diff options
Diffstat (limited to 'arch')
444 files changed, 4775 insertions, 2700 deletions
diff --git a/arch/arc/Kconfig b/arch/arc/Kconfig index 2c2ac3f3ff80..6312f607932f 100644 --- a/arch/arc/Kconfig +++ b/arch/arc/Kconfig @@ -445,6 +445,7 @@ config LINUX_LINK_BASE However some customers have peripherals mapped at this addr, so Linux needs to be scooted a bit. If you don't know what the above means, leave this setting alone. + This needs to match memory start address specified in Device Tree config HIGHMEM bool "High Memory Support" diff --git a/arch/arc/Makefile b/arch/arc/Makefile index cf0cf34eeb24..aeb19021099e 100644 --- a/arch/arc/Makefile +++ b/arch/arc/Makefile @@ -81,7 +81,7 @@ endif LIBGCC := $(shell $(CC) $(cflags-y) --print-libgcc-file-name) # Modules with short calls might break for calls into builtin-kernel -KBUILD_CFLAGS_MODULE += -mlong-calls +KBUILD_CFLAGS_MODULE += -mlong-calls -mno-millicode # Finally dump eveything into kernel build system KBUILD_CFLAGS += $(cflags-y) diff --git a/arch/arc/boot/dts/axs10x_mb.dtsi b/arch/arc/boot/dts/axs10x_mb.dtsi index f3db32154973..44a578c10732 100644 --- a/arch/arc/boot/dts/axs10x_mb.dtsi +++ b/arch/arc/boot/dts/axs10x_mb.dtsi @@ -46,6 +46,7 @@ snps,pbl = < 32 >; clocks = <&apbclk>; clock-names = "stmmaceth"; + max-speed = <100>; }; ehci@0x40000 { diff --git a/arch/arc/boot/dts/nsim_hs.dts b/arch/arc/boot/dts/nsim_hs.dts index b0eb0e7fe21d..fc81879bc1f5 100644 --- a/arch/arc/boot/dts/nsim_hs.dts +++ b/arch/arc/boot/dts/nsim_hs.dts @@ -17,7 +17,8 @@ memory { device_type = "memory"; - reg = <0x0 0x80000000 0x0 0x40000000 /* 1 GB low mem */ + /* CONFIG_LINUX_LINK_BASE needs to match low mem start */ + reg = <0x0 0x80000000 0x0 0x20000000 /* 512 MB low mem */ 0x1 0x00000000 0x0 0x40000000>; /* 1 GB highmem */ }; diff --git a/arch/arc/configs/axs101_defconfig b/arch/arc/configs/axs101_defconfig index c92c0ef1e9d2..f1ac9818b751 100644 --- a/arch/arc/configs/axs101_defconfig +++ b/arch/arc/configs/axs101_defconfig @@ -1,4 +1,4 @@ -CONFIG_CROSS_COMPILE="arc-linux-uclibc-" +CONFIG_CROSS_COMPILE="arc-linux-" CONFIG_DEFAULT_HOSTNAME="ARCLinux" # CONFIG_SWAP is not set CONFIG_SYSVIPC=y diff --git a/arch/arc/configs/axs103_defconfig b/arch/arc/configs/axs103_defconfig index cfac24e0e7b6..323486d6ee83 100644 --- a/arch/arc/configs/axs103_defconfig +++ b/arch/arc/configs/axs103_defconfig @@ -1,4 +1,4 @@ -CONFIG_CROSS_COMPILE="arc-linux-uclibc-" +CONFIG_CROSS_COMPILE="arc-linux-" CONFIG_DEFAULT_HOSTNAME="ARCLinux" # CONFIG_SWAP is not set CONFIG_SYSVIPC=y diff --git a/arch/arc/configs/axs103_smp_defconfig b/arch/arc/configs/axs103_smp_defconfig index 9922a118a15a..66191cd0447e 100644 --- a/arch/arc/configs/axs103_smp_defconfig +++ b/arch/arc/configs/axs103_smp_defconfig @@ -1,4 +1,4 @@ -CONFIG_CROSS_COMPILE="arc-linux-uclibc-" +CONFIG_CROSS_COMPILE="arc-linux-" CONFIG_DEFAULT_HOSTNAME="ARCLinux" # CONFIG_SWAP is not set CONFIG_SYSVIPC=y diff --git a/arch/arc/configs/nsim_hs_defconfig b/arch/arc/configs/nsim_hs_defconfig index f761a7c70761..f68838e8068a 100644 --- a/arch/arc/configs/nsim_hs_defconfig +++ b/arch/arc/configs/nsim_hs_defconfig @@ -1,4 +1,4 @@ -CONFIG_CROSS_COMPILE="arc-linux-uclibc-" +CONFIG_CROSS_COMPILE="arc-linux-" # CONFIG_LOCALVERSION_AUTO is not set CONFIG_DEFAULT_HOSTNAME="ARCLinux" # CONFIG_SWAP is not set diff --git a/arch/arc/configs/nsim_hs_smp_defconfig b/arch/arc/configs/nsim_hs_smp_defconfig index dc6f74f41283..96bd1c20fb0b 100644 --- a/arch/arc/configs/nsim_hs_smp_defconfig +++ b/arch/arc/configs/nsim_hs_smp_defconfig @@ -1,4 +1,4 @@ -CONFIG_CROSS_COMPILE="arc-linux-uclibc-" +CONFIG_CROSS_COMPILE="arc-linux-" # CONFIG_LOCALVERSION_AUTO is not set CONFIG_DEFAULT_HOSTNAME="ARCLinux" # CONFIG_SWAP is not set diff --git a/arch/arc/configs/nsimosci_hs_defconfig b/arch/arc/configs/nsimosci_hs_defconfig index 3fef0a210c56..fcae66683ca0 100644 --- a/arch/arc/configs/nsimosci_hs_defconfig +++ b/arch/arc/configs/nsimosci_hs_defconfig @@ -1,4 +1,4 @@ -CONFIG_CROSS_COMPILE="arc-linux-uclibc-" +CONFIG_CROSS_COMPILE="arc-linux-" # CONFIG_LOCALVERSION_AUTO is not set CONFIG_DEFAULT_HOSTNAME="ARCLinux" # CONFIG_SWAP is not set diff --git a/arch/arc/configs/nsimosci_hs_smp_defconfig b/arch/arc/configs/nsimosci_hs_smp_defconfig index 51784837daae..b01b659168ea 100644 --- a/arch/arc/configs/nsimosci_hs_smp_defconfig +++ b/arch/arc/configs/nsimosci_hs_smp_defconfig @@ -1,4 +1,4 @@ -CONFIG_CROSS_COMPILE="arc-linux-uclibc-" +CONFIG_CROSS_COMPILE="arc-linux-" CONFIG_DEFAULT_HOSTNAME="ARCLinux" # CONFIG_SWAP is not set CONFIG_SYSVIPC=y diff --git a/arch/arc/configs/vdk_hs38_defconfig b/arch/arc/configs/vdk_hs38_defconfig index ef35ef3923dd..a07f20de221b 100644 --- a/arch/arc/configs/vdk_hs38_defconfig +++ b/arch/arc/configs/vdk_hs38_defconfig @@ -1,4 +1,4 @@ -CONFIG_CROSS_COMPILE="arc-linux-uclibc-" +CONFIG_CROSS_COMPILE="arc-linux-" # CONFIG_LOCALVERSION_AUTO is not set CONFIG_DEFAULT_HOSTNAME="ARCLinux" # CONFIG_CROSS_MEMORY_ATTACH is not set diff --git a/arch/arc/configs/vdk_hs38_smp_defconfig b/arch/arc/configs/vdk_hs38_smp_defconfig index 634509e5e572..f36c047b33ca 100644 --- a/arch/arc/configs/vdk_hs38_smp_defconfig +++ b/arch/arc/configs/vdk_hs38_smp_defconfig @@ -1,4 +1,4 @@ -CONFIG_CROSS_COMPILE="arc-linux-uclibc-" +CONFIG_CROSS_COMPILE="arc-linux-" # CONFIG_LOCALVERSION_AUTO is not set CONFIG_DEFAULT_HOSTNAME="ARCLinux" # CONFIG_CROSS_MEMORY_ATTACH is not set diff --git a/arch/arc/include/asm/cache.h b/arch/arc/include/asm/cache.h index abf06e81c929..210ef3e72332 100644 --- a/arch/arc/include/asm/cache.h +++ b/arch/arc/include/asm/cache.h @@ -62,9 +62,7 @@ extern int ioc_exists; #define ARC_REG_IC_IVIC 0x10 #define ARC_REG_IC_CTRL 0x11 #define ARC_REG_IC_IVIL 0x19 -#if defined(CONFIG_ARC_MMU_V3) || defined(CONFIG_ARC_MMU_V4) #define ARC_REG_IC_PTAG 0x1E -#endif #define ARC_REG_IC_PTAG_HI 0x1F /* Bit val in IC_CTRL */ diff --git a/arch/arc/include/asm/irqflags-arcv2.h b/arch/arc/include/asm/irqflags-arcv2.h index ad481c24070d..258b0e5ad332 100644 --- a/arch/arc/include/asm/irqflags-arcv2.h +++ b/arch/arc/include/asm/irqflags-arcv2.h @@ -37,6 +37,9 @@ #define ISA_INIT_STATUS_BITS (STATUS_IE_MASK | STATUS_AD_MASK | \ (ARCV2_IRQ_DEF_PRIO << 1)) +/* SLEEP needs default irq priority (<=) which can interrupt the doze */ +#define ISA_SLEEP_ARG (0x10 | ARCV2_IRQ_DEF_PRIO) + #ifndef __ASSEMBLY__ /* diff --git a/arch/arc/include/asm/irqflags-compact.h b/arch/arc/include/asm/irqflags-compact.h index d8c608174617..c1d36458bfb7 100644 --- a/arch/arc/include/asm/irqflags-compact.h +++ b/arch/arc/include/asm/irqflags-compact.h @@ -43,6 +43,8 @@ #define ISA_INIT_STATUS_BITS STATUS_IE_MASK +#define ISA_SLEEP_ARG 0x3 + #ifndef __ASSEMBLY__ /****************************************************************** diff --git a/arch/arc/include/asm/mach_desc.h b/arch/arc/include/asm/mach_desc.h index 6ff657a904b6..c28e6c347b49 100644 --- a/arch/arc/include/asm/mach_desc.h +++ b/arch/arc/include/asm/mach_desc.h @@ -23,7 +23,7 @@ * @dt_compat: Array of device tree 'compatible' strings * (XXX: although only 1st entry is looked at) * @init_early: Very early callback [called from setup_arch()] - * @init_cpu_smp: for each CPU as it is coming up (SMP as well as UP) + * @init_per_cpu: for each CPU as it is coming up (SMP as well as UP) * [(M):init_IRQ(), (o):start_kernel_secondary()] * @init_machine: arch initcall level callback (e.g. populate static * platform devices or parse Devicetree) @@ -35,7 +35,7 @@ struct machine_desc { const char **dt_compat; void (*init_early)(void); #ifdef CONFIG_SMP - void (*init_cpu_smp)(unsigned int); + void (*init_per_cpu)(unsigned int); #endif void (*init_machine)(void); void (*init_late)(void); diff --git a/arch/arc/include/asm/smp.h b/arch/arc/include/asm/smp.h index 133c867d15af..991380438d6b 100644 --- a/arch/arc/include/asm/smp.h +++ b/arch/arc/include/asm/smp.h @@ -48,7 +48,7 @@ extern int smp_ipi_irq_setup(int cpu, int irq); * @init_early_smp: A SMP specific h/w block can init itself * Could be common across platforms so not covered by * mach_desc->init_early() - * @init_irq_cpu: Called for each core so SMP h/w block driver can do + * @init_per_cpu: Called for each core so SMP h/w block driver can do * any needed setup per cpu (e.g. IPI request) * @cpu_kick: For Master to kickstart a cpu (optionally at a PC) * @ipi_send: To send IPI to a @cpu @@ -57,7 +57,7 @@ extern int smp_ipi_irq_setup(int cpu, int irq); struct plat_smp_ops { const char *info; void (*init_early_smp)(void); - void (*init_irq_cpu)(int cpu); + void (*init_per_cpu)(int cpu); void (*cpu_kick)(int cpu, unsigned long pc); void (*ipi_send)(int cpu); void (*ipi_clear)(int irq); diff --git a/arch/arc/include/asm/unwind.h b/arch/arc/include/asm/unwind.h index 7ca628b6ee2a..c11a25bb8158 100644 --- a/arch/arc/include/asm/unwind.h +++ b/arch/arc/include/asm/unwind.h @@ -112,7 +112,6 @@ struct unwind_frame_info { extern int arc_unwind(struct unwind_frame_info *frame); extern void arc_unwind_init(void); -extern void arc_unwind_setup(void); extern void *unwind_add_table(struct module *module, const void *table_start, unsigned long table_size); extern void unwind_remove_table(void *handle, int init_only); @@ -152,9 +151,6 @@ static inline void arc_unwind_init(void) { } -static inline void arc_unwind_setup(void) -{ -} #define unwind_add_table(a, b, c) #define unwind_remove_table(a, b) diff --git a/arch/arc/kernel/ctx_sw.c b/arch/arc/kernel/ctx_sw.c index c14a5bea0c76..5d446df2c413 100644 --- a/arch/arc/kernel/ctx_sw.c +++ b/arch/arc/kernel/ctx_sw.c @@ -58,8 +58,6 @@ __switch_to(struct task_struct *prev_task, struct task_struct *next_task) "st sp, [r24] \n\t" #endif - "sync \n\t" - /* * setup _current_task with incoming tsk. * optionally, set r25 to that as well diff --git a/arch/arc/kernel/ctx_sw_asm.S b/arch/arc/kernel/ctx_sw_asm.S index e248594097e7..e6890b1f8650 100644 --- a/arch/arc/kernel/ctx_sw_asm.S +++ b/arch/arc/kernel/ctx_sw_asm.S @@ -44,9 +44,6 @@ __switch_to: * don't need to do anything special to return it */ - /* hardware memory barrier */ - sync - /* * switch to new task, contained in r1 * Temp reg r3 is required to get the ptr to store val diff --git a/arch/arc/kernel/intc-arcv2.c b/arch/arc/kernel/intc-arcv2.c index 26c156827479..0394f9f61b46 100644 --- a/arch/arc/kernel/intc-arcv2.c +++ b/arch/arc/kernel/intc-arcv2.c @@ -106,10 +106,21 @@ static struct irq_chip arcv2_irq_chip = { static int arcv2_irq_map(struct irq_domain *d, unsigned int irq, irq_hw_number_t hw) { - if (irq == TIMER0_IRQ || irq == IPI_IRQ) + /* + * core intc IRQs [16, 23]: + * Statically assigned always private-per-core (Timers, WDT, IPI, PCT) + */ + if (hw < 24) { + /* + * A subsequent request_percpu_irq() fails if percpu_devid is + * not set. That in turns sets NOAUTOEN, meaning each core needs + * to call enable_percpu_irq() + */ + irq_set_percpu_devid(irq); irq_set_chip_and_handler(irq, &arcv2_irq_chip, handle_percpu_irq); - else + } else { irq_set_chip_and_handler(irq, &arcv2_irq_chip, handle_level_irq); + } return 0; } diff --git a/arch/arc/kernel/irq.c b/arch/arc/kernel/irq.c index 2ee226546c6a..ba17f85285cf 100644 --- a/arch/arc/kernel/irq.c +++ b/arch/arc/kernel/irq.c @@ -29,11 +29,11 @@ void __init init_IRQ(void) #ifdef CONFIG_SMP /* a SMP H/w block could do IPI IRQ request here */ - if (plat_smp_ops.init_irq_cpu) - plat_smp_ops.init_irq_cpu(smp_processor_id()); + if (plat_smp_ops.init_per_cpu) + plat_smp_ops.init_per_cpu(smp_processor_id()); - if (machine_desc->init_cpu_smp) - machine_desc->init_cpu_smp(smp_processor_id()); + if (machine_desc->init_per_cpu) + machine_desc->init_per_cpu(smp_processor_id()); #endif } @@ -51,6 +51,18 @@ void arch_do_IRQ(unsigned int irq, struct pt_regs *regs) set_irq_regs(old_regs); } +/* + * API called for requesting percpu interrupts - called by each CPU + * - For boot CPU, actually request the IRQ with genirq core + enables + * - For subsequent callers only enable called locally + * + * Relies on being called by boot cpu first (i.e. request called ahead) of + * any enable as expected by genirq. Hence Suitable only for TIMER, IPI + * which are guaranteed to be setup on boot core first. + * Late probed peripherals such as perf can't use this as there no guarantee + * of being called on boot CPU first. + */ + void arc_request_percpu_irq(int irq, int cpu, irqreturn_t (*isr)(int irq, void *dev), const char *irq_nm, @@ -60,14 +72,17 @@ void arc_request_percpu_irq(int irq, int cpu, if (!cpu) { int rc; +#ifdef CONFIG_ISA_ARCOMPACT /* - * These 2 calls are essential to making percpu IRQ APIs work - * Ideally these details could be hidden in irq chip map function - * but the issue is IPIs IRQs being static (non-DT) and platform - * specific, so we can't identify them there. + * A subsequent request_percpu_irq() fails if percpu_devid is + * not set. That in turns sets NOAUTOEN, meaning each core needs + * to call enable_percpu_irq() + * + * For ARCv2, this is done in irq map function since we know + * which irqs are strictly per cpu */ irq_set_percpu_devid(irq); - irq_modify_status(irq, IRQ_NOAUTOEN, 0); /* @irq, @clr, @set */ +#endif rc = request_percpu_irq(irq, isr, irq_nm, percpu_dev); if (rc) diff --git a/arch/arc/kernel/mcip.c b/arch/arc/kernel/mcip.c index 74a9b074ac3e..bd237acdf4f2 100644 --- a/arch/arc/kernel/mcip.c +++ b/arch/arc/kernel/mcip.c @@ -132,7 +132,7 @@ static void mcip_probe_n_setup(void) struct plat_smp_ops plat_smp_ops = { .info = smp_cpuinfo_buf, .init_early_smp = mcip_probe_n_setup, - .init_irq_cpu = mcip_setup_per_cpu, + .init_per_cpu = mcip_setup_per_cpu, .ipi_send = mcip_ipi_send, .ipi_clear = mcip_ipi_clear, }; diff --git a/arch/arc/kernel/perf_event.c b/arch/arc/kernel/perf_event.c index 0c08bb1ce15a..8b134cfe5e1f 100644 --- a/arch/arc/kernel/perf_event.c +++ b/arch/arc/kernel/perf_event.c @@ -428,12 +428,11 @@ static irqreturn_t arc_pmu_intr(int irq, void *dev) #endif /* CONFIG_ISA_ARCV2 */ -void arc_cpu_pmu_irq_init(void) +static void arc_cpu_pmu_irq_init(void *data) { - struct arc_pmu_cpu *pmu_cpu = this_cpu_ptr(&arc_pmu_cpu); + int irq = *(int *)data; - arc_request_percpu_irq(arc_pmu->irq, smp_processor_id(), arc_pmu_intr, - "ARC perf counters", pmu_cpu); + enable_percpu_irq(irq, IRQ_TYPE_NONE); /* Clear all pending interrupt flags */ write_aux_reg(ARC_REG_PCT_INT_ACT, 0xffffffff); @@ -515,7 +514,6 @@ static int arc_pmu_device_probe(struct platform_device *pdev) if (has_interrupts) { int irq = platform_get_irq(pdev, 0); - unsigned long flags; if (irq < 0) { pr_err("Cannot get IRQ number for the platform\n"); @@ -524,24 +522,12 @@ static int arc_pmu_device_probe(struct platform_device *pdev) arc_pmu->irq = irq; - /* - * arc_cpu_pmu_irq_init() needs to be called on all cores for - * their respective local PMU. - * However we use opencoded on_each_cpu() to ensure it is called - * on core0 first, so that arc_request_percpu_irq() sets up - * AUTOEN etc. Otherwise enable_percpu_irq() fails to enable - * perf IRQ on non master cores. - * see arc_request_percpu_irq() - */ - preempt_disable(); - local_irq_save(flags); - arc_cpu_pmu_irq_init(); - local_irq_restore(flags); - smp_call_function((smp_call_func_t)arc_cpu_pmu_irq_init, 0, 1); - preempt_enable(); - - /* Clean all pending interrupt flags */ - write_aux_reg(ARC_REG_PCT_INT_ACT, 0xffffffff); + /* intc map function ensures irq_set_percpu_devid() called */ + request_percpu_irq(irq, arc_pmu_intr, "ARC perf counters", + this_cpu_ptr(&arc_pmu_cpu)); + + on_each_cpu(arc_cpu_pmu_irq_init, &irq, 1); + } else arc_pmu->pmu.capabilities |= PERF_PMU_CAP_NO_INTERRUPT; diff --git a/arch/arc/kernel/process.c b/arch/arc/kernel/process.c index 91d5a0f1f3f7..a3f750e76b68 100644 --- a/arch/arc/kernel/process.c +++ b/arch/arc/kernel/process.c @@ -44,11 +44,10 @@ SYSCALL_DEFINE0(arc_gettls) void arch_cpu_idle(void) { /* sleep, but enable all interrupts before committing */ - if (is_isa_arcompact()) { - __asm__("sleep 0x3"); - } else { - __asm__("sleep 0x10"); - } + __asm__ __volatile__( + "sleep %0 \n" + : + :"I"(ISA_SLEEP_ARG)); /* can't be "r" has to be embedded const */ } asmlinkage void ret_from_fork(void); diff --git a/arch/arc/kernel/setup.c b/arch/arc/kernel/setup.c index c33e77c0ad3e..e1b87444ea9a 100644 --- a/arch/arc/kernel/setup.c +++ b/arch/arc/kernel/setup.c @@ -429,7 +429,6 @@ void __init setup_arch(char **cmdline_p) #endif arc_unwind_init(); - arc_unwind_setup(); } static int __init customize_machine(void) diff --git a/arch/arc/kernel/smp.c b/arch/arc/kernel/smp.c index 580587805fa3..ef6e9e15b82a 100644 --- a/arch/arc/kernel/smp.c +++ b/arch/arc/kernel/smp.c @@ -132,11 +132,11 @@ void start_kernel_secondary(void) pr_info("## CPU%u LIVE ##: Executing Code...\n", cpu); /* Some SMP H/w setup - for each cpu */ - if (plat_smp_ops.init_irq_cpu) - plat_smp_ops.init_irq_cpu(cpu); + if (plat_smp_ops.init_per_cpu) + plat_smp_ops.init_per_cpu(cpu); - if (machine_desc->init_cpu_smp) - machine_desc->init_cpu_smp(cpu); + if (machine_desc->init_per_cpu) + machine_desc->init_per_cpu(cpu); arc_local_timer_setup(); diff --git a/arch/arc/kernel/unwind.c b/arch/arc/kernel/unwind.c index 93c6ea52b671..5eb707640e9c 100644 --- a/arch/arc/kernel/unwind.c +++ b/arch/arc/kernel/unwind.c @@ -170,6 +170,23 @@ static struct unwind_table *find_table(unsigned long pc) static unsigned long read_pointer(const u8 **pLoc, const void *end, signed ptrType); +static void init_unwind_hdr(struct unwind_table *table, + void *(*alloc) (unsigned long)); + +/* + * wrappers for header alloc (vs. calling one vs. other at call site) + * to elide section mismatches warnings + */ +static void *__init unw_hdr_alloc_early(unsigned long sz) +{ + return __alloc_bootmem_nopanic(sz, sizeof(unsigned int), + MAX_DMA_ADDRESS); +} + +static void *unw_hdr_alloc(unsigned long sz) +{ + return kmalloc(sz, GFP_KERNEL); +} static void init_unwind_table(struct unwind_table *table, const char *name, const void *core_start, unsigned long core_size, @@ -209,6 +226,8 @@ void __init arc_unwind_init(void) __start_unwind, __end_unwind - __start_unwind, NULL, 0); /*__start_unwind_hdr, __end_unwind_hdr - __start_unwind_hdr);*/ + + init_unwind_hdr(&root_table, unw_hdr_alloc_early); } static const u32 bad_cie, not_fde; @@ -241,8 +260,8 @@ static void swap_eh_frame_hdr_table_entries(void *p1, void *p2, int size) e2->fde = v; } -static void __init setup_unwind_table(struct unwind_table *table, - void *(*alloc) (unsigned long)) +static void init_unwind_hdr(struct unwind_table *table, + void *(*alloc) (unsigned long)) { const u8 *ptr; unsigned long tableSize = table->size, hdrSize; @@ -277,10 +296,10 @@ static void __init setup_unwind_table(struct unwind_table *table, if (cie == ¬_fde) continue; if (cie == NULL || cie == &bad_cie) - return; + goto ret_err; ptrType = fde_pointer_type(cie); if (ptrType < 0) - return; + goto ret_err; ptr = (const u8 *)(fde + 2); if (!read_pointer(&ptr, (const u8 *)(fde + 1) + *fde, @@ -296,13 +315,15 @@ static void __init setup_unwind_table(struct unwind_table *table, } if (tableSize || !n) - return; + goto ret_err; hdrSize = 4 + sizeof(unsigned long) + sizeof(unsigned int) + 2 * n * sizeof(unsigned long); + header = alloc(hdrSize); if (!header) - return; + goto ret_err; + header->version = 1; header->eh_frame_ptr_enc = DW_EH_PE_abs | DW_EH_PE_native; header->fde_count_enc = DW_EH_PE_abs | DW_EH_PE_data4; @@ -340,18 +361,10 @@ static void __init setup_unwind_table(struct unwind_table *table, table->hdrsz = hdrSize; smp_wmb(); table->header = (const void *)header; -} - -static void *__init balloc(unsigned long sz) -{ - return __alloc_bootmem_nopanic(sz, - sizeof(unsigned int), - __pa(MAX_DMA_ADDRESS)); -} + return; -void __init arc_unwind_setup(void) -{ - setup_unwind_table(&root_table, balloc); +ret_err: + panic("Attention !!! Dwarf FDE parsing errors\n");; } #ifdef CONFIG_MODULES @@ -377,6 +390,8 @@ void *unwind_add_table(struct module *module, const void *table_start, table_start, table_size, NULL, 0); + init_unwind_hdr(table, unw_hdr_alloc); + #ifdef UNWIND_DEBUG unw_debug("Table added for [%s] %lx %lx\n", module->name, table->core.pc, table->core.range); @@ -439,6 +454,7 @@ void unwind_remove_table(void *handle, int init_only) info.init_only = init_only; unlink_table(&info); /* XXX: SMP */ + kfree(table->header); kfree(table); } @@ -588,9 +604,6 @@ static signed fde_pointer_type(const u32 *cie) const u8 *ptr = (const u8 *)(cie + 2); unsigned version = *ptr; - if (version != 1) - return -1; /* unsupported */ - if (*++ptr) { const char *aug; const u8 *end = (const u8 *)(cie + 1) + *cie; @@ -986,42 +999,13 @@ int arc_unwind(struct unwind_frame_info *frame) (const u8 *)(fde + 1) + *fde, ptrType); - if (pc >= endLoc) + if (pc >= endLoc) { fde = NULL; - } else - fde = NULL; - } - if (fde == NULL) { - for (fde = table->address, tableSize = table->size; - cie = NULL, tableSize > sizeof(*fde) - && tableSize - sizeof(*fde) >= *fde; - tableSize -= sizeof(*fde) + *fde, - fde += 1 + *fde / sizeof(*fde)) { - cie = cie_for_fde(fde, table); - if (cie == &bad_cie) { cie = NULL; - break; } - if (cie == NULL - || cie == ¬_fde - || (ptrType = fde_pointer_type(cie)) < 0) - continue; - ptr = (const u8 *)(fde + 2); - startLoc = read_pointer(&ptr, - (const u8 *)(fde + 1) + - *fde, ptrType); - if (!startLoc) - continue; - if (!(ptrType & DW_EH_PE_indirect)) - ptrType &= - DW_EH_PE_FORM | DW_EH_PE_signed; - endLoc = - startLoc + read_pointer(&ptr, - (const u8 *)(fde + - 1) + - *fde, ptrType); - if (pc >= startLoc && pc < endLoc) - break; + } else { + fde = NULL; + cie = NULL; } } } @@ -1031,9 +1015,7 @@ int arc_unwind(struct unwind_frame_info *frame) ptr = (const u8 *)(cie + 2); end = (const u8 *)(cie + 1) + *cie; frame->call_frame = 1; - if ((state.version = *ptr) != 1) - cie = NULL; /* unsupported version */ - else if (*++ptr) { + if (*++ptr) { /* check if augmentation size is first (thus present) */ if (*ptr == 'z') { while (++ptr < end && *ptr) { diff --git a/arch/arc/mm/highmem.c b/arch/arc/mm/highmem.c index 065ee6bfa82a..92dd92cad7f9 100644 --- a/arch/arc/mm/highmem.c +++ b/arch/arc/mm/highmem.c @@ -111,7 +111,7 @@ void __kunmap_atomic(void *kv) } EXPORT_SYMBOL(__kunmap_atomic); -noinline pte_t *alloc_kmap_pgtable(unsigned long kvaddr) +static noinline pte_t * __init alloc_kmap_pgtable(unsigned long kvaddr) { pgd_t *pgd_k; pud_t *pud_k; @@ -127,7 +127,7 @@ noinline pte_t *alloc_kmap_pgtable(unsigned long kvaddr) return pte_k; } -void kmap_init(void) +void __init kmap_init(void) { /* Due to recursive include hell, we can't do this in processor.h */ BUILD_BUG_ON(PAGE_OFFSET < (VMALLOC_END + FIXMAP_SIZE + PKMAP_SIZE)); diff --git a/arch/arc/mm/init.c b/arch/arc/mm/init.c index a9305b5a2cd4..7d2c4fbf4f22 100644 --- a/arch/arc/mm/init.c +++ b/arch/arc/mm/init.c @@ -51,7 +51,9 @@ void __init early_init_dt_add_memory_arch(u64 base, u64 size) int in_use = 0; if (!low_mem_sz) { - BUG_ON(base != low_mem_start); + if (base != low_mem_start) + panic("CONFIG_LINUX_LINK_BASE != DT memory { }"); + low_mem_sz = size; in_use = 1; } else { diff --git a/arch/arc/mm/tlb.c b/arch/arc/mm/tlb.c index 0ee739846847..daf2bf52b984 100644 --- a/arch/arc/mm/tlb.c +++ b/arch/arc/mm/tlb.c @@ -619,10 +619,10 @@ void update_mmu_cache(struct vm_area_struct *vma, unsigned long vaddr_unaligned, int dirty = !test_and_set_bit(PG_dc_clean, &page->flags); if (dirty) { - /* wback + inv dcache lines */ + /* wback + inv dcache lines (K-mapping) */ __flush_dcache_page(paddr, paddr); - /* invalidate any existing icache lines */ + /* invalidate any existing icache lines (U-mapping) */ if (vma->vm_flags & VM_EXEC) __inv_icache_page(paddr, vaddr); } diff --git a/arch/arm/Kconfig b/arch/arm/Kconfig index 0365cbbc9179..688dc7b0d951 100644 --- a/arch/arm/Kconfig +++ b/arch/arm/Kconfig @@ -76,6 +76,8 @@ config ARM select IRQ_FORCED_THREADING select MODULES_USE_ELF_REL select NO_BOOTMEM + select OF_EARLY_FLATTREE if OF + select OF_RESERVED_MEM if OF select OLD_SIGACTION select OLD_SIGSUSPEND3 select PERF_USE_VMALLOC @@ -609,6 +611,7 @@ config ARCH_PXA select AUTO_ZRELADDR select COMMON_CLK select CLKDEV_LOOKUP + select CLKSRC_PXA select CLKSRC_MMIO select CLKSRC_OF select GENERIC_CLOCKEVENTS @@ -648,6 +651,8 @@ config ARCH_SA1100 select ARCH_SPARSEMEM_ENABLE select CLKDEV_LOOKUP select CLKSRC_MMIO + select CLKSRC_PXA + select CLKSRC_OF if OF select CPU_FREQ select CPU_SA1100 select GENERIC_CLOCKEVENTS @@ -1822,8 +1827,6 @@ config USE_OF bool "Flattened Device Tree support" select IRQ_DOMAIN select OF - select OF_EARLY_FLATTREE - select OF_RESERVED_MEM help Include support for flattened device tree machine descriptions. diff --git a/arch/arm/boot/dts/am4372.dtsi b/arch/arm/boot/dts/am4372.dtsi index d83ff9c9701e..de8791a4d131 100644 --- a/arch/arm/boot/dts/am4372.dtsi +++ b/arch/arm/boot/dts/am4372.dtsi @@ -74,7 +74,7 @@ reg = <0x48240200 0x100>; interrupts = <GIC_PPI 11 IRQ_TYPE_LEVEL_HIGH>; interrupt-parent = <&gic>; - clocks = <&dpll_mpu_m2_ck>; + clocks = <&mpu_periphclk>; }; local_timer: timer@48240600 { @@ -82,7 +82,7 @@ reg = <0x48240600 0x100>; interrupts = <GIC_PPI 13 IRQ_TYPE_LEVEL_HIGH>; interrupt-parent = <&gic>; - clocks = <&dpll_mpu_m2_ck>; + clocks = <&mpu_periphclk>; }; l2-cache-controller@48242000 { diff --git a/arch/arm/boot/dts/am43xx-clocks.dtsi b/arch/arm/boot/dts/am43xx-clocks.dtsi index cc88728d751d..a38af2bfbfcf 100644 --- a/arch/arm/boot/dts/am43xx-clocks.dtsi +++ b/arch/arm/boot/dts/am43xx-clocks.dtsi @@ -259,6 +259,14 @@ ti,invert-autoidle-bit; }; + mpu_periphclk: mpu_periphclk { + #clock-cells = <0>; + compatible = "fixed-factor-clock"; + clocks = <&dpll_mpu_m2_ck>; + clock-mult = <1>; + clock-div = <2>; + }; + dpll_ddr_ck: dpll_ddr_ck { #clock-cells = <0>; compatible = "ti,am3-dpll-clock"; diff --git a/arch/arm/boot/dts/am57xx-beagle-x15.dts b/arch/arm/boot/dts/am57xx-beagle-x15.dts index d9ba6b879fc1..00352e761b8c 100644 --- a/arch/arm/boot/dts/am57xx-beagle-x15.dts +++ b/arch/arm/boot/dts/am57xx-beagle-x15.dts @@ -604,6 +604,7 @@ reg = <0x6f>; interrupts-extended = <&crossbar_mpu GIC_SPI 2 IRQ_TYPE_EDGE_RISING>, <&dra7_pmx_core 0x424>; + interrupt-names = "irq", "wakeup"; pinctrl-names = "default"; pinctrl-0 = <&mcp79410_pins_default>; diff --git a/arch/arm/boot/dts/animeo_ip.dts b/arch/arm/boot/dts/animeo_ip.dts index 4e0ad3b82796..0962f2fa3f6e 100644 --- a/arch/arm/boot/dts/animeo_ip.dts +++ b/arch/arm/boot/dts/animeo_ip.dts @@ -155,21 +155,21 @@ label = "keyswitch_in"; gpios = <&pioB 1 GPIO_ACTIVE_HIGH>; linux,code = <28>; - gpio-key,wakeup; + wakeup-source; }; error_in { label = "error_in"; gpios = <&pioB 2 GPIO_ACTIVE_HIGH>; linux,code = <29>; - gpio-key,wakeup; + wakeup-source; }; btn { label = "btn"; gpios = <&pioC 23 GPIO_ACTIVE_HIGH>; linux,code = <31>; - gpio-key,wakeup; + wakeup-source; }; }; }; diff --git a/arch/arm/boot/dts/armada-38x.dtsi b/arch/arm/boot/dts/armada-38x.dtsi index c6a0e9d7f1a9..e8b7f6726772 100644 --- a/arch/arm/boot/dts/armada-38x.dtsi +++ b/arch/arm/boot/dts/armada-38x.dtsi @@ -498,6 +498,7 @@ reg = <0x70000 0x4000>; interrupts-extended = <&mpic 8>; clocks = <&gateclk 4>; + tx-csum-limit = <9800>; status = "disabled"; }; diff --git a/arch/arm/boot/dts/at91-foxg20.dts b/arch/arm/boot/dts/at91-foxg20.dts index f89598af4c2b..6bf873e7d96c 100644 --- a/arch/arm/boot/dts/at91-foxg20.dts +++ b/arch/arm/boot/dts/at91-foxg20.dts @@ -159,7 +159,7 @@ label = "Button"; gpios = <&pioC 4 GPIO_ACTIVE_LOW>; linux,code = <0x103>; - gpio-key,wakeup; + wakeup-source; }; }; }; diff --git a/arch/arm/boot/dts/at91-kizbox.dts b/arch/arm/boot/dts/at91-kizbox.dts index bf18ece0c027..229e989eb60d 100644 --- a/arch/arm/boot/dts/at91-kizbox.dts +++ b/arch/arm/boot/dts/at91-kizbox.dts @@ -24,15 +24,6 @@ }; clocks { - #address-cells = <1>; - #size-cells = <1>; - ranges; - - main_clock: clock@0 { - compatible = "atmel,osc", "fixed-clock"; - clock-frequency = <18432000>; - }; - main_xtal { clock-frequency = <18432000>; }; @@ -94,14 +85,14 @@ label = "PB_RST"; gpios = <&pioB 30 GPIO_ACTIVE_HIGH>; linux,code = <0x100>; - gpio-key,wakeup; + wakeup-source; }; user { label = "PB_USER"; gpios = <&pioB 31 GPIO_ACTIVE_HIGH>; linux,code = <0x101>; - gpio-key,wakeup; + wakeup-source; }; }; diff --git a/arch/arm/boot/dts/at91-kizbox2.dts b/arch/arm/boot/dts/at91-kizbox2.dts index f0b1563cb3f1..50a14568f094 100644 --- a/arch/arm/boot/dts/at91-kizbox2.dts +++ b/arch/arm/boot/dts/at91-kizbox2.dts @@ -171,21 +171,21 @@ label = "PB_PROG"; gpios = <&pioE 27 GPIO_ACTIVE_LOW>; linux,code = <0x102>; - gpio-key,wakeup; + wakeup-source; }; reset { label = "PB_RST"; gpios = <&pioE 29 GPIO_ACTIVE_LOW>; linux,code = <0x100>; - gpio-key,wakeup; + wakeup-source; }; user { label = "PB_USER"; gpios = <&pioE 31 GPIO_ACTIVE_HIGH>; linux,code = <0x101>; - gpio-key,wakeup; + wakeup-source; }; }; diff --git a/arch/arm/boot/dts/at91-kizboxmini.dts b/arch/arm/boot/dts/at91-kizboxmini.dts index 9f72b4932634..9682d105d4d8 100644 --- a/arch/arm/boot/dts/at91-kizboxmini.dts +++ b/arch/arm/boot/dts/at91-kizboxmini.dts @@ -98,14 +98,14 @@ label = "PB_PROG"; gpios = <&pioC 17 GPIO_ACTIVE_LOW>; linux,code = <0x102>; - gpio-key,wakeup; + wakeup-source; }; reset { label = "PB_RST"; gpios = <&pioC 16 GPIO_ACTIVE_LOW>; linux,code = <0x100>; - gpio-key,wakeup; + wakeup-source; }; }; diff --git a/arch/arm/boot/dts/at91-qil_a9260.dts b/arch/arm/boot/dts/at91-qil_a9260.dts index a9aef53ab764..4f2eebf4a560 100644 --- a/arch/arm/boot/dts/at91-qil_a9260.dts +++ b/arch/arm/boot/dts/at91-qil_a9260.dts @@ -183,7 +183,7 @@ label = "user_pb"; gpios = <&pioB 10 GPIO_ACTIVE_LOW>; linux,code = <28>; - gpio-key,wakeup; + wakeup-source; }; }; diff --git a/arch/arm/boot/dts/at91-sama5d2_xplained.dts b/arch/arm/boot/dts/at91-sama5d2_xplained.dts index e07c2b206beb..e74df327cdd3 100644 --- a/arch/arm/boot/dts/at91-sama5d2_xplained.dts +++ b/arch/arm/boot/dts/at91-sama5d2_xplained.dts @@ -45,6 +45,7 @@ /dts-v1/; #include "sama5d2.dtsi" #include "sama5d2-pinfunc.h" +#include <dt-bindings/mfd/atmel-flexcom.h> / { model = "Atmel SAMA5D2 Xplained"; @@ -59,15 +60,6 @@ }; clocks { - #address-cells = <1>; - #size-cells = <1>; - ranges; - - main_clock: clock@0 { - compatible = "atmel,osc", "fixed-clock"; - clock-frequency = <12000000>; - }; - slow_xtal { clock-frequency = <32768>; }; @@ -91,6 +83,22 @@ status = "okay"; }; + sdmmc0: sdio-host@a0000000 { + bus-width = <8>; + pinctrl-names = "default"; + pinctrl-0 = <&pinctrl_sdmmc0_default>; + non-removable; + mmc-ddr-1_8v; + status = "okay"; + }; + + sdmmc1: sdio-host@b0000000 { + bus-width = <4>; + pinctrl-names = "default"; + pinctrl-0 = <&pinctrl_sdmmc1_default>; + status = "okay"; /* conflict with qspi0 */ + }; + apb { spi0: spi@f8000000 { pinctrl-names = "default"; @@ -176,17 +184,55 @@ regulator-name = "VDD_SDHC_1V8"; regulator-min-microvolt = <1800000>; regulator-max-microvolt = <1800000>; + regulator-always-on; }; }; }; }; + flx0: flexcom@f8034000 { + atmel,flexcom-mode = <ATMEL_FLEXCOM_MODE_USART>; + status = "disabled"; /* conflict with ISC_D2 & ISC_D3 data pins */ + + uart5: serial@200 { + compatible = "atmel,at91sam9260-usart"; + reg = <0x200 0x200>; + interrupts = <19 IRQ_TYPE_LEVEL_HIGH 7>; + clocks = <&flx0_clk>; + clock-names = "usart"; + pinctrl-names = "default"; + pinctrl-0 = <&pinctrl_flx0_default>; + atmel,fifo-size = <32>; + status = "okay"; + }; + }; + uart3: serial@fc008000 { pinctrl-names = "default"; pinctrl-0 = <&pinctrl_uart3_default>; status = "okay"; }; + flx4: flexcom@fc018000 { + atmel,flexcom-mode = <ATMEL_FLEXCOM_MODE_TWI>; + status = "okay"; + + i2c2: i2c@600 { + compatible = "atmel,sama5d2-i2c"; + reg = <0x600 0x200>; + interrupts = <23 IRQ_TYPE_LEVEL_HIGH 7>; + dmas = <0>, <0>; + dma-names = "tx", "rx"; + #address-cells = <1>; + #size-cells = <0>; + clocks = <&flx4_clk>; + pinctrl-names = "default"; + pinctrl-0 = <&pinctrl_flx4_default>; + atmel,fifo-size = <16>; + status = "okay"; + }; + }; + i2c1: i2c@fc028000 { dmas = <0>, <0>; pinctrl-names = "default"; @@ -201,6 +247,18 @@ }; pinctrl@fc038000 { + pinctrl_flx0_default: flx0_default { + pinmux = <PIN_PB28__FLEXCOM0_IO0>, + <PIN_PB29__FLEXCOM0_IO1>; + bias-disable; + }; + + pinctrl_flx4_default: flx4_default { + pinmux = <PIN_PD12__FLEXCOM4_IO0>, + <PIN_PD13__FLEXCOM4_IO1>; + bias-disable; + }; + pinctrl_i2c0_default: i2c0_default { pinmux = <PIN_PD21__TWD0>, <PIN_PD22__TWCK0>; @@ -227,6 +285,46 @@ bias-disable; }; + pinctrl_sdmmc0_default: sdmmc0_default { + cmd_data { + pinmux = <PIN_PA1__SDMMC0_CMD>, + <PIN_PA2__SDMMC0_DAT0>, + <PIN_PA3__SDMMC0_DAT1>, + <PIN_PA4__SDMMC0_DAT2>, + <PIN_PA5__SDMMC0_DAT3>, + <PIN_PA6__SDMMC0_DAT4>, + <PIN_PA7__SDMMC0_DAT5>, + <PIN_PA8__SDMMC0_DAT6>, + <PIN_PA9__SDMMC0_DAT7>; + bias-pull-up; + }; + + ck_cd_rstn_vddsel { + pinmux = <PIN_PA0__SDMMC0_CK>, + <PIN_PA10__SDMMC0_RSTN>, + <PIN_PA11__SDMMC0_VDDSEL>, + <PIN_PA13__SDMMC0_CD>; + bias-disable; + }; + }; + + pinctrl_sdmmc1_default: sdmmc1_default { + cmd_data { + pinmux = <PIN_PA28__SDMMC1_CMD>, + <PIN_PA18__SDMMC1_DAT0>, + <PIN_PA19__SDMMC1_DAT1>, + <PIN_PA20__SDMMC1_DAT2>, + <PIN_PA21__SDMMC1_DAT3>; + bias-pull-up; + }; + + conf-ck_cd { + pinmux = <PIN_PA22__SDMMC1_CK>, + <PIN_PA30__SDMMC1_CD>; + bias-disable; + }; + }; + pinctrl_spi0_default: spi0_default { pinmux = <PIN_PA14__SPI0_SPCK>, <PIN_PA15__SPI0_MOSI>, diff --git a/arch/arm/boot/dts/at91-sama5d3_xplained.dts b/arch/arm/boot/dts/at91-sama5d3_xplained.dts index 8488ac53d22d..ff888d21c786 100644 --- a/arch/arm/boot/dts/at91-sama5d3_xplained.dts +++ b/arch/arm/boot/dts/at91-sama5d3_xplained.dts @@ -315,7 +315,7 @@ label = "PB_USER"; gpios = <&pioE 29 GPIO_ACTIVE_LOW>; linux,code = <0x104>; - gpio-key,wakeup; + wakeup-source; }; }; diff --git a/arch/arm/boot/dts/at91-sama5d4_xplained.dts b/arch/arm/boot/dts/at91-sama5d4_xplained.dts index 45371a1b61b3..131614f28e75 100644 --- a/arch/arm/boot/dts/at91-sama5d4_xplained.dts +++ b/arch/arm/boot/dts/at91-sama5d4_xplained.dts @@ -50,7 +50,6 @@ compatible = "atmel,sama5d4-xplained", "atmel,sama5d4", "atmel,sama5"; chosen { - bootargs = "ignore_loglevel earlyprintk"; stdout-path = "serial0:115200n8"; }; @@ -59,15 +58,6 @@ }; clocks { - #address-cells = <1>; - #size-cells = <1>; - ranges; - - main_clock: clock@0 { - compatible = "atmel,osc", "fixed-clock"; - clock-frequency = <12000000>; - }; - slow_xtal { clock-frequency = <32768>; }; @@ -235,7 +225,7 @@ label = "pb_user1"; gpios = <&pioE 8 GPIO_ACTIVE_HIGH>; linux,code = <0x100>; - gpio-key,wakeup; + wakeup-source; }; }; diff --git a/arch/arm/boot/dts/at91-sama5d4ek.dts b/arch/arm/boot/dts/at91-sama5d4ek.dts index 6d272c0125e3..2d4a33100af6 100644 --- a/arch/arm/boot/dts/at91-sama5d4ek.dts +++ b/arch/arm/boot/dts/at91-sama5d4ek.dts @@ -50,7 +50,6 @@ compatible = "atmel,sama5d4ek", "atmel,sama5d4", "atmel,sama5"; chosen { - bootargs = "ignore_loglevel earlyprintk"; stdout-path = "serial0:115200n8"; }; @@ -59,15 +58,6 @@ }; clocks { - #address-cells = <1>; - #size-cells = <1>; - ranges; - - main_clock: clock@0 { - compatible = "atmel,osc", "fixed-clock"; - clock-frequency = <12000000>; - }; - slow_xtal { clock-frequency = <32768>; }; @@ -304,7 +294,7 @@ label = "pb_user1"; gpios = <&pioE 13 GPIO_ACTIVE_HIGH>; linux,code = <0x100>; - gpio-key,wakeup; + wakeup-source; }; }; diff --git a/arch/arm/boot/dts/at91rm9200ek.dts b/arch/arm/boot/dts/at91rm9200ek.dts index 8dab4b75ca97..f90e1c2d3caa 100644 --- a/arch/arm/boot/dts/at91rm9200ek.dts +++ b/arch/arm/boot/dts/at91rm9200ek.dts @@ -21,15 +21,6 @@ }; clocks { - #address-cells = <1>; - #size-cells = <1>; - ranges; - - main_clock: clock@0 { - compatible = "atmel,osc", "fixed-clock"; - clock-frequency = <18432000>; - }; - slow_xtal { clock-frequency = <32768>; }; diff --git a/arch/arm/boot/dts/at91sam9261ek.dts b/arch/arm/boot/dts/at91sam9261ek.dts index 2e92ac020f23..55bd51f07fa6 100644 --- a/arch/arm/boot/dts/at91sam9261ek.dts +++ b/arch/arm/boot/dts/at91sam9261ek.dts @@ -22,15 +22,6 @@ }; clocks { - #address-cells = <1>; - #size-cells = <1>; - ranges; - - main_clock: clock@0 { - compatible = "atmel,osc", "fixed-clock"; - clock-frequency = <18432000>; - }; - slow_xtal { clock-frequency = <32768>; }; @@ -149,7 +140,7 @@ ti,debounce-tol = /bits/ 16 <65535>; ti,debounce-max = /bits/ 16 <1>; - linux,wakeup; + wakeup-source; }; }; @@ -193,28 +184,28 @@ label = "button_0"; gpios = <&pioA 27 GPIO_ACTIVE_LOW>; linux,code = <256>; - gpio-key,wakeup; + wakeup-source; }; button_1 { label = "button_1"; gpios = <&pioA 26 GPIO_ACTIVE_LOW>; linux,code = <257>; - gpio-key,wakeup; + wakeup-source; }; button_2 { label = "button_2"; gpios = <&pioA 25 GPIO_ACTIVE_LOW>; linux,code = <258>; - gpio-key,wakeup; + wakeup-source; }; button_3 { label = "button_3"; gpios = <&pioA 24 GPIO_ACTIVE_LOW>; linux,code = <259>; - gpio-key,wakeup; + wakeup-source; }; }; }; diff --git a/arch/arm/boot/dts/at91sam9263ek.dts b/arch/arm/boot/dts/at91sam9263ek.dts index 23381276ffb8..59df9d73d276 100644 --- a/arch/arm/boot/dts/at91sam9263ek.dts +++ b/arch/arm/boot/dts/at91sam9263ek.dts @@ -22,15 +22,6 @@ }; clocks { - #address-cells = <1>; - #size-cells = <1>; - ranges; - - main_clock: clock@0 { - compatible = "atmel,osc", "fixed-clock"; - clock-frequency = <16367660>; - }; - slow_xtal { clock-frequency = <32768>; }; @@ -213,14 +204,14 @@ label = "left_click"; gpios = <&pioC 5 GPIO_ACTIVE_LOW>; linux,code = <272>; - gpio-key,wakeup; + wakeup-source; }; right_click { label = "right_click"; gpios = <&pioC 4 GPIO_ACTIVE_LOW>; linux,code = <273>; - gpio-key,wakeup; + wakeup-source; }; }; diff --git a/arch/arm/boot/dts/at91sam9g20ek_common.dtsi b/arch/arm/boot/dts/at91sam9g20ek_common.dtsi index 57548a2c5a1e..e9cc99b6353a 100644 --- a/arch/arm/boot/dts/at91sam9g20ek_common.dtsi +++ b/arch/arm/boot/dts/at91sam9g20ek_common.dtsi @@ -19,15 +19,6 @@ }; clocks { - #address-cells = <1>; - #size-cells = <1>; - ranges; - - main_clock: clock@0 { - compatible = "atmel,osc", "fixed-clock"; - clock-frequency = <18432000>; - }; - slow_xtal { clock-frequency = <32768>; }; @@ -206,14 +197,14 @@ label = "Button 3"; gpios = <&pioA 30 GPIO_ACTIVE_LOW>; linux,code = <0x103>; - gpio-key,wakeup; + wakeup-source; }; btn4 { label = "Button 4"; gpios = <&pioA 31 GPIO_ACTIVE_LOW>; linux,code = <0x104>; - gpio-key,wakeup; + wakeup-source; }; }; diff --git a/arch/arm/boot/dts/at91sam9m10g45ek.dts b/arch/arm/boot/dts/at91sam9m10g45ek.dts index 9d16ef8453c5..2400c99134f7 100644 --- a/arch/arm/boot/dts/at91sam9m10g45ek.dts +++ b/arch/arm/boot/dts/at91sam9m10g45ek.dts @@ -24,15 +24,6 @@ }; clocks { - #address-cells = <1>; - #size-cells = <1>; - ranges; - - main_clock: clock@0 { - compatible = "atmel,osc", "fixed-clock"; - clock-frequency = <12000000>; - }; - slow_xtal { clock-frequency = <32768>; }; @@ -323,14 +314,14 @@ label = "left_click"; gpios = <&pioB 6 GPIO_ACTIVE_LOW>; linux,code = <272>; - gpio-key,wakeup; + wakeup-source; }; right_click { label = "right_click"; gpios = <&pioB 7 GPIO_ACTIVE_LOW>; linux,code = <273>; - gpio-key,wakeup; + wakeup-source; }; left { diff --git a/arch/arm/boot/dts/at91sam9n12ek.dts b/arch/arm/boot/dts/at91sam9n12ek.dts index acf3451a332d..ca4ddf86817a 100644 --- a/arch/arm/boot/dts/at91sam9n12ek.dts +++ b/arch/arm/boot/dts/at91sam9n12ek.dts @@ -23,15 +23,6 @@ }; clocks { - #address-cells = <1>; - #size-cells = <1>; - ranges; - - main_clock: clock@0 { - compatible = "atmel,osc", "fixed-clock"; - clock-frequency = <16000000>; - }; - slow_xtal { clock-frequency = <32768>; }; @@ -219,7 +210,7 @@ label = "Enter"; gpios = <&pioB 3 GPIO_ACTIVE_LOW>; linux,code = <28>; - gpio-key,wakeup; + wakeup-source; }; }; diff --git a/arch/arm/boot/dts/at91sam9rlek.dts b/arch/arm/boot/dts/at91sam9rlek.dts index 558c9f220bed..f10566f759cd 100644 --- a/arch/arm/boot/dts/at91sam9rlek.dts +++ b/arch/arm/boot/dts/at91sam9rlek.dts @@ -22,15 +22,6 @@ }; clocks { - #address-cells = <1>; - #size-cells = <1>; - ranges; - - main_clock: clock { - compatible = "atmel,osc", "fixed-clock"; - clock-frequency = <12000000>; - }; - slow_xtal { clock-frequency = <32768>; }; @@ -225,14 +216,14 @@ label = "right_click"; gpios = <&pioB 0 GPIO_ACTIVE_LOW>; linux,code = <273>; - gpio-key,wakeup; + wakeup-source; }; left_click { label = "left_click"; gpios = <&pioB 1 GPIO_ACTIVE_LOW>; linux,code = <272>; - gpio-key,wakeup; + wakeup-source; }; }; diff --git a/arch/arm/boot/dts/at91sam9x5cm.dtsi b/arch/arm/boot/dts/at91sam9x5cm.dtsi index 26112ebd15fc..b098ad8cd93a 100644 --- a/arch/arm/boot/dts/at91sam9x5cm.dtsi +++ b/arch/arm/boot/dts/at91sam9x5cm.dtsi @@ -13,17 +13,6 @@ }; clocks { - #address-cells = <1>; - #size-cells = <1>; - ranges; - - main_clock: clock@0 { - compatible = "atmel,osc", "fixed-clock"; - clock-frequency = <12000000>; - }; - }; - - clocks { slow_xtal { clock-frequency = <32768>; }; diff --git a/arch/arm/boot/dts/berlin2q.dtsi b/arch/arm/boot/dts/berlin2q.dtsi index 8ea177f375dd..fb1da99996ea 100644 --- a/arch/arm/boot/dts/berlin2q.dtsi +++ b/arch/arm/boot/dts/berlin2q.dtsi @@ -118,7 +118,8 @@ sdhci0: sdhci@ab0000 { compatible = "mrvl,pxav3-mmc"; reg = <0xab0000 0x200>; - clocks = <&chip_clk CLKID_SDIO1XIN>; + clocks = <&chip_clk CLKID_SDIO1XIN>, <&chip_clk CLKID_SDIO>; + clock-names = "io", "core"; interrupts = <GIC_SPI 17 IRQ_TYPE_LEVEL_HIGH>; status = "disabled"; }; @@ -126,7 +127,8 @@ sdhci1: sdhci@ab0800 { compatible = "mrvl,pxav3-mmc"; reg = <0xab0800 0x200>; - clocks = <&chip_clk CLKID_SDIO1XIN>; + clocks = <&chip_clk CLKID_SDIO1XIN>, <&chip_clk CLKID_SDIO>; + clock-names = "io", "core"; interrupts = <GIC_SPI 20 IRQ_TYPE_LEVEL_HIGH>; status = "disabled"; }; @@ -135,7 +137,7 @@ compatible = "mrvl,pxav3-mmc"; reg = <0xab1000 0x200>; interrupts = <GIC_SPI 28 IRQ_TYPE_LEVEL_HIGH>; - clocks = <&chip_clk CLKID_NFC_ECC>, <&chip_clk CLKID_NFC>; + clocks = <&chip_clk CLKID_NFC_ECC>, <&chip_clk CLKID_SDIO>; clock-names = "io", "core"; status = "disabled"; }; diff --git a/arch/arm/boot/dts/dm816x.dtsi b/arch/arm/boot/dts/dm816x.dtsi index 3c99cfa1a876..eee636de4cd8 100644 --- a/arch/arm/boot/dts/dm816x.dtsi +++ b/arch/arm/boot/dts/dm816x.dtsi @@ -218,6 +218,7 @@ reg = <0x480c8000 0x2000>; interrupts = <77>; ti,hwmods = "mailbox"; + #mbox-cells = <1>; ti,mbox-num-users = <4>; ti,mbox-num-fifos = <12>; mbox_dsp: mbox_dsp { @@ -279,8 +280,11 @@ ti,spi-num-cs = <4>; ti,hwmods = "mcspi1"; dmas = <&edma 16 &edma 17 - &edma 18 &edma 19>; - dma-names = "tx0", "rx0", "tx1", "rx1"; + &edma 18 &edma 19 + &edma 20 &edma 21 + &edma 22 &edma 23>; + dma-names = "tx0", "rx0", "tx1", "rx1", + "tx2", "rx2", "tx3", "rx3"; }; mmc1: mmc@48060000 { diff --git a/arch/arm/boot/dts/dra7.dtsi b/arch/arm/boot/dts/dra7.dtsi index bc672fb91466..fe99231cbde5 100644 --- a/arch/arm/boot/dts/dra7.dtsi +++ b/arch/arm/boot/dts/dra7.dtsi @@ -1459,8 +1459,8 @@ interrupt-names = "tx", "rx"; dmas = <&sdma_xbar 133>, <&sdma_xbar 132>; dma-names = "tx", "rx"; - clocks = <&mcasp3_ahclkx_mux>; - clock-names = "fck"; + clocks = <&mcasp3_aux_gfclk_mux>, <&mcasp3_ahclkx_mux>; + clock-names = "fck", "ahclkx"; status = "disabled"; }; diff --git a/arch/arm/boot/dts/imx27.dtsi b/arch/arm/boot/dts/imx27.dtsi index feb9d34b239c..f818ea483aeb 100644 --- a/arch/arm/boot/dts/imx27.dtsi +++ b/arch/arm/boot/dts/imx27.dtsi @@ -486,7 +486,10 @@ compatible = "fsl,imx27-usb"; reg = <0x10024000 0x200>; interrupts = <56>; - clocks = <&clks IMX27_CLK_USB_IPG_GATE>; + clocks = <&clks IMX27_CLK_USB_IPG_GATE>, + <&clks IMX27_CLK_USB_AHB_GATE>, + <&clks IMX27_CLK_USB_DIV>; + clock-names = "ipg", "ahb", "per"; fsl,usbmisc = <&usbmisc 0>; status = "disabled"; }; @@ -495,7 +498,10 @@ compatible = "fsl,imx27-usb"; reg = <0x10024200 0x200>; interrupts = <54>; - clocks = <&clks IMX27_CLK_USB_IPG_GATE>; + clocks = <&clks IMX27_CLK_USB_IPG_GATE>, + <&clks IMX27_CLK_USB_AHB_GATE>, + <&clks IMX27_CLK_USB_DIV>; + clock-names = "ipg", "ahb", "per"; fsl,usbmisc = <&usbmisc 1>; dr_mode = "host"; status = "disabled"; @@ -505,7 +511,10 @@ compatible = "fsl,imx27-usb"; reg = <0x10024400 0x200>; interrupts = <55>; - clocks = <&clks IMX27_CLK_USB_IPG_GATE>; + clocks = <&clks IMX27_CLK_USB_IPG_GATE>, + <&clks IMX27_CLK_USB_AHB_GATE>, + <&clks IMX27_CLK_USB_DIV>; + clock-names = "ipg", "ahb", "per"; fsl,usbmisc = <&usbmisc 2>; dr_mode = "host"; status = "disabled"; @@ -515,7 +524,6 @@ #index-cells = <1>; compatible = "fsl,imx27-usbmisc"; reg = <0x10024600 0x200>; - clocks = <&clks IMX27_CLK_USB_AHB_GATE>; }; sahara2: sahara@10025000 { diff --git a/arch/arm/boot/dts/imx6q-gw5400-a.dts b/arch/arm/boot/dts/imx6q-gw5400-a.dts index 58adf176425a..a51834e1dd27 100644 --- a/arch/arm/boot/dts/imx6q-gw5400-a.dts +++ b/arch/arm/boot/dts/imx6q-gw5400-a.dts @@ -154,7 +154,7 @@ &fec { pinctrl-names = "default"; pinctrl-0 = <&pinctrl_enet>; - phy-mode = "rgmii"; + phy-mode = "rgmii-id"; phy-reset-gpios = <&gpio1 30 GPIO_ACTIVE_HIGH>; status = "okay"; }; diff --git a/arch/arm/boot/dts/imx6qdl-gw51xx.dtsi b/arch/arm/boot/dts/imx6qdl-gw51xx.dtsi index 7b31fdb79ced..dc0cebfe22d7 100644 --- a/arch/arm/boot/dts/imx6qdl-gw51xx.dtsi +++ b/arch/arm/boot/dts/imx6qdl-gw51xx.dtsi @@ -94,7 +94,7 @@ &fec { pinctrl-names = "default"; pinctrl-0 = <&pinctrl_enet>; - phy-mode = "rgmii"; + phy-mode = "rgmii-id"; phy-reset-gpios = <&gpio1 30 GPIO_ACTIVE_LOW>; status = "okay"; }; diff --git a/arch/arm/boot/dts/imx6qdl-gw52xx.dtsi b/arch/arm/boot/dts/imx6qdl-gw52xx.dtsi index 1b66328a8498..18cd4114a23e 100644 --- a/arch/arm/boot/dts/imx6qdl-gw52xx.dtsi +++ b/arch/arm/boot/dts/imx6qdl-gw52xx.dtsi @@ -154,7 +154,7 @@ &fec { pinctrl-names = "default"; pinctrl-0 = <&pinctrl_enet>; - phy-mode = "rgmii"; + phy-mode = "rgmii-id"; phy-reset-gpios = <&gpio1 30 GPIO_ACTIVE_LOW>; status = "okay"; }; diff --git a/arch/arm/boot/dts/imx6qdl-gw53xx.dtsi b/arch/arm/boot/dts/imx6qdl-gw53xx.dtsi index 7c51839ff934..eea90f37bbb8 100644 --- a/arch/arm/boot/dts/imx6qdl-gw53xx.dtsi +++ b/arch/arm/boot/dts/imx6qdl-gw53xx.dtsi @@ -155,7 +155,7 @@ &fec { pinctrl-names = "default"; pinctrl-0 = <&pinctrl_enet>; - phy-mode = "rgmii"; + phy-mode = "rgmii-id"; phy-reset-gpios = <&gpio1 30 GPIO_ACTIVE_LOW>; status = "okay"; }; diff --git a/arch/arm/boot/dts/imx6qdl-gw54xx.dtsi b/arch/arm/boot/dts/imx6qdl-gw54xx.dtsi index 929e0b37bd9e..6c11a2ae35ef 100644 --- a/arch/arm/boot/dts/imx6qdl-gw54xx.dtsi +++ b/arch/arm/boot/dts/imx6qdl-gw54xx.dtsi @@ -145,7 +145,7 @@ &fec { pinctrl-names = "default"; pinctrl-0 = <&pinctrl_enet>; - phy-mode = "rgmii"; + phy-mode = "rgmii-id"; phy-reset-gpios = <&gpio1 30 GPIO_ACTIVE_LOW>; status = "okay"; }; diff --git a/arch/arm/boot/dts/imx6qdl-sabreauto.dtsi b/arch/arm/boot/dts/imx6qdl-sabreauto.dtsi index 8263fc18a7d9..d354d406954d 100644 --- a/arch/arm/boot/dts/imx6qdl-sabreauto.dtsi +++ b/arch/arm/boot/dts/imx6qdl-sabreauto.dtsi @@ -113,14 +113,14 @@ &clks { assigned-clocks = <&clks IMX6QDL_PLL4_BYPASS_SRC>, <&clks IMX6QDL_PLL4_BYPASS>, - <&clks IMX6QDL_CLK_PLL4_POST_DIV>, <&clks IMX6QDL_CLK_LDB_DI0_SEL>, - <&clks IMX6QDL_CLK_LDB_DI1_SEL>; + <&clks IMX6QDL_CLK_LDB_DI1_SEL>, + <&clks IMX6QDL_CLK_PLL4_POST_DIV>; assigned-clock-parents = <&clks IMX6QDL_CLK_LVDS2_IN>, <&clks IMX6QDL_PLL4_BYPASS_SRC>, <&clks IMX6QDL_CLK_PLL3_USB_OTG>, <&clks IMX6QDL_CLK_PLL3_USB_OTG>; - assigned-clock-rates = <0>, <0>, <24576000>; + assigned-clock-rates = <0>, <0>, <0>, <0>, <24576000>; }; &ecspi1 { diff --git a/arch/arm/boot/dts/k2l-netcp.dtsi b/arch/arm/boot/dts/k2l-netcp.dtsi index 01aef230773d..5acbd0dcc2ab 100644 --- a/arch/arm/boot/dts/k2l-netcp.dtsi +++ b/arch/arm/boot/dts/k2l-netcp.dtsi @@ -137,7 +137,7 @@ netcp: netcp@26000000 { /* NetCP address range */ ranges = <0 0x26000000 0x1000000>; - clocks = <&papllclk>, <&clkcpgmac>, <&chipclk12>; + clocks = <&clkosr>, <&papllclk>, <&clkcpgmac>, <&chipclk12>; dma-coherent; ti,navigator-dmas = <&dma_gbe 0>, diff --git a/arch/arm/boot/dts/kirkwood-ts219.dtsi b/arch/arm/boot/dts/kirkwood-ts219.dtsi index c56ab6bbfe3c..0e46560551f4 100644 --- a/arch/arm/boot/dts/kirkwood-ts219.dtsi +++ b/arch/arm/boot/dts/kirkwood-ts219.dtsi @@ -40,7 +40,7 @@ }; poweroff@12100 { compatible = "qnap,power-off"; - reg = <0x12000 0x100>; + reg = <0x12100 0x100>; clocks = <&gate_clk 7>; }; spi@10600 { diff --git a/arch/arm/boot/dts/omap4-duovero-parlor.dts b/arch/arm/boot/dts/omap4-duovero-parlor.dts index 1a78f013f37a..b75f7b2b7c4a 100644 --- a/arch/arm/boot/dts/omap4-duovero-parlor.dts +++ b/arch/arm/boot/dts/omap4-duovero-parlor.dts @@ -189,3 +189,7 @@ }; }; +&uart3 { + interrupts-extended = <&wakeupgen GIC_SPI 74 IRQ_TYPE_LEVEL_HIGH + &omap4_pmx_core OMAP4_UART3_RX>; +}; diff --git a/arch/arm/boot/dts/rk3288-veyron-minnie.dts b/arch/arm/boot/dts/rk3288-veyron-minnie.dts index 8fd8ef2c72da..85f0373df498 100644 --- a/arch/arm/boot/dts/rk3288-veyron-minnie.dts +++ b/arch/arm/boot/dts/rk3288-veyron-minnie.dts @@ -86,6 +86,10 @@ }; }; +&emmc { + /delete-property/mmc-hs200-1_8v; +}; + &gpio_keys { pinctrl-0 = <&pwr_key_l &ap_lid_int_l &volum_down_l &volum_up_l>; diff --git a/arch/arm/boot/dts/rk3288.dtsi b/arch/arm/boot/dts/rk3288.dtsi index 6a79c9c526b8..04ea209f1737 100644 --- a/arch/arm/boot/dts/rk3288.dtsi +++ b/arch/arm/boot/dts/rk3288.dtsi @@ -452,8 +452,10 @@ clock-names = "tsadc", "apb_pclk"; resets = <&cru SRST_TSADC>; reset-names = "tsadc-apb"; - pinctrl-names = "default"; - pinctrl-0 = <&otp_out>; + pinctrl-names = "init", "default", "sleep"; + pinctrl-0 = <&otp_gpio>; + pinctrl-1 = <&otp_out>; + pinctrl-2 = <&otp_gpio>; #thermal-sensor-cells = <1>; rockchip,hw-tshut-temp = <95000>; status = "disabled"; @@ -1395,6 +1397,10 @@ }; tsadc { + otp_gpio: otp-gpio { + rockchip,pins = <0 10 RK_FUNC_GPIO &pcfg_pull_none>; + }; + otp_out: otp-out { rockchip,pins = <0 10 RK_FUNC_1 &pcfg_pull_none>; }; diff --git a/arch/arm/boot/dts/sama5d35ek.dts b/arch/arm/boot/dts/sama5d35ek.dts index d9a9aca1ccfd..e812f5c1bf70 100644 --- a/arch/arm/boot/dts/sama5d35ek.dts +++ b/arch/arm/boot/dts/sama5d35ek.dts @@ -49,7 +49,7 @@ label = "pb_user1"; gpios = <&pioE 27 GPIO_ACTIVE_HIGH>; linux,code = <0x100>; - gpio-key,wakeup; + wakeup-source; }; }; }; diff --git a/arch/arm/boot/dts/sama5d4.dtsi b/arch/arm/boot/dts/sama5d4.dtsi index 15bbaf690047..2193637b9cd2 100644 --- a/arch/arm/boot/dts/sama5d4.dtsi +++ b/arch/arm/boot/dts/sama5d4.dtsi @@ -1300,7 +1300,7 @@ }; watchdog@fc068640 { - compatible = "atmel,at91sam9260-wdt"; + compatible = "atmel,sama5d4-wdt"; reg = <0xfc068640 0x10>; clocks = <&clk32k>; status = "disabled"; diff --git a/arch/arm/boot/dts/ste-nomadik-stn8815.dtsi b/arch/arm/boot/dts/ste-nomadik-stn8815.dtsi index 314f59c12162..d0c743853318 100644 --- a/arch/arm/boot/dts/ste-nomadik-stn8815.dtsi +++ b/arch/arm/boot/dts/ste-nomadik-stn8815.dtsi @@ -25,9 +25,9 @@ cache-sets = <512>; cache-line-size = <32>; /* At full speed latency must be >=2 */ - arm,tag-latency = <2>; - arm,data-latency = <2 2>; - arm,dirty-latency = <2>; + arm,tag-latency = <8>; + arm,data-latency = <8 8>; + arm,dirty-latency = <8>; }; mtu0: mtu@101e2000 { diff --git a/arch/arm/boot/dts/sun6i-a31s-primo81.dts b/arch/arm/boot/dts/sun6i-a31s-primo81.dts index 2d4250b1faf8..68b479b8772c 100644 --- a/arch/arm/boot/dts/sun6i-a31s-primo81.dts +++ b/arch/arm/boot/dts/sun6i-a31s-primo81.dts @@ -83,6 +83,7 @@ reg = <0x5d>; interrupt-parent = <&pio>; interrupts = <0 3 IRQ_TYPE_LEVEL_HIGH>; /* PA3 */ + touchscreen-swapped-x-y; }; }; diff --git a/arch/arm/boot/dts/tegra124-nyan.dtsi b/arch/arm/boot/dts/tegra124-nyan.dtsi index 40c23a0b7cfc..ec1aa64ded68 100644 --- a/arch/arm/boot/dts/tegra124-nyan.dtsi +++ b/arch/arm/boot/dts/tegra124-nyan.dtsi @@ -399,7 +399,7 @@ /* CPU DFLL clock */ clock@0,70110000 { - status = "okay"; + status = "disabled"; vdd-cpu-supply = <&vdd_cpu>; nvidia,i2c-fs-rate = <400000>; }; diff --git a/arch/arm/boot/dts/usb_a9260_common.dtsi b/arch/arm/boot/dts/usb_a9260_common.dtsi index 12edafefd44a..9beea8976584 100644 --- a/arch/arm/boot/dts/usb_a9260_common.dtsi +++ b/arch/arm/boot/dts/usb_a9260_common.dtsi @@ -115,7 +115,7 @@ label = "user_pb"; gpios = <&pioB 10 GPIO_ACTIVE_LOW>; linux,code = <28>; - gpio-key,wakeup; + wakeup-source; }; }; diff --git a/arch/arm/boot/dts/usb_a9263.dts b/arch/arm/boot/dts/usb_a9263.dts index 68c0de36c339..8cc6edb29694 100644 --- a/arch/arm/boot/dts/usb_a9263.dts +++ b/arch/arm/boot/dts/usb_a9263.dts @@ -143,7 +143,7 @@ label = "user_pb"; gpios = <&pioB 10 GPIO_ACTIVE_LOW>; linux,code = <28>; - gpio-key,wakeup; + wakeup-source; }; }; diff --git a/arch/arm/boot/dts/versatile-ab.dts b/arch/arm/boot/dts/versatile-ab.dts index 01f40197ea13..3279bf1a17a1 100644 --- a/arch/arm/boot/dts/versatile-ab.dts +++ b/arch/arm/boot/dts/versatile-ab.dts @@ -110,7 +110,11 @@ interrupt-parent = <&vic>; interrupts = <31>; /* Cascaded to vic */ clear-mask = <0xffffffff>; - valid-mask = <0xffc203f8>; + /* + * Valid interrupt lines mask according to + * table 4-36 page 4-50 of ARM DUI 0225D + */ + valid-mask = <0x0760031b>; }; dma@10130000 { @@ -266,8 +270,8 @@ }; mmc@5000 { compatible = "arm,pl180", "arm,primecell"; - reg = < 0x5000 0x1000>; - interrupts-extended = <&vic 22 &sic 2>; + reg = <0x5000 0x1000>; + interrupts-extended = <&vic 22 &sic 1>; clocks = <&xtal24mhz>, <&pclk>; clock-names = "mclk", "apb_pclk"; }; diff --git a/arch/arm/boot/dts/versatile-pb.dts b/arch/arm/boot/dts/versatile-pb.dts index b83137f66034..33a8eb28374e 100644 --- a/arch/arm/boot/dts/versatile-pb.dts +++ b/arch/arm/boot/dts/versatile-pb.dts @@ -5,6 +5,16 @@ compatible = "arm,versatile-pb"; amba { + /* The Versatile PB is using more SIC IRQ lines than the AB */ + sic: intc@10003000 { + clear-mask = <0xffffffff>; + /* + * Valid interrupt lines mask according to + * figure 3-30 page 3-74 of ARM DUI 0224B + */ + valid-mask = <0x7fe003ff>; + }; + gpio2: gpio@101e6000 { compatible = "arm,pl061", "arm,primecell"; reg = <0x101e6000 0x1000>; @@ -67,6 +77,13 @@ }; fpga { + mmc@5000 { + /* + * Overrides the interrupt assignment from + * the Versatile AB board file. + */ + interrupts-extended = <&sic 22 &sic 23>; + }; uart@9000 { compatible = "arm,pl011", "arm,primecell"; reg = <0x9000 0x1000>; @@ -86,7 +103,8 @@ mmc@b000 { compatible = "arm,pl180", "arm,primecell"; reg = <0xb000 0x1000>; - interrupts-extended = <&vic 23 &sic 2>; + interrupt-parent = <&sic>; + interrupts = <1>, <2>; clocks = <&xtal24mhz>, <&pclk>; clock-names = "mclk", "apb_pclk"; }; diff --git a/arch/arm/boot/dts/vf610-colibri.dtsi b/arch/arm/boot/dts/vf610-colibri.dtsi index 19fe045b8334..2d7eab755210 100644 --- a/arch/arm/boot/dts/vf610-colibri.dtsi +++ b/arch/arm/boot/dts/vf610-colibri.dtsi @@ -18,8 +18,3 @@ reg = <0x80000000 0x10000000>; }; }; - -&L2 { - arm,data-latency = <2 1 2>; - arm,tag-latency = <3 2 3>; -}; diff --git a/arch/arm/boot/dts/vf610.dtsi b/arch/arm/boot/dts/vf610.dtsi index 5f8eb1bd782b..58bc6e448be5 100644 --- a/arch/arm/boot/dts/vf610.dtsi +++ b/arch/arm/boot/dts/vf610.dtsi @@ -19,7 +19,7 @@ reg = <0x40006000 0x1000>; cache-unified; cache-level = <2>; - arm,data-latency = <1 1 1>; + arm,data-latency = <3 3 3>; arm,tag-latency = <2 2 2>; }; }; diff --git a/arch/arm/boot/dts/vfxxx.dtsi b/arch/arm/boot/dts/vfxxx.dtsi index 6736bae43a5b..3cd1b27f2697 100644 --- a/arch/arm/boot/dts/vfxxx.dtsi +++ b/arch/arm/boot/dts/vfxxx.dtsi @@ -158,7 +158,7 @@ interrupts = <67 IRQ_TYPE_LEVEL_HIGH>; clocks = <&clks VF610_CLK_DSPI0>; clock-names = "dspi"; - spi-num-chipselects = <5>; + spi-num-chipselects = <6>; status = "disabled"; }; @@ -170,7 +170,7 @@ interrupts = <68 IRQ_TYPE_LEVEL_HIGH>; clocks = <&clks VF610_CLK_DSPI1>; clock-names = "dspi"; - spi-num-chipselects = <5>; + spi-num-chipselects = <4>; status = "disabled"; }; @@ -178,8 +178,10 @@ compatible = "fsl,vf610-sai"; reg = <0x40031000 0x1000>; interrupts = <86 IRQ_TYPE_LEVEL_HIGH>; - clocks = <&clks VF610_CLK_SAI2>; - clock-names = "sai"; + clocks = <&clks VF610_CLK_SAI2>, + <&clks VF610_CLK_SAI2_DIV>, + <&clks 0>, <&clks 0>; + clock-names = "bus", "mclk1", "mclk2", "mclk3"; dma-names = "tx", "rx"; dmas = <&edma0 0 21>, <&edma0 0 20>; @@ -461,6 +463,8 @@ clock-names = "adc"; #io-channel-cells = <1>; status = "disabled"; + fsl,adck-max-frequency = <30000000>, <40000000>, + <20000000>; }; esdhc0: esdhc@400b1000 { @@ -472,8 +476,6 @@ <&clks VF610_CLK_ESDHC0>; clock-names = "ipg", "ahb", "per"; status = "disabled"; - fsl,adck-max-frequency = <30000000>, <40000000>, - <20000000>; }; esdhc1: esdhc@400b2000 { diff --git a/arch/arm/boot/dts/wm8650.dtsi b/arch/arm/boot/dts/wm8650.dtsi index b1c59a766a13..e12213d16693 100644 --- a/arch/arm/boot/dts/wm8650.dtsi +++ b/arch/arm/boot/dts/wm8650.dtsi @@ -187,6 +187,15 @@ interrupts = <43>; }; + sdhc@d800a000 { + compatible = "wm,wm8505-sdhc"; + reg = <0xd800a000 0x400>; + interrupts = <20>, <21>; + clocks = <&clksdhc>; + bus-width = <4>; + sdon-inverted; + }; + fb: fb@d8050800 { compatible = "wm,wm8505-fb"; reg = <0xd8050800 0x200>; diff --git a/arch/arm/configs/at91_dt_defconfig b/arch/arm/configs/at91_dt_defconfig index 1b1e5acd76e2..e4b1be66b3f5 100644 --- a/arch/arm/configs/at91_dt_defconfig +++ b/arch/arm/configs/at91_dt_defconfig @@ -125,7 +125,6 @@ CONFIG_POWER_RESET=y # CONFIG_HWMON is not set CONFIG_WATCHDOG=y CONFIG_AT91SAM9X_WATCHDOG=y -CONFIG_SSB=m CONFIG_MFD_ATMEL_HLCDC=y CONFIG_REGULATOR=y CONFIG_REGULATOR_FIXED_VOLTAGE=y diff --git a/arch/arm/configs/multi_v7_defconfig b/arch/arm/configs/multi_v7_defconfig index 69a22fdb52a5..cd7b198fc79e 100644 --- a/arch/arm/configs/multi_v7_defconfig +++ b/arch/arm/configs/multi_v7_defconfig @@ -366,6 +366,7 @@ CONFIG_BATTERY_MAX17042=m CONFIG_CHARGER_MAX14577=m CONFIG_CHARGER_MAX77693=m CONFIG_CHARGER_TPS65090=y +CONFIG_AXP20X_POWER=m CONFIG_POWER_RESET_AS3722=y CONFIG_POWER_RESET_GPIO=y CONFIG_POWER_RESET_GPIO_RESTART=y diff --git a/arch/arm/configs/sama5_defconfig b/arch/arm/configs/sama5_defconfig index a0c57ac88b27..63f7e6ce649a 100644 --- a/arch/arm/configs/sama5_defconfig +++ b/arch/arm/configs/sama5_defconfig @@ -129,7 +129,6 @@ CONFIG_GPIO_SYSFS=y CONFIG_POWER_SUPPLY=y CONFIG_POWER_RESET=y # CONFIG_HWMON is not set -CONFIG_SSB=m CONFIG_MFD_ATMEL_FLEXCOM=y CONFIG_REGULATOR=y CONFIG_REGULATOR_FIXED_VOLTAGE=y diff --git a/arch/arm/configs/sunxi_defconfig b/arch/arm/configs/sunxi_defconfig index 3c36e16fcacf..b503a89441bf 100644 --- a/arch/arm/configs/sunxi_defconfig +++ b/arch/arm/configs/sunxi_defconfig @@ -84,6 +84,7 @@ CONFIG_SPI_SUN4I=y CONFIG_SPI_SUN6I=y CONFIG_GPIO_SYSFS=y CONFIG_POWER_SUPPLY=y +CONFIG_AXP20X_POWER=y CONFIG_THERMAL=y CONFIG_CPU_THERMAL=y CONFIG_WATCHDOG=y diff --git a/arch/arm/include/asm/arch_gicv3.h b/arch/arm/include/asm/arch_gicv3.h index 6607d976e07d..7da5503c0591 100644 --- a/arch/arm/include/asm/arch_gicv3.h +++ b/arch/arm/include/asm/arch_gicv3.h @@ -21,6 +21,7 @@ #ifndef __ASSEMBLY__ #include <linux/io.h> +#include <asm/barrier.h> #define __ACCESS_CP15(CRn, Op1, CRm, Op2) p15, Op1, %0, CRn, CRm, Op2 #define __ACCESS_CP15_64(Op1, CRm) p15, Op1, %Q0, %R0, CRm diff --git a/arch/arm/include/asm/irq.h b/arch/arm/include/asm/irq.h index be1d07d59ee9..1bd9510de1b9 100644 --- a/arch/arm/include/asm/irq.h +++ b/arch/arm/include/asm/irq.h @@ -40,6 +40,11 @@ extern void arch_trigger_all_cpu_backtrace(bool); #define arch_trigger_all_cpu_backtrace(x) arch_trigger_all_cpu_backtrace(x) #endif +static inline int nr_legacy_irqs(void) +{ + return NR_IRQS_LEGACY; +} + #endif #endif diff --git a/arch/arm/include/asm/kvm_emulate.h b/arch/arm/include/asm/kvm_emulate.h index a9c80a2ea1a7..3095df091ff8 100644 --- a/arch/arm/include/asm/kvm_emulate.h +++ b/arch/arm/include/asm/kvm_emulate.h @@ -28,6 +28,18 @@ unsigned long *vcpu_reg(struct kvm_vcpu *vcpu, u8 reg_num); unsigned long *vcpu_spsr(struct kvm_vcpu *vcpu); +static inline unsigned long vcpu_get_reg(struct kvm_vcpu *vcpu, + u8 reg_num) +{ + return *vcpu_reg(vcpu, reg_num); +} + +static inline void vcpu_set_reg(struct kvm_vcpu *vcpu, u8 reg_num, + unsigned long val) +{ + *vcpu_reg(vcpu, reg_num) = val; +} + bool kvm_condition_valid(struct kvm_vcpu *vcpu); void kvm_skip_instr(struct kvm_vcpu *vcpu, bool is_wide_instr); void kvm_inject_undefined(struct kvm_vcpu *vcpu); diff --git a/arch/arm/include/asm/uaccess.h b/arch/arm/include/asm/uaccess.h index 8cc85a4ebec2..35c9db857ebe 100644 --- a/arch/arm/include/asm/uaccess.h +++ b/arch/arm/include/asm/uaccess.h @@ -510,10 +510,14 @@ __copy_to_user_std(void __user *to, const void *from, unsigned long n); static inline unsigned long __must_check __copy_to_user(void __user *to, const void *from, unsigned long n) { +#ifndef CONFIG_UACCESS_WITH_MEMCPY unsigned int __ua_flags = uaccess_save_and_enable(); n = arm_copy_to_user(to, from, n); uaccess_restore(__ua_flags); return n; +#else + return arm_copy_to_user(to, from, n); +#endif } extern unsigned long __must_check diff --git a/arch/arm/include/uapi/asm/unistd.h b/arch/arm/include/uapi/asm/unistd.h index 7a2a32a1d5a8..ede692ffa32e 100644 --- a/arch/arm/include/uapi/asm/unistd.h +++ b/arch/arm/include/uapi/asm/unistd.h @@ -416,6 +416,7 @@ #define __NR_execveat (__NR_SYSCALL_BASE+387) #define __NR_userfaultfd (__NR_SYSCALL_BASE+388) #define __NR_membarrier (__NR_SYSCALL_BASE+389) +#define __NR_mlock2 (__NR_SYSCALL_BASE+390) /* * The following SWIs are ARM private. diff --git a/arch/arm/kernel/bios32.c b/arch/arm/kernel/bios32.c index 6551d28c27e6..066f7f9ba411 100644 --- a/arch/arm/kernel/bios32.c +++ b/arch/arm/kernel/bios32.c @@ -17,11 +17,6 @@ #include <asm/mach/pci.h> static int debug_pci; -static resource_size_t (*align_resource)(struct pci_dev *dev, - const struct resource *res, - resource_size_t start, - resource_size_t size, - resource_size_t align) = NULL; /* * We can't use pci_get_device() here since we are @@ -461,7 +456,6 @@ static void pcibios_init_hw(struct device *parent, struct hw_pci *hw, sys->busnr = busnr; sys->swizzle = hw->swizzle; sys->map_irq = hw->map_irq; - align_resource = hw->align_resource; INIT_LIST_HEAD(&sys->resources); if (hw->private_data) @@ -470,6 +464,8 @@ static void pcibios_init_hw(struct device *parent, struct hw_pci *hw, ret = hw->setup(nr, sys); if (ret > 0) { + struct pci_host_bridge *host_bridge; + ret = pcibios_init_resources(nr, sys); if (ret) { kfree(sys); @@ -491,6 +487,9 @@ static void pcibios_init_hw(struct device *parent, struct hw_pci *hw, busnr = sys->bus->busn_res.end + 1; list_add(&sys->node, head); + + host_bridge = pci_find_host_bridge(sys->bus); + host_bridge->align_resource = hw->align_resource; } else { kfree(sys); if (ret < 0) @@ -578,14 +577,18 @@ resource_size_t pcibios_align_resource(void *data, const struct resource *res, { struct pci_dev *dev = data; resource_size_t start = res->start; + struct pci_host_bridge *host_bridge; if (res->flags & IORESOURCE_IO && start & 0x300) start = (start + 0x3ff) & ~0x3ff; start = (start + align - 1) & ~(align - 1); - if (align_resource) - return align_resource(dev, res, start, size, align); + host_bridge = pci_find_host_bridge(dev->bus); + + if (host_bridge->align_resource) + return host_bridge->align_resource(dev, res, + start, size, align); return start; } diff --git a/arch/arm/kernel/calls.S b/arch/arm/kernel/calls.S index fde6c88d560c..ac368bb068d1 100644 --- a/arch/arm/kernel/calls.S +++ b/arch/arm/kernel/calls.S @@ -399,6 +399,7 @@ CALL(sys_execveat) CALL(sys_userfaultfd) CALL(sys_membarrier) + CALL(sys_mlock2) #ifndef syscalls_counted .equ syscalls_padding, ((NR_syscalls + 3) & ~3) - NR_syscalls #define syscalls_counted diff --git a/arch/arm/kernel/process.c b/arch/arm/kernel/process.c index 7a7c4cea5523..4adfb46e3ee9 100644 --- a/arch/arm/kernel/process.c +++ b/arch/arm/kernel/process.c @@ -95,6 +95,22 @@ void __show_regs(struct pt_regs *regs) { unsigned long flags; char buf[64]; +#ifndef CONFIG_CPU_V7M + unsigned int domain; +#ifdef CONFIG_CPU_SW_DOMAIN_PAN + /* + * Get the domain register for the parent context. In user + * mode, we don't save the DACR, so lets use what it should + * be. For other modes, we place it after the pt_regs struct. + */ + if (user_mode(regs)) + domain = DACR_UACCESS_ENABLE; + else + domain = *(unsigned int *)(regs + 1); +#else + domain = get_domain(); +#endif +#endif show_regs_print_info(KERN_DEFAULT); @@ -123,21 +139,8 @@ void __show_regs(struct pt_regs *regs) #ifndef CONFIG_CPU_V7M { - unsigned int domain = get_domain(); const char *segment; -#ifdef CONFIG_CPU_SW_DOMAIN_PAN - /* - * Get the domain register for the parent context. In user - * mode, we don't save the DACR, so lets use what it should - * be. For other modes, we place it after the pt_regs struct. - */ - if (user_mode(regs)) - domain = DACR_UACCESS_ENABLE; - else - domain = *(unsigned int *)(regs + 1); -#endif - if ((domain & domain_mask(DOMAIN_USER)) == domain_val(DOMAIN_USER, DOMAIN_NOACCESS)) segment = "none"; @@ -163,11 +166,11 @@ void __show_regs(struct pt_regs *regs) buf[0] = '\0'; #ifdef CONFIG_CPU_CP15_MMU { - unsigned int transbase, dac = get_domain(); + unsigned int transbase; asm("mrc p15, 0, %0, c2, c0\n\t" : "=r" (transbase)); snprintf(buf, sizeof(buf), " Table: %08x DAC: %08x", - transbase, dac); + transbase, domain); } #endif asm("mrc p15, 0, %0, c1, c0\n" : "=r" (ctrl)); diff --git a/arch/arm/kernel/swp_emulate.c b/arch/arm/kernel/swp_emulate.c index 5b26e7efa9ea..c3fe769d7558 100644 --- a/arch/arm/kernel/swp_emulate.c +++ b/arch/arm/kernel/swp_emulate.c @@ -36,10 +36,10 @@ */ #define __user_swpX_asm(data, addr, res, temp, B) \ __asm__ __volatile__( \ - " mov %2, %1\n" \ - "0: ldrex"B" %1, [%3]\n" \ - "1: strex"B" %0, %2, [%3]\n" \ + "0: ldrex"B" %2, [%3]\n" \ + "1: strex"B" %0, %1, [%3]\n" \ " cmp %0, #0\n" \ + " moveq %1, %2\n" \ " movne %0, %4\n" \ "2:\n" \ " .section .text.fixup,\"ax\"\n" \ diff --git a/arch/arm/kernel/sys_oabi-compat.c b/arch/arm/kernel/sys_oabi-compat.c index b83f3b7737fb..087acb569b63 100644 --- a/arch/arm/kernel/sys_oabi-compat.c +++ b/arch/arm/kernel/sys_oabi-compat.c @@ -193,15 +193,44 @@ struct oabi_flock64 { pid_t l_pid; } __attribute__ ((packed,aligned(4))); -asmlinkage long sys_oabi_fcntl64(unsigned int fd, unsigned int cmd, +static long do_locks(unsigned int fd, unsigned int cmd, unsigned long arg) { - struct oabi_flock64 user; struct flock64 kernel; - mm_segment_t fs = USER_DS; /* initialized to kill a warning */ - unsigned long local_arg = arg; - int ret; + struct oabi_flock64 user; + mm_segment_t fs; + long ret; + + if (copy_from_user(&user, (struct oabi_flock64 __user *)arg, + sizeof(user))) + return -EFAULT; + kernel.l_type = user.l_type; + kernel.l_whence = user.l_whence; + kernel.l_start = user.l_start; + kernel.l_len = user.l_len; + kernel.l_pid = user.l_pid; + + fs = get_fs(); + set_fs(KERNEL_DS); + ret = sys_fcntl64(fd, cmd, (unsigned long)&kernel); + set_fs(fs); + + if (!ret && (cmd == F_GETLK64 || cmd == F_OFD_GETLK)) { + user.l_type = kernel.l_type; + user.l_whence = kernel.l_whence; + user.l_start = kernel.l_start; + user.l_len = kernel.l_len; + user.l_pid = kernel.l_pid; + if (copy_to_user((struct oabi_flock64 __user *)arg, + &user, sizeof(user))) + ret = -EFAULT; + } + return ret; +} +asmlinkage long sys_oabi_fcntl64(unsigned int fd, unsigned int cmd, + unsigned long arg) +{ switch (cmd) { case F_OFD_GETLK: case F_OFD_SETLK: @@ -209,39 +238,11 @@ asmlinkage long sys_oabi_fcntl64(unsigned int fd, unsigned int cmd, case F_GETLK64: case F_SETLK64: case F_SETLKW64: - if (copy_from_user(&user, (struct oabi_flock64 __user *)arg, - sizeof(user))) - return -EFAULT; - kernel.l_type = user.l_type; - kernel.l_whence = user.l_whence; - kernel.l_start = user.l_start; - kernel.l_len = user.l_len; - kernel.l_pid = user.l_pid; - local_arg = (unsigned long)&kernel; - fs = get_fs(); - set_fs(KERNEL_DS); - } - - ret = sys_fcntl64(fd, cmd, local_arg); + return do_locks(fd, cmd, arg); - switch (cmd) { - case F_GETLK64: - if (!ret) { - user.l_type = kernel.l_type; - user.l_whence = kernel.l_whence; - user.l_start = kernel.l_start; - user.l_len = kernel.l_len; - user.l_pid = kernel.l_pid; - if (copy_to_user((struct oabi_flock64 __user *)arg, - &user, sizeof(user))) - ret = -EFAULT; - } - case F_SETLK64: - case F_SETLKW64: - set_fs(fs); + default: + return sys_fcntl64(fd, cmd, arg); } - - return ret; } struct oabi_epoll_event { diff --git a/arch/arm/kvm/arm.c b/arch/arm/kvm/arm.c index eab83b2435b8..e06fd299de08 100644 --- a/arch/arm/kvm/arm.c +++ b/arch/arm/kvm/arm.c @@ -564,17 +564,12 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu, struct kvm_run *run) vcpu_sleep(vcpu); /* - * Disarming the background timer must be done in a - * preemptible context, as this call may sleep. - */ - kvm_timer_flush_hwstate(vcpu); - - /* * Preparing the interrupts to be injected also * involves poking the GIC, which must be done in a * non-preemptible context. */ preempt_disable(); + kvm_timer_flush_hwstate(vcpu); kvm_vgic_flush_hwstate(vcpu); local_irq_disable(); diff --git a/arch/arm/kvm/mmio.c b/arch/arm/kvm/mmio.c index 974b1c606d04..3a10c9f1d0a4 100644 --- a/arch/arm/kvm/mmio.c +++ b/arch/arm/kvm/mmio.c @@ -115,7 +115,7 @@ int kvm_handle_mmio_return(struct kvm_vcpu *vcpu, struct kvm_run *run) trace_kvm_mmio(KVM_TRACE_MMIO_READ, len, run->mmio.phys_addr, data); data = vcpu_data_host_to_guest(vcpu, data, len); - *vcpu_reg(vcpu, vcpu->arch.mmio_decode.rt) = data; + vcpu_set_reg(vcpu, vcpu->arch.mmio_decode.rt, data); } return 0; @@ -186,7 +186,8 @@ int io_mem_abort(struct kvm_vcpu *vcpu, struct kvm_run *run, rt = vcpu->arch.mmio_decode.rt; if (is_write) { - data = vcpu_data_guest_to_host(vcpu, *vcpu_reg(vcpu, rt), len); + data = vcpu_data_guest_to_host(vcpu, vcpu_get_reg(vcpu, rt), + len); trace_kvm_mmio(KVM_TRACE_MMIO_WRITE, len, fault_ipa, data); mmio_write_buf(data_buf, len, data); diff --git a/arch/arm/kvm/mmu.c b/arch/arm/kvm/mmu.c index 6984342da13d..61d96a645ff3 100644 --- a/arch/arm/kvm/mmu.c +++ b/arch/arm/kvm/mmu.c @@ -98,6 +98,11 @@ static void kvm_flush_dcache_pud(pud_t pud) __kvm_flush_dcache_pud(pud); } +static bool kvm_is_device_pfn(unsigned long pfn) +{ + return !pfn_valid(pfn); +} + /** * stage2_dissolve_pmd() - clear and flush huge PMD entry * @kvm: pointer to kvm structure. @@ -213,7 +218,7 @@ static void unmap_ptes(struct kvm *kvm, pmd_t *pmd, kvm_tlb_flush_vmid_ipa(kvm, addr); /* No need to invalidate the cache for device mappings */ - if ((pte_val(old_pte) & PAGE_S2_DEVICE) != PAGE_S2_DEVICE) + if (!kvm_is_device_pfn(pte_pfn(old_pte))) kvm_flush_dcache_pte(old_pte); put_page(virt_to_page(pte)); @@ -305,8 +310,7 @@ static void stage2_flush_ptes(struct kvm *kvm, pmd_t *pmd, pte = pte_offset_kernel(pmd, addr); do { - if (!pte_none(*pte) && - (pte_val(*pte) & PAGE_S2_DEVICE) != PAGE_S2_DEVICE) + if (!pte_none(*pte) && !kvm_is_device_pfn(pte_pfn(*pte))) kvm_flush_dcache_pte(*pte); } while (pte++, addr += PAGE_SIZE, addr != end); } @@ -1037,11 +1041,6 @@ static bool kvm_is_write_fault(struct kvm_vcpu *vcpu) return kvm_vcpu_dabt_iswrite(vcpu); } -static bool kvm_is_device_pfn(unsigned long pfn) -{ - return !pfn_valid(pfn); -} - /** * stage2_wp_ptes - write protect PMD range * @pmd: pointer to pmd entry diff --git a/arch/arm/kvm/psci.c b/arch/arm/kvm/psci.c index 0b556968a6da..a9b3b905e661 100644 --- a/arch/arm/kvm/psci.c +++ b/arch/arm/kvm/psci.c @@ -75,7 +75,7 @@ static unsigned long kvm_psci_vcpu_on(struct kvm_vcpu *source_vcpu) unsigned long context_id; phys_addr_t target_pc; - cpu_id = *vcpu_reg(source_vcpu, 1) & MPIDR_HWID_BITMASK; + cpu_id = vcpu_get_reg(source_vcpu, 1) & MPIDR_HWID_BITMASK; if (vcpu_mode_is_32bit(source_vcpu)) cpu_id &= ~((u32) 0); @@ -94,8 +94,8 @@ static unsigned long kvm_psci_vcpu_on(struct kvm_vcpu *source_vcpu) return PSCI_RET_INVALID_PARAMS; } - target_pc = *vcpu_reg(source_vcpu, 2); - context_id = *vcpu_reg(source_vcpu, 3); + target_pc = vcpu_get_reg(source_vcpu, 2); + context_id = vcpu_get_reg(source_vcpu, 3); kvm_reset_vcpu(vcpu); @@ -114,7 +114,7 @@ static unsigned long kvm_psci_vcpu_on(struct kvm_vcpu *source_vcpu) * NOTE: We always update r0 (or x0) because for PSCI v0.1 * the general puspose registers are undefined upon CPU_ON. */ - *vcpu_reg(vcpu, 0) = context_id; + vcpu_set_reg(vcpu, 0, context_id); vcpu->arch.power_off = false; smp_mb(); /* Make sure the above is visible */ @@ -134,8 +134,8 @@ static unsigned long kvm_psci_vcpu_affinity_info(struct kvm_vcpu *vcpu) struct kvm *kvm = vcpu->kvm; struct kvm_vcpu *tmp; - target_affinity = *vcpu_reg(vcpu, 1); - lowest_affinity_level = *vcpu_reg(vcpu, 2); + target_affinity = vcpu_get_reg(vcpu, 1); + lowest_affinity_level = vcpu_get_reg(vcpu, 2); /* Determine target affinity mask */ target_affinity_mask = psci_affinity_mask(lowest_affinity_level); @@ -209,7 +209,7 @@ int kvm_psci_version(struct kvm_vcpu *vcpu) static int kvm_psci_0_2_call(struct kvm_vcpu *vcpu) { int ret = 1; - unsigned long psci_fn = *vcpu_reg(vcpu, 0) & ~((u32) 0); + unsigned long psci_fn = vcpu_get_reg(vcpu, 0) & ~((u32) 0); unsigned long val; switch (psci_fn) { @@ -273,13 +273,13 @@ static int kvm_psci_0_2_call(struct kvm_vcpu *vcpu) break; } - *vcpu_reg(vcpu, 0) = val; + vcpu_set_reg(vcpu, 0, val); return ret; } static int kvm_psci_0_1_call(struct kvm_vcpu *vcpu) { - unsigned long psci_fn = *vcpu_reg(vcpu, 0) & ~((u32) 0); + unsigned long psci_fn = vcpu_get_reg(vcpu, 0) & ~((u32) 0); unsigned long val; switch (psci_fn) { @@ -295,7 +295,7 @@ static int kvm_psci_0_1_call(struct kvm_vcpu *vcpu) break; } - *vcpu_reg(vcpu, 0) = val; + vcpu_set_reg(vcpu, 0, val); return 1; } diff --git a/arch/arm/lib/uaccess_with_memcpy.c b/arch/arm/lib/uaccess_with_memcpy.c index d72b90905132..588bbc288396 100644 --- a/arch/arm/lib/uaccess_with_memcpy.c +++ b/arch/arm/lib/uaccess_with_memcpy.c @@ -88,6 +88,7 @@ pin_page_for_write(const void __user *_addr, pte_t **ptep, spinlock_t **ptlp) static unsigned long noinline __copy_to_user_memcpy(void __user *to, const void *from, unsigned long n) { + unsigned long ua_flags; int atomic; if (unlikely(segment_eq(get_fs(), KERNEL_DS))) { @@ -118,7 +119,9 @@ __copy_to_user_memcpy(void __user *to, const void *from, unsigned long n) if (tocopy > n) tocopy = n; + ua_flags = uaccess_save_and_enable(); memcpy((void *)to, from, tocopy); + uaccess_restore(ua_flags); to += tocopy; from += tocopy; n -= tocopy; @@ -145,14 +148,21 @@ arm_copy_to_user(void __user *to, const void *from, unsigned long n) * With frame pointer disabled, tail call optimization kicks in * as well making this test almost invisible. */ - if (n < 64) - return __copy_to_user_std(to, from, n); - return __copy_to_user_memcpy(to, from, n); + if (n < 64) { + unsigned long ua_flags = uaccess_save_and_enable(); + n = __copy_to_user_std(to, from, n); + uaccess_restore(ua_flags); + } else { + n = __copy_to_user_memcpy(to, from, n); + } + return n; } static unsigned long noinline __clear_user_memset(void __user *addr, unsigned long n) { + unsigned long ua_flags; + if (unlikely(segment_eq(get_fs(), KERNEL_DS))) { memset((void *)addr, 0, n); return 0; @@ -175,7 +185,9 @@ __clear_user_memset(void __user *addr, unsigned long n) if (tocopy > n) tocopy = n; + ua_flags = uaccess_save_and_enable(); memset((void *)addr, 0, tocopy); + uaccess_restore(ua_flags); addr += tocopy; n -= tocopy; @@ -193,9 +205,14 @@ out: unsigned long arm_clear_user(void __user *addr, unsigned long n) { /* See rational for this in __copy_to_user() above. */ - if (n < 64) - return __clear_user_std(addr, n); - return __clear_user_memset(addr, n); + if (n < 64) { + unsigned long ua_flags = uaccess_save_and_enable(); + n = __clear_user_std(addr, n); + uaccess_restore(ua_flags); + } else { + n = __clear_user_memset(addr, n); + } + return n; } #if 0 diff --git a/arch/arm/mach-at91/Kconfig b/arch/arm/mach-at91/Kconfig index 92673006e55c..28656c2b54a0 100644 --- a/arch/arm/mach-at91/Kconfig +++ b/arch/arm/mach-at91/Kconfig @@ -4,7 +4,6 @@ menuconfig ARCH_AT91 select ARCH_REQUIRE_GPIOLIB select COMMON_CLK_AT91 select PINCTRL - select PINCTRL_AT91 select SOC_BUS if ARCH_AT91 @@ -17,6 +16,7 @@ config SOC_SAMA5D2 select HAVE_AT91_USB_CLK select HAVE_AT91_H32MX select HAVE_AT91_GENERATED_CLK + select PINCTRL_AT91PIO4 help Select this if ou are using one of Atmel's SAMA5D2 family SoC. @@ -27,6 +27,7 @@ config SOC_SAMA5D3 select HAVE_AT91_UTMI select HAVE_AT91_SMD select HAVE_AT91_USB_CLK + select PINCTRL_AT91 help Select this if you are using one of Atmel's SAMA5D3 family SoC. This support covers SAMA5D31, SAMA5D33, SAMA5D34, SAMA5D35, SAMA5D36. @@ -40,6 +41,7 @@ config SOC_SAMA5D4 select HAVE_AT91_SMD select HAVE_AT91_USB_CLK select HAVE_AT91_H32MX + select PINCTRL_AT91 help Select this if you are using one of Atmel's SAMA5D4 family SoC. @@ -50,6 +52,7 @@ config SOC_AT91RM9200 select CPU_ARM920T select HAVE_AT91_USB_CLK select MIGHT_HAVE_PCI + select PINCTRL_AT91 select SOC_SAM_V4_V5 select SRAM if PM help @@ -65,6 +68,7 @@ config SOC_AT91SAM9 select HAVE_AT91_UTMI select HAVE_FB_ATMEL select MEMORY + select PINCTRL_AT91 select SOC_SAM_V4_V5 select SRAM if PM help diff --git a/arch/arm/mach-at91/pm.c b/arch/arm/mach-at91/pm.c index 80e277cfcc8b..23726fb31741 100644 --- a/arch/arm/mach-at91/pm.c +++ b/arch/arm/mach-at91/pm.c @@ -41,8 +41,10 @@ * implementation should be moved down into the pinctrl driver and get * called as part of the generic suspend/resume path. */ +#ifdef CONFIG_PINCTRL_AT91 extern void at91_pinctrl_gpio_suspend(void); extern void at91_pinctrl_gpio_resume(void); +#endif static struct { unsigned long uhp_udp_mask; @@ -151,8 +153,9 @@ static void at91_pm_suspend(suspend_state_t state) static int at91_pm_enter(suspend_state_t state) { +#ifdef CONFIG_PINCTRL_AT91 at91_pinctrl_gpio_suspend(); - +#endif switch (state) { /* * Suspend-to-RAM is like STANDBY plus slow clock mode, so @@ -192,7 +195,9 @@ static int at91_pm_enter(suspend_state_t state) error: target_state = PM_SUSPEND_ON; +#ifdef CONFIG_PINCTRL_AT91 at91_pinctrl_gpio_resume(); +#endif return 0; } diff --git a/arch/arm/mach-dove/include/mach/entry-macro.S b/arch/arm/mach-dove/include/mach/entry-macro.S index 72d622baaad3..df1d44bdc375 100644 --- a/arch/arm/mach-dove/include/mach/entry-macro.S +++ b/arch/arm/mach-dove/include/mach/entry-macro.S @@ -18,13 +18,13 @@ @ check low interrupts ldr \irqstat, [\base, #IRQ_CAUSE_LOW_OFF] ldr \tmp, [\base, #IRQ_MASK_LOW_OFF] - mov \irqnr, #31 + mov \irqnr, #32 ands \irqstat, \irqstat, \tmp @ if no low interrupts set, check high interrupts ldreq \irqstat, [\base, #IRQ_CAUSE_HIGH_OFF] ldreq \tmp, [\base, #IRQ_MASK_HIGH_OFF] - moveq \irqnr, #63 + moveq \irqnr, #64 andeqs \irqstat, \irqstat, \tmp @ find first active interrupt source diff --git a/arch/arm/mach-exynos/Kconfig b/arch/arm/mach-exynos/Kconfig index 3a10f1a8317a..ff105399aae4 100644 --- a/arch/arm/mach-exynos/Kconfig +++ b/arch/arm/mach-exynos/Kconfig @@ -27,6 +27,7 @@ menuconfig ARCH_EXYNOS select SRAM select THERMAL select MFD_SYSCON + select CLKSRC_EXYNOS_MCT help Support for SAMSUNG EXYNOS SoCs (EXYNOS4/5) diff --git a/arch/arm/mach-exynos/pmu.c b/arch/arm/mach-exynos/pmu.c index de68938ee6aa..c21e41dad19c 100644 --- a/arch/arm/mach-exynos/pmu.c +++ b/arch/arm/mach-exynos/pmu.c @@ -748,8 +748,12 @@ static void exynos5_powerdown_conf(enum sys_powerdown mode) void exynos_sys_powerdown_conf(enum sys_powerdown mode) { unsigned int i; + const struct exynos_pmu_data *pmu_data; + + if (!pmu_context) + return; - const struct exynos_pmu_data *pmu_data = pmu_context->pmu_data; + pmu_data = pmu_context->pmu_data; if (pmu_data->powerdown_conf) pmu_data->powerdown_conf(mode); diff --git a/arch/arm/mach-imx/gpc.c b/arch/arm/mach-imx/gpc.c index 8e7976a4c3e7..cfc696b972f3 100644 --- a/arch/arm/mach-imx/gpc.c +++ b/arch/arm/mach-imx/gpc.c @@ -177,6 +177,7 @@ static struct irq_chip imx_gpc_chip = { .irq_unmask = imx_gpc_irq_unmask, .irq_retrigger = irq_chip_retrigger_hierarchy, .irq_set_wake = imx_gpc_irq_set_wake, + .irq_set_type = irq_chip_set_type_parent, #ifdef CONFIG_SMP .irq_set_affinity = irq_chip_set_affinity_parent, #endif diff --git a/arch/arm/mach-ixp4xx/include/mach/io.h b/arch/arm/mach-ixp4xx/include/mach/io.h index b02439019963..7a0c13bf4269 100644 --- a/arch/arm/mach-ixp4xx/include/mach/io.h +++ b/arch/arm/mach-ixp4xx/include/mach/io.h @@ -143,7 +143,7 @@ static inline void __indirect_writesl(volatile void __iomem *bus_addr, writel(*vaddr++, bus_addr); } -static inline unsigned char __indirect_readb(const volatile void __iomem *p) +static inline u8 __indirect_readb(const volatile void __iomem *p) { u32 addr = (u32)p; u32 n, byte_enables, data; @@ -166,7 +166,7 @@ static inline void __indirect_readsb(const volatile void __iomem *bus_addr, *vaddr++ = readb(bus_addr); } -static inline unsigned short __indirect_readw(const volatile void __iomem *p) +static inline u16 __indirect_readw(const volatile void __iomem *p) { u32 addr = (u32)p; u32 n, byte_enables, data; @@ -189,7 +189,7 @@ static inline void __indirect_readsw(const volatile void __iomem *bus_addr, *vaddr++ = readw(bus_addr); } -static inline unsigned long __indirect_readl(const volatile void __iomem *p) +static inline u32 __indirect_readl(const volatile void __iomem *p) { u32 addr = (__force u32)p; u32 data; @@ -350,7 +350,7 @@ static inline void insl(u32 io_addr, void *p, u32 count) ((unsigned long)p <= (PIO_MASK + PIO_OFFSET))) #define ioread8(p) ioread8(p) -static inline unsigned int ioread8(const void __iomem *addr) +static inline u8 ioread8(const void __iomem *addr) { unsigned long port = (unsigned long __force)addr; if (__is_io_address(port)) @@ -378,7 +378,7 @@ static inline void ioread8_rep(const void __iomem *addr, void *vaddr, u32 count) } #define ioread16(p) ioread16(p) -static inline unsigned int ioread16(const void __iomem *addr) +static inline u16 ioread16(const void __iomem *addr) { unsigned long port = (unsigned long __force)addr; if (__is_io_address(port)) @@ -407,7 +407,7 @@ static inline void ioread16_rep(const void __iomem *addr, void *vaddr, } #define ioread32(p) ioread32(p) -static inline unsigned int ioread32(const void __iomem *addr) +static inline u32 ioread32(const void __iomem *addr) { unsigned long port = (unsigned long __force)addr; if (__is_io_address(port)) diff --git a/arch/arm/mach-omap2/Kconfig b/arch/arm/mach-omap2/Kconfig index 5076d3f334d2..0517f0c1581a 100644 --- a/arch/arm/mach-omap2/Kconfig +++ b/arch/arm/mach-omap2/Kconfig @@ -65,6 +65,8 @@ config SOC_AM43XX select MACH_OMAP_GENERIC select MIGHT_HAVE_CACHE_L2X0 select HAVE_ARM_SCU + select GENERIC_CLOCKEVENTS_BROADCAST + select HAVE_ARM_TWD config SOC_DRA7XX bool "TI DRA7XX" @@ -121,6 +123,7 @@ config ARCH_OMAP2PLUS_TYPICAL select NEON if CPU_V7 select PM select REGULATOR + select REGULATOR_FIXED_VOLTAGE select TWL4030_CORE if ARCH_OMAP3 || ARCH_OMAP4 select TWL4030_POWER if ARCH_OMAP3 || ARCH_OMAP4 select VFP @@ -201,7 +204,6 @@ config MACH_OMAP3_PANDORA depends on ARCH_OMAP3 default y select OMAP_PACKAGE_CBB - select REGULATOR_FIXED_VOLTAGE if REGULATOR config MACH_NOKIA_N810 bool diff --git a/arch/arm/mach-omap2/gpmc-onenand.c b/arch/arm/mach-omap2/gpmc-onenand.c index 17a6f752a436..7b76ce01c21d 100644 --- a/arch/arm/mach-omap2/gpmc-onenand.c +++ b/arch/arm/mach-omap2/gpmc-onenand.c @@ -149,8 +149,8 @@ static int omap2_onenand_get_freq(struct omap_onenand_platform_data *cfg, freq = 104; break; default: - freq = 54; - break; + pr_err("onenand rate not detected, bad GPMC async timings?\n"); + freq = 0; } return freq; @@ -271,6 +271,11 @@ static int omap2_onenand_setup_async(void __iomem *onenand_base) struct gpmc_timings t; int ret; + /* + * Note that we need to keep sync_write set for the call to + * omap2_onenand_set_async_mode() to work to detect the onenand + * supported clock rate for the sync timings. + */ if (gpmc_onenand_data->of_node) { gpmc_read_settings_dt(gpmc_onenand_data->of_node, &onenand_async); @@ -281,12 +286,9 @@ static int omap2_onenand_setup_async(void __iomem *onenand_base) else gpmc_onenand_data->flags |= ONENAND_SYNC_READ; onenand_async.sync_read = false; - onenand_async.sync_write = false; } } - omap2_onenand_set_async_mode(onenand_base); - omap2_onenand_calc_async_timings(&t); ret = gpmc_cs_program_settings(gpmc_onenand_data->cs, &onenand_async); @@ -310,6 +312,8 @@ static int omap2_onenand_setup_sync(void __iomem *onenand_base, int *freq_ptr) if (!freq) { /* Very first call freq is not known */ freq = omap2_onenand_get_freq(gpmc_onenand_data, onenand_base); + if (!freq) + return -ENODEV; set_onenand_cfg(onenand_base); } diff --git a/arch/arm/mach-omap2/omap-smp.c b/arch/arm/mach-omap2/omap-smp.c index 5305ec7341ec..79e1f876d1c9 100644 --- a/arch/arm/mach-omap2/omap-smp.c +++ b/arch/arm/mach-omap2/omap-smp.c @@ -143,9 +143,9 @@ static int omap4_boot_secondary(unsigned int cpu, struct task_struct *idle) * Ensure that CPU power state is set to ON to avoid CPU * powerdomain transition on wfi */ - clkdm_wakeup(cpu1_clkdm); - omap_set_pwrdm_state(cpu1_pwrdm, PWRDM_POWER_ON); - clkdm_allow_idle(cpu1_clkdm); + clkdm_wakeup_nolock(cpu1_clkdm); + pwrdm_set_next_pwrst(cpu1_pwrdm, PWRDM_POWER_ON); + clkdm_allow_idle_nolock(cpu1_clkdm); if (IS_PM44XX_ERRATUM(PM_OMAP4_ROM_SMP_BOOT_ERRATUM_GICD)) { while (gic_dist_disabled()) { diff --git a/arch/arm/mach-omap2/omap_hwmod.c b/arch/arm/mach-omap2/omap_hwmod.c index cc8a987149e2..48495ad82aba 100644 --- a/arch/arm/mach-omap2/omap_hwmod.c +++ b/arch/arm/mach-omap2/omap_hwmod.c @@ -890,6 +890,36 @@ static int _init_opt_clks(struct omap_hwmod *oh) return ret; } +static void _enable_optional_clocks(struct omap_hwmod *oh) +{ + struct omap_hwmod_opt_clk *oc; + int i; + + pr_debug("omap_hwmod: %s: enabling optional clocks\n", oh->name); + + for (i = oh->opt_clks_cnt, oc = oh->opt_clks; i > 0; i--, oc++) + if (oc->_clk) { + pr_debug("omap_hwmod: enable %s:%s\n", oc->role, + __clk_get_name(oc->_clk)); + clk_enable(oc->_clk); + } +} + +static void _disable_optional_clocks(struct omap_hwmod *oh) +{ + struct omap_hwmod_opt_clk *oc; + int i; + + pr_debug("omap_hwmod: %s: disabling optional clocks\n", oh->name); + + for (i = oh->opt_clks_cnt, oc = oh->opt_clks; i > 0; i--, oc++) + if (oc->_clk) { + pr_debug("omap_hwmod: disable %s:%s\n", oc->role, + __clk_get_name(oc->_clk)); + clk_disable(oc->_clk); + } +} + /** * _enable_clocks - enable hwmod main clock and interface clocks * @oh: struct omap_hwmod * @@ -917,6 +947,9 @@ static int _enable_clocks(struct omap_hwmod *oh) clk_enable(os->_clk); } + if (oh->flags & HWMOD_OPT_CLKS_NEEDED) + _enable_optional_clocks(oh); + /* The opt clocks are controlled by the device driver. */ return 0; @@ -948,41 +981,14 @@ static int _disable_clocks(struct omap_hwmod *oh) clk_disable(os->_clk); } + if (oh->flags & HWMOD_OPT_CLKS_NEEDED) + _disable_optional_clocks(oh); + /* The opt clocks are controlled by the device driver. */ return 0; } -static void _enable_optional_clocks(struct omap_hwmod *oh) -{ - struct omap_hwmod_opt_clk *oc; - int i; - - pr_debug("omap_hwmod: %s: enabling optional clocks\n", oh->name); - - for (i = oh->opt_clks_cnt, oc = oh->opt_clks; i > 0; i--, oc++) - if (oc->_clk) { - pr_debug("omap_hwmod: enable %s:%s\n", oc->role, - __clk_get_name(oc->_clk)); - clk_enable(oc->_clk); - } -} - -static void _disable_optional_clocks(struct omap_hwmod *oh) -{ - struct omap_hwmod_opt_clk *oc; - int i; - - pr_debug("omap_hwmod: %s: disabling optional clocks\n", oh->name); - - for (i = oh->opt_clks_cnt, oc = oh->opt_clks; i > 0; i--, oc++) - if (oc->_clk) { - pr_debug("omap_hwmod: disable %s:%s\n", oc->role, - __clk_get_name(oc->_clk)); - clk_disable(oc->_clk); - } -} - /** * _omap4_enable_module - enable CLKCTRL modulemode on OMAP4 * @oh: struct omap_hwmod * diff --git a/arch/arm/mach-omap2/omap_hwmod.h b/arch/arm/mach-omap2/omap_hwmod.h index ca6df1a73475..76bce11c85a4 100644 --- a/arch/arm/mach-omap2/omap_hwmod.h +++ b/arch/arm/mach-omap2/omap_hwmod.h @@ -523,6 +523,8 @@ struct omap_hwmod_omap4_prcm { * HWMOD_RECONFIG_IO_CHAIN: omap_hwmod code needs to reconfigure wake-up * events by calling _reconfigure_io_chain() when a device is enabled * or idled. + * HWMOD_OPT_CLKS_NEEDED: The optional clocks are needed for the module to + * operate and they need to be handled at the same time as the main_clk. */ #define HWMOD_SWSUP_SIDLE (1 << 0) #define HWMOD_SWSUP_MSTANDBY (1 << 1) @@ -538,6 +540,7 @@ struct omap_hwmod_omap4_prcm { #define HWMOD_FORCE_MSTANDBY (1 << 11) #define HWMOD_SWSUP_SIDLE_ACT (1 << 12) #define HWMOD_RECONFIG_IO_CHAIN (1 << 13) +#define HWMOD_OPT_CLKS_NEEDED (1 << 14) /* * omap_hwmod._int_flags definitions diff --git a/arch/arm/mach-omap2/omap_hwmod_7xx_data.c b/arch/arm/mach-omap2/omap_hwmod_7xx_data.c index 51d1ecb384bd..ee4e04434a94 100644 --- a/arch/arm/mach-omap2/omap_hwmod_7xx_data.c +++ b/arch/arm/mach-omap2/omap_hwmod_7xx_data.c @@ -1298,6 +1298,44 @@ static struct omap_hwmod dra7xx_mcspi4_hwmod = { }; /* + * 'mcasp' class + * + */ +static struct omap_hwmod_class_sysconfig dra7xx_mcasp_sysc = { + .sysc_offs = 0x0004, + .sysc_flags = SYSC_HAS_SIDLEMODE, + .idlemodes = (SIDLE_FORCE | SIDLE_NO | SIDLE_SMART), + .sysc_fields = &omap_hwmod_sysc_type3, +}; + +static struct omap_hwmod_class dra7xx_mcasp_hwmod_class = { + .name = "mcasp", + .sysc = &dra7xx_mcasp_sysc, +}; + +/* mcasp3 */ +static struct omap_hwmod_opt_clk mcasp3_opt_clks[] = { + { .role = "ahclkx", .clk = "mcasp3_ahclkx_mux" }, +}; + +static struct omap_hwmod dra7xx_mcasp3_hwmod = { + .name = "mcasp3", + .class = &dra7xx_mcasp_hwmod_class, + .clkdm_name = "l4per2_clkdm", + .main_clk = "mcasp3_aux_gfclk_mux", + .flags = HWMOD_OPT_CLKS_NEEDED, + .prcm = { + .omap4 = { + .clkctrl_offs = DRA7XX_CM_L4PER2_MCASP3_CLKCTRL_OFFSET, + .context_offs = DRA7XX_RM_L4PER2_MCASP3_CONTEXT_OFFSET, + .modulemode = MODULEMODE_SWCTRL, + }, + }, + .opt_clks = mcasp3_opt_clks, + .opt_clks_cnt = ARRAY_SIZE(mcasp3_opt_clks), +}; + +/* * 'mmc' class * */ @@ -2566,6 +2604,22 @@ static struct omap_hwmod_ocp_if dra7xx_l3_main_1__hdmi = { .user = OCP_USER_MPU | OCP_USER_SDMA, }; +/* l4_per2 -> mcasp3 */ +static struct omap_hwmod_ocp_if dra7xx_l4_per2__mcasp3 = { + .master = &dra7xx_l4_per2_hwmod, + .slave = &dra7xx_mcasp3_hwmod, + .clk = "l4_root_clk_div", + .user = OCP_USER_MPU | OCP_USER_SDMA, +}; + +/* l3_main_1 -> mcasp3 */ +static struct omap_hwmod_ocp_if dra7xx_l3_main_1__mcasp3 = { + .master = &dra7xx_l3_main_1_hwmod, + .slave = &dra7xx_mcasp3_hwmod, + .clk = "l3_iclk_div", + .user = OCP_USER_MPU | OCP_USER_SDMA, +}; + /* l4_per1 -> elm */ static struct omap_hwmod_ocp_if dra7xx_l4_per1__elm = { .master = &dra7xx_l4_per1_hwmod, @@ -3308,6 +3362,8 @@ static struct omap_hwmod_ocp_if *dra7xx_hwmod_ocp_ifs[] __initdata = { &dra7xx_l4_wkup__dcan1, &dra7xx_l4_per2__dcan2, &dra7xx_l4_per2__cpgmac0, + &dra7xx_l4_per2__mcasp3, + &dra7xx_l3_main_1__mcasp3, &dra7xx_gmac__mdio, &dra7xx_l4_cfg__dma_system, &dra7xx_l3_main_1__dss, diff --git a/arch/arm/mach-omap2/omap_hwmod_81xx_data.c b/arch/arm/mach-omap2/omap_hwmod_81xx_data.c index b1288f56d509..6256052893ec 100644 --- a/arch/arm/mach-omap2/omap_hwmod_81xx_data.c +++ b/arch/arm/mach-omap2/omap_hwmod_81xx_data.c @@ -144,6 +144,7 @@ static struct omap_hwmod dm81xx_l4_ls_hwmod = { .name = "l4_ls", .clkdm_name = "alwon_l3s_clkdm", .class = &l4_hwmod_class, + .flags = HWMOD_NO_IDLEST, }; /* @@ -155,6 +156,7 @@ static struct omap_hwmod dm81xx_l4_hs_hwmod = { .name = "l4_hs", .clkdm_name = "alwon_l3_med_clkdm", .class = &l4_hwmod_class, + .flags = HWMOD_NO_IDLEST, }; /* L3 slow -> L4 ls peripheral interface running at 125MHz */ @@ -850,6 +852,7 @@ static struct omap_hwmod dm816x_emac0_hwmod = { .name = "emac0", .clkdm_name = "alwon_ethernet_clkdm", .class = &dm816x_emac_hwmod_class, + .flags = HWMOD_NO_IDLEST, }; static struct omap_hwmod_ocp_if dm81xx_l4_hs__emac0 = { diff --git a/arch/arm/mach-omap2/pdata-quirks.c b/arch/arm/mach-omap2/pdata-quirks.c index 1dfe34654c43..58144779dec4 100644 --- a/arch/arm/mach-omap2/pdata-quirks.c +++ b/arch/arm/mach-omap2/pdata-quirks.c @@ -24,9 +24,6 @@ #include <linux/platform_data/iommu-omap.h> #include <linux/platform_data/wkup_m3.h> -#include <asm/siginfo.h> -#include <asm/signal.h> - #include "common.h" #include "common-board-devices.h" #include "dss-common.h" @@ -385,29 +382,6 @@ static void __init omap3_pandora_legacy_init(void) } #endif /* CONFIG_ARCH_OMAP3 */ -#ifdef CONFIG_SOC_TI81XX -static int fault_fixed_up; - -static int t410_abort_handler(unsigned long addr, unsigned int fsr, - struct pt_regs *regs) -{ - if ((fsr == 0x406 || fsr == 0xc06) && !fault_fixed_up) { - pr_warn("External imprecise Data abort at addr=%#lx, fsr=%#x ignored.\n", - addr, fsr); - fault_fixed_up = 1; - return 0; - } - - return 1; -} - -static void __init t410_abort_init(void) -{ - hook_fault_code(16 + 6, t410_abort_handler, SIGBUS, BUS_OBJERR, - "imprecise external abort"); -} -#endif - #if defined(CONFIG_ARCH_OMAP4) || defined(CONFIG_SOC_OMAP5) static struct iommu_platform_data omap4_iommu_pdata = { .reset_name = "mmu_cache", @@ -536,9 +510,6 @@ static struct pdata_init pdata_quirks[] __initdata = { { "openpandora,omap3-pandora-600mhz", omap3_pandora_legacy_init, }, { "openpandora,omap3-pandora-1ghz", omap3_pandora_legacy_init, }, #endif -#ifdef CONFIG_SOC_TI81XX - { "hp,t410", t410_abort_init, }, -#endif #ifdef CONFIG_SOC_OMAP5 { "ti,omap5-uevm", omap5_uevm_legacy_init, }, #endif diff --git a/arch/arm/mach-omap2/pm34xx.c b/arch/arm/mach-omap2/pm34xx.c index 87b98bf92366..2dbd3785ee6f 100644 --- a/arch/arm/mach-omap2/pm34xx.c +++ b/arch/arm/mach-omap2/pm34xx.c @@ -301,11 +301,11 @@ static void omap3_pm_idle(void) if (omap_irq_pending()) return; - trace_cpu_idle(1, smp_processor_id()); + trace_cpu_idle_rcuidle(1, smp_processor_id()); omap_sram_idle(); - trace_cpu_idle(PWR_EVENT_EXIT, smp_processor_id()); + trace_cpu_idle_rcuidle(PWR_EVENT_EXIT, smp_processor_id()); } #ifdef CONFIG_SUSPEND diff --git a/arch/arm/mach-omap2/timer.c b/arch/arm/mach-omap2/timer.c index b18ebbefae09..f86692dbcfd5 100644 --- a/arch/arm/mach-omap2/timer.c +++ b/arch/arm/mach-omap2/timer.c @@ -320,6 +320,12 @@ static int __init omap_dm_timer_init_one(struct omap_dm_timer *timer, return r; } +#if !defined(CONFIG_SMP) && defined(CONFIG_GENERIC_CLOCKEVENTS_BROADCAST) +void tick_broadcast(const struct cpumask *mask) +{ +} +#endif + static void __init omap2_gp_clockevent_init(int gptimer_id, const char *fck_source, const char *property) diff --git a/arch/arm/mach-orion5x/include/mach/entry-macro.S b/arch/arm/mach-orion5x/include/mach/entry-macro.S index 79eb502a1e64..73919a36b577 100644 --- a/arch/arm/mach-orion5x/include/mach/entry-macro.S +++ b/arch/arm/mach-orion5x/include/mach/entry-macro.S @@ -21,5 +21,5 @@ @ find cause bits that are unmasked ands \irqstat, \irqstat, \tmp @ clear Z flag if any clzne \irqnr, \irqstat @ calc irqnr - rsbne \irqnr, \irqnr, #31 + rsbne \irqnr, \irqnr, #32 .endm diff --git a/arch/arm/mach-pxa/ezx.c b/arch/arm/mach-pxa/ezx.c index 9a9c15bfcd34..7c0d5618be5e 100644 --- a/arch/arm/mach-pxa/ezx.c +++ b/arch/arm/mach-pxa/ezx.c @@ -889,6 +889,7 @@ static void __init e680_init(void) pxa_set_keypad_info(&e680_keypad_platform_data); + pwm_add_table(ezx_pwm_lookup, ARRAY_SIZE(ezx_pwm_lookup)); platform_add_devices(ARRAY_AND_SIZE(ezx_devices)); platform_add_devices(ARRAY_AND_SIZE(e680_devices)); } @@ -956,6 +957,7 @@ static void __init a1200_init(void) pxa_set_keypad_info(&a1200_keypad_platform_data); + pwm_add_table(ezx_pwm_lookup, ARRAY_SIZE(ezx_pwm_lookup)); platform_add_devices(ARRAY_AND_SIZE(ezx_devices)); platform_add_devices(ARRAY_AND_SIZE(a1200_devices)); } @@ -1148,6 +1150,7 @@ static void __init a910_init(void) platform_device_register(&a910_camera); } + pwm_add_table(ezx_pwm_lookup, ARRAY_SIZE(ezx_pwm_lookup)); platform_add_devices(ARRAY_AND_SIZE(ezx_devices)); platform_add_devices(ARRAY_AND_SIZE(a910_devices)); } @@ -1215,6 +1218,7 @@ static void __init e6_init(void) pxa_set_keypad_info(&e6_keypad_platform_data); + pwm_add_table(ezx_pwm_lookup, ARRAY_SIZE(ezx_pwm_lookup)); platform_add_devices(ARRAY_AND_SIZE(ezx_devices)); platform_add_devices(ARRAY_AND_SIZE(e6_devices)); } @@ -1256,6 +1260,7 @@ static void __init e2_init(void) pxa_set_keypad_info(&e2_keypad_platform_data); + pwm_add_table(ezx_pwm_lookup, ARRAY_SIZE(ezx_pwm_lookup)); platform_add_devices(ARRAY_AND_SIZE(ezx_devices)); platform_add_devices(ARRAY_AND_SIZE(e2_devices)); } diff --git a/arch/arm/mach-pxa/palm27x.c b/arch/arm/mach-pxa/palm27x.c index 13eba2b26e0a..8fbfb10047ec 100644 --- a/arch/arm/mach-pxa/palm27x.c +++ b/arch/arm/mach-pxa/palm27x.c @@ -344,7 +344,7 @@ void __init palm27x_pwm_init(int bl, int lcd) { palm_bl_power = bl; palm_lcd_power = lcd; - pwm_add_lookup(palm27x_pwm_lookup, ARRAY_SIZE(palm27x_pwm_lookup)); + pwm_add_table(palm27x_pwm_lookup, ARRAY_SIZE(palm27x_pwm_lookup)); platform_device_register(&palm27x_backlight); } #endif diff --git a/arch/arm/mach-pxa/palmtc.c b/arch/arm/mach-pxa/palmtc.c index aebf6de62468..0b5c3876720c 100644 --- a/arch/arm/mach-pxa/palmtc.c +++ b/arch/arm/mach-pxa/palmtc.c @@ -169,7 +169,7 @@ static inline void palmtc_keys_init(void) {} #if defined(CONFIG_BACKLIGHT_PWM) || defined(CONFIG_BACKLIGHT_PWM_MODULE) static struct pwm_lookup palmtc_pwm_lookup[] = { PWM_LOOKUP("pxa25x-pwm.1", 0, "pwm-backlight.0", NULL, PALMTC_PERIOD_NS, - PWM_PERIOD_NORMAL), + PWM_POLARITY_NORMAL), }; static struct platform_pwm_backlight_data palmtc_backlight_data = { diff --git a/arch/arm/mach-s3c24xx/pll-s3c2440-12000000.c b/arch/arm/mach-s3c24xx/pll-s3c2440-12000000.c index a19460e6e7b0..b355fca6cc2e 100644 --- a/arch/arm/mach-s3c24xx/pll-s3c2440-12000000.c +++ b/arch/arm/mach-s3c24xx/pll-s3c2440-12000000.c @@ -20,7 +20,7 @@ #include <plat/cpu.h> #include <plat/cpu-freq-core.h> -static struct cpufreq_frequency_table s3c2440_plls_12[] __initdata = { +static struct cpufreq_frequency_table s3c2440_plls_12[] = { { .frequency = 75000000, .driver_data = PLLVAL(0x75, 3, 3), }, /* FVco 600.000000 */ { .frequency = 80000000, .driver_data = PLLVAL(0x98, 4, 3), }, /* FVco 640.000000 */ { .frequency = 90000000, .driver_data = PLLVAL(0x70, 2, 3), }, /* FVco 720.000000 */ diff --git a/arch/arm/mach-s3c24xx/pll-s3c2440-16934400.c b/arch/arm/mach-s3c24xx/pll-s3c2440-16934400.c index 1191b2905625..be9a248b5ce9 100644 --- a/arch/arm/mach-s3c24xx/pll-s3c2440-16934400.c +++ b/arch/arm/mach-s3c24xx/pll-s3c2440-16934400.c @@ -20,7 +20,7 @@ #include <plat/cpu.h> #include <plat/cpu-freq-core.h> -static struct cpufreq_frequency_table s3c2440_plls_169344[] __initdata = { +static struct cpufreq_frequency_table s3c2440_plls_169344[] = { { .frequency = 78019200, .driver_data = PLLVAL(121, 5, 3), }, /* FVco 624.153600 */ { .frequency = 84067200, .driver_data = PLLVAL(131, 5, 3), }, /* FVco 672.537600 */ { .frequency = 90115200, .driver_data = PLLVAL(141, 5, 3), }, /* FVco 720.921600 */ diff --git a/arch/arm/mach-shmobile/setup-r8a7793.c b/arch/arm/mach-shmobile/setup-r8a7793.c index 1d2825cb7a65..5fce87f7f254 100644 --- a/arch/arm/mach-shmobile/setup-r8a7793.c +++ b/arch/arm/mach-shmobile/setup-r8a7793.c @@ -19,7 +19,7 @@ #include "common.h" #include "rcar-gen2.h" -static const char *r8a7793_boards_compat_dt[] __initconst = { +static const char * const r8a7793_boards_compat_dt[] __initconst = { "renesas,r8a7793", NULL, }; diff --git a/arch/arm/mach-sti/Kconfig b/arch/arm/mach-sti/Kconfig index 125865daaf17..12dd1dc0a041 100644 --- a/arch/arm/mach-sti/Kconfig +++ b/arch/arm/mach-sti/Kconfig @@ -3,6 +3,7 @@ menuconfig ARCH_STI select ARM_GIC select ST_IRQCHIP select ARM_GLOBAL_TIMER + select CLKSRC_ST_LPC select PINCTRL select PINCTRL_ST select MFD_SYSCON diff --git a/arch/arm/mach-ux500/Kconfig b/arch/arm/mach-ux500/Kconfig index c9ac19b24e5a..5eacdd61e61c 100644 --- a/arch/arm/mach-ux500/Kconfig +++ b/arch/arm/mach-ux500/Kconfig @@ -32,6 +32,7 @@ config UX500_SOC_DB8500 select PINCTRL_AB8540 select REGULATOR select REGULATOR_DB8500_PRCMU + select CLKSRC_DBX500_PRCMU select PM_GENERIC_DOMAINS if PM config MACH_MOP500 diff --git a/arch/arm/mach-zx/Kconfig b/arch/arm/mach-zx/Kconfig index 7fdc5bf24f9b..446334a25cf5 100644 --- a/arch/arm/mach-zx/Kconfig +++ b/arch/arm/mach-zx/Kconfig @@ -13,7 +13,7 @@ config SOC_ZX296702 select ARM_GLOBAL_TIMER select HAVE_ARM_SCU if SMP select HAVE_ARM_TWD if SMP - select PM_GENERIC_DOMAINS + select PM_GENERIC_DOMAINS if PM help Support for ZTE ZX296702 SoC which is a dual core CortexA9MP endif diff --git a/arch/arm/mm/context.c b/arch/arm/mm/context.c index 845769e41332..c8c8b9ed02e0 100644 --- a/arch/arm/mm/context.c +++ b/arch/arm/mm/context.c @@ -165,13 +165,28 @@ static void flush_context(unsigned int cpu) __flush_icache_all(); } -static int is_reserved_asid(u64 asid) +static bool check_update_reserved_asid(u64 asid, u64 newasid) { int cpu; - for_each_possible_cpu(cpu) - if (per_cpu(reserved_asids, cpu) == asid) - return 1; - return 0; + bool hit = false; + + /* + * Iterate over the set of reserved ASIDs looking for a match. + * If we find one, then we can update our mm to use newasid + * (i.e. the same ASID in the current generation) but we can't + * exit the loop early, since we need to ensure that all copies + * of the old ASID are updated to reflect the mm. Failure to do + * so could result in us missing the reserved ASID in a future + * generation. + */ + for_each_possible_cpu(cpu) { + if (per_cpu(reserved_asids, cpu) == asid) { + hit = true; + per_cpu(reserved_asids, cpu) = newasid; + } + } + + return hit; } static u64 new_context(struct mm_struct *mm, unsigned int cpu) @@ -181,12 +196,14 @@ static u64 new_context(struct mm_struct *mm, unsigned int cpu) u64 generation = atomic64_read(&asid_generation); if (asid != 0) { + u64 newasid = generation | (asid & ~ASID_MASK); + /* * If our current ASID was active during a rollover, we * can continue to use it and this was just a false alarm. */ - if (is_reserved_asid(asid)) - return generation | (asid & ~ASID_MASK); + if (check_update_reserved_asid(asid, newasid)) + return newasid; /* * We had a valid ASID in a previous life, so try to re-use @@ -194,7 +211,7 @@ static u64 new_context(struct mm_struct *mm, unsigned int cpu) */ asid &= ~ASID_MASK; if (!__test_and_set_bit(asid, asid_map)) - goto bump_gen; + return newasid; } /* @@ -216,11 +233,8 @@ static u64 new_context(struct mm_struct *mm, unsigned int cpu) __set_bit(asid, asid_map); cur_idx = asid; - -bump_gen: - asid |= generation; cpumask_clear(mm_cpumask(mm)); - return asid; + return asid | generation; } void check_and_switch_context(struct mm_struct *mm, struct task_struct *tsk) diff --git a/arch/arm/mm/dma-mapping.c b/arch/arm/mm/dma-mapping.c index e62400e5fb99..534a60ae282e 100644 --- a/arch/arm/mm/dma-mapping.c +++ b/arch/arm/mm/dma-mapping.c @@ -1521,7 +1521,7 @@ static int __map_sg_chunk(struct device *dev, struct scatterlist *sg, return -ENOMEM; for (count = 0, s = sg; count < (size >> PAGE_SHIFT); s = sg_next(s)) { - phys_addr_t phys = sg_phys(s) & PAGE_MASK; + phys_addr_t phys = page_to_phys(sg_page(s)); unsigned int len = PAGE_ALIGN(s->offset + s->length); if (!is_coherent && diff --git a/arch/arm/mm/init.c b/arch/arm/mm/init.c index 8a63b4cdc0f2..7f8cd1b3557f 100644 --- a/arch/arm/mm/init.c +++ b/arch/arm/mm/init.c @@ -22,6 +22,7 @@ #include <linux/memblock.h> #include <linux/dma-contiguous.h> #include <linux/sizes.h> +#include <linux/stop_machine.h> #include <asm/cp15.h> #include <asm/mach-types.h> @@ -627,12 +628,10 @@ static struct section_perm ro_perms[] = { * safe to be called with preemption disabled, as under stop_machine(). */ static inline void section_update(unsigned long addr, pmdval_t mask, - pmdval_t prot) + pmdval_t prot, struct mm_struct *mm) { - struct mm_struct *mm; pmd_t *pmd; - mm = current->active_mm; pmd = pmd_offset(pud_offset(pgd_offset(mm, addr), addr), addr); #ifdef CONFIG_ARM_LPAE @@ -656,49 +655,82 @@ static inline bool arch_has_strict_perms(void) return !!(get_cr() & CR_XP); } -#define set_section_perms(perms, field) { \ - size_t i; \ - unsigned long addr; \ - \ - if (!arch_has_strict_perms()) \ - return; \ - \ - for (i = 0; i < ARRAY_SIZE(perms); i++) { \ - if (!IS_ALIGNED(perms[i].start, SECTION_SIZE) || \ - !IS_ALIGNED(perms[i].end, SECTION_SIZE)) { \ - pr_err("BUG: section %lx-%lx not aligned to %lx\n", \ - perms[i].start, perms[i].end, \ - SECTION_SIZE); \ - continue; \ - } \ - \ - for (addr = perms[i].start; \ - addr < perms[i].end; \ - addr += SECTION_SIZE) \ - section_update(addr, perms[i].mask, \ - perms[i].field); \ - } \ +void set_section_perms(struct section_perm *perms, int n, bool set, + struct mm_struct *mm) +{ + size_t i; + unsigned long addr; + + if (!arch_has_strict_perms()) + return; + + for (i = 0; i < n; i++) { + if (!IS_ALIGNED(perms[i].start, SECTION_SIZE) || + !IS_ALIGNED(perms[i].end, SECTION_SIZE)) { + pr_err("BUG: section %lx-%lx not aligned to %lx\n", + perms[i].start, perms[i].end, + SECTION_SIZE); + continue; + } + + for (addr = perms[i].start; + addr < perms[i].end; + addr += SECTION_SIZE) + section_update(addr, perms[i].mask, + set ? perms[i].prot : perms[i].clear, mm); + } + } -static inline void fix_kernmem_perms(void) +static void update_sections_early(struct section_perm perms[], int n) { - set_section_perms(nx_perms, prot); + struct task_struct *t, *s; + + read_lock(&tasklist_lock); + for_each_process(t) { + if (t->flags & PF_KTHREAD) + continue; + for_each_thread(t, s) + set_section_perms(perms, n, true, s->mm); + } + read_unlock(&tasklist_lock); + set_section_perms(perms, n, true, current->active_mm); + set_section_perms(perms, n, true, &init_mm); +} + +int __fix_kernmem_perms(void *unused) +{ + update_sections_early(nx_perms, ARRAY_SIZE(nx_perms)); + return 0; +} + +void fix_kernmem_perms(void) +{ + stop_machine(__fix_kernmem_perms, NULL, NULL); } #ifdef CONFIG_DEBUG_RODATA +int __mark_rodata_ro(void *unused) +{ + update_sections_early(ro_perms, ARRAY_SIZE(ro_perms)); + return 0; +} + void mark_rodata_ro(void) { - set_section_perms(ro_perms, prot); + stop_machine(__mark_rodata_ro, NULL, NULL); } void set_kernel_text_rw(void) { - set_section_perms(ro_perms, clear); + set_section_perms(ro_perms, ARRAY_SIZE(ro_perms), false, + current->active_mm); } void set_kernel_text_ro(void) { - set_section_perms(ro_perms, prot); + set_section_perms(ro_perms, ARRAY_SIZE(ro_perms), true, + current->active_mm); } #endif /* CONFIG_DEBUG_RODATA */ diff --git a/arch/arm/mm/proc-v7.S b/arch/arm/mm/proc-v7.S index de2b246fed38..8e1ea433c3f1 100644 --- a/arch/arm/mm/proc-v7.S +++ b/arch/arm/mm/proc-v7.S @@ -95,7 +95,7 @@ ENDPROC(cpu_v7_dcache_clean_area) .equ cpu_v7_suspend_size, 4 * 9 #ifdef CONFIG_ARM_CPU_SUSPEND ENTRY(cpu_v7_do_suspend) - stmfd sp!, {r4 - r10, lr} + stmfd sp!, {r4 - r11, lr} mrc p15, 0, r4, c13, c0, 0 @ FCSE/PID mrc p15, 0, r5, c13, c0, 3 @ User r/o thread ID stmia r0!, {r4 - r5} @@ -112,7 +112,7 @@ ENTRY(cpu_v7_do_suspend) mrc p15, 0, r9, c1, c0, 1 @ Auxiliary control register mrc p15, 0, r10, c1, c0, 2 @ Co-processor access control stmia r0, {r5 - r11} - ldmfd sp!, {r4 - r10, pc} + ldmfd sp!, {r4 - r11, pc} ENDPROC(cpu_v7_do_suspend) ENTRY(cpu_v7_do_resume) diff --git a/arch/arm/net/bpf_jit_32.c b/arch/arm/net/bpf_jit_32.c index 2f4b14cfddb4..93d0b6d0b63e 100644 --- a/arch/arm/net/bpf_jit_32.c +++ b/arch/arm/net/bpf_jit_32.c @@ -187,19 +187,6 @@ static inline int mem_words_used(struct jit_ctx *ctx) return fls(ctx->seen & SEEN_MEM); } -static inline bool is_load_to_a(u16 inst) -{ - switch (inst) { - case BPF_LD | BPF_W | BPF_LEN: - case BPF_LD | BPF_W | BPF_ABS: - case BPF_LD | BPF_H | BPF_ABS: - case BPF_LD | BPF_B | BPF_ABS: - return true; - default: - return false; - } -} - static void jit_fill_hole(void *area, unsigned int size) { u32 *ptr; @@ -211,7 +198,6 @@ static void jit_fill_hole(void *area, unsigned int size) static void build_prologue(struct jit_ctx *ctx) { u16 reg_set = saved_regs(ctx); - u16 first_inst = ctx->skf->insns[0].code; u16 off; #ifdef CONFIG_FRAME_POINTER @@ -241,7 +227,7 @@ static void build_prologue(struct jit_ctx *ctx) emit(ARM_MOV_I(r_X, 0), ctx); /* do not leak kernel data to userspace */ - if ((first_inst != (BPF_RET | BPF_K)) && !(is_load_to_a(first_inst))) + if (bpf_needs_clear_a(&ctx->skf->insns[0])) emit(ARM_MOV_I(r_A, 0), ctx); /* stack space for the BPF_MEM words */ @@ -770,7 +756,8 @@ load_ind: case BPF_ALU | BPF_RSH | BPF_K: if (unlikely(k > 31)) return -1; - emit(ARM_LSR_I(r_A, r_A, k), ctx); + if (k) + emit(ARM_LSR_I(r_A, r_A, k), ctx); break; case BPF_ALU | BPF_RSH | BPF_X: update_on_xread(ctx); @@ -1061,7 +1048,7 @@ void bpf_jit_compile(struct bpf_prog *fp) } build_epilogue(&ctx); - flush_icache_range((u32)ctx.target, (u32)(ctx.target + ctx.idx)); + flush_icache_range((u32)header, (u32)(ctx.target + ctx.idx)); #if __LINUX_ARM_ARCH__ < 7 if (ctx.imm_count) diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig index 9ac16a482ff1..871f21783866 100644 --- a/arch/arm64/Kconfig +++ b/arch/arm64/Kconfig @@ -49,7 +49,7 @@ config ARM64 select HAVE_ARCH_AUDITSYSCALL select HAVE_ARCH_BITREVERSE select HAVE_ARCH_JUMP_LABEL - select HAVE_ARCH_KASAN if SPARSEMEM_VMEMMAP + select HAVE_ARCH_KASAN if SPARSEMEM_VMEMMAP && !(ARM64_16K_PAGES && ARM64_VA_BITS_48) select HAVE_ARCH_KGDB select HAVE_ARCH_SECCOMP_FILTER select HAVE_ARCH_TRACEHOOK @@ -316,6 +316,27 @@ config ARM64_ERRATUM_832075 If unsure, say Y. +config ARM64_ERRATUM_834220 + bool "Cortex-A57: 834220: Stage 2 translation fault might be incorrectly reported in presence of a Stage 1 fault" + depends on KVM + default y + help + This option adds an alternative code sequence to work around ARM + erratum 834220 on Cortex-A57 parts up to r1p2. + + Affected Cortex-A57 parts might report a Stage 2 translation + fault as the result of a Stage 1 fault for load crossing a + page boundary when there is a permission or device memory + alignment fault at Stage 1 and a translation fault at Stage 2. + + The workaround is to verify that the Stage 1 translation + doesn't generate a fault before handling the Stage 2 fault. + Please note that this does not necessarily enable the workaround, + as it depends on the alternative framework, which will only patch + the kernel if an affected CPU is detected. + + If unsure, say Y. + config ARM64_ERRATUM_845719 bool "Cortex-A53: 845719: a load might read incorrect data" depends on COMPAT diff --git a/arch/arm64/boot/dts/freescale/fsl-ls2080a.dtsi b/arch/arm64/boot/dts/freescale/fsl-ls2080a.dtsi index e81cd48d6245..925552e7b4f3 100644 --- a/arch/arm64/boot/dts/freescale/fsl-ls2080a.dtsi +++ b/arch/arm64/boot/dts/freescale/fsl-ls2080a.dtsi @@ -269,6 +269,7 @@ clock-frequency = <0>; /* Updated by bootloader */ voltage-ranges = <1800 1800 3300 3300>; sdhci,auto-cmd12; + little-endian; bus-width = <4>; }; @@ -277,6 +278,7 @@ reg = <0x0 0x2300000 0x0 0x10000>; interrupts = <0 36 0x4>; /* Level high type */ gpio-controller; + little-endian; #gpio-cells = <2>; interrupt-controller; #interrupt-cells = <2>; @@ -287,6 +289,7 @@ reg = <0x0 0x2310000 0x0 0x10000>; interrupts = <0 36 0x4>; /* Level high type */ gpio-controller; + little-endian; #gpio-cells = <2>; interrupt-controller; #interrupt-cells = <2>; @@ -297,6 +300,7 @@ reg = <0x0 0x2320000 0x0 0x10000>; interrupts = <0 37 0x4>; /* Level high type */ gpio-controller; + little-endian; #gpio-cells = <2>; interrupt-controller; #interrupt-cells = <2>; @@ -307,6 +311,7 @@ reg = <0x0 0x2330000 0x0 0x10000>; interrupts = <0 37 0x4>; /* Level high type */ gpio-controller; + little-endian; #gpio-cells = <2>; interrupt-controller; #interrupt-cells = <2>; diff --git a/arch/arm64/crypto/aes-ce-cipher.c b/arch/arm64/crypto/aes-ce-cipher.c index ce47792a983d..f7bd9bf0bbb3 100644 --- a/arch/arm64/crypto/aes-ce-cipher.c +++ b/arch/arm64/crypto/aes-ce-cipher.c @@ -237,7 +237,7 @@ EXPORT_SYMBOL(ce_aes_setkey); static struct crypto_alg aes_alg = { .cra_name = "aes", .cra_driver_name = "aes-ce", - .cra_priority = 300, + .cra_priority = 250, .cra_flags = CRYPTO_ALG_TYPE_CIPHER, .cra_blocksize = AES_BLOCK_SIZE, .cra_ctxsize = sizeof(struct crypto_aes_ctx), diff --git a/arch/arm64/include/asm/arch_gicv3.h b/arch/arm64/include/asm/arch_gicv3.h index 030cdcb46c6b..2731d3b25ed2 100644 --- a/arch/arm64/include/asm/arch_gicv3.h +++ b/arch/arm64/include/asm/arch_gicv3.h @@ -77,6 +77,7 @@ #ifndef __ASSEMBLY__ #include <linux/stringify.h> +#include <asm/barrier.h> /* * Low-level accessors diff --git a/arch/arm64/include/asm/barrier.h b/arch/arm64/include/asm/barrier.h index 624f9679f4b0..9622eb48f894 100644 --- a/arch/arm64/include/asm/barrier.h +++ b/arch/arm64/include/asm/barrier.h @@ -64,27 +64,31 @@ do { \ #define smp_load_acquire(p) \ ({ \ - typeof(*p) ___p1; \ + union { typeof(*p) __val; char __c[1]; } __u; \ compiletime_assert_atomic_type(*p); \ switch (sizeof(*p)) { \ case 1: \ asm volatile ("ldarb %w0, %1" \ - : "=r" (___p1) : "Q" (*p) : "memory"); \ + : "=r" (*(__u8 *)__u.__c) \ + : "Q" (*p) : "memory"); \ break; \ case 2: \ asm volatile ("ldarh %w0, %1" \ - : "=r" (___p1) : "Q" (*p) : "memory"); \ + : "=r" (*(__u16 *)__u.__c) \ + : "Q" (*p) : "memory"); \ break; \ case 4: \ asm volatile ("ldar %w0, %1" \ - : "=r" (___p1) : "Q" (*p) : "memory"); \ + : "=r" (*(__u32 *)__u.__c) \ + : "Q" (*p) : "memory"); \ break; \ case 8: \ asm volatile ("ldar %0, %1" \ - : "=r" (___p1) : "Q" (*p) : "memory"); \ + : "=r" (*(__u64 *)__u.__c) \ + : "Q" (*p) : "memory"); \ break; \ } \ - ___p1; \ + __u.__val; \ }) #define read_barrier_depends() do { } while(0) diff --git a/arch/arm64/include/asm/compat.h b/arch/arm64/include/asm/compat.h index 7fbed6919b54..eb8432bb82b8 100644 --- a/arch/arm64/include/asm/compat.h +++ b/arch/arm64/include/asm/compat.h @@ -23,7 +23,6 @@ */ #include <linux/types.h> #include <linux/sched.h> -#include <linux/ptrace.h> #define COMPAT_USER_HZ 100 #ifdef __AARCH64EB__ @@ -234,7 +233,7 @@ static inline compat_uptr_t ptr_to_compat(void __user *uptr) return (u32)(unsigned long)uptr; } -#define compat_user_stack_pointer() (user_stack_pointer(current_pt_regs())) +#define compat_user_stack_pointer() (user_stack_pointer(task_pt_regs(current))) static inline void __user *arch_compat_alloc_user_space(long len) { diff --git a/arch/arm64/include/asm/cpufeature.h b/arch/arm64/include/asm/cpufeature.h index 11d5bb0fdd54..8f271b83f910 100644 --- a/arch/arm64/include/asm/cpufeature.h +++ b/arch/arm64/include/asm/cpufeature.h @@ -29,8 +29,9 @@ #define ARM64_HAS_PAN 4 #define ARM64_HAS_LSE_ATOMICS 5 #define ARM64_WORKAROUND_CAVIUM_23154 6 +#define ARM64_WORKAROUND_834220 7 -#define ARM64_NCAPS 7 +#define ARM64_NCAPS 8 #ifndef __ASSEMBLY__ @@ -46,8 +47,12 @@ enum ftr_type { #define FTR_STRICT true /* SANITY check strict matching required */ #define FTR_NONSTRICT false /* SANITY check ignored */ +#define FTR_SIGNED true /* Value should be treated as signed */ +#define FTR_UNSIGNED false /* Value should be treated as unsigned */ + struct arm64_ftr_bits { - bool strict; /* CPU Sanity check: strict matching required ? */ + bool sign; /* Value is signed ? */ + bool strict; /* CPU Sanity check: strict matching required ? */ enum ftr_type type; u8 shift; u8 width; @@ -123,6 +128,18 @@ cpuid_feature_extract_field(u64 features, int field) return cpuid_feature_extract_field_width(features, field, 4); } +static inline unsigned int __attribute_const__ +cpuid_feature_extract_unsigned_field_width(u64 features, int field, int width) +{ + return (u64)(features << (64 - width - field)) >> (64 - width); +} + +static inline unsigned int __attribute_const__ +cpuid_feature_extract_unsigned_field(u64 features, int field) +{ + return cpuid_feature_extract_unsigned_field_width(features, field, 4); +} + static inline u64 arm64_ftr_mask(struct arm64_ftr_bits *ftrp) { return (u64)GENMASK(ftrp->shift + ftrp->width - 1, ftrp->shift); @@ -130,7 +147,9 @@ static inline u64 arm64_ftr_mask(struct arm64_ftr_bits *ftrp) static inline s64 arm64_ftr_value(struct arm64_ftr_bits *ftrp, u64 val) { - return cpuid_feature_extract_field_width(val, ftrp->shift, ftrp->width); + return ftrp->sign ? + cpuid_feature_extract_field_width(val, ftrp->shift, ftrp->width) : + cpuid_feature_extract_unsigned_field_width(val, ftrp->shift, ftrp->width); } static inline bool id_aa64mmfr0_mixed_endian_el0(u64 mmfr0) diff --git a/arch/arm64/include/asm/dma-mapping.h b/arch/arm64/include/asm/dma-mapping.h index 54d0ead41afc..61e08f360e31 100644 --- a/arch/arm64/include/asm/dma-mapping.h +++ b/arch/arm64/include/asm/dma-mapping.h @@ -18,7 +18,6 @@ #ifdef __KERNEL__ -#include <linux/acpi.h> #include <linux/types.h> #include <linux/vmalloc.h> @@ -26,22 +25,16 @@ #include <asm/xen/hypervisor.h> #define DMA_ERROR_CODE (~(dma_addr_t)0) -extern struct dma_map_ops *dma_ops; extern struct dma_map_ops dummy_dma_ops; static inline struct dma_map_ops *__generic_dma_ops(struct device *dev) { - if (unlikely(!dev)) - return dma_ops; - else if (dev->archdata.dma_ops) + if (dev && dev->archdata.dma_ops) return dev->archdata.dma_ops; - else if (acpi_disabled) - return dma_ops; /* - * When ACPI is enabled, if arch_set_dma_ops is not called, - * we will disable device DMA capability by setting it - * to dummy_dma_ops. + * We expect no ISA devices, and all other DMA masters are expected to + * have someone call arch_setup_dma_ops at device creation time. */ return &dummy_dma_ops; } diff --git a/arch/arm64/include/asm/hw_breakpoint.h b/arch/arm64/include/asm/hw_breakpoint.h index e54415ec6935..9732908bfc8a 100644 --- a/arch/arm64/include/asm/hw_breakpoint.h +++ b/arch/arm64/include/asm/hw_breakpoint.h @@ -138,16 +138,18 @@ extern struct pmu perf_ops_bp; /* Determine number of BRP registers available. */ static inline int get_num_brps(void) { + u64 dfr0 = read_system_reg(SYS_ID_AA64DFR0_EL1); return 1 + - cpuid_feature_extract_field(read_system_reg(SYS_ID_AA64DFR0_EL1), + cpuid_feature_extract_unsigned_field(dfr0, ID_AA64DFR0_BRPS_SHIFT); } /* Determine number of WRP registers available. */ static inline int get_num_wrps(void) { + u64 dfr0 = read_system_reg(SYS_ID_AA64DFR0_EL1); return 1 + - cpuid_feature_extract_field(read_system_reg(SYS_ID_AA64DFR0_EL1), + cpuid_feature_extract_unsigned_field(dfr0, ID_AA64DFR0_WRPS_SHIFT); } diff --git a/arch/arm64/include/asm/irq.h b/arch/arm64/include/asm/irq.h index 23eb450b820b..8e8d30684392 100644 --- a/arch/arm64/include/asm/irq.h +++ b/arch/arm64/include/asm/irq.h @@ -7,4 +7,9 @@ struct pt_regs; extern void set_handle_irq(void (*handle_irq)(struct pt_regs *)); +static inline int nr_legacy_irqs(void) +{ + return 0; +} + #endif diff --git a/arch/arm64/include/asm/kvm_emulate.h b/arch/arm64/include/asm/kvm_emulate.h index 17e92f05b1fe..25a40213bd9b 100644 --- a/arch/arm64/include/asm/kvm_emulate.h +++ b/arch/arm64/include/asm/kvm_emulate.h @@ -99,12 +99,22 @@ static inline void vcpu_set_thumb(struct kvm_vcpu *vcpu) *vcpu_cpsr(vcpu) |= COMPAT_PSR_T_BIT; } -static inline unsigned long *vcpu_reg(const struct kvm_vcpu *vcpu, u8 reg_num) +/* + * vcpu_get_reg and vcpu_set_reg should always be passed a register number + * coming from a read of ESR_EL2. Otherwise, it may give the wrong result on + * AArch32 with banked registers. + */ +static inline unsigned long vcpu_get_reg(const struct kvm_vcpu *vcpu, + u8 reg_num) { - if (vcpu_mode_is_32bit(vcpu)) - return vcpu_reg32(vcpu, reg_num); + return (reg_num == 31) ? 0 : vcpu_gp_regs(vcpu)->regs.regs[reg_num]; +} - return (unsigned long *)&vcpu_gp_regs(vcpu)->regs.regs[reg_num]; +static inline void vcpu_set_reg(struct kvm_vcpu *vcpu, u8 reg_num, + unsigned long val) +{ + if (reg_num != 31) + vcpu_gp_regs(vcpu)->regs.regs[reg_num] = val; } /* Get vcpu SPSR for current mode */ diff --git a/arch/arm64/include/asm/mmu_context.h b/arch/arm64/include/asm/mmu_context.h index c0e87898ba96..24165784b803 100644 --- a/arch/arm64/include/asm/mmu_context.h +++ b/arch/arm64/include/asm/mmu_context.h @@ -101,7 +101,7 @@ static inline void cpu_set_default_tcr_t0sz(void) #define destroy_context(mm) do { } while(0) void check_and_switch_context(struct mm_struct *mm, unsigned int cpu); -#define init_new_context(tsk,mm) ({ atomic64_set(&mm->context.id, 0); 0; }) +#define init_new_context(tsk,mm) ({ atomic64_set(&(mm)->context.id, 0); 0; }) /* * This is called when "tsk" is about to enter lazy TLB mode. diff --git a/arch/arm64/include/asm/pgtable.h b/arch/arm64/include/asm/pgtable.h index 9819a9426b69..63f52b55defe 100644 --- a/arch/arm64/include/asm/pgtable.h +++ b/arch/arm64/include/asm/pgtable.h @@ -81,6 +81,7 @@ extern void __pgd_error(const char *file, int line, unsigned long val); #define PAGE_KERNEL __pgprot(_PAGE_DEFAULT | PTE_PXN | PTE_UXN | PTE_DIRTY | PTE_WRITE) #define PAGE_KERNEL_RO __pgprot(_PAGE_DEFAULT | PTE_PXN | PTE_UXN | PTE_DIRTY | PTE_RDONLY) +#define PAGE_KERNEL_ROX __pgprot(_PAGE_DEFAULT | PTE_UXN | PTE_DIRTY | PTE_RDONLY) #define PAGE_KERNEL_EXEC __pgprot(_PAGE_DEFAULT | PTE_UXN | PTE_DIRTY | PTE_WRITE) #define PAGE_KERNEL_EXEC_CONT __pgprot(_PAGE_DEFAULT | PTE_UXN | PTE_DIRTY | PTE_WRITE | PTE_CONT) @@ -275,10 +276,14 @@ static inline void set_pte_at(struct mm_struct *mm, unsigned long addr, * hardware updates of the pte (ptep_set_access_flags safely changes * valid ptes without going through an invalid entry). */ - if (IS_ENABLED(CONFIG_DEBUG_VM) && IS_ENABLED(CONFIG_ARM64_HW_AFDBM) && - pte_valid(*ptep)) { - BUG_ON(!pte_young(pte)); - BUG_ON(pte_write(*ptep) && !pte_dirty(pte)); + if (IS_ENABLED(CONFIG_ARM64_HW_AFDBM) && + pte_valid(*ptep) && pte_valid(pte)) { + VM_WARN_ONCE(!pte_young(pte), + "%s: racy access flag clearing: 0x%016llx -> 0x%016llx", + __func__, pte_val(*ptep), pte_val(pte)); + VM_WARN_ONCE(pte_write(*ptep) && !pte_dirty(pte), + "%s: racy dirty state clearing: 0x%016llx -> 0x%016llx", + __func__, pte_val(*ptep), pte_val(pte)); } set_pte(ptep, pte); diff --git a/arch/arm64/kernel/cpu_errata.c b/arch/arm64/kernel/cpu_errata.c index 24926f2504f7..feb6b4efa641 100644 --- a/arch/arm64/kernel/cpu_errata.c +++ b/arch/arm64/kernel/cpu_errata.c @@ -75,6 +75,15 @@ const struct arm64_cpu_capabilities arm64_errata[] = { (1 << MIDR_VARIANT_SHIFT) | 2), }, #endif +#ifdef CONFIG_ARM64_ERRATUM_834220 + { + /* Cortex-A57 r0p0 - r1p2 */ + .desc = "ARM erratum 834220", + .capability = ARM64_WORKAROUND_834220, + MIDR_RANGE(MIDR_CORTEX_A57, 0x00, + (1 << MIDR_VARIANT_SHIFT) | 2), + }, +#endif #ifdef CONFIG_ARM64_ERRATUM_845719 { /* Cortex-A53 r0p[01234] */ diff --git a/arch/arm64/kernel/cpufeature.c b/arch/arm64/kernel/cpufeature.c index c8cf89223b5a..0669c63281ea 100644 --- a/arch/arm64/kernel/cpufeature.c +++ b/arch/arm64/kernel/cpufeature.c @@ -44,8 +44,9 @@ unsigned int compat_elf_hwcap2 __read_mostly; DECLARE_BITMAP(cpu_hwcaps, ARM64_NCAPS); -#define ARM64_FTR_BITS(STRICT, TYPE, SHIFT, WIDTH, SAFE_VAL) \ +#define __ARM64_FTR_BITS(SIGNED, STRICT, TYPE, SHIFT, WIDTH, SAFE_VAL) \ { \ + .sign = SIGNED, \ .strict = STRICT, \ .type = TYPE, \ .shift = SHIFT, \ @@ -53,6 +54,14 @@ DECLARE_BITMAP(cpu_hwcaps, ARM64_NCAPS); .safe_val = SAFE_VAL, \ } +/* Define a feature with signed values */ +#define ARM64_FTR_BITS(STRICT, TYPE, SHIFT, WIDTH, SAFE_VAL) \ + __ARM64_FTR_BITS(FTR_SIGNED, STRICT, TYPE, SHIFT, WIDTH, SAFE_VAL) + +/* Define a feature with unsigned value */ +#define U_ARM64_FTR_BITS(STRICT, TYPE, SHIFT, WIDTH, SAFE_VAL) \ + __ARM64_FTR_BITS(FTR_UNSIGNED, STRICT, TYPE, SHIFT, WIDTH, SAFE_VAL) + #define ARM64_FTR_END \ { \ .width = 0, \ @@ -99,7 +108,7 @@ static struct arm64_ftr_bits ftr_id_aa64mmfr0[] = { * Differing PARange is fine as long as all peripherals and memory are mapped * within the minimum PARange of all CPUs */ - ARM64_FTR_BITS(FTR_NONSTRICT, FTR_LOWER_SAFE, ID_AA64MMFR0_PARANGE_SHIFT, 4, 0), + U_ARM64_FTR_BITS(FTR_NONSTRICT, FTR_LOWER_SAFE, ID_AA64MMFR0_PARANGE_SHIFT, 4, 0), ARM64_FTR_END, }; @@ -115,18 +124,18 @@ static struct arm64_ftr_bits ftr_id_aa64mmfr1[] = { }; static struct arm64_ftr_bits ftr_ctr[] = { - ARM64_FTR_BITS(FTR_STRICT, FTR_EXACT, 31, 1, 1), /* RAO */ + U_ARM64_FTR_BITS(FTR_STRICT, FTR_EXACT, 31, 1, 1), /* RAO */ ARM64_FTR_BITS(FTR_STRICT, FTR_EXACT, 28, 3, 0), - ARM64_FTR_BITS(FTR_STRICT, FTR_HIGHER_SAFE, 24, 4, 0), /* CWG */ - ARM64_FTR_BITS(FTR_STRICT, FTR_LOWER_SAFE, 20, 4, 0), /* ERG */ - ARM64_FTR_BITS(FTR_STRICT, FTR_LOWER_SAFE, 16, 4, 1), /* DminLine */ + U_ARM64_FTR_BITS(FTR_STRICT, FTR_HIGHER_SAFE, 24, 4, 0), /* CWG */ + U_ARM64_FTR_BITS(FTR_STRICT, FTR_LOWER_SAFE, 20, 4, 0), /* ERG */ + U_ARM64_FTR_BITS(FTR_STRICT, FTR_LOWER_SAFE, 16, 4, 1), /* DminLine */ /* * Linux can handle differing I-cache policies. Userspace JITs will * make use of *minLine */ - ARM64_FTR_BITS(FTR_NONSTRICT, FTR_EXACT, 14, 2, 0), /* L1Ip */ + U_ARM64_FTR_BITS(FTR_NONSTRICT, FTR_EXACT, 14, 2, 0), /* L1Ip */ ARM64_FTR_BITS(FTR_STRICT, FTR_EXACT, 4, 10, 0), /* RAZ */ - ARM64_FTR_BITS(FTR_STRICT, FTR_LOWER_SAFE, 0, 4, 0), /* IminLine */ + U_ARM64_FTR_BITS(FTR_STRICT, FTR_LOWER_SAFE, 0, 4, 0), /* IminLine */ ARM64_FTR_END, }; @@ -144,12 +153,12 @@ static struct arm64_ftr_bits ftr_id_mmfr0[] = { static struct arm64_ftr_bits ftr_id_aa64dfr0[] = { ARM64_FTR_BITS(FTR_STRICT, FTR_EXACT, 32, 32, 0), - ARM64_FTR_BITS(FTR_STRICT, FTR_LOWER_SAFE, ID_AA64DFR0_CTX_CMPS_SHIFT, 4, 0), - ARM64_FTR_BITS(FTR_STRICT, FTR_LOWER_SAFE, ID_AA64DFR0_WRPS_SHIFT, 4, 0), - ARM64_FTR_BITS(FTR_STRICT, FTR_LOWER_SAFE, ID_AA64DFR0_BRPS_SHIFT, 4, 0), - ARM64_FTR_BITS(FTR_STRICT, FTR_EXACT, ID_AA64DFR0_PMUVER_SHIFT, 4, 0), - ARM64_FTR_BITS(FTR_STRICT, FTR_EXACT, ID_AA64DFR0_TRACEVER_SHIFT, 4, 0), - ARM64_FTR_BITS(FTR_STRICT, FTR_EXACT, ID_AA64DFR0_DEBUGVER_SHIFT, 4, 0x6), + U_ARM64_FTR_BITS(FTR_STRICT, FTR_LOWER_SAFE, ID_AA64DFR0_CTX_CMPS_SHIFT, 4, 0), + U_ARM64_FTR_BITS(FTR_STRICT, FTR_LOWER_SAFE, ID_AA64DFR0_WRPS_SHIFT, 4, 0), + U_ARM64_FTR_BITS(FTR_STRICT, FTR_LOWER_SAFE, ID_AA64DFR0_BRPS_SHIFT, 4, 0), + U_ARM64_FTR_BITS(FTR_STRICT, FTR_EXACT, ID_AA64DFR0_PMUVER_SHIFT, 4, 0), + U_ARM64_FTR_BITS(FTR_STRICT, FTR_EXACT, ID_AA64DFR0_TRACEVER_SHIFT, 4, 0), + U_ARM64_FTR_BITS(FTR_STRICT, FTR_EXACT, ID_AA64DFR0_DEBUGVER_SHIFT, 4, 0x6), ARM64_FTR_END, }; diff --git a/arch/arm64/kernel/cpuinfo.c b/arch/arm64/kernel/cpuinfo.c index 706679d0a0b4..212ae6361d8b 100644 --- a/arch/arm64/kernel/cpuinfo.c +++ b/arch/arm64/kernel/cpuinfo.c @@ -30,6 +30,7 @@ #include <linux/seq_file.h> #include <linux/sched.h> #include <linux/smp.h> +#include <linux/delay.h> /* * In case the boot CPU is hotpluggable, we record its initial state and @@ -112,6 +113,10 @@ static int c_show(struct seq_file *m, void *v) */ seq_printf(m, "processor\t: %d\n", i); + seq_printf(m, "BogoMIPS\t: %lu.%02lu\n", + loops_per_jiffy / (500000UL/HZ), + loops_per_jiffy / (5000UL/HZ) % 100); + /* * Dump out the common processor features in a single line. * Userspace should read the hwcaps with getauxval(AT_HWCAP) diff --git a/arch/arm64/kernel/efi.c b/arch/arm64/kernel/efi.c index de46b50f4cdf..4eeb17198cfa 100644 --- a/arch/arm64/kernel/efi.c +++ b/arch/arm64/kernel/efi.c @@ -127,7 +127,11 @@ static int __init uefi_init(void) table_size = sizeof(efi_config_table_64_t) * efi.systab->nr_tables; config_tables = early_memremap(efi_to_phys(efi.systab->tables), table_size); - + if (config_tables == NULL) { + pr_warn("Unable to map EFI config table array.\n"); + retval = -ENOMEM; + goto out; + } retval = efi_config_parse_tables(config_tables, efi.systab->nr_tables, sizeof(efi_config_table_64_t), NULL); @@ -209,6 +213,14 @@ void __init efi_init(void) PAGE_ALIGN(params.mmap_size + (params.mmap & ~PAGE_MASK))); memmap.phys_map = params.mmap; memmap.map = early_memremap(params.mmap, params.mmap_size); + if (memmap.map == NULL) { + /* + * If we are booting via UEFI, the UEFI memory map is the only + * description of memory we have, so there is little point in + * proceeding if we cannot access it. + */ + panic("Unable to map EFI memory map.\n"); + } memmap.map_end = memmap.map + params.mmap_size; memmap.desc_size = params.desc_size; memmap.desc_version = params.desc_ver; @@ -224,8 +236,9 @@ static bool __init efi_virtmap_init(void) { efi_memory_desc_t *md; + init_new_context(NULL, &efi_mm); + for_each_efi_memory_desc(&memmap, md) { - u64 paddr, npages, size; pgprot_t prot; if (!(md->attribute & EFI_MEMORY_RUNTIME)) @@ -233,11 +246,6 @@ static bool __init efi_virtmap_init(void) if (md->virt_addr == 0) return false; - paddr = md->phys_addr; - npages = md->num_pages; - memrange_efi_to_native(&paddr, &npages); - size = npages << PAGE_SHIFT; - pr_info(" EFI remap 0x%016llx => %p\n", md->phys_addr, (void *)md->virt_addr); @@ -254,7 +262,9 @@ static bool __init efi_virtmap_init(void) else prot = PAGE_KERNEL; - create_pgd_mapping(&efi_mm, paddr, md->virt_addr, size, prot); + create_pgd_mapping(&efi_mm, md->phys_addr, md->virt_addr, + md->num_pages << EFI_PAGE_SHIFT, + __pgprot(pgprot_val(prot) | PTE_NG)); } return true; } @@ -270,12 +280,12 @@ static int __init arm64_enable_runtime_services(void) if (!efi_enabled(EFI_BOOT)) { pr_info("EFI services will not be available.\n"); - return -1; + return 0; } if (efi_runtime_disabled()) { pr_info("EFI runtime services will be disabled.\n"); - return -1; + return 0; } pr_info("Remapping and enabling EFI services.\n"); @@ -285,7 +295,7 @@ static int __init arm64_enable_runtime_services(void) mapsize); if (!memmap.map) { pr_err("Failed to remap EFI memory map\n"); - return -1; + return -ENOMEM; } memmap.map_end = memmap.map + mapsize; efi.memmap = &memmap; @@ -294,13 +304,13 @@ static int __init arm64_enable_runtime_services(void) sizeof(efi_system_table_t)); if (!efi.systab) { pr_err("Failed to remap EFI System Table\n"); - return -1; + return -ENOMEM; } set_bit(EFI_SYSTEM_TABLES, &efi.flags); if (!efi_virtmap_init()) { pr_err("No UEFI virtual mapping was installed -- runtime services will not be available\n"); - return -1; + return -ENOMEM; } /* Set up runtime services function pointers */ @@ -329,14 +339,7 @@ core_initcall(arm64_dmi_init); static void efi_set_pgd(struct mm_struct *mm) { - if (mm == &init_mm) - cpu_set_reserved_ttbr0(); - else - cpu_switch_mm(mm->pgd, mm); - - local_flush_tlb_all(); - if (icache_is_aivivt()) - __local_flush_icache_all(); + switch_mm(NULL, mm, NULL); } void efi_virtmap_load(void) diff --git a/arch/arm64/kernel/suspend.c b/arch/arm64/kernel/suspend.c index fce95e17cf7f..1095aa483a1c 100644 --- a/arch/arm64/kernel/suspend.c +++ b/arch/arm64/kernel/suspend.c @@ -1,3 +1,4 @@ +#include <linux/ftrace.h> #include <linux/percpu.h> #include <linux/slab.h> #include <asm/cacheflush.h> @@ -71,6 +72,13 @@ int cpu_suspend(unsigned long arg, int (*fn)(unsigned long)) local_dbg_save(flags); /* + * Function graph tracer state gets incosistent when the kernel + * calls functions that never return (aka suspend finishers) hence + * disable graph tracing during their execution. + */ + pause_graph_tracing(); + + /* * mm context saved on the stack, it will be restored when * the cpu comes out of reset through the identity mapped * page tables, so that the thread address space is properly @@ -111,6 +119,8 @@ int cpu_suspend(unsigned long arg, int (*fn)(unsigned long)) hw_breakpoint_restore(NULL); } + unpause_graph_tracing(); + /* * Restore pstate flags. OS lock and mdscr have been already * restored, so from this point onwards, debugging is fully diff --git a/arch/arm64/kernel/vmlinux.lds.S b/arch/arm64/kernel/vmlinux.lds.S index 1ee2c3937d4e..71426a78db12 100644 --- a/arch/arm64/kernel/vmlinux.lds.S +++ b/arch/arm64/kernel/vmlinux.lds.S @@ -5,6 +5,7 @@ */ #include <asm-generic/vmlinux.lds.h> +#include <asm/cache.h> #include <asm/kernel-pgtable.h> #include <asm/thread_info.h> #include <asm/memory.h> @@ -140,7 +141,7 @@ SECTIONS ARM_EXIT_KEEP(EXIT_DATA) } - PERCPU_SECTION(64) + PERCPU_SECTION(L1_CACHE_BYTES) . = ALIGN(PAGE_SIZE); __init_end = .; @@ -158,7 +159,7 @@ SECTIONS . = ALIGN(PAGE_SIZE); _data = .; _sdata = .; - RW_DATA_SECTION(64, PAGE_SIZE, THREAD_SIZE) + RW_DATA_SECTION(L1_CACHE_BYTES, PAGE_SIZE, THREAD_SIZE) PECOFF_EDATA_PADDING _edata = .; diff --git a/arch/arm64/kvm/handle_exit.c b/arch/arm64/kvm/handle_exit.c index 68a0759b1375..15f0477b0d2a 100644 --- a/arch/arm64/kvm/handle_exit.c +++ b/arch/arm64/kvm/handle_exit.c @@ -37,7 +37,7 @@ static int handle_hvc(struct kvm_vcpu *vcpu, struct kvm_run *run) { int ret; - trace_kvm_hvc_arm64(*vcpu_pc(vcpu), *vcpu_reg(vcpu, 0), + trace_kvm_hvc_arm64(*vcpu_pc(vcpu), vcpu_get_reg(vcpu, 0), kvm_vcpu_hvc_get_imm(vcpu)); ret = kvm_psci_call(vcpu); diff --git a/arch/arm64/kvm/hyp.S b/arch/arm64/kvm/hyp.S index 1599701ef044..86c289832272 100644 --- a/arch/arm64/kvm/hyp.S +++ b/arch/arm64/kvm/hyp.S @@ -864,6 +864,10 @@ ENTRY(__kvm_flush_vm_context) ENDPROC(__kvm_flush_vm_context) __kvm_hyp_panic: + // Stash PAR_EL1 before corrupting it in __restore_sysregs + mrs x0, par_el1 + push x0, xzr + // Guess the context by looking at VTTBR: // If zero, then we're already a host. // Otherwise restore a minimal host context before panicing. @@ -898,7 +902,7 @@ __kvm_hyp_panic: mrs x3, esr_el2 mrs x4, far_el2 mrs x5, hpfar_el2 - mrs x6, par_el1 + pop x6, xzr // active context PAR_EL1 mrs x7, tpidr_el2 mov lr, #(PSR_F_BIT | PSR_I_BIT | PSR_A_BIT | PSR_D_BIT |\ @@ -914,7 +918,7 @@ __kvm_hyp_panic: ENDPROC(__kvm_hyp_panic) __hyp_panic_str: - .ascii "HYP panic:\nPS:%08x PC:%p ESR:%p\nFAR:%p HPFAR:%p PAR:%p\nVCPU:%p\n\0" + .ascii "HYP panic:\nPS:%08x PC:%016x ESR:%08x\nFAR:%016x HPFAR:%016x PAR:%016x\nVCPU:%p\n\0" .align 2 @@ -1015,9 +1019,15 @@ el1_trap: b.ne 1f // Not an abort we care about /* This is an abort. Check for permission fault */ +alternative_if_not ARM64_WORKAROUND_834220 and x2, x1, #ESR_ELx_FSC_TYPE cmp x2, #FSC_PERM b.ne 1f // Not a permission fault +alternative_else + nop // Use the permission fault path to + nop // check for a valid S1 translation, + nop // regardless of the ESR value. +alternative_endif /* * Check for Stage-1 page table walk, which is guaranteed diff --git a/arch/arm64/kvm/inject_fault.c b/arch/arm64/kvm/inject_fault.c index 85c57158dcd9..648112e90ed5 100644 --- a/arch/arm64/kvm/inject_fault.c +++ b/arch/arm64/kvm/inject_fault.c @@ -48,7 +48,7 @@ static void prepare_fault32(struct kvm_vcpu *vcpu, u32 mode, u32 vect_offset) /* Note: These now point to the banked copies */ *vcpu_spsr(vcpu) = new_spsr_value; - *vcpu_reg(vcpu, 14) = *vcpu_pc(vcpu) + return_offset; + *vcpu_reg32(vcpu, 14) = *vcpu_pc(vcpu) + return_offset; /* Branch to exception vector */ if (sctlr & (1 << 13)) diff --git a/arch/arm64/kvm/sys_regs.c b/arch/arm64/kvm/sys_regs.c index 87a64e8db04c..d2650e84faf2 100644 --- a/arch/arm64/kvm/sys_regs.c +++ b/arch/arm64/kvm/sys_regs.c @@ -78,7 +78,7 @@ static u32 get_ccsidr(u32 csselr) * See note at ARMv7 ARM B1.14.4 (TL;DR: S/W ops are not easily virtualized). */ static bool access_dcsw(struct kvm_vcpu *vcpu, - const struct sys_reg_params *p, + struct sys_reg_params *p, const struct sys_reg_desc *r) { if (!p->is_write) @@ -94,21 +94,19 @@ static bool access_dcsw(struct kvm_vcpu *vcpu, * sys_regs and leave it in complete control of the caches. */ static bool access_vm_reg(struct kvm_vcpu *vcpu, - const struct sys_reg_params *p, + struct sys_reg_params *p, const struct sys_reg_desc *r) { - unsigned long val; bool was_enabled = vcpu_has_cache_enabled(vcpu); BUG_ON(!p->is_write); - val = *vcpu_reg(vcpu, p->Rt); if (!p->is_aarch32) { - vcpu_sys_reg(vcpu, r->reg) = val; + vcpu_sys_reg(vcpu, r->reg) = p->regval; } else { if (!p->is_32bit) - vcpu_cp15_64_high(vcpu, r->reg) = val >> 32; - vcpu_cp15_64_low(vcpu, r->reg) = val & 0xffffffffUL; + vcpu_cp15_64_high(vcpu, r->reg) = upper_32_bits(p->regval); + vcpu_cp15_64_low(vcpu, r->reg) = lower_32_bits(p->regval); } kvm_toggle_cache(vcpu, was_enabled); @@ -122,22 +120,19 @@ static bool access_vm_reg(struct kvm_vcpu *vcpu, * for both AArch64 and AArch32 accesses. */ static bool access_gic_sgi(struct kvm_vcpu *vcpu, - const struct sys_reg_params *p, + struct sys_reg_params *p, const struct sys_reg_desc *r) { - u64 val; - if (!p->is_write) return read_from_write_only(vcpu, p); - val = *vcpu_reg(vcpu, p->Rt); - vgic_v3_dispatch_sgi(vcpu, val); + vgic_v3_dispatch_sgi(vcpu, p->regval); return true; } static bool trap_raz_wi(struct kvm_vcpu *vcpu, - const struct sys_reg_params *p, + struct sys_reg_params *p, const struct sys_reg_desc *r) { if (p->is_write) @@ -147,19 +142,19 @@ static bool trap_raz_wi(struct kvm_vcpu *vcpu, } static bool trap_oslsr_el1(struct kvm_vcpu *vcpu, - const struct sys_reg_params *p, + struct sys_reg_params *p, const struct sys_reg_desc *r) { if (p->is_write) { return ignore_write(vcpu, p); } else { - *vcpu_reg(vcpu, p->Rt) = (1 << 3); + p->regval = (1 << 3); return true; } } static bool trap_dbgauthstatus_el1(struct kvm_vcpu *vcpu, - const struct sys_reg_params *p, + struct sys_reg_params *p, const struct sys_reg_desc *r) { if (p->is_write) { @@ -167,7 +162,7 @@ static bool trap_dbgauthstatus_el1(struct kvm_vcpu *vcpu, } else { u32 val; asm volatile("mrs %0, dbgauthstatus_el1" : "=r" (val)); - *vcpu_reg(vcpu, p->Rt) = val; + p->regval = val; return true; } } @@ -200,17 +195,17 @@ static bool trap_dbgauthstatus_el1(struct kvm_vcpu *vcpu, * now use the debug registers. */ static bool trap_debug_regs(struct kvm_vcpu *vcpu, - const struct sys_reg_params *p, + struct sys_reg_params *p, const struct sys_reg_desc *r) { if (p->is_write) { - vcpu_sys_reg(vcpu, r->reg) = *vcpu_reg(vcpu, p->Rt); + vcpu_sys_reg(vcpu, r->reg) = p->regval; vcpu->arch.debug_flags |= KVM_ARM64_DEBUG_DIRTY; } else { - *vcpu_reg(vcpu, p->Rt) = vcpu_sys_reg(vcpu, r->reg); + p->regval = vcpu_sys_reg(vcpu, r->reg); } - trace_trap_reg(__func__, r->reg, p->is_write, *vcpu_reg(vcpu, p->Rt)); + trace_trap_reg(__func__, r->reg, p->is_write, p->regval); return true; } @@ -225,10 +220,10 @@ static bool trap_debug_regs(struct kvm_vcpu *vcpu, * hyp.S code switches between host and guest values in future. */ static inline void reg_to_dbg(struct kvm_vcpu *vcpu, - const struct sys_reg_params *p, + struct sys_reg_params *p, u64 *dbg_reg) { - u64 val = *vcpu_reg(vcpu, p->Rt); + u64 val = p->regval; if (p->is_32bit) { val &= 0xffffffffUL; @@ -240,19 +235,16 @@ static inline void reg_to_dbg(struct kvm_vcpu *vcpu, } static inline void dbg_to_reg(struct kvm_vcpu *vcpu, - const struct sys_reg_params *p, + struct sys_reg_params *p, u64 *dbg_reg) { - u64 val = *dbg_reg; - + p->regval = *dbg_reg; if (p->is_32bit) - val &= 0xffffffffUL; - - *vcpu_reg(vcpu, p->Rt) = val; + p->regval &= 0xffffffffUL; } static inline bool trap_bvr(struct kvm_vcpu *vcpu, - const struct sys_reg_params *p, + struct sys_reg_params *p, const struct sys_reg_desc *rd) { u64 *dbg_reg = &vcpu->arch.vcpu_debug_state.dbg_bvr[rd->reg]; @@ -294,7 +286,7 @@ static inline void reset_bvr(struct kvm_vcpu *vcpu, } static inline bool trap_bcr(struct kvm_vcpu *vcpu, - const struct sys_reg_params *p, + struct sys_reg_params *p, const struct sys_reg_desc *rd) { u64 *dbg_reg = &vcpu->arch.vcpu_debug_state.dbg_bcr[rd->reg]; @@ -337,7 +329,7 @@ static inline void reset_bcr(struct kvm_vcpu *vcpu, } static inline bool trap_wvr(struct kvm_vcpu *vcpu, - const struct sys_reg_params *p, + struct sys_reg_params *p, const struct sys_reg_desc *rd) { u64 *dbg_reg = &vcpu->arch.vcpu_debug_state.dbg_wvr[rd->reg]; @@ -380,7 +372,7 @@ static inline void reset_wvr(struct kvm_vcpu *vcpu, } static inline bool trap_wcr(struct kvm_vcpu *vcpu, - const struct sys_reg_params *p, + struct sys_reg_params *p, const struct sys_reg_desc *rd) { u64 *dbg_reg = &vcpu->arch.vcpu_debug_state.dbg_wcr[rd->reg]; @@ -687,7 +679,7 @@ static const struct sys_reg_desc sys_reg_descs[] = { }; static bool trap_dbgidr(struct kvm_vcpu *vcpu, - const struct sys_reg_params *p, + struct sys_reg_params *p, const struct sys_reg_desc *r) { if (p->is_write) { @@ -697,23 +689,23 @@ static bool trap_dbgidr(struct kvm_vcpu *vcpu, u64 pfr = read_system_reg(SYS_ID_AA64PFR0_EL1); u32 el3 = !!cpuid_feature_extract_field(pfr, ID_AA64PFR0_EL3_SHIFT); - *vcpu_reg(vcpu, p->Rt) = ((((dfr >> ID_AA64DFR0_WRPS_SHIFT) & 0xf) << 28) | - (((dfr >> ID_AA64DFR0_BRPS_SHIFT) & 0xf) << 24) | - (((dfr >> ID_AA64DFR0_CTX_CMPS_SHIFT) & 0xf) << 20) | - (6 << 16) | (el3 << 14) | (el3 << 12)); + p->regval = ((((dfr >> ID_AA64DFR0_WRPS_SHIFT) & 0xf) << 28) | + (((dfr >> ID_AA64DFR0_BRPS_SHIFT) & 0xf) << 24) | + (((dfr >> ID_AA64DFR0_CTX_CMPS_SHIFT) & 0xf) << 20) + | (6 << 16) | (el3 << 14) | (el3 << 12)); return true; } } static bool trap_debug32(struct kvm_vcpu *vcpu, - const struct sys_reg_params *p, + struct sys_reg_params *p, const struct sys_reg_desc *r) { if (p->is_write) { - vcpu_cp14(vcpu, r->reg) = *vcpu_reg(vcpu, p->Rt); + vcpu_cp14(vcpu, r->reg) = p->regval; vcpu->arch.debug_flags |= KVM_ARM64_DEBUG_DIRTY; } else { - *vcpu_reg(vcpu, p->Rt) = vcpu_cp14(vcpu, r->reg); + p->regval = vcpu_cp14(vcpu, r->reg); } return true; @@ -731,7 +723,7 @@ static bool trap_debug32(struct kvm_vcpu *vcpu, */ static inline bool trap_xvr(struct kvm_vcpu *vcpu, - const struct sys_reg_params *p, + struct sys_reg_params *p, const struct sys_reg_desc *rd) { u64 *dbg_reg = &vcpu->arch.vcpu_debug_state.dbg_bvr[rd->reg]; @@ -740,12 +732,12 @@ static inline bool trap_xvr(struct kvm_vcpu *vcpu, u64 val = *dbg_reg; val &= 0xffffffffUL; - val |= *vcpu_reg(vcpu, p->Rt) << 32; + val |= p->regval << 32; *dbg_reg = val; vcpu->arch.debug_flags |= KVM_ARM64_DEBUG_DIRTY; } else { - *vcpu_reg(vcpu, p->Rt) = *dbg_reg >> 32; + p->regval = *dbg_reg >> 32; } trace_trap_reg(__func__, rd->reg, p->is_write, *dbg_reg); @@ -991,7 +983,7 @@ int kvm_handle_cp14_load_store(struct kvm_vcpu *vcpu, struct kvm_run *run) * Return 0 if the access has been handled, and -1 if not. */ static int emulate_cp(struct kvm_vcpu *vcpu, - const struct sys_reg_params *params, + struct sys_reg_params *params, const struct sys_reg_desc *table, size_t num) { @@ -1062,12 +1054,12 @@ static int kvm_handle_cp_64(struct kvm_vcpu *vcpu, { struct sys_reg_params params; u32 hsr = kvm_vcpu_get_hsr(vcpu); + int Rt = (hsr >> 5) & 0xf; int Rt2 = (hsr >> 10) & 0xf; params.is_aarch32 = true; params.is_32bit = false; params.CRm = (hsr >> 1) & 0xf; - params.Rt = (hsr >> 5) & 0xf; params.is_write = ((hsr & 1) == 0); params.Op0 = 0; @@ -1076,15 +1068,12 @@ static int kvm_handle_cp_64(struct kvm_vcpu *vcpu, params.CRn = 0; /* - * Massive hack here. Store Rt2 in the top 32bits so we only - * have one register to deal with. As we use the same trap + * Make a 64-bit value out of Rt and Rt2. As we use the same trap * backends between AArch32 and AArch64, we get away with it. */ if (params.is_write) { - u64 val = *vcpu_reg(vcpu, params.Rt); - val &= 0xffffffff; - val |= *vcpu_reg(vcpu, Rt2) << 32; - *vcpu_reg(vcpu, params.Rt) = val; + params.regval = vcpu_get_reg(vcpu, Rt) & 0xffffffff; + params.regval |= vcpu_get_reg(vcpu, Rt2) << 32; } if (!emulate_cp(vcpu, ¶ms, target_specific, nr_specific)) @@ -1095,11 +1084,10 @@ static int kvm_handle_cp_64(struct kvm_vcpu *vcpu, unhandled_cp_access(vcpu, ¶ms); out: - /* Do the opposite hack for the read side */ + /* Split up the value between registers for the read side */ if (!params.is_write) { - u64 val = *vcpu_reg(vcpu, params.Rt); - val >>= 32; - *vcpu_reg(vcpu, Rt2) = val; + vcpu_set_reg(vcpu, Rt, lower_32_bits(params.regval)); + vcpu_set_reg(vcpu, Rt2, upper_32_bits(params.regval)); } return 1; @@ -1118,21 +1106,24 @@ static int kvm_handle_cp_32(struct kvm_vcpu *vcpu, { struct sys_reg_params params; u32 hsr = kvm_vcpu_get_hsr(vcpu); + int Rt = (hsr >> 5) & 0xf; params.is_aarch32 = true; params.is_32bit = true; params.CRm = (hsr >> 1) & 0xf; - params.Rt = (hsr >> 5) & 0xf; + params.regval = vcpu_get_reg(vcpu, Rt); params.is_write = ((hsr & 1) == 0); params.CRn = (hsr >> 10) & 0xf; params.Op0 = 0; params.Op1 = (hsr >> 14) & 0x7; params.Op2 = (hsr >> 17) & 0x7; - if (!emulate_cp(vcpu, ¶ms, target_specific, nr_specific)) - return 1; - if (!emulate_cp(vcpu, ¶ms, global, nr_global)) + if (!emulate_cp(vcpu, ¶ms, target_specific, nr_specific) || + !emulate_cp(vcpu, ¶ms, global, nr_global)) { + if (!params.is_write) + vcpu_set_reg(vcpu, Rt, params.regval); return 1; + } unhandled_cp_access(vcpu, ¶ms); return 1; @@ -1175,7 +1166,7 @@ int kvm_handle_cp14_32(struct kvm_vcpu *vcpu, struct kvm_run *run) } static int emulate_sys_reg(struct kvm_vcpu *vcpu, - const struct sys_reg_params *params) + struct sys_reg_params *params) { size_t num; const struct sys_reg_desc *table, *r; @@ -1230,6 +1221,8 @@ int kvm_handle_sys_reg(struct kvm_vcpu *vcpu, struct kvm_run *run) { struct sys_reg_params params; unsigned long esr = kvm_vcpu_get_hsr(vcpu); + int Rt = (esr >> 5) & 0x1f; + int ret; trace_kvm_handle_sys_reg(esr); @@ -1240,10 +1233,14 @@ int kvm_handle_sys_reg(struct kvm_vcpu *vcpu, struct kvm_run *run) params.CRn = (esr >> 10) & 0xf; params.CRm = (esr >> 1) & 0xf; params.Op2 = (esr >> 17) & 0x7; - params.Rt = (esr >> 5) & 0x1f; + params.regval = vcpu_get_reg(vcpu, Rt); params.is_write = !(esr & 1); - return emulate_sys_reg(vcpu, ¶ms); + ret = emulate_sys_reg(vcpu, ¶ms); + + if (!params.is_write) + vcpu_set_reg(vcpu, Rt, params.regval); + return ret; } /****************************************************************************** diff --git a/arch/arm64/kvm/sys_regs.h b/arch/arm64/kvm/sys_regs.h index eaa324e4db4d..dbbb01cfbee9 100644 --- a/arch/arm64/kvm/sys_regs.h +++ b/arch/arm64/kvm/sys_regs.h @@ -28,7 +28,7 @@ struct sys_reg_params { u8 CRn; u8 CRm; u8 Op2; - u8 Rt; + u64 regval; bool is_write; bool is_aarch32; bool is_32bit; /* Only valid if is_aarch32 is true */ @@ -44,7 +44,7 @@ struct sys_reg_desc { /* Trapped access from guest, if non-NULL. */ bool (*access)(struct kvm_vcpu *, - const struct sys_reg_params *, + struct sys_reg_params *, const struct sys_reg_desc *); /* Initialization for vcpu. */ @@ -77,9 +77,9 @@ static inline bool ignore_write(struct kvm_vcpu *vcpu, } static inline bool read_zero(struct kvm_vcpu *vcpu, - const struct sys_reg_params *p) + struct sys_reg_params *p) { - *vcpu_reg(vcpu, p->Rt) = 0; + p->regval = 0; return true; } diff --git a/arch/arm64/kvm/sys_regs_generic_v8.c b/arch/arm64/kvm/sys_regs_generic_v8.c index 1e4576824165..ed90578fa120 100644 --- a/arch/arm64/kvm/sys_regs_generic_v8.c +++ b/arch/arm64/kvm/sys_regs_generic_v8.c @@ -31,13 +31,13 @@ #include "sys_regs.h" static bool access_actlr(struct kvm_vcpu *vcpu, - const struct sys_reg_params *p, + struct sys_reg_params *p, const struct sys_reg_desc *r) { if (p->is_write) return ignore_write(vcpu, p); - *vcpu_reg(vcpu, p->Rt) = vcpu_sys_reg(vcpu, ACTLR_EL1); + p->regval = vcpu_sys_reg(vcpu, ACTLR_EL1); return true; } diff --git a/arch/arm64/mm/context.c b/arch/arm64/mm/context.c index f636a2639f03..e87f53ff5f58 100644 --- a/arch/arm64/mm/context.c +++ b/arch/arm64/mm/context.c @@ -76,13 +76,28 @@ static void flush_context(unsigned int cpu) __flush_icache_all(); } -static int is_reserved_asid(u64 asid) +static bool check_update_reserved_asid(u64 asid, u64 newasid) { int cpu; - for_each_possible_cpu(cpu) - if (per_cpu(reserved_asids, cpu) == asid) - return 1; - return 0; + bool hit = false; + + /* + * Iterate over the set of reserved ASIDs looking for a match. + * If we find one, then we can update our mm to use newasid + * (i.e. the same ASID in the current generation) but we can't + * exit the loop early, since we need to ensure that all copies + * of the old ASID are updated to reflect the mm. Failure to do + * so could result in us missing the reserved ASID in a future + * generation. + */ + for_each_possible_cpu(cpu) { + if (per_cpu(reserved_asids, cpu) == asid) { + hit = true; + per_cpu(reserved_asids, cpu) = newasid; + } + } + + return hit; } static u64 new_context(struct mm_struct *mm, unsigned int cpu) @@ -92,12 +107,14 @@ static u64 new_context(struct mm_struct *mm, unsigned int cpu) u64 generation = atomic64_read(&asid_generation); if (asid != 0) { + u64 newasid = generation | (asid & ~ASID_MASK); + /* * If our current ASID was active during a rollover, we * can continue to use it and this was just a false alarm. */ - if (is_reserved_asid(asid)) - return generation | (asid & ~ASID_MASK); + if (check_update_reserved_asid(asid, newasid)) + return newasid; /* * We had a valid ASID in a previous life, so try to re-use @@ -105,7 +122,7 @@ static u64 new_context(struct mm_struct *mm, unsigned int cpu) */ asid &= ~ASID_MASK; if (!__test_and_set_bit(asid, asid_map)) - goto bump_gen; + return newasid; } /* @@ -129,10 +146,7 @@ static u64 new_context(struct mm_struct *mm, unsigned int cpu) set_asid: __set_bit(asid, asid_map); cur_idx = asid; - -bump_gen: - asid |= generation; - return asid; + return asid | generation; } void check_and_switch_context(struct mm_struct *mm, unsigned int cpu) diff --git a/arch/arm64/mm/dma-mapping.c b/arch/arm64/mm/dma-mapping.c index 131a199114b4..7963aa4b5d28 100644 --- a/arch/arm64/mm/dma-mapping.c +++ b/arch/arm64/mm/dma-mapping.c @@ -18,6 +18,7 @@ */ #include <linux/gfp.h> +#include <linux/acpi.h> #include <linux/export.h> #include <linux/slab.h> #include <linux/genalloc.h> @@ -28,9 +29,6 @@ #include <asm/cacheflush.h> -struct dma_map_ops *dma_ops; -EXPORT_SYMBOL(dma_ops); - static pgprot_t __get_dma_pgprot(struct dma_attrs *attrs, pgprot_t prot, bool coherent) { @@ -515,13 +513,7 @@ EXPORT_SYMBOL(dummy_dma_ops); static int __init arm64_dma_init(void) { - int ret; - - dma_ops = &swiotlb_dma_ops; - - ret = atomic_pool_init(); - - return ret; + return atomic_pool_init(); } arch_initcall(arm64_dma_init); @@ -552,10 +544,14 @@ static void *__iommu_alloc_attrs(struct device *dev, size_t size, { bool coherent = is_device_dma_coherent(dev); int ioprot = dma_direction_to_prot(DMA_BIDIRECTIONAL, coherent); + size_t iosize = size; void *addr; if (WARN(!dev, "cannot create IOMMU mapping for unknown device\n")) return NULL; + + size = PAGE_ALIGN(size); + /* * Some drivers rely on this, and we probably don't want the * possibility of stale kernel data being read by devices anyway. @@ -566,7 +562,7 @@ static void *__iommu_alloc_attrs(struct device *dev, size_t size, struct page **pages; pgprot_t prot = __get_dma_pgprot(attrs, PAGE_KERNEL, coherent); - pages = iommu_dma_alloc(dev, size, gfp, ioprot, handle, + pages = iommu_dma_alloc(dev, iosize, gfp, ioprot, handle, flush_page); if (!pages) return NULL; @@ -574,7 +570,7 @@ static void *__iommu_alloc_attrs(struct device *dev, size_t size, addr = dma_common_pages_remap(pages, size, VM_USERMAP, prot, __builtin_return_address(0)); if (!addr) - iommu_dma_free(dev, pages, size, handle); + iommu_dma_free(dev, pages, iosize, handle); } else { struct page *page; /* @@ -591,7 +587,7 @@ static void *__iommu_alloc_attrs(struct device *dev, size_t size, if (!addr) return NULL; - *handle = iommu_dma_map_page(dev, page, 0, size, ioprot); + *handle = iommu_dma_map_page(dev, page, 0, iosize, ioprot); if (iommu_dma_mapping_error(dev, *handle)) { if (coherent) __free_pages(page, get_order(size)); @@ -606,6 +602,9 @@ static void *__iommu_alloc_attrs(struct device *dev, size_t size, static void __iommu_free_attrs(struct device *dev, size_t size, void *cpu_addr, dma_addr_t handle, struct dma_attrs *attrs) { + size_t iosize = size; + + size = PAGE_ALIGN(size); /* * @cpu_addr will be one of 3 things depending on how it was allocated: * - A remapped array of pages from iommu_dma_alloc(), for all @@ -617,17 +616,17 @@ static void __iommu_free_attrs(struct device *dev, size_t size, void *cpu_addr, * Hence how dodgy the below logic looks... */ if (__in_atomic_pool(cpu_addr, size)) { - iommu_dma_unmap_page(dev, handle, size, 0, NULL); + iommu_dma_unmap_page(dev, handle, iosize, 0, NULL); __free_from_pool(cpu_addr, size); } else if (is_vmalloc_addr(cpu_addr)){ struct vm_struct *area = find_vm_area(cpu_addr); if (WARN_ON(!area || !area->pages)) return; - iommu_dma_free(dev, area->pages, size, &handle); + iommu_dma_free(dev, area->pages, iosize, &handle); dma_common_free_remap(cpu_addr, size, VM_USERMAP); } else { - iommu_dma_unmap_page(dev, handle, size, 0, NULL); + iommu_dma_unmap_page(dev, handle, iosize, 0, NULL); __free_pages(virt_to_page(cpu_addr), get_order(size)); } } @@ -984,8 +983,8 @@ static void __iommu_setup_dma_ops(struct device *dev, u64 dma_base, u64 size, void arch_setup_dma_ops(struct device *dev, u64 dma_base, u64 size, struct iommu_ops *iommu, bool coherent) { - if (!acpi_disabled && !dev->archdata.dma_ops) - dev->archdata.dma_ops = dma_ops; + if (!dev->archdata.dma_ops) + dev->archdata.dma_ops = &swiotlb_dma_ops; dev->archdata.dma_coherent = coherent; __iommu_setup_dma_ops(dev, dma_base, size, iommu); diff --git a/arch/arm64/mm/fault.c b/arch/arm64/mm/fault.c index 19211c4a8911..92ddac1e8ca2 100644 --- a/arch/arm64/mm/fault.c +++ b/arch/arm64/mm/fault.c @@ -393,16 +393,16 @@ static struct fault_info { { do_translation_fault, SIGSEGV, SEGV_MAPERR, "level 1 translation fault" }, { do_translation_fault, SIGSEGV, SEGV_MAPERR, "level 2 translation fault" }, { do_page_fault, SIGSEGV, SEGV_MAPERR, "level 3 translation fault" }, - { do_bad, SIGBUS, 0, "reserved access flag fault" }, + { do_bad, SIGBUS, 0, "unknown 8" }, { do_page_fault, SIGSEGV, SEGV_ACCERR, "level 1 access flag fault" }, { do_page_fault, SIGSEGV, SEGV_ACCERR, "level 2 access flag fault" }, { do_page_fault, SIGSEGV, SEGV_ACCERR, "level 3 access flag fault" }, - { do_bad, SIGBUS, 0, "reserved permission fault" }, + { do_bad, SIGBUS, 0, "unknown 12" }, { do_page_fault, SIGSEGV, SEGV_ACCERR, "level 1 permission fault" }, { do_page_fault, SIGSEGV, SEGV_ACCERR, "level 2 permission fault" }, { do_page_fault, SIGSEGV, SEGV_ACCERR, "level 3 permission fault" }, { do_bad, SIGBUS, 0, "synchronous external abort" }, - { do_bad, SIGBUS, 0, "asynchronous external abort" }, + { do_bad, SIGBUS, 0, "unknown 17" }, { do_bad, SIGBUS, 0, "unknown 18" }, { do_bad, SIGBUS, 0, "unknown 19" }, { do_bad, SIGBUS, 0, "synchronous abort (translation table walk)" }, @@ -410,16 +410,16 @@ static struct fault_info { { do_bad, SIGBUS, 0, "synchronous abort (translation table walk)" }, { do_bad, SIGBUS, 0, "synchronous abort (translation table walk)" }, { do_bad, SIGBUS, 0, "synchronous parity error" }, - { do_bad, SIGBUS, 0, "asynchronous parity error" }, + { do_bad, SIGBUS, 0, "unknown 25" }, { do_bad, SIGBUS, 0, "unknown 26" }, { do_bad, SIGBUS, 0, "unknown 27" }, - { do_bad, SIGBUS, 0, "synchronous parity error (translation table walk" }, - { do_bad, SIGBUS, 0, "synchronous parity error (translation table walk" }, - { do_bad, SIGBUS, 0, "synchronous parity error (translation table walk" }, - { do_bad, SIGBUS, 0, "synchronous parity error (translation table walk" }, + { do_bad, SIGBUS, 0, "synchronous parity error (translation table walk)" }, + { do_bad, SIGBUS, 0, "synchronous parity error (translation table walk)" }, + { do_bad, SIGBUS, 0, "synchronous parity error (translation table walk)" }, + { do_bad, SIGBUS, 0, "synchronous parity error (translation table walk)" }, { do_bad, SIGBUS, 0, "unknown 32" }, { do_bad, SIGBUS, BUS_ADRALN, "alignment fault" }, - { do_bad, SIGBUS, 0, "debug event" }, + { do_bad, SIGBUS, 0, "unknown 34" }, { do_bad, SIGBUS, 0, "unknown 35" }, { do_bad, SIGBUS, 0, "unknown 36" }, { do_bad, SIGBUS, 0, "unknown 37" }, @@ -433,21 +433,21 @@ static struct fault_info { { do_bad, SIGBUS, 0, "unknown 45" }, { do_bad, SIGBUS, 0, "unknown 46" }, { do_bad, SIGBUS, 0, "unknown 47" }, - { do_bad, SIGBUS, 0, "unknown 48" }, + { do_bad, SIGBUS, 0, "TLB conflict abort" }, { do_bad, SIGBUS, 0, "unknown 49" }, { do_bad, SIGBUS, 0, "unknown 50" }, { do_bad, SIGBUS, 0, "unknown 51" }, { do_bad, SIGBUS, 0, "implementation fault (lockdown abort)" }, - { do_bad, SIGBUS, 0, "unknown 53" }, + { do_bad, SIGBUS, 0, "implementation fault (unsupported exclusive)" }, { do_bad, SIGBUS, 0, "unknown 54" }, { do_bad, SIGBUS, 0, "unknown 55" }, { do_bad, SIGBUS, 0, "unknown 56" }, { do_bad, SIGBUS, 0, "unknown 57" }, - { do_bad, SIGBUS, 0, "implementation fault (coprocessor abort)" }, + { do_bad, SIGBUS, 0, "unknown 58" }, { do_bad, SIGBUS, 0, "unknown 59" }, { do_bad, SIGBUS, 0, "unknown 60" }, - { do_bad, SIGBUS, 0, "unknown 61" }, - { do_bad, SIGBUS, 0, "unknown 62" }, + { do_bad, SIGBUS, 0, "section domain fault" }, + { do_bad, SIGBUS, 0, "page domain fault" }, { do_bad, SIGBUS, 0, "unknown 63" }, }; diff --git a/arch/arm64/mm/mmu.c b/arch/arm64/mm/mmu.c index e3f563c81c48..873e363048c6 100644 --- a/arch/arm64/mm/mmu.c +++ b/arch/arm64/mm/mmu.c @@ -64,8 +64,12 @@ EXPORT_SYMBOL(phys_mem_access_prot); static void __init *early_alloc(unsigned long sz) { - void *ptr = __va(memblock_alloc(sz, sz)); - BUG_ON(!ptr); + phys_addr_t phys; + void *ptr; + + phys = memblock_alloc(sz, sz); + BUG_ON(!phys); + ptr = __va(phys); memset(ptr, 0, sz); return ptr; } @@ -81,55 +85,19 @@ static void split_pmd(pmd_t *pmd, pte_t *pte) do { /* * Need to have the least restrictive permissions available - * permissions will be fixed up later. Default the new page - * range as contiguous ptes. + * permissions will be fixed up later */ - set_pte(pte, pfn_pte(pfn, PAGE_KERNEL_EXEC_CONT)); + set_pte(pte, pfn_pte(pfn, PAGE_KERNEL_EXEC)); pfn++; } while (pte++, i++, i < PTRS_PER_PTE); } -/* - * Given a PTE with the CONT bit set, determine where the CONT range - * starts, and clear the entire range of PTE CONT bits. - */ -static void clear_cont_pte_range(pte_t *pte, unsigned long addr) -{ - int i; - - pte -= CONT_RANGE_OFFSET(addr); - for (i = 0; i < CONT_PTES; i++) { - set_pte(pte, pte_mknoncont(*pte)); - pte++; - } - flush_tlb_all(); -} - -/* - * Given a range of PTEs set the pfn and provided page protection flags - */ -static void __populate_init_pte(pte_t *pte, unsigned long addr, - unsigned long end, phys_addr_t phys, - pgprot_t prot) -{ - unsigned long pfn = __phys_to_pfn(phys); - - do { - /* clear all the bits except the pfn, then apply the prot */ - set_pte(pte, pfn_pte(pfn, prot)); - pte++; - pfn++; - addr += PAGE_SIZE; - } while (addr != end); -} - static void alloc_init_pte(pmd_t *pmd, unsigned long addr, - unsigned long end, phys_addr_t phys, + unsigned long end, unsigned long pfn, pgprot_t prot, void *(*alloc)(unsigned long size)) { pte_t *pte; - unsigned long next; if (pmd_none(*pmd) || pmd_sect(*pmd)) { pte = alloc(PTRS_PER_PTE * sizeof(pte_t)); @@ -142,27 +110,9 @@ static void alloc_init_pte(pmd_t *pmd, unsigned long addr, pte = pte_offset_kernel(pmd, addr); do { - next = min(end, (addr + CONT_SIZE) & CONT_MASK); - if (((addr | next | phys) & ~CONT_MASK) == 0) { - /* a block of CONT_PTES */ - __populate_init_pte(pte, addr, next, phys, - __pgprot(pgprot_val(prot) | PTE_CONT)); - } else { - /* - * If the range being split is already inside of a - * contiguous range but this PTE isn't going to be - * contiguous, then we want to unmark the adjacent - * ranges, then update the portion of the range we - * are interrested in. - */ - clear_cont_pte_range(pte, addr); - __populate_init_pte(pte, addr, next, phys, prot); - } - - pte += (next - addr) >> PAGE_SHIFT; - phys += next - addr; - addr = next; - } while (addr != end); + set_pte(pte, pfn_pte(pfn, prot)); + pfn++; + } while (pte++, addr += PAGE_SIZE, addr != end); } static void split_pud(pud_t *old_pud, pmd_t *pmd) @@ -223,7 +173,8 @@ static void alloc_init_pmd(struct mm_struct *mm, pud_t *pud, } } } else { - alloc_init_pte(pmd, addr, next, phys, prot, alloc); + alloc_init_pte(pmd, addr, next, __phys_to_pfn(phys), + prot, alloc); } phys += next - addr; } while (pmd++, addr = next, addr != end); @@ -362,8 +313,8 @@ static void __init __map_memblock(phys_addr_t start, phys_addr_t end) * for now. This will get more fine grained later once all memory * is mapped */ - unsigned long kernel_x_start = round_down(__pa(_stext), SECTION_SIZE); - unsigned long kernel_x_end = round_up(__pa(__init_end), SECTION_SIZE); + unsigned long kernel_x_start = round_down(__pa(_stext), SWAPPER_BLOCK_SIZE); + unsigned long kernel_x_end = round_up(__pa(__init_end), SWAPPER_BLOCK_SIZE); if (end < kernel_x_start) { create_mapping(start, __phys_to_virt(start), @@ -451,18 +402,18 @@ static void __init fixup_executable(void) { #ifdef CONFIG_DEBUG_RODATA /* now that we are actually fully mapped, make the start/end more fine grained */ - if (!IS_ALIGNED((unsigned long)_stext, SECTION_SIZE)) { + if (!IS_ALIGNED((unsigned long)_stext, SWAPPER_BLOCK_SIZE)) { unsigned long aligned_start = round_down(__pa(_stext), - SECTION_SIZE); + SWAPPER_BLOCK_SIZE); create_mapping(aligned_start, __phys_to_virt(aligned_start), __pa(_stext) - aligned_start, PAGE_KERNEL); } - if (!IS_ALIGNED((unsigned long)__init_end, SECTION_SIZE)) { + if (!IS_ALIGNED((unsigned long)__init_end, SWAPPER_BLOCK_SIZE)) { unsigned long aligned_end = round_up(__pa(__init_end), - SECTION_SIZE); + SWAPPER_BLOCK_SIZE); create_mapping(__pa(__init_end), (unsigned long)__init_end, aligned_end - __pa(__init_end), PAGE_KERNEL); @@ -475,7 +426,7 @@ void mark_rodata_ro(void) { create_mapping_late(__pa(_stext), (unsigned long)_stext, (unsigned long)_etext - (unsigned long)_stext, - PAGE_KERNEL_EXEC | PTE_RDONLY); + PAGE_KERNEL_ROX); } #endif diff --git a/arch/arm64/net/bpf_jit_comp.c b/arch/arm64/net/bpf_jit_comp.c index cf3c7d4a1b58..b162ad70effc 100644 --- a/arch/arm64/net/bpf_jit_comp.c +++ b/arch/arm64/net/bpf_jit_comp.c @@ -50,7 +50,7 @@ static const int bpf2a64[] = { [BPF_REG_8] = A64_R(21), [BPF_REG_9] = A64_R(22), /* read-only frame pointer to access stack */ - [BPF_REG_FP] = A64_FP, + [BPF_REG_FP] = A64_R(25), /* temporary register for internal BPF JIT */ [TMP_REG_1] = A64_R(23), [TMP_REG_2] = A64_R(24), @@ -139,6 +139,12 @@ static inline int epilogue_offset(const struct jit_ctx *ctx) /* Stack must be multiples of 16B */ #define STACK_ALIGN(sz) (((sz) + 15) & ~15) +#define _STACK_SIZE \ + (MAX_BPF_STACK \ + + 4 /* extra for skb_copy_bits buffer */) + +#define STACK_SIZE STACK_ALIGN(_STACK_SIZE) + static void build_prologue(struct jit_ctx *ctx) { const u8 r6 = bpf2a64[BPF_REG_6]; @@ -150,10 +156,35 @@ static void build_prologue(struct jit_ctx *ctx) const u8 rx = bpf2a64[BPF_REG_X]; const u8 tmp1 = bpf2a64[TMP_REG_1]; const u8 tmp2 = bpf2a64[TMP_REG_2]; - int stack_size = MAX_BPF_STACK; - stack_size += 4; /* extra for skb_copy_bits buffer */ - stack_size = STACK_ALIGN(stack_size); + /* + * BPF prog stack layout + * + * high + * original A64_SP => 0:+-----+ BPF prologue + * |FP/LR| + * current A64_FP => -16:+-----+ + * | ... | callee saved registers + * +-----+ + * | | x25/x26 + * BPF fp register => -80:+-----+ <= (BPF_FP) + * | | + * | ... | BPF prog stack + * | | + * +-----+ <= (BPF_FP - MAX_BPF_STACK) + * |RSVD | JIT scratchpad + * current A64_SP => +-----+ <= (BPF_FP - STACK_SIZE) + * | | + * | ... | Function call stack + * | | + * +-----+ + * low + * + */ + + /* Save FP and LR registers to stay align with ARM64 AAPCS */ + emit(A64_PUSH(A64_FP, A64_LR, A64_SP), ctx); + emit(A64_MOV(1, A64_FP, A64_SP), ctx); /* Save callee-saved register */ emit(A64_PUSH(r6, r7, A64_SP), ctx); @@ -161,12 +192,15 @@ static void build_prologue(struct jit_ctx *ctx) if (ctx->tmp_used) emit(A64_PUSH(tmp1, tmp2, A64_SP), ctx); - /* Set up BPF stack */ - emit(A64_SUB_I(1, A64_SP, A64_SP, stack_size), ctx); + /* Save fp (x25) and x26. SP requires 16 bytes alignment */ + emit(A64_PUSH(fp, A64_R(26), A64_SP), ctx); - /* Set up frame pointer */ + /* Set up BPF prog stack base register (x25) */ emit(A64_MOV(1, fp, A64_SP), ctx); + /* Set up function call stack */ + emit(A64_SUB_I(1, A64_SP, A64_SP, STACK_SIZE), ctx); + /* Clear registers A and X */ emit_a64_mov_i64(ra, 0, ctx); emit_a64_mov_i64(rx, 0, ctx); @@ -182,13 +216,12 @@ static void build_epilogue(struct jit_ctx *ctx) const u8 fp = bpf2a64[BPF_REG_FP]; const u8 tmp1 = bpf2a64[TMP_REG_1]; const u8 tmp2 = bpf2a64[TMP_REG_2]; - int stack_size = MAX_BPF_STACK; - - stack_size += 4; /* extra for skb_copy_bits buffer */ - stack_size = STACK_ALIGN(stack_size); /* We're done with BPF stack */ - emit(A64_ADD_I(1, A64_SP, A64_SP, stack_size), ctx); + emit(A64_ADD_I(1, A64_SP, A64_SP, STACK_SIZE), ctx); + + /* Restore fs (x25) and x26 */ + emit(A64_POP(fp, A64_R(26), A64_SP), ctx); /* Restore callee-saved register */ if (ctx->tmp_used) @@ -196,8 +229,8 @@ static void build_epilogue(struct jit_ctx *ctx) emit(A64_POP(r8, r9, A64_SP), ctx); emit(A64_POP(r6, r7, A64_SP), ctx); - /* Restore frame pointer */ - emit(A64_MOV(1, fp, A64_SP), ctx); + /* Restore FP/LR registers */ + emit(A64_POP(A64_FP, A64_LR, A64_SP), ctx); /* Set return value */ emit(A64_MOV(1, A64_R(0), r0), ctx); @@ -557,7 +590,25 @@ emit_cond_jmp: case BPF_ST | BPF_MEM | BPF_H: case BPF_ST | BPF_MEM | BPF_B: case BPF_ST | BPF_MEM | BPF_DW: - goto notyet; + /* Load imm to a register then store it */ + ctx->tmp_used = 1; + emit_a64_mov_i(1, tmp2, off, ctx); + emit_a64_mov_i(1, tmp, imm, ctx); + switch (BPF_SIZE(code)) { + case BPF_W: + emit(A64_STR32(tmp, dst, tmp2), ctx); + break; + case BPF_H: + emit(A64_STRH(tmp, dst, tmp2), ctx); + break; + case BPF_B: + emit(A64_STRB(tmp, dst, tmp2), ctx); + break; + case BPF_DW: + emit(A64_STR64(tmp, dst, tmp2), ctx); + break; + } + break; /* STX: *(size *)(dst + off) = src */ case BPF_STX | BPF_MEM | BPF_W: @@ -624,7 +675,7 @@ emit_cond_jmp: return -EINVAL; } emit_a64_mov_i64(r3, size, ctx); - emit(A64_ADD_I(1, r4, fp, MAX_BPF_STACK), ctx); + emit(A64_SUB_I(1, r4, fp, STACK_SIZE), ctx); emit_a64_mov_i64(r5, (unsigned long)bpf_load_pointer, ctx); emit(A64_PUSH(A64_FP, A64_LR, A64_SP), ctx); emit(A64_MOV(1, A64_FP, A64_SP), ctx); @@ -758,7 +809,7 @@ void bpf_int_jit_compile(struct bpf_prog *prog) if (bpf_jit_enable > 1) bpf_jit_dump(prog->len, image_size, 2, ctx.image); - bpf_flush_icache(ctx.image, ctx.image + ctx.idx); + bpf_flush_icache(header, ctx.image + ctx.idx); set_memory_ro((unsigned long)header, header->pages); prog->bpf_func = (void *)ctx.image; diff --git a/arch/blackfin/include/asm/cmpxchg.h b/arch/blackfin/include/asm/cmpxchg.h index c05868cc61c1..253928854299 100644 --- a/arch/blackfin/include/asm/cmpxchg.h +++ b/arch/blackfin/include/asm/cmpxchg.h @@ -128,6 +128,5 @@ static inline unsigned long __xchg(unsigned long x, volatile void *ptr, #endif /* !CONFIG_SMP */ #define xchg(ptr, x) ((__typeof__(*(ptr)))__xchg((unsigned long)(x), (ptr), sizeof(*(ptr)))) -#define tas(ptr) ((void)xchg((ptr), 1)) #endif /* __ARCH_BLACKFIN_CMPXCHG__ */ diff --git a/arch/blackfin/kernel/perf_event.c b/arch/blackfin/kernel/perf_event.c index 1e9c8b0bf486..170d786807c4 100644 --- a/arch/blackfin/kernel/perf_event.c +++ b/arch/blackfin/kernel/perf_event.c @@ -14,7 +14,7 @@ * Copyright (C) 2008-2009 Red Hat, Inc., Ingo Molnar * Copyright (C) 2009 Jaswinder Singh Rajput * Copyright (C) 2009 Advanced Micro Devices, Inc., Robert Richter - * Copyright (C) 2008-2009 Red Hat, Inc., Peter Zijlstra <pzijlstr@redhat.com> + * Copyright (C) 2008-2009 Red Hat, Inc., Peter Zijlstra * Copyright (C) 2009 Intel Corporation, <markus.t.metzger@intel.com> * * ppc: diff --git a/arch/c6x/include/asm/cmpxchg.h b/arch/c6x/include/asm/cmpxchg.h index b27c8cefb8c3..93d0a5a047a2 100644 --- a/arch/c6x/include/asm/cmpxchg.h +++ b/arch/c6x/include/asm/cmpxchg.h @@ -47,8 +47,6 @@ static inline unsigned int __xchg(unsigned int x, volatile void *ptr, int size) #define xchg(ptr, x) \ ((__typeof__(*(ptr)))__xchg((unsigned int)(x), (void *) (ptr), \ sizeof(*(ptr)))) -#define tas(ptr) xchg((ptr), 1) - #include <asm-generic/cmpxchg-local.h> diff --git a/arch/frv/include/asm/cmpxchg.h b/arch/frv/include/asm/cmpxchg.h index 5b04dd0aecab..a899765102ea 100644 --- a/arch/frv/include/asm/cmpxchg.h +++ b/arch/frv/include/asm/cmpxchg.h @@ -69,8 +69,6 @@ extern uint32_t __xchg_32(uint32_t i, volatile void *v); #endif -#define tas(ptr) (xchg((ptr), 1)) - /*****************************************************************************/ /* * compare and conditionally exchange value with memory diff --git a/arch/h8300/Kconfig b/arch/h8300/Kconfig index dd3ac75776ad..2e20333cbce9 100644 --- a/arch/h8300/Kconfig +++ b/arch/h8300/Kconfig @@ -17,6 +17,7 @@ config H8300 select HAVE_MEMBLOCK select HAVE_DMA_ATTRS select CLKSRC_OF + select H8300_TMR8 config RWSEM_GENERIC_SPINLOCK def_bool y diff --git a/arch/h8300/include/asm/io.h b/arch/h8300/include/asm/io.h index bb837cded268..f0e14f3a800d 100644 --- a/arch/h8300/include/asm/io.h +++ b/arch/h8300/include/asm/io.h @@ -3,40 +3,45 @@ #ifdef __KERNEL__ -#include <asm-generic/io.h> - /* H8/300 internal I/O functions */ -static inline unsigned char ctrl_inb(unsigned long addr) + +#define __raw_readb __raw_readb +static inline u8 __raw_readb(const volatile void __iomem *addr) { - return *(volatile unsigned char *)addr; + return *(volatile u8 *)addr; } -static inline unsigned short ctrl_inw(unsigned long addr) +#define __raw_readw __raw_readw +static inline u16 __raw_readw(const volatile void __iomem *addr) { - return *(volatile unsigned short *)addr; + return *(volatile u16 *)addr; } -static inline unsigned long ctrl_inl(unsigned long addr) +#define __raw_readl __raw_readl +static inline u32 __raw_readl(const volatile void __iomem *addr) { - return *(volatile unsigned long *)addr; + return *(volatile u32 *)addr; } -static inline void ctrl_outb(unsigned char b, unsigned long addr) +#define __raw_writeb __raw_writeb +static inline void __raw_writeb(u8 b, const volatile void __iomem *addr) { - *(volatile unsigned char *)addr = b; + *(volatile u8 *)addr = b; } -static inline void ctrl_outw(unsigned short b, unsigned long addr) +#define __raw_writew __raw_writew +static inline void __raw_writew(u16 b, const volatile void __iomem *addr) { - *(volatile unsigned short *)addr = b; + *(volatile u16 *)addr = b; } -static inline void ctrl_outl(unsigned long b, unsigned long addr) +#define __raw_writel __raw_writel +static inline void __raw_writel(u32 b, const volatile void __iomem *addr) { - *(volatile unsigned long *)addr = b; + *(volatile u32 *)addr = b; } -static inline void ctrl_bclr(int b, unsigned char *addr) +static inline void ctrl_bclr(int b, void __iomem *addr) { if (__builtin_constant_p(b)) __asm__("bclr %1,%0" : "+WU"(*addr): "i"(b)); @@ -44,7 +49,7 @@ static inline void ctrl_bclr(int b, unsigned char *addr) __asm__("bclr %w1,%0" : "+WU"(*addr): "r"(b)); } -static inline void ctrl_bset(int b, unsigned char *addr) +static inline void ctrl_bset(int b, void __iomem *addr) { if (__builtin_constant_p(b)) __asm__("bset %1,%0" : "+WU"(*addr): "i"(b)); @@ -52,6 +57,8 @@ static inline void ctrl_bset(int b, unsigned char *addr) __asm__("bset %w1,%0" : "+WU"(*addr): "r"(b)); } +#include <asm-generic/io.h> + #endif /* __KERNEL__ */ #endif /* _H8300_IO_H */ diff --git a/arch/h8300/kernel/setup.c b/arch/h8300/kernel/setup.c index c772abe6d19c..e4985dfa91dc 100644 --- a/arch/h8300/kernel/setup.c +++ b/arch/h8300/kernel/setup.c @@ -207,14 +207,14 @@ device_initcall(device_probe); #define get_wait(base, addr) ({ \ int baddr; \ baddr = ((addr) / 0x200000 * 2); \ - w *= (ctrl_inw((unsigned long)(base) + 2) & (3 << baddr)) + 1; \ + w *= (readw((base) + 2) & (3 << baddr)) + 1; \ }) #endif #if defined(CONFIG_CPU_H8S) #define get_wait(base, addr) ({ \ int baddr; \ baddr = ((addr) / 0x200000 * 16); \ - w *= (ctrl_inl((unsigned long)(base) + 2) & (7 << baddr)) + 1; \ + w *= (readl((base) + 2) & (7 << baddr)) + 1; \ }) #endif @@ -228,8 +228,8 @@ static __init int access_timing(void) bsc = of_find_compatible_node(NULL, NULL, "renesas,h8300-bsc"); base = of_iomap(bsc, 0); - w = (ctrl_inb((unsigned long)base + 0) & bit)?2:1; - if (ctrl_inb((unsigned long)base + 1) & bit) + w = (readb(base + 0) & bit)?2:1; + if (readb(base + 1) & bit) w *= get_wait(base, addr); else w *= 2; diff --git a/arch/ia64/include/asm/barrier.h b/arch/ia64/include/asm/barrier.h index df896a1c41d3..209c4b817c95 100644 --- a/arch/ia64/include/asm/barrier.h +++ b/arch/ia64/include/asm/barrier.h @@ -77,7 +77,7 @@ do { \ ___p1; \ }) -#define smp_store_mb(var, value) do { WRITE_ONCE(var, value); mb(); } while (0) +#define smp_store_mb(var, value) do { WRITE_ONCE(var, value); smp_mb(); } while (0) /* * The group barrier in front of the rsm & ssm are necessary to ensure diff --git a/arch/ia64/include/asm/unistd.h b/arch/ia64/include/asm/unistd.h index db73390568c8..74c132d901bd 100644 --- a/arch/ia64/include/asm/unistd.h +++ b/arch/ia64/include/asm/unistd.h @@ -11,7 +11,7 @@ -#define NR_syscalls 322 /* length of syscall table */ +#define NR_syscalls 323 /* length of syscall table */ /* * The following defines stop scripts/checksyscalls.sh from complaining about diff --git a/arch/ia64/include/uapi/asm/unistd.h b/arch/ia64/include/uapi/asm/unistd.h index 9038726e7d26..762edce7572e 100644 --- a/arch/ia64/include/uapi/asm/unistd.h +++ b/arch/ia64/include/uapi/asm/unistd.h @@ -335,5 +335,6 @@ #define __NR_userfaultfd 1343 #define __NR_membarrier 1344 #define __NR_kcmp 1345 +#define __NR_mlock2 1346 #endif /* _UAPI_ASM_IA64_UNISTD_H */ diff --git a/arch/ia64/kernel/entry.S b/arch/ia64/kernel/entry.S index dcd97f84d065..534a74acb849 100644 --- a/arch/ia64/kernel/entry.S +++ b/arch/ia64/kernel/entry.S @@ -1771,5 +1771,6 @@ sys_call_table: data8 sys_userfaultfd data8 sys_membarrier data8 sys_kcmp // 1345 + data8 sys_mlock2 .org sys_call_table + 8*NR_syscalls // guard against failures to increase NR_syscalls diff --git a/arch/m32r/include/asm/Kbuild b/arch/m32r/include/asm/Kbuild index fd104bd221ce..860e440611c9 100644 --- a/arch/m32r/include/asm/Kbuild +++ b/arch/m32r/include/asm/Kbuild @@ -3,6 +3,7 @@ generic-y += clkdev.h generic-y += cputime.h generic-y += exec.h generic-y += irq_work.h +generic-y += kvm_para.h generic-y += mcs_spinlock.h generic-y += mm-arch-hooks.h generic-y += module.h diff --git a/arch/m32r/include/asm/io.h b/arch/m32r/include/asm/io.h index 61b8931bc192..4b0f5e001d4d 100644 --- a/arch/m32r/include/asm/io.h +++ b/arch/m32r/include/asm/io.h @@ -168,13 +168,21 @@ static inline void _writel(unsigned long l, unsigned long addr) #define writew_relaxed writew #define writel_relaxed writel -#define ioread8 read +#define ioread8 readb #define ioread16 readw #define ioread32 readl #define iowrite8 writeb #define iowrite16 writew #define iowrite32 writel +#define ioread8_rep(p, dst, count) insb((unsigned long)(p), (dst), (count)) +#define ioread16_rep(p, dst, count) insw((unsigned long)(p), (dst), (count)) +#define ioread32_rep(p, dst, count) insl((unsigned long)(p), (dst), (count)) + +#define iowrite8_rep(p, src, count) outsb((unsigned long)(p), (src), (count)) +#define iowrite16_rep(p, src, count) outsw((unsigned long)(p), (src), (count)) +#define iowrite32_rep(p, src, count) outsl((unsigned long)(p), (src), (count)) + #define ioread16be(addr) be16_to_cpu(readw(addr)) #define ioread32be(addr) be32_to_cpu(readl(addr)) #define iowrite16be(v, addr) writew(cpu_to_be16(v), (addr)) diff --git a/arch/m68k/coldfire/m54xx.c b/arch/m68k/coldfire/m54xx.c index f7836c6a6b60..c32f76791f48 100644 --- a/arch/m68k/coldfire/m54xx.c +++ b/arch/m68k/coldfire/m54xx.c @@ -98,7 +98,7 @@ static void __init mcf54xx_bootmem_alloc(void) memstart = PAGE_ALIGN(_ramstart); min_low_pfn = PFN_DOWN(_rambase); start_pfn = PFN_DOWN(memstart); - max_low_pfn = PFN_DOWN(_ramend); + max_pfn = max_low_pfn = PFN_DOWN(_ramend); high_memory = (void *)_ramend; m68k_virt_to_node_shift = fls(_ramend - _rambase - 1) - 6; diff --git a/arch/m68k/include/asm/unistd.h b/arch/m68k/include/asm/unistd.h index 0793a7f17417..f9d96bf86910 100644 --- a/arch/m68k/include/asm/unistd.h +++ b/arch/m68k/include/asm/unistd.h @@ -4,7 +4,7 @@ #include <uapi/asm/unistd.h> -#define NR_syscalls 375 +#define NR_syscalls 376 #define __ARCH_WANT_OLD_READDIR #define __ARCH_WANT_OLD_STAT diff --git a/arch/m68k/include/uapi/asm/unistd.h b/arch/m68k/include/uapi/asm/unistd.h index 5e6fae6c275f..36cf129de663 100644 --- a/arch/m68k/include/uapi/asm/unistd.h +++ b/arch/m68k/include/uapi/asm/unistd.h @@ -380,5 +380,6 @@ #define __NR_sendmmsg 372 #define __NR_userfaultfd 373 #define __NR_membarrier 374 +#define __NR_mlock2 375 #endif /* _UAPI_ASM_M68K_UNISTD_H_ */ diff --git a/arch/m68k/kernel/setup_no.c b/arch/m68k/kernel/setup_no.c index 88c27d94a721..76b9113f3092 100644 --- a/arch/m68k/kernel/setup_no.c +++ b/arch/m68k/kernel/setup_no.c @@ -238,11 +238,14 @@ void __init setup_arch(char **cmdline_p) * Give all the memory to the bootmap allocator, tell it to put the * boot mem_map at the start of memory. */ + min_low_pfn = PFN_DOWN(memory_start); + max_pfn = max_low_pfn = PFN_DOWN(memory_end); + bootmap_size = init_bootmem_node( NODE_DATA(0), - memory_start >> PAGE_SHIFT, /* map goes here */ - PAGE_OFFSET >> PAGE_SHIFT, /* 0 on coldfire */ - memory_end >> PAGE_SHIFT); + min_low_pfn, /* map goes here */ + PFN_DOWN(PAGE_OFFSET), + max_pfn); /* * Free the usable memory, we have to make sure we do not free * the bootmem bitmap so we then reserve it after freeing it :-) diff --git a/arch/m68k/kernel/syscalltable.S b/arch/m68k/kernel/syscalltable.S index 5dd0e80042f5..282cd903f4c4 100644 --- a/arch/m68k/kernel/syscalltable.S +++ b/arch/m68k/kernel/syscalltable.S @@ -395,3 +395,4 @@ ENTRY(sys_call_table) .long sys_sendmmsg .long sys_userfaultfd .long sys_membarrier + .long sys_mlock2 /* 375 */ diff --git a/arch/m68k/mm/motorola.c b/arch/m68k/mm/motorola.c index b958916e5eac..8f37fdd80be9 100644 --- a/arch/m68k/mm/motorola.c +++ b/arch/m68k/mm/motorola.c @@ -250,7 +250,7 @@ void __init paging_init(void) high_memory = phys_to_virt(max_addr); min_low_pfn = availmem >> PAGE_SHIFT; - max_low_pfn = max_addr >> PAGE_SHIFT; + max_pfn = max_low_pfn = max_addr >> PAGE_SHIFT; for (i = 0; i < m68k_num_memory; i++) { addr = m68k_memory[i].addr; diff --git a/arch/m68k/sun3/config.c b/arch/m68k/sun3/config.c index a8b942bf7163..2a5f43a68ae3 100644 --- a/arch/m68k/sun3/config.c +++ b/arch/m68k/sun3/config.c @@ -118,13 +118,13 @@ static void __init sun3_bootmem_alloc(unsigned long memory_start, memory_end = memory_end & PAGE_MASK; start_page = __pa(memory_start) >> PAGE_SHIFT; - num_pages = __pa(memory_end) >> PAGE_SHIFT; + max_pfn = num_pages = __pa(memory_end) >> PAGE_SHIFT; high_memory = (void *)memory_end; availmem = memory_start; m68k_setup_node(0); - availmem += init_bootmem_node(NODE_DATA(0), start_page, 0, num_pages); + availmem += init_bootmem(start_page, num_pages); availmem = (availmem + (PAGE_SIZE-1)) & PAGE_MASK; free_bootmem(__pa(availmem), memory_end - (availmem)); diff --git a/arch/microblaze/kernel/dma.c b/arch/microblaze/kernel/dma.c index c89da6312954..bf4dec229437 100644 --- a/arch/microblaze/kernel/dma.c +++ b/arch/microblaze/kernel/dma.c @@ -61,7 +61,8 @@ static int dma_direct_map_sg(struct device *dev, struct scatterlist *sgl, /* FIXME this part of code is untested */ for_each_sg(sgl, sg, nents, i) { sg->dma_address = sg_phys(sg); - __dma_sync(sg_phys(sg), sg->length, direction); + __dma_sync(page_to_phys(sg_page(sg)) + sg->offset, + sg->length, direction); } return nents; diff --git a/arch/mips/ath79/setup.c b/arch/mips/ath79/setup.c index 1ba21204ebe0..8755d618e116 100644 --- a/arch/mips/ath79/setup.c +++ b/arch/mips/ath79/setup.c @@ -216,9 +216,9 @@ void __init plat_mem_setup(void) AR71XX_RESET_SIZE); ath79_pll_base = ioremap_nocache(AR71XX_PLL_BASE, AR71XX_PLL_SIZE); + ath79_detect_sys_type(); ath79_ddr_ctrl_init(); - ath79_detect_sys_type(); if (mips_machtype != ATH79_MACH_GENERIC_OF) detect_memory_region(0, ATH79_MEM_SIZE_MIN, ATH79_MEM_SIZE_MAX); @@ -281,3 +281,8 @@ MIPS_MACHINE(ATH79_MACH_GENERIC, "Generic", "Generic AR71XX/AR724X/AR913X based board", ath79_generic_init); + +MIPS_MACHINE(ATH79_MACH_GENERIC_OF, + "DTB", + "Generic AR71XX/AR724X/AR913X based board (DT)", + NULL); diff --git a/arch/mips/boot/dts/qca/ar9132.dtsi b/arch/mips/boot/dts/qca/ar9132.dtsi index fb7734eadbf0..13d0439496a9 100644 --- a/arch/mips/boot/dts/qca/ar9132.dtsi +++ b/arch/mips/boot/dts/qca/ar9132.dtsi @@ -107,7 +107,7 @@ miscintc: interrupt-controller@18060010 { compatible = "qca,ar9132-misc-intc", "qca,ar7100-misc-intc"; - reg = <0x18060010 0x4>; + reg = <0x18060010 0x8>; interrupt-parent = <&cpuintc>; interrupts = <6>; diff --git a/arch/mips/include/asm/page.h b/arch/mips/include/asm/page.h index ad1fccdb8d13..2046c0230224 100644 --- a/arch/mips/include/asm/page.h +++ b/arch/mips/include/asm/page.h @@ -200,8 +200,9 @@ static inline int pfn_valid(unsigned long pfn) { /* avoid <linux/mm.h> include hell */ extern unsigned long max_mapnr; + unsigned long pfn_offset = ARCH_PFN_OFFSET; - return pfn >= ARCH_PFN_OFFSET && pfn < max_mapnr; + return pfn >= pfn_offset && pfn < max_mapnr; } #elif defined(CONFIG_SPARSEMEM) diff --git a/arch/mips/include/asm/uaccess.h b/arch/mips/include/asm/uaccess.h index 5305d694ffe5..095ecafe6bd3 100644 --- a/arch/mips/include/asm/uaccess.h +++ b/arch/mips/include/asm/uaccess.h @@ -599,7 +599,7 @@ extern void __put_user_unknown(void); * On error, the variable @x is set to zero. */ #define __get_user_unaligned(x,ptr) \ - __get_user__unalignednocheck((x),(ptr),sizeof(*(ptr))) + __get_user_unaligned_nocheck((x),(ptr),sizeof(*(ptr))) /* * Yuck. We need two variants, one for 64bit operation and one @@ -620,8 +620,8 @@ extern void __get_user_unaligned_unknown(void); do { \ switch (size) { \ case 1: __get_data_asm(val, "lb", ptr); break; \ - case 2: __get_user_unaligned_asm(val, "ulh", ptr); break; \ - case 4: __get_user_unaligned_asm(val, "ulw", ptr); break; \ + case 2: __get_data_unaligned_asm(val, "ulh", ptr); break; \ + case 4: __get_data_unaligned_asm(val, "ulw", ptr); break; \ case 8: __GET_USER_UNALIGNED_DW(val, ptr); break; \ default: __get_user_unaligned_unknown(); break; \ } \ @@ -1122,9 +1122,15 @@ extern size_t __copy_in_user_eva(void *__to, const void *__from, size_t __n); __cu_to = (to); \ __cu_from = (from); \ __cu_len = (n); \ - might_fault(); \ - __cu_len = __invoke_copy_from_user(__cu_to, __cu_from, \ - __cu_len); \ + if (eva_kernel_access()) { \ + __cu_len = __invoke_copy_from_kernel(__cu_to, \ + __cu_from, \ + __cu_len); \ + } else { \ + might_fault(); \ + __cu_len = __invoke_copy_from_user(__cu_to, __cu_from, \ + __cu_len); \ + } \ __cu_len; \ }) @@ -1229,16 +1235,28 @@ __clear_user(void __user *addr, __kernel_size_t size) { __kernel_size_t res; - might_fault(); - __asm__ __volatile__( - "move\t$4, %1\n\t" - "move\t$5, $0\n\t" - "move\t$6, %2\n\t" - __MODULE_JAL(__bzero) - "move\t%0, $6" - : "=r" (res) - : "r" (addr), "r" (size) - : "$4", "$5", "$6", __UA_t0, __UA_t1, "$31"); + if (eva_kernel_access()) { + __asm__ __volatile__( + "move\t$4, %1\n\t" + "move\t$5, $0\n\t" + "move\t$6, %2\n\t" + __MODULE_JAL(__bzero_kernel) + "move\t%0, $6" + : "=r" (res) + : "r" (addr), "r" (size) + : "$4", "$5", "$6", __UA_t0, __UA_t1, "$31"); + } else { + might_fault(); + __asm__ __volatile__( + "move\t$4, %1\n\t" + "move\t$5, $0\n\t" + "move\t$6, %2\n\t" + __MODULE_JAL(__bzero) + "move\t%0, $6" + : "=r" (res) + : "r" (addr), "r" (size) + : "$4", "$5", "$6", __UA_t0, __UA_t1, "$31"); + } return res; } @@ -1384,7 +1402,7 @@ static inline long strlen_user(const char __user *s) might_fault(); __asm__ __volatile__( "move\t$4, %1\n\t" - __MODULE_JAL(__strlen_kernel_asm) + __MODULE_JAL(__strlen_user_asm) "move\t%0, $2" : "=r" (res) : "r" (s) diff --git a/arch/mips/kernel/cps-vec.S b/arch/mips/kernel/cps-vec.S index 8fd5a276cad2..ac81edd44563 100644 --- a/arch/mips/kernel/cps-vec.S +++ b/arch/mips/kernel/cps-vec.S @@ -257,7 +257,6 @@ LEAF(mips_cps_core_init) has_mt t0, 3f .set push - .set mips64r2 .set mt /* Only allow 1 TC per VPE to execute... */ @@ -376,7 +375,6 @@ LEAF(mips_cps_boot_vpes) nop .set push - .set mips64r2 .set mt 1: /* Enter VPE configuration state */ diff --git a/arch/mips/kernel/mips_ksyms.c b/arch/mips/kernel/mips_ksyms.c index 291af0b5c482..e2b6ab74643d 100644 --- a/arch/mips/kernel/mips_ksyms.c +++ b/arch/mips/kernel/mips_ksyms.c @@ -17,6 +17,7 @@ #include <asm/fpu.h> #include <asm/msa.h> +extern void *__bzero_kernel(void *__s, size_t __count); extern void *__bzero(void *__s, size_t __count); extern long __strncpy_from_kernel_nocheck_asm(char *__to, const char *__from, long __len); @@ -64,6 +65,7 @@ EXPORT_SYMBOL(__copy_from_user_eva); EXPORT_SYMBOL(__copy_in_user_eva); EXPORT_SYMBOL(__copy_to_user_eva); EXPORT_SYMBOL(__copy_user_inatomic_eva); +EXPORT_SYMBOL(__bzero_kernel); #endif EXPORT_SYMBOL(__bzero); EXPORT_SYMBOL(__strncpy_from_kernel_nocheck_asm); diff --git a/arch/mips/kvm/emulate.c b/arch/mips/kvm/emulate.c index d5fa3eaf39a1..41b1b090f56f 100644 --- a/arch/mips/kvm/emulate.c +++ b/arch/mips/kvm/emulate.c @@ -1581,7 +1581,7 @@ enum emulation_result kvm_mips_emulate_cache(uint32_t inst, uint32_t *opc, base = (inst >> 21) & 0x1f; op_inst = (inst >> 16) & 0x1f; - offset = inst & 0xffff; + offset = (int16_t)inst; cache = (inst >> 16) & 0x3; op = (inst >> 18) & 0x7; diff --git a/arch/mips/kvm/locore.S b/arch/mips/kvm/locore.S index 7bab3a4e8f7d..7e2210846b8b 100644 --- a/arch/mips/kvm/locore.S +++ b/arch/mips/kvm/locore.S @@ -157,9 +157,11 @@ FEXPORT(__kvm_mips_vcpu_run) FEXPORT(__kvm_mips_load_asid) /* Set the ASID for the Guest Kernel */ - INT_SLL t0, t0, 1 /* with kseg0 @ 0x40000000, kernel */ - /* addresses shift to 0x80000000 */ - bltz t0, 1f /* If kernel */ + PTR_L t0, VCPU_COP0(k1) + LONG_L t0, COP0_STATUS(t0) + andi t0, KSU_USER | ST0_ERL | ST0_EXL + xori t0, KSU_USER + bnez t0, 1f /* If kernel */ INT_ADDIU t1, k1, VCPU_GUEST_KERNEL_ASID /* (BD) */ INT_ADDIU t1, k1, VCPU_GUEST_USER_ASID /* else user */ 1: @@ -474,9 +476,11 @@ __kvm_mips_return_to_guest: mtc0 t0, CP0_EPC /* Set the ASID for the Guest Kernel */ - INT_SLL t0, t0, 1 /* with kseg0 @ 0x40000000, kernel */ - /* addresses shift to 0x80000000 */ - bltz t0, 1f /* If kernel */ + PTR_L t0, VCPU_COP0(k1) + LONG_L t0, COP0_STATUS(t0) + andi t0, KSU_USER | ST0_ERL | ST0_EXL + xori t0, KSU_USER + bnez t0, 1f /* If kernel */ INT_ADDIU t1, k1, VCPU_GUEST_KERNEL_ASID /* (BD) */ INT_ADDIU t1, k1, VCPU_GUEST_USER_ASID /* else user */ 1: diff --git a/arch/mips/kvm/mips.c b/arch/mips/kvm/mips.c index 49ff3bfc007e..b9b803facdbf 100644 --- a/arch/mips/kvm/mips.c +++ b/arch/mips/kvm/mips.c @@ -279,7 +279,7 @@ struct kvm_vcpu *kvm_arch_vcpu_create(struct kvm *kvm, unsigned int id) if (!gebase) { err = -ENOMEM; - goto out_free_cpu; + goto out_uninit_cpu; } kvm_debug("Allocated %d bytes for KVM Exception Handlers @ %p\n", ALIGN(size, PAGE_SIZE), gebase); @@ -343,6 +343,9 @@ struct kvm_vcpu *kvm_arch_vcpu_create(struct kvm *kvm, unsigned int id) out_free_gebase: kfree(gebase); +out_uninit_cpu: + kvm_vcpu_uninit(vcpu); + out_free_cpu: kfree(vcpu); diff --git a/arch/mips/lib/memset.S b/arch/mips/lib/memset.S index b8e63fd00375..8f0019a2e5c8 100644 --- a/arch/mips/lib/memset.S +++ b/arch/mips/lib/memset.S @@ -283,6 +283,8 @@ LEAF(memset) 1: #ifndef CONFIG_EVA FEXPORT(__bzero) +#else +FEXPORT(__bzero_kernel) #endif __BUILD_BZERO LEGACY_MODE diff --git a/arch/mips/mm/dma-default.c b/arch/mips/mm/dma-default.c index d8117be729a2..730d394ce5f0 100644 --- a/arch/mips/mm/dma-default.c +++ b/arch/mips/mm/dma-default.c @@ -145,7 +145,7 @@ static void *mips_dma_alloc_coherent(struct device *dev, size_t size, gfp = massage_gfp_flags(dev, gfp); - if (IS_ENABLED(CONFIG_DMA_CMA) && !(gfp & GFP_ATOMIC)) + if (IS_ENABLED(CONFIG_DMA_CMA) && gfpflags_allow_blocking(gfp)) page = dma_alloc_from_contiguous(dev, count, get_order(size)); if (!page) diff --git a/arch/mips/net/bpf_jit.c b/arch/mips/net/bpf_jit.c index 77cb27309db2..1a8c96035716 100644 --- a/arch/mips/net/bpf_jit.c +++ b/arch/mips/net/bpf_jit.c @@ -521,19 +521,6 @@ static inline u16 align_sp(unsigned int num) return num; } -static bool is_load_to_a(u16 inst) -{ - switch (inst) { - case BPF_LD | BPF_W | BPF_LEN: - case BPF_LD | BPF_W | BPF_ABS: - case BPF_LD | BPF_H | BPF_ABS: - case BPF_LD | BPF_B | BPF_ABS: - return true; - default: - return false; - } -} - static void save_bpf_jit_regs(struct jit_ctx *ctx, unsigned offset) { int i = 0, real_off = 0; @@ -614,7 +601,6 @@ static unsigned int get_stack_depth(struct jit_ctx *ctx) static void build_prologue(struct jit_ctx *ctx) { - u16 first_inst = ctx->skf->insns[0].code; int sp_off; /* Calculate the total offset for the stack pointer */ @@ -641,7 +627,7 @@ static void build_prologue(struct jit_ctx *ctx) emit_jit_reg_move(r_X, r_zero, ctx); /* Do not leak kernel data to userspace */ - if ((first_inst != (BPF_RET | BPF_K)) && !(is_load_to_a(first_inst))) + if (bpf_needs_clear_a(&ctx->skf->insns[0])) emit_jit_reg_move(r_A, r_zero, ctx); } diff --git a/arch/mips/pci/pci-rt2880.c b/arch/mips/pci/pci-rt2880.c index 8a978022630b..a245cad4372a 100644 --- a/arch/mips/pci/pci-rt2880.c +++ b/arch/mips/pci/pci-rt2880.c @@ -11,6 +11,7 @@ * by the Free Software Foundation. */ +#include <linux/delay.h> #include <linux/types.h> #include <linux/pci.h> #include <linux/io.h> @@ -220,7 +221,6 @@ int __init pcibios_map_irq(const struct pci_dev *dev, u8 slot, u8 pin) static int rt288x_pci_probe(struct platform_device *pdev) { void __iomem *io_map_base; - int i; rt2880_pci_base = ioremap_nocache(RT2880_PCI_BASE, PAGE_SIZE); @@ -232,8 +232,7 @@ static int rt288x_pci_probe(struct platform_device *pdev) ioport_resource.end = RT2880_PCI_IO_BASE + RT2880_PCI_IO_SIZE - 1; rt2880_pci_reg_write(0, RT2880_PCI_REG_PCICFG_ADDR); - for (i = 0; i < 0xfffff; i++) - ; + udelay(1); rt2880_pci_reg_write(0x79, RT2880_PCI_REG_ARBCTL); rt2880_pci_reg_write(0x07FF0001, RT2880_PCI_REG_BAR0SETUP_ADDR); diff --git a/arch/mips/pmcs-msp71xx/msp_setup.c b/arch/mips/pmcs-msp71xx/msp_setup.c index 4f925e06c414..9d293b3e9130 100644 --- a/arch/mips/pmcs-msp71xx/msp_setup.c +++ b/arch/mips/pmcs-msp71xx/msp_setup.c @@ -10,6 +10,8 @@ * option) any later version. */ +#include <linux/delay.h> + #include <asm/bootinfo.h> #include <asm/cacheflush.h> #include <asm/idle.h> @@ -37,7 +39,6 @@ extern void msp_serial_setup(void); void msp7120_reset(void) { void *start, *end, *iptr; - register int i; /* Diasble all interrupts */ local_irq_disable(); @@ -77,7 +78,7 @@ void msp7120_reset(void) */ /* Wait a bit for the DDRC to settle */ - for (i = 0; i < 100000000; i++); + mdelay(125); #if defined(CONFIG_PMC_MSP7120_GW) /* diff --git a/arch/mips/sni/reset.c b/arch/mips/sni/reset.c index 244f9427625b..6afa34346b81 100644 --- a/arch/mips/sni/reset.c +++ b/arch/mips/sni/reset.c @@ -3,6 +3,8 @@ * * Reset a SNI machine. */ +#include <linux/delay.h> + #include <asm/io.h> #include <asm/reboot.h> #include <asm/sni.h> @@ -24,7 +26,7 @@ static inline void kb_wait(void) /* XXX This ends up at the ARC firmware prompt ... */ void sni_machine_restart(char *command) { - int i, j; + int i; /* This does a normal via the keyboard controller like a PC. We can do that easier ... */ @@ -32,9 +34,9 @@ void sni_machine_restart(char *command) for (;;) { for (i = 0; i < 100; i++) { kb_wait(); - for (j = 0; j < 100000 ; j++) - /* nothing */; + udelay(50); outb_p(0xfe, 0x64); /* pulse reset low */ + udelay(50); } } } diff --git a/arch/mips/vdso/Makefile b/arch/mips/vdso/Makefile index ef5f348f386a..14568900fc1d 100644 --- a/arch/mips/vdso/Makefile +++ b/arch/mips/vdso/Makefile @@ -26,8 +26,8 @@ aflags-vdso := $(ccflags-vdso) \ # the comments on that file. # ifndef CONFIG_CPU_MIPSR6 - ifeq ($(call ld-ifversion, -gt, 22400000, y),) - $(warning MIPS VDSO requires binutils > 2.24) + ifeq ($(call ld-ifversion, -lt, 22500000, y),y) + $(warning MIPS VDSO requires binutils >= 2.25) obj-vdso-y := $(filter-out gettimeofday.o, $(obj-vdso-y)) ccflags-vdso += -DDISABLE_MIPS_VDSO endif diff --git a/arch/mn10300/Kconfig b/arch/mn10300/Kconfig index 4434b54e1d87..78ae5552fdb8 100644 --- a/arch/mn10300/Kconfig +++ b/arch/mn10300/Kconfig @@ -1,6 +1,7 @@ config MN10300 def_bool y select HAVE_OPROFILE + select HAVE_UID16 select GENERIC_IRQ_SHOW select ARCH_WANT_IPC_PARSE_VERSION select HAVE_ARCH_TRACEHOOK @@ -37,9 +38,6 @@ config HIGHMEM config NUMA def_bool n -config UID16 - def_bool y - config RWSEM_GENERIC_SPINLOCK def_bool y diff --git a/arch/nios2/mm/cacheflush.c b/arch/nios2/mm/cacheflush.c index 223cdcc8203f..87bf88ed04c6 100644 --- a/arch/nios2/mm/cacheflush.c +++ b/arch/nios2/mm/cacheflush.c @@ -23,22 +23,6 @@ static void __flush_dcache(unsigned long start, unsigned long end) end += (cpuinfo.dcache_line_size - 1); end &= ~(cpuinfo.dcache_line_size - 1); - for (addr = start; addr < end; addr += cpuinfo.dcache_line_size) { - __asm__ __volatile__ (" flushda 0(%0)\n" - : /* Outputs */ - : /* Inputs */ "r"(addr) - /* : No clobber */); - } -} - -static void __flush_dcache_all(unsigned long start, unsigned long end) -{ - unsigned long addr; - - start &= ~(cpuinfo.dcache_line_size - 1); - end += (cpuinfo.dcache_line_size - 1); - end &= ~(cpuinfo.dcache_line_size - 1); - if (end > start + cpuinfo.dcache_size) end = start + cpuinfo.dcache_size; @@ -112,7 +96,7 @@ static void flush_aliases(struct address_space *mapping, struct page *page) void flush_cache_all(void) { - __flush_dcache_all(0, cpuinfo.dcache_size); + __flush_dcache(0, cpuinfo.dcache_size); __flush_icache(0, cpuinfo.icache_size); } @@ -182,7 +166,7 @@ void __flush_dcache_page(struct address_space *mapping, struct page *page) */ unsigned long start = (unsigned long)page_address(page); - __flush_dcache_all(start, start + PAGE_SIZE); + __flush_dcache(start, start + PAGE_SIZE); } void flush_dcache_page(struct page *page) @@ -268,7 +252,7 @@ void copy_from_user_page(struct vm_area_struct *vma, struct page *page, { flush_cache_page(vma, user_vaddr, page_to_pfn(page)); memcpy(dst, src, len); - __flush_dcache_all((unsigned long)src, (unsigned long)src + len); + __flush_dcache((unsigned long)src, (unsigned long)src + len); if (vma->vm_flags & VM_EXEC) __flush_icache((unsigned long)src, (unsigned long)src + len); } @@ -279,7 +263,7 @@ void copy_to_user_page(struct vm_area_struct *vma, struct page *page, { flush_cache_page(vma, user_vaddr, page_to_pfn(page)); memcpy(dst, src, len); - __flush_dcache_all((unsigned long)dst, (unsigned long)dst + len); + __flush_dcache((unsigned long)dst, (unsigned long)dst + len); if (vma->vm_flags & VM_EXEC) __flush_icache((unsigned long)dst, (unsigned long)dst + len); } diff --git a/arch/parisc/Kconfig b/arch/parisc/Kconfig index c36546959e86..729f89163bc3 100644 --- a/arch/parisc/Kconfig +++ b/arch/parisc/Kconfig @@ -108,6 +108,9 @@ config PGTABLE_LEVELS default 3 if 64BIT && PARISC_PAGE_SIZE_4KB default 2 +config SYS_SUPPORTS_HUGETLBFS + def_bool y if PA20 + source "init/Kconfig" source "kernel/Kconfig.freezer" diff --git a/arch/parisc/include/asm/hugetlb.h b/arch/parisc/include/asm/hugetlb.h new file mode 100644 index 000000000000..7d56a9ccb752 --- /dev/null +++ b/arch/parisc/include/asm/hugetlb.h @@ -0,0 +1,85 @@ +#ifndef _ASM_PARISC64_HUGETLB_H +#define _ASM_PARISC64_HUGETLB_H + +#include <asm/page.h> +#include <asm-generic/hugetlb.h> + + +void set_huge_pte_at(struct mm_struct *mm, unsigned long addr, + pte_t *ptep, pte_t pte); + +pte_t huge_ptep_get_and_clear(struct mm_struct *mm, unsigned long addr, + pte_t *ptep); + +static inline int is_hugepage_only_range(struct mm_struct *mm, + unsigned long addr, + unsigned long len) { + return 0; +} + +/* + * If the arch doesn't supply something else, assume that hugepage + * size aligned regions are ok without further preparation. + */ +static inline int prepare_hugepage_range(struct file *file, + unsigned long addr, unsigned long len) +{ + if (len & ~HPAGE_MASK) + return -EINVAL; + if (addr & ~HPAGE_MASK) + return -EINVAL; + return 0; +} + +static inline void hugetlb_free_pgd_range(struct mmu_gather *tlb, + unsigned long addr, unsigned long end, + unsigned long floor, + unsigned long ceiling) +{ + free_pgd_range(tlb, addr, end, floor, ceiling); +} + +static inline void huge_ptep_clear_flush(struct vm_area_struct *vma, + unsigned long addr, pte_t *ptep) +{ +} + +static inline int huge_pte_none(pte_t pte) +{ + return pte_none(pte); +} + +static inline pte_t huge_pte_wrprotect(pte_t pte) +{ + return pte_wrprotect(pte); +} + +static inline void huge_ptep_set_wrprotect(struct mm_struct *mm, + unsigned long addr, pte_t *ptep) +{ + pte_t old_pte = *ptep; + set_huge_pte_at(mm, addr, ptep, pte_wrprotect(old_pte)); +} + +static inline int huge_ptep_set_access_flags(struct vm_area_struct *vma, + unsigned long addr, pte_t *ptep, + pte_t pte, int dirty) +{ + int changed = !pte_same(*ptep, pte); + if (changed) { + set_huge_pte_at(vma->vm_mm, addr, ptep, pte); + flush_tlb_page(vma, addr); + } + return changed; +} + +static inline pte_t huge_ptep_get(pte_t *ptep) +{ + return *ptep; +} + +static inline void arch_clear_hugepage_flags(struct page *page) +{ +} + +#endif /* _ASM_PARISC64_HUGETLB_H */ diff --git a/arch/parisc/include/asm/page.h b/arch/parisc/include/asm/page.h index 60d5d174dfe4..80e742a1c162 100644 --- a/arch/parisc/include/asm/page.h +++ b/arch/parisc/include/asm/page.h @@ -145,11 +145,22 @@ extern int npmem_ranges; #endif /* CONFIG_DISCONTIGMEM */ #ifdef CONFIG_HUGETLB_PAGE -#define HPAGE_SHIFT 22 /* 4MB (is this fixed?) */ +#define HPAGE_SHIFT PMD_SHIFT /* fixed for transparent huge pages */ #define HPAGE_SIZE ((1UL) << HPAGE_SHIFT) #define HPAGE_MASK (~(HPAGE_SIZE - 1)) #define HUGETLB_PAGE_ORDER (HPAGE_SHIFT - PAGE_SHIFT) + +#if defined(CONFIG_64BIT) && defined(CONFIG_PARISC_PAGE_SIZE_4KB) +# define REAL_HPAGE_SHIFT 20 /* 20 = 1MB */ +# define _HUGE_PAGE_SIZE_ENCODING_DEFAULT _PAGE_SIZE_ENCODING_1M +#elif !defined(CONFIG_64BIT) && defined(CONFIG_PARISC_PAGE_SIZE_4KB) +# define REAL_HPAGE_SHIFT 22 /* 22 = 4MB */ +# define _HUGE_PAGE_SIZE_ENCODING_DEFAULT _PAGE_SIZE_ENCODING_4M +#else +# define REAL_HPAGE_SHIFT 24 /* 24 = 16MB */ +# define _HUGE_PAGE_SIZE_ENCODING_DEFAULT _PAGE_SIZE_ENCODING_16M #endif +#endif /* CONFIG_HUGETLB_PAGE */ #define virt_addr_valid(kaddr) pfn_valid(__pa(kaddr) >> PAGE_SHIFT) diff --git a/arch/parisc/include/asm/pgalloc.h b/arch/parisc/include/asm/pgalloc.h index 3edbb9fc91b4..f2fd327dce2e 100644 --- a/arch/parisc/include/asm/pgalloc.h +++ b/arch/parisc/include/asm/pgalloc.h @@ -35,7 +35,7 @@ static inline pgd_t *pgd_alloc(struct mm_struct *mm) PxD_FLAG_VALID | PxD_FLAG_ATTACHED) + (__u32)(__pa((unsigned long)pgd) >> PxD_VALUE_SHIFT)); - /* The first pmd entry also is marked with _PAGE_GATEWAY as + /* The first pmd entry also is marked with PxD_FLAG_ATTACHED as * a signal that this pmd may not be freed */ __pgd_val_set(*pgd, PxD_FLAG_ATTACHED); #endif diff --git a/arch/parisc/include/asm/pgtable.h b/arch/parisc/include/asm/pgtable.h index f93c4a4e6580..291cee28ccb6 100644 --- a/arch/parisc/include/asm/pgtable.h +++ b/arch/parisc/include/asm/pgtable.h @@ -83,7 +83,11 @@ static inline void purge_tlb_entries(struct mm_struct *mm, unsigned long addr) printk("%s:%d: bad pgd %08lx.\n", __FILE__, __LINE__, (unsigned long)pgd_val(e)) /* This is the size of the initially mapped kernel memory */ -#define KERNEL_INITIAL_ORDER 24 /* 0 to 1<<24 = 16MB */ +#ifdef CONFIG_64BIT +#define KERNEL_INITIAL_ORDER 25 /* 1<<25 = 32MB */ +#else +#define KERNEL_INITIAL_ORDER 24 /* 1<<24 = 16MB */ +#endif #define KERNEL_INITIAL_SIZE (1 << KERNEL_INITIAL_ORDER) #if CONFIG_PGTABLE_LEVELS == 3 @@ -167,7 +171,7 @@ static inline void purge_tlb_entries(struct mm_struct *mm, unsigned long addr) #define _PAGE_NO_CACHE_BIT 24 /* (0x080) Uncached Page (U bit) */ #define _PAGE_ACCESSED_BIT 23 /* (0x100) Software: Page Accessed */ #define _PAGE_PRESENT_BIT 22 /* (0x200) Software: translation valid */ -/* bit 21 was formerly the FLUSH bit but is now unused */ +#define _PAGE_HPAGE_BIT 21 /* (0x400) Software: Huge Page */ #define _PAGE_USER_BIT 20 /* (0x800) Software: User accessible page */ /* N.B. The bits are defined in terms of a 32 bit word above, so the */ @@ -194,6 +198,7 @@ static inline void purge_tlb_entries(struct mm_struct *mm, unsigned long addr) #define _PAGE_NO_CACHE (1 << xlate_pabit(_PAGE_NO_CACHE_BIT)) #define _PAGE_ACCESSED (1 << xlate_pabit(_PAGE_ACCESSED_BIT)) #define _PAGE_PRESENT (1 << xlate_pabit(_PAGE_PRESENT_BIT)) +#define _PAGE_HUGE (1 << xlate_pabit(_PAGE_HPAGE_BIT)) #define _PAGE_USER (1 << xlate_pabit(_PAGE_USER_BIT)) #define _PAGE_TABLE (_PAGE_PRESENT | _PAGE_READ | _PAGE_WRITE | _PAGE_DIRTY | _PAGE_ACCESSED) @@ -217,7 +222,7 @@ static inline void purge_tlb_entries(struct mm_struct *mm, unsigned long addr) #define PxD_FLAG_VALID (1 << xlate_pabit(_PxD_VALID_BIT)) #define PxD_FLAG_MASK (0xf) #define PxD_FLAG_SHIFT (4) -#define PxD_VALUE_SHIFT (8) /* (PAGE_SHIFT-PxD_FLAG_SHIFT) */ +#define PxD_VALUE_SHIFT (PFN_PTE_SHIFT-PxD_FLAG_SHIFT) #ifndef __ASSEMBLY__ @@ -363,6 +368,19 @@ static inline pte_t pte_mkwrite(pte_t pte) { pte_val(pte) |= _PAGE_WRITE; return static inline pte_t pte_mkspecial(pte_t pte) { return pte; } /* + * Huge pte definitions. + */ +#ifdef CONFIG_HUGETLB_PAGE +#define pte_huge(pte) (pte_val(pte) & _PAGE_HUGE) +#define pte_mkhuge(pte) (__pte(pte_val(pte) | \ + (parisc_requires_coherency() ? 0 : _PAGE_HUGE))) +#else +#define pte_huge(pte) (0) +#define pte_mkhuge(pte) (pte) +#endif + + +/* * Conversion functions: convert a page and protection to a page entry, * and a page entry and page directory to the page they refer to. */ @@ -410,8 +428,9 @@ static inline pte_t pte_modify(pte_t pte, pgprot_t newprot) /* Find an entry in the second-level page table.. */ #if CONFIG_PGTABLE_LEVELS == 3 +#define pmd_index(addr) (((addr) >> PMD_SHIFT) & (PTRS_PER_PMD - 1)) #define pmd_offset(dir,address) \ -((pmd_t *) pgd_page_vaddr(*(dir)) + (((address)>>PMD_SHIFT) & (PTRS_PER_PMD-1))) +((pmd_t *) pgd_page_vaddr(*(dir)) + pmd_index(address)) #else #define pmd_offset(dir,addr) ((pmd_t *) dir) #endif diff --git a/arch/parisc/include/asm/processor.h b/arch/parisc/include/asm/processor.h index 54adb60c0a42..7e759ecb1343 100644 --- a/arch/parisc/include/asm/processor.h +++ b/arch/parisc/include/asm/processor.h @@ -192,33 +192,6 @@ void show_trace(struct task_struct *task, unsigned long *stack); */ typedef unsigned int elf_caddr_t; -#define start_thread_som(regs, new_pc, new_sp) do { \ - unsigned long *sp = (unsigned long *)new_sp; \ - __u32 spaceid = (__u32)current->mm->context; \ - unsigned long pc = (unsigned long)new_pc; \ - /* offset pc for priv. level */ \ - pc |= 3; \ - \ - regs->iasq[0] = spaceid; \ - regs->iasq[1] = spaceid; \ - regs->iaoq[0] = pc; \ - regs->iaoq[1] = pc + 4; \ - regs->sr[2] = LINUX_GATEWAY_SPACE; \ - regs->sr[3] = 0xffff; \ - regs->sr[4] = spaceid; \ - regs->sr[5] = spaceid; \ - regs->sr[6] = spaceid; \ - regs->sr[7] = spaceid; \ - regs->gr[ 0] = USER_PSW; \ - regs->gr[30] = ((new_sp)+63)&~63; \ - regs->gr[31] = pc; \ - \ - get_user(regs->gr[26],&sp[0]); \ - get_user(regs->gr[25],&sp[-1]); \ - get_user(regs->gr[24],&sp[-2]); \ - get_user(regs->gr[23],&sp[-3]); \ -} while(0) - /* The ELF abi wants things done a "wee bit" differently than * som does. Supporting this behavior here avoids * having our own version of create_elf_tables. diff --git a/arch/parisc/include/uapi/asm/mman.h b/arch/parisc/include/uapi/asm/mman.h index ecc3ae1ca28e..dd4d1876a020 100644 --- a/arch/parisc/include/uapi/asm/mman.h +++ b/arch/parisc/include/uapi/asm/mman.h @@ -49,16 +49,6 @@ #define MADV_DONTFORK 10 /* don't inherit across fork */ #define MADV_DOFORK 11 /* do inherit across fork */ -/* The range 12-64 is reserved for page size specification. */ -#define MADV_4K_PAGES 12 /* Use 4K pages */ -#define MADV_16K_PAGES 14 /* Use 16K pages */ -#define MADV_64K_PAGES 16 /* Use 64K pages */ -#define MADV_256K_PAGES 18 /* Use 256K pages */ -#define MADV_1M_PAGES 20 /* Use 1 Megabyte pages */ -#define MADV_4M_PAGES 22 /* Use 4 Megabyte pages */ -#define MADV_16M_PAGES 24 /* Use 16 Megabyte pages */ -#define MADV_64M_PAGES 26 /* Use 64 Megabyte pages */ - #define MADV_MERGEABLE 65 /* KSM may merge identical pages */ #define MADV_UNMERGEABLE 66 /* KSM may not merge identical pages */ diff --git a/arch/parisc/include/uapi/asm/unistd.h b/arch/parisc/include/uapi/asm/unistd.h index 33170384d3ac..35bdccbb2036 100644 --- a/arch/parisc/include/uapi/asm/unistd.h +++ b/arch/parisc/include/uapi/asm/unistd.h @@ -360,8 +360,9 @@ #define __NR_execveat (__NR_Linux + 342) #define __NR_membarrier (__NR_Linux + 343) #define __NR_userfaultfd (__NR_Linux + 344) +#define __NR_mlock2 (__NR_Linux + 345) -#define __NR_Linux_syscalls (__NR_userfaultfd + 1) +#define __NR_Linux_syscalls (__NR_mlock2 + 1) #define __IGNORE_select /* newselect */ diff --git a/arch/parisc/kernel/asm-offsets.c b/arch/parisc/kernel/asm-offsets.c index 59001cea13f9..d2f62570a7b1 100644 --- a/arch/parisc/kernel/asm-offsets.c +++ b/arch/parisc/kernel/asm-offsets.c @@ -290,6 +290,14 @@ int main(void) DEFINE(ASM_PFN_PTE_SHIFT, PFN_PTE_SHIFT); DEFINE(ASM_PT_INITIAL, PT_INITIAL); BLANK(); + /* HUGEPAGE_SIZE is only used in vmlinux.lds.S to align kernel text + * and kernel data on physical huge pages */ +#ifdef CONFIG_HUGETLB_PAGE + DEFINE(HUGEPAGE_SIZE, 1UL << REAL_HPAGE_SHIFT); +#else + DEFINE(HUGEPAGE_SIZE, PAGE_SIZE); +#endif + BLANK(); DEFINE(EXCDATA_IP, offsetof(struct exception_data, fault_ip)); DEFINE(EXCDATA_SPACE, offsetof(struct exception_data, fault_space)); DEFINE(EXCDATA_ADDR, offsetof(struct exception_data, fault_addr)); diff --git a/arch/parisc/kernel/entry.S b/arch/parisc/kernel/entry.S index c5ef4081b01d..623496c11756 100644 --- a/arch/parisc/kernel/entry.S +++ b/arch/parisc/kernel/entry.S @@ -502,21 +502,38 @@ STREG \pte,0(\ptp) .endm + /* We have (depending on the page size): + * - 38 to 52-bit Physical Page Number + * - 12 to 26-bit page offset + */ /* bitshift difference between a PFN (based on kernel's PAGE_SIZE) * to a CPU TLB 4k PFN (4k => 12 bits to shift) */ - #define PAGE_ADD_SHIFT (PAGE_SHIFT-12) + #define PAGE_ADD_SHIFT (PAGE_SHIFT-12) + #define PAGE_ADD_HUGE_SHIFT (REAL_HPAGE_SHIFT-12) /* Drop prot bits and convert to page addr for iitlbt and idtlbt */ - .macro convert_for_tlb_insert20 pte + .macro convert_for_tlb_insert20 pte,tmp +#ifdef CONFIG_HUGETLB_PAGE + copy \pte,\tmp + extrd,u \tmp,(63-ASM_PFN_PTE_SHIFT)+(63-58)+PAGE_ADD_SHIFT,\ + 64-PAGE_SHIFT-PAGE_ADD_SHIFT,\pte + + depdi _PAGE_SIZE_ENCODING_DEFAULT,63,\ + (63-58)+PAGE_ADD_SHIFT,\pte + extrd,u,*= \tmp,_PAGE_HPAGE_BIT+32,1,%r0 + depdi _HUGE_PAGE_SIZE_ENCODING_DEFAULT,63,\ + (63-58)+PAGE_ADD_HUGE_SHIFT,\pte +#else /* Huge pages disabled */ extrd,u \pte,(63-ASM_PFN_PTE_SHIFT)+(63-58)+PAGE_ADD_SHIFT,\ 64-PAGE_SHIFT-PAGE_ADD_SHIFT,\pte depdi _PAGE_SIZE_ENCODING_DEFAULT,63,\ (63-58)+PAGE_ADD_SHIFT,\pte +#endif .endm /* Convert the pte and prot to tlb insertion values. How * this happens is quite subtle, read below */ - .macro make_insert_tlb spc,pte,prot + .macro make_insert_tlb spc,pte,prot,tmp space_to_prot \spc \prot /* create prot id from space */ /* The following is the real subtlety. This is depositing * T <-> _PAGE_REFTRAP @@ -553,7 +570,7 @@ depdi 1,12,1,\prot /* Drop prot bits and convert to page addr for iitlbt and idtlbt */ - convert_for_tlb_insert20 \pte + convert_for_tlb_insert20 \pte \tmp .endm /* Identical macro to make_insert_tlb above, except it @@ -646,17 +663,12 @@ /* - * Align fault_vector_20 on 4K boundary so that both - * fault_vector_11 and fault_vector_20 are on the - * same page. This is only necessary as long as we - * write protect the kernel text, which we may stop - * doing once we use large page translations to cover - * the static part of the kernel address space. + * Fault_vectors are architecturally required to be aligned on a 2K + * boundary */ .text - - .align 4096 + .align 2048 ENTRY(fault_vector_20) /* First vector is invalid (0) */ @@ -1147,7 +1159,7 @@ dtlb_miss_20w: tlb_lock spc,ptp,pte,t0,t1,dtlb_check_alias_20w update_accessed ptp,pte,t0,t1 - make_insert_tlb spc,pte,prot + make_insert_tlb spc,pte,prot,t1 idtlbt pte,prot @@ -1173,7 +1185,7 @@ nadtlb_miss_20w: tlb_lock spc,ptp,pte,t0,t1,nadtlb_check_alias_20w update_accessed ptp,pte,t0,t1 - make_insert_tlb spc,pte,prot + make_insert_tlb spc,pte,prot,t1 idtlbt pte,prot @@ -1267,7 +1279,7 @@ dtlb_miss_20: tlb_lock spc,ptp,pte,t0,t1,dtlb_check_alias_20 update_accessed ptp,pte,t0,t1 - make_insert_tlb spc,pte,prot + make_insert_tlb spc,pte,prot,t1 f_extend pte,t1 @@ -1295,7 +1307,7 @@ nadtlb_miss_20: tlb_lock spc,ptp,pte,t0,t1,nadtlb_check_alias_20 update_accessed ptp,pte,t0,t1 - make_insert_tlb spc,pte,prot + make_insert_tlb spc,pte,prot,t1 f_extend pte,t1 @@ -1404,7 +1416,7 @@ itlb_miss_20w: tlb_lock spc,ptp,pte,t0,t1,itlb_fault update_accessed ptp,pte,t0,t1 - make_insert_tlb spc,pte,prot + make_insert_tlb spc,pte,prot,t1 iitlbt pte,prot @@ -1428,7 +1440,7 @@ naitlb_miss_20w: tlb_lock spc,ptp,pte,t0,t1,naitlb_check_alias_20w update_accessed ptp,pte,t0,t1 - make_insert_tlb spc,pte,prot + make_insert_tlb spc,pte,prot,t1 iitlbt pte,prot @@ -1514,7 +1526,7 @@ itlb_miss_20: tlb_lock spc,ptp,pte,t0,t1,itlb_fault update_accessed ptp,pte,t0,t1 - make_insert_tlb spc,pte,prot + make_insert_tlb spc,pte,prot,t1 f_extend pte,t1 @@ -1534,7 +1546,7 @@ naitlb_miss_20: tlb_lock spc,ptp,pte,t0,t1,naitlb_check_alias_20 update_accessed ptp,pte,t0,t1 - make_insert_tlb spc,pte,prot + make_insert_tlb spc,pte,prot,t1 f_extend pte,t1 @@ -1566,7 +1578,7 @@ dbit_trap_20w: tlb_lock spc,ptp,pte,t0,t1,dbit_fault update_dirty ptp,pte,t1 - make_insert_tlb spc,pte,prot + make_insert_tlb spc,pte,prot,t1 idtlbt pte,prot @@ -1610,7 +1622,7 @@ dbit_trap_20: tlb_lock spc,ptp,pte,t0,t1,dbit_fault update_dirty ptp,pte,t1 - make_insert_tlb spc,pte,prot + make_insert_tlb spc,pte,prot,t1 f_extend pte,t1 diff --git a/arch/parisc/kernel/head.S b/arch/parisc/kernel/head.S index e7d64527aff9..75aa0db9f69e 100644 --- a/arch/parisc/kernel/head.S +++ b/arch/parisc/kernel/head.S @@ -69,7 +69,7 @@ $bss_loop: stw,ma %arg2,4(%r1) stw,ma %arg3,4(%r1) - /* Initialize startup VM. Just map first 8/16 MB of memory */ + /* Initialize startup VM. Just map first 16/32 MB of memory */ load32 PA(swapper_pg_dir),%r4 mtctl %r4,%cr24 /* Initialize kernel root pointer */ mtctl %r4,%cr25 /* Initialize user root pointer */ @@ -107,7 +107,7 @@ $bss_loop: /* Now initialize the PTEs themselves. We use RWX for * everything ... it will get remapped correctly later */ ldo 0+_PAGE_KERNEL_RWX(%r0),%r3 /* Hardwired 0 phys addr start */ - ldi (1<<(KERNEL_INITIAL_ORDER-PAGE_SHIFT)),%r11 /* PFN count */ + load32 (1<<(KERNEL_INITIAL_ORDER-PAGE_SHIFT)),%r11 /* PFN count */ load32 PA(pg0),%r1 $pgt_fill_loop: diff --git a/arch/parisc/kernel/pci.c b/arch/parisc/kernel/pci.c index 64f2764a8cef..c99f3dde455c 100644 --- a/arch/parisc/kernel/pci.c +++ b/arch/parisc/kernel/pci.c @@ -171,24 +171,6 @@ void pcibios_set_master(struct pci_dev *dev) } -void __init pcibios_init_bus(struct pci_bus *bus) -{ - struct pci_dev *dev = bus->self; - unsigned short bridge_ctl; - - /* We deal only with pci controllers and pci-pci bridges. */ - if (!dev || (dev->class >> 8) != PCI_CLASS_BRIDGE_PCI) - return; - - /* PCI-PCI bridge - set the cache line and default latency - (32) for primary and secondary buses. */ - pci_write_config_byte(dev, PCI_SEC_LATENCY_TIMER, 32); - - pci_read_config_word(dev, PCI_BRIDGE_CONTROL, &bridge_ctl); - bridge_ctl |= PCI_BRIDGE_CTL_PARITY | PCI_BRIDGE_CTL_SERR; - pci_write_config_word(dev, PCI_BRIDGE_CONTROL, bridge_ctl); -} - /* * pcibios align resources() is called every time generic PCI code * wants to generate a new address. The process of looking for diff --git a/arch/parisc/kernel/setup.c b/arch/parisc/kernel/setup.c index 72a3c658ad7b..f7ea626e29c9 100644 --- a/arch/parisc/kernel/setup.c +++ b/arch/parisc/kernel/setup.c @@ -130,7 +130,16 @@ void __init setup_arch(char **cmdline_p) printk(KERN_INFO "The 32-bit Kernel has started...\n"); #endif - printk(KERN_INFO "Default page size is %dKB.\n", (int)(PAGE_SIZE / 1024)); + printk(KERN_INFO "Kernel default page size is %d KB. Huge pages ", + (int)(PAGE_SIZE / 1024)); +#ifdef CONFIG_HUGETLB_PAGE + printk(KERN_CONT "enabled with %d MB physical and %d MB virtual size", + 1 << (REAL_HPAGE_SHIFT - 20), 1 << (HPAGE_SHIFT - 20)); +#else + printk(KERN_CONT "disabled"); +#endif + printk(KERN_CONT ".\n"); + pdc_console_init(); @@ -377,6 +386,7 @@ arch_initcall(parisc_init); void start_parisc(void) { extern void start_kernel(void); + extern void early_trap_init(void); int ret, cpunum; struct pdc_coproc_cfg coproc_cfg; @@ -397,6 +407,8 @@ void start_parisc(void) panic("must have an fpu to boot linux"); } + early_trap_init(); /* initialize checksum of fault_vector */ + start_kernel(); // not reached } diff --git a/arch/parisc/kernel/signal.c b/arch/parisc/kernel/signal.c index dc1ea796fd60..2264f68f3c2f 100644 --- a/arch/parisc/kernel/signal.c +++ b/arch/parisc/kernel/signal.c @@ -435,6 +435,55 @@ handle_signal(struct ksignal *ksig, struct pt_regs *regs, int in_syscall) regs->gr[28]); } +/* + * Check how the syscall number gets loaded into %r20 within + * the delay branch in userspace and adjust as needed. + */ + +static void check_syscallno_in_delay_branch(struct pt_regs *regs) +{ + u32 opcode, source_reg; + u32 __user *uaddr; + int err; + + /* Usually we don't have to restore %r20 (the system call number) + * because it gets loaded in the delay slot of the branch external + * instruction via the ldi instruction. + * In some cases a register-to-register copy instruction might have + * been used instead, in which case we need to copy the syscall + * number into the source register before returning to userspace. + */ + + /* A syscall is just a branch, so all we have to do is fiddle the + * return pointer so that the ble instruction gets executed again. + */ + regs->gr[31] -= 8; /* delayed branching */ + + /* Get assembler opcode of code in delay branch */ + uaddr = (unsigned int *) ((regs->gr[31] & ~3) + 4); + err = get_user(opcode, uaddr); + if (err) + return; + + /* Check if delay branch uses "ldi int,%r20" */ + if ((opcode & 0xffff0000) == 0x34140000) + return; /* everything ok, just return */ + + /* Check if delay branch uses "nop" */ + if (opcode == INSN_NOP) + return; + + /* Check if delay branch uses "copy %rX,%r20" */ + if ((opcode & 0xffe0ffff) == 0x08000254) { + source_reg = (opcode >> 16) & 31; + regs->gr[source_reg] = regs->gr[20]; + return; + } + + pr_warn("syscall restart: %s (pid %d): unexpected opcode 0x%08x\n", + current->comm, task_pid_nr(current), opcode); +} + static inline void syscall_restart(struct pt_regs *regs, struct k_sigaction *ka) { @@ -457,10 +506,7 @@ syscall_restart(struct pt_regs *regs, struct k_sigaction *ka) } /* fallthrough */ case -ERESTARTNOINTR: - /* A syscall is just a branch, so all - * we have to do is fiddle the return pointer. - */ - regs->gr[31] -= 8; /* delayed branching */ + check_syscallno_in_delay_branch(regs); break; } } @@ -510,15 +556,9 @@ insert_restart_trampoline(struct pt_regs *regs) } case -ERESTARTNOHAND: case -ERESTARTSYS: - case -ERESTARTNOINTR: { - /* Hooray for delayed branching. We don't - * have to restore %r20 (the system call - * number) because it gets loaded in the delay - * slot of the branch external instruction. - */ - regs->gr[31] -= 8; + case -ERESTARTNOINTR: + check_syscallno_in_delay_branch(regs); return; - } default: break; } diff --git a/arch/parisc/kernel/syscall.S b/arch/parisc/kernel/syscall.S index 0b8d26d3ba43..3fbd7252a4b2 100644 --- a/arch/parisc/kernel/syscall.S +++ b/arch/parisc/kernel/syscall.S @@ -369,7 +369,7 @@ tracesys_exit: ldo -16(%r30),%r29 /* Reference param save area */ #endif ldo TASK_REGS(%r1),%r26 - bl do_syscall_trace_exit,%r2 + BL do_syscall_trace_exit,%r2 STREG %r28,TASK_PT_GR28(%r1) /* save return value now */ ldo -THREAD_SZ_ALGN-FRAME_SIZE(%r30),%r1 /* get task ptr */ LDREG TI_TASK(%r1), %r1 @@ -390,7 +390,7 @@ tracesys_sigexit: #ifdef CONFIG_64BIT ldo -16(%r30),%r29 /* Reference param save area */ #endif - bl do_syscall_trace_exit,%r2 + BL do_syscall_trace_exit,%r2 ldo TASK_REGS(%r1),%r26 ldil L%syscall_exit_rfi,%r1 diff --git a/arch/parisc/kernel/syscall_table.S b/arch/parisc/kernel/syscall_table.S index 78c3ef8c348d..d4ffcfbc9885 100644 --- a/arch/parisc/kernel/syscall_table.S +++ b/arch/parisc/kernel/syscall_table.S @@ -440,6 +440,7 @@ ENTRY_COMP(execveat) ENTRY_SAME(membarrier) ENTRY_SAME(userfaultfd) + ENTRY_SAME(mlock2) /* 345 */ .ifne (. - 90b) - (__NR_Linux_syscalls * (91b - 90b)) diff --git a/arch/parisc/kernel/traps.c b/arch/parisc/kernel/traps.c index b99b39f1da02..553b09855cfd 100644 --- a/arch/parisc/kernel/traps.c +++ b/arch/parisc/kernel/traps.c @@ -807,7 +807,7 @@ void notrace handle_interruption(int code, struct pt_regs *regs) } -int __init check_ivt(void *iva) +void __init initialize_ivt(const void *iva) { extern u32 os_hpmc_size; extern const u32 os_hpmc[]; @@ -818,8 +818,8 @@ int __init check_ivt(void *iva) u32 *hpmcp; u32 length; - if (strcmp((char *)iva, "cows can fly")) - return -1; + if (strcmp((const char *)iva, "cows can fly")) + panic("IVT invalid"); ivap = (u32 *)iva; @@ -839,28 +839,23 @@ int __init check_ivt(void *iva) check += ivap[i]; ivap[5] = -check; - - return 0; } -#ifndef CONFIG_64BIT -extern const void fault_vector_11; -#endif -extern const void fault_vector_20; -void __init trap_init(void) +/* early_trap_init() is called before we set up kernel mappings and + * write-protect the kernel */ +void __init early_trap_init(void) { - void *iva; + extern const void fault_vector_20; - if (boot_cpu_data.cpu_type >= pcxu) - iva = (void *) &fault_vector_20; - else -#ifdef CONFIG_64BIT - panic("Can't boot 64-bit OS on PA1.1 processor!"); -#else - iva = (void *) &fault_vector_11; +#ifndef CONFIG_64BIT + extern const void fault_vector_11; + initialize_ivt(&fault_vector_11); #endif - if (check_ivt(iva)) - panic("IVT invalid"); + initialize_ivt(&fault_vector_20); +} + +void __init trap_init(void) +{ } diff --git a/arch/parisc/kernel/vmlinux.lds.S b/arch/parisc/kernel/vmlinux.lds.S index 0dacc5ca555a..308f29081d46 100644 --- a/arch/parisc/kernel/vmlinux.lds.S +++ b/arch/parisc/kernel/vmlinux.lds.S @@ -60,7 +60,7 @@ SECTIONS EXIT_DATA } PERCPU_SECTION(8) - . = ALIGN(PAGE_SIZE); + . = ALIGN(HUGEPAGE_SIZE); __init_end = .; /* freed after init ends here */ @@ -116,7 +116,7 @@ SECTIONS * that we can properly leave these * as writable */ - . = ALIGN(PAGE_SIZE); + . = ALIGN(HUGEPAGE_SIZE); data_start = .; EXCEPTION_TABLE(8) @@ -135,8 +135,11 @@ SECTIONS _edata = .; /* BSS */ - BSS_SECTION(PAGE_SIZE, PAGE_SIZE, 8) + BSS_SECTION(PAGE_SIZE, PAGE_SIZE, PAGE_SIZE) + + /* bootmap is allocated in setup_bootmem() directly behind bss. */ + . = ALIGN(HUGEPAGE_SIZE); _end = . ; STABS_DEBUG diff --git a/arch/parisc/mm/Makefile b/arch/parisc/mm/Makefile index 758ceefb373a..134393de69d2 100644 --- a/arch/parisc/mm/Makefile +++ b/arch/parisc/mm/Makefile @@ -3,3 +3,4 @@ # obj-y := init.o fault.o ioremap.o +obj-$(CONFIG_HUGETLB_PAGE) += hugetlbpage.o diff --git a/arch/parisc/mm/hugetlbpage.c b/arch/parisc/mm/hugetlbpage.c new file mode 100644 index 000000000000..f6fdc77a72bd --- /dev/null +++ b/arch/parisc/mm/hugetlbpage.c @@ -0,0 +1,161 @@ +/* + * PARISC64 Huge TLB page support. + * + * This parisc implementation is heavily based on the SPARC and x86 code. + * + * Copyright (C) 2015 Helge Deller <deller@gmx.de> + */ + +#include <linux/fs.h> +#include <linux/mm.h> +#include <linux/hugetlb.h> +#include <linux/pagemap.h> +#include <linux/sysctl.h> + +#include <asm/mman.h> +#include <asm/pgalloc.h> +#include <asm/tlb.h> +#include <asm/tlbflush.h> +#include <asm/cacheflush.h> +#include <asm/mmu_context.h> + + +unsigned long +hugetlb_get_unmapped_area(struct file *file, unsigned long addr, + unsigned long len, unsigned long pgoff, unsigned long flags) +{ + struct hstate *h = hstate_file(file); + + if (len & ~huge_page_mask(h)) + return -EINVAL; + if (len > TASK_SIZE) + return -ENOMEM; + + if (flags & MAP_FIXED) + if (prepare_hugepage_range(file, addr, len)) + return -EINVAL; + + if (addr) + addr = ALIGN(addr, huge_page_size(h)); + + /* we need to make sure the colouring is OK */ + return arch_get_unmapped_area(file, addr, len, pgoff, flags); +} + + +pte_t *huge_pte_alloc(struct mm_struct *mm, + unsigned long addr, unsigned long sz) +{ + pgd_t *pgd; + pud_t *pud; + pmd_t *pmd; + pte_t *pte = NULL; + + /* We must align the address, because our caller will run + * set_huge_pte_at() on whatever we return, which writes out + * all of the sub-ptes for the hugepage range. So we have + * to give it the first such sub-pte. + */ + addr &= HPAGE_MASK; + + pgd = pgd_offset(mm, addr); + pud = pud_alloc(mm, pgd, addr); + if (pud) { + pmd = pmd_alloc(mm, pud, addr); + if (pmd) + pte = pte_alloc_map(mm, NULL, pmd, addr); + } + return pte; +} + +pte_t *huge_pte_offset(struct mm_struct *mm, unsigned long addr) +{ + pgd_t *pgd; + pud_t *pud; + pmd_t *pmd; + pte_t *pte = NULL; + + addr &= HPAGE_MASK; + + pgd = pgd_offset(mm, addr); + if (!pgd_none(*pgd)) { + pud = pud_offset(pgd, addr); + if (!pud_none(*pud)) { + pmd = pmd_offset(pud, addr); + if (!pmd_none(*pmd)) + pte = pte_offset_map(pmd, addr); + } + } + return pte; +} + +/* Purge data and instruction TLB entries. Must be called holding + * the pa_tlb_lock. The TLB purge instructions are slow on SMP + * machines since the purge must be broadcast to all CPUs. + */ +static inline void purge_tlb_entries_huge(struct mm_struct *mm, unsigned long addr) +{ + int i; + + /* We may use multiple physical huge pages (e.g. 2x1 MB) to emulate + * Linux standard huge pages (e.g. 2 MB) */ + BUILD_BUG_ON(REAL_HPAGE_SHIFT > HPAGE_SHIFT); + + addr &= HPAGE_MASK; + addr |= _HUGE_PAGE_SIZE_ENCODING_DEFAULT; + + for (i = 0; i < (1 << (HPAGE_SHIFT-REAL_HPAGE_SHIFT)); i++) { + mtsp(mm->context, 1); + pdtlb(addr); + if (unlikely(split_tlb)) + pitlb(addr); + addr += (1UL << REAL_HPAGE_SHIFT); + } +} + +void set_huge_pte_at(struct mm_struct *mm, unsigned long addr, + pte_t *ptep, pte_t entry) +{ + unsigned long addr_start; + int i; + + addr &= HPAGE_MASK; + addr_start = addr; + + for (i = 0; i < (1 << HUGETLB_PAGE_ORDER); i++) { + /* Directly write pte entry. We could call set_pte_at(mm, addr, ptep, entry) + * instead, but then we get double locking on pa_tlb_lock. */ + *ptep = entry; + ptep++; + + /* Drop the PAGE_SIZE/non-huge tlb entry */ + purge_tlb_entries(mm, addr); + + addr += PAGE_SIZE; + pte_val(entry) += PAGE_SIZE; + } + + purge_tlb_entries_huge(mm, addr_start); +} + + +pte_t huge_ptep_get_and_clear(struct mm_struct *mm, unsigned long addr, + pte_t *ptep) +{ + pte_t entry; + + entry = *ptep; + set_huge_pte_at(mm, addr, ptep, __pte(0)); + + return entry; +} + +int pmd_huge(pmd_t pmd) +{ + return 0; +} + +int pud_huge(pud_t pud) +{ + return 0; +} diff --git a/arch/parisc/mm/init.c b/arch/parisc/mm/init.c index c5fec4890fdf..1b366c477687 100644 --- a/arch/parisc/mm/init.c +++ b/arch/parisc/mm/init.c @@ -409,15 +409,11 @@ static void __init map_pages(unsigned long start_vaddr, unsigned long vaddr; unsigned long ro_start; unsigned long ro_end; - unsigned long fv_addr; - unsigned long gw_addr; - extern const unsigned long fault_vector_20; - extern void * const linux_gateway_page; + unsigned long kernel_end; ro_start = __pa((unsigned long)_text); ro_end = __pa((unsigned long)&data_start); - fv_addr = __pa((unsigned long)&fault_vector_20) & PAGE_MASK; - gw_addr = __pa((unsigned long)&linux_gateway_page) & PAGE_MASK; + kernel_end = __pa((unsigned long)&_end); end_paddr = start_paddr + size; @@ -475,24 +471,25 @@ static void __init map_pages(unsigned long start_vaddr, for (tmp2 = start_pte; tmp2 < PTRS_PER_PTE; tmp2++, pg_table++) { pte_t pte; - /* - * Map the fault vector writable so we can - * write the HPMC checksum. - */ if (force) pte = __mk_pte(address, pgprot); - else if (parisc_text_address(vaddr) && - address != fv_addr) + else if (parisc_text_address(vaddr)) { pte = __mk_pte(address, PAGE_KERNEL_EXEC); + if (address >= ro_start && address < kernel_end) + pte = pte_mkhuge(pte); + } else #if defined(CONFIG_PARISC_PAGE_SIZE_4KB) - if (address >= ro_start && address < ro_end - && address != fv_addr - && address != gw_addr) - pte = __mk_pte(address, PAGE_KERNEL_RO); - else + if (address >= ro_start && address < ro_end) { + pte = __mk_pte(address, PAGE_KERNEL_EXEC); + pte = pte_mkhuge(pte); + } else #endif + { pte = __mk_pte(address, pgprot); + if (address >= ro_start && address < kernel_end) + pte = pte_mkhuge(pte); + } if (address >= end_paddr) { if (force) @@ -536,15 +533,12 @@ void free_initmem(void) /* force the kernel to see the new TLB entries */ __flush_tlb_range(0, init_begin, init_end); - /* Attempt to catch anyone trying to execute code here - * by filling the page with BRK insns. - */ - memset((void *)init_begin, 0x00, init_end - init_begin); + /* finally dump all the instructions which were cached, since the * pages are no-longer executable */ flush_icache_range(init_begin, init_end); - free_initmem_default(-1); + free_initmem_default(POISON_FREE_INITMEM); /* set up a new led state on systems shipped LED State panel */ pdc_chassis_send_status(PDC_CHASSIS_DIRECT_BCOMPLETE); @@ -728,8 +722,8 @@ static void __init pagetable_init(void) unsigned long size; start_paddr = pmem_ranges[range].start_pfn << PAGE_SHIFT; - end_paddr = start_paddr + (pmem_ranges[range].pages << PAGE_SHIFT); size = pmem_ranges[range].pages << PAGE_SHIFT; + end_paddr = start_paddr + size; map_pages((unsigned long)__va(start_paddr), start_paddr, size, PAGE_KERNEL, 0); diff --git a/arch/powerpc/boot/dts/sbc8641d.dts b/arch/powerpc/boot/dts/sbc8641d.dts index 631ede72e226..68f0ed7626bd 100644 --- a/arch/powerpc/boot/dts/sbc8641d.dts +++ b/arch/powerpc/boot/dts/sbc8641d.dts @@ -227,23 +227,15 @@ reg = <0x520 0x20>; phy0: ethernet-phy@1f { - interrupt-parent = <&mpic>; - interrupts = <10 1>; reg = <0x1f>; }; phy1: ethernet-phy@0 { - interrupt-parent = <&mpic>; - interrupts = <10 1>; reg = <0>; }; phy2: ethernet-phy@1 { - interrupt-parent = <&mpic>; - interrupts = <10 1>; reg = <1>; }; phy3: ethernet-phy@2 { - interrupt-parent = <&mpic>; - interrupts = <10 1>; reg = <2>; }; tbi0: tbi-phy@11 { diff --git a/arch/powerpc/include/asm/barrier.h b/arch/powerpc/include/asm/barrier.h index 0eca6efc0631..a7af5fb7b914 100644 --- a/arch/powerpc/include/asm/barrier.h +++ b/arch/powerpc/include/asm/barrier.h @@ -34,7 +34,7 @@ #define rmb() __asm__ __volatile__ ("sync" : : : "memory") #define wmb() __asm__ __volatile__ ("sync" : : : "memory") -#define smp_store_mb(var, value) do { WRITE_ONCE(var, value); mb(); } while (0) +#define smp_store_mb(var, value) do { WRITE_ONCE(var, value); smp_mb(); } while (0) #ifdef __SUBARCH_HAS_LWSYNC # define SMPWMB LWSYNC diff --git a/arch/powerpc/include/asm/reg.h b/arch/powerpc/include/asm/reg.h index a908ada8e0a5..2220f7a60def 100644 --- a/arch/powerpc/include/asm/reg.h +++ b/arch/powerpc/include/asm/reg.h @@ -108,6 +108,7 @@ #define MSR_TS_T __MASK(MSR_TS_T_LG) /* Transaction Transactional */ #define MSR_TS_MASK (MSR_TS_T | MSR_TS_S) /* Transaction State bits */ #define MSR_TM_ACTIVE(x) (((x) & MSR_TS_MASK) != 0) /* Transaction active? */ +#define MSR_TM_RESV(x) (((x) & MSR_TS_MASK) == MSR_TS_MASK) /* Reserved */ #define MSR_TM_TRANSACTIONAL(x) (((x) & MSR_TS_MASK) == MSR_TS_T) #define MSR_TM_SUSPENDED(x) (((x) & MSR_TS_MASK) == MSR_TS_S) diff --git a/arch/powerpc/include/asm/systbl.h b/arch/powerpc/include/asm/systbl.h index c9e26cb264f4..5654ece02c0d 100644 --- a/arch/powerpc/include/asm/systbl.h +++ b/arch/powerpc/include/asm/systbl.h @@ -370,15 +370,16 @@ COMPAT_SYS(execveat) PPC64ONLY(switch_endian) SYSCALL_SPU(userfaultfd) SYSCALL_SPU(membarrier) -SYSCALL(semop) -SYSCALL(semget) -COMPAT_SYS(semctl) -COMPAT_SYS(semtimedop) -COMPAT_SYS(msgsnd) -COMPAT_SYS(msgrcv) -SYSCALL(msgget) -COMPAT_SYS(msgctl) -COMPAT_SYS(shmat) -SYSCALL(shmdt) -SYSCALL(shmget) -COMPAT_SYS(shmctl) +SYSCALL(ni_syscall) +SYSCALL(ni_syscall) +SYSCALL(ni_syscall) +SYSCALL(ni_syscall) +SYSCALL(ni_syscall) +SYSCALL(ni_syscall) +SYSCALL(ni_syscall) +SYSCALL(ni_syscall) +SYSCALL(ni_syscall) +SYSCALL(ni_syscall) +SYSCALL(ni_syscall) +SYSCALL(ni_syscall) +SYSCALL(mlock2) diff --git a/arch/powerpc/include/asm/unistd.h b/arch/powerpc/include/asm/unistd.h index 6d8f8023ac27..4b6b8ace18e0 100644 --- a/arch/powerpc/include/asm/unistd.h +++ b/arch/powerpc/include/asm/unistd.h @@ -12,7 +12,7 @@ #include <uapi/asm/unistd.h> -#define __NR_syscalls 378 +#define __NR_syscalls 379 #define __NR__exit __NR_exit #define NR_syscalls __NR_syscalls diff --git a/arch/powerpc/include/uapi/asm/unistd.h b/arch/powerpc/include/uapi/asm/unistd.h index 81579e93c659..12a05652377a 100644 --- a/arch/powerpc/include/uapi/asm/unistd.h +++ b/arch/powerpc/include/uapi/asm/unistd.h @@ -388,17 +388,6 @@ #define __NR_switch_endian 363 #define __NR_userfaultfd 364 #define __NR_membarrier 365 -#define __NR_semop 366 -#define __NR_semget 367 -#define __NR_semctl 368 -#define __NR_semtimedop 369 -#define __NR_msgsnd 370 -#define __NR_msgrcv 371 -#define __NR_msgget 372 -#define __NR_msgctl 373 -#define __NR_shmat 374 -#define __NR_shmdt 375 -#define __NR_shmget 376 -#define __NR_shmctl 377 +#define __NR_mlock2 378 #endif /* _UAPI_ASM_POWERPC_UNISTD_H_ */ diff --git a/arch/powerpc/kernel/eeh_driver.c b/arch/powerpc/kernel/eeh_driver.c index 80dfe8965df9..8d14feb40f12 100644 --- a/arch/powerpc/kernel/eeh_driver.c +++ b/arch/powerpc/kernel/eeh_driver.c @@ -590,16 +590,10 @@ static int eeh_reset_device(struct eeh_pe *pe, struct pci_bus *bus) eeh_ops->configure_bridge(pe); eeh_pe_restore_bars(pe); - /* - * If it's PHB PE, the frozen state on all available PEs should have - * been cleared by the PHB reset. Otherwise, we unfreeze the PE and its - * child PEs because they might be in frozen state. - */ - if (!(pe->type & EEH_PE_PHB)) { - rc = eeh_clear_pe_frozen_state(pe, false); - if (rc) - return rc; - } + /* Clear frozen state */ + rc = eeh_clear_pe_frozen_state(pe, false); + if (rc) + return rc; /* Give the system 5 seconds to finish running the user-space * hotplug shutdown scripts, e.g. ifdown for ethernet. Yes, diff --git a/arch/powerpc/kernel/process.c b/arch/powerpc/kernel/process.c index 75b6676c1a0b..646bf4d222c1 100644 --- a/arch/powerpc/kernel/process.c +++ b/arch/powerpc/kernel/process.c @@ -551,6 +551,24 @@ static void tm_reclaim_thread(struct thread_struct *thr, msr_diff &= MSR_FP | MSR_VEC | MSR_VSX | MSR_FE0 | MSR_FE1; } + /* + * Use the current MSR TM suspended bit to track if we have + * checkpointed state outstanding. + * On signal delivery, we'd normally reclaim the checkpointed + * state to obtain stack pointer (see:get_tm_stackpointer()). + * This will then directly return to userspace without going + * through __switch_to(). However, if the stack frame is bad, + * we need to exit this thread which calls __switch_to() which + * will again attempt to reclaim the already saved tm state. + * Hence we need to check that we've not already reclaimed + * this state. + * We do this using the current MSR, rather tracking it in + * some specific thread_struct bit, as it has the additional + * benifit of checking for a potential TM bad thing exception. + */ + if (!MSR_TM_SUSPENDED(mfmsr())) + return; + tm_reclaim(thr, thr->regs->msr, cause); /* Having done the reclaim, we now have the checkpointed diff --git a/arch/powerpc/kernel/signal_32.c b/arch/powerpc/kernel/signal_32.c index 0dbee465af7a..ef7c24e84a62 100644 --- a/arch/powerpc/kernel/signal_32.c +++ b/arch/powerpc/kernel/signal_32.c @@ -875,6 +875,15 @@ static long restore_tm_user_regs(struct pt_regs *regs, return 1; #endif /* CONFIG_SPE */ + /* Get the top half of the MSR from the user context */ + if (__get_user(msr_hi, &tm_sr->mc_gregs[PT_MSR])) + return 1; + msr_hi <<= 32; + /* If TM bits are set to the reserved value, it's an invalid context */ + if (MSR_TM_RESV(msr_hi)) + return 1; + /* Pull in the MSR TM bits from the user context */ + regs->msr = (regs->msr & ~MSR_TS_MASK) | (msr_hi & MSR_TS_MASK); /* Now, recheckpoint. This loads up all of the checkpointed (older) * registers, including FP and V[S]Rs. After recheckpointing, the * transactional versions should be loaded. @@ -884,11 +893,6 @@ static long restore_tm_user_regs(struct pt_regs *regs, current->thread.tm_texasr |= TEXASR_FS; /* This loads the checkpointed FP/VEC state, if used */ tm_recheckpoint(¤t->thread, msr); - /* Get the top half of the MSR */ - if (__get_user(msr_hi, &tm_sr->mc_gregs[PT_MSR])) - return 1; - /* Pull in MSR TM from user context */ - regs->msr = (regs->msr & ~MSR_TS_MASK) | ((msr_hi<<32) & MSR_TS_MASK); /* This loads the speculative FP/VEC state, if used */ if (msr & MSR_FP) { diff --git a/arch/powerpc/kernel/signal_64.c b/arch/powerpc/kernel/signal_64.c index 20756dfb9f34..c676ecec0869 100644 --- a/arch/powerpc/kernel/signal_64.c +++ b/arch/powerpc/kernel/signal_64.c @@ -438,6 +438,10 @@ static long restore_tm_sigcontexts(struct pt_regs *regs, /* get MSR separately, transfer the LE bit if doing signal return */ err |= __get_user(msr, &sc->gp_regs[PT_MSR]); + /* Don't allow reserved mode. */ + if (MSR_TM_RESV(msr)) + return -EINVAL; + /* pull in MSR TM from user context */ regs->msr = (regs->msr & ~MSR_TS_MASK) | (msr & MSR_TS_MASK); diff --git a/arch/powerpc/kvm/book3s_hv.c b/arch/powerpc/kvm/book3s_hv.c index 54b45b73195f..a7352b59e6f9 100644 --- a/arch/powerpc/kvm/book3s_hv.c +++ b/arch/powerpc/kvm/book3s_hv.c @@ -224,6 +224,12 @@ static void kvmppc_core_vcpu_put_hv(struct kvm_vcpu *vcpu) static void kvmppc_set_msr_hv(struct kvm_vcpu *vcpu, u64 msr) { + /* + * Check for illegal transactional state bit combination + * and if we find it, force the TS field to a safe state. + */ + if ((msr & MSR_TS_MASK) == MSR_TS_MASK) + msr &= ~MSR_TS_MASK; vcpu->arch.shregs.msr = msr; kvmppc_end_cede(vcpu); } diff --git a/arch/powerpc/net/bpf_jit_comp.c b/arch/powerpc/net/bpf_jit_comp.c index 04782164ee67..2d66a8446198 100644 --- a/arch/powerpc/net/bpf_jit_comp.c +++ b/arch/powerpc/net/bpf_jit_comp.c @@ -78,18 +78,9 @@ static void bpf_jit_build_prologue(struct bpf_prog *fp, u32 *image, PPC_LI(r_X, 0); } - switch (filter[0].code) { - case BPF_RET | BPF_K: - case BPF_LD | BPF_W | BPF_LEN: - case BPF_LD | BPF_W | BPF_ABS: - case BPF_LD | BPF_H | BPF_ABS: - case BPF_LD | BPF_B | BPF_ABS: - /* first instruction sets A register (or is RET 'constant') */ - break; - default: - /* make sure we dont leak kernel information to user */ + /* make sure we dont leak kernel information to user */ + if (bpf_needs_clear_a(&filter[0])) PPC_LI(r_A, 0); - } } static void bpf_jit_build_epilogue(u32 *image, struct codegen_context *ctx) diff --git a/arch/powerpc/platforms/powernv/opal-irqchip.c b/arch/powerpc/platforms/powernv/opal-irqchip.c index 6ccfb6c1c707..e505223b4ec5 100644 --- a/arch/powerpc/platforms/powernv/opal-irqchip.c +++ b/arch/powerpc/platforms/powernv/opal-irqchip.c @@ -43,11 +43,34 @@ static unsigned int opal_irq_count; static unsigned int *opal_irqs; static void opal_handle_irq_work(struct irq_work *work); -static __be64 last_outstanding_events; +static u64 last_outstanding_events; static struct irq_work opal_event_irq_work = { .func = opal_handle_irq_work, }; +void opal_handle_events(uint64_t events) +{ + int virq, hwirq = 0; + u64 mask = opal_event_irqchip.mask; + + if (!in_irq() && (events & mask)) { + last_outstanding_events = events; + irq_work_queue(&opal_event_irq_work); + return; + } + + while (events & mask) { + hwirq = fls64(events) - 1; + if (BIT_ULL(hwirq) & mask) { + virq = irq_find_mapping(opal_event_irqchip.domain, + hwirq); + if (virq) + generic_handle_irq(virq); + } + events &= ~BIT_ULL(hwirq); + } +} + static void opal_event_mask(struct irq_data *d) { clear_bit(d->hwirq, &opal_event_irqchip.mask); @@ -55,9 +78,21 @@ static void opal_event_mask(struct irq_data *d) static void opal_event_unmask(struct irq_data *d) { + __be64 events; + set_bit(d->hwirq, &opal_event_irqchip.mask); - opal_poll_events(&last_outstanding_events); + opal_poll_events(&events); + last_outstanding_events = be64_to_cpu(events); + + /* + * We can't just handle the events now with opal_handle_events(). + * If we did we would deadlock when opal_event_unmask() is called from + * handle_level_irq() with the irq descriptor lock held, because + * calling opal_handle_events() would call generic_handle_irq() and + * then handle_level_irq() which would try to take the descriptor lock + * again. Instead queue the events for later. + */ if (last_outstanding_events & opal_event_irqchip.mask) /* Need to retrigger the interrupt */ irq_work_queue(&opal_event_irq_work); @@ -96,29 +131,6 @@ static int opal_event_map(struct irq_domain *d, unsigned int irq, return 0; } -void opal_handle_events(uint64_t events) -{ - int virq, hwirq = 0; - u64 mask = opal_event_irqchip.mask; - - if (!in_irq() && (events & mask)) { - last_outstanding_events = events; - irq_work_queue(&opal_event_irq_work); - return; - } - - while (events & mask) { - hwirq = fls64(events) - 1; - if (BIT_ULL(hwirq) & mask) { - virq = irq_find_mapping(opal_event_irqchip.domain, - hwirq); - if (virq) - generic_handle_irq(virq); - } - events &= ~BIT_ULL(hwirq); - } -} - static irqreturn_t opal_interrupt(int irq, void *data) { __be64 events; @@ -131,7 +143,7 @@ static irqreturn_t opal_interrupt(int irq, void *data) static void opal_handle_irq_work(struct irq_work *work) { - opal_handle_events(be64_to_cpu(last_outstanding_events)); + opal_handle_events(last_outstanding_events); } static int opal_event_match(struct irq_domain *h, struct device_node *node, diff --git a/arch/powerpc/platforms/powernv/opal.c b/arch/powerpc/platforms/powernv/opal.c index 4296d55e88f3..57cffb80bc36 100644 --- a/arch/powerpc/platforms/powernv/opal.c +++ b/arch/powerpc/platforms/powernv/opal.c @@ -278,7 +278,7 @@ static void opal_handle_message(void) /* Sanity check */ if (type >= OPAL_MSG_TYPE_MAX) { - pr_warning("%s: Unknown message type: %u\n", __func__, type); + pr_warn_once("%s: Unknown message type: %u\n", __func__, type); return; } opal_message_do_notify(type, (void *)&msg); diff --git a/arch/s390/include/asm/barrier.h b/arch/s390/include/asm/barrier.h index d68e11e0df5e..7ffd0b19135c 100644 --- a/arch/s390/include/asm/barrier.h +++ b/arch/s390/include/asm/barrier.h @@ -36,7 +36,7 @@ #define smp_mb__before_atomic() smp_mb() #define smp_mb__after_atomic() smp_mb() -#define smp_store_mb(var, value) do { WRITE_ONCE(var, value); mb(); } while (0) +#define smp_store_mb(var, value) do { WRITE_ONCE(var, value); smp_mb(); } while (0) #define smp_store_release(p, v) \ do { \ diff --git a/arch/s390/include/asm/cio.h b/arch/s390/include/asm/cio.h index 0c5d8ee657f0..d1e7b0a0feeb 100644 --- a/arch/s390/include/asm/cio.h +++ b/arch/s390/include/asm/cio.h @@ -312,6 +312,7 @@ extern void css_schedule_reprobe(void); extern void reipl_ccw_dev(struct ccw_dev_id *id); struct cio_iplinfo { + u8 ssid; u16 devno; int is_qdio; }; diff --git a/arch/s390/include/asm/elf.h b/arch/s390/include/asm/elf.h index 3ad48f22de78..bab6739a1154 100644 --- a/arch/s390/include/asm/elf.h +++ b/arch/s390/include/asm/elf.h @@ -206,9 +206,16 @@ do { \ } while (0) #endif /* CONFIG_COMPAT */ -extern unsigned long mmap_rnd_mask; - -#define STACK_RND_MASK (test_thread_flag(TIF_31BIT) ? 0x7ff : mmap_rnd_mask) +/* + * Cache aliasing on the latest machines calls for a mapping granularity + * of 512KB. For 64-bit processes use a 512KB alignment and a randomization + * of up to 1GB. For 31-bit processes the virtual address space is limited, + * use no alignment and limit the randomization to 8MB. + */ +#define BRK_RND_MASK (is_32bit_task() ? 0x7ffUL : 0x3ffffUL) +#define MMAP_RND_MASK (is_32bit_task() ? 0x7ffUL : 0x3ff80UL) +#define MMAP_ALIGN_MASK (is_32bit_task() ? 0 : 0x7fUL) +#define STACK_RND_MASK MMAP_RND_MASK #define ARCH_DLINFO \ do { \ diff --git a/arch/s390/include/asm/ipl.h b/arch/s390/include/asm/ipl.h index 39ae6a359747..86634e71b69f 100644 --- a/arch/s390/include/asm/ipl.h +++ b/arch/s390/include/asm/ipl.h @@ -64,7 +64,8 @@ struct ipl_block_fcp { struct ipl_block_ccw { u8 reserved1[84]; - u8 reserved2[2]; + u16 reserved2 : 13; + u8 ssid : 3; u16 devno; u8 vm_flags; u8 reserved3[3]; diff --git a/arch/s390/include/asm/pci_dma.h b/arch/s390/include/asm/pci_dma.h index 7a7abf1a5537..1aac41e83ea1 100644 --- a/arch/s390/include/asm/pci_dma.h +++ b/arch/s390/include/asm/pci_dma.h @@ -195,5 +195,7 @@ void zpci_dma_exit_device(struct zpci_dev *); void dma_free_seg_table(unsigned long); unsigned long *dma_alloc_cpu_table(void); void dma_cleanup_tables(unsigned long *); -void dma_update_cpu_trans(unsigned long *, void *, dma_addr_t, int); +unsigned long *dma_walk_cpu_trans(unsigned long *rto, dma_addr_t dma_addr); +void dma_update_cpu_trans(unsigned long *entry, void *page_addr, int flags); + #endif diff --git a/arch/s390/include/asm/trace/diag.h b/arch/s390/include/asm/trace/diag.h index 776f307960cc..cc6cfe7889da 100644 --- a/arch/s390/include/asm/trace/diag.h +++ b/arch/s390/include/asm/trace/diag.h @@ -19,7 +19,7 @@ #define TRACE_INCLUDE_PATH asm/trace #define TRACE_INCLUDE_FILE diag -TRACE_EVENT(diagnose, +TRACE_EVENT(s390_diagnose, TP_PROTO(unsigned short nr), TP_ARGS(nr), TP_STRUCT__entry( @@ -32,9 +32,9 @@ TRACE_EVENT(diagnose, ); #ifdef CONFIG_TRACEPOINTS -void trace_diagnose_norecursion(int diag_nr); +void trace_s390_diagnose_norecursion(int diag_nr); #else -static inline void trace_diagnose_norecursion(int diag_nr) { } +static inline void trace_s390_diagnose_norecursion(int diag_nr) { } #endif #endif /* _TRACE_S390_DIAG_H */ diff --git a/arch/s390/include/uapi/asm/unistd.h b/arch/s390/include/uapi/asm/unistd.h index a848adba1504..34ec202472c6 100644 --- a/arch/s390/include/uapi/asm/unistd.h +++ b/arch/s390/include/uapi/asm/unistd.h @@ -192,14 +192,14 @@ #define __NR_set_tid_address 252 #define __NR_fadvise64 253 #define __NR_timer_create 254 -#define __NR_timer_settime (__NR_timer_create+1) -#define __NR_timer_gettime (__NR_timer_create+2) -#define __NR_timer_getoverrun (__NR_timer_create+3) -#define __NR_timer_delete (__NR_timer_create+4) -#define __NR_clock_settime (__NR_timer_create+5) -#define __NR_clock_gettime (__NR_timer_create+6) -#define __NR_clock_getres (__NR_timer_create+7) -#define __NR_clock_nanosleep (__NR_timer_create+8) +#define __NR_timer_settime 255 +#define __NR_timer_gettime 256 +#define __NR_timer_getoverrun 257 +#define __NR_timer_delete 258 +#define __NR_clock_settime 259 +#define __NR_clock_gettime 260 +#define __NR_clock_getres 261 +#define __NR_clock_nanosleep 262 /* Number 263 is reserved for vserver */ #define __NR_statfs64 265 #define __NR_fstatfs64 266 @@ -309,7 +309,8 @@ #define __NR_recvfrom 371 #define __NR_recvmsg 372 #define __NR_shutdown 373 -#define NR_syscalls 374 +#define __NR_mlock2 374 +#define NR_syscalls 375 /* * There are some system calls that are not present on 64 bit, some diff --git a/arch/s390/kernel/compat_wrapper.c b/arch/s390/kernel/compat_wrapper.c index 09f194052df3..fac4eeddef91 100644 --- a/arch/s390/kernel/compat_wrapper.c +++ b/arch/s390/kernel/compat_wrapper.c @@ -176,3 +176,4 @@ COMPAT_SYSCALL_WRAP4(accept4, int, fd, struct sockaddr __user *, upeer_sockaddr, COMPAT_SYSCALL_WRAP3(getsockname, int, fd, struct sockaddr __user *, usockaddr, int __user *, usockaddr_len); COMPAT_SYSCALL_WRAP3(getpeername, int, fd, struct sockaddr __user *, usockaddr, int __user *, usockaddr_len); COMPAT_SYSCALL_WRAP6(sendto, int, fd, void __user *, buff, size_t, len, unsigned int, flags, struct sockaddr __user *, addr, int, addr_len); +COMPAT_SYSCALL_WRAP3(mlock2, unsigned long, start, size_t, len, int, flags); diff --git a/arch/s390/kernel/diag.c b/arch/s390/kernel/diag.c index f98766ede4e1..48b37b8357e6 100644 --- a/arch/s390/kernel/diag.c +++ b/arch/s390/kernel/diag.c @@ -121,14 +121,14 @@ device_initcall(show_diag_stat_init); void diag_stat_inc(enum diag_stat_enum nr) { this_cpu_inc(diag_stat.counter[nr]); - trace_diagnose(diag_map[nr].code); + trace_s390_diagnose(diag_map[nr].code); } EXPORT_SYMBOL(diag_stat_inc); void diag_stat_inc_norecursion(enum diag_stat_enum nr) { this_cpu_inc(diag_stat.counter[nr]); - trace_diagnose_norecursion(diag_map[nr].code); + trace_s390_diagnose_norecursion(diag_map[nr].code); } EXPORT_SYMBOL(diag_stat_inc_norecursion); diff --git a/arch/s390/kernel/dis.c b/arch/s390/kernel/dis.c index 8140d10c6785..6e72961608f0 100644 --- a/arch/s390/kernel/dis.c +++ b/arch/s390/kernel/dis.c @@ -1920,16 +1920,23 @@ static int print_insn(char *buffer, unsigned char *code, unsigned long addr) } if (separator) ptr += sprintf(ptr, "%c", separator); + /* + * Use four '%' characters below because of the + * following two conversions: + * + * 1) sprintf: %%%%r -> %%r + * 2) printk : %%r -> %r + */ if (operand->flags & OPERAND_GPR) - ptr += sprintf(ptr, "%%r%i", value); + ptr += sprintf(ptr, "%%%%r%i", value); else if (operand->flags & OPERAND_FPR) - ptr += sprintf(ptr, "%%f%i", value); + ptr += sprintf(ptr, "%%%%f%i", value); else if (operand->flags & OPERAND_AR) - ptr += sprintf(ptr, "%%a%i", value); + ptr += sprintf(ptr, "%%%%a%i", value); else if (operand->flags & OPERAND_CR) - ptr += sprintf(ptr, "%%c%i", value); + ptr += sprintf(ptr, "%%%%c%i", value); else if (operand->flags & OPERAND_VR) - ptr += sprintf(ptr, "%%v%i", value); + ptr += sprintf(ptr, "%%%%v%i", value); else if (operand->flags & OPERAND_PCREL) ptr += sprintf(ptr, "%lx", (signed int) value + addr); diff --git a/arch/s390/kernel/head.S b/arch/s390/kernel/head.S index 1255c6c5353e..301ee9c70688 100644 --- a/arch/s390/kernel/head.S +++ b/arch/s390/kernel/head.S @@ -26,6 +26,7 @@ #include <asm/asm-offsets.h> #include <asm/thread_info.h> #include <asm/page.h> +#include <asm/ptrace.h> #define ARCH_OFFSET 4 @@ -59,19 +60,6 @@ __HEAD .long 0x020006e0,0x20000050 .org 0x200 -# -# subroutine to set architecture mode -# -.Lsetmode: - mvi __LC_AR_MODE_ID,1 # set esame flag - slr %r0,%r0 # set cpuid to zero - lhi %r1,2 # mode 2 = esame (dump) - sigp %r1,%r0,0x12 # switch to esame mode - bras %r13,0f - .fill 16,4,0x0 -0: lmh %r0,%r15,0(%r13) # clear high-order half of gprs - sam31 # switch to 31 bit addressing mode - br %r14 # # subroutine to wait for end I/O @@ -159,7 +147,14 @@ __HEAD .long 0x02200050,0x00000000 iplstart: - bas %r14,.Lsetmode # Immediately switch to 64 bit mode + mvi __LC_AR_MODE_ID,1 # set esame flag + slr %r0,%r0 # set cpuid to zero + lhi %r1,2 # mode 2 = esame (dump) + sigp %r1,%r0,0x12 # switch to esame mode + bras %r13,0f + .fill 16,4,0x0 +0: lmh %r0,%r15,0(%r13) # clear high-order half of gprs + sam31 # switch to 31 bit addressing mode lh %r1,0xb8 # test if subchannel number bct %r1,.Lnoload # is valid l %r1,0xb8 # load ipl subchannel number @@ -269,71 +264,6 @@ iplstart: .Lcpuid:.fill 8,1,0 # -# SALIPL loader support. Based on a patch by Rob van der Heij. -# This entry point is called directly from the SALIPL loader and -# doesn't need a builtin ipl record. -# - .org 0x800 -ENTRY(start) - stm %r0,%r15,0x07b0 # store registers - bas %r14,.Lsetmode # Immediately switch to 64 bit mode - basr %r12,%r0 -.base: - l %r11,.parm - l %r8,.cmd # pointer to command buffer - - ltr %r9,%r9 # do we have SALIPL parameters? - bp .sk8x8 - - mvc 0(64,%r8),0x00b0 # copy saved registers - xc 64(240-64,%r8),0(%r8) # remainder of buffer - tr 0(64,%r8),.lowcase - b .gotr -.sk8x8: - mvc 0(240,%r8),0(%r9) # copy iplparms into buffer -.gotr: - slr %r0,%r0 - st %r0,INITRD_SIZE+ARCH_OFFSET-PARMAREA(%r11) - st %r0,INITRD_START+ARCH_OFFSET-PARMAREA(%r11) - j startup # continue with startup -.cmd: .long COMMAND_LINE # address of command line buffer -.parm: .long PARMAREA -.lowcase: - .byte 0x00,0x01,0x02,0x03,0x04,0x05,0x06,0x07 - .byte 0x08,0x09,0x0a,0x0b,0x0c,0x0d,0x0e,0x0f - .byte 0x10,0x11,0x12,0x13,0x14,0x15,0x16,0x17 - .byte 0x18,0x19,0x1a,0x1b,0x1c,0x1d,0x1e,0x1f - .byte 0x20,0x21,0x22,0x23,0x24,0x25,0x26,0x27 - .byte 0x28,0x29,0x2a,0x2b,0x2c,0x2d,0x2e,0x2f - .byte 0x30,0x31,0x32,0x33,0x34,0x35,0x36,0x37 - .byte 0x38,0x39,0x3a,0x3b,0x3c,0x3d,0x3e,0x3f - .byte 0x40,0x41,0x42,0x43,0x44,0x45,0x46,0x47 - .byte 0x48,0x49,0x4a,0x4b,0x4c,0x4d,0x4e,0x4f - .byte 0x50,0x51,0x52,0x53,0x54,0x55,0x56,0x57 - .byte 0x58,0x59,0x5a,0x5b,0x5c,0x5d,0x5e,0x5f - .byte 0x60,0x61,0x62,0x63,0x64,0x65,0x66,0x67 - .byte 0x68,0x69,0x6a,0x6b,0x6c,0x6d,0x6e,0x6f - .byte 0x70,0x71,0x72,0x73,0x74,0x75,0x76,0x77 - .byte 0x78,0x79,0x7a,0x7b,0x7c,0x7d,0x7e,0x7f - - .byte 0x80,0x81,0x82,0x83,0x84,0x85,0x86,0x87 - .byte 0x88,0x89,0x8a,0x8b,0x8c,0x8d,0x8e,0x8f - .byte 0x90,0x91,0x92,0x93,0x94,0x95,0x96,0x97 - .byte 0x98,0x99,0x9a,0x9b,0x9c,0x9d,0x9e,0x9f - .byte 0xa0,0xa1,0xa2,0xa3,0xa4,0xa5,0xa6,0xa7 - .byte 0xa8,0xa9,0xaa,0xab,0xac,0xad,0xae,0xaf - .byte 0xb0,0xb1,0xb2,0xb3,0xb4,0xb5,0xb6,0xb7 - .byte 0xb8,0xb9,0xba,0xbb,0xbc,0xbd,0xbe,0xbf - .byte 0xc0,0x81,0x82,0x83,0x84,0x85,0x86,0x87 # .abcdefg - .byte 0x88,0x89,0xca,0xcb,0xcc,0xcd,0xce,0xcf # hi - .byte 0xd0,0x91,0x92,0x93,0x94,0x95,0x96,0x97 # .jklmnop - .byte 0x98,0x99,0xda,0xdb,0xdc,0xdd,0xde,0xdf # qr - .byte 0xe0,0xe1,0xa2,0xa3,0xa4,0xa5,0xa6,0xa7 # ..stuvwx - .byte 0xa8,0xa9,0xea,0xeb,0xec,0xed,0xee,0xef # yz - .byte 0xf0,0xf1,0xf2,0xf3,0xf4,0xf5,0xf6,0xf7 - .byte 0xf8,0xf9,0xfa,0xfb,0xfc,0xfd,0xfe,0xff - -# # startup-code at 0x10000, running in absolute addressing mode # this is called either by the ipl loader or directly by PSW restart # or linload or SALIPL @@ -364,7 +294,7 @@ ENTRY(startup_kdump) bras %r13,0f .fill 16,4,0x0 0: lmh %r0,%r15,0(%r13) # clear high-order half of gprs - sam31 # switch to 31 bit addressing mode + sam64 # switch to 64 bit addressing mode basr %r13,0 # get base .LPG0: xc 0x200(256),0x200 # partially clear lowcore @@ -395,7 +325,7 @@ ENTRY(startup_kdump) jnz 1b j 4f 2: l %r15,.Lstack-.LPG0(%r13) - ahi %r15,-96 + ahi %r15,-STACK_FRAME_OVERHEAD la %r2,.Lals_string-.LPG0(%r13) l %r3,.Lsclp_print-.LPG0(%r13) basr %r14,%r3 @@ -429,8 +359,7 @@ ENTRY(startup_kdump) .long 1, 0xc0000000 #endif 4: - /* Continue with 64bit startup code in head64.S */ - sam64 # switch to 64 bit mode + /* Continue with startup code in head64.S */ jg startup_continue .align 8 diff --git a/arch/s390/kernel/ipl.c b/arch/s390/kernel/ipl.c index f6d8acd7e136..b1f0a90f933b 100644 --- a/arch/s390/kernel/ipl.c +++ b/arch/s390/kernel/ipl.c @@ -121,6 +121,7 @@ static char *dump_type_str(enum dump_type type) * Must be in data section since the bss section * is not cleared when these are accessed. */ +static u8 ipl_ssid __attribute__((__section__(".data"))) = 0; static u16 ipl_devno __attribute__((__section__(".data"))) = 0; u32 ipl_flags __attribute__((__section__(".data"))) = 0; @@ -197,6 +198,33 @@ static ssize_t sys_##_prefix##_##_name##_show(struct kobject *kobj, \ return snprintf(page, PAGE_SIZE, _format, ##args); \ } +#define IPL_ATTR_CCW_STORE_FN(_prefix, _name, _ipl_blk) \ +static ssize_t sys_##_prefix##_##_name##_store(struct kobject *kobj, \ + struct kobj_attribute *attr, \ + const char *buf, size_t len) \ +{ \ + unsigned long long ssid, devno; \ + \ + if (sscanf(buf, "0.%llx.%llx\n", &ssid, &devno) != 2) \ + return -EINVAL; \ + \ + if (ssid > __MAX_SSID || devno > __MAX_SUBCHANNEL) \ + return -EINVAL; \ + \ + _ipl_blk.ssid = ssid; \ + _ipl_blk.devno = devno; \ + return len; \ +} + +#define DEFINE_IPL_CCW_ATTR_RW(_prefix, _name, _ipl_blk) \ +IPL_ATTR_SHOW_FN(_prefix, _name, "0.%x.%04x\n", \ + _ipl_blk.ssid, _ipl_blk.devno); \ +IPL_ATTR_CCW_STORE_FN(_prefix, _name, _ipl_blk); \ +static struct kobj_attribute sys_##_prefix##_##_name##_attr = \ + __ATTR(_name, (S_IRUGO | S_IWUSR), \ + sys_##_prefix##_##_name##_show, \ + sys_##_prefix##_##_name##_store) \ + #define DEFINE_IPL_ATTR_RO(_prefix, _name, _format, _value) \ IPL_ATTR_SHOW_FN(_prefix, _name, _format, _value) \ static struct kobj_attribute sys_##_prefix##_##_name##_attr = \ @@ -395,7 +423,7 @@ static ssize_t sys_ipl_device_show(struct kobject *kobj, switch (ipl_info.type) { case IPL_TYPE_CCW: - return sprintf(page, "0.0.%04x\n", ipl_devno); + return sprintf(page, "0.%x.%04x\n", ipl_ssid, ipl_devno); case IPL_TYPE_FCP: case IPL_TYPE_FCP_DUMP: return sprintf(page, "0.0.%04x\n", ipl->ipl_info.fcp.devno); @@ -687,21 +715,14 @@ static ssize_t reipl_fcp_scpdata_write(struct file *filp, struct kobject *kobj, struct bin_attribute *attr, char *buf, loff_t off, size_t count) { + size_t scpdata_len = count; size_t padding; - size_t scpdata_len; - - if (off < 0) - return -EINVAL; - if (off >= DIAG308_SCPDATA_SIZE) - return -ENOSPC; - if (count > DIAG308_SCPDATA_SIZE - off) - count = DIAG308_SCPDATA_SIZE - off; - - memcpy(reipl_block_fcp->ipl_info.fcp.scp_data, buf + off, count); - scpdata_len = off + count; + if (off) + return -EINVAL; + memcpy(reipl_block_fcp->ipl_info.fcp.scp_data, buf, count); if (scpdata_len % 8) { padding = 8 - (scpdata_len % 8); memset(reipl_block_fcp->ipl_info.fcp.scp_data + scpdata_len, @@ -717,7 +738,7 @@ static ssize_t reipl_fcp_scpdata_write(struct file *filp, struct kobject *kobj, } static struct bin_attribute sys_reipl_fcp_scp_data_attr = __BIN_ATTR(scp_data, (S_IRUGO | S_IWUSR), reipl_fcp_scpdata_read, - reipl_fcp_scpdata_write, PAGE_SIZE); + reipl_fcp_scpdata_write, DIAG308_SCPDATA_SIZE); static struct bin_attribute *reipl_fcp_bin_attrs[] = { &sys_reipl_fcp_scp_data_attr, @@ -814,9 +835,7 @@ static struct attribute_group reipl_fcp_attr_group = { }; /* CCW reipl device attributes */ - -DEFINE_IPL_ATTR_RW(reipl_ccw, device, "0.0.%04llx\n", "0.0.%llx\n", - reipl_block_ccw->ipl_info.ccw.devno); +DEFINE_IPL_CCW_ATTR_RW(reipl_ccw, device, reipl_block_ccw->ipl_info.ccw); /* NSS wrapper */ static ssize_t reipl_nss_loadparm_show(struct kobject *kobj, @@ -1056,8 +1075,8 @@ static void __reipl_run(void *unused) switch (reipl_method) { case REIPL_METHOD_CCW_CIO: + devid.ssid = reipl_block_ccw->ipl_info.ccw.ssid; devid.devno = reipl_block_ccw->ipl_info.ccw.devno; - devid.ssid = 0; reipl_ccw_dev(&devid); break; case REIPL_METHOD_CCW_VM: @@ -1192,6 +1211,7 @@ static int __init reipl_ccw_init(void) reipl_block_ccw_init(reipl_block_ccw); if (ipl_info.type == IPL_TYPE_CCW) { + reipl_block_ccw->ipl_info.ccw.ssid = ipl_ssid; reipl_block_ccw->ipl_info.ccw.devno = ipl_devno; reipl_block_ccw_fill_parms(reipl_block_ccw); } @@ -1336,9 +1356,7 @@ static struct attribute_group dump_fcp_attr_group = { }; /* CCW dump device attributes */ - -DEFINE_IPL_ATTR_RW(dump_ccw, device, "0.0.%04llx\n", "0.0.%llx\n", - dump_block_ccw->ipl_info.ccw.devno); +DEFINE_IPL_CCW_ATTR_RW(dump_ccw, device, dump_block_ccw->ipl_info.ccw); static struct attribute *dump_ccw_attrs[] = { &sys_dump_ccw_device_attr.attr, @@ -1418,8 +1436,8 @@ static void __dump_run(void *unused) switch (dump_method) { case DUMP_METHOD_CCW_CIO: + devid.ssid = dump_block_ccw->ipl_info.ccw.ssid; devid.devno = dump_block_ccw->ipl_info.ccw.devno; - devid.ssid = 0; reipl_ccw_dev(&devid); break; case DUMP_METHOD_CCW_VM: @@ -1939,14 +1957,14 @@ void __init setup_ipl(void) ipl_info.type = get_ipl_type(); switch (ipl_info.type) { case IPL_TYPE_CCW: + ipl_info.data.ccw.dev_id.ssid = ipl_ssid; ipl_info.data.ccw.dev_id.devno = ipl_devno; - ipl_info.data.ccw.dev_id.ssid = 0; break; case IPL_TYPE_FCP: case IPL_TYPE_FCP_DUMP: + ipl_info.data.fcp.dev_id.ssid = 0; ipl_info.data.fcp.dev_id.devno = IPL_PARMBLOCK_START->ipl_info.fcp.devno; - ipl_info.data.fcp.dev_id.ssid = 0; ipl_info.data.fcp.wwpn = IPL_PARMBLOCK_START->ipl_info.fcp.wwpn; ipl_info.data.fcp.lun = IPL_PARMBLOCK_START->ipl_info.fcp.lun; break; @@ -1978,6 +1996,7 @@ void __init ipl_save_parameters(void) if (cio_get_iplinfo(&iplinfo)) return; + ipl_ssid = iplinfo.ssid; ipl_devno = iplinfo.devno; ipl_flags |= IPL_DEVNO_VALID; if (!iplinfo.is_qdio) diff --git a/arch/s390/kernel/process.c b/arch/s390/kernel/process.c index 688a3aad9c79..114ee8b96f17 100644 --- a/arch/s390/kernel/process.c +++ b/arch/s390/kernel/process.c @@ -243,11 +243,7 @@ unsigned long arch_align_stack(unsigned long sp) static inline unsigned long brk_rnd(void) { - /* 8MB for 32bit, 1GB for 64bit */ - if (is_32bit_task()) - return (get_random_int() & 0x7ffUL) << PAGE_SHIFT; - else - return (get_random_int() & 0x3ffffUL) << PAGE_SHIFT; + return (get_random_int() & BRK_RND_MASK) << PAGE_SHIFT; } unsigned long arch_randomize_brk(struct mm_struct *mm) diff --git a/arch/s390/kernel/sclp.c b/arch/s390/kernel/sclp.c index fa0bdff1d413..9fe7781a45cd 100644 --- a/arch/s390/kernel/sclp.c +++ b/arch/s390/kernel/sclp.c @@ -21,7 +21,7 @@ static void _sclp_wait_int(void) __ctl_load(cr0_new, 0, 0); psw_ext_save = S390_lowcore.external_new_psw; - psw_mask = __extract_psw() & (PSW_MASK_EA | PSW_MASK_BA); + psw_mask = __extract_psw(); S390_lowcore.external_new_psw.mask = psw_mask; psw_wait.mask = psw_mask | PSW_MASK_EXT | PSW_MASK_WAIT; S390_lowcore.ext_int_code = 0; diff --git a/arch/s390/kernel/setup.c b/arch/s390/kernel/setup.c index ce0cbd6ba7ca..c837bcacf218 100644 --- a/arch/s390/kernel/setup.c +++ b/arch/s390/kernel/setup.c @@ -764,9 +764,6 @@ static int __init setup_hwcaps(void) get_cpu_id(&cpu_id); add_device_randomness(&cpu_id, sizeof(cpu_id)); switch (cpu_id.machine) { - case 0x9672: - strcpy(elf_platform, "g5"); - break; case 0x2064: case 0x2066: default: /* Use "z900" as default for 64 bit kernels. */ diff --git a/arch/s390/kernel/syscalls.S b/arch/s390/kernel/syscalls.S index 8c56929c8d82..5378c3ea1b98 100644 --- a/arch/s390/kernel/syscalls.S +++ b/arch/s390/kernel/syscalls.S @@ -382,3 +382,4 @@ SYSCALL(sys_sendmsg,compat_sys_sendmsg) /* 370 */ SYSCALL(sys_recvfrom,compat_sys_recvfrom) SYSCALL(sys_recvmsg,compat_sys_recvmsg) SYSCALL(sys_shutdown,sys_shutdown) +SYSCALL(sys_mlock2,compat_sys_mlock2) diff --git a/arch/s390/kernel/trace.c b/arch/s390/kernel/trace.c index 73239bb576c4..21a5df99552b 100644 --- a/arch/s390/kernel/trace.c +++ b/arch/s390/kernel/trace.c @@ -9,11 +9,11 @@ #define CREATE_TRACE_POINTS #include <asm/trace/diag.h> -EXPORT_TRACEPOINT_SYMBOL(diagnose); +EXPORT_TRACEPOINT_SYMBOL(s390_diagnose); static DEFINE_PER_CPU(unsigned int, diagnose_trace_depth); -void trace_diagnose_norecursion(int diag_nr) +void trace_s390_diagnose_norecursion(int diag_nr) { unsigned long flags; unsigned int *depth; @@ -22,7 +22,7 @@ void trace_diagnose_norecursion(int diag_nr) depth = this_cpu_ptr(&diagnose_trace_depth); if (*depth == 0) { (*depth)++; - trace_diagnose(diag_nr); + trace_s390_diagnose(diag_nr); (*depth)--; } local_irq_restore(flags); diff --git a/arch/s390/kvm/interrupt.c b/arch/s390/kvm/interrupt.c index 373e32346d68..6a75352f453c 100644 --- a/arch/s390/kvm/interrupt.c +++ b/arch/s390/kvm/interrupt.c @@ -1030,8 +1030,7 @@ static int __inject_extcall(struct kvm_vcpu *vcpu, struct kvm_s390_irq *irq) src_id, 0); /* sending vcpu invalid */ - if (src_id >= KVM_MAX_VCPUS || - kvm_get_vcpu(vcpu->kvm, src_id) == NULL) + if (kvm_get_vcpu_by_id(vcpu->kvm, src_id) == NULL) return -EINVAL; if (sclp.has_sigpif) @@ -1110,6 +1109,10 @@ static int __inject_sigp_emergency(struct kvm_vcpu *vcpu, trace_kvm_s390_inject_vcpu(vcpu->vcpu_id, KVM_S390_INT_EMERGENCY, irq->u.emerg.code, 0); + /* sending vcpu invalid */ + if (kvm_get_vcpu_by_id(vcpu->kvm, irq->u.emerg.code) == NULL) + return -EINVAL; + set_bit(irq->u.emerg.code, li->sigp_emerg_pending); set_bit(IRQ_PEND_EXT_EMERGENCY, &li->pending_irqs); atomic_or(CPUSTAT_EXT_INT, li->cpuflags); diff --git a/arch/s390/kvm/kvm-s390.c b/arch/s390/kvm/kvm-s390.c index 8fe2f1c722dc..846589281b04 100644 --- a/arch/s390/kvm/kvm-s390.c +++ b/arch/s390/kvm/kvm-s390.c @@ -342,12 +342,16 @@ static int kvm_vm_ioctl_enable_cap(struct kvm *kvm, struct kvm_enable_cap *cap) r = 0; break; case KVM_CAP_S390_VECTOR_REGISTERS: - if (MACHINE_HAS_VX) { + mutex_lock(&kvm->lock); + if (atomic_read(&kvm->online_vcpus)) { + r = -EBUSY; + } else if (MACHINE_HAS_VX) { set_kvm_facility(kvm->arch.model.fac->mask, 129); set_kvm_facility(kvm->arch.model.fac->list, 129); r = 0; } else r = -EINVAL; + mutex_unlock(&kvm->lock); VM_EVENT(kvm, 3, "ENABLE: CAP_S390_VECTOR_REGISTERS %s", r ? "(not available)" : "(success)"); break; diff --git a/arch/s390/kvm/priv.c b/arch/s390/kvm/priv.c index 77191b85ea7a..d76b51cb4b62 100644 --- a/arch/s390/kvm/priv.c +++ b/arch/s390/kvm/priv.c @@ -660,7 +660,7 @@ static int handle_pfmf(struct kvm_vcpu *vcpu) kvm_s390_get_regs_rre(vcpu, ®1, ®2); - if (!MACHINE_HAS_PFMF) + if (!test_kvm_facility(vcpu->kvm, 8)) return kvm_s390_inject_program_int(vcpu, PGM_OPERATION); if (vcpu->arch.sie_block->gpsw.mask & PSW_MASK_PSTATE) diff --git a/arch/s390/kvm/sigp.c b/arch/s390/kvm/sigp.c index da690b69f9fe..77c22d685c7a 100644 --- a/arch/s390/kvm/sigp.c +++ b/arch/s390/kvm/sigp.c @@ -291,12 +291,8 @@ static int handle_sigp_dst(struct kvm_vcpu *vcpu, u8 order_code, u16 cpu_addr, u32 parameter, u64 *status_reg) { int rc; - struct kvm_vcpu *dst_vcpu; + struct kvm_vcpu *dst_vcpu = kvm_get_vcpu_by_id(vcpu->kvm, cpu_addr); - if (cpu_addr >= KVM_MAX_VCPUS) - return SIGP_CC_NOT_OPERATIONAL; - - dst_vcpu = kvm_get_vcpu(vcpu->kvm, cpu_addr); if (!dst_vcpu) return SIGP_CC_NOT_OPERATIONAL; @@ -478,7 +474,7 @@ int kvm_s390_handle_sigp_pei(struct kvm_vcpu *vcpu) trace_kvm_s390_handle_sigp_pei(vcpu, order_code, cpu_addr); if (order_code == SIGP_EXTERNAL_CALL) { - dest_vcpu = kvm_get_vcpu(vcpu->kvm, cpu_addr); + dest_vcpu = kvm_get_vcpu_by_id(vcpu->kvm, cpu_addr); BUG_ON(dest_vcpu == NULL); kvm_s390_vcpu_wakeup(dest_vcpu); diff --git a/arch/s390/mm/init.c b/arch/s390/mm/init.c index c3c07d3505ba..c722400c7697 100644 --- a/arch/s390/mm/init.c +++ b/arch/s390/mm/init.c @@ -48,37 +48,13 @@ EXPORT_SYMBOL(zero_page_mask); static void __init setup_zero_pages(void) { - struct cpuid cpu_id; unsigned int order; struct page *page; int i; - get_cpu_id(&cpu_id); - switch (cpu_id.machine) { - case 0x9672: /* g5 */ - case 0x2064: /* z900 */ - case 0x2066: /* z900 */ - case 0x2084: /* z990 */ - case 0x2086: /* z990 */ - case 0x2094: /* z9-109 */ - case 0x2096: /* z9-109 */ - order = 0; - break; - case 0x2097: /* z10 */ - case 0x2098: /* z10 */ - case 0x2817: /* z196 */ - case 0x2818: /* z196 */ - order = 2; - break; - case 0x2827: /* zEC12 */ - case 0x2828: /* zEC12 */ - order = 5; - break; - case 0x2964: /* z13 */ - default: - order = 7; - break; - } + /* Latest machines require a mapping granularity of 512KB */ + order = 7; + /* Limit number of empty zero pages for small memory sizes */ while (order > 2 && (totalram_pages >> 10) < (1UL << order)) order--; diff --git a/arch/s390/mm/mmap.c b/arch/s390/mm/mmap.c index 6e552af08c76..ea01477b4aa6 100644 --- a/arch/s390/mm/mmap.c +++ b/arch/s390/mm/mmap.c @@ -31,9 +31,6 @@ #include <linux/security.h> #include <asm/pgalloc.h> -unsigned long mmap_rnd_mask; -static unsigned long mmap_align_mask; - static unsigned long stack_maxrandom_size(void) { if (!(current->flags & PF_RANDOMIZE)) @@ -62,10 +59,7 @@ static inline int mmap_is_legacy(void) unsigned long arch_mmap_rnd(void) { - if (is_32bit_task()) - return (get_random_int() & 0x7ff) << PAGE_SHIFT; - else - return (get_random_int() & mmap_rnd_mask) << PAGE_SHIFT; + return (get_random_int() & MMAP_RND_MASK) << PAGE_SHIFT; } static unsigned long mmap_base_legacy(unsigned long rnd) @@ -92,7 +86,6 @@ arch_get_unmapped_area(struct file *filp, unsigned long addr, struct mm_struct *mm = current->mm; struct vm_area_struct *vma; struct vm_unmapped_area_info info; - int do_color_align; if (len > TASK_SIZE - mmap_min_addr) return -ENOMEM; @@ -108,15 +101,14 @@ arch_get_unmapped_area(struct file *filp, unsigned long addr, return addr; } - do_color_align = 0; - if (filp || (flags & MAP_SHARED)) - do_color_align = !is_32bit_task(); - info.flags = 0; info.length = len; info.low_limit = mm->mmap_base; info.high_limit = TASK_SIZE; - info.align_mask = do_color_align ? (mmap_align_mask << PAGE_SHIFT) : 0; + if (filp || (flags & MAP_SHARED)) + info.align_mask = MMAP_ALIGN_MASK << PAGE_SHIFT; + else + info.align_mask = 0; info.align_offset = pgoff << PAGE_SHIFT; return vm_unmapped_area(&info); } @@ -130,7 +122,6 @@ arch_get_unmapped_area_topdown(struct file *filp, const unsigned long addr0, struct mm_struct *mm = current->mm; unsigned long addr = addr0; struct vm_unmapped_area_info info; - int do_color_align; /* requested length too big for entire address space */ if (len > TASK_SIZE - mmap_min_addr) @@ -148,15 +139,14 @@ arch_get_unmapped_area_topdown(struct file *filp, const unsigned long addr0, return addr; } - do_color_align = 0; - if (filp || (flags & MAP_SHARED)) - do_color_align = !is_32bit_task(); - info.flags = VM_UNMAPPED_AREA_TOPDOWN; info.length = len; info.low_limit = max(PAGE_SIZE, mmap_min_addr); info.high_limit = mm->mmap_base; - info.align_mask = do_color_align ? (mmap_align_mask << PAGE_SHIFT) : 0; + if (filp || (flags & MAP_SHARED)) + info.align_mask = MMAP_ALIGN_MASK << PAGE_SHIFT; + else + info.align_mask = 0; info.align_offset = pgoff << PAGE_SHIFT; addr = vm_unmapped_area(&info); @@ -254,35 +244,3 @@ void arch_pick_mmap_layout(struct mm_struct *mm) mm->get_unmapped_area = s390_get_unmapped_area_topdown; } } - -static int __init setup_mmap_rnd(void) -{ - struct cpuid cpu_id; - - get_cpu_id(&cpu_id); - switch (cpu_id.machine) { - case 0x9672: - case 0x2064: - case 0x2066: - case 0x2084: - case 0x2086: - case 0x2094: - case 0x2096: - case 0x2097: - case 0x2098: - case 0x2817: - case 0x2818: - case 0x2827: - case 0x2828: - mmap_rnd_mask = 0x7ffUL; - mmap_align_mask = 0UL; - break; - case 0x2964: /* z13 */ - default: - mmap_rnd_mask = 0x3ff80UL; - mmap_align_mask = 0x7fUL; - break; - } - return 0; -} -early_initcall(setup_mmap_rnd); diff --git a/arch/s390/pci/pci_dma.c b/arch/s390/pci/pci_dma.c index 37d10f74425a..d348f2c09a1e 100644 --- a/arch/s390/pci/pci_dma.c +++ b/arch/s390/pci/pci_dma.c @@ -33,7 +33,7 @@ unsigned long *dma_alloc_cpu_table(void) return NULL; for (entry = table; entry < table + ZPCI_TABLE_ENTRIES; entry++) - *entry = ZPCI_TABLE_INVALID | ZPCI_TABLE_PROTECTED; + *entry = ZPCI_TABLE_INVALID; return table; } @@ -51,7 +51,7 @@ static unsigned long *dma_alloc_page_table(void) return NULL; for (entry = table; entry < table + ZPCI_PT_ENTRIES; entry++) - *entry = ZPCI_PTE_INVALID | ZPCI_TABLE_PROTECTED; + *entry = ZPCI_PTE_INVALID; return table; } @@ -95,7 +95,7 @@ static unsigned long *dma_get_page_table_origin(unsigned long *entry) return pto; } -static unsigned long *dma_walk_cpu_trans(unsigned long *rto, dma_addr_t dma_addr) +unsigned long *dma_walk_cpu_trans(unsigned long *rto, dma_addr_t dma_addr) { unsigned long *sto, *pto; unsigned int rtx, sx, px; @@ -114,20 +114,10 @@ static unsigned long *dma_walk_cpu_trans(unsigned long *rto, dma_addr_t dma_addr return &pto[px]; } -void dma_update_cpu_trans(unsigned long *dma_table, void *page_addr, - dma_addr_t dma_addr, int flags) +void dma_update_cpu_trans(unsigned long *entry, void *page_addr, int flags) { - unsigned long *entry; - - entry = dma_walk_cpu_trans(dma_table, dma_addr); - if (!entry) { - WARN_ON_ONCE(1); - return; - } - if (flags & ZPCI_PTE_INVALID) { invalidate_pt_entry(entry); - return; } else { set_pt_pfaa(entry, page_addr); validate_pt_entry(entry); @@ -146,18 +136,25 @@ static int dma_update_trans(struct zpci_dev *zdev, unsigned long pa, u8 *page_addr = (u8 *) (pa & PAGE_MASK); dma_addr_t start_dma_addr = dma_addr; unsigned long irq_flags; + unsigned long *entry; int i, rc = 0; if (!nr_pages) return -EINVAL; spin_lock_irqsave(&zdev->dma_table_lock, irq_flags); - if (!zdev->dma_table) + if (!zdev->dma_table) { + rc = -EINVAL; goto no_refresh; + } for (i = 0; i < nr_pages; i++) { - dma_update_cpu_trans(zdev->dma_table, page_addr, dma_addr, - flags); + entry = dma_walk_cpu_trans(zdev->dma_table, dma_addr); + if (!entry) { + rc = -ENOMEM; + goto undo_cpu_trans; + } + dma_update_cpu_trans(entry, page_addr, flags); page_addr += PAGE_SIZE; dma_addr += PAGE_SIZE; } @@ -176,6 +173,18 @@ static int dma_update_trans(struct zpci_dev *zdev, unsigned long pa, rc = zpci_refresh_trans((u64) zdev->fh << 32, start_dma_addr, nr_pages * PAGE_SIZE); +undo_cpu_trans: + if (rc && ((flags & ZPCI_PTE_VALID_MASK) == ZPCI_PTE_VALID)) { + flags = ZPCI_PTE_INVALID; + while (i-- > 0) { + page_addr -= PAGE_SIZE; + dma_addr -= PAGE_SIZE; + entry = dma_walk_cpu_trans(zdev->dma_table, dma_addr); + if (!entry) + break; + dma_update_cpu_trans(entry, page_addr, flags); + } + } no_refresh: spin_unlock_irqrestore(&zdev->dma_table_lock, irq_flags); @@ -260,6 +269,16 @@ out: spin_unlock_irqrestore(&zdev->iommu_bitmap_lock, flags); } +static inline void zpci_err_dma(unsigned long rc, unsigned long addr) +{ + struct { + unsigned long rc; + unsigned long addr; + } __packed data = {rc, addr}; + + zpci_err_hex(&data, sizeof(data)); +} + static dma_addr_t s390_dma_map_pages(struct device *dev, struct page *page, unsigned long offset, size_t size, enum dma_data_direction direction, @@ -270,33 +289,40 @@ static dma_addr_t s390_dma_map_pages(struct device *dev, struct page *page, unsigned long pa = page_to_phys(page) + offset; int flags = ZPCI_PTE_VALID; dma_addr_t dma_addr; + int ret; /* This rounds up number of pages based on size and offset */ nr_pages = iommu_num_pages(pa, size, PAGE_SIZE); iommu_page_index = dma_alloc_iommu(zdev, nr_pages); - if (iommu_page_index == -1) + if (iommu_page_index == -1) { + ret = -ENOSPC; goto out_err; + } /* Use rounded up size */ size = nr_pages * PAGE_SIZE; dma_addr = zdev->start_dma + iommu_page_index * PAGE_SIZE; - if (dma_addr + size > zdev->end_dma) + if (dma_addr + size > zdev->end_dma) { + ret = -ERANGE; goto out_free; + } if (direction == DMA_NONE || direction == DMA_TO_DEVICE) flags |= ZPCI_TABLE_PROTECTED; - if (!dma_update_trans(zdev, pa, dma_addr, size, flags)) { - atomic64_add(nr_pages, &zdev->mapped_pages); - return dma_addr + (offset & ~PAGE_MASK); - } + ret = dma_update_trans(zdev, pa, dma_addr, size, flags); + if (ret) + goto out_free; + + atomic64_add(nr_pages, &zdev->mapped_pages); + return dma_addr + (offset & ~PAGE_MASK); out_free: dma_free_iommu(zdev, iommu_page_index, nr_pages); out_err: zpci_err("map error:\n"); - zpci_err_hex(&pa, sizeof(pa)); + zpci_err_dma(ret, pa); return DMA_ERROR_CODE; } @@ -306,14 +332,16 @@ static void s390_dma_unmap_pages(struct device *dev, dma_addr_t dma_addr, { struct zpci_dev *zdev = to_zpci(to_pci_dev(dev)); unsigned long iommu_page_index; - int npages; + int npages, ret; npages = iommu_num_pages(dma_addr, size, PAGE_SIZE); dma_addr = dma_addr & PAGE_MASK; - if (dma_update_trans(zdev, 0, dma_addr, npages * PAGE_SIZE, - ZPCI_TABLE_PROTECTED | ZPCI_PTE_INVALID)) { + ret = dma_update_trans(zdev, 0, dma_addr, npages * PAGE_SIZE, + ZPCI_PTE_INVALID); + if (ret) { zpci_err("unmap error:\n"); - zpci_err_hex(&dma_addr, sizeof(dma_addr)); + zpci_err_dma(ret, dma_addr); + return; } atomic64_add(npages, &zdev->unmapped_pages); diff --git a/arch/sh/include/uapi/asm/unistd_64.h b/arch/sh/include/uapi/asm/unistd_64.h index e6820c86e8c7..47ebd5b5ed55 100644 --- a/arch/sh/include/uapi/asm/unistd_64.h +++ b/arch/sh/include/uapi/asm/unistd_64.h @@ -278,7 +278,7 @@ #define __NR_fsetxattr 256 #define __NR_getxattr 257 #define __NR_lgetxattr 258 -#define __NR_fgetxattr 269 +#define __NR_fgetxattr 259 #define __NR_listxattr 260 #define __NR_llistxattr 261 #define __NR_flistxattr 262 diff --git a/arch/sh/kernel/perf_event.c b/arch/sh/kernel/perf_event.c index 7cfd7f153966..4dca18347ee9 100644 --- a/arch/sh/kernel/perf_event.c +++ b/arch/sh/kernel/perf_event.c @@ -10,7 +10,7 @@ * Copyright (C) 2008-2009 Red Hat, Inc., Ingo Molnar * Copyright (C) 2009 Jaswinder Singh Rajput * Copyright (C) 2009 Advanced Micro Devices, Inc., Robert Richter - * Copyright (C) 2008-2009 Red Hat, Inc., Peter Zijlstra <pzijlstr@redhat.com> + * Copyright (C) 2008-2009 Red Hat, Inc., Peter Zijlstra * Copyright (C) 2009 Intel Corporation, <markus.t.metzger@intel.com> * * ppc: diff --git a/arch/sparc/include/asm/elf_64.h b/arch/sparc/include/asm/elf_64.h index 370ca1e71ffb..93310837c2df 100644 --- a/arch/sparc/include/asm/elf_64.h +++ b/arch/sparc/include/asm/elf_64.h @@ -95,6 +95,7 @@ * really available. So we simply advertise only "crypto" support. */ #define HWCAP_SPARC_CRYPTO 0x04000000 /* CRYPTO insns available */ +#define HWCAP_SPARC_ADI 0x08000000 /* ADI available */ #define CORE_DUMP_USE_REGSET diff --git a/arch/sparc/include/uapi/asm/unistd.h b/arch/sparc/include/uapi/asm/unistd.h index efe9479f837b..1c26d440d288 100644 --- a/arch/sparc/include/uapi/asm/unistd.h +++ b/arch/sparc/include/uapi/asm/unistd.h @@ -417,8 +417,13 @@ #define __NR_bpf 349 #define __NR_execveat 350 #define __NR_membarrier 351 +#define __NR_userfaultfd 352 +#define __NR_bind 353 +#define __NR_listen 354 +#define __NR_setsockopt 355 +#define __NR_mlock2 356 -#define NR_syscalls 352 +#define NR_syscalls 357 /* Bitmask values returned from kern_features system call. */ #define KERN_FEATURE_MIXED_MODE_STACK 0x00000001 diff --git a/arch/sparc/kernel/head_64.S b/arch/sparc/kernel/head_64.S index 3d61fcae7ee3..f2d30cab5b3f 100644 --- a/arch/sparc/kernel/head_64.S +++ b/arch/sparc/kernel/head_64.S @@ -946,6 +946,12 @@ ENTRY(__retl_one) mov 1, %o0 ENDPROC(__retl_one) +ENTRY(__retl_one_fp) + VISExitHalf + retl + mov 1, %o0 +ENDPROC(__retl_one_fp) + ENTRY(__ret_one_asi) wr %g0, ASI_AIUS, %asi ret @@ -958,6 +964,13 @@ ENTRY(__retl_one_asi) mov 1, %o0 ENDPROC(__retl_one_asi) +ENTRY(__retl_one_asi_fp) + wr %g0, ASI_AIUS, %asi + VISExitHalf + retl + mov 1, %o0 +ENDPROC(__retl_one_asi_fp) + ENTRY(__retl_o1) retl mov %o1, %o0 diff --git a/arch/sparc/kernel/perf_event.c b/arch/sparc/kernel/perf_event.c index b0da5aedb336..6596f66ce112 100644 --- a/arch/sparc/kernel/perf_event.c +++ b/arch/sparc/kernel/perf_event.c @@ -9,7 +9,7 @@ * Copyright (C) 2008-2009 Red Hat, Inc., Ingo Molnar * Copyright (C) 2009 Jaswinder Singh Rajput * Copyright (C) 2009 Advanced Micro Devices, Inc., Robert Richter - * Copyright (C) 2008-2009 Red Hat, Inc., Peter Zijlstra <pzijlstr@redhat.com> + * Copyright (C) 2008-2009 Red Hat, Inc., Peter Zijlstra */ #include <linux/perf_event.h> @@ -1828,11 +1828,18 @@ static void perf_callchain_user_32(struct perf_callchain_entry *entry, void perf_callchain_user(struct perf_callchain_entry *entry, struct pt_regs *regs) { + u64 saved_fault_address = current_thread_info()->fault_address; + u8 saved_fault_code = get_thread_fault_code(); + mm_segment_t old_fs; + perf_callchain_store(entry, regs->tpc); if (!current->mm) return; + old_fs = get_fs(); + set_fs(USER_DS); + flushw_user(); pagefault_disable(); @@ -1843,4 +1850,8 @@ perf_callchain_user(struct perf_callchain_entry *entry, struct pt_regs *regs) perf_callchain_user_64(entry, regs); pagefault_enable(); + + set_fs(old_fs); + set_thread_fault_code(saved_fault_code); + current_thread_info()->fault_address = saved_fault_address; } diff --git a/arch/sparc/kernel/rtrap_64.S b/arch/sparc/kernel/rtrap_64.S index 39f0c662f4c8..d08bdaffdbfc 100644 --- a/arch/sparc/kernel/rtrap_64.S +++ b/arch/sparc/kernel/rtrap_64.S @@ -73,7 +73,13 @@ rtrap_nmi: ldx [%sp + PTREGS_OFF + PT_V9_TSTATE], %l1 andn %l1, %l4, %l1 srl %l4, 20, %l4 ba,pt %xcc, rtrap_no_irq_enable - wrpr %l4, %pil + nop + /* Do not actually set the %pil here. We will do that + * below after we clear PSTATE_IE in the %pstate register. + * If we re-enable interrupts here, we can recurse down + * the hardirq stack potentially endlessly, causing a + * stack overflow. + */ .align 64 .globl rtrap_irq, rtrap, irqsz_patchme, rtrap_xcall diff --git a/arch/sparc/kernel/setup_64.c b/arch/sparc/kernel/setup_64.c index f7b261749383..f3185e2b028b 100644 --- a/arch/sparc/kernel/setup_64.c +++ b/arch/sparc/kernel/setup_64.c @@ -380,7 +380,8 @@ static const char *hwcaps[] = { */ "mul32", "div32", "fsmuld", "v8plus", "popc", "vis", "vis2", "ASIBlkInit", "fmaf", "vis3", "hpc", "random", "trans", "fjfmau", - "ima", "cspare", "pause", "cbcond", + "ima", "cspare", "pause", "cbcond", NULL /*reserved for crypto */, + "adp", }; static const char *crypto_hwcaps[] = { @@ -396,7 +397,7 @@ void cpucap_info(struct seq_file *m) seq_puts(m, "cpucaps\t\t: "); for (i = 0; i < ARRAY_SIZE(hwcaps); i++) { unsigned long bit = 1UL << i; - if (caps & bit) { + if (hwcaps[i] && (caps & bit)) { seq_printf(m, "%s%s", printed ? "," : "", hwcaps[i]); printed++; @@ -450,7 +451,7 @@ static void __init report_hwcaps(unsigned long caps) for (i = 0; i < ARRAY_SIZE(hwcaps); i++) { unsigned long bit = 1UL << i; - if (caps & bit) + if (hwcaps[i] && (caps & bit)) report_one_hwcap(&printed, hwcaps[i]); } if (caps & HWCAP_SPARC_CRYPTO) @@ -485,7 +486,7 @@ static unsigned long __init mdesc_cpu_hwcap_list(void) for (i = 0; i < ARRAY_SIZE(hwcaps); i++) { unsigned long bit = 1UL << i; - if (!strcmp(prop, hwcaps[i])) { + if (hwcaps[i] && !strcmp(prop, hwcaps[i])) { caps |= bit; break; } diff --git a/arch/sparc/kernel/systbls_32.S b/arch/sparc/kernel/systbls_32.S index cc23b62b6e38..e663b6c78de2 100644 --- a/arch/sparc/kernel/systbls_32.S +++ b/arch/sparc/kernel/systbls_32.S @@ -35,18 +35,18 @@ sys_call_table: /*80*/ .long sys_setgroups16, sys_getpgrp, sys_setgroups, sys_setitimer, sys_ftruncate64 /*85*/ .long sys_swapon, sys_getitimer, sys_setuid, sys_sethostname, sys_setgid /*90*/ .long sys_dup2, sys_setfsuid, sys_fcntl, sys_select, sys_setfsgid -/*95*/ .long sys_fsync, sys_setpriority, sys_nis_syscall, sys_nis_syscall, sys_nis_syscall +/*95*/ .long sys_fsync, sys_setpriority, sys_socket, sys_connect, sys_accept /*100*/ .long sys_getpriority, sys_rt_sigreturn, sys_rt_sigaction, sys_rt_sigprocmask, sys_rt_sigpending /*105*/ .long sys_rt_sigtimedwait, sys_rt_sigqueueinfo, sys_rt_sigsuspend, sys_setresuid, sys_getresuid -/*110*/ .long sys_setresgid, sys_getresgid, sys_setregid, sys_nis_syscall, sys_nis_syscall -/*115*/ .long sys_getgroups, sys_gettimeofday, sys_getrusage, sys_nis_syscall, sys_getcwd +/*110*/ .long sys_setresgid, sys_getresgid, sys_setregid, sys_recvmsg, sys_sendmsg +/*115*/ .long sys_getgroups, sys_gettimeofday, sys_getrusage, sys_getsockopt, sys_getcwd /*120*/ .long sys_readv, sys_writev, sys_settimeofday, sys_fchown16, sys_fchmod -/*125*/ .long sys_nis_syscall, sys_setreuid16, sys_setregid16, sys_rename, sys_truncate -/*130*/ .long sys_ftruncate, sys_flock, sys_lstat64, sys_nis_syscall, sys_nis_syscall -/*135*/ .long sys_nis_syscall, sys_mkdir, sys_rmdir, sys_utimes, sys_stat64 -/*140*/ .long sys_sendfile64, sys_nis_syscall, sys_futex, sys_gettid, sys_getrlimit +/*125*/ .long sys_recvfrom, sys_setreuid16, sys_setregid16, sys_rename, sys_truncate +/*130*/ .long sys_ftruncate, sys_flock, sys_lstat64, sys_sendto, sys_shutdown +/*135*/ .long sys_socketpair, sys_mkdir, sys_rmdir, sys_utimes, sys_stat64 +/*140*/ .long sys_sendfile64, sys_getpeername, sys_futex, sys_gettid, sys_getrlimit /*145*/ .long sys_setrlimit, sys_pivot_root, sys_prctl, sys_pciconfig_read, sys_pciconfig_write -/*150*/ .long sys_nis_syscall, sys_inotify_init, sys_inotify_add_watch, sys_poll, sys_getdents64 +/*150*/ .long sys_getsockname, sys_inotify_init, sys_inotify_add_watch, sys_poll, sys_getdents64 /*155*/ .long sys_fcntl64, sys_inotify_rm_watch, sys_statfs, sys_fstatfs, sys_oldumount /*160*/ .long sys_sched_setaffinity, sys_sched_getaffinity, sys_getdomainname, sys_setdomainname, sys_nis_syscall /*165*/ .long sys_quotactl, sys_set_tid_address, sys_mount, sys_ustat, sys_setxattr @@ -87,4 +87,5 @@ sys_call_table: /*335*/ .long sys_syncfs, sys_sendmmsg, sys_setns, sys_process_vm_readv, sys_process_vm_writev /*340*/ .long sys_ni_syscall, sys_kcmp, sys_finit_module, sys_sched_setattr, sys_sched_getattr /*345*/ .long sys_renameat2, sys_seccomp, sys_getrandom, sys_memfd_create, sys_bpf -/*350*/ .long sys_execveat, sys_membarrier +/*350*/ .long sys_execveat, sys_membarrier, sys_userfaultfd, sys_bind, sys_listen +/*355*/ .long sys_setsockopt, sys_mlock2 diff --git a/arch/sparc/kernel/systbls_64.S b/arch/sparc/kernel/systbls_64.S index f229468a7479..1557121f4cdc 100644 --- a/arch/sparc/kernel/systbls_64.S +++ b/arch/sparc/kernel/systbls_64.S @@ -37,15 +37,15 @@ sys_call_table32: /*80*/ .word sys_setgroups16, sys_getpgrp, sys_setgroups, compat_sys_setitimer, sys32_ftruncate64 .word sys_swapon, compat_sys_getitimer, sys_setuid, sys_sethostname, sys_setgid /*90*/ .word sys_dup2, sys_setfsuid, compat_sys_fcntl, sys32_select, sys_setfsgid - .word sys_fsync, sys_setpriority, sys_nis_syscall, sys_nis_syscall, sys_nis_syscall + .word sys_fsync, sys_setpriority, sys_socket, sys_connect, sys_accept /*100*/ .word sys_getpriority, sys32_rt_sigreturn, compat_sys_rt_sigaction, compat_sys_rt_sigprocmask, compat_sys_rt_sigpending .word compat_sys_rt_sigtimedwait, compat_sys_rt_sigqueueinfo, compat_sys_rt_sigsuspend, sys_setresuid, sys_getresuid -/*110*/ .word sys_setresgid, sys_getresgid, sys_setregid, sys_nis_syscall, sys_nis_syscall - .word sys_getgroups, compat_sys_gettimeofday, compat_sys_getrusage, sys_nis_syscall, sys_getcwd +/*110*/ .word sys_setresgid, sys_getresgid, sys_setregid, compat_sys_recvmsg, compat_sys_sendmsg + .word sys_getgroups, compat_sys_gettimeofday, compat_sys_getrusage, compat_sys_getsockopt, sys_getcwd /*120*/ .word compat_sys_readv, compat_sys_writev, compat_sys_settimeofday, sys_fchown16, sys_fchmod - .word sys_nis_syscall, sys_setreuid16, sys_setregid16, sys_rename, compat_sys_truncate -/*130*/ .word compat_sys_ftruncate, sys_flock, compat_sys_lstat64, sys_nis_syscall, sys_nis_syscall - .word sys_nis_syscall, sys_mkdir, sys_rmdir, compat_sys_utimes, compat_sys_stat64 + .word sys_recvfrom, sys_setreuid16, sys_setregid16, sys_rename, compat_sys_truncate +/*130*/ .word compat_sys_ftruncate, sys_flock, compat_sys_lstat64, sys_sendto, sys_shutdown + .word sys_socketpair, sys_mkdir, sys_rmdir, compat_sys_utimes, compat_sys_stat64 /*140*/ .word sys_sendfile64, sys_nis_syscall, sys32_futex, sys_gettid, compat_sys_getrlimit .word compat_sys_setrlimit, sys_pivot_root, sys_prctl, sys_pciconfig_read, sys_pciconfig_write /*150*/ .word sys_nis_syscall, sys_inotify_init, sys_inotify_add_watch, sys_poll, sys_getdents64 @@ -88,7 +88,8 @@ sys_call_table32: .word sys_syncfs, compat_sys_sendmmsg, sys_setns, compat_sys_process_vm_readv, compat_sys_process_vm_writev /*340*/ .word sys_kern_features, sys_kcmp, sys_finit_module, sys_sched_setattr, sys_sched_getattr .word sys32_renameat2, sys_seccomp, sys_getrandom, sys_memfd_create, sys_bpf -/*350*/ .word sys32_execveat, sys_membarrier +/*350*/ .word sys32_execveat, sys_membarrier, sys_userfaultfd, sys_bind, sys_listen + .word compat_sys_setsockopt, sys_mlock2 #endif /* CONFIG_COMPAT */ @@ -168,4 +169,5 @@ sys_call_table: .word sys_syncfs, sys_sendmmsg, sys_setns, sys_process_vm_readv, sys_process_vm_writev /*340*/ .word sys_kern_features, sys_kcmp, sys_finit_module, sys_sched_setattr, sys_sched_getattr .word sys_renameat2, sys_seccomp, sys_getrandom, sys_memfd_create, sys_bpf -/*350*/ .word sys64_execveat, sys_membarrier +/*350*/ .word sys64_execveat, sys_membarrier, sys_userfaultfd, sys_bind, sys_listen + .word sys_setsockopt, sys_mlock2 diff --git a/arch/sparc/lib/NG2copy_from_user.S b/arch/sparc/lib/NG2copy_from_user.S index 119ccb9a54f4..d5242b8c4f94 100644 --- a/arch/sparc/lib/NG2copy_from_user.S +++ b/arch/sparc/lib/NG2copy_from_user.S @@ -11,6 +11,14 @@ .text; \ .align 4; +#define EX_LD_FP(x) \ +98: x; \ + .section __ex_table,"a";\ + .align 4; \ + .word 98b, __retl_one_asi_fp;\ + .text; \ + .align 4; + #ifndef ASI_AIUS #define ASI_AIUS 0x11 #endif diff --git a/arch/sparc/lib/NG2copy_to_user.S b/arch/sparc/lib/NG2copy_to_user.S index 7fe1ccefd9d0..4e962d993b10 100644 --- a/arch/sparc/lib/NG2copy_to_user.S +++ b/arch/sparc/lib/NG2copy_to_user.S @@ -11,6 +11,14 @@ .text; \ .align 4; +#define EX_ST_FP(x) \ +98: x; \ + .section __ex_table,"a";\ + .align 4; \ + .word 98b, __retl_one_asi_fp;\ + .text; \ + .align 4; + #ifndef ASI_AIUS #define ASI_AIUS 0x11 #endif diff --git a/arch/sparc/lib/NG2memcpy.S b/arch/sparc/lib/NG2memcpy.S index 30eee6e8a81b..d5f585df2f3f 100644 --- a/arch/sparc/lib/NG2memcpy.S +++ b/arch/sparc/lib/NG2memcpy.S @@ -34,10 +34,16 @@ #ifndef EX_LD #define EX_LD(x) x #endif +#ifndef EX_LD_FP +#define EX_LD_FP(x) x +#endif #ifndef EX_ST #define EX_ST(x) x #endif +#ifndef EX_ST_FP +#define EX_ST_FP(x) x +#endif #ifndef EX_RETVAL #define EX_RETVAL(x) x @@ -134,40 +140,40 @@ fsrc2 %x6, %f12; \ fsrc2 %x7, %f14; #define FREG_LOAD_1(base, x0) \ - EX_LD(LOAD(ldd, base + 0x00, %x0)) + EX_LD_FP(LOAD(ldd, base + 0x00, %x0)) #define FREG_LOAD_2(base, x0, x1) \ - EX_LD(LOAD(ldd, base + 0x00, %x0)); \ - EX_LD(LOAD(ldd, base + 0x08, %x1)); + EX_LD_FP(LOAD(ldd, base + 0x00, %x0)); \ + EX_LD_FP(LOAD(ldd, base + 0x08, %x1)); #define FREG_LOAD_3(base, x0, x1, x2) \ - EX_LD(LOAD(ldd, base + 0x00, %x0)); \ - EX_LD(LOAD(ldd, base + 0x08, %x1)); \ - EX_LD(LOAD(ldd, base + 0x10, %x2)); + EX_LD_FP(LOAD(ldd, base + 0x00, %x0)); \ + EX_LD_FP(LOAD(ldd, base + 0x08, %x1)); \ + EX_LD_FP(LOAD(ldd, base + 0x10, %x2)); #define FREG_LOAD_4(base, x0, x1, x2, x3) \ - EX_LD(LOAD(ldd, base + 0x00, %x0)); \ - EX_LD(LOAD(ldd, base + 0x08, %x1)); \ - EX_LD(LOAD(ldd, base + 0x10, %x2)); \ - EX_LD(LOAD(ldd, base + 0x18, %x3)); + EX_LD_FP(LOAD(ldd, base + 0x00, %x0)); \ + EX_LD_FP(LOAD(ldd, base + 0x08, %x1)); \ + EX_LD_FP(LOAD(ldd, base + 0x10, %x2)); \ + EX_LD_FP(LOAD(ldd, base + 0x18, %x3)); #define FREG_LOAD_5(base, x0, x1, x2, x3, x4) \ - EX_LD(LOAD(ldd, base + 0x00, %x0)); \ - EX_LD(LOAD(ldd, base + 0x08, %x1)); \ - EX_LD(LOAD(ldd, base + 0x10, %x2)); \ - EX_LD(LOAD(ldd, base + 0x18, %x3)); \ - EX_LD(LOAD(ldd, base + 0x20, %x4)); + EX_LD_FP(LOAD(ldd, base + 0x00, %x0)); \ + EX_LD_FP(LOAD(ldd, base + 0x08, %x1)); \ + EX_LD_FP(LOAD(ldd, base + 0x10, %x2)); \ + EX_LD_FP(LOAD(ldd, base + 0x18, %x3)); \ + EX_LD_FP(LOAD(ldd, base + 0x20, %x4)); #define FREG_LOAD_6(base, x0, x1, x2, x3, x4, x5) \ - EX_LD(LOAD(ldd, base + 0x00, %x0)); \ - EX_LD(LOAD(ldd, base + 0x08, %x1)); \ - EX_LD(LOAD(ldd, base + 0x10, %x2)); \ - EX_LD(LOAD(ldd, base + 0x18, %x3)); \ - EX_LD(LOAD(ldd, base + 0x20, %x4)); \ - EX_LD(LOAD(ldd, base + 0x28, %x5)); + EX_LD_FP(LOAD(ldd, base + 0x00, %x0)); \ + EX_LD_FP(LOAD(ldd, base + 0x08, %x1)); \ + EX_LD_FP(LOAD(ldd, base + 0x10, %x2)); \ + EX_LD_FP(LOAD(ldd, base + 0x18, %x3)); \ + EX_LD_FP(LOAD(ldd, base + 0x20, %x4)); \ + EX_LD_FP(LOAD(ldd, base + 0x28, %x5)); #define FREG_LOAD_7(base, x0, x1, x2, x3, x4, x5, x6) \ - EX_LD(LOAD(ldd, base + 0x00, %x0)); \ - EX_LD(LOAD(ldd, base + 0x08, %x1)); \ - EX_LD(LOAD(ldd, base + 0x10, %x2)); \ - EX_LD(LOAD(ldd, base + 0x18, %x3)); \ - EX_LD(LOAD(ldd, base + 0x20, %x4)); \ - EX_LD(LOAD(ldd, base + 0x28, %x5)); \ - EX_LD(LOAD(ldd, base + 0x30, %x6)); + EX_LD_FP(LOAD(ldd, base + 0x00, %x0)); \ + EX_LD_FP(LOAD(ldd, base + 0x08, %x1)); \ + EX_LD_FP(LOAD(ldd, base + 0x10, %x2)); \ + EX_LD_FP(LOAD(ldd, base + 0x18, %x3)); \ + EX_LD_FP(LOAD(ldd, base + 0x20, %x4)); \ + EX_LD_FP(LOAD(ldd, base + 0x28, %x5)); \ + EX_LD_FP(LOAD(ldd, base + 0x30, %x6)); .register %g2,#scratch .register %g3,#scratch @@ -275,11 +281,11 @@ FUNC_NAME: /* %o0=dst, %o1=src, %o2=len */ nop /* fall through for 0 < low bits < 8 */ 110: sub %o4, 64, %g2 - EX_LD(LOAD_BLK(%g2, %f0)) -1: EX_ST(STORE_INIT(%g0, %o4 + %g3)) - EX_LD(LOAD_BLK(%o4, %f16)) + EX_LD_FP(LOAD_BLK(%g2, %f0)) +1: EX_ST_FP(STORE_INIT(%g0, %o4 + %g3)) + EX_LD_FP(LOAD_BLK(%o4, %f16)) FREG_FROB(f0, f2, f4, f6, f8, f10, f12, f14, f16) - EX_ST(STORE_BLK(%f0, %o4 + %g3)) + EX_ST_FP(STORE_BLK(%f0, %o4 + %g3)) FREG_MOVE_8(f16, f18, f20, f22, f24, f26, f28, f30) subcc %g1, 64, %g1 add %o4, 64, %o4 @@ -290,10 +296,10 @@ FUNC_NAME: /* %o0=dst, %o1=src, %o2=len */ 120: sub %o4, 56, %g2 FREG_LOAD_7(%g2, f0, f2, f4, f6, f8, f10, f12) -1: EX_ST(STORE_INIT(%g0, %o4 + %g3)) - EX_LD(LOAD_BLK(%o4, %f16)) +1: EX_ST_FP(STORE_INIT(%g0, %o4 + %g3)) + EX_LD_FP(LOAD_BLK(%o4, %f16)) FREG_FROB(f0, f2, f4, f6, f8, f10, f12, f16, f18) - EX_ST(STORE_BLK(%f0, %o4 + %g3)) + EX_ST_FP(STORE_BLK(%f0, %o4 + %g3)) FREG_MOVE_7(f18, f20, f22, f24, f26, f28, f30) subcc %g1, 64, %g1 add %o4, 64, %o4 @@ -304,10 +310,10 @@ FUNC_NAME: /* %o0=dst, %o1=src, %o2=len */ 130: sub %o4, 48, %g2 FREG_LOAD_6(%g2, f0, f2, f4, f6, f8, f10) -1: EX_ST(STORE_INIT(%g0, %o4 + %g3)) - EX_LD(LOAD_BLK(%o4, %f16)) +1: EX_ST_FP(STORE_INIT(%g0, %o4 + %g3)) + EX_LD_FP(LOAD_BLK(%o4, %f16)) FREG_FROB(f0, f2, f4, f6, f8, f10, f16, f18, f20) - EX_ST(STORE_BLK(%f0, %o4 + %g3)) + EX_ST_FP(STORE_BLK(%f0, %o4 + %g3)) FREG_MOVE_6(f20, f22, f24, f26, f28, f30) subcc %g1, 64, %g1 add %o4, 64, %o4 @@ -318,10 +324,10 @@ FUNC_NAME: /* %o0=dst, %o1=src, %o2=len */ 140: sub %o4, 40, %g2 FREG_LOAD_5(%g2, f0, f2, f4, f6, f8) -1: EX_ST(STORE_INIT(%g0, %o4 + %g3)) - EX_LD(LOAD_BLK(%o4, %f16)) +1: EX_ST_FP(STORE_INIT(%g0, %o4 + %g3)) + EX_LD_FP(LOAD_BLK(%o4, %f16)) FREG_FROB(f0, f2, f4, f6, f8, f16, f18, f20, f22) - EX_ST(STORE_BLK(%f0, %o4 + %g3)) + EX_ST_FP(STORE_BLK(%f0, %o4 + %g3)) FREG_MOVE_5(f22, f24, f26, f28, f30) subcc %g1, 64, %g1 add %o4, 64, %o4 @@ -332,10 +338,10 @@ FUNC_NAME: /* %o0=dst, %o1=src, %o2=len */ 150: sub %o4, 32, %g2 FREG_LOAD_4(%g2, f0, f2, f4, f6) -1: EX_ST(STORE_INIT(%g0, %o4 + %g3)) - EX_LD(LOAD_BLK(%o4, %f16)) +1: EX_ST_FP(STORE_INIT(%g0, %o4 + %g3)) + EX_LD_FP(LOAD_BLK(%o4, %f16)) FREG_FROB(f0, f2, f4, f6, f16, f18, f20, f22, f24) - EX_ST(STORE_BLK(%f0, %o4 + %g3)) + EX_ST_FP(STORE_BLK(%f0, %o4 + %g3)) FREG_MOVE_4(f24, f26, f28, f30) subcc %g1, 64, %g1 add %o4, 64, %o4 @@ -346,10 +352,10 @@ FUNC_NAME: /* %o0=dst, %o1=src, %o2=len */ 160: sub %o4, 24, %g2 FREG_LOAD_3(%g2, f0, f2, f4) -1: EX_ST(STORE_INIT(%g0, %o4 + %g3)) - EX_LD(LOAD_BLK(%o4, %f16)) +1: EX_ST_FP(STORE_INIT(%g0, %o4 + %g3)) + EX_LD_FP(LOAD_BLK(%o4, %f16)) FREG_FROB(f0, f2, f4, f16, f18, f20, f22, f24, f26) - EX_ST(STORE_BLK(%f0, %o4 + %g3)) + EX_ST_FP(STORE_BLK(%f0, %o4 + %g3)) FREG_MOVE_3(f26, f28, f30) subcc %g1, 64, %g1 add %o4, 64, %o4 @@ -360,10 +366,10 @@ FUNC_NAME: /* %o0=dst, %o1=src, %o2=len */ 170: sub %o4, 16, %g2 FREG_LOAD_2(%g2, f0, f2) -1: EX_ST(STORE_INIT(%g0, %o4 + %g3)) - EX_LD(LOAD_BLK(%o4, %f16)) +1: EX_ST_FP(STORE_INIT(%g0, %o4 + %g3)) + EX_LD_FP(LOAD_BLK(%o4, %f16)) FREG_FROB(f0, f2, f16, f18, f20, f22, f24, f26, f28) - EX_ST(STORE_BLK(%f0, %o4 + %g3)) + EX_ST_FP(STORE_BLK(%f0, %o4 + %g3)) FREG_MOVE_2(f28, f30) subcc %g1, 64, %g1 add %o4, 64, %o4 @@ -374,10 +380,10 @@ FUNC_NAME: /* %o0=dst, %o1=src, %o2=len */ 180: sub %o4, 8, %g2 FREG_LOAD_1(%g2, f0) -1: EX_ST(STORE_INIT(%g0, %o4 + %g3)) - EX_LD(LOAD_BLK(%o4, %f16)) +1: EX_ST_FP(STORE_INIT(%g0, %o4 + %g3)) + EX_LD_FP(LOAD_BLK(%o4, %f16)) FREG_FROB(f0, f16, f18, f20, f22, f24, f26, f28, f30) - EX_ST(STORE_BLK(%f0, %o4 + %g3)) + EX_ST_FP(STORE_BLK(%f0, %o4 + %g3)) FREG_MOVE_1(f30) subcc %g1, 64, %g1 add %o4, 64, %o4 @@ -387,10 +393,10 @@ FUNC_NAME: /* %o0=dst, %o1=src, %o2=len */ nop 190: -1: EX_ST(STORE_INIT(%g0, %o4 + %g3)) +1: EX_ST_FP(STORE_INIT(%g0, %o4 + %g3)) subcc %g1, 64, %g1 - EX_LD(LOAD_BLK(%o4, %f0)) - EX_ST(STORE_BLK(%f0, %o4 + %g3)) + EX_LD_FP(LOAD_BLK(%o4, %f0)) + EX_ST_FP(STORE_BLK(%f0, %o4 + %g3)) add %o4, 64, %o4 bne,pt %xcc, 1b LOAD(prefetch, %o4 + 64, #one_read) diff --git a/arch/sparc/lib/NG4copy_from_user.S b/arch/sparc/lib/NG4copy_from_user.S index fd9f903ffa32..2e8ee7ad07a9 100644 --- a/arch/sparc/lib/NG4copy_from_user.S +++ b/arch/sparc/lib/NG4copy_from_user.S @@ -11,6 +11,14 @@ .text; \ .align 4; +#define EX_LD_FP(x) \ +98: x; \ + .section __ex_table,"a";\ + .align 4; \ + .word 98b, __retl_one_asi_fp;\ + .text; \ + .align 4; + #ifndef ASI_AIUS #define ASI_AIUS 0x11 #endif diff --git a/arch/sparc/lib/NG4copy_to_user.S b/arch/sparc/lib/NG4copy_to_user.S index 9744c4540a8d..be0bf4590df8 100644 --- a/arch/sparc/lib/NG4copy_to_user.S +++ b/arch/sparc/lib/NG4copy_to_user.S @@ -11,6 +11,14 @@ .text; \ .align 4; +#define EX_ST_FP(x) \ +98: x; \ + .section __ex_table,"a";\ + .align 4; \ + .word 98b, __retl_one_asi_fp;\ + .text; \ + .align 4; + #ifndef ASI_AIUS #define ASI_AIUS 0x11 #endif diff --git a/arch/sparc/lib/NG4memcpy.S b/arch/sparc/lib/NG4memcpy.S index 83aeeb1dffdb..8e13ee1f4454 100644 --- a/arch/sparc/lib/NG4memcpy.S +++ b/arch/sparc/lib/NG4memcpy.S @@ -48,10 +48,16 @@ #ifndef EX_LD #define EX_LD(x) x #endif +#ifndef EX_LD_FP +#define EX_LD_FP(x) x +#endif #ifndef EX_ST #define EX_ST(x) x #endif +#ifndef EX_ST_FP +#define EX_ST_FP(x) x +#endif #ifndef EX_RETVAL #define EX_RETVAL(x) x @@ -210,17 +216,17 @@ FUNC_NAME: /* %o0=dst, %o1=src, %o2=len */ sub %o2, %o4, %o2 alignaddr %o1, %g0, %g1 add %o1, %o4, %o1 - EX_LD(LOAD(ldd, %g1 + 0x00, %f0)) -1: EX_LD(LOAD(ldd, %g1 + 0x08, %f2)) + EX_LD_FP(LOAD(ldd, %g1 + 0x00, %f0)) +1: EX_LD_FP(LOAD(ldd, %g1 + 0x08, %f2)) subcc %o4, 0x40, %o4 - EX_LD(LOAD(ldd, %g1 + 0x10, %f4)) - EX_LD(LOAD(ldd, %g1 + 0x18, %f6)) - EX_LD(LOAD(ldd, %g1 + 0x20, %f8)) - EX_LD(LOAD(ldd, %g1 + 0x28, %f10)) - EX_LD(LOAD(ldd, %g1 + 0x30, %f12)) - EX_LD(LOAD(ldd, %g1 + 0x38, %f14)) + EX_LD_FP(LOAD(ldd, %g1 + 0x10, %f4)) + EX_LD_FP(LOAD(ldd, %g1 + 0x18, %f6)) + EX_LD_FP(LOAD(ldd, %g1 + 0x20, %f8)) + EX_LD_FP(LOAD(ldd, %g1 + 0x28, %f10)) + EX_LD_FP(LOAD(ldd, %g1 + 0x30, %f12)) + EX_LD_FP(LOAD(ldd, %g1 + 0x38, %f14)) faligndata %f0, %f2, %f16 - EX_LD(LOAD(ldd, %g1 + 0x40, %f0)) + EX_LD_FP(LOAD(ldd, %g1 + 0x40, %f0)) faligndata %f2, %f4, %f18 add %g1, 0x40, %g1 faligndata %f4, %f6, %f20 @@ -229,14 +235,14 @@ FUNC_NAME: /* %o0=dst, %o1=src, %o2=len */ faligndata %f10, %f12, %f26 faligndata %f12, %f14, %f28 faligndata %f14, %f0, %f30 - EX_ST(STORE(std, %f16, %o0 + 0x00)) - EX_ST(STORE(std, %f18, %o0 + 0x08)) - EX_ST(STORE(std, %f20, %o0 + 0x10)) - EX_ST(STORE(std, %f22, %o0 + 0x18)) - EX_ST(STORE(std, %f24, %o0 + 0x20)) - EX_ST(STORE(std, %f26, %o0 + 0x28)) - EX_ST(STORE(std, %f28, %o0 + 0x30)) - EX_ST(STORE(std, %f30, %o0 + 0x38)) + EX_ST_FP(STORE(std, %f16, %o0 + 0x00)) + EX_ST_FP(STORE(std, %f18, %o0 + 0x08)) + EX_ST_FP(STORE(std, %f20, %o0 + 0x10)) + EX_ST_FP(STORE(std, %f22, %o0 + 0x18)) + EX_ST_FP(STORE(std, %f24, %o0 + 0x20)) + EX_ST_FP(STORE(std, %f26, %o0 + 0x28)) + EX_ST_FP(STORE(std, %f28, %o0 + 0x30)) + EX_ST_FP(STORE(std, %f30, %o0 + 0x38)) add %o0, 0x40, %o0 bne,pt %icc, 1b LOAD(prefetch, %g1 + 0x200, #n_reads_strong) diff --git a/arch/sparc/lib/U1copy_from_user.S b/arch/sparc/lib/U1copy_from_user.S index a6ae2ea04bf5..ecc5692fa2b4 100644 --- a/arch/sparc/lib/U1copy_from_user.S +++ b/arch/sparc/lib/U1copy_from_user.S @@ -11,6 +11,14 @@ .text; \ .align 4; +#define EX_LD_FP(x) \ +98: x; \ + .section __ex_table,"a";\ + .align 4; \ + .word 98b, __retl_one_fp;\ + .text; \ + .align 4; + #define FUNC_NAME ___copy_from_user #define LOAD(type,addr,dest) type##a [addr] %asi, dest #define LOAD_BLK(addr,dest) ldda [addr] ASI_BLK_AIUS, dest diff --git a/arch/sparc/lib/U1copy_to_user.S b/arch/sparc/lib/U1copy_to_user.S index f4b970eeb485..9eea392e44d4 100644 --- a/arch/sparc/lib/U1copy_to_user.S +++ b/arch/sparc/lib/U1copy_to_user.S @@ -11,6 +11,14 @@ .text; \ .align 4; +#define EX_ST_FP(x) \ +98: x; \ + .section __ex_table,"a";\ + .align 4; \ + .word 98b, __retl_one_fp;\ + .text; \ + .align 4; + #define FUNC_NAME ___copy_to_user #define STORE(type,src,addr) type##a src, [addr] ASI_AIUS #define STORE_BLK(src,addr) stda src, [addr] ASI_BLK_AIUS diff --git a/arch/sparc/lib/U1memcpy.S b/arch/sparc/lib/U1memcpy.S index b67142b7768e..3e6209ebb7d7 100644 --- a/arch/sparc/lib/U1memcpy.S +++ b/arch/sparc/lib/U1memcpy.S @@ -25,10 +25,16 @@ #ifndef EX_LD #define EX_LD(x) x #endif +#ifndef EX_LD_FP +#define EX_LD_FP(x) x +#endif #ifndef EX_ST #define EX_ST(x) x #endif +#ifndef EX_ST_FP +#define EX_ST_FP(x) x +#endif #ifndef EX_RETVAL #define EX_RETVAL(x) x @@ -73,8 +79,8 @@ faligndata %f8, %f9, %f62; #define MAIN_LOOP_CHUNK(src, dest, fdest, fsrc, len, jmptgt) \ - EX_LD(LOAD_BLK(%src, %fdest)); \ - EX_ST(STORE_BLK(%fsrc, %dest)); \ + EX_LD_FP(LOAD_BLK(%src, %fdest)); \ + EX_ST_FP(STORE_BLK(%fsrc, %dest)); \ add %src, 0x40, %src; \ subcc %len, 0x40, %len; \ be,pn %xcc, jmptgt; \ @@ -89,12 +95,12 @@ #define DO_SYNC membar #Sync; #define STORE_SYNC(dest, fsrc) \ - EX_ST(STORE_BLK(%fsrc, %dest)); \ + EX_ST_FP(STORE_BLK(%fsrc, %dest)); \ add %dest, 0x40, %dest; \ DO_SYNC #define STORE_JUMP(dest, fsrc, target) \ - EX_ST(STORE_BLK(%fsrc, %dest)); \ + EX_ST_FP(STORE_BLK(%fsrc, %dest)); \ add %dest, 0x40, %dest; \ ba,pt %xcc, target; \ nop; @@ -103,7 +109,7 @@ subcc %left, 8, %left;\ bl,pn %xcc, 95f; \ faligndata %f0, %f1, %f48; \ - EX_ST(STORE(std, %f48, %dest)); \ + EX_ST_FP(STORE(std, %f48, %dest)); \ add %dest, 8, %dest; #define UNEVEN_VISCHUNK_LAST(dest, f0, f1, left) \ @@ -160,8 +166,8 @@ FUNC_NAME: /* %o0=dst, %o1=src, %o2=len */ and %g2, 0x38, %g2 1: subcc %g1, 0x1, %g1 - EX_LD(LOAD(ldub, %o1 + 0x00, %o3)) - EX_ST(STORE(stb, %o3, %o1 + %GLOBAL_SPARE)) + EX_LD_FP(LOAD(ldub, %o1 + 0x00, %o3)) + EX_ST_FP(STORE(stb, %o3, %o1 + %GLOBAL_SPARE)) bgu,pt %XCC, 1b add %o1, 0x1, %o1 @@ -172,20 +178,20 @@ FUNC_NAME: /* %o0=dst, %o1=src, %o2=len */ be,pt %icc, 3f alignaddr %o1, %g0, %o1 - EX_LD(LOAD(ldd, %o1, %f4)) -1: EX_LD(LOAD(ldd, %o1 + 0x8, %f6)) + EX_LD_FP(LOAD(ldd, %o1, %f4)) +1: EX_LD_FP(LOAD(ldd, %o1 + 0x8, %f6)) add %o1, 0x8, %o1 subcc %g2, 0x8, %g2 faligndata %f4, %f6, %f0 - EX_ST(STORE(std, %f0, %o0)) + EX_ST_FP(STORE(std, %f0, %o0)) be,pn %icc, 3f add %o0, 0x8, %o0 - EX_LD(LOAD(ldd, %o1 + 0x8, %f4)) + EX_LD_FP(LOAD(ldd, %o1 + 0x8, %f4)) add %o1, 0x8, %o1 subcc %g2, 0x8, %g2 faligndata %f6, %f4, %f0 - EX_ST(STORE(std, %f0, %o0)) + EX_ST_FP(STORE(std, %f0, %o0)) bne,pt %icc, 1b add %o0, 0x8, %o0 @@ -208,13 +214,13 @@ FUNC_NAME: /* %o0=dst, %o1=src, %o2=len */ add %g1, %GLOBAL_SPARE, %g1 subcc %o2, %g3, %o2 - EX_LD(LOAD_BLK(%o1, %f0)) + EX_LD_FP(LOAD_BLK(%o1, %f0)) add %o1, 0x40, %o1 add %g1, %g3, %g1 - EX_LD(LOAD_BLK(%o1, %f16)) + EX_LD_FP(LOAD_BLK(%o1, %f16)) add %o1, 0x40, %o1 sub %GLOBAL_SPARE, 0x80, %GLOBAL_SPARE - EX_LD(LOAD_BLK(%o1, %f32)) + EX_LD_FP(LOAD_BLK(%o1, %f32)) add %o1, 0x40, %o1 /* There are 8 instances of the unrolled loop, @@ -426,28 +432,28 @@ FUNC_NAME: /* %o0=dst, %o1=src, %o2=len */ 62: FINISH_VISCHUNK(o0, f44, f46, g3) 63: UNEVEN_VISCHUNK_LAST(o0, f46, f0, g3) -93: EX_LD(LOAD(ldd, %o1, %f2)) +93: EX_LD_FP(LOAD(ldd, %o1, %f2)) add %o1, 8, %o1 subcc %g3, 8, %g3 faligndata %f0, %f2, %f8 - EX_ST(STORE(std, %f8, %o0)) + EX_ST_FP(STORE(std, %f8, %o0)) bl,pn %xcc, 95f add %o0, 8, %o0 - EX_LD(LOAD(ldd, %o1, %f0)) + EX_LD_FP(LOAD(ldd, %o1, %f0)) add %o1, 8, %o1 subcc %g3, 8, %g3 faligndata %f2, %f0, %f8 - EX_ST(STORE(std, %f8, %o0)) + EX_ST_FP(STORE(std, %f8, %o0)) bge,pt %xcc, 93b add %o0, 8, %o0 95: brz,pt %o2, 2f mov %g1, %o1 -1: EX_LD(LOAD(ldub, %o1, %o3)) +1: EX_LD_FP(LOAD(ldub, %o1, %o3)) add %o1, 1, %o1 subcc %o2, 1, %o2 - EX_ST(STORE(stb, %o3, %o0)) + EX_ST_FP(STORE(stb, %o3, %o0)) bne,pt %xcc, 1b add %o0, 1, %o0 diff --git a/arch/sparc/lib/U3copy_from_user.S b/arch/sparc/lib/U3copy_from_user.S index b1acd1331c33..88ad73d86fe4 100644 --- a/arch/sparc/lib/U3copy_from_user.S +++ b/arch/sparc/lib/U3copy_from_user.S @@ -11,6 +11,14 @@ .text; \ .align 4; +#define EX_LD_FP(x) \ +98: x; \ + .section __ex_table,"a";\ + .align 4; \ + .word 98b, __retl_one_fp;\ + .text; \ + .align 4; + #define FUNC_NAME U3copy_from_user #define LOAD(type,addr,dest) type##a [addr] %asi, dest #define EX_RETVAL(x) 0 diff --git a/arch/sparc/lib/U3copy_to_user.S b/arch/sparc/lib/U3copy_to_user.S index ef1e493afdfa..845139d75537 100644 --- a/arch/sparc/lib/U3copy_to_user.S +++ b/arch/sparc/lib/U3copy_to_user.S @@ -11,6 +11,14 @@ .text; \ .align 4; +#define EX_ST_FP(x) \ +98: x; \ + .section __ex_table,"a";\ + .align 4; \ + .word 98b, __retl_one_fp;\ + .text; \ + .align 4; + #define FUNC_NAME U3copy_to_user #define STORE(type,src,addr) type##a src, [addr] ASI_AIUS #define STORE_BLK(src,addr) stda src, [addr] ASI_BLK_AIUS diff --git a/arch/sparc/lib/U3memcpy.S b/arch/sparc/lib/U3memcpy.S index 7cae9cc6a204..491ee69e4995 100644 --- a/arch/sparc/lib/U3memcpy.S +++ b/arch/sparc/lib/U3memcpy.S @@ -24,10 +24,16 @@ #ifndef EX_LD #define EX_LD(x) x #endif +#ifndef EX_LD_FP +#define EX_LD_FP(x) x +#endif #ifndef EX_ST #define EX_ST(x) x #endif +#ifndef EX_ST_FP +#define EX_ST_FP(x) x +#endif #ifndef EX_RETVAL #define EX_RETVAL(x) x @@ -120,8 +126,8 @@ FUNC_NAME: /* %o0=dst, %o1=src, %o2=len */ and %g2, 0x38, %g2 1: subcc %g1, 0x1, %g1 - EX_LD(LOAD(ldub, %o1 + 0x00, %o3)) - EX_ST(STORE(stb, %o3, %o1 + GLOBAL_SPARE)) + EX_LD_FP(LOAD(ldub, %o1 + 0x00, %o3)) + EX_ST_FP(STORE(stb, %o3, %o1 + GLOBAL_SPARE)) bgu,pt %XCC, 1b add %o1, 0x1, %o1 @@ -132,20 +138,20 @@ FUNC_NAME: /* %o0=dst, %o1=src, %o2=len */ be,pt %icc, 3f alignaddr %o1, %g0, %o1 - EX_LD(LOAD(ldd, %o1, %f4)) -1: EX_LD(LOAD(ldd, %o1 + 0x8, %f6)) + EX_LD_FP(LOAD(ldd, %o1, %f4)) +1: EX_LD_FP(LOAD(ldd, %o1 + 0x8, %f6)) add %o1, 0x8, %o1 subcc %g2, 0x8, %g2 faligndata %f4, %f6, %f0 - EX_ST(STORE(std, %f0, %o0)) + EX_ST_FP(STORE(std, %f0, %o0)) be,pn %icc, 3f add %o0, 0x8, %o0 - EX_LD(LOAD(ldd, %o1 + 0x8, %f4)) + EX_LD_FP(LOAD(ldd, %o1 + 0x8, %f4)) add %o1, 0x8, %o1 subcc %g2, 0x8, %g2 faligndata %f6, %f4, %f2 - EX_ST(STORE(std, %f2, %o0)) + EX_ST_FP(STORE(std, %f2, %o0)) bne,pt %icc, 1b add %o0, 0x8, %o0 @@ -155,25 +161,25 @@ FUNC_NAME: /* %o0=dst, %o1=src, %o2=len */ LOAD(prefetch, %o1 + 0x080, #one_read) LOAD(prefetch, %o1 + 0x0c0, #one_read) LOAD(prefetch, %o1 + 0x100, #one_read) - EX_LD(LOAD(ldd, %o1 + 0x000, %f0)) + EX_LD_FP(LOAD(ldd, %o1 + 0x000, %f0)) LOAD(prefetch, %o1 + 0x140, #one_read) - EX_LD(LOAD(ldd, %o1 + 0x008, %f2)) + EX_LD_FP(LOAD(ldd, %o1 + 0x008, %f2)) LOAD(prefetch, %o1 + 0x180, #one_read) - EX_LD(LOAD(ldd, %o1 + 0x010, %f4)) + EX_LD_FP(LOAD(ldd, %o1 + 0x010, %f4)) LOAD(prefetch, %o1 + 0x1c0, #one_read) faligndata %f0, %f2, %f16 - EX_LD(LOAD(ldd, %o1 + 0x018, %f6)) + EX_LD_FP(LOAD(ldd, %o1 + 0x018, %f6)) faligndata %f2, %f4, %f18 - EX_LD(LOAD(ldd, %o1 + 0x020, %f8)) + EX_LD_FP(LOAD(ldd, %o1 + 0x020, %f8)) faligndata %f4, %f6, %f20 - EX_LD(LOAD(ldd, %o1 + 0x028, %f10)) + EX_LD_FP(LOAD(ldd, %o1 + 0x028, %f10)) faligndata %f6, %f8, %f22 - EX_LD(LOAD(ldd, %o1 + 0x030, %f12)) + EX_LD_FP(LOAD(ldd, %o1 + 0x030, %f12)) faligndata %f8, %f10, %f24 - EX_LD(LOAD(ldd, %o1 + 0x038, %f14)) + EX_LD_FP(LOAD(ldd, %o1 + 0x038, %f14)) faligndata %f10, %f12, %f26 - EX_LD(LOAD(ldd, %o1 + 0x040, %f0)) + EX_LD_FP(LOAD(ldd, %o1 + 0x040, %f0)) subcc GLOBAL_SPARE, 0x80, GLOBAL_SPARE add %o1, 0x40, %o1 @@ -184,26 +190,26 @@ FUNC_NAME: /* %o0=dst, %o1=src, %o2=len */ .align 64 1: - EX_LD(LOAD(ldd, %o1 + 0x008, %f2)) + EX_LD_FP(LOAD(ldd, %o1 + 0x008, %f2)) faligndata %f12, %f14, %f28 - EX_LD(LOAD(ldd, %o1 + 0x010, %f4)) + EX_LD_FP(LOAD(ldd, %o1 + 0x010, %f4)) faligndata %f14, %f0, %f30 - EX_ST(STORE_BLK(%f16, %o0)) - EX_LD(LOAD(ldd, %o1 + 0x018, %f6)) + EX_ST_FP(STORE_BLK(%f16, %o0)) + EX_LD_FP(LOAD(ldd, %o1 + 0x018, %f6)) faligndata %f0, %f2, %f16 add %o0, 0x40, %o0 - EX_LD(LOAD(ldd, %o1 + 0x020, %f8)) + EX_LD_FP(LOAD(ldd, %o1 + 0x020, %f8)) faligndata %f2, %f4, %f18 - EX_LD(LOAD(ldd, %o1 + 0x028, %f10)) + EX_LD_FP(LOAD(ldd, %o1 + 0x028, %f10)) faligndata %f4, %f6, %f20 - EX_LD(LOAD(ldd, %o1 + 0x030, %f12)) + EX_LD_FP(LOAD(ldd, %o1 + 0x030, %f12)) subcc %o3, 0x01, %o3 faligndata %f6, %f8, %f22 - EX_LD(LOAD(ldd, %o1 + 0x038, %f14)) + EX_LD_FP(LOAD(ldd, %o1 + 0x038, %f14)) faligndata %f8, %f10, %f24 - EX_LD(LOAD(ldd, %o1 + 0x040, %f0)) + EX_LD_FP(LOAD(ldd, %o1 + 0x040, %f0)) LOAD(prefetch, %o1 + 0x1c0, #one_read) faligndata %f10, %f12, %f26 bg,pt %XCC, 1b @@ -211,29 +217,29 @@ FUNC_NAME: /* %o0=dst, %o1=src, %o2=len */ /* Finally we copy the last full 64-byte block. */ 2: - EX_LD(LOAD(ldd, %o1 + 0x008, %f2)) + EX_LD_FP(LOAD(ldd, %o1 + 0x008, %f2)) faligndata %f12, %f14, %f28 - EX_LD(LOAD(ldd, %o1 + 0x010, %f4)) + EX_LD_FP(LOAD(ldd, %o1 + 0x010, %f4)) faligndata %f14, %f0, %f30 - EX_ST(STORE_BLK(%f16, %o0)) - EX_LD(LOAD(ldd, %o1 + 0x018, %f6)) + EX_ST_FP(STORE_BLK(%f16, %o0)) + EX_LD_FP(LOAD(ldd, %o1 + 0x018, %f6)) faligndata %f0, %f2, %f16 - EX_LD(LOAD(ldd, %o1 + 0x020, %f8)) + EX_LD_FP(LOAD(ldd, %o1 + 0x020, %f8)) faligndata %f2, %f4, %f18 - EX_LD(LOAD(ldd, %o1 + 0x028, %f10)) + EX_LD_FP(LOAD(ldd, %o1 + 0x028, %f10)) faligndata %f4, %f6, %f20 - EX_LD(LOAD(ldd, %o1 + 0x030, %f12)) + EX_LD_FP(LOAD(ldd, %o1 + 0x030, %f12)) faligndata %f6, %f8, %f22 - EX_LD(LOAD(ldd, %o1 + 0x038, %f14)) + EX_LD_FP(LOAD(ldd, %o1 + 0x038, %f14)) faligndata %f8, %f10, %f24 cmp %g1, 0 be,pt %XCC, 1f add %o0, 0x40, %o0 - EX_LD(LOAD(ldd, %o1 + 0x040, %f0)) + EX_LD_FP(LOAD(ldd, %o1 + 0x040, %f0)) 1: faligndata %f10, %f12, %f26 faligndata %f12, %f14, %f28 faligndata %f14, %f0, %f30 - EX_ST(STORE_BLK(%f16, %o0)) + EX_ST_FP(STORE_BLK(%f16, %o0)) add %o0, 0x40, %o0 add %o1, 0x40, %o1 membar #Sync @@ -253,20 +259,20 @@ FUNC_NAME: /* %o0=dst, %o1=src, %o2=len */ sub %o2, %g2, %o2 be,a,pt %XCC, 1f - EX_LD(LOAD(ldd, %o1 + 0x00, %f0)) + EX_LD_FP(LOAD(ldd, %o1 + 0x00, %f0)) -1: EX_LD(LOAD(ldd, %o1 + 0x08, %f2)) +1: EX_LD_FP(LOAD(ldd, %o1 + 0x08, %f2)) add %o1, 0x8, %o1 subcc %g2, 0x8, %g2 faligndata %f0, %f2, %f8 - EX_ST(STORE(std, %f8, %o0)) + EX_ST_FP(STORE(std, %f8, %o0)) be,pn %XCC, 2f add %o0, 0x8, %o0 - EX_LD(LOAD(ldd, %o1 + 0x08, %f0)) + EX_LD_FP(LOAD(ldd, %o1 + 0x08, %f0)) add %o1, 0x8, %o1 subcc %g2, 0x8, %g2 faligndata %f2, %f0, %f8 - EX_ST(STORE(std, %f8, %o0)) + EX_ST_FP(STORE(std, %f8, %o0)) bne,pn %XCC, 1b add %o0, 0x8, %o0 diff --git a/arch/sparc/net/bpf_jit_comp.c b/arch/sparc/net/bpf_jit_comp.c index 22564f5f2364..3e6e05a7c4c2 100644 --- a/arch/sparc/net/bpf_jit_comp.c +++ b/arch/sparc/net/bpf_jit_comp.c @@ -420,22 +420,9 @@ void bpf_jit_compile(struct bpf_prog *fp) } emit_reg_move(O7, r_saved_O7); - switch (filter[0].code) { - case BPF_RET | BPF_K: - case BPF_LD | BPF_W | BPF_LEN: - case BPF_LD | BPF_W | BPF_ABS: - case BPF_LD | BPF_H | BPF_ABS: - case BPF_LD | BPF_B | BPF_ABS: - /* The first instruction sets the A register (or is - * a "RET 'constant'") - */ - break; - default: - /* Make sure we dont leak kernel information to the - * user. - */ + /* Make sure we dont leak kernel information to the user. */ + if (bpf_needs_clear_a(&filter[0])) emit_clear(r_A); /* A = 0 */ - } for (i = 0; i < flen; i++) { unsigned int K = filter[i].k; diff --git a/arch/tile/Kconfig b/arch/tile/Kconfig index 106c21bd7f44..8ec7a4599c08 100644 --- a/arch/tile/Kconfig +++ b/arch/tile/Kconfig @@ -176,8 +176,6 @@ config NR_CPUS smaller kernel memory footprint results from using a smaller value on chips with fewer tiles. -if TILEGX - choice prompt "Kernel page size" default PAGE_SIZE_64KB @@ -188,8 +186,11 @@ choice connections, etc., it may be better to select 16KB, which uses memory more efficiently at some cost in TLB performance. - Note that this option is TILE-Gx specific; currently - TILEPro page size is set by rebuilding the hypervisor. + Note that for TILEPro, you must also rebuild the hypervisor + with a matching page size. + +config PAGE_SIZE_4KB + bool "4KB" if TILEPRO config PAGE_SIZE_16KB bool "16KB" @@ -199,8 +200,6 @@ config PAGE_SIZE_64KB endchoice -endif - source "kernel/Kconfig.hz" config KEXEC diff --git a/arch/tile/include/asm/cmpxchg.h b/arch/tile/include/asm/cmpxchg.h index 0ccda3c425be..25d5899497be 100644 --- a/arch/tile/include/asm/cmpxchg.h +++ b/arch/tile/include/asm/cmpxchg.h @@ -127,8 +127,6 @@ long long _atomic64_cmpxchg(long long *v, long long o, long long n); #endif -#define tas(ptr) xchg((ptr), 1) - #endif /* __ASSEMBLY__ */ #endif /* _ASM_TILE_CMPXCHG_H */ diff --git a/arch/tile/include/asm/page.h b/arch/tile/include/asm/page.h index a213a8d84a95..8eca6a0e1762 100644 --- a/arch/tile/include/asm/page.h +++ b/arch/tile/include/asm/page.h @@ -20,15 +20,17 @@ #include <arch/chip.h> /* PAGE_SHIFT and HPAGE_SHIFT determine the page sizes. */ -#if defined(CONFIG_PAGE_SIZE_16KB) +#if defined(CONFIG_PAGE_SIZE_4KB) /* tilepro only */ +#define PAGE_SHIFT 12 +#define CTX_PAGE_FLAG HV_CTX_PG_SM_4K +#elif defined(CONFIG_PAGE_SIZE_16KB) #define PAGE_SHIFT 14 #define CTX_PAGE_FLAG HV_CTX_PG_SM_16K #elif defined(CONFIG_PAGE_SIZE_64KB) #define PAGE_SHIFT 16 #define CTX_PAGE_FLAG HV_CTX_PG_SM_64K #else -#define PAGE_SHIFT HV_LOG2_DEFAULT_PAGE_SIZE_SMALL -#define CTX_PAGE_FLAG 0 +#error Page size not specified in Kconfig #endif #define HPAGE_SHIFT HV_LOG2_DEFAULT_PAGE_SIZE_LARGE diff --git a/arch/tile/kernel/perf_event.c b/arch/tile/kernel/perf_event.c index bb509cee3b59..8767060d70fb 100644 --- a/arch/tile/kernel/perf_event.c +++ b/arch/tile/kernel/perf_event.c @@ -21,7 +21,7 @@ * Copyright (C) 2008-2009 Red Hat, Inc., Ingo Molnar * Copyright (C) 2009 Jaswinder Singh Rajput * Copyright (C) 2009 Advanced Micro Devices, Inc., Robert Richter - * Copyright (C) 2008-2009 Red Hat, Inc., Peter Zijlstra <pzijlstr@redhat.com> + * Copyright (C) 2008-2009 Red Hat, Inc., Peter Zijlstra * Copyright (C) 2009 Intel Corporation, <markus.t.metzger@intel.com> * Copyright (C) 2009 Google, Inc., Stephane Eranian */ diff --git a/arch/um/Makefile b/arch/um/Makefile index 25ed4098640e..e3abe6f3156d 100644 --- a/arch/um/Makefile +++ b/arch/um/Makefile @@ -131,7 +131,7 @@ export LDS_ELF_FORMAT := $(ELF_FORMAT) # The wrappers will select whether using "malloc" or the kernel allocator. LINK_WRAPS = -Wl,--wrap,malloc -Wl,--wrap,free -Wl,--wrap,calloc -LD_FLAGS_CMDLINE = $(foreach opt,$(LDFLAGS),-Wl,$(opt)) -lrt +LD_FLAGS_CMDLINE = $(foreach opt,$(LDFLAGS),-Wl,$(opt)) # Used by link-vmlinux.sh which has special support for um link export CFLAGS_vmlinux := $(LINK-y) $(LINK_WRAPS) $(LD_FLAGS_CMDLINE) diff --git a/arch/um/drivers/net_user.c b/arch/um/drivers/net_user.c index e697a4136707..e9f8445861dc 100644 --- a/arch/um/drivers/net_user.c +++ b/arch/um/drivers/net_user.c @@ -249,21 +249,23 @@ void close_addr(unsigned char *addr, unsigned char *netmask, void *arg) char *split_if_spec(char *str, ...) { - char **arg, *end; + char **arg, *end, *ret = NULL; va_list ap; va_start(ap, str); while ((arg = va_arg(ap, char **)) != NULL) { if (*str == '\0') - return NULL; + goto out; end = strchr(str, ','); if (end != str) *arg = str; if (end == NULL) - return NULL; + goto out; *end++ = '\0'; str = end; } + ret = str; +out: va_end(ap); - return str; + return ret; } diff --git a/arch/um/kernel/signal.c b/arch/um/kernel/signal.c index 57acbd67d85d..fc8be0e3a4ff 100644 --- a/arch/um/kernel/signal.c +++ b/arch/um/kernel/signal.c @@ -69,7 +69,7 @@ void do_signal(struct pt_regs *regs) struct ksignal ksig; int handled_sig = 0; - while (get_signal(&ksig)) { + if (get_signal(&ksig)) { handled_sig = 1; /* Whee! Actually deliver the signal. */ handle_signal(&ksig, regs); diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig index db3622f22b61..258965d56beb 100644 --- a/arch/x86/Kconfig +++ b/arch/x86/Kconfig @@ -349,6 +349,17 @@ config X86_FEATURE_NAMES If in doubt, say Y. +config X86_FAST_FEATURE_TESTS + bool "Fast CPU feature tests" if EMBEDDED + default y + ---help--- + Some fast-paths in the kernel depend on the capabilities of the CPU. + Say Y here for the kernel to patch in the appropriate code at runtime + based on the capabilities of the CPU. The infrastructure for patching + code at runtime takes up some additional space; space-constrained + embedded systems may wish to say N here to produce smaller, slightly + slower code. + config X86_X2APIC bool "Support x2apic" depends on X86_LOCAL_APIC && X86_64 && (IRQ_REMAP || HYPERVISOR_GUEST) @@ -687,6 +698,14 @@ config PARAVIRT_SPINLOCKS If you are unsure how to answer this question, answer Y. +config QUEUED_LOCK_STAT + bool "Paravirt queued spinlock statistics" + depends on PARAVIRT_SPINLOCKS && DEBUG_FS && QUEUED_SPINLOCKS + ---help--- + Enable the collection of statistical data on the slowpath + behavior of paravirtualized queued spinlocks and report + them on debugfs. + source "arch/x86/xen/Kconfig" config KVM_GUEST diff --git a/arch/x86/Kconfig.debug b/arch/x86/Kconfig.debug index 137dfa96aa14..110253ce83af 100644 --- a/arch/x86/Kconfig.debug +++ b/arch/x86/Kconfig.debug @@ -69,7 +69,7 @@ config X86_PTDUMP_CORE def_bool n config X86_PTDUMP - bool "Export kernel pagetable layout to userspace via debugfs" + tristate "Export kernel pagetable layout to userspace via debugfs" depends on DEBUG_KERNEL select DEBUG_FS select X86_PTDUMP_CORE diff --git a/arch/x86/boot/boot.h b/arch/x86/boot/boot.h index 0033e96c3f09..9011a88353de 100644 --- a/arch/x86/boot/boot.h +++ b/arch/x86/boot/boot.h @@ -23,7 +23,6 @@ #include <stdarg.h> #include <linux/types.h> #include <linux/edd.h> -#include <asm/boot.h> #include <asm/setup.h> #include "bitops.h" #include "ctype.h" diff --git a/arch/x86/boot/video-mode.c b/arch/x86/boot/video-mode.c index aa8a96b052e3..95c7a818c0ed 100644 --- a/arch/x86/boot/video-mode.c +++ b/arch/x86/boot/video-mode.c @@ -19,6 +19,8 @@ #include "video.h" #include "vesa.h" +#include <uapi/asm/boot.h> + /* * Common variables */ diff --git a/arch/x86/boot/video.c b/arch/x86/boot/video.c index 05111bb8d018..77780e386e9b 100644 --- a/arch/x86/boot/video.c +++ b/arch/x86/boot/video.c @@ -13,6 +13,8 @@ * Select video mode */ +#include <uapi/asm/boot.h> + #include "boot.h" #include "video.h" #include "vesa.h" diff --git a/arch/x86/crypto/chacha20_glue.c b/arch/x86/crypto/chacha20_glue.c index 722bacea040e..8baaff5af0b5 100644 --- a/arch/x86/crypto/chacha20_glue.c +++ b/arch/x86/crypto/chacha20_glue.c @@ -125,7 +125,7 @@ static struct crypto_alg alg = { static int __init chacha20_simd_mod_init(void) { - if (!cpu_has_ssse3) + if (!boot_cpu_has(X86_FEATURE_SSSE3)) return -ENODEV; #ifdef CONFIG_AS_AVX2 diff --git a/arch/x86/crypto/crc32c-intel_glue.c b/arch/x86/crypto/crc32c-intel_glue.c index 81a595d75cf5..0e9871693f24 100644 --- a/arch/x86/crypto/crc32c-intel_glue.c +++ b/arch/x86/crypto/crc32c-intel_glue.c @@ -257,7 +257,7 @@ static int __init crc32c_intel_mod_init(void) if (!x86_match_cpu(crc32c_cpu_id)) return -ENODEV; #ifdef CONFIG_X86_64 - if (cpu_has_pclmulqdq) { + if (boot_cpu_has(X86_FEATURE_PCLMULQDQ)) { alg.update = crc32c_pcl_intel_update; alg.finup = crc32c_pcl_intel_finup; alg.digest = crc32c_pcl_intel_digest; diff --git a/arch/x86/entry/calling.h b/arch/x86/entry/calling.h index 3c71dd947c7b..e32206e09868 100644 --- a/arch/x86/entry/calling.h +++ b/arch/x86/entry/calling.h @@ -1,3 +1,5 @@ +#include <linux/jump_label.h> + /* x86 function call convention, 64-bit: @@ -232,3 +234,16 @@ For 32-bit we have the following conventions - kernel is built with #endif /* CONFIG_X86_64 */ +/* + * This does 'call enter_from_user_mode' unless we can avoid it based on + * kernel config or using the static jump infrastructure. + */ +.macro CALL_enter_from_user_mode +#ifdef CONFIG_CONTEXT_TRACKING +#ifdef HAVE_JUMP_LABEL + STATIC_JUMP_IF_FALSE .Lafter_call_\@, context_tracking_enabled, def=0 +#endif + call enter_from_user_mode +.Lafter_call_\@: +#endif +.endm diff --git a/arch/x86/entry/common.c b/arch/x86/entry/common.c index a89fdbc1f0be..03663740c866 100644 --- a/arch/x86/entry/common.c +++ b/arch/x86/entry/common.c @@ -421,7 +421,7 @@ __visible long do_fast_syscall_32(struct pt_regs *regs) regs->ip = landing_pad; /* - * Fetch ECX from where the vDSO stashed it. + * Fetch EBP from where the vDSO stashed it. * * WARNING: We are in CONTEXT_USER and RCU isn't paying attention! */ @@ -432,10 +432,10 @@ __visible long do_fast_syscall_32(struct pt_regs *regs) * Micro-optimization: the pointer we're following is explicitly * 32 bits, so it can't be out of range. */ - __get_user(*(u32 *)®s->cx, + __get_user(*(u32 *)®s->bp, (u32 __user __force *)(unsigned long)(u32)regs->sp) #else - get_user(*(u32 *)®s->cx, + get_user(*(u32 *)®s->bp, (u32 __user __force *)(unsigned long)(u32)regs->sp) #endif ) { diff --git a/arch/x86/entry/entry_32.S b/arch/x86/entry/entry_32.S index 3eb572ed3d7a..77d8c5112900 100644 --- a/arch/x86/entry/entry_32.S +++ b/arch/x86/entry/entry_32.S @@ -292,7 +292,7 @@ ENTRY(entry_SYSENTER_32) movl TSS_sysenter_sp0(%esp), %esp sysenter_past_esp: pushl $__USER_DS /* pt_regs->ss */ - pushl %ecx /* pt_regs->cx */ + pushl %ebp /* pt_regs->sp (stashed in bp) */ pushfl /* pt_regs->flags (except IF = 0) */ orl $X86_EFLAGS_IF, (%esp) /* Fix IF */ pushl $__USER_CS /* pt_regs->cs */ @@ -308,8 +308,9 @@ sysenter_past_esp: movl %esp, %eax call do_fast_syscall_32 - testl %eax, %eax - jz .Lsyscall_32_done + /* XEN PV guests always use IRET path */ + ALTERNATIVE "testl %eax, %eax; jz .Lsyscall_32_done", \ + "jmp .Lsyscall_32_done", X86_FEATURE_XENPV /* Opportunistic SYSEXIT */ TRACE_IRQS_ON /* User mode traces as IRQs on. */ @@ -328,7 +329,8 @@ sysenter_past_esp: * Return back to the vDSO, which will pop ecx and edx. * Don't bother with DS and ES (they already contain __USER_DS). */ - ENABLE_INTERRUPTS_SYSEXIT + sti + sysexit .pushsection .fixup, "ax" 2: movl $0, PT_FS(%esp) @@ -551,11 +553,6 @@ ENTRY(native_iret) iret _ASM_EXTABLE(native_iret, iret_exc) END(native_iret) - -ENTRY(native_irq_enable_sysexit) - sti - sysexit -END(native_irq_enable_sysexit) #endif ENTRY(overflow) diff --git a/arch/x86/entry/entry_64.S b/arch/x86/entry/entry_64.S index 53616ca03244..9d34d3cfceb6 100644 --- a/arch/x86/entry/entry_64.S +++ b/arch/x86/entry/entry_64.S @@ -509,9 +509,18 @@ END(irq_entries_start) * tracking that we're in kernel mode. */ SWAPGS -#ifdef CONFIG_CONTEXT_TRACKING - call enter_from_user_mode -#endif + + /* + * We need to tell lockdep that IRQs are off. We can't do this until + * we fix gsbase, and we should do it before enter_from_user_mode + * (which can take locks). Since TRACE_IRQS_OFF idempotent, + * the simplest way to handle it is to just call it twice if + * we enter from user mode. There's no reason to optimize this since + * TRACE_IRQS_OFF is a no-op if lockdep is off. + */ + TRACE_IRQS_OFF + + CALL_enter_from_user_mode 1: /* @@ -1049,12 +1058,16 @@ ENTRY(error_entry) SWAPGS .Lerror_entry_from_usermode_after_swapgs: -#ifdef CONFIG_CONTEXT_TRACKING - call enter_from_user_mode -#endif + /* + * We need to tell lockdep that IRQs are off. We can't do this until + * we fix gsbase, and we should do it before enter_from_user_mode + * (which can take locks). + */ + TRACE_IRQS_OFF + CALL_enter_from_user_mode + ret .Lerror_entry_done: - TRACE_IRQS_OFF ret diff --git a/arch/x86/entry/entry_64_compat.S b/arch/x86/entry/entry_64_compat.S index c3201830a85e..ff1c6d61f332 100644 --- a/arch/x86/entry/entry_64_compat.S +++ b/arch/x86/entry/entry_64_compat.S @@ -18,13 +18,6 @@ .section .entry.text, "ax" -#ifdef CONFIG_PARAVIRT -ENTRY(native_usergs_sysret32) - swapgs - sysretl -ENDPROC(native_usergs_sysret32) -#endif - /* * 32-bit SYSENTER instruction entry. * @@ -63,7 +56,7 @@ ENTRY(entry_SYSENTER_compat) /* Construct struct pt_regs on stack */ pushq $__USER32_DS /* pt_regs->ss */ - pushq %rcx /* pt_regs->sp */ + pushq %rbp /* pt_regs->sp (stashed in bp) */ /* * Push flags. This is nasty. First, interrupts are currently @@ -82,14 +75,14 @@ ENTRY(entry_SYSENTER_compat) pushq %rdi /* pt_regs->di */ pushq %rsi /* pt_regs->si */ pushq %rdx /* pt_regs->dx */ - pushq %rcx /* pt_regs->cx (will be overwritten) */ + pushq %rcx /* pt_regs->cx */ pushq $-ENOSYS /* pt_regs->ax */ pushq %r8 /* pt_regs->r8 = 0 */ pushq %r8 /* pt_regs->r9 = 0 */ pushq %r8 /* pt_regs->r10 = 0 */ pushq %r8 /* pt_regs->r11 = 0 */ pushq %rbx /* pt_regs->rbx */ - pushq %rbp /* pt_regs->rbp */ + pushq %rbp /* pt_regs->rbp (will be overwritten) */ pushq %r8 /* pt_regs->r12 = 0 */ pushq %r8 /* pt_regs->r13 = 0 */ pushq %r8 /* pt_regs->r14 = 0 */ @@ -103,15 +96,15 @@ ENTRY(entry_SYSENTER_compat) * This needs to happen before enabling interrupts so that * we don't get preempted with NT set. * - * NB.: sysenter_fix_flags is a label with the code under it moved + * NB.: .Lsysenter_fix_flags is a label with the code under it moved * out-of-line as an optimization: NT is unlikely to be set in the * majority of the cases and instead of polluting the I$ unnecessarily, * we're keeping that code behind a branch which will predict as * not-taken and therefore its instructions won't be fetched. */ testl $X86_EFLAGS_NT, EFLAGS(%rsp) - jnz sysenter_fix_flags -sysenter_flags_fixed: + jnz .Lsysenter_fix_flags +.Lsysenter_flags_fixed: /* * User mode is traced as though IRQs are on, and SYSENTER @@ -121,14 +114,15 @@ sysenter_flags_fixed: movq %rsp, %rdi call do_fast_syscall_32 - testl %eax, %eax - jz .Lsyscall_32_done + /* XEN PV guests always use IRET path */ + ALTERNATIVE "testl %eax, %eax; jz .Lsyscall_32_done", \ + "jmp .Lsyscall_32_done", X86_FEATURE_XENPV jmp sysret32_from_system_call -sysenter_fix_flags: +.Lsysenter_fix_flags: pushq $X86_EFLAGS_FIXED popfq - jmp sysenter_flags_fixed + jmp .Lsysenter_flags_fixed ENDPROC(entry_SYSENTER_compat) /* @@ -178,7 +172,7 @@ ENTRY(entry_SYSCALL_compat) pushq %rdi /* pt_regs->di */ pushq %rsi /* pt_regs->si */ pushq %rdx /* pt_regs->dx */ - pushq %rcx /* pt_regs->cx (will be overwritten) */ + pushq %rbp /* pt_regs->cx (stashed in bp) */ pushq $-ENOSYS /* pt_regs->ax */ xorq %r8,%r8 pushq %r8 /* pt_regs->r8 = 0 */ @@ -186,7 +180,7 @@ ENTRY(entry_SYSCALL_compat) pushq %r8 /* pt_regs->r10 = 0 */ pushq %r8 /* pt_regs->r11 = 0 */ pushq %rbx /* pt_regs->rbx */ - pushq %rbp /* pt_regs->rbp */ + pushq %rbp /* pt_regs->rbp (will be overwritten) */ pushq %r8 /* pt_regs->r12 = 0 */ pushq %r8 /* pt_regs->r13 = 0 */ pushq %r8 /* pt_regs->r14 = 0 */ @@ -200,8 +194,9 @@ ENTRY(entry_SYSCALL_compat) movq %rsp, %rdi call do_fast_syscall_32 - testl %eax, %eax - jz .Lsyscall_32_done + /* XEN PV guests always use IRET path */ + ALTERNATIVE "testl %eax, %eax; jz .Lsyscall_32_done", \ + "jmp .Lsyscall_32_done", X86_FEATURE_XENPV /* Opportunistic SYSRET */ sysret32_from_system_call: @@ -236,7 +231,8 @@ sysret32_from_system_call: xorq %r9, %r9 xorq %r10, %r10 movq RSP-ORIG_RAX(%rsp), %rsp - USERGS_SYSRET32 + swapgs + sysretl END(entry_SYSCALL_compat) /* diff --git a/arch/x86/entry/vdso/vclock_gettime.c b/arch/x86/entry/vdso/vclock_gettime.c index ca94fa649251..8602f06c759f 100644 --- a/arch/x86/entry/vdso/vclock_gettime.c +++ b/arch/x86/entry/vdso/vclock_gettime.c @@ -17,8 +17,10 @@ #include <asm/vvar.h> #include <asm/unistd.h> #include <asm/msr.h> +#include <asm/pvclock.h> #include <linux/math64.h> #include <linux/time.h> +#include <linux/kernel.h> #define gtod (&VVAR(vsyscall_gtod_data)) @@ -36,12 +38,12 @@ static notrace cycle_t vread_hpet(void) } #endif -#ifndef BUILD_VDSO32 +#ifdef CONFIG_PARAVIRT_CLOCK +extern u8 pvclock_page + __attribute__((visibility("hidden"))); +#endif -#include <linux/kernel.h> -#include <asm/vsyscall.h> -#include <asm/fixmap.h> -#include <asm/pvclock.h> +#ifndef BUILD_VDSO32 notrace static long vdso_fallback_gettime(long clock, struct timespec *ts) { @@ -60,75 +62,6 @@ notrace static long vdso_fallback_gtod(struct timeval *tv, struct timezone *tz) return ret; } -#ifdef CONFIG_PARAVIRT_CLOCK - -static notrace const struct pvclock_vsyscall_time_info *get_pvti(int cpu) -{ - const struct pvclock_vsyscall_time_info *pvti_base; - int idx = cpu / (PAGE_SIZE/PVTI_SIZE); - int offset = cpu % (PAGE_SIZE/PVTI_SIZE); - - BUG_ON(PVCLOCK_FIXMAP_BEGIN + idx > PVCLOCK_FIXMAP_END); - - pvti_base = (struct pvclock_vsyscall_time_info *) - __fix_to_virt(PVCLOCK_FIXMAP_BEGIN+idx); - - return &pvti_base[offset]; -} - -static notrace cycle_t vread_pvclock(int *mode) -{ - const struct pvclock_vsyscall_time_info *pvti; - cycle_t ret; - u64 last; - u32 version; - u8 flags; - unsigned cpu, cpu1; - - - /* - * Note: hypervisor must guarantee that: - * 1. cpu ID number maps 1:1 to per-CPU pvclock time info. - * 2. that per-CPU pvclock time info is updated if the - * underlying CPU changes. - * 3. that version is increased whenever underlying CPU - * changes. - * - */ - do { - cpu = __getcpu() & VGETCPU_CPU_MASK; - /* TODO: We can put vcpu id into higher bits of pvti.version. - * This will save a couple of cycles by getting rid of - * __getcpu() calls (Gleb). - */ - - pvti = get_pvti(cpu); - - version = __pvclock_read_cycles(&pvti->pvti, &ret, &flags); - - /* - * Test we're still on the cpu as well as the version. - * We could have been migrated just after the first - * vgetcpu but before fetching the version, so we - * wouldn't notice a version change. - */ - cpu1 = __getcpu() & VGETCPU_CPU_MASK; - } while (unlikely(cpu != cpu1 || - (pvti->pvti.version & 1) || - pvti->pvti.version != version)); - - if (unlikely(!(flags & PVCLOCK_TSC_STABLE_BIT))) - *mode = VCLOCK_NONE; - - /* refer to tsc.c read_tsc() comment for rationale */ - last = gtod->cycle_last; - - if (likely(ret >= last)) - return ret; - - return last; -} -#endif #else @@ -162,15 +95,77 @@ notrace static long vdso_fallback_gtod(struct timeval *tv, struct timezone *tz) return ret; } +#endif + #ifdef CONFIG_PARAVIRT_CLOCK +static notrace const struct pvclock_vsyscall_time_info *get_pvti0(void) +{ + return (const struct pvclock_vsyscall_time_info *)&pvclock_page; +} static notrace cycle_t vread_pvclock(int *mode) { - *mode = VCLOCK_NONE; - return 0; -} -#endif + const struct pvclock_vcpu_time_info *pvti = &get_pvti0()->pvti; + cycle_t ret; + u64 tsc, pvti_tsc; + u64 last, delta, pvti_system_time; + u32 version, pvti_tsc_to_system_mul, pvti_tsc_shift; + + /* + * Note: The kernel and hypervisor must guarantee that cpu ID + * number maps 1:1 to per-CPU pvclock time info. + * + * Because the hypervisor is entirely unaware of guest userspace + * preemption, it cannot guarantee that per-CPU pvclock time + * info is updated if the underlying CPU changes or that that + * version is increased whenever underlying CPU changes. + * + * On KVM, we are guaranteed that pvti updates for any vCPU are + * atomic as seen by *all* vCPUs. This is an even stronger + * guarantee than we get with a normal seqlock. + * + * On Xen, we don't appear to have that guarantee, but Xen still + * supplies a valid seqlock using the version field. + + * We only do pvclock vdso timing at all if + * PVCLOCK_TSC_STABLE_BIT is set, and we interpret that bit to + * mean that all vCPUs have matching pvti and that the TSC is + * synced, so we can just look at vCPU 0's pvti. + */ + if (unlikely(!(pvti->flags & PVCLOCK_TSC_STABLE_BIT))) { + *mode = VCLOCK_NONE; + return 0; + } + + do { + version = pvti->version; + + smp_rmb(); + + tsc = rdtsc_ordered(); + pvti_tsc_to_system_mul = pvti->tsc_to_system_mul; + pvti_tsc_shift = pvti->tsc_shift; + pvti_system_time = pvti->system_time; + pvti_tsc = pvti->tsc_timestamp; + + /* Make sure that the version double-check is last. */ + smp_rmb(); + } while (unlikely((version & 1) || version != pvti->version)); + + delta = tsc - pvti_tsc; + ret = pvti_system_time + + pvclock_scale_delta(delta, pvti_tsc_to_system_mul, + pvti_tsc_shift); + + /* refer to vread_tsc() comment for rationale */ + last = gtod->cycle_last; + + if (likely(ret >= last)) + return ret; + + return last; +} #endif notrace static cycle_t vread_tsc(void) diff --git a/arch/x86/entry/vdso/vdso-layout.lds.S b/arch/x86/entry/vdso/vdso-layout.lds.S index de2c921025f5..4158acc17df0 100644 --- a/arch/x86/entry/vdso/vdso-layout.lds.S +++ b/arch/x86/entry/vdso/vdso-layout.lds.S @@ -25,7 +25,7 @@ SECTIONS * segment. */ - vvar_start = . - 2 * PAGE_SIZE; + vvar_start = . - 3 * PAGE_SIZE; vvar_page = vvar_start; /* Place all vvars at the offsets in asm/vvar.h. */ @@ -36,6 +36,7 @@ SECTIONS #undef EMIT_VVAR hpet_page = vvar_start + PAGE_SIZE; + pvclock_page = vvar_start + 2 * PAGE_SIZE; . = SIZEOF_HEADERS; diff --git a/arch/x86/entry/vdso/vdso2c.c b/arch/x86/entry/vdso/vdso2c.c index 785d9922b106..491020b2826d 100644 --- a/arch/x86/entry/vdso/vdso2c.c +++ b/arch/x86/entry/vdso/vdso2c.c @@ -73,6 +73,7 @@ enum { sym_vvar_start, sym_vvar_page, sym_hpet_page, + sym_pvclock_page, sym_VDSO_FAKE_SECTION_TABLE_START, sym_VDSO_FAKE_SECTION_TABLE_END, }; @@ -80,6 +81,7 @@ enum { const int special_pages[] = { sym_vvar_page, sym_hpet_page, + sym_pvclock_page, }; struct vdso_sym { @@ -91,6 +93,7 @@ struct vdso_sym required_syms[] = { [sym_vvar_start] = {"vvar_start", true}, [sym_vvar_page] = {"vvar_page", true}, [sym_hpet_page] = {"hpet_page", true}, + [sym_pvclock_page] = {"pvclock_page", true}, [sym_VDSO_FAKE_SECTION_TABLE_START] = { "VDSO_FAKE_SECTION_TABLE_START", false }, diff --git a/arch/x86/entry/vdso/vdso32/system_call.S b/arch/x86/entry/vdso/vdso32/system_call.S index 93bd8452383f..3a1d9297074b 100644 --- a/arch/x86/entry/vdso/vdso32/system_call.S +++ b/arch/x86/entry/vdso/vdso32/system_call.S @@ -1,5 +1,5 @@ /* - * Code for the vDSO. This version uses the old int $0x80 method. + * AT_SYSINFO entry point */ #include <asm/dwarf2.h> @@ -21,35 +21,67 @@ __kernel_vsyscall: /* * Reshuffle regs so that all of any of the entry instructions * will preserve enough state. + * + * A really nice entry sequence would be: + * pushl %edx + * pushl %ecx + * movl %esp, %ecx + * + * Unfortunately, naughty Android versions between July and December + * 2015 actually hardcode the traditional Linux SYSENTER entry + * sequence. That is severely broken for a number of reasons (ask + * anyone with an AMD CPU, for example). Nonetheless, we try to keep + * it working approximately as well as it ever worked. + * + * This link may eludicate some of the history: + * https://android-review.googlesource.com/#/q/Iac3295376d61ef83e713ac9b528f3b50aa780cd7 + * personally, I find it hard to understand what's going on there. + * + * Note to future user developers: DO NOT USE SYSENTER IN YOUR CODE. + * Execute an indirect call to the address in the AT_SYSINFO auxv + * entry. That is the ONLY correct way to make a fast 32-bit system + * call on Linux. (Open-coding int $0x80 is also fine, but it's + * slow.) */ + pushl %ecx + CFI_ADJUST_CFA_OFFSET 4 + CFI_REL_OFFSET ecx, 0 pushl %edx CFI_ADJUST_CFA_OFFSET 4 CFI_REL_OFFSET edx, 0 - pushl %ecx + pushl %ebp CFI_ADJUST_CFA_OFFSET 4 - CFI_REL_OFFSET ecx, 0 - movl %esp, %ecx + CFI_REL_OFFSET ebp, 0 + + #define SYSENTER_SEQUENCE "movl %esp, %ebp; sysenter" + #define SYSCALL_SEQUENCE "movl %ecx, %ebp; syscall" #ifdef CONFIG_X86_64 /* If SYSENTER (Intel) or SYSCALL32 (AMD) is available, use it. */ - ALTERNATIVE_2 "", "sysenter", X86_FEATURE_SYSENTER32, \ - "syscall", X86_FEATURE_SYSCALL32 + ALTERNATIVE_2 "", SYSENTER_SEQUENCE, X86_FEATURE_SYSENTER32, \ + SYSCALL_SEQUENCE, X86_FEATURE_SYSCALL32 #else - ALTERNATIVE "", "sysenter", X86_FEATURE_SEP + ALTERNATIVE "", SYSENTER_SEQUENCE, X86_FEATURE_SEP #endif /* Enter using int $0x80 */ - movl (%esp), %ecx int $0x80 GLOBAL(int80_landing_pad) - /* Restore ECX and EDX in case they were clobbered. */ - popl %ecx - CFI_RESTORE ecx + /* + * Restore EDX and ECX in case they were clobbered. EBP is not + * clobbered (the kernel restores it), but it's cleaner and + * probably faster to pop it than to adjust ESP using addl. + */ + popl %ebp + CFI_RESTORE ebp CFI_ADJUST_CFA_OFFSET -4 popl %edx CFI_RESTORE edx CFI_ADJUST_CFA_OFFSET -4 + popl %ecx + CFI_RESTORE ecx + CFI_ADJUST_CFA_OFFSET -4 ret CFI_ENDPROC diff --git a/arch/x86/entry/vdso/vma.c b/arch/x86/entry/vdso/vma.c index 64df47148160..b8f69e264ac4 100644 --- a/arch/x86/entry/vdso/vma.c +++ b/arch/x86/entry/vdso/vma.c @@ -12,6 +12,7 @@ #include <linux/random.h> #include <linux/elf.h> #include <linux/cpu.h> +#include <asm/pvclock.h> #include <asm/vgtod.h> #include <asm/proto.h> #include <asm/vdso.h> @@ -100,6 +101,7 @@ static int map_vdso(const struct vdso_image *image, bool calculate_addr) .name = "[vvar]", .pages = no_pages, }; + struct pvclock_vsyscall_time_info *pvti; if (calculate_addr) { addr = vdso_addr(current->mm->start_stack, @@ -169,6 +171,18 @@ static int map_vdso(const struct vdso_image *image, bool calculate_addr) } #endif + pvti = pvclock_pvti_cpu0_va(); + if (pvti && image->sym_pvclock_page) { + ret = remap_pfn_range(vma, + text_start + image->sym_pvclock_page, + __pa(pvti) >> PAGE_SHIFT, + PAGE_SIZE, + PAGE_READONLY); + + if (ret) + goto up_fail; + } + up_fail: if (ret) current->mm->context.vdso = NULL; diff --git a/arch/x86/include/asm/apic.h b/arch/x86/include/asm/apic.h index a30316bf801a..c80f6b6f3da2 100644 --- a/arch/x86/include/asm/apic.h +++ b/arch/x86/include/asm/apic.h @@ -23,6 +23,11 @@ #define APIC_VERBOSE 1 #define APIC_DEBUG 2 +/* Macros for apic_extnmi which controls external NMI masking */ +#define APIC_EXTNMI_BSP 0 /* Default */ +#define APIC_EXTNMI_ALL 1 +#define APIC_EXTNMI_NONE 2 + /* * Define the default level of output to be very little * This can be turned up by using apic=verbose for more @@ -303,6 +308,7 @@ struct apic { unsigned int *apicid); /* ipi */ + void (*send_IPI)(int cpu, int vector); void (*send_IPI_mask)(const struct cpumask *mask, int vector); void (*send_IPI_mask_allbutself)(const struct cpumask *mask, int vector); diff --git a/arch/x86/include/asm/atomic.h b/arch/x86/include/asm/atomic.h index ae5fb83e6d91..3e8674288198 100644 --- a/arch/x86/include/asm/atomic.h +++ b/arch/x86/include/asm/atomic.h @@ -3,7 +3,6 @@ #include <linux/compiler.h> #include <linux/types.h> -#include <asm/processor.h> #include <asm/alternative.h> #include <asm/cmpxchg.h> #include <asm/rmwcc.h> diff --git a/arch/x86/include/asm/atomic64_32.h b/arch/x86/include/asm/atomic64_32.h index a11c30b77fb5..a984111135b1 100644 --- a/arch/x86/include/asm/atomic64_32.h +++ b/arch/x86/include/asm/atomic64_32.h @@ -3,7 +3,6 @@ #include <linux/compiler.h> #include <linux/types.h> -#include <asm/processor.h> //#include <asm/cmpxchg.h> /* An 64bit atomic type */ diff --git a/arch/x86/include/asm/calgary.h b/arch/x86/include/asm/calgary.h index 0d467b338835..a8303ebe089f 100644 --- a/arch/x86/include/asm/calgary.h +++ b/arch/x86/include/asm/calgary.h @@ -31,7 +31,7 @@ #include <asm/types.h> struct iommu_table { - struct cal_chipset_ops *chip_ops; /* chipset specific funcs */ + const struct cal_chipset_ops *chip_ops; /* chipset specific funcs */ unsigned long it_base; /* mapped address of tce table */ unsigned long it_hint; /* Hint for next alloc */ unsigned long *it_map; /* A simple allocation bitmap for now */ diff --git a/arch/x86/include/asm/cmpxchg_32.h b/arch/x86/include/asm/cmpxchg_32.h index f7e142926481..e4959d023af8 100644 --- a/arch/x86/include/asm/cmpxchg_32.h +++ b/arch/x86/include/asm/cmpxchg_32.h @@ -109,6 +109,6 @@ static inline u64 __cmpxchg64_local(volatile u64 *ptr, u64 old, u64 new) #endif -#define system_has_cmpxchg_double() cpu_has_cx8 +#define system_has_cmpxchg_double() boot_cpu_has(X86_FEATURE_CX8) #endif /* _ASM_X86_CMPXCHG_32_H */ diff --git a/arch/x86/include/asm/cmpxchg_64.h b/arch/x86/include/asm/cmpxchg_64.h index 1af94697aae5..caa23a34c963 100644 --- a/arch/x86/include/asm/cmpxchg_64.h +++ b/arch/x86/include/asm/cmpxchg_64.h @@ -18,6 +18,6 @@ static inline void set_64bit(volatile u64 *ptr, u64 val) cmpxchg_local((ptr), (o), (n)); \ }) -#define system_has_cmpxchg_double() cpu_has_cx16 +#define system_has_cmpxchg_double() boot_cpu_has(X86_FEATURE_CX16) #endif /* _ASM_X86_CMPXCHG_64_H */ diff --git a/arch/x86/include/asm/cpu.h b/arch/x86/include/asm/cpu.h index bf2caa1dedc5..678637ad7476 100644 --- a/arch/x86/include/asm/cpu.h +++ b/arch/x86/include/asm/cpu.h @@ -36,4 +36,7 @@ extern int _debug_hotplug_cpu(int cpu, int action); int mwait_usable(const struct cpuinfo_x86 *); +unsigned int x86_family(unsigned int sig); +unsigned int x86_model(unsigned int sig); +unsigned int x86_stepping(unsigned int sig); #endif /* _ASM_X86_CPU_H */ diff --git a/arch/x86/include/asm/cpufeature.h b/arch/x86/include/asm/cpufeature.h index e4f8010f22e0..7ad8c9464297 100644 --- a/arch/x86/include/asm/cpufeature.h +++ b/arch/x86/include/asm/cpufeature.h @@ -12,7 +12,7 @@ #include <asm/disabled-features.h> #endif -#define NCAPINTS 14 /* N 32-bit words worth of info */ +#define NCAPINTS 16 /* N 32-bit words worth of info */ #define NBUGINTS 1 /* N 32-bit bug flags */ /* @@ -181,22 +181,17 @@ /* * Auxiliary flags: Linux defined - For features scattered in various - * CPUID levels like 0x6, 0xA etc, word 7 + * CPUID levels like 0x6, 0xA etc, word 7. + * + * Reuse free bits when adding new feature flags! */ -#define X86_FEATURE_IDA ( 7*32+ 0) /* Intel Dynamic Acceleration */ -#define X86_FEATURE_ARAT ( 7*32+ 1) /* Always Running APIC Timer */ + #define X86_FEATURE_CPB ( 7*32+ 2) /* AMD Core Performance Boost */ #define X86_FEATURE_EPB ( 7*32+ 3) /* IA32_ENERGY_PERF_BIAS support */ -#define X86_FEATURE_PLN ( 7*32+ 5) /* Intel Power Limit Notification */ -#define X86_FEATURE_PTS ( 7*32+ 6) /* Intel Package Thermal Status */ -#define X86_FEATURE_DTHERM ( 7*32+ 7) /* Digital Thermal Sensor */ + #define X86_FEATURE_HW_PSTATE ( 7*32+ 8) /* AMD HW-PState */ #define X86_FEATURE_PROC_FEEDBACK ( 7*32+ 9) /* AMD ProcFeedbackInterface */ -#define X86_FEATURE_HWP ( 7*32+ 10) /* "hwp" Intel HWP */ -#define X86_FEATURE_HWP_NOTIFY ( 7*32+ 11) /* Intel HWP_NOTIFY */ -#define X86_FEATURE_HWP_ACT_WINDOW ( 7*32+ 12) /* Intel HWP_ACT_WINDOW */ -#define X86_FEATURE_HWP_EPP ( 7*32+13) /* Intel HWP_EPP */ -#define X86_FEATURE_HWP_PKG_REQ ( 7*32+14) /* Intel HWP_PKG_REQ */ + #define X86_FEATURE_INTEL_PT ( 7*32+15) /* Intel Processor Trace */ /* Virtualization flags: Linux defined, word 8 */ @@ -205,17 +200,9 @@ #define X86_FEATURE_FLEXPRIORITY ( 8*32+ 2) /* Intel FlexPriority */ #define X86_FEATURE_EPT ( 8*32+ 3) /* Intel Extended Page Table */ #define X86_FEATURE_VPID ( 8*32+ 4) /* Intel Virtual Processor ID */ -#define X86_FEATURE_NPT ( 8*32+ 5) /* AMD Nested Page Table support */ -#define X86_FEATURE_LBRV ( 8*32+ 6) /* AMD LBR Virtualization support */ -#define X86_FEATURE_SVML ( 8*32+ 7) /* "svm_lock" AMD SVM locking MSR */ -#define X86_FEATURE_NRIPS ( 8*32+ 8) /* "nrip_save" AMD SVM next_rip save */ -#define X86_FEATURE_TSCRATEMSR ( 8*32+ 9) /* "tsc_scale" AMD TSC scaling support */ -#define X86_FEATURE_VMCBCLEAN ( 8*32+10) /* "vmcb_clean" AMD VMCB clean bits support */ -#define X86_FEATURE_FLUSHBYASID ( 8*32+11) /* AMD flush-by-ASID support */ -#define X86_FEATURE_DECODEASSISTS ( 8*32+12) /* AMD Decode Assists support */ -#define X86_FEATURE_PAUSEFILTER ( 8*32+13) /* AMD filtered pause intercept */ -#define X86_FEATURE_PFTHRESHOLD ( 8*32+14) /* AMD pause filter threshold */ + #define X86_FEATURE_VMMCALL ( 8*32+15) /* Prefer vmmcall to vmcall */ +#define X86_FEATURE_XENPV ( 8*32+16) /* "" Xen paravirtual guest */ /* Intel-defined CPU features, CPUID level 0x00000007:0 (ebx), word 9 */ @@ -258,6 +245,30 @@ /* AMD-defined CPU features, CPUID level 0x80000008 (ebx), word 13 */ #define X86_FEATURE_CLZERO (13*32+0) /* CLZERO instruction */ +/* Thermal and Power Management Leaf, CPUID level 0x00000006 (eax), word 14 */ +#define X86_FEATURE_DTHERM (14*32+ 0) /* Digital Thermal Sensor */ +#define X86_FEATURE_IDA (14*32+ 1) /* Intel Dynamic Acceleration */ +#define X86_FEATURE_ARAT (14*32+ 2) /* Always Running APIC Timer */ +#define X86_FEATURE_PLN (14*32+ 4) /* Intel Power Limit Notification */ +#define X86_FEATURE_PTS (14*32+ 6) /* Intel Package Thermal Status */ +#define X86_FEATURE_HWP (14*32+ 7) /* Intel Hardware P-states */ +#define X86_FEATURE_HWP_NOTIFY (14*32+ 8) /* HWP Notification */ +#define X86_FEATURE_HWP_ACT_WINDOW (14*32+ 9) /* HWP Activity Window */ +#define X86_FEATURE_HWP_EPP (14*32+10) /* HWP Energy Perf. Preference */ +#define X86_FEATURE_HWP_PKG_REQ (14*32+11) /* HWP Package Level Request */ + +/* AMD SVM Feature Identification, CPUID level 0x8000000a (edx), word 15 */ +#define X86_FEATURE_NPT (15*32+ 0) /* Nested Page Table support */ +#define X86_FEATURE_LBRV (15*32+ 1) /* LBR Virtualization support */ +#define X86_FEATURE_SVML (15*32+ 2) /* "svm_lock" SVM locking MSR */ +#define X86_FEATURE_NRIPS (15*32+ 3) /* "nrip_save" SVM next_rip save */ +#define X86_FEATURE_TSCRATEMSR (15*32+ 4) /* "tsc_scale" TSC scaling support */ +#define X86_FEATURE_VMCBCLEAN (15*32+ 5) /* "vmcb_clean" VMCB clean bits support */ +#define X86_FEATURE_FLUSHBYASID (15*32+ 6) /* flush-by-ASID support */ +#define X86_FEATURE_DECODEASSISTS (15*32+ 7) /* Decode Assists support */ +#define X86_FEATURE_PAUSEFILTER (15*32+10) /* filtered pause intercept */ +#define X86_FEATURE_PFTHRESHOLD (15*32+12) /* pause filter threshold */ + /* * BUG word(s) */ @@ -278,6 +289,26 @@ #include <asm/asm.h> #include <linux/bitops.h> +enum cpuid_leafs +{ + CPUID_1_EDX = 0, + CPUID_8000_0001_EDX, + CPUID_8086_0001_EDX, + CPUID_LNX_1, + CPUID_1_ECX, + CPUID_C000_0001_EDX, + CPUID_8000_0001_ECX, + CPUID_LNX_2, + CPUID_LNX_3, + CPUID_7_0_EBX, + CPUID_D_1_EAX, + CPUID_F_0_EDX, + CPUID_F_1_EDX, + CPUID_8000_0008_EBX, + CPUID_6_EAX, + CPUID_8000_000A_EDX, +}; + #ifdef CONFIG_X86_FEATURE_NAMES extern const char * const x86_cap_flags[NCAPINTS*32]; extern const char * const x86_power_flags[32]; @@ -355,60 +386,31 @@ extern const char * const x86_bug_flags[NBUGINTS*32]; } while (0) #define cpu_has_fpu boot_cpu_has(X86_FEATURE_FPU) -#define cpu_has_de boot_cpu_has(X86_FEATURE_DE) #define cpu_has_pse boot_cpu_has(X86_FEATURE_PSE) #define cpu_has_tsc boot_cpu_has(X86_FEATURE_TSC) #define cpu_has_pge boot_cpu_has(X86_FEATURE_PGE) #define cpu_has_apic boot_cpu_has(X86_FEATURE_APIC) -#define cpu_has_sep boot_cpu_has(X86_FEATURE_SEP) -#define cpu_has_mtrr boot_cpu_has(X86_FEATURE_MTRR) -#define cpu_has_mmx boot_cpu_has(X86_FEATURE_MMX) #define cpu_has_fxsr boot_cpu_has(X86_FEATURE_FXSR) #define cpu_has_xmm boot_cpu_has(X86_FEATURE_XMM) #define cpu_has_xmm2 boot_cpu_has(X86_FEATURE_XMM2) -#define cpu_has_xmm3 boot_cpu_has(X86_FEATURE_XMM3) -#define cpu_has_ssse3 boot_cpu_has(X86_FEATURE_SSSE3) #define cpu_has_aes boot_cpu_has(X86_FEATURE_AES) #define cpu_has_avx boot_cpu_has(X86_FEATURE_AVX) #define cpu_has_avx2 boot_cpu_has(X86_FEATURE_AVX2) -#define cpu_has_ht boot_cpu_has(X86_FEATURE_HT) -#define cpu_has_nx boot_cpu_has(X86_FEATURE_NX) -#define cpu_has_xstore boot_cpu_has(X86_FEATURE_XSTORE) -#define cpu_has_xstore_enabled boot_cpu_has(X86_FEATURE_XSTORE_EN) -#define cpu_has_xcrypt boot_cpu_has(X86_FEATURE_XCRYPT) -#define cpu_has_xcrypt_enabled boot_cpu_has(X86_FEATURE_XCRYPT_EN) -#define cpu_has_ace2 boot_cpu_has(X86_FEATURE_ACE2) -#define cpu_has_ace2_enabled boot_cpu_has(X86_FEATURE_ACE2_EN) -#define cpu_has_phe boot_cpu_has(X86_FEATURE_PHE) -#define cpu_has_phe_enabled boot_cpu_has(X86_FEATURE_PHE_EN) -#define cpu_has_pmm boot_cpu_has(X86_FEATURE_PMM) -#define cpu_has_pmm_enabled boot_cpu_has(X86_FEATURE_PMM_EN) -#define cpu_has_ds boot_cpu_has(X86_FEATURE_DS) -#define cpu_has_pebs boot_cpu_has(X86_FEATURE_PEBS) #define cpu_has_clflush boot_cpu_has(X86_FEATURE_CLFLUSH) -#define cpu_has_bts boot_cpu_has(X86_FEATURE_BTS) #define cpu_has_gbpages boot_cpu_has(X86_FEATURE_GBPAGES) #define cpu_has_arch_perfmon boot_cpu_has(X86_FEATURE_ARCH_PERFMON) #define cpu_has_pat boot_cpu_has(X86_FEATURE_PAT) -#define cpu_has_xmm4_1 boot_cpu_has(X86_FEATURE_XMM4_1) -#define cpu_has_xmm4_2 boot_cpu_has(X86_FEATURE_XMM4_2) #define cpu_has_x2apic boot_cpu_has(X86_FEATURE_X2APIC) #define cpu_has_xsave boot_cpu_has(X86_FEATURE_XSAVE) -#define cpu_has_xsaveopt boot_cpu_has(X86_FEATURE_XSAVEOPT) #define cpu_has_xsaves boot_cpu_has(X86_FEATURE_XSAVES) #define cpu_has_osxsave boot_cpu_has(X86_FEATURE_OSXSAVE) #define cpu_has_hypervisor boot_cpu_has(X86_FEATURE_HYPERVISOR) -#define cpu_has_pclmulqdq boot_cpu_has(X86_FEATURE_PCLMULQDQ) -#define cpu_has_perfctr_core boot_cpu_has(X86_FEATURE_PERFCTR_CORE) -#define cpu_has_perfctr_nb boot_cpu_has(X86_FEATURE_PERFCTR_NB) -#define cpu_has_perfctr_l2 boot_cpu_has(X86_FEATURE_PERFCTR_L2) -#define cpu_has_cx8 boot_cpu_has(X86_FEATURE_CX8) -#define cpu_has_cx16 boot_cpu_has(X86_FEATURE_CX16) -#define cpu_has_eager_fpu boot_cpu_has(X86_FEATURE_EAGER_FPU) -#define cpu_has_topoext boot_cpu_has(X86_FEATURE_TOPOEXT) -#define cpu_has_bpext boot_cpu_has(X86_FEATURE_BPEXT) - -#if __GNUC__ >= 4 +/* + * Do not add any more of those clumsy macros - use static_cpu_has_safe() for + * fast paths and boot_cpu_has() otherwise! + */ + +#if __GNUC__ >= 4 && defined(CONFIG_X86_FAST_FEATURE_TESTS) extern void warn_pre_alternatives(void); extern bool __static_cpu_has_safe(u16 bit); diff --git a/arch/x86/include/asm/fixmap.h b/arch/x86/include/asm/fixmap.h index f80d70009ff8..6d7d0e52ed5a 100644 --- a/arch/x86/include/asm/fixmap.h +++ b/arch/x86/include/asm/fixmap.h @@ -19,7 +19,6 @@ #include <asm/acpi.h> #include <asm/apicdef.h> #include <asm/page.h> -#include <asm/pvclock.h> #ifdef CONFIG_X86_32 #include <linux/threads.h> #include <asm/kmap_types.h> @@ -72,10 +71,6 @@ enum fixed_addresses { #ifdef CONFIG_X86_VSYSCALL_EMULATION VSYSCALL_PAGE = (FIXADDR_TOP - VSYSCALL_ADDR) >> PAGE_SHIFT, #endif -#ifdef CONFIG_PARAVIRT_CLOCK - PVCLOCK_FIXMAP_BEGIN, - PVCLOCK_FIXMAP_END = PVCLOCK_FIXMAP_BEGIN+PVCLOCK_VSYSCALL_NR_PAGES-1, -#endif #endif FIX_DBGP_BASE, FIX_EARLYCON_MEM_BASE, diff --git a/arch/x86/include/asm/fpu/internal.h b/arch/x86/include/asm/fpu/internal.h index 3c3550c3a4a3..eadcdd5bb946 100644 --- a/arch/x86/include/asm/fpu/internal.h +++ b/arch/x86/include/asm/fpu/internal.h @@ -224,18 +224,67 @@ static inline void copy_fxregs_to_kernel(struct fpu *fpu) #define XRSTOR ".byte " REX_PREFIX "0x0f,0xae,0x2f" #define XRSTORS ".byte " REX_PREFIX "0x0f,0xc7,0x1f" -/* xstate instruction fault handler: */ -#define xstate_fault(__err) \ - \ - ".section .fixup,\"ax\"\n" \ - \ - "3: movl $-2,%[_err]\n" \ - " jmp 2b\n" \ - \ - ".previous\n" \ - \ - _ASM_EXTABLE(1b, 3b) \ - : [_err] "=r" (__err) +#define XSTATE_OP(op, st, lmask, hmask, err) \ + asm volatile("1:" op "\n\t" \ + "xor %[err], %[err]\n" \ + "2:\n\t" \ + ".pushsection .fixup,\"ax\"\n\t" \ + "3: movl $-2,%[err]\n\t" \ + "jmp 2b\n\t" \ + ".popsection\n\t" \ + _ASM_EXTABLE(1b, 3b) \ + : [err] "=r" (err) \ + : "D" (st), "m" (*st), "a" (lmask), "d" (hmask) \ + : "memory") + +/* + * If XSAVES is enabled, it replaces XSAVEOPT because it supports a compact + * format and supervisor states in addition to modified optimization in + * XSAVEOPT. + * + * Otherwise, if XSAVEOPT is enabled, XSAVEOPT replaces XSAVE because XSAVEOPT + * supports modified optimization which is not supported by XSAVE. + * + * We use XSAVE as a fallback. + * + * The 661 label is defined in the ALTERNATIVE* macros as the address of the + * original instruction which gets replaced. We need to use it here as the + * address of the instruction where we might get an exception at. + */ +#define XSTATE_XSAVE(st, lmask, hmask, err) \ + asm volatile(ALTERNATIVE_2(XSAVE, \ + XSAVEOPT, X86_FEATURE_XSAVEOPT, \ + XSAVES, X86_FEATURE_XSAVES) \ + "\n" \ + "xor %[err], %[err]\n" \ + "3:\n" \ + ".pushsection .fixup,\"ax\"\n" \ + "4: movl $-2, %[err]\n" \ + "jmp 3b\n" \ + ".popsection\n" \ + _ASM_EXTABLE(661b, 4b) \ + : [err] "=r" (err) \ + : "D" (st), "m" (*st), "a" (lmask), "d" (hmask) \ + : "memory") + +/* + * Use XRSTORS to restore context if it is enabled. XRSTORS supports compact + * XSAVE area format. + */ +#define XSTATE_XRESTORE(st, lmask, hmask, err) \ + asm volatile(ALTERNATIVE(XRSTOR, \ + XRSTORS, X86_FEATURE_XSAVES) \ + "\n" \ + "xor %[err], %[err]\n" \ + "3:\n" \ + ".pushsection .fixup,\"ax\"\n" \ + "4: movl $-2, %[err]\n" \ + "jmp 3b\n" \ + ".popsection\n" \ + _ASM_EXTABLE(661b, 4b) \ + : [err] "=r" (err) \ + : "D" (st), "m" (*st), "a" (lmask), "d" (hmask) \ + : "memory") /* * This function is called only during boot time when x86 caps are not set @@ -246,22 +295,14 @@ static inline void copy_xregs_to_kernel_booting(struct xregs_state *xstate) u64 mask = -1; u32 lmask = mask; u32 hmask = mask >> 32; - int err = 0; + int err; WARN_ON(system_state != SYSTEM_BOOTING); - if (boot_cpu_has(X86_FEATURE_XSAVES)) - asm volatile("1:"XSAVES"\n\t" - "2:\n\t" - xstate_fault(err) - : "D" (xstate), "m" (*xstate), "a" (lmask), "d" (hmask), "0" (err) - : "memory"); + if (static_cpu_has_safe(X86_FEATURE_XSAVES)) + XSTATE_OP(XSAVES, xstate, lmask, hmask, err); else - asm volatile("1:"XSAVE"\n\t" - "2:\n\t" - xstate_fault(err) - : "D" (xstate), "m" (*xstate), "a" (lmask), "d" (hmask), "0" (err) - : "memory"); + XSTATE_OP(XSAVE, xstate, lmask, hmask, err); /* We should never fault when copying to a kernel buffer: */ WARN_ON_FPU(err); @@ -276,22 +317,14 @@ static inline void copy_kernel_to_xregs_booting(struct xregs_state *xstate) u64 mask = -1; u32 lmask = mask; u32 hmask = mask >> 32; - int err = 0; + int err; WARN_ON(system_state != SYSTEM_BOOTING); - if (boot_cpu_has(X86_FEATURE_XSAVES)) - asm volatile("1:"XRSTORS"\n\t" - "2:\n\t" - xstate_fault(err) - : "D" (xstate), "m" (*xstate), "a" (lmask), "d" (hmask), "0" (err) - : "memory"); + if (static_cpu_has_safe(X86_FEATURE_XSAVES)) + XSTATE_OP(XRSTORS, xstate, lmask, hmask, err); else - asm volatile("1:"XRSTOR"\n\t" - "2:\n\t" - xstate_fault(err) - : "D" (xstate), "m" (*xstate), "a" (lmask), "d" (hmask), "0" (err) - : "memory"); + XSTATE_OP(XRSTOR, xstate, lmask, hmask, err); /* We should never fault when copying from a kernel buffer: */ WARN_ON_FPU(err); @@ -305,33 +338,11 @@ static inline void copy_xregs_to_kernel(struct xregs_state *xstate) u64 mask = -1; u32 lmask = mask; u32 hmask = mask >> 32; - int err = 0; + int err; WARN_ON(!alternatives_patched); - /* - * If xsaves is enabled, xsaves replaces xsaveopt because - * it supports compact format and supervisor states in addition to - * modified optimization in xsaveopt. - * - * Otherwise, if xsaveopt is enabled, xsaveopt replaces xsave - * because xsaveopt supports modified optimization which is not - * supported by xsave. - * - * If none of xsaves and xsaveopt is enabled, use xsave. - */ - alternative_input_2( - "1:"XSAVE, - XSAVEOPT, - X86_FEATURE_XSAVEOPT, - XSAVES, - X86_FEATURE_XSAVES, - [xstate] "D" (xstate), "a" (lmask), "d" (hmask) : - "memory"); - asm volatile("2:\n\t" - xstate_fault(err) - : "0" (err) - : "memory"); + XSTATE_XSAVE(xstate, lmask, hmask, err); /* We should never fault when copying to a kernel buffer: */ WARN_ON_FPU(err); @@ -344,23 +355,9 @@ static inline void copy_kernel_to_xregs(struct xregs_state *xstate, u64 mask) { u32 lmask = mask; u32 hmask = mask >> 32; - int err = 0; + int err; - /* - * Use xrstors to restore context if it is enabled. xrstors supports - * compacted format of xsave area which is not supported by xrstor. - */ - alternative_input( - "1: " XRSTOR, - XRSTORS, - X86_FEATURE_XSAVES, - "D" (xstate), "m" (*xstate), "a" (lmask), "d" (hmask) - : "memory"); - - asm volatile("2:\n" - xstate_fault(err) - : "0" (err) - : "memory"); + XSTATE_XRESTORE(xstate, lmask, hmask, err); /* We should never fault when copying from a kernel buffer: */ WARN_ON_FPU(err); @@ -388,12 +385,10 @@ static inline int copy_xregs_to_user(struct xregs_state __user *buf) if (unlikely(err)) return -EFAULT; - __asm__ __volatile__(ASM_STAC "\n" - "1:"XSAVE"\n" - "2: " ASM_CLAC "\n" - xstate_fault(err) - : "D" (buf), "a" (-1), "d" (-1), "0" (err) - : "memory"); + stac(); + XSTATE_OP(XSAVE, buf, -1, -1, err); + clac(); + return err; } @@ -405,14 +400,12 @@ static inline int copy_user_to_xregs(struct xregs_state __user *buf, u64 mask) struct xregs_state *xstate = ((__force struct xregs_state *)buf); u32 lmask = mask; u32 hmask = mask >> 32; - int err = 0; - - __asm__ __volatile__(ASM_STAC "\n" - "1:"XRSTOR"\n" - "2: " ASM_CLAC "\n" - xstate_fault(err) - : "D" (xstate), "a" (lmask), "d" (hmask), "0" (err) - : "memory"); /* memory required? */ + int err; + + stac(); + XSTATE_OP(XRSTOR, xstate, lmask, hmask, err); + clac(); + return err; } diff --git a/arch/x86/include/asm/intel_pt.h b/arch/x86/include/asm/intel_pt.h new file mode 100644 index 000000000000..e1a411786bf5 --- /dev/null +++ b/arch/x86/include/asm/intel_pt.h @@ -0,0 +1,10 @@ +#ifndef _ASM_X86_INTEL_PT_H +#define _ASM_X86_INTEL_PT_H + +#if defined(CONFIG_PERF_EVENTS) && defined(CONFIG_CPU_SUP_INTEL) +void cpu_emergency_stop_pt(void); +#else +static inline void cpu_emergency_stop_pt(void) {} +#endif + +#endif /* _ASM_X86_INTEL_PT_H */ diff --git a/arch/x86/include/asm/ipi.h b/arch/x86/include/asm/ipi.h index 615fa9061b57..cfc9a0d2d07c 100644 --- a/arch/x86/include/asm/ipi.h +++ b/arch/x86/include/asm/ipi.h @@ -119,6 +119,8 @@ static inline void native_apic_mem_write(APIC_ICR, cfg); } +extern void default_send_IPI_single(int cpu, int vector); +extern void default_send_IPI_single_phys(int cpu, int vector); extern void default_send_IPI_mask_sequence_phys(const struct cpumask *mask, int vector); extern void default_send_IPI_mask_allbutself_phys(const struct cpumask *mask, diff --git a/arch/x86/include/asm/jump_label.h b/arch/x86/include/asm/jump_label.h index 5daeca3d0f9e..adc54c12cbd1 100644 --- a/arch/x86/include/asm/jump_label.h +++ b/arch/x86/include/asm/jump_label.h @@ -1,12 +1,18 @@ #ifndef _ASM_X86_JUMP_LABEL_H #define _ASM_X86_JUMP_LABEL_H -#ifndef __ASSEMBLY__ - -#include <linux/stringify.h> -#include <linux/types.h> -#include <asm/nops.h> -#include <asm/asm.h> +#ifndef HAVE_JUMP_LABEL +/* + * For better or for worse, if jump labels (the gcc extension) are missing, + * then the entire static branch patching infrastructure is compiled out. + * If that happens, the code in here will malfunction. Raise a compiler + * error instead. + * + * In theory, jump labels and the static branch patching infrastructure + * could be decoupled to fix this. + */ +#error asm/jump_label.h included on a non-jump-label kernel +#endif #define JUMP_LABEL_NOP_SIZE 5 @@ -16,6 +22,14 @@ # define STATIC_KEY_INIT_NOP GENERIC_NOP5_ATOMIC #endif +#include <asm/asm.h> +#include <asm/nops.h> + +#ifndef __ASSEMBLY__ + +#include <linux/stringify.h> +#include <linux/types.h> + static __always_inline bool arch_static_branch(struct static_key *key, bool branch) { asm_volatile_goto("1:" @@ -59,5 +73,40 @@ struct jump_entry { jump_label_t key; }; -#endif /* __ASSEMBLY__ */ +#else /* __ASSEMBLY__ */ + +.macro STATIC_JUMP_IF_TRUE target, key, def +.Lstatic_jump_\@: + .if \def + /* Equivalent to "jmp.d32 \target" */ + .byte 0xe9 + .long \target - .Lstatic_jump_after_\@ +.Lstatic_jump_after_\@: + .else + .byte STATIC_KEY_INIT_NOP + .endif + .pushsection __jump_table, "aw" + _ASM_ALIGN + _ASM_PTR .Lstatic_jump_\@, \target, \key + .popsection +.endm + +.macro STATIC_JUMP_IF_FALSE target, key, def +.Lstatic_jump_\@: + .if \def + .byte STATIC_KEY_INIT_NOP + .else + /* Equivalent to "jmp.d32 \target" */ + .byte 0xe9 + .long \target - .Lstatic_jump_after_\@ +.Lstatic_jump_after_\@: + .endif + .pushsection __jump_table, "aw" + _ASM_ALIGN + _ASM_PTR .Lstatic_jump_\@, \target, \key + 1 + .popsection +.endm + +#endif /* __ASSEMBLY__ */ + #endif diff --git a/arch/x86/include/asm/microcode.h b/arch/x86/include/asm/microcode.h index 34e62b1dcfce..1e1b07a5a738 100644 --- a/arch/x86/include/asm/microcode.h +++ b/arch/x86/include/asm/microcode.h @@ -1,6 +1,7 @@ #ifndef _ASM_X86_MICROCODE_H #define _ASM_X86_MICROCODE_H +#include <asm/cpu.h> #include <linux/earlycpio.h> #define native_rdmsr(msr, val1, val2) \ @@ -95,14 +96,14 @@ static inline void __exit exit_amd_microcode(void) {} /* * In early loading microcode phase on BSP, boot_cpu_data is not set up yet. - * x86_vendor() gets vendor id for BSP. + * x86_cpuid_vendor() gets vendor id for BSP. * * In 32 bit AP case, accessing boot_cpu_data needs linear address. To simplify - * coding, we still use x86_vendor() to get vendor id for AP. + * coding, we still use x86_cpuid_vendor() to get vendor id for AP. * - * x86_vendor() gets vendor information directly from CPUID. + * x86_cpuid_vendor() gets vendor information directly from CPUID. */ -static inline int x86_vendor(void) +static inline int x86_cpuid_vendor(void) { u32 eax = 0x00000000; u32 ebx, ecx = 0, edx; @@ -118,40 +119,14 @@ static inline int x86_vendor(void) return X86_VENDOR_UNKNOWN; } -static inline unsigned int __x86_family(unsigned int sig) -{ - unsigned int x86; - - x86 = (sig >> 8) & 0xf; - - if (x86 == 0xf) - x86 += (sig >> 20) & 0xff; - - return x86; -} - -static inline unsigned int x86_family(void) +static inline unsigned int x86_cpuid_family(void) { u32 eax = 0x00000001; u32 ebx, ecx = 0, edx; native_cpuid(&eax, &ebx, &ecx, &edx); - return __x86_family(eax); -} - -static inline unsigned int x86_model(unsigned int sig) -{ - unsigned int x86, model; - - x86 = __x86_family(sig); - - model = (sig >> 4) & 0xf; - - if (x86 == 0x6 || x86 == 0xf) - model += ((sig >> 16) & 0xf) << 4; - - return model; + return x86_family(eax); } #ifdef CONFIG_MICROCODE diff --git a/arch/x86/include/asm/msi.h b/arch/x86/include/asm/msi.h index 93724cc62177..eb4b09b41df5 100644 --- a/arch/x86/include/asm/msi.h +++ b/arch/x86/include/asm/msi.h @@ -1,7 +1,13 @@ #ifndef _ASM_X86_MSI_H #define _ASM_X86_MSI_H #include <asm/hw_irq.h> +#include <asm/irqdomain.h> typedef struct irq_alloc_info msi_alloc_info_t; +int pci_msi_prepare(struct irq_domain *domain, struct device *dev, int nvec, + msi_alloc_info_t *arg); + +void pci_msi_set_desc(msi_alloc_info_t *arg, struct msi_desc *desc); + #endif /* _ASM_X86_MSI_H */ diff --git a/arch/x86/include/asm/msr-index.h b/arch/x86/include/asm/msr-index.h index 9f3905697f12..b05402ef3b84 100644 --- a/arch/x86/include/asm/msr-index.h +++ b/arch/x86/include/asm/msr-index.h @@ -35,7 +35,7 @@ #define MSR_IA32_PERFCTR0 0x000000c1 #define MSR_IA32_PERFCTR1 0x000000c2 #define MSR_FSB_FREQ 0x000000cd -#define MSR_NHM_PLATFORM_INFO 0x000000ce +#define MSR_PLATFORM_INFO 0x000000ce #define MSR_NHM_SNB_PKG_CST_CFG_CTL 0x000000e2 #define NHM_C3_AUTO_DEMOTE (1UL << 25) @@ -44,7 +44,6 @@ #define SNB_C1_AUTO_UNDEMOTE (1UL << 27) #define SNB_C3_AUTO_UNDEMOTE (1UL << 28) -#define MSR_PLATFORM_INFO 0x000000ce #define MSR_MTRRcap 0x000000fe #define MSR_IA32_BBL_CR_CTL 0x00000119 #define MSR_IA32_BBL_CR_CTL3 0x0000011e @@ -322,6 +321,7 @@ #define MSR_F15H_PERF_CTR 0xc0010201 #define MSR_F15H_NB_PERF_CTL 0xc0010240 #define MSR_F15H_NB_PERF_CTR 0xc0010241 +#define MSR_F15H_IC_CFG 0xc0011021 /* Fam 10h MSRs */ #define MSR_FAM10H_MMIO_CONF_BASE 0xc0010058 diff --git a/arch/x86/include/asm/msr-trace.h b/arch/x86/include/asm/msr-trace.h new file mode 100644 index 000000000000..7567225747d8 --- /dev/null +++ b/arch/x86/include/asm/msr-trace.h @@ -0,0 +1,57 @@ +#undef TRACE_SYSTEM +#define TRACE_SYSTEM msr + +#undef TRACE_INCLUDE_FILE +#define TRACE_INCLUDE_FILE msr-trace + +#undef TRACE_INCLUDE_PATH +#define TRACE_INCLUDE_PATH asm/ + +#if !defined(_TRACE_MSR_H) || defined(TRACE_HEADER_MULTI_READ) +#define _TRACE_MSR_H + +#include <linux/tracepoint.h> + +/* + * Tracing for x86 model specific registers. Directly maps to the + * RDMSR/WRMSR instructions. + */ + +DECLARE_EVENT_CLASS(msr_trace_class, + TP_PROTO(unsigned msr, u64 val, int failed), + TP_ARGS(msr, val, failed), + TP_STRUCT__entry( + __field( unsigned, msr ) + __field( u64, val ) + __field( int, failed ) + ), + TP_fast_assign( + __entry->msr = msr; + __entry->val = val; + __entry->failed = failed; + ), + TP_printk("%x, value %llx%s", + __entry->msr, + __entry->val, + __entry->failed ? " #GP" : "") +); + +DEFINE_EVENT(msr_trace_class, read_msr, + TP_PROTO(unsigned msr, u64 val, int failed), + TP_ARGS(msr, val, failed) +); + +DEFINE_EVENT(msr_trace_class, write_msr, + TP_PROTO(unsigned msr, u64 val, int failed), + TP_ARGS(msr, val, failed) +); + +DEFINE_EVENT(msr_trace_class, rdpmc, + TP_PROTO(unsigned msr, u64 val, int failed), + TP_ARGS(msr, val, failed) +); + +#endif /* _TRACE_MSR_H */ + +/* This part must be outside protection */ +#include <trace/define_trace.h> diff --git a/arch/x86/include/asm/msr.h b/arch/x86/include/asm/msr.h index 77d8b284e4a7..93fb7c1cffda 100644 --- a/arch/x86/include/asm/msr.h +++ b/arch/x86/include/asm/msr.h @@ -32,6 +32,16 @@ struct msr_regs_info { int err; }; +struct saved_msr { + bool valid; + struct msr_info info; +}; + +struct saved_msrs { + unsigned int num; + struct saved_msr *array; +}; + static inline unsigned long long native_read_tscp(unsigned int *aux) { unsigned long low, high; @@ -57,11 +67,34 @@ static inline unsigned long long native_read_tscp(unsigned int *aux) #define EAX_EDX_RET(val, low, high) "=A" (val) #endif +#ifdef CONFIG_TRACEPOINTS +/* + * Be very careful with includes. This header is prone to include loops. + */ +#include <asm/atomic.h> +#include <linux/tracepoint-defs.h> + +extern struct tracepoint __tracepoint_read_msr; +extern struct tracepoint __tracepoint_write_msr; +extern struct tracepoint __tracepoint_rdpmc; +#define msr_tracepoint_active(t) static_key_false(&(t).key) +extern void do_trace_write_msr(unsigned msr, u64 val, int failed); +extern void do_trace_read_msr(unsigned msr, u64 val, int failed); +extern void do_trace_rdpmc(unsigned msr, u64 val, int failed); +#else +#define msr_tracepoint_active(t) false +static inline void do_trace_write_msr(unsigned msr, u64 val, int failed) {} +static inline void do_trace_read_msr(unsigned msr, u64 val, int failed) {} +static inline void do_trace_rdpmc(unsigned msr, u64 val, int failed) {} +#endif + static inline unsigned long long native_read_msr(unsigned int msr) { DECLARE_ARGS(val, low, high); asm volatile("rdmsr" : EAX_EDX_RET(val, low, high) : "c" (msr)); + if (msr_tracepoint_active(__tracepoint_read_msr)) + do_trace_read_msr(msr, EAX_EDX_VAL(val, low, high), 0); return EAX_EDX_VAL(val, low, high); } @@ -78,6 +111,8 @@ static inline unsigned long long native_read_msr_safe(unsigned int msr, _ASM_EXTABLE(2b, 3b) : [err] "=r" (*err), EAX_EDX_RET(val, low, high) : "c" (msr), [fault] "i" (-EIO)); + if (msr_tracepoint_active(__tracepoint_read_msr)) + do_trace_read_msr(msr, EAX_EDX_VAL(val, low, high), *err); return EAX_EDX_VAL(val, low, high); } @@ -85,6 +120,8 @@ static inline void native_write_msr(unsigned int msr, unsigned low, unsigned high) { asm volatile("wrmsr" : : "c" (msr), "a"(low), "d" (high) : "memory"); + if (msr_tracepoint_active(__tracepoint_read_msr)) + do_trace_write_msr(msr, ((u64)high << 32 | low), 0); } /* Can be uninlined because referenced by paravirt */ @@ -102,6 +139,8 @@ notrace static inline int native_write_msr_safe(unsigned int msr, : "c" (msr), "0" (low), "d" (high), [fault] "i" (-EIO) : "memory"); + if (msr_tracepoint_active(__tracepoint_read_msr)) + do_trace_write_msr(msr, ((u64)high << 32 | low), err); return err; } @@ -160,6 +199,8 @@ static inline unsigned long long native_read_pmc(int counter) DECLARE_ARGS(val, low, high); asm volatile("rdpmc" : EAX_EDX_RET(val, low, high) : "c" (counter)); + if (msr_tracepoint_active(__tracepoint_rdpmc)) + do_trace_rdpmc(counter, EAX_EDX_VAL(val, low, high), 0); return EAX_EDX_VAL(val, low, high); } @@ -190,7 +231,7 @@ static inline void wrmsr(unsigned msr, unsigned low, unsigned high) static inline void wrmsrl(unsigned msr, u64 val) { - native_write_msr(msr, (u32)val, (u32)(val >> 32)); + native_write_msr(msr, (u32)(val & 0xffffffffULL), (u32)(val >> 32)); } /* wrmsr with exception handling */ diff --git a/arch/x86/include/asm/page_types.h b/arch/x86/include/asm/page_types.h index c5b7fb2774d0..7bd0099384ca 100644 --- a/arch/x86/include/asm/page_types.h +++ b/arch/x86/include/asm/page_types.h @@ -5,23 +5,25 @@ #include <linux/types.h> /* PAGE_SHIFT determines the page size */ -#define PAGE_SHIFT 12 -#define PAGE_SIZE (_AC(1,UL) << PAGE_SHIFT) -#define PAGE_MASK (~(PAGE_SIZE-1)) +#define PAGE_SHIFT 12 +#define PAGE_SIZE (_AC(1,UL) << PAGE_SHIFT) +#define PAGE_MASK (~(PAGE_SIZE-1)) + +#define PMD_PAGE_SIZE (_AC(1, UL) << PMD_SHIFT) +#define PMD_PAGE_MASK (~(PMD_PAGE_SIZE-1)) + +#define PUD_PAGE_SIZE (_AC(1, UL) << PUD_SHIFT) +#define PUD_PAGE_MASK (~(PUD_PAGE_SIZE-1)) #define __PHYSICAL_MASK ((phys_addr_t)((1ULL << __PHYSICAL_MASK_SHIFT) - 1)) #define __VIRTUAL_MASK ((1UL << __VIRTUAL_MASK_SHIFT) - 1) -/* Cast PAGE_MASK to a signed type so that it is sign-extended if +/* Cast *PAGE_MASK to a signed type so that it is sign-extended if virtual addresses are 32-bits but physical addresses are larger (ie, 32-bit PAE). */ #define PHYSICAL_PAGE_MASK (((signed long)PAGE_MASK) & __PHYSICAL_MASK) - -#define PMD_PAGE_SIZE (_AC(1, UL) << PMD_SHIFT) -#define PMD_PAGE_MASK (~(PMD_PAGE_SIZE-1)) - -#define PUD_PAGE_SIZE (_AC(1, UL) << PUD_SHIFT) -#define PUD_PAGE_MASK (~(PUD_PAGE_SIZE-1)) +#define PHYSICAL_PMD_PAGE_MASK (((signed long)PMD_PAGE_MASK) & __PHYSICAL_MASK) +#define PHYSICAL_PUD_PAGE_MASK (((signed long)PUD_PAGE_MASK) & __PHYSICAL_MASK) #define HPAGE_SHIFT PMD_SHIFT #define HPAGE_SIZE (_AC(1,UL) << HPAGE_SHIFT) diff --git a/arch/x86/include/asm/paravirt.h b/arch/x86/include/asm/paravirt.h index 10d0596433f8..f6192502149e 100644 --- a/arch/x86/include/asm/paravirt.h +++ b/arch/x86/include/asm/paravirt.h @@ -19,6 +19,12 @@ static inline int paravirt_enabled(void) return pv_info.paravirt_enabled; } +static inline int paravirt_has_feature(unsigned int feature) +{ + WARN_ON_ONCE(!pv_info.paravirt_enabled); + return (pv_info.features & feature); +} + static inline void load_sp0(struct tss_struct *tss, struct thread_struct *thread) { @@ -285,15 +291,6 @@ static inline void slow_down_io(void) #endif } -#ifdef CONFIG_SMP -static inline void startup_ipi_hook(int phys_apicid, unsigned long start_eip, - unsigned long start_esp) -{ - PVOP_VCALL3(pv_apic_ops.startup_ipi_hook, - phys_apicid, start_eip, start_esp); -} -#endif - static inline void paravirt_activate_mm(struct mm_struct *prev, struct mm_struct *next) { @@ -375,23 +372,6 @@ static inline void pte_update(struct mm_struct *mm, unsigned long addr, { PVOP_VCALL3(pv_mmu_ops.pte_update, mm, addr, ptep); } -static inline void pmd_update(struct mm_struct *mm, unsigned long addr, - pmd_t *pmdp) -{ - PVOP_VCALL3(pv_mmu_ops.pmd_update, mm, addr, pmdp); -} - -static inline void pte_update_defer(struct mm_struct *mm, unsigned long addr, - pte_t *ptep) -{ - PVOP_VCALL3(pv_mmu_ops.pte_update_defer, mm, addr, ptep); -} - -static inline void pmd_update_defer(struct mm_struct *mm, unsigned long addr, - pmd_t *pmdp) -{ - PVOP_VCALL3(pv_mmu_ops.pmd_update_defer, mm, addr, pmdp); -} static inline pte_t __pte(pteval_t val) { @@ -922,23 +902,11 @@ extern void default_banner(void); call PARA_INDIRECT(pv_irq_ops+PV_IRQ_irq_enable); \ PV_RESTORE_REGS(clobbers | CLBR_CALLEE_SAVE);) -#define USERGS_SYSRET32 \ - PARA_SITE(PARA_PATCH(pv_cpu_ops, PV_CPU_usergs_sysret32), \ - CLBR_NONE, \ - jmp PARA_INDIRECT(pv_cpu_ops+PV_CPU_usergs_sysret32)) - #ifdef CONFIG_X86_32 #define GET_CR0_INTO_EAX \ push %ecx; push %edx; \ call PARA_INDIRECT(pv_cpu_ops+PV_CPU_read_cr0); \ pop %edx; pop %ecx - -#define ENABLE_INTERRUPTS_SYSEXIT \ - PARA_SITE(PARA_PATCH(pv_cpu_ops, PV_CPU_irq_enable_sysexit), \ - CLBR_NONE, \ - jmp PARA_INDIRECT(pv_cpu_ops+PV_CPU_irq_enable_sysexit)) - - #else /* !CONFIG_X86_32 */ /* diff --git a/arch/x86/include/asm/paravirt_types.h b/arch/x86/include/asm/paravirt_types.h index 31247b5bff7c..77db5616a473 100644 --- a/arch/x86/include/asm/paravirt_types.h +++ b/arch/x86/include/asm/paravirt_types.h @@ -70,9 +70,14 @@ struct pv_info { #endif int paravirt_enabled; + unsigned int features; /* valid only if paravirt_enabled is set */ const char *name; }; +#define paravirt_has(x) paravirt_has_feature(PV_SUPPORTED_##x) +/* Supported features */ +#define PV_SUPPORTED_RTC (1<<0) + struct pv_init_ops { /* * Patch may replace one of the defined code sequences with @@ -157,15 +162,6 @@ struct pv_cpu_ops { u64 (*read_pmc)(int counter); -#ifdef CONFIG_X86_32 - /* - * Atomically enable interrupts and return to userspace. This - * is only used in 32-bit kernels. 64-bit kernels use - * usergs_sysret32 instead. - */ - void (*irq_enable_sysexit)(void); -#endif - /* * Switch to usermode gs and return to 64-bit usermode using * sysret. Only used in 64-bit kernels to return to 64-bit @@ -174,14 +170,6 @@ struct pv_cpu_ops { */ void (*usergs_sysret64)(void); - /* - * Switch to usermode gs and return to 32-bit usermode using - * sysret. Used to return to 32-on-64 compat processes. - * Other usermode register state, including %esp, must already - * be restored. - */ - void (*usergs_sysret32)(void); - /* Normal iret. Jump to this with the standard iret stack frame set up. */ void (*iret)(void); @@ -215,14 +203,6 @@ struct pv_irq_ops { #endif }; -struct pv_apic_ops { -#ifdef CONFIG_X86_LOCAL_APIC - void (*startup_ipi_hook)(int phys_apicid, - unsigned long start_eip, - unsigned long start_esp); -#endif -}; - struct pv_mmu_ops { unsigned long (*read_cr2)(void); void (*write_cr2)(unsigned long); @@ -274,12 +254,6 @@ struct pv_mmu_ops { pmd_t *pmdp, pmd_t pmdval); void (*pte_update)(struct mm_struct *mm, unsigned long addr, pte_t *ptep); - void (*pte_update_defer)(struct mm_struct *mm, - unsigned long addr, pte_t *ptep); - void (*pmd_update)(struct mm_struct *mm, unsigned long addr, - pmd_t *pmdp); - void (*pmd_update_defer)(struct mm_struct *mm, - unsigned long addr, pmd_t *pmdp); pte_t (*ptep_modify_prot_start)(struct mm_struct *mm, unsigned long addr, pte_t *ptep); @@ -354,7 +328,6 @@ struct paravirt_patch_template { struct pv_time_ops pv_time_ops; struct pv_cpu_ops pv_cpu_ops; struct pv_irq_ops pv_irq_ops; - struct pv_apic_ops pv_apic_ops; struct pv_mmu_ops pv_mmu_ops; struct pv_lock_ops pv_lock_ops; }; @@ -364,7 +337,6 @@ extern struct pv_init_ops pv_init_ops; extern struct pv_time_ops pv_time_ops; extern struct pv_cpu_ops pv_cpu_ops; extern struct pv_irq_ops pv_irq_ops; -extern struct pv_apic_ops pv_apic_ops; extern struct pv_mmu_ops pv_mmu_ops; extern struct pv_lock_ops pv_lock_ops; @@ -402,10 +374,8 @@ extern struct pv_lock_ops pv_lock_ops; __visible extern const char start_##ops##_##name[], end_##ops##_##name[]; \ asm(NATIVE_LABEL("start_", ops, name) code NATIVE_LABEL("end_", ops, name)) -unsigned paravirt_patch_nop(void); unsigned paravirt_patch_ident_32(void *insnbuf, unsigned len); unsigned paravirt_patch_ident_64(void *insnbuf, unsigned len); -unsigned paravirt_patch_ignore(unsigned len); unsigned paravirt_patch_call(void *insnbuf, const void *target, u16 tgt_clobbers, unsigned long addr, u16 site_clobbers, diff --git a/arch/x86/include/asm/pgtable.h b/arch/x86/include/asm/pgtable.h index 6ec0c8b2e9df..d3eee663c41f 100644 --- a/arch/x86/include/asm/pgtable.h +++ b/arch/x86/include/asm/pgtable.h @@ -69,9 +69,6 @@ extern struct mm_struct *pgd_page_get_mm(struct page *page); #define pmd_clear(pmd) native_pmd_clear(pmd) #define pte_update(mm, addr, ptep) do { } while (0) -#define pte_update_defer(mm, addr, ptep) do { } while (0) -#define pmd_update(mm, addr, ptep) do { } while (0) -#define pmd_update_defer(mm, addr, ptep) do { } while (0) #define pgd_val(x) native_pgd_val(x) #define __pgd(x) native_make_pgd(x) @@ -731,14 +728,9 @@ static inline void native_set_pmd_at(struct mm_struct *mm, unsigned long addr, * updates should either be sets, clears, or set_pte_atomic for P->P * transitions, which means this hook should only be called for user PTEs. * This hook implies a P->P protection or access change has taken place, which - * requires a subsequent TLB flush. The notification can optionally be delayed - * until the TLB flush event by using the pte_update_defer form of the - * interface, but care must be taken to assure that the flush happens while - * still holding the same page table lock so that the shadow and primary pages - * do not become out of sync on SMP. + * requires a subsequent TLB flush. */ #define pte_update(mm, addr, ptep) do { } while (0) -#define pte_update_defer(mm, addr, ptep) do { } while (0) #endif /* @@ -830,9 +822,7 @@ static inline int pmd_write(pmd_t pmd) static inline pmd_t pmdp_huge_get_and_clear(struct mm_struct *mm, unsigned long addr, pmd_t *pmdp) { - pmd_t pmd = native_pmdp_get_and_clear(pmdp); - pmd_update(mm, addr, pmdp); - return pmd; + return native_pmdp_get_and_clear(pmdp); } #define __HAVE_ARCH_PMDP_SET_WRPROTECT @@ -840,7 +830,6 @@ static inline void pmdp_set_wrprotect(struct mm_struct *mm, unsigned long addr, pmd_t *pmdp) { clear_bit(_PAGE_BIT_RW, (unsigned long *)pmdp); - pmd_update(mm, addr, pmdp); } /* diff --git a/arch/x86/include/asm/pgtable_types.h b/arch/x86/include/asm/pgtable_types.h index dd5b0aa9dd2f..a471cadb9630 100644 --- a/arch/x86/include/asm/pgtable_types.h +++ b/arch/x86/include/asm/pgtable_types.h @@ -279,17 +279,14 @@ static inline pmdval_t native_pmd_val(pmd_t pmd) static inline pudval_t pud_pfn_mask(pud_t pud) { if (native_pud_val(pud) & _PAGE_PSE) - return PUD_PAGE_MASK & PHYSICAL_PAGE_MASK; + return PHYSICAL_PUD_PAGE_MASK; else return PTE_PFN_MASK; } static inline pudval_t pud_flags_mask(pud_t pud) { - if (native_pud_val(pud) & _PAGE_PSE) - return ~(PUD_PAGE_MASK & (pudval_t)PHYSICAL_PAGE_MASK); - else - return ~PTE_PFN_MASK; + return ~pud_pfn_mask(pud); } static inline pudval_t pud_flags(pud_t pud) @@ -300,17 +297,14 @@ static inline pudval_t pud_flags(pud_t pud) static inline pmdval_t pmd_pfn_mask(pmd_t pmd) { if (native_pmd_val(pmd) & _PAGE_PSE) - return PMD_PAGE_MASK & PHYSICAL_PAGE_MASK; + return PHYSICAL_PMD_PAGE_MASK; else return PTE_PFN_MASK; } static inline pmdval_t pmd_flags_mask(pmd_t pmd) { - if (native_pmd_val(pmd) & _PAGE_PSE) - return ~(PMD_PAGE_MASK & (pmdval_t)PHYSICAL_PAGE_MASK); - else - return ~PTE_PFN_MASK; + return ~pmd_pfn_mask(pmd); } static inline pmdval_t pmd_flags(pmd_t pmd) diff --git a/arch/x86/include/asm/processor.h b/arch/x86/include/asm/processor.h index 67522256c7ff..2d5a50cb61a2 100644 --- a/arch/x86/include/asm/processor.h +++ b/arch/x86/include/asm/processor.h @@ -472,6 +472,7 @@ static inline unsigned long current_top_of_stack(void) #else #define __cpuid native_cpuid #define paravirt_enabled() 0 +#define paravirt_has(x) 0 static inline void load_sp0(struct tss_struct *tss, struct thread_struct *thread) diff --git a/arch/x86/include/asm/pvclock.h b/arch/x86/include/asm/pvclock.h index 7a6bed5c08bc..fdcc04020636 100644 --- a/arch/x86/include/asm/pvclock.h +++ b/arch/x86/include/asm/pvclock.h @@ -4,6 +4,15 @@ #include <linux/clocksource.h> #include <asm/pvclock-abi.h> +#ifdef CONFIG_KVM_GUEST +extern struct pvclock_vsyscall_time_info *pvclock_pvti_cpu0_va(void); +#else +static inline struct pvclock_vsyscall_time_info *pvclock_pvti_cpu0_va(void) +{ + return NULL; +} +#endif + /* some helper functions for xen and kvm pv clock sources */ cycle_t pvclock_clocksource_read(struct pvclock_vcpu_time_info *src); u8 pvclock_read_flags(struct pvclock_vcpu_time_info *src); @@ -91,10 +100,5 @@ struct pvclock_vsyscall_time_info { } __attribute__((__aligned__(SMP_CACHE_BYTES))); #define PVTI_SIZE sizeof(struct pvclock_vsyscall_time_info) -#define PVCLOCK_VSYSCALL_NR_PAGES (((NR_CPUS-1)/(PAGE_SIZE/PVTI_SIZE))+1) - -int __init pvclock_init_vsyscall(struct pvclock_vsyscall_time_info *i, - int size); -struct pvclock_vcpu_time_info *pvclock_get_vsyscall_time_info(int cpu); #endif /* _ASM_X86_PVCLOCK_H */ diff --git a/arch/x86/include/asm/qspinlock_paravirt.h b/arch/x86/include/asm/qspinlock_paravirt.h index b002e711ba88..9f92c180ed2f 100644 --- a/arch/x86/include/asm/qspinlock_paravirt.h +++ b/arch/x86/include/asm/qspinlock_paravirt.h @@ -1,6 +1,65 @@ #ifndef __ASM_QSPINLOCK_PARAVIRT_H #define __ASM_QSPINLOCK_PARAVIRT_H +/* + * For x86-64, PV_CALLEE_SAVE_REGS_THUNK() saves and restores 8 64-bit + * registers. For i386, however, only 1 32-bit register needs to be saved + * and restored. So an optimized version of __pv_queued_spin_unlock() is + * hand-coded for 64-bit, but it isn't worthwhile to do it for 32-bit. + */ +#ifdef CONFIG_64BIT + +PV_CALLEE_SAVE_REGS_THUNK(__pv_queued_spin_unlock_slowpath); +#define __pv_queued_spin_unlock __pv_queued_spin_unlock +#define PV_UNLOCK "__raw_callee_save___pv_queued_spin_unlock" +#define PV_UNLOCK_SLOWPATH "__raw_callee_save___pv_queued_spin_unlock_slowpath" + +/* + * Optimized assembly version of __raw_callee_save___pv_queued_spin_unlock + * which combines the registers saving trunk and the body of the following + * C code: + * + * void __pv_queued_spin_unlock(struct qspinlock *lock) + * { + * struct __qspinlock *l = (void *)lock; + * u8 lockval = cmpxchg(&l->locked, _Q_LOCKED_VAL, 0); + * + * if (likely(lockval == _Q_LOCKED_VAL)) + * return; + * pv_queued_spin_unlock_slowpath(lock, lockval); + * } + * + * For x86-64, + * rdi = lock (first argument) + * rsi = lockval (second argument) + * rdx = internal variable (set to 0) + */ +asm (".pushsection .text;" + ".globl " PV_UNLOCK ";" + ".align 4,0x90;" + PV_UNLOCK ": " + "push %rdx;" + "mov $0x1,%eax;" + "xor %edx,%edx;" + "lock cmpxchg %dl,(%rdi);" + "cmp $0x1,%al;" + "jne .slowpath;" + "pop %rdx;" + "ret;" + ".slowpath: " + "push %rsi;" + "movzbl %al,%esi;" + "call " PV_UNLOCK_SLOWPATH ";" + "pop %rsi;" + "pop %rdx;" + "ret;" + ".size " PV_UNLOCK ", .-" PV_UNLOCK ";" + ".popsection"); + +#else /* CONFIG_64BIT */ + +extern void __pv_queued_spin_unlock(struct qspinlock *lock); PV_CALLEE_SAVE_REGS_THUNK(__pv_queued_spin_unlock); +#endif /* CONFIG_64BIT */ #endif diff --git a/arch/x86/include/asm/reboot.h b/arch/x86/include/asm/reboot.h index a82c4f1b4d83..2cb1cc253d51 100644 --- a/arch/x86/include/asm/reboot.h +++ b/arch/x86/include/asm/reboot.h @@ -25,5 +25,6 @@ void __noreturn machine_real_restart(unsigned int type); typedef void (*nmi_shootdown_cb)(int, struct pt_regs*); void nmi_shootdown_cpus(nmi_shootdown_cb callback); +void run_crash_ipi_callback(struct pt_regs *regs); #endif /* _ASM_X86_REBOOT_H */ diff --git a/arch/x86/include/asm/smp.h b/arch/x86/include/asm/smp.h index 222a6a3ca2b5..dfcf0727623b 100644 --- a/arch/x86/include/asm/smp.h +++ b/arch/x86/include/asm/smp.h @@ -21,15 +21,6 @@ extern int smp_num_siblings; extern unsigned int num_processors; -static inline bool cpu_has_ht_siblings(void) -{ - bool has_siblings = false; -#ifdef CONFIG_SMP - has_siblings = cpu_has_ht && smp_num_siblings > 1; -#endif - return has_siblings; -} - DECLARE_PER_CPU_READ_MOSTLY(cpumask_var_t, cpu_sibling_map); DECLARE_PER_CPU_READ_MOSTLY(cpumask_var_t, cpu_core_map); /* cpus sharing the last level cache: */ @@ -74,9 +65,6 @@ struct smp_ops { extern void set_cpu_sibling_map(int cpu); #ifdef CONFIG_SMP -#ifndef CONFIG_PARAVIRT -#define startup_ipi_hook(phys_apicid, start_eip, start_esp) do { } while (0) -#endif extern struct smp_ops smp_ops; static inline void smp_send_stop(void) diff --git a/arch/x86/include/asm/suspend_32.h b/arch/x86/include/asm/suspend_32.h index d1793f06854d..8e9dbe7b73a1 100644 --- a/arch/x86/include/asm/suspend_32.h +++ b/arch/x86/include/asm/suspend_32.h @@ -15,6 +15,7 @@ struct saved_context { unsigned long cr0, cr2, cr3, cr4; u64 misc_enable; bool misc_enable_saved; + struct saved_msrs saved_msrs; struct desc_ptr gdt_desc; struct desc_ptr idt; u16 ldt; diff --git a/arch/x86/include/asm/suspend_64.h b/arch/x86/include/asm/suspend_64.h index 7ebf0ebe4e68..6136a18152af 100644 --- a/arch/x86/include/asm/suspend_64.h +++ b/arch/x86/include/asm/suspend_64.h @@ -24,6 +24,7 @@ struct saved_context { unsigned long cr0, cr2, cr3, cr4, cr8; u64 misc_enable; bool misc_enable_saved; + struct saved_msrs saved_msrs; unsigned long efer; u16 gdt_pad; /* Unused */ struct desc_ptr gdt_desc; diff --git a/arch/x86/include/asm/uaccess.h b/arch/x86/include/asm/uaccess.h index 09b1b0ab94b7..660458af425d 100644 --- a/arch/x86/include/asm/uaccess.h +++ b/arch/x86/include/asm/uaccess.h @@ -745,5 +745,14 @@ copy_to_user(void __user *to, const void *from, unsigned long n) #undef __copy_from_user_overflow #undef __copy_to_user_overflow +/* + * We rely on the nested NMI work to allow atomic faults from the NMI path; the + * nested NMI paths are careful to preserve CR2. + * + * Caller must use pagefault_enable/disable, or run in interrupt context, + * and also do a uaccess_ok() check + */ +#define __copy_from_user_nmi __copy_from_user_inatomic + #endif /* _ASM_X86_UACCESS_H */ diff --git a/arch/x86/include/asm/vdso.h b/arch/x86/include/asm/vdso.h index 756de9190aec..deabaf9759b6 100644 --- a/arch/x86/include/asm/vdso.h +++ b/arch/x86/include/asm/vdso.h @@ -22,6 +22,7 @@ struct vdso_image { long sym_vvar_page; long sym_hpet_page; + long sym_pvclock_page; long sym_VDSO32_NOTE_MASK; long sym___kernel_sigreturn; long sym___kernel_rt_sigreturn; diff --git a/arch/x86/include/asm/x86_init.h b/arch/x86/include/asm/x86_init.h index 48d34d28f5a6..1ae89a2721d6 100644 --- a/arch/x86/include/asm/x86_init.h +++ b/arch/x86/include/asm/x86_init.h @@ -1,7 +1,6 @@ #ifndef _ASM_X86_PLATFORM_H #define _ASM_X86_PLATFORM_H -#include <asm/pgtable_types.h> #include <asm/bootparam.h> struct mpc_bus; @@ -83,13 +82,11 @@ struct x86_init_paging { * struct x86_init_timers - platform specific timer setup * @setup_perpcu_clockev: set up the per cpu clock event device for the * boot cpu - * @tsc_pre_init: platform function called before TSC init * @timer_init: initialize the platform timer (default PIT/HPET) * @wallclock_init: init the wallclock device */ struct x86_init_timers { void (*setup_percpu_clockev)(void); - void (*tsc_pre_init)(void); void (*timer_init)(void); void (*wallclock_init)(void); }; diff --git a/arch/x86/include/asm/xor_32.h b/arch/x86/include/asm/xor_32.h index 5a08bc8bff33..c54beb44c4c1 100644 --- a/arch/x86/include/asm/xor_32.h +++ b/arch/x86/include/asm/xor_32.h @@ -553,7 +553,7 @@ do { \ if (cpu_has_xmm) { \ xor_speed(&xor_block_pIII_sse); \ xor_speed(&xor_block_sse_pf64); \ - } else if (cpu_has_mmx) { \ + } else if (boot_cpu_has(X86_FEATURE_MMX)) { \ xor_speed(&xor_block_pII_mmx); \ xor_speed(&xor_block_p5_mmx); \ } else { \ diff --git a/arch/x86/include/uapi/asm/mce.h b/arch/x86/include/uapi/asm/mce.h index 03429da2fa80..2184943341bf 100644 --- a/arch/x86/include/uapi/asm/mce.h +++ b/arch/x86/include/uapi/asm/mce.h @@ -16,7 +16,7 @@ struct mce { __u8 cpuvendor; /* cpu vendor as encoded in system.h */ __u8 inject_flags; /* software inject flags */ __u8 severity; - __u8 usable_addr; + __u8 pad; __u32 cpuid; /* CPUID 1 EAX */ __u8 cs; /* code segment */ __u8 bank; /* machine check bank */ diff --git a/arch/x86/kernel/apic/apic.c b/arch/x86/kernel/apic/apic.c index 2f69e3b184f6..8a5cddac7d44 100644 --- a/arch/x86/kernel/apic/apic.c +++ b/arch/x86/kernel/apic/apic.c @@ -82,6 +82,12 @@ physid_mask_t phys_cpu_present_map; static unsigned int disabled_cpu_apicid __read_mostly = BAD_APICID; /* + * This variable controls which CPUs receive external NMIs. By default, + * external NMIs are delivered only to the BSP. + */ +static int apic_extnmi = APIC_EXTNMI_BSP; + +/* * Map cpu index to physical APIC ID */ DEFINE_EARLY_PER_CPU_READ_MOSTLY(u16, x86_cpu_to_apicid, BAD_APICID); @@ -1161,6 +1167,8 @@ void __init init_bsp_APIC(void) value = APIC_DM_NMI; if (!lapic_is_integrated()) /* 82489DX */ value |= APIC_LVT_LEVEL_TRIGGER; + if (apic_extnmi == APIC_EXTNMI_NONE) + value |= APIC_LVT_MASKED; apic_write(APIC_LVT1, value); } @@ -1378,9 +1386,11 @@ void setup_local_APIC(void) apic_write(APIC_LVT0, value); /* - * only the BP should see the LINT1 NMI signal, obviously. + * Only the BSP sees the LINT1 NMI signal by default. This can be + * modified by apic_extnmi= boot option. */ - if (!cpu) + if ((!cpu && apic_extnmi != APIC_EXTNMI_NONE) || + apic_extnmi == APIC_EXTNMI_ALL) value = APIC_DM_NMI; else value = APIC_DM_NMI | APIC_LVT_MASKED; @@ -2270,6 +2280,7 @@ static struct { unsigned int apic_tmict; unsigned int apic_tdcr; unsigned int apic_thmr; + unsigned int apic_cmci; } apic_pm_state; static int lapic_suspend(void) @@ -2299,6 +2310,10 @@ static int lapic_suspend(void) if (maxlvt >= 5) apic_pm_state.apic_thmr = apic_read(APIC_LVTTHMR); #endif +#ifdef CONFIG_X86_MCE_INTEL + if (maxlvt >= 6) + apic_pm_state.apic_cmci = apic_read(APIC_LVTCMCI); +#endif local_irq_save(flags); disable_local_APIC(); @@ -2355,10 +2370,14 @@ static void lapic_resume(void) apic_write(APIC_SPIV, apic_pm_state.apic_spiv); apic_write(APIC_LVT0, apic_pm_state.apic_lvt0); apic_write(APIC_LVT1, apic_pm_state.apic_lvt1); -#if defined(CONFIG_X86_MCE_INTEL) +#ifdef CONFIG_X86_THERMAL_VECTOR if (maxlvt >= 5) apic_write(APIC_LVTTHMR, apic_pm_state.apic_thmr); #endif +#ifdef CONFIG_X86_MCE_INTEL + if (maxlvt >= 6) + apic_write(APIC_LVTCMCI, apic_pm_state.apic_cmci); +#endif if (maxlvt >= 4) apic_write(APIC_LVTPC, apic_pm_state.apic_lvtpc); apic_write(APIC_LVTT, apic_pm_state.apic_lvtt); @@ -2548,3 +2567,23 @@ static int __init apic_set_disabled_cpu_apicid(char *arg) return 0; } early_param("disable_cpu_apicid", apic_set_disabled_cpu_apicid); + +static int __init apic_set_extnmi(char *arg) +{ + if (!arg) + return -EINVAL; + + if (!strncmp("all", arg, 3)) + apic_extnmi = APIC_EXTNMI_ALL; + else if (!strncmp("none", arg, 4)) + apic_extnmi = APIC_EXTNMI_NONE; + else if (!strncmp("bsp", arg, 3)) + apic_extnmi = APIC_EXTNMI_BSP; + else { + pr_warn("Unknown external NMI delivery mode `%s' ignored\n", arg); + return -EINVAL; + } + + return 0; +} +early_param("apic_extnmi", apic_set_extnmi); diff --git a/arch/x86/kernel/apic/apic_flat_64.c b/arch/x86/kernel/apic/apic_flat_64.c index f92ab36979a2..9968f30cca3e 100644 --- a/arch/x86/kernel/apic/apic_flat_64.c +++ b/arch/x86/kernel/apic/apic_flat_64.c @@ -185,6 +185,7 @@ static struct apic apic_flat = { .cpu_mask_to_apicid_and = flat_cpu_mask_to_apicid_and, + .send_IPI = default_send_IPI_single, .send_IPI_mask = flat_send_IPI_mask, .send_IPI_mask_allbutself = flat_send_IPI_mask_allbutself, .send_IPI_allbutself = flat_send_IPI_allbutself, @@ -230,17 +231,6 @@ static int physflat_acpi_madt_oem_check(char *oem_id, char *oem_table_id) return 0; } -static void physflat_send_IPI_mask(const struct cpumask *cpumask, int vector) -{ - default_send_IPI_mask_sequence_phys(cpumask, vector); -} - -static void physflat_send_IPI_mask_allbutself(const struct cpumask *cpumask, - int vector) -{ - default_send_IPI_mask_allbutself_phys(cpumask, vector); -} - static void physflat_send_IPI_allbutself(int vector) { default_send_IPI_mask_allbutself_phys(cpu_online_mask, vector); @@ -248,7 +238,7 @@ static void physflat_send_IPI_allbutself(int vector) static void physflat_send_IPI_all(int vector) { - physflat_send_IPI_mask(cpu_online_mask, vector); + default_send_IPI_mask_sequence_phys(cpu_online_mask, vector); } static int physflat_probe(void) @@ -292,8 +282,9 @@ static struct apic apic_physflat = { .cpu_mask_to_apicid_and = default_cpu_mask_to_apicid_and, - .send_IPI_mask = physflat_send_IPI_mask, - .send_IPI_mask_allbutself = physflat_send_IPI_mask_allbutself, + .send_IPI = default_send_IPI_single_phys, + .send_IPI_mask = default_send_IPI_mask_sequence_phys, + .send_IPI_mask_allbutself = default_send_IPI_mask_allbutself_phys, .send_IPI_allbutself = physflat_send_IPI_allbutself, .send_IPI_all = physflat_send_IPI_all, .send_IPI_self = apic_send_IPI_self, diff --git a/arch/x86/kernel/apic/apic_noop.c b/arch/x86/kernel/apic/apic_noop.c index 0d96749cfcac..331a7a07c48f 100644 --- a/arch/x86/kernel/apic/apic_noop.c +++ b/arch/x86/kernel/apic/apic_noop.c @@ -30,6 +30,7 @@ #include <asm/e820.h> static void noop_init_apic_ldr(void) { } +static void noop_send_IPI(int cpu, int vector) { } static void noop_send_IPI_mask(const struct cpumask *cpumask, int vector) { } static void noop_send_IPI_mask_allbutself(const struct cpumask *cpumask, int vector) { } static void noop_send_IPI_allbutself(int vector) { } @@ -144,6 +145,7 @@ struct apic apic_noop = { .cpu_mask_to_apicid_and = flat_cpu_mask_to_apicid_and, + .send_IPI = noop_send_IPI, .send_IPI_mask = noop_send_IPI_mask, .send_IPI_mask_allbutself = noop_send_IPI_mask_allbutself, .send_IPI_allbutself = noop_send_IPI_allbutself, diff --git a/arch/x86/kernel/apic/apic_numachip.c b/arch/x86/kernel/apic/apic_numachip.c index 38dd5efdd04c..c80c02c6ec49 100644 --- a/arch/x86/kernel/apic/apic_numachip.c +++ b/arch/x86/kernel/apic/apic_numachip.c @@ -193,20 +193,17 @@ static int __init numachip_system_init(void) case 1: init_extra_mapping_uc(NUMACHIP_LCSR_BASE, NUMACHIP_LCSR_SIZE); numachip_apic_icr_write = numachip1_apic_icr_write; - x86_init.pci.arch_init = pci_numachip_init; break; case 2: init_extra_mapping_uc(NUMACHIP2_LCSR_BASE, NUMACHIP2_LCSR_SIZE); numachip_apic_icr_write = numachip2_apic_icr_write; - - /* Use MCFG config cycles rather than locked CF8 cycles */ - raw_pci_ops = &pci_mmcfg; break; default: return 0; } x86_cpuinit.fixup_cpu_id = fixup_cpu_id; + x86_init.pci.arch_init = pci_numachip_init; return 0; } @@ -276,6 +273,7 @@ static const struct apic apic_numachip1 __refconst = { .cpu_mask_to_apicid_and = default_cpu_mask_to_apicid_and, + .send_IPI = numachip_send_IPI_one, .send_IPI_mask = numachip_send_IPI_mask, .send_IPI_mask_allbutself = numachip_send_IPI_mask_allbutself, .send_IPI_allbutself = numachip_send_IPI_allbutself, @@ -327,6 +325,7 @@ static const struct apic apic_numachip2 __refconst = { .cpu_mask_to_apicid_and = default_cpu_mask_to_apicid_and, + .send_IPI = numachip_send_IPI_one, .send_IPI_mask = numachip_send_IPI_mask, .send_IPI_mask_allbutself = numachip_send_IPI_mask_allbutself, .send_IPI_allbutself = numachip_send_IPI_allbutself, diff --git a/arch/x86/kernel/apic/bigsmp_32.c b/arch/x86/kernel/apic/bigsmp_32.c index 971cf8875939..cf9bd896c12d 100644 --- a/arch/x86/kernel/apic/bigsmp_32.c +++ b/arch/x86/kernel/apic/bigsmp_32.c @@ -96,11 +96,6 @@ static int bigsmp_phys_pkg_id(int cpuid_apic, int index_msb) return cpuid_apic >> index_msb; } -static inline void bigsmp_send_IPI_mask(const struct cpumask *mask, int vector) -{ - default_send_IPI_mask_sequence_phys(mask, vector); -} - static void bigsmp_send_IPI_allbutself(int vector) { default_send_IPI_mask_allbutself_phys(cpu_online_mask, vector); @@ -108,7 +103,7 @@ static void bigsmp_send_IPI_allbutself(int vector) static void bigsmp_send_IPI_all(int vector) { - bigsmp_send_IPI_mask(cpu_online_mask, vector); + default_send_IPI_mask_sequence_phys(cpu_online_mask, vector); } static int dmi_bigsmp; /* can be set by dmi scanners */ @@ -180,7 +175,8 @@ static struct apic apic_bigsmp = { .cpu_mask_to_apicid_and = default_cpu_mask_to_apicid_and, - .send_IPI_mask = bigsmp_send_IPI_mask, + .send_IPI = default_send_IPI_single_phys, + .send_IPI_mask = default_send_IPI_mask_sequence_phys, .send_IPI_mask_allbutself = NULL, .send_IPI_allbutself = bigsmp_send_IPI_allbutself, .send_IPI_all = bigsmp_send_IPI_all, diff --git a/arch/x86/kernel/apic/ipi.c b/arch/x86/kernel/apic/ipi.c index 62071569bd50..eb45fc9b6124 100644 --- a/arch/x86/kernel/apic/ipi.c +++ b/arch/x86/kernel/apic/ipi.c @@ -18,6 +18,16 @@ #include <asm/proto.h> #include <asm/ipi.h> +void default_send_IPI_single_phys(int cpu, int vector) +{ + unsigned long flags; + + local_irq_save(flags); + __default_send_IPI_dest_field(per_cpu(x86_cpu_to_apicid, cpu), + vector, APIC_DEST_PHYSICAL); + local_irq_restore(flags); +} + void default_send_IPI_mask_sequence_phys(const struct cpumask *mask, int vector) { unsigned long query_cpu; @@ -55,6 +65,14 @@ void default_send_IPI_mask_allbutself_phys(const struct cpumask *mask, local_irq_restore(flags); } +/* + * Helper function for APICs which insist on cpumasks + */ +void default_send_IPI_single(int cpu, int vector) +{ + apic->send_IPI_mask(cpumask_of(cpu), vector); +} + #ifdef CONFIG_X86_32 void default_send_IPI_mask_sequence_logical(const struct cpumask *mask, diff --git a/arch/x86/kernel/apic/msi.c b/arch/x86/kernel/apic/msi.c index 5f1feb6854af..ade25320df96 100644 --- a/arch/x86/kernel/apic/msi.c +++ b/arch/x86/kernel/apic/msi.c @@ -96,8 +96,8 @@ static irq_hw_number_t pci_msi_get_hwirq(struct msi_domain_info *info, return arg->msi_hwirq; } -static int pci_msi_prepare(struct irq_domain *domain, struct device *dev, - int nvec, msi_alloc_info_t *arg) +int pci_msi_prepare(struct irq_domain *domain, struct device *dev, int nvec, + msi_alloc_info_t *arg) { struct pci_dev *pdev = to_pci_dev(dev); struct msi_desc *desc = first_pci_msi_entry(pdev); @@ -113,11 +113,13 @@ static int pci_msi_prepare(struct irq_domain *domain, struct device *dev, return 0; } +EXPORT_SYMBOL_GPL(pci_msi_prepare); -static void pci_msi_set_desc(msi_alloc_info_t *arg, struct msi_desc *desc) +void pci_msi_set_desc(msi_alloc_info_t *arg, struct msi_desc *desc) { arg->msi_hwirq = pci_msi_domain_calc_hwirq(arg->msi_dev, desc); } +EXPORT_SYMBOL_GPL(pci_msi_set_desc); static struct msi_domain_ops pci_msi_domain_ops = { .get_hwirq = pci_msi_get_hwirq, diff --git a/arch/x86/kernel/apic/probe_32.c b/arch/x86/kernel/apic/probe_32.c index 7694ae6c1199..f316e34abb42 100644 --- a/arch/x86/kernel/apic/probe_32.c +++ b/arch/x86/kernel/apic/probe_32.c @@ -105,6 +105,7 @@ static struct apic apic_default = { .cpu_mask_to_apicid_and = flat_cpu_mask_to_apicid_and, + .send_IPI = default_send_IPI_single, .send_IPI_mask = default_send_IPI_mask_logical, .send_IPI_mask_allbutself = default_send_IPI_mask_allbutself_logical, .send_IPI_allbutself = default_send_IPI_allbutself, diff --git a/arch/x86/kernel/apic/vector.c b/arch/x86/kernel/apic/vector.c index 861bc59c8f25..908cb37da171 100644 --- a/arch/x86/kernel/apic/vector.c +++ b/arch/x86/kernel/apic/vector.c @@ -29,6 +29,7 @@ struct apic_chip_data { }; struct irq_domain *x86_vector_domain; +EXPORT_SYMBOL_GPL(x86_vector_domain); static DEFINE_RAW_SPINLOCK(vector_lock); static cpumask_var_t vector_cpumask; static struct irq_chip lapic_controller; @@ -66,6 +67,7 @@ struct irq_cfg *irqd_cfg(struct irq_data *irq_data) return data ? &data->cfg : NULL; } +EXPORT_SYMBOL_GPL(irqd_cfg); struct irq_cfg *irq_cfg(unsigned int irq) { diff --git a/arch/x86/kernel/apic/x2apic_cluster.c b/arch/x86/kernel/apic/x2apic_cluster.c index cc8311c4d298..aca8b75c1552 100644 --- a/arch/x86/kernel/apic/x2apic_cluster.c +++ b/arch/x86/kernel/apic/x2apic_cluster.c @@ -23,6 +23,14 @@ static inline u32 x2apic_cluster(int cpu) return per_cpu(x86_cpu_to_logical_apicid, cpu) >> 16; } +static void x2apic_send_IPI(int cpu, int vector) +{ + u32 dest = per_cpu(x86_cpu_to_logical_apicid, cpu); + + x2apic_wrmsr_fence(); + __x2apic_send_IPI_dest(dest, vector, APIC_DEST_LOGICAL); +} + static void __x2apic_send_IPI_mask(const struct cpumask *mask, int vector, int apic_dest) { @@ -266,6 +274,7 @@ static struct apic apic_x2apic_cluster = { .cpu_mask_to_apicid_and = x2apic_cpu_mask_to_apicid_and, + .send_IPI = x2apic_send_IPI, .send_IPI_mask = x2apic_send_IPI_mask, .send_IPI_mask_allbutself = x2apic_send_IPI_mask_allbutself, .send_IPI_allbutself = x2apic_send_IPI_allbutself, diff --git a/arch/x86/kernel/apic/x2apic_phys.c b/arch/x86/kernel/apic/x2apic_phys.c index 662e9150ea6f..a1242e2c12e6 100644 --- a/arch/x86/kernel/apic/x2apic_phys.c +++ b/arch/x86/kernel/apic/x2apic_phys.c @@ -36,6 +36,14 @@ static int x2apic_acpi_madt_oem_check(char *oem_id, char *oem_table_id) return x2apic_enabled() && (x2apic_phys || x2apic_fadt_phys()); } +static void x2apic_send_IPI(int cpu, int vector) +{ + u32 dest = per_cpu(x86_cpu_to_apicid, cpu); + + x2apic_wrmsr_fence(); + __x2apic_send_IPI_dest(dest, vector, APIC_DEST_PHYSICAL); +} + static void __x2apic_send_IPI_mask(const struct cpumask *mask, int vector, int apic_dest) { @@ -122,6 +130,7 @@ static struct apic apic_x2apic_phys = { .cpu_mask_to_apicid_and = default_cpu_mask_to_apicid_and, + .send_IPI = x2apic_send_IPI, .send_IPI_mask = x2apic_send_IPI_mask, .send_IPI_mask_allbutself = x2apic_send_IPI_mask_allbutself, .send_IPI_allbutself = x2apic_send_IPI_allbutself, diff --git a/arch/x86/kernel/apic/x2apic_uv_x.c b/arch/x86/kernel/apic/x2apic_uv_x.c index 4a139465f1d4..d760c6bb37b5 100644 --- a/arch/x86/kernel/apic/x2apic_uv_x.c +++ b/arch/x86/kernel/apic/x2apic_uv_x.c @@ -406,6 +406,7 @@ static struct apic __refdata apic_x2apic_uv_x = { .cpu_mask_to_apicid_and = uv_cpu_mask_to_apicid_and, + .send_IPI = uv_send_IPI_one, .send_IPI_mask = uv_send_IPI_mask, .send_IPI_mask_allbutself = uv_send_IPI_mask_allbutself, .send_IPI_allbutself = uv_send_IPI_allbutself, diff --git a/arch/x86/kernel/asm-offsets.c b/arch/x86/kernel/asm-offsets.c index 439df975bc7a..84a7524b202c 100644 --- a/arch/x86/kernel/asm-offsets.c +++ b/arch/x86/kernel/asm-offsets.c @@ -65,9 +65,6 @@ void common(void) { OFFSET(PV_IRQ_irq_disable, pv_irq_ops, irq_disable); OFFSET(PV_IRQ_irq_enable, pv_irq_ops, irq_enable); OFFSET(PV_CPU_iret, pv_cpu_ops, iret); -#ifdef CONFIG_X86_32 - OFFSET(PV_CPU_irq_enable_sysexit, pv_cpu_ops, irq_enable_sysexit); -#endif OFFSET(PV_CPU_read_cr0, pv_cpu_ops, read_cr0); OFFSET(PV_MMU_read_cr2, pv_mmu_ops, read_cr2); #endif diff --git a/arch/x86/kernel/asm-offsets_64.c b/arch/x86/kernel/asm-offsets_64.c index d8f42f902a0f..f2edafb5f24e 100644 --- a/arch/x86/kernel/asm-offsets_64.c +++ b/arch/x86/kernel/asm-offsets_64.c @@ -23,7 +23,6 @@ int main(void) { #ifdef CONFIG_PARAVIRT OFFSET(PV_IRQ_adjust_exception_frame, pv_irq_ops, adjust_exception_frame); - OFFSET(PV_CPU_usergs_sysret32, pv_cpu_ops, usergs_sysret32); OFFSET(PV_CPU_usergs_sysret64, pv_cpu_ops, usergs_sysret64); OFFSET(PV_CPU_swapgs, pv_cpu_ops, swapgs); BLANK(); diff --git a/arch/x86/kernel/cpu/amd.c b/arch/x86/kernel/cpu/amd.c index a8816b325162..e678ddeed030 100644 --- a/arch/x86/kernel/cpu/amd.c +++ b/arch/x86/kernel/cpu/amd.c @@ -304,7 +304,7 @@ static void amd_get_topology(struct cpuinfo_x86 *c) int cpu = smp_processor_id(); /* get information required for multi-node processors */ - if (cpu_has_topoext) { + if (boot_cpu_has(X86_FEATURE_TOPOEXT)) { u32 eax, ebx, ecx, edx; cpuid(0x8000001e, &eax, &ebx, &ecx, &edx); @@ -678,9 +678,9 @@ static void init_amd_bd(struct cpuinfo_x86 *c) * Disable it on the affected CPUs. */ if ((c->x86_model >= 0x02) && (c->x86_model < 0x20)) { - if (!rdmsrl_safe(0xc0011021, &value) && !(value & 0x1E)) { + if (!rdmsrl_safe(MSR_F15H_IC_CFG, &value) && !(value & 0x1E)) { value |= 0x1E; - wrmsrl_safe(0xc0011021, value); + wrmsrl_safe(MSR_F15H_IC_CFG, value); } } } @@ -922,7 +922,7 @@ static bool cpu_has_amd_erratum(struct cpuinfo_x86 *cpu, const int *erratum) void set_dr_addr_mask(unsigned long mask, int dr) { - if (!cpu_has_bpext) + if (!boot_cpu_has(X86_FEATURE_BPEXT)) return; switch (dr) { diff --git a/arch/x86/kernel/cpu/centaur.c b/arch/x86/kernel/cpu/centaur.c index d8fba5c15fbd..ae20be6e483c 100644 --- a/arch/x86/kernel/cpu/centaur.c +++ b/arch/x86/kernel/cpu/centaur.c @@ -43,7 +43,7 @@ static void init_c3(struct cpuinfo_x86 *c) /* store Centaur Extended Feature Flags as * word 5 of the CPU capability bit array */ - c->x86_capability[5] = cpuid_edx(0xC0000001); + c->x86_capability[CPUID_C000_0001_EDX] = cpuid_edx(0xC0000001); } #ifdef CONFIG_X86_32 /* Cyrix III family needs CX8 & PGE explicitly enabled. */ diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c index 4ddd780aeac9..37830de8f60a 100644 --- a/arch/x86/kernel/cpu/common.c +++ b/arch/x86/kernel/cpu/common.c @@ -273,10 +273,9 @@ __setup("nosmap", setup_disable_smap); static __always_inline void setup_smap(struct cpuinfo_x86 *c) { - unsigned long eflags; + unsigned long eflags = native_save_fl(); /* This should have been cleared long ago */ - raw_local_save_flags(eflags); BUG_ON(eflags & X86_EFLAGS_AC); if (cpu_has(c, X86_FEATURE_SMAP)) { @@ -582,14 +581,9 @@ void cpu_detect(struct cpuinfo_x86 *c) u32 junk, tfms, cap0, misc; cpuid(0x00000001, &tfms, &misc, &junk, &cap0); - c->x86 = (tfms >> 8) & 0xf; - c->x86_model = (tfms >> 4) & 0xf; - c->x86_mask = tfms & 0xf; - - if (c->x86 == 0xf) - c->x86 += (tfms >> 20) & 0xff; - if (c->x86 >= 0x6) - c->x86_model += ((tfms >> 16) & 0xf) << 4; + c->x86 = x86_family(tfms); + c->x86_model = x86_model(tfms); + c->x86_mask = x86_stepping(tfms); if (cap0 & (1<<19)) { c->x86_clflush_size = ((misc >> 8) & 0xff) * 8; @@ -600,50 +594,47 @@ void cpu_detect(struct cpuinfo_x86 *c) void get_cpu_cap(struct cpuinfo_x86 *c) { - u32 tfms, xlvl; - u32 ebx; + u32 eax, ebx, ecx, edx; /* Intel-defined flags: level 0x00000001 */ if (c->cpuid_level >= 0x00000001) { - u32 capability, excap; + cpuid(0x00000001, &eax, &ebx, &ecx, &edx); - cpuid(0x00000001, &tfms, &ebx, &excap, &capability); - c->x86_capability[0] = capability; - c->x86_capability[4] = excap; + c->x86_capability[CPUID_1_ECX] = ecx; + c->x86_capability[CPUID_1_EDX] = edx; } /* Additional Intel-defined flags: level 0x00000007 */ if (c->cpuid_level >= 0x00000007) { - u32 eax, ebx, ecx, edx; - cpuid_count(0x00000007, 0, &eax, &ebx, &ecx, &edx); - c->x86_capability[9] = ebx; + c->x86_capability[CPUID_7_0_EBX] = ebx; + + c->x86_capability[CPUID_6_EAX] = cpuid_eax(0x00000006); } /* Extended state features: level 0x0000000d */ if (c->cpuid_level >= 0x0000000d) { - u32 eax, ebx, ecx, edx; - cpuid_count(0x0000000d, 1, &eax, &ebx, &ecx, &edx); - c->x86_capability[10] = eax; + c->x86_capability[CPUID_D_1_EAX] = eax; } /* Additional Intel-defined flags: level 0x0000000F */ if (c->cpuid_level >= 0x0000000F) { - u32 eax, ebx, ecx, edx; /* QoS sub-leaf, EAX=0Fh, ECX=0 */ cpuid_count(0x0000000F, 0, &eax, &ebx, &ecx, &edx); - c->x86_capability[11] = edx; + c->x86_capability[CPUID_F_0_EDX] = edx; + if (cpu_has(c, X86_FEATURE_CQM_LLC)) { /* will be overridden if occupancy monitoring exists */ c->x86_cache_max_rmid = ebx; /* QoS sub-leaf, EAX=0Fh, ECX=1 */ cpuid_count(0x0000000F, 1, &eax, &ebx, &ecx, &edx); - c->x86_capability[12] = edx; + c->x86_capability[CPUID_F_1_EDX] = edx; + if (cpu_has(c, X86_FEATURE_CQM_OCCUP_LLC)) { c->x86_cache_max_rmid = ecx; c->x86_cache_occ_scale = ebx; @@ -655,22 +646,24 @@ void get_cpu_cap(struct cpuinfo_x86 *c) } /* AMD-defined flags: level 0x80000001 */ - xlvl = cpuid_eax(0x80000000); - c->extended_cpuid_level = xlvl; + eax = cpuid_eax(0x80000000); + c->extended_cpuid_level = eax; - if ((xlvl & 0xffff0000) == 0x80000000) { - if (xlvl >= 0x80000001) { - c->x86_capability[1] = cpuid_edx(0x80000001); - c->x86_capability[6] = cpuid_ecx(0x80000001); + if ((eax & 0xffff0000) == 0x80000000) { + if (eax >= 0x80000001) { + cpuid(0x80000001, &eax, &ebx, &ecx, &edx); + + c->x86_capability[CPUID_8000_0001_ECX] = ecx; + c->x86_capability[CPUID_8000_0001_EDX] = edx; } } if (c->extended_cpuid_level >= 0x80000008) { - u32 eax = cpuid_eax(0x80000008); + cpuid(0x80000008, &eax, &ebx, &ecx, &edx); c->x86_virt_bits = (eax >> 8) & 0xff; c->x86_phys_bits = eax & 0xff; - c->x86_capability[13] = cpuid_ebx(0x80000008); + c->x86_capability[CPUID_8000_0008_EBX] = ebx; } #ifdef CONFIG_X86_32 else if (cpu_has(c, X86_FEATURE_PAE) || cpu_has(c, X86_FEATURE_PSE36)) @@ -680,6 +673,9 @@ void get_cpu_cap(struct cpuinfo_x86 *c) if (c->extended_cpuid_level >= 0x80000007) c->x86_power = cpuid_edx(0x80000007); + if (c->extended_cpuid_level >= 0x8000000a) + c->x86_capability[CPUID_8000_000A_EDX] = cpuid_edx(0x8000000a); + init_scattered_cpuid_features(c); } @@ -1186,7 +1182,7 @@ void syscall_init(void) * They both write to the same internal register. STAR allows to * set CS/DS but only a 32bit target. LSTAR sets the 64bit rip. */ - wrmsrl(MSR_STAR, ((u64)__USER32_CS)<<48 | ((u64)__KERNEL_CS)<<32); + wrmsr(MSR_STAR, 0, (__USER32_CS << 16) | __KERNEL_CS); wrmsrl(MSR_LSTAR, (unsigned long)entry_SYSCALL_64); #ifdef CONFIG_IA32_EMULATION @@ -1444,7 +1440,9 @@ void cpu_init(void) printk(KERN_INFO "Initializing CPU#%d\n", cpu); - if (cpu_feature_enabled(X86_FEATURE_VME) || cpu_has_tsc || cpu_has_de) + if (cpu_feature_enabled(X86_FEATURE_VME) || + cpu_has_tsc || + boot_cpu_has(X86_FEATURE_DE)) cr4_clear_bits(X86_CR4_VME|X86_CR4_PVI|X86_CR4_TSD|X86_CR4_DE); load_current_idt(); diff --git a/arch/x86/kernel/cpu/intel.c b/arch/x86/kernel/cpu/intel.c index 209ac1e7d1f0..565648bc1a0a 100644 --- a/arch/x86/kernel/cpu/intel.c +++ b/arch/x86/kernel/cpu/intel.c @@ -445,7 +445,8 @@ static void init_intel(struct cpuinfo_x86 *c) if (cpu_has_xmm2) set_cpu_cap(c, X86_FEATURE_LFENCE_RDTSC); - if (cpu_has_ds) { + + if (boot_cpu_has(X86_FEATURE_DS)) { unsigned int l1; rdmsr(MSR_IA32_MISC_ENABLE, l1, l2); if (!(l1 & (1<<11))) diff --git a/arch/x86/kernel/cpu/intel_cacheinfo.c b/arch/x86/kernel/cpu/intel_cacheinfo.c index e38d338a6447..0b6c52388cf4 100644 --- a/arch/x86/kernel/cpu/intel_cacheinfo.c +++ b/arch/x86/kernel/cpu/intel_cacheinfo.c @@ -591,7 +591,7 @@ cpuid4_cache_lookup_regs(int index, struct _cpuid4_info_regs *this_leaf) unsigned edx; if (boot_cpu_data.x86_vendor == X86_VENDOR_AMD) { - if (cpu_has_topoext) + if (boot_cpu_has(X86_FEATURE_TOPOEXT)) cpuid_count(0x8000001d, index, &eax.full, &ebx.full, &ecx.full, &edx); else @@ -637,7 +637,7 @@ static int find_num_cache_leaves(struct cpuinfo_x86 *c) void init_amd_cacheinfo(struct cpuinfo_x86 *c) { - if (cpu_has_topoext) { + if (boot_cpu_has(X86_FEATURE_TOPOEXT)) { num_cache_leaves = find_num_cache_leaves(c); } else if (c->extended_cpuid_level >= 0x80000006) { if (cpuid_edx(0x80000006) & 0xf000) @@ -809,7 +809,7 @@ static int __cache_amd_cpumap_setup(unsigned int cpu, int index, struct cacheinfo *this_leaf; int i, sibling; - if (cpu_has_topoext) { + if (boot_cpu_has(X86_FEATURE_TOPOEXT)) { unsigned int apicid, nshared, first, last; this_leaf = this_cpu_ci->info_list + index; diff --git a/arch/x86/kernel/cpu/mcheck/mce.c b/arch/x86/kernel/cpu/mcheck/mce.c index c5b0d562dbf5..a006f4cd792b 100644 --- a/arch/x86/kernel/cpu/mcheck/mce.c +++ b/arch/x86/kernel/cpu/mcheck/mce.c @@ -114,7 +114,6 @@ static struct work_struct mce_work; static struct irq_work mce_irq_work; static void (*quirk_no_way_out)(int bank, struct mce *m, struct pt_regs *regs); -static int mce_usable_address(struct mce *m); /* * CPU/chipset specific EDAC code can register a notifier call here to print @@ -475,6 +474,28 @@ static void mce_report_event(struct pt_regs *regs) irq_work_queue(&mce_irq_work); } +/* + * Check if the address reported by the CPU is in a format we can parse. + * It would be possible to add code for most other cases, but all would + * be somewhat complicated (e.g. segment offset would require an instruction + * parser). So only support physical addresses up to page granuality for now. + */ +static int mce_usable_address(struct mce *m) +{ + if (!(m->status & MCI_STATUS_MISCV) || !(m->status & MCI_STATUS_ADDRV)) + return 0; + + /* Checks after this one are Intel-specific: */ + if (boot_cpu_data.x86_vendor != X86_VENDOR_INTEL) + return 1; + + if (MCI_MISC_ADDR_LSB(m->misc) > PAGE_SHIFT) + return 0; + if (MCI_MISC_ADDR_MODE(m->misc) != MCI_MISC_ADDR_PHYS) + return 0; + return 1; +} + static int srao_decode_notifier(struct notifier_block *nb, unsigned long val, void *data) { @@ -484,7 +505,7 @@ static int srao_decode_notifier(struct notifier_block *nb, unsigned long val, if (!mce) return NOTIFY_DONE; - if (mce->usable_addr && (mce->severity == MCE_AO_SEVERITY)) { + if (mce_usable_address(mce) && (mce->severity == MCE_AO_SEVERITY)) { pfn = mce->addr >> PAGE_SHIFT; memory_failure(pfn, MCE_VECTOR, 0); } @@ -522,10 +543,10 @@ static bool memory_error(struct mce *m) struct cpuinfo_x86 *c = &boot_cpu_data; if (c->x86_vendor == X86_VENDOR_AMD) { - /* - * coming soon - */ - return false; + /* ErrCodeExt[20:16] */ + u8 xec = (m->status >> 16) & 0x1f; + + return (xec == 0x0 || xec == 0x8); } else if (c->x86_vendor == X86_VENDOR_INTEL) { /* * Intel SDM Volume 3B - 15.9.2 Compound Error Codes @@ -567,7 +588,7 @@ DEFINE_PER_CPU(unsigned, mce_poll_count); */ bool machine_check_poll(enum mcp_flags flags, mce_banks_t *b) { - bool error_logged = false; + bool error_seen = false; struct mce m; int severity; int i; @@ -601,6 +622,8 @@ bool machine_check_poll(enum mcp_flags flags, mce_banks_t *b) (m.status & (mca_cfg.ser ? MCI_STATUS_S : MCI_STATUS_UC))) continue; + error_seen = true; + mce_read_aux(&m, i); if (!(flags & MCP_TIMESTAMP)) @@ -608,27 +631,24 @@ bool machine_check_poll(enum mcp_flags flags, mce_banks_t *b) severity = mce_severity(&m, mca_cfg.tolerant, NULL, false); - /* - * In the cases where we don't have a valid address after all, - * do not add it into the ring buffer. - */ - if (severity == MCE_DEFERRED_SEVERITY && memory_error(&m)) { - if (m.status & MCI_STATUS_ADDRV) { + if (severity == MCE_DEFERRED_SEVERITY && memory_error(&m)) + if (m.status & MCI_STATUS_ADDRV) m.severity = severity; - m.usable_addr = mce_usable_address(&m); - - if (!mce_gen_pool_add(&m)) - mce_schedule_work(); - } - } /* * Don't get the IP here because it's unlikely to * have anything to do with the actual error location. */ - if (!(flags & MCP_DONTLOG) && !mca_cfg.dont_log_ce) { - error_logged = true; + if (!(flags & MCP_DONTLOG) && !mca_cfg.dont_log_ce) mce_log(&m); + else if (mce_usable_address(&m)) { + /* + * Although we skipped logging this, we still want + * to take action. Add to the pool so the registered + * notifiers will see it. + */ + if (!mce_gen_pool_add(&m)) + mce_schedule_work(); } /* @@ -644,7 +664,7 @@ bool machine_check_poll(enum mcp_flags flags, mce_banks_t *b) sync_core(); - return error_logged; + return error_seen; } EXPORT_SYMBOL_GPL(machine_check_poll); @@ -931,23 +951,6 @@ reset: return ret; } -/* - * Check if the address reported by the CPU is in a format we can parse. - * It would be possible to add code for most other cases, but all would - * be somewhat complicated (e.g. segment offset would require an instruction - * parser). So only support physical addresses up to page granuality for now. - */ -static int mce_usable_address(struct mce *m) -{ - if (!(m->status & MCI_STATUS_MISCV) || !(m->status & MCI_STATUS_ADDRV)) - return 0; - if (MCI_MISC_ADDR_LSB(m->misc) > PAGE_SHIFT) - return 0; - if (MCI_MISC_ADDR_MODE(m->misc) != MCI_MISC_ADDR_PHYS) - return 0; - return 1; -} - static void mce_clear_state(unsigned long *toclear) { int i; @@ -999,6 +1002,17 @@ void do_machine_check(struct pt_regs *regs, long error_code) int flags = MF_ACTION_REQUIRED; int lmce = 0; + /* If this CPU is offline, just bail out. */ + if (cpu_is_offline(smp_processor_id())) { + u64 mcgstatus; + + mcgstatus = mce_rdmsrl(MSR_IA32_MCG_STATUS); + if (mcgstatus & MCG_STATUS_RIPV) { + mce_wrmsrl(MSR_IA32_MCG_STATUS, 0); + return; + } + } + ist_enter(regs); this_cpu_inc(mce_exception_count); @@ -1089,7 +1103,6 @@ void do_machine_check(struct pt_regs *regs, long error_code) /* assuming valid severity level != 0 */ m.severity = severity; - m.usable_addr = mce_usable_address(&m); mce_log(&m); diff --git a/arch/x86/kernel/cpu/microcode/core.c b/arch/x86/kernel/cpu/microcode/core.c index 7fc27f1cca58..faec7120c508 100644 --- a/arch/x86/kernel/cpu/microcode/core.c +++ b/arch/x86/kernel/cpu/microcode/core.c @@ -129,8 +129,8 @@ void __init load_ucode_bsp(void) if (!have_cpuid_p()) return; - vendor = x86_vendor(); - family = x86_family(); + vendor = x86_cpuid_vendor(); + family = x86_cpuid_family(); switch (vendor) { case X86_VENDOR_INTEL: @@ -165,8 +165,8 @@ void load_ucode_ap(void) if (!have_cpuid_p()) return; - vendor = x86_vendor(); - family = x86_family(); + vendor = x86_cpuid_vendor(); + family = x86_cpuid_family(); switch (vendor) { case X86_VENDOR_INTEL: @@ -206,8 +206,8 @@ void reload_early_microcode(void) { int vendor, family; - vendor = x86_vendor(); - family = x86_family(); + vendor = x86_cpuid_vendor(); + family = x86_cpuid_family(); switch (vendor) { case X86_VENDOR_INTEL: @@ -698,3 +698,4 @@ int __init microcode_init(void) return error; } +late_initcall(microcode_init); diff --git a/arch/x86/kernel/cpu/microcode/intel.c b/arch/x86/kernel/cpu/microcode/intel.c index ce47402eb2f9..ee81c544ee0d 100644 --- a/arch/x86/kernel/cpu/microcode/intel.c +++ b/arch/x86/kernel/cpu/microcode/intel.c @@ -145,10 +145,10 @@ matching_model_microcode(struct microcode_header_intel *mc_header, int ext_sigcount, i; struct extended_signature *ext_sig; - fam = __x86_family(sig); + fam = x86_family(sig); model = x86_model(sig); - fam_ucode = __x86_family(mc_header->sig); + fam_ucode = x86_family(mc_header->sig); model_ucode = x86_model(mc_header->sig); if (fam == fam_ucode && model == model_ucode) @@ -163,7 +163,7 @@ matching_model_microcode(struct microcode_header_intel *mc_header, ext_sigcount = ext_header->count; for (i = 0; i < ext_sigcount; i++) { - fam_ucode = __x86_family(ext_sig->sig); + fam_ucode = x86_family(ext_sig->sig); model_ucode = x86_model(ext_sig->sig); if (fam == fam_ucode && model == model_ucode) @@ -365,7 +365,7 @@ static int collect_cpu_info_early(struct ucode_cpu_info *uci) native_cpuid(&eax, &ebx, &ecx, &edx); csig.sig = eax; - family = __x86_family(csig.sig); + family = x86_family(csig.sig); model = x86_model(csig.sig); if ((model >= 5) || (family > 6)) { @@ -521,16 +521,12 @@ static bool __init load_builtin_intel_microcode(struct cpio_data *cp) { #ifdef CONFIG_X86_64 unsigned int eax = 0x00000001, ebx, ecx = 0, edx; - unsigned int family, model, stepping; char name[30]; native_cpuid(&eax, &ebx, &ecx, &edx); - family = __x86_family(eax); - model = x86_model(eax); - stepping = eax & 0xf; - - sprintf(name, "intel-ucode/%02x-%02x-%02x", family, model, stepping); + sprintf(name, "intel-ucode/%02x-%02x-%02x", + x86_family(eax), x86_model(eax), x86_stepping(eax)); return get_builtin_firmware(cp, name); #else diff --git a/arch/x86/kernel/cpu/mtrr/cleanup.c b/arch/x86/kernel/cpu/mtrr/cleanup.c index 70d7c93f4550..0d98503c2245 100644 --- a/arch/x86/kernel/cpu/mtrr/cleanup.c +++ b/arch/x86/kernel/cpu/mtrr/cleanup.c @@ -593,9 +593,16 @@ mtrr_calc_range_state(u64 chunk_size, u64 gran_size, unsigned long x_remove_base, unsigned long x_remove_size, int i) { - static struct range range_new[RANGE_NUM]; + /* + * range_new should really be an automatic variable, but + * putting 4096 bytes on the stack is frowned upon, to put it + * mildly. It is safe to make it a static __initdata variable, + * since mtrr_calc_range_state is only called during init and + * there's no way it will call itself recursively. + */ + static struct range range_new[RANGE_NUM] __initdata; unsigned long range_sums_new; - static int nr_range_new; + int nr_range_new; int num_reg; /* Convert ranges to var ranges state: */ diff --git a/arch/x86/kernel/cpu/mtrr/generic.c b/arch/x86/kernel/cpu/mtrr/generic.c index 3b533cf37c74..c870af161008 100644 --- a/arch/x86/kernel/cpu/mtrr/generic.c +++ b/arch/x86/kernel/cpu/mtrr/generic.c @@ -349,7 +349,7 @@ static void get_fixed_ranges(mtrr_type *frs) void mtrr_save_fixed_ranges(void *info) { - if (cpu_has_mtrr) + if (boot_cpu_has(X86_FEATURE_MTRR)) get_fixed_ranges(mtrr_state.fixed_ranges); } diff --git a/arch/x86/kernel/cpu/mtrr/main.c b/arch/x86/kernel/cpu/mtrr/main.c index f891b4750f04..5c3d149ee91c 100644 --- a/arch/x86/kernel/cpu/mtrr/main.c +++ b/arch/x86/kernel/cpu/mtrr/main.c @@ -682,7 +682,7 @@ void __init mtrr_bp_init(void) phys_addr = 32; - if (cpu_has_mtrr) { + if (boot_cpu_has(X86_FEATURE_MTRR)) { mtrr_if = &generic_mtrr_ops; size_or_mask = SIZE_OR_MASK_BITS(36); size_and_mask = 0x00f00000; diff --git a/arch/x86/kernel/cpu/perf_event.c b/arch/x86/kernel/cpu/perf_event.c index 4562cf070c27..1b443db2db50 100644 --- a/arch/x86/kernel/cpu/perf_event.c +++ b/arch/x86/kernel/cpu/perf_event.c @@ -5,7 +5,7 @@ * Copyright (C) 2008-2009 Red Hat, Inc., Ingo Molnar * Copyright (C) 2009 Jaswinder Singh Rajput * Copyright (C) 2009 Advanced Micro Devices, Inc., Robert Richter - * Copyright (C) 2008-2009 Red Hat, Inc., Peter Zijlstra <pzijlstr@redhat.com> + * Copyright (C) 2008-2009 Red Hat, Inc., Peter Zijlstra * Copyright (C) 2009 Intel Corporation, <markus.t.metzger@intel.com> * Copyright (C) 2009 Google, Inc., Stephane Eranian * @@ -482,6 +482,9 @@ int x86_pmu_hw_config(struct perf_event *event) /* Support for IP fixup */ if (x86_pmu.lbr_nr || x86_pmu.intel_cap.pebs_format >= 2) precise++; + + if (x86_pmu.pebs_prec_dist) + precise++; } if (event->attr.precise_ip > precise) @@ -1531,6 +1534,7 @@ static void __init filter_events(struct attribute **attrs) { struct device_attribute *d; struct perf_pmu_events_attr *pmu_attr; + int offset = 0; int i, j; for (i = 0; attrs[i]; i++) { @@ -1539,7 +1543,7 @@ static void __init filter_events(struct attribute **attrs) /* str trumps id */ if (pmu_attr->event_str) continue; - if (x86_pmu.event_map(i)) + if (x86_pmu.event_map(i + offset)) continue; for (j = i; attrs[j]; j++) @@ -1547,6 +1551,14 @@ static void __init filter_events(struct attribute **attrs) /* Check the shifted attr. */ i--; + + /* + * event_map() is index based, the attrs array is organized + * by increasing event index. If we shift the events, then + * we need to compensate for the event_map(), otherwise + * we are looking up the wrong event in the map + */ + offset++; } } @@ -2250,12 +2262,19 @@ perf_callchain_user32(struct pt_regs *regs, struct perf_callchain_entry *entry) ss_base = get_segment_base(regs->ss); fp = compat_ptr(ss_base + regs->bp); + pagefault_disable(); while (entry->nr < PERF_MAX_STACK_DEPTH) { unsigned long bytes; frame.next_frame = 0; frame.return_address = 0; - bytes = copy_from_user_nmi(&frame, fp, sizeof(frame)); + if (!access_ok(VERIFY_READ, fp, 8)) + break; + + bytes = __copy_from_user_nmi(&frame.next_frame, fp, 4); + if (bytes != 0) + break; + bytes = __copy_from_user_nmi(&frame.return_address, fp+4, 4); if (bytes != 0) break; @@ -2265,6 +2284,7 @@ perf_callchain_user32(struct pt_regs *regs, struct perf_callchain_entry *entry) perf_callchain_store(entry, cs_base + frame.return_address); fp = compat_ptr(ss_base + frame.next_frame); } + pagefault_enable(); return 1; } #else @@ -2302,12 +2322,19 @@ perf_callchain_user(struct perf_callchain_entry *entry, struct pt_regs *regs) if (perf_callchain_user32(regs, entry)) return; + pagefault_disable(); while (entry->nr < PERF_MAX_STACK_DEPTH) { unsigned long bytes; frame.next_frame = NULL; frame.return_address = 0; - bytes = copy_from_user_nmi(&frame, fp, sizeof(frame)); + if (!access_ok(VERIFY_READ, fp, 16)) + break; + + bytes = __copy_from_user_nmi(&frame.next_frame, fp, 8); + if (bytes != 0) + break; + bytes = __copy_from_user_nmi(&frame.return_address, fp+8, 8); if (bytes != 0) break; @@ -2315,8 +2342,9 @@ perf_callchain_user(struct perf_callchain_entry *entry, struct pt_regs *regs) break; perf_callchain_store(entry, frame.return_address); - fp = frame.next_frame; + fp = (void __user *)frame.next_frame; } + pagefault_enable(); } /* diff --git a/arch/x86/kernel/cpu/perf_event.h b/arch/x86/kernel/cpu/perf_event.h index 499f533dd3cc..7bb61e32fb29 100644 --- a/arch/x86/kernel/cpu/perf_event.h +++ b/arch/x86/kernel/cpu/perf_event.h @@ -5,7 +5,7 @@ * Copyright (C) 2008-2009 Red Hat, Inc., Ingo Molnar * Copyright (C) 2009 Jaswinder Singh Rajput * Copyright (C) 2009 Advanced Micro Devices, Inc., Robert Richter - * Copyright (C) 2008-2009 Red Hat, Inc., Peter Zijlstra <pzijlstr@redhat.com> + * Copyright (C) 2008-2009 Red Hat, Inc., Peter Zijlstra * Copyright (C) 2009 Intel Corporation, <markus.t.metzger@intel.com> * Copyright (C) 2009 Google, Inc., Stephane Eranian * @@ -14,17 +14,7 @@ #include <linux/perf_event.h> -#if 0 -#undef wrmsrl -#define wrmsrl(msr, val) \ -do { \ - unsigned int _msr = (msr); \ - u64 _val = (val); \ - trace_printk("wrmsrl(%x, %Lx)\n", (unsigned int)(_msr), \ - (unsigned long long)(_val)); \ - native_write_msr((_msr), (u32)(_val), (u32)(_val >> 32)); \ -} while (0) -#endif +/* To enable MSR tracing please use the generic trace points. */ /* * | NHM/WSM | SNB | @@ -318,6 +308,10 @@ struct cpu_hw_events { #define INTEL_UEVENT_CONSTRAINT(c, n) \ EVENT_CONSTRAINT(c, n, INTEL_ARCH_EVENT_MASK) +/* Constraint on specific umask bit only + event */ +#define INTEL_UBIT_EVENT_CONSTRAINT(c, n) \ + EVENT_CONSTRAINT(c, n, ARCH_PERFMON_EVENTSEL_EVENT|(c)) + /* Like UEVENT_CONSTRAINT, but match flags too */ #define INTEL_FLAGS_UEVENT_CONSTRAINT(c, n) \ EVENT_CONSTRAINT(c, n, INTEL_ARCH_EVENT_MASK|X86_ALL_EVENT_FLAGS) @@ -387,7 +381,7 @@ struct cpu_hw_events { /* Check flags and event code/umask, and set the HSW N/A flag */ #define INTEL_FLAGS_UEVENT_CONSTRAINT_DATALA_NA(code, n) \ __EVENT_CONSTRAINT(code, n, \ - INTEL_ARCH_EVENT_MASK|INTEL_ARCH_EVENT_MASK, \ + INTEL_ARCH_EVENT_MASK|X86_ALL_EVENT_FLAGS, \ HWEIGHT(n), 0, PERF_X86_EVENT_PEBS_NA_HSW) @@ -589,7 +583,8 @@ struct x86_pmu { bts_active :1, pebs :1, pebs_active :1, - pebs_broken :1; + pebs_broken :1, + pebs_prec_dist :1; int pebs_record_size; void (*drain_pebs)(struct pt_regs *regs); struct event_constraint *pebs_constraints; @@ -627,6 +622,7 @@ struct x86_perf_task_context { u64 lbr_from[MAX_LBR_ENTRIES]; u64 lbr_to[MAX_LBR_ENTRIES]; u64 lbr_info[MAX_LBR_ENTRIES]; + int tos; int lbr_callstack_users; int lbr_stack_state; }; @@ -906,6 +902,8 @@ void intel_pmu_lbr_init_hsw(void); void intel_pmu_lbr_init_skl(void); +void intel_pmu_lbr_init_knl(void); + int intel_pmu_setup_lbr_filter(struct perf_event *event); void intel_pt_interrupt(void); diff --git a/arch/x86/kernel/cpu/perf_event_amd.c b/arch/x86/kernel/cpu/perf_event_amd.c index 1cee5d2d7ece..58610539b048 100644 --- a/arch/x86/kernel/cpu/perf_event_amd.c +++ b/arch/x86/kernel/cpu/perf_event_amd.c @@ -18,7 +18,7 @@ static __initconst const u64 amd_hw_cache_event_ids [ C(RESULT_MISS) ] = 0x0141, /* Data Cache Misses */ }, [ C(OP_WRITE) ] = { - [ C(RESULT_ACCESS) ] = 0x0142, /* Data Cache Refills :system */ + [ C(RESULT_ACCESS) ] = 0, [ C(RESULT_MISS) ] = 0, }, [ C(OP_PREFETCH) ] = { @@ -160,7 +160,7 @@ static inline int amd_pmu_addr_offset(int index, bool eventsel) if (offset) return offset; - if (!cpu_has_perfctr_core) + if (!boot_cpu_has(X86_FEATURE_PERFCTR_CORE)) offset = index; else offset = index << 1; @@ -652,7 +652,7 @@ static __initconst const struct x86_pmu amd_pmu = { static int __init amd_core_pmu_init(void) { - if (!cpu_has_perfctr_core) + if (!boot_cpu_has(X86_FEATURE_PERFCTR_CORE)) return 0; switch (boot_cpu_data.x86) { diff --git a/arch/x86/kernel/cpu/perf_event_amd_uncore.c b/arch/x86/kernel/cpu/perf_event_amd_uncore.c index cc6cedb8f25d..49742746a6c9 100644 --- a/arch/x86/kernel/cpu/perf_event_amd_uncore.c +++ b/arch/x86/kernel/cpu/perf_event_amd_uncore.c @@ -523,10 +523,10 @@ static int __init amd_uncore_init(void) if (boot_cpu_data.x86_vendor != X86_VENDOR_AMD) goto fail_nodev; - if (!cpu_has_topoext) + if (!boot_cpu_has(X86_FEATURE_TOPOEXT)) goto fail_nodev; - if (cpu_has_perfctr_nb) { + if (boot_cpu_has(X86_FEATURE_PERFCTR_NB)) { amd_uncore_nb = alloc_percpu(struct amd_uncore *); if (!amd_uncore_nb) { ret = -ENOMEM; @@ -540,7 +540,7 @@ static int __init amd_uncore_init(void) ret = 0; } - if (cpu_has_perfctr_l2) { + if (boot_cpu_has(X86_FEATURE_PERFCTR_L2)) { amd_uncore_l2 = alloc_percpu(struct amd_uncore *); if (!amd_uncore_l2) { ret = -ENOMEM; @@ -583,10 +583,11 @@ fail_online: /* amd_uncore_nb/l2 should have been freed by cleanup_cpu_online */ amd_uncore_nb = amd_uncore_l2 = NULL; - if (cpu_has_perfctr_l2) + + if (boot_cpu_has(X86_FEATURE_PERFCTR_L2)) perf_pmu_unregister(&amd_l2_pmu); fail_l2: - if (cpu_has_perfctr_nb) + if (boot_cpu_has(X86_FEATURE_PERFCTR_NB)) perf_pmu_unregister(&amd_nb_pmu); if (amd_uncore_l2) free_percpu(amd_uncore_l2); diff --git a/arch/x86/kernel/cpu/perf_event_intel.c b/arch/x86/kernel/cpu/perf_event_intel.c index f63360be2238..a667078a5180 100644 --- a/arch/x86/kernel/cpu/perf_event_intel.c +++ b/arch/x86/kernel/cpu/perf_event_intel.c @@ -185,6 +185,14 @@ struct event_constraint intel_skl_event_constraints[] = { EVENT_CONSTRAINT_END }; +static struct extra_reg intel_knl_extra_regs[] __read_mostly = { + INTEL_UEVENT_EXTRA_REG(0x01b7, + MSR_OFFCORE_RSP_0, 0x7f9ffbffffull, RSP_0), + INTEL_UEVENT_EXTRA_REG(0x02b7, + MSR_OFFCORE_RSP_1, 0x3f9ffbffffull, RSP_1), + EVENT_EXTRA_END +}; + static struct extra_reg intel_snb_extra_regs[] __read_mostly = { /* must define OFFCORE_RSP_X first, see intel_fixup_er() */ INTEL_UEVENT_EXTRA_REG(0x01b7, MSR_OFFCORE_RSP_0, 0x3f807f8fffull, RSP_0), @@ -232,7 +240,7 @@ static struct event_constraint intel_hsw_event_constraints[] = { FIXED_EVENT_CONSTRAINT(0x00c0, 0), /* INST_RETIRED.ANY */ FIXED_EVENT_CONSTRAINT(0x003c, 1), /* CPU_CLK_UNHALTED.CORE */ FIXED_EVENT_CONSTRAINT(0x0300, 2), /* CPU_CLK_UNHALTED.REF */ - INTEL_EVENT_CONSTRAINT(0x48, 0x4), /* L1D_PEND_MISS.* */ + INTEL_UEVENT_CONSTRAINT(0x148, 0x4), /* L1D_PEND_MISS.PENDING */ INTEL_UEVENT_CONSTRAINT(0x01c0, 0x2), /* INST_RETIRED.PREC_DIST */ INTEL_EVENT_CONSTRAINT(0xcd, 0x8), /* MEM_TRANS_RETIRED.LOAD_LATENCY */ /* CYCLE_ACTIVITY.CYCLES_L1D_PENDING */ @@ -255,7 +263,7 @@ struct event_constraint intel_bdw_event_constraints[] = { FIXED_EVENT_CONSTRAINT(0x003c, 1), /* CPU_CLK_UNHALTED.CORE */ FIXED_EVENT_CONSTRAINT(0x0300, 2), /* CPU_CLK_UNHALTED.REF */ INTEL_UEVENT_CONSTRAINT(0x148, 0x4), /* L1D_PEND_MISS.PENDING */ - INTEL_UEVENT_CONSTRAINT(0x8a3, 0x4), /* CYCLE_ACTIVITY.CYCLES_L1D_MISS */ + INTEL_UBIT_EVENT_CONSTRAINT(0x8a3, 0x4), /* CYCLE_ACTIVITY.CYCLES_L1D_MISS */ EVENT_CONSTRAINT_END }; @@ -1457,6 +1465,42 @@ static __initconst const u64 slm_hw_cache_event_ids }, }; +#define KNL_OT_L2_HITE BIT_ULL(19) /* Other Tile L2 Hit */ +#define KNL_OT_L2_HITF BIT_ULL(20) /* Other Tile L2 Hit */ +#define KNL_MCDRAM_LOCAL BIT_ULL(21) +#define KNL_MCDRAM_FAR BIT_ULL(22) +#define KNL_DDR_LOCAL BIT_ULL(23) +#define KNL_DDR_FAR BIT_ULL(24) +#define KNL_DRAM_ANY (KNL_MCDRAM_LOCAL | KNL_MCDRAM_FAR | \ + KNL_DDR_LOCAL | KNL_DDR_FAR) +#define KNL_L2_READ SLM_DMND_READ +#define KNL_L2_WRITE SLM_DMND_WRITE +#define KNL_L2_PREFETCH SLM_DMND_PREFETCH +#define KNL_L2_ACCESS SLM_LLC_ACCESS +#define KNL_L2_MISS (KNL_OT_L2_HITE | KNL_OT_L2_HITF | \ + KNL_DRAM_ANY | SNB_SNP_ANY | \ + SNB_NON_DRAM) + +static __initconst const u64 knl_hw_cache_extra_regs + [PERF_COUNT_HW_CACHE_MAX] + [PERF_COUNT_HW_CACHE_OP_MAX] + [PERF_COUNT_HW_CACHE_RESULT_MAX] = { + [C(LL)] = { + [C(OP_READ)] = { + [C(RESULT_ACCESS)] = KNL_L2_READ | KNL_L2_ACCESS, + [C(RESULT_MISS)] = 0, + }, + [C(OP_WRITE)] = { + [C(RESULT_ACCESS)] = KNL_L2_WRITE | KNL_L2_ACCESS, + [C(RESULT_MISS)] = KNL_L2_WRITE | KNL_L2_MISS, + }, + [C(OP_PREFETCH)] = { + [C(RESULT_ACCESS)] = KNL_L2_PREFETCH | KNL_L2_ACCESS, + [C(RESULT_MISS)] = KNL_L2_PREFETCH | KNL_L2_MISS, + }, + }, +}; + /* * Use from PMIs where the LBRs are already disabled. */ @@ -2475,6 +2519,44 @@ static void intel_pebs_aliases_snb(struct perf_event *event) } } +static void intel_pebs_aliases_precdist(struct perf_event *event) +{ + if ((event->hw.config & X86_RAW_EVENT_MASK) == 0x003c) { + /* + * Use an alternative encoding for CPU_CLK_UNHALTED.THREAD_P + * (0x003c) so that we can use it with PEBS. + * + * The regular CPU_CLK_UNHALTED.THREAD_P event (0x003c) isn't + * PEBS capable. However we can use INST_RETIRED.PREC_DIST + * (0x01c0), which is a PEBS capable event, to get the same + * count. + * + * The PREC_DIST event has special support to minimize sample + * shadowing effects. One drawback is that it can be + * only programmed on counter 1, but that seems like an + * acceptable trade off. + */ + u64 alt_config = X86_CONFIG(.event=0xc0, .umask=0x01, .inv=1, .cmask=16); + + alt_config |= (event->hw.config & ~X86_RAW_EVENT_MASK); + event->hw.config = alt_config; + } +} + +static void intel_pebs_aliases_ivb(struct perf_event *event) +{ + if (event->attr.precise_ip < 3) + return intel_pebs_aliases_snb(event); + return intel_pebs_aliases_precdist(event); +} + +static void intel_pebs_aliases_skl(struct perf_event *event) +{ + if (event->attr.precise_ip < 3) + return intel_pebs_aliases_core2(event); + return intel_pebs_aliases_precdist(event); +} + static unsigned long intel_pmu_free_running_flags(struct perf_event *event) { unsigned long flags = x86_pmu.free_running_flags; @@ -3332,6 +3414,7 @@ __init int intel_pmu_init(void) x86_pmu.event_constraints = intel_gen_event_constraints; x86_pmu.pebs_constraints = intel_atom_pebs_event_constraints; + x86_pmu.pebs_aliases = intel_pebs_aliases_core2; pr_cont("Atom events, "); break; @@ -3431,7 +3514,8 @@ __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.pebs_aliases = intel_pebs_aliases_ivb; + x86_pmu.pebs_prec_dist = true; if (boot_cpu_data.x86_model == 62) x86_pmu.extra_regs = intel_snbep_extra_regs; else @@ -3464,7 +3548,8 @@ __init int intel_pmu_init(void) x86_pmu.event_constraints = intel_hsw_event_constraints; x86_pmu.pebs_constraints = intel_hsw_pebs_event_constraints; x86_pmu.extra_regs = intel_snbep_extra_regs; - x86_pmu.pebs_aliases = intel_pebs_aliases_snb; + x86_pmu.pebs_aliases = intel_pebs_aliases_ivb; + x86_pmu.pebs_prec_dist = true; /* all extra regs are per-cpu when HT is on */ x86_pmu.flags |= PMU_FL_HAS_RSP_1; x86_pmu.flags |= PMU_FL_NO_HT_SHARING; @@ -3499,7 +3584,8 @@ __init int intel_pmu_init(void) x86_pmu.event_constraints = intel_bdw_event_constraints; x86_pmu.pebs_constraints = intel_hsw_pebs_event_constraints; x86_pmu.extra_regs = intel_snbep_extra_regs; - x86_pmu.pebs_aliases = intel_pebs_aliases_snb; + x86_pmu.pebs_aliases = intel_pebs_aliases_ivb; + x86_pmu.pebs_prec_dist = true; /* all extra regs are per-cpu when HT is on */ x86_pmu.flags |= PMU_FL_HAS_RSP_1; x86_pmu.flags |= PMU_FL_NO_HT_SHARING; @@ -3511,6 +3597,24 @@ __init int intel_pmu_init(void) pr_cont("Broadwell events, "); break; + case 87: /* Knights Landing Xeon Phi */ + memcpy(hw_cache_event_ids, + slm_hw_cache_event_ids, sizeof(hw_cache_event_ids)); + memcpy(hw_cache_extra_regs, + knl_hw_cache_extra_regs, sizeof(hw_cache_extra_regs)); + intel_pmu_lbr_init_knl(); + + x86_pmu.event_constraints = intel_slm_event_constraints; + x86_pmu.pebs_constraints = intel_slm_pebs_event_constraints; + x86_pmu.extra_regs = intel_knl_extra_regs; + + /* all extra regs are per-cpu when HT is on */ + x86_pmu.flags |= PMU_FL_HAS_RSP_1; + x86_pmu.flags |= PMU_FL_NO_HT_SHARING; + + pr_cont("Knights Landing events, "); + break; + case 78: /* 14nm Skylake Mobile */ case 94: /* 14nm Skylake Desktop */ x86_pmu.late_ack = true; @@ -3521,7 +3625,8 @@ __init int intel_pmu_init(void) x86_pmu.event_constraints = intel_skl_event_constraints; x86_pmu.pebs_constraints = intel_skl_pebs_event_constraints; x86_pmu.extra_regs = intel_skl_extra_regs; - x86_pmu.pebs_aliases = intel_pebs_aliases_snb; + x86_pmu.pebs_aliases = intel_pebs_aliases_skl; + x86_pmu.pebs_prec_dist = true; /* all extra regs are per-cpu when HT is on */ x86_pmu.flags |= PMU_FL_HAS_RSP_1; x86_pmu.flags |= PMU_FL_NO_HT_SHARING; diff --git a/arch/x86/kernel/cpu/perf_event_intel_cqm.c b/arch/x86/kernel/cpu/perf_event_intel_cqm.c index 377e8f8ed391..a316ca96f1b6 100644 --- a/arch/x86/kernel/cpu/perf_event_intel_cqm.c +++ b/arch/x86/kernel/cpu/perf_event_intel_cqm.c @@ -298,7 +298,7 @@ static bool __match_event(struct perf_event *a, struct perf_event *b) static inline struct perf_cgroup *event_to_cgroup(struct perf_event *event) { if (event->attach_state & PERF_ATTACH_TASK) - return perf_cgroup_from_task(event->hw.target); + return perf_cgroup_from_task(event->hw.target, event->ctx); return event->cgrp; } diff --git a/arch/x86/kernel/cpu/perf_event_intel_ds.c b/arch/x86/kernel/cpu/perf_event_intel_ds.c index 5db1c7755548..10602f0a438f 100644 --- a/arch/x86/kernel/cpu/perf_event_intel_ds.c +++ b/arch/x86/kernel/cpu/perf_event_intel_ds.c @@ -620,6 +620,8 @@ struct event_constraint intel_atom_pebs_event_constraints[] = { INTEL_FLAGS_EVENT_CONSTRAINT(0xcb, 0x1), /* MEM_LOAD_RETIRED.* */ /* INST_RETIRED.ANY_P, inv=1, cmask=16 (cycles:p). */ INTEL_FLAGS_EVENT_CONSTRAINT(0x108000c0, 0x01), + /* Allow all events as PEBS with no flags */ + INTEL_ALL_EVENT_CONSTRAINT(0, 0x1), EVENT_CONSTRAINT_END }; @@ -686,6 +688,8 @@ struct event_constraint intel_ivb_pebs_event_constraints[] = { INTEL_PST_CONSTRAINT(0x02cd, 0x8), /* MEM_TRANS_RETIRED.PRECISE_STORES */ /* UOPS_RETIRED.ALL, inv=1, cmask=16 (cycles:p). */ INTEL_FLAGS_EVENT_CONSTRAINT(0x108001c2, 0xf), + /* INST_RETIRED.PREC_DIST, inv=1, cmask=16 (cycles:ppp). */ + INTEL_FLAGS_EVENT_CONSTRAINT(0x108001c0, 0x2), INTEL_EXCLEVT_CONSTRAINT(0xd0, 0xf), /* MEM_UOP_RETIRED.* */ INTEL_EXCLEVT_CONSTRAINT(0xd1, 0xf), /* MEM_LOAD_UOPS_RETIRED.* */ INTEL_EXCLEVT_CONSTRAINT(0xd2, 0xf), /* MEM_LOAD_UOPS_LLC_HIT_RETIRED.* */ @@ -700,6 +704,8 @@ struct event_constraint intel_hsw_pebs_event_constraints[] = { INTEL_PLD_CONSTRAINT(0x01cd, 0xf), /* MEM_TRANS_RETIRED.* */ /* UOPS_RETIRED.ALL, inv=1, cmask=16 (cycles:p). */ INTEL_FLAGS_EVENT_CONSTRAINT(0x108001c2, 0xf), + /* INST_RETIRED.PREC_DIST, inv=1, cmask=16 (cycles:ppp). */ + INTEL_FLAGS_EVENT_CONSTRAINT(0x108001c0, 0x2), INTEL_FLAGS_UEVENT_CONSTRAINT_DATALA_NA(0x01c2, 0xf), /* UOPS_RETIRED.ALL */ INTEL_FLAGS_UEVENT_CONSTRAINT_DATALA_XLD(0x11d0, 0xf), /* MEM_UOPS_RETIRED.STLB_MISS_LOADS */ INTEL_FLAGS_UEVENT_CONSTRAINT_DATALA_XLD(0x21d0, 0xf), /* MEM_UOPS_RETIRED.LOCK_LOADS */ @@ -718,9 +724,10 @@ struct event_constraint intel_hsw_pebs_event_constraints[] = { struct event_constraint intel_skl_pebs_event_constraints[] = { INTEL_FLAGS_UEVENT_CONSTRAINT(0x1c0, 0x2), /* INST_RETIRED.PREC_DIST */ - INTEL_FLAGS_UEVENT_CONSTRAINT_DATALA_NA(0x01c2, 0xf), /* UOPS_RETIRED.ALL */ - /* UOPS_RETIRED.ALL, inv=1, cmask=16 (cycles:p). */ - INTEL_FLAGS_EVENT_CONSTRAINT(0x108001c2, 0xf), + /* INST_RETIRED.PREC_DIST, inv=1, cmask=16 (cycles:ppp). */ + INTEL_FLAGS_EVENT_CONSTRAINT(0x108001c0, 0x2), + /* INST_RETIRED.TOTAL_CYCLES_PS (inv=1, cmask=16) (cycles:p). */ + INTEL_FLAGS_EVENT_CONSTRAINT(0x108000c0, 0x0f), INTEL_PLD_CONSTRAINT(0x1cd, 0xf), /* MEM_TRANS_RETIRED.* */ INTEL_FLAGS_UEVENT_CONSTRAINT_DATALA_LD(0x11d0, 0xf), /* MEM_INST_RETIRED.STLB_MISS_LOADS */ INTEL_FLAGS_UEVENT_CONSTRAINT_DATALA_ST(0x12d0, 0xf), /* MEM_INST_RETIRED.STLB_MISS_STORES */ @@ -1101,6 +1108,13 @@ get_next_pebs_record_by_bit(void *base, void *top, int bit) void *at; u64 pebs_status; + /* + * fmt0 does not have a status bitfield (does not use + * perf_record_nhm format) + */ + if (x86_pmu.intel_cap.pebs_format < 1) + return base; + if (base == NULL) return NULL; @@ -1186,7 +1200,7 @@ static void intel_pmu_drain_pebs_core(struct pt_regs *iregs) if (!event->attr.precise_ip) return; - n = (top - at) / x86_pmu.pebs_record_size; + n = top - at; if (n <= 0) return; @@ -1230,12 +1244,21 @@ static void intel_pmu_drain_pebs_nhm(struct pt_regs *iregs) pebs_status = p->status & cpuc->pebs_enabled; pebs_status &= (1ULL << x86_pmu.max_pebs_events) - 1; + /* + * On some CPUs the PEBS status can be zero when PEBS is + * racing with clearing of GLOBAL_STATUS. + * + * Normally we would drop that record, but in the + * case when there is only a single active PEBS event + * we can assume it's for that event. + */ + if (!pebs_status && cpuc->pebs_enabled && + !(cpuc->pebs_enabled & (cpuc->pebs_enabled-1))) + pebs_status = cpuc->pebs_enabled; + bit = find_first_bit((unsigned long *)&pebs_status, x86_pmu.max_pebs_events); - if (WARN(bit >= x86_pmu.max_pebs_events, - "PEBS record without PEBS event! status=%Lx pebs_enabled=%Lx active_mask=%Lx", - (unsigned long long)p->status, (unsigned long long)cpuc->pebs_enabled, - *(unsigned long long *)cpuc->active_mask)) + if (bit >= x86_pmu.max_pebs_events) continue; /* diff --git a/arch/x86/kernel/cpu/perf_event_intel_lbr.c b/arch/x86/kernel/cpu/perf_event_intel_lbr.c index bfd0b717e944..653f88d25987 100644 --- a/arch/x86/kernel/cpu/perf_event_intel_lbr.c +++ b/arch/x86/kernel/cpu/perf_event_intel_lbr.c @@ -42,6 +42,13 @@ static enum { #define LBR_FAR_BIT 8 /* do not capture far branches */ #define LBR_CALL_STACK_BIT 9 /* enable call stack */ +/* + * Following bit only exists in Linux; we mask it out before writing it to + * the actual MSR. But it helps the constraint perf code to understand + * that this is a separate configuration. + */ +#define LBR_NO_INFO_BIT 63 /* don't read LBR_INFO. */ + #define LBR_KERNEL (1 << LBR_KERNEL_BIT) #define LBR_USER (1 << LBR_USER_BIT) #define LBR_JCC (1 << LBR_JCC_BIT) @@ -52,6 +59,7 @@ static enum { #define LBR_IND_JMP (1 << LBR_IND_JMP_BIT) #define LBR_FAR (1 << LBR_FAR_BIT) #define LBR_CALL_STACK (1 << LBR_CALL_STACK_BIT) +#define LBR_NO_INFO (1ULL << LBR_NO_INFO_BIT) #define LBR_PLM (LBR_KERNEL | LBR_USER) @@ -152,8 +160,8 @@ static void __intel_pmu_lbr_enable(bool pmi) * did not change. */ if (cpuc->lbr_sel) - lbr_select = cpuc->lbr_sel->config; - if (!pmi) + lbr_select = cpuc->lbr_sel->config & x86_pmu.lbr_sel_mask; + if (!pmi && cpuc->lbr_sel) wrmsrl(MSR_LBR_SELECT, lbr_select); rdmsrl(MSR_IA32_DEBUGCTLMSR, debugctl); @@ -239,7 +247,7 @@ static void __intel_pmu_lbr_restore(struct x86_perf_task_context *task_ctx) } mask = x86_pmu.lbr_nr - 1; - tos = intel_pmu_lbr_tos(); + tos = task_ctx->tos; for (i = 0; i < tos; i++) { lbr_idx = (tos - i) & mask; wrmsrl(x86_pmu.lbr_from + lbr_idx, task_ctx->lbr_from[i]); @@ -247,6 +255,7 @@ static void __intel_pmu_lbr_restore(struct x86_perf_task_context *task_ctx) if (x86_pmu.intel_cap.lbr_format == LBR_FORMAT_INFO) wrmsrl(MSR_LBR_INFO_0 + lbr_idx, task_ctx->lbr_info[i]); } + wrmsrl(x86_pmu.lbr_tos, tos); task_ctx->lbr_stack_state = LBR_NONE; } @@ -270,6 +279,7 @@ static void __intel_pmu_lbr_save(struct x86_perf_task_context *task_ctx) if (x86_pmu.intel_cap.lbr_format == LBR_FORMAT_INFO) rdmsrl(MSR_LBR_INFO_0 + lbr_idx, task_ctx->lbr_info[i]); } + task_ctx->tos = tos; task_ctx->lbr_stack_state = LBR_VALID; } @@ -420,6 +430,7 @@ static void intel_pmu_lbr_read_32(struct cpu_hw_events *cpuc) */ static void intel_pmu_lbr_read_64(struct cpu_hw_events *cpuc) { + bool need_info = false; unsigned long mask = x86_pmu.lbr_nr - 1; int lbr_format = x86_pmu.intel_cap.lbr_format; u64 tos = intel_pmu_lbr_tos(); @@ -427,8 +438,11 @@ static void intel_pmu_lbr_read_64(struct cpu_hw_events *cpuc) int out = 0; int num = x86_pmu.lbr_nr; - if (cpuc->lbr_sel->config & LBR_CALL_STACK) - num = tos; + if (cpuc->lbr_sel) { + need_info = !(cpuc->lbr_sel->config & LBR_NO_INFO); + if (cpuc->lbr_sel->config & LBR_CALL_STACK) + num = tos; + } for (i = 0; i < num; i++) { unsigned long lbr_idx = (tos - i) & mask; @@ -440,7 +454,7 @@ static void intel_pmu_lbr_read_64(struct cpu_hw_events *cpuc) rdmsrl(x86_pmu.lbr_from + lbr_idx, from); rdmsrl(x86_pmu.lbr_to + lbr_idx, to); - if (lbr_format == LBR_FORMAT_INFO) { + if (lbr_format == LBR_FORMAT_INFO && need_info) { u64 info; rdmsrl(MSR_LBR_INFO_0 + lbr_idx, info); @@ -588,6 +602,7 @@ static int intel_pmu_setup_hw_lbr_filter(struct perf_event *event) if (v != LBR_IGN) mask |= v; } + reg = &event->hw.branch_reg; reg->idx = EXTRA_REG_LBR; @@ -598,6 +613,11 @@ static int intel_pmu_setup_hw_lbr_filter(struct perf_event *event) */ reg->config = mask ^ x86_pmu.lbr_sel_mask; + if ((br_type & PERF_SAMPLE_BRANCH_NO_CYCLES) && + (br_type & PERF_SAMPLE_BRANCH_NO_FLAGS) && + (x86_pmu.intel_cap.lbr_format == LBR_FORMAT_INFO)) + reg->config |= LBR_NO_INFO; + return 0; } @@ -1026,3 +1046,17 @@ void __init intel_pmu_lbr_init_atom(void) */ pr_cont("8-deep LBR, "); } + +/* Knights Landing */ +void intel_pmu_lbr_init_knl(void) +{ + x86_pmu.lbr_nr = 8; + x86_pmu.lbr_tos = MSR_LBR_TOS; + x86_pmu.lbr_from = MSR_LBR_NHM_FROM; + x86_pmu.lbr_to = MSR_LBR_NHM_TO; + + x86_pmu.lbr_sel_mask = LBR_SEL_MASK; + x86_pmu.lbr_sel_map = snb_lbr_sel_map; + + pr_cont("8-deep LBR, "); +} diff --git a/arch/x86/kernel/cpu/perf_event_intel_pt.c b/arch/x86/kernel/cpu/perf_event_intel_pt.c index 868e1194337f..c0bbd1033b7c 100644 --- a/arch/x86/kernel/cpu/perf_event_intel_pt.c +++ b/arch/x86/kernel/cpu/perf_event_intel_pt.c @@ -27,6 +27,7 @@ #include <asm/perf_event.h> #include <asm/insn.h> #include <asm/io.h> +#include <asm/intel_pt.h> #include "perf_event.h" #include "intel_pt.h" @@ -1122,6 +1123,14 @@ static int pt_event_init(struct perf_event *event) return 0; } +void cpu_emergency_stop_pt(void) +{ + struct pt *pt = this_cpu_ptr(&pt_ctx); + + if (pt->handle.event) + pt_event_stop(pt->handle.event, PERF_EF_UPDATE); +} + static __init int pt_init(void) { int ret, cpu, prior_warn = 0; diff --git a/arch/x86/kernel/cpu/perf_event_intel_rapl.c b/arch/x86/kernel/cpu/perf_event_intel_rapl.c index ed446bdcbf31..24a351ad628d 100644 --- a/arch/x86/kernel/cpu/perf_event_intel_rapl.c +++ b/arch/x86/kernel/cpu/perf_event_intel_rapl.c @@ -63,7 +63,7 @@ #define INTEL_RAPL_PP1 0x4 /* pseudo-encoding */ #define NR_RAPL_DOMAINS 0x4 -static const char *rapl_domain_names[NR_RAPL_DOMAINS] __initconst = { +static const char *const rapl_domain_names[NR_RAPL_DOMAINS] __initconst = { "pp0-core", "package", "dram", @@ -109,11 +109,11 @@ static struct kobj_attribute format_attr_##_var = \ #define RAPL_CNTR_WIDTH 32 /* 32-bit rapl counters */ -#define RAPL_EVENT_ATTR_STR(_name, v, str) \ -static struct perf_pmu_events_attr event_attr_##v = { \ - .attr = __ATTR(_name, 0444, rapl_sysfs_show, NULL), \ - .id = 0, \ - .event_str = str, \ +#define RAPL_EVENT_ATTR_STR(_name, v, str) \ +static struct perf_pmu_events_attr event_attr_##v = { \ + .attr = __ATTR(_name, 0444, perf_event_sysfs_show, NULL), \ + .id = 0, \ + .event_str = str, \ }; struct rapl_pmu { @@ -405,19 +405,6 @@ static struct attribute_group rapl_pmu_attr_group = { .attrs = rapl_pmu_attrs, }; -static ssize_t rapl_sysfs_show(struct device *dev, - struct device_attribute *attr, - char *page) -{ - struct perf_pmu_events_attr *pmu_attr = \ - container_of(attr, struct perf_pmu_events_attr, attr); - - if (pmu_attr->event_str) - return sprintf(page, "%s", pmu_attr->event_str); - - return 0; -} - RAPL_EVENT_ATTR_STR(energy-cores, rapl_cores, "event=0x01"); RAPL_EVENT_ATTR_STR(energy-pkg , rapl_pkg, "event=0x02"); RAPL_EVENT_ATTR_STR(energy-ram , rapl_ram, "event=0x03"); diff --git a/arch/x86/kernel/cpu/perf_event_intel_uncore.c b/arch/x86/kernel/cpu/perf_event_intel_uncore.c index 61215a69b03d..f97f8075bf04 100644 --- a/arch/x86/kernel/cpu/perf_event_intel_uncore.c +++ b/arch/x86/kernel/cpu/perf_event_intel_uncore.c @@ -884,6 +884,15 @@ static int uncore_pci_probe(struct pci_dev *pdev, const struct pci_device_id *id * each box has a different function id. */ pmu = &type->pmus[UNCORE_PCI_DEV_IDX(id->driver_data)]; + /* Knights Landing uses a common PCI device ID for multiple instances of + * an uncore PMU device type. There is only one entry per device type in + * the knl_uncore_pci_ids table inspite of multiple devices present for + * some device types. Hence PCI device idx would be 0 for all devices. + * So increment pmu pointer to point to an unused array element. + */ + if (boot_cpu_data.x86_model == 87) + while (pmu->func_id >= 0) + pmu++; if (pmu->func_id < 0) pmu->func_id = pdev->devfn; else @@ -966,6 +975,7 @@ static int __init uncore_pci_init(void) case 63: /* Haswell-EP */ ret = hswep_uncore_pci_init(); break; + case 79: /* BDX-EP */ case 86: /* BDX-DE */ ret = bdx_uncore_pci_init(); break; @@ -982,6 +992,9 @@ static int __init uncore_pci_init(void) case 61: /* Broadwell */ ret = bdw_uncore_pci_init(); break; + case 87: /* Knights Landing */ + ret = knl_uncore_pci_init(); + break; default: return 0; } @@ -1287,9 +1300,13 @@ static int __init uncore_cpu_init(void) case 63: /* Haswell-EP */ hswep_uncore_cpu_init(); break; + case 79: /* BDX-EP */ case 86: /* BDX-DE */ bdx_uncore_cpu_init(); break; + case 87: /* Knights Landing */ + knl_uncore_cpu_init(); + break; default: return 0; } diff --git a/arch/x86/kernel/cpu/perf_event_intel_uncore.h b/arch/x86/kernel/cpu/perf_event_intel_uncore.h index 2f0a4a98e16b..07aa2d6bd710 100644 --- a/arch/x86/kernel/cpu/perf_event_intel_uncore.h +++ b/arch/x86/kernel/cpu/perf_event_intel_uncore.h @@ -338,6 +338,7 @@ int hsw_uncore_pci_init(void); int bdw_uncore_pci_init(void); void snb_uncore_cpu_init(void); void nhm_uncore_cpu_init(void); +int snb_pci2phy_map_init(int devid); /* perf_event_intel_uncore_snbep.c */ int snbep_uncore_pci_init(void); @@ -348,6 +349,8 @@ int hswep_uncore_pci_init(void); void hswep_uncore_cpu_init(void); int bdx_uncore_pci_init(void); void bdx_uncore_cpu_init(void); +int knl_uncore_pci_init(void); +void knl_uncore_cpu_init(void); /* perf_event_intel_uncore_nhmex.c */ void nhmex_uncore_cpu_init(void); diff --git a/arch/x86/kernel/cpu/perf_event_intel_uncore_snb.c b/arch/x86/kernel/cpu/perf_event_intel_uncore_snb.c index 845256158a10..0b934820fafd 100644 --- a/arch/x86/kernel/cpu/perf_event_intel_uncore_snb.c +++ b/arch/x86/kernel/cpu/perf_event_intel_uncore_snb.c @@ -417,7 +417,7 @@ static void snb_uncore_imc_event_del(struct perf_event *event, int flags) } } -static int snb_pci2phy_map_init(int devid) +int snb_pci2phy_map_init(int devid) { struct pci_dev *dev = NULL; struct pci2phy_map *map; diff --git a/arch/x86/kernel/cpu/perf_event_intel_uncore_snbep.c b/arch/x86/kernel/cpu/perf_event_intel_uncore_snbep.c index f0f4fcba252e..33acb884ccf1 100644 --- a/arch/x86/kernel/cpu/perf_event_intel_uncore_snbep.c +++ b/arch/x86/kernel/cpu/perf_event_intel_uncore_snbep.c @@ -209,31 +209,98 @@ #define HSWEP_PCU_MSR_PMON_BOX_CTL 0x710 #define HSWEP_PCU_MSR_PMON_BOX_FILTER 0x715 +/* KNL Ubox */ +#define KNL_U_MSR_PMON_RAW_EVENT_MASK \ + (SNBEP_U_MSR_PMON_RAW_EVENT_MASK | \ + SNBEP_CBO_PMON_CTL_TID_EN) +/* KNL CHA */ +#define KNL_CHA_MSR_OFFSET 0xc +#define KNL_CHA_MSR_PMON_CTL_QOR (1 << 16) +#define KNL_CHA_MSR_PMON_RAW_EVENT_MASK \ + (SNBEP_CBO_MSR_PMON_RAW_EVENT_MASK | \ + KNL_CHA_MSR_PMON_CTL_QOR) +#define KNL_CHA_MSR_PMON_BOX_FILTER_TID 0x1ff +#define KNL_CHA_MSR_PMON_BOX_FILTER_STATE (7 << 18) +#define KNL_CHA_MSR_PMON_BOX_FILTER_OP (0xfffffe2aULL << 32) + +/* KNL EDC/MC UCLK */ +#define KNL_UCLK_MSR_PMON_CTR0_LOW 0x400 +#define KNL_UCLK_MSR_PMON_CTL0 0x420 +#define KNL_UCLK_MSR_PMON_BOX_CTL 0x430 +#define KNL_UCLK_MSR_PMON_UCLK_FIXED_LOW 0x44c +#define KNL_UCLK_MSR_PMON_UCLK_FIXED_CTL 0x454 +#define KNL_PMON_FIXED_CTL_EN 0x1 + +/* KNL EDC */ +#define KNL_EDC0_ECLK_MSR_PMON_CTR0_LOW 0xa00 +#define KNL_EDC0_ECLK_MSR_PMON_CTL0 0xa20 +#define KNL_EDC0_ECLK_MSR_PMON_BOX_CTL 0xa30 +#define KNL_EDC0_ECLK_MSR_PMON_ECLK_FIXED_LOW 0xa3c +#define KNL_EDC0_ECLK_MSR_PMON_ECLK_FIXED_CTL 0xa44 + +/* KNL MC */ +#define KNL_MC0_CH0_MSR_PMON_CTR0_LOW 0xb00 +#define KNL_MC0_CH0_MSR_PMON_CTL0 0xb20 +#define KNL_MC0_CH0_MSR_PMON_BOX_CTL 0xb30 +#define KNL_MC0_CH0_MSR_PMON_FIXED_LOW 0xb3c +#define KNL_MC0_CH0_MSR_PMON_FIXED_CTL 0xb44 + +/* KNL IRP */ +#define KNL_IRP_PCI_PMON_BOX_CTL 0xf0 +#define KNL_IRP_PCI_PMON_RAW_EVENT_MASK (SNBEP_PMON_RAW_EVENT_MASK | \ + KNL_CHA_MSR_PMON_CTL_QOR) +/* KNL PCU */ +#define KNL_PCU_PMON_CTL_EV_SEL_MASK 0x0000007f +#define KNL_PCU_PMON_CTL_USE_OCC_CTR (1 << 7) +#define KNL_PCU_MSR_PMON_CTL_TRESH_MASK 0x3f000000 +#define KNL_PCU_MSR_PMON_RAW_EVENT_MASK \ + (KNL_PCU_PMON_CTL_EV_SEL_MASK | \ + KNL_PCU_PMON_CTL_USE_OCC_CTR | \ + SNBEP_PCU_MSR_PMON_CTL_OCC_SEL_MASK | \ + SNBEP_PMON_CTL_EDGE_DET | \ + SNBEP_CBO_PMON_CTL_TID_EN | \ + SNBEP_PMON_CTL_EV_SEL_EXT | \ + SNBEP_PMON_CTL_INVERT | \ + KNL_PCU_MSR_PMON_CTL_TRESH_MASK | \ + SNBEP_PCU_MSR_PMON_CTL_OCC_INVERT | \ + SNBEP_PCU_MSR_PMON_CTL_OCC_EDGE_DET) DEFINE_UNCORE_FORMAT_ATTR(event, event, "config:0-7"); +DEFINE_UNCORE_FORMAT_ATTR(event2, event, "config:0-6"); DEFINE_UNCORE_FORMAT_ATTR(event_ext, event, "config:0-7,21"); +DEFINE_UNCORE_FORMAT_ATTR(use_occ_ctr, use_occ_ctr, "config:7"); DEFINE_UNCORE_FORMAT_ATTR(umask, umask, "config:8-15"); +DEFINE_UNCORE_FORMAT_ATTR(qor, qor, "config:16"); DEFINE_UNCORE_FORMAT_ATTR(edge, edge, "config:18"); DEFINE_UNCORE_FORMAT_ATTR(tid_en, tid_en, "config:19"); DEFINE_UNCORE_FORMAT_ATTR(inv, inv, "config:23"); DEFINE_UNCORE_FORMAT_ATTR(thresh8, thresh, "config:24-31"); +DEFINE_UNCORE_FORMAT_ATTR(thresh6, thresh, "config:24-29"); DEFINE_UNCORE_FORMAT_ATTR(thresh5, thresh, "config:24-28"); DEFINE_UNCORE_FORMAT_ATTR(occ_sel, occ_sel, "config:14-15"); DEFINE_UNCORE_FORMAT_ATTR(occ_invert, occ_invert, "config:30"); DEFINE_UNCORE_FORMAT_ATTR(occ_edge, occ_edge, "config:14-51"); +DEFINE_UNCORE_FORMAT_ATTR(occ_edge_det, occ_edge_det, "config:31"); DEFINE_UNCORE_FORMAT_ATTR(filter_tid, filter_tid, "config1:0-4"); DEFINE_UNCORE_FORMAT_ATTR(filter_tid2, filter_tid, "config1:0"); DEFINE_UNCORE_FORMAT_ATTR(filter_tid3, filter_tid, "config1:0-5"); +DEFINE_UNCORE_FORMAT_ATTR(filter_tid4, filter_tid, "config1:0-8"); DEFINE_UNCORE_FORMAT_ATTR(filter_cid, filter_cid, "config1:5"); DEFINE_UNCORE_FORMAT_ATTR(filter_link, filter_link, "config1:5-8"); DEFINE_UNCORE_FORMAT_ATTR(filter_link2, filter_link, "config1:6-8"); +DEFINE_UNCORE_FORMAT_ATTR(filter_link3, filter_link, "config1:12"); DEFINE_UNCORE_FORMAT_ATTR(filter_nid, filter_nid, "config1:10-17"); DEFINE_UNCORE_FORMAT_ATTR(filter_nid2, filter_nid, "config1:32-47"); DEFINE_UNCORE_FORMAT_ATTR(filter_state, filter_state, "config1:18-22"); DEFINE_UNCORE_FORMAT_ATTR(filter_state2, filter_state, "config1:17-22"); DEFINE_UNCORE_FORMAT_ATTR(filter_state3, filter_state, "config1:17-23"); +DEFINE_UNCORE_FORMAT_ATTR(filter_state4, filter_state, "config1:18-20"); +DEFINE_UNCORE_FORMAT_ATTR(filter_local, filter_local, "config1:33"); +DEFINE_UNCORE_FORMAT_ATTR(filter_all_op, filter_all_op, "config1:35"); +DEFINE_UNCORE_FORMAT_ATTR(filter_nnm, filter_nnm, "config1:37"); DEFINE_UNCORE_FORMAT_ATTR(filter_opc, filter_opc, "config1:23-31"); DEFINE_UNCORE_FORMAT_ATTR(filter_opc2, filter_opc, "config1:52-60"); +DEFINE_UNCORE_FORMAT_ATTR(filter_opc3, filter_opc, "config1:41-60"); DEFINE_UNCORE_FORMAT_ATTR(filter_nc, filter_nc, "config1:62"); DEFINE_UNCORE_FORMAT_ATTR(filter_c6, filter_c6, "config1:61"); DEFINE_UNCORE_FORMAT_ATTR(filter_isoc, filter_isoc, "config1:63"); @@ -315,8 +382,9 @@ static u64 snbep_uncore_pci_read_counter(struct intel_uncore_box *box, struct pe static void snbep_uncore_pci_init_box(struct intel_uncore_box *box) { struct pci_dev *pdev = box->pci_dev; + int box_ctl = uncore_pci_box_ctl(box); - pci_write_config_dword(pdev, SNBEP_PCI_PMON_BOX_CTL, SNBEP_PMON_BOX_CTL_INT); + pci_write_config_dword(pdev, box_ctl, SNBEP_PMON_BOX_CTL_INT); } static void snbep_uncore_msr_disable_box(struct intel_uncore_box *box) @@ -1728,6 +1796,419 @@ int ivbep_uncore_pci_init(void) } /* end of IvyTown uncore support */ +/* KNL uncore support */ +static struct attribute *knl_uncore_ubox_formats_attr[] = { + &format_attr_event.attr, + &format_attr_umask.attr, + &format_attr_edge.attr, + &format_attr_tid_en.attr, + &format_attr_inv.attr, + &format_attr_thresh5.attr, + NULL, +}; + +static struct attribute_group knl_uncore_ubox_format_group = { + .name = "format", + .attrs = knl_uncore_ubox_formats_attr, +}; + +static struct intel_uncore_type knl_uncore_ubox = { + .name = "ubox", + .num_counters = 2, + .num_boxes = 1, + .perf_ctr_bits = 48, + .fixed_ctr_bits = 48, + .perf_ctr = HSWEP_U_MSR_PMON_CTR0, + .event_ctl = HSWEP_U_MSR_PMON_CTL0, + .event_mask = KNL_U_MSR_PMON_RAW_EVENT_MASK, + .fixed_ctr = HSWEP_U_MSR_PMON_UCLK_FIXED_CTR, + .fixed_ctl = HSWEP_U_MSR_PMON_UCLK_FIXED_CTL, + .ops = &snbep_uncore_msr_ops, + .format_group = &knl_uncore_ubox_format_group, +}; + +static struct attribute *knl_uncore_cha_formats_attr[] = { + &format_attr_event.attr, + &format_attr_umask.attr, + &format_attr_qor.attr, + &format_attr_edge.attr, + &format_attr_tid_en.attr, + &format_attr_inv.attr, + &format_attr_thresh8.attr, + &format_attr_filter_tid4.attr, + &format_attr_filter_link3.attr, + &format_attr_filter_state4.attr, + &format_attr_filter_local.attr, + &format_attr_filter_all_op.attr, + &format_attr_filter_nnm.attr, + &format_attr_filter_opc3.attr, + &format_attr_filter_nc.attr, + &format_attr_filter_isoc.attr, + NULL, +}; + +static struct attribute_group knl_uncore_cha_format_group = { + .name = "format", + .attrs = knl_uncore_cha_formats_attr, +}; + +static struct event_constraint knl_uncore_cha_constraints[] = { + UNCORE_EVENT_CONSTRAINT(0x11, 0x1), + UNCORE_EVENT_CONSTRAINT(0x1f, 0x1), + UNCORE_EVENT_CONSTRAINT(0x36, 0x1), + EVENT_CONSTRAINT_END +}; + +static struct extra_reg knl_uncore_cha_extra_regs[] = { + SNBEP_CBO_EVENT_EXTRA_REG(SNBEP_CBO_PMON_CTL_TID_EN, + SNBEP_CBO_PMON_CTL_TID_EN, 0x1), + SNBEP_CBO_EVENT_EXTRA_REG(0x3d, 0xff, 0x2), + SNBEP_CBO_EVENT_EXTRA_REG(0x35, 0xff, 0x4), + SNBEP_CBO_EVENT_EXTRA_REG(0x36, 0xff, 0x4), + EVENT_EXTRA_END +}; + +static u64 knl_cha_filter_mask(int fields) +{ + u64 mask = 0; + + if (fields & 0x1) + mask |= KNL_CHA_MSR_PMON_BOX_FILTER_TID; + if (fields & 0x2) + mask |= KNL_CHA_MSR_PMON_BOX_FILTER_STATE; + if (fields & 0x4) + mask |= KNL_CHA_MSR_PMON_BOX_FILTER_OP; + return mask; +} + +static struct event_constraint * +knl_cha_get_constraint(struct intel_uncore_box *box, struct perf_event *event) +{ + return __snbep_cbox_get_constraint(box, event, knl_cha_filter_mask); +} + +static int knl_cha_hw_config(struct intel_uncore_box *box, + struct perf_event *event) +{ + struct hw_perf_event_extra *reg1 = &event->hw.extra_reg; + struct extra_reg *er; + int idx = 0; + + for (er = knl_uncore_cha_extra_regs; er->msr; er++) { + if (er->event != (event->hw.config & er->config_mask)) + continue; + idx |= er->idx; + } + + if (idx) { + reg1->reg = HSWEP_C0_MSR_PMON_BOX_FILTER0 + + KNL_CHA_MSR_OFFSET * box->pmu->pmu_idx; + reg1->config = event->attr.config1 & knl_cha_filter_mask(idx); + reg1->idx = idx; + } + return 0; +} + +static void hswep_cbox_enable_event(struct intel_uncore_box *box, + struct perf_event *event); + +static struct intel_uncore_ops knl_uncore_cha_ops = { + .init_box = snbep_uncore_msr_init_box, + .disable_box = snbep_uncore_msr_disable_box, + .enable_box = snbep_uncore_msr_enable_box, + .disable_event = snbep_uncore_msr_disable_event, + .enable_event = hswep_cbox_enable_event, + .read_counter = uncore_msr_read_counter, + .hw_config = knl_cha_hw_config, + .get_constraint = knl_cha_get_constraint, + .put_constraint = snbep_cbox_put_constraint, +}; + +static struct intel_uncore_type knl_uncore_cha = { + .name = "cha", + .num_counters = 4, + .num_boxes = 38, + .perf_ctr_bits = 48, + .event_ctl = HSWEP_C0_MSR_PMON_CTL0, + .perf_ctr = HSWEP_C0_MSR_PMON_CTR0, + .event_mask = KNL_CHA_MSR_PMON_RAW_EVENT_MASK, + .box_ctl = HSWEP_C0_MSR_PMON_BOX_CTL, + .msr_offset = KNL_CHA_MSR_OFFSET, + .num_shared_regs = 1, + .constraints = knl_uncore_cha_constraints, + .ops = &knl_uncore_cha_ops, + .format_group = &knl_uncore_cha_format_group, +}; + +static struct attribute *knl_uncore_pcu_formats_attr[] = { + &format_attr_event2.attr, + &format_attr_use_occ_ctr.attr, + &format_attr_occ_sel.attr, + &format_attr_edge.attr, + &format_attr_tid_en.attr, + &format_attr_inv.attr, + &format_attr_thresh6.attr, + &format_attr_occ_invert.attr, + &format_attr_occ_edge_det.attr, + NULL, +}; + +static struct attribute_group knl_uncore_pcu_format_group = { + .name = "format", + .attrs = knl_uncore_pcu_formats_attr, +}; + +static struct intel_uncore_type knl_uncore_pcu = { + .name = "pcu", + .num_counters = 4, + .num_boxes = 1, + .perf_ctr_bits = 48, + .perf_ctr = HSWEP_PCU_MSR_PMON_CTR0, + .event_ctl = HSWEP_PCU_MSR_PMON_CTL0, + .event_mask = KNL_PCU_MSR_PMON_RAW_EVENT_MASK, + .box_ctl = HSWEP_PCU_MSR_PMON_BOX_CTL, + .ops = &snbep_uncore_msr_ops, + .format_group = &knl_uncore_pcu_format_group, +}; + +static struct intel_uncore_type *knl_msr_uncores[] = { + &knl_uncore_ubox, + &knl_uncore_cha, + &knl_uncore_pcu, + NULL, +}; + +void knl_uncore_cpu_init(void) +{ + uncore_msr_uncores = knl_msr_uncores; +} + +static void knl_uncore_imc_enable_box(struct intel_uncore_box *box) +{ + struct pci_dev *pdev = box->pci_dev; + int box_ctl = uncore_pci_box_ctl(box); + + pci_write_config_dword(pdev, box_ctl, 0); +} + +static void knl_uncore_imc_enable_event(struct intel_uncore_box *box, + struct perf_event *event) +{ + struct pci_dev *pdev = box->pci_dev; + struct hw_perf_event *hwc = &event->hw; + + if ((event->attr.config & SNBEP_PMON_CTL_EV_SEL_MASK) + == UNCORE_FIXED_EVENT) + pci_write_config_dword(pdev, hwc->config_base, + hwc->config | KNL_PMON_FIXED_CTL_EN); + else + pci_write_config_dword(pdev, hwc->config_base, + hwc->config | SNBEP_PMON_CTL_EN); +} + +static struct intel_uncore_ops knl_uncore_imc_ops = { + .init_box = snbep_uncore_pci_init_box, + .disable_box = snbep_uncore_pci_disable_box, + .enable_box = knl_uncore_imc_enable_box, + .read_counter = snbep_uncore_pci_read_counter, + .enable_event = knl_uncore_imc_enable_event, + .disable_event = snbep_uncore_pci_disable_event, +}; + +static struct intel_uncore_type knl_uncore_imc_uclk = { + .name = "imc_uclk", + .num_counters = 4, + .num_boxes = 2, + .perf_ctr_bits = 48, + .fixed_ctr_bits = 48, + .perf_ctr = KNL_UCLK_MSR_PMON_CTR0_LOW, + .event_ctl = KNL_UCLK_MSR_PMON_CTL0, + .event_mask = SNBEP_PMON_RAW_EVENT_MASK, + .fixed_ctr = KNL_UCLK_MSR_PMON_UCLK_FIXED_LOW, + .fixed_ctl = KNL_UCLK_MSR_PMON_UCLK_FIXED_CTL, + .box_ctl = KNL_UCLK_MSR_PMON_BOX_CTL, + .ops = &knl_uncore_imc_ops, + .format_group = &snbep_uncore_format_group, +}; + +static struct intel_uncore_type knl_uncore_imc_dclk = { + .name = "imc", + .num_counters = 4, + .num_boxes = 6, + .perf_ctr_bits = 48, + .fixed_ctr_bits = 48, + .perf_ctr = KNL_MC0_CH0_MSR_PMON_CTR0_LOW, + .event_ctl = KNL_MC0_CH0_MSR_PMON_CTL0, + .event_mask = SNBEP_PMON_RAW_EVENT_MASK, + .fixed_ctr = KNL_MC0_CH0_MSR_PMON_FIXED_LOW, + .fixed_ctl = KNL_MC0_CH0_MSR_PMON_FIXED_CTL, + .box_ctl = KNL_MC0_CH0_MSR_PMON_BOX_CTL, + .ops = &knl_uncore_imc_ops, + .format_group = &snbep_uncore_format_group, +}; + +static struct intel_uncore_type knl_uncore_edc_uclk = { + .name = "edc_uclk", + .num_counters = 4, + .num_boxes = 8, + .perf_ctr_bits = 48, + .fixed_ctr_bits = 48, + .perf_ctr = KNL_UCLK_MSR_PMON_CTR0_LOW, + .event_ctl = KNL_UCLK_MSR_PMON_CTL0, + .event_mask = SNBEP_PMON_RAW_EVENT_MASK, + .fixed_ctr = KNL_UCLK_MSR_PMON_UCLK_FIXED_LOW, + .fixed_ctl = KNL_UCLK_MSR_PMON_UCLK_FIXED_CTL, + .box_ctl = KNL_UCLK_MSR_PMON_BOX_CTL, + .ops = &knl_uncore_imc_ops, + .format_group = &snbep_uncore_format_group, +}; + +static struct intel_uncore_type knl_uncore_edc_eclk = { + .name = "edc_eclk", + .num_counters = 4, + .num_boxes = 8, + .perf_ctr_bits = 48, + .fixed_ctr_bits = 48, + .perf_ctr = KNL_EDC0_ECLK_MSR_PMON_CTR0_LOW, + .event_ctl = KNL_EDC0_ECLK_MSR_PMON_CTL0, + .event_mask = SNBEP_PMON_RAW_EVENT_MASK, + .fixed_ctr = KNL_EDC0_ECLK_MSR_PMON_ECLK_FIXED_LOW, + .fixed_ctl = KNL_EDC0_ECLK_MSR_PMON_ECLK_FIXED_CTL, + .box_ctl = KNL_EDC0_ECLK_MSR_PMON_BOX_CTL, + .ops = &knl_uncore_imc_ops, + .format_group = &snbep_uncore_format_group, +}; + +static struct event_constraint knl_uncore_m2pcie_constraints[] = { + UNCORE_EVENT_CONSTRAINT(0x23, 0x3), + EVENT_CONSTRAINT_END +}; + +static struct intel_uncore_type knl_uncore_m2pcie = { + .name = "m2pcie", + .num_counters = 4, + .num_boxes = 1, + .perf_ctr_bits = 48, + .constraints = knl_uncore_m2pcie_constraints, + SNBEP_UNCORE_PCI_COMMON_INIT(), +}; + +static struct attribute *knl_uncore_irp_formats_attr[] = { + &format_attr_event.attr, + &format_attr_umask.attr, + &format_attr_qor.attr, + &format_attr_edge.attr, + &format_attr_inv.attr, + &format_attr_thresh8.attr, + NULL, +}; + +static struct attribute_group knl_uncore_irp_format_group = { + .name = "format", + .attrs = knl_uncore_irp_formats_attr, +}; + +static struct intel_uncore_type knl_uncore_irp = { + .name = "irp", + .num_counters = 2, + .num_boxes = 1, + .perf_ctr_bits = 48, + .perf_ctr = SNBEP_PCI_PMON_CTR0, + .event_ctl = SNBEP_PCI_PMON_CTL0, + .event_mask = KNL_IRP_PCI_PMON_RAW_EVENT_MASK, + .box_ctl = KNL_IRP_PCI_PMON_BOX_CTL, + .ops = &snbep_uncore_pci_ops, + .format_group = &knl_uncore_irp_format_group, +}; + +enum { + KNL_PCI_UNCORE_MC_UCLK, + KNL_PCI_UNCORE_MC_DCLK, + KNL_PCI_UNCORE_EDC_UCLK, + KNL_PCI_UNCORE_EDC_ECLK, + KNL_PCI_UNCORE_M2PCIE, + KNL_PCI_UNCORE_IRP, +}; + +static struct intel_uncore_type *knl_pci_uncores[] = { + [KNL_PCI_UNCORE_MC_UCLK] = &knl_uncore_imc_uclk, + [KNL_PCI_UNCORE_MC_DCLK] = &knl_uncore_imc_dclk, + [KNL_PCI_UNCORE_EDC_UCLK] = &knl_uncore_edc_uclk, + [KNL_PCI_UNCORE_EDC_ECLK] = &knl_uncore_edc_eclk, + [KNL_PCI_UNCORE_M2PCIE] = &knl_uncore_m2pcie, + [KNL_PCI_UNCORE_IRP] = &knl_uncore_irp, + NULL, +}; + +/* + * KNL uses a common PCI device ID for multiple instances of an Uncore PMU + * device type. prior to KNL, each instance of a PMU device type had a unique + * device ID. + * + * PCI Device ID Uncore PMU Devices + * ---------------------------------- + * 0x7841 MC0 UClk, MC1 UClk + * 0x7843 MC0 DClk CH 0, MC0 DClk CH 1, MC0 DClk CH 2, + * MC1 DClk CH 0, MC1 DClk CH 1, MC1 DClk CH 2 + * 0x7833 EDC0 UClk, EDC1 UClk, EDC2 UClk, EDC3 UClk, + * EDC4 UClk, EDC5 UClk, EDC6 UClk, EDC7 UClk + * 0x7835 EDC0 EClk, EDC1 EClk, EDC2 EClk, EDC3 EClk, + * EDC4 EClk, EDC5 EClk, EDC6 EClk, EDC7 EClk + * 0x7817 M2PCIe + * 0x7814 IRP +*/ + +static const struct pci_device_id knl_uncore_pci_ids[] = { + { /* MC UClk */ + PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x7841), + .driver_data = UNCORE_PCI_DEV_DATA(KNL_PCI_UNCORE_MC_UCLK, 0), + }, + { /* MC DClk Channel */ + PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x7843), + .driver_data = UNCORE_PCI_DEV_DATA(KNL_PCI_UNCORE_MC_DCLK, 0), + }, + { /* EDC UClk */ + PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x7833), + .driver_data = UNCORE_PCI_DEV_DATA(KNL_PCI_UNCORE_EDC_UCLK, 0), + }, + { /* EDC EClk */ + PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x7835), + .driver_data = UNCORE_PCI_DEV_DATA(KNL_PCI_UNCORE_EDC_ECLK, 0), + }, + { /* M2PCIe */ + PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x7817), + .driver_data = UNCORE_PCI_DEV_DATA(KNL_PCI_UNCORE_M2PCIE, 0), + }, + { /* IRP */ + PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x7814), + .driver_data = UNCORE_PCI_DEV_DATA(KNL_PCI_UNCORE_IRP, 0), + }, + { /* end: all zeroes */ } +}; + +static struct pci_driver knl_uncore_pci_driver = { + .name = "knl_uncore", + .id_table = knl_uncore_pci_ids, +}; + +int knl_uncore_pci_init(void) +{ + int ret; + + /* All KNL PCI based PMON units are on the same PCI bus except IRP */ + ret = snb_pci2phy_map_init(0x7814); /* IRP */ + if (ret) + return ret; + ret = snb_pci2phy_map_init(0x7817); /* M2PCIe */ + if (ret) + return ret; + uncore_pci_uncores = knl_pci_uncores; + uncore_pci_driver = &knl_uncore_pci_driver; + return 0; +} + +/* end of KNL uncore support */ + /* Haswell-EP uncore support */ static struct attribute *hswep_uncore_ubox_formats_attr[] = { &format_attr_event.attr, @@ -2338,7 +2819,7 @@ int hswep_uncore_pci_init(void) } /* end of Haswell-EP uncore support */ -/* BDX-DE uncore support */ +/* BDX uncore support */ static struct intel_uncore_type bdx_uncore_ubox = { .name = "ubox", @@ -2360,13 +2841,14 @@ static struct event_constraint bdx_uncore_cbox_constraints[] = { UNCORE_EVENT_CONSTRAINT(0x09, 0x3), UNCORE_EVENT_CONSTRAINT(0x11, 0x1), UNCORE_EVENT_CONSTRAINT(0x36, 0x1), + UNCORE_EVENT_CONSTRAINT(0x3e, 0x1), EVENT_CONSTRAINT_END }; static struct intel_uncore_type bdx_uncore_cbox = { .name = "cbox", .num_counters = 4, - .num_boxes = 8, + .num_boxes = 24, .perf_ctr_bits = 48, .event_ctl = HSWEP_C0_MSR_PMON_CTL0, .perf_ctr = HSWEP_C0_MSR_PMON_CTR0, @@ -2379,9 +2861,24 @@ static struct intel_uncore_type bdx_uncore_cbox = { .format_group = &hswep_uncore_cbox_format_group, }; +static struct intel_uncore_type bdx_uncore_sbox = { + .name = "sbox", + .num_counters = 4, + .num_boxes = 4, + .perf_ctr_bits = 48, + .event_ctl = HSWEP_S0_MSR_PMON_CTL0, + .perf_ctr = HSWEP_S0_MSR_PMON_CTR0, + .event_mask = HSWEP_S_MSR_PMON_RAW_EVENT_MASK, + .box_ctl = HSWEP_S0_MSR_PMON_BOX_CTL, + .msr_offset = HSWEP_SBOX_MSR_OFFSET, + .ops = &hswep_uncore_sbox_msr_ops, + .format_group = &hswep_uncore_sbox_format_group, +}; + static struct intel_uncore_type *bdx_msr_uncores[] = { &bdx_uncore_ubox, &bdx_uncore_cbox, + &bdx_uncore_sbox, &hswep_uncore_pcu, NULL, }; @@ -2396,7 +2893,7 @@ void bdx_uncore_cpu_init(void) static struct intel_uncore_type bdx_uncore_ha = { .name = "ha", .num_counters = 4, - .num_boxes = 1, + .num_boxes = 2, .perf_ctr_bits = 48, SNBEP_UNCORE_PCI_COMMON_INIT(), }; @@ -2404,7 +2901,7 @@ static struct intel_uncore_type bdx_uncore_ha = { static struct intel_uncore_type bdx_uncore_imc = { .name = "imc", .num_counters = 5, - .num_boxes = 2, + .num_boxes = 8, .perf_ctr_bits = 48, .fixed_ctr_bits = 48, .fixed_ctr = SNBEP_MC_CHy_PCI_PMON_FIXED_CTR, @@ -2424,6 +2921,19 @@ static struct intel_uncore_type bdx_uncore_irp = { .format_group = &snbep_uncore_format_group, }; +static struct intel_uncore_type bdx_uncore_qpi = { + .name = "qpi", + .num_counters = 4, + .num_boxes = 3, + .perf_ctr_bits = 48, + .perf_ctr = SNBEP_PCI_PMON_CTR0, + .event_ctl = SNBEP_PCI_PMON_CTL0, + .event_mask = SNBEP_QPI_PCI_PMON_RAW_EVENT_MASK, + .box_ctl = SNBEP_PCI_PMON_BOX_CTL, + .num_shared_regs = 1, + .ops = &snbep_uncore_qpi_ops, + .format_group = &snbep_uncore_qpi_format_group, +}; static struct event_constraint bdx_uncore_r2pcie_constraints[] = { UNCORE_EVENT_CONSTRAINT(0x10, 0x3), @@ -2432,6 +2942,8 @@ static struct event_constraint bdx_uncore_r2pcie_constraints[] = { UNCORE_EVENT_CONSTRAINT(0x23, 0x1), UNCORE_EVENT_CONSTRAINT(0x25, 0x1), UNCORE_EVENT_CONSTRAINT(0x26, 0x3), + UNCORE_EVENT_CONSTRAINT(0x28, 0x3), + UNCORE_EVENT_CONSTRAINT(0x2c, 0x3), UNCORE_EVENT_CONSTRAINT(0x2d, 0x3), EVENT_CONSTRAINT_END }; @@ -2445,18 +2957,65 @@ static struct intel_uncore_type bdx_uncore_r2pcie = { SNBEP_UNCORE_PCI_COMMON_INIT(), }; +static struct event_constraint bdx_uncore_r3qpi_constraints[] = { + UNCORE_EVENT_CONSTRAINT(0x01, 0x7), + UNCORE_EVENT_CONSTRAINT(0x07, 0x7), + UNCORE_EVENT_CONSTRAINT(0x08, 0x7), + UNCORE_EVENT_CONSTRAINT(0x09, 0x7), + UNCORE_EVENT_CONSTRAINT(0x0a, 0x7), + UNCORE_EVENT_CONSTRAINT(0x0e, 0x7), + UNCORE_EVENT_CONSTRAINT(0x10, 0x3), + UNCORE_EVENT_CONSTRAINT(0x11, 0x3), + UNCORE_EVENT_CONSTRAINT(0x13, 0x1), + UNCORE_EVENT_CONSTRAINT(0x14, 0x3), + UNCORE_EVENT_CONSTRAINT(0x15, 0x3), + UNCORE_EVENT_CONSTRAINT(0x1f, 0x3), + UNCORE_EVENT_CONSTRAINT(0x20, 0x3), + UNCORE_EVENT_CONSTRAINT(0x21, 0x3), + UNCORE_EVENT_CONSTRAINT(0x22, 0x3), + UNCORE_EVENT_CONSTRAINT(0x23, 0x3), + UNCORE_EVENT_CONSTRAINT(0x25, 0x3), + UNCORE_EVENT_CONSTRAINT(0x26, 0x3), + UNCORE_EVENT_CONSTRAINT(0x28, 0x3), + UNCORE_EVENT_CONSTRAINT(0x29, 0x3), + UNCORE_EVENT_CONSTRAINT(0x2c, 0x3), + UNCORE_EVENT_CONSTRAINT(0x2d, 0x3), + UNCORE_EVENT_CONSTRAINT(0x2e, 0x3), + UNCORE_EVENT_CONSTRAINT(0x2f, 0x3), + UNCORE_EVENT_CONSTRAINT(0x33, 0x3), + UNCORE_EVENT_CONSTRAINT(0x34, 0x3), + UNCORE_EVENT_CONSTRAINT(0x36, 0x3), + UNCORE_EVENT_CONSTRAINT(0x37, 0x3), + UNCORE_EVENT_CONSTRAINT(0x38, 0x3), + UNCORE_EVENT_CONSTRAINT(0x39, 0x3), + EVENT_CONSTRAINT_END +}; + +static struct intel_uncore_type bdx_uncore_r3qpi = { + .name = "r3qpi", + .num_counters = 3, + .num_boxes = 3, + .perf_ctr_bits = 48, + .constraints = bdx_uncore_r3qpi_constraints, + SNBEP_UNCORE_PCI_COMMON_INIT(), +}; + enum { BDX_PCI_UNCORE_HA, BDX_PCI_UNCORE_IMC, BDX_PCI_UNCORE_IRP, + BDX_PCI_UNCORE_QPI, BDX_PCI_UNCORE_R2PCIE, + BDX_PCI_UNCORE_R3QPI, }; static struct intel_uncore_type *bdx_pci_uncores[] = { [BDX_PCI_UNCORE_HA] = &bdx_uncore_ha, [BDX_PCI_UNCORE_IMC] = &bdx_uncore_imc, [BDX_PCI_UNCORE_IRP] = &bdx_uncore_irp, + [BDX_PCI_UNCORE_QPI] = &bdx_uncore_qpi, [BDX_PCI_UNCORE_R2PCIE] = &bdx_uncore_r2pcie, + [BDX_PCI_UNCORE_R3QPI] = &bdx_uncore_r3qpi, NULL, }; @@ -2465,6 +3024,10 @@ static const struct pci_device_id bdx_uncore_pci_ids[] = { PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x6f30), .driver_data = UNCORE_PCI_DEV_DATA(BDX_PCI_UNCORE_HA, 0), }, + { /* Home Agent 1 */ + PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x6f38), + .driver_data = UNCORE_PCI_DEV_DATA(BDX_PCI_UNCORE_HA, 1), + }, { /* MC0 Channel 0 */ PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x6fb0), .driver_data = UNCORE_PCI_DEV_DATA(BDX_PCI_UNCORE_IMC, 0), @@ -2473,14 +3036,74 @@ static const struct pci_device_id bdx_uncore_pci_ids[] = { PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x6fb1), .driver_data = UNCORE_PCI_DEV_DATA(BDX_PCI_UNCORE_IMC, 1), }, + { /* MC0 Channel 2 */ + PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x6fb4), + .driver_data = UNCORE_PCI_DEV_DATA(BDX_PCI_UNCORE_IMC, 2), + }, + { /* MC0 Channel 3 */ + PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x6fb5), + .driver_data = UNCORE_PCI_DEV_DATA(BDX_PCI_UNCORE_IMC, 3), + }, + { /* MC1 Channel 0 */ + PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x6fd0), + .driver_data = UNCORE_PCI_DEV_DATA(BDX_PCI_UNCORE_IMC, 4), + }, + { /* MC1 Channel 1 */ + PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x6fd1), + .driver_data = UNCORE_PCI_DEV_DATA(BDX_PCI_UNCORE_IMC, 5), + }, + { /* MC1 Channel 2 */ + PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x6fd4), + .driver_data = UNCORE_PCI_DEV_DATA(BDX_PCI_UNCORE_IMC, 6), + }, + { /* MC1 Channel 3 */ + PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x6fd5), + .driver_data = UNCORE_PCI_DEV_DATA(BDX_PCI_UNCORE_IMC, 7), + }, { /* IRP */ PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x6f39), .driver_data = UNCORE_PCI_DEV_DATA(BDX_PCI_UNCORE_IRP, 0), }, + { /* QPI0 Port 0 */ + PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x6f32), + .driver_data = UNCORE_PCI_DEV_DATA(BDX_PCI_UNCORE_QPI, 0), + }, + { /* QPI0 Port 1 */ + PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x6f33), + .driver_data = UNCORE_PCI_DEV_DATA(BDX_PCI_UNCORE_QPI, 1), + }, + { /* QPI1 Port 2 */ + PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x6f3a), + .driver_data = UNCORE_PCI_DEV_DATA(BDX_PCI_UNCORE_QPI, 2), + }, { /* R2PCIe */ PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x6f34), .driver_data = UNCORE_PCI_DEV_DATA(BDX_PCI_UNCORE_R2PCIE, 0), }, + { /* R3QPI0 Link 0 */ + PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x6f36), + .driver_data = UNCORE_PCI_DEV_DATA(BDX_PCI_UNCORE_R3QPI, 0), + }, + { /* R3QPI0 Link 1 */ + PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x6f37), + .driver_data = UNCORE_PCI_DEV_DATA(BDX_PCI_UNCORE_R3QPI, 1), + }, + { /* R3QPI1 Link 2 */ + PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x6f3e), + .driver_data = UNCORE_PCI_DEV_DATA(BDX_PCI_UNCORE_R3QPI, 2), + }, + { /* QPI Port 0 filter */ + PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x6f86), + .driver_data = UNCORE_PCI_DEV_DATA(UNCORE_EXTRA_PCI_DEV, 0), + }, + { /* QPI Port 1 filter */ + PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x6f96), + .driver_data = UNCORE_PCI_DEV_DATA(UNCORE_EXTRA_PCI_DEV, 1), + }, + { /* QPI Port 2 filter */ + PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x6f46), + .driver_data = UNCORE_PCI_DEV_DATA(UNCORE_EXTRA_PCI_DEV, 2), + }, { /* end: all zeroes */ } }; @@ -2500,4 +3123,4 @@ int bdx_uncore_pci_init(void) return 0; } -/* end of BDX-DE uncore support */ +/* end of BDX uncore support */ diff --git a/arch/x86/kernel/cpu/rdrand.c b/arch/x86/kernel/cpu/rdrand.c index 136ac74dee82..819d94982e07 100644 --- a/arch/x86/kernel/cpu/rdrand.c +++ b/arch/x86/kernel/cpu/rdrand.c @@ -33,28 +33,27 @@ static int __init x86_rdrand_setup(char *s) __setup("nordrand", x86_rdrand_setup); /* - * Force a reseed cycle; we are architecturally guaranteed a reseed - * after no more than 512 128-bit chunks of random data. This also - * acts as a test of the CPU capability. + * RDRAND has Built-In-Self-Test (BIST) that runs on every invocation. + * Run the instruction a few times as a sanity check. + * If it fails, it is simple to disable RDRAND here. */ -#define RESEED_LOOP ((512*128)/sizeof(unsigned long)) +#define SANITY_CHECK_LOOPS 8 void x86_init_rdrand(struct cpuinfo_x86 *c) { #ifdef CONFIG_ARCH_RANDOM unsigned long tmp; - int i, count, ok; + int i; if (!cpu_has(c, X86_FEATURE_RDRAND)) - return; /* Nothing to do */ + return; - for (count = i = 0; i < RESEED_LOOP; i++) { - ok = rdrand_long(&tmp); - if (ok) - count++; + for (i = 0; i < SANITY_CHECK_LOOPS; i++) { + if (!rdrand_long(&tmp)) { + clear_cpu_cap(c, X86_FEATURE_RDRAND); + printk_once(KERN_WARNING "rdrand: disabled\n"); + return; + } } - - if (count != RESEED_LOOP) - clear_cpu_cap(c, X86_FEATURE_RDRAND); #endif } diff --git a/arch/x86/kernel/cpu/scattered.c b/arch/x86/kernel/cpu/scattered.c index 608fb26c7254..8cb57df9398d 100644 --- a/arch/x86/kernel/cpu/scattered.c +++ b/arch/x86/kernel/cpu/scattered.c @@ -31,32 +31,12 @@ void init_scattered_cpuid_features(struct cpuinfo_x86 *c) const struct cpuid_bit *cb; static const struct cpuid_bit cpuid_bits[] = { - { X86_FEATURE_DTHERM, CR_EAX, 0, 0x00000006, 0 }, - { X86_FEATURE_IDA, CR_EAX, 1, 0x00000006, 0 }, - { X86_FEATURE_ARAT, CR_EAX, 2, 0x00000006, 0 }, - { X86_FEATURE_PLN, CR_EAX, 4, 0x00000006, 0 }, - { X86_FEATURE_PTS, CR_EAX, 6, 0x00000006, 0 }, - { X86_FEATURE_HWP, CR_EAX, 7, 0x00000006, 0 }, - { X86_FEATURE_HWP_NOTIFY, CR_EAX, 8, 0x00000006, 0 }, - { X86_FEATURE_HWP_ACT_WINDOW, CR_EAX, 9, 0x00000006, 0 }, - { X86_FEATURE_HWP_EPP, CR_EAX,10, 0x00000006, 0 }, - { X86_FEATURE_HWP_PKG_REQ, CR_EAX,11, 0x00000006, 0 }, { X86_FEATURE_INTEL_PT, CR_EBX,25, 0x00000007, 0 }, { X86_FEATURE_APERFMPERF, CR_ECX, 0, 0x00000006, 0 }, { X86_FEATURE_EPB, CR_ECX, 3, 0x00000006, 0 }, { X86_FEATURE_HW_PSTATE, CR_EDX, 7, 0x80000007, 0 }, { X86_FEATURE_CPB, CR_EDX, 9, 0x80000007, 0 }, { X86_FEATURE_PROC_FEEDBACK, CR_EDX,11, 0x80000007, 0 }, - { X86_FEATURE_NPT, CR_EDX, 0, 0x8000000a, 0 }, - { X86_FEATURE_LBRV, CR_EDX, 1, 0x8000000a, 0 }, - { X86_FEATURE_SVML, CR_EDX, 2, 0x8000000a, 0 }, - { X86_FEATURE_NRIPS, CR_EDX, 3, 0x8000000a, 0 }, - { X86_FEATURE_TSCRATEMSR, CR_EDX, 4, 0x8000000a, 0 }, - { X86_FEATURE_VMCBCLEAN, CR_EDX, 5, 0x8000000a, 0 }, - { X86_FEATURE_FLUSHBYASID, CR_EDX, 6, 0x8000000a, 0 }, - { X86_FEATURE_DECODEASSISTS, CR_EDX, 7, 0x8000000a, 0 }, - { X86_FEATURE_PAUSEFILTER, CR_EDX,10, 0x8000000a, 0 }, - { X86_FEATURE_PFTHRESHOLD, CR_EDX,12, 0x8000000a, 0 }, { 0, 0, 0, 0, 0 } }; diff --git a/arch/x86/kernel/cpu/transmeta.c b/arch/x86/kernel/cpu/transmeta.c index 3fa0e5ad86b4..252da7aceca6 100644 --- a/arch/x86/kernel/cpu/transmeta.c +++ b/arch/x86/kernel/cpu/transmeta.c @@ -12,7 +12,7 @@ static void early_init_transmeta(struct cpuinfo_x86 *c) xlvl = cpuid_eax(0x80860000); if ((xlvl & 0xffff0000) == 0x80860000) { if (xlvl >= 0x80860001) - c->x86_capability[2] = cpuid_edx(0x80860001); + c->x86_capability[CPUID_8086_0001_EDX] = cpuid_edx(0x80860001); } } @@ -82,7 +82,7 @@ static void init_transmeta(struct cpuinfo_x86 *c) /* Unhide possibly hidden capability flags */ rdmsr(0x80860004, cap_mask, uk); wrmsr(0x80860004, ~0, uk); - c->x86_capability[0] = cpuid_edx(0x00000001); + c->x86_capability[CPUID_1_EDX] = cpuid_edx(0x00000001); wrmsr(0x80860004, cap_mask, uk); /* All Transmeta CPUs have a constant TSC */ diff --git a/arch/x86/kernel/crash.c b/arch/x86/kernel/crash.c index 2c1910f6717e..58f34319b29a 100644 --- a/arch/x86/kernel/crash.c +++ b/arch/x86/kernel/crash.c @@ -35,6 +35,7 @@ #include <asm/cpu.h> #include <asm/reboot.h> #include <asm/virtext.h> +#include <asm/intel_pt.h> /* Alignment required for elf header segment */ #define ELF_CORE_HEADER_ALIGN 4096 @@ -125,6 +126,11 @@ static void kdump_nmi_callback(int cpu, struct pt_regs *regs) cpu_emergency_vmxoff(); cpu_emergency_svm_disable(); + /* + * Disable Intel PT to stop its logging + */ + cpu_emergency_stop_pt(); + disable_local_APIC(); } @@ -169,6 +175,11 @@ void native_machine_crash_shutdown(struct pt_regs *regs) cpu_emergency_vmxoff(); cpu_emergency_svm_disable(); + /* + * Disable Intel PT to stop its logging + */ + cpu_emergency_stop_pt(); + #ifdef CONFIG_X86_IO_APIC /* Prevent crash_kexec() from deadlocking on ioapic_lock. */ ioapic_zap_locks(); diff --git a/arch/x86/kernel/fpu/init.c b/arch/x86/kernel/fpu/init.c index be39b5fde4b9..7b2978ab30df 100644 --- a/arch/x86/kernel/fpu/init.c +++ b/arch/x86/kernel/fpu/init.c @@ -12,7 +12,7 @@ */ static void fpu__init_cpu_ctx_switch(void) { - if (!cpu_has_eager_fpu) + if (!boot_cpu_has(X86_FEATURE_EAGER_FPU)) stts(); else clts(); @@ -143,9 +143,18 @@ static void __init fpu__init_system_generic(void) unsigned int xstate_size; EXPORT_SYMBOL_GPL(xstate_size); -/* Enforce that 'MEMBER' is the last field of 'TYPE': */ +/* Get alignment of the TYPE. */ +#define TYPE_ALIGN(TYPE) offsetof(struct { char x; TYPE test; }, test) + +/* + * Enforce that 'MEMBER' is the last field of 'TYPE'. + * + * Align the computed size with alignment of the TYPE, + * because that's how C aligns structs. + */ #define CHECK_MEMBER_AT_END_OF(TYPE, MEMBER) \ - BUILD_BUG_ON(sizeof(TYPE) != offsetofend(TYPE, MEMBER)) + BUILD_BUG_ON(sizeof(TYPE) != ALIGN(offsetofend(TYPE, MEMBER), \ + TYPE_ALIGN(TYPE))) /* * We append the 'struct fpu' to the task_struct: @@ -188,7 +197,7 @@ static void __init fpu__init_task_struct_size(void) */ static void __init fpu__init_system_xstate_size_legacy(void) { - static int on_boot_cpu = 1; + static int on_boot_cpu __initdata = 1; WARN_ON_FPU(!on_boot_cpu); on_boot_cpu = 0; @@ -278,7 +287,7 @@ __setup("eagerfpu=", eager_fpu_setup); */ static void __init fpu__init_system_ctx_switch(void) { - static bool on_boot_cpu = 1; + static bool on_boot_cpu __initdata = 1; WARN_ON_FPU(!on_boot_cpu); on_boot_cpu = 0; @@ -287,7 +296,7 @@ static void __init fpu__init_system_ctx_switch(void) current_thread_info()->status = 0; /* Auto enable eagerfpu for xsaveopt */ - if (cpu_has_xsaveopt && eagerfpu != DISABLE) + if (boot_cpu_has(X86_FEATURE_XSAVEOPT) && eagerfpu != DISABLE) eagerfpu = ENABLE; if (xfeatures_mask & XFEATURE_MASK_EAGER) { diff --git a/arch/x86/kernel/fpu/signal.c b/arch/x86/kernel/fpu/signal.c index ef29b742cea7..31c6a60505e6 100644 --- a/arch/x86/kernel/fpu/signal.c +++ b/arch/x86/kernel/fpu/signal.c @@ -385,20 +385,19 @@ fpu__alloc_mathframe(unsigned long sp, int ia32_frame, */ void fpu__init_prepare_fx_sw_frame(void) { - int fsave_header_size = sizeof(struct fregs_state); int size = xstate_size + FP_XSTATE_MAGIC2_SIZE; - if (config_enabled(CONFIG_X86_32)) - size += fsave_header_size; - fx_sw_reserved.magic1 = FP_XSTATE_MAGIC1; fx_sw_reserved.extended_size = size; fx_sw_reserved.xfeatures = xfeatures_mask; fx_sw_reserved.xstate_size = xstate_size; - if (config_enabled(CONFIG_IA32_EMULATION)) { + if (config_enabled(CONFIG_IA32_EMULATION) || + config_enabled(CONFIG_X86_32)) { + int fsave_header_size = sizeof(struct fregs_state); + fx_sw_reserved_ia32 = fx_sw_reserved; - fx_sw_reserved_ia32.extended_size += fsave_header_size; + fx_sw_reserved_ia32.extended_size = size + fsave_header_size; } } diff --git a/arch/x86/kernel/fpu/xstate.c b/arch/x86/kernel/fpu/xstate.c index 6454f2731b56..40f100285984 100644 --- a/arch/x86/kernel/fpu/xstate.c +++ b/arch/x86/kernel/fpu/xstate.c @@ -297,7 +297,7 @@ static void __init setup_xstate_comp(void) */ static void __init setup_init_fpu_buf(void) { - static int on_boot_cpu = 1; + static int on_boot_cpu __initdata = 1; WARN_ON_FPU(!on_boot_cpu); on_boot_cpu = 0; @@ -608,7 +608,7 @@ static void fpu__init_disable_system_xstate(void) void __init fpu__init_system_xstate(void) { unsigned int eax, ebx, ecx, edx; - static int on_boot_cpu = 1; + static int on_boot_cpu __initdata = 1; int err; WARN_ON_FPU(!on_boot_cpu); @@ -694,7 +694,6 @@ void *get_xsave_addr(struct xregs_state *xsave, int xstate_feature) if (!boot_cpu_has(X86_FEATURE_XSAVE)) return NULL; - xsave = ¤t->thread.fpu.state.xsave; /* * We should not ever be requesting features that we * have not enabled. Remember that pcntxt_mask is diff --git a/arch/x86/kernel/hw_breakpoint.c b/arch/x86/kernel/hw_breakpoint.c index 50a3fad5b89f..2bcfb5f2bc44 100644 --- a/arch/x86/kernel/hw_breakpoint.c +++ b/arch/x86/kernel/hw_breakpoint.c @@ -300,6 +300,10 @@ static int arch_build_bp_info(struct perf_event *bp) return -EINVAL; if (bp->attr.bp_addr & (bp->attr.bp_len - 1)) return -EINVAL; + + if (!boot_cpu_has(X86_FEATURE_BPEXT)) + return -EOPNOTSUPP; + /* * It's impossible to use a range breakpoint to fake out * user vs kernel detection because bp_len - 1 can't @@ -307,8 +311,6 @@ static int arch_build_bp_info(struct perf_event *bp) * breakpoints, then we'll have to check for kprobe-blacklisted * addresses anywhere in the range. */ - if (!cpu_has_bpext) - return -EOPNOTSUPP; info->mask = bp->attr.bp_len - 1; info->len = X86_BREAKPOINT_LEN_1; } diff --git a/arch/x86/kernel/irq_work.c b/arch/x86/kernel/irq_work.c index dc5fa6a1e8d6..3512ba607361 100644 --- a/arch/x86/kernel/irq_work.c +++ b/arch/x86/kernel/irq_work.c @@ -1,7 +1,7 @@ /* * x86 specific code for irq_work * - * Copyright (C) 2010 Red Hat, Inc., Peter Zijlstra <pzijlstr@redhat.com> + * Copyright (C) 2010 Red Hat, Inc., Peter Zijlstra */ #include <linux/kernel.h> diff --git a/arch/x86/kernel/kvmclock.c b/arch/x86/kernel/kvmclock.c index 2bd81e302427..72cef58693c7 100644 --- a/arch/x86/kernel/kvmclock.c +++ b/arch/x86/kernel/kvmclock.c @@ -45,6 +45,11 @@ early_param("no-kvmclock", parse_no_kvmclock); static struct pvclock_vsyscall_time_info *hv_clock; static struct pvclock_wall_clock wall_clock; +struct pvclock_vsyscall_time_info *pvclock_pvti_cpu0_va(void) +{ + return hv_clock; +} + /* * The wallclock is the time of day when we booted. Since then, some time may * have elapsed since the hypervisor wrote the data. So we try to account for @@ -305,7 +310,6 @@ int __init kvm_setup_vsyscall_timeinfo(void) { #ifdef CONFIG_X86_64 int cpu; - int ret; u8 flags; struct pvclock_vcpu_time_info *vcpu_time; unsigned int size; @@ -325,11 +329,6 @@ int __init kvm_setup_vsyscall_timeinfo(void) return 1; } - if ((ret = pvclock_init_vsyscall(hv_clock, size))) { - put_cpu(); - return ret; - } - put_cpu(); kvm_clock.archdata.vclock_mode = VCLOCK_PVCLOCK; diff --git a/arch/x86/kernel/mcount_64.S b/arch/x86/kernel/mcount_64.S index 94ea120fa21f..87e1762e2bca 100644 --- a/arch/x86/kernel/mcount_64.S +++ b/arch/x86/kernel/mcount_64.S @@ -278,6 +278,12 @@ trace: /* save_mcount_regs fills in first two parameters */ save_mcount_regs + /* + * When DYNAMIC_FTRACE is not defined, ARCH_SUPPORTS_FTRACE_OPS is not + * set (see include/asm/ftrace.h and include/linux/ftrace.h). Only the + * ip and parent ip are used and the list function is called when + * function tracing is enabled. + */ call *ftrace_trace_function restore_mcount_regs diff --git a/arch/x86/kernel/nmi.c b/arch/x86/kernel/nmi.c index 697f90db0e37..8a2cdd736fa4 100644 --- a/arch/x86/kernel/nmi.c +++ b/arch/x86/kernel/nmi.c @@ -29,6 +29,7 @@ #include <asm/mach_traps.h> #include <asm/nmi.h> #include <asm/x86_init.h> +#include <asm/reboot.h> #define CREATE_TRACE_POINTS #include <trace/events/nmi.h> @@ -231,7 +232,7 @@ pci_serr_error(unsigned char reason, struct pt_regs *regs) #endif if (panic_on_unrecovered_nmi) - panic("NMI: Not continuing"); + nmi_panic(regs, "NMI: Not continuing"); pr_emerg("Dazed and confused, but trying to continue\n"); @@ -255,8 +256,16 @@ io_check_error(unsigned char reason, struct pt_regs *regs) reason, smp_processor_id()); show_regs(regs); - if (panic_on_io_nmi) - panic("NMI IOCK error: Not continuing"); + if (panic_on_io_nmi) { + nmi_panic(regs, "NMI IOCK error: Not continuing"); + + /* + * If we end up here, it means we have received an NMI while + * processing panic(). Simply return without delaying and + * re-enabling NMIs. + */ + return; + } /* Re-enable the IOCK line, wait for a few seconds */ reason = (reason & NMI_REASON_CLEAR_MASK) | NMI_REASON_CLEAR_IOCHK; @@ -297,7 +306,7 @@ unknown_nmi_error(unsigned char reason, struct pt_regs *regs) pr_emerg("Do you have a strange power saving mode enabled?\n"); if (unknown_nmi_panic || panic_on_unrecovered_nmi) - panic("NMI: Not continuing"); + nmi_panic(regs, "NMI: Not continuing"); pr_emerg("Dazed and confused, but trying to continue\n"); } @@ -348,8 +357,19 @@ static void default_do_nmi(struct pt_regs *regs) return; } - /* Non-CPU-specific NMI: NMI sources can be processed on any CPU */ - raw_spin_lock(&nmi_reason_lock); + /* + * Non-CPU-specific NMI: NMI sources can be processed on any CPU. + * + * Another CPU may be processing panic routines while holding + * nmi_reason_lock. Check if the CPU issued the IPI for crash dumping, + * and if so, call its callback directly. If there is no CPU preparing + * crash dump, we simply loop here. + */ + while (!raw_spin_trylock(&nmi_reason_lock)) { + run_crash_ipi_callback(regs); + cpu_relax(); + } + reason = x86_platform.get_nmi_reason(); if (reason & NMI_REASON_MASK) { diff --git a/arch/x86/kernel/paravirt.c b/arch/x86/kernel/paravirt.c index c2130aef3f9d..f08ac28b8136 100644 --- a/arch/x86/kernel/paravirt.c +++ b/arch/x86/kernel/paravirt.c @@ -74,16 +74,6 @@ void __init default_banner(void) /* Undefined instruction for dealing with missing ops pointers. */ static const unsigned char ud2a[] = { 0x0f, 0x0b }; -unsigned paravirt_patch_nop(void) -{ - return 0; -} - -unsigned paravirt_patch_ignore(unsigned len) -{ - return len; -} - struct branch { unsigned char opcode; u32 delta; @@ -133,7 +123,6 @@ static void *get_call_destination(u8 type) .pv_time_ops = pv_time_ops, .pv_cpu_ops = pv_cpu_ops, .pv_irq_ops = pv_irq_ops, - .pv_apic_ops = pv_apic_ops, .pv_mmu_ops = pv_mmu_ops, #ifdef CONFIG_PARAVIRT_SPINLOCKS .pv_lock_ops = pv_lock_ops, @@ -152,8 +141,7 @@ unsigned paravirt_patch_default(u8 type, u16 clobbers, void *insnbuf, /* If there's no function, patch it with a ud2a (BUG) */ ret = paravirt_patch_insns(insnbuf, len, ud2a, ud2a+sizeof(ud2a)); else if (opfunc == _paravirt_nop) - /* If the operation is a nop, then nop the callsite */ - ret = paravirt_patch_nop(); + ret = 0; /* identity functions just return their single argument */ else if (opfunc == _paravirt_ident_32) @@ -162,10 +150,6 @@ unsigned paravirt_patch_default(u8 type, u16 clobbers, void *insnbuf, ret = paravirt_patch_ident_64(insnbuf, len); else if (type == PARAVIRT_PATCH(pv_cpu_ops.iret) || -#ifdef CONFIG_X86_32 - type == PARAVIRT_PATCH(pv_cpu_ops.irq_enable_sysexit) || -#endif - type == PARAVIRT_PATCH(pv_cpu_ops.usergs_sysret32) || type == PARAVIRT_PATCH(pv_cpu_ops.usergs_sysret64)) /* If operation requires a jmp, then jmp */ ret = paravirt_patch_jmp(insnbuf, opfunc, addr, len); @@ -220,8 +204,6 @@ static u64 native_steal_clock(int cpu) /* These are in entry.S */ extern void native_iret(void); -extern void native_irq_enable_sysexit(void); -extern void native_usergs_sysret32(void); extern void native_usergs_sysret64(void); static struct resource reserve_ioports = { @@ -379,13 +361,7 @@ __visible struct pv_cpu_ops pv_cpu_ops = { .load_sp0 = native_load_sp0, -#if defined(CONFIG_X86_32) - .irq_enable_sysexit = native_irq_enable_sysexit, -#endif #ifdef CONFIG_X86_64 -#ifdef CONFIG_IA32_EMULATION - .usergs_sysret32 = native_usergs_sysret32, -#endif .usergs_sysret64 = native_usergs_sysret64, #endif .iret = native_iret, @@ -403,12 +379,6 @@ NOKPROBE_SYMBOL(native_get_debugreg); NOKPROBE_SYMBOL(native_set_debugreg); NOKPROBE_SYMBOL(native_load_idt); -struct pv_apic_ops pv_apic_ops = { -#ifdef CONFIG_X86_LOCAL_APIC - .startup_ipi_hook = paravirt_nop, -#endif -}; - #if defined(CONFIG_X86_32) && !defined(CONFIG_X86_PAE) /* 32-bit pagetable entries */ #define PTE_IDENT __PV_IS_CALLEE_SAVE(_paravirt_ident_32) @@ -444,9 +414,6 @@ struct pv_mmu_ops pv_mmu_ops = { .set_pmd = native_set_pmd, .set_pmd_at = native_set_pmd_at, .pte_update = paravirt_nop, - .pte_update_defer = paravirt_nop, - .pmd_update = paravirt_nop, - .pmd_update_defer = paravirt_nop, .ptep_modify_prot_start = __ptep_modify_prot_start, .ptep_modify_prot_commit = __ptep_modify_prot_commit, @@ -492,6 +459,5 @@ struct pv_mmu_ops pv_mmu_ops = { EXPORT_SYMBOL_GPL(pv_time_ops); EXPORT_SYMBOL (pv_cpu_ops); EXPORT_SYMBOL (pv_mmu_ops); -EXPORT_SYMBOL_GPL(pv_apic_ops); EXPORT_SYMBOL_GPL(pv_info); EXPORT_SYMBOL (pv_irq_ops); diff --git a/arch/x86/kernel/paravirt_patch_32.c b/arch/x86/kernel/paravirt_patch_32.c index c89f50a76e97..158dc0650d5d 100644 --- a/arch/x86/kernel/paravirt_patch_32.c +++ b/arch/x86/kernel/paravirt_patch_32.c @@ -5,7 +5,6 @@ DEF_NATIVE(pv_irq_ops, irq_enable, "sti"); DEF_NATIVE(pv_irq_ops, restore_fl, "push %eax; popf"); DEF_NATIVE(pv_irq_ops, save_fl, "pushf; pop %eax"); DEF_NATIVE(pv_cpu_ops, iret, "iret"); -DEF_NATIVE(pv_cpu_ops, irq_enable_sysexit, "sti; sysexit"); DEF_NATIVE(pv_mmu_ops, read_cr2, "mov %cr2, %eax"); DEF_NATIVE(pv_mmu_ops, write_cr3, "mov %eax, %cr3"); DEF_NATIVE(pv_mmu_ops, read_cr3, "mov %cr3, %eax"); @@ -46,7 +45,6 @@ unsigned native_patch(u8 type, u16 clobbers, void *ibuf, PATCH_SITE(pv_irq_ops, restore_fl); PATCH_SITE(pv_irq_ops, save_fl); PATCH_SITE(pv_cpu_ops, iret); - PATCH_SITE(pv_cpu_ops, irq_enable_sysexit); PATCH_SITE(pv_mmu_ops, read_cr2); PATCH_SITE(pv_mmu_ops, read_cr3); PATCH_SITE(pv_mmu_ops, write_cr3); diff --git a/arch/x86/kernel/paravirt_patch_64.c b/arch/x86/kernel/paravirt_patch_64.c index 8aa05583bc42..e70087a04cc8 100644 --- a/arch/x86/kernel/paravirt_patch_64.c +++ b/arch/x86/kernel/paravirt_patch_64.c @@ -13,9 +13,7 @@ DEF_NATIVE(pv_mmu_ops, flush_tlb_single, "invlpg (%rdi)"); DEF_NATIVE(pv_cpu_ops, clts, "clts"); DEF_NATIVE(pv_cpu_ops, wbinvd, "wbinvd"); -DEF_NATIVE(pv_cpu_ops, irq_enable_sysexit, "swapgs; sti; sysexit"); DEF_NATIVE(pv_cpu_ops, usergs_sysret64, "swapgs; sysretq"); -DEF_NATIVE(pv_cpu_ops, usergs_sysret32, "swapgs; sysretl"); DEF_NATIVE(pv_cpu_ops, swapgs, "swapgs"); DEF_NATIVE(, mov32, "mov %edi, %eax"); @@ -55,7 +53,6 @@ unsigned native_patch(u8 type, u16 clobbers, void *ibuf, PATCH_SITE(pv_irq_ops, save_fl); PATCH_SITE(pv_irq_ops, irq_enable); PATCH_SITE(pv_irq_ops, irq_disable); - PATCH_SITE(pv_cpu_ops, usergs_sysret32); PATCH_SITE(pv_cpu_ops, usergs_sysret64); PATCH_SITE(pv_cpu_ops, swapgs); PATCH_SITE(pv_mmu_ops, read_cr2); diff --git a/arch/x86/kernel/pci-calgary_64.c b/arch/x86/kernel/pci-calgary_64.c index 0497f719977d..833b1d329c47 100644 --- a/arch/x86/kernel/pci-calgary_64.c +++ b/arch/x86/kernel/pci-calgary_64.c @@ -180,13 +180,13 @@ static void calioc2_dump_error_regs(struct iommu_table *tbl); static void calgary_init_bitmap_from_tce_table(struct iommu_table *tbl); static void get_tce_space_from_tar(void); -static struct cal_chipset_ops calgary_chip_ops = { +static const struct cal_chipset_ops calgary_chip_ops = { .handle_quirks = calgary_handle_quirks, .tce_cache_blast = calgary_tce_cache_blast, .dump_error_regs = calgary_dump_error_regs }; -static struct cal_chipset_ops calioc2_chip_ops = { +static const struct cal_chipset_ops calioc2_chip_ops = { .handle_quirks = calioc2_handle_quirks, .tce_cache_blast = calioc2_tce_cache_blast, .dump_error_regs = calioc2_dump_error_regs diff --git a/arch/x86/kernel/pci-swiotlb.c b/arch/x86/kernel/pci-swiotlb.c index adf0392d549a..7c577a178859 100644 --- a/arch/x86/kernel/pci-swiotlb.c +++ b/arch/x86/kernel/pci-swiotlb.c @@ -88,7 +88,7 @@ int __init pci_swiotlb_detect_4gb(void) { /* don't initialize swiotlb if iommu=off (no_iommu=1) */ #ifdef CONFIG_X86_64 - if (!no_iommu && max_pfn > MAX_DMA32_PFN) + if (!no_iommu && max_possible_pfn > MAX_DMA32_PFN) swiotlb = 1; #endif return swiotlb; diff --git a/arch/x86/kernel/pmem.c b/arch/x86/kernel/pmem.c index 4f00b63d7ff3..14415aff1813 100644 --- a/arch/x86/kernel/pmem.c +++ b/arch/x86/kernel/pmem.c @@ -4,10 +4,22 @@ */ #include <linux/platform_device.h> #include <linux/module.h> +#include <linux/ioport.h> + +static int found(u64 start, u64 end, void *data) +{ + return 1; +} static __init int register_e820_pmem(void) { + char *pmem = "Persistent Memory (legacy)"; struct platform_device *pdev; + int rc; + + rc = walk_iomem_res(pmem, IORESOURCE_MEM, 0, -1, NULL, found); + if (rc <= 0) + return 0; /* * See drivers/nvdimm/e820.c for the implementation, this is diff --git a/arch/x86/kernel/process_64.c b/arch/x86/kernel/process_64.c index e835d263a33b..b9d99e0f82c4 100644 --- a/arch/x86/kernel/process_64.c +++ b/arch/x86/kernel/process_64.c @@ -125,7 +125,7 @@ void release_thread(struct task_struct *dead_task) if (dead_task->mm->context.ldt) { pr_warn("WARNING: dead process %s still has LDT? <%p/%d>\n", dead_task->comm, - dead_task->mm->context.ldt, + dead_task->mm->context.ldt->entries, dead_task->mm->context.ldt->size); BUG(); } diff --git a/arch/x86/kernel/ptrace.c b/arch/x86/kernel/ptrace.c index 558f50edebca..32e9d9cbb884 100644 --- a/arch/x86/kernel/ptrace.c +++ b/arch/x86/kernel/ptrace.c @@ -124,21 +124,6 @@ const char *regs_query_register_name(unsigned int offset) return NULL; } -static const int arg_offs_table[] = { -#ifdef CONFIG_X86_32 - [0] = offsetof(struct pt_regs, ax), - [1] = offsetof(struct pt_regs, dx), - [2] = offsetof(struct pt_regs, cx) -#else /* CONFIG_X86_64 */ - [0] = offsetof(struct pt_regs, di), - [1] = offsetof(struct pt_regs, si), - [2] = offsetof(struct pt_regs, dx), - [3] = offsetof(struct pt_regs, cx), - [4] = offsetof(struct pt_regs, r8), - [5] = offsetof(struct pt_regs, r9) -#endif -}; - /* * does not yet catch signals sent when the child dies. * in exit.c or in signal.c. diff --git a/arch/x86/kernel/pvclock.c b/arch/x86/kernel/pvclock.c index 2f355d229a58..99bfc025111d 100644 --- a/arch/x86/kernel/pvclock.c +++ b/arch/x86/kernel/pvclock.c @@ -140,27 +140,3 @@ void pvclock_read_wallclock(struct pvclock_wall_clock *wall_clock, set_normalized_timespec(ts, now.tv_sec, now.tv_nsec); } - -#ifdef CONFIG_X86_64 -/* - * Initialize the generic pvclock vsyscall state. This will allocate - * a/some page(s) for the per-vcpu pvclock information, set up a - * fixmap mapping for the page(s) - */ - -int __init pvclock_init_vsyscall(struct pvclock_vsyscall_time_info *i, - int size) -{ - int idx; - - WARN_ON (size != PVCLOCK_VSYSCALL_NR_PAGES*PAGE_SIZE); - - for (idx = 0; idx <= (PVCLOCK_FIXMAP_END-PVCLOCK_FIXMAP_BEGIN); idx++) { - __set_fixmap(PVCLOCK_FIXMAP_BEGIN + idx, - __pa(i) + (idx*PAGE_SIZE), - PAGE_KERNEL_VVAR); - } - - return 0; -} -#endif diff --git a/arch/x86/kernel/reboot.c b/arch/x86/kernel/reboot.c index 02693dd9a079..d64889aa2d46 100644 --- a/arch/x86/kernel/reboot.c +++ b/arch/x86/kernel/reboot.c @@ -718,6 +718,7 @@ static int crashing_cpu; static nmi_shootdown_cb shootdown_callback; static atomic_t waiting_for_crash_ipi; +static int crash_ipi_issued; static int crash_nmi_callback(unsigned int val, struct pt_regs *regs) { @@ -780,6 +781,9 @@ void nmi_shootdown_cpus(nmi_shootdown_cb callback) smp_send_nmi_allbutself(); + /* Kick CPUs looping in NMI context. */ + WRITE_ONCE(crash_ipi_issued, 1); + msecs = 1000; /* Wait at most a second for the other cpus to stop */ while ((atomic_read(&waiting_for_crash_ipi) > 0) && msecs) { mdelay(1); @@ -788,9 +792,35 @@ void nmi_shootdown_cpus(nmi_shootdown_cb callback) /* Leave the nmi callback set */ } + +/* + * Check if the crash dumping IPI got issued and if so, call its callback + * directly. This function is used when we have already been in NMI handler. + * It doesn't return. + */ +void run_crash_ipi_callback(struct pt_regs *regs) +{ + if (crash_ipi_issued) + crash_nmi_callback(0, regs); +} + +/* Override the weak function in kernel/panic.c */ +void nmi_panic_self_stop(struct pt_regs *regs) +{ + while (1) { + /* If no CPU is preparing crash dump, we simply loop here. */ + run_crash_ipi_callback(regs); + cpu_relax(); + } +} + #else /* !CONFIG_SMP */ void nmi_shootdown_cpus(nmi_shootdown_cb callback) { /* No other CPUs to shoot down */ } + +void run_crash_ipi_callback(struct pt_regs *regs) +{ +} #endif diff --git a/arch/x86/kernel/rtc.c b/arch/x86/kernel/rtc.c index cd9685235df9..4af8d063fb36 100644 --- a/arch/x86/kernel/rtc.c +++ b/arch/x86/kernel/rtc.c @@ -200,6 +200,9 @@ static __init int add_rtc_cmos(void) } #endif + if (paravirt_enabled() && !paravirt_has(RTC)) + return -ENODEV; + platform_device_register(&rtc_device); dev_info(&rtc_device.dev, "registered platform RTC device (no PNP device found)\n"); diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c index 29db25f9a745..d3d80e6d42a2 100644 --- a/arch/x86/kernel/setup.c +++ b/arch/x86/kernel/setup.c @@ -1048,6 +1048,8 @@ void __init setup_arch(char **cmdline_p) if (mtrr_trim_uncached_memory(max_pfn)) max_pfn = e820_end_of_ram_pfn(); + max_possible_pfn = max_pfn; + #ifdef CONFIG_X86_32 /* max_low_pfn get updated here */ find_low_pfn_range(); @@ -1250,8 +1252,6 @@ void __init setup_arch(char **cmdline_p) if (efi_enabled(EFI_BOOT)) efi_apply_memmap_quirks(); #endif - - microcode_init(); } #ifdef CONFIG_X86_32 diff --git a/arch/x86/kernel/signal.c b/arch/x86/kernel/signal.c index b7ffb7c00075..cb6282c3638f 100644 --- a/arch/x86/kernel/signal.c +++ b/arch/x86/kernel/signal.c @@ -690,12 +690,15 @@ handle_signal(struct ksignal *ksig, struct pt_regs *regs) signal_setup_done(failed, ksig, stepping); } -#ifdef CONFIG_X86_32 -#define NR_restart_syscall __NR_restart_syscall -#else /* !CONFIG_X86_32 */ -#define NR_restart_syscall \ - test_thread_flag(TIF_IA32) ? __NR_ia32_restart_syscall : __NR_restart_syscall -#endif /* CONFIG_X86_32 */ +static inline unsigned long get_nr_restart_syscall(const struct pt_regs *regs) +{ +#if defined(CONFIG_X86_32) || !defined(CONFIG_X86_64) + return __NR_restart_syscall; +#else /* !CONFIG_X86_32 && CONFIG_X86_64 */ + return test_thread_flag(TIF_IA32) ? __NR_ia32_restart_syscall : + __NR_restart_syscall | (regs->orig_ax & __X32_SYSCALL_BIT); +#endif /* CONFIG_X86_32 || !CONFIG_X86_64 */ +} /* * Note that 'init' is a special process: it doesn't get signals it doesn't @@ -724,7 +727,7 @@ void do_signal(struct pt_regs *regs) break; case -ERESTART_RESTARTBLOCK: - regs->ax = NR_restart_syscall; + regs->ax = get_nr_restart_syscall(regs); regs->ip -= 2; break; } diff --git a/arch/x86/kernel/smp.c b/arch/x86/kernel/smp.c index 12c8286206ce..658777cf3851 100644 --- a/arch/x86/kernel/smp.c +++ b/arch/x86/kernel/smp.c @@ -125,12 +125,12 @@ static void native_smp_send_reschedule(int cpu) WARN_ON(1); return; } - apic->send_IPI_mask(cpumask_of(cpu), RESCHEDULE_VECTOR); + apic->send_IPI(cpu, RESCHEDULE_VECTOR); } void native_send_call_func_single_ipi(int cpu) { - apic->send_IPI_mask(cpumask_of(cpu), CALL_FUNCTION_SINGLE_VECTOR); + apic->send_IPI(cpu, CALL_FUNCTION_SINGLE_VECTOR); } void native_send_call_func_ipi(const struct cpumask *mask) diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c index 892ee2e5ecbc..24d57f77b3c1 100644 --- a/arch/x86/kernel/smpboot.c +++ b/arch/x86/kernel/smpboot.c @@ -304,7 +304,7 @@ do { \ static bool match_smt(struct cpuinfo_x86 *c, struct cpuinfo_x86 *o) { - if (cpu_has_topoext) { + if (boot_cpu_has(X86_FEATURE_TOPOEXT)) { int cpu1 = c->cpu_index, cpu2 = o->cpu_index; if (c->phys_proc_id == o->phys_proc_id && @@ -509,7 +509,7 @@ void __inquire_remote_apic(int apicid) */ #define UDELAY_10MS_DEFAULT 10000 -static unsigned int init_udelay = INT_MAX; +static unsigned int init_udelay = UINT_MAX; static int __init cpu_init_udelay(char *str) { @@ -522,14 +522,15 @@ early_param("cpu_init_udelay", cpu_init_udelay); static void __init smp_quirk_init_udelay(void) { /* if cmdline changed it from default, leave it alone */ - if (init_udelay != INT_MAX) + if (init_udelay != UINT_MAX) return; /* if modern processor, use no delay */ if (((boot_cpu_data.x86_vendor == X86_VENDOR_INTEL) && (boot_cpu_data.x86 == 6)) || - ((boot_cpu_data.x86_vendor == X86_VENDOR_AMD) && (boot_cpu_data.x86 >= 0xF))) + ((boot_cpu_data.x86_vendor == X86_VENDOR_AMD) && (boot_cpu_data.x86 >= 0xF))) { init_udelay = 0; - + return; + } /* else, use legacy delay */ init_udelay = UDELAY_10MS_DEFAULT; } @@ -629,13 +630,6 @@ wakeup_secondary_cpu_via_init(int phys_apicid, unsigned long start_eip) num_starts = 0; /* - * Paravirt / VMI wants a startup IPI hook here to set up the - * target processor state. - */ - startup_ipi_hook(phys_apicid, (unsigned long) start_secondary, - stack_start); - - /* * Run STARTUP IPI loop. */ pr_debug("#startup loops: %d\n", num_starts); diff --git a/arch/x86/kernel/tsc.c b/arch/x86/kernel/tsc.c index c7c4d9c51e99..3d743da828d3 100644 --- a/arch/x86/kernel/tsc.c +++ b/arch/x86/kernel/tsc.c @@ -1185,8 +1185,6 @@ void __init tsc_init(void) u64 lpj; int cpu; - x86_init.timers.tsc_pre_init(); - if (!cpu_has_tsc) { setup_clear_cpu_cap(X86_FEATURE_TSC_DEADLINE_TIMER); return; diff --git a/arch/x86/kernel/vm86_32.c b/arch/x86/kernel/vm86_32.c index 524619351961..483231ebbb0b 100644 --- a/arch/x86/kernel/vm86_32.c +++ b/arch/x86/kernel/vm86_32.c @@ -357,8 +357,10 @@ static long do_sys_vm86(struct vm86plus_struct __user *user_vm86, bool plus) tss = &per_cpu(cpu_tss, get_cpu()); /* make room for real-mode segments */ tsk->thread.sp0 += 16; - if (cpu_has_sep) + + if (static_cpu_has_safe(X86_FEATURE_SEP)) tsk->thread.sysenter_cs = 0; + load_sp0(tss, &tsk->thread); put_cpu(); diff --git a/arch/x86/kernel/x86_init.c b/arch/x86/kernel/x86_init.c index 3839628d962e..dad5fe9633a3 100644 --- a/arch/x86/kernel/x86_init.c +++ b/arch/x86/kernel/x86_init.c @@ -68,7 +68,6 @@ struct x86_init_ops x86_init __initdata = { .timers = { .setup_percpu_clockev = setup_boot_APIC_clock, - .tsc_pre_init = x86_init_noop, .timer_init = hpet_time_init, .wallclock_init = x86_init_noop, }, diff --git a/arch/x86/kvm/cpuid.h b/arch/x86/kvm/cpuid.h index 06332cb7e7d1..c8eda1498121 100644 --- a/arch/x86/kvm/cpuid.h +++ b/arch/x86/kvm/cpuid.h @@ -2,6 +2,7 @@ #define ARCH_X86_KVM_CPUID_H #include "x86.h" +#include <asm/cpu.h> int kvm_update_cpuid(struct kvm_vcpu *vcpu); struct kvm_cpuid_entry2 *kvm_find_cpuid_entry(struct kvm_vcpu *vcpu, @@ -38,6 +39,14 @@ static inline bool guest_cpuid_has_xsave(struct kvm_vcpu *vcpu) return best && (best->ecx & bit(X86_FEATURE_XSAVE)); } +static inline bool guest_cpuid_has_mtrr(struct kvm_vcpu *vcpu) +{ + struct kvm_cpuid_entry2 *best; + + best = kvm_find_cpuid_entry(vcpu, 1, 0); + return best && (best->edx & bit(X86_FEATURE_MTRR)); +} + static inline bool guest_cpuid_has_tsc_adjust(struct kvm_vcpu *vcpu) { struct kvm_cpuid_entry2 *best; @@ -170,4 +179,37 @@ static inline bool guest_cpuid_has_nrips(struct kvm_vcpu *vcpu) } #undef BIT_NRIPS +static inline int guest_cpuid_family(struct kvm_vcpu *vcpu) +{ + struct kvm_cpuid_entry2 *best; + + best = kvm_find_cpuid_entry(vcpu, 0x1, 0); + if (!best) + return -1; + + return x86_family(best->eax); +} + +static inline int guest_cpuid_model(struct kvm_vcpu *vcpu) +{ + struct kvm_cpuid_entry2 *best; + + best = kvm_find_cpuid_entry(vcpu, 0x1, 0); + if (!best) + return -1; + + return x86_model(best->eax); +} + +static inline int guest_cpuid_stepping(struct kvm_vcpu *vcpu) +{ + struct kvm_cpuid_entry2 *best; + + best = kvm_find_cpuid_entry(vcpu, 0x1, 0); + if (!best) + return -1; + + return x86_stepping(best->eax); +} + #endif diff --git a/arch/x86/kvm/i8254.c b/arch/x86/kvm/i8254.c index 08116ff227cc..b0ea42b78ccd 100644 --- a/arch/x86/kvm/i8254.c +++ b/arch/x86/kvm/i8254.c @@ -420,6 +420,7 @@ void kvm_pit_load_count(struct kvm *kvm, int channel, u32 val, int hpet_legacy_s u8 saved_mode; if (hpet_legacy_start) { /* save existing mode for later reenablement */ + WARN_ON(channel != 0); saved_mode = kvm->arch.vpit->pit_state.channels[0].mode; kvm->arch.vpit->pit_state.channels[0].mode = 0xff; /* disable timer */ pit_load_count(kvm, channel, val); diff --git a/arch/x86/kvm/mtrr.c b/arch/x86/kvm/mtrr.c index 9e8bf13572e6..3f8c732117ec 100644 --- a/arch/x86/kvm/mtrr.c +++ b/arch/x86/kvm/mtrr.c @@ -120,14 +120,22 @@ static u8 mtrr_default_type(struct kvm_mtrr *mtrr_state) return mtrr_state->deftype & IA32_MTRR_DEF_TYPE_TYPE_MASK; } -static u8 mtrr_disabled_type(void) +static u8 mtrr_disabled_type(struct kvm_vcpu *vcpu) { /* * Intel SDM 11.11.2.2: all MTRRs are disabled when * IA32_MTRR_DEF_TYPE.E bit is cleared, and the UC * memory type is applied to all of physical memory. + * + * However, virtual machines can be run with CPUID such that + * there are no MTRRs. In that case, the firmware will never + * enable MTRRs and it is obviously undesirable to run the + * guest entirely with UC memory and we use WB. */ - return MTRR_TYPE_UNCACHABLE; + if (guest_cpuid_has_mtrr(vcpu)) + return MTRR_TYPE_UNCACHABLE; + else + return MTRR_TYPE_WRBACK; } /* @@ -267,7 +275,7 @@ static int fixed_mtrr_addr_to_seg(u64 addr) for (seg = 0; seg < seg_num; seg++) { mtrr_seg = &fixed_seg_table[seg]; - if (mtrr_seg->start >= addr && addr < mtrr_seg->end) + if (mtrr_seg->start <= addr && addr < mtrr_seg->end) return seg; } @@ -300,7 +308,6 @@ static void var_mtrr_range(struct kvm_mtrr_range *range, u64 *start, u64 *end) *start = range->base & PAGE_MASK; mask = range->mask & PAGE_MASK; - mask |= ~0ULL << boot_cpu_data.x86_phys_bits; /* This cannot overflow because writing to the reserved bits of * variable MTRRs causes a #GP. @@ -356,10 +363,14 @@ static void set_var_mtrr_msr(struct kvm_vcpu *vcpu, u32 msr, u64 data) if (var_mtrr_range_is_valid(cur)) list_del(&mtrr_state->var_ranges[index].node); + /* Extend the mask with all 1 bits to the left, since those + * bits must implicitly be 0. The bits are then cleared + * when reading them. + */ if (!is_mtrr_mask) cur->base = data; else - cur->mask = data; + cur->mask = data | (-1LL << cpuid_maxphyaddr(vcpu)); /* add it to the list if it's enabled. */ if (var_mtrr_range_is_valid(cur)) { @@ -426,6 +437,8 @@ int kvm_mtrr_get_msr(struct kvm_vcpu *vcpu, u32 msr, u64 *pdata) *pdata = vcpu->arch.mtrr_state.var_ranges[index].base; else *pdata = vcpu->arch.mtrr_state.var_ranges[index].mask; + + *pdata &= (1ULL << cpuid_maxphyaddr(vcpu)) - 1; } return 0; @@ -670,7 +683,7 @@ u8 kvm_mtrr_get_guest_memory_type(struct kvm_vcpu *vcpu, gfn_t gfn) } if (iter.mtrr_disabled) - return mtrr_disabled_type(); + return mtrr_disabled_type(vcpu); /* not contained in any MTRRs. */ if (type == -1) diff --git a/arch/x86/kvm/svm.c b/arch/x86/kvm/svm.c index 83a1c643f9a5..22aef20bf9c7 100644 --- a/arch/x86/kvm/svm.c +++ b/arch/x86/kvm/svm.c @@ -3053,6 +3053,23 @@ static int svm_get_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info) case MSR_IA32_UCODE_REV: msr_info->data = 0x01000065; break; + case MSR_F15H_IC_CFG: { + + int family, model; + + family = guest_cpuid_family(vcpu); + model = guest_cpuid_model(vcpu); + + if (family < 0 || model < 0) + return kvm_get_msr_common(vcpu, msr_info); + + msr_info->data = 0; + + if (family == 0x15 && + (model >= 0x2 && model < 0x20)) + msr_info->data = 0x1E; + } + break; default: return kvm_get_msr_common(vcpu, msr_info); } @@ -3422,6 +3439,8 @@ static int handle_exit(struct kvm_vcpu *vcpu) struct kvm_run *kvm_run = vcpu->run; u32 exit_code = svm->vmcb->control.exit_code; + trace_kvm_exit(exit_code, vcpu, KVM_ISA_SVM); + if (!is_cr_intercept(svm, INTERCEPT_CR0_WRITE)) vcpu->arch.cr0 = svm->vmcb->save.cr0; if (npt_enabled) @@ -3892,8 +3911,6 @@ static void svm_vcpu_run(struct kvm_vcpu *vcpu) vcpu->arch.regs[VCPU_REGS_RSP] = svm->vmcb->save.rsp; vcpu->arch.regs[VCPU_REGS_RIP] = svm->vmcb->save.rip; - trace_kvm_exit(svm->vmcb->control.exit_code, vcpu, KVM_ISA_SVM); - if (unlikely(svm->vmcb->control.exit_code == SVM_EXIT_NMI)) kvm_before_handle_nmi(&svm->vcpu); diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c index 87acc5221740..44976a596fa6 100644 --- a/arch/x86/kvm/vmx.c +++ b/arch/x86/kvm/vmx.c @@ -2803,7 +2803,7 @@ static int vmx_get_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info) msr_info->data = vcpu->arch.ia32_xss; break; case MSR_TSC_AUX: - if (!guest_cpuid_has_rdtscp(vcpu)) + if (!guest_cpuid_has_rdtscp(vcpu) && !msr_info->host_initiated) return 1; /* Otherwise falls through */ default: @@ -2909,7 +2909,7 @@ static int vmx_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info) clear_atomic_switch_msr(vmx, MSR_IA32_XSS); break; case MSR_TSC_AUX: - if (!guest_cpuid_has_rdtscp(vcpu)) + if (!guest_cpuid_has_rdtscp(vcpu) && !msr_info->host_initiated) return 1; /* Check reserved bit, higher 32 bits should be zero */ if ((data >> 32) != 0) @@ -7394,11 +7394,6 @@ static int handle_invvpid(struct kvm_vcpu *vcpu) switch (type) { case VMX_VPID_EXTENT_ALL_CONTEXT: - if (get_vmcs12(vcpu)->virtual_processor_id == 0) { - nested_vmx_failValid(vcpu, - VMXERR_INVALID_OPERAND_TO_INVEPT_INVVPID); - return 1; - } __vmx_flush_tlb(vcpu, to_vmx(vcpu)->nested.vpid02); nested_vmx_succeed(vcpu); break; @@ -8047,6 +8042,8 @@ static int vmx_handle_exit(struct kvm_vcpu *vcpu) u32 exit_reason = vmx->exit_reason; u32 vectoring_info = vmx->idt_vectoring_info; + trace_kvm_exit(exit_reason, vcpu, KVM_ISA_VMX); + /* * Flush logged GPAs PML buffer, this will make dirty_bitmap more * updated. Another good is, in kvm_vm_ioctl_get_dirty_log, before @@ -8673,7 +8670,6 @@ static void __noclone vmx_vcpu_run(struct kvm_vcpu *vcpu) vmx->loaded_vmcs->launched = 1; vmx->exit_reason = vmcs_read32(VM_EXIT_REASON); - trace_kvm_exit(vmx->exit_reason, vcpu, KVM_ISA_VMX); /* * the KVM_REQ_EVENT optimization bit is only on for one entry, and if diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index 00462bd63129..97592e190413 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -2763,6 +2763,26 @@ static int kvm_vcpu_ioctl_set_lapic(struct kvm_vcpu *vcpu, return 0; } +static int kvm_cpu_accept_dm_intr(struct kvm_vcpu *vcpu) +{ + return (!lapic_in_kernel(vcpu) || + kvm_apic_accept_pic_intr(vcpu)); +} + +/* + * if userspace requested an interrupt window, check that the + * interrupt window is open. + * + * No need to exit to userspace if we already have an interrupt queued. + */ +static int kvm_vcpu_ready_for_interrupt_injection(struct kvm_vcpu *vcpu) +{ + return kvm_arch_interrupt_allowed(vcpu) && + !kvm_cpu_has_interrupt(vcpu) && + !kvm_event_needs_reinjection(vcpu) && + kvm_cpu_accept_dm_intr(vcpu); +} + static int kvm_vcpu_ioctl_interrupt(struct kvm_vcpu *vcpu, struct kvm_interrupt *irq) { @@ -2786,6 +2806,7 @@ static int kvm_vcpu_ioctl_interrupt(struct kvm_vcpu *vcpu, return -EEXIST; vcpu->arch.pending_external_vector = irq->irq; + kvm_make_request(KVM_REQ_EVENT, vcpu); return 0; } @@ -3551,9 +3572,11 @@ static int kvm_vm_ioctl_get_pit(struct kvm *kvm, struct kvm_pit_state *ps) static int kvm_vm_ioctl_set_pit(struct kvm *kvm, struct kvm_pit_state *ps) { + int i; mutex_lock(&kvm->arch.vpit->pit_state.lock); memcpy(&kvm->arch.vpit->pit_state, ps, sizeof(struct kvm_pit_state)); - kvm_pit_load_count(kvm, 0, ps->channels[0].count, 0); + for (i = 0; i < 3; i++) + kvm_pit_load_count(kvm, i, ps->channels[i].count, 0); mutex_unlock(&kvm->arch.vpit->pit_state.lock); return 0; } @@ -3572,6 +3595,7 @@ static int kvm_vm_ioctl_get_pit2(struct kvm *kvm, struct kvm_pit_state2 *ps) static int kvm_vm_ioctl_set_pit2(struct kvm *kvm, struct kvm_pit_state2 *ps) { int start = 0; + int i; u32 prev_legacy, cur_legacy; mutex_lock(&kvm->arch.vpit->pit_state.lock); prev_legacy = kvm->arch.vpit->pit_state.flags & KVM_PIT_FLAGS_HPET_LEGACY; @@ -3581,7 +3605,9 @@ static int kvm_vm_ioctl_set_pit2(struct kvm *kvm, struct kvm_pit_state2 *ps) memcpy(&kvm->arch.vpit->pit_state.channels, &ps->channels, sizeof(kvm->arch.vpit->pit_state.channels)); kvm->arch.vpit->pit_state.flags = ps->flags; - kvm_pit_load_count(kvm, 0, kvm->arch.vpit->pit_state.channels[0].count, start); + for (i = 0; i < 3; i++) + kvm_pit_load_count(kvm, i, kvm->arch.vpit->pit_state.channels[i].count, + start && i == 0); mutex_unlock(&kvm->arch.vpit->pit_state.lock); return 0; } @@ -5910,23 +5936,10 @@ static int emulator_fix_hypercall(struct x86_emulate_ctxt *ctxt) return emulator_write_emulated(ctxt, rip, instruction, 3, NULL); } -/* - * Check if userspace requested an interrupt window, and that the - * interrupt window is open. - * - * No need to exit to userspace if we already have an interrupt queued. - */ static int dm_request_for_irq_injection(struct kvm_vcpu *vcpu) { - if (!vcpu->run->request_interrupt_window || pic_in_kernel(vcpu->kvm)) - return false; - - if (kvm_cpu_has_interrupt(vcpu)) - return false; - - return (irqchip_split(vcpu->kvm) - ? kvm_apic_accept_pic_intr(vcpu) - : kvm_arch_interrupt_allowed(vcpu)); + return vcpu->run->request_interrupt_window && + likely(!pic_in_kernel(vcpu->kvm)); } static void post_kvm_run_save(struct kvm_vcpu *vcpu) @@ -5937,17 +5950,9 @@ static void post_kvm_run_save(struct kvm_vcpu *vcpu) kvm_run->flags = is_smm(vcpu) ? KVM_RUN_X86_SMM : 0; kvm_run->cr8 = kvm_get_cr8(vcpu); kvm_run->apic_base = kvm_get_apic_base(vcpu); - if (!irqchip_in_kernel(vcpu->kvm)) - kvm_run->ready_for_interrupt_injection = - kvm_arch_interrupt_allowed(vcpu) && - !kvm_cpu_has_interrupt(vcpu) && - !kvm_event_needs_reinjection(vcpu); - else if (!pic_in_kernel(vcpu->kvm)) - kvm_run->ready_for_interrupt_injection = - kvm_apic_accept_pic_intr(vcpu) && - !kvm_cpu_has_interrupt(vcpu); - else - kvm_run->ready_for_interrupt_injection = 1; + kvm_run->ready_for_interrupt_injection = + pic_in_kernel(vcpu->kvm) || + kvm_vcpu_ready_for_interrupt_injection(vcpu); } static void update_cr8_intercept(struct kvm_vcpu *vcpu) @@ -6360,8 +6365,10 @@ void kvm_arch_mmu_notifier_invalidate_page(struct kvm *kvm, static int vcpu_enter_guest(struct kvm_vcpu *vcpu) { int r; - bool req_int_win = !lapic_in_kernel(vcpu) && - vcpu->run->request_interrupt_window; + bool req_int_win = + dm_request_for_irq_injection(vcpu) && + kvm_cpu_accept_dm_intr(vcpu); + bool req_immediate_exit = false; if (vcpu->requests) { @@ -6513,6 +6520,8 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu) if (req_immediate_exit) smp_send_reschedule(vcpu->cpu); + trace_kvm_entry(vcpu->vcpu_id); + wait_lapic_expire(vcpu); __kvm_guest_enter(); if (unlikely(vcpu->arch.switch_db_regs)) { @@ -6525,8 +6534,6 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu) vcpu->arch.switch_db_regs &= ~KVM_DEBUGREG_RELOAD; } - trace_kvm_entry(vcpu->vcpu_id); - wait_lapic_expire(vcpu); kvm_x86_ops->run(vcpu); /* @@ -6663,7 +6670,8 @@ static int vcpu_run(struct kvm_vcpu *vcpu) if (kvm_cpu_has_pending_timer(vcpu)) kvm_inject_pending_timer_irqs(vcpu); - if (dm_request_for_irq_injection(vcpu)) { + if (dm_request_for_irq_injection(vcpu) && + kvm_vcpu_ready_for_interrupt_injection(vcpu)) { r = 0; vcpu->run->exit_reason = KVM_EXIT_IRQ_WINDOW_OPEN; ++vcpu->stat.request_irq_exits; diff --git a/arch/x86/lguest/boot.c b/arch/x86/lguest/boot.c index a0d09f6c6533..4ba229ac3f4f 100644 --- a/arch/x86/lguest/boot.c +++ b/arch/x86/lguest/boot.c @@ -1414,6 +1414,7 @@ __init void lguest_init(void) pv_info.kernel_rpl = 1; /* Everyone except Xen runs with this set. */ pv_info.shared_kernel_pmd = 1; + pv_info.features = 0; /* * We set up all the lguest overrides for sensitive operations. These @@ -1472,7 +1473,6 @@ __init void lguest_init(void) 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; #ifdef CONFIG_X86_LOCAL_APIC /* APIC read/write intercepts */ diff --git a/arch/x86/lib/Makefile b/arch/x86/lib/Makefile index f2587888d987..a501fa25da41 100644 --- a/arch/x86/lib/Makefile +++ b/arch/x86/lib/Makefile @@ -16,7 +16,7 @@ clean-files := inat-tables.c obj-$(CONFIG_SMP) += msr-smp.o cache-smp.o -lib-y := delay.o misc.o cmdline.o +lib-y := delay.o misc.o cmdline.o cpu.o lib-y += usercopy_$(BITS).o usercopy.o getuser.o putuser.o lib-y += memcpy_$(BITS).o lib-$(CONFIG_RWSEM_XCHGADD_ALGORITHM) += rwsem.o diff --git a/arch/x86/lib/cpu.c b/arch/x86/lib/cpu.c new file mode 100644 index 000000000000..aa417a97511c --- /dev/null +++ b/arch/x86/lib/cpu.c @@ -0,0 +1,35 @@ +#include <linux/module.h> + +unsigned int x86_family(unsigned int sig) +{ + unsigned int x86; + + x86 = (sig >> 8) & 0xf; + + if (x86 == 0xf) + x86 += (sig >> 20) & 0xff; + + return x86; +} +EXPORT_SYMBOL_GPL(x86_family); + +unsigned int x86_model(unsigned int sig) +{ + unsigned int fam, model; + + fam = x86_family(sig); + + model = (sig >> 4) & 0xf; + + if (fam >= 0x6) + model += ((sig >> 16) & 0xf) << 4; + + return model; +} +EXPORT_SYMBOL_GPL(x86_model); + +unsigned int x86_stepping(unsigned int sig) +{ + return sig & 0xf; +} +EXPORT_SYMBOL_GPL(x86_stepping); diff --git a/arch/x86/lib/msr.c b/arch/x86/lib/msr.c index 43623739c7cf..004c861b1648 100644 --- a/arch/x86/lib/msr.c +++ b/arch/x86/lib/msr.c @@ -1,6 +1,8 @@ #include <linux/module.h> #include <linux/preempt.h> #include <asm/msr.h> +#define CREATE_TRACE_POINTS +#include <asm/msr-trace.h> struct msr *msrs_alloc(void) { @@ -108,3 +110,27 @@ int msr_clear_bit(u32 msr, u8 bit) { return __flip_bit(msr, bit, false); } + +#ifdef CONFIG_TRACEPOINTS +void do_trace_write_msr(unsigned msr, u64 val, int failed) +{ + trace_write_msr(msr, val, failed); +} +EXPORT_SYMBOL(do_trace_write_msr); +EXPORT_TRACEPOINT_SYMBOL(write_msr); + +void do_trace_read_msr(unsigned msr, u64 val, int failed) +{ + trace_read_msr(msr, val, failed); +} +EXPORT_SYMBOL(do_trace_read_msr); +EXPORT_TRACEPOINT_SYMBOL(read_msr); + +void do_trace_rdpmc(unsigned counter, u64 val, int failed) +{ + trace_rdpmc(counter, val, failed); +} +EXPORT_SYMBOL(do_trace_rdpmc); +EXPORT_TRACEPOINT_SYMBOL(rdpmc); + +#endif diff --git a/arch/x86/mm/Makefile b/arch/x86/mm/Makefile index 65c47fda26fc..f9d38a48e3c8 100644 --- a/arch/x86/mm/Makefile +++ b/arch/x86/mm/Makefile @@ -15,6 +15,7 @@ obj-$(CONFIG_X86_32) += pgtable_32.o iomap_32.o obj-$(CONFIG_HUGETLB_PAGE) += hugetlbpage.o obj-$(CONFIG_X86_PTDUMP_CORE) += dump_pagetables.o +obj-$(CONFIG_X86_PTDUMP) += debug_pagetables.o obj-$(CONFIG_HIGHMEM) += highmem_32.o diff --git a/arch/x86/mm/debug_pagetables.c b/arch/x86/mm/debug_pagetables.c new file mode 100644 index 000000000000..bfcffdf6c577 --- /dev/null +++ b/arch/x86/mm/debug_pagetables.c @@ -0,0 +1,46 @@ +#include <linux/debugfs.h> +#include <linux/module.h> +#include <linux/seq_file.h> +#include <asm/pgtable.h> + +static int ptdump_show(struct seq_file *m, void *v) +{ + ptdump_walk_pgd_level(m, NULL); + return 0; +} + +static int ptdump_open(struct inode *inode, struct file *filp) +{ + return single_open(filp, ptdump_show, NULL); +} + +static const struct file_operations ptdump_fops = { + .owner = THIS_MODULE, + .open = ptdump_open, + .read = seq_read, + .llseek = seq_lseek, + .release = single_release, +}; + +static struct dentry *pe; + +static int __init pt_dump_debug_init(void) +{ + pe = debugfs_create_file("kernel_page_tables", S_IRUSR, NULL, NULL, + &ptdump_fops); + if (!pe) + return -ENOMEM; + + return 0; +} + +static void __exit pt_dump_debug_exit(void) +{ + debugfs_remove_recursive(pe); +} + +module_init(pt_dump_debug_init); +module_exit(pt_dump_debug_exit); +MODULE_LICENSE("GPL"); +MODULE_AUTHOR("Arjan van de Ven <arjan@linux.intel.com>"); +MODULE_DESCRIPTION("Kernel debugging helper that dumps pagetables"); diff --git a/arch/x86/mm/dump_pagetables.c b/arch/x86/mm/dump_pagetables.c index a035c2aa7801..4a6f1d9b5106 100644 --- a/arch/x86/mm/dump_pagetables.c +++ b/arch/x86/mm/dump_pagetables.c @@ -89,7 +89,7 @@ static struct addr_marker address_markers[] = { { 0/* VMALLOC_START */, "vmalloc() Area" }, { 0/*VMALLOC_END*/, "vmalloc() End" }, # ifdef CONFIG_HIGHMEM - { 0/*PKMAP_BASE*/, "Persisent kmap() Area" }, + { 0/*PKMAP_BASE*/, "Persistent kmap() Area" }, # endif { 0/*FIXADDR_START*/, "Fixmap Area" }, #endif @@ -426,38 +426,15 @@ void ptdump_walk_pgd_level(struct seq_file *m, pgd_t *pgd) { ptdump_walk_pgd_level_core(m, pgd, false); } +EXPORT_SYMBOL_GPL(ptdump_walk_pgd_level); void ptdump_walk_pgd_level_checkwx(void) { ptdump_walk_pgd_level_core(NULL, NULL, true); } -#ifdef CONFIG_X86_PTDUMP -static int ptdump_show(struct seq_file *m, void *v) +static int __init pt_dump_init(void) { - ptdump_walk_pgd_level(m, NULL); - return 0; -} - -static int ptdump_open(struct inode *inode, struct file *filp) -{ - return single_open(filp, ptdump_show, NULL); -} - -static const struct file_operations ptdump_fops = { - .open = ptdump_open, - .read = seq_read, - .llseek = seq_lseek, - .release = single_release, -}; -#endif - -static int pt_dump_init(void) -{ -#ifdef CONFIG_X86_PTDUMP - struct dentry *pe; -#endif - #ifdef CONFIG_X86_32 /* Not a compile-time constant on x86-32 */ address_markers[VMALLOC_START_NR].start_address = VMALLOC_START; @@ -468,13 +445,6 @@ static int pt_dump_init(void) address_markers[FIXADDR_START_NR].start_address = FIXADDR_START; #endif -#ifdef CONFIG_X86_PTDUMP - pe = debugfs_create_file("kernel_page_tables", 0600, NULL, NULL, - &ptdump_fops); - if (!pe) - return -ENOMEM; -#endif - return 0; } diff --git a/arch/x86/mm/ioremap.c b/arch/x86/mm/ioremap.c index b9c78f3bcd67..0d8d53d1f5cc 100644 --- a/arch/x86/mm/ioremap.c +++ b/arch/x86/mm/ioremap.c @@ -194,8 +194,8 @@ static void __iomem *__ioremap_caller(resource_size_t phys_addr, * Check if the request spans more than any BAR in the iomem resource * tree. */ - WARN_ONCE(iomem_map_sanity_check(unaligned_phys_addr, unaligned_size), - KERN_INFO "Info: mapping multiple BARs. Your kernel is fine."); + if (iomem_map_sanity_check(unaligned_phys_addr, unaligned_size)) + pr_warn("caller %pS mapping multiple BARs\n", caller); return ret_addr; err_free_area: diff --git a/arch/x86/mm/mpx.c b/arch/x86/mm/mpx.c index b0ae85f90f10..b2fd67da1701 100644 --- a/arch/x86/mm/mpx.c +++ b/arch/x86/mm/mpx.c @@ -101,19 +101,19 @@ static int get_reg_offset(struct insn *insn, struct pt_regs *regs, switch (type) { case REG_TYPE_RM: regno = X86_MODRM_RM(insn->modrm.value); - if (X86_REX_B(insn->rex_prefix.value) == 1) + if (X86_REX_B(insn->rex_prefix.value)) regno += 8; break; case REG_TYPE_INDEX: regno = X86_SIB_INDEX(insn->sib.value); - if (X86_REX_X(insn->rex_prefix.value) == 1) + if (X86_REX_X(insn->rex_prefix.value)) regno += 8; break; case REG_TYPE_BASE: regno = X86_SIB_BASE(insn->sib.value); - if (X86_REX_B(insn->rex_prefix.value) == 1) + if (X86_REX_B(insn->rex_prefix.value)) regno += 8; break; @@ -586,6 +586,29 @@ static unsigned long mpx_bd_entry_to_bt_addr(struct mm_struct *mm, } /* + * We only want to do a 4-byte get_user() on 32-bit. Otherwise, + * we might run off the end of the bounds table if we are on + * a 64-bit kernel and try to get 8 bytes. + */ +int get_user_bd_entry(struct mm_struct *mm, unsigned long *bd_entry_ret, + long __user *bd_entry_ptr) +{ + u32 bd_entry_32; + int ret; + + if (is_64bit_mm(mm)) + return get_user(*bd_entry_ret, bd_entry_ptr); + + /* + * Note that get_user() uses the type of the *pointer* to + * establish the size of the get, not the destination. + */ + ret = get_user(bd_entry_32, (u32 __user *)bd_entry_ptr); + *bd_entry_ret = bd_entry_32; + return ret; +} + +/* * Get the base of bounds tables pointed by specific bounds * directory entry. */ @@ -605,7 +628,7 @@ static int get_bt_addr(struct mm_struct *mm, int need_write = 0; pagefault_disable(); - ret = get_user(bd_entry, bd_entry_ptr); + ret = get_user_bd_entry(mm, &bd_entry, bd_entry_ptr); pagefault_enable(); if (!ret) break; @@ -700,11 +723,23 @@ static unsigned long mpx_get_bt_entry_offset_bytes(struct mm_struct *mm, */ static inline unsigned long bd_entry_virt_space(struct mm_struct *mm) { - unsigned long long virt_space = (1ULL << boot_cpu_data.x86_virt_bits); - if (is_64bit_mm(mm)) - return virt_space / MPX_BD_NR_ENTRIES_64; - else - return virt_space / MPX_BD_NR_ENTRIES_32; + unsigned long long virt_space; + unsigned long long GB = (1ULL << 30); + + /* + * This covers 32-bit emulation as well as 32-bit kernels + * running on 64-bit harware. + */ + if (!is_64bit_mm(mm)) + return (4ULL * GB) / MPX_BD_NR_ENTRIES_32; + + /* + * 'x86_virt_bits' returns what the hardware is capable + * of, and returns the full >32-bit adddress space when + * running 32-bit kernels on 64-bit hardware. + */ + virt_space = (1ULL << boot_cpu_data.x86_virt_bits); + return virt_space / MPX_BD_NR_ENTRIES_64; } /* diff --git a/arch/x86/mm/pageattr.c b/arch/x86/mm/pageattr.c index a3137a4feed1..6000ad7f560c 100644 --- a/arch/x86/mm/pageattr.c +++ b/arch/x86/mm/pageattr.c @@ -129,14 +129,16 @@ within(unsigned long addr, unsigned long start, unsigned long end) */ void clflush_cache_range(void *vaddr, unsigned int size) { - unsigned long clflush_mask = boot_cpu_data.x86_clflush_size - 1; + const unsigned long clflush_size = boot_cpu_data.x86_clflush_size; + void *p = (void *)((unsigned long)vaddr & ~(clflush_size - 1)); void *vend = vaddr + size; - void *p; + + if (p >= vend) + return; mb(); - for (p = (void *)((unsigned long)vaddr & ~clflush_mask); - p < vend; p += boot_cpu_data.x86_clflush_size) + for (; p < vend; p += clflush_size) clflushopt(p); mb(); diff --git a/arch/x86/mm/pat.c b/arch/x86/mm/pat.c index 188e3e07eeeb..031782e74231 100644 --- a/arch/x86/mm/pat.c +++ b/arch/x86/mm/pat.c @@ -586,7 +586,7 @@ int free_memtype(u64 start, u64 end) entry = rbt_memtype_erase(start, end); spin_unlock(&memtype_lock); - if (!entry) { + if (IS_ERR(entry)) { pr_info("x86/PAT: %s:%d freeing invalid memtype [mem %#010Lx-%#010Lx]\n", current->comm, current->pid, start, end - 1); return -EINVAL; @@ -992,6 +992,16 @@ void untrack_pfn(struct vm_area_struct *vma, unsigned long pfn, vma->vm_flags &= ~VM_PAT; } +/* + * untrack_pfn_moved is called, while mremapping a pfnmap for a new region, + * with the old vma after its pfnmap page table has been removed. The new + * vma has a new pfnmap to the same pfn & cache type with VM_PAT set. + */ +void untrack_pfn_moved(struct vm_area_struct *vma) +{ + vma->vm_flags &= ~VM_PAT; +} + pgprot_t pgprot_writecombine(pgprot_t prot) { return __pgprot(pgprot_val(prot) | diff --git a/arch/x86/mm/pat_rbtree.c b/arch/x86/mm/pat_rbtree.c index 63931080366a..2f7702253ccf 100644 --- a/arch/x86/mm/pat_rbtree.c +++ b/arch/x86/mm/pat_rbtree.c @@ -98,8 +98,13 @@ static struct memtype *memtype_rb_lowest_match(struct rb_root *root, return last_lower; /* Returns NULL if there is no overlap */ } -static struct memtype *memtype_rb_exact_match(struct rb_root *root, - u64 start, u64 end) +enum { + MEMTYPE_EXACT_MATCH = 0, + MEMTYPE_END_MATCH = 1 +}; + +static struct memtype *memtype_rb_match(struct rb_root *root, + u64 start, u64 end, int match_type) { struct memtype *match; @@ -107,7 +112,12 @@ static struct memtype *memtype_rb_exact_match(struct rb_root *root, while (match != NULL && match->start < end) { struct rb_node *node; - if (match->start == start && match->end == end) + if ((match_type == MEMTYPE_EXACT_MATCH) && + (match->start == start) && (match->end == end)) + return match; + + if ((match_type == MEMTYPE_END_MATCH) && + (match->start < start) && (match->end == end)) return match; node = rb_next(&match->rb); @@ -117,7 +127,7 @@ static struct memtype *memtype_rb_exact_match(struct rb_root *root, match = NULL; } - return NULL; /* Returns NULL if there is no exact match */ + return NULL; /* Returns NULL if there is no match */ } static int memtype_rb_check_conflict(struct rb_root *root, @@ -210,12 +220,36 @@ struct memtype *rbt_memtype_erase(u64 start, u64 end) { struct memtype *data; - data = memtype_rb_exact_match(&memtype_rbroot, start, end); - if (!data) - goto out; + /* + * Since the memtype_rbroot tree allows overlapping ranges, + * rbt_memtype_erase() checks with EXACT_MATCH first, i.e. free + * a whole node for the munmap case. If no such entry is found, + * it then checks with END_MATCH, i.e. shrink the size of a node + * from the end for the mremap case. + */ + data = memtype_rb_match(&memtype_rbroot, start, end, + MEMTYPE_EXACT_MATCH); + if (!data) { + data = memtype_rb_match(&memtype_rbroot, start, end, + MEMTYPE_END_MATCH); + if (!data) + return ERR_PTR(-EINVAL); + } + + if (data->start == start) { + /* munmap: erase this node */ + rb_erase_augmented(&data->rb, &memtype_rbroot, + &memtype_rb_augment_cb); + } else { + /* mremap: update the end value of this node */ + rb_erase_augmented(&data->rb, &memtype_rbroot, + &memtype_rb_augment_cb); + data->end = start; + data->subtree_max_end = data->end; + memtype_rb_insert(&memtype_rbroot, data); + return NULL; + } - rb_erase_augmented(&data->rb, &memtype_rbroot, &memtype_rb_augment_cb); -out: return data; } diff --git a/arch/x86/mm/pgtable.c b/arch/x86/mm/pgtable.c index fb0a9dd1d6e4..ee9c2e3a7199 100644 --- a/arch/x86/mm/pgtable.c +++ b/arch/x86/mm/pgtable.c @@ -414,7 +414,7 @@ int ptep_set_access_flags(struct vm_area_struct *vma, if (changed && dirty) { *ptep = entry; - pte_update_defer(vma->vm_mm, address, ptep); + pte_update(vma->vm_mm, address, ptep); } return changed; @@ -431,7 +431,6 @@ int pmdp_set_access_flags(struct vm_area_struct *vma, if (changed && dirty) { *pmdp = entry; - pmd_update_defer(vma->vm_mm, address, pmdp); /* * We had a write-protection fault here and changed the pmd * to to more permissive. No need to flush the TLB for that, @@ -469,9 +468,6 @@ int pmdp_test_and_clear_young(struct vm_area_struct *vma, ret = test_and_clear_bit(_PAGE_BIT_ACCESSED, (unsigned long *)pmdp); - if (ret) - pmd_update(vma->vm_mm, addr, pmdp); - return ret; } #endif @@ -518,7 +514,6 @@ void pmdp_splitting_flush(struct vm_area_struct *vma, set = !test_and_set_bit(_PAGE_BIT_SPLITTING, (unsigned long *)pmdp); if (set) { - pmd_update(vma->vm_mm, address, pmdp); /* need tlb flush only to serialize against gup-fast */ flush_tlb_range(vma, address, address + HPAGE_PMD_SIZE); } diff --git a/arch/x86/mm/setup_nx.c b/arch/x86/mm/setup_nx.c index 90555bf60aa4..92e2eacb3321 100644 --- a/arch/x86/mm/setup_nx.c +++ b/arch/x86/mm/setup_nx.c @@ -31,7 +31,7 @@ early_param("noexec", noexec_setup); void x86_configure_nx(void) { - if (cpu_has_nx && !disable_nx) + if (boot_cpu_has(X86_FEATURE_NX) && !disable_nx) __supported_pte_mask |= _PAGE_NX; else __supported_pte_mask &= ~_PAGE_NX; @@ -39,7 +39,7 @@ void x86_configure_nx(void) void __init x86_report_nx(void) { - if (!cpu_has_nx) { + if (!boot_cpu_has(X86_FEATURE_NX)) { printk(KERN_NOTICE "Notice: NX (Execute Disable) protection " "missing in CPU!\n"); } else { diff --git a/arch/x86/mm/srat.c b/arch/x86/mm/srat.c index c2aea63bee20..b5f821881465 100644 --- a/arch/x86/mm/srat.c +++ b/arch/x86/mm/srat.c @@ -203,6 +203,8 @@ acpi_numa_memory_affinity_init(struct acpi_srat_mem_affinity *ma) pr_warn("SRAT: Failed to mark hotplug range [mem %#010Lx-%#010Lx] in memblock\n", (unsigned long long)start, (unsigned long long)end - 1); + max_possible_pfn = max(max_possible_pfn, PFN_UP(end - 1)); + return 0; out_err_bad_srat: bad_srat(); diff --git a/arch/x86/pci/bus_numa.c b/arch/x86/pci/bus_numa.c index 7bcf06a7cd12..6eb3c8af96e2 100644 --- a/arch/x86/pci/bus_numa.c +++ b/arch/x86/pci/bus_numa.c @@ -50,18 +50,9 @@ void x86_pci_root_bus_resources(int bus, struct list_head *resources) if (!found) pci_add_resource(resources, &info->busn); - list_for_each_entry(root_res, &info->resources, list) { - struct resource *res; - struct resource *root; + list_for_each_entry(root_res, &info->resources, list) + pci_add_resource(resources, &root_res->res); - res = &root_res->res; - pci_add_resource(resources, res); - if (res->flags & IORESOURCE_IO) - root = &ioport_resource; - else - root = &iomem_resource; - insert_resource(root, res); - } return; default_resources: diff --git a/arch/x86/platform/uv/uv_nmi.c b/arch/x86/platform/uv/uv_nmi.c index 327f21c3bde1..8dd80050d705 100644 --- a/arch/x86/platform/uv/uv_nmi.c +++ b/arch/x86/platform/uv/uv_nmi.c @@ -28,6 +28,7 @@ #include <linux/nmi.h> #include <linux/sched.h> #include <linux/slab.h> +#include <linux/clocksource.h> #include <asm/apic.h> #include <asm/current.h> diff --git a/arch/x86/power/cpu.c b/arch/x86/power/cpu.c index 9ab52791fed5..d5f64996394a 100644 --- a/arch/x86/power/cpu.c +++ b/arch/x86/power/cpu.c @@ -23,6 +23,7 @@ #include <asm/debugreg.h> #include <asm/cpu.h> #include <asm/mmu_context.h> +#include <linux/dmi.h> #ifdef CONFIG_X86_32 __visible unsigned long saved_context_ebx; @@ -32,6 +33,29 @@ __visible unsigned long saved_context_eflags; #endif struct saved_context saved_context; +static void msr_save_context(struct saved_context *ctxt) +{ + struct saved_msr *msr = ctxt->saved_msrs.array; + struct saved_msr *end = msr + ctxt->saved_msrs.num; + + while (msr < end) { + msr->valid = !rdmsrl_safe(msr->info.msr_no, &msr->info.reg.q); + msr++; + } +} + +static void msr_restore_context(struct saved_context *ctxt) +{ + struct saved_msr *msr = ctxt->saved_msrs.array; + struct saved_msr *end = msr + ctxt->saved_msrs.num; + + while (msr < end) { + if (msr->valid) + wrmsrl(msr->info.msr_no, msr->info.reg.q); + msr++; + } +} + /** * __save_processor_state - save CPU registers before creating a * hibernation image and before restoring the memory state from it @@ -111,6 +135,7 @@ static void __save_processor_state(struct saved_context *ctxt) #endif ctxt->misc_enable_saved = !rdmsrl_safe(MSR_IA32_MISC_ENABLE, &ctxt->misc_enable); + msr_save_context(ctxt); } /* Needed by apm.c */ @@ -229,6 +254,7 @@ static void notrace __restore_processor_state(struct saved_context *ctxt) x86_platform.restore_sched_clock_state(); mtrr_bp_restore(); perf_restore_debug_store(); + msr_restore_context(ctxt); } /* Needed by apm.c */ @@ -320,3 +346,69 @@ static int __init bsp_pm_check_init(void) } core_initcall(bsp_pm_check_init); + +static int msr_init_context(const u32 *msr_id, const int total_num) +{ + int i = 0; + struct saved_msr *msr_array; + + if (saved_context.saved_msrs.array || saved_context.saved_msrs.num > 0) { + pr_err("x86/pm: MSR quirk already applied, please check your DMI match table.\n"); + return -EINVAL; + } + + msr_array = kmalloc_array(total_num, sizeof(struct saved_msr), GFP_KERNEL); + if (!msr_array) { + pr_err("x86/pm: Can not allocate memory to save/restore MSRs during suspend.\n"); + return -ENOMEM; + } + + for (i = 0; i < total_num; i++) { + msr_array[i].info.msr_no = msr_id[i]; + msr_array[i].valid = false; + msr_array[i].info.reg.q = 0; + } + saved_context.saved_msrs.num = total_num; + saved_context.saved_msrs.array = msr_array; + + return 0; +} + +/* + * The following section is a quirk framework for problematic BIOSen: + * Sometimes MSRs are modified by the BIOSen after suspended to + * RAM, this might cause unexpected behavior after wakeup. + * Thus we save/restore these specified MSRs across suspend/resume + * in order to work around it. + * + * For any further problematic BIOSen/platforms, + * please add your own function similar to msr_initialize_bdw. + */ +static int msr_initialize_bdw(const struct dmi_system_id *d) +{ + /* Add any extra MSR ids into this array. */ + u32 bdw_msr_id[] = { MSR_IA32_THERM_CONTROL }; + + pr_info("x86/pm: %s detected, MSR saving is needed during suspending.\n", d->ident); + return msr_init_context(bdw_msr_id, ARRAY_SIZE(bdw_msr_id)); +} + +static struct dmi_system_id msr_save_dmi_table[] = { + { + .callback = msr_initialize_bdw, + .ident = "BROADWELL BDX_EP", + .matches = { + DMI_MATCH(DMI_PRODUCT_NAME, "GRANTLEY"), + DMI_MATCH(DMI_PRODUCT_VERSION, "E63448-400"), + }, + }, + {} +}; + +static int pm_check_save_msr(void) +{ + dmi_check_system(msr_save_dmi_table); + return 0; +} + +device_initcall(pm_check_save_msr); diff --git a/arch/x86/um/signal.c b/arch/x86/um/signal.c index 06934a8a4872..14fcd01ed992 100644 --- a/arch/x86/um/signal.c +++ b/arch/x86/um/signal.c @@ -211,7 +211,7 @@ static int copy_sc_from_user(struct pt_regs *regs, if (err) return 1; - err = convert_fxsr_from_user(&fpx, sc.fpstate); + err = convert_fxsr_from_user(&fpx, (void *)sc.fpstate); if (err) return 1; @@ -227,7 +227,7 @@ static int copy_sc_from_user(struct pt_regs *regs, { struct user_i387_struct fp; - err = copy_from_user(&fp, sc.fpstate, + err = copy_from_user(&fp, (void *)sc.fpstate, sizeof(struct user_i387_struct)); if (err) return 1; @@ -291,7 +291,7 @@ static int copy_sc_to_user(struct sigcontext __user *to, #endif #undef PUTREG sc.oldmask = mask; - sc.fpstate = to_fp; + sc.fpstate = (unsigned long)to_fp; err = copy_to_user(to, &sc, sizeof(struct sigcontext)); if (err) @@ -468,12 +468,10 @@ long sys_sigreturn(void) struct sigframe __user *frame = (struct sigframe __user *)(sp - 8); sigset_t set; struct sigcontext __user *sc = &frame->sc; - unsigned long __user *oldmask = &sc->oldmask; - unsigned long __user *extramask = frame->extramask; int sig_size = (_NSIG_WORDS - 1) * sizeof(unsigned long); - if (copy_from_user(&set.sig[0], oldmask, sizeof(set.sig[0])) || - copy_from_user(&set.sig[1], extramask, sig_size)) + if (copy_from_user(&set.sig[0], &sc->oldmask, sizeof(set.sig[0])) || + copy_from_user(&set.sig[1], frame->extramask, sig_size)) goto segfault; set_current_blocked(&set); @@ -505,6 +503,7 @@ int setup_signal_stack_si(unsigned long stack_top, struct ksignal *ksig, { struct rt_sigframe __user *frame; int err = 0, sig = ksig->sig; + unsigned long fp_to; frame = (struct rt_sigframe __user *) round_down(stack_top - sizeof(struct rt_sigframe), 16); @@ -526,7 +525,10 @@ int setup_signal_stack_si(unsigned long stack_top, struct ksignal *ksig, err |= __save_altstack(&frame->uc.uc_stack, PT_REGS_SP(regs)); err |= copy_sc_to_user(&frame->uc.uc_mcontext, &frame->fpstate, regs, set->sig[0]); - err |= __put_user(&frame->fpstate, &frame->uc.uc_mcontext.fpstate); + + fp_to = (unsigned long)&frame->fpstate; + + err |= __put_user(fp_to, &frame->uc.uc_mcontext.fpstate); if (sizeof(*set) == 16) { err |= __put_user(set->sig[0], &frame->uc.uc_sigmask.sig[0]); err |= __put_user(set->sig[1], &frame->uc.uc_sigmask.sig[1]); diff --git a/arch/x86/xen/enlighten.c b/arch/x86/xen/enlighten.c index 5774800ff583..23063923e364 100644 --- a/arch/x86/xen/enlighten.c +++ b/arch/x86/xen/enlighten.c @@ -1192,7 +1192,7 @@ static const struct pv_info xen_info __initconst = { #ifdef CONFIG_X86_64 .extra_user_64bit_cs = FLAT_USER_CS64, #endif - + .features = 0, .name = "Xen", }; @@ -1229,10 +1229,7 @@ static const struct pv_cpu_ops xen_cpu_ops __initconst = { .iret = xen_iret, #ifdef CONFIG_X86_64 - .usergs_sysret32 = xen_sysret32, .usergs_sysret64 = xen_sysret64, -#else - .irq_enable_sysexit = xen_sysexit, #endif .load_tr_desc = paravirt_nop, @@ -1265,12 +1262,6 @@ static const struct pv_cpu_ops xen_cpu_ops __initconst = { .end_context_switch = xen_end_context_switch, }; -static const struct pv_apic_ops xen_apic_ops __initconst = { -#ifdef CONFIG_X86_LOCAL_APIC - .startup_ipi_hook = paravirt_nop, -#endif -}; - static void xen_reboot(int reason) { struct sched_shutdown r = { .reason = reason }; @@ -1535,8 +1526,9 @@ asmlinkage __visible void __init xen_start_kernel(void) /* Install Xen paravirt ops */ pv_info = xen_info; + if (xen_initial_domain()) + pv_info.features |= PV_SUPPORTED_RTC; pv_init_ops = xen_init_ops; - pv_apic_ops = xen_apic_ops; if (!xen_pvh_domain()) { pv_cpu_ops = xen_cpu_ops; @@ -1886,8 +1878,10 @@ EXPORT_SYMBOL_GPL(xen_hvm_need_lapic); static void xen_set_cpu_features(struct cpuinfo_x86 *c) { - if (xen_pv_domain()) + if (xen_pv_domain()) { clear_cpu_bug(c, X86_BUG_SYSRET_SS_ATTRS); + set_cpu_cap(c, X86_FEATURE_XENPV); + } } const struct hypervisor_x86 x86_hyper_xen = { diff --git a/arch/x86/xen/mmu.c b/arch/x86/xen/mmu.c index ac161db63388..c913ca4f6958 100644 --- a/arch/x86/xen/mmu.c +++ b/arch/x86/xen/mmu.c @@ -2436,7 +2436,6 @@ static const struct pv_mmu_ops xen_mmu_ops __initconst = { .flush_tlb_others = xen_flush_tlb_others, .pte_update = paravirt_nop, - .pte_update_defer = paravirt_nop, .pgd_alloc = xen_pgd_alloc, .pgd_free = xen_pgd_free, @@ -2495,14 +2494,9 @@ void __init xen_init_mmu_ops(void) { x86_init.paging.pagetable_init = xen_pagetable_init; - /* Optimization - we can use the HVM one but it has no idea which - * VCPUs are descheduled - which means that it will needlessly IPI - * them. Xen knows so let it do the job. - */ - if (xen_feature(XENFEAT_auto_translated_physmap)) { - pv_mmu_ops.flush_tlb_others = xen_flush_tlb_others; + if (xen_feature(XENFEAT_auto_translated_physmap)) return; - } + pv_mmu_ops = xen_mmu_ops; memset(dummy_mapping, 0xff, PAGE_SIZE); diff --git a/arch/x86/xen/suspend.c b/arch/x86/xen/suspend.c index feddabdab448..df0c40559583 100644 --- a/arch/x86/xen/suspend.c +++ b/arch/x86/xen/suspend.c @@ -1,6 +1,7 @@ #include <linux/types.h> #include <linux/tick.h> +#include <xen/xen.h> #include <xen/interface/xen.h> #include <xen/grant_table.h> #include <xen/events.h> @@ -68,26 +69,16 @@ static void xen_pv_post_suspend(int suspend_cancelled) void xen_arch_pre_suspend(void) { - int cpu; - - for_each_online_cpu(cpu) - xen_pmu_finish(cpu); - if (xen_pv_domain()) xen_pv_pre_suspend(); } void xen_arch_post_suspend(int cancelled) { - int cpu; - if (xen_pv_domain()) xen_pv_post_suspend(cancelled); else xen_hvm_post_suspend(cancelled); - - for_each_online_cpu(cpu) - xen_pmu_init(cpu); } static void xen_vcpu_notify_restore(void *data) @@ -106,10 +97,20 @@ static void xen_vcpu_notify_suspend(void *data) void xen_arch_resume(void) { + int cpu; + on_each_cpu(xen_vcpu_notify_restore, NULL, 1); + + for_each_online_cpu(cpu) + xen_pmu_init(cpu); } void xen_arch_suspend(void) { + int cpu; + + for_each_online_cpu(cpu) + xen_pmu_finish(cpu); + on_each_cpu(xen_vcpu_notify_suspend, NULL, 1); } diff --git a/arch/x86/xen/xen-asm_32.S b/arch/x86/xen/xen-asm_32.S index fd92a64d748e..feb6d40a0860 100644 --- a/arch/x86/xen/xen-asm_32.S +++ b/arch/x86/xen/xen-asm_32.S @@ -35,20 +35,6 @@ check_events: ret /* - * We can't use sysexit directly, because we're not running in ring0. - * But we can easily fake it up using iret. Assuming xen_sysexit is - * jumped to with a standard stack frame, we can just strip it back to - * a standard iret frame and use iret. - */ -ENTRY(xen_sysexit) - movl PT_EAX(%esp), %eax /* Shouldn't be necessary? */ - orl $X86_EFLAGS_IF, PT_EFLAGS(%esp) - lea PT_EIP(%esp), %esp - - jmp xen_iret -ENDPROC(xen_sysexit) - -/* * This is run where a normal iret would be run, with the same stack setup: * 8: eflags * 4: cs diff --git a/arch/x86/xen/xen-asm_64.S b/arch/x86/xen/xen-asm_64.S index f22667abf7b9..cc8acc410ddb 100644 --- a/arch/x86/xen/xen-asm_64.S +++ b/arch/x86/xen/xen-asm_64.S @@ -68,25 +68,6 @@ ENTRY(xen_sysret64) ENDPATCH(xen_sysret64) RELOC(xen_sysret64, 1b+1) -ENTRY(xen_sysret32) - /* - * We're already on the usermode stack at this point, but - * still with the kernel gs, so we can easily switch back - */ - movq %rsp, PER_CPU_VAR(rsp_scratch) - movq PER_CPU_VAR(cpu_current_top_of_stack), %rsp - - pushq $__USER32_DS - pushq PER_CPU_VAR(rsp_scratch) - pushq %r11 - pushq $__USER32_CS - pushq %rcx - - pushq $0 -1: jmp hypercall_iret -ENDPATCH(xen_sysret32) -RELOC(xen_sysret32, 1b+1) - /* * Xen handles syscall callbacks much like ordinary exceptions, which * means we have: diff --git a/arch/x86/xen/xen-ops.h b/arch/x86/xen/xen-ops.h index 1399423f3418..4140b070f2e9 100644 --- a/arch/x86/xen/xen-ops.h +++ b/arch/x86/xen/xen-ops.h @@ -139,9 +139,6 @@ DECL_ASM(void, xen_restore_fl_direct, unsigned long); /* These are not functions, and cannot be called normally */ __visible void xen_iret(void); -#ifdef CONFIG_X86_32 -__visible void xen_sysexit(void); -#endif __visible void xen_sysret32(void); __visible void xen_sysret64(void); __visible void xen_adjust_exception_frame(void); |