/Kconfig b/arch/arm/mm/Kconfig index 025d173..4045c49 100644 --- a/arch/arm/mm/Kconfig +++ b/arch/arm/mm/Kconfig @@ -43,7 +43,7 @@ config CPU_ARM740T depends on !MMU select CPU_32v4T select CPU_ABRT_LV4T - select CPU_CACHE_V3 # although the core is v4t + select CPU_CACHE_V4 select CPU_CP15_MPU select CPU_PABRT_LEGACY help @@ -469,9 +469,6 @@ config CPU_PABRT_V7 bool # The cache model -config CPU_CACHE_V3 - bool - config CPU_CACHE_V4 bool diff --git a/arch/arm/mm/Makefile b/arch/arm/mm/Makefile index 4e333fa..9e51be9 100644 --- a/arch/arm/mm/Makefile +++ b/arch/arm/mm/Makefile @@ -33,7 +33,6 @@ obj-$(CONFIG_CPU_PABRT_LEGACY) += pabort-legacy.o obj-$(CONFIG_CPU_PABRT_V6) += pabort-v6.o obj-$(CONFIG_CPU_PABRT_V7) += pabort-v7.o -obj-$(CONFIG_CPU_CACHE_V3) += cache-v3.o obj-$(CONFIG_CPU_CACHE_V4) += cache-v4.o obj-$(CONFIG_CPU_CACHE_V4WT) += cache-v4wt.o obj-$(CONFIG_CPU_CACHE_V4WB) += cache-v4wb.o diff --git a/arch/arm/mm/cache-feroceon-l2.c b/arch/arm/mm/cache-feroceon-l2.c index dd3d591..48bc3c0 100644 --- a/arch/arm/mm/cache-feroceon-l2.c +++ b/arch/arm/mm/cache-feroceon-l2.c @@ -343,6 +343,7 @@ void __init feroceon_l2_init(int __l2_wt_override) outer_cache.inv_range = feroceon_l2_inv_range; outer_cache.clean_range = feroceon_l2_clean_range; outer_cache.flush_range = feroceon_l2_flush_range; + outer_cache.inv_all = l2_inv_all; enable_l2(); diff --git a/arch/arm/mm/cache-l2x0.c b/arch/arm/mm/cache-l2x0.c index c2f3739..c465fac 100644 --- a/arch/arm/mm/cache-l2x0.c +++ b/arch/arm/mm/cache-l2x0.c @@ -299,7 +299,7 @@ static void l2x0_unlock(u32 cache_id) int lockregs; int i; - switch (cache_id) { + switch (cache_id & L2X0_CACHE_ID_PART_MASK) { case L2X0_CACHE_ID_PART_L310: lockregs = 8; break; @@ -333,15 +333,14 @@ void __init l2x0_init(void __iomem *base, u32 aux_val, u32 aux_mask) if (cache_id_part_number_from_dt) cache_id = cache_id_part_number_from_dt; else - cache_id = readl_relaxed(l2x0_base + L2X0_CACHE_ID) - & L2X0_CACHE_ID_PART_MASK; + cache_id = readl_relaxed(l2x0_base + L2X0_CACHE_ID); aux = readl_relaxed(l2x0_base + L2X0_AUX_CTRL); aux &= aux_mask; aux |= aux_val; /* Determine the number of ways */ - switch (cache_id) { + switch (cache_id & L2X0_CACHE_ID_PART_MASK) { case L2X0_CACHE_ID_PART_L310: if (aux & (1 << 16)) ways = 16; @@ -725,7 +724,6 @@ static const struct l2x0_of_data pl310_data = { .flush_all = l2x0_flush_all, .inv_all = l2x0_inv_all, .disable = l2x0_disable, - .set_debug = pl310_set_debug, }, }; @@ -814,9 +812,8 @@ int __init l2x0_of_init(u32 aux_val, u32 aux_mask) data->save(); of_init = true; - l2x0_init(l2x0_base, aux_val, aux_mask); - memcpy(&outer_cache, &data->outer_cache, sizeof(outer_cache)); + l2x0_init(l2x0_base, aux_val, aux_mask); return 0; } diff --git a/arch/arm/mm/cache-v3.S b/arch/arm/mm/cache-v3.S deleted file mode 100644 index 8a3fade..0000000 --- a/arch/arm/mm/cache-v3.S +++ /dev/null @@ -1,137 +0,0 @@ -/* - * linux/arch/arm/mm/cache-v3.S - * - * Copyright (C) 1997-2002 Russell king - * - * 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> -#include <asm/page.h> -#include "proc-macros.S" - -/* - * flush_icache_all() - * - * Unconditionally clean and invalidate the entire icache. - */ -ENTRY(v3_flush_icache_all) - mov pc, lr -ENDPROC(v3_flush_icache_all) - -/* - * flush_user_cache_all() - * - * Invalidate all cache entries in a particular address - * space. - * - * - mm - mm_struct describing address space - */ -ENTRY(v3_flush_user_cache_all) - /* FALLTHROUGH */ -/* - * flush_kern_cache_all() - * - * Clean and invalidate the entire cache. - */ -ENTRY(v3_flush_kern_cache_all) - /* FALLTHROUGH */ - -/* - * flush_user_cache_range(start, end, flags) - * - * Invalidate a range of cache entries in the specified - * address space. - * - * - start - start address (may not be aligned) - * - end - end address (exclusive, may not be aligned) - * - flags - vma_area_struct flags describing address space - */ -ENTRY(v3_flush_user_cache_range) - mov ip, #0 - mcreq p15, 0, ip, c7, c0, 0 @ flush ID cache - mov pc, lr - -/* - * coherent_kern_range(start, end) - * - * Ensure coherency between the Icache and the Dcache in the - * region described by start. If you have non-snooping - * Harvard caches, you need to implement this function. - * - * - start - virtual start address - * - end - virtual end address - */ -ENTRY(v3_coherent_kern_range) - /* FALLTHROUGH */ - -/* - * coherent_user_range(start, end) - * - * Ensure coherency between the Icache and the Dcache in the - * region described by start. If you have non-snooping - * Harvard caches, you need to implement this function. - * - * - start - virtual start address - * - end - virtual end address - */ -ENTRY(v3_coherent_user_range) - mov r0, #0 - mov pc, lr - -/* - * flush_kern_dcache_area(void *page, size_t size) - * - * Ensure no D cache aliasing occurs, either with itself or - * the I cache - * - * - addr - kernel address - * - size - region size - */ -ENTRY(v3_flush_kern_dcache_area) - /* FALLTHROUGH */ - -/* - * dma_flush_range(start, end) - * - * Clean and invalidate the specified virtual address range. - * - * - start - virtual start address - * - end - virtual end address - */ -ENTRY(v3_dma_flush_range) - mov r0, #0 - mcr p15, 0, r0, c7, c0, 0 @ flush ID cache - mov pc, lr - -/* - * dma_unmap_area(start, size, dir) - * - start - kernel virtual start address - * - size - size of region - * - dir - DMA direction - */ -ENTRY(v3_dma_unmap_area) - teq r2, #DMA_TO_DEVICE - bne v3_dma_flush_range - /* FALLTHROUGH */ - -/* - * dma_map_area(start, size, dir) - * - start - kernel virtual start address - * - size - size of region - * - dir - DMA direction - */ -ENTRY(v3_dma_map_area) - mov pc, lr -ENDPROC(v3_dma_unmap_area) -ENDPROC(v3_dma_map_area) - - .globl v3_flush_kern_cache_louis - .equ v3_flush_kern_cache_louis, v3_flush_kern_cache_all - - __INITDATA - - @ define struct cpu_cache_fns (see <asm/cacheflush.h> and proc-macros.S) - define_cache_functions v3 diff --git a/arch/arm/mm/cache-v4.S b/arch/arm/mm/cache-v4.S index 43e5d77..a7ba68f 100644 --- a/arch/arm/mm/cache-v4.S +++ b/arch/arm/mm/cache-v4.S @@ -58,7 +58,7 @@ ENTRY(v4_flush_kern_cache_all) ENTRY(v4_flush_user_cache_range) #ifdef CONFIG_CPU_CP15 mov ip, #0 - mcreq p15, 0, ip, c7, c7, 0 @ flush ID cache + mcr p15, 0, ip, c7, c7, 0 @ flush ID cache mov pc, lr #else /* FALLTHROUGH */ diff --git a/arch/arm/mm/context.c b/arch/arm/mm/context.c index a5a4b2bc..2ac3737 100644 --- a/arch/arm/mm/context.c +++ b/arch/arm/mm/context.c @@ -48,7 +48,7 @@ static DEFINE_RAW_SPINLOCK(cpu_asid_lock); static atomic64_t asid_generation = ATOMIC64_INIT(ASID_FIRST_VERSION); static DECLARE_BITMAP(asid_map, NUM_USER_ASIDS); -static DEFINE_PER_CPU(atomic64_t, active_asids); +DEFINE_PER_CPU(atomic64_t, active_asids); static DEFINE_PER_CPU(u64, reserved_asids); static cpumask_t tlb_flush_pending; @@ -215,6 +215,7 @@ void check_and_switch_context(struct mm_struct *mm, struct task_struct *tsk) if (cpumask_test_and_clear_cpu(cpu, &tlb_flush_pending)) { local_flush_bp_all(); local_flush_tlb_all(); + dummy_flush_tlb_a15_erratum(); } atomic64_set(&per_cpu(active_asids, cpu), asid); diff --git a/arch/arm/mm/mmu.c b/arch/arm/mm/mmu.c index e95a996..a84ff76 100644 --- a/arch/arm/mm/mmu.c +++ b/arch/arm/mm/mmu.c @@ -34,6 +34,7 @@ #include <asm/mach/pci.h> #include "mm.h" +#include "tcm.h" /* * empty_zero_page is a special page that is used for @@ -598,39 +599,60 @@ static void __init alloc_init_pte(pmd_t *pmd, unsigned long addr, } while (pte++, addr += PAGE_SIZE, addr != end); } -static void __init alloc_init_section(pud_t *pud, unsigned long addr, - unsigned long end, phys_addr_t phys, - const struct mem_type *type) +static void __init map_init_section(pmd_t *pmd, unsigned long addr, + unsigned long end, phys_addr_t phys, + const struct mem_type *type) { - pmd_t *pmd = pmd_offset(pud, addr); - +#ifndef CONFIG_ARM_LPAE /* - * Try a section mapping - end, addr and phys must all be aligned - * to a section boundary. Note that PMDs refer to the individual - * L1 entries, whereas PGDs refer to a group of L1 entries making - * up one logical pointer to an L2 table. + * In classic MMU format, puds and pmds are folded in to + * the pgds. pmd_offset gives the PGD entry. PGDs refer to a + * group of L1 entries making up one logical pointer to + * an L2 table (2MB), where as PMDs refer to the individual + * L1 entries (1MB). Hence increment to get the correct + * offset for odd 1MB sections. + * (See arch/arm/include/asm/pgtable-2level.h) */ - if (type->prot_sect && ((addr | end | phys) & ~SECTION_MASK) == 0) { - pmd_t *p = pmd; - -#ifndef CONFIG_ARM_LPAE - if (addr & SECTION_SIZE) - pmd++; + if (addr & SECTION_SIZE) + pmd++; #endif + do { + *pmd = __pmd(phys | type->prot_sect); + phys += SECTION_SIZE; + } while (pmd++, addr += SECTION_SIZE, addr != end); - do { - *pmd = __pmd(phys | type->prot_sect); - phys += SECTION_SIZE; - } while (pmd++, addr += SECTION_SIZE, addr != end); + flush_pmd_entry(pmd); +} - flush_pmd_entry(p); - } else { +static void __init alloc_init_pmd(pud_t *pud, unsigned long addr, + unsigned long end, phys_addr_t phys, + const struct mem_type *type) +{ + pmd_t *pmd = pmd_offset(pud, addr); + unsigned long next; + + do { /* - * No need to loop; pte's aren't interested in the - * individual L1 entries. + * With LPAE, we must loop over to map + * all the pmds for the given range. */ - alloc_init_pte(pmd, addr, end, __phys_to_pfn(phys), type); - } + next = pmd_addr_end(addr, end); + + /* + * Try a section mapping - addr, next and phys must all be + * aligned to a section boundary. + */ + if (type->prot_sect && + ((addr | next | phys) & ~SECTION_MASK) == 0) { + map_init_section(pmd, addr, next, phys, type); + } else { + alloc_init_pte(pmd, addr, next, + __phys_to_pfn(phys), type); + } + + phys += next - addr; + + } while (pmd++, addr = next, addr != end); } static void __init alloc_init_pud(pgd_t *pgd, unsigned long addr, @@ -641,7 +663,7 @@ static void __init alloc_init_pud(pgd_t *pgd, unsigned long addr, do { next = pud_addr_end(addr, end); - alloc_init_section(pud, addr, next, phys, type); + alloc_init_pmd(pud, addr, next, phys, type); phys += next - addr; } while (pud++, addr = next, addr != end); } @@ -1256,6 +1278,7 @@ void __init paging_init(struct machine_desc *mdesc) dma_contiguous_remap(); devicemaps_init(mdesc); kmap_init(); + tcm_init(); top_pmd = pmd_off_k(0xffff0000); diff --git a/arch/arm/mm/proc-arm740.S b/arch/arm/mm/proc-arm740.S index dc5de5d..fde2d2a 100644 --- a/arch/arm/mm/proc-arm740.S +++ b/arch/arm/mm/proc-arm740.S @@ -77,24 +77,27 @@ __arm740_setup: mcr p15, 0, r0, c6, c0 @ set area 0, default ldr r0, =(CONFIG_DRAM_BASE & 0xFFFFF000) @ base[31:12] of RAM - ldr r1, =(CONFIG_DRAM_SIZE >> 12) @ size of RAM (must be >= 4KB) - mov r2, #10 @ 11 is the minimum (4KB) -1: add r2, r2, #1 @ area size *= 2 - mov r1, r1, lsr #1 + ldr r3, =(CONFIG_DRAM_SIZE >> 12) @ size of RAM (must be >= 4KB) + mov r4, #10 @ 11 is the minimum (4KB) +1: add r4, r4, #1 @ area size *= 2 + movs r3, r3, lsr #1 bne 1b @ count not zero r-shift - orr r0, r0, r2, lsl #1 @ the area register value + orr r0, r0, r4, lsl #1 @ the area register value orr r0, r0, #1 @ set enable bit mcr p15, 0, r0, c6, c1 @ set area 1, RAM ldr r0, =(CONFIG_FLASH_MEM_BASE & 0xFFFFF000) @ base[31:12] of FLASH - ldr r1, =(CONFIG_FLASH_SIZE >> 12) @ size of FLASH (must be >= 4KB) - mov r2, #10 @ 11 is the minimum (4KB) -1: add r2, r2, #1 @ area size *= 2 - mov r1, r1, lsr #1 + ldr r3, =(CONFIG_FLASH_SIZE >> 12) @ size of FLASH (must be >= 4KB) + cmp r3, #0 + moveq r0, #0 + beq 2f + mov r4, #10 @ 11 is the minimum (4KB) +1: add r4, r4, #1 @ area size *= 2 + movs r3, r3, lsr #1 bne 1b @ count not zero r-shift - orr r0, r0, r2, lsl #1 @ the area register value + orr r0, r0, r4, lsl #1 @ the area register value orr r0, r0, #1 @ set enable bit - mcr p15, 0, r0, c6, c2 @ set area 2, ROM/FLASH +2: mcr p15, 0, r0, c6, c2 @ set area 2, ROM/FLASH mov r0, #0x06 mcr p15, 0, r0, c2, c0 @ Region 1&2 cacheable @@ -137,13 +140,14 @@ __arm740_proc_info: .long 0x41807400 .long 0xfffffff0 .long 0 + .long 0 b __arm740_setup .long cpu_arch_name .long cpu_elf_name - .long HWCAP_SWP | HWCAP_HALF | HWCAP_26BIT + .long HWCAP_SWP | HWCAP_HALF | HWCAP_THUMB | HWCAP_26BIT .long cpu_arm740_name .long arm740_processor_functions .long 0 .long 0 - .long v3_cache_fns @ cache model + .long v4_cache_fns @ cache model .size __arm740_proc_info, . - __arm740_proc_info diff --git a/arch/arm/mm/proc-arm920.S b/arch/arm/mm/proc-arm920.S index 2c3b942..2556cf1 100644 --- a/arch/arm/mm/proc-arm920.S +++ b/arch/arm/mm/proc-arm920.S @@ -387,7 +387,7 @@ ENTRY(cpu_arm920_set_pte_ext) /* Suspend/resume support: taken from arch/arm/plat-s3c24xx/sleep.S */ .globl cpu_arm920_suspend_size .equ cpu_arm920_suspend_size, 4 * 3 -#ifdef CONFIG_PM_SLEEP +#ifdef CONFIG_ARM_CPU_SUSPEND ENTRY(cpu_arm920_do_suspend) stmfd sp!, {r4 - r6, lr} mrc p15, 0, r4, c13, c0, 0 @ PID diff --git a/arch/arm/mm/proc-arm926.S b/arch/arm/mm/proc-arm926.S index f1803f7..344c8a5 100644 --- a/arch/arm/mm/proc-arm926.S +++ b/arch/arm/mm/proc-arm926.S @@ -402,7 +402,7 @@ ENTRY(cpu_arm926_set_pte_ext) /* Suspend/resume support: taken from arch/arm/plat-s3c24xx/sleep.S */ .globl cpu_arm926_suspend_size .equ cpu_arm926_suspend_size, 4 * 3 -#ifdef CONFIG_PM_SLEEP +#ifdef CONFIG_ARM_CPU_SUSPEND ENTRY(cpu_arm926_do_suspend) stmfd sp!, {r4 - r6, lr} mrc p15, 0, r4, c13, c0, 0 @ PID diff --git a/arch/arm/mm/proc-mohawk.S b/arch/arm/mm/proc-mohawk.S index 82f9cdc..0b60dd3 100644 --- a/arch/arm/mm/proc-mohawk.S +++ b/arch/arm/mm/proc-mohawk.S @@ -350,7 +350,7 @@ ENTRY(cpu_mohawk_set_pte_ext) .globl cpu_mohawk_suspend_size .equ cpu_mohawk_suspend_size, 4 * 6 -#ifdef CONFIG_PM_SLEEP +#ifdef CONFIG_ARM_CPU_SUSPEND ENTRY(cpu_mohawk_do_suspend) stmfd sp!, {r4 - r9, lr} mrc p14, 0, r4, c6, c0, 0 @ clock configuration, for turbo mode diff --git a/arch/arm/mm/proc-sa1100.S b/arch/arm/mm/proc-sa1100.S index 3aa0da1..d92dfd0 100644 --- a/arch/arm/mm/proc-sa1100.S +++ b/arch/arm/mm/proc-sa1100.S @@ -172,7 +172,7 @@ ENTRY(cpu_sa1100_set_pte_ext) .globl cpu_sa1100_suspend_size .equ cpu_sa1100_suspend_size, 4 * 3 -#ifdef CONFIG_PM_SLEEP +#ifdef CONFIG_ARM_CPU_SUSPEND ENTRY(cpu_sa1100_do_suspend) stmfd sp!, {r4 - r6, lr} mrc p15, 0, r4, c3, c0, 0 @ domain ID diff --git a/arch/arm/mm/proc-syms.c b/arch/arm/mm/proc-syms.c index 3e6210b..054b491 100644 --- a/arch/arm/mm/proc-syms.c +++ b/arch/arm/mm/proc-syms.c @@ -17,7 +17,9 @@ #ifndef MULTI_CPU EXPORT_SYMBOL(cpu_dcache_clean_area); +#ifdef CONFIG_MMU EXPORT_SYMBOL(cpu_set_pte_ext); +#endif #else EXPORT_SYMBOL(processor); #endif diff --git a/arch/arm/mm/proc-v6.S b/arch/arm/mm/proc-v6.S index bcaaa8d..5c07ee4 100644 --- a/arch/arm/mm/proc-v6.S +++ b/arch/arm/mm/proc-v6.S @@ -138,7 +138,7 @@ ENTRY(cpu_v6_set_pte_ext) /* Suspend/resume support: taken from arch/arm/mach-s3c64xx/sleep.S */ .globl cpu_v6_suspend_size .equ cpu_v6_suspend_size, 4 * 6 -#ifdef CONFIG_PM_SLEEP +#ifdef CONFIG_ARM_CPU_SUSPEND ENTRY(cpu_v6_do_suspend) stmfd sp!, {r4 - r9, lr} mrc p15, 0, r4, c13, c0, 0 @ FCSE/PID diff --git a/arch/arm/mm/proc-v7.S b/arch/arm/mm/proc-v7.S index 3a3c015..f584d3f 100644 --- a/arch/arm/mm/proc-v7.S +++ b/arch/arm/mm/proc-v7.S @@ -420,7 +420,7 @@ __v7_pj4b_proc_info: __v7_ca7mp_proc_info: .long 0x410fc070 .long 0xff0ffff0 - __v7_proc __v7_ca7mp_setup, hwcaps = HWCAP_IDIV + __v7_proc __v7_ca7mp_setup .size __v7_ca7mp_proc_info, . - __v7_ca7mp_proc_info /* @@ -430,10 +430,25 @@ __v7_ca7mp_proc_info: __v7_ca15mp_proc_info: .long 0x410fc0f0 .long 0xff0ffff0 - __v7_proc __v7_ca15mp_setup, hwcaps = HWCAP_IDIV + __v7_proc __v7_ca15mp_setup .size __v7_ca15mp_proc_info, . - __v7_ca15mp_proc_info /* + * Qualcomm Inc. Krait processors. + */ + .type __krait_proc_info, #object +__krait_proc_info: + .long 0x510f0400 @ Required ID value + .long 0xff0ffc00 @ Mask for ID + /* + * Some Krait processors don't indicate support for SDIV and UDIV + * instructions in the ARM instruction set, even though they actually + * do support them. + */ + __v7_proc __v7_setup, hwcaps = HWCAP_IDIV + .size __krait_proc_info, . - __krait_proc_info + + /* * Match any ARMv7 processor core. */ .type __v7_proc_info, #object diff --git a/arch/arm/mm/proc-xsc3.S b/arch/arm/mm/proc-xsc3.S index eb93d64..e8efd83 100644 --- a/arch/arm/mm/proc-xsc3.S +++ b/arch/arm/mm/proc-xsc3.S @@ -413,7 +413,7 @@ ENTRY(cpu_xsc3_set_pte_ext) .globl cpu_xsc3_suspend_size .equ cpu_xsc3_suspend_size, 4 * 6 -#ifdef CONFIG_PM_SLEEP +#ifdef CONFIG_ARM_CPU_SUSPEND ENTRY(cpu_xsc3_do_suspend) stmfd sp!, {r4 - r9, lr} mrc p14, 0, r4, c6, c0, 0 @ clock configuration, for turbo mode diff --git a/arch/arm/mm/proc-xscale.S b/arch/arm/mm/proc-xscale.S index 2551036..e766f88 100644 --- a/arch/arm/mm/proc-xscale.S +++ b/arch/arm/mm/proc-xscale.S @@ -528,7 +528,7 @@ ENTRY(cpu_xscale_set_pte_ext) .globl cpu_xscale_suspend_size .equ cpu_xscale_suspend_size, 4 * 6 -#ifdef CONFIG_PM_SLEEP +#ifdef CONFIG_ARM_CPU_SUSPEND ENTRY(cpu_xscale_do_suspend) stmfd sp!, {r4 - r9, lr} mrc p14, 0, r4, c6, c0, 0 @ clock configuration, for turbo mode diff --git a/arch/arm/kernel/tcm.h b/arch/arm/mm/tcm.h index 8015ad4..8015ad4 100644 --- a/arch/arm/kernel/tcm.h +++ b/arch/arm/mm/tcm.h diff --git a/arch/avr32/include/asm/io.h b/arch/avr32/include/asm/io.h index cf60d0a..fc6483f 100644 --- a/arch/avr32/include/asm/io.h +++ b/arch/avr32/include/asm/io.h @@ -165,6 +165,10 @@ BUILDIO_IOPORT(l, u32) #define readw_be __raw_readw #define readl_be __raw_readl +#define writeb_relaxed writeb +#define writew_relaxed writew +#define writel_relaxed writel + #define writeb_be __raw_writeb #define writew_be __raw_writew #define writel_be __raw_writel diff --git a/arch/c6x/include/asm/irqflags.h b/arch/c6x/include/asm/irqflags.h index cf78e09..2c71d56 100644 --- a/arch/c6x/include/asm/irqflags.h +++ b/arch/c6x/include/asm/irqflags.h @@ -27,7 +27,7 @@ static inline unsigned long arch_local_save_flags(void) /* set interrupt enabled status */ static inline void arch_local_irq_restore(unsigned long flags) { - asm volatile (" mvc .s2 %0,CSR\n" : : "b"(flags)); + asm volatile (" mvc .s2 %0,CSR\n" : : "b"(flags) : "memory"); } /* unconditionally enable interrupts */ diff --git a/arch/ia64/kernel/palinfo.c b/arch/ia64/kernel/palinfo.c index 77597e5..79521d5 100644 --- a/arch/ia64/kernel/palinfo.c +++ b/arch/ia64/kernel/palinfo.c @@ -849,17 +849,6 @@ static palinfo_entry_t palinfo_entries[]={ #define NR_PALINFO_ENTRIES (int) ARRAY_SIZE(palinfo_entries) -/* - * this array is used to keep track of the proc entries we create. This is - * required in the module mode when we need to remove all entries. The procfs code - * does not do recursion of deletion - * - * Notes: - * - +1 accounts for the cpuN directory entry in /proc/pal - */ -#define NR_PALINFO_PROC_ENTRIES (NR_CPUS*(NR_PALINFO_ENTRIES+1)) - -static struct proc_dir_entry *palinfo_proc_entries[NR_PALINFO_PROC_ENTRIES]; static struct proc_dir_entry *palinfo_dir; /* @@ -971,60 +960,32 @@ palinfo_read_entry(char *page, char **start, off_t off, int count, int *eof, voi static void __cpuinit create_palinfo_proc_entries(unsigned int cpu) { -# define CPUSTR "cpu%d" - pal_func_cpu_u_t f; - struct proc_dir_entry **pdir; struct proc_dir_entry *cpu_dir; int j; - char cpustr[sizeof(CPUSTR)]; - - - /* - * we keep track of created entries in a depth-first order for - * cleanup purposes. Each entry is stored into palinfo_proc_entries - */ - sprintf(cpustr,CPUSTR, cpu); + char cpustr[3+4+1]; /* cpu numbers are up to 4095 on itanic */ + sprintf(cpustr, "cpu%d", cpu); cpu_dir = proc_mkdir(cpustr, palinfo_dir); + if (!cpu_dir) + return; f.req_cpu = cpu; - /* - * Compute the location to store per cpu entries - * We dont store the top level entry in this list, but - * remove it finally after removing all cpu entries. - */ - pdir = &palinfo_proc_entries[cpu*(NR_PALINFO_ENTRIES+1)]; - *pdir++ = cpu_dir; for (j=0; j < NR_PALINFO_ENTRIES; j++) { f.func_id = j; - *pdir = create_proc_read_entry( - palinfo_entries[j].name, 0, cpu_dir, - palinfo_read_entry, (void *)f.value); - pdir++; + create_proc_read_entry( + palinfo_entries[j].name, 0, cpu_dir, + palinfo_read_entry, (void *)f.value); } } static void remove_palinfo_proc_entries(unsigned int hcpu) { - int j; - struct proc_dir_entry *cpu_dir, **pdir; - - pdir = &palinfo_proc_entries[hcpu*(NR_PALINFO_ENTRIES+1)]; - cpu_dir = *pdir; - *pdir++=NULL; - for (j=0; j < (NR_PALINFO_ENTRIES); j++) { - if ((*pdir)) { - remove_proc_entry ((*pdir)->name, cpu_dir); - *pdir ++= NULL; - } - } - - if (cpu_dir) { - remove_proc_entry(cpu_dir->name, palinfo_dir); - } + char cpustr[3+4+1]; /* cpu numbers are up to 4095 on itanic */ + sprintf(cpustr, "cpu%d", hcpu); + remove_proc_subtree(cpustr, palinfo_dir); } static int __cpuinit palinfo_cpu_callback(struct notifier_block *nfb, @@ -1058,6 +1019,8 @@ palinfo_init(void) printk(KERN_INFO "PAL Information Facility v%s\n", PALINFO_VERSION); palinfo_dir = proc_mkdir("pal", NULL); + if (!palinfo_dir) + return -ENOMEM; /* Create palinfo dirs in /proc for all online cpus */ for_each_online_cpu(i) { @@ -1073,22 +1036,8 @@ palinfo_init(void) static void __exit palinfo_exit(void) { - int i = 0; - - /* remove all nodes: depth first pass. Could optimize this */ - for_each_online_cpu(i) { - remove_palinfo_proc_entries(i); - } - - /* - * Remove the top level entry finally - */ - remove_proc_entry(palinfo_dir->name, NULL); - - /* - * Unregister from cpu notifier callbacks - */ unregister_hotcpu_notifier(&palinfo_cpu_notifier); + remove_proc_subtree("pal", NULL); } module_init(palinfo_init); diff --git a/arch/m68k/include/asm/gpio.h b/arch/m68k/include/asm/gpio.h index 4395ffc..8cc8343 100644 --- a/arch/m68k/include/asm/gpio.h +++ b/arch/m68k/include/asm/gpio.h @@ -86,4 +86,24 @@ static inline int gpio_cansleep(unsigned gpio) return gpio < MCFGPIO_PIN_MAX ? 0 : __gpio_cansleep(gpio); } +static inline int gpio_request_one(unsigned gpio, unsigned long flags, const char *label) +{ + int err; + + err = gpio_request(gpio, label); + if (err) + return err; + + if (flags & GPIOF_DIR_IN) + err = gpio_direction_input(gpio); + else + err = gpio_direction_output(gpio, + (flags & GPIOF_INIT_HIGH) ? 1 : 0); + + if (err) + gpio_free(gpio); + + return err; +} + #endif diff --git a/arch/metag/mm/Kconfig b/arch/metag/mm/Kconfig index 975f2f4..ccf2576 100644 --- a/arch/metag/mm/Kconfig +++ b/arch/metag/mm/Kconfig @@ -93,11 +93,6 @@ config ARCH_SPARSEMEM_ENABLE config ARCH_SPARSEMEM_DEFAULT def_bool y -config MAX_ACTIVE_REGIONS - int - default "2" if SPARSEMEM - default "1" - config ARCH_POPULATES_NODE_MAP def_bool y diff --git a/arch/mips/Kconfig b/arch/mips/Kconfig index cd2e21f..51244bf 100644 --- a/arch/mips/Kconfig +++ b/arch/mips/Kconfig @@ -18,7 +18,7 @@ config MIPS select HAVE_KRETPROBES select HAVE_DEBUG_KMEMLEAK select ARCH_BINFMT_ELF_RANDOMIZE_PIE - select HAVE_ARCH_TRANSPARENT_HUGEPAGE + select HAVE_ARCH_TRANSPARENT_HUGEPAGE if CPU_SUPPORTS_HUGEPAGES && 64BIT select RTC_LIB if !MACH_LOONGSON select GENERIC_ATOMIC64 if !64BIT select ARCH_HAS_ATOMIC64_DEC_IF_POSITIVE @@ -657,7 +657,7 @@ config SNI_RM bool "SNI RM200/300/400" select FW_ARC if CPU_LITTLE_ENDIAN select FW_ARC32 if CPU_LITTLE_ENDIAN - select SNIPROM if CPU_BIG_ENDIAN + select FW_SNIPROM if CPU_BIG_ENDIAN select ARCH_MAY_HAVE_PC_FDC select BOOT_ELF32 select CEVT_R4K @@ -1144,7 +1144,7 @@ config DEFAULT_SGI_PARTITION config FW_ARC32 bool -config SNIPROM +config FW_SNIPROM bool config BOOT_ELF32 @@ -1493,7 +1493,6 @@ config CPU_XLP select CPU_SUPPORTS_32BIT_KERNEL select CPU_SUPPORTS_64BIT_KERNEL select CPU_SUPPORTS_HIGHMEM - select CPU_HAS_LLSC select WEAK_ORDERING select WEAK_REORDERING_BEYOND_LLSC select CPU_HAS_PREFETCH diff --git a/arch/mips/bcm63xx/boards/board_bcm963xx.c b/arch/mips/bcm63xx/boards/board_bcm963xx.c index ed1949c..9aa7d44 100644 --- a/arch/mips/bcm63xx/boards/board_bcm963xx.c +++ b/arch/mips/bcm63xx/boards/board_bcm963xx.c @@ -745,10 +745,7 @@ void __init board_prom_init(void) strcpy(cfe_version, "unknown"); printk(KERN_INFO PFX "CFE version: %s\n", cfe_version); - if (bcm63xx_nvram_init(boot_addr + BCM963XX_NVRAM_OFFSET)) { - printk(KERN_ERR PFX "invalid nvram checksum\n"); - return; - } + bcm63xx_nvram_init(boot_addr + BCM963XX_NVRAM_OFFSET); board_name = bcm63xx_nvram_get_name(); /* find board by name */ diff --git a/arch/mips/bcm63xx/nvram.c b/arch/mips/bcm63xx/nvram.c index 6206116..a4b8864 100644 --- a/arch/mips/bcm63xx/nvram.c +++ b/arch/mips/bcm63xx/nvram.c @@ -38,7 +38,7 @@ struct bcm963xx_nvram { static struct bcm963xx_nvram nvram; static int mac_addr_used; -int __init bcm63xx_nvram_init(void *addr) +void __init bcm63xx_nvram_init(void *addr) { unsigned int check_len; u32 crc, expected_crc; @@ -60,9 +60,8 @@ int __init bcm63xx_nvram_init(void *addr) crc = crc32_le(~0, (u8 *)&nvram, check_len); if (crc != expected_crc) - return -EINVAL; - - return 0; + pr_warn("nvram checksum failed, contents may be invalid (expected %08x, got %08x)\n", + expected_crc, crc); } u8 *bcm63xx_nvram_get_name(void) diff --git a/arch/mips/bcm63xx/setup.c b/arch/mips/bcm63xx/setup.c index 314231b..35e18e9 100644 --- a/arch/mips/bcm63xx/setup.c +++ b/arch/mips/bcm63xx/setup.c @@ -157,4 +157,4 @@ int __init bcm63xx_register_devices(void) return board_register_devices(); } -device_initcall(bcm63xx_register_devices); +arch_initcall(bcm63xx_register_devices); diff --git a/arch/mips/cavium-octeon/setup.c b/arch/mips/cavium-octeon/setup.c index c594a3d..b0baa29 100644 --- a/arch/mips/cavium-octeon/setup.c +++ b/arch/mips/cavium-octeon/setup.c @@ -174,7 +174,10 @@ static int octeon_kexec_prepare(struct kimage *image) static void octeon_generic_shutdown(void) { - int cpu, i; + int i; +#ifdef CONFIG_SMP + int cpu; +#endif struct cvmx_bootmem_desc *bootmem_desc; void *named_block_array_ptr; diff --git a/arch/mips/include/asm/mach-bcm63xx/bcm63xx_nvram.h b/arch/mips/include/asm/mach-bcm63xx/bcm63xx_nvram.h index 62d6a3b..4e0b6bc 100644 --- a/arch/mips/include/asm/mach-bcm63xx/bcm63xx_nvram.h +++ b/arch/mips/include/asm/mach-bcm63xx/bcm63xx_nvram.h @@ -9,10 +9,8 @@ * * Initialized the local nvram copy from the target address and checks * its checksum. - * - * Returns 0 on success. */ -int __init bcm63xx_nvram_init(void *nvram); +void bcm63xx_nvram_init(void *nvram); /** * bcm63xx_nvram_get_name() - returns the board name according to nvram diff --git a/arch/mips/include/asm/mach-sead3/cpu-feature-overrides.h b/arch/mips/include/asm/mach-sead3/cpu-feature-overrides.h index d9c8284..193c091 100644 --- a/arch/mips/include/asm/mach-sead3/cpu-feature-overrides.h +++ b/arch/mips/include/asm/mach-sead3/cpu-feature-overrides.h @@ -28,11 +28,7 @@ /* #define cpu_has_prefetch ? */ #define cpu_has_mcheck 1 /* #define cpu_has_ejtag ? */ -#ifdef CONFIG_CPU_HAS_LLSC #define cpu_has_llsc 1 -#else -#define cpu_has_llsc 0 -#endif /* #define cpu_has_vtag_icache ? */ /* #define cpu_has_dc_aliases ? */ /* #define cpu_has_ic_fills_f_dc ? */ diff --git a/arch/mips/include/asm/mipsregs.h b/arch/mips/include/asm/mipsregs.h index 12b70c2..0da44d4 100644 --- a/arch/mips/include/asm/mipsregs.h +++ b/arch/mips/include/asm/mipsregs.h @@ -1166,7 +1166,10 @@ do { \ unsigned int __dspctl; \ \ __asm__ __volatile__( \ + " .set push \n" \ + " .set dsp \n" \ " rddsp %0, %x1 \n" \ + " .set pop \n" \ : "=r" (__dspctl) \ : "i" (mask)); \ __dspctl; \ @@ -1175,30 +1178,198 @@ do { \ #define wrdsp(val, mask) \ do { \ __asm__ __volatile__( \ + " .set push \n" \ + " .set dsp \n" \ " wrdsp %0, %x1 \n" \ + " .set pop \n" \ : \ : "r" (val), "i" (mask)); \ } while (0) -#define mflo0() ({ long mflo0; __asm__("mflo %0, $ac0" : "=r" (mflo0)); mflo0;}) -#define mflo1() ({ long mflo1; __asm__("mflo %0, $ac1" : "=r" (mflo1)); mflo1;}) -#define mflo2() ({ long mflo2; __asm__("mflo %0, $ac2" : "=r" (mflo2)); mflo2;}) -#define mflo3() ({ long mflo3; __asm__("mflo %0, $ac3" : "=r" (mflo3)); mflo3;}) - -#define mfhi0() ({ long mfhi0; __asm__("mfhi %0, $ac0" : "=r" (mfhi0)); mfhi0;}) -#define mfhi1() ({ long mfhi1; __asm__("mfhi %0, $ac1" : "=r" (mfhi1)); mfhi1;}) -#define mfhi2() ({ long mfhi2; __asm__("mfhi %0, $ac2" : "=r" (mfhi2)); mfhi2;}) -#define mfhi3() ({ long mfhi3; __asm__("mfhi %0, $ac3" : "=r" (mfhi3)); mfhi3;}) - -#define mtlo0(x) __asm__("mtlo %0, $ac0" ::"r" (x)) -#define mtlo1(x) __asm__("mtlo %0, $ac1" ::"r" (x)) -#define mtlo2(x) __asm__("mtlo %0, $ac2" ::"r" (x)) -#define mtlo3(x) __asm__("mtlo %0, $ac3" ::"r" (x)) - -#define mthi0(x) __asm__("mthi %0, $ac0" ::"r" (x)) -#define mthi1(x) __asm__("mthi %0, $ac1" ::"r" (x)) -#define mthi2(x) __asm__("mthi %0, $ac2" ::"r" (x)) -#define mthi3(x) __asm__("mthi %0, $ac3" ::"r" (x)) +#define mflo0() \ +({ \ + long mflo0; \ + __asm__( \ + " .set push \n" \ + " .set dsp \n" \ + " mflo %0, $ac0 \n" \ + " .set pop \n" \ + : "=r" (mflo0)); \ + mflo0; \ +}) + +#define mflo1() \ +({ \ + long mflo1; \ + __asm__( \ + " .set push \n" \ + " .set dsp \n" \ + " mflo %0, $ac1 \n" \ + " .set pop \n" \ + : "=r" (mflo1)); \ + mflo1; \ +}) + +#define mflo2() \ +({ \ + long mflo2; \ + __asm__( \ + " .set push \n" \ + " .set dsp \n" \ + " mflo %0, $ac2 \n" \ + " .set pop \n" \ + : "=r" (mflo2)); \ + mflo2; \ +}) + +#define mflo3() \ +({ \ + long mflo3; \ + __asm__( \ + " .set push \n" \ + " .set dsp \n" \ + " mflo %0, $ac3 \n" \ + " .set pop \n" \ + : "=r" (mflo3)); \ + mflo3; \ +}) + +#define mfhi0() \ +({ \ + long mfhi0; \ + __asm__( \ + " .set push \n" \ + " .set dsp \n" \ + " mfhi %0, $ac0 \n" \ + " .set pop \n" \ + : "=r" (mfhi0)); \ + mfhi0; \ +}) + +#define mfhi1() \ +({ \ + long mfhi1; \ + __asm__( \ + " .set push \n" \ + " .set dsp \n" \ + " mfhi %0, $ac1 \n" \ + " .set pop \n" \ + : "=r" (mfhi1)); \ + mfhi1; \ +}) + +#define mfhi2() \ +({ \ + long mfhi2; \ + __asm__( \ + " .set push \n" \ + " .set dsp \n" \ + " mfhi %0, $ac2 \n" \ + " .set pop \n" \ + : "=r" (mfhi2)); \ + mfhi2; \ +}) + +#define mfhi3() \ +({ \ + long mfhi3; \ + __asm__( \ + " .set push \n" \ + " .set dsp \n" \ + " mfhi %0, $ac3 \n" \ + " .set pop \n" \ + : "=r" (mfhi3)); \ + mfhi3; \ +}) + + +#define mtlo0(x) \ +({ \ + __asm__( \ + " .set push \n" \ + " .set dsp \n" \ + " mtlo %0, $ac0 \n" \ + " .set pop \n" \ + : \ + : "r" (x)); \ +}) + +#define mtlo1(x) \ +({ \ + __asm__( \ + " .set push \n" \ + " .set dsp \n" \ + " mtlo %0, $ac1 \n" \ + " .set pop \n" \ + : \ + : "r" (x)); \ +}) + +#define mtlo2(x) \ +({ \ + __asm__( \ + " .set push \n" \ + " .set dsp \n" \ + " mtlo %0, $ac2 \n" \ + " .set pop \n" \ + : \ + : "r" (x)); \ +}) + +#define mtlo3(x) \ +({ \ + __asm__( \ + " .set push \n" \ + " .set dsp \n" \ + " mtlo %0, $ac3 \n" \ + " .set pop \n" \ + : \ + : "r" (x)); \ +}) + +#define mthi0(x) \ +({ \ + __asm__( \ + " .set push \n" \ + " .set dsp \n" \ + " mthi %0, $ac0 \n" \ + " .set pop \n" \ + : \ + : "r" (x)); \ +}) + +#define mthi1(x) \ +({ \ + __asm__( \ + " .set push \n" \ + " .set dsp \n" \ + " mthi %0, $ac1 \n" \ + " .set pop \n" \ + : \ + : "r" (x)); \ +}) + +#define mthi2(x) \ +({ \ + __asm__( \ + " .set push \n" \ + " .set dsp \n" \ + " mthi %0, $ac2 \n" \ + " .set pop \n" \ + : \ + : "r" (x)); \ +}) + +#define mthi3(x) \ +({ \ + __asm__( \ + " .set push \n" \ + " .set dsp \n" \ + " mthi %0, $ac3 \n" \ + " .set pop \n" \ + : \ + : "r" (x)); \ +}) #else diff --git a/arch/mips/include/asm/signal.h b/arch/mips/include/asm/signal.h index 197f636..8efe5a9 100644 --- a/arch/mips/include/asm/signal.h +++ b/arch/mips/include/asm/signal.h @@ -21,6 +21,6 @@ #include <asm/sigcontext.h> #include <asm/siginfo.h> -#define __ARCH_HAS_ODD_SIGACTION +#define __ARCH_HAS_IRIX_SIGACTION #endif /* _ASM_SIGNAL_H */ diff --git a/arch/mips/include/uapi/asm/signal.h b/arch/mips/include/uapi/asm/signal.h index d6b18b4..addb9f5 100644 --- a/arch/mips/include/uapi/asm/signal.h +++ b/arch/mips/include/uapi/asm/signal.h @@ -72,6 +72,12 @@ typedef unsigned long old_sigset_t; /* at least 32 bits */ * * SA_ONESHOT and SA_NOMASK are the historical Linux names for the Single * Unix names RESETHAND and NODEFER respectively. + * + * SA_RESTORER used to be defined as 0x04000000 but only the O32 ABI ever + * supported its use and no libc was using it, so the entire sa-restorer + * functionality was removed with lmo commit 39bffc12c3580ab for 2.5.48 + * retaining only the SA_RESTORER definition as a reminder to avoid + * accidental reuse of the mask bit. */ #define SA_ONSTACK 0x08000000 #define SA_RESETHAND 0x80000000 @@ -84,8 +90,6 @@ typedef unsigned long old_sigset_t; /* at least 32 bits */ #define SA_NOMASK SA_NODEFER #define SA_ONESHOT SA_RESETHAND -#define SA_RESTORER 0x04000000 /* Only for o32 */ - #define MINSIGSTKSZ 2048 #define SIGSTKSZ 8192 diff --git a/arch/mips/kernel/Makefile b/arch/mips/kernel/Makefile index f81d98f..de75fb5 100644 --- a/arch/mips/kernel/Makefile +++ b/arch/mips/kernel/Makefile @@ -100,29 +100,16 @@ obj-$(CONFIG_HW_PERF_EVENTS) += perf_event_mipsxx.o obj-$(CONFIG_JUMP_LABEL) += jump_label.o # -# DSP ASE supported for MIPS32 or MIPS64 Release 2 cores only. It is safe -# to enable DSP assembler support here even if the MIPS Release 2 CPU we -# are targetting does not support DSP because all code-paths making use of -# it properly check that the running CPU *actually does* support these -# instructions. +# DSP ASE supported for MIPS32 or MIPS64 Release 2 cores only. It is not +# safe to unconditionnaly use the assembler -mdsp / -mdspr2 switches +# here because the compiler may use DSP ASE instructions (such as lwx) in +# code paths where we cannot check that the CPU we are running on supports it. +# Proper abstraction using HAVE_AS_DSP and macros is done in +# arch/mips/include/asm/mipsregs.h. # ifeq ($(CONFIG_CPU_MIPSR2), y) CFLAGS_DSP = -DHAVE_AS_DSP -# -# Check if assembler supports DSP ASE -# -ifeq ($(call cc-option-yn,-mdsp), y) -CFLAGS_DSP += -mdsp -endif - -# -# Check if assembler supports DSP ASE Rev2 -# -ifeq ($(call cc-option-yn,-mdspr2), y) -CFLAGS_DSP += -mdspr2 -endif - CFLAGS_signal.o = $(CFLAGS_DSP) CFLAGS_signal32.o = $(CFLAGS_DSP) CFLAGS_process.o = $(CFLAGS_DSP) diff --git a/arch/mips/kernel/cpu-probe.c b/arch/mips/kernel/cpu-probe.c index 6bfccc2..5fe66a0 100644 --- a/arch/mips/kernel/cpu-probe.c +++ b/arch/mips/kernel/cpu-probe.c @@ -580,6 +580,9 @@ static inline void cpu_probe_legacy(struct cpuinfo_mips *c, unsigned int cpu) c->tlbsize = 48; break; case PRID_IMP_VR41XX: + set_isa(c, MIPS_CPU_ISA_III); + c->options = R4K_OPTS; + c->tlbsize = 32; switch (c->processor_id & 0xf0) { case PRID_REV_VR4111: c->cputype = CPU_VR4111; @@ -604,6 +607,7 @@ static inline void cpu_probe_legacy(struct cpuinfo_mips *c, unsigned int cpu) __cpu_name[cpu] = "NEC VR4131"; } else { c->cputype = CPU_VR4133; + c->options |= MIPS_CPU_LLSC; __cpu_name[cpu] = "NEC VR4133"; } break; @@ -613,9 +617,6 @@ static inline void cpu_probe_legacy(struct cpuinfo_mips *c, unsigned int cpu) __cpu_name[cpu] = "NEC Vr41xx"; break; } - set_isa(c, MIPS_CPU_ISA_III); - c->options = R4K_OPTS; - c->tlbsize = 32; break; case PRID_IMP_R4300: c->cputype = CPU_R4300; @@ -1226,10 +1227,8 @@ __cpuinit void cpu_probe(void) if (c->options & MIPS_CPU_FPU) { c->fpu_id = cpu_get_fpu_id(); - if (c->isa_level == MIPS_CPU_ISA_M32R1 || - c->isa_level == MIPS_CPU_ISA_M32R2 || - c->isa_level == MIPS_CPU_ISA_M64R1 || - c->isa_level == MIPS_CPU_ISA_M64R2) { + if (c->isa_level & (MIPS_CPU_ISA_M32R1 | MIPS_CPU_ISA_M32R2 | + MIPS_CPU_ISA_M64R1 | MIPS_CPU_ISA_M64R2)) { if (c->fpu_id & MIPS_FPIR_3D) c->ases |= MIPS_ASE_MIPS3D; } diff --git a/arch/mips/kernel/linux32.c b/arch/mips/kernel/linux32.c index 8eeee1c..db9655f 100644 --- a/arch/mips/kernel/linux32.c +++ b/arch/mips/kernel/linux32.c @@ -171,7 +171,7 @@ SYSCALL_DEFINE6(32_ipc, u32, call, long, first, long, second, long, third, err = compat_sys_shmctl(first, second, compat_ptr(ptr)); break; default: - err = -EINVAL; + err = -ENOSYS; break; } diff --git a/arch/mips/kernel/mcount.S b/arch/mips/kernel/mcount.S index 1658676..33d0671 100644 --- a/arch/mips/kernel/mcount.S +++ b/arch/mips/kernel/mcount.S @@ -46,10 +46,9 @@ PTR_L a5, PT_R9(sp) PTR_L a6, PT_R10(sp) PTR_L a7, PT_R11(sp) -#else - PTR_ADDIU sp, PT_SIZE #endif -.endm + PTR_ADDIU sp, PT_SIZE + .endm .macro RETURN_BACK jr ra @@ -68,7 +67,11 @@ NESTED(ftrace_caller, PT_SIZE, ra) .globl _mcount _mcount: b ftrace_stub - addiu sp,sp,8 +#ifdef CONFIG_32BIT + addiu sp,sp,8 +#else + nop +#endif /* When tracing is activated, it calls ftrace_caller+8 (aka here) */ lw t1, function_trace_stop diff --git a/arch/mips/kernel/proc.c b/arch/mips/kernel/proc.c index 135c4aa..7a54f74 100644 --- a/arch/mips/kernel/proc.c +++ b/arch/mips/kernel/proc.c @@ -67,7 +67,7 @@ static int show_cpuinfo(struct seq_file *m, void *v) if (cpu_has_mips_r) { seq_printf(m, "isa\t\t\t:"); if (cpu_has_mips_1) - seq_printf(m, "%s", "mips1"); + seq_printf(m, "%s", " mips1"); if (cpu_has_mips_2) seq_printf(m, "%s", " mips2"); if (cpu_has_mips_3) diff --git a/arch/mips/kernel/traps.c b/arch/mips/kernel/traps.c index a200b5b..c3abb881 100644 --- a/arch/mips/kernel/traps.c +++ b/arch/mips/kernel/traps.c @@ -1571,7 +1571,7 @@ void __cpuinit per_cpu_trap_init(bool is_boot_cpu) #ifdef CONFIG_64BIT status_set |= ST0_FR|ST0_KX|ST0_SX|ST0_UX; #endif - if (current_cpu_data.isa_level == MIPS_CPU_ISA_IV) + if (current_cpu_data.isa_level & MIPS_CPU_ISA_IV) status_set |= ST0_XX; if (cpu_has_dsp) status_set |= ST0_MX; diff --git a/arch/mips/lib/bitops.c b/arch/mips/lib/bitops.c index 81f1dcf..a64daee 100644 --- a/arch/mips/lib/bitops.c +++ b/arch/mips/lib/bitops.c @@ -90,12 +90,12 @@ int __mips_test_and_set_bit(unsigned long nr, unsigned bit = nr & SZLONG_MASK; unsigned long mask; unsigned long flags; - unsigned long res; + int res; a += nr >> SZLONG_LOG; mask = 1UL << bit; raw_local_irq_save(flags); - res = (mask & *a); + res = (mask & *a) != 0; *a |= mask; raw_local_irq_restore(flags); return res; @@ -116,12 +116,12 @@ int __mips_test_and_set_bit_lock(unsigned long nr, unsigned bit = nr & SZLONG_MASK; unsigned long mask; unsigned long flags; - unsigned long res; + int res; a += nr >> SZLONG_LOG; mask = 1UL << bit; raw_local_irq_save(flags); - res = (mask & *a); + res = (mask & *a) != 0; *a |= mask; raw_local_irq_restore(flags); return res; @@ -141,12 +141,12 @@ int __mips_test_and_clear_bit(unsigned long nr, volatile unsigned long *addr) unsigned bit = nr & SZLONG_MASK; unsigned long mask; unsigned long flags; - unsigned long res; + int res; a += nr >> SZLONG_LOG; mask = 1UL << bit; raw_local_irq_save(flags); - res = (mask & *a); + res = (mask & *a) != 0; *a &= ~mask; raw_local_irq_restore(flags); return res; @@ -166,12 +166,12 @@ int __mips_test_and_change_bit(unsigned long nr, volatile unsigned long *addr) unsigned bit = nr & SZLONG_MASK; unsigned long mask; unsigned long flags; - unsigned long res; + int res; a += nr >> SZLONG_LOG; mask = 1UL << bit; raw_local_irq_save(flags); - res = (mask & *a); + res = (mask & *a) != 0; *a ^= mask; raw_local_irq_restore(flags); return res; diff --git a/arch/mips/lib/csum_partial.S b/arch/mips/lib/csum_partial.S index 507147a..a6adffb 100644 --- a/arch/mips/lib/csum_partial.S +++ b/arch/mips/lib/csum_partial.S @@ -270,7 +270,7 @@ LEAF(csum_partial) #endif /* odd buffer alignment? */ -#ifdef CPU_MIPSR2 +#ifdef CONFIG_CPU_MIPSR2 wsbh v1, sum movn sum, v1, t7 #else @@ -670,7 +670,7 @@ EXC( sb t0, NBYTES-2(dst), .Ls_exc) addu sum, v1 #endif -#ifdef CPU_MIPSR2 +#ifdef CONFIG_CPU_MIPSR2 wsbh v1, sum movn sum, v1, odd #else diff --git a/arch/mips/mm/c-r4k.c b/arch/mips/mm/c-r4k.c index ecca559..2078915 100644 --- a/arch/mips/mm/c-r4k.c +++ b/arch/mips/mm/c-r4k.c @@ -1247,10 +1247,8 @@ static void __cpuinit setup_scache(void) return; default: - if (c->isa_level == MIPS_CPU_ISA_M32R1 || - c->isa_level == MIPS_CPU_ISA_M32R2 || - c->isa_level == MIPS_CPU_ISA_M64R1 || - c->isa_level == MIPS_CPU_ISA_M64R2) { + if (c->isa_level & (MIPS_CPU_ISA_M32R1 | MIPS_CPU_ISA_M32R2 | + MIPS_CPU_ISA_M64R1 | MIPS_CPU_ISA_M64R2)) { #ifdef CONFIG_MIPS_CPU_SCACHE if (mips_sc_init ()) { scache_size = c->scache.ways * c->scache.sets * c->scache.linesz; diff --git a/arch/mips/mm/sc-mips.c b/arch/mips/mm/sc-mips.c index 93d937b..df96da7 100644 --- a/arch/mips/mm/sc-mips.c +++ b/arch/mips/mm/sc-mips.c @@ -98,10 +98,8 @@ static inline int __init mips_sc_probe(void) c->scache.flags |= MIPS_CACHE_NOT_PRESENT; /* Ignore anything but MIPSxx processors */ - if (c->isa_level != MIPS_CPU_ISA_M32R1 && - c->isa_level != MIPS_CPU_ISA_M32R2 && - c->isa_level != MIPS_CPU_ISA_M64R1 && - c->isa_level != MIPS_CPU_ISA_M64R2) + if (!(c->isa_level & (MIPS_CPU_ISA_M32R1 | MIPS_CPU_ISA_M32R2 | + MIPS_CPU_ISA_M64R1 | MIPS_CPU_ISA_M64R2))) return 0; /* Does this MIPS32/MIPS64 CPU have a config2 register? */ diff --git a/arch/mips/pci/pci-alchemy.c b/arch/mips/pci/pci-alchemy.c index 38a80c8..d1faece 100644 --- a/arch/mips/pci/pci-alchemy.c +++ b/arch/mips/pci/pci-alchemy.c @@ -19,7 +19,7 @@ #include <asm/mach-au1x00/au1000.h> #include <asm/tlbmisc.h> -#ifdef CONFIG_DEBUG_PCI +#ifdef CONFIG_PCI_DEBUG #define DBG(x...) printk(KERN_DEBUG x) #else #define DBG(x...) do {} while (0) @@ -162,7 +162,7 @@ static int config_access(unsigned char access_type, struct pci_bus *bus, if (status & (1 << 29)) { *data = 0xffffffff; error = -1; - DBG("alchemy-pci: master abort on cfg access %d bus %d dev %d", + DBG("alchemy-pci: master abort on cfg access %d bus %d dev %d\n", access_type, bus->number, device); } else if ((status >> 28) & 0xf) { DBG("alchemy-pci: PCI ERR detected: dev %d, status %lx\n", diff --git a/arch/powerpc/Kconfig b/arch/powerpc/Kconfig index ea5bb04..a9ae673 100644 --- a/arch/powerpc/Kconfig +++ b/arch/powerpc/Kconfig @@ -428,11 +428,6 @@ config NODES_SHIFT default "4" depends on NEED_MULTIPLE_NODES -config MAX_ACTIVE_REGIONS - int - default "256" if PPC64 - default "32" - config ARCH_SELECT_MEMORY_MODEL def_bool y depends on PPC64 @@ -647,14 +642,14 @@ menu "Bus options" config ISA bool "Support for ISA-bus hardware" - depends on PPC_PREP || PPC_CHRP + depends on PPC_CHRP select PPC_I8259 help Find out whether you have ISA slots on your motherboard. ISA is the name of a bus system, i.e. the way the CPU talks to the other stuff inside your box. If you have an Apple machine, say N here; if you - have an IBM RS/6000 or pSeries machine or a PReP machine, say Y. If - you have an embedded board, consult your board documentation. + have an IBM RS/6000 or pSeries machine, say Y. If you have an + embedded board, consult your board documentation. config ZONE_DMA bool @@ -745,7 +740,6 @@ config PCI bool "PCI support" if PPC_PCI_CHOICE default y if !40x && !CPM2 && !8xx && !PPC_83xx \ && !PPC_85xx && !PPC_86xx && !GAMECUBE_COMMON - default PCI_PERMEDIA if !4xx && !CPM2 && !8xx default PCI_QSPAN if !4xx && !CPM2 && 8xx select ARCH_SUPPORTS_MSI select GENERIC_PCI_IOMAP @@ -969,7 +963,7 @@ config TASK_SIZE_BOOL config TASK_SIZE hex "Size of user task space" if TASK_SIZE_BOOL - default "0x80000000" if PPC_PREP || PPC_8xx + default "0x80000000" if PPC_8xx default "0xc0000000" config CONSISTENT_SIZE_BOOL diff --git a/arch/powerpc/configs/ps3_defconfig b/arch/powerpc/configs/ps3_defconfig index 7a5c15f..f791962 100644 --- a/arch/powerpc/configs/ps3_defconfig +++ b/arch/powerpc/configs/ps3_defconfig @@ -3,11 +3,11 @@ CONFIG_TUNE_CELL=y CONFIG_ALTIVEC=y CONFIG_SMP=y CONFIG_NR_CPUS=2 -CONFIG_EXPERIMENTAL=y CONFIG_SYSVIPC=y CONFIG_POSIX_MQUEUE=y CONFIG_HIGH_RES_TIMERS=y CONFIG_BLK_DEV_INITRD=y +CONFIG_RD_LZMA=y CONFIG_CC_OPTIMIZE_FOR_SIZE=y CONFIG_EMBEDDED=y # CONFIG_PERF_EVENTS is not set diff --git a/arch/powerpc/include/asm/bitops.h b/arch/powerpc/include/asm/bitops.h index 08bd299..910194e 100644 --- a/arch/powerpc/include/asm/bitops.h +++ b/arch/powerpc/include/asm/bitops.h @@ -53,7 +53,7 @@ #define smp_mb__after_clear_bit() smp_mb() /* Macro for generating the ***_bits() functions */ -#define DEFINE_BITOP(fn, op, prefix, postfix) \ +#define DEFINE_BITOP(fn, op, prefix) \ static __inline__ void fn(unsigned long mask, \ volatile unsigned long *_p) \ { \ @@ -66,16 +66,15 @@ static __inline__ void fn(unsigned long mask, \ PPC405_ERR77(0,%3) \ PPC_STLCX "%0,0,%3\n" \ "bne- 1b\n" \ - postfix \ : "=&r" (old), "+m" (*p) \ : "r" (mask), "r" (p) \ : "cc", "memory"); \ } -DEFINE_BITOP(set_bits, or, "", "") -DEFINE_BITOP(clear_bits, andc, "", "") -DEFINE_BITOP(clear_bits_unlock, andc, PPC_RELEASE_BARRIER, "") -DEFINE_BITOP(change_bits, xor, "", "") +DEFINE_BITOP(set_bits, or, "") +DEFINE_BITOP(clear_bits, andc, "") +DEFINE_BITOP(clear_bits_unlock, andc, PPC_RELEASE_BARRIER) +DEFINE_BITOP(change_bits, xor, "") static __inline__ void set_bit(int nr, volatile unsigned long *addr) { diff --git a/arch/powerpc/include/asm/cputable.h b/arch/powerpc/include/asm/cputable.h index fb3245e..ccadad6 100644 --- a/arch/powerpc/include/asm/cputable.h +++ b/arch/powerpc/include/asm/cputable.h @@ -52,6 +52,7 @@ struct cpu_spec { char *cpu_name; unsigned long cpu_features; /* Kernel features */ unsigned int cpu_user_features; /* Userland features */ + unsigned int cpu_user_features2; /* Userland features v2 */ unsigned int mmu_features; /* MMU features */ /* cache line sizes */ diff --git a/arch/powerpc/include/asm/dma.h b/arch/powerpc/include/asm/dma.h index f6813e9..a5c6d83 100644 --- a/arch/powerpc/include/asm/dma.h +++ b/arch/powerpc/include/asm/dma.h @@ -16,10 +16,6 @@ * * None of this really applies for Power Macintoshes. There is * basically just enough here to get kernel/dma.c to compile. - * - * There may be some comments or restrictions made here which are - * not valid for the PReP platform. Take what you read - * with a grain of salt. */ #include <asm/io.h> @@ -57,7 +53,6 @@ * - page registers for 5-7 don't use data bit 0, represent 128K pages * - page registers for 0-3 use bit 0, represent 64K pages * - * On PReP, DMA transfers are limited to the lower 16MB of _physical_ memory. * On CHRP, the W83C553F (and VLSI Tollgate?) support full 32 bit addressing. * Note that addresses loaded into registers must be _physical_ addresses, * not logical addresses (which may differ if paging is active). diff --git a/arch/powerpc/include/asm/elf.h b/arch/powerpc/include/asm/elf.h index ac9790f..cc0655a 100644 --- a/arch/powerpc/include/asm/elf.h +++ b/arch/powerpc/include/asm/elf.h @@ -61,6 +61,7 @@ typedef elf_vrregset_t elf_fpxregset_t; instruction set this cpu supports. This could be done in userspace, but it's not easy, and we've already done it here. */ # define ELF_HWCAP (cur_cpu_spec->cpu_user_features) +# define ELF_HWCAP2 (cur_cpu_spec->cpu_user_features2) /* This yields a string that ld.so will use to load implementation specific libraries for optimization. This is more specific in diff --git a/arch/powerpc/include/asm/exception-64s.h b/arch/powerpc/include/asm/exception-64s.h index 05e6d2e..8e5fae8 100644 --- a/arch/powerpc/include/asm/exception-64s.h +++ b/arch/powerpc/include/asm/exception-64s.h @@ -414,7 +414,6 @@ label##_relon_hv: \ #define SOFTEN_NOTEST_HV(vec) _SOFTEN_TEST(EXC_HV, vec) #define __MASKABLE_EXCEPTION_PSERIES(vec, label, h, extra) \ - HMT_MEDIUM_PPR_DISCARD; \ SET_SCRATCH0(r13); /* save r13 */ \ EXCEPTION_PROLOG_0(PACA_EXGEN); \ __EXCEPTION_PROLOG_1(PACA_EXGEN, extra, vec); \ @@ -427,6 +426,7 @@ label##_relon_hv: \ . = loc; \ .globl label##_pSeries; \ label##_pSeries: \ + HMT_MEDIUM_PPR_DISCARD; \ _MASKABLE_EXCEPTION_PSERIES(vec, label, \ EXC_STD, SOFTEN_TEST_PR) diff --git a/arch/powerpc/include/asm/firmware.h b/arch/powerpc/include/asm/firmware.h index 097dee5..0df5464 100644 --- a/arch/powerpc/include/asm/firmware.h +++ b/arch/powerpc/include/asm/firmware.h @@ -18,7 +18,6 @@ #include <asm/feature-fixups.h> /* firmware feature bitmask values */ -#define FIRMWARE_MAX_FEATURES 63 #define FW_FEATURE_PFT ASM_CONST(0x0000000000000001) #define FW_FEATURE_TCE ASM_CONST(0x0000000000000002) @@ -51,6 +50,8 @@ #define FW_FEATURE_OPALv2 ASM_CONST(0x0000000020000000) #define FW_FEATURE_SET_MODE ASM_CONST(0x0000000040000000) #define FW_FEATURE_BEST_ENERGY ASM_CONST(0x0000000080000000) +#define FW_FEATURE_TYPE1_AFFINITY ASM_CONST(0x0000000100000000) +#define FW_FEATURE_PRRN ASM_CONST(0x0000000200000000) #ifndef __ASSEMBLY__ @@ -65,7 +66,8 @@ enum { FW_FEATURE_BULK_REMOVE | FW_FEATURE_XDABR | FW_FEATURE_MULTITCE | FW_FEATURE_SPLPAR | FW_FEATURE_LPAR | FW_FEATURE_CMO | FW_FEATURE_VPHN | FW_FEATURE_XCMO | - FW_FEATURE_SET_MODE | FW_FEATURE_BEST_ENERGY, + FW_FEATURE_SET_MODE | FW_FEATURE_BEST_ENERGY | + FW_FEATURE_TYPE1_AFFINITY | FW_FEATURE_PRRN, FW_FEATURE_PSERIES_ALWAYS = 0, FW_FEATURE_POWERNV_POSSIBLE = FW_FEATURE_OPAL | FW_FEATURE_OPALv2, FW_FEATURE_POWERNV_ALWAYS = 0, diff --git a/arch/powerpc/include/asm/hardirq.h b/arch/powerpc/include/asm/hardirq.h index 3147a29..3bdcfce 100644 --- a/arch/powerpc/include/asm/hardirq.h +++ b/arch/powerpc/include/asm/hardirq.h @@ -10,6 +10,9 @@ typedef struct { unsigned int pmu_irqs; unsigned int mce_exceptions; unsigned int spurious_irqs; +#ifdef CONFIG_PPC_DOORBELL + unsigned int doorbell_irqs; +#endif } ____cacheline_aligned irq_cpustat_t; DECLARE_PER_CPU_SHARED_ALIGNED(irq_cpustat_t, irq_stat); diff --git a/arch/powerpc/include/asm/io.h b/arch/powerpc/include/asm/io.h index f94ef42..dd15e5e 100644 --- a/arch/powerpc/include/asm/io.h +++ b/arch/powerpc/include/asm/io.h @@ -15,10 +15,6 @@ extern int check_legacy_ioport(unsigned long base_port); #define I8042_DATA_REG 0x60 #define FDC_BASE 0x3f0 -/* only relevant for PReP */ -#define _PIDXR 0x279 -#define _PNPWRP 0xa79 -#define PNPBIOS_BASE 0xf000 #if defined(CONFIG_PPC64) && defined(CONFIG_PCI) extern struct pci_dev *isa_bridge_pcidev; diff --git a/arch/powerpc/include/asm/opal.h b/arch/powerpc/include/asm/opal.h index a4b28f1..b6c8b58 100644 --- a/arch/powerpc/include/asm/opal.h +++ b/arch/powerpc/include/asm/opal.h @@ -117,6 +117,7 @@ extern int opal_enter_rtas(struct rtas_args *args, #define OPAL_SET_SLOT_LED_STATUS 55 #define OPAL_GET_EPOW_STATUS 56 #define OPAL_SET_SYSTEM_ATTENTION_LED 57 +#define OPAL_PCI_MSI_EOI 63 #ifndef __ASSEMBLY__ @@ -506,6 +507,7 @@ int64_t opal_pci_get_xive_reissue(uint64_t phb_id, uint32_t xive_number, uint8_t *p_bit, uint8_t *q_bit); int64_t opal_pci_set_xive_reissue(uint64_t phb_id, uint32_t xive_number, uint8_t p_bit, uint8_t q_bit); +int64_t opal_pci_msi_eoi(uint64_t phb_id, uint32_t hw_irq); int64_t opal_pci_set_xive_pe(uint64_t phb_id, uint32_t pe_number, uint32_t xive_num); int64_t opal_get_xive_source(uint64_t phb_id, uint32_t xive_num, diff --git a/arch/powerpc/include/asm/page_64.h b/arch/powerpc/include/asm/page_64.h index cd915d6..88693ce 100644 --- a/arch/powerpc/include/asm/page_64.h +++ b/arch/powerpc/include/asm/page_64.h @@ -99,8 +99,7 @@ extern unsigned long slice_get_unmapped_area(unsigned long addr, unsigned long len, unsigned long flags, unsigned int psize, - int topdown, - int use_cache); + int topdown); extern unsigned int get_slice_psize(struct mm_struct *mm, unsigned long addr); diff --git a/arch/powerpc/include/asm/parport.h b/arch/powerpc/include/asm/parport.h index 6dc2577..a452968 100644 --- a/arch/powerpc/include/asm/parport.h +++ b/arch/powerpc/include/asm/parport.h @@ -21,9 +21,7 @@ static int parport_pc_find_nonpci_ports (int autoirq, int autodma) int count = 0; int virq; - for (np = NULL; (np = of_find_compatible_node(np, - "parallel", - "pnpPNP,400")) != NULL;) { + for_each_compatible_node(np, "parallel", "pnpPNP,400") { prop = of_get_property(np, "reg", &propsize); if (!prop || propsize > 6*sizeof(u32)) continue; diff --git a/arch/powerpc/include/asm/perf_event_server.h b/arch/powerpc/include/asm/perf_event_server.h index d0aec72..f265049 100644 --- a/arch/powerpc/include/asm/perf_event_server.h +++ b/arch/powerpc/include/asm/perf_event_server.h @@ -33,6 +33,8 @@ struct power_pmu { unsigned long *valp); int (*get_alternatives)(u64 event_id, unsigned int flags, u64 alt[]); + u64 (*bhrb_filter_map)(u64 branch_sample_type); + void (*config_bhrb)(u64 pmu_bhrb_filter); void (*disable_pmc)(unsigned int pmc, unsigned long mmcr[]); int (*limited_pmc_event)(u64 event_id); u32 flags; @@ -42,6 +44,9 @@ struct power_pmu { int (*cache_events)[PERF_COUNT_HW_CACHE_MAX] [PERF_COUNT_HW_CACHE_OP_MAX] [PERF_COUNT_HW_CACHE_RESULT_MAX]; + + /* BHRB entries in the PMU */ + int bhrb_nr; }; /* @@ -52,6 +57,9 @@ struct power_pmu { #define PPMU_NO_SIPR 0x00000004 /* no SIPR/HV in MMCRA at all */ #define PPMU_NO_CONT_SAMPLING 0x00000008 /* no continuous sampling */ #define PPMU_SIAR_VALID 0x00000010 /* Processor has SIAR Valid bit */ +#define PPMU_HAS_SSLOT 0x00000020 /* Has sampled slot in MMCRA */ +#define PPMU_HAS_SIER 0x00000040 /* Has SIER */ +#define PPMU_BHRB 0x00000080 /* has BHRB feature enabled */ /* * Values for flags to get_alternatives() @@ -65,6 +73,7 @@ extern int register_power_pmu(struct power_pmu *); struct pt_regs; extern unsigned long perf_misc_flags(struct pt_regs *regs); extern unsigned long perf_instruction_pointer(struct pt_regs *regs); +extern unsigned long int read_bhrb(int n); /* * Only override the default definitions in include/linux/perf_event.h diff --git a/arch/powerpc/include/asm/ppc-opcode.h b/arch/powerpc/include/asm/ppc-opcode.h index 8752bc8..0c34e48 100644 --- a/arch/powerpc/include/asm/ppc-opcode.h +++ b/arch/powerpc/include/asm/ppc-opcode.h @@ -82,6 +82,8 @@ #define __REGA0_R31 31 /* sorted alphabetically */ +#define PPC_INST_BHRBE 0x7c00025c +#define PPC_INST_CLRBHRB 0x7c00035c #define PPC_INST_DCBA 0x7c0005ec #define PPC_INST_DCBA_MASK 0xfc0007fe #define PPC_INST_DCBAL 0x7c2005ec @@ -297,6 +299,12 @@ #define PPC_NAP stringify_in_c(.long PPC_INST_NAP) #define PPC_SLEEP stringify_in_c(.long PPC_INST_SLEEP) +/* BHRB instructions */ +#define PPC_CLRBHRB stringify_in_c(.long PPC_INST_CLRBHRB) +#define PPC_MFBHRBE(r, n) stringify_in_c(.long PPC_INST_BHRBE | \ + __PPC_RT(r) | \ + (((n) & 0x3ff) << 11)) + /* Transactional memory instructions */ #define TRECHKPT stringify_in_c(.long PPC_INST_TRECHKPT) #define TRECLAIM(r) stringify_in_c(.long PPC_INST_TRECLAIM \ diff --git a/arch/powerpc/include/asm/processor.h b/arch/powerpc/include/asm/processor.h index 7ff9eaa..0a4cc5d 100644 --- a/arch/powerpc/include/asm/processor.h +++ b/arch/powerpc/include/asm/processor.h @@ -40,7 +40,7 @@ * -- BenH. */ -/* PREP sub-platform types see residual.h for these */ +/* PREP sub-platform types. Unused */ #define _PREP_Motorola 0x01 /* motorola prep */ #define _PREP_Firm 0x02 /* firmworks prep */ #define _PREP_IBM 0x00 /* ibm prep */ @@ -56,13 +56,6 @@ extern int _chrp_type; -#ifdef CONFIG_PPC_PREP - -/* what kind of prep workstation we are */ -extern int _prep_type; - -#endif /* CONFIG_PPC_PREP */ - #endif /* defined(__KERNEL__) && defined(CONFIG_PPC32) */ /* diff --git a/arch/powerpc/include/asm/prom.h b/arch/powerpc/include/asm/prom.h index 99c92d5..bc2da15 100644 --- a/arch/powerpc/include/asm/prom.h +++ b/arch/powerpc/include/asm/prom.h @@ -74,6 +74,75 @@ struct of_drconf_cell { #define DRCONF_MEM_AI_INVALID 0x00000040 #define DRCONF_MEM_RESERVED 0x00000080 +/* + * There are two methods for telling firmware what our capabilities are. + * Newer machines have an "ibm,client-architecture-support" method on the + * root node. For older machines, we have to call the "process-elf-header" + * method in the /packages/elf-loader node, passing it a fake 32-bit + * ELF header containing a couple of PT_NOTE sections that contain + * structures that contain various information. + */ + +/* New method - extensible architecture description vector. */ + +/* Option vector bits - generic bits in byte 1 */ +#define OV_IGNORE 0x80 /* ignore this vector */ +#define OV_CESSATION_POLICY 0x40 /* halt if unsupported option present*/ + +/* Option vector 1: processor architectures supported */ +#define OV1_PPC_2_00 0x80 /* set if we support PowerPC 2.00 */ +#define OV1_PPC_2_01 0x40 /* set if we support PowerPC 2.01 */ +#define OV1_PPC_2_02 0x20 /* set if we support PowerPC 2.02 */ +#define OV1_PPC_2_03 0x10 /* set if we support PowerPC 2.03 */ +#define OV1_PPC_2_04 0x08 /* set if we support PowerPC 2.04 */ +#define OV1_PPC_2_05 0x04 /* set if we support PowerPC 2.05 */ +#define OV1_PPC_2_06 0x02 /* set if we support PowerPC 2.06 */ +#define OV1_PPC_2_07 0x01 /* set if we support PowerPC 2.07 */ + +/* Option vector 2: Open Firmware options supported */ +#define OV2_REAL_MODE 0x20 /* set if we want OF in real mode */ + +/* Option vector 3: processor options supported */ +#define OV3_FP 0x80 /* floating point */ +#define OV3_VMX 0x40 /* VMX/Altivec */ +#define OV3_DFP 0x20 /* decimal FP */ + +/* Option vector 4: IBM PAPR implementation */ +#define OV4_MIN_ENT_CAP 0x01 /* minimum VP entitled capacity */ + +/* Option vector 5: PAPR/OF options supported + * These bits are also used in firmware_has_feature() to validate + * the capabilities reported for vector 5 in the device tree so we + * encode the vector index in the define and use the OV5_FEAT() + * and OV5_INDX() macros to extract the desired information. + */ +#define OV5_FEAT(x) ((x) & 0xff) +#define OV5_INDX(x) ((x) >> 8) +#define OV5_LPAR 0x0280 /* logical partitioning supported */ +#define OV5_SPLPAR 0x0240 /* shared-processor LPAR supported */ +/* ibm,dynamic-reconfiguration-memory property supported */ +#define OV5_DRCONF_MEMORY 0x0220 +#define OV5_LARGE_PAGES 0x0210 /* large pages supported */ +#define OV5_DONATE_DEDICATE_CPU 0x0202 /* donate dedicated CPU support */ +#define OV5_MSI 0x0201 /* PCIe/MSI support */ +#define OV5_CMO 0x0480 /* Cooperative Memory Overcommitment */ +#define OV5_XCMO 0x0440 /* Page Coalescing */ +#define OV5_TYPE1_AFFINITY 0x0580 /* Type 1 NUMA affinity */ +#define OV5_PRRN 0x0540 /* Platform Resource Reassignment */ +#define OV5_PFO_HW_RNG 0x0E80 /* PFO Random Number Generator */ +#define OV5_PFO_HW_842 0x0E40 /* PFO Compression Accelerator */ +#define OV5_PFO_HW_ENCR 0x0E20 /* PFO Encryption Accelerator */ +#define OV5_SUB_PROCESSORS 0x0F01 /* 1,2,or 4 Sub-Processors supported */ + +/* Option Vector 6: IBM PAPR hints */ +#define OV6_LINUX 0x02 /* Linux is our OS */ + +/* + * The architecture vector has an array of PVR mask/value pairs, + * followed by # option vectors - 1, followed by the option vectors. + */ +extern unsigned char ibm_architecture_vec[]; + /* These includes are put at the bottom because they may contain things * that are overridden by this file. Ideally they shouldn't be included * by this file, but there are a bunch of .c files that currently depend diff --git a/arch/powerpc/include/asm/ptrace.h b/arch/powerpc/include/asm/ptrace.h index 5f99568..becc08e 100644 --- a/arch/powerpc/include/asm/ptrace.h +++ b/arch/powerpc/include/asm/ptrace.h @@ -92,7 +92,8 @@ static inline long regs_return_value(struct pt_regs *regs) } while(0) struct task_struct; -extern unsigned long ptrace_get_reg(struct task_struct *task, int regno); +extern int ptrace_get_reg(struct task_struct *task, int regno, + unsigned long *data); extern int ptrace_put_reg(struct task_struct *task, int regno, unsigned long data); diff --git a/arch/powerpc/include/asm/reg.h b/arch/powerpc/include/asm/reg.h index c9c67fc..5c6fbe2 100644 --- a/arch/powerpc/include/asm/reg.h +++ b/arch/powerpc/include/asm/reg.h @@ -268,6 +268,13 @@ #define SPRN_FSCR 0x099 /* Facility Status & Control Register */ #define FSCR_TAR (1 << (63-55)) /* Enable Target Address Register */ #define FSCR_DSCR (1 << (63-61)) /* Enable Data Stream Control Register */ +#define SPRN_HFSCR 0xbe /* HV=1 Facility Status & Control Register */ +#define HFSCR_TAR (1 << (63-55)) /* Enable Target Address Register */ +#define HFSCR_TM (1 << (63-58)) /* Enable Transactional Memory */ +#define HFSCR_PM (1 << (63-60)) /* Enable prob/priv access to PMU SPRs */ +#define HFSCR_DSCR (1 << (63-61)) /* Enable Data Stream Control Register */ +#define HFSCR_VECVSX (1 << (63-62)) /* Enable VMX/VSX */ +#define HFSCR_FP (1 << (63-63)) /* Enable Floating Point */ #define SPRN_TAR 0x32f /* Target Address Register */ #define SPRN_LPCR 0x13E /* LPAR Control Register */ #define LPCR_VPM0 (1ul << (63-0)) @@ -631,6 +638,7 @@ #define MMCR0_FCWAIT 0x00000002UL /* freeze counter in WAIT state */ #define MMCR0_FCHV 0x00000001UL /* freeze conditions in hypervisor mode */ #define SPRN_MMCR1 798 +#define SPRN_MMCR2 769 #define SPRN_MMCRA 0x312 #define MMCRA_SDSYNC 0x80000000UL /* SDAR synced with SIAR */ #define MMCRA_SDAR_DCACHE_MISS 0x40000000UL @@ -649,6 +657,10 @@ #define POWER7P_MMCRA_SIAR_VALID 0x10000000 /* P7+ SIAR contents valid */ #define POWER7P_MMCRA_SDAR_VALID 0x08000000 /* P7+ SDAR contents valid */ +#define SPRN_MMCRH 316 /* Hypervisor monitor mode control register */ +#define SPRN_MMCRS 894 /* Supervisor monitor mode control register */ +#define SPRN_MMCRC 851 /* Core monitor mode control register */ + #define SPRN_PMC1 787 #define SPRN_PMC2 788 #define SPRN_PMC3 789 @@ -659,6 +671,11 @@ #define SPRN_PMC8 794 #define SPRN_SIAR 780 #define SPRN_SDAR 781 +#define SPRN_SIER 784 +#define SIER_SIPR 0x2000000 /* Sampled MSR_PR */ +#define SIER_SIHV 0x1000000 /* Sampled MSR_HV */ +#define SIER_SIAR_VALID 0x0400000 /* SIAR contents valid */ +#define SIER_SDAR_VALID 0x0200000 /* SDAR contents valid */ #define SPRN_PA6T_MMCR0 795 #define PA6T_MMCR0_EN0 0x0000000000000001UL diff --git a/arch/powerpc/include/asm/rtas.h b/arch/powerpc/include/asm/rtas.h index aef00c6..a8bc2bb 100644 --- a/arch/powerpc/include/asm/rtas.h +++ b/arch/powerpc/include/asm/rtas.h @@ -143,6 +143,8 @@ struct rtas_suspend_me_data { #define RTAS_TYPE_PMGM_TIME_ALARM 0x6f #define RTAS_TYPE_PMGM_CONFIG_CHANGE 0x70 #define RTAS_TYPE_PMGM_SERVICE_PROC 0x71 +/* Platform Resource Reassignment Notification */ +#define RTAS_TYPE_PRRN 0xA0 /* RTAS check-exception vector offset */ #define RTAS_VECTOR_EXTERNAL_INTERRUPT 0x500 @@ -277,6 +279,10 @@ extern int early_init_dt_scan_rtas(unsigned long node, extern void pSeries_log_error(char *buf, unsigned int err_type, int fatal); +#ifdef CONFIG_PPC_PSERIES +extern int pseries_devicetree_update(s32 scope); +#endif + #ifdef CONFIG_PPC_RTAS_DAEMON extern void rtas_cancel_event_scan(void); #else diff --git a/arch/powerpc/include/asm/smp.h b/arch/powerpc/include/asm/smp.h index 195ce2a..ffbaabe 100644 --- a/arch/powerpc/include/asm/smp.h +++ b/arch/powerpc/include/asm/smp.h @@ -143,6 +143,8 @@ extern void __cpu_die(unsigned int cpu); /* for UP */ #define hard_smp_processor_id() get_hard_smp_processor_id(0) #define smp_setup_cpu_maps() +static inline void inhibit_secondary_onlining(void) {} +static inline void uninhibit_secondary_onlining(void) {} #endif /* CONFIG_SMP */ diff --git a/arch/powerpc/include/asm/topology.h b/arch/powerpc/include/asm/topology.h index 852ed1b..161ab66 100644 --- a/arch/powerpc/include/asm/topology.h +++ b/arch/powerpc/include/asm/topology.h @@ -71,6 +71,7 @@ static inline void sysfs_remove_device_from_node(struct device *dev, #if defined(CONFIG_NUMA) && defined(CONFIG_PPC_SPLPAR) extern int start_topology_update(void); extern int stop_topology_update(void); +extern int prrn_is_enabled(void); #else static inline int start_topology_update(void) { @@ -80,6 +81,10 @@ static inline int stop_topology_update(void) { return 0; } +static inline int prrn_is_enabled(void) +{ + return 0; +} #endif /* CONFIG_NUMA && CONFIG_PPC_SPLPAR */ #include <asm-generic/topology.h> diff --git a/arch/powerpc/include/asm/xics.h b/arch/powerpc/include/asm/xics.h index 4ae9a09..282d43a 100644 --- a/arch/powerpc/include/asm/xics.h +++ b/arch/powerpc/include/asm/xics.h @@ -150,6 +150,7 @@ extern void xics_register_ics(struct ics *ics); extern void xics_teardown_cpu(void); extern void xics_kexec_teardown_cpu(int secondary); extern void xics_migrate_irqs_away(void); +extern void icp_native_eoi(struct irq_data *d); #ifdef CONFIG_SMP extern int xics_get_irq_server(unsigned int virq, const struct cpumask *cpumask, unsigned int strict_check); diff --git a/arch/powerpc/include/uapi/asm/ptrace.h b/arch/powerpc/include/uapi/asm/ptrace.h index 66b9ca4..77d2ed3 100644 --- a/arch/powerpc/include/uapi/asm/ptrace.h +++ b/arch/powerpc/include/uapi/asm/ptrace.h @@ -211,6 +211,7 @@ struct ppc_debug_info { #define PPC_DEBUG_FEATURE_INSN_BP_MASK 0x0000000000000002 #define PPC_DEBUG_FEATURE_DATA_BP_RANGE 0x0000000000000004 #define PPC_DEBUG_FEATURE_DATA_BP_MASK 0x0000000000000008 +#define PPC_DEBUG_FEATURE_DATA_BP_DAWR 0x0000000000000010 #ifndef __ASSEMBLY__ diff --git a/arch/powerpc/kernel/cpu_setup_power.S b/arch/powerpc/kernel/cpu_setup_power.S index ea847ab..e0c419b 100644 --- a/arch/powerpc/kernel/cpu_setup_power.S +++ b/arch/powerpc/kernel/cpu_setup_power.S @@ -49,6 +49,7 @@ _GLOBAL(__restore_cpu_power7) _GLOBAL(__setup_cpu_power8) mflr r11 bl __init_FSCR + bl __init_PMU bl __init_hvmode_206 mtlr r11 beqlr @@ -57,22 +58,28 @@ _GLOBAL(__setup_cpu_power8) mfspr r3,SPRN_LPCR oris r3, r3, LPCR_AIL_3@h bl __init_LPCR + bl __init_HFSCR bl __init_TLB + bl __init_PMU_HV mtlr r11 blr _GLOBAL(__restore_cpu_power8) mflr r11 bl __init_FSCR + bl __init_PMU mfmsr r3 rldicl. r0,r3,4,63 + mtlr r11 beqlr li r0,0 mtspr SPRN_LPID,r0 mfspr r3,SPRN_LPCR oris r3, r3, LPCR_AIL_3@h bl __init_LPCR + bl __init_HFSCR bl __init_TLB + bl __init_PMU_HV mtlr r11 blr @@ -120,6 +127,12 @@ __init_FSCR: mtspr SPRN_FSCR,r3 blr +__init_HFSCR: + mfspr r3,SPRN_HFSCR + ori r3,r3,HFSCR_TAR|HFSCR_TM|HFSCR_DSCR|HFSCR_VECVSX|HFSCR_FP|HFSCR_PM + mtspr SPRN_HFSCR,r3 + blr + __init_TLB: /* Clear the TLB */ li r6,128 @@ -131,3 +144,18 @@ __init_TLB: bdnz 2b ptesync 1: blr + +__init_PMU_HV: + li r5,0 + mtspr SPRN_MMCRC,r5 + mtspr SPRN_MMCRH,r5 + blr + +__init_PMU: + li r5,0 + mtspr SPRN_MMCRS,r5 + mtspr SPRN_MMCRA,r5 + mtspr SPRN_MMCR0,r5 + mtspr SPRN_MMCR1,r5 + mtspr SPRN_MMCR2,r5 + blr diff --git a/arch/powerpc/kernel/dbell.c b/arch/powerpc/kernel/dbell.c index 9ebbc24..d55c76c 100644 --- a/arch/powerpc/kernel/dbell.c +++ b/arch/powerpc/kernel/dbell.c @@ -41,6 +41,8 @@ void doorbell_exception(struct pt_regs *regs) may_hard_irq_enable(); + __get_cpu_var(irq_stat).doorbell_irqs++; + smp_ipi_demux(); irq_exit(); diff --git a/arch/powerpc/kernel/entry_64.S b/arch/powerpc/kernel/entry_64.S index 256c5bf..04d69c4 100644 --- a/arch/powerpc/kernel/entry_64.S +++ b/arch/powerpc/kernel/entry_64.S @@ -304,7 +304,7 @@ syscall_exit_work: subi r12,r12,TI_FLAGS 4: /* Anything else left to do? */ - SET_DEFAULT_THREAD_PPR(r3, r9) /* Set thread.ppr = 3 */ + SET_DEFAULT_THREAD_PPR(r3, r10) /* Set thread.ppr = 3 */ andi. r0,r9,(_TIF_SYSCALL_T_OR_A|_TIF_SINGLESTEP) beq .ret_from_except_lite @@ -657,7 +657,7 @@ resume_kernel: /* Clear _TIF_EMULATE_STACK_STORE flag */ lis r11,_TIF_EMULATE_STACK_STORE@h addi r5,r9,TI_FLAGS - ldarx r4,0,r5 +0: ldarx r4,0,r5 andc r4,r4,r11 stdcx. r4,0,r5 bne- 0b diff --git a/arch/powerpc/kernel/exceptions-64s.S b/arch/powerpc/kernel/exceptions-64s.S index 56bd923..80d56f0 100644 --- a/arch/powerpc/kernel/exceptions-64s.S +++ b/arch/powerpc/kernel/exceptions-64s.S @@ -235,6 +235,7 @@ instruction_access_slb_pSeries: .globl hardware_interrupt_hv; hardware_interrupt_pSeries: hardware_interrupt_hv: + HMT_MEDIUM_PPR_DISCARD BEGIN_FTR_SECTION _MASKABLE_EXCEPTION_PSERIES(0x502, hardware_interrupt, EXC_HV, SOFTEN_TEST_HV) @@ -254,7 +255,11 @@ hardware_interrupt_hv: STD_EXCEPTION_PSERIES(0x800, 0x800, fp_unavailable) KVM_HANDLER_PR(PACA_EXGEN, EXC_STD, 0x800) - MASKABLE_EXCEPTION_PSERIES(0x900, 0x900, decrementer) + . = 0x900 + .globl decrementer_pSeries +decrementer_pSeries: + _MASKABLE_EXCEPTION_PSERIES(0x900, decrementer, EXC_STD, SOFTEN_TEST_PR) + STD_EXCEPTION_HV(0x980, 0x982, hdecrementer) MASKABLE_EXCEPTION_PSERIES(0xa00, 0xa00, doorbell_super) @@ -797,7 +802,7 @@ hardware_interrupt_relon_hv: _MASKABLE_RELON_EXCEPTION_PSERIES(0x502, hardware_interrupt, EXC_HV, SOFTEN_TEST_HV) FTR_SECTION_ELSE _MASKABLE_RELON_EXCEPTION_PSERIES(0x500, hardware_interrupt, EXC_STD, SOFTEN_TEST_PR) - ALT_FTR_SECTION_END_IFSET(CPU_FTR_ARCH_206) + ALT_FTR_SECTION_END_IFSET(CPU_FTR_HVMODE) STD_RELON_EXCEPTION_PSERIES(0x4600, 0x600, alignment) STD_RELON_EXCEPTION_PSERIES(0x4700, 0x700, program_check) STD_RELON_EXCEPTION_PSERIES(0x4800, 0x800, fp_unavailable) @@ -870,10 +875,6 @@ tm_unavailable_relon_pSeries_1: . = 0x5500 b denorm_exception_hv #endif -#ifdef CONFIG_HVC_SCOM - STD_RELON_EXCEPTION_HV(0x5600, 0x1600, maintence_interrupt) - KVM_HANDLER_SKIP(PACA_EXGEN, EXC_HV, 0x1600) -#endif /* CONFIG_HVC_SCOM */ STD_RELON_EXCEPTION_PSERIES(0x5700, 0x1700, altivec_assist) /* Other future vectors */ diff --git a/arch/powerpc/kernel/head_64.S b/arch/powerpc/kernel/head_64.S index 0886ae6..b61363d 100644 --- a/arch/powerpc/kernel/head_64.S +++ b/arch/powerpc/kernel/head_64.S @@ -509,6 +509,7 @@ _GLOBAL(copy_and_flush) sync addi r5,r5,8 addi r6,r6,8 + isync blr .align 8 diff --git a/arch/powerpc/kernel/iommu.c b/arch/powerpc/kernel/iommu.c index 31c4fdc..c0d0dbd 100644 --- a/arch/powerpc/kernel/iommu.c +++ b/arch/powerpc/kernel/iommu.c @@ -102,7 +102,7 @@ static int __init fail_iommu_debugfs(void) struct dentry *dir = fault_create_debugfs_attr("fail_iommu", NULL, &fail_iommu); - return IS_ERR(dir) ? PTR_ERR(dir) : 0; + return PTR_RET(dir); } late_initcall(fail_iommu_debugfs); diff --git a/arch/powerpc/kernel/irq.c b/arch/powerpc/kernel/irq.c index 4f97fe34..5cbcf4d 100644 --- a/arch/powerpc/kernel/irq.c +++ b/arch/powerpc/kernel/irq.c @@ -374,6 +374,15 @@ int arch_show_interrupts(struct seq_file *p, int prec) seq_printf(p, "%10u ", per_cpu(irq_stat, j).mce_exceptions); seq_printf(p, " Machine check exceptions\n"); +#ifdef CONFIG_PPC_DOORBELL + if (cpu_has_feature(CPU_FTR_DBELL)) { + seq_printf(p, "%*s: ", prec, "DBL"); + for_each_online_cpu(j) + seq_printf(p, "%10u ", per_cpu(irq_stat, j).doorbell_irqs); + seq_printf(p, " Doorbell interrupts\n"); + } +#endif + return 0; } @@ -387,6 +396,9 @@ u64 arch_irq_stat_cpu(unsigned int cpu) sum += per_cpu(irq_stat, cpu).pmu_irqs; sum += per_cpu(irq_stat, cpu).mce_exceptions; sum += per_cpu(irq_stat, cpu).spurious_irqs; +#ifdef CONFIG_PPC_DOORBELL + sum += per_cpu(irq_stat, cpu).doorbell_irqs; +#endif return sum; } diff --git a/arch/powerpc/kernel/kgdb.c b/arch/powerpc/kernel/kgdb.c index 5ca82cd..c1eef24 100644 --- a/arch/powerpc/kernel/kgdb.c +++ b/arch/powerpc/kernel/kgdb.c @@ -159,7 +159,7 @@ static int kgdb_singlestep(struct pt_regs *regs) if (user_mode(regs)) return 0; - backup_current_thread_info = (struct thread_info *)kmalloc(sizeof(struct thread_info), GFP_KERNEL); + backup_current_thread_info = kmalloc(sizeof(struct thread_info), GFP_KERNEL); /* * On Book E and perhaps other processors, singlestep is handled on * the critical exception stack. This causes current_thread_info() diff --git a/arch/powerpc/kernel/lparcfg.c b/arch/powerpc/kernel/lparcfg.c index f5725bc..ab297f4 100644 --- a/arch/powerpc/kernel/lparcfg.c +++ b/arch/powerpc/kernel/lparcfg.c @@ -301,6 +301,7 @@ static void parse_system_parameter_string(struct seq_file *m) __pa(rtas_data_buf), RTAS_DATA_BUF_SIZE); memcpy(local_buffer, rtas_data_buf, SPLPAR_MAXLENGTH); + local_buffer[SPLPAR_MAXLENGTH - 1] = '\0'; spin_unlock(&rtas_data_buf_lock); if (call_status != 0) { diff --git a/arch/powerpc/kernel/nvram_64.c b/arch/powerpc/kernel/nvram_64.c index bec1e93..48fbc2b 100644 --- a/arch/powerpc/kernel/nvram_64.c +++ b/arch/powerpc/kernel/nvram_64.c @@ -511,8 +511,7 @@ int __init nvram_scan_partitions(void) "detected: 0-length partition\n"); goto out; } - tmp_part = (struct nvram_partition *) - kmalloc(sizeof(struct nvram_partition), GFP_KERNEL); + tmp_part = kmalloc(sizeof(struct nvram_partition), GFP_KERNEL); err = -ENOMEM; if (!tmp_part) { printk(KERN_ERR "nvram_scan_partitions: kmalloc failed\n"); diff --git a/arch/powerpc/kernel/pci-common.c b/arch/powerpc/kernel/pci-common.c index fa12ae4..f325dc9 100644 --- a/arch/powerpc/kernel/pci-common.c +++ b/arch/powerpc/kernel/pci-common.c @@ -30,6 +30,7 @@ #include <linux/irq.h> #include <linux/vmalloc.h> #include <linux/slab.h> +#include <linux/vgaarb.h> #include <asm/processor.h> #include <asm/io.h> @@ -1023,6 +1024,27 @@ void pcibios_setup_bus_self(struct pci_bus *bus) ppc_md.pci_dma_bus_setup(bus); } +void pcibios_setup_device(struct pci_dev *dev) +{ + /* Fixup NUMA node as it may not be setup yet by the generic + * code and is needed by the DMA init + */ + set_dev_node(&dev->dev, pcibus_to_node(dev->bus)); + + /* Hook up default DMA ops */ + set_dma_ops(&dev->dev, pci_dma_ops); + set_dma_offset(&dev->dev, PCI_DRAM_OFFSET); + + /* Additional platform DMA/iommu setup */ + if (ppc_md.pci_dma_dev_setup) + ppc_md.pci_dma_dev_setup(dev); + + /* Read default IRQs and fixup if necessary */ + pci_read_irq_line(dev); + if (ppc_md.pci_irq_fixup) + ppc_md.pci_irq_fixup(dev); +} + void pcibios_setup_bus_devices(struct pci_bus *bus) { struct pci_dev *dev; @@ -1037,23 +1059,7 @@ void pcibios_setup_bus_devices(struct pci_bus *bus) if (dev->is_added) continue; - /* Fixup NUMA node as it may not be setup yet by the generic - * code and is needed by the DMA init - */ - set_dev_node(&dev->dev, pcibus_to_node(dev->bus)); - - /* Hook up default DMA ops */ - set_dma_ops(&dev->dev, pci_dma_ops); - set_dma_offset(&dev->dev, PCI_DRAM_OFFSET); - - /* Additional platform DMA/iommu setup */ - if (ppc_md.pci_dma_dev_setup) - ppc_md.pci_dma_dev_setup(dev); - - /* Read default IRQs and fixup if necessary */ - pci_read_irq_line(dev); - if (ppc_md.pci_irq_fixup) - ppc_md.pci_irq_fixup(dev); + pcibios_setup_device(dev); } } @@ -1494,6 +1500,10 @@ int pcibios_enable_device(struct pci_dev *dev, int mask) if (ppc_md.pcibios_enable_device_hook(dev)) return -EINVAL; + /* avoid pcie irq fix up impact on cardbus */ + if (dev->hdr_type != PCI_HEADER_TYPE_CARDBUS) + pcibios_setup_device(dev); + return pci_enable_resources(dev, mask); } @@ -1725,3 +1735,15 @@ static void fixup_hide_host_resource_fsl(struct pci_dev *dev) } DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_MOTOROLA, PCI_ANY_ID, fixup_hide_host_resource_fsl); DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_FREESCALE, PCI_ANY_ID, fixup_hide_host_resource_fsl); + +static void fixup_vga(struct pci_dev *pdev) +{ + u16 cmd; + + pci_read_config_word(pdev, PCI_COMMAND, &cmd); + if ((cmd & (PCI_COMMAND_IO | PCI_COMMAND_MEMORY)) || !vga_default_device()) + vga_set_default_device(pdev); + +} +DECLARE_PCI_FIXUP_CLASS_FINAL(PCI_ANY_ID, PCI_ANY_ID, + PCI_CLASS_DISPLAY_VGA, 8, fixup_vga); diff --git a/arch/powerpc/kernel/process.c b/arch/powerpc/kernel/process.c index 59dd545..c0dea6f 100644 --- a/arch/powerpc/kernel/process.c +++ b/arch/powerpc/kernel/process.c @@ -555,10 +555,12 @@ static inline void tm_recheckpoint_new_task(struct task_struct *new) new->thread.regs->msr |= (MSR_FP | new->thread.fpexc_mode); } +#ifdef CONFIG_ALTIVEC if (msr & MSR_VEC) { do_load_up_transact_altivec(&new->thread); new->thread.regs->msr |= MSR_VEC; } +#endif /* We may as well turn on VSX too since all the state is restored now */ if (msr & MSR_VSX) new->thread.regs->msr |= MSR_VSX; @@ -910,10 +912,6 @@ int arch_dup_task_struct(struct task_struct *dst, struct task_struct *src) flush_altivec_to_thread(src); flush_vsx_to_thread(src); flush_spe_to_thread(src); -#ifdef CONFIG_HAVE_HW_BREAKPOINT - flush_ptrace_hw_breakpoint(src); -#endif /* CONFIG_HAVE_HW_BREAKPOINT */ - *dst = *src; return 0; } @@ -984,6 +982,10 @@ int copy_thread(unsigned long clone_flags, unsigned long usp, p->thread.ksp_limit = (unsigned long)task_stack_page(p) + _ALIGN_UP(sizeof(struct thread_info), 16); +#ifdef CONFIG_HAVE_HW_BREAKPOINT + p->thread.ptrace_bps[0] = NULL; +#endif + #ifdef CONFIG_PPC_STD_MMU_64 if (mmu_has_feature(MMU_FTR_SLB)) { unsigned long sp_vsid; diff --git a/arch/powerpc/kernel/prom_init.c b/arch/powerpc/kernel/prom_init.c index 13f8d16..5eccda9 100644 --- a/arch/powerpc/kernel/prom_init.c +++ b/arch/powerpc/kernel/prom_init.c @@ -627,16 +627,11 @@ static void __init early_cmdline_parse(void) #if defined(CONFIG_PPC_PSERIES) || defined(CONFIG_PPC_POWERNV) /* - * There are two methods for telling firmware what our capabilities are. - * Newer machines have an "ibm,client-architecture-support" method on the - * root node. For older machines, we have to call the "process-elf-header" - * method in the /packages/elf-loader node, passing it a fake 32-bit - * ELF header containing a couple of PT_NOTE sections that contain - * structures that contain various information. - */ - -/* - * New method - extensible architecture description vector. + * The architecture vector has an array of PVR mask/value pairs, + * followed by # option vectors - 1, followed by the option vectors. + * + * See prom.h for the definition of the bits specified in the + * architecture vector. * * Because the description vector contains a mix of byte and word * values, we declare it as an unsigned char array, and use this @@ -645,65 +640,7 @@ static void __init early_cmdline_parse(void) #define W(x) ((x) >> 24) & 0xff, ((x) >> 16) & 0xff, \ ((x) >> 8) & 0xff, (x) & 0xff -/* Option vector bits - generic bits in byte 1 */ -#define OV_IGNORE 0x80 /* ignore this vector */ -#define OV_CESSATION_POLICY 0x40 /* halt if unsupported option present*/ - -/* Option vector 1: processor architectures supported */ -#define OV1_PPC_2_00 0x80 /* set if we support PowerPC 2.00 */ -#define OV1_PPC_2_01 0x40 /* set if we support PowerPC 2.01 */ -#define OV1_PPC_2_02 0x20 /* set if we support PowerPC 2.02 */ -#define OV1_PPC_2_03 0x10 /* set if we support PowerPC 2.03 */ -#define OV1_PPC_2_04 0x08 /* set if we support PowerPC 2.04 */ -#define OV1_PPC_2_05 0x04 /* set if we support PowerPC 2.05 */ -#define OV1_PPC_2_06 0x02 /* set if we support PowerPC 2.06 */ -#define OV1_PPC_2_07 0x01 /* set if we support PowerPC 2.07 */ - -/* Option vector 2: Open Firmware options supported */ -#define OV2_REAL_MODE 0x20 /* set if we want OF in real mode */ - -/* Option vector 3: processor options supported */ -#define OV3_FP 0x80 /* floating point */ -#define OV3_VMX 0x40 /* VMX/Altivec */ -#define OV3_DFP 0x20 /* decimal FP */ - -/* Option vector 4: IBM PAPR implementation */ -#define OV4_MIN_ENT_CAP 0x01 /* minimum VP entitled capacity */ - -/* Option vector 5: PAPR/OF options supported */ -#define OV5_LPAR 0x80 /* logical partitioning supported */ -#define OV5_SPLPAR 0x40 /* shared-processor LPAR supported */ -/* ibm,dynamic-reconfiguration-memory property supported */ -#define OV5_DRCONF_MEMORY 0x20 -#define OV5_LARGE_PAGES 0x10 /* large pages supported */ -#define OV5_DONATE_DEDICATE_CPU 0x02 /* donate dedicated CPU support */ -/* PCIe/MSI support. Without MSI full PCIe is not supported */ -#ifdef CONFIG_PCI_MSI -#define OV5_MSI 0x01 /* PCIe/MSI support */ -#else -#define OV5_MSI 0x00 -#endif /* CONFIG_PCI_MSI */ -#ifdef CONFIG_PPC_SMLPAR -#define OV5_CMO 0x80 /* Cooperative Memory Overcommitment */ -#define OV5_XCMO 0x40 /* Page Coalescing */ -#else -#define OV5_CMO 0x00 -#define OV5_XCMO 0x00 -#endif -#define OV5_TYPE1_AFFINITY 0x80 /* Type 1 NUMA affinity */ -#define OV5_PFO_HW_RNG 0x80 /* PFO Random Number Generator */ -#define OV5_PFO_HW_842 0x40 /* PFO Compression Accelerator */ -#define OV5_PFO_HW_ENCR 0x20 /* PFO Encryption Accelerator */ -#define OV5_SUB_PROCESSORS 0x01 /* 1,2,or 4 Sub-Processors supported */ - -/* Option Vector 6: IBM PAPR hints */ -#define OV6_LINUX 0x02 /* Linux is our OS */ - -/* - * The architecture vector has an array of PVR mask/value pairs, - * followed by # option vectors - 1, followed by the option vectors. - */ -static unsigned char ibm_architecture_vec[] = { +unsigned char ibm_architecture_vec[] = { W(0xfffe0000), W(0x003a0000), /* POWER5/POWER5+ */ W(0xffff0000), W(0x003e0000), /* POWER6 */ W(0xffff0000), W(0x003f0000), /* POWER7 */ @@ -747,11 +684,21 @@ static unsigned char ibm_architecture_vec[] = { /* option vector 5: PAPR/OF options */ 19 - 2, /* length */ 0, /* don't ignore, don't halt */ - OV5_LPAR | OV5_SPLPAR | OV5_LARGE_PAGES | OV5_DRCONF_MEMORY | - OV5_DONATE_DEDICATE_CPU | OV5_MSI, + OV5_FEAT(OV5_LPAR) | OV5_FEAT(OV5_SPLPAR) | OV5_FEAT(OV5_LARGE_PAGES) | + OV5_FEAT(OV5_DRCONF_MEMORY) | OV5_FEAT(OV5_DONATE_DEDICATE_CPU) | +#ifdef CONFIG_PCI_MSI + /* PCIe/MSI support. Without MSI full PCIe is not supported */ + OV5_FEAT(OV5_MSI), +#else 0, - OV5_CMO | OV5_XCMO, - OV5_TYPE1_AFFINITY, +#endif + 0, +#ifdef CONFIG_PPC_SMLPAR + OV5_FEAT(OV5_CMO) | OV5_FEAT(OV5_XCMO), +#else + 0, +#endif + OV5_FEAT(OV5_TYPE1_AFFINITY) | OV5_FEAT(OV5_PRRN), 0, 0, 0, @@ -765,8 +712,9 @@ static unsigned char ibm_architecture_vec[] = { 0, 0, 0, - OV5_PFO_HW_RNG | OV5_PFO_HW_ENCR | OV5_PFO_HW_842, - OV5_SUB_PROCESSORS, + OV5_FEAT(OV5_PFO_HW_RNG) | OV5_FEAT(OV5_PFO_HW_ENCR) | + OV5_FEAT(OV5_PFO_HW_842), + OV5_FEAT(OV5_SUB_PROCESSORS), /* option vector 6: IBM PAPR hints */ 4 - 2, /* length */ 0, diff --git a/arch/powerpc/kernel/ptrace.c b/arch/powerpc/kernel/ptrace.c index f9b30c6..3b14d32 100644 --- a/arch/powerpc/kernel/ptrace.c +++ b/arch/powerpc/kernel/ptrace.c @@ -180,9 +180,10 @@ static int set_user_msr(struct task_struct *task, unsigned long msr) } #ifdef CONFIG_PPC64 -static unsigned long get_user_dscr(struct task_struct *task) +static int get_user_dscr(struct task_struct *task, unsigned long *data) { - return task->thread.dscr; + *data = task->thread.dscr; + return 0; } static int set_user_dscr(struct task_struct *task, unsigned long dscr) @@ -192,7 +193,7 @@ static int set_user_dscr(struct task_struct *task, unsigned long dscr) return 0; } #else -static unsigned long get_user_dscr(struct task_struct *task) +static int get_user_dscr(struct task_struct *task, unsigned long *data) { return -EIO; } @@ -216,19 +217,23 @@ static int set_user_trap(struct task_struct *task, unsigned long trap) /* * Get contents of register REGNO in task TASK. */ -unsigned long ptrace_get_reg(struct task_struct *task, int regno) +int ptrace_get_reg(struct task_struct *task, int regno, unsigned long *data) { - if (task->thread.regs == NULL) + if ((task->thread.regs == NULL) || !data) return -EIO; - if (regno == PT_MSR) - return get_user_msr(task); + if (regno == PT_MSR) { + *data = get_user_msr(task); + return 0; + } if (regno == PT_DSCR) - return get_user_dscr(task); + return get_user_dscr(task, data); - if (regno < (sizeof(struct pt_regs) / sizeof(unsigned long))) - return ((unsigned long *)task->thread.regs)[regno]; + if (regno < (sizeof(struct pt_regs) / sizeof(unsigned long))) { + *data = ((unsigned long *)task->thread.regs)[regno]; + return 0; + } return -EIO; } @@ -1560,7 +1565,9 @@ long arch_ptrace(struct task_struct *child, long request, CHECK_FULL_REGS(child->thread.regs); if (index < PT_FPR0) { - tmp = ptrace_get_reg(child, (int) index); + ret = ptrace_get_reg(child, (int) index, &tmp); + if (ret) + break; } else { unsigned int fpidx = index - PT_FPR0; @@ -1637,6 +1644,8 @@ long arch_ptrace(struct task_struct *child, long request, dbginfo.sizeof_condition = 0; #ifdef CONFIG_HAVE_HW_BREAKPOINT dbginfo.features = PPC_DEBUG_FEATURE_DATA_BP_RANGE; + if (cpu_has_feature(CPU_FTR_DAWR)) + dbginfo.features |= PPC_DEBUG_FEATURE_DATA_BP_DAWR; #else dbginfo.features = 0; #endif /* CONFIG_HAVE_HW_BREAKPOINT */ diff --git a/arch/powerpc/kernel/ptrace32.c b/arch/powerpc/kernel/ptrace32.c index c0244e7..f51599e 100644 --- a/arch/powerpc/kernel/ptrace32.c +++ b/arch/powerpc/kernel/ptrace32.c @@ -95,7 +95,9 @@ long compat_arch_ptrace(struct task_struct *child, compat_long_t request, CHECK_FULL_REGS(child->thread.regs); if (index < PT_FPR0) { - tmp = ptrace_get_reg(child, index); + ret = ptrace_get_reg(child, index, &tmp); + if (ret) + break; } else { flush_fp_to_thread(child); /* @@ -148,7 +150,11 @@ long compat_arch_ptrace(struct task_struct *child, compat_long_t request, tmp = ((u64 *)child->thread.fpr) [FPRINDEX_3264(numReg)]; } else { /* register within PT_REGS struct */ - tmp = ptrace_get_reg(child, numReg); + unsigned long tmp2; + ret = ptrace_get_reg(child, numReg, &tmp2); + if (ret) + break; + tmp = tmp2; } reg32bits = ((u32*)&tmp)[part]; ret = put_user(reg32bits, (u32 __user *)data); @@ -232,7 +238,10 @@ long compat_arch_ptrace(struct task_struct *child, compat_long_t request, break; CHECK_FULL_REGS(child->thread.regs); if (numReg < PT_FPR0) { - unsigned long freg = ptrace_get_reg(child, numReg); + unsigned long freg; + ret = ptrace_get_reg(child, numReg, &freg); + if (ret) + break; if (index % 2) freg = (freg & ~0xfffffffful) | (data & 0xfffffffful); else diff --git a/arch/powerpc/kernel/rtas_flash.c b/arch/powerpc/kernel/rtas_flash.c index c642f01..a3e4034 100644 --- a/arch/powerpc/kernel/rtas_flash.c +++ b/arch/powerpc/kernel/rtas_flash.c @@ -57,13 +57,31 @@ #define VALIDATE_READY -1001 /* Firmware image ready for validation */ #define VALIDATE_PARAM_ERR -3 /* RTAS Parameter Error */ #define VALIDATE_HW_ERR -1 /* RTAS Hardware Error */ -#define VALIDATE_TMP_UPDATE 0 /* Validate Return Status */ -#define VALIDATE_FLASH_AUTH 1 /* Validate Return Status */ -#define VALIDATE_INVALID_IMG 2 /* Validate Return Status */ -#define VALIDATE_CUR_UNKNOWN 3 /* Validate Return Status */ -#define VALIDATE_TMP_COMMIT_DL 4 /* Validate Return Status */ -#define VALIDATE_TMP_COMMIT 5 /* Validate Return Status */ -#define VALIDATE_TMP_UPDATE_DL 6 /* Validate Return Status */ + +/* ibm,validate-flash-image update result tokens */ +#define VALIDATE_TMP_UPDATE 0 /* T side will be updated */ +#define VALIDATE_FLASH_AUTH 1 /* Partition does not have authority */ +#define VALIDATE_INVALID_IMG 2 /* Candidate image is not valid */ +#define VALIDATE_CUR_UNKNOWN 3 /* Current fixpack level is unknown */ +/* + * Current T side will be committed to P side before being replace with new + * image, and the new image is downlevel from current image + */ +#define VALIDATE_TMP_COMMIT_DL 4 +/* + * Current T side will be committed to P side before being replaced with new + * image + */ +#define VALIDATE_TMP_COMMIT 5 +/* + * T side will be updated with a downlevel image + */ +#define VALIDATE_TMP_UPDATE_DL 6 +/* + * The candidate image's release date is later than the system's firmware + * service entitlement date - service warranty period has expired + */ +#define VALIDATE_OUT_OF_WRNTY 7 /* ibm,manage-flash-image operation tokens */ #define RTAS_REJECT_TMP_IMG 0 @@ -790,6 +808,11 @@ static void __exit rtas_flash_cleanup(void) { rtas_flash_term_hook = NULL; + if (rtas_firmware_flash_list) { + free_flash_list(rtas_firmware_flash_list); + rtas_firmware_flash_list = NULL; + } + if (flash_block_cache) kmem_cache_destroy(flash_block_cache); diff --git a/arch/powerpc/kernel/rtas_pci.c b/arch/powerpc/kernel/rtas_pci.c index 71cb20d..6e7b7cd 100644 --- a/arch/powerpc/kernel/rtas_pci.c +++ b/arch/powerpc/kernel/rtas_pci.c @@ -201,7 +201,7 @@ static void python_countermeasures(struct device_node *dev) iounmap(chip_regs); } -void __init init_pci_config_tokens (void) +void __init init_pci_config_tokens(void) { read_pci_config = rtas_token("read-pci-config"); write_pci_config = rtas_token("write-pci-config"); @@ -209,7 +209,7 @@ void __init init_pci_config_tokens (void) ibm_write_pci_config = rtas_token("ibm,write-pci-config"); } -unsigned long get_phb_buid (struct device_node *phb) +unsigned long get_phb_buid(struct device_node *phb) { struct resource r; diff --git a/arch/powerpc/kernel/rtasd.c b/arch/powerpc/kernel/rtasd.c index 1045ff4..1130c53 100644 --- a/arch/powerpc/kernel/rtasd.c +++ b/arch/powerpc/kernel/rtasd.c @@ -29,6 +29,7 @@ #include <asm/nvram.h> #include <linux/atomic.h> #include <asm/machdep.h> +#include <asm/topology.h> static DEFINE_SPINLOCK(rtasd_log_lock); @@ -87,6 +88,8 @@ static char *rtas_event_type(int type) return "Resource Deallocation Event"; case RTAS_TYPE_DUMP: return "Dump Notification Event"; + case RTAS_TYPE_PRRN: + return "Platform Resource Reassignment Event"; } return rtas_type[0]; @@ -265,9 +268,51 @@ void pSeries_log_error(char *buf, unsigned int err_type, int fatal) spin_unlock_irqrestore(&rtasd_log_lock, s); return; } +} + +#ifdef CONFIG_PPC_PSERIES +static s32 prrn_update_scope; +static void prrn_work_fn(struct work_struct *work) +{ + /* + * For PRRN, we must pass the negative of the scope value in + * the RTAS event. + */ + pseries_devicetree_update(-prrn_update_scope); } +static DECLARE_WORK(prrn_work, prrn_work_fn); + +void prrn_schedule_update(u32 scope) +{ + flush_work(&prrn_work); + prrn_update_scope = scope; + schedule_work(&prrn_work); +} + +static void handle_rtas_event(const struct rtas_error_log *log) +{ + if (log->type == RTAS_TYPE_PRRN) { + /* For PRRN Events the extended log length is used to denote + * the scope for calling rtas update-nodes. + */ + if (prrn_is_enabled()) + prrn_schedule_update(log->extended_log_length); + } + + return; +} + +#else + +static void handle_rtas_event(const struct rtas_error_log *log) +{ + return; +} + +#endif + static int rtas_log_open(struct inode * inode, struct file * file) { return 0; @@ -388,8 +433,10 @@ static void do_event_scan(void) break; } - if (error == 0) + if (error == 0) { pSeries_log_error(logdata, ERR_TYPE_RTAS_LOG, 0); + handle_rtas_event((struct rtas_error_log *)logdata); + } } while(error == 0); } diff --git a/arch/powerpc/kernel/setup-common.c b/arch/powerpc/kernel/setup-common.c index bdc499c..63d051f 100644 --- a/arch/powerpc/kernel/setup-common.c +++ b/arch/powerpc/kernel/setup-common.c @@ -621,12 +621,6 @@ int check_legacy_ioport(unsigned long base_port) case FDC_BASE: /* FDC1 */ np = of_find_node_by_type(NULL, "fdc"); break; -#ifdef CONFIG_PPC_PREP - case _PIDXR: - case _PNPWRP: - case PNPBIOS_BASE: - /* implement me */ -#endif default: /* ipmi is supposed to fail here */ break; diff --git a/arch/powerpc/kernel/signal_32.c b/arch/powerpc/kernel/signal_32.c index 3acb28e..95068bf 100644 --- a/arch/powerpc/kernel/signal_32.c +++ b/arch/powerpc/kernel/signal_32.c @@ -866,10 +866,12 @@ static long restore_tm_user_regs(struct pt_regs *regs, do_load_up_transact_fpu(¤t->thread); regs->msr |= (MSR_FP | current->thread.fpexc_mode); } +#ifdef CONFIG_ALTIVEC if (msr & MSR_VEC) { do_load_up_transact_altivec(¤t->thread); regs->msr |= MSR_VEC; } +#endif return 0; } diff --git a/arch/powerpc/kernel/signal_64.c b/arch/powerpc/kernel/signal_64.c index 995f854..c179428 100644 --- a/arch/powerpc/kernel/signal_64.c +++ b/arch/powerpc/kernel/signal_64.c @@ -522,10 +522,12 @@ static long restore_tm_sigcontexts(struct pt_regs *regs, do_load_up_transact_fpu(¤t->thread); regs->msr |= (MSR_FP | current->thread.fpexc_mode); } +#ifdef CONFIG_ALTIVEC if (msr & MSR_VEC) { do_load_up_transact_altivec(¤t->thread); regs->msr |= MSR_VEC; } +#endif return err; } diff --git a/arch/powerpc/kernel/time.c b/arch/powerpc/kernel/time.c index f77fa22..5fc29ad 100644 --- a/arch/powerpc/kernel/time.c +++ b/arch/powerpc/kernel/time.c @@ -1049,10 +1049,8 @@ static int __init rtc_init(void) return -ENODEV; pdev = platform_device_register_simple("rtc-generic", -1, NULL, 0); - if (IS_ERR(pdev)) - return PTR_ERR(pdev); - return 0; + return PTR_RET(pdev); } module_init(rtc_init); diff --git a/arch/powerpc/kernel/tm.S b/arch/powerpc/kernel/tm.S index 84dbace..2da67e7 100644 --- a/arch/powerpc/kernel/tm.S +++ b/arch/powerpc/kernel/tm.S @@ -309,6 +309,7 @@ _GLOBAL(tm_recheckpoint) or r5, r6, r5 /* Set MSR.FP+.VSX/.VEC */ mtmsr r5 +#ifdef CONFIG_ALTIVEC /* FP and VEC registers: These are recheckpointed from thread.fpr[] * and thread.vr[] respectively. The thread.transact_fpr[] version * is more modern, and will be loaded subsequently by any FPUnavailable @@ -323,6 +324,7 @@ _GLOBAL(tm_recheckpoint) REST_32VRS(0, r5, r3) /* r5 scratch, r3 THREAD ptr */ ld r5, THREAD_VRSAVE(r3) mtspr SPRN_VRSAVE, r5 +#endif dont_restore_vec: andi. r0, r4, MSR_FP diff --git a/arch/powerpc/kernel/vdso.c b/arch/powerpc/kernel/vdso.c index 1b2076f..d4f463a 100644 --- a/arch/powerpc/kernel/vdso.c +++ b/arch/powerpc/kernel/vdso.c @@ -113,6 +113,10 @@ static struct vdso_patch_def vdso_patches[] = { CPU_FTR_USE_TB, 0, "__kernel_get_tbfreq", NULL }, + { + CPU_FTR_USE_TB, 0, + "__kernel_time", NULL + }, }; /* diff --git a/arch/powerpc/kernel/vdso32/gettimeofday.S b/arch/powerpc/kernel/vdso32/gettimeofday.S index 4ee09ee..27e2f62 100644 --- a/arch/powerpc/kernel/vdso32/gettimeofday.S +++ b/arch/powerpc/kernel/vdso32/gettimeofday.S @@ -181,6 +181,32 @@ V_FUNCTION_END(__kernel_clock_getres) /* + * Exact prototype of time() + * + * time_t time(time *t); + * + */ +V_FUNCTION_BEGIN(__kernel_time) + .cfi_startproc + mflr r12 + .cfi_register lr,r12 + + mr r11,r3 /* r11 holds t */ + bl __get_datapage@local + mr r9, r3 /* datapage ptr in r9 */ + + lwz r3,STAMP_XTIME+TSPEC_TV_SEC(r9) + + cmplwi r11,0 /* check if t is NULL */ + beq 2f + stw r3,0(r11) /* store result at *t */ +2: mtlr r12 + crclr cr0*4+so + blr + .cfi_endproc +V_FUNCTION_END(__kernel_time) + +/* * This is the core of clock_gettime() and gettimeofday(), * it returns the current time in r3 (seconds) and r4. * On entry, r7 gives the resolution of r4, either USEC_PER_SEC diff --git a/arch/powerpc/kernel/vdso32/vdso32.lds.S b/arch/powerpc/kernel/vdso32/vdso32.lds.S index 43200ba..f223409 100644 --- a/arch/powerpc/kernel/vdso32/vdso32.lds.S +++ b/arch/powerpc/kernel/vdso32/vdso32.lds.S @@ -150,6 +150,7 @@ VERSION #ifdef CONFIG_PPC64 __kernel_getcpu; #endif + __kernel_time; local: *; }; diff --git a/arch/powerpc/kernel/vdso64/gettimeofday.S b/arch/powerpc/kernel/vdso64/gettimeofday.S index e97a9a0..a76b4af 100644 --- a/arch/powerpc/kernel/vdso64/gettimeofday.S +++ b/arch/powerpc/kernel/vdso64/gettimeofday.S @@ -164,6 +164,32 @@ V_FUNCTION_BEGIN(__kernel_clock_getres) .cfi_endproc V_FUNCTION_END(__kernel_clock_getres) +/* + * Exact prototype of time() + * + * time_t time(time *t); + * + */ +V_FUNCTION_BEGIN(__kernel_time) + .cfi_startproc + mflr r12 + .cfi_register lr,r12 + + mr r11,r3 /* r11 holds t */ + bl V_LOCAL_FUNC(__get_datapage) + + ld r4,STAMP_XTIME+TSPC64_TV_SEC(r3) + + cmpldi r11,0 /* check if t is NULL */ + beq 2f + std r4,0(r11) /* store result at *t */ +2: mtlr r12 + crclr cr0*4+so + mr r3,r4 + blr + .cfi_endproc +V_FUNCTION_END(__kernel_time) + /* * This is the core of clock_gettime() and gettimeofday(), diff --git a/arch/powerpc/kernel/vdso64/vdso64.lds.S b/arch/powerpc/kernel/vdso64/vdso64.lds.S index e6c1758..e486381 100644 --- a/arch/powerpc/kernel/vdso64/vdso64.lds.S +++ b/arch/powerpc/kernel/vdso64/vdso64.lds.S @@ -147,6 +147,7 @@ VERSION __kernel_sync_dicache_p5; __kernel_sigtramp_rt64; __kernel_getcpu; + __kernel_time; local: *; }; diff --git a/arch/powerpc/kvm/book3s_hv_interrupts.S b/arch/powerpc/kvm/book3s_hv_interrupts.S index 84035a5..37f1cc4 100644 --- a/arch/powerpc/kvm/book3s_hv_interrupts.S +++ b/arch/powerpc/kvm/book3s_hv_interrupts.S @@ -122,11 +122,16 @@ END_FTR_SECTION_IFSET(CPU_FTR_ARCH_201) add r8,r8,r7 std r8,HSTATE_DECEXP(r13) +#ifdef CONFIG_SMP /* * On PPC970, if the guest vcpu has an external interrupt pending, * send ourselves an IPI so as to interrupt the guest once it * enables interrupts. (It must have interrupts disabled, * otherwise we would already have delivered the interrupt.) + * + * XXX If this is a UP build, smp_send_reschedule is not available, + * so the interrupt will be delayed until the next time the vcpu + * enters the guest with interrupts enabled. */ BEGIN_FTR_SECTION ld r0, VCPU_PENDING_EXC(r4) @@ -141,6 +146,7 @@ BEGIN_FTR_SECTION mr r4, r31 32: END_FTR_SECTION_IFSET(CPU_FTR_ARCH_201) +#endif /* CONFIG_SMP */ /* Jump to partition switch code */ bl .kvmppc_hv_entry_trampoline diff --git a/arch/powerpc/kvm/book3s_pr.c b/arch/powerpc/kvm/book3s_pr.c index 5e93438..dbdc15a 100644 --- a/arch/powerpc/kvm/book3s_pr.c +++ b/arch/powerpc/kvm/book3s_pr.c @@ -1039,7 +1039,7 @@ struct kvm_vcpu *kvmppc_core_vcpu_create(struct kvm *kvm, unsigned int id) if (!vcpu_book3s) goto out; - vcpu_book3s->shadow_vcpu = (struct kvmppc_book3s_shadow_vcpu *) + vcpu_book3s->shadow_vcpu = kzalloc(sizeof(*vcpu_book3s->shadow_vcpu), GFP_KERNEL); if (!vcpu_book3s->shadow_vcpu) goto free_vcpu; diff --git a/arch/powerpc/kvm/e500.h b/arch/powerpc/kvm/e500.h index 41cefd4..33db48a 100644 --- a/arch/powerpc/kvm/e500.h +++ b/arch/powerpc/kvm/e500.h @@ -26,17 +26,20 @@ #define E500_PID_NUM 3 #define E500_TLB_NUM 2 -#define E500_TLB_VALID 1 -#define E500_TLB_BITMAP 2 +/* entry is mapped somewhere in host TLB */ +#define E500_TLB_VALID (1 << 0) +/* TLB1 entry is mapped by host TLB1, tracked by bitmaps */ +#define E500_TLB_BITMAP (1 << 1) +/* TLB1 entry is mapped by host TLB0 */ #define E500_TLB_TLB0 (1 << 2) struct tlbe_ref { - pfn_t pfn; - unsigned int flags; /* E500_TLB_* */ + pfn_t pfn; /* valid only for TLB0, except briefly */ + unsigned int flags; /* E500_TLB_* */ }; struct tlbe_priv { - struct tlbe_ref ref; /* TLB0 only -- TLB1 uses tlb_refs */ + struct tlbe_ref ref; }; #ifdef CONFIG_KVM_E500V2 @@ -63,17 +66,6 @@ struct kvmppc_vcpu_e500 { unsigned int gtlb_nv[E500_TLB_NUM]; - /* - * information associated with each host TLB entry -- - * TLB1 only for now. If/when guest TLB1 entries can be - * mapped with host TLB0, this will be used for that too. - * - * We don't want to use this for guest TLB0 because then we'd - * have the overhead of doing the translation again even if - * the entry is still in the guest TLB (e.g. we swapped out - * and back, and our host TLB entries got evicted). - */ - struct tlbe_ref *tlb_refs[E500_TLB_NUM]; unsigned int host_tlb1_nv; u32 svr; diff --git a/arch/powerpc/kvm/e500_mmu_host.c b/arch/powerpc/kvm/e500_mmu_host.c index a222edf..1c6a9d72 100644 --- a/arch/powerpc/kvm/e500_mmu_host.c +++ b/arch/powerpc/kvm/e500_mmu_host.c @@ -193,8 +193,11 @@ void inval_gtlbe_on_host(struct kvmppc_vcpu_e500 *vcpu_e500, int tlbsel, struct tlbe_ref *ref = &vcpu_e500->gtlb_priv[tlbsel][esel].ref; /* Don't bother with unmapped entries */ - if (!(ref->flags & E500_TLB_VALID)) - return; + if (!(ref->flags & E500_TLB_VALID)) { + WARN(ref->flags & (E500_TLB_BITMAP | E500_TLB_TLB0), + "%s: flags %x\n", __func__, ref->flags); + WARN_ON(tlbsel == 1 && vcpu_e500->g2h_tlb1_map[esel]); + } if (tlbsel == 1 && ref->flags & E500_TLB_BITMAP) { u64 tmp = vcpu_e500->g2h_tlb1_map[esel]; @@ -248,7 +251,7 @@ static inline void kvmppc_e500_ref_setup(struct tlbe_ref *ref, pfn_t pfn) { ref->pfn = pfn; - ref->flags = E500_TLB_VALID; + ref->flags |= E500_TLB_VALID; if (tlbe_is_writable(gtlbe)) kvm_set_pfn_dirty(pfn); @@ -257,6 +260,7 @@ static inline void kvmppc_e500_ref_setup(struct tlbe_ref *ref, static inline void kvmppc_e500_ref_release(struct tlbe_ref *ref) { if (ref->flags & E500_TLB_VALID) { + /* FIXME: don't log bogus pfn for TLB1 */ trace_kvm_booke206_ref_release(ref->pfn, ref->flags); ref->flags = 0; } @@ -274,36 +278,23 @@ static void clear_tlb1_bitmap(struct kvmppc_vcpu_e500 *vcpu_e500) static void clear_tlb_privs(struct kvmppc_vcpu_e500 *vcpu_e500) { - int tlbsel = 0; - int i; - - for (i = 0; i < vcpu_e500->gtlb_params[tlbsel].entries; i++) { - struct tlbe_ref *ref = - &vcpu_e500->gtlb_priv[tlbsel][i].ref; - kvmppc_e500_ref_release(ref); - } -} - -static void clear_tlb_refs(struct kvmppc_vcpu_e500 *vcpu_e500) -{ - int stlbsel = 1; + int tlbsel; int i; - kvmppc_e500_tlbil_all(vcpu_e500); - - for (i = 0; i < host_tlb_params[stlbsel].entries; i++) { - struct tlbe_ref *ref = - &vcpu_e500->tlb_refs[stlbsel][i]; - kvmppc_e500_ref_release(ref); + for (tlbsel = 0; tlbsel <= 1; tlbsel++) { + for (i = 0; i < vcpu_e500->gtlb_params[tlbsel].entries; i++) { + struct tlbe_ref *ref = + &vcpu_e500->gtlb_priv[tlbsel][i].ref; + kvmppc_e500_ref_release(ref); + } } - - clear_tlb_privs(vcpu_e500); } void kvmppc_core_flush_tlb(struct kvm_vcpu *vcpu) { struct kvmppc_vcpu_e500 *vcpu_e500 = to_e500(vcpu); - clear_tlb_refs(vcpu_e500); + kvmppc_e500_tlbil_all(vcpu_e500); + clear_tlb_privs(vcpu_e500); clear_tlb1_bitmap(vcpu_e500); } @@ -458,8 +449,6 @@ static inline int kvmppc_e500_shadow_map(struct kvmppc_vcpu_e500 *vcpu_e500, gvaddr &= ~((tsize_pages << PAGE_SHIFT) - 1); } - /* Drop old ref and setup new one. */ - kvmppc_e500_ref_release(ref); kvmppc_e500_ref_setup(ref, gtlbe, pfn); kvmppc_e500_setup_stlbe(&vcpu_e500->vcpu, gtlbe, tsize, @@ -507,14 +496,15 @@ static int kvmppc_e500_tlb1_map_tlb1(struct kvmppc_vcpu_e500 *vcpu_e500, if (unlikely(vcpu_e500->host_tlb1_nv >= tlb1_max_shadow_size())) vcpu_e500->host_tlb1_nv = 0; - vcpu_e500->tlb_refs[1][sesel] = *ref; - vcpu_e500->g2h_tlb1_map[esel] |= (u64)1 << sesel; - vcpu_e500->gtlb_priv[1][esel].ref.flags |= E500_TLB_BITMAP; if (vcpu_e500->h2g_tlb1_rmap[sesel]) { - unsigned int idx = vcpu_e500->h2g_tlb1_rmap[sesel]; + unsigned int idx = vcpu_e500->h2g_tlb1_rmap[sesel] - 1; vcpu_e500->g2h_tlb1_map[idx] &= ~(1ULL << sesel); } - vcpu_e500->h2g_tlb1_rmap[sesel] = esel; + + vcpu_e500->gtlb_priv[1][esel].ref.flags |= E500_TLB_BITMAP; + vcpu_e500->g2h_tlb1_map[esel] |= (u64)1 << sesel; + vcpu_e500->h2g_tlb1_rmap[sesel] = esel + 1; + WARN_ON(!(ref->flags & E500_TLB_VALID)); return sesel; } @@ -526,13 +516,12 @@ static int kvmppc_e500_tlb1_map(struct kvmppc_vcpu_e500 *vcpu_e500, u64 gvaddr, gfn_t gfn, struct kvm_book3e_206_tlb_entry *gtlbe, struct kvm_book3e_206_tlb_entry *stlbe, int esel) { - struct tlbe_ref ref; + struct tlbe_ref *ref = &vcpu_e500->gtlb_priv[1][esel].ref; int sesel; int r; - ref.flags = 0; r = kvmppc_e500_shadow_map(vcpu_e500, gvaddr, gfn, gtlbe, 1, stlbe, - &ref); + ref); if (r) return r; @@ -544,7 +533,7 @@ static int kvmppc_e500_tlb1_map(struct kvmppc_vcpu_e500 *vcpu_e500, } /* Otherwise map into TLB1 */ - sesel = kvmppc_e500_tlb1_map_tlb1(vcpu_e500, &ref, esel); + sesel = kvmppc_e500_tlb1_map_tlb1(vcpu_e500, ref, esel); write_stlbe(vcpu_e500, gtlbe, stlbe, 1, sesel); return 0; @@ -565,7 +554,7 @@ void kvmppc_mmu_map(struct kvm_vcpu *vcpu, u64 eaddr, gpa_t gpaddr, case 0: priv = &vcpu_e500->gtlb_priv[tlbsel][esel]; - /* Triggers after clear_tlb_refs or on initial mapping */ + /* Triggers after clear_tlb_privs or on initial mapping */ if (!(priv->ref.flags & E500_TLB_VALID)) { kvmppc_e500_tlb0_map(vcpu_e500, esel, &stlbe); } else { @@ -665,35 +654,16 @@ int e500_mmu_host_init(struct kvmppc_vcpu_e500 *vcpu_e500) host_tlb_params[0].entries / host_tlb_params[0].ways; host_tlb_params[1].sets = 1; - vcpu_e500->tlb_refs[0] = - kzalloc(sizeof(struct tlbe_ref) * host_tlb_params[0].entries, - GFP_KERNEL); - if (!vcpu_e500->tlb_refs[0]) - goto err; - - vcpu_e500->tlb_refs[1] = - kzalloc(sizeof(struct tlbe_ref) * host_tlb_params[1].entries, - GFP_KERNEL); - if (!vcpu_e500->tlb_refs[1]) - goto err; - vcpu_e500->h2g_tlb1_rmap = kzalloc(sizeof(unsigned int) * host_tlb_params[1].entries, GFP_KERNEL); if (!vcpu_e500->h2g_tlb1_rmap) - goto err; + return -EINVAL; return 0; - -err: - kfree(vcpu_e500->tlb_refs[0]); - kfree(vcpu_e500->tlb_refs[1]); - return -EINVAL; } void e500_mmu_host_uninit(struct kvmppc_vcpu_e500 *vcpu_e500) { kfree(vcpu_e500->h2g_tlb1_rmap); - kfree(vcpu_e500->tlb_refs[0]); - kfree(vcpu_e500->tlb_refs[1]); } diff --git a/arch/powerpc/kvm/e500mc.c b/arch/powerpc/kvm/e500mc.c index 1f89d26..2f4baa0 100644 --- a/arch/powerpc/kvm/e500mc.c +++ b/arch/powerpc/kvm/e500mc.c @@ -108,6 +108,8 @@ void kvmppc_mmu_msr_notify(struct kvm_vcpu *vcpu, u32 old_msr) { } +static DEFINE_PER_CPU(struct kvm_vcpu *, last_vcpu_on_cpu); + void kvmppc_core_vcpu_load(struct kvm_vcpu *vcpu, int cpu) { struct kvmppc_vcpu_e500 *vcpu_e500 = to_e500(vcpu); @@ -136,8 +138,11 @@ void kvmppc_core_vcpu_load(struct kvm_vcpu *vcpu, int cpu) mtspr(SPRN_GDEAR, vcpu->arch.shared->dar); mtspr(SPRN_GESR, vcpu->arch.shared->esr); - if (vcpu->arch.oldpir != mfspr(SPRN_PIR)) + if (vcpu->arch.oldpir != mfspr(SPRN_PIR) || + __get_cpu_var(last_vcpu_on_cpu) != vcpu) { kvmppc_e500_tlbil_all(vcpu_e500); + __get_cpu_var(last_vcpu_on_cpu) = vcpu; + } kvmppc_load_guest_fp(vcpu); } diff --git a/arch/powerpc/mm/hash_utils_64.c b/arch/powerpc/mm/hash_utils_64.c index f410c3e..1ed4419 100644 --- a/arch/powerpc/mm/hash_utils_64.c +++ b/arch/powerpc/mm/hash_utils_64.c @@ -1230,24 +1230,60 @@ void low_hash_fault(struct pt_regs *regs, unsigned long address, int rc) bad_page_fault(regs, address, SIGBUS); } +long hpte_insert_repeating(unsigned long hash, unsigned long vpn, + unsigned long pa, unsigned long rflags, + unsigned long vflags, int psize, int ssize) +{ + unsigned long hpte_group; + long slot; + +repeat: + hpte_group = ((hash & htab_hash_mask) * + HPTES_PER_GROUP) & ~0x7UL; + + /* Insert into the hash table, primary slot */ + slot = ppc_md.hpte_insert(hpte_group, vpn, pa, rflags, vflags, + psize, ssize); + + /* Primary is full, try the secondary */ + if (unlikely(slot == -1)) { + hpte_group = ((~hash & htab_hash_mask) * + HPTES_PER_GROUP) & ~0x7UL; + slot = ppc_md.hpte_insert(hpte_group, vpn, pa, rflags, + vflags | HPTE_V_SECONDARY, + psize, ssize); + if (slot == -1) { + if (mftb() & 0x1) + hpte_group = ((hash & htab_hash_mask) * + HPTES_PER_GROUP)&~0x7UL; + + ppc_md.hpte_remove(hpte_group); + goto repeat; + } + } + + return slot; +} + #ifdef CONFIG_DEBUG_PAGEALLOC static void kernel_map_linear_page(unsigned long vaddr, unsigned long lmi) { - unsigned long hash, hpteg; + unsigned long hash; unsigned long vsid = get_kernel_vsid(vaddr, mmu_kernel_ssize); unsigned long vpn = hpt_vpn(vaddr, vsid, mmu_kernel_ssize); unsigned long mode = htab_convert_pte_flags(PAGE_KERNEL); - int ret; + long ret; hash = hpt_hash(vpn, PAGE_SHIFT, mmu_kernel_ssize); - hpteg = ((hash & htab_hash_mask) * HPTES_PER_GROUP); /* Don't create HPTE entries for bad address */ if (!vsid) return; - ret = ppc_md.hpte_insert(hpteg, vpn, __pa(vaddr), - mode, HPTE_V_BOLTED, - mmu_linear_psize, mmu_kernel_ssize); + + ret = hpte_insert_repeating(hash, vpn, __pa(vaddr), mode, + HPTE_V_BOLTED, + mmu_linear_psize, mmu_kernel_ssize); + BUG_ON (ret < 0); spin_lock(&linear_map_hash_lock); BUG_ON(linear_map_hash_slots[lmi] & 0x80); diff --git a/arch/powerpc/mm/hugetlbpage-hash64.c b/arch/powerpc/mm/hugetlbpage-hash64.c index cecad34..b913f41 100644 --- a/arch/powerpc/mm/hugetlbpage-hash64.c +++ b/arch/powerpc/mm/hugetlbpage-hash64.c @@ -14,6 +14,10 @@ #include <asm/cacheflush.h> #include <asm/machdep.h> +extern long hpte_insert_repeating(unsigned long hash, unsigned long vpn, + unsigned long pa, unsigned long rlags, + unsigned long vflags, int psize, int ssize); + int __hash_page_huge(unsigned long ea, unsigned long access, unsigned long vsid, pte_t *ptep, unsigned long trap, int local, int ssize, unsigned int shift, unsigned int mmu_psize) @@ -83,14 +87,9 @@ int __hash_page_huge(unsigned long ea, unsigned long access, unsigned long vsid, if (likely(!(old_pte & _PAGE_HASHPTE))) { unsigned long hash = hpt_hash(vpn, shift, ssize); - unsigned long hpte_group; pa = pte_pfn(__pte(old_pte)) << PAGE_SHIFT; -repeat: - hpte_group = ((hash & htab_hash_mask) * - HPTES_PER_GROUP) & ~0x7UL; - /* clear HPTE slot informations in new PTE */ #ifdef CONFIG_PPC_64K_PAGES new_pte = (new_pte & ~_PAGE_HPTEFLAGS) | _PAGE_HPTE_SUB0; @@ -101,26 +100,8 @@ repeat: rflags |= (new_pte & (_PAGE_WRITETHRU | _PAGE_NO_CACHE | _PAGE_COHERENT | _PAGE_GUARDED)); - /* Insert into the hash table, primary slot */ - slot = ppc_md.hpte_insert(hpte_group, vpn, pa, rflags, 0, - mmu_psize, ssize); - - /* Primary is full, try the secondary */ - if (unlikely(slot == -1)) { - hpte_group = ((~hash & htab_hash_mask) * - HPTES_PER_GROUP) & ~0x7UL; - slot = ppc_md.hpte_insert(hpte_group, vpn, pa, rflags, - HPTE_V_SECONDARY, - mmu_psize, ssize); - if (slot == -1) { - if (mftb() & 0x1) - hpte_group = ((hash & htab_hash_mask) * - HPTES_PER_GROUP)&~0x7UL; - - ppc_md.hpte_remove(hpte_group); - goto repeat; - } - } + slot = hpte_insert_repeating(hash, vpn, pa, rflags, 0, + mmu_psize, ssize); /* * Hypervisor failure. Restore old pte and return -1 diff --git a/arch/powerpc/mm/hugetlbpage.c b/arch/powerpc/mm/hugetlbpage.c index 1a6de0a..5dc52d8 100644 --- a/arch/powerpc/mm/hugetlbpage.c +++ b/arch/powerpc/mm/hugetlbpage.c @@ -742,7 +742,7 @@ unsigned long hugetlb_get_unmapped_area(struct file *file, unsigned long addr, struct hstate *hstate = hstate_file(file); int mmu_psize = shift_to_mmu_psize(huge_page_shift(hstate)); - return slice_get_unmapped_area(addr, len, flags, mmu_psize, 1, 0); + return slice_get_unmapped_area(addr, len, flags, mmu_psize, 1); } #endif diff --git a/arch/powerpc/mm/icswx.c b/arch/powerpc/mm/icswx.c index 8cdbd86..915412e 100644 --- a/arch/powerpc/mm/icswx.c +++ b/arch/powerpc/mm/icswx.c @@ -67,7 +67,7 @@ void switch_cop(struct mm_struct *next) { -#ifdef CONFIG_ICSWX_PID +#ifdef CONFIG_PPC_ICSWX_PID mtspr(SPRN_PID, next->context.cop_pid); #endif mtspr(SPRN_ACOP, next->context.acop); diff --git a/arch/powerpc/mm/mem.c b/arch/powerpc/mm/mem.c index f1f7409..056732e 100644 --- a/arch/powerpc/mm/mem.c +++ b/arch/powerpc/mm/mem.c @@ -66,10 +66,9 @@ unsigned long long memory_limit; #ifdef CONFIG_HIGHMEM pte_t *kmap_pte; +EXPORT_SYMBOL(kmap_pte); pgprot_t kmap_prot; - EXPORT_SYMBOL(kmap_prot); -EXPORT_SYMBOL(kmap_pte); static inline pte_t *virt_to_kpte(unsigned long vaddr) { diff --git a/arch/powerpc/mm/numa.c b/arch/powerpc/mm/numa.c index bba87ca..2d13f90 100644 --- a/arch/powerpc/mm/numa.c +++ b/arch/powerpc/mm/numa.c @@ -22,6 +22,10 @@ #include <linux/pfn.h> #include <linux/cpuset.h> #include <linux/node.h> +#include <linux/stop_machine.h> +#include <linux/proc_fs.h> +#include <linux/seq_file.h> +#include <linux/uaccess.h> #include <asm/sparsemem.h> #include <asm/prom.h> #include <asm/smp.h> @@ -29,6 +33,7 @@ #include <asm/paca.h> #include <asm/hvcall.h> #include <asm/setup.h> +#include <asm/vdso.h> static int numa_enabled = 1; @@ -79,7 +84,7 @@ static void __init setup_node_to_cpumask_map(void) dbg("Node to cpumask map for %d nodes\n", nr_node_ids); } -static int __cpuinit fake_numa_create_new_node(unsigned long end_pfn, +static int __init fake_numa_create_new_node(unsigned long end_pfn, unsigned int *nid) { unsigned long long mem; @@ -201,7 +206,7 @@ int __node_distance(int a, int b) int distance = LOCAL_DISTANCE; if (!form1_affinity) - return distance; + return ((a == b) ? LOCAL_DISTANCE : REMOTE_DISTANCE); for (i = 0; i < distance_ref_points_depth; i++) { if (distance_lookup_table[a][i] == distance_lookup_table[b][i]) @@ -291,9 +296,7 @@ EXPORT_SYMBOL_GPL(of_node_to_nid); static int __init find_min_common_depth(void) { int depth; - struct device_node *chosen; struct device_node *root; - const char *vec5; if (firmware_has_feature(FW_FEATURE_OPAL)) root = of_find_node_by_path("/ibm,opal"); @@ -325,24 +328,10 @@ static int __init find_min_common_depth(void) distance_ref_points_depth /= sizeof(int); -#define VEC5_AFFINITY_BYTE 5 -#define VEC5_AFFINITY 0x80 - - if (firmware_has_feature(FW_FEATURE_OPAL)) + if (firmware_has_feature(FW_FEATURE_OPAL) || + firmware_has_feature(FW_FEATURE_TYPE1_AFFINITY)) { + dbg("Using form 1 affinity\n"); form1_affinity = 1; - else { - chosen = of_find_node_by_path("/chosen"); - if (chosen) { - vec5 = of_get_property(chosen, - "ibm,architecture-vec-5", NULL); - if (vec5 && (vec5[VEC5_AFFINITY_BYTE] & - VEC5_AFFINITY)) { - dbg("Using form 1 affinity\n"); - form1_affinity = 1; - } - - of_node_put(chosen); - } } if (form1_affinity) { @@ -1270,10 +1259,18 @@ u64 memory_hotplug_max(void) /* Virtual Processor Home Node (VPHN) support */ #ifdef CONFIG_PPC_SPLPAR +struct topology_update_data { + struct topology_update_data *next; + unsigned int cpu; + int old_nid; + int new_nid; +}; + static u8 vphn_cpu_change_counts[NR_CPUS][MAX_DISTANCE_REF_POINTS]; static cpumask_t cpu_associativity_changes_mask; static int vphn_enabled; -static void set_topology_timer(void); +static int prrn_enabled; +static void reset_topology_timer(void); /* * Store the current values of the associativity change counters in the @@ -1309,11 +1306,9 @@ static void setup_cpu_associativity_change_counters(void) */ static int update_cpu_associativity_changes_mask(void) { - int cpu, nr_cpus = 0; + int cpu; cpumask_t *changes = &cpu_associativity_changes_mask; - cpumask_clear(changes); - for_each_possible_cpu(cpu) { int i, changed = 0; u8 *counts = vphn_cpu_change_counts[cpu]; @@ -1327,11 +1322,10 @@ static int update_cpu_associativity_changes_mask(void) } if (changed) { cpumask_set_cpu(cpu, changes); - nr_cpus++; } } - return nr_cpus; + return cpumask_weight(changes); } /* @@ -1423,40 +1417,84 @@ static long vphn_get_associativity(unsigned long cpu, } /* + * Update the CPU maps and sysfs entries for a single CPU when its NUMA + * characteristics change. This function doesn't perform any locking and is + * only safe to call from stop_machine(). + */ +static int update_cpu_topology(void *data) +{ + struct topology_update_data *update; + unsigned long cpu; + + if (!data) + return -EINVAL; + + cpu = get_cpu(); + + for (update = data; update; update = update->next) { + if (cpu != update->cpu) + continue; + + unregister_cpu_under_node(update->cpu, update->old_nid); + unmap_cpu_from_node(update->cpu); + map_cpu_to_node(update->cpu, update->new_nid); + vdso_getcpu_init(); + register_cpu_under_node(update->cpu, update->new_nid); + } + + return 0; +} + +/* * Update the node maps and sysfs entries for each cpu whose home node * has changed. Returns 1 when the topology has changed, and 0 otherwise. */ int arch_update_cpu_topology(void) { - int cpu, nid, old_nid, changed = 0; + unsigned int cpu, changed = 0; + struct topology_update_data *updates, *ud; unsigned int associativity[VPHN_ASSOC_BUFSIZE] = {0}; + cpumask_t updated_cpus; struct device *dev; + int weight, i = 0; + + weight = cpumask_weight(&cpu_associativity_changes_mask); + if (!weight) + return 0; + + updates = kzalloc(weight * (sizeof(*updates)), GFP_KERNEL); + if (!updates) + return 0; - for_each_cpu(cpu,&cpu_associativity_changes_mask) { + cpumask_clear(&updated_cpus); + + for_each_cpu(cpu, &cpu_associativity_changes_mask) { + ud = &updates[i++]; + ud->cpu = cpu; vphn_get_associativity(cpu, associativity); - nid = associativity_to_nid(associativity); + ud->new_nid = associativity_to_nid(associativity); - if (nid < 0 || !node_online(nid)) - nid = first_online_node; + if (ud->new_nid < 0 || !node_online(ud->new_nid)) + ud->new_nid = first_online_node; - old_nid = numa_cpu_lookup_table[cpu]; + ud->old_nid = numa_cpu_lookup_table[cpu]; + cpumask_set_cpu(cpu, &updated_cpus); - /* Disable hotplug while we update the cpu - * masks and sysfs. - */ - get_online_cpus(); - unregister_cpu_under_node(cpu, old_nid); - unmap_cpu_from_node(cpu); - map_cpu_to_node(cpu, nid); - register_cpu_under_node(cpu, nid); - put_online_cpus(); - - dev = get_cpu_device(cpu); + if (i < weight) + ud->next = &updates[i]; + } + + stop_machine(update_cpu_topology, &updates[0], &updated_cpus); + + for (ud = &updates[0]; ud; ud = ud->next) { + dev = get_cpu_device(ud->cpu); if (dev) kobject_uevent(&dev->kobj, KOBJ_CHANGE); + cpumask_clear_cpu(ud->cpu, &cpu_associativity_changes_mask); changed = 1; } + kfree(updates); return changed; } @@ -1473,49 +1511,157 @@ void topology_schedule_update(void) static void topology_timer_fn(unsigned long ignored) { - if (!vphn_enabled) - return; - if (update_cpu_associativity_changes_mask() > 0) + if (prrn_enabled && cpumask_weight(&cpu_associativity_changes_mask)) topology_schedule_update(); - set_topology_timer(); + else if (vphn_enabled) { + if (update_cpu_associativity_changes_mask() > 0) + topology_schedule_update(); + reset_topology_timer(); + } } static struct timer_list topology_timer = TIMER_INITIALIZER(topology_timer_fn, 0, 0); -static void set_topology_timer(void) +static void reset_topology_timer(void) { topology_timer.data = 0; topology_timer.expires = jiffies + 60 * HZ; - add_timer(&topology_timer); + mod_timer(&topology_timer, topology_timer.expires); +} + +static void stage_topology_update(int core_id) +{ + cpumask_or(&cpu_associativity_changes_mask, + &cpu_associativity_changes_mask, cpu_sibling_mask(core_id)); + reset_topology_timer(); +} + +static int dt_update_callback(struct notifier_block *nb, + unsigned long action, void *data) +{ + struct of_prop_reconfig *update; + int rc = NOTIFY_DONE; + + switch (action) { + case OF_RECONFIG_UPDATE_PROPERTY: + update = (struct of_prop_reconfig *)data; + if (!of_prop_cmp(update->dn->type, "cpu") && + !of_prop_cmp(update->prop->name, "ibm,associativity")) { + u32 core_id; + of_property_read_u32(update->dn, "reg", &core_id); + stage_topology_update(core_id); + rc = NOTIFY_OK; + } + break; + } + + return rc; } +static struct notifier_block dt_update_nb = { + .notifier_call = dt_update_callback, +}; + /* - * Start polling for VPHN associativity changes. + * Start polling for associativity changes. */ int start_topology_update(void) { int rc = 0; - /* Disabled until races with load balancing are fixed */ - if (0 && firmware_has_feature(FW_FEATURE_VPHN) && - get_lppaca()->shared_proc) { - vphn_enabled = 1; - setup_cpu_associativity_change_counters(); - init_timer_deferrable(&topology_timer); - set_topology_timer(); - rc = 1; + if (firmware_has_feature(FW_FEATURE_PRRN)) { + if (!prrn_enabled) { + prrn_enabled = 1; + vphn_enabled = 0; + rc = of_reconfig_notifier_register(&dt_update_nb); + } + } else if (firmware_has_feature(FW_FEATURE_VPHN) && + get_lppaca()->shared_proc) { + if (!vphn_enabled) { + prrn_enabled = 0; + vphn_enabled = 1; + setup_cpu_associativity_change_counters(); + init_timer_deferrable(&topology_timer); + reset_topology_timer(); + } } return rc; } -__initcall(start_topology_update); /* * Disable polling for VPHN associativity changes. */ int stop_topology_update(void) { - vphn_enabled = 0; - return del_timer_sync(&topology_timer); + int rc = 0; + + if (prrn_enabled) { + prrn_enabled = 0; + rc = of_reconfig_notifier_unregister(&dt_update_nb); + } else if (vphn_enabled) { + vphn_enabled = 0; + rc = del_timer_sync(&topology_timer); + } + + return rc; +} + +int prrn_is_enabled(void) +{ + return prrn_enabled; +} + +static int topology_read(struct seq_file *file, void *v) +{ + if (vphn_enabled || prrn_enabled) + seq_puts(file, "on\n"); + else + seq_puts(file, "off\n"); + + return 0; +} + +static int topology_open(struct inode *inode, struct file *file) +{ + return single_open(file, topology_read, NULL); +} + +static ssize_t topology_write(struct file *file, const char __user *buf, + size_t count, loff_t *off) +{ + char kbuf[4]; /* "on" or "off" plus null. */ + int read_len; + + read_len = count < 3 ? count : 3; + if (copy_from_user(kbuf, buf, read_len)) + return -EINVAL; + + kbuf[read_len] = '\0'; + + if (!strncmp(kbuf, "on", 2)) + start_topology_update(); + else if (!strncmp(kbuf, "off", 3)) + stop_topology_update(); + else + return -EINVAL; + + return count; +} + +static const struct file_operations topology_ops = { + .read = seq_read, + .write = topology_write, + .open = topology_open, + .release = single_release +}; + +static int topology_update_init(void) +{ + start_topology_update(); + proc_create("powerpc/topology_updates", 644, NULL, &topology_ops); + + return 0; } +device_initcall(topology_update_init); #endif /* CONFIG_PPC_SPLPAR */ diff --git a/arch/powerpc/mm/slice.c b/arch/powerpc/mm/slice.c index cf9dada..3e99c14 100644 --- a/arch/powerpc/mm/slice.c +++ b/arch/powerpc/mm/slice.c @@ -237,134 +237,112 @@ static void slice_convert(struct mm_struct *mm, struct slice_mask mask, int psiz #endif } +/* + * Compute which slice addr is part of; + * set *boundary_addr to the start or end boundary of that slice + * (depending on 'end' parameter); + * return boolean indicating if the slice is marked as available in the + * 'available' slice_mark. + */ +static bool slice_scan_available(unsigned long addr, + struct slice_mask available, + int end, + unsigned long *boundary_addr) +{ + unsigned long slice; + if (addr < SLICE_LOW_TOP) { + slice = GET_LOW_SLICE_INDEX(addr); + *boundary_addr = (slice + end) << SLICE_LOW_SHIFT; + return !!(available.low_slices & (1u << slice)); + } else { + slice = GET_HIGH_SLICE_INDEX(addr); + *boundary_addr = (slice + end) ? + ((slice + end) << SLICE_HIGH_SHIFT) : SLICE_LOW_TOP; + return !!(available.high_slices & (1u << slice)); + } +} + static unsigned long slice_find_area_bottomup(struct mm_struct *mm, unsigned long len, struct slice_mask available, - int psize, int use_cache) + int psize) { - struct vm_area_struct *vma; - unsigned long start_addr, addr; - struct slice_mask mask; int pshift = max_t(int, mmu_psize_defs[psize].shift, PAGE_SHIFT); - - if (use_cache) { - if (len <= mm->cached_hole_size) { - start_addr = addr = TASK_UNMAPPED_BASE; - mm->cached_hole_size = 0; - } else - start_addr = addr = mm->free_area_cache; - } else - start_addr = addr = TASK_UNMAPPED_BASE; - -full_search: - for (;;) { - addr = _ALIGN_UP(addr, 1ul << pshift); - if ((TASK_SIZE - len) < addr) - break; - vma = find_vma(mm, addr); - BUG_ON(vma && (addr >= vma->vm_end)); - - mask = slice_range_to_mask(addr, len); - if (!slice_check_fit(mask, available)) { - if (addr < SLICE_LOW_TOP) - addr = _ALIGN_UP(addr + 1, 1ul << SLICE_LOW_SHIFT); - else - addr = _ALIGN_UP(addr + 1, 1ul << SLICE_HIGH_SHIFT); + unsigned long addr, found, next_end; + struct vm_unmapped_area_info info; + + info.flags = 0; + info.length = len; + info.align_mask = PAGE_MASK & ((1ul << pshift) - 1); + info.align_offset = 0; + + addr = TASK_UNMAPPED_BASE; + while (addr < TASK_SIZE) { + info.low_limit = addr; + if (!slice_scan_available(addr, available, 1, &addr)) continue; + + next_slice: + /* + * At this point [info.low_limit; addr) covers + * available slices only and ends at a slice boundary. + * Check if we need to reduce the range, or if we can + * extend it to cover the next available slice. + */ + if (addr >= TASK_SIZE) + addr = TASK_SIZE; + else if (slice_scan_available(addr, available, 1, &next_end)) { + addr = next_end; + goto next_slice; } - if (!vma || addr + len <= vma->vm_start) { - /* - * Remember the place where we stopped the search: - */ - if (use_cache) - mm->free_area_cache = addr + len; - return addr; - } - if (use_cache && (addr + mm->cached_hole_size) < vma->vm_start) - mm->cached_hole_size = vma->vm_start - addr; - addr = vma->vm_end; - } + info.high_limit = addr; - /* Make sure we didn't miss any holes */ - if (use_cache && start_addr != TASK_UNMAPPED_BASE) { - start_addr = addr = TASK_UNMAPPED_BASE; - mm->cached_hole_size = 0; - goto full_search; + found = vm_unmapped_area(&info); + if (!(found & ~PAGE_MASK)) + return found; } + return -ENOMEM; } static unsigned long slice_find_area_topdown(struct mm_struct *mm, unsigned long len, struct slice_mask available, - int psize, int use_cache) + int psize) { - struct vm_area_struct *vma; - unsigned long addr; - struct slice_mask mask; int pshift = max_t(int, mmu_psize_defs[psize].shift, PAGE_SHIFT); + unsigned long addr, found, prev; + struct vm_unmapped_area_info info; - /* check if free_area_cache is useful for us */ - if (use_cache) { - if (len <= mm->cached_hole_size) { - mm->cached_hole_size = 0; - mm->free_area_cache = mm->mmap_base; - } - - /* either no address requested or can't fit in requested - * address hole - */ - addr = mm->free_area_cache; - - /* make sure it can fit in the remaining address space */ - if (addr > len) { - addr = _ALIGN_DOWN(addr - len, 1ul << pshift); - mask = slice_range_to_mask(addr, len); - if (slice_check_fit(mask, available) && - slice_area_is_free(mm, addr, len)) - /* remember the address as a hint for - * next time - */ - return (mm->free_area_cache = addr); - } - } + info.flags = VM_UNMAPPED_AREA_TOPDOWN; + info.length = len; + info.align_mask = PAGE_MASK & ((1ul << pshift) - 1); + info.align_offset = 0; addr = mm->mmap_base; - while (addr > len) { - /* Go down by chunk size */ - addr = _ALIGN_DOWN(addr - len, 1ul << pshift); - - /* Check for hit with different page size */ - mask = slice_range_to_mask(addr, len); - if (!slice_check_fit(mask, available)) { - if (addr < SLICE_LOW_TOP) - addr = _ALIGN_DOWN(addr, 1ul << SLICE_LOW_SHIFT); - else if (addr < (1ul << SLICE_HIGH_SHIFT)) - addr = SLICE_LOW_TOP; - else - addr = _ALIGN_DOWN(addr, 1ul << SLICE_HIGH_SHIFT); + while (addr > PAGE_SIZE) { + info.high_limit = addr; + if (!slice_scan_available(addr - 1, available, 0, &addr)) continue; - } + prev_slice: /* - * Lookup failure means no vma is above this address, - * else if new region fits below vma->vm_start, - * return with success: + * At this point [addr; info.high_limit) covers + * available slices only and starts at a slice boundary. + * Check if we need to reduce the range, or if we can + * extend it to cover the previous available slice. */ - vma = find_vma(mm, addr); - if (!vma || (addr + len) <= vma->vm_start) { - /* remember the address as a hint for next time */ - if (use_cache) - mm->free_area_cache = addr; - return addr; + if (addr < PAGE_SIZE) + addr = PAGE_SIZE; + else if (slice_scan_available(addr - 1, available, 0, &prev)) { + addr = prev; + goto prev_slice; } + info.low_limit = addr; - /* remember the largest hole we saw so far */ - if (use_cache && (addr + mm->cached_hole_size) < vma->vm_start) - mm->cached_hole_size = vma->vm_start - addr; - - /* try just below the current vma->vm_start */ - addr = vma->vm_start; + found = vm_unmapped_area(&info); + if (!(found & ~PAGE_MASK)) + return found; } /* @@ -373,28 +351,18 @@ static unsigned long slice_find_area_topdown(struct mm_struct *mm, * can happen with large stack limits and large mmap() * allocations. */ - addr = slice_find_area_bottomup(mm, len, available, psize, 0); - - /* - * Restore the topdown base: - */ - if (use_cache) { - mm->free_area_cache = mm->mmap_base; - mm->cached_hole_size = ~0UL; - } - - return addr; + return slice_find_area_bottomup(mm, len, available, psize); } static unsigned long slice_find_area(struct mm_struct *mm, unsigned long len, struct slice_mask mask, int psize, - int topdown, int use_cache) + int topdown) { if (topdown) - return slice_find_area_topdown(mm, len, mask, psize, use_cache); + return slice_find_area_topdown(mm, len, mask, psize); else - return slice_find_area_bottomup(mm, len, mask, psize, use_cache); + return slice_find_area_bottomup(mm, len, mask, psize); } #define or_mask(dst, src) do { \ @@ -415,7 +383,7 @@ static unsigned long slice_find_area(struct mm_struct *mm, unsigned long len, unsigned long slice_get_unmapped_area(unsigned long addr, unsigned long len, unsigned long flags, unsigned int psize, - int topdown, int use_cache) + int topdown) { struct slice_mask mask = {0, 0}; struct slice_mask good_mask; @@ -430,8 +398,8 @@ unsigned long slice_get_unmapped_area(unsigned long addr, unsigned long len, BUG_ON(mm->task_size == 0); slice_dbg("slice_get_unmapped_area(mm=%p, psize=%d...\n", mm, psize); - slice_dbg(" addr=%lx, len=%lx, flags=%lx, topdown=%d, use_cache=%d\n", - addr, len, flags, topdown, use_cache); + slice_dbg(" addr=%lx, len=%lx, flags=%lx, topdown=%d\n", + addr, len, flags, topdown); if (len > mm->task_size) return -ENOMEM; @@ -503,8 +471,7 @@ unsigned long slice_get_unmapped_area(unsigned long addr, unsigned long len, /* Now let's see if we can find something in the existing * slices for that size */ - newaddr = slice_find_area(mm, len, good_mask, psize, topdown, - use_cache); + newaddr = slice_find_area(mm, len, good_mask, psize, topdown); if (newaddr != -ENOMEM) { /* Found within the good mask, we don't have to setup, * we thus return directly @@ -536,8 +503,7 @@ unsigned long slice_get_unmapped_area(unsigned long addr, unsigned long len, * anywhere in the good area. */ if (addr) { - addr = slice_find_area(mm, len, good_mask, psize, topdown, - use_cache); + addr = slice_find_area(mm, len, good_mask, psize, topdown); if (addr != -ENOMEM) { slice_dbg(" found area at 0x%lx\n", addr); return addr; @@ -547,15 +513,14 @@ unsigned long slice_get_unmapped_area(unsigned long addr, unsigned long len, /* Now let's see if we can find something in the existing slices * for that size plus free slices */ - addr = slice_find_area(mm, len, potential_mask, psize, topdown, - use_cache); + addr = slice_find_area(mm, len, potential_mask, psize, topdown); #ifdef CONFIG_PPC_64K_PAGES if (addr == -ENOMEM && psize == MMU_PAGE_64K) { /* retry the search with 4k-page slices included */ or_mask(potential_mask, compat_mask); addr = slice_find_area(mm, len, potential_mask, psize, - topdown, use_cache); + topdown); } #endif @@ -586,8 +551,7 @@ unsigned long arch_get_unmapped_area(struct file *filp, unsigned long flags) { return slice_get_unmapped_area(addr, len, flags, - current->mm->context.user_psize, - 0, 1); + current->mm->context.user_psize, 0); } unsigned long arch_get_unmapped_area_topdown(struct file *filp, @@ -597,8 +561,7 @@ unsigned long arch_get_unmapped_area_topdown(struct file *filp, const unsigned long flags) { return slice_get_unmapped_area(addr0, len, flags, - current->mm->context.user_psize, - 1, 1); + current->mm->context.user_psize, 1); } unsigned int get_slice_psize(struct mm_struct *mm, unsigned long addr) diff --git a/arch/powerpc/perf/Makefile b/arch/powerpc/perf/Makefile index af3fac2..510fae1 100644 --- a/arch/powerpc/perf/Makefile +++ b/arch/powerpc/perf/Makefile @@ -2,9 +2,10 @@ subdir-ccflags-$(CONFIG_PPC_WERROR) := -Werror obj-$(CONFIG_PERF_EVENTS) += callchain.o -obj-$(CONFIG_PPC_PERF_CTRS) += core-book3s.o +obj-$(CONFIG_PPC_PERF_CTRS) += core-book3s.o bhrb.o obj64-$(CONFIG_PPC_PERF_CTRS) += power4-pmu.o ppc970-pmu.o power5-pmu.o \ - power5+-pmu.o power6-pmu.o power7-pmu.o + power5+-pmu.o power6-pmu.o power7-pmu.o \ + power8-pmu.o obj32-$(CONFIG_PPC_PERF_CTRS) += mpc7450-pmu.o obj-$(CONFIG_FSL_EMB_PERF_EVENT) += core-fsl-emb.o diff --git a/arch/powerpc/perf/bhrb.S b/arch/powerpc/perf/bhrb.S new file mode 100644 index 0000000..d85f9a5 --- /dev/null +++ b/arch/powerpc/perf/bhrb.S @@ -0,0 +1,44 @@ +/* + * Basic assembly code to read BHRB entries + * + * Copyright 2013 Anshuman Khandual, IBM 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; either version + * 2 of the License, or (at your option) any later version. + */ +#include <asm/ppc_asm.h> +#include <asm/ppc-opcode.h> + + .text + +.balign 8 + +/* r3 = n (where n = [0-31]) + * The maximum number of BHRB entries supported with PPC_MFBHRBE instruction + * is 1024. We have limited number of table entries here as POWER8 implements + * 32 BHRB entries. + */ + +/* .global read_bhrb */ +_GLOBAL(read_bhrb) + cmpldi r3,31 + bgt 1f + ld r4,bhrb_table@got(r2) + sldi r3,r3,3 + add r3,r4,r3 + mtctr r3 + bctr +1: li r3,0 + blr + +#define MFBHRB_TABLE1(n) PPC_MFBHRBE(R3,n); blr +#define MFBHRB_TABLE2(n) MFBHRB_TABLE1(n); MFBHRB_TABLE1(n+1) +#define MFBHRB_TABLE4(n) MFBHRB_TABLE2(n); MFBHRB_TABLE2(n+2) +#define MFBHRB_TABLE8(n) MFBHRB_TABLE4(n); MFBHRB_TABLE4(n+4) +#define MFBHRB_TABLE16(n) MFBHRB_TABLE8(n); MFBHRB_TABLE8(n+8) +#define MFBHRB_TABLE32(n) MFBHRB_TABLE16(n); MFBHRB_TABLE16(n+16) + +bhrb_table: + MFBHRB_TABLE32(0) diff --git a/arch/powerpc/perf/core-book3s.c b/arch/powerpc/perf/core-book3s.c index 65362e9..c627843 100644 --- a/arch/powerpc/perf/core-book3s.c +++ b/arch/powerpc/perf/core-book3s.c @@ -19,6 +19,11 @@ #include <asm/firmware.h> #include <asm/ptrace.h> +#define BHRB_MAX_ENTRIES 32 +#define BHRB_TARGET 0x0000000000000002 +#define BHRB_PREDICTION 0x0000000000000001 +#define BHRB_EA 0xFFFFFFFFFFFFFFFC + struct cpu_hw_events { int n_events; int n_percpu; @@ -38,7 +43,15 @@ struct cpu_hw_events { unsigned int group_flag; int n_txn_start; + + /* BHRB bits */ + u64 bhrb_filter; /* BHRB HW branch filter */ + int bhrb_users; + void *bhrb_context; + struct perf_branch_stack bhrb_stack; + struct perf_branch_entry bhrb_entries[BHRB_MAX_ENTRIES]; }; + DEFINE_PER_CPU(struct cpu_hw_events, cpu_hw_events); struct power_pmu *ppmu; @@ -89,6 +102,11 @@ static inline int siar_valid(struct pt_regs *regs) #endif /* CONFIG_PPC32 */ +static bool regs_use_siar(struct pt_regs *regs) +{ + return !!(regs->result & 1); +} + /* * Things that are specific to 64-bit implementations. */ @@ -98,11 +116,12 @@ static inline unsigned long perf_ip_adjust(struct pt_regs *regs) { unsigned long mmcra = regs->dsisr; - if ((mmcra & MMCRA_SAMPLE_ENABLE) && !(ppmu->flags & PPMU_ALT_SIPR)) { + if ((ppmu->flags & PPMU_HAS_SSLOT) && (mmcra & MMCRA_SAMPLE_ENABLE)) { unsigned long slot = (mmcra & MMCRA_SLOT) >> MMCRA_SLOT_SHIFT; if (slot > 1) return 4 * (slot - 1); } + return 0; } @@ -130,24 +149,35 @@ static inline void perf_get_data_addr(struct pt_regs *regs, u64 *addrp) *addrp = mfspr(SPRN_SDAR); } -static bool mmcra_sihv(unsigned long mmcra) +static bool regs_sihv(struct pt_regs *regs) { unsigned long sihv = MMCRA_SIHV; + if (ppmu->flags & PPMU_HAS_SIER) + return !!(regs->dar & SIER_SIHV); + if (ppmu->flags & PPMU_ALT_SIPR) sihv = POWER6_MMCRA_SIHV; - return !!(mmcra & sihv); + return !!(regs->dsisr & sihv); } -static bool mmcra_sipr(unsigned long mmcra) +static bool regs_sipr(struct pt_regs *regs) { unsigned long sipr = MMCRA_SIPR; + if (ppmu->flags & PPMU_HAS_SIER) + return !!(regs->dar & SIER_SIPR); + if (ppmu->flags & PPMU_ALT_SIPR) sipr = POWER6_MMCRA_SIPR; - return !!(mmcra & sipr); + return !!(regs->dsisr & sipr); +} + +static bool regs_no_sipr(struct pt_regs *regs) +{ + return !!(regs->result & 2); } static inline u32 perf_flags_from_msr(struct pt_regs *regs) @@ -161,8 +191,7 @@ static inline u32 perf_flags_from_msr(struct pt_regs *regs) static inline u32 perf_get_misc_flags(struct pt_regs *regs) { - unsigned long mmcra = regs->dsisr; - unsigned long use_siar = regs->result; + bool use_siar = regs_use_siar(regs); if (!use_siar) return perf_flags_from_msr(regs); @@ -173,7 +202,7 @@ static inline u32 perf_get_misc_flags(struct pt_regs *regs) * SIAR which should give slightly more reliable * results */ - if (ppmu->flags & PPMU_NO_SIPR) { + if (regs_no_sipr(regs)) { unsigned long siar = mfspr(SPRN_SIAR); if (siar >= PAGE_OFFSET) return PERF_RECORD_MISC_KERNEL; @@ -181,16 +210,19 @@ static inline u32 perf_get_misc_flags(struct pt_regs *regs) } /* PR has priority over HV, so order below is important */ - if (mmcra_sipr(mmcra)) + if (regs_sipr(regs)) return PERF_RECORD_MISC_USER; - if (mmcra_sihv(mmcra) && (freeze_events_kernel != MMCR0_FCHV)) + + if (regs_sihv(regs) && (freeze_events_kernel != MMCR0_FCHV)) return PERF_RECORD_MISC_HYPERVISOR; + return PERF_RECORD_MISC_KERNEL; } /* * Overload regs->dsisr to store MMCRA so we only need to read it once * on each interrupt. + * Overload regs->dar to store SIER if we have it. * Overload regs->result to specify whether we should use the MSR (result * is zero) or the SIAR (result is non zero). */ @@ -200,6 +232,24 @@ static inline void perf_read_regs(struct pt_regs *regs) int marked = mmcra & MMCRA_SAMPLE_ENABLE; int use_siar; + regs->dsisr = mmcra; + regs->result = 0; + + if (ppmu->flags & PPMU_NO_SIPR) + regs->result |= 2; + + /* + * On power8 if we're in random sampling mode, the SIER is updated. + * If we're in continuous sampling mode, we don't have SIPR. + */ + if (ppmu->flags & PPMU_HAS_SIER) { + if (marked) + regs->dar = mfspr(SPRN_SIER); + else + regs->result |= 2; + } + + /* * If this isn't a PMU exception (eg a software event) the SIAR is * not valid. Use pt_regs. @@ -223,13 +273,12 @@ static inline void perf_read_regs(struct pt_regs *regs) use_siar = 1; else if ((ppmu->flags & PPMU_NO_CONT_SAMPLING)) use_siar = 0; - else if (!(ppmu->flags & PPMU_NO_SIPR) && mmcra_sipr(mmcra)) + else if (!regs_no_sipr(regs) && regs_sipr(regs)) use_siar = 0; else use_siar = 1; - regs->dsisr = mmcra; - regs->result = use_siar; + regs->result |= use_siar; } /* @@ -822,6 +871,9 @@ static void power_pmu_enable(struct pmu *pmu) } out: + if (cpuhw->bhrb_users) + ppmu->config_bhrb(cpuhw->bhrb_filter); + local_irq_restore(flags); } @@ -852,6 +904,47 @@ static int collect_events(struct perf_event *group, int max_count, return n; } +/* Reset all possible BHRB entries */ +static void power_pmu_bhrb_reset(void) +{ + asm volatile(PPC_CLRBHRB); +} + +void power_pmu_bhrb_enable(struct perf_event *event) +{ + struct cpu_hw_events *cpuhw = &__get_cpu_var(cpu_hw_events); + + if (!ppmu->bhrb_nr) + return; + + /* Clear BHRB if we changed task context to avoid data leaks */ + if (event->ctx->task && cpuhw->bhrb_context != event->ctx) { + power_pmu_bhrb_reset(); + cpuhw->bhrb_context = event->ctx; + } + cpuhw->bhrb_users++; +} + +void power_pmu_bhrb_disable(struct perf_event *event) +{ + struct cpu_hw_events *cpuhw = &__get_cpu_var(cpu_hw_events); + + if (!ppmu->bhrb_nr) + return; + + cpuhw->bhrb_users--; + WARN_ON_ONCE(cpuhw->bhrb_users < 0); + + if (!cpuhw->disabled && !cpuhw->bhrb_users) { + /* BHRB cannot be turned off when other + * events are active on the PMU. + */ + + /* avoid stale pointer */ + cpuhw->bhrb_context = NULL; + } +} + /* * Add a event to the PMU. * If all events are not already frozen, then we disable and @@ -911,6 +1004,9 @@ nocheck: ret = 0; out: + if (has_branch_stack(event)) + power_pmu_bhrb_enable(event); + perf_pmu_enable(event->pmu); local_irq_restore(flags); return ret; @@ -963,6 +1059,9 @@ static void power_pmu_del(struct perf_event *event, int ef_flags) cpuhw->mmcr[0] &= ~(MMCR0_PMXE | MMCR0_FCECE); } + if (has_branch_stack(event)) + power_pmu_bhrb_disable(event); + perf_pmu_enable(event->pmu); local_irq_restore(flags); } @@ -1081,6 +1180,15 @@ int power_pmu_commit_txn(struct pmu *pmu) return 0; } +/* Called from ctxsw to prevent one process's branch entries to + * mingle with the other process's entries during context switch. + */ +void power_pmu_flush_branch_stack(void) +{ + if (ppmu->bhrb_nr) + power_pmu_bhrb_reset(); +} + /* * Return 1 if we might be able to put event on a limited PMC, * or 0 if not. @@ -1195,9 +1303,11 @@ static int power_pmu_event_init(struct perf_event *event) if (!ppmu) return -ENOENT; - /* does not support taken branch sampling */ - if (has_branch_stack(event)) - return -EOPNOTSUPP; + if (has_branch_stack(event)) { + /* PMU has BHRB enabled */ + if (!(ppmu->flags & PPMU_BHRB)) + return -EOPNOTSUPP; + } switch (event->attr.type) { case PERF_TYPE_HARDWARE: @@ -1278,6 +1388,15 @@ static int power_pmu_event_init(struct perf_event *event) cpuhw = &get_cpu_var(cpu_hw_events); err = power_check_constraints(cpuhw, events, cflags, n + 1); + + if (has_branch_stack(event)) { + cpuhw->bhrb_filter = ppmu->bhrb_filter_map( + event->attr.branch_sample_type); + + if(cpuhw->bhrb_filter == -1) + return -EOPNOTSUPP; + } + put_cpu_var(cpu_hw_events); if (err) return -EINVAL; @@ -1336,8 +1455,79 @@ struct pmu power_pmu = { .cancel_txn = power_pmu_cancel_txn, .commit_txn = power_pmu_commit_txn, .event_idx = power_pmu_event_idx, + .flush_branch_stack = power_pmu_flush_branch_stack, }; +/* Processing BHRB entries */ +void power_pmu_bhrb_read(struct cpu_hw_events *cpuhw) +{ + u64 val; + u64 addr; + int r_index, u_index, target, pred; + + r_index = 0; + u_index = 0; + while (r_index < ppmu->bhrb_nr) { + /* Assembly read function */ + val = read_bhrb(r_index); + + /* Terminal marker: End of valid BHRB entries */ + if (val == 0) { + break; + } else { + /* BHRB field break up */ + addr = val & BHRB_EA; + pred = val & BHRB_PREDICTION; + target = val & BHRB_TARGET; + + /* Probable Missed entry: Not applicable for POWER8 */ + if ((addr == 0) && (target == 0) && (pred == 1)) { + r_index++; + continue; + } + + /* Real Missed entry: Power8 based missed entry */ + if ((addr == 0) && (target == 1) && (pred == 1)) { + r_index++; + continue; + } + + /* Reserved condition: Not a valid entry */ + if ((addr == 0) && (target == 1) && (pred == 0)) { + r_index++; + continue; + } + + /* Is a target address */ + if (val & BHRB_TARGET) { + /* First address cannot be a target address */ + if (r_index == 0) { + r_index++; + continue; + } + + /* Update target address for the previous entry */ + cpuhw->bhrb_entries[u_index - 1].to = addr; + cpuhw->bhrb_entries[u_index - 1].mispred = pred; + cpuhw->bhrb_entries[u_index - 1].predicted = ~pred; + + /* Dont increment u_index */ + r_index++; + } else { + /* Update address, flags for current entry */ + cpuhw->bhrb_entries[u_index].from = addr; + cpuhw->bhrb_entries[u_index].mispred = pred; + cpuhw->bhrb_entries[u_index].predicted = ~pred; + + /* Successfully popullated one entry */ + u_index++; + r_index++; + } + } + } + cpuhw->bhrb_stack.nr = u_index; + return; +} /* * A counter has overflowed; update its count and record @@ -1397,6 +1587,13 @@ static void record_and_restart(struct perf_event *event, unsigned long val, if (event->attr.sample_type & PERF_SAMPLE_ADDR) perf_get_data_addr(regs, &data.addr); + if (event->attr.sample_type & PERF_SAMPLE_BRANCH_STACK) { + struct cpu_hw_events *cpuhw; + cpuhw = &__get_cpu_var(cpu_hw_events); + power_pmu_bhrb_read(cpuhw); + data.br_stack = &cpuhw->bhrb_stack; + } + if (perf_event_overflow(event, &data, regs)) power_pmu_stop(event, 0); } @@ -1422,7 +1619,7 @@ unsigned long perf_misc_flags(struct pt_regs *regs) */ unsigned long perf_instruction_pointer(struct pt_regs *regs) { - unsigned long use_siar = regs->result; + bool use_siar = regs_use_siar(regs); if (use_siar && siar_valid(regs)) return mfspr(SPRN_SIAR) + perf_ip_adjust(regs); diff --git a/arch/powerpc/perf/power5+-pmu.c b/arch/powerpc/perf/power5+-pmu.c index a8757ba..b03b6dc 100644 --- a/arch/powerpc/perf/power5+-pmu.c +++ b/arch/powerpc/perf/power5+-pmu.c @@ -671,7 +671,7 @@ static struct power_pmu power5p_pmu = { .get_alternatives = power5p_get_alternatives, .disable_pmc = power5p_disable_pmc, .limited_pmc_event = power5p_limited_pmc_event, - .flags = PPMU_LIMITED_PMC5_6, + .flags = PPMU_LIMITED_PMC5_6 | PPMU_HAS_SSLOT, .n_generic = ARRAY_SIZE(power5p_generic_events), .generic_events = power5p_generic_events, .cache_events = &power5p_cache_events, diff --git a/arch/powerpc/perf/power5-pmu.c b/arch/powerpc/perf/power5-pmu.c index e7f06eb..1e8ce42 100644 --- a/arch/powerpc/perf/power5-pmu.c +++ b/arch/powerpc/perf/power5-pmu.c @@ -615,6 +615,7 @@ static struct power_pmu power5_pmu = { .n_generic = ARRAY_SIZE(power5_generic_events), .generic_events = power5_generic_events, .cache_events = &power5_cache_events, + .flags = PPMU_HAS_SSLOT, }; static int __init init_power5_pmu(void) diff --git a/arch/powerpc/perf/power8-pmu.c b/arch/powerpc/perf/power8-pmu.c new file mode 100644 index 0000000..f7d1c4f --- /dev/null +++ b/arch/powerpc/perf/power8-pmu.c @@ -0,0 +1,592 @@ +/* + * Performance counter support for POWER8 processors. + * + * Copyright 2009 Paul Mackerras, IBM Corporation. + * Copyright 2013 Michael Ellerman, IBM 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; either version + * 2 of the License, or (at your option) any later version. + */ + +#include <linux/kernel.h> +#include <linux/perf_event.h> +#include <asm/firmware.h> + + +/* + * Some power8 event codes. + */ +#define PM_CYC 0x0001e +#define PM_GCT_NOSLOT_CYC 0x100f8 +#define PM_CMPLU_STALL 0x4000a +#define PM_INST_CMPL 0x00002 +#define PM_BRU_FIN 0x10068 +#define PM_BR_MPRED_CMPL 0x400f6 + + +/* + * Raw event encoding for POWER8: + * + * 60 56 52 48 44 40 36 32 + * | - - - - | - - - - | - - - - | - - - - | - - - - | - - - - | - - - - | - - - - | + * [ thresh_cmp ] [ thresh_ctl ] + * | + * thresh start/stop OR FAB match -* + * + * 28 24 20 16 12 8 4 0 + * | - - - - | - - - - | - - - - | - - - - | - - - - | - - - - | - - - - | - - - - | + * [ ] [ sample ] [cache] [ pmc ] [unit ] c m [ pmcxsel ] + * | | | | | + * | | | | *- mark + * | | *- L1/L2/L3 cache_sel | + * | | | + * | *- sampling mode for marked events *- combine + * | + * *- thresh_sel + * + * Below uses IBM bit numbering. + * + * MMCR1[x:y] = unit (PMCxUNIT) + * MMCR1[x] = combine (PMCxCOMB) + * + * if pmc == 3 and unit == 0 and pmcxsel[0:6] == 0b0101011 + * # PM_MRK_FAB_RSP_MATCH + * MMCR1[20:27] = thresh_ctl (FAB_CRESP_MATCH / FAB_TYPE_MATCH) + * else if pmc == 4 and unit == 0xf and pmcxsel[0:6] == 0b0101001 + * # PM_MRK_FAB_RSP_MATCH_CYC + * MMCR1[20:27] = thresh_ctl (FAB_CRESP_MATCH / FAB_TYPE_MATCH) + * else + * MMCRA[48:55] = thresh_ctl (THRESH START/END) + * + * if thresh_sel: + * MMCRA[45:47] = thresh_sel + * + * if thresh_cmp: + * MMCRA[22:24] = thresh_cmp[0:2] + * MMCRA[25:31] = thresh_cmp[3:9] + * + * if unit == 6 or unit == 7 + * MMCRC[53:55] = cache_sel[1:3] (L2EVENT_SEL) + * else if unit == 8 or unit == 9: + * if cache_sel[0] == 0: # L3 bank + * MMCRC[47:49] = cache_sel[1:3] (L3EVENT_SEL0) + * else if cache_sel[0] == 1: + * MMCRC[50:51] = cache_sel[2:3] (L3EVENT_SEL1) + * else if cache_sel[1]: # L1 event + * MMCR1[16] = cache_sel[2] +Â * MMCR1[17] = cache_sel[3] + * + * if mark: + * MMCRA[63] = 1 (SAMPLE_ENABLE) + * MMCRA[57:59] = sample[0:2] (RAND_SAMP_ELIG) +Â * MMCRA[61:62] = sample[3:4] (RAND_SAMP_MODE) + * + */ + +#define EVENT_THR_CMP_SHIFT 40 /* Threshold CMP value */ +#define EVENT_THR_CMP_MASK 0x3ff +#define EVENT_THR_CTL_SHIFT 32 /* Threshold control value (start/stop) */ +#define EVENT_THR_CTL_MASK 0xffull +#define EVENT_THR_SEL_SHIFT 29 /* Threshold select value */ +#define EVENT_THR_SEL_MASK 0x7 +#define EVENT_THRESH_SHIFT 29 /* All threshold bits */ +#define EVENT_THRESH_MASK 0x1fffffull +#define EVENT_SAMPLE_SHIFT 24 /* Sampling mode & eligibility */ +#define EVENT_SAMPLE_MASK 0x1f +#define EVENT_CACHE_SEL_SHIFT 20 /* L2/L3 cache select */ +#define EVENT_CACHE_SEL_MASK 0xf +#define EVENT_IS_L1 (4 << EVENT_CACHE_SEL_SHIFT) +#define EVENT_PMC_SHIFT 16 /* PMC number (1-based) */ +#define EVENT_PMC_MASK 0xf +#define EVENT_UNIT_SHIFT 12 /* Unit */ +#define EVENT_UNIT_MASK 0xf +#define EVENT_COMBINE_SHIFT 11 /* Combine bit */ +#define EVENT_COMBINE_MASK 0x1 +#define EVENT_MARKED_SHIFT 8 /* Marked bit */ +#define EVENT_MARKED_MASK 0x1 +#define EVENT_IS_MARKED (EVENT_MARKED_MASK << EVENT_MARKED_SHIFT) +#define EVENT_PSEL_MASK 0xff /* PMCxSEL value */ + +/* MMCRA IFM bits - POWER8 */ +#define POWER8_MMCRA_IFM1 0x0000000040000000UL +#define POWER8_MMCRA_IFM2 0x0000000080000000UL +#define POWER8_MMCRA_IFM3 0x00000000C0000000UL + +#define ONLY_PLM \ + (PERF_SAMPLE_BRANCH_USER |\ + PERF_SAMPLE_BRANCH_KERNEL |\ + PERF_SAMPLE_BRANCH_HV) + +/* + * Layout of constraint bits: + * + * 60 56 52 48 44 40 36 32 + * | - - - - | - - - - | - - - - | - - - - | - - - - | - - - - | - - - - | - - - - | + * [ fab_match ] [ thresh_cmp ] [ thresh_ctl ] [ ] + * | + * thresh_sel -* + * + * 28 24 20 16 12 8 4 0 + * | - - - - | - - - - | - - - - | - - - - | - - - - | - - - - | - - - - | - - - - | + * [ ] [ sample ] [ ] [6] [5] [4] [3] [2] [1] + * | | + * L1 I/D qualifier -* | Count of events for each PMC. + * | p1, p2, p3, p4, p5, p6. + * nc - number of counters -* + * + * The PMC fields P1..P6, and NC, are adder fields. As we accumulate constraints + * we want the low bit of each field to be added to any existing value. + * + * Everything else is a value field. + */ + +#define CNST_FAB_MATCH_VAL(v) (((v) & EVENT_THR_CTL_MASK) << 56) +#define CNST_FAB_MATCH_MASK CNST_FAB_MATCH_VAL(EVENT_THR_CTL_MASK) + +/* We just throw all the threshold bits into the constraint */ +#define CNST_THRESH_VAL(v) (((v) & EVENT_THRESH_MASK) << 32) +#define CNST_THRESH_MASK CNST_THRESH_VAL(EVENT_THRESH_MASK) + +#define CNST_L1_QUAL_VAL(v) (((v) & 3) << 22) +#define CNST_L1_QUAL_MASK CNST_L1_QUAL_VAL(3) + +#define CNST_SAMPLE_VAL(v) (((v) & EVENT_SAMPLE_MASK) << 16) +#define CNST_SAMPLE_MASK CNST_SAMPLE_VAL(EVENT_SAMPLE_MASK) + +/* + * For NC we are counting up to 4 events. This requires three bits, and we need + * the fifth event to overflow and set the 4th bit. To achieve that we bias the + * fields by 3 in test_adder. + */ +#define CNST_NC_SHIFT 12 +#define CNST_NC_VAL (1 << CNST_NC_SHIFT) +#define CNST_NC_MASK (8 << CNST_NC_SHIFT) +#define POWER8_TEST_ADDER (3 << CNST_NC_SHIFT) + +/* + * For the per-PMC fields we have two bits. The low bit is added, so if two + * events ask for the same PMC the sum will overflow, setting the high bit, + * indicating an error. So our mask sets the high bit. + */ +#define CNST_PMC_SHIFT(pmc) ((pmc - 1) * 2) +#define CNST_PMC_VAL(pmc) (1 << CNST_PMC_SHIFT(pmc)) +#define CNST_PMC_MASK(pmc) (2 << CNST_PMC_SHIFT(pmc)) + +/* Our add_fields is defined as: */ +#define POWER8_ADD_FIELDS \ + CNST_PMC_VAL(1) | CNST_PMC_VAL(2) | CNST_PMC_VAL(3) | \ + CNST_PMC_VAL(4) | CNST_PMC_VAL(5) | CNST_PMC_VAL(6) | CNST_NC_VAL + + +/* Bits in MMCR1 for POWER8 */ +#define MMCR1_UNIT_SHIFT(pmc) (60 - (4 * ((pmc) - 1))) +#define MMCR1_COMBINE_SHIFT(pmc) (35 - ((pmc) - 1)) +#define MMCR1_PMCSEL_SHIFT(pmc) (24 - (((pmc) - 1)) * 8) +#define MMCR1_DC_QUAL_SHIFT 47 +#define MMCR1_IC_QUAL_SHIFT 46 + +/* Bits in MMCRA for POWER8 */ +#define MMCRA_SAMP_MODE_SHIFT 1 +#define MMCRA_SAMP_ELIG_SHIFT 4 +#define MMCRA_THR_CTL_SHIFT 8 +#define MMCRA_THR_SEL_SHIFT 16 +#define MMCRA_THR_CMP_SHIFT 32 +#define MMCRA_SDAR_MODE_TLB (1ull << 42) + + +static inline bool event_is_fab_match(u64 event) +{ + /* Only check pmc, unit and pmcxsel, ignore the edge bit (0) */ + event &= 0xff0fe; + + /* PM_MRK_FAB_RSP_MATCH & PM_MRK_FAB_RSP_MATCH_CYC */ + return (event == 0x30056 || event == 0x4f052); +} + +static int power8_get_constraint(u64 event, unsigned long *maskp, unsigned long *valp) +{ + unsigned int unit, pmc, cache; + unsigned long mask, value; + + mask = value = 0; + + pmc = (event >> EVENT_PMC_SHIFT) & EVENT_PMC_MASK; + unit = (event >> EVENT_UNIT_SHIFT) & EVENT_UNIT_MASK; + cache = (event >> EVENT_CACHE_SEL_SHIFT) & EVENT_CACHE_SEL_MASK; + + if (pmc) { + if (pmc > 6) + return -1; + + mask |= CNST_PMC_MASK(pmc); + value |= CNST_PMC_VAL(pmc); + + if (pmc >= 5 && event != 0x500fa && event != 0x600f4) + return -1; + } + + if (pmc <= 4) { + /* + * Add to number of counters in use. Note this includes events with + * a PMC of 0 - they still need a PMC, it's just assigned later. + * Don't count events on PMC 5 & 6, there is only one valid event + * on each of those counters, and they are handled above. + */ + mask |= CNST_NC_MASK; + value |= CNST_NC_VAL; + } + + if (unit >= 6 && unit <= 9) { + /* + * L2/L3 events contain a cache selector field, which is + * supposed to be programmed into MMCRC. However MMCRC is only + * HV writable, and there is no API for guest kernels to modify + * it. The solution is for the hypervisor to initialise the + * field to zeroes, and for us to only ever allow events that + * have a cache selector of zero. + */ + if (cache) + return -1; + + } else if (event & EVENT_IS_L1) { + mask |= CNST_L1_QUAL_MASK; + value |= CNST_L1_QUAL_VAL(cache); + } + + if (event & EVENT_IS_MARKED) { + mask |= CNST_SAMPLE_MASK; + value |= CNST_SAMPLE_VAL(event >> EVENT_SAMPLE_SHIFT); + } + + /* + * Special case for PM_MRK_FAB_RSP_MATCH and PM_MRK_FAB_RSP_MATCH_CYC, + * the threshold control bits are used for the match value. + */ + if (event_is_fab_match(event)) { + mask |= CNST_FAB_MATCH_MASK; + value |= CNST_FAB_MATCH_VAL(event >> EVENT_THR_CTL_SHIFT); + } else { + /* + * Check the mantissa upper two bits are not zero, unless the + * exponent is also zero. See the THRESH_CMP_MANTISSA doc. + */ + unsigned int cmp, exp; + + cmp = (event >> EVENT_THR_CMP_SHIFT) & EVENT_THR_CMP_MASK; + exp = cmp >> 7; + + if (exp && (cmp & 0x60) == 0) + return -1; + + mask |= CNST_THRESH_MASK; + value |= CNST_THRESH_VAL(event >> EVENT_THRESH_SHIFT); + } + + *maskp = mask; + *valp = value; + + return 0; +} + +static int power8_compute_mmcr(u64 event[], int n_ev, + unsigned int hwc[], unsigned long mmcr[]) +{ + unsigned long mmcra, mmcr1, unit, combine, psel, cache, val; + unsigned int pmc, pmc_inuse; + int i; + + pmc_inuse = 0; + + /* First pass to count resource use */ + for (i = 0; i < n_ev; ++i) { + pmc = (event[i] >> EVENT_PMC_SHIFT) & EVENT_PMC_MASK; + if (pmc) + pmc_inuse |= 1 << pmc; + } + + /* In continous sampling mode, update SDAR on TLB miss */ + mmcra = MMCRA_SDAR_MODE_TLB; + mmcr1 = 0; + + /* Second pass: assign PMCs, set all MMCR1 fields */ + for (i = 0; i < n_ev; ++i) { + pmc = (event[i] >> EVENT_PMC_SHIFT) & EVENT_PMC_MASK; + unit = (event[i] >> EVENT_UNIT_SHIFT) & EVENT_UNIT_MASK; + combine = (event[i] >> EVENT_COMBINE_SHIFT) & EVENT_COMBINE_MASK; + psel = event[i] & EVENT_PSEL_MASK; + + if (!pmc) { + for (pmc = 1; pmc <= 4; ++pmc) { + if (!(pmc_inuse & (1 << pmc))) + break; + } + + pmc_inuse |= 1 << pmc; + } + + if (pmc <= 4) { + mmcr1 |= unit << MMCR1_UNIT_SHIFT(pmc); + mmcr1 |= combine << MMCR1_COMBINE_SHIFT(pmc); + mmcr1 |= psel << MMCR1_PMCSEL_SHIFT(pmc); + } + + if (event[i] & EVENT_IS_L1) { + cache = event[i] >> EVENT_CACHE_SEL_SHIFT; + mmcr1 |= (cache & 1) << MMCR1_IC_QUAL_SHIFT; + cache >>= 1; + mmcr1 |= (cache & 1) << MMCR1_DC_QUAL_SHIFT; + } + + if (event[i] & EVENT_IS_MARKED) { + mmcra |= MMCRA_SAMPLE_ENABLE; + + val = (event[i] >> EVENT_SAMPLE_SHIFT) & EVENT_SAMPLE_MASK; + if (val) { + mmcra |= (val & 3) << MMCRA_SAMP_MODE_SHIFT; + mmcra |= (val >> 2) << MMCRA_SAMP_ELIG_SHIFT; + } + } + + /* + * PM_MRK_FAB_RSP_MATCH and PM_MRK_FAB_RSP_MATCH_CYC, + * the threshold bits are used for the match value. + */ + if (event_is_fab_match(event[i])) { + mmcr1 |= (event[i] >> EVENT_THR_CTL_SHIFT) & + EVENT_THR_CTL_MASK; + } else { + val = (event[i] >> EVENT_THR_CTL_SHIFT) & EVENT_THR_CTL_MASK; + mmcra |= val << MMCRA_THR_CTL_SHIFT; + val = (event[i] >> EVENT_THR_SEL_SHIFT) & EVENT_THR_SEL_MASK; + mmcra |= val << MMCRA_THR_SEL_SHIFT; + val = (event[i] >> EVENT_THR_CMP_SHIFT) & EVENT_THR_CMP_MASK; + mmcra |= val << MMCRA_THR_CMP_SHIFT; + } + + hwc[i] = pmc - 1; + } + + /* Return MMCRx values */ + mmcr[0] = 0; + + /* pmc_inuse is 1-based */ + if (pmc_inuse & 2) + mmcr[0] = MMCR0_PMC1CE; + + if (pmc_inuse & 0x7c) + mmcr[0] |= MMCR0_PMCjCE; + + mmcr[1] = mmcr1; + mmcr[2] = mmcra; + + return 0; +} + +#define MAX_ALT 2 + +/* Table of alternatives, sorted by column 0 */ +static const unsigned int event_alternatives[][MAX_ALT] = { + { 0x10134, 0x301e2 }, /* PM_MRK_ST_CMPL */ + { 0x10138, 0x40138 }, /* PM_BR_MRK_2PATH */ + { 0x18082, 0x3e05e }, /* PM_L3_CO_MEPF */ + { 0x1d14e, 0x401e8 }, /* PM_MRK_DATA_FROM_L2MISS */ + { 0x1e054, 0x4000a }, /* PM_CMPLU_STALL */ + { 0x20036, 0x40036 }, /* PM_BR_2PATH */ + { 0x200f2, 0x300f2 }, /* PM_INST_DISP */ + { 0x200f4, 0x600f4 }, /* PM_RUN_CYC */ + { 0x2013c, 0x3012e }, /* PM_MRK_FILT_MATCH */ + { 0x3e054, 0x400f0 }, /* PM_LD_MISS_L1 */ + { 0x400fa, 0x500fa }, /* PM_RUN_INST_CMPL */ +}; + +/* + * Scan the alternatives table for a match and return the + * index into the alternatives table if found, else -1. + */ +static int find_alternative(u64 event) +{ + int i, j; + + for (i = 0; i < ARRAY_SIZE(event_alternatives); ++i) { + if (event < event_alternatives[i][0]) + break; + + for (j = 0; j < MAX_ALT && event_alternatives[i][j]; ++j) + if (event == event_alternatives[i][j]) + return i; + } + + return -1; +} + +static int power8_get_alternatives(u64 event, unsigned int flags, u64 alt[]) +{ + int i, j, num_alt = 0; + u64 alt_event; + + alt[num_alt++] = event; + + i = find_alternative(event); + if (i >= 0) { + /* Filter out the original event, it's already in alt[0] */ + for (j = 0; j < MAX_ALT; ++j) { + alt_event = event_alternatives[i][j]; + if (alt_event && alt_event != event) + alt[num_alt++] = alt_event; + } + } + + if (flags & PPMU_ONLY_COUNT_RUN) { + /* + * We're only counting in RUN state, so PM_CYC is equivalent to + * PM_RUN_CYC and PM_INST_CMPL === PM_RUN_INST_CMPL. + */ + j = num_alt; + for (i = 0; i < num_alt; ++i) { + switch (alt[i]) { + case 0x1e: /* PM_CYC */ + alt[j++] = 0x600f4; /* PM_RUN_CYC */ + break; + case 0x600f4: /* PM_RUN_CYC */ + alt[j++] = 0x1e; + break; + case 0x2: /* PM_PPC_CMPL */ + alt[j++] = 0x500fa; /* PM_RUN_INST_CMPL */ + break; + case 0x500fa: /* PM_RUN_INST_CMPL */ + alt[j++] = 0x2; /* PM_PPC_CMPL */ + break; + } + } + num_alt = j; + } + + return num_alt; +} + +static void power8_disable_pmc(unsigned int pmc, unsigned long mmcr[]) +{ + if (pmc <= 3) + mmcr[1] &= ~(0xffUL << MMCR1_PMCSEL_SHIFT(pmc + 1)); +} + +PMU_FORMAT_ATTR(event, "config:0-49"); +PMU_FORMAT_ATTR(pmcxsel, "config:0-7"); +PMU_FORMAT_ATTR(mark, "config:8"); +PMU_FORMAT_ATTR(combine, "config:11"); +PMU_FORMAT_ATTR(unit, "config:12-15"); +PMU_FORMAT_ATTR(pmc, "config:16-19"); +PMU_FORMAT_ATTR(cache_sel, "config:20-23"); +PMU_FORMAT_ATTR(sample_mode, "config:24-28"); +PMU_FORMAT_ATTR(thresh_sel, "config:29-31"); +PMU_FORMAT_ATTR(thresh_stop, "config:32-35"); +PMU_FORMAT_ATTR(thresh_start, "config:36-39"); +PMU_FORMAT_ATTR(thresh_cmp, "config:40-49"); + +static struct attribute *power8_pmu_format_attr[] = { + &format_attr_event.attr, + &format_attr_pmcxsel.attr, + &format_attr_mark.attr, + &format_attr_combine.attr, + &format_attr_unit.attr, + &format_attr_pmc.attr, + &format_attr_cache_sel.attr, + &format_attr_sample_mode.attr, + &format_attr_thresh_sel.attr, + &format_attr_thresh_stop.attr, + &format_attr_thresh_start.attr, + &format_attr_thresh_cmp.attr, + NULL, +}; + +struct attribute_group power8_pmu_format_group = { + .name = "format", + .attrs = power8_pmu_format_attr, +}; + +static const struct attribute_group *power8_pmu_attr_groups[] = { + &power8_pmu_format_group, + NULL, +}; + +static int power8_generic_events[] = { + [PERF_COUNT_HW_CPU_CYCLES] = PM_CYC, + [PERF_COUNT_HW_STALLED_CYCLES_FRONTEND] = PM_GCT_NOSLOT_CYC, + [PERF_COUNT_HW_STALLED_CYCLES_BACKEND] = PM_CMPLU_STALL, + [PERF_COUNT_HW_INSTRUCTIONS] = PM_INST_CMPL, + [PERF_COUNT_HW_BRANCH_INSTRUCTIONS] = PM_BRU_FIN, + [PERF_COUNT_HW_BRANCH_MISSES] = PM_BR_MPRED_CMPL, +}; + +static u64 power8_bhrb_filter_map(u64 branch_sample_type) +{ + u64 pmu_bhrb_filter = 0; + u64 br_privilege = branch_sample_type & ONLY_PLM; + + /* BHRB and regular PMU events share the same prvillege state + * filter configuration. BHRB is always recorded along with a + * regular PMU event. So privilege state filter criteria for BHRB + * and the companion PMU events has to be the same. As a default + * "perf record" tool sets all privillege bits ON when no filter + * criteria is provided in the command line. So as along as all + * privillege bits are ON or they are OFF, we are good to go. + */ + if ((br_privilege != 7) && (br_privilege != 0)) + return -1; + + /* No branch filter requested */ + if (branch_sample_type & PERF_SAMPLE_BRANCH_ANY) + return pmu_bhrb_filter; + + /* Invalid branch filter options - HW does not support */ + if (branch_sample_type & PERF_SAMPLE_BRANCH_ANY_RETURN) + return -1; + + if (branch_sample_type & PERF_SAMPLE_BRANCH_IND_CALL) + return -1; + + if (branch_sample_type & PERF_SAMPLE_BRANCH_ANY_CALL) { + pmu_bhrb_filter |= POWER8_MMCRA_IFM1; + return pmu_bhrb_filter; + } + + /* Every thing else is unsupported */ + return -1; +} + +static void power8_config_bhrb(u64 pmu_bhrb_filter) +{ + /* Enable BHRB filter in PMU */ + mtspr(SPRN_MMCRA, (mfspr(SPRN_MMCRA) | pmu_bhrb_filter)); +} + +static struct power_pmu power8_pmu = { + .name = "POWER8", + .n_counter = 6, + .max_alternatives = MAX_ALT + 1, + .add_fields = POWER8_ADD_FIELDS, + .test_adder = POWER8_TEST_ADDER, + .compute_mmcr = power8_compute_mmcr, + .config_bhrb = power8_config_bhrb, + .bhrb_filter_map = power8_bhrb_filter_map, + .get_constraint = power8_get_constraint, + .get_alternatives = power8_get_alternatives, + .disable_pmc = power8_disable_pmc, + .flags = PPMU_HAS_SSLOT | PPMU_HAS_SIER | PPMU_BHRB, + .n_generic = ARRAY_SIZE(power8_generic_events), + .generic_events = power8_generic_events, + .attr_groups = power8_pmu_attr_groups, + .bhrb_nr = 32, +}; + +static int __init init_power8_pmu(void) +{ + if (!cur_cpu_spec->oprofile_cpu_type || + strcmp(cur_cpu_spec->oprofile_cpu_type, "ppc64/power8")) + return -ENODEV; + + return register_power_pmu(&power8_pmu); +} +early_initcall(init_power8_pmu); diff --git a/arch/powerpc/platforms/40x/Kconfig b/arch/powerpc/platforms/40x/Kconfig index a392d12..bd40bbb 100644 --- a/arch/powerpc/platforms/40x/Kconfig +++ b/arch/powerpc/platforms/40x/Kconfig @@ -20,7 +20,6 @@ config HOTFOOT bool "Hotfoot" depends on 40x default n - select 405EP select PPC40x_SIMPLE select PCI help @@ -105,9 +104,6 @@ config 405GP select IBM405_ERR51 select IBM_EMAC_ZMII -config 405EP - bool - config 405EX bool select IBM_EMAC_EMAC4 @@ -119,9 +115,6 @@ config 405EZ select IBM_EMAC_MAL_CLR_ICINTSTAT select IBM_EMAC_MAL_COMMON_ERR -config 405GPR - bool - config XILINX_VIRTEX bool select DEFAULT_UIMAGE diff --git a/arch/powerpc/platforms/Kconfig b/arch/powerpc/platforms/Kconfig index 52de8bc..9089ae7 100644 --- a/arch/powerpc/platforms/Kconfig +++ b/arch/powerpc/platforms/Kconfig @@ -6,7 +6,6 @@ source "arch/powerpc/platforms/chrp/Kconfig" source "arch/powerpc/platforms/512x/Kconfig" source "arch/powerpc/platforms/52xx/Kconfig" source "arch/powerpc/platforms/powermac/Kconfig" -source "arch/powerpc/platforms/prep/Kconfig" source "arch/powerpc/platforms/maple/Kconfig" source "arch/powerpc/platforms/pasemi/Kconfig" source "arch/powerpc/platforms/ps3/Kconfig" @@ -233,7 +232,7 @@ endmenu config PPC601_SYNC_FIX bool "Workarounds for PPC601 bugs" - depends on 6xx && (PPC_PREP || PPC_PMAC) + depends on 6xx && PPC_PMAC help Some versions of the PPC601 (the first PowerPC chip) have bugs which mean that extra synchronization instructions are required near diff --git a/arch/powerpc/platforms/cell/pmu.c b/arch/powerpc/platforms/cell/pmu.c index 59c1a16..348a27b 100644 --- a/arch/powerpc/platforms/cell/pmu.c +++ b/arch/powerpc/platforms/cell/pmu.c @@ -382,7 +382,7 @@ static int __init cbe_init_pm_irq(void) unsigned int irq; int rc, node; - for_each_node(node) { + for_each_online_node(node) { irq = irq_create_mapping(NULL, IIC_IRQ_IOEX_PMI | (node << IIC_IRQ_NODE_SHIFT)); if (irq == NO_IRQ) { diff --git a/arch/powerpc/platforms/cell/spufs/file.c b/arch/powerpc/platforms/cell/spufs/file.c index 68c57d3..0026a37 100644 --- a/arch/powerpc/platforms/cell/spufs/file.c +++ b/arch/powerpc/platforms/cell/spufs/file.c @@ -352,7 +352,7 @@ static unsigned long spufs_get_unmapped_area(struct file *file, /* Else, try to obtain a 64K pages slice */ return slice_get_unmapped_area(addr, len, flags, - MMU_PAGE_64K, 1, 0); + MMU_PAGE_64K, 1); } #endif /* CONFIG_SPU_FS_64K_LS */ diff --git a/arch/powerpc/platforms/cell/spufs/inode.c b/arch/powerpc/platforms/cell/spufs/inode.c index 3f3bb4c..35f77a4 100644 --- a/arch/powerpc/platforms/cell/spufs/inode.c +++ b/arch/powerpc/platforms/cell/spufs/inode.c @@ -99,6 +99,7 @@ spufs_new_inode(struct super_block *sb, umode_t mode) if (!inode) goto out; + inode->i_ino = get_next_ino(); inode->i_mode = mode; inode->i_uid = current_fsuid(); inode->i_gid = current_fsgid(); diff --git a/arch/powerpc/platforms/embedded6xx/Kconfig b/arch/powerpc/platforms/embedded6xx/Kconfig index 5a8f50a9..302ba43 100644 --- a/arch/powerpc/platforms/embedded6xx/Kconfig +++ b/arch/powerpc/platforms/embedded6xx/Kconfig @@ -9,7 +9,6 @@ config LINKSTATION select FSL_SOC select PPC_UDBG_16550 if SERIAL_8250 select DEFAULT_UIMAGE - select MPC10X_OPENPIC select MPC10X_BRIDGE help Select LINKSTATION if configuring for one of PPC- (MPC8241) @@ -24,7 +23,6 @@ config STORCENTER select MPIC select FSL_SOC select PPC_UDBG_16550 if SERIAL_8250 - select MPC10X_OPENPIC select MPC10X_BRIDGE help Select STORCENTER if configuring for the iomega StorCenter @@ -84,9 +82,6 @@ config MV64X60 select PPC_INDIRECT_PCI select CHECK_CACHE_COHERENCY -config MPC10X_OPENPIC - bool - config GAMECUBE_COMMON bool diff --git a/arch/powerpc/platforms/powernv/Kconfig b/arch/powerpc/platforms/powernv/Kconfig index 74fea5c..d3e840d 100644 --- a/arch/powerpc/platforms/powernv/Kconfig +++ b/arch/powerpc/platforms/powernv/Kconfig @@ -8,6 +8,11 @@ config PPC_POWERNV select PPC_PCI_CHOICE if EMBEDDED default y +config POWERNV_MSI + bool "Support PCI MSI on PowerNV platform" + depends on PCI_MSI + default y + config PPC_POWERNV_RTAS depends on PPC_POWERNV bool "Support for RTAS based PowerNV platforms such as BML" diff --git a/arch/powerpc/platforms/powernv/opal-wrappers.S b/arch/powerpc/platforms/powernv/opal-wrappers.S index 3bb07e5..6fabe92 100644 --- a/arch/powerpc/platforms/powernv/opal-wrappers.S +++ b/arch/powerpc/platforms/powernv/opal-wrappers.S @@ -107,3 +107,4 @@ OPAL_CALL(opal_pci_mask_pe_error, OPAL_PCI_MASK_PE_ERROR); OPAL_CALL(opal_set_slot_led_status, OPAL_SET_SLOT_LED_STATUS); OPAL_CALL(opal_get_epow_status, OPAL_GET_EPOW_STATUS); OPAL_CALL(opal_set_system_attention_led, OPAL_SET_SYSTEM_ATTENTION_LED); +OPAL_CALL(opal_pci_msi_eoi, OPAL_PCI_MSI_EOI); diff --git a/arch/powerpc/platforms/powernv/pci-ioda.c b/arch/powerpc/platforms/powernv/pci-ioda.c index 8e90e89..8c6c9cf 100644 --- a/arch/powerpc/platforms/powernv/pci-ioda.c +++ b/arch/powerpc/platforms/powernv/pci-ioda.c @@ -26,10 +26,12 @@ #include <asm/prom.h> #include <asm/pci-bridge.h> #include <asm/machdep.h> +#include <asm/msi_bitmap.h> #include <asm/ppc-pci.h> #include <asm/opal.h> #include <asm/iommu.h> #include <asm/tce.h> +#include <asm/xics.h> #include "powernv.h" #include "pci.h" @@ -87,6 +89,7 @@ static int pnv_ioda_alloc_pe(struct pnv_phb *phb) return IODA_INVALID_PE; } while(test_and_set_bit(pe, phb->ioda.pe_alloc)); + phb->ioda.pe_array[pe].phb = phb; phb->ioda.pe_array[pe].pe_number = pe; return pe; } @@ -431,22 +434,102 @@ static void pnv_pci_ioda_setup_PEs(void) } } -static void pnv_pci_ioda_dma_dev_setup(struct pnv_phb *phb, struct pci_dev *dev) +static void pnv_pci_ioda_dma_dev_setup(struct pnv_phb *phb, struct pci_dev *pdev) { - /* We delay DMA setup after we have assigned all PE# */ + struct pci_dn *pdn = pnv_ioda_get_pdn(pdev); + struct pnv_ioda_pe *pe; + + /* + * The function can be called while the PE# + * hasn't been assigned. Do nothing for the + * case. + */ + if (!pdn || pdn->pe_number == IODA_INVALID_PE) + return; + + pe = &phb->ioda.pe_array[pdn->pe_number]; + set_iommu_table_base(&pdev->dev, &pe->tce32_table); } -static void pnv_ioda_setup_bus_dma(struct pnv_ioda_pe *pe, struct pci_bus *bus) +static void pnv_pci_ioda1_tce_invalidate(struct iommu_table *tbl, + u64 *startp, u64 *endp) { - struct pci_dev *dev; + u64 __iomem *invalidate = (u64 __iomem *)tbl->it_index; + unsigned long start, end, inc; + + start = __pa(startp); + end = __pa(endp); + + /* BML uses this case for p6/p7/galaxy2: Shift addr and put in node */ + if (tbl->it_busno) { + start <<= 12; + end <<= 12; + inc = 128 << 12; + start |= tbl->it_busno; + end |= tbl->it_busno; + } else if (tbl->it_type & TCE_PCI_SWINV_PAIR) { + /* p7ioc-style invalidation, 2 TCEs per write */ + start |= (1ull << 63); + end |= (1ull << 63); + inc = 16; + } else { + /* Default (older HW) */ + inc = 128; + } - list_for_each_entry(dev, &bus->devices, bus_list) { - set_iommu_table_base(&dev->dev, &pe->tce32_table); - if (dev->subordinate) - pnv_ioda_setup_bus_dma(pe, dev->subordinate); + end |= inc - 1; /* round up end to be different than start */ + + mb(); /* Ensure above stores are visible */ + while (start <= end) { + __raw_writeq(start, invalidate); + start += inc; + } + + /* + * The iommu layer will do another mb() for us on build() + * and we don't care on free() + */ +} + +static void pnv_pci_ioda2_tce_invalidate(struct pnv_ioda_pe *pe, + struct iommu_table *tbl, + u64 *startp, u64 *endp) +{ + unsigned long start, end, inc; + u64 __iomem *invalidate = (u64 __iomem *)tbl->it_index; + + /* We'll invalidate DMA address in PE scope */ + start = 0x2ul << 60; + start |= (pe->pe_number & 0xFF); + end = start; + + /* Figure out the start, end and step */ + inc = tbl->it_offset + (((u64)startp - tbl->it_base) / sizeof(u64)); + start |= (inc << 12); + inc = tbl->it_offset + (((u64)endp - tbl->it_base) / sizeof(u64)); + end |= (inc << 12); + inc = (0x1ul << 12); + mb(); + + while (start <= end) { + __raw_writeq(start, invalidate); + start += inc; } } +void pnv_pci_ioda_tce_invalidate(struct iommu_table *tbl, + u64 *startp, u64 *endp) +{ + struct pnv_ioda_pe *pe = container_of(tbl, struct pnv_ioda_pe, + tce32_table); + struct pnv_phb *phb = pe->phb; + + if (phb->type == PNV_PHB_IODA1) + pnv_pci_ioda1_tce_invalidate(tbl, startp, endp); + else + pnv_pci_ioda2_tce_invalidate(pe, tbl, startp, endp); +} + static void pnv_pci_ioda_setup_dma_pe(struct pnv_phb *phb, struct pnv_ioda_pe *pe, unsigned int base, unsigned int segs) @@ -518,16 +601,11 @@ static void pnv_pci_ioda_setup_dma_pe(struct pnv_phb *phb, */ tbl->it_busno = 0; tbl->it_index = (unsigned long)ioremap(be64_to_cpup(swinvp), 8); - tbl->it_type = TCE_PCI_SWINV_CREATE | TCE_PCI_SWINV_FREE - | TCE_PCI_SWINV_PAIR; + tbl->it_type = TCE_PCI_SWINV_CREATE | TCE_PCI_SWINV_FREE | + TCE_PCI_SWINV_PAIR; } iommu_init_table(tbl, phb->hose->node); - if (pe->pdev) - set_iommu_table_base(&pe->pdev->dev, tbl); - else - pnv_ioda_setup_bus_dma(pe, pe->pbus); - return; fail: /* XXX Failure: Try to fallback to 64-bit only ? */ @@ -537,6 +615,76 @@ static void pnv_pci_ioda_setup_dma_pe(struct pnv_phb *phb, __free_pages(tce_mem, get_order(TCE32_TABLE_SIZE * segs)); } +static void pnv_pci_ioda2_setup_dma_pe(struct pnv_phb *phb, + struct pnv_ioda_pe *pe) +{ + struct page *tce_mem = NULL; + void *addr; + const __be64 *swinvp; + struct iommu_table *tbl; + unsigned int tce_table_size, end; + int64_t rc; + + /* We shouldn't already have a 32-bit DMA associated */ + if (WARN_ON(pe->tce32_seg >= 0)) + return; + + /* The PE will reserve all possible 32-bits space */ + pe->tce32_seg = 0; + end = (1 << ilog2(phb->ioda.m32_pci_base)); + tce_table_size = (end / 0x1000) * 8; + pe_info(pe, "Setting up 32-bit TCE table at 0..%08x\n", + end); + + /* Allocate TCE table */ + tce_mem = alloc_pages_node(phb->hose->node, GFP_KERNEL, + get_order(tce_table_size)); + if (!tce_mem) { + pe_err(pe, "Failed to allocate a 32-bit TCE memory\n"); + goto fail; + } + addr = page_address(tce_mem); + memset(addr, 0, tce_table_size); + + /* + * Map TCE table through TVT. The TVE index is the PE number + * shifted by 1 bit for 32-bits DMA space. + */ + rc = opal_pci_map_pe_dma_window(phb->opal_id, pe->pe_number, + pe->pe_number << 1, 1, __pa(addr), + tce_table_size, 0x1000); + if (rc) { + pe_err(pe, "Failed to configure 32-bit TCE table," + " err %ld\n", rc); + goto fail; + } + + /* Setup linux iommu table */ + tbl = &pe->tce32_table; + pnv_pci_setup_iommu_table(tbl, addr, tce_table_size, 0); + + /* OPAL variant of PHB3 invalidated TCEs */ + swinvp = of_get_property(phb->hose->dn, "ibm,opal-tce-kill", NULL); + if (swinvp) { + /* We need a couple more fields -- an address and a data + * to or. Since the bus is only printed out on table free + * errors, and on the first pass the data will be a relative + * bus number, print that out instead. + */ + tbl->it_busno = 0; + tbl->it_index = (unsigned long)ioremap(be64_to_cpup(swinvp), 8); + tbl->it_type = TCE_PCI_SWINV_CREATE | TCE_PCI_SWINV_FREE; + } + iommu_init_table(tbl, phb->hose->node); + + return; +fail: + if (pe->tce32_seg >= 0) + pe->tce32_seg = -1; + if (tce_mem) + __free_pages(tce_mem, get_order(tce_table_size)); +} + static void pnv_ioda_setup_dma(struct pnv_phb *phb) { struct pci_controller *hose = phb->hose; @@ -579,20 +727,49 @@ static void pnv_ioda_setup_dma(struct pnv_phb *phb) if (segs > remaining) segs = remaining; } - pe_info(pe, "DMA weight %d, assigned %d DMA32 segments\n", - pe->dma_weight, segs); - pnv_pci_ioda_setup_dma_pe(phb, pe, base, segs); + + /* + * For IODA2 compliant PHB3, we needn't care about the weight. + * The all available 32-bits DMA space will be assigned to + * the specific PE. + */ + if (phb->type == PNV_PHB_IODA1) { + pe_info(pe, "DMA weight %d, assigned %d DMA32 segments\n", + pe->dma_weight, segs); + pnv_pci_ioda_setup_dma_pe(phb, pe, base, segs); + } else { + pe_info(pe, "Assign DMA32 space\n"); + segs = 0; + pnv_pci_ioda2_setup_dma_pe(phb, pe); + } + remaining -= segs; base += segs; } } #ifdef CONFIG_PCI_MSI +static void pnv_ioda2_msi_eoi(struct irq_data *d) +{ + unsigned int hw_irq = (unsigned int)irqd_to_hwirq(d); + struct irq_chip *chip = irq_data_get_irq_chip(d); + struct pnv_phb *phb = container_of(chip, struct pnv_phb, + ioda.irq_chip); + int64_t rc; + + rc = opal_pci_msi_eoi(phb->opal_id, hw_irq); + WARN_ON_ONCE(rc); + + icp_native_eoi(d); +} + static int pnv_pci_ioda_msi_setup(struct pnv_phb *phb, struct pci_dev *dev, - unsigned int hwirq, unsigned int is_64, - struct msi_msg *msg) + unsigned int hwirq, unsigned int virq, + unsigned int is_64, struct msi_msg *msg) { struct pnv_ioda_pe *pe = pnv_ioda_get_pe(dev); + struct irq_data *idata; + struct irq_chip *ichip; unsigned int xive_num = hwirq - phb->msi_base; uint64_t addr64; uint32_t addr32, data; @@ -637,6 +814,23 @@ static int pnv_pci_ioda_msi_setup(struct pnv_phb *phb, struct pci_dev *dev, } msg->data = data; + /* + * Change the IRQ chip for the MSI interrupts on PHB3. + * The corresponding IRQ chip should be populated for + * the first time. + */ + if (phb->type == PNV_PHB_IODA2) { + if (!phb->ioda.irq_chip_init) { + idata = irq_get_irq_data(virq); + ichip = irq_data_get_irq_chip(idata); + phb->ioda.irq_chip_init = 1; + phb->ioda.irq_chip = *ichip; + phb->ioda.irq_chip.irq_eoi = pnv_ioda2_msi_eoi; + } + + irq_set_chip(virq, &phb->ioda.irq_chip); + } + pr_devel("%s: %s-bit MSI on hwirq %x (xive #%d)," " address=%x_%08x data=%x PE# %d\n", pci_name(dev), is_64 ? "64" : "32", hwirq, xive_num, @@ -647,7 +841,7 @@ static int pnv_pci_ioda_msi_setup(struct pnv_phb *phb, struct pci_dev *dev, static void pnv_pci_init_ioda_msis(struct pnv_phb *phb) { - unsigned int bmap_size; + unsigned int count; const __be32 *prop = of_get_property(phb->hose->dn, "ibm,opal-msi-ranges", NULL); if (!prop) { @@ -658,18 +852,17 @@ static void pnv_pci_init_ioda_msis(struct pnv_phb *phb) return; phb->msi_base = be32_to_cpup(prop); - phb->msi_count = be32_to_cpup(prop + 1); - bmap_size = BITS_TO_LONGS(phb->msi_count) * sizeof(unsigned long); - phb->msi_map = zalloc_maybe_bootmem(bmap_size, GFP_KERNEL); - if (!phb->msi_map) { + count = be32_to_cpup(prop + 1); + if (msi_bitmap_alloc(&phb->msi_bmp, count, phb->hose->dn)) { pr_err("PCI %d: Failed to allocate MSI bitmap !\n", phb->hose->global_number); return; } + phb->msi_setup = pnv_pci_ioda_msi_setup; phb->msi32_support = 1; pr_info(" Allocated bitmap for %d MSIs (base IRQ 0x%x)\n", - phb->msi_count, phb->msi_base); + count, phb->msi_base); } #else static void pnv_pci_init_ioda_msis(struct pnv_phb *phb) { } @@ -852,18 +1045,19 @@ static u32 pnv_ioda_bdfn_to_pe(struct pnv_phb *phb, struct pci_bus *bus, return phb->ioda.pe_rmap[(bus->number << 8) | devfn]; } -void __init pnv_pci_init_ioda1_phb(struct device_node *np) +void __init pnv_pci_init_ioda_phb(struct device_node *np, int ioda_type) { struct pci_controller *hose; static int primary = 1; struct pnv_phb *phb; unsigned long size, m32map_off, iomap_off, pemap_off; const u64 *prop64; + const u32 *prop32; u64 phb_id; void *aux; long rc; - pr_info(" Initializing IODA OPAL PHB %s\n", np->full_name); + pr_info(" Initializing IODA%d OPAL PHB %s\n", ioda_type, np->full_name); prop64 = of_get_property(np, "ibm,opal-phbid", NULL); if (!prop64) { @@ -890,37 +1084,34 @@ void __init pnv_pci_init_ioda1_phb(struct device_node *np) hose->last_busno = 0xff; hose->private_data = phb; phb->opal_id = phb_id; - phb->type = PNV_PHB_IODA1; + phb->type = ioda_type; /* Detect specific models for error handling */ if (of_device_is_compatible(np, "ibm,p7ioc-pciex")) phb->model = PNV_PHB_MODEL_P7IOC; + else if (of_device_is_compatible(np, "ibm,p8-pciex")) + phb->model = PNV_PHB_MODEL_PHB3; else phb->model = PNV_PHB_MODEL_UNKNOWN; - /* We parse "ranges" now since we need to deduce the register base - * from the IO base - */ + /* Parse 32-bit and IO ranges (if any) */ pci_process_bridge_OF_ranges(phb->hose, np, primary); primary = 0; - /* Magic formula from Milton */ + /* Get registers */ phb->regs = of_iomap(np, 0); if (phb->regs == NULL) pr_err(" Failed to map registers !\n"); - - /* XXX This is hack-a-thon. This needs to be changed so that: - * - we obtain stuff like PE# etc... from device-tree - * - we properly re-allocate M32 ourselves - * (the OFW one isn't very good) - */ - /* Initialize more IODA stuff */ - phb->ioda.total_pe = 128; + prop32 = of_get_property(np, "ibm,opal-num-pes", NULL); + if (!prop32) + phb->ioda.total_pe = 1; + else + phb->ioda.total_pe = *prop32; phb->ioda.m32_size = resource_size(&hose->mem_resources[0]); - /* OFW Has already off top 64k of M32 space (MSI space) */ + /* FW Has already off top 64k of M32 space (MSI space) */ phb->ioda.m32_size += 0x10000; phb->ioda.m32_segsize = phb->ioda.m32_size / phb->ioda.total_pe; @@ -930,7 +1121,10 @@ void __init pnv_pci_init_ioda1_phb(struct device_node *np) phb->ioda.io_segsize = phb->ioda.io_size / phb->ioda.total_pe; phb->ioda.io_pci_base = 0; /* XXX calculate this ? */ - /* Allocate aux data & arrays */ + /* Allocate aux data & arrays + * + * XXX TODO: Don't allocate io segmap on PHB3 + */ size = _ALIGN_UP(phb->ioda.total_pe / 8, sizeof(unsigned long)); m32map_off = size; size += phb->ioda.total_pe * sizeof(phb->ioda.m32_segmap[0]); @@ -960,7 +1154,7 @@ void __init pnv_pci_init_ioda1_phb(struct device_node *np) hose->mem_resources[2].start = 0; hose->mem_resources[2].end = 0; -#if 0 +#if 0 /* We should really do that ... */ rc = opal_pci_set_phb_mem_window(opal->phb_id, window_type, window_num, @@ -974,16 +1168,6 @@ void __init pnv_pci_init_ioda1_phb(struct device_node *np) phb->ioda.m32_size, phb->ioda.m32_segsize, phb->ioda.io_size, phb->ioda.io_segsize); - if (phb->regs) { - pr_devel(" BUID = 0x%016llx\n", in_be64(phb->regs + 0x100)); - pr_devel(" PHB2_CR = 0x%016llx\n", in_be64(phb->regs + 0x160)); - pr_devel(" IO_BAR = 0x%016llx\n", in_be64(phb->regs + 0x170)); - pr_devel(" IO_BAMR = 0x%016llx\n", in_be64(phb->regs + 0x178)); - pr_devel(" IO_SAR = 0x%016llx\n", in_be64(phb->regs + 0x180)); - pr_devel(" M32_BAR = 0x%016llx\n", in_be64(phb->regs + 0x190)); - pr_devel(" M32_BAMR = 0x%016llx\n", in_be64(phb->regs + 0x198)); - pr_devel(" M32_SAR = 0x%016llx\n", in_be64(phb->regs + 0x1a0)); - } phb->hose->ops = &pnv_pci_ops; /* Setup RID -> PE mapping function */ @@ -1011,7 +1195,18 @@ void __init pnv_pci_init_ioda1_phb(struct device_node *np) rc = opal_pci_reset(phb_id, OPAL_PCI_IODA_TABLE_RESET, OPAL_ASSERT_RESET); if (rc) pr_warning(" OPAL Error %ld performing IODA table reset !\n", rc); - opal_pci_set_pe(phb_id, 0, 0, 7, 1, 1 , OPAL_MAP_PE); + + /* + * On IODA1 map everything to PE#0, on IODA2 we assume the IODA reset + * has cleared the RTT which has the same effect + */ + if (ioda_type == PNV_PHB_IODA1) + opal_pci_set_pe(phb_id, 0, 0, 7, 1, 1 , OPAL_MAP_PE); +} + +void pnv_pci_init_ioda2_phb(struct device_node *np) +{ + pnv_pci_init_ioda_phb(np, PNV_PHB_IODA2); } void __init pnv_pci_init_ioda_hub(struct device_node *np) @@ -1034,6 +1229,6 @@ void __init pnv_pci_init_ioda_hub(struct device_node *np) for_each_child_of_node(np, phbn) { /* Look for IODA1 PHBs */ if (of_device_is_compatible(phbn, "ibm,ioda-phb")) - pnv_pci_init_ioda1_phb(phbn); + pnv_pci_init_ioda_phb(phbn, PNV_PHB_IODA1); } } diff --git a/arch/powerpc/platforms/powernv/pci-p5ioc2.c b/arch/powerpc/platforms/powernv/pci-p5ioc2.c index 7db8771..92b37a0 100644 --- a/arch/powerpc/platforms/powernv/pci-p5ioc2.c +++ b/arch/powerpc/platforms/powernv/pci-p5ioc2.c @@ -26,6 +26,7 @@ #include <asm/prom.h> #include <asm/pci-bridge.h> #include <asm/machdep.h> +#include <asm/msi_bitmap.h> #include <asm/ppc-pci.h> #include <asm/opal.h> #include <asm/iommu.h> @@ -41,8 +42,8 @@ #ifdef CONFIG_PCI_MSI static int pnv_pci_p5ioc2_msi_setup(struct pnv_phb *phb, struct pci_dev *dev, - unsigned int hwirq, unsigned int is_64, - struct msi_msg *msg) + unsigned int hwirq, unsigned int virq, + unsigned int is_64, struct msi_msg *msg) { if (WARN_ON(!is_64)) return -ENXIO; @@ -55,7 +56,7 @@ static int pnv_pci_p5ioc2_msi_setup(struct pnv_phb *phb, struct pci_dev *dev, static void pnv_pci_init_p5ioc2_msis(struct pnv_phb *phb) { - unsigned int bmap_size; + unsigned int count; const __be32 *prop = of_get_property(phb->hose->dn, "ibm,opal-msi-ranges", NULL); if (!prop) @@ -67,10 +68,8 @@ static void pnv_pci_init_p5ioc2_msis(struct pnv_phb *phb) if (of_device_is_compatible(phb->hose->dn, "ibm,p5ioc2-pcix")) return; phb->msi_base = be32_to_cpup(prop); - phb->msi_count = be32_to_cpup(prop + 1); - bmap_size = BITS_TO_LONGS(phb->msi_count) * sizeof(unsigned long); - phb->msi_map = zalloc_maybe_bootmem(bmap_size, GFP_KERNEL); - if (!phb->msi_map) { + count = be32_to_cpup(prop + 1); + if (msi_bitmap_alloc(&phb->msi_bmp, count, phb->hose->dn)) { pr_err("PCI %d: Failed to allocate MSI bitmap !\n", phb->hose->global_number); return; @@ -78,7 +77,7 @@ static void pnv_pci_init_p5ioc2_msis(struct pnv_phb *phb) phb->msi_setup = pnv_pci_p5ioc2_msi_setup; phb->msi32_support = 0; pr_info(" Allocated bitmap for %d MSIs (base IRQ 0x%x)\n", - phb->msi_count, phb->msi_base); + count, phb->msi_base); } #else static void pnv_pci_init_p5ioc2_msis(struct pnv_phb *phb) { } diff --git a/arch/powerpc/platforms/powernv/pci.c b/arch/powerpc/platforms/powernv/pci.c index b8b8e0b..55dfca844 100644 --- a/arch/powerpc/platforms/powernv/pci.c +++ b/arch/powerpc/platforms/powernv/pci.c @@ -26,6 +26,7 @@ #include <asm/prom.h> #include <asm/pci-bridge.h> #include <asm/machdep.h> +#include <asm/msi_bitmap.h> #include <asm/ppc-pci.h> #include <asm/opal.h> #include <asm/iommu.h> @@ -47,43 +48,7 @@ static int pnv_msi_check_device(struct pci_dev* pdev, int nvec, int type) struct pci_controller *hose = pci_bus_to_host(pdev->bus); struct pnv_phb *phb = hose->private_data; - return (phb && phb->msi_map) ? 0 : -ENODEV; -} - -static unsigned int pnv_get_one_msi(struct pnv_phb *phb) -{ - unsigned long flags; - unsigned int id, rc; - - spin_lock_irqsave(&phb->lock, flags); - - id = find_next_zero_bit(phb->msi_map, phb->msi_count, phb->msi_next); - if (id >= phb->msi_count && phb->msi_next) - id = find_next_zero_bit(phb->msi_map, phb->msi_count, 0); - if (id >= phb->msi_count) { - rc = 0; - goto out; - } - __set_bit(id, phb->msi_map); - rc = id + phb->msi_base; -out: - spin_unlock_irqrestore(&phb->lock, flags); - return rc; -} - -static void pnv_put_msi(struct pnv_phb *phb, unsigned int hwirq) -{ - unsigned long flags; - unsigned int id; - - if (WARN_ON(hwirq < phb->msi_base || - hwirq >= (phb->msi_base + phb->msi_count))) - return; - id = hwirq - phb->msi_base; - - spin_lock_irqsave(&phb->lock, flags); - __clear_bit(id, phb->msi_map); - spin_unlock_irqrestore(&phb->lock, flags); + return (phb && phb->msi_bmp.bitmap) ? 0 : -ENODEV; } static int pnv_setup_msi_irqs(struct pci_dev *pdev, int nvec, int type) @@ -92,7 +57,8 @@ static int pnv_setup_msi_irqs(struct pci_dev *pdev, int nvec, int type) struct pnv_phb *phb = hose->private_data; struct msi_desc *entry; struct msi_msg msg; - unsigned int hwirq, virq; + int hwirq; + unsigned int virq; int rc; if (WARN_ON(!phb)) @@ -104,25 +70,25 @@ static int pnv_setup_msi_irqs(struct pci_dev *pdev, int nvec, int type) pci_name(pdev)); return -ENXIO; } - hwirq = pnv_get_one_msi(phb); - if (!hwirq) { + hwirq = msi_bitmap_alloc_hwirqs(&phb->msi_bmp, 1); + if (hwirq < 0) { pr_warn("%s: Failed to find a free MSI\n", pci_name(pdev)); return -ENOSPC; } - virq = irq_create_mapping(NULL, hwirq); + virq = irq_create_mapping(NULL, phb->msi_base + hwirq); if (virq == NO_IRQ) { pr_warn("%s: Failed to map MSI to linux irq\n", pci_name(pdev)); - pnv_put_msi(phb, hwirq); + msi_bitmap_free_hwirqs(&phb->msi_bmp, hwirq, 1); return -ENOMEM; } - rc = phb->msi_setup(phb, pdev, hwirq, entry->msi_attrib.is_64, - &msg); + rc = phb->msi_setup(phb, pdev, phb->msi_base + hwirq, + virq, entry->msi_attrib.is_64, &msg); if (rc) { pr_warn("%s: Failed to setup MSI\n", pci_name(pdev)); irq_dispose_mapping(virq); - pnv_put_msi(phb, hwirq); + msi_bitmap_free_hwirqs(&phb->msi_bmp, hwirq, 1); return rc; } irq_set_msi_desc(virq, entry); @@ -144,7 +110,8 @@ static void pnv_teardown_msi_irqs(struct pci_dev *pdev) if (entry->irq == NO_IRQ) continue; irq_set_msi_desc(entry->irq, NULL); - pnv_put_msi(phb, virq_to_hw(entry->irq)); + msi_bitmap_free_hwirqs(&phb->msi_bmp, + virq_to_hw(entry->irq) - phb->msi_base, 1); irq_dispose_mapping(entry->irq); } } @@ -362,48 +329,6 @@ struct pci_ops pnv_pci_ops = { .write = pnv_pci_write_config, }; - -static void pnv_tce_invalidate(struct iommu_table *tbl, - u64 *startp, u64 *endp) -{ - u64 __iomem *invalidate = (u64 __iomem *)tbl->it_index; - unsigned long start, end, inc; - - start = __pa(startp); - end = __pa(endp); - - - /* BML uses this case for p6/p7/galaxy2: Shift addr and put in node */ - if (tbl->it_busno) { - start <<= 12; - end <<= 12; - inc = 128 << 12; - start |= tbl->it_busno; - end |= tbl->it_busno; - } - /* p7ioc-style invalidation, 2 TCEs per write */ - else if (tbl->it_type & TCE_PCI_SWINV_PAIR) { - start |= (1ull << 63); - end |= (1ull << 63); - inc = 16; - } - /* Default (older HW) */ - else - inc = 128; - - end |= inc - 1; /* round up end to be different than start */ - - mb(); /* Ensure above stores are visible */ - while (start <= end) { - __raw_writeq(start, invalidate); - start += inc; - } - /* The iommu layer will do another mb() for us on build() and - * we don't care on free() - */ -} - - static int pnv_tce_build(struct iommu_table *tbl, long index, long npages, unsigned long uaddr, enum dma_data_direction direction, struct dma_attrs *attrs) @@ -428,7 +353,7 @@ static int pnv_tce_build(struct iommu_table *tbl, long index, long npages, * of flags if that becomes the case */ if (tbl->it_type & TCE_PCI_SWINV_CREATE) - pnv_tce_invalidate(tbl, tces, tcep - 1); + pnv_pci_ioda_tce_invalidate(tbl, tces, tcep - 1); return 0; } @@ -442,8 +367,8 @@ static void pnv_tce_free(struct iommu_table *tbl, long index, long npages) while (npages--) *(tcep++) = 0; - if (tbl->it_type & TCE_PCI_SWINV_FREE) - pnv_tce_invalidate(tbl, tces, tcep - 1); + if (tbl->it_type & TCE_PCI_SWINV_CREATE) + pnv_pci_ioda_tce_invalidate(tbl, tces, tcep - 1); } static unsigned long pnv_tce_get(struct iommu_table *tbl, long index) @@ -525,7 +450,7 @@ static void pnv_pci_dma_dev_setup(struct pci_dev *pdev) pnv_pci_dma_fallback_setup(hose, pdev); } -/* Fixup wrong class code in p7ioc root complex */ +/* Fixup wrong class code in p7ioc and p8 root complex */ static void pnv_p7ioc_rc_quirk(struct pci_dev *dev) { dev->class = PCI_CLASS_BRIDGE_PCI << 8; @@ -591,6 +516,10 @@ void __init pnv_pci_init(void) if (!found_ioda) for_each_compatible_node(np, NULL, "ibm,p5ioc2") pnv_pci_init_p5ioc2_hub(np); + + /* Look for ioda2 built-in PHB3's */ + for_each_compatible_node(np, NULL, "ibm,ioda2-phb") + pnv_pci_init_ioda2_phb(np); } /* Setup the linkage between OF nodes and PHBs */ diff --git a/arch/powerpc/platforms/powernv/pci.h b/arch/powerpc/platforms/powernv/pci.h index 7cfb7c8..48dc4bb 100644 --- a/arch/powerpc/platforms/powernv/pci.h +++ b/arch/powerpc/platforms/powernv/pci.h @@ -4,9 +4,9 @@ struct pci_dn; enum pnv_phb_type { - PNV_PHB_P5IOC2, - PNV_PHB_IODA1, - PNV_PHB_IODA2, + PNV_PHB_P5IOC2 = 0, + PNV_PHB_IODA1 = 1, + PNV_PHB_IODA2 = 2, }; /* Precise PHB model for error management */ @@ -14,6 +14,7 @@ enum pnv_phb_model { PNV_PHB_MODEL_UNKNOWN, PNV_PHB_MODEL_P5IOC2, PNV_PHB_MODEL_P7IOC, + PNV_PHB_MODEL_PHB3, }; #define PNV_PCI_DIAG_BUF_SIZE 4096 @@ -22,8 +23,10 @@ enum pnv_phb_model { #define PNV_IODA_PE_BUS_ALL (1 << 2) /* PE has subordinate buses */ /* Data associated with a PE, including IOMMU tracking etc.. */ +struct pnv_phb; struct pnv_ioda_pe { unsigned long flags; + struct pnv_phb *phb; /* A PE can be associated with a single device or an * entire bus (& children). In the former case, pdev @@ -73,15 +76,13 @@ struct pnv_phb { spinlock_t lock; #ifdef CONFIG_PCI_MSI - unsigned long *msi_map; unsigned int msi_base; - unsigned int msi_count; - unsigned int msi_next; unsigned int msi32_support; + struct msi_bitmap msi_bmp; #endif int (*msi_setup)(struct pnv_phb *phb, struct pci_dev *dev, - unsigned int hwirq, unsigned int is_64, - struct msi_msg *msg); + unsigned int hwirq, unsigned int virq, + unsigned int is_64, struct msi_msg *msg); void (*dma_dev_setup)(struct pnv_phb *phb, struct pci_dev *pdev); void (*fixup_phb)(struct pci_controller *hose); u32 (*bdfn_to_pe)(struct pnv_phb *phb, struct pci_bus *bus, u32 devfn); @@ -109,6 +110,10 @@ struct pnv_phb { unsigned int *io_segmap; struct pnv_ioda_pe *pe_array; + /* IRQ chip */ + int irq_chip_init; + struct irq_chip irq_chip; + /* Sorted list of used PE's based * on the sequence of creation */ @@ -150,6 +155,7 @@ extern void pnv_pci_setup_iommu_table(struct iommu_table *tbl, u64 dma_offset); extern void pnv_pci_init_p5ioc2_hub(struct device_node *np); extern void pnv_pci_init_ioda_hub(struct device_node *np); - - +extern void pnv_pci_init_ioda2_phb(struct device_node *np); +extern void pnv_pci_ioda_tce_invalidate(struct iommu_table *tbl, + u64 *startp, u64 *endp); #endif /* __POWERNV_PCI_H */ diff --git a/arch/powerpc/platforms/prep/Kconfig b/arch/powerpc/platforms/prep/Kconfig deleted file mode 100644 index 1547f66..0000000 --- a/arch/powerpc/platforms/prep/Kconfig +++ /dev/null @@ -1,23 +0,0 @@ -config PPC_PREP - bool "PowerPC Reference Platform (PReP) based machines" - depends on 6xx && BROKEN - select HAVE_PCSPKR_PLATFORM - select MPIC - select PPC_I8259 - select PPC_INDIRECT_PCI - select PPC_UDBG_16550 - select PPC_NATIVE - default n - -config PREP_RESIDUAL - bool "Support for PReP Residual Data" - depends on PPC_PREP - help - Some PReP systems have residual data passed to the kernel by the - firmware. This allows detection of memory size, devices present and - other useful pieces of information. Sometimes this information is - not present or incorrect, in which case it could lead to the machine - behaving incorrectly. If this happens, either disable PREP_RESIDUAL - or pass the 'noresidual' option to the kernel. - - If you are running a PReP system, say Y here, otherwise say N. diff --git a/arch/powerpc/platforms/ps3/time.c b/arch/powerpc/platforms/ps3/time.c index 40b5cb4..cba1e6b 100644 --- a/arch/powerpc/platforms/ps3/time.c +++ b/arch/powerpc/platforms/ps3/time.c @@ -89,10 +89,8 @@ static int __init ps3_rtc_init(void) return -ENODEV; pdev = platform_device_register_simple("rtc-ps3", -1, NULL, 0); - if (IS_ERR(pdev)) - return PTR_ERR(pdev); - return 0; + return PTR_RET(pdev); } module_init(ps3_rtc_init); diff --git a/arch/powerpc/platforms/pseries/firmware.c b/arch/powerpc/platforms/pseries/firmware.c index aa3693f..8c80588 100644 --- a/arch/powerpc/platforms/pseries/firmware.c +++ b/arch/powerpc/platforms/pseries/firmware.c @@ -28,18 +28,18 @@ #include "pseries.h" -typedef struct { +struct hypertas_fw_feature { unsigned long val; char * name; -} firmware_feature_t; +}; /* * The names in this table match names in rtas/ibm,hypertas-functions. If the * entry ends in a '*', only upto the '*' is matched. Otherwise the entire * string must match. */ -static __initdata firmware_feature_t -firmware_features_table[FIRMWARE_MAX_FEATURES] = { +static __initdata struct hypertas_fw_feature +hypertas_fw_features_table[] = { {FW_FEATURE_PFT, "hcall-pft"}, {FW_FEATURE_TCE, "hcall-tce"}, {FW_FEATURE_SPRG0, "hcall-sprg0"}, @@ -69,20 +69,18 @@ firmware_features_table[FIRMWARE_MAX_FEATURES] = { * device-tree/ibm,hypertas-functions. Ultimately this functionality may * be moved into prom.c prom_init(). */ -void __init fw_feature_init(const char *hypertas, unsigned long len) +void __init fw_hypertas_feature_init(const char *hypertas, unsigned long len) { const char *s; int i; - pr_debug(" -> fw_feature_init()\n"); + pr_debug(" -> fw_hypertas_feature_init()\n"); for (s = hypertas; s < hypertas + len; s += strlen(s) + 1) { - for (i = 0; i < FIRMWARE_MAX_FEATURES; i++) { - const char *name = firmware_features_table[i].name; + for (i = 0; i < ARRAY_SIZE(hypertas_fw_features_table); i++) { + const char *name = hypertas_fw_features_table[i].name; size_t size; - /* check value against table of strings */ - if (!name) - continue; + /* * If there is a '*' at the end of name, only check * upto there @@ -96,10 +94,40 @@ void __init fw_feature_init(const char *hypertas, unsigned long len) /* we have a match */ powerpc_firmware_features |= - firmware_features_table[i].val; + hypertas_fw_features_table[i].val; break; } } - pr_debug(" <- fw_feature_init()\n"); + pr_debug(" <- fw_hypertas_feature_init()\n"); +} + +struct vec5_fw_feature { + unsigned long val; + unsigned int feature; +}; + +static __initdata struct vec5_fw_feature +vec5_fw_features_table[] = { + {FW_FEATURE_TYPE1_AFFINITY, OV5_TYPE1_AFFINITY}, + {FW_FEATURE_PRRN, OV5_PRRN}, +}; + +void __init fw_vec5_feature_init(const char *vec5, unsigned long len) +{ + unsigned int index, feat; + int i; + + pr_debug(" -> fw_vec5_feature_init()\n"); + + for (i = 0; i < ARRAY_SIZE(vec5_fw_features_table); i++) { + index = OV5_INDX(vec5_fw_features_table[i].feature); + feat = OV5_FEAT(vec5_fw_features_table[i].feature); + + if (vec5[index] & feat) + powerpc_firmware_features |= + vec5_fw_features_table[i].val; + } + + pr_debug(" <- fw_vec5_feature_init()\n"); } diff --git a/arch/powerpc/platforms/pseries/iommu.c b/arch/powerpc/platforms/pseries/iommu.c index 1b2a174..86ae364 100644 --- a/arch/powerpc/platforms/pseries/iommu.c +++ b/arch/powerpc/platforms/pseries/iommu.c @@ -924,6 +924,13 @@ static void restore_default_window(struct pci_dev *dev, __restore_default_window(pci_dev_to_eeh_dev(dev), ddw_restore_token); } +struct failed_ddw_pdn { + struct device_node *pdn; + struct list_head list; +}; + +static LIST_HEAD(failed_ddw_pdn_list); + /* * If the PE supports dynamic dma windows, and there is space for a table * that can map all pages in a linear offset, then setup such a table, @@ -951,6 +958,7 @@ static u64 enable_ddw(struct pci_dev *dev, struct device_node *pdn) struct dynamic_dma_window_prop *ddwprop; const void *dma_window = NULL; unsigned long liobn, offset, size; + struct failed_ddw_pdn *fpdn; mutex_lock(&direct_window_init_mutex); @@ -959,6 +967,18 @@ static u64 enable_ddw(struct pci_dev *dev, struct device_node *pdn) goto out_unlock; /* + * If we already went through this for a previous function of + * the same device and failed, we don't want to muck with the + * DMA window again, as it will race with in-flight operations + * and can lead to EEHs. The above mutex protects access to the + * list. + */ + list_for_each_entry(fpdn, &failed_ddw_pdn_list, list) { + if (!strcmp(fpdn->pdn->full_name, pdn->full_name)) + goto out_unlock; + } + + /* * the ibm,ddw-applicable property holds the tokens for: * ibm,query-pe-dma-window * ibm,create-pe-dma-window @@ -1114,6 +1134,12 @@ out_restore_window: if (ddw_restore_token) restore_default_window(dev, ddw_restore_token); + fpdn = kzalloc(sizeof(*fpdn), GFP_KERNEL); + if (!fpdn) + goto out_unlock; + fpdn->pdn = pdn; + list_add(&fpdn->list, &failed_ddw_pdn_list); + out_unlock: mutex_unlock(&direct_window_init_mutex); return dma_addr; diff --git a/arch/powerpc/platforms/pseries/lpar.c b/arch/powerpc/platforms/pseries/lpar.c index 0da39fe..299731e 100644 --- a/arch/powerpc/platforms/pseries/lpar.c +++ b/arch/powerpc/platforms/pseries/lpar.c @@ -186,7 +186,13 @@ static long pSeries_lpar_hpte_remove(unsigned long hpte_group) (0x1UL << 4), &dummy1, &dummy2); if (lpar_rc == H_SUCCESS) return i; - BUG_ON(lpar_rc != H_NOT_FOUND); + + /* + * The test for adjunct partition is performed before the + * ANDCOND test. H_RESOURCE may be returned, so we need to + * check for that as well. + */ + BUG_ON(lpar_rc != H_NOT_FOUND && lpar_rc != H_RESOURCE); slot_offset++; slot_offset &= 0x7; diff --git a/arch/powerpc/platforms/pseries/mobility.c b/arch/powerpc/platforms/pseries/mobility.c index 6573808..3d01eee 100644 --- a/arch/powerpc/platforms/pseries/mobility.c +++ b/arch/powerpc/platforms/pseries/mobility.c @@ -37,14 +37,16 @@ struct update_props_workarea { #define UPDATE_DT_NODE 0x02000000 #define ADD_DT_NODE 0x03000000 -static int mobility_rtas_call(int token, char *buf) +#define MIGRATION_SCOPE (1) + +static int mobility_rtas_call(int token, char *buf, s32 scope) { int rc; spin_lock(&rtas_data_buf_lock); memcpy(rtas_data_buf, buf, RTAS_DATA_BUF_SIZE); - rc = rtas_call(token, 2, 1, NULL, rtas_data_buf, 1); + rc = rtas_call(token, 2, 1, NULL, rtas_data_buf, scope); memcpy(buf, rtas_data_buf, RTAS_DATA_BUF_SIZE); spin_unlock(&rtas_data_buf_lock); @@ -123,7 +125,7 @@ static int update_dt_property(struct device_node *dn, struct property **prop, return 0; } -static int update_dt_node(u32 phandle) +static int update_dt_node(u32 phandle, s32 scope) { struct update_props_workarea *upwa; struct device_node *dn; @@ -132,6 +134,7 @@ static int update_dt_node(u32 phandle) char *prop_data; char *rtas_buf; int update_properties_token; + u32 vd; update_properties_token = rtas_token("ibm,update-properties"); if (update_properties_token == RTAS_UNKNOWN_SERVICE) @@ -151,19 +154,31 @@ static int update_dt_node(u32 phandle) upwa->phandle = phandle; do { - rc = mobility_rtas_call(update_properties_token, rtas_buf); + rc = mobility_rtas_call(update_properties_token, rtas_buf, + scope); if (rc < 0) break; prop_data = rtas_buf + sizeof(*upwa); - for (i = 0; i < upwa->nprops; i++) { + /* The first element of the buffer is the path of the node + * being updated in the form of a 8 byte string length + * followed by the string. Skip past this to get to the + * properties being updated. + */ + vd = *prop_data++; + prop_data += vd; + + /* The path we skipped over is counted as one of the elements + * returned so start counting at one. + */ + for (i = 1; i < upwa->nprops; i++) { char *prop_name; - u32 vd; - prop_name = prop_data + 1; + prop_name = prop_data; prop_data += strlen(prop_name) + 1; - vd = *prop_data++; + vd = *(u32 *)prop_data; + prop_data += sizeof(vd); switch (vd) { case 0x00000000: @@ -219,7 +234,7 @@ static int add_dt_node(u32 parent_phandle, u32 drc_index) return rc; } -static int pseries_devicetree_update(void) +int pseries_devicetree_update(s32 scope) { char *rtas_buf; u32 *data; @@ -235,7 +250,7 @@ static int pseries_devicetree_update(void) return -ENOMEM; do { - rc = mobility_rtas_call(update_nodes_token, rtas_buf); + rc = mobility_rtas_call(update_nodes_token, rtas_buf, scope); if (rc && rc != 1) break; @@ -256,7 +271,7 @@ static int pseries_devicetree_update(void) delete_dt_node(phandle); break; case UPDATE_DT_NODE: - update_dt_node(phandle); + update_dt_node(phandle, scope); break; case ADD_DT_NODE: drc_index = *data++; @@ -276,7 +291,7 @@ void post_mobility_fixup(void) int rc; int activate_fw_token; - rc = pseries_devicetree_update(); + rc = pseries_devicetree_update(MIGRATION_SCOPE); if (rc) { printk(KERN_ERR "Initial post-mobility device tree update " "failed: %d\n", rc); @@ -292,7 +307,7 @@ void post_mobility_fixup(void) rc = rtas_call(activate_fw_token, 0, 1, NULL); if (!rc) { - rc = pseries_devicetree_update(); + rc = pseries_devicetree_update(MIGRATION_SCOPE); if (rc) printk(KERN_ERR "Secondary post-mobility device tree " "update failed: %d\n", rc); diff --git a/arch/powerpc/platforms/pseries/plpar_wrappers.h b/arch/powerpc/platforms/pseries/plpar_wrappers.h index f368668..f35787b 100644 --- a/arch/powerpc/platforms/pseries/plpar_wrappers.h +++ b/arch/powerpc/platforms/pseries/plpar_wrappers.h @@ -58,40 +58,39 @@ static inline long extended_cede_processor(unsigned long latency_hint) static inline long vpa_call(unsigned long flags, unsigned long cpu, unsigned long vpa) { - /* flags are in bits 16-18 (counting from most significant bit) */ - flags = flags << (63 - 18); + flags = flags << H_VPA_FUNC_SHIFT; return plpar_hcall_norets(H_REGISTER_VPA, flags, cpu, vpa); } static inline long unregister_vpa(unsigned long cpu) { - return vpa_call(0x5, cpu, 0); + return vpa_call(H_VPA_DEREG_VPA, cpu, 0); } static inline long register_vpa(unsigned long cpu, unsigned long vpa) { - return vpa_call(0x1, cpu, vpa); + return vpa_call(H_VPA_REG_VPA, cpu, vpa); } static inline long unregister_slb_shadow(unsigned long cpu) { - return vpa_call(0x7, cpu, 0); + return vpa_call(H_VPA_DEREG_SLB, cpu, 0); } static inline long register_slb_shadow(unsigned long cpu, unsigned long vpa) { - return vpa_call(0x3, cpu, vpa); + return vpa_call(H_VPA_REG_SLB, cpu, vpa); } static inline long unregister_dtl(unsigned long cpu) { - return vpa_call(0x6, cpu, 0); + return vpa_call(H_VPA_DEREG_DTL, cpu, 0); } static inline long register_dtl(unsigned long cpu, unsigned long vpa) { - return vpa_call(0x2, cpu, vpa); + return vpa_call(H_VPA_REG_DTL, cpu, vpa); } static inline long plpar_page_set_loaned(unsigned long vpa) diff --git a/arch/powerpc/platforms/pseries/pseries.h b/arch/powerpc/platforms/pseries/pseries.h index 9a3dda0..8af71e4 100644 --- a/arch/powerpc/platforms/pseries/pseries.h +++ b/arch/powerpc/platforms/pseries/pseries.h @@ -19,7 +19,10 @@ extern void request_event_sources_irqs(struct device_node *np, #include <linux/of.h> -extern void __init fw_feature_init(const char *hypertas, unsigned long len); +extern void __init fw_hypertas_feature_init(const char *hypertas, + unsigned long len); +extern void __init fw_vec5_feature_init(const char *hypertas, + unsigned long len); struct pt_regs; diff --git a/arch/powerpc/platforms/pseries/setup.c b/arch/powerpc/platforms/pseries/setup.c index 8bcc9ca..ac932a9 100644 --- a/arch/powerpc/platforms/pseries/setup.c +++ b/arch/powerpc/platforms/pseries/setup.c @@ -628,25 +628,39 @@ static void __init pSeries_init_early(void) * Called very early, MMU is off, device-tree isn't unflattened */ -static int __init pSeries_probe_hypertas(unsigned long node, - const char *uname, int depth, - void *data) +static int __init pseries_probe_fw_features(unsigned long node, + const char *uname, int depth, + void *data) { - const char *hypertas; + const char *prop; unsigned long len; + static int hypertas_found; + static int vec5_found; - if (depth != 1 || - (strcmp(uname, "rtas") != 0 && strcmp(uname, "rtas@0") != 0)) + if (depth != 1) return 0; - hypertas = of_get_flat_dt_prop(node, "ibm,hypertas-functions", &len); - if (!hypertas) - return 1; + if (!strcmp(uname, "rtas") || !strcmp(uname, "rtas@0")) { + prop = of_get_flat_dt_prop(node, "ibm,hypertas-functions", + &len); + if (prop) { + powerpc_firmware_features |= FW_FEATURE_LPAR; + fw_hypertas_feature_init(prop, len); + } - powerpc_firmware_features |= FW_FEATURE_LPAR; - fw_feature_init(hypertas, len); + hypertas_found = 1; + } - return 1; + if (!strcmp(uname, "chosen")) { + prop = of_get_flat_dt_prop(node, "ibm,architecture-vec-5", + &len); + if (prop) + fw_vec5_feature_init(prop, len); + + vec5_found = 1; + } + + return hypertas_found && vec5_found; } static int __init pSeries_probe(void) @@ -669,7 +683,7 @@ static int __init pSeries_probe(void) pr_debug("pSeries detected, looking for LPAR capability...\n"); /* Now try to figure out if we are running on LPAR */ - of_scan_flat_dt(pSeries_probe_hypertas, NULL); + of_scan_flat_dt(pseries_probe_fw_features, NULL); if (firmware_has_feature(FW_FEATURE_LPAR)) hpte_init_lpar(); diff --git a/arch/powerpc/platforms/wsp/Kconfig b/arch/powerpc/platforms/wsp/Kconfig index 79d2225..422a175 100644 --- a/arch/powerpc/platforms/wsp/Kconfig +++ b/arch/powerpc/platforms/wsp/Kconfig @@ -9,7 +9,6 @@ config PPC_WSP select PCI select PPC_IO_WORKAROUNDS if PCI select PPC_INDIRECT_PIO if PCI - select PPC_WSP_COPRO default n menu "WSP platform selection" @@ -29,7 +28,3 @@ config PPC_CHROMA default y endmenu - -config PPC_A2_DD2 - bool "Support for DD2 based A2/WSP systems" - depends on PPC_A2 diff --git a/arch/powerpc/sysdev/Kconfig b/arch/powerpc/sysdev/Kconfig index a84fecf..ab4cb54 100644 --- a/arch/powerpc/sysdev/Kconfig +++ b/arch/powerpc/sysdev/Kconfig @@ -19,6 +19,7 @@ config PPC_MSI_BITMAP default y if MPIC default y if FSL_PCI default y if PPC4xx_MSI + default y if POWERNV_MSI source "arch/powerpc/sysdev/xics/Kconfig" diff --git a/arch/powerpc/sysdev/rtc_cmos_setup.c b/arch/powerpc/sysdev/rtc_cmos_setup.c index 9afba92..af79e1e 100644 --- a/arch/powerpc/sysdev/rtc_cmos_setup.c +++ b/arch/powerpc/sysdev/rtc_cmos_setup.c @@ -62,10 +62,7 @@ static int __init add_rtc(void) pd = platform_device_register_simple("rtc_cmos", -1, &res[0], num_res); - if (IS_ERR(pd)) - return PTR_ERR(pd); - - return 0; + return PTR_RET(pd); } fs_initcall(add_rtc); diff --git a/arch/powerpc/sysdev/xics/icp-native.c b/arch/powerpc/sysdev/xics/icp-native.c index 48861d3..89db29d 100644 --- a/arch/powerpc/sysdev/xics/icp-native.c +++ b/arch/powerpc/sysdev/xics/icp-native.c @@ -81,7 +81,7 @@ static void icp_native_set_cpu_priority(unsigned char cppr) iosync(); } -static void icp_native_eoi(struct irq_data *d) +void icp_native_eoi(struct irq_data *d) { unsigned int hw_irq = (unsigned int)irqd_to_hwirq(d); diff --git a/arch/s390/include/asm/io.h b/arch/s390/include/asm/io.h index 27cb321..379d96e 100644 --- a/arch/s390/include/asm/io.h +++ b/arch/s390/include/asm/io.h @@ -50,10 +50,6 @@ void unxlate_dev_mem_ptr(unsigned long phys, void *addr); #define ioremap_nocache(addr, size) ioremap(addr, size) #define ioremap_wc ioremap_nocache -/* TODO: s390 cannot support io_remap_pfn_range... */ -#define io_remap_pfn_range(vma, vaddr, pfn, size, prot) \ - remap_pfn_range(vma, vaddr, pfn, size, prot) - static inline void __iomem *ioremap(unsigned long offset, unsigned long size) { return (void __iomem *) offset; diff --git a/arch/s390/include/asm/pgtable.h b/arch/s390/include/asm/pgtable.h index 4a29308..3cb47cf 100644 --- a/arch/s390/include/asm/pgtable.h +++ b/arch/s390/include/asm/pgtable.h @@ -57,6 +57,10 @@ extern unsigned long zero_page_mask; (((unsigned long)(vaddr)) &zero_page_mask)))) #define __HAVE_COLOR_ZERO_PAGE +/* TODO: s390 cannot support io_remap_pfn_range... */ +#define io_remap_pfn_range(vma, vaddr, pfn, size, prot) \ + remap_pfn_range(vma, vaddr, pfn, size, prot) + #endif /* !__ASSEMBLY__ */ /* @@ -344,6 +348,7 @@ extern unsigned long MODULES_END; #define _REGION3_ENTRY_CO 0x100 /* change-recording override */ /* Bits in the segment table entry */ +#define _SEGMENT_ENTRY_ORIGIN_LARGE ~0xfffffUL /* large page address */ #define _SEGMENT_ENTRY_ORIGIN ~0x7ffUL/* segment table origin */ #define _SEGMENT_ENTRY_RO 0x200 /* page protection bit */ #define _SEGMENT_ENTRY_INV 0x20 /* invalid segment table entry */ @@ -1531,7 +1536,8 @@ extern int s390_enable_sie(void); /* * No page table caches to initialise */ -#define pgtable_cache_init() do { } while (0) +static inline void pgtable_cache_init(void) { } +static inline void check_pgt_cache(void) { } #include <asm-generic/pgtable.h> diff --git a/arch/s390/lib/uaccess_pt.c b/arch/s390/lib/uaccess_pt.c index dff631d..466fb33 100644 --- a/arch/s390/lib/uaccess_pt.c +++ b/arch/s390/lib/uaccess_pt.c @@ -77,42 +77,69 @@ static size_t copy_in_kernel(size_t count, void __user *to, * >= -4095 (IS_ERR_VALUE(x) returns true), a fault has occured and the address * contains the (negative) exception code. */ -static __always_inline unsigned long follow_table(struct mm_struct *mm, - unsigned long addr, int write) +#ifdef CONFIG_64BIT +static unsigned long follow_table(struct mm_struct *mm, + unsigned long address, int write) { - pgd_t *pgd; - pud_t *pud; - pmd_t *pmd; - pte_t *ptep; + unsigned long *table = (unsigned long *)__pa(mm->pgd); + + switch (mm->context.asce_bits & _ASCE_TYPE_MASK) { + case _ASCE_TYPE_REGION1: + table = table + ((address >> 53) & 0x7ff); + if (unlikely(*table & _REGION_ENTRY_INV)) + return -0x39UL; + table = (unsigned long *)(*table & _REGION_ENTRY_ORIGIN); + case _ASCE_TYPE_REGION2: + table = table + ((address >> 42) & 0x7ff); + if (unlikely(*table & _REGION_ENTRY_INV)) + return -0x3aUL; + table = (unsigned long *)(*table & _REGION_ENTRY_ORIGIN); + case _ASCE_TYPE_REGION3: + table = table + ((address >> 31) & 0x7ff); + if (unlikely(*table & _REGION_ENTRY_INV)) + return -0x3bUL; + table = (unsigned long *)(*table & _REGION_ENTRY_ORIGIN); + case _ASCE_TYPE_SEGMENT: + table = table + ((address >> 20) & 0x7ff); + if (unlikely(*table & _SEGMENT_ENTRY_INV)) + return -0x10UL; + if (unlikely(*table & _SEGMENT_ENTRY_LARGE)) { + if (write && (*table & _SEGMENT_ENTRY_RO)) + return -0x04UL; + return (*table & _SEGMENT_ENTRY_ORIGIN_LARGE) + + (address & ~_SEGMENT_ENTRY_ORIGIN_LARGE); + } + table = (unsigned long *)(*table & _SEGMENT_ENTRY_ORIGIN); + } + table = table + ((address >> 12) & 0xff); + if (unlikely(*table & _PAGE_INVALID)) + return -0x11UL; + if (write && (*table & _PAGE_RO)) + return -0x04UL; + return (*table & PAGE_MASK) + (address & ~PAGE_MASK); +} - pgd = pgd_offset(mm, addr); - if (pgd_none(*pgd) || unlikely(pgd_bad(*pgd))) - return -0x3aUL; +#else /* CONFIG_64BIT */ - pud = pud_offset(pgd, addr); - if (pud_none(*pud) || unlikely(pud_bad(*pud))) - return -0x3bUL; +static unsigned long follow_table(struct mm_struct *mm, + unsigned long address, int write) +{ + unsigned long *table = (unsigned long *)__pa(mm->pgd); - pmd = pmd_offset(pud, addr); - if (pmd_none(*pmd)) + table = table + ((address >> 20) & 0x7ff); + if (unlikely(*table & _SEGMENT_ENTRY_INV)) return -0x10UL; - if (pmd_large(*pmd)) { - if (write && (pmd_val(*pmd) & _SEGMENT_ENTRY_RO)) - return -0x04UL; - return (pmd_val(*pmd) & HPAGE_MASK) + (addr & ~HPAGE_MASK); - } - if (unlikely(pmd_bad(*pmd))) - return -0x10UL; - - ptep = pte_offset_map(pmd, addr); - if (!pte_present(*ptep)) + table = (unsigned long *)(*table & _SEGMENT_ENTRY_ORIGIN); + table = table + ((address >> 12) & 0xff); + if (unlikely(*table & _PAGE_INVALID)) return -0x11UL; - if (write && (!pte_write(*ptep) || !pte_dirty(*ptep))) + if (write && (*table & _PAGE_RO)) return -0x04UL; - - return (pte_val(*ptep) & PAGE_MASK) + (addr & ~PAGE_MASK); + return (*table & PAGE_MASK) + (address & ~PAGE_MASK); } +#endif /* CONFIG_64BIT */ + static __always_inline size_t __user_copy_pt(unsigned long uaddr, void *kptr, size_t n, int write_user) { @@ -197,7 +224,7 @@ size_t copy_to_user_pt(size_t n, void __user *to, const void *from) static size_t clear_user_pt(size_t n, void __user *to) { - void *zpage = &empty_zero_page; + void *zpage = (void *) empty_zero_page; long done, size, ret; done = 0; diff --git a/arch/sh/mm/Kconfig b/arch/sh/mm/Kconfig index 5a43a87..dba285e 100644 --- a/arch/sh/mm/Kconfig +++ b/arch/sh/mm/Kconfig @@ -137,13 +137,6 @@ config ARCH_SPARSEMEM_ENABLE config ARCH_SPARSEMEM_DEFAULT def_bool y -config MAX_ACTIVE_REGIONS - int - default "6" if (CPU_SUBTYPE_SHX3 && SPARSEMEM) - default "2" if SPARSEMEM && (CPU_SUBTYPE_SH7722 || \ - CPU_SUBTYPE_SH7785) - default "1" - config ARCH_SELECT_MEMORY_MODEL def_bool y diff --git a/arch/sparc/include/asm/Kbuild b/arch/sparc/include/asm/Kbuild index e26d430..ff18e3c 100644 --- a/arch/sparc/include/asm/Kbuild +++ b/arch/sparc/include/asm/Kbuild @@ -2,11 +2,16 @@ generic-y += clkdev.h +generic-y += cputime.h generic-y += div64.h +generic-y += emergency-restart.h generic-y += exec.h generic-y += local64.h +generic-y += mutex.h generic-y += irq_regs.h generic-y += local.h generic-y += module.h +generic-y += serial.h generic-y += trace_clock.h +generic-y += types.h generic-y += word-at-a-time.h diff --git a/arch/sparc/include/asm/cputime.h b/arch/sparc/include/asm/cputime.h deleted file mode 100644 index 1a642b8..0000000 --- a/arch/sparc/include/asm/cputime.h +++ /dev/null @@ -1,6 +0,0 @@ -#ifndef __SPARC_CPUTIME_H -#define __SPARC_CPUTIME_H - -#include <asm-generic/cputime.h> - -#endif /* __SPARC_CPUTIME_H */ diff --git a/arch/sparc/include/asm/emergency-restart.h b/arch/sparc/include/asm/emergency-restart.h deleted file mode 100644 index 108d8c4..0000000 --- a/arch/sparc/include/asm/emergency-restart.h +++ /dev/null @@ -1,6 +0,0 @@ -#ifndef _ASM_EMERGENCY_RESTART_H -#define _ASM_EMERGENCY_RESTART_H - -#include <asm-generic/emergency-restart.h> - -#endif /* _ASM_EMERGENCY_RESTART_H */ diff --git a/arch/sparc/include/asm/mutex.h b/arch/sparc/include/asm/mutex.h deleted file mode 100644 index 458c1f7..0000000 --- a/arch/sparc/include/asm/mutex.h +++ /dev/null @@ -1,9 +0,0 @@ -/* - * Pull in the generic implementation for the mutex fastpath. - * - * TODO: implement optimized primitives instead, or leave the generic - * implementation in place, or pick the atomic_xchg() based generic - * implementation. (see asm-generic/mutex-xchg.h for details) - */ - -#include <asm-generic/mutex-dec.h> diff --git a/arch/sparc/include/asm/pgtable_64.h b/arch/sparc/include/asm/pgtable_64.h index 08fcce90..7619f2f 100644 --- a/arch/sparc/include/asm/pgtable_64.h +++ b/arch/sparc/include/asm/pgtable_64.h @@ -915,6 +915,7 @@ static inline int io_remap_pfn_range(struct vm_area_struct *vma, return remap_pfn_range(vma, from, phys_base >> PAGE_SHIFT, size, prot); } +#include <asm/tlbflush.h> #include <asm-generic/pgtable.h> /* We provide our own get_unmapped_area to cope with VA holes and diff --git a/arch/sparc/include/asm/serial.h b/arch/sparc/include/asm/serial.h deleted file mode 100644 index f90d61c..0000000 --- a/arch/sparc/include/asm/serial.h +++ /dev/null @@ -1,6 +0,0 @@ -#ifndef __SPARC_SERIAL_H -#define __SPARC_SERIAL_H - -#define BASE_BAUD ( 1843200 / 16 ) - -#endif /* __SPARC_SERIAL_H */ diff --git a/arch/sparc/include/asm/smp_32.h b/arch/sparc/include/asm/smp_32.h index b73da3c..3c8917f 100644 --- a/arch/sparc/include/asm/smp_32.h +++ b/arch/sparc/include/asm/smp_32.h @@ -36,7 +36,6 @@ typedef void (*smpfunc_t)(unsigned long, unsigned long, unsigned long, unsigned long, unsigned long); void cpu_panic(void); -extern void smp4m_irq_rotate(int cpu); /* * General functions that each host system must provide. @@ -46,7 +45,6 @@ void sun4m_init_smp(void); void sun4d_init_smp(void); void smp_callin(void); -void smp_boot_cpus(void); void smp_store_cpu_info(int); void smp_resched_interrupt(void); @@ -107,9 +105,6 @@ extern int hard_smp_processor_id(void); #define raw_smp_processor_id() (current_thread_info()->cpu) -#define prof_multiplier(__cpu) cpu_data(__cpu).multiplier -#define prof_counter(__cpu) cpu_data(__cpu).counter - void smp_setup_cpu_possible_map(void); #endif /* !(__ASSEMBLY__) */ diff --git a/arch/sparc/include/asm/switch_to_64.h b/arch/sparc/include/asm/switch_to_64.h index cad36f5..c7de332 100644 --- a/arch/sparc/include/asm/switch_to_64.h +++ b/arch/sparc/include/asm/switch_to_64.h @@ -18,8 +18,7 @@ do { \ * and 2 stores in this critical code path. -DaveM */ #define switch_to(prev, next, last) \ -do { flush_tlb_pending(); \ - save_and_clear_fpu(); \ +do { save_and_clear_fpu(); \ /* If you are tempted to conditionalize the following */ \ /* so that ASI is only written if it changes, think again. */ \ __asm__ __volatile__("wr %%g0, %0, %%asi" \ diff --git a/arch/sparc/include/asm/tlbflush_64.h b/arch/sparc/include/asm/tlbflush_64.h index 2ef4634..f0d6a97 100644 --- a/arch/sparc/include/asm/tlbflush_64.h +++ b/arch/sparc/include/asm/tlbflush_64.h @@ -11,24 +11,40 @@ struct tlb_batch { struct mm_struct *mm; unsigned long tlb_nr; + unsigned long active; unsigned long vaddrs[TLB_BATCH_NR]; }; extern void flush_tsb_kernel_range(unsigned long start, unsigned long end); extern void flush_tsb_user(struct tlb_batch *tb); +extern void flush_tsb_user_page(struct mm_struct *mm, unsigned long vaddr); /* TLB flush operations. */ -extern void flush_tlb_pending(void); +static inline void flush_tlb_mm(struct mm_struct *mm) +{ +} + +static inline void flush_tlb_page(struct vm_area_struct *vma, + unsigned long vmaddr) +{ +} + +static inline void flush_tlb_range(struct vm_area_struct *vma, + unsigned long start, unsigned long end) +{ +} + +#define __HAVE_ARCH_ENTER_LAZY_MMU_MODE -#define flush_tlb_range(vma,start,end) \ - do { (void)(start); flush_tlb_pending(); } while (0) -#define flush_tlb_page(vma,addr) flush_tlb_pending() -#define flush_tlb_mm(mm) flush_tlb_pending() +extern void flush_tlb_pending(void); +extern void arch_enter_lazy_mmu_mode(void); +extern void arch_leave_lazy_mmu_mode(void); +#define arch_flush_lazy_mmu_mode() do {} while (0) /* Local cpu only. */ extern void __flush_tlb_all(void); - +extern void __flush_tlb_page(unsigned long context, unsigned long vaddr); extern void __flush_tlb_kernel_range(unsigned long start, unsigned long end); #ifndef CONFIG_SMP @@ -38,15 +54,24 @@ do { flush_tsb_kernel_range(start,end); \ __flush_tlb_kernel_range(start,end); \ } while (0) +static inline void global_flush_tlb_page(struct mm_struct *mm, unsigned long vaddr) +{ + __flush_tlb_page(CTX_HWBITS(mm->context), vaddr); +} + #else /* CONFIG_SMP */ extern void smp_flush_tlb_kernel_range(unsigned long start, unsigned long end); +extern void smp_flush_tlb_page(struct mm_struct *mm, unsigned long vaddr); #define flush_tlb_kernel_range(start, end) \ do { flush_tsb_kernel_range(start,end); \ smp_flush_tlb_kernel_range(start, end); \ } while (0) +#define global_flush_tlb_page(mm, vaddr) \ + smp_flush_tlb_page(mm, vaddr) + #endif /* ! CONFIG_SMP */ #endif /* _SPARC64_TLBFLUSH_H */ diff --git a/arch/sparc/include/uapi/asm/Kbuild b/arch/sparc/include/uapi/asm/Kbuild index ce175af..b5843ee 100644 --- a/arch/sparc/include/uapi/asm/Kbuild +++ b/arch/sparc/include/uapi/asm/Kbuild @@ -44,7 +44,6 @@ header-y += swab.h header-y += termbits.h header-y += termios.h header-y += traps.h -header-y += types.h header-y += uctx.h header-y += unistd.h header-y += utrap.h diff --git a/arch/sparc/include/uapi/asm/types.h b/arch/sparc/include/uapi/asm/types.h deleted file mode 100644 index 383d156..0000000 --- a/arch/sparc/include/uapi/asm/types.h +++ /dev/null @@ -1,17 +0,0 @@ -#ifndef _SPARC_TYPES_H -#define _SPARC_TYPES_H -/* - * This file is never included by application software unless - * explicitly requested (e.g., via linux/types.h) in which case the - * application is Linux specific so (user-) name space pollution is - * not a major issue. However, for interoperability, libraries still - * need to be careful to avoid a name clashes. - */ - -#if defined(__sparc__) - -#include <asm-generic/int-ll64.h> - -#endif /* defined(__sparc__) */ - -#endif /* defined(_SPARC_TYPES_H) */ diff --git a/arch/sparc/kernel/smp_64.c b/arch/sparc/kernel/smp_64.c index 537eb66..ca64d2a 100644 --- a/arch/sparc/kernel/smp_64.c +++ b/arch/sparc/kernel/smp_64.c @@ -849,7 +849,7 @@ void smp_tsb_sync(struct mm_struct *mm) } extern unsigned long xcall_flush_tlb_mm; -extern unsigned long xcall_flush_tlb_pending; +extern unsigned long xcall_flush_tlb_page; extern unsigned long xcall_flush_tlb_kernel_range; extern unsigned long xcall_fetch_glob_regs; extern unsigned long xcall_fetch_glob_pmu; @@ -1074,23 +1074,56 @@ local_flush_and_out: put_cpu(); } +struct tlb_pending_info { + unsigned long ctx; + unsigned long nr; + unsigned long *vaddrs; +}; + +static void tlb_pending_func(void *info) +{ + struct tlb_pending_info *t = info; + + __flush_tlb_pending(t->ctx, t->nr, t->vaddrs); +} + void smp_flush_tlb_pending(struct mm_struct *mm, unsigned long nr, unsigned long *vaddrs) { u32 ctx = CTX_HWBITS(mm->context); + struct tlb_pending_info info; int cpu = get_cpu(); + info.ctx = ctx; + info.nr = nr; + info.vaddrs = vaddrs; + if (mm == current->mm && atomic_read(&mm->mm_users) == 1) cpumask_copy(mm_cpumask(mm), cpumask_of(cpu)); else - smp_cross_call_masked(&xcall_flush_tlb_pending, - ctx, nr, (unsigned long) vaddrs, - mm_cpumask(mm)); + smp_call_function_many(mm_cpumask(mm), tlb_pending_func, + &info, 1); __flush_tlb_pending(ctx, nr, vaddrs); put_cpu(); } +void smp_flush_tlb_page(struct mm_struct *mm, unsigned long vaddr) +{ + unsigned long context = CTX_HWBITS(mm->context); + int cpu = get_cpu(); + + if (mm == current->mm && atomic_read(&mm->mm_users) == 1) + cpumask_copy(mm_cpumask(mm), cpumask_of(cpu)); + else + smp_cross_call_masked(&xcall_flush_tlb_page, + context, vaddr, 0, + mm_cpumask(mm)); + __flush_tlb_page(context, vaddr); + + put_cpu(); +} + void smp_flush_tlb_kernel_range(unsigned long start, unsigned long end) { start &= PAGE_MASK; diff --git a/arch/sparc/lib/bitext.c b/arch/sparc/lib/bitext.c index 48d00e7..8ec4e9c 100644 --- a/arch/sparc/lib/bitext.c +++ b/arch/sparc/lib/bitext.c @@ -119,11 +119,7 @@ void bit_map_clear(struct bit_map *t, int offset, int len) void bit_map_init(struct bit_map *t, unsigned long *map, int size) { - - if ((size & 07) != 0) - BUG(); - memset(map, 0, size>>3); - + bitmap_zero(map, size); memset(t, 0, sizeof *t); spin_lock_init(&t->lock); t->map = map; diff --git a/arch/sparc/mm/iommu.c b/arch/sparc/mm/iommu.c index 0f4f719..28f96f2 100644 --- a/arch/sparc/mm/iommu.c +++ b/arch/sparc/mm/iommu.c @@ -34,7 +34,7 @@ #define IOMMU_RNGE IOMMU_RNGE_256MB #define IOMMU_START 0xF0000000 #define IOMMU_WINSIZE (256*1024*1024U) -#define IOMMU_NPTES (IOMMU_WINSIZE/PAGE_SIZE) /* 64K PTEs, 265KB */ +#define IOMMU_NPTES (IOMMU_WINSIZE/PAGE_SIZE) /* 64K PTEs, 256KB */ #define IOMMU_ORDER 6 /* 4096 * (1<<6) */ /* srmmu.c */ diff --git a/arch/sparc/mm/srmmu.c b/arch/sparc/mm/srmmu.c index c38bb72..036c279 100644 --- a/arch/sparc/mm/srmmu.c +++ b/arch/sparc/mm/srmmu.c @@ -280,7 +280,9 @@ static void __init srmmu_nocache_init(void) SRMMU_NOCACHE_ALIGN_MAX, 0UL); memset(srmmu_nocache_pool, 0, srmmu_nocache_size); - srmmu_nocache_bitmap = __alloc_bootmem(bitmap_bits >> 3, SMP_CACHE_BYTES, 0UL); + srmmu_nocache_bitmap = + __alloc_bootmem(BITS_TO_LONGS(bitmap_bits) * sizeof(long), + SMP_CACHE_BYTES, 0UL); bit_map_init(&srmmu_nocache_map, srmmu_nocache_bitmap, bitmap_bits); srmmu_swapper_pg_dir = __srmmu_get_nocache(SRMMU_PGD_TABLE_SIZE, SRMMU_PGD_TABLE_SIZE); diff --git a/arch/sparc/mm/tlb.c b/arch/sparc/mm/tlb.c index ba6ae7f..272aa4f 100644 --- a/arch/sparc/mm/tlb.c +++ b/arch/sparc/mm/tlb.c @@ -24,11 +24,17 @@ static DEFINE_PER_CPU(struct tlb_batch, tlb_batch); void flush_tlb_pending(void) { struct tlb_batch *tb = &get_cpu_var(tlb_batch); + struct mm_struct *mm = tb->mm; - if (tb->tlb_nr) { - flush_tsb_user(tb); + if (!tb->tlb_nr) + goto out; - if (CTX_VALID(tb->mm->context)) { + flush_tsb_user(tb); + + if (CTX_VALID(mm->context)) { + if (tb->tlb_nr == 1) { + global_flush_tlb_page(mm, tb->vaddrs[0]); + } else { #ifdef CONFIG_SMP smp_flush_tlb_pending(tb->mm, tb->tlb_nr, &tb->vaddrs[0]); @@ -37,12 +43,30 @@ void flush_tlb_pending(void) tb->tlb_nr, &tb->vaddrs[0]); #endif } - tb->tlb_nr = 0; } + tb->tlb_nr = 0; + +out: put_cpu_var(tlb_batch); } +void arch_enter_lazy_mmu_mode(void) +{ + struct tlb_batch *tb = &__get_cpu_var(tlb_batch); + + tb->active = 1; +} + +void arch_leave_lazy_mmu_mode(void) +{ + struct tlb_batch *tb = &__get_cpu_var(tlb_batch); + + if (tb->tlb_nr) + flush_tlb_pending(); + tb->active = 0; +} + static void tlb_batch_add_one(struct mm_struct *mm, unsigned long vaddr, bool exec) { @@ -60,6 +84,12 @@ static void tlb_batch_add_one(struct mm_struct *mm, unsigned long vaddr, nr = 0; } + if (!tb->active) { + global_flush_tlb_page(mm, vaddr); + flush_tsb_user_page(mm, vaddr); + return; + } + if (nr == 0) tb->mm = mm; diff --git a/arch/sparc/mm/tsb.c b/arch/sparc/mm/tsb.c index 428982b..2cc3bce 100644 --- a/arch/sparc/mm/tsb.c +++ b/arch/sparc/mm/tsb.c @@ -7,11 +7,10 @@ #include <linux/preempt.h> #include <linux/slab.h> #include <asm/page.h> -#include <asm/tlbflush.h> -#include <asm/tlb.h> -#include <asm/mmu_context.h> #include <asm/pgtable.h> +#include <asm/mmu_context.h> #include <asm/tsb.h> +#include <asm/tlb.h> #include <asm/oplib.h> extern struct tsb swapper_tsb[KERNEL_TSB_NENTRIES]; @@ -46,23 +45,27 @@ void flush_tsb_kernel_range(unsigned long start, unsigned long end) } } -static void __flush_tsb_one(struct tlb_batch *tb, unsigned long hash_shift, - unsigned long tsb, unsigned long nentries) +static void __flush_tsb_one_entry(unsigned long tsb, unsigned long v, + unsigned long hash_shift, + unsigned long nentries) { - unsigned long i; + unsigned long tag, ent, hash; - for (i = 0; i < tb->tlb_nr; i++) { - unsigned long v = tb->vaddrs[i]; - unsigned long tag, ent, hash; + v &= ~0x1UL; + hash = tsb_hash(v, hash_shift, nentries); + ent = tsb + (hash * sizeof(struct tsb)); + tag = (v >> 22UL); - v &= ~0x1UL; + tsb_flush(ent, tag); +} - hash = tsb_hash(v, hash_shift, nentries); - ent = tsb + (hash * sizeof(struct tsb)); - tag = (v >> 22UL); +static void __flush_tsb_one(struct tlb_batch *tb, unsigned long hash_shift, + unsigned long tsb, unsigned long nentries) +{ + unsigned long i; - tsb_flush(ent, tag); - } + for (i = 0; i < tb->tlb_nr; i++) + __flush_tsb_one_entry(tsb, tb->vaddrs[i], hash_shift, nentries); } void flush_tsb_user(struct tlb_batch *tb) @@ -90,6 +93,30 @@ void flush_tsb_user(struct tlb_batch *tb) spin_unlock_irqrestore(&mm->context.lock, flags); } +void flush_tsb_user_page(struct mm_struct *mm, unsigned long vaddr) +{ + unsigned long nentries, base, flags; + + spin_lock_irqsave(&mm->context.lock, flags); + + base = (unsigned long) mm->context.tsb_block[MM_TSB_BASE].tsb; + nentries = mm->context.tsb_block[MM_TSB_BASE].tsb_nentries; + if (tlb_type == cheetah_plus || tlb_type == hypervisor) + base = __pa(base); + __flush_tsb_one_entry(base, vaddr, PAGE_SHIFT, nentries); + +#if defined(CONFIG_HUGETLB_PAGE) || defined(CONFIG_TRANSPARENT_HUGEPAGE) + if (mm->context.tsb_block[MM_TSB_HUGE].tsb) { + base = (unsigned long) mm->context.tsb_block[MM_TSB_HUGE].tsb; + nentries = mm->context.tsb_block[MM_TSB_HUGE].tsb_nentries; + if (tlb_type == cheetah_plus || tlb_type == hypervisor) + base = __pa(base); + __flush_tsb_one_entry(base, vaddr, HPAGE_SHIFT, nentries); + } +#endif + spin_unlock_irqrestore(&mm->context.lock, flags); +} + #define HV_PGSZ_IDX_BASE HV_PGSZ_IDX_8K #define HV_PGSZ_MASK_BASE HV_PGSZ_MASK_8K diff --git a/arch/sparc/mm/ultra.S b/arch/sparc/mm/ultra.S index f8e13d4..432aa0c 100644 --- a/arch/sparc/mm/ultra.S +++ b/arch/sparc/mm/ultra.S @@ -53,6 +53,33 @@ __flush_tlb_mm: /* 18 insns */ nop .align 32 + .globl __flush_tlb_page +__flush_tlb_page: /* 22 insns */ + /* %o0 = context, %o1 = vaddr */ + rdpr %pstate, %g7 + andn %g7, PSTATE_IE, %g2 + wrpr %g2, %pstate + mov SECONDARY_CONTEXT, %o4 + ldxa [%o4] ASI_DMMU, %g2 + stxa %o0, [%o4] ASI_DMMU + andcc %o1, 1, %g0 + andn %o1, 1, %o3 + be,pn %icc, 1f + or %o3, 0x10, %o3 + stxa %g0, [%o3] ASI_IMMU_DEMAP +1: stxa %g0, [%o3] ASI_DMMU_DEMAP + membar #Sync + stxa %g2, [%o4] ASI_DMMU + sethi %hi(KERNBASE), %o4 + flush %o4 + retl + wrpr %g7, 0x0, %pstate + nop + nop + nop + nop + + .align 32 .globl __flush_tlb_pending __flush_tlb_pending: /* 26 insns */ /* %o0 = context, %o1 = nr, %o2 = vaddrs[] */ @@ -203,6 +230,31 @@ __cheetah_flush_tlb_mm: /* 19 insns */ retl wrpr %g7, 0x0, %pstate +__cheetah_flush_tlb_page: /* 22 insns */ + /* %o0 = context, %o1 = vaddr */ + rdpr %pstate, %g7 + andn %g7, PSTATE_IE, %g2 + wrpr %g2, 0x0, %pstate + wrpr %g0, 1, %tl + mov PRIMARY_CONTEXT, %o4 + ldxa [%o4] ASI_DMMU, %g2 + srlx %g2, CTX_PGSZ1_NUC_SHIFT, %o3 + sllx %o3, CTX_PGSZ1_NUC_SHIFT, %o3 + or %o0, %o3, %o0 /* Preserve nucleus page size fields */ + stxa %o0, [%o4] ASI_DMMU + andcc %o1, 1, %g0 + be,pn %icc, 1f + andn %o1, 1, %o3 + stxa %g0, [%o3] ASI_IMMU_DEMAP +1: stxa %g0, [%o3] ASI_DMMU_DEMAP + membar #Sync + stxa %g2, [%o4] ASI_DMMU + sethi %hi(KERNBASE), %o4 + flush %o4 + wrpr %g0, 0, %tl + retl + wrpr %g7, 0x0, %pstate + __cheetah_flush_tlb_pending: /* 27 insns */ /* %o0 = context, %o1 = nr, %o2 = vaddrs[] */ rdpr %pstate, %g7 @@ -269,6 +321,20 @@ __hypervisor_flush_tlb_mm: /* 10 insns */ retl nop +__hypervisor_flush_tlb_page: /* 11 insns */ + /* %o0 = context, %o1 = vaddr */ + mov %o0, %g2 + mov %o1, %o0 /* ARG0: vaddr + IMMU-bit */ + mov %g2, %o1 /* ARG1: mmu context */ + mov HV_MMU_ALL, %o2 /* ARG2: flags */ + srlx %o0, PAGE_SHIFT, %o0 + sllx %o0, PAGE_SHIFT, %o0 + ta HV_MMU_UNMAP_ADDR_TRAP + brnz,pn %o0, __hypervisor_tlb_tl0_error + mov HV_MMU_UNMAP_ADDR_TRAP, %o1 + retl + nop + __hypervisor_flush_tlb_pending: /* 16 insns */ /* %o0 = context, %o1 = nr, %o2 = vaddrs[] */ sllx %o1, 3, %g1 @@ -339,6 +405,13 @@ cheetah_patch_cachetlbops: call tlb_patch_one mov 19, %o2 + sethi %hi(__flush_tlb_page), %o0 + or %o0, %lo(__flush_tlb_page), %o0 + sethi %hi(__cheetah_flush_tlb_page), %o1 + or %o1, %lo(__cheetah_flush_tlb_page), %o1 + call tlb_patch_one + mov 22, %o2 + sethi %hi(__flush_tlb_pending), %o0 or %o0, %lo(__flush_tlb_pending), %o0 sethi %hi(__cheetah_flush_tlb_pending), %o1 @@ -397,10 +470,9 @@ xcall_flush_tlb_mm: /* 21 insns */ nop nop - .globl xcall_flush_tlb_pending -xcall_flush_tlb_pending: /* 21 insns */ - /* %g5=context, %g1=nr, %g7=vaddrs[] */ - sllx %g1, 3, %g1 + .globl xcall_flush_tlb_page +xcall_flush_tlb_page: /* 17 insns */ + /* %g5=context, %g1=vaddr */ mov PRIMARY_CONTEXT, %g4 ldxa [%g4] ASI_DMMU, %g2 srlx %g2, CTX_PGSZ1_NUC_SHIFT, %g4 @@ -408,20 +480,16 @@ xcall_flush_tlb_pending: /* 21 insns */ or %g5, %g4, %g5 mov PRIMARY_CONTEXT, %g4 stxa %g5, [%g4] ASI_DMMU -1: sub %g1, (1 << 3), %g1 - ldx [%g7 + %g1], %g5 - andcc %g5, 0x1, %g0 + andcc %g1, 0x1, %g0 be,pn %icc, 2f - - andn %g5, 0x1, %g5 + andn %g1, 0x1, %g5 stxa %g0, [%g5] ASI_IMMU_DEMAP 2: stxa %g0, [%g5] ASI_DMMU_DEMAP membar #Sync - brnz,pt %g1, 1b - nop stxa %g2, [%g4] ASI_DMMU retry nop + nop .globl xcall_flush_tlb_kernel_range xcall_flush_tlb_kernel_range: /* 25 insns */ @@ -656,15 +724,13 @@ __hypervisor_xcall_flush_tlb_mm: /* 21 insns */ membar #Sync retry - .globl __hypervisor_xcall_flush_tlb_pending -__hypervisor_xcall_flush_tlb_pending: /* 21 insns */ - /* %g5=ctx, %g1=nr, %g7=vaddrs[], %g2,%g3,%g4,g6=scratch */ - sllx %g1, 3, %g1 + .globl __hypervisor_xcall_flush_tlb_page +__hypervisor_xcall_flush_tlb_page: /* 17 insns */ + /* %g5=ctx, %g1=vaddr */ mov %o0, %g2 mov %o1, %g3 mov %o2, %g4 -1: sub %g1, (1 << 3), %g1 - ldx [%g7 + %g1], %o0 /* ARG0: virtual address */ + mov %g1, %o0 /* ARG0: virtual address */ mov %g5, %o1 /* ARG1: mmu context */ mov HV_MMU_ALL, %o2 /* ARG2: flags */ srlx %o0, PAGE_SHIFT, %o0 @@ -673,8 +739,6 @@ __hypervisor_xcall_flush_tlb_pending: /* 21 insns */ mov HV_MMU_UNMAP_ADDR_TRAP, %g6 brnz,a,pn %o0, __hypervisor_tlb_xcall_error mov %o0, %g5 - brnz,pt %g1, 1b - nop mov %g2, %o0 mov %g3, %o1 mov %g4, %o2 @@ -757,6 +821,13 @@ hypervisor_patch_cachetlbops: call tlb_patch_one mov 10, %o2 + sethi %hi(__flush_tlb_page), %o0 + or %o0, %lo(__flush_tlb_page), %o0 + sethi %hi(__hypervisor_flush_tlb_page), %o1 + or %o1, %lo(__hypervisor_flush_tlb_page), %o1 + call tlb_patch_one + mov 11, %o2 + sethi %hi(__flush_tlb_pending), %o0 or %o0, %lo(__flush_tlb_pending), %o0 sethi %hi(__hypervisor_flush_tlb_pending), %o1 @@ -788,12 +859,12 @@ hypervisor_patch_cachetlbops: call tlb_patch_one mov 21, %o2 - sethi %hi(xcall_flush_tlb_pending), %o0 - or %o0, %lo(xcall_flush_tlb_pending), %o0 - sethi %hi(__hypervisor_xcall_flush_tlb_pending), %o1 - or %o1, %lo(__hypervisor_xcall_flush_tlb_pending), %o1 + sethi %hi(xcall_flush_tlb_page), %o0 + or %o0, %lo(xcall_flush_tlb_page), %o0 + sethi %hi(__hypervisor_xcall_flush_tlb_page), %o1 + or %o1, %lo(__hypervisor_xcall_flush_tlb_page), %o1 call tlb_patch_one - mov 21, %o2 + mov 17, %o2 sethi %hi(xcall_flush_tlb_kernel_range), %o0 or %o0, %lo(xcall_flush_tlb_kernel_range), %o0 diff --git a/arch/tile/include/asm/irqflags.h b/arch/tile/include/asm/irqflags.h index 241c0bb..c96f9bb 100644 --- a/arch/tile/include/asm/irqflags.h +++ b/arch/tile/include/asm/irqflags.h @@ -40,7 +40,15 @@ #include <asm/percpu.h> #include <arch/spr_def.h> -/* Set and clear kernel interrupt masks. */ +/* + * Set and clear kernel interrupt masks. + * + * NOTE: __insn_mtspr() is a compiler builtin marked as a memory + * clobber. We rely on it being equivalent to a compiler barrier in + * this code since arch_local_irq_save() and friends must act as + * compiler barriers. This compiler semantic is baked into enough + * places that the compiler will maintain it going forward. + */ #if CHIP_HAS_SPLIT_INTR_MASK() #if INT_PERF_COUNT < 32 || INT_AUX_PERF_COUNT < 32 || INT_MEM_ERROR >= 32 # error Fix assumptions about which word various interrupts are in diff --git a/arch/tile/kernel/setup.c b/arch/tile/kernel/setup.c index d1e15f7..7a5aa1a 100644 --- a/arch/tile/kernel/setup.c +++ b/arch/tile/kernel/setup.c @@ -1004,15 +1004,8 @@ void __cpuinit setup_cpu(int boot) #ifdef CONFIG_BLK_DEV_INITRD -/* - * Note that the kernel can potentially support other compression - * techniques than gz, though we don't do so by default. If we ever - * decide to do so we can either look for other filename extensions, - * or just allow a file with this name to be compressed with an - * arbitrary compressor (somewhat counterintuitively). - */ static int __initdata set_initramfs_file; -static char __initdata initramfs_file[128] = "initramfs.cpio.gz"; +static char __initdata initramfs_file[128] = "initramfs"; static int __init setup_initramfs_file(char *str) { @@ -1026,9 +1019,9 @@ static int __init setup_initramfs_file(char *str) early_param("initramfs_file", setup_initramfs_file); /* - * We look for an "initramfs.cpio.gz" file in the hvfs. - * If there is one, we allocate some memory for it and it will be - * unpacked to the initramfs. + * We look for a file called "initramfs" in the hvfs. If there is one, we + * allocate some memory for it and it will be unpacked to the initramfs. + * If it's compressed, the initd code will uncompress it first. */ static void __init load_hv_initrd(void) { @@ -1038,10 +1031,16 @@ static void __init load_hv_initrd(void) fd = hv_fs_findfile((HV_VirtAddr) initramfs_file); if (fd == HV_ENOENT) { - if (set_initramfs_file) + if (set_initramfs_file) { pr_warning("No such hvfs initramfs file '%s'\n", initramfs_file); - return; + return; + } else { + /* Try old backwards-compatible name. */ + fd = hv_fs_findfile((HV_VirtAddr)"initramfs.cpio.gz"); + if (fd == HV_ENOENT) + return; + } } BUG_ON(fd < 0); stat = hv_fs_fstat(fd); diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig index 70c0f3d..15b5cef 100644 --- a/arch/x86/Kconfig +++ b/arch/x86/Kconfig @@ -1549,6 +1549,7 @@ config X86_SMAP config EFI bool "EFI runtime service support" depends on ACPI + select UCS2_STRING ---help--- This enables the kernel to use EFI runtime services that are available (such as the EFI variable services). diff --git a/arch/x86/boot/compressed/Makefile b/arch/x86/boot/compressed/Makefile index 8a84501..5ef205c 100644 --- a/arch/x86/boot/compressed/Makefile +++ b/arch/x86/boot/compressed/Makefile @@ -4,7 +4,7 @@ # create a compressed vmlinux image from the original vmlinux # -targets := vmlinux.lds vmlinux vmlinux.bin vmlinux.bin.gz vmlinux.bin.bz2 vmlinux.bin.lzma vmlinux.bin.xz vmlinux.bin.lzo head_$(BITS).o misc.o string.o cmdline.o early_serial_console.o piggy.o +targets := vmlinux vmlinux.bin vmlinux.bin.gz vmlinux.bin.bz2 vmlinux.bin.lzma vmlinux.bin.xz vmlinux.bin.lzo KBUILD_CFLAGS := -m$(BITS) -D__KERNEL__ $(LINUX_INCLUDE) -O2 KBUILD_CFLAGS += -fno-strict-aliasing -fPIC @@ -29,7 +29,6 @@ VMLINUX_OBJS = $(obj)/vmlinux.lds $(obj)/head_$(BITS).o $(obj)/misc.o \ $(obj)/piggy.o $(obj)/eboot.o: KBUILD_CFLAGS += -fshort-wchar -mno-red-zone -$(obj)/efi_stub_$(BITS).o: KBUILD_CLFAGS += -fshort-wchar -mno-red-zone ifeq ($(CONFIG_EFI_STUB), y) VMLINUX_OBJS += $(obj)/eboot.o $(obj)/efi_stub_$(BITS).o @@ -43,7 +42,7 @@ OBJCOPYFLAGS_vmlinux.bin := -R .comment -S $(obj)/vmlinux.bin: vmlinux FORCE $(call if_changed,objcopy) -targets += vmlinux.bin.all vmlinux.relocs +targets += $(patsubst $(obj)/%,%,$(VMLINUX_OBJS)) vmlinux.bin.all vmlinux.relocs CMD_RELOCS = arch/x86/tools/relocs quiet_cmd_relocs = RELOCS $@ diff --git a/arch/x86/boot/compressed/eboot.c b/arch/x86/boot/compressed/eboot.c index c205035..8615f75 100644 --- a/arch/x86/boot/compressed/eboot.c +++ b/arch/x86/boot/compressed/eboot.c @@ -251,6 +251,51 @@ static void find_bits(unsigned long mask, u8 *pos, u8 *size) *size = len; } +static efi_status_t setup_efi_vars(struct boot_params *params) +{ + struct setup_data *data; + struct efi_var_bootdata *efidata; + u64 store_size, remaining_size, var_size; + efi_status_t status; + + if (!sys_table->runtime->query_variable_info) + return EFI_UNSUPPORTED; + + data = (struct setup_data *)(unsigned long)params->hdr.setup_data; + + while (data && data->next) + data = (struct setup_data *)(unsigned long)data->next; + + status = efi_call_phys4(sys_table->runtime->query_variable_info, + EFI_VARIABLE_NON_VOLATILE | + EFI_VARIABLE_BOOTSERVICE_ACCESS | + EFI_VARIABLE_RUNTIME_ACCESS, &store_size, + &remaining_size, &var_size); + + if (status != EFI_SUCCESS) + return status; + + status = efi_call_phys3(sys_table->boottime->allocate_pool, + EFI_LOADER_DATA, sizeof(*efidata), &efidata); + + if (status != EFI_SUCCESS) + return status; + + efidata->data.type = SETUP_EFI_VARS; + efidata->data.len = sizeof(struct efi_var_bootdata) - + sizeof(struct setup_data); + efidata->data.next = 0; + efidata->store_size = store_size; + efidata->remaining_size = remaining_size; + efidata->max_var_size = var_size; + + if (data) + data->next = (unsigned long)efidata; + else + params->hdr.setup_data = (unsigned long)efidata; + +} + static efi_status_t setup_efi_pci(struct boot_params *params) { efi_pci_io_protocol *pci; @@ -1157,6 +1202,8 @@ struct boot_params *efi_main(void *handle, efi_system_table_t *_table, setup_graphics(boot_params); + setup_efi_vars(boot_params); + setup_efi_pci(boot_params); status = efi_call_phys3(sys_table->boottime->allocate_pool, diff --git a/arch/x86/include/asm/efi.h b/arch/x86/include/asm/efi.h index 60c89f3..2fb5d58 100644 --- a/arch/x86/include/asm/efi.h +++ b/arch/x86/include/asm/efi.h @@ -102,6 +102,13 @@ extern void efi_call_phys_epilog(void); extern void efi_unmap_memmap(void); extern void efi_memory_uc(u64 addr, unsigned long size); +struct efi_var_bootdata { + struct setup_data data; + u64 store_size; + u64 remaining_size; + u64 max_var_size; +}; + #ifdef CONFIG_EFI static inline bool efi_is_native(void) diff --git a/arch/x86/include/asm/paravirt.h b/arch/x86/include/asm/paravirt.h index 5edd174..7361e47 100644 --- a/arch/x86/include/asm/paravirt.h +++ b/arch/x86/include/asm/paravirt.h @@ -703,7 +703,10 @@ static inline void arch_leave_lazy_mmu_mode(void) PVOP_VCALL0(pv_mmu_ops.lazy_mode.leave); } -void arch_flush_lazy_mmu_mode(void); +static inline void arch_flush_lazy_mmu_mode(void) +{ + PVOP_VCALL0(pv_mmu_ops.lazy_mode.flush); +} static inline void __set_fixmap(unsigned /* enum fixed_addresses */ idx, phys_addr_t phys, pgprot_t flags) diff --git a/arch/x86/include/asm/paravirt_types.h b/arch/x86/include/asm/paravirt_types.h index 142236e..b3b0ec1 100644 --- a/arch/x86/include/asm/paravirt_types.h +++ b/arch/x86/include/asm/paravirt_types.h @@ -91,6 +91,7 @@ struct pv_lazy_ops { /* Set deferred update mode, used for batching operations. */ void (*enter)(void); void (*leave)(void); + void (*flush)(void); }; struct pv_time_ops { @@ -679,6 +680,7 @@ void paravirt_end_context_switch(struct task_struct *next); void paravirt_enter_lazy_mmu(void); void paravirt_leave_lazy_mmu(void); +void paravirt_flush_lazy_mmu(void); void _paravirt_nop(void); u32 _paravirt_ident_32(u32); diff --git a/arch/x86/include/asm/syscall.h b/arch/x86/include/asm/syscall.h index 1ace47b..2e188d6 100644 --- a/arch/x86/include/asm/syscall.h +++ b/arch/x86/include/asm/syscall.h @@ -29,13 +29,13 @@ extern const unsigned long sys_call_table[]; */ static inline int syscall_get_nr(struct task_struct *task, struct pt_regs *regs) { - return regs->orig_ax & __SYSCALL_MASK; + return regs->orig_ax; } static inline void syscall_rollback(struct task_struct *task, struct pt_regs *regs) { - regs->ax = regs->orig_ax & __SYSCALL_MASK; + regs->ax = regs->orig_ax; } static inline long syscall_get_error(struct task_struct *task, diff --git a/arch/x86/include/asm/tlb.h b/arch/x86/include/asm/tlb.h index 4fef207..c779730 100644 --- a/arch/x86/include/asm/tlb.h +++ b/arch/x86/include/asm/tlb.h @@ -7,7 +7,7 @@ #define tlb_flush(tlb) \ { \ - if (tlb->fullmm == 0) \ + if (!tlb->fullmm && !tlb->need_flush_all) \ flush_tlb_mm_range(tlb->mm, tlb->start, tlb->end, 0UL); \ else \ flush_tlb_mm_range(tlb->mm, 0UL, TLB_FLUSH_ALL, 0UL); \ diff --git a/arch/x86/include/uapi/asm/bootparam.h b/arch/x86/include/uapi/asm/bootparam.h index c15ddaf..0874424 100644 --- a/arch/x86/include/uapi/asm/bootparam.h +++ b/arch/x86/include/uapi/asm/bootparam.h @@ -6,6 +6,7 @@ #define SETUP_E820_EXT 1 #define SETUP_DTB 2 #define SETUP_PCI 3 +#define SETUP_EFI_VARS 4 /* ram_size flags */ #define RAMDISK_IMAGE_START_MASK 0x07FF diff --git a/arch/x86/kernel/cpu/mshyperv.c b/arch/x86/kernel/cpu/mshyperv.c index a7d26d8..8f4be53 100644 --- a/arch/x86/kernel/cpu/mshyperv.c +++ b/arch/x86/kernel/cpu/mshyperv.c @@ -35,13 +35,6 @@ static bool __init ms_hyperv_platform(void) if (!boot_cpu_has(X86_FEATURE_HYPERVISOR)) return false; - /* - * Xen emulates Hyper-V to support enlightened Windows. - * Check to see first if we are on a Xen Hypervisor. - */ - if (xen_cpuid_base()) - return false; - cpuid(HYPERV_CPUID_VENDOR_AND_MAX_FUNCTIONS, &eax, &hyp_signature[0], &hyp_signature[1], &hyp_signature[2]); @@ -82,12 +75,6 @@ static void __init ms_hyperv_init_platform(void) if (ms_hyperv.features & HV_X64_MSR_TIME_REF_COUNT_AVAILABLE) clocksource_register_hz(&hyperv_cs, NSEC_PER_SEC/100); -#if IS_ENABLED(CONFIG_HYPERV) - /* - * Setup the IDT for hypervisor callback. - */ - alloc_intr_gate(HYPERVISOR_CALLBACK_VECTOR, hyperv_callback_vector); -#endif } const __refconst struct hypervisor_x86 x86_hyper_ms_hyperv = { @@ -103,6 +90,11 @@ static irq_handler_t vmbus_isr; void hv_register_vmbus_handler(int irq, irq_handler_t handler) { + /* + * Setup the IDT for hypervisor callback. + */ + alloc_intr_gate(HYPERVISOR_CALLBACK_VECTOR, hyperv_callback_vector); + vmbus_irq = irq; vmbus_isr = handler; } diff --git a/arch/x86/kernel/cpu/perf_event_intel.c b/arch/x86/kernel/cpu/perf_event_intel.c index dab7580..cc45deb 100644 --- a/arch/x86/kernel/cpu/perf_event_intel.c +++ b/arch/x86/kernel/cpu/perf_event_intel.c @@ -153,8 +153,14 @@ static struct event_constraint intel_gen_event_constraints[] __read_mostly = }; static struct extra_reg intel_snb_extra_regs[] __read_mostly = { - INTEL_EVENT_EXTRA_REG(0xb7, MSR_OFFCORE_RSP_0, 0x3fffffffffull, RSP_0), - INTEL_EVENT_EXTRA_REG(0xbb, MSR_OFFCORE_RSP_1, 0x3fffffffffull, RSP_1), + INTEL_EVENT_EXTRA_REG(0xb7, MSR_OFFCORE_RSP_0, 0x3f807f8fffull, RSP_0), + INTEL_EVENT_EXTRA_REG(0xbb, MSR_OFFCORE_RSP_1, 0x3f807f8fffull, RSP_1), + EVENT_EXTRA_END +}; + +static struct extra_reg intel_snbep_extra_regs[] __read_mostly = { + INTEL_EVENT_EXTRA_REG(0xb7, MSR_OFFCORE_RSP_0, 0x3fffff8fffull, RSP_0), + INTEL_EVENT_EXTRA_REG(0xbb, MSR_OFFCORE_RSP_1, 0x3fffff8fffull, RSP_1), EVENT_EXTRA_END }; @@ -2097,7 +2103,10 @@ __init int intel_pmu_init(void) x86_pmu.event_constraints = intel_snb_event_constraints; x86_pmu.pebs_constraints = intel_snb_pebs_event_constraints; x86_pmu.pebs_aliases = intel_pebs_aliases_snb; - x86_pmu.extra_regs = intel_snb_extra_regs; + if (boot_cpu_data.x86_model == 45) + x86_pmu.extra_regs = intel_snbep_extra_regs; + else + x86_pmu.extra_regs = intel_snb_extra_regs; /* all extra regs are per-cpu when HT is on */ x86_pmu.er_flags |= ERF_HAS_RSP_1; x86_pmu.er_flags |= ERF_NO_HT_SHARING; @@ -2123,7 +2132,10 @@ __init int intel_pmu_init(void) x86_pmu.event_constraints = intel_ivb_event_constraints; x86_pmu.pebs_constraints = intel_ivb_pebs_event_constraints; x86_pmu.pebs_aliases = intel_pebs_aliases_snb; - x86_pmu.extra_regs = intel_snb_extra_regs; + if (boot_cpu_data.x86_model == 62) + x86_pmu.extra_regs = intel_snbep_extra_regs; + else + x86_pmu.extra_regs = intel_snb_extra_regs; /* all extra regs are per-cpu when HT is on */ x86_pmu.er_flags |= ERF_HAS_RSP_1; x86_pmu.er_flags |= ERF_NO_HT_SHARING; diff --git a/arch/x86/kernel/cpu/perf_event_intel_ds.c b/arch/x86/kernel/cpu/perf_event_intel_ds.c index b05a575..26830f3 100644 --- a/arch/x86/kernel/cpu/perf_event_intel_ds.c +++ b/arch/x86/kernel/cpu/perf_event_intel_ds.c @@ -314,10 +314,11 @@ int intel_pmu_drain_bts_buffer(void) if (top <= at) return 0; + memset(®s, 0, sizeof(regs)); + ds->bts_index = ds->bts_buffer_base; perf_sample_data_init(&data, 0, event->hw.last_period); - regs.ip = 0; /* * Prepare a generic sample, i.e. fill in the invariant fields. diff --git a/arch/x86/kernel/microcode_core_early.c b/arch/x86/kernel/microcode_core_early.c index 577db84..833d51d 100644 --- a/arch/x86/kernel/microcode_core_early.c +++ b/arch/x86/kernel/microcode_core_early.c @@ -45,9 +45,6 @@ static int __cpuinit x86_vendor(void) u32 eax = 0x00000000; u32 ebx, ecx = 0, edx; - if (!have_cpuid_p()) - return X86_VENDOR_UNKNOWN; - native_cpuid(&eax, &ebx, &ecx, &edx); if (CPUID_IS(CPUID_INTEL1, CPUID_INTEL2, CPUID_INTEL3, ebx, ecx, edx)) @@ -59,18 +56,45 @@ static int __cpuinit x86_vendor(void) return X86_VENDOR_UNKNOWN; } +static int __cpuinit x86_family(void) +{ + u32 eax = 0x00000001; + u32 ebx, ecx = 0, edx; + int x86; + + native_cpuid(&eax, &ebx, &ecx, &edx); + + x86 = (eax >> 8) & 0xf; + if (x86 == 15) + x86 += (eax >> 20) & 0xff; + + return x86; +} + void __init load_ucode_bsp(void) { - int vendor = x86_vendor(); + int vendor, x86; + + if (!have_cpuid_p()) + return; - if (vendor == X86_VENDOR_INTEL) + vendor = x86_vendor(); + x86 = x86_family(); + + if (vendor == X86_VENDOR_INTEL && x86 >= 6) load_ucode_intel_bsp(); } void __cpuinit load_ucode_ap(void) { - int vendor = x86_vendor(); + int vendor, x86; + + if (!have_cpuid_p()) + return; + + vendor = x86_vendor(); + x86 = x86_family(); - if (vendor == X86_VENDOR_INTEL) + if (vendor == X86_VENDOR_INTEL && x86 >= 6) load_ucode_intel_ap(); } diff --git a/arch/x86/kernel/paravirt.c b/arch/x86/kernel/paravirt.c index 17fff18..8bfb335 100644 --- a/arch/x86/kernel/paravirt.c +++ b/arch/x86/kernel/paravirt.c @@ -263,6 +263,18 @@ void paravirt_leave_lazy_mmu(void) leave_lazy(PARAVIRT_LAZY_MMU); } +void paravirt_flush_lazy_mmu(void) +{ + preempt_disable(); + + if (paravirt_get_lazy_mode() == PARAVIRT_LAZY_MMU) { + arch_leave_lazy_mmu_mode(); + arch_enter_lazy_mmu_mode(); + } + + preempt_enable(); +} + void paravirt_start_context_switch(struct task_struct *prev) { BUG_ON(preemptible()); @@ -292,18 +304,6 @@ enum paravirt_lazy_mode paravirt_get_lazy_mode(void) return this_cpu_read(paravirt_lazy_mode); } -void arch_flush_lazy_mmu_mode(void) -{ - preempt_disable(); - - if (paravirt_get_lazy_mode() == PARAVIRT_LAZY_MMU) { - arch_leave_lazy_mmu_mode(); - arch_enter_lazy_mmu_mode(); - } - - preempt_enable(); -} - struct pv_info pv_info = { .name = "bare hardware", .paravirt_enabled = 0, @@ -475,6 +475,7 @@ struct pv_mmu_ops pv_mmu_ops = { .lazy_mode = { .enter = paravirt_nop, .leave = paravirt_nop, + .flush = paravirt_nop, }, .set_fixmap = native_set_fixmap, diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c index 90d8cc9..fae9134 100644 --- a/arch/x86/kernel/setup.c +++ b/arch/x86/kernel/setup.c @@ -507,11 +507,14 @@ static void __init memblock_x86_reserve_range_setup_data(void) /* * Keep the crash kernel below this limit. On 32 bits earlier kernels * would limit the kernel to the low 512 MiB due to mapping restrictions. + * On 64bit, old kexec-tools need to under 896MiB. */ #ifdef CONFIG_X86_32 -# define CRASH_KERNEL_ADDR_MAX (512 << 20) +# define CRASH_KERNEL_ADDR_LOW_MAX (512 << 20) +# define CRASH_KERNEL_ADDR_HIGH_MAX (512 << 20) #else -# define CRASH_KERNEL_ADDR_MAX MAXMEM +# define CRASH_KERNEL_ADDR_LOW_MAX (896UL<<20) +# define CRASH_KERNEL_ADDR_HIGH_MAX MAXMEM #endif static void __init reserve_crashkernel_low(void) @@ -521,19 +524,35 @@ static void __init reserve_crashkernel_low(void) unsigned long long low_base = 0, low_size = 0; unsigned long total_low_mem; unsigned long long base; + bool auto_set = false; int ret; total_low_mem = memblock_mem_size(1UL<<(32-PAGE_SHIFT)); + /* crashkernel=Y,low */ ret = parse_crashkernel_low(boot_command_line, total_low_mem, &low_size, &base); - if (ret != 0 || low_size <= 0) - return; + if (ret != 0) { + /* + * two parts from lib/swiotlb.c: + * swiotlb size: user specified with swiotlb= or default. + * swiotlb overflow buffer: now is hardcoded to 32k. + * We round it to 8M for other buffers that + * may need to stay low too. + */ + low_size = swiotlb_size_or_default() + (8UL<<20); + auto_set = true; + } else { + /* passed with crashkernel=0,low ? */ + if (!low_size) + return; + } low_base = memblock_find_in_range(low_size, (1ULL<<32), low_size, alignment); if (!low_base) { - pr_info("crashkernel low reservation failed - No suitable area found.\n"); + if (!auto_set) + pr_info("crashkernel low reservation failed - No suitable area found.\n"); return; } @@ -554,14 +573,22 @@ static void __init reserve_crashkernel(void) const unsigned long long alignment = 16<<20; /* 16M */ unsigned long long total_mem; unsigned long long crash_size, crash_base; + bool high = false; int ret; total_mem = memblock_phys_mem_size(); + /* crashkernel=XM */ ret = parse_crashkernel(boot_command_line, total_mem, &crash_size, &crash_base); - if (ret != 0 || crash_size <= 0) - return; + if (ret != 0 || crash_size <= 0) { + /* crashkernel=X,high */ + ret = parse_crashkernel_high(boot_command_line, total_mem, + &crash_size, &crash_base); + if (ret != 0 || crash_size <= 0) + return; + high = true; + } /* 0 means: find the address automatically */ if (crash_base <= 0) { @@ -569,7 +596,9 @@ static void __init reserve_crashkernel(void) * kexec want bzImage is below CRASH_KERNEL_ADDR_MAX */ crash_base = memblock_find_in_range(alignment, - CRASH_KERNEL_ADDR_MAX, crash_size, alignment); + high ? CRASH_KERNEL_ADDR_HIGH_MAX : + CRASH_KERNEL_ADDR_LOW_MAX, + crash_size, alignment); if (!crash_base) { pr_info("crashkernel reservation failed - No suitable area found.\n"); diff --git a/arch/x86/kvm/lapic.c b/arch/x86/kvm/lapic.c index 02b51dd..f77df1c 100644 --- a/arch/x86/kvm/lapic.c +++ b/arch/x86/kvm/lapic.c @@ -1857,7 +1857,7 @@ int kvm_lapic_enable_pv_eoi(struct kvm_vcpu *vcpu, u64 data) if (!pv_eoi_enabled(vcpu)) return 0; return kvm_gfn_to_hva_cache_init(vcpu->kvm, &vcpu->arch.pv_eoi.data, - addr); + addr, sizeof(u8)); } void kvm_lapic_init(void) diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index f19ac0a..e172132 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -1823,7 +1823,8 @@ static int kvm_pv_enable_async_pf(struct kvm_vcpu *vcpu, u64 data) return 0; } - if (kvm_gfn_to_hva_cache_init(vcpu->kvm, &vcpu->arch.apf.data, gpa)) + if (kvm_gfn_to_hva_cache_init(vcpu->kvm, &vcpu->arch.apf.data, gpa, + sizeof(u32))) return 1; vcpu->arch.apf.send_user_only = !(data & KVM_ASYNC_PF_SEND_ALWAYS); @@ -1952,12 +1953,9 @@ int kvm_set_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info) gpa_offset = data & ~(PAGE_MASK | 1); - /* Check that the address is 32-byte aligned. */ - if (gpa_offset & (sizeof(struct pvclock_vcpu_time_info) - 1)) - break; - if (kvm_gfn_to_hva_cache_init(vcpu->kvm, - &vcpu->arch.pv_time, data & ~1ULL)) + &vcpu->arch.pv_time, data & ~1ULL, + sizeof(struct pvclock_vcpu_time_info))) vcpu->arch.pv_time_enabled = false; else vcpu->arch.pv_time_enabled = true; @@ -1977,7 +1975,8 @@ int kvm_set_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info) return 1; if (kvm_gfn_to_hva_cache_init(vcpu->kvm, &vcpu->arch.st.stime, - data & KVM_STEAL_VALID_BITS)) + data & KVM_STEAL_VALID_BITS, + sizeof(struct kvm_steal_time))) return 1; vcpu->arch.st.msr_val = data; diff --git a/arch/x86/lguest/boot.c b/arch/x86/lguest/boot.c index 1cbd89c..7114c63 100644 --- a/arch/x86/lguest/boot.c +++ b/arch/x86/lguest/boot.c @@ -1334,6 +1334,7 @@ __init void lguest_init(void) pv_mmu_ops.read_cr3 = lguest_read_cr3; pv_mmu_ops.lazy_mode.enter = paravirt_enter_lazy_mmu; pv_mmu_ops.lazy_mode.leave = lguest_leave_lazy_mmu_mode; + pv_mmu_ops.lazy_mode.flush = paravirt_flush_lazy_mmu; pv_mmu_ops.pte_update = lguest_pte_update; pv_mmu_ops.pte_update_defer = lguest_pte_update; diff --git a/arch/x86/mm/fault.c b/arch/x86/mm/fault.c index 2b97525..0e88336 100644 --- a/arch/x86/mm/fault.c +++ b/arch/x86/mm/fault.c @@ -378,10 +378,12 @@ static noinline __kprobes int vmalloc_fault(unsigned long address) if (pgd_none(*pgd_ref)) return -1; - if (pgd_none(*pgd)) + if (pgd_none(*pgd)) { set_pgd(pgd, *pgd_ref); - else + arch_flush_lazy_mmu_mode(); + } else { BUG_ON(pgd_page_vaddr(*pgd) != pgd_page_vaddr(*pgd_ref)); + } /* * Below here mismatches are bugs because these lower tables diff --git a/arch/x86/mm/pageattr-test.c b/arch/x86/mm/pageattr-test.c index b008656..0e38951 100644 --- a/arch/x86/mm/pageattr-test.c +++ b/arch/x86/mm/pageattr-test.c @@ -68,7 +68,7 @@ static int print_split(struct split_state *s) s->gpg++; i += GPS/PAGE_SIZE; } else if (level == PG_LEVEL_2M) { - if (!(pte_val(*pte) & _PAGE_PSE)) { + if ((pte_val(*pte) & _PAGE_PRESENT) && !(pte_val(*pte) & _PAGE_PSE)) { printk(KERN_ERR "%lx level %d but not PSE %Lx\n", addr, level, (u64)pte_val(*pte)); diff --git a/arch/x86/mm/pageattr.c b/arch/x86/mm/pageattr.c index 091934e..fb4e73e 100644 --- a/arch/x86/mm/pageattr.c +++ b/arch/x86/mm/pageattr.c @@ -467,7 +467,7 @@ try_preserve_large_page(pte_t *kpte, unsigned long address, * We are safe now. Check whether the new pgprot is the same: */ old_pte = *kpte; - old_prot = new_prot = req_prot = pte_pgprot(old_pte); + old_prot = req_prot = pte_pgprot(old_pte); pgprot_val(req_prot) &= ~pgprot_val(cpa->mask_clr); pgprot_val(req_prot) |= pgprot_val(cpa->mask_set); @@ -478,12 +478,12 @@ try_preserve_large_page(pte_t *kpte, unsigned long address, * a non present pmd. The canon_pgprot will clear _PAGE_GLOBAL * for the ancient hardware that doesn't support it. */ - if (pgprot_val(new_prot) & _PAGE_PRESENT) - pgprot_val(new_prot) |= _PAGE_PSE | _PAGE_GLOBAL; + if (pgprot_val(req_prot) & _PAGE_PRESENT) + pgprot_val(req_prot) |= _PAGE_PSE | _PAGE_GLOBAL; else - pgprot_val(new_prot) &= ~(_PAGE_PSE | _PAGE_GLOBAL); + pgprot_val(req_prot) &= ~(_PAGE_PSE | _PAGE_GLOBAL); - new_prot = canon_pgprot(new_prot); + req_prot = canon_pgprot(req_prot); /* * old_pte points to the large page base address. So we need @@ -1413,6 +1413,8 @@ void kernel_map_pages(struct page *page, int numpages, int enable) * but that can deadlock->flush only current cpu: */ __flush_tlb_all(); + + arch_flush_lazy_mmu_mode(); } #ifdef CONFIG_HIBERNATION diff --git a/arch/x86/mm/pgtable.c b/arch/x86/mm/pgtable.c index 193350b..17fda6a 100644 --- a/arch/x86/mm/pgtable.c +++ b/arch/x86/mm/pgtable.c @@ -58,6 +58,13 @@ void ___pte_free_tlb(struct mmu_gather *tlb, struct page *pte) void ___pmd_free_tlb(struct mmu_gather *tlb, pmd_t *pmd) { paravirt_release_pmd(__pa(pmd) >> PAGE_SHIFT); + /* + * NOTE! For PAE, any changes to the top page-directory-pointer-table + * entries need a full cr3 reload to flush. + */ +#ifdef CONFIG_X86_PAE + tlb->need_flush_all = 1; +#endif tlb_remove_page(tlb, virt_to_page(pmd)); } diff --git a/arch/x86/platform/efi/efi.c b/arch/x86/platform/efi/efi.c index 5f2ecaf..e4a86a6 100644 --- a/arch/x86/platform/efi/efi.c +++ b/arch/x86/platform/efi/efi.c @@ -41,6 +41,7 @@ #include <linux/io.h> #include <linux/reboot.h> #include <linux/bcd.h> +#include <linux/ucs2_string.h> #include <asm/setup.h> #include <asm/efi.h> @@ -51,6 +52,13 @@ #define EFI_DEBUG 1 +/* + * There's some additional metadata associated with each + * variable. Intel's reference implementation is 60 bytes - bump that + * to account for potential alignment constraints + */ +#define VAR_METADATA_SIZE 64 + struct efi __read_mostly efi = { .mps = EFI_INVALID_TABLE_ADDR, .acpi = EFI_INVALID_TABLE_ADDR, @@ -69,6 +77,13 @@ struct efi_memory_map memmap; static struct efi efi_phys __initdata; static efi_system_table_t efi_systab __initdata; +static u64 efi_var_store_size; +static u64 efi_var_remaining_size; +static u64 efi_var_max_var_size; +static u64 boot_used_size; +static u64 boot_var_size; +static u64 active_size; + unsigned long x86_efi_facility; /* @@ -98,6 +113,15 @@ static int __init setup_add_efi_memmap(char *arg) } early_param("add_efi_memmap", setup_add_efi_memmap); +static bool efi_no_storage_paranoia; + +static int __init setup_storage_paranoia(char *arg) +{ + efi_no_storage_paranoia = true; + return 0; +} +early_param("efi_no_storage_paranoia", setup_storage_paranoia); + static efi_status_t virt_efi_get_time(efi_time_t *tm, efi_time_cap_t *tc) { @@ -162,8 +186,53 @@ static efi_status_t virt_efi_get_next_variable(unsigned long *name_size, efi_char16_t *name, efi_guid_t *vendor) { - return efi_call_virt3(get_next_variable, - name_size, name, vendor); + efi_status_t status; + static bool finished = false; + static u64 var_size; + + status = efi_call_virt3(get_next_variable, + name_size, name, vendor); + + if (status == EFI_NOT_FOUND) { + finished = true; + if (var_size < boot_used_size) { + boot_var_size = boot_used_size - var_size; + active_size += boot_var_size; + } else { + printk(KERN_WARNING FW_BUG "efi: Inconsistent initial sizes\n"); + } + } + + if (boot_used_size && !finished) { + unsigned long size; + u32 attr; + efi_status_t s; + void *tmp; + + s = virt_efi_get_variable(name, vendor, &attr, &size, NULL); + + if (s != EFI_BUFFER_TOO_SMALL || !size) + return status; + + tmp = kmalloc(size, GFP_ATOMIC); + + if (!tmp) + return status; + + s = virt_efi_get_variable(name, vendor, &attr, &size, tmp); + + if (s == EFI_SUCCESS && (attr & EFI_VARIABLE_NON_VOLATILE)) { + var_size += size; + var_size += ucs2_strsize(name, 1024); + active_size += size; + active_size += VAR_METADATA_SIZE; + active_size += ucs2_strsize(name, 1024); + } + + kfree(tmp); + } + + return status; } static efi_status_t virt_efi_set_variable(efi_char16_t *name, @@ -172,9 +241,34 @@ static efi_status_t virt_efi_set_variable(efi_char16_t *name, unsigned long data_size, void *data) { - return efi_call_virt5(set_variable, - name, vendor, attr, - data_size, data); + efi_status_t status; + u32 orig_attr = 0; + unsigned long orig_size = 0; + + status = virt_efi_get_variable(name, vendor, &orig_attr, &orig_size, + NULL); + + if (status != EFI_BUFFER_TOO_SMALL) + orig_size = 0; + + status = efi_call_virt5(set_variable, + name, vendor, attr, + data_size, data); + + if (status == EFI_SUCCESS) { + if (orig_size) { + active_size -= orig_size; + active_size -= ucs2_strsize(name, 1024); + active_size -= VAR_METADATA_SIZE; + } + if (data_size) { + active_size += data_size; + active_size += ucs2_strsize(name, 1024); + active_size += VAR_METADATA_SIZE; + } + } + + return status; } static efi_status_t virt_efi_query_variable_info(u32 attr, @@ -682,6 +776,9 @@ void __init efi_init(void) char vendor[100] = "unknown"; int i = 0; void *tmp; + struct setup_data *data; + struct efi_var_bootdata *efi_var_data; + u64 pa_data; #ifdef CONFIG_X86_32 if (boot_params.efi_info.efi_systab_hi || @@ -699,6 +796,22 @@ void __init efi_init(void) if (efi_systab_init(efi_phys.systab)) return; + pa_data = boot_params.hdr.setup_data; + while (pa_data) { + data = early_ioremap(pa_data, sizeof(*efi_var_data)); + if (data->type == SETUP_EFI_VARS) { + efi_var_data = (struct efi_var_bootdata *)data; + + efi_var_store_size = efi_var_data->store_size; + efi_var_remaining_size = efi_var_data->remaining_size; + efi_var_max_var_size = efi_var_data->max_var_size; + } + pa_data = data->next; + early_iounmap(data, sizeof(*efi_var_data)); + } + + boot_used_size = efi_var_store_size - efi_var_remaining_size; + set_bit(EFI_SYSTEM_TABLES, &x86_efi_facility); /* @@ -999,3 +1112,48 @@ u64 efi_mem_attributes(unsigned long phys_addr) } return 0; } + +/* + * Some firmware has serious problems when using more than 50% of the EFI + * variable store, i.e. it triggers bugs that can brick machines. Ensure that + * we never use more than this safe limit. + * + * Return EFI_SUCCESS if it is safe to write 'size' bytes to the variable + * store. + */ +efi_status_t efi_query_variable_store(u32 attributes, unsigned long size) +{ + efi_status_t status; + u64 storage_size, remaining_size, max_size; + + status = efi.query_variable_info(attributes, &storage_size, + &remaining_size, &max_size); + if (status != EFI_SUCCESS) + return status; + + if (!max_size && remaining_size > size) + printk_once(KERN_ERR FW_BUG "Broken EFI implementation" + " is returning MaxVariableSize=0\n"); + /* + * Some firmware implementations refuse to boot if there's insufficient + * space in the variable store. We account for that by refusing the + * write if permitting it would reduce the available space to under + * 50%. However, some firmware won't reclaim variable space until + * after the used (not merely the actively used) space drops below + * a threshold. We can approximate that case with the value calculated + * above. If both the firmware and our calculations indicate that the + * available space would drop below 50%, refuse the write. + */ + + if (!storage_size || size > remaining_size || + (max_size && size > max_size)) + return EFI_OUT_OF_RESOURCES; + + if (!efi_no_storage_paranoia && + ((active_size + size + VAR_METADATA_SIZE > storage_size / 2) && + (remaining_size - size < storage_size / 2))) + return EFI_OUT_OF_RESOURCES; + + return EFI_SUCCESS; +} +EXPORT_SYMBOL_GPL(efi_query_variable_store); diff --git a/arch/x86/xen/mmu.c b/arch/x86/xen/mmu.c index 6afbb2c..e006c18 100644 --- a/arch/x86/xen/mmu.c +++ b/arch/x86/xen/mmu.c @@ -1748,14 +1748,18 @@ static void *m2v(phys_addr_t maddr) } /* Set the page permissions on an identity-mapped pages */ -static void set_page_prot(void *addr, pgprot_t prot) +static void set_page_prot_flags(void *addr, pgprot_t prot, unsigned long flags) { unsigned long pfn = __pa(addr) >> PAGE_SHIFT; pte_t pte = pfn_pte(pfn, prot); - if (HYPERVISOR_update_va_mapping((unsigned long)addr, pte, 0)) + if (HYPERVISOR_update_va_mapping((unsigned long)addr, pte, flags)) BUG(); } +static void set_page_prot(void *addr, pgprot_t prot) +{ + return set_page_prot_flags(addr, prot, UVMF_NONE); +} #ifdef CONFIG_X86_32 static void __init xen_map_identity_early(pmd_t *pmd, unsigned long max_pfn) { @@ -1839,12 +1843,12 @@ static void __init check_pt_base(unsigned long *pt_base, unsigned long *pt_end, unsigned long addr) { if (*pt_base == PFN_DOWN(__pa(addr))) { - set_page_prot((void *)addr, PAGE_KERNEL); + set_page_prot_flags((void *)addr, PAGE_KERNEL, UVMF_INVLPG); clear_page((void *)addr); (*pt_base)++; } if (*pt_end == PFN_DOWN(__pa(addr))) { - set_page_prot((void *)addr, PAGE_KERNEL); + set_page_prot_flags((void *)addr, PAGE_KERNEL, UVMF_INVLPG); clear_page((void *)addr); (*pt_end)--; } @@ -2196,6 +2200,7 @@ static const struct pv_mmu_ops xen_mmu_ops __initconst = { .lazy_mode = { .enter = paravirt_enter_lazy_mmu, .leave = xen_leave_lazy_mmu, + .flush = paravirt_flush_lazy_mmu, }, .set_fixmap = xen_set_fixmap, |
