diff options
Diffstat (limited to 'arch')
653 files changed, 11445 insertions, 6559 deletions
diff --git a/arch/Kconfig b/arch/Kconfig index ded747c7b74c..f1cf895c040f 100644 --- a/arch/Kconfig +++ b/arch/Kconfig @@ -207,9 +207,6 @@ config HAVE_DMA_ATTRS config HAVE_DMA_CONTIGUOUS bool -config USE_GENERIC_SMP_HELPERS - bool - config GENERIC_SMP_IDLE_THREAD bool diff --git a/arch/alpha/Kconfig b/arch/alpha/Kconfig index 35a300d4a9fb..d39dc9b95a2c 100644 --- a/arch/alpha/Kconfig +++ b/arch/alpha/Kconfig @@ -1,6 +1,7 @@ config ALPHA bool default y + select ARCH_MIGHT_HAVE_PC_PARPORT select HAVE_AOUT select HAVE_IDE select HAVE_OPROFILE @@ -15,8 +16,8 @@ config ALPHA select ARCH_WANT_IPC_PARSE_VERSION select ARCH_HAVE_NMI_SAFE_CMPXCHG select ARCH_HAS_ATOMIC64_DEC_IF_POSITIVE + select GENERIC_CLOCKEVENTS select GENERIC_SMP_IDLE_THREAD - select GENERIC_CMOS_UPDATE select GENERIC_STRNCPY_FROM_USER select GENERIC_STRNLEN_USER select HAVE_MOD_ARCH_SPECIFIC @@ -487,6 +488,20 @@ config VGA_HOSE which always have multiple hoses, and whose consoles support it. +config ALPHA_QEMU + bool "Run under QEMU emulation" + depends on !ALPHA_GENERIC + ---help--- + Assume the presence of special features supported by QEMU PALcode + that reduce the overhead of system emulation. + + Generic kernels will auto-detect QEMU. But when building a + system-specific kernel, the assumption is that we want to + elimiate as many runtime tests as possible. + + If unsure, say N. + + config ALPHA_SRM bool "Use SRM as bootloader" if ALPHA_CABRIOLET || ALPHA_AVANTI_CH || ALPHA_EB64P || ALPHA_PC164 || ALPHA_TAKARA || ALPHA_EB164 || ALPHA_ALCOR || ALPHA_MIATA || ALPHA_LX164 || ALPHA_SX164 || ALPHA_NAUTILUS || ALPHA_NONAME depends on TTY @@ -522,7 +537,6 @@ config ARCH_MAY_HAVE_PC_FDC config SMP bool "Symmetric multi-processing support" depends on ALPHA_SABLE || ALPHA_LYNX || ALPHA_RAWHIDE || ALPHA_DP264 || ALPHA_WILDFIRE || ALPHA_TITAN || ALPHA_GENERIC || ALPHA_SHARK || ALPHA_MARVEL - select USE_GENERIC_SMP_HELPERS ---help--- This enables support for systems with more than one CPU. If you have a system with only one CPU, like most personal computers, say N. If @@ -572,6 +586,30 @@ config NUMA Access). This option is for configuring high-end multiprocessor server machines. If in doubt, say N. +config ALPHA_WTINT + bool "Use WTINT" if ALPHA_SRM || ALPHA_GENERIC + default y if ALPHA_QEMU + default n if ALPHA_EV5 || ALPHA_EV56 || (ALPHA_EV4 && !ALPHA_LCA) + default n if !ALPHA_SRM && !ALPHA_GENERIC + default y if SMP + ---help--- + The Wait for Interrupt (WTINT) PALcall attempts to place the CPU + to sleep until the next interrupt. This may reduce the power + consumed, and the heat produced by the computer. However, it has + the side effect of making the cycle counter unreliable as a timing + device across the sleep. + + For emulation under QEMU, definitely say Y here, as we have other + mechanisms for measuring time than the cycle counter. + + For EV4 (but not LCA), EV5 and EV56 systems, or for systems running + MILO, sleep mode is not supported so you might as well say N here. + + For SMP systems we cannot use the cycle counter for timing anyway, + so you might as well say Y here. + + If unsure, say N. + config NODES_SHIFT int default "7" @@ -613,9 +651,41 @@ config VERBOSE_MCHECK_ON Take the default (1) unless you want more control or more info. +choice + prompt "Timer interrupt frequency (HZ)?" + default HZ_128 if ALPHA_QEMU + default HZ_1200 if ALPHA_RAWHIDE + default HZ_1024 + ---help--- + The frequency at which timer interrupts occur. A high frequency + minimizes latency, whereas a low frequency minimizes overhead of + process accounting. The later effect is especially significant + when being run under QEMU. + + Note that some Alpha hardware cannot change the interrupt frequency + of the timer. If unsure, say 1024 (or 1200 for Rawhide). + + config HZ_32 + bool "32 Hz" + config HZ_64 + bool "64 Hz" + config HZ_128 + bool "128 Hz" + config HZ_256 + bool "256 Hz" + config HZ_1024 + bool "1024 Hz" + config HZ_1200 + bool "1200 Hz" +endchoice + config HZ - int - default 1200 if ALPHA_RAWHIDE + int + default 32 if HZ_32 + default 64 if HZ_64 + default 128 if HZ_128 + default 256 if HZ_256 + default 1200 if HZ_1200 default 1024 source "drivers/pci/Kconfig" diff --git a/arch/alpha/include/asm/machvec.h b/arch/alpha/include/asm/machvec.h index 72dbf2359270..75cb3641ed2f 100644 --- a/arch/alpha/include/asm/machvec.h +++ b/arch/alpha/include/asm/machvec.h @@ -33,6 +33,7 @@ struct alpha_machine_vector int nr_irqs; int rtc_port; + int rtc_boot_cpu_only; unsigned int max_asn; unsigned long max_isa_dma_address; unsigned long irq_probe_mask; @@ -95,9 +96,6 @@ struct alpha_machine_vector struct _alpha_agp_info *(*agp_info)(void); - unsigned int (*rtc_get_time)(struct rtc_time *); - int (*rtc_set_time)(struct rtc_time *); - const char *vector_name; /* NUMA information */ @@ -126,13 +124,19 @@ extern struct alpha_machine_vector alpha_mv; #ifdef CONFIG_ALPHA_GENERIC extern int alpha_using_srm; +extern int alpha_using_qemu; #else -#ifdef CONFIG_ALPHA_SRM -#define alpha_using_srm 1 -#else -#define alpha_using_srm 0 -#endif +# ifdef CONFIG_ALPHA_SRM +# define alpha_using_srm 1 +# else +# define alpha_using_srm 0 +# endif +# ifdef CONFIG_ALPHA_QEMU +# define alpha_using_qemu 1 +# else +# define alpha_using_qemu 0 +# endif #endif /* GENERIC */ -#endif +#endif /* __KERNEL__ */ #endif /* __ALPHA_MACHVEC_H */ diff --git a/arch/alpha/include/asm/pal.h b/arch/alpha/include/asm/pal.h index 6fcd2b5b08f0..5422a47646fc 100644 --- a/arch/alpha/include/asm/pal.h +++ b/arch/alpha/include/asm/pal.h @@ -89,6 +89,7 @@ __CALL_PAL_W1(wrmces, unsigned long); __CALL_PAL_RW2(wrperfmon, unsigned long, unsigned long, unsigned long); __CALL_PAL_W1(wrusp, unsigned long); __CALL_PAL_W1(wrvptptr, unsigned long); +__CALL_PAL_RW1(wtint, unsigned long, unsigned long); /* * TB routines.. @@ -111,5 +112,75 @@ __CALL_PAL_W1(wrvptptr, unsigned long); #define tbiap() __tbi(-1, /* no second argument */) #define tbia() __tbi(-2, /* no second argument */) +/* + * QEMU Cserv routines.. + */ + +static inline unsigned long +qemu_get_walltime(void) +{ + register unsigned long v0 __asm__("$0"); + register unsigned long a0 __asm__("$16") = 3; + + asm("call_pal %2 # cserve get_time" + : "=r"(v0), "+r"(a0) + : "i"(PAL_cserve) + : "$17", "$18", "$19", "$20", "$21"); + + return v0; +} + +static inline unsigned long +qemu_get_alarm(void) +{ + register unsigned long v0 __asm__("$0"); + register unsigned long a0 __asm__("$16") = 4; + + asm("call_pal %2 # cserve get_alarm" + : "=r"(v0), "+r"(a0) + : "i"(PAL_cserve) + : "$17", "$18", "$19", "$20", "$21"); + + return v0; +} + +static inline void +qemu_set_alarm_rel(unsigned long expire) +{ + register unsigned long a0 __asm__("$16") = 5; + register unsigned long a1 __asm__("$17") = expire; + + asm volatile("call_pal %2 # cserve set_alarm_rel" + : "+r"(a0), "+r"(a1) + : "i"(PAL_cserve) + : "$0", "$18", "$19", "$20", "$21"); +} + +static inline void +qemu_set_alarm_abs(unsigned long expire) +{ + register unsigned long a0 __asm__("$16") = 6; + register unsigned long a1 __asm__("$17") = expire; + + asm volatile("call_pal %2 # cserve set_alarm_abs" + : "+r"(a0), "+r"(a1) + : "i"(PAL_cserve) + : "$0", "$18", "$19", "$20", "$21"); +} + +static inline unsigned long +qemu_get_vmtime(void) +{ + register unsigned long v0 __asm__("$0"); + register unsigned long a0 __asm__("$16") = 7; + + asm("call_pal %2 # cserve get_time" + : "=r"(v0), "+r"(a0) + : "i"(PAL_cserve) + : "$17", "$18", "$19", "$20", "$21"); + + return v0; +} + #endif /* !__ASSEMBLY__ */ #endif /* __ALPHA_PAL_H */ diff --git a/arch/alpha/include/asm/pgalloc.h b/arch/alpha/include/asm/pgalloc.h index bc2a0daf2d92..aab14a019c20 100644 --- a/arch/alpha/include/asm/pgalloc.h +++ b/arch/alpha/include/asm/pgalloc.h @@ -72,7 +72,10 @@ pte_alloc_one(struct mm_struct *mm, unsigned long address) if (!pte) return NULL; page = virt_to_page(pte); - pgtable_page_ctor(page); + if (!pgtable_page_ctor(page)) { + __free_page(page); + return NULL; + } return page; } diff --git a/arch/alpha/include/asm/rtc.h b/arch/alpha/include/asm/rtc.h index d70408d36677..f71c3b0ed360 100644 --- a/arch/alpha/include/asm/rtc.h +++ b/arch/alpha/include/asm/rtc.h @@ -1,12 +1 @@ -#ifndef _ALPHA_RTC_H -#define _ALPHA_RTC_H - -#if defined(CONFIG_ALPHA_MARVEL) && defined(CONFIG_SMP) \ - || defined(CONFIG_ALPHA_GENERIC) -# define get_rtc_time alpha_mv.rtc_get_time -# define set_rtc_time alpha_mv.rtc_set_time -#endif - #include <asm-generic/rtc.h> - -#endif diff --git a/arch/alpha/include/asm/string.h b/arch/alpha/include/asm/string.h index b02b8a282940..c2911f591704 100644 --- a/arch/alpha/include/asm/string.h +++ b/arch/alpha/include/asm/string.h @@ -22,15 +22,27 @@ extern void * __memcpy(void *, const void *, size_t); #define __HAVE_ARCH_MEMSET extern void * __constant_c_memset(void *, unsigned long, size_t); +extern void * ___memset(void *, int, size_t); extern void * __memset(void *, int, size_t); extern void * memset(void *, int, size_t); -#define memset(s, c, n) \ -(__builtin_constant_p(c) \ - ? (__builtin_constant_p(n) && (c) == 0 \ - ? __builtin_memset((s),0,(n)) \ - : __constant_c_memset((s),0x0101010101010101UL*(unsigned char)(c),(n))) \ - : __memset((s),(c),(n))) +/* For gcc 3.x, we cannot have the inline function named "memset" because + the __builtin_memset will attempt to resolve to the inline as well, + leading to a "sorry" about unimplemented recursive inlining. */ +extern inline void *__memset(void *s, int c, size_t n) +{ + if (__builtin_constant_p(c)) { + if (__builtin_constant_p(n)) { + return __builtin_memset(s, c, n); + } else { + unsigned long c8 = (c & 0xff) * 0x0101010101010101UL; + return __constant_c_memset(s, c8, n); + } + } + return ___memset(s, c, n); +} + +#define memset __memset #define __HAVE_ARCH_STRCPY extern char * strcpy(char *,const char *); diff --git a/arch/alpha/include/asm/thread_info.h b/arch/alpha/include/asm/thread_info.h index 52cd2a4a3ff4..453597b91f3a 100644 --- a/arch/alpha/include/asm/thread_info.h +++ b/arch/alpha/include/asm/thread_info.h @@ -58,8 +58,6 @@ register struct thread_info *__current_thread_info __asm__("$8"); #define THREAD_SIZE_ORDER 1 #define THREAD_SIZE (2*PAGE_SIZE) -#define PREEMPT_ACTIVE 0x40000000 - /* * Thread information flags: * - these are process state flags and used from assembly diff --git a/arch/alpha/include/uapi/asm/pal.h b/arch/alpha/include/uapi/asm/pal.h index 3c0ce08e5f59..dfc8140b9088 100644 --- a/arch/alpha/include/uapi/asm/pal.h +++ b/arch/alpha/include/uapi/asm/pal.h @@ -46,6 +46,7 @@ #define PAL_rdusp 58 #define PAL_whami 60 #define PAL_retsys 61 +#define PAL_wtint 62 #define PAL_rti 63 diff --git a/arch/alpha/kernel/Makefile b/arch/alpha/kernel/Makefile index 84ec46b38f7d..0d54650e78fc 100644 --- a/arch/alpha/kernel/Makefile +++ b/arch/alpha/kernel/Makefile @@ -16,6 +16,7 @@ obj-$(CONFIG_PCI) += pci.o pci_iommu.o pci-sysfs.o obj-$(CONFIG_SRM_ENV) += srm_env.o obj-$(CONFIG_MODULES) += module.o obj-$(CONFIG_PERF_EVENTS) += perf_event.o +obj-$(CONFIG_RTC_DRV_ALPHA) += rtc.o ifdef CONFIG_ALPHA_GENERIC diff --git a/arch/alpha/kernel/alpha_ksyms.c b/arch/alpha/kernel/alpha_ksyms.c index 89566b346c0f..f4c7ab6f43b0 100644 --- a/arch/alpha/kernel/alpha_ksyms.c +++ b/arch/alpha/kernel/alpha_ksyms.c @@ -40,6 +40,7 @@ EXPORT_SYMBOL(strrchr); EXPORT_SYMBOL(memmove); EXPORT_SYMBOL(__memcpy); EXPORT_SYMBOL(__memset); +EXPORT_SYMBOL(___memset); EXPORT_SYMBOL(__memsetw); EXPORT_SYMBOL(__constant_c_memset); EXPORT_SYMBOL(copy_page); diff --git a/arch/alpha/kernel/irq_alpha.c b/arch/alpha/kernel/irq_alpha.c index 28e4429596f3..1c8625cb0e25 100644 --- a/arch/alpha/kernel/irq_alpha.c +++ b/arch/alpha/kernel/irq_alpha.c @@ -66,21 +66,7 @@ do_entInt(unsigned long type, unsigned long vector, break; case 1: old_regs = set_irq_regs(regs); -#ifdef CONFIG_SMP - { - long cpu; - - smp_percpu_timer_interrupt(regs); - cpu = smp_processor_id(); - if (cpu != boot_cpuid) { - kstat_incr_irqs_this_cpu(RTC_IRQ, irq_to_desc(RTC_IRQ)); - } else { - handle_irq(RTC_IRQ); - } - } -#else handle_irq(RTC_IRQ); -#endif set_irq_regs(old_regs); return; case 2: @@ -228,7 +214,7 @@ process_mcheck_info(unsigned long vector, unsigned long la_ptr, */ struct irqaction timer_irqaction = { - .handler = timer_interrupt, + .handler = rtc_timer_interrupt, .name = "timer", }; diff --git a/arch/alpha/kernel/machvec_impl.h b/arch/alpha/kernel/machvec_impl.h index 7fa62488bd16..f54bdf658cd0 100644 --- a/arch/alpha/kernel/machvec_impl.h +++ b/arch/alpha/kernel/machvec_impl.h @@ -43,10 +43,7 @@ #define CAT1(x,y) x##y #define CAT(x,y) CAT1(x,y) -#define DO_DEFAULT_RTC \ - .rtc_port = 0x70, \ - .rtc_get_time = common_get_rtc_time, \ - .rtc_set_time = common_set_rtc_time +#define DO_DEFAULT_RTC .rtc_port = 0x70 #define DO_EV4_MMU \ .max_asn = EV4_MAX_ASN, \ diff --git a/arch/alpha/kernel/perf_event.c b/arch/alpha/kernel/perf_event.c index d821b17047e0..c52e7f0ee5f6 100644 --- a/arch/alpha/kernel/perf_event.c +++ b/arch/alpha/kernel/perf_event.c @@ -83,6 +83,8 @@ struct alpha_pmu_t { long pmc_left[3]; /* Subroutine for allocation of PMCs. Enforces constraints. */ int (*check_constraints)(struct perf_event **, unsigned long *, int); + /* Subroutine for checking validity of a raw event for this PMU. */ + int (*raw_event_valid)(u64 config); }; /* @@ -203,6 +205,12 @@ success: } +static int ev67_raw_event_valid(u64 config) +{ + return config >= EV67_CYCLES && config < EV67_LAST_ET; +}; + + static const struct alpha_pmu_t ev67_pmu = { .event_map = ev67_perfmon_event_map, .max_events = ARRAY_SIZE(ev67_perfmon_event_map), @@ -211,7 +219,8 @@ static const struct alpha_pmu_t ev67_pmu = { .pmc_count_mask = {EV67_PCTR_0_COUNT_MASK, EV67_PCTR_1_COUNT_MASK, 0}, .pmc_max_period = {(1UL<<20) - 1, (1UL<<20) - 1, 0}, .pmc_left = {16, 4, 0}, - .check_constraints = ev67_check_constraints + .check_constraints = ev67_check_constraints, + .raw_event_valid = ev67_raw_event_valid, }; @@ -609,7 +618,9 @@ static int __hw_perf_event_init(struct perf_event *event) } else if (attr->type == PERF_TYPE_HW_CACHE) { return -EOPNOTSUPP; } else if (attr->type == PERF_TYPE_RAW) { - ev = attr->config & 0xff; + if (!alpha_pmu->raw_event_valid(attr->config)) + return -EINVAL; + ev = attr->config; } else { return -EOPNOTSUPP; } diff --git a/arch/alpha/kernel/process.c b/arch/alpha/kernel/process.c index f2360a74e5d5..1941a07b5811 100644 --- a/arch/alpha/kernel/process.c +++ b/arch/alpha/kernel/process.c @@ -46,6 +46,23 @@ void (*pm_power_off)(void) = machine_power_off; EXPORT_SYMBOL(pm_power_off); +#ifdef CONFIG_ALPHA_WTINT +/* + * Sleep the CPU. + * EV6, LCA45 and QEMU know how to power down, skipping N timer interrupts. + */ +void arch_cpu_idle(void) +{ + wtint(0); + local_irq_enable(); +} + +void arch_cpu_idle_dead(void) +{ + wtint(INT_MAX); +} +#endif /* ALPHA_WTINT */ + struct halt_info { int mode; char *restart_cmd; diff --git a/arch/alpha/kernel/proto.h b/arch/alpha/kernel/proto.h index d3e52d3fd592..da2d6ec9c370 100644 --- a/arch/alpha/kernel/proto.h +++ b/arch/alpha/kernel/proto.h @@ -135,17 +135,15 @@ extern void unregister_srm_console(void); /* smp.c */ extern void setup_smp(void); extern void handle_ipi(struct pt_regs *); -extern void smp_percpu_timer_interrupt(struct pt_regs *); /* bios32.c */ /* extern void reset_for_srm(void); */ /* time.c */ -extern irqreturn_t timer_interrupt(int irq, void *dev); +extern irqreturn_t rtc_timer_interrupt(int irq, void *dev); +extern void init_clockevent(void); extern void common_init_rtc(void); extern unsigned long est_cycle_freq; -extern unsigned int common_get_rtc_time(struct rtc_time *time); -extern int common_set_rtc_time(struct rtc_time *time); /* smc37c93x.c */ extern void SMC93x_Init(void); diff --git a/arch/alpha/kernel/rtc.c b/arch/alpha/kernel/rtc.c new file mode 100644 index 000000000000..c8d284d8521f --- /dev/null +++ b/arch/alpha/kernel/rtc.c @@ -0,0 +1,323 @@ +/* + * linux/arch/alpha/kernel/rtc.c + * + * Copyright (C) 1991, 1992, 1995, 1999, 2000 Linus Torvalds + * + * This file contains date handling. + */ +#include <linux/errno.h> +#include <linux/init.h> +#include <linux/kernel.h> +#include <linux/param.h> +#include <linux/string.h> +#include <linux/mc146818rtc.h> +#include <linux/bcd.h> +#include <linux/rtc.h> +#include <linux/platform_device.h> + +#include <asm/rtc.h> + +#include "proto.h" + + +/* + * Support for the RTC device. + * + * We don't want to use the rtc-cmos driver, because we don't want to support + * alarms, as that would be indistinguishable from timer interrupts. + * + * Further, generic code is really, really tied to a 1900 epoch. This is + * true in __get_rtc_time as well as the users of struct rtc_time e.g. + * rtc_tm_to_time. Thankfully all of the other epochs in use are later + * than 1900, and so it's easy to adjust. + */ + +static unsigned long rtc_epoch; + +static int __init +specifiy_epoch(char *str) +{ + unsigned long epoch = simple_strtoul(str, NULL, 0); + if (epoch < 1900) + printk("Ignoring invalid user specified epoch %lu\n", epoch); + else + rtc_epoch = epoch; + return 1; +} +__setup("epoch=", specifiy_epoch); + +static void __init +init_rtc_epoch(void) +{ + int epoch, year, ctrl; + + if (rtc_epoch != 0) { + /* The epoch was specified on the command-line. */ + return; + } + + /* Detect the epoch in use on this computer. */ + ctrl = CMOS_READ(RTC_CONTROL); + year = CMOS_READ(RTC_YEAR); + if (!(ctrl & RTC_DM_BINARY) || RTC_ALWAYS_BCD) + year = bcd2bin(year); + + /* PC-like is standard; used for year >= 70 */ + epoch = 1900; + if (year < 20) { + epoch = 2000; + } else if (year >= 20 && year < 48) { + /* NT epoch */ + epoch = 1980; + } else if (year >= 48 && year < 70) { + /* Digital UNIX epoch */ + epoch = 1952; + } + rtc_epoch = epoch; + + printk(KERN_INFO "Using epoch %d for rtc year %d\n", epoch, year); +} + +static int +alpha_rtc_read_time(struct device *dev, struct rtc_time *tm) +{ + __get_rtc_time(tm); + + /* Adjust for non-default epochs. It's easier to depend on the + generic __get_rtc_time and adjust the epoch here than create + a copy of __get_rtc_time with the edits we need. */ + if (rtc_epoch != 1900) { + int year = tm->tm_year; + /* Undo the century adjustment made in __get_rtc_time. */ + if (year >= 100) + year -= 100; + year += rtc_epoch - 1900; + /* Redo the century adjustment with the epoch in place. */ + if (year <= 69) + year += 100; + tm->tm_year = year; + } + + return rtc_valid_tm(tm); +} + +static int +alpha_rtc_set_time(struct device *dev, struct rtc_time *tm) +{ + struct rtc_time xtm; + + if (rtc_epoch != 1900) { + xtm = *tm; + xtm.tm_year -= rtc_epoch - 1900; + tm = &xtm; + } + + return __set_rtc_time(tm); +} + +static int +alpha_rtc_set_mmss(struct device *dev, unsigned long nowtime) +{ + int retval = 0; + int real_seconds, real_minutes, cmos_minutes; + unsigned char save_control, save_freq_select; + + /* Note: This code only updates minutes and seconds. Comments + indicate this was to avoid messing with unknown time zones, + and with the epoch nonsense described above. In order for + this to work, the existing clock cannot be off by more than + 15 minutes. + + ??? This choice is may be out of date. The x86 port does + not have problems with timezones, and the epoch processing has + now been fixed in alpha_set_rtc_time. + + In either case, one can always force a full rtc update with + the userland hwclock program, so surely 15 minute accuracy + is no real burden. */ + + /* In order to set the CMOS clock precisely, we have to be called + 500 ms after the second nowtime has started, because when + nowtime is written into the registers of the CMOS clock, it will + jump to the next second precisely 500 ms later. Check the Motorola + MC146818A or Dallas DS12887 data sheet for details. */ + + /* irq are locally disabled here */ + spin_lock(&rtc_lock); + /* Tell the clock it's being set */ + save_control = CMOS_READ(RTC_CONTROL); + CMOS_WRITE((save_control|RTC_SET), RTC_CONTROL); + + /* Stop and reset prescaler */ + save_freq_select = CMOS_READ(RTC_FREQ_SELECT); + CMOS_WRITE((save_freq_select|RTC_DIV_RESET2), RTC_FREQ_SELECT); + + cmos_minutes = CMOS_READ(RTC_MINUTES); + if (!(save_control & RTC_DM_BINARY) || RTC_ALWAYS_BCD) + cmos_minutes = bcd2bin(cmos_minutes); + + real_seconds = nowtime % 60; + real_minutes = nowtime / 60; + if (((abs(real_minutes - cmos_minutes) + 15) / 30) & 1) { + /* correct for half hour time zone */ + real_minutes += 30; + } + real_minutes %= 60; + + if (abs(real_minutes - cmos_minutes) < 30) { + if (!(save_control & RTC_DM_BINARY) || RTC_ALWAYS_BCD) { + real_seconds = bin2bcd(real_seconds); + real_minutes = bin2bcd(real_minutes); + } + CMOS_WRITE(real_seconds,RTC_SECONDS); + CMOS_WRITE(real_minutes,RTC_MINUTES); + } else { + printk_once(KERN_NOTICE + "set_rtc_mmss: can't update from %d to %d\n", + cmos_minutes, real_minutes); + retval = -1; + } + + /* The following flags have to be released exactly in this order, + * otherwise the DS12887 (popular MC146818A clone with integrated + * battery and quartz) will not reset the oscillator and will not + * update precisely 500 ms later. You won't find this mentioned in + * the Dallas Semiconductor data sheets, but who believes data + * sheets anyway ... -- Markus Kuhn + */ + CMOS_WRITE(save_control, RTC_CONTROL); + CMOS_WRITE(save_freq_select, RTC_FREQ_SELECT); + spin_unlock(&rtc_lock); + + return retval; +} + +static int +alpha_rtc_ioctl(struct device *dev, unsigned int cmd, unsigned long arg) +{ + switch (cmd) { + case RTC_EPOCH_READ: + return put_user(rtc_epoch, (unsigned long __user *)arg); + case RTC_EPOCH_SET: + if (arg < 1900) + return -EINVAL; + rtc_epoch = arg; + return 0; + default: + return -ENOIOCTLCMD; + } +} + +static const struct rtc_class_ops alpha_rtc_ops = { + .read_time = alpha_rtc_read_time, + .set_time = alpha_rtc_set_time, + .set_mmss = alpha_rtc_set_mmss, + .ioctl = alpha_rtc_ioctl, +}; + +/* + * Similarly, except do the actual CMOS access on the boot cpu only. + * This requires marshalling the data across an interprocessor call. + */ + +#if defined(CONFIG_SMP) && \ + (defined(CONFIG_ALPHA_GENERIC) || defined(CONFIG_ALPHA_MARVEL)) +# define HAVE_REMOTE_RTC 1 + +union remote_data { + struct rtc_time *tm; + unsigned long now; + long retval; +}; + +static void +do_remote_read(void *data) +{ + union remote_data *x = data; + x->retval = alpha_rtc_read_time(NULL, x->tm); +} + +static int +remote_read_time(struct device *dev, struct rtc_time *tm) +{ + union remote_data x; + if (smp_processor_id() != boot_cpuid) { + x.tm = tm; + smp_call_function_single(boot_cpuid, do_remote_read, &x, 1); + return x.retval; + } + return alpha_rtc_read_time(NULL, tm); +} + +static void +do_remote_set(void *data) +{ + union remote_data *x = data; + x->retval = alpha_rtc_set_time(NULL, x->tm); +} + +static int +remote_set_time(struct device *dev, struct rtc_time *tm) +{ + union remote_data x; + if (smp_processor_id() != boot_cpuid) { + x.tm = tm; + smp_call_function_single(boot_cpuid, do_remote_set, &x, 1); + return x.retval; + } + return alpha_rtc_set_time(NULL, tm); +} + +static void +do_remote_mmss(void *data) +{ + union remote_data *x = data; + x->retval = alpha_rtc_set_mmss(NULL, x->now); +} + +static int +remote_set_mmss(struct device *dev, unsigned long now) +{ + union remote_data x; + if (smp_processor_id() != boot_cpuid) { + x.now = now; + smp_call_function_single(boot_cpuid, do_remote_mmss, &x, 1); + return x.retval; + } + return alpha_rtc_set_mmss(NULL, now); +} + +static const struct rtc_class_ops remote_rtc_ops = { + .read_time = remote_read_time, + .set_time = remote_set_time, + .set_mmss = remote_set_mmss, + .ioctl = alpha_rtc_ioctl, +}; +#endif + +static int __init +alpha_rtc_init(void) +{ + const struct rtc_class_ops *ops; + struct platform_device *pdev; + struct rtc_device *rtc; + const char *name; + + init_rtc_epoch(); + name = "rtc-alpha"; + ops = &alpha_rtc_ops; + +#ifdef HAVE_REMOTE_RTC + if (alpha_mv.rtc_boot_cpu_only) + ops = &remote_rtc_ops; +#endif + + pdev = platform_device_register_simple(name, -1, NULL, 0); + rtc = devm_rtc_device_register(&pdev->dev, name, ops, THIS_MODULE); + if (IS_ERR(rtc)) + return PTR_ERR(rtc); + + platform_set_drvdata(pdev, rtc); + return 0; +} +device_initcall(alpha_rtc_init); diff --git a/arch/alpha/kernel/setup.c b/arch/alpha/kernel/setup.c index 9e3107cc5ebb..b20af76f12c1 100644 --- a/arch/alpha/kernel/setup.c +++ b/arch/alpha/kernel/setup.c @@ -115,10 +115,17 @@ unsigned long alpha_agpgart_size = DEFAULT_AGP_APER_SIZE; #ifdef CONFIG_ALPHA_GENERIC struct alpha_machine_vector alpha_mv; +#endif + +#ifndef alpha_using_srm int alpha_using_srm; EXPORT_SYMBOL(alpha_using_srm); #endif +#ifndef alpha_using_qemu +int alpha_using_qemu; +#endif + static struct alpha_machine_vector *get_sysvec(unsigned long, unsigned long, unsigned long); static struct alpha_machine_vector *get_sysvec_byname(const char *); @@ -529,11 +536,15 @@ setup_arch(char **cmdline_p) atomic_notifier_chain_register(&panic_notifier_list, &alpha_panic_block); -#ifdef CONFIG_ALPHA_GENERIC +#ifndef alpha_using_srm /* Assume that we've booted from SRM if we haven't booted from MILO. Detect the later by looking for "MILO" in the system serial nr. */ alpha_using_srm = strncmp((const char *)hwrpb->ssn, "MILO", 4) != 0; #endif +#ifndef alpha_using_qemu + /* Similarly, look for QEMU. */ + alpha_using_qemu = strstr((const char *)hwrpb->ssn, "QEMU") != 0; +#endif /* If we are using SRM, we want to allow callbacks as early as possible, so do this NOW, and then @@ -1207,6 +1218,7 @@ show_cpuinfo(struct seq_file *f, void *slot) char *systype_name; char *sysvariation_name; int nr_processors; + unsigned long timer_freq; cpu_index = (unsigned) (cpu->type - 1); cpu_name = "Unknown"; @@ -1218,6 +1230,12 @@ show_cpuinfo(struct seq_file *f, void *slot) nr_processors = get_nr_processors(cpu, hwrpb->nr_processors); +#if CONFIG_HZ == 1024 || CONFIG_HZ == 1200 + timer_freq = (100UL * hwrpb->intr_freq) / 4096; +#else + timer_freq = 100UL * CONFIG_HZ; +#endif + seq_printf(f, "cpu\t\t\t: Alpha\n" "cpu model\t\t: %s\n" "cpu variation\t\t: %ld\n" @@ -1243,8 +1261,7 @@ show_cpuinfo(struct seq_file *f, void *slot) (char*)hwrpb->ssn, est_cycle_freq ? : hwrpb->cycle_freq, est_cycle_freq ? "est." : "", - hwrpb->intr_freq / 4096, - (100 * hwrpb->intr_freq / 4096) % 100, + timer_freq / 100, timer_freq % 100, hwrpb->pagesize, hwrpb->pa_bits, hwrpb->max_asn, diff --git a/arch/alpha/kernel/smp.c b/arch/alpha/kernel/smp.c index 9dbbcb3b9146..99ac36d5de4e 100644 --- a/arch/alpha/kernel/smp.c +++ b/arch/alpha/kernel/smp.c @@ -138,9 +138,11 @@ smp_callin(void) /* Get our local ticker going. */ smp_setup_percpu_timer(cpuid); + init_clockevent(); /* Call platform-specific callin, if specified */ - if (alpha_mv.smp_callin) alpha_mv.smp_callin(); + if (alpha_mv.smp_callin) + alpha_mv.smp_callin(); /* All kernel threads share the same mm context. */ atomic_inc(&init_mm.mm_count); @@ -498,35 +500,6 @@ smp_cpus_done(unsigned int max_cpus) ((bogosum + 2500) / (5000/HZ)) % 100); } - -void -smp_percpu_timer_interrupt(struct pt_regs *regs) -{ - struct pt_regs *old_regs; - int cpu = smp_processor_id(); - unsigned long user = user_mode(regs); - struct cpuinfo_alpha *data = &cpu_data[cpu]; - - old_regs = set_irq_regs(regs); - - /* Record kernel PC. */ - profile_tick(CPU_PROFILING); - - if (!--data->prof_counter) { - /* We need to make like a normal interrupt -- otherwise - timer interrupts ignore the global interrupt lock, - which would be a Bad Thing. */ - irq_enter(); - - update_process_times(user); - - data->prof_counter = data->prof_multiplier; - - irq_exit(); - } - set_irq_regs(old_regs); -} - int setup_profiling_timer(unsigned int multiplier) { diff --git a/arch/alpha/kernel/sys_jensen.c b/arch/alpha/kernel/sys_jensen.c index 5a0af11b3a61..608f2a7fa0a3 100644 --- a/arch/alpha/kernel/sys_jensen.c +++ b/arch/alpha/kernel/sys_jensen.c @@ -224,8 +224,6 @@ struct alpha_machine_vector jensen_mv __initmv = { .machine_check = jensen_machine_check, .max_isa_dma_address = ALPHA_MAX_ISA_DMA_ADDRESS, .rtc_port = 0x170, - .rtc_get_time = common_get_rtc_time, - .rtc_set_time = common_set_rtc_time, .nr_irqs = 16, .device_interrupt = jensen_device_interrupt, diff --git a/arch/alpha/kernel/sys_marvel.c b/arch/alpha/kernel/sys_marvel.c index c92e389ff219..f21d61fab678 100644 --- a/arch/alpha/kernel/sys_marvel.c +++ b/arch/alpha/kernel/sys_marvel.c @@ -22,7 +22,6 @@ #include <asm/hwrpb.h> #include <asm/tlbflush.h> #include <asm/vga.h> -#include <asm/rtc.h> #include "proto.h" #include "err_impl.h" @@ -400,57 +399,6 @@ marvel_init_rtc(void) init_rtc_irq(); } -struct marvel_rtc_time { - struct rtc_time *time; - int retval; -}; - -#ifdef CONFIG_SMP -static void -smp_get_rtc_time(void *data) -{ - struct marvel_rtc_time *mrt = data; - mrt->retval = __get_rtc_time(mrt->time); -} - -static void -smp_set_rtc_time(void *data) -{ - struct marvel_rtc_time *mrt = data; - mrt->retval = __set_rtc_time(mrt->time); -} -#endif - -static unsigned int -marvel_get_rtc_time(struct rtc_time *time) -{ -#ifdef CONFIG_SMP - struct marvel_rtc_time mrt; - - if (smp_processor_id() != boot_cpuid) { - mrt.time = time; - smp_call_function_single(boot_cpuid, smp_get_rtc_time, &mrt, 1); - return mrt.retval; - } -#endif - return __get_rtc_time(time); -} - -static int -marvel_set_rtc_time(struct rtc_time *time) -{ -#ifdef CONFIG_SMP - struct marvel_rtc_time mrt; - - if (smp_processor_id() != boot_cpuid) { - mrt.time = time; - smp_call_function_single(boot_cpuid, smp_set_rtc_time, &mrt, 1); - return mrt.retval; - } -#endif - return __set_rtc_time(time); -} - static void marvel_smp_callin(void) { @@ -492,8 +440,7 @@ struct alpha_machine_vector marvel_ev7_mv __initmv = { .vector_name = "MARVEL/EV7", DO_EV7_MMU, .rtc_port = 0x70, - .rtc_get_time = marvel_get_rtc_time, - .rtc_set_time = marvel_set_rtc_time, + .rtc_boot_cpu_only = 1, DO_MARVEL_IO, .machine_check = marvel_machine_check, .max_isa_dma_address = ALPHA_MAX_ISA_DMA_ADDRESS, diff --git a/arch/alpha/kernel/time.c b/arch/alpha/kernel/time.c index ea3395036556..ee39cee8064c 100644 --- a/arch/alpha/kernel/time.c +++ b/arch/alpha/kernel/time.c @@ -3,13 +3,7 @@ * * Copyright (C) 1991, 1992, 1995, 1999, 2000 Linus Torvalds * - * This file contains the PC-specific time handling details: - * reading the RTC at bootup, etc.. - * 1994-07-02 Alan Modra - * fixed set_rtc_mmss, fixed time.year for >= 2000, new mktime - * 1995-03-26 Markus Kuhn - * fixed 500 ms bug at call to set_rtc_mmss, fixed DS12887 - * precision CMOS clock update + * This file contains the clocksource time handling. * 1997-09-10 Updated NTP code according to technical memorandum Jan '96 * "A Kernel Model for Precision Timekeeping" by Dave Mills * 1997-01-09 Adrian Sun @@ -21,9 +15,6 @@ * 1999-04-16 Thorsten Kranzkowski (dl8bcu@gmx.net) * fixed algorithm in do_gettimeofday() for calculating the precise time * from processor cycle counter (now taking lost_ticks into account) - * 2000-08-13 Jan-Benedict Glaw <jbglaw@lug-owl.de> - * Fixed time_init to be aware of epoches != 1900. This prevents - * booting up in 2048 for me;) Code is stolen from rtc.c. * 2003-06-03 R. Scott Bailey <scott.bailey@eds.com> * Tighten sanity in time_init from 1% (10,000 PPM) to 250 PPM */ @@ -46,40 +37,19 @@ #include <asm/uaccess.h> #include <asm/io.h> #include <asm/hwrpb.h> -#include <asm/rtc.h> #include <linux/mc146818rtc.h> #include <linux/time.h> #include <linux/timex.h> #include <linux/clocksource.h> +#include <linux/clockchips.h> #include "proto.h" #include "irq_impl.h" -static int set_rtc_mmss(unsigned long); - DEFINE_SPINLOCK(rtc_lock); EXPORT_SYMBOL(rtc_lock); -#define TICK_SIZE (tick_nsec / 1000) - -/* - * Shift amount by which scaled_ticks_per_cycle is scaled. Shifting - * by 48 gives us 16 bits for HZ while keeping the accuracy good even - * for large CPU clock rates. - */ -#define FIX_SHIFT 48 - -/* lump static variables together for more efficient access: */ -static struct { - /* cycle counter last time it got invoked */ - __u32 last_time; - /* ticks/cycle * 2^48 */ - unsigned long scaled_ticks_per_cycle; - /* partial unused tick */ - unsigned long partial_tick; -} state; - unsigned long est_cycle_freq; #ifdef CONFIG_IRQ_WORK @@ -108,109 +78,156 @@ static inline __u32 rpcc(void) return __builtin_alpha_rpcc(); } -int update_persistent_clock(struct timespec now) -{ - return set_rtc_mmss(now.tv_sec); -} -void read_persistent_clock(struct timespec *ts) + +/* + * The RTC as a clock_event_device primitive. + */ + +static DEFINE_PER_CPU(struct clock_event_device, cpu_ce); + +irqreturn_t +rtc_timer_interrupt(int irq, void *dev) { - unsigned int year, mon, day, hour, min, sec, epoch; - - sec = CMOS_READ(RTC_SECONDS); - min = CMOS_READ(RTC_MINUTES); - hour = CMOS_READ(RTC_HOURS); - day = CMOS_READ(RTC_DAY_OF_MONTH); - mon = CMOS_READ(RTC_MONTH); - year = CMOS_READ(RTC_YEAR); - - if (!(CMOS_READ(RTC_CONTROL) & RTC_DM_BINARY) || RTC_ALWAYS_BCD) { - sec = bcd2bin(sec); - min = bcd2bin(min); - hour = bcd2bin(hour); - day = bcd2bin(day); - mon = bcd2bin(mon); - year = bcd2bin(year); - } + int cpu = smp_processor_id(); + struct clock_event_device *ce = &per_cpu(cpu_ce, cpu); - /* PC-like is standard; used for year >= 70 */ - epoch = 1900; - if (year < 20) - epoch = 2000; - else if (year >= 20 && year < 48) - /* NT epoch */ - epoch = 1980; - else if (year >= 48 && year < 70) - /* Digital UNIX epoch */ - epoch = 1952; + /* Don't run the hook for UNUSED or SHUTDOWN. */ + if (likely(ce->mode == CLOCK_EVT_MODE_PERIODIC)) + ce->event_handler(ce); - printk(KERN_INFO "Using epoch = %d\n", epoch); + if (test_irq_work_pending()) { + clear_irq_work_pending(); + irq_work_run(); + } - if ((year += epoch) < 1970) - year += 100; + return IRQ_HANDLED; +} - ts->tv_sec = mktime(year, mon, day, hour, min, sec); - ts->tv_nsec = 0; +static void +rtc_ce_set_mode(enum clock_event_mode mode, struct clock_event_device *ce) +{ + /* The mode member of CE is updated in generic code. + Since we only support periodic events, nothing to do. */ +} + +static int +rtc_ce_set_next_event(unsigned long evt, struct clock_event_device *ce) +{ + /* This hook is for oneshot mode, which we don't support. */ + return -EINVAL; } +static void __init +init_rtc_clockevent(void) +{ + int cpu = smp_processor_id(); + struct clock_event_device *ce = &per_cpu(cpu_ce, cpu); + + *ce = (struct clock_event_device){ + .name = "rtc", + .features = CLOCK_EVT_FEAT_PERIODIC, + .rating = 100, + .cpumask = cpumask_of(cpu), + .set_mode = rtc_ce_set_mode, + .set_next_event = rtc_ce_set_next_event, + }; + clockevents_config_and_register(ce, CONFIG_HZ, 0, 0); +} + /* - * timer_interrupt() needs to keep up the real-time clock, - * as well as call the "xtime_update()" routine every clocktick + * The QEMU clock as a clocksource primitive. */ -irqreturn_t timer_interrupt(int irq, void *dev) + +static cycle_t +qemu_cs_read(struct clocksource *cs) { - unsigned long delta; - __u32 now; - long nticks; + return qemu_get_vmtime(); +} -#ifndef CONFIG_SMP - /* Not SMP, do kernel PC profiling here. */ - profile_tick(CPU_PROFILING); -#endif +static struct clocksource qemu_cs = { + .name = "qemu", + .rating = 400, + .read = qemu_cs_read, + .mask = CLOCKSOURCE_MASK(64), + .flags = CLOCK_SOURCE_IS_CONTINUOUS, + .max_idle_ns = LONG_MAX +}; - /* - * Calculate how many ticks have passed since the last update, - * including any previous partial leftover. Save any resulting - * fraction for the next pass. - */ - now = rpcc(); - delta = now - state.last_time; - state.last_time = now; - delta = delta * state.scaled_ticks_per_cycle + state.partial_tick; - state.partial_tick = delta & ((1UL << FIX_SHIFT) - 1); - nticks = delta >> FIX_SHIFT; - if (nticks) - xtime_update(nticks); +/* + * The QEMU alarm as a clock_event_device primitive. + */ - if (test_irq_work_pending()) { - clear_irq_work_pending(); - irq_work_run(); - } +static void +qemu_ce_set_mode(enum clock_event_mode mode, struct clock_event_device *ce) +{ + /* The mode member of CE is updated for us in generic code. + Just make sure that the event is disabled. */ + qemu_set_alarm_abs(0); +} -#ifndef CONFIG_SMP - while (nticks--) - update_process_times(user_mode(get_irq_regs())); -#endif +static int +qemu_ce_set_next_event(unsigned long evt, struct clock_event_device *ce) +{ + qemu_set_alarm_rel(evt); + return 0; +} +static irqreturn_t +qemu_timer_interrupt(int irq, void *dev) +{ + int cpu = smp_processor_id(); + struct clock_event_device *ce = &per_cpu(cpu_ce, cpu); + + ce->event_handler(ce); return IRQ_HANDLED; } +static void __init +init_qemu_clockevent(void) +{ + int cpu = smp_processor_id(); + struct clock_event_device *ce = &per_cpu(cpu_ce, cpu); + + *ce = (struct clock_event_device){ + .name = "qemu", + .features = CLOCK_EVT_FEAT_ONESHOT, + .rating = 400, + .cpumask = cpumask_of(cpu), + .set_mode = qemu_ce_set_mode, + .set_next_event = qemu_ce_set_next_event, + }; + + clockevents_config_and_register(ce, NSEC_PER_SEC, 1000, LONG_MAX); +} + + void __init common_init_rtc(void) { - unsigned char x; + unsigned char x, sel = 0; /* Reset periodic interrupt frequency. */ - x = CMOS_READ(RTC_FREQ_SELECT) & 0x3f; - /* Test includes known working values on various platforms - where 0x26 is wrong; we refuse to change those. */ - if (x != 0x26 && x != 0x25 && x != 0x19 && x != 0x06) { - printk("Setting RTC_FREQ to 1024 Hz (%x)\n", x); - CMOS_WRITE(0x26, RTC_FREQ_SELECT); +#if CONFIG_HZ == 1024 || CONFIG_HZ == 1200 + x = CMOS_READ(RTC_FREQ_SELECT) & 0x3f; + /* Test includes known working values on various platforms + where 0x26 is wrong; we refuse to change those. */ + if (x != 0x26 && x != 0x25 && x != 0x19 && x != 0x06) { + sel = RTC_REF_CLCK_32KHZ + 6; } +#elif CONFIG_HZ == 256 || CONFIG_HZ == 128 || CONFIG_HZ == 64 || CONFIG_HZ == 32 + sel = RTC_REF_CLCK_32KHZ + __builtin_ffs(32768 / CONFIG_HZ); +#else +# error "Unknown HZ from arch/alpha/Kconfig" +#endif + if (sel) { + printk(KERN_INFO "Setting RTC_FREQ to %d Hz (%x)\n", + CONFIG_HZ, sel); + CMOS_WRITE(sel, RTC_FREQ_SELECT); + } /* Turn on periodic interrupts. */ x = CMOS_READ(RTC_CONTROL); @@ -233,16 +250,37 @@ common_init_rtc(void) init_rtc_irq(); } -unsigned int common_get_rtc_time(struct rtc_time *time) -{ - return __get_rtc_time(time); -} + +#ifndef CONFIG_ALPHA_WTINT +/* + * The RPCC as a clocksource primitive. + * + * While we have free-running timecounters running on all CPUs, and we make + * a half-hearted attempt in init_rtc_rpcc_info to sync the timecounter + * with the wall clock, that initialization isn't kept up-to-date across + * different time counters in SMP mode. Therefore we can only use this + * method when there's only one CPU enabled. + * + * When using the WTINT PALcall, the RPCC may shift to a lower frequency, + * or stop altogether, while waiting for the interrupt. Therefore we cannot + * use this method when WTINT is in use. + */ -int common_set_rtc_time(struct rtc_time *time) +static cycle_t read_rpcc(struct clocksource *cs) { - return __set_rtc_time(time); + return rpcc(); } +static struct clocksource clocksource_rpcc = { + .name = "rpcc", + .rating = 300, + .read = read_rpcc, + .mask = CLOCKSOURCE_MASK(32), + .flags = CLOCK_SOURCE_IS_CONTINUOUS +}; +#endif /* ALPHA_WTINT */ + + /* Validate a computed cycle counter result against the known bounds for the given processor core. There's too much brokenness in the way of timing hardware for any one method to work everywhere. :-( @@ -353,33 +391,6 @@ rpcc_after_update_in_progress(void) return rpcc(); } -#ifndef CONFIG_SMP -/* Until and unless we figure out how to get cpu cycle counters - in sync and keep them there, we can't use the rpcc. */ -static cycle_t read_rpcc(struct clocksource *cs) -{ - cycle_t ret = (cycle_t)rpcc(); - return ret; -} - -static struct clocksource clocksource_rpcc = { - .name = "rpcc", - .rating = 300, - .read = read_rpcc, - .mask = CLOCKSOURCE_MASK(32), - .flags = CLOCK_SOURCE_IS_CONTINUOUS -}; - -static inline void register_rpcc_clocksource(long cycle_freq) -{ - clocksource_register_hz(&clocksource_rpcc, cycle_freq); -} -#else /* !CONFIG_SMP */ -static inline void register_rpcc_clocksource(long cycle_freq) -{ -} -#endif /* !CONFIG_SMP */ - void __init time_init(void) { @@ -387,6 +398,15 @@ time_init(void) unsigned long cycle_freq, tolerance; long diff; + if (alpha_using_qemu) { + clocksource_register_hz(&qemu_cs, NSEC_PER_SEC); + init_qemu_clockevent(); + + timer_irqaction.handler = qemu_timer_interrupt; + init_rtc_irq(); + return; + } + /* Calibrate CPU clock -- attempt #1. */ if (!est_cycle_freq) est_cycle_freq = validate_cc_value(calibrate_cc_with_pit()); @@ -421,100 +441,25 @@ time_init(void) "and unable to estimate a proper value!\n"); } - /* From John Bowman <bowman@math.ualberta.ca>: allow the values - to settle, as the Update-In-Progress bit going low isn't good - enough on some hardware. 2ms is our guess; we haven't found - bogomips yet, but this is close on a 500Mhz box. */ - __delay(1000000); - - - if (HZ > (1<<16)) { - extern void __you_loose (void); - __you_loose(); - } - - register_rpcc_clocksource(cycle_freq); - - state.last_time = cc1; - state.scaled_ticks_per_cycle - = ((unsigned long) HZ << FIX_SHIFT) / cycle_freq; - state.partial_tick = 0L; + /* See above for restrictions on using clocksource_rpcc. */ +#ifndef CONFIG_ALPHA_WTINT + if (hwrpb->nr_processors == 1) + clocksource_register_hz(&clocksource_rpcc, cycle_freq); +#endif /* Startup the timer source. */ alpha_mv.init_rtc(); + init_rtc_clockevent(); } -/* - * In order to set the CMOS clock precisely, set_rtc_mmss has to be - * called 500 ms after the second nowtime has started, because when - * nowtime is written into the registers of the CMOS clock, it will - * jump to the next second precisely 500 ms later. Check the Motorola - * MC146818A or Dallas DS12887 data sheet for details. - * - * BUG: This routine does not handle hour overflow properly; it just - * sets the minutes. Usually you won't notice until after reboot! - */ - - -static int -set_rtc_mmss(unsigned long nowtime) +/* Initialize the clock_event_device for secondary cpus. */ +#ifdef CONFIG_SMP +void __init +init_clockevent(void) { - int retval = 0; - int real_seconds, real_minutes, cmos_minutes; - unsigned char save_control, save_freq_select; - - /* irq are locally disabled here */ - spin_lock(&rtc_lock); - /* Tell the clock it's being set */ - save_control = CMOS_READ(RTC_CONTROL); - CMOS_WRITE((save_control|RTC_SET), RTC_CONTROL); - - /* Stop and reset prescaler */ - save_freq_select = CMOS_READ(RTC_FREQ_SELECT); - CMOS_WRITE((save_freq_select|RTC_DIV_RESET2), RTC_FREQ_SELECT); - - cmos_minutes = CMOS_READ(RTC_MINUTES); - if (!(save_control & RTC_DM_BINARY) || RTC_ALWAYS_BCD) - cmos_minutes = bcd2bin(cmos_minutes); - - /* - * since we're only adjusting minutes and seconds, - * don't interfere with hour overflow. This avoids - * messing with unknown time zones but requires your - * RTC not to be off by more than 15 minutes - */ - real_seconds = nowtime % 60; - real_minutes = nowtime / 60; - if (((abs(real_minutes - cmos_minutes) + 15)/30) & 1) { - /* correct for half hour time zone */ - real_minutes += 30; - } - real_minutes %= 60; - - if (abs(real_minutes - cmos_minutes) < 30) { - if (!(save_control & RTC_DM_BINARY) || RTC_ALWAYS_BCD) { - real_seconds = bin2bcd(real_seconds); - real_minutes = bin2bcd(real_minutes); - } - CMOS_WRITE(real_seconds,RTC_SECONDS); - CMOS_WRITE(real_minutes,RTC_MINUTES); - } else { - printk_once(KERN_NOTICE - "set_rtc_mmss: can't update from %d to %d\n", - cmos_minutes, real_minutes); - retval = -1; - } - - /* The following flags have to be released exactly in this order, - * otherwise the DS12887 (popular MC146818A clone with integrated - * battery and quartz) will not reset the oscillator and will not - * update precisely 500 ms later. You won't find this mentioned in - * the Dallas Semiconductor data sheets, but who believes data - * sheets anyway ... -- Markus Kuhn - */ - CMOS_WRITE(save_control, RTC_CONTROL); - CMOS_WRITE(save_freq_select, RTC_FREQ_SELECT); - spin_unlock(&rtc_lock); - - return retval; + if (alpha_using_qemu) + init_qemu_clockevent(); + else + init_rtc_clockevent(); } +#endif diff --git a/arch/alpha/kernel/traps.c b/arch/alpha/kernel/traps.c index bd0665cdc840..9c4c189eb22f 100644 --- a/arch/alpha/kernel/traps.c +++ b/arch/alpha/kernel/traps.c @@ -241,6 +241,21 @@ do_entIF(unsigned long type, struct pt_regs *regs) (const char *)(data[1] | (long)data[2] << 32), data[0]); } +#ifdef CONFIG_ALPHA_WTINT + if (type == 4) { + /* If CALL_PAL WTINT is totally unsupported by the + PALcode, e.g. MILO, "emulate" it by overwriting + the insn. */ + unsigned int *pinsn + = (unsigned int *) regs->pc - 1; + if (*pinsn == PAL_wtint) { + *pinsn = 0x47e01400; /* mov 0,$0 */ + imb(); + regs->r0 = 0; + return; + } + } +#endif /* ALPHA_WTINT */ die_if_kernel((type == 1 ? "Kernel Bug" : "Instruction fault"), regs, type, NULL); } diff --git a/arch/alpha/lib/csum_partial_copy.c b/arch/alpha/lib/csum_partial_copy.c index ffb19b7da999..ff3c10721caf 100644 --- a/arch/alpha/lib/csum_partial_copy.c +++ b/arch/alpha/lib/csum_partial_copy.c @@ -130,7 +130,7 @@ csum_partial_cfu_aligned(const unsigned long __user *src, unsigned long *dst, *dst = word | tmp; checksum += carry; } - if (err) *errp = err; + if (err && errp) *errp = err; return checksum; } @@ -185,7 +185,7 @@ csum_partial_cfu_dest_aligned(const unsigned long __user *src, *dst = word | tmp; checksum += carry; } - if (err) *errp = err; + if (err && errp) *errp = err; return checksum; } @@ -242,7 +242,7 @@ csum_partial_cfu_src_aligned(const unsigned long __user *src, stq_u(partial_dest | second_dest, dst); out: checksum += carry; - if (err) *errp = err; + if (err && errp) *errp = err; return checksum; } @@ -325,7 +325,7 @@ csum_partial_cfu_unaligned(const unsigned long __user * src, stq_u(partial_dest | word | second_dest, dst); checksum += carry; } - if (err) *errp = err; + if (err && errp) *errp = err; return checksum; } @@ -339,7 +339,7 @@ csum_partial_copy_from_user(const void __user *src, void *dst, int len, if (len) { if (!access_ok(VERIFY_READ, src, len)) { - *errp = -EFAULT; + if (errp) *errp = -EFAULT; memset(dst, 0, len); return sum; } diff --git a/arch/alpha/lib/ev6-memset.S b/arch/alpha/lib/ev6-memset.S index d8b94e1c7fca..356bb2fdd705 100644 --- a/arch/alpha/lib/ev6-memset.S +++ b/arch/alpha/lib/ev6-memset.S @@ -30,14 +30,15 @@ .set noat .set noreorder .text + .globl memset .globl __memset + .globl ___memset .globl __memsetw .globl __constant_c_memset - .globl memset - .ent __memset + .ent ___memset .align 5 -__memset: +___memset: .frame $30,0,$26,0 .prologue 0 @@ -227,7 +228,7 @@ end_b: nop nop ret $31,($26),1 # L0 : - .end __memset + .end ___memset /* * This is the original body of code, prior to replication and @@ -594,4 +595,5 @@ end_w: .end __memsetw -memset = __memset +memset = ___memset +__memset = ___memset diff --git a/arch/alpha/lib/memset.S b/arch/alpha/lib/memset.S index 311b8cfc6914..76ccc6d1f364 100644 --- a/arch/alpha/lib/memset.S +++ b/arch/alpha/lib/memset.S @@ -19,11 +19,13 @@ .text .globl memset .globl __memset + .globl ___memset .globl __memsetw .globl __constant_c_memset - .ent __memset + + .ent ___memset .align 5 -__memset: +___memset: .frame $30,0,$26,0 .prologue 0 @@ -103,7 +105,7 @@ within_one_quad: end: ret $31,($26),1 /* E1 */ - .end __memset + .end ___memset .align 5 .ent __memsetw @@ -121,4 +123,5 @@ __memsetw: .end __memsetw -memset = __memset +memset = ___memset +__memset = ___memset diff --git a/arch/arc/Kconfig b/arch/arc/Kconfig index 5ede5460c806..2ee0c9bfd032 100644 --- a/arch/arc/Kconfig +++ b/arch/arc/Kconfig @@ -125,7 +125,6 @@ config ARC_PLAT_NEEDS_CPU_TO_DMA config SMP bool "Symmetric Multi-Processing (Incomplete)" default n - select USE_GENERIC_SMP_HELPERS help This enables support for systems with more than one CPU. If you have a system with only one CPU, like most personal computers, say N. If diff --git a/arch/arc/boot/dts/abilis_tb100.dtsi b/arch/arc/boot/dts/abilis_tb100.dtsi index d9f8249aa66e..3942634f805a 100644 --- a/arch/arc/boot/dts/abilis_tb100.dtsi +++ b/arch/arc/boot/dts/abilis_tb100.dtsi @@ -43,124 +43,124 @@ iomux: iomux@FF10601c { /* Port 1 */ pctl_tsin_s0: pctl-tsin-s0 { /* Serial TS-in 0 */ - pingrp = "mis0_pins"; + abilis,function = "mis0"; }; pctl_tsin_s1: pctl-tsin-s1 { /* Serial TS-in 1 */ - pingrp = "mis1_pins"; + abilis,function = "mis1"; }; pctl_gpio_a: pctl-gpio-a { /* GPIO bank A */ - pingrp = "gpioa_pins"; + abilis,function = "gpioa"; }; pctl_tsin_p1: pctl-tsin-p1 { /* Parallel TS-in 1 */ - pingrp = "mip1_pins"; + abilis,function = "mip1"; }; /* Port 2 */ pctl_tsin_s2: pctl-tsin-s2 { /* Serial TS-in 2 */ - pingrp = "mis2_pins"; + abilis,function = "mis2"; }; pctl_tsin_s3: pctl-tsin-s3 { /* Serial TS-in 3 */ - pingrp = "mis3_pins"; + abilis,function = "mis3"; }; pctl_gpio_c: pctl-gpio-c { /* GPIO bank C */ - pingrp = "gpioc_pins"; + abilis,function = "gpioc"; }; pctl_tsin_p3: pctl-tsin-p3 { /* Parallel TS-in 3 */ - pingrp = "mip3_pins"; + abilis,function = "mip3"; }; /* Port 3 */ pctl_tsin_s4: pctl-tsin-s4 { /* Serial TS-in 4 */ - pingrp = "mis4_pins"; + abilis,function = "mis4"; }; pctl_tsin_s5: pctl-tsin-s5 { /* Serial TS-in 5 */ - pingrp = "mis5_pins"; + abilis,function = "mis5"; }; pctl_gpio_e: pctl-gpio-e { /* GPIO bank E */ - pingrp = "gpioe_pins"; + abilis,function = "gpioe"; }; pctl_tsin_p5: pctl-tsin-p5 { /* Parallel TS-in 5 */ - pingrp = "mip5_pins"; + abilis,function = "mip5"; }; /* Port 4 */ pctl_tsin_s6: pctl-tsin-s6 { /* Serial TS-in 6 */ - pingrp = "mis6_pins"; + abilis,function = "mis6"; }; pctl_tsin_s7: pctl-tsin-s7 { /* Serial TS-in 7 */ - pingrp = "mis7_pins"; + abilis,function = "mis7"; }; pctl_gpio_g: pctl-gpio-g { /* GPIO bank G */ - pingrp = "gpiog_pins"; + abilis,function = "gpiog"; }; pctl_tsin_p7: pctl-tsin-p7 { /* Parallel TS-in 7 */ - pingrp = "mip7_pins"; + abilis,function = "mip7"; }; /* Port 5 */ pctl_gpio_j: pctl-gpio-j { /* GPIO bank J */ - pingrp = "gpioj_pins"; + abilis,function = "gpioj"; }; pctl_gpio_k: pctl-gpio-k { /* GPIO bank K */ - pingrp = "gpiok_pins"; + abilis,function = "gpiok"; }; pctl_ciplus: pctl-ciplus { /* CI+ interface */ - pingrp = "ciplus_pins"; + abilis,function = "ciplus"; }; pctl_mcard: pctl-mcard { /* M-Card interface */ - pingrp = "mcard_pins"; + abilis,function = "mcard"; }; /* Port 6 */ pctl_tsout_p: pctl-tsout-p { /* Parallel TS-out */ - pingrp = "mop_pins"; + abilis,function = "mop"; }; pctl_tsout_s0: pctl-tsout-s0 { /* Serial TS-out 0 */ - pingrp = "mos0_pins"; + abilis,function = "mos0"; }; pctl_tsout_s1: pctl-tsout-s1 { /* Serial TS-out 1 */ - pingrp = "mos1_pins"; + abilis,function = "mos1"; }; pctl_tsout_s2: pctl-tsout-s2 { /* Serial TS-out 2 */ - pingrp = "mos2_pins"; + abilis,function = "mos2"; }; pctl_tsout_s3: pctl-tsout-s3 { /* Serial TS-out 3 */ - pingrp = "mos3_pins"; + abilis,function = "mos3"; }; /* Port 7 */ pctl_uart0: pctl-uart0 { /* UART 0 */ - pingrp = "uart0_pins"; + abilis,function = "uart0"; }; pctl_uart1: pctl-uart1 { /* UART 1 */ - pingrp = "uart1_pins"; + abilis,function = "uart1"; }; pctl_gpio_l: pctl-gpio-l { /* GPIO bank L */ - pingrp = "gpiol_pins"; + abilis,function = "gpiol"; }; pctl_gpio_m: pctl-gpio-m { /* GPIO bank M */ - pingrp = "gpiom_pins"; + abilis,function = "gpiom"; }; /* Port 8 */ pctl_spi3: pctl-spi3 { - pingrp = "spi3_pins"; + abilis,function = "spi3"; }; /* Port 9 */ pctl_spi1: pctl-spi1 { - pingrp = "spi1_pins"; + abilis,function = "spi1"; }; pctl_gpio_n: pctl-gpio-n { - pingrp = "gpion_pins"; + abilis,function = "gpion"; }; /* Unmuxed GPIOs */ pctl_gpio_b: pctl-gpio-b { - pingrp = "gpiob_pins"; + abilis,function = "gpiob"; }; pctl_gpio_d: pctl-gpio-d { - pingrp = "gpiod_pins"; + abilis,function = "gpiod"; }; pctl_gpio_f: pctl-gpio-f { - pingrp = "gpiof_pins"; + abilis,function = "gpiof"; }; pctl_gpio_h: pctl-gpio-h { - pingrp = "gpioh_pins"; + abilis,function = "gpioh"; }; pctl_gpio_i: pctl-gpio-i { - pingrp = "gpioi_pins"; + abilis,function = "gpioi"; }; }; @@ -172,9 +172,10 @@ interrupts = <27 2>; reg = <0xFF140000 0x1000>; gpio-controller; - #gpio-cells = <1>; - gpio-base = <0>; - gpio-pins = <&pctl_gpio_a>; + #gpio-cells = <2>; + abilis,ngpio = <3>; + gpio-ranges = <&iomux 0 0 0>; + gpio-ranges-group-names = "gpioa"; }; gpiob: gpio@FF141000 { compatible = "abilis,tb10x-gpio"; @@ -184,9 +185,10 @@ interrupts = <27 2>; reg = <0xFF141000 0x1000>; gpio-controller; - #gpio-cells = <1>; - gpio-base = <3>; - gpio-pins = <&pctl_gpio_b>; + #gpio-cells = <2>; + abilis,ngpio = <2>; + gpio-ranges = <&iomux 0 0 0>; + gpio-ranges-group-names = "gpiob"; }; gpioc: gpio@FF142000 { compatible = "abilis,tb10x-gpio"; @@ -196,9 +198,10 @@ interrupts = <27 2>; reg = <0xFF142000 0x1000>; gpio-controller; - #gpio-cells = <1>; - gpio-base = <5>; - gpio-pins = <&pctl_gpio_c>; + #gpio-cells = <2>; + abilis,ngpio = <3>; + gpio-ranges = <&iomux 0 0 0>; + gpio-ranges-group-names = "gpioc"; }; gpiod: gpio@FF143000 { compatible = "abilis,tb10x-gpio"; @@ -208,9 +211,10 @@ interrupts = <27 2>; reg = <0xFF143000 0x1000>; gpio-controller; - #gpio-cells = <1>; - gpio-base = <8>; - gpio-pins = <&pctl_gpio_d>; + #gpio-cells = <2>; + abilis,ngpio = <2>; + gpio-ranges = <&iomux 0 0 0>; + gpio-ranges-group-names = "gpiod"; }; gpioe: gpio@FF144000 { compatible = "abilis,tb10x-gpio"; @@ -220,9 +224,10 @@ interrupts = <27 2>; reg = <0xFF144000 0x1000>; gpio-controller; - #gpio-cells = <1>; - gpio-base = <10>; - gpio-pins = <&pctl_gpio_e>; + #gpio-cells = <2>; + abilis,ngpio = <3>; + gpio-ranges = <&iomux 0 0 0>; + gpio-ranges-group-names = "gpioe"; }; gpiof: gpio@FF145000 { compatible = "abilis,tb10x-gpio"; @@ -232,9 +237,10 @@ interrupts = <27 2>; reg = <0xFF145000 0x1000>; gpio-controller; - #gpio-cells = <1>; - gpio-base = <13>; - gpio-pins = <&pctl_gpio_f>; + #gpio-cells = <2>; + abilis,ngpio = <2>; + gpio-ranges = <&iomux 0 0 0>; + gpio-ranges-group-names = "gpiof"; }; gpiog: gpio@FF146000 { compatible = "abilis,tb10x-gpio"; @@ -244,9 +250,10 @@ interrupts = <27 2>; reg = <0xFF146000 0x1000>; gpio-controller; - #gpio-cells = <1>; - gpio-base = <15>; - gpio-pins = <&pctl_gpio_g>; + #gpio-cells = <2>; + abilis,ngpio = <3>; + gpio-ranges = <&iomux 0 0 0>; + gpio-ranges-group-names = "gpiog"; }; gpioh: gpio@FF147000 { compatible = "abilis,tb10x-gpio"; @@ -256,9 +263,10 @@ interrupts = <27 2>; reg = <0xFF147000 0x1000>; gpio-controller; - #gpio-cells = <1>; - gpio-base = <18>; - gpio-pins = <&pctl_gpio_h>; + #gpio-cells = <2>; + abilis,ngpio = <2>; + gpio-ranges = <&iomux 0 0 0>; + gpio-ranges-group-names = "gpioh"; }; gpioi: gpio@FF148000 { compatible = "abilis,tb10x-gpio"; @@ -268,9 +276,10 @@ interrupts = <27 2>; reg = <0xFF148000 0x1000>; gpio-controller; - #gpio-cells = <1>; - gpio-base = <20>; - gpio-pins = <&pctl_gpio_i>; + #gpio-cells = <2>; + abilis,ngpio = <12>; + gpio-ranges = <&iomux 0 0 0>; + gpio-ranges-group-names = "gpioi"; }; gpioj: gpio@FF149000 { compatible = "abilis,tb10x-gpio"; @@ -280,9 +289,10 @@ interrupts = <27 2>; reg = <0xFF149000 0x1000>; gpio-controller; - #gpio-cells = <1>; - gpio-base = <32>; - gpio-pins = <&pctl_gpio_j>; + #gpio-cells = <2>; + abilis,ngpio = <32>; + gpio-ranges = <&iomux 0 0 0>; + gpio-ranges-group-names = "gpioj"; }; gpiok: gpio@FF14a000 { compatible = "abilis,tb10x-gpio"; @@ -292,9 +302,10 @@ interrupts = <27 2>; reg = <0xFF14A000 0x1000>; gpio-controller; - #gpio-cells = <1>; - gpio-base = <64>; - gpio-pins = <&pctl_gpio_k>; + #gpio-cells = <2>; + abilis,ngpio = <22>; + gpio-ranges = <&iomux 0 0 0>; + gpio-ranges-group-names = "gpiok"; }; gpiol: gpio@FF14b000 { compatible = "abilis,tb10x-gpio"; @@ -304,9 +315,10 @@ interrupts = <27 2>; reg = <0xFF14B000 0x1000>; gpio-controller; - #gpio-cells = <1>; - gpio-base = <86>; - gpio-pins = <&pctl_gpio_l>; + #gpio-cells = <2>; + abilis,ngpio = <4>; + gpio-ranges = <&iomux 0 0 0>; + gpio-ranges-group-names = "gpiol"; }; gpiom: gpio@FF14c000 { compatible = "abilis,tb10x-gpio"; @@ -316,9 +328,10 @@ interrupts = <27 2>; reg = <0xFF14C000 0x1000>; gpio-controller; - #gpio-cells = <1>; - gpio-base = <90>; - gpio-pins = <&pctl_gpio_m>; + #gpio-cells = <2>; + abilis,ngpio = <4>; + gpio-ranges = <&iomux 0 0 0>; + gpio-ranges-group-names = "gpiom"; }; gpion: gpio@FF14d000 { compatible = "abilis,tb10x-gpio"; @@ -328,9 +341,10 @@ interrupts = <27 2>; reg = <0xFF14D000 0x1000>; gpio-controller; - #gpio-cells = <1>; - gpio-base = <94>; - gpio-pins = <&pctl_gpio_n>; + #gpio-cells = <2>; + abilis,ngpio = <5>; + gpio-ranges = <&iomux 0 0 0>; + gpio-ranges-group-names = "gpion"; }; }; }; diff --git a/arch/arc/boot/dts/abilis_tb100_dvk.dts b/arch/arc/boot/dts/abilis_tb100_dvk.dts index ebc313a9f5b2..3dd6ed941464 100644 --- a/arch/arc/boot/dts/abilis_tb100_dvk.dts +++ b/arch/arc/boot/dts/abilis_tb100_dvk.dts @@ -64,62 +64,62 @@ compatible = "gpio-leds"; power { label = "Power"; - gpios = <&gpioi 0>; + gpios = <&gpioi 0 0>; linux,default-trigger = "default-on"; }; heartbeat { label = "Heartbeat"; - gpios = <&gpioi 1>; + gpios = <&gpioi 1 0>; linux,default-trigger = "heartbeat"; }; led2 { label = "LED2"; - gpios = <&gpioi 2>; + gpios = <&gpioi 2 0>; default-state = "off"; }; led3 { label = "LED3"; - gpios = <&gpioi 3>; + gpios = <&gpioi 3 0>; default-state = "off"; }; led4 { label = "LED4"; - gpios = <&gpioi 4>; + gpios = <&gpioi 4 0>; default-state = "off"; }; led5 { label = "LED5"; - gpios = <&gpioi 5>; + gpios = <&gpioi 5 0>; default-state = "off"; }; led6 { label = "LED6"; - gpios = <&gpioi 6>; + gpios = <&gpioi 6 0>; default-state = "off"; }; led7 { label = "LED7"; - gpios = <&gpioi 7>; + gpios = <&gpioi 7 0>; default-state = "off"; }; led8 { label = "LED8"; - gpios = <&gpioi 8>; + gpios = <&gpioi 8 0>; default-state = "off"; }; led9 { label = "LED9"; - gpios = <&gpioi 9>; + gpios = <&gpioi 9 0>; default-state = "off"; }; led10 { label = "LED10"; - gpios = <&gpioi 10>; + gpios = <&gpioi 10 0>; default-state = "off"; }; led11 { label = "LED11"; - gpios = <&gpioi 11>; + gpios = <&gpioi 11 0>; default-state = "off"; }; }; diff --git a/arch/arc/boot/dts/abilis_tb101.dtsi b/arch/arc/boot/dts/abilis_tb101.dtsi index da8ca7941e67..b0467229a5c4 100644 --- a/arch/arc/boot/dts/abilis_tb101.dtsi +++ b/arch/arc/boot/dts/abilis_tb101.dtsi @@ -43,133 +43,133 @@ iomux: iomux@FF10601c { /* Port 1 */ pctl_tsin_s0: pctl-tsin-s0 { /* Serial TS-in 0 */ - pingrp = "mis0_pins"; + abilis,function = "mis0"; }; pctl_tsin_s1: pctl-tsin-s1 { /* Serial TS-in 1 */ - pingrp = "mis1_pins"; + abilis,function = "mis1"; }; pctl_gpio_a: pctl-gpio-a { /* GPIO bank A */ - pingrp = "gpioa_pins"; + abilis,function = "gpioa"; }; pctl_tsin_p1: pctl-tsin-p1 { /* Parallel TS-in 1 */ - pingrp = "mip1_pins"; + abilis,function = "mip1"; }; /* Port 2 */ pctl_tsin_s2: pctl-tsin-s2 { /* Serial TS-in 2 */ - pingrp = "mis2_pins"; + abilis,function = "mis2"; }; pctl_tsin_s3: pctl-tsin-s3 { /* Serial TS-in 3 */ - pingrp = "mis3_pins"; + abilis,function = "mis3"; }; pctl_gpio_c: pctl-gpio-c { /* GPIO bank C */ - pingrp = "gpioc_pins"; + abilis,function = "gpioc"; }; pctl_tsin_p3: pctl-tsin-p3 { /* Parallel TS-in 3 */ - pingrp = "mip3_pins"; + abilis,function = "mip3"; }; /* Port 3 */ pctl_tsin_s4: pctl-tsin-s4 { /* Serial TS-in 4 */ - pingrp = "mis4_pins"; + abilis,function = "mis4"; }; pctl_tsin_s5: pctl-tsin-s5 { /* Serial TS-in 5 */ - pingrp = "mis5_pins"; + abilis,function = "mis5"; }; pctl_gpio_e: pctl-gpio-e { /* GPIO bank E */ - pingrp = "gpioe_pins"; + abilis,function = "gpioe"; }; pctl_tsin_p5: pctl-tsin-p5 { /* Parallel TS-in 5 */ - pingrp = "mip5_pins"; + abilis,function = "mip5"; }; /* Port 4 */ pctl_tsin_s6: pctl-tsin-s6 { /* Serial TS-in 6 */ - pingrp = "mis6_pins"; + abilis,function = "mis6"; }; pctl_tsin_s7: pctl-tsin-s7 { /* Serial TS-in 7 */ - pingrp = "mis7_pins"; + abilis,function = "mis7"; }; pctl_gpio_g: pctl-gpio-g { /* GPIO bank G */ - pingrp = "gpiog_pins"; + abilis,function = "gpiog"; }; pctl_tsin_p7: pctl-tsin-p7 { /* Parallel TS-in 7 */ - pingrp = "mip7_pins"; + abilis,function = "mip7"; }; /* Port 5 */ pctl_gpio_j: pctl-gpio-j { /* GPIO bank J */ - pingrp = "gpioj_pins"; + abilis,function = "gpioj"; }; pctl_gpio_k: pctl-gpio-k { /* GPIO bank K */ - pingrp = "gpiok_pins"; + abilis,function = "gpiok"; }; pctl_ciplus: pctl-ciplus { /* CI+ interface */ - pingrp = "ciplus_pins"; + abilis,function = "ciplus"; }; pctl_mcard: pctl-mcard { /* M-Card interface */ - pingrp = "mcard_pins"; + abilis,function = "mcard"; }; pctl_stc0: pctl-stc0 { /* Smart card I/F 0 */ - pingrp = "stc0_pins"; + abilis,function = "stc0"; }; pctl_stc1: pctl-stc1 { /* Smart card I/F 1 */ - pingrp = "stc1_pins"; + abilis,function = "stc1"; }; /* Port 6 */ pctl_tsout_p: pctl-tsout-p { /* Parallel TS-out */ - pingrp = "mop_pins"; + abilis,function = "mop"; }; pctl_tsout_s0: pctl-tsout-s0 { /* Serial TS-out 0 */ - pingrp = "mos0_pins"; + abilis,function = "mos0"; }; pctl_tsout_s1: pctl-tsout-s1 { /* Serial TS-out 1 */ - pingrp = "mos1_pins"; + abilis,function = "mos1"; }; pctl_tsout_s2: pctl-tsout-s2 { /* Serial TS-out 2 */ - pingrp = "mos2_pins"; + abilis,function = "mos2"; }; pctl_tsout_s3: pctl-tsout-s3 { /* Serial TS-out 3 */ - pingrp = "mos3_pins"; + abilis,function = "mos3"; }; /* Port 7 */ pctl_uart0: pctl-uart0 { /* UART 0 */ - pingrp = "uart0_pins"; + abilis,function = "uart0"; }; pctl_uart1: pctl-uart1 { /* UART 1 */ - pingrp = "uart1_pins"; + abilis,function = "uart1"; }; pctl_gpio_l: pctl-gpio-l { /* GPIO bank L */ - pingrp = "gpiol_pins"; + abilis,function = "gpiol"; }; pctl_gpio_m: pctl-gpio-m { /* GPIO bank M */ - pingrp = "gpiom_pins"; + abilis,function = "gpiom"; }; /* Port 8 */ pctl_spi3: pctl-spi3 { - pingrp = "spi3_pins"; + abilis,function = "spi3"; }; pctl_jtag: pctl-jtag { - pingrp = "jtag_pins"; + abilis,function = "jtag"; }; /* Port 9 */ pctl_spi1: pctl-spi1 { - pingrp = "spi1_pins"; + abilis,function = "spi1"; }; pctl_gpio_n: pctl-gpio-n { - pingrp = "gpion_pins"; + abilis,function = "gpion"; }; /* Unmuxed GPIOs */ pctl_gpio_b: pctl-gpio-b { - pingrp = "gpiob_pins"; + abilis,function = "gpiob"; }; pctl_gpio_d: pctl-gpio-d { - pingrp = "gpiod_pins"; + abilis,function = "gpiod"; }; pctl_gpio_f: pctl-gpio-f { - pingrp = "gpiof_pins"; + abilis,function = "gpiof"; }; pctl_gpio_h: pctl-gpio-h { - pingrp = "gpioh_pins"; + abilis,function = "gpioh"; }; pctl_gpio_i: pctl-gpio-i { - pingrp = "gpioi_pins"; + abilis,function = "gpioi"; }; }; @@ -181,9 +181,10 @@ interrupts = <27 2>; reg = <0xFF140000 0x1000>; gpio-controller; - #gpio-cells = <1>; - gpio-base = <0>; - gpio-pins = <&pctl_gpio_a>; + #gpio-cells = <2>; + abilis,ngpio = <3>; + gpio-ranges = <&iomux 0 0 0>; + gpio-ranges-group-names = "gpioa"; }; gpiob: gpio@FF141000 { compatible = "abilis,tb10x-gpio"; @@ -193,9 +194,10 @@ interrupts = <27 2>; reg = <0xFF141000 0x1000>; gpio-controller; - #gpio-cells = <1>; - gpio-base = <3>; - gpio-pins = <&pctl_gpio_b>; + #gpio-cells = <2>; + abilis,ngpio = <2>; + gpio-ranges = <&iomux 0 0 0>; + gpio-ranges-group-names = "gpiob"; }; gpioc: gpio@FF142000 { compatible = "abilis,tb10x-gpio"; @@ -205,9 +207,10 @@ interrupts = <27 2>; reg = <0xFF142000 0x1000>; gpio-controller; - #gpio-cells = <1>; - gpio-base = <5>; - gpio-pins = <&pctl_gpio_c>; + #gpio-cells = <2>; + abilis,ngpio = <3>; + gpio-ranges = <&iomux 0 0 0>; + gpio-ranges-group-names = "gpioc"; }; gpiod: gpio@FF143000 { compatible = "abilis,tb10x-gpio"; @@ -217,9 +220,10 @@ interrupts = <27 2>; reg = <0xFF143000 0x1000>; gpio-controller; - #gpio-cells = <1>; - gpio-base = <8>; - gpio-pins = <&pctl_gpio_d>; + #gpio-cells = <2>; + abilis,ngpio = <2>; + gpio-ranges = <&iomux 0 0 0>; + gpio-ranges-group-names = "gpiod"; }; gpioe: gpio@FF144000 { compatible = "abilis,tb10x-gpio"; @@ -229,9 +233,10 @@ interrupts = <27 2>; reg = <0xFF144000 0x1000>; gpio-controller; - #gpio-cells = <1>; - gpio-base = <10>; - gpio-pins = <&pctl_gpio_e>; + #gpio-cells = <2>; + abilis,ngpio = <3>; + gpio-ranges = <&iomux 0 0 0>; + gpio-ranges-group-names = "gpioe"; }; gpiof: gpio@FF145000 { compatible = "abilis,tb10x-gpio"; @@ -241,9 +246,10 @@ interrupts = <27 2>; reg = <0xFF145000 0x1000>; gpio-controller; - #gpio-cells = <1>; - gpio-base = <13>; - gpio-pins = <&pctl_gpio_f>; + #gpio-cells = <2>; + abilis,ngpio = <2>; + gpio-ranges = <&iomux 0 0 0>; + gpio-ranges-group-names = "gpiof"; }; gpiog: gpio@FF146000 { compatible = "abilis,tb10x-gpio"; @@ -253,9 +259,10 @@ interrupts = <27 2>; reg = <0xFF146000 0x1000>; gpio-controller; - #gpio-cells = <1>; - gpio-base = <15>; - gpio-pins = <&pctl_gpio_g>; + #gpio-cells = <2>; + abilis,ngpio = <3>; + gpio-ranges = <&iomux 0 0 0>; + gpio-ranges-group-names = "gpiog"; }; gpioh: gpio@FF147000 { compatible = "abilis,tb10x-gpio"; @@ -265,9 +272,10 @@ interrupts = <27 2>; reg = <0xFF147000 0x1000>; gpio-controller; - #gpio-cells = <1>; - gpio-base = <18>; - gpio-pins = <&pctl_gpio_h>; + #gpio-cells = <2>; + abilis,ngpio = <2>; + gpio-ranges = <&iomux 0 0 0>; + gpio-ranges-group-names = "gpioh"; }; gpioi: gpio@FF148000 { compatible = "abilis,tb10x-gpio"; @@ -277,9 +285,10 @@ interrupts = <27 2>; reg = <0xFF148000 0x1000>; gpio-controller; - #gpio-cells = <1>; - gpio-base = <20>; - gpio-pins = <&pctl_gpio_i>; + #gpio-cells = <2>; + abilis,ngpio = <12>; + gpio-ranges = <&iomux 0 0 0>; + gpio-ranges-group-names = "gpioi"; }; gpioj: gpio@FF149000 { compatible = "abilis,tb10x-gpio"; @@ -289,9 +298,10 @@ interrupts = <27 2>; reg = <0xFF149000 0x1000>; gpio-controller; - #gpio-cells = <1>; - gpio-base = <32>; - gpio-pins = <&pctl_gpio_j>; + #gpio-cells = <2>; + abilis,ngpio = <32>; + gpio-ranges = <&iomux 0 0 0>; + gpio-ranges-group-names = "gpioj"; }; gpiok: gpio@FF14a000 { compatible = "abilis,tb10x-gpio"; @@ -301,9 +311,10 @@ interrupts = <27 2>; reg = <0xFF14A000 0x1000>; gpio-controller; - #gpio-cells = <1>; - gpio-base = <64>; - gpio-pins = <&pctl_gpio_k>; + #gpio-cells = <2>; + abilis,ngpio = <22>; + gpio-ranges = <&iomux 0 0 0>; + gpio-ranges-group-names = "gpiok"; }; gpiol: gpio@FF14b000 { compatible = "abilis,tb10x-gpio"; @@ -313,9 +324,10 @@ interrupts = <27 2>; reg = <0xFF14B000 0x1000>; gpio-controller; - #gpio-cells = <1>; - gpio-base = <86>; - gpio-pins = <&pctl_gpio_l>; + #gpio-cells = <2>; + abilis,ngpio = <4>; + gpio-ranges = <&iomux 0 0 0>; + gpio-ranges-group-names = "gpiol"; }; gpiom: gpio@FF14c000 { compatible = "abilis,tb10x-gpio"; @@ -325,9 +337,10 @@ interrupts = <27 2>; reg = <0xFF14C000 0x1000>; gpio-controller; - #gpio-cells = <1>; - gpio-base = <90>; - gpio-pins = <&pctl_gpio_m>; + #gpio-cells = <2>; + abilis,ngpio = <4>; + gpio-ranges = <&iomux 0 0 0>; + gpio-ranges-group-names = "gpiom"; }; gpion: gpio@FF14d000 { compatible = "abilis,tb10x-gpio"; @@ -337,9 +350,10 @@ interrupts = <27 2>; reg = <0xFF14D000 0x1000>; gpio-controller; - #gpio-cells = <1>; - gpio-base = <94>; - gpio-pins = <&pctl_gpio_n>; + #gpio-cells = <2>; + abilis,ngpio = <5>; + gpio-ranges = <&iomux 0 0 0>; + gpio-ranges-group-names = "gpion"; }; }; }; diff --git a/arch/arc/boot/dts/abilis_tb101_dvk.dts b/arch/arc/boot/dts/abilis_tb101_dvk.dts index b204657993aa..1cf51c280f28 100644 --- a/arch/arc/boot/dts/abilis_tb101_dvk.dts +++ b/arch/arc/boot/dts/abilis_tb101_dvk.dts @@ -64,62 +64,62 @@ compatible = "gpio-leds"; power { label = "Power"; - gpios = <&gpioi 0>; + gpios = <&gpioi 0 0>; linux,default-trigger = "default-on"; }; heartbeat { label = "Heartbeat"; - gpios = <&gpioi 1>; + gpios = <&gpioi 1 0>; linux,default-trigger = "heartbeat"; }; led2 { label = "LED2"; - gpios = <&gpioi 2>; + gpios = <&gpioi 2 0>; default-state = "off"; }; led3 { label = "LED3"; - gpios = <&gpioi 3>; + gpios = <&gpioi 3 0>; default-state = "off"; }; led4 { label = "LED4"; - gpios = <&gpioi 4>; + gpios = <&gpioi 4 0>; default-state = "off"; }; led5 { label = "LED5"; - gpios = <&gpioi 5>; + gpios = <&gpioi 5 0>; default-state = "off"; }; led6 { label = "LED6"; - gpios = <&gpioi 6>; + gpios = <&gpioi 6 0>; default-state = "off"; }; led7 { label = "LED7"; - gpios = <&gpioi 7>; + gpios = <&gpioi 7 0>; default-state = "off"; }; led8 { label = "LED8"; - gpios = <&gpioi 8>; + gpios = <&gpioi 8 0>; default-state = "off"; }; led9 { label = "LED9"; - gpios = <&gpioi 9>; + gpios = <&gpioi 9 0>; default-state = "off"; }; led10 { label = "LED10"; - gpios = <&gpioi 10>; + gpios = <&gpioi 10 0>; default-state = "off"; }; led11 { label = "LED11"; - gpios = <&gpioi 11>; + gpios = <&gpioi 11 0>; default-state = "off"; }; }; diff --git a/arch/arc/boot/dts/abilis_tb10x.dtsi b/arch/arc/boot/dts/abilis_tb10x.dtsi index edf56f4749e1..a098d7c05e96 100644 --- a/arch/arc/boot/dts/abilis_tb10x.dtsi +++ b/arch/arc/boot/dts/abilis_tb10x.dtsi @@ -62,9 +62,8 @@ }; iomux: iomux@FF10601c { - #address-cells = <1>; - #size-cells = <1>; compatible = "abilis,tb10x-iomux"; + #gpio-range-cells = <3>; reg = <0xFF10601c 0x4>; }; diff --git a/arch/arc/boot/dts/angel4.dts b/arch/arc/boot/dts/angel4.dts index 4fb2d6f655bd..bcf662d21a57 100644 --- a/arch/arc/boot/dts/angel4.dts +++ b/arch/arc/boot/dts/angel4.dts @@ -67,5 +67,9 @@ reg = <1>; }; }; + + arcpmu0: pmu { + compatible = "snps,arc700-pmu"; + }; }; }; diff --git a/arch/arc/configs/fpga_noramfs_defconfig b/arch/arc/configs/fpga_noramfs_defconfig new file mode 100644 index 000000000000..5276a52f6a2f --- /dev/null +++ b/arch/arc/configs/fpga_noramfs_defconfig @@ -0,0 +1,64 @@ +CONFIG_CROSS_COMPILE="arc-linux-uclibc-" +# CONFIG_LOCALVERSION_AUTO is not set +CONFIG_DEFAULT_HOSTNAME="ARCLinux" +# CONFIG_SWAP is not set +CONFIG_HIGH_RES_TIMERS=y +CONFIG_IKCONFIG=y +CONFIG_IKCONFIG_PROC=y +CONFIG_NAMESPACES=y +# CONFIG_UTS_NS is not set +# CONFIG_PID_NS is not set +CONFIG_BLK_DEV_INITRD=y +CONFIG_KALLSYMS_ALL=y +CONFIG_EMBEDDED=y +# CONFIG_SLUB_DEBUG is not set +# CONFIG_COMPAT_BRK is not set +CONFIG_KPROBES=y +CONFIG_MODULES=y +# CONFIG_LBDAF is not set +# CONFIG_BLK_DEV_BSG is not set +# CONFIG_IOSCHED_DEADLINE is not set +# CONFIG_IOSCHED_CFQ is not set +CONFIG_ARC_PLAT_FPGA_LEGACY=y +CONFIG_ARC_BOARD_ML509=y +# CONFIG_ARC_HAS_RTSC is not set +CONFIG_ARC_BUILTIN_DTB_NAME="angel4" +CONFIG_PREEMPT=y +# CONFIG_COMPACTION is not set +# CONFIG_CROSS_MEMORY_ATTACH is not set +CONFIG_NET=y +CONFIG_PACKET=y +CONFIG_UNIX=y +CONFIG_UNIX_DIAG=y +CONFIG_NET_KEY=y +CONFIG_INET=y +# CONFIG_IPV6 is not set +# CONFIG_STANDALONE is not set +# CONFIG_PREVENT_FIRMWARE_BUILD is not set +# CONFIG_FIRMWARE_IN_KERNEL is not set +# CONFIG_BLK_DEV is not set +CONFIG_NETDEVICES=y +CONFIG_ARC_EMAC=y +CONFIG_LXT_PHY=y +# CONFIG_INPUT_MOUSEDEV_PSAUX is not set +# CONFIG_INPUT_KEYBOARD is not set +# CONFIG_INPUT_MOUSE is not set +# CONFIG_SERIO is not set +# CONFIG_LEGACY_PTYS is not set +# CONFIG_DEVKMEM is not set +CONFIG_SERIAL_ARC=y +CONFIG_SERIAL_ARC_CONSOLE=y +# CONFIG_HW_RANDOM is not set +# CONFIG_HWMON is not set +# CONFIG_VGA_CONSOLE is not set +# CONFIG_HID is not set +# CONFIG_USB_SUPPORT is not set +# CONFIG_IOMMU_SUPPORT is not set +CONFIG_EXT2_FS=y +CONFIG_EXT2_FS_XATTR=y +CONFIG_TMPFS=y +# CONFIG_MISC_FILESYSTEMS is not set +CONFIG_NFS_FS=y +# CONFIG_ENABLE_WARN_DEPRECATED is not set +# CONFIG_ENABLE_MUST_CHECK is not set +CONFIG_XZ_DEC=y diff --git a/arch/arc/include/asm/perf_event.h b/arch/arc/include/asm/perf_event.h index 115ad96480e6..cbf755e32a03 100644 --- a/arch/arc/include/asm/perf_event.h +++ b/arch/arc/include/asm/perf_event.h @@ -1,5 +1,7 @@ /* - * Copyright (C) 2011-2012 Synopsys, Inc. (www.synopsys.com) + * Linux performance counter support for ARC + * + * Copyright (C) 2011-2013 Synopsys, Inc. (www.synopsys.com) * * This program is free software; you can redistribute it and/or modify * it under the terms of the GNU General Public License version 2 as @@ -10,4 +12,204 @@ #ifndef __ASM_PERF_EVENT_H #define __ASM_PERF_EVENT_H +/* real maximum varies per CPU, this is the maximum supported by the driver */ +#define ARC_PMU_MAX_HWEVENTS 64 + +#define ARC_REG_CC_BUILD 0xF6 +#define ARC_REG_CC_INDEX 0x240 +#define ARC_REG_CC_NAME0 0x241 +#define ARC_REG_CC_NAME1 0x242 + +#define ARC_REG_PCT_BUILD 0xF5 +#define ARC_REG_PCT_COUNTL 0x250 +#define ARC_REG_PCT_COUNTH 0x251 +#define ARC_REG_PCT_SNAPL 0x252 +#define ARC_REG_PCT_SNAPH 0x253 +#define ARC_REG_PCT_CONFIG 0x254 +#define ARC_REG_PCT_CONTROL 0x255 +#define ARC_REG_PCT_INDEX 0x256 + +#define ARC_REG_PCT_CONTROL_CC (1 << 16) /* clear counts */ +#define ARC_REG_PCT_CONTROL_SN (1 << 17) /* snapshot */ + +struct arc_reg_pct_build { +#ifdef CONFIG_CPU_BIG_ENDIAN + unsigned int m:8, c:8, r:6, s:2, v:8; +#else + unsigned int v:8, s:2, r:6, c:8, m:8; +#endif +}; + +struct arc_reg_cc_build { +#ifdef CONFIG_CPU_BIG_ENDIAN + unsigned int c:16, r:8, v:8; +#else + unsigned int v:8, r:8, c:16; +#endif +}; + +#define PERF_COUNT_ARC_DCLM (PERF_COUNT_HW_MAX + 0) +#define PERF_COUNT_ARC_DCSM (PERF_COUNT_HW_MAX + 1) +#define PERF_COUNT_ARC_ICM (PERF_COUNT_HW_MAX + 2) +#define PERF_COUNT_ARC_BPOK (PERF_COUNT_HW_MAX + 3) +#define PERF_COUNT_ARC_EDTLB (PERF_COUNT_HW_MAX + 4) +#define PERF_COUNT_ARC_EITLB (PERF_COUNT_HW_MAX + 5) +#define PERF_COUNT_ARC_HW_MAX (PERF_COUNT_HW_MAX + 6) + +/* + * The "generalized" performance events seem to really be a copy + * of the available events on x86 processors; the mapping to ARC + * events is not always possible 1-to-1. Fortunately, there doesn't + * seem to be an exact definition for these events, so we can cheat + * a bit where necessary. + * + * In particular, the following PERF events may behave a bit differently + * compared to other architectures: + * + * PERF_COUNT_HW_CPU_CYCLES + * Cycles not in halted state + * + * PERF_COUNT_HW_REF_CPU_CYCLES + * Reference cycles not in halted state, same as PERF_COUNT_HW_CPU_CYCLES + * for now as we don't do Dynamic Voltage/Frequency Scaling (yet) + * + * PERF_COUNT_HW_BUS_CYCLES + * Unclear what this means, Intel uses 0x013c, which according to + * their datasheet means "unhalted reference cycles". It sounds similar + * to PERF_COUNT_HW_REF_CPU_CYCLES, and we use the same counter for it. + * + * PERF_COUNT_HW_STALLED_CYCLES_BACKEND + * PERF_COUNT_HW_STALLED_CYCLES_FRONTEND + * The ARC 700 can either measure stalls per pipeline stage, or all stalls + * combined; for now we assign all stalls to STALLED_CYCLES_BACKEND + * and all pipeline flushes (e.g. caused by mispredicts, etc.) to + * STALLED_CYCLES_FRONTEND. + * + * We could start multiple performance counters and combine everything + * afterwards, but that makes it complicated. + * + * Note that I$ cache misses aren't counted by either of the two! + */ + +static const char * const arc_pmu_ev_hw_map[] = { + [PERF_COUNT_HW_CPU_CYCLES] = "crun", + [PERF_COUNT_HW_REF_CPU_CYCLES] = "crun", + [PERF_COUNT_HW_BUS_CYCLES] = "crun", + [PERF_COUNT_HW_INSTRUCTIONS] = "iall", + [PERF_COUNT_HW_BRANCH_MISSES] = "bpfail", + [PERF_COUNT_HW_BRANCH_INSTRUCTIONS] = "ijmp", + [PERF_COUNT_HW_STALLED_CYCLES_FRONTEND] = "bflush", + [PERF_COUNT_HW_STALLED_CYCLES_BACKEND] = "bstall", + [PERF_COUNT_ARC_DCLM] = "dclm", + [PERF_COUNT_ARC_DCSM] = "dcsm", + [PERF_COUNT_ARC_ICM] = "icm", + [PERF_COUNT_ARC_BPOK] = "bpok", + [PERF_COUNT_ARC_EDTLB] = "edtlb", + [PERF_COUNT_ARC_EITLB] = "eitlb", +}; + +#define C(_x) PERF_COUNT_HW_CACHE_##_x +#define CACHE_OP_UNSUPPORTED 0xffff + +static const unsigned arc_pmu_cache_map[C(MAX)][C(OP_MAX)][C(RESULT_MAX)] = { + [C(L1D)] = { + [C(OP_READ)] = { + [C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED, + [C(RESULT_MISS)] = PERF_COUNT_ARC_DCLM, + }, + [C(OP_WRITE)] = { + [C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED, + [C(RESULT_MISS)] = PERF_COUNT_ARC_DCSM, + }, + [C(OP_PREFETCH)] = { + [C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED, + [C(RESULT_MISS)] = CACHE_OP_UNSUPPORTED, + }, + }, + [C(L1I)] = { + [C(OP_READ)] = { + [C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED, + [C(RESULT_MISS)] = PERF_COUNT_ARC_ICM, + }, + [C(OP_WRITE)] = { + [C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED, + [C(RESULT_MISS)] = CACHE_OP_UNSUPPORTED, + }, + [C(OP_PREFETCH)] = { + [C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED, + [C(RESULT_MISS)] = CACHE_OP_UNSUPPORTED, + }, + }, + [C(LL)] = { + [C(OP_READ)] = { + [C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED, + [C(RESULT_MISS)] = CACHE_OP_UNSUPPORTED, + }, + [C(OP_WRITE)] = { + [C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED, + [C(RESULT_MISS)] = CACHE_OP_UNSUPPORTED, + }, + [C(OP_PREFETCH)] = { + [C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED, + [C(RESULT_MISS)] = CACHE_OP_UNSUPPORTED, + }, + }, + [C(DTLB)] = { + [C(OP_READ)] = { + [C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED, + [C(RESULT_MISS)] = PERF_COUNT_ARC_EDTLB, + }, + [C(OP_WRITE)] = { + [C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED, + [C(RESULT_MISS)] = CACHE_OP_UNSUPPORTED, + }, + [C(OP_PREFETCH)] = { + [C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED, + [C(RESULT_MISS)] = CACHE_OP_UNSUPPORTED, + }, + }, + [C(ITLB)] = { + [C(OP_READ)] = { + [C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED, + [C(RESULT_MISS)] = PERF_COUNT_ARC_EITLB, + }, + [C(OP_WRITE)] = { + [C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED, + [C(RESULT_MISS)] = CACHE_OP_UNSUPPORTED, + }, + [C(OP_PREFETCH)] = { + [C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED, + [C(RESULT_MISS)] = CACHE_OP_UNSUPPORTED, + }, + }, + [C(BPU)] = { + [C(OP_READ)] = { + [C(RESULT_ACCESS)] = PERF_COUNT_HW_BRANCH_INSTRUCTIONS, + [C(RESULT_MISS)] = PERF_COUNT_HW_BRANCH_MISSES, + }, + [C(OP_WRITE)] = { + [C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED, + [C(RESULT_MISS)] = CACHE_OP_UNSUPPORTED, + }, + [C(OP_PREFETCH)] = { + [C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED, + [C(RESULT_MISS)] = CACHE_OP_UNSUPPORTED, + }, + }, + [C(NODE)] = { + [C(OP_READ)] = { + [C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED, + [C(RESULT_MISS)] = CACHE_OP_UNSUPPORTED, + }, + [C(OP_WRITE)] = { + [C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED, + [C(RESULT_MISS)] = CACHE_OP_UNSUPPORTED, + }, + [C(OP_PREFETCH)] = { + [C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED, + [C(RESULT_MISS)] = CACHE_OP_UNSUPPORTED, + }, + }, +}; + #endif /* __ASM_PERF_EVENT_H */ diff --git a/arch/arc/include/asm/pgalloc.h b/arch/arc/include/asm/pgalloc.h index 36a9f20c21a3..81208bfd9dcb 100644 --- a/arch/arc/include/asm/pgalloc.h +++ b/arch/arc/include/asm/pgalloc.h @@ -105,11 +105,16 @@ static inline pgtable_t pte_alloc_one(struct mm_struct *mm, unsigned long address) { pgtable_t pte_pg; + struct page *page; pte_pg = __get_free_pages(GFP_KERNEL | __GFP_REPEAT, __get_order_pte()); - if (pte_pg) { - memzero((void *)pte_pg, PTRS_PER_PTE * 4); - pgtable_page_ctor(virt_to_page(pte_pg)); + if (!pte_pg) + return 0; + memzero((void *)pte_pg, PTRS_PER_PTE * 4); + page = virt_to_page(pte_pg); + if (!pgtable_page_ctor(page)) { + __free_page(page); + return 0; } return pte_pg; diff --git a/arch/arc/include/asm/thread_info.h b/arch/arc/include/asm/thread_info.h index 2d50a4cdd7f3..45be21672011 100644 --- a/arch/arc/include/asm/thread_info.h +++ b/arch/arc/include/asm/thread_info.h @@ -80,8 +80,6 @@ static inline __attribute_const__ struct thread_info *current_thread_info(void) #endif /* !__ASSEMBLY__ */ -#define PREEMPT_ACTIVE 0x10000000 - /* * thread information flags * - these are process state flags that various assembly files may need to diff --git a/arch/arc/kernel/Makefile b/arch/arc/kernel/Makefile index c242ef07ba70..8004b4fa6461 100644 --- a/arch/arc/kernel/Makefile +++ b/arch/arc/kernel/Makefile @@ -19,6 +19,7 @@ obj-$(CONFIG_KPROBES) += kprobes.o obj-$(CONFIG_ARC_MISALIGN_ACCESS) += unaligned.o obj-$(CONFIG_KGDB) += kgdb.o obj-$(CONFIG_ARC_METAWARE_HLINK) += arc_hostlink.o +obj-$(CONFIG_PERF_EVENTS) += perf_event.o obj-$(CONFIG_ARC_FPU_SAVE_RESTORE) += fpu.o CFLAGS_fpu.o += -mdpfp diff --git a/arch/arc/kernel/kprobes.c b/arch/arc/kernel/kprobes.c index eb1c2ee5eaf0..42b05046fad9 100644 --- a/arch/arc/kernel/kprobes.c +++ b/arch/arc/kernel/kprobes.c @@ -327,7 +327,7 @@ int __kprobes kprobe_fault_handler(struct pt_regs *regs, unsigned long trapnr) */ /* We increment the nmissed count for accounting, - * we can also use npre/npostfault count for accouting + * we can also use npre/npostfault count for accounting * these specific fault cases. */ kprobes_inc_nmissed_count(cur); diff --git a/arch/arc/kernel/perf_event.c b/arch/arc/kernel/perf_event.c new file mode 100644 index 000000000000..e46d81f70979 --- /dev/null +++ b/arch/arc/kernel/perf_event.c @@ -0,0 +1,326 @@ +/* + * Linux performance counter support for ARC700 series + * + * Copyright (C) 2013 Synopsys, Inc. (www.synopsys.com) + * + * This code is inspired by the perf support of various other architectures. + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + * + */ +#include <linux/errno.h> +#include <linux/module.h> +#include <linux/of.h> +#include <linux/perf_event.h> +#include <linux/platform_device.h> +#include <asm/arcregs.h> + +struct arc_pmu { + struct pmu pmu; + int counter_size; /* in bits */ + int n_counters; + unsigned long used_mask[BITS_TO_LONGS(ARC_PMU_MAX_HWEVENTS)]; + int ev_hw_idx[PERF_COUNT_ARC_HW_MAX]; +}; + +/* read counter #idx; note that counter# != event# on ARC! */ +static uint64_t arc_pmu_read_counter(int idx) +{ + uint32_t tmp; + uint64_t result; + + /* + * ARC supports making 'snapshots' of the counters, so we don't + * need to care about counters wrapping to 0 underneath our feet + */ + write_aux_reg(ARC_REG_PCT_INDEX, idx); + tmp = read_aux_reg(ARC_REG_PCT_CONTROL); + write_aux_reg(ARC_REG_PCT_CONTROL, tmp | ARC_REG_PCT_CONTROL_SN); + result = (uint64_t) (read_aux_reg(ARC_REG_PCT_SNAPH)) << 32; + result |= read_aux_reg(ARC_REG_PCT_SNAPL); + + return result; +} + +static void arc_perf_event_update(struct perf_event *event, + struct hw_perf_event *hwc, int idx) +{ + struct arc_pmu *arc_pmu = container_of(event->pmu, struct arc_pmu, pmu); + uint64_t prev_raw_count, new_raw_count; + int64_t delta; + + do { + prev_raw_count = local64_read(&hwc->prev_count); + new_raw_count = arc_pmu_read_counter(idx); + } while (local64_cmpxchg(&hwc->prev_count, prev_raw_count, + new_raw_count) != prev_raw_count); + + delta = (new_raw_count - prev_raw_count) & + ((1ULL << arc_pmu->counter_size) - 1ULL); + + local64_add(delta, &event->count); + local64_sub(delta, &hwc->period_left); +} + +static void arc_pmu_read(struct perf_event *event) +{ + arc_perf_event_update(event, &event->hw, event->hw.idx); +} + +static int arc_pmu_cache_event(u64 config) +{ + unsigned int cache_type, cache_op, cache_result; + int ret; + + cache_type = (config >> 0) & 0xff; + cache_op = (config >> 8) & 0xff; + cache_result = (config >> 16) & 0xff; + if (cache_type >= PERF_COUNT_HW_CACHE_MAX) + return -EINVAL; + if (cache_type >= PERF_COUNT_HW_CACHE_OP_MAX) + return -EINVAL; + if (cache_type >= PERF_COUNT_HW_CACHE_RESULT_MAX) + return -EINVAL; + + ret = arc_pmu_cache_map[cache_type][cache_op][cache_result]; + + if (ret == CACHE_OP_UNSUPPORTED) + return -ENOENT; + + return ret; +} + +/* initializes hw_perf_event structure if event is supported */ +static int arc_pmu_event_init(struct perf_event *event) +{ + struct arc_pmu *arc_pmu = container_of(event->pmu, struct arc_pmu, pmu); + struct hw_perf_event *hwc = &event->hw; + int ret; + + /* ARC 700 PMU does not support sampling events */ + if (is_sampling_event(event)) + return -ENOENT; + + switch (event->attr.type) { + case PERF_TYPE_HARDWARE: + if (event->attr.config >= PERF_COUNT_HW_MAX) + return -ENOENT; + if (arc_pmu->ev_hw_idx[event->attr.config] < 0) + return -ENOENT; + hwc->config = arc_pmu->ev_hw_idx[event->attr.config]; + pr_debug("initializing event %d with cfg %d\n", + (int) event->attr.config, (int) hwc->config); + return 0; + case PERF_TYPE_HW_CACHE: + ret = arc_pmu_cache_event(event->attr.config); + if (ret < 0) + return ret; + hwc->config = arc_pmu->ev_hw_idx[ret]; + return 0; + default: + return -ENOENT; + } +} + +/* starts all counters */ +static void arc_pmu_enable(struct pmu *pmu) +{ + uint32_t tmp; + tmp = read_aux_reg(ARC_REG_PCT_CONTROL); + write_aux_reg(ARC_REG_PCT_CONTROL, (tmp & 0xffff0000) | 0x1); +} + +/* stops all counters */ +static void arc_pmu_disable(struct pmu *pmu) +{ + uint32_t tmp; + tmp = read_aux_reg(ARC_REG_PCT_CONTROL); + write_aux_reg(ARC_REG_PCT_CONTROL, (tmp & 0xffff0000) | 0x0); +} + +/* + * Assigns hardware counter to hardware condition. + * Note that there is no separate start/stop mechanism; + * stopping is achieved by assigning the 'never' condition + */ +static void arc_pmu_start(struct perf_event *event, int flags) +{ + struct hw_perf_event *hwc = &event->hw; + int idx = hwc->idx; + + if (WARN_ON_ONCE(idx == -1)) + return; + + if (flags & PERF_EF_RELOAD) + WARN_ON_ONCE(!(event->hw.state & PERF_HES_UPTODATE)); + + event->hw.state = 0; + + /* enable ARC pmu here */ + write_aux_reg(ARC_REG_PCT_INDEX, idx); + write_aux_reg(ARC_REG_PCT_CONFIG, hwc->config); +} + +static void arc_pmu_stop(struct perf_event *event, int flags) +{ + struct hw_perf_event *hwc = &event->hw; + int idx = hwc->idx; + + if (!(event->hw.state & PERF_HES_STOPPED)) { + /* stop ARC pmu here */ + write_aux_reg(ARC_REG_PCT_INDEX, idx); + + /* condition code #0 is always "never" */ + write_aux_reg(ARC_REG_PCT_CONFIG, 0); + + event->hw.state |= PERF_HES_STOPPED; + } + + if ((flags & PERF_EF_UPDATE) && + !(event->hw.state & PERF_HES_UPTODATE)) { + arc_perf_event_update(event, &event->hw, idx); + event->hw.state |= PERF_HES_UPTODATE; + } +} + +static void arc_pmu_del(struct perf_event *event, int flags) +{ + struct arc_pmu *arc_pmu = container_of(event->pmu, struct arc_pmu, pmu); + + arc_pmu_stop(event, PERF_EF_UPDATE); + __clear_bit(event->hw.idx, arc_pmu->used_mask); + + perf_event_update_userpage(event); +} + +/* allocate hardware counter and optionally start counting */ +static int arc_pmu_add(struct perf_event *event, int flags) +{ + struct arc_pmu *arc_pmu = container_of(event->pmu, struct arc_pmu, pmu); + struct hw_perf_event *hwc = &event->hw; + int idx = hwc->idx; + + if (__test_and_set_bit(idx, arc_pmu->used_mask)) { + idx = find_first_zero_bit(arc_pmu->used_mask, + arc_pmu->n_counters); + if (idx == arc_pmu->n_counters) + return -EAGAIN; + + __set_bit(idx, arc_pmu->used_mask); + hwc->idx = idx; + } + + write_aux_reg(ARC_REG_PCT_INDEX, idx); + write_aux_reg(ARC_REG_PCT_CONFIG, 0); + write_aux_reg(ARC_REG_PCT_COUNTL, 0); + write_aux_reg(ARC_REG_PCT_COUNTH, 0); + local64_set(&hwc->prev_count, 0); + + hwc->state = PERF_HES_UPTODATE | PERF_HES_STOPPED; + if (flags & PERF_EF_START) + arc_pmu_start(event, PERF_EF_RELOAD); + + perf_event_update_userpage(event); + + return 0; +} + +static int arc_pmu_device_probe(struct platform_device *pdev) +{ + struct arc_pmu *arc_pmu; + struct arc_reg_pct_build pct_bcr; + struct arc_reg_cc_build cc_bcr; + int i, j, ret; + + union cc_name { + struct { + uint32_t word0, word1; + char sentinel; + } indiv; + char str[9]; + } cc_name; + + + READ_BCR(ARC_REG_PCT_BUILD, pct_bcr); + if (!pct_bcr.v) { + pr_err("This core does not have performance counters!\n"); + return -ENODEV; + } + + arc_pmu = devm_kzalloc(&pdev->dev, sizeof(struct arc_pmu), + GFP_KERNEL); + if (!arc_pmu) + return -ENOMEM; + + arc_pmu->n_counters = pct_bcr.c; + BUG_ON(arc_pmu->n_counters > ARC_PMU_MAX_HWEVENTS); + + arc_pmu->counter_size = 32 + (pct_bcr.s << 4); + pr_info("ARC PMU found with %d counters of size %d bits\n", + arc_pmu->n_counters, arc_pmu->counter_size); + + READ_BCR(ARC_REG_CC_BUILD, cc_bcr); + + if (!cc_bcr.v) + pr_err("Strange! Performance counters exist, but no countable conditions?\n"); + + pr_info("ARC PMU has %d countable conditions\n", cc_bcr.c); + + cc_name.str[8] = 0; + for (i = 0; i < PERF_COUNT_HW_MAX; i++) + arc_pmu->ev_hw_idx[i] = -1; + + for (j = 0; j < cc_bcr.c; j++) { + write_aux_reg(ARC_REG_CC_INDEX, j); + cc_name.indiv.word0 = read_aux_reg(ARC_REG_CC_NAME0); + cc_name.indiv.word1 = read_aux_reg(ARC_REG_CC_NAME1); + for (i = 0; i < ARRAY_SIZE(arc_pmu_ev_hw_map); i++) { + if (arc_pmu_ev_hw_map[i] && + !strcmp(arc_pmu_ev_hw_map[i], cc_name.str) && + strlen(arc_pmu_ev_hw_map[i])) { + pr_debug("mapping %d to idx %d with name %s\n", + i, j, cc_name.str); + arc_pmu->ev_hw_idx[i] = j; + } + } + } + + arc_pmu->pmu = (struct pmu) { + .pmu_enable = arc_pmu_enable, + .pmu_disable = arc_pmu_disable, + .event_init = arc_pmu_event_init, + .add = arc_pmu_add, + .del = arc_pmu_del, + .start = arc_pmu_start, + .stop = arc_pmu_stop, + .read = arc_pmu_read, + }; + + ret = perf_pmu_register(&arc_pmu->pmu, pdev->name, PERF_TYPE_RAW); + + return ret; +} + +#ifdef CONFIG_OF +static const struct of_device_id arc_pmu_match[] = { + { .compatible = "snps,arc700-pmu" }, + {}, +}; +MODULE_DEVICE_TABLE(of, arc_pmu_match); +#endif + +static struct platform_driver arc_pmu_driver = { + .driver = { + .name = "arc700-pmu", + .of_match_table = of_match_ptr(arc_pmu_match), + }, + .probe = arc_pmu_device_probe, +}; + +module_platform_driver(arc_pmu_driver); + +MODULE_LICENSE("GPL"); +MODULE_AUTHOR("Mischa Jonker <mjonker@synopsys.com>"); +MODULE_DESCRIPTION("ARC PMU driver"); diff --git a/arch/arc/plat-tb10x/Kconfig b/arch/arc/plat-tb10x/Kconfig index 1ab386bb5da8..6994c188dc88 100644 --- a/arch/arc/plat-tb10x/Kconfig +++ b/arch/arc/plat-tb10x/Kconfig @@ -20,8 +20,10 @@ menuconfig ARC_PLAT_TB10X bool "Abilis TB10x" select COMMON_CLK select PINCTRL + select PINCTRL_TB10X select PINMUX select ARCH_REQUIRE_GPIOLIB + select GPIO_TB10X select TB10X_IRQC help Support for platforms based on the TB10x home media gateway SOC by diff --git a/arch/arm/Kconfig b/arch/arm/Kconfig index c2a372a6994f..c1f1a7eee953 100644 --- a/arch/arm/Kconfig +++ b/arch/arm/Kconfig @@ -5,6 +5,7 @@ config ARM select ARCH_HAS_ATOMIC64_DEC_IF_POSITIVE select ARCH_HAS_TICK_BROADCAST if GENERIC_CLOCKEVENTS_BROADCAST select ARCH_HAVE_CUSTOM_GPIO_H + select ARCH_MIGHT_HAVE_PC_PARPORT select ARCH_USE_CMPXCHG_LOCKREF select ARCH_WANT_IPC_PARSE_VERSION select BUILDTIME_EXTABLE_SORT if MMU @@ -1432,7 +1433,6 @@ config SMP depends on GENERIC_CLOCKEVENTS depends on HAVE_SMP depends on MMU || ARM_MPU - select USE_GENERIC_SMP_HELPERS help This enables support for systems with more than one CPU. If you have a system with only one CPU, like most personal computers, say N. If @@ -1868,6 +1868,12 @@ config CC_STACKPROTECTOR neutralized via a kernel panic. This feature requires gcc version 4.2 or above. +config SWIOTLB + def_bool y + +config IOMMU_HELPER + def_bool SWIOTLB + config XEN_DOM0 def_bool y depends on XEN @@ -1878,6 +1884,7 @@ config XEN depends on CPU_V7 && !CPU_V6 depends on !GENERIC_ATOMIC64 select ARM_PSCI + select SWIOTLB_XEN help Say Y if you want to run Linux in a Virtual Machine on Xen on ARM. diff --git a/arch/arm/boot/dts/am335x-evm.dts b/arch/arm/boot/dts/am335x-evm.dts index 987429436171..7e6c64ed966d 100644 --- a/arch/arm/boot/dts/am335x-evm.dts +++ b/arch/arm/boot/dts/am335x-evm.dts @@ -630,7 +630,7 @@ tsc { ti,wires = <4>; ti,x-plate-resistance = <200>; - ti,coordiante-readouts = <5>; + ti,coordinate-readouts = <5>; ti,wire-config = <0x00 0x11 0x22 0x33>; }; diff --git a/arch/arm/boot/dts/am335x-evmsk.dts b/arch/arm/boot/dts/am335x-evmsk.dts index 03febf85fd2f..4718ec4a4dbf 100644 --- a/arch/arm/boot/dts/am335x-evmsk.dts +++ b/arch/arm/boot/dts/am335x-evmsk.dts @@ -485,3 +485,13 @@ tx-num-evt = <1>; rx-num-evt = <1>; }; + +&tscadc { + status = "okay"; + tsc { + ti,wires = <4>; + ti,x-plate-resistance = <200>; + ti,coordinate-readouts = <5>; + ti,wire-config = <0x00 0x11 0x22 0x33>; + }; +}; diff --git a/arch/arm/boot/dts/ecx-2000.dts b/arch/arm/boot/dts/ecx-2000.dts index 139b40cc3a23..2ccbb57fbfa8 100644 --- a/arch/arm/boot/dts/ecx-2000.dts +++ b/arch/arm/boot/dts/ecx-2000.dts @@ -85,6 +85,12 @@ <1 10 0xf08>; }; + memory-controller@fff00000 { + compatible = "calxeda,ecx-2000-ddr-ctrl"; + reg = <0xfff00000 0x1000>; + interrupts = <0 91 4>; + }; + intc: interrupt-controller@fff11000 { compatible = "arm,cortex-a15-gic"; #interrupt-cells = <3>; diff --git a/arch/arm/boot/dts/ecx-common.dtsi b/arch/arm/boot/dts/ecx-common.dtsi index bc22557d7a6a..b90045a8f8e3 100644 --- a/arch/arm/boot/dts/ecx-common.dtsi +++ b/arch/arm/boot/dts/ecx-common.dtsi @@ -53,12 +53,6 @@ status = "disabled"; }; - memory-controller@fff00000 { - compatible = "calxeda,hb-ddr-ctrl"; - reg = <0xfff00000 0x1000>; - interrupts = <0 91 4>; - }; - ipc@fff20000 { compatible = "arm,pl320", "arm,primecell"; reg = <0xfff20000 0x1000>; diff --git a/arch/arm/boot/dts/highbank.dts b/arch/arm/boot/dts/highbank.dts index 6aad34ad9517..ed14aeac0566 100644 --- a/arch/arm/boot/dts/highbank.dts +++ b/arch/arm/boot/dts/highbank.dts @@ -86,6 +86,12 @@ soc { ranges = <0x00000000 0x00000000 0xffffffff>; + memory-controller@fff00000 { + compatible = "calxeda,hb-ddr-ctrl"; + reg = <0xfff00000 0x1000>; + interrupts = <0 91 4>; + }; + timer@fff10600 { compatible = "arm,cortex-a9-twd-timer"; reg = <0xfff10600 0x20>; diff --git a/arch/arm/boot/dts/imx51.dtsi b/arch/arm/boot/dts/imx51.dtsi index f4dcff3a9969..4bcdd3ad15e5 100644 --- a/arch/arm/boot/dts/imx51.dtsi +++ b/arch/arm/boot/dts/imx51.dtsi @@ -190,7 +190,7 @@ usbphy0: usbphy@0 { compatible = "usb-nop-xceiv"; - clocks = <&clks 124>; + clocks = <&clks 75>; clock-names = "main_clk"; status = "okay"; }; diff --git a/arch/arm/boot/dts/twl4030.dtsi b/arch/arm/boot/dts/twl4030.dtsi index fb1b2ec8eaa9..4217096ee677 100644 --- a/arch/arm/boot/dts/twl4030.dtsi +++ b/arch/arm/boot/dts/twl4030.dtsi @@ -19,6 +19,12 @@ interrupts = <11>; }; + charger: bci { + compatible = "ti,twl4030-bci"; + interrupts = <9>, <2>; + bci3v1-supply = <&vusb3v1>; + }; + watchdog { compatible = "ti,twl4030-wdt"; }; diff --git a/arch/arm/common/edma.c b/arch/arm/common/edma.c index 8e1a0245907f..41bca32409fc 100644 --- a/arch/arm/common/edma.c +++ b/arch/arm/common/edma.c @@ -404,7 +404,7 @@ static irqreturn_t dma_irq_handler(int irq, void *data) BIT(slot)); if (edma_cc[ctlr]->intr_data[channel].callback) edma_cc[ctlr]->intr_data[channel].callback( - channel, DMA_COMPLETE, + channel, EDMA_DMA_COMPLETE, edma_cc[ctlr]->intr_data[channel].data); } } while (sh_ipr); @@ -459,7 +459,7 @@ static irqreturn_t dma_ccerr_handler(int irq, void *data) callback) { edma_cc[ctlr]->intr_data[k]. callback(k, - DMA_CC_ERROR, + EDMA_DMA_CC_ERROR, edma_cc[ctlr]->intr_data [k].data); } diff --git a/arch/arm/configs/prima2_defconfig b/arch/arm/configs/prima2_defconfig index 002a1ceadceb..23591dba47a0 100644 --- a/arch/arm/configs/prima2_defconfig +++ b/arch/arm/configs/prima2_defconfig @@ -39,6 +39,7 @@ CONFIG_SPI=y CONFIG_SPI_SIRF=y CONFIG_SPI_SPIDEV=y # CONFIG_HWMON is not set +CONFIG_WATCHDOG=y CONFIG_USB_GADGET=y CONFIG_USB_MASS_STORAGE=m CONFIG_MMC=y diff --git a/arch/arm/configs/vt8500_v6_v7_defconfig b/arch/arm/configs/vt8500_v6_v7_defconfig new file mode 100644 index 000000000000..f0520176acd0 --- /dev/null +++ b/arch/arm/configs/vt8500_v6_v7_defconfig @@ -0,0 +1,90 @@ +CONFIG_IRQ_DOMAIN_DEBUG=y +CONFIG_NO_HZ=y +CONFIG_HIGH_RES_TIMERS=y +CONFIG_BLK_DEV_INITRD=y +CONFIG_ARCH_MULTI_V6=y +CONFIG_ARCH_WM8750=y +CONFIG_ARCH_WM8850=y +CONFIG_ARM_ERRATA_720789=y +CONFIG_ARM_ERRATA_754322=y +CONFIG_ARM_ERRATA_775420=y +CONFIG_HAVE_ARM_ARCH_TIMER=y +CONFIG_AEABI=y +CONFIG_HIGHMEM=y +CONFIG_HIGHPTE=y +CONFIG_ARM_APPENDED_DTB=y +CONFIG_ARM_ATAG_DTB_COMPAT=y +CONFIG_VFP=y +CONFIG_NEON=y +CONFIG_PM_RUNTIME=y +CONFIG_NET=y +CONFIG_UNIX=y +CONFIG_INET=y +CONFIG_IP_PNP=y +CONFIG_IP_PNP_DHCP=y +CONFIG_DEVTMPFS=y +CONFIG_DEVTMPFS_MOUNT=y +CONFIG_PROC_DEVICETREE=y +CONFIG_EEPROM_93CX6=y +CONFIG_SCSI=y +CONFIG_BLK_DEV_SD=y +CONFIG_NETDEVICES=y +# CONFIG_NET_CADENCE is not set +# CONFIG_NET_VENDOR_BROADCOM is not set +# CONFIG_NET_VENDOR_CIRRUS is not set +# CONFIG_NET_VENDOR_FARADAY is not set +# CONFIG_NET_VENDOR_INTEL is not set +# CONFIG_NET_VENDOR_MARVELL is not set +# CONFIG_NET_VENDOR_MICREL is not set +# CONFIG_NET_VENDOR_NATSEMI is not set +# CONFIG_NET_VENDOR_SEEQ is not set +# CONFIG_NET_VENDOR_SMSC is not set +# CONFIG_NET_VENDOR_STMICRO is not set +CONFIG_VIA_VELOCITY=y +# CONFIG_NET_VENDOR_WIZNET is not set +CONFIG_PHYLIB=y +CONFIG_INPUT_MATRIXKMAP=y +CONFIG_SERIAL_VT8500=y +CONFIG_SERIAL_VT8500_CONSOLE=y +CONFIG_I2C=y +CONFIG_I2C_WMT=y +CONFIG_PINCTRL_SINGLE=y +CONFIG_PINCTRL_WM8750=y +CONFIG_GPIO_GENERIC_PLATFORM=y +CONFIG_POWER_SUPPLY=y +CONFIG_POWER_RESET=y +CONFIG_MFD_SYSCON=y +CONFIG_REGULATOR=y +CONFIG_REGULATOR_FIXED_VOLTAGE=y +CONFIG_REGULATOR_GPIO=y +CONFIG_USB=y +CONFIG_USB_EHCI_HCD=y +CONFIG_USB_EHCI_HCD_PLATFORM=y +CONFIG_USB_UHCI_HCD=y +CONFIG_USB_STORAGE=y +CONFIG_NOP_USB_XCEIV=y +CONFIG_USB_GPIO_VBUS=y +CONFIG_USB_ULPI=y +CONFIG_MMC=y +CONFIG_MMC_DEBUG=y +CONFIG_NEW_LEDS=y +CONFIG_LEDS_CLASS=y +CONFIG_LEDS_TRIGGERS=y +CONFIG_RTC_CLASS=y +CONFIG_RTC_DRV_VT8500=y +CONFIG_DMADEVICES=y +CONFIG_COMMON_CLK_DEBUG=y +# CONFIG_IOMMU_SUPPORT is not set +CONFIG_PWM=y +CONFIG_PWM_VT8500=y +CONFIG_RESET_CONTROLLER=y +CONFIG_GENERIC_PHY=y +CONFIG_EXT4_FS=y +CONFIG_TMPFS=y +CONFIG_NFS_FS=y +CONFIG_NFS_V3_ACL=y +CONFIG_NFS_V4=y +CONFIG_ROOT_NFS=y +CONFIG_PRINTK_TIME=y +CONFIG_DEBUG_KERNEL=y +CONFIG_LOCKUP_DETECTOR=y diff --git a/arch/arm/include/asm/dma-mapping.h b/arch/arm/include/asm/dma-mapping.h index 863cd84eb1a2..e701a4d9aa59 100644 --- a/arch/arm/include/asm/dma-mapping.h +++ b/arch/arm/include/asm/dma-mapping.h @@ -11,17 +11,28 @@ #include <asm-generic/dma-coherent.h> #include <asm/memory.h> +#include <xen/xen.h> +#include <asm/xen/hypervisor.h> + #define DMA_ERROR_CODE (~0) extern struct dma_map_ops arm_dma_ops; extern struct dma_map_ops arm_coherent_dma_ops; -static inline struct dma_map_ops *get_dma_ops(struct device *dev) +static inline struct dma_map_ops *__generic_dma_ops(struct device *dev) { if (dev && dev->archdata.dma_ops) return dev->archdata.dma_ops; return &arm_dma_ops; } +static inline struct dma_map_ops *get_dma_ops(struct device *dev) +{ + if (xen_initial_domain()) + return xen_dma_ops; + else + return __generic_dma_ops(dev); +} + static inline void set_dma_ops(struct device *dev, struct dma_map_ops *ops) { BUG_ON(!dev); @@ -94,6 +105,39 @@ static inline unsigned long dma_max_pfn(struct device *dev) } #define dma_max_pfn(dev) dma_max_pfn(dev) +static inline dma_addr_t phys_to_dma(struct device *dev, phys_addr_t paddr) +{ + unsigned int offset = paddr & ~PAGE_MASK; + return pfn_to_dma(dev, __phys_to_pfn(paddr)) + offset; +} + +static inline phys_addr_t dma_to_phys(struct device *dev, dma_addr_t dev_addr) +{ + unsigned int offset = dev_addr & ~PAGE_MASK; + return __pfn_to_phys(dma_to_pfn(dev, dev_addr)) + offset; +} + +static inline bool dma_capable(struct device *dev, dma_addr_t addr, size_t size) +{ + u64 limit, mask; + + if (!dev->dma_mask) + return 0; + + mask = *dev->dma_mask; + + limit = (mask + 1) & ~mask; + if (limit && size > limit) + return 0; + + if ((addr | (addr + size - 1)) & ~mask) + return 0; + + return 1; +} + +static inline void dma_mark_clean(void *addr, size_t size) { } + /* * DMA errors are defined by all-bits-set in the DMA address. */ diff --git a/arch/arm/include/asm/hardware/iop3xx-adma.h b/arch/arm/include/asm/hardware/iop3xx-adma.h index 9b28f1243bdc..240b29ef17db 100644 --- a/arch/arm/include/asm/hardware/iop3xx-adma.h +++ b/arch/arm/include/asm/hardware/iop3xx-adma.h @@ -393,36 +393,6 @@ static inline int iop_chan_zero_sum_slot_count(size_t len, int src_cnt, return slot_cnt; } -static inline int iop_desc_is_pq(struct iop_adma_desc_slot *desc) -{ - return 0; -} - -static inline u32 iop_desc_get_dest_addr(struct iop_adma_desc_slot *desc, - struct iop_adma_chan *chan) -{ - union iop3xx_desc hw_desc = { .ptr = desc->hw_desc, }; - - switch (chan->device->id) { - case DMA0_ID: - case DMA1_ID: - return hw_desc.dma->dest_addr; - case AAU_ID: - return hw_desc.aau->dest_addr; - default: - BUG(); - } - return 0; -} - - -static inline u32 iop_desc_get_qdest_addr(struct iop_adma_desc_slot *desc, - struct iop_adma_chan *chan) -{ - BUG(); - return 0; -} - static inline u32 iop_desc_get_byte_count(struct iop_adma_desc_slot *desc, struct iop_adma_chan *chan) { diff --git a/arch/arm/include/asm/hardware/iop_adma.h b/arch/arm/include/asm/hardware/iop_adma.h index 122f86d8c991..250760e08103 100644 --- a/arch/arm/include/asm/hardware/iop_adma.h +++ b/arch/arm/include/asm/hardware/iop_adma.h @@ -82,8 +82,6 @@ struct iop_adma_chan { * @slot_cnt: total slots used in an transaction (group of operations) * @slots_per_op: number of slots per operation * @idx: pool index - * @unmap_src_cnt: number of xor sources - * @unmap_len: transaction bytecount * @tx_list: list of descriptors that are associated with one operation * @async_tx: support for the async_tx api * @group_list: list of slots that make up a multi-descriptor transaction @@ -99,8 +97,6 @@ struct iop_adma_desc_slot { u16 slot_cnt; u16 slots_per_op; u16 idx; - u16 unmap_src_cnt; - size_t unmap_len; struct list_head tx_list; struct dma_async_tx_descriptor async_tx; union { diff --git a/arch/arm/include/asm/io.h b/arch/arm/include/asm/io.h index d070741b2b37..3c597c222ef2 100644 --- a/arch/arm/include/asm/io.h +++ b/arch/arm/include/asm/io.h @@ -24,9 +24,11 @@ #ifdef __KERNEL__ #include <linux/types.h> +#include <linux/blk_types.h> #include <asm/byteorder.h> #include <asm/memory.h> #include <asm-generic/pci_iomap.h> +#include <xen/xen.h> /* * ISA I/O bus memory addresses are 1:1 with the physical address. @@ -372,6 +374,13 @@ extern void pci_iounmap(struct pci_dev *dev, void __iomem *addr); #define BIOVEC_MERGEABLE(vec1, vec2) \ ((bvec_to_phys((vec1)) + (vec1)->bv_len) == bvec_to_phys((vec2))) +struct bio_vec; +extern bool xen_biovec_phys_mergeable(const struct bio_vec *vec1, + const struct bio_vec *vec2); +#define BIOVEC_PHYS_MERGEABLE(vec1, vec2) \ + (__BIOVEC_PHYS_MERGEABLE(vec1, vec2) && \ + (!xen_domain() || xen_biovec_phys_mergeable(vec1, vec2))) + #ifdef CONFIG_MMU #define ARCH_HAS_VALID_PHYS_ADDR_RANGE extern int valid_phys_addr_range(phys_addr_t addr, size_t size); diff --git a/arch/arm/include/asm/kvm_arm.h b/arch/arm/include/asm/kvm_arm.h index 64e96960de29..1d3153c7eb41 100644 --- a/arch/arm/include/asm/kvm_arm.h +++ b/arch/arm/include/asm/kvm_arm.h @@ -57,6 +57,7 @@ * TSC: Trap SMC * TSW: Trap cache operations by set/way * TWI: Trap WFI + * TWE: Trap WFE * TIDCP: Trap L2CTLR/L2ECTLR * BSU_IS: Upgrade barriers to the inner shareable domain * FB: Force broadcast of all maintainance operations @@ -67,7 +68,7 @@ */ #define HCR_GUEST_MASK (HCR_TSC | HCR_TSW | HCR_TWI | HCR_VM | HCR_BSU_IS | \ HCR_FB | HCR_TAC | HCR_AMO | HCR_IMO | HCR_FMO | \ - HCR_SWIO | HCR_TIDCP) + HCR_TWE | HCR_SWIO | HCR_TIDCP) #define HCR_VIRT_EXCP_MASK (HCR_VA | HCR_VI | HCR_VF) /* System Control Register (SCTLR) bits */ @@ -95,12 +96,12 @@ #define TTBCR_IRGN1 (3 << 24) #define TTBCR_EPD1 (1 << 23) #define TTBCR_A1 (1 << 22) -#define TTBCR_T1SZ (3 << 16) +#define TTBCR_T1SZ (7 << 16) #define TTBCR_SH0 (3 << 12) #define TTBCR_ORGN0 (3 << 10) #define TTBCR_IRGN0 (3 << 8) #define TTBCR_EPD0 (1 << 7) -#define TTBCR_T0SZ 3 +#define TTBCR_T0SZ (7 << 0) #define HTCR_MASK (TTBCR_T0SZ | TTBCR_IRGN0 | TTBCR_ORGN0 | TTBCR_SH0) /* Hyp System Trap Register */ @@ -208,6 +209,8 @@ #define HSR_EC_DABT (0x24) #define HSR_EC_DABT_HYP (0x25) +#define HSR_WFI_IS_WFE (1U << 0) + #define HSR_HVC_IMM_MASK ((1UL << 16) - 1) #define HSR_DABT_S1PTW (1U << 7) diff --git a/arch/arm/include/asm/kvm_asm.h b/arch/arm/include/asm/kvm_asm.h index a2f43ddcc300..661da11f76f4 100644 --- a/arch/arm/include/asm/kvm_asm.h +++ b/arch/arm/include/asm/kvm_asm.h @@ -39,7 +39,7 @@ #define c6_IFAR 17 /* Instruction Fault Address Register */ #define c7_PAR 18 /* Physical Address Register */ #define c7_PAR_high 19 /* PAR top 32 bits */ -#define c9_L2CTLR 20 /* Cortex A15 L2 Control Register */ +#define c9_L2CTLR 20 /* Cortex A15/A7 L2 Control Register */ #define c10_PRRR 21 /* Primary Region Remap Register */ #define c10_NMRR 22 /* Normal Memory Remap Register */ #define c12_VBAR 23 /* Vector Base Address Register */ diff --git a/arch/arm/include/asm/kvm_emulate.h b/arch/arm/include/asm/kvm_emulate.h index a464e8d7b6c5..0fa90c962ac8 100644 --- a/arch/arm/include/asm/kvm_emulate.h +++ b/arch/arm/include/asm/kvm_emulate.h @@ -157,4 +157,55 @@ static inline u32 kvm_vcpu_hvc_get_imm(struct kvm_vcpu *vcpu) return kvm_vcpu_get_hsr(vcpu) & HSR_HVC_IMM_MASK; } +static inline unsigned long kvm_vcpu_get_mpidr(struct kvm_vcpu *vcpu) +{ + return vcpu->arch.cp15[c0_MPIDR]; +} + +static inline void kvm_vcpu_set_be(struct kvm_vcpu *vcpu) +{ + *vcpu_cpsr(vcpu) |= PSR_E_BIT; +} + +static inline bool kvm_vcpu_is_be(struct kvm_vcpu *vcpu) +{ + return !!(*vcpu_cpsr(vcpu) & PSR_E_BIT); +} + +static inline unsigned long vcpu_data_guest_to_host(struct kvm_vcpu *vcpu, + unsigned long data, + unsigned int len) +{ + if (kvm_vcpu_is_be(vcpu)) { + switch (len) { + case 1: + return data & 0xff; + case 2: + return be16_to_cpu(data & 0xffff); + default: + return be32_to_cpu(data); + } + } + + return data; /* Leave LE untouched */ +} + +static inline unsigned long vcpu_data_host_to_guest(struct kvm_vcpu *vcpu, + unsigned long data, + unsigned int len) +{ + if (kvm_vcpu_is_be(vcpu)) { + switch (len) { + case 1: + return data & 0xff; + case 2: + return cpu_to_be16(data & 0xffff); + default: + return cpu_to_be32(data); + } + } + + return data; /* Leave LE untouched */ +} + #endif /* __ARM_KVM_EMULATE_H__ */ diff --git a/arch/arm/include/asm/kvm_host.h b/arch/arm/include/asm/kvm_host.h index 7d22517d8071..8a6f6db14ee4 100644 --- a/arch/arm/include/asm/kvm_host.h +++ b/arch/arm/include/asm/kvm_host.h @@ -38,11 +38,6 @@ #define KVM_VCPU_MAX_FEATURES 1 -/* We don't currently support large pages. */ -#define KVM_HPAGE_GFN_SHIFT(x) 0 -#define KVM_NR_PAGE_SIZES 1 -#define KVM_PAGES_PER_HPAGE(x) (1UL<<31) - #include <kvm/arm_vgic.h> struct kvm_vcpu; @@ -154,6 +149,7 @@ struct kvm_vcpu_stat { struct kvm_vcpu_init; int kvm_vcpu_set_target(struct kvm_vcpu *vcpu, const struct kvm_vcpu_init *init); +int kvm_vcpu_preferred_target(struct kvm_vcpu_init *init); unsigned long kvm_arm_num_regs(struct kvm_vcpu *vcpu); int kvm_arm_copy_reg_indices(struct kvm_vcpu *vcpu, u64 __user *indices); struct kvm_one_reg; diff --git a/arch/arm/include/asm/kvm_mmu.h b/arch/arm/include/asm/kvm_mmu.h index 9b28c41f4ba9..77de4a41cc50 100644 --- a/arch/arm/include/asm/kvm_mmu.h +++ b/arch/arm/include/asm/kvm_mmu.h @@ -62,6 +62,12 @@ phys_addr_t kvm_get_idmap_vector(void); int kvm_mmu_init(void); void kvm_clear_hyp_idmap(void); +static inline void kvm_set_pmd(pmd_t *pmd, pmd_t new_pmd) +{ + *pmd = new_pmd; + flush_pmd_entry(pmd); +} + static inline void kvm_set_pte(pte_t *pte, pte_t new_pte) { *pte = new_pte; @@ -103,9 +109,15 @@ static inline void kvm_set_s2pte_writable(pte_t *pte) pte_val(*pte) |= L_PTE_S2_RDWR; } +static inline void kvm_set_s2pmd_writable(pmd_t *pmd) +{ + pmd_val(*pmd) |= L_PMD_S2_RDWR; +} + struct kvm; -static inline void coherent_icache_guest_page(struct kvm *kvm, gfn_t gfn) +static inline void coherent_icache_guest_page(struct kvm *kvm, hva_t hva, + unsigned long size) { /* * If we are going to insert an instruction page and the icache is @@ -120,8 +132,7 @@ static inline void coherent_icache_guest_page(struct kvm *kvm, gfn_t gfn) * need any kind of flushing (DDI 0406C.b - Page B3-1392). */ if (icache_is_pipt()) { - unsigned long hva = gfn_to_hva(kvm, gfn); - __cpuc_coherent_user_range(hva, hva + PAGE_SIZE); + __cpuc_coherent_user_range(hva, hva + size); } else if (!icache_is_vivt_asid_tagged()) { /* any kind of VIPT cache */ __flush_icache_all(); diff --git a/arch/arm/include/asm/pgalloc.h b/arch/arm/include/asm/pgalloc.h index 943504f53f57..78a779361682 100644 --- a/arch/arm/include/asm/pgalloc.h +++ b/arch/arm/include/asm/pgalloc.h @@ -102,12 +102,14 @@ pte_alloc_one(struct mm_struct *mm, unsigned long addr) #else pte = alloc_pages(PGALLOC_GFP, 0); #endif - if (pte) { - if (!PageHighMem(pte)) - clean_pte_table(page_address(pte)); - pgtable_page_ctor(pte); + if (!pte) + return NULL; + if (!PageHighMem(pte)) + clean_pte_table(page_address(pte)); + if (!pgtable_page_ctor(pte)) { + __free_page(pte); + return NULL; } - return pte; } diff --git a/arch/arm/include/asm/pgtable-3level.h b/arch/arm/include/asm/pgtable-3level.h index 39c54cfa03e9..4f9503908dca 100644 --- a/arch/arm/include/asm/pgtable-3level.h +++ b/arch/arm/include/asm/pgtable-3level.h @@ -126,6 +126,8 @@ #define L_PTE_S2_RDONLY (_AT(pteval_t, 1) << 6) /* HAP[1] */ #define L_PTE_S2_RDWR (_AT(pteval_t, 3) << 6) /* HAP[2:1] */ +#define L_PMD_S2_RDWR (_AT(pmdval_t, 3) << 6) /* HAP[2:1] */ + /* * Hyp-mode PL2 PTE definitions for LPAE. */ diff --git a/arch/arm/include/asm/thread_info.h b/arch/arm/include/asm/thread_info.h index df5e13d64f2c..71a06b293489 100644 --- a/arch/arm/include/asm/thread_info.h +++ b/arch/arm/include/asm/thread_info.h @@ -141,12 +141,6 @@ extern int vfp_restore_user_hwstate(struct user_vfp __user *, #endif /* - * We use bit 30 of the preempt_count to indicate that kernel - * preemption is occurring. See <asm/hardirq.h>. - */ -#define PREEMPT_ACTIVE 0x40000000 - -/* * thread information flags: * TIF_SYSCALL_TRACE - syscall trace active * TIF_SYSCAL_AUDIT - syscall auditing active diff --git a/arch/arm/include/asm/xen/hypervisor.h b/arch/arm/include/asm/xen/hypervisor.h index d7ab99a0c9eb..1317ee40f4df 100644 --- a/arch/arm/include/asm/xen/hypervisor.h +++ b/arch/arm/include/asm/xen/hypervisor.h @@ -16,4 +16,6 @@ static inline enum paravirt_lazy_mode paravirt_get_lazy_mode(void) return PARAVIRT_LAZY_NONE; } +extern struct dma_map_ops *xen_dma_ops; + #endif /* _ASM_ARM_XEN_HYPERVISOR_H */ diff --git a/arch/arm/include/asm/xen/page-coherent.h b/arch/arm/include/asm/xen/page-coherent.h new file mode 100644 index 000000000000..1109017499e5 --- /dev/null +++ b/arch/arm/include/asm/xen/page-coherent.h @@ -0,0 +1,50 @@ +#ifndef _ASM_ARM_XEN_PAGE_COHERENT_H +#define _ASM_ARM_XEN_PAGE_COHERENT_H + +#include <asm/page.h> +#include <linux/dma-attrs.h> +#include <linux/dma-mapping.h> + +static inline void *xen_alloc_coherent_pages(struct device *hwdev, size_t size, + dma_addr_t *dma_handle, gfp_t flags, + struct dma_attrs *attrs) +{ + return __generic_dma_ops(hwdev)->alloc(hwdev, size, dma_handle, flags, attrs); +} + +static inline void xen_free_coherent_pages(struct device *hwdev, size_t size, + void *cpu_addr, dma_addr_t dma_handle, + struct dma_attrs *attrs) +{ + __generic_dma_ops(hwdev)->free(hwdev, size, cpu_addr, dma_handle, attrs); +} + +static inline void xen_dma_map_page(struct device *hwdev, struct page *page, + unsigned long offset, size_t size, enum dma_data_direction dir, + struct dma_attrs *attrs) +{ + __generic_dma_ops(hwdev)->map_page(hwdev, page, offset, size, dir, attrs); +} + +static inline void xen_dma_unmap_page(struct device *hwdev, dma_addr_t handle, + size_t size, enum dma_data_direction dir, + struct dma_attrs *attrs) +{ + if (__generic_dma_ops(hwdev)->unmap_page) + __generic_dma_ops(hwdev)->unmap_page(hwdev, handle, size, dir, attrs); +} + +static inline void xen_dma_sync_single_for_cpu(struct device *hwdev, + dma_addr_t handle, size_t size, enum dma_data_direction dir) +{ + if (__generic_dma_ops(hwdev)->sync_single_for_cpu) + __generic_dma_ops(hwdev)->sync_single_for_cpu(hwdev, handle, size, dir); +} + +static inline void xen_dma_sync_single_for_device(struct device *hwdev, + dma_addr_t handle, size_t size, enum dma_data_direction dir) +{ + if (__generic_dma_ops(hwdev)->sync_single_for_device) + __generic_dma_ops(hwdev)->sync_single_for_device(hwdev, handle, size, dir); +} +#endif /* _ASM_ARM_XEN_PAGE_COHERENT_H */ diff --git a/arch/arm/include/asm/xen/page.h b/arch/arm/include/asm/xen/page.h index 359a7b50b158..75579a9d6f76 100644 --- a/arch/arm/include/asm/xen/page.h +++ b/arch/arm/include/asm/xen/page.h @@ -6,12 +6,12 @@ #include <linux/pfn.h> #include <linux/types.h> +#include <linux/dma-mapping.h> +#include <xen/xen.h> #include <xen/interface/grant_table.h> -#define pfn_to_mfn(pfn) (pfn) #define phys_to_machine_mapping_valid(pfn) (1) -#define mfn_to_pfn(mfn) (mfn) #define mfn_to_virt(m) (__va(mfn_to_pfn(m) << PAGE_SHIFT)) #define pte_mfn pte_pfn @@ -32,6 +32,38 @@ typedef struct xpaddr { #define INVALID_P2M_ENTRY (~0UL) +unsigned long __pfn_to_mfn(unsigned long pfn); +unsigned long __mfn_to_pfn(unsigned long mfn); +extern struct rb_root phys_to_mach; + +static inline unsigned long pfn_to_mfn(unsigned long pfn) +{ + unsigned long mfn; + + if (phys_to_mach.rb_node != NULL) { + mfn = __pfn_to_mfn(pfn); + if (mfn != INVALID_P2M_ENTRY) + return mfn; + } + + return pfn; +} + +static inline unsigned long mfn_to_pfn(unsigned long mfn) +{ + unsigned long pfn; + + if (phys_to_mach.rb_node != NULL) { + pfn = __mfn_to_pfn(mfn); + if (pfn != INVALID_P2M_ENTRY) + return pfn; + } + + return mfn; +} + +#define mfn_to_local_pfn(mfn) mfn_to_pfn(mfn) + static inline xmaddr_t phys_to_machine(xpaddr_t phys) { unsigned offset = phys.paddr & ~PAGE_MASK; @@ -76,11 +108,9 @@ static inline int m2p_remove_override(struct page *page, bool clear_pte) return 0; } -static inline bool __set_phys_to_machine(unsigned long pfn, unsigned long mfn) -{ - BUG_ON(pfn != mfn && mfn != INVALID_P2M_ENTRY); - return true; -} +bool __set_phys_to_machine(unsigned long pfn, unsigned long mfn); +bool __set_phys_to_machine_multi(unsigned long pfn, unsigned long mfn, + unsigned long nr_pages); static inline bool set_phys_to_machine(unsigned long pfn, unsigned long mfn) { diff --git a/arch/arm/include/uapi/asm/kvm.h b/arch/arm/include/uapi/asm/kvm.h index c1ee007523d7..c498b60c0505 100644 --- a/arch/arm/include/uapi/asm/kvm.h +++ b/arch/arm/include/uapi/asm/kvm.h @@ -63,7 +63,8 @@ struct kvm_regs { /* Supported Processor Types */ #define KVM_ARM_TARGET_CORTEX_A15 0 -#define KVM_ARM_NUM_TARGETS 1 +#define KVM_ARM_TARGET_CORTEX_A7 1 +#define KVM_ARM_NUM_TARGETS 2 /* KVM_ARM_SET_DEVICE_ADDR ioctl id encoding */ #define KVM_ARM_DEVICE_TYPE_SHIFT 0 diff --git a/arch/arm/kvm/Kconfig b/arch/arm/kvm/Kconfig index ebf5015508b5..466bd299b1a8 100644 --- a/arch/arm/kvm/Kconfig +++ b/arch/arm/kvm/Kconfig @@ -20,6 +20,7 @@ config KVM bool "Kernel-based Virtual Machine (KVM) support" select PREEMPT_NOTIFIERS select ANON_INODES + select HAVE_KVM_CPU_RELAX_INTERCEPT select KVM_MMIO select KVM_ARM_HOST depends on ARM_VIRT_EXT && ARM_LPAE diff --git a/arch/arm/kvm/Makefile b/arch/arm/kvm/Makefile index d99bee4950e5..789bca9e64a7 100644 --- a/arch/arm/kvm/Makefile +++ b/arch/arm/kvm/Makefile @@ -19,6 +19,6 @@ kvm-arm-y = $(KVM)/kvm_main.o $(KVM)/coalesced_mmio.o obj-y += kvm-arm.o init.o interrupts.o obj-y += arm.o handle_exit.o guest.o mmu.o emulate.o reset.o -obj-y += coproc.o coproc_a15.o mmio.o psci.o perf.o +obj-y += coproc.o coproc_a15.o coproc_a7.o mmio.o psci.o perf.o obj-$(CONFIG_KVM_ARM_VGIC) += $(KVM)/arm/vgic.o obj-$(CONFIG_KVM_ARM_TIMER) += $(KVM)/arm/arch_timer.o diff --git a/arch/arm/kvm/arm.c b/arch/arm/kvm/arm.c index aea7ccb8d397..2a700e00528d 100644 --- a/arch/arm/kvm/arm.c +++ b/arch/arm/kvm/arm.c @@ -152,12 +152,13 @@ int kvm_arch_vcpu_fault(struct kvm_vcpu *vcpu, struct vm_fault *vmf) return VM_FAULT_SIGBUS; } -void kvm_arch_free_memslot(struct kvm_memory_slot *free, +void kvm_arch_free_memslot(struct kvm *kvm, struct kvm_memory_slot *free, struct kvm_memory_slot *dont) { } -int kvm_arch_create_memslot(struct kvm_memory_slot *slot, unsigned long npages) +int kvm_arch_create_memslot(struct kvm *kvm, struct kvm_memory_slot *slot, + unsigned long npages) { return 0; } @@ -797,6 +798,19 @@ long kvm_arch_vm_ioctl(struct file *filp, return -EFAULT; return kvm_vm_ioctl_set_device_addr(kvm, &dev_addr); } + case KVM_ARM_PREFERRED_TARGET: { + int err; + struct kvm_vcpu_init init; + + err = kvm_vcpu_preferred_target(&init); + if (err) + return err; + + if (copy_to_user(argp, &init, sizeof(init))) + return -EFAULT; + + return 0; + } default: return -EINVAL; } diff --git a/arch/arm/kvm/coproc.c b/arch/arm/kvm/coproc.c index db9cf692d4dd..78c0885d6501 100644 --- a/arch/arm/kvm/coproc.c +++ b/arch/arm/kvm/coproc.c @@ -71,6 +71,98 @@ int kvm_handle_cp14_access(struct kvm_vcpu *vcpu, struct kvm_run *run) return 1; } +static void reset_mpidr(struct kvm_vcpu *vcpu, const struct coproc_reg *r) +{ + /* + * Compute guest MPIDR. We build a virtual cluster out of the + * vcpu_id, but we read the 'U' bit from the underlying + * hardware directly. + */ + vcpu->arch.cp15[c0_MPIDR] = ((read_cpuid_mpidr() & MPIDR_SMP_BITMASK) | + ((vcpu->vcpu_id >> 2) << MPIDR_LEVEL_BITS) | + (vcpu->vcpu_id & 3)); +} + +/* TRM entries A7:4.3.31 A15:4.3.28 - RO WI */ +static bool access_actlr(struct kvm_vcpu *vcpu, + const struct coproc_params *p, + const struct coproc_reg *r) +{ + if (p->is_write) + return ignore_write(vcpu, p); + + *vcpu_reg(vcpu, p->Rt1) = vcpu->arch.cp15[c1_ACTLR]; + return true; +} + +/* TRM entries A7:4.3.56, A15:4.3.60 - R/O. */ +static bool access_cbar(struct kvm_vcpu *vcpu, + const struct coproc_params *p, + const struct coproc_reg *r) +{ + if (p->is_write) + return write_to_read_only(vcpu, p); + return read_zero(vcpu, p); +} + +/* TRM entries A7:4.3.49, A15:4.3.48 - R/O WI */ +static bool access_l2ctlr(struct kvm_vcpu *vcpu, + const struct coproc_params *p, + const struct coproc_reg *r) +{ + if (p->is_write) + return ignore_write(vcpu, p); + + *vcpu_reg(vcpu, p->Rt1) = vcpu->arch.cp15[c9_L2CTLR]; + return true; +} + +static void reset_l2ctlr(struct kvm_vcpu *vcpu, const struct coproc_reg *r) +{ + u32 l2ctlr, ncores; + + asm volatile("mrc p15, 1, %0, c9, c0, 2\n" : "=r" (l2ctlr)); + l2ctlr &= ~(3 << 24); + ncores = atomic_read(&vcpu->kvm->online_vcpus) - 1; + /* How many cores in the current cluster and the next ones */ + ncores -= (vcpu->vcpu_id & ~3); + /* Cap it to the maximum number of cores in a single cluster */ + ncores = min(ncores, 3U); + l2ctlr |= (ncores & 3) << 24; + + vcpu->arch.cp15[c9_L2CTLR] = l2ctlr; +} + +static void reset_actlr(struct kvm_vcpu *vcpu, const struct coproc_reg *r) +{ + u32 actlr; + + /* ACTLR contains SMP bit: make sure you create all cpus first! */ + asm volatile("mrc p15, 0, %0, c1, c0, 1\n" : "=r" (actlr)); + /* Make the SMP bit consistent with the guest configuration */ + if (atomic_read(&vcpu->kvm->online_vcpus) > 1) + actlr |= 1U << 6; + else + actlr &= ~(1U << 6); + + vcpu->arch.cp15[c1_ACTLR] = actlr; +} + +/* + * TRM entries: A7:4.3.50, A15:4.3.49 + * R/O WI (even if NSACR.NS_L2ERR, a write of 1 is ignored). + */ +static bool access_l2ectlr(struct kvm_vcpu *vcpu, + const struct coproc_params *p, + const struct coproc_reg *r) +{ + if (p->is_write) + return ignore_write(vcpu, p); + + *vcpu_reg(vcpu, p->Rt1) = 0; + return true; +} + /* See note at ARM ARM B1.14.4 */ static bool access_dcsw(struct kvm_vcpu *vcpu, const struct coproc_params *p, @@ -153,10 +245,22 @@ static bool pm_fake(struct kvm_vcpu *vcpu, * registers preceding 32-bit ones. */ static const struct coproc_reg cp15_regs[] = { + /* MPIDR: we use VMPIDR for guest access. */ + { CRn( 0), CRm( 0), Op1( 0), Op2( 5), is32, + NULL, reset_mpidr, c0_MPIDR }, + /* CSSELR: swapped by interrupt.S. */ { CRn( 0), CRm( 0), Op1( 2), Op2( 0), is32, NULL, reset_unknown, c0_CSSELR }, + /* ACTLR: trapped by HCR.TAC bit. */ + { CRn( 1), CRm( 0), Op1( 0), Op2( 1), is32, + access_actlr, reset_actlr, c1_ACTLR }, + + /* CPACR: swapped by interrupt.S. */ + { CRn( 1), CRm( 0), Op1( 0), Op2( 2), is32, + NULL, reset_val, c1_CPACR, 0x00000000 }, + /* TTBR0/TTBR1: swapped by interrupt.S. */ { CRm64( 2), Op1( 0), is64, NULL, reset_unknown64, c2_TTBR0 }, { CRm64( 2), Op1( 1), is64, NULL, reset_unknown64, c2_TTBR1 }, @@ -195,6 +299,13 @@ static const struct coproc_reg cp15_regs[] = { { CRn( 7), CRm(10), Op1( 0), Op2( 2), is32, access_dcsw}, { CRn( 7), CRm(14), Op1( 0), Op2( 2), is32, access_dcsw}, /* + * L2CTLR access (guest wants to know #CPUs). + */ + { CRn( 9), CRm( 0), Op1( 1), Op2( 2), is32, + access_l2ctlr, reset_l2ctlr, c9_L2CTLR }, + { CRn( 9), CRm( 0), Op1( 1), Op2( 3), is32, access_l2ectlr}, + + /* * Dummy performance monitor implementation. */ { CRn( 9), CRm(12), Op1( 0), Op2( 0), is32, access_pmcr}, @@ -234,6 +345,9 @@ static const struct coproc_reg cp15_regs[] = { /* CNTKCTL: swapped by interrupt.S. */ { CRn(14), CRm( 1), Op1( 0), Op2( 0), is32, NULL, reset_val, c14_CNTKCTL, 0x00000000 }, + + /* The Configuration Base Address Register. */ + { CRn(15), CRm( 0), Op1( 4), Op2( 0), is32, access_cbar}, }; /* Target specific emulation tables */ @@ -241,6 +355,12 @@ static struct kvm_coproc_target_table *target_tables[KVM_ARM_NUM_TARGETS]; void kvm_register_target_coproc_table(struct kvm_coproc_target_table *table) { + unsigned int i; + + for (i = 1; i < table->num; i++) + BUG_ON(cmp_reg(&table->table[i-1], + &table->table[i]) >= 0); + target_tables[table->target] = table; } diff --git a/arch/arm/kvm/coproc_a15.c b/arch/arm/kvm/coproc_a15.c index cf93472b9dd6..bb0cac1410cc 100644 --- a/arch/arm/kvm/coproc_a15.c +++ b/arch/arm/kvm/coproc_a15.c @@ -17,101 +17,12 @@ * Foundation, 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301, USA. */ #include <linux/kvm_host.h> -#include <asm/cputype.h> -#include <asm/kvm_arm.h> -#include <asm/kvm_host.h> -#include <asm/kvm_emulate.h> #include <asm/kvm_coproc.h> +#include <asm/kvm_emulate.h> #include <linux/init.h> -static void reset_mpidr(struct kvm_vcpu *vcpu, const struct coproc_reg *r) -{ - /* - * Compute guest MPIDR: - * (Even if we present only one VCPU to the guest on an SMP - * host we don't set the U bit in the MPIDR, or vice versa, as - * revealing the underlying hardware properties is likely to - * be the best choice). - */ - vcpu->arch.cp15[c0_MPIDR] = (read_cpuid_mpidr() & ~MPIDR_LEVEL_MASK) - | (vcpu->vcpu_id & MPIDR_LEVEL_MASK); -} - #include "coproc.h" -/* A15 TRM 4.3.28: RO WI */ -static bool access_actlr(struct kvm_vcpu *vcpu, - const struct coproc_params *p, - const struct coproc_reg *r) -{ - if (p->is_write) - return ignore_write(vcpu, p); - - *vcpu_reg(vcpu, p->Rt1) = vcpu->arch.cp15[c1_ACTLR]; - return true; -} - -/* A15 TRM 4.3.60: R/O. */ -static bool access_cbar(struct kvm_vcpu *vcpu, - const struct coproc_params *p, - const struct coproc_reg *r) -{ - if (p->is_write) - return write_to_read_only(vcpu, p); - return read_zero(vcpu, p); -} - -/* A15 TRM 4.3.48: R/O WI. */ -static bool access_l2ctlr(struct kvm_vcpu *vcpu, - const struct coproc_params *p, - const struct coproc_reg *r) -{ - if (p->is_write) - return ignore_write(vcpu, p); - - *vcpu_reg(vcpu, p->Rt1) = vcpu->arch.cp15[c9_L2CTLR]; - return true; -} - -static void reset_l2ctlr(struct kvm_vcpu *vcpu, const struct coproc_reg *r) -{ - u32 l2ctlr, ncores; - - asm volatile("mrc p15, 1, %0, c9, c0, 2\n" : "=r" (l2ctlr)); - l2ctlr &= ~(3 << 24); - ncores = atomic_read(&vcpu->kvm->online_vcpus) - 1; - l2ctlr |= (ncores & 3) << 24; - - vcpu->arch.cp15[c9_L2CTLR] = l2ctlr; -} - -static void reset_actlr(struct kvm_vcpu *vcpu, const struct coproc_reg *r) -{ - u32 actlr; - - /* ACTLR contains SMP bit: make sure you create all cpus first! */ - asm volatile("mrc p15, 0, %0, c1, c0, 1\n" : "=r" (actlr)); - /* Make the SMP bit consistent with the guest configuration */ - if (atomic_read(&vcpu->kvm->online_vcpus) > 1) - actlr |= 1U << 6; - else - actlr &= ~(1U << 6); - - vcpu->arch.cp15[c1_ACTLR] = actlr; -} - -/* A15 TRM 4.3.49: R/O WI (even if NSACR.NS_L2ERR, a write of 1 is ignored). */ -static bool access_l2ectlr(struct kvm_vcpu *vcpu, - const struct coproc_params *p, - const struct coproc_reg *r) -{ - if (p->is_write) - return ignore_write(vcpu, p); - - *vcpu_reg(vcpu, p->Rt1) = 0; - return true; -} - /* * A15-specific CP15 registers. * CRn denotes the primary register number, but is copied to the CRm in the @@ -121,29 +32,9 @@ static bool access_l2ectlr(struct kvm_vcpu *vcpu, * registers preceding 32-bit ones. */ static const struct coproc_reg a15_regs[] = { - /* MPIDR: we use VMPIDR for guest access. */ - { CRn( 0), CRm( 0), Op1( 0), Op2( 5), is32, - NULL, reset_mpidr, c0_MPIDR }, - /* SCTLR: swapped by interrupt.S. */ { CRn( 1), CRm( 0), Op1( 0), Op2( 0), is32, NULL, reset_val, c1_SCTLR, 0x00C50078 }, - /* ACTLR: trapped by HCR.TAC bit. */ - { CRn( 1), CRm( 0), Op1( 0), Op2( 1), is32, - access_actlr, reset_actlr, c1_ACTLR }, - /* CPACR: swapped by interrupt.S. */ - { CRn( 1), CRm( 0), Op1( 0), Op2( 2), is32, - NULL, reset_val, c1_CPACR, 0x00000000 }, - - /* - * L2CTLR access (guest wants to know #CPUs). - */ - { CRn( 9), CRm( 0), Op1( 1), Op2( 2), is32, - access_l2ctlr, reset_l2ctlr, c9_L2CTLR }, - { CRn( 9), CRm( 0), Op1( 1), Op2( 3), is32, access_l2ectlr}, - - /* The Configuration Base Address Register. */ - { CRn(15), CRm( 0), Op1( 4), Op2( 0), is32, access_cbar}, }; static struct kvm_coproc_target_table a15_target_table = { @@ -154,12 +45,6 @@ static struct kvm_coproc_target_table a15_target_table = { static int __init coproc_a15_init(void) { - unsigned int i; - - for (i = 1; i < ARRAY_SIZE(a15_regs); i++) - BUG_ON(cmp_reg(&a15_regs[i-1], - &a15_regs[i]) >= 0); - kvm_register_target_coproc_table(&a15_target_table); return 0; } diff --git a/arch/arm/kvm/coproc_a7.c b/arch/arm/kvm/coproc_a7.c new file mode 100644 index 000000000000..1df767331588 --- /dev/null +++ b/arch/arm/kvm/coproc_a7.c @@ -0,0 +1,54 @@ +/* + * Copyright (C) 2012 - Virtual Open Systems and Columbia University + * Copyright (C) 2013 - ARM Ltd + * + * Authors: Rusty Russell <rusty@rustcorp.au> + * Christoffer Dall <c.dall@virtualopensystems.com> + * Jonathan Austin <jonathan.austin@arm.com> + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License, version 2, as + * published by the Free Software Foundation. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program; if not, write to the Free Software + * Foundation, 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301, USA. + */ +#include <linux/kvm_host.h> +#include <asm/kvm_coproc.h> +#include <asm/kvm_emulate.h> +#include <linux/init.h> + +#include "coproc.h" + +/* + * Cortex-A7 specific CP15 registers. + * CRn denotes the primary register number, but is copied to the CRm in the + * user space API for 64-bit register access in line with the terminology used + * in the ARM ARM. + * Important: Must be sorted ascending by CRn, CRM, Op1, Op2 and with 64-bit + * registers preceding 32-bit ones. + */ +static const struct coproc_reg a7_regs[] = { + /* SCTLR: swapped by interrupt.S. */ + { CRn( 1), CRm( 0), Op1( 0), Op2( 0), is32, + NULL, reset_val, c1_SCTLR, 0x00C50878 }, +}; + +static struct kvm_coproc_target_table a7_target_table = { + .target = KVM_ARM_TARGET_CORTEX_A7, + .table = a7_regs, + .num = ARRAY_SIZE(a7_regs), +}; + +static int __init coproc_a7_init(void) +{ + kvm_register_target_coproc_table(&a7_target_table); + return 0; +} +late_initcall(coproc_a7_init); diff --git a/arch/arm/kvm/emulate.c b/arch/arm/kvm/emulate.c index bdede9e7da51..d6c005283678 100644 --- a/arch/arm/kvm/emulate.c +++ b/arch/arm/kvm/emulate.c @@ -354,7 +354,7 @@ static void inject_abt(struct kvm_vcpu *vcpu, bool is_pabt, unsigned long addr) *vcpu_pc(vcpu) = exc_vector_base(vcpu) + vect_offset; if (is_pabt) { - /* Set DFAR and DFSR */ + /* Set IFAR and IFSR */ vcpu->arch.cp15[c6_IFAR] = addr; is_lpae = (vcpu->arch.cp15[c2_TTBCR] >> 31); /* Always give debug fault for now - should give guest a clue */ diff --git a/arch/arm/kvm/guest.c b/arch/arm/kvm/guest.c index 152d03612181..20f8d97904af 100644 --- a/arch/arm/kvm/guest.c +++ b/arch/arm/kvm/guest.c @@ -190,6 +190,8 @@ int __attribute_const__ kvm_target_cpu(void) return -EINVAL; switch (part_number) { + case ARM_CPU_PART_CORTEX_A7: + return KVM_ARM_TARGET_CORTEX_A7; case ARM_CPU_PART_CORTEX_A15: return KVM_ARM_TARGET_CORTEX_A15; default: @@ -202,7 +204,7 @@ int kvm_vcpu_set_target(struct kvm_vcpu *vcpu, { unsigned int i; - /* We can only do a cortex A15 for now. */ + /* We can only cope with guest==host and only on A15/A7 (for now). */ if (init->target != kvm_target_cpu()) return -EINVAL; @@ -222,6 +224,26 @@ int kvm_vcpu_set_target(struct kvm_vcpu *vcpu, return kvm_reset_vcpu(vcpu); } +int kvm_vcpu_preferred_target(struct kvm_vcpu_init *init) +{ + int target = kvm_target_cpu(); + + if (target < 0) + return -ENODEV; + + memset(init, 0, sizeof(*init)); + + /* + * For now, we don't return any features. + * In future, we might use features to return target + * specific features available for the preferred + * target type. + */ + init->target = (__u32)target; + + return 0; +} + int kvm_arch_vcpu_ioctl_get_fpu(struct kvm_vcpu *vcpu, struct kvm_fpu *fpu) { return -EINVAL; diff --git a/arch/arm/kvm/handle_exit.c b/arch/arm/kvm/handle_exit.c index df4c82d47ad7..a92079011a83 100644 --- a/arch/arm/kvm/handle_exit.c +++ b/arch/arm/kvm/handle_exit.c @@ -73,23 +73,29 @@ static int handle_dabt_hyp(struct kvm_vcpu *vcpu, struct kvm_run *run) } /** - * kvm_handle_wfi - handle a wait-for-interrupts instruction executed by a guest + * kvm_handle_wfx - handle a WFI or WFE instructions trapped in guests * @vcpu: the vcpu pointer * @run: the kvm_run structure pointer * - * Simply sets the wait_for_interrupts flag on the vcpu structure, which will - * halt execution of world-switches and schedule other host processes until - * there is an incoming IRQ or FIQ to the VM. + * WFE: Yield the CPU and come back to this vcpu when the scheduler + * decides to. + * WFI: Simply call kvm_vcpu_block(), which will halt execution of + * world-switches and schedule other host processes until there is an + * incoming IRQ or FIQ to the VM. */ -static int kvm_handle_wfi(struct kvm_vcpu *vcpu, struct kvm_run *run) +static int kvm_handle_wfx(struct kvm_vcpu *vcpu, struct kvm_run *run) { trace_kvm_wfi(*vcpu_pc(vcpu)); - kvm_vcpu_block(vcpu); + if (kvm_vcpu_get_hsr(vcpu) & HSR_WFI_IS_WFE) + kvm_vcpu_on_spin(vcpu); + else + kvm_vcpu_block(vcpu); + return 1; } static exit_handle_fn arm_exit_handlers[] = { - [HSR_EC_WFI] = kvm_handle_wfi, + [HSR_EC_WFI] = kvm_handle_wfx, [HSR_EC_CP15_32] = kvm_handle_cp15_32, [HSR_EC_CP15_64] = kvm_handle_cp15_64, [HSR_EC_CP14_MR] = kvm_handle_cp14_access, diff --git a/arch/arm/kvm/mmio.c b/arch/arm/kvm/mmio.c index 0c25d9487d53..4cb5a93182e9 100644 --- a/arch/arm/kvm/mmio.c +++ b/arch/arm/kvm/mmio.c @@ -23,6 +23,68 @@ #include "trace.h" +static void mmio_write_buf(char *buf, unsigned int len, unsigned long data) +{ + void *datap = NULL; + union { + u8 byte; + u16 hword; + u32 word; + u64 dword; + } tmp; + + switch (len) { + case 1: + tmp.byte = data; + datap = &tmp.byte; + break; + case 2: + tmp.hword = data; + datap = &tmp.hword; + break; + case 4: + tmp.word = data; + datap = &tmp.word; + break; + case 8: + tmp.dword = data; + datap = &tmp.dword; + break; + } + + memcpy(buf, datap, len); +} + +static unsigned long mmio_read_buf(char *buf, unsigned int len) +{ + unsigned long data = 0; + union { + u16 hword; + u32 word; + u64 dword; + } tmp; + + switch (len) { + case 1: + data = buf[0]; + break; + case 2: + memcpy(&tmp.hword, buf, len); + data = tmp.hword; + break; + case 4: + memcpy(&tmp.word, buf, len); + data = tmp.word; + break; + case 8: + memcpy(&tmp.dword, buf, len); + data = tmp.dword; + break; + } + + return data; +} + /** * kvm_handle_mmio_return -- Handle MMIO loads after user space emulation * @vcpu: The VCPU pointer @@ -33,28 +95,27 @@ */ int kvm_handle_mmio_return(struct kvm_vcpu *vcpu, struct kvm_run *run) { - unsigned long *dest; + unsigned long data; unsigned int len; int mask; if (!run->mmio.is_write) { - dest = vcpu_reg(vcpu, vcpu->arch.mmio_decode.rt); - *dest = 0; - len = run->mmio.len; if (len > sizeof(unsigned long)) return -EINVAL; - memcpy(dest, run->mmio.data, len); - - trace_kvm_mmio(KVM_TRACE_MMIO_READ, len, run->mmio.phys_addr, - *((u64 *)run->mmio.data)); + data = mmio_read_buf(run->mmio.data, len); if (vcpu->arch.mmio_decode.sign_extend && len < sizeof(unsigned long)) { mask = 1U << ((len * 8) - 1); - *dest = (*dest ^ mask) - mask; + data = (data ^ mask) - mask; } + + 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; } return 0; @@ -105,6 +166,7 @@ int io_mem_abort(struct kvm_vcpu *vcpu, struct kvm_run *run, phys_addr_t fault_ipa) { struct kvm_exit_mmio mmio; + unsigned long data; unsigned long rt; int ret; @@ -125,13 +187,15 @@ int io_mem_abort(struct kvm_vcpu *vcpu, struct kvm_run *run, } rt = vcpu->arch.mmio_decode.rt; + data = vcpu_data_guest_to_host(vcpu, *vcpu_reg(vcpu, rt), mmio.len); + trace_kvm_mmio((mmio.is_write) ? KVM_TRACE_MMIO_WRITE : KVM_TRACE_MMIO_READ_UNSATISFIED, mmio.len, fault_ipa, - (mmio.is_write) ? *vcpu_reg(vcpu, rt) : 0); + (mmio.is_write) ? data : 0); if (mmio.is_write) - memcpy(mmio.data, vcpu_reg(vcpu, rt), mmio.len); + mmio_write_buf(mmio.data, mmio.len, data); if (vgic_handle_mmio(vcpu, run, &mmio)) return 1; diff --git a/arch/arm/kvm/mmu.c b/arch/arm/kvm/mmu.c index b0de86b56c13..580906989db1 100644 --- a/arch/arm/kvm/mmu.c +++ b/arch/arm/kvm/mmu.c @@ -19,6 +19,7 @@ #include <linux/mman.h> #include <linux/kvm_host.h> #include <linux/io.h> +#include <linux/hugetlb.h> #include <trace/events/kvm.h> #include <asm/pgalloc.h> #include <asm/cacheflush.h> @@ -41,6 +42,8 @@ static unsigned long hyp_idmap_start; static unsigned long hyp_idmap_end; static phys_addr_t hyp_idmap_vector; +#define kvm_pmd_huge(_x) (pmd_huge(_x) || pmd_trans_huge(_x)) + static void kvm_tlb_flush_vmid_ipa(struct kvm *kvm, phys_addr_t ipa) { /* @@ -93,19 +96,29 @@ static bool page_empty(void *ptr) static void clear_pud_entry(struct kvm *kvm, pud_t *pud, phys_addr_t addr) { - pmd_t *pmd_table = pmd_offset(pud, 0); - pud_clear(pud); - kvm_tlb_flush_vmid_ipa(kvm, addr); - pmd_free(NULL, pmd_table); + if (pud_huge(*pud)) { + pud_clear(pud); + kvm_tlb_flush_vmid_ipa(kvm, addr); + } else { + pmd_t *pmd_table = pmd_offset(pud, 0); + pud_clear(pud); + kvm_tlb_flush_vmid_ipa(kvm, addr); + pmd_free(NULL, pmd_table); + } put_page(virt_to_page(pud)); } static void clear_pmd_entry(struct kvm *kvm, pmd_t *pmd, phys_addr_t addr) { - pte_t *pte_table = pte_offset_kernel(pmd, 0); - pmd_clear(pmd); - kvm_tlb_flush_vmid_ipa(kvm, addr); - pte_free_kernel(NULL, pte_table); + if (kvm_pmd_huge(*pmd)) { + pmd_clear(pmd); + kvm_tlb_flush_vmid_ipa(kvm, addr); + } else { + pte_t *pte_table = pte_offset_kernel(pmd, 0); + pmd_clear(pmd); + kvm_tlb_flush_vmid_ipa(kvm, addr); + pte_free_kernel(NULL, pte_table); + } put_page(virt_to_page(pmd)); } @@ -136,18 +149,32 @@ static void unmap_range(struct kvm *kvm, pgd_t *pgdp, continue; } + if (pud_huge(*pud)) { + /* + * If we are dealing with a huge pud, just clear it and + * move on. + */ + clear_pud_entry(kvm, pud, addr); + addr = pud_addr_end(addr, end); + continue; + } + pmd = pmd_offset(pud, addr); if (pmd_none(*pmd)) { addr = pmd_addr_end(addr, end); continue; } - pte = pte_offset_kernel(pmd, addr); - clear_pte_entry(kvm, pte, addr); - next = addr + PAGE_SIZE; + if (!kvm_pmd_huge(*pmd)) { + pte = pte_offset_kernel(pmd, addr); + clear_pte_entry(kvm, pte, addr); + next = addr + PAGE_SIZE; + } - /* If we emptied the pte, walk back up the ladder */ - if (page_empty(pte)) { + /* + * If the pmd entry is to be cleared, walk back up the ladder + */ + if (kvm_pmd_huge(*pmd) || page_empty(pte)) { clear_pmd_entry(kvm, pmd, addr); next = pmd_addr_end(addr, end); if (page_empty(pmd) && !page_empty(pud)) { @@ -307,6 +334,17 @@ out: return err; } +static phys_addr_t kvm_kaddr_to_phys(void *kaddr) +{ + if (!is_vmalloc_addr(kaddr)) { + BUG_ON(!virt_addr_valid(kaddr)); + return __pa(kaddr); + } else { + return page_to_phys(vmalloc_to_page(kaddr)) + + offset_in_page(kaddr); + } +} + /** * create_hyp_mappings - duplicate a kernel virtual address range in Hyp mode * @from: The virtual kernel start address of the range @@ -318,16 +356,27 @@ out: */ int create_hyp_mappings(void *from, void *to) { - unsigned long phys_addr = virt_to_phys(from); + phys_addr_t phys_addr; + unsigned long virt_addr; unsigned long start = KERN_TO_HYP((unsigned long)from); unsigned long end = KERN_TO_HYP((unsigned long)to); - /* Check for a valid kernel memory mapping */ - if (!virt_addr_valid(from) || !virt_addr_valid(to - 1)) - return -EINVAL; + start = start & PAGE_MASK; + end = PAGE_ALIGN(end); - return __create_hyp_mappings(hyp_pgd, start, end, - __phys_to_pfn(phys_addr), PAGE_HYP); + for (virt_addr = start; virt_addr < end; virt_addr += PAGE_SIZE) { + int err; + + phys_addr = kvm_kaddr_to_phys(from + virt_addr - start); + err = __create_hyp_mappings(hyp_pgd, virt_addr, + virt_addr + PAGE_SIZE, + __phys_to_pfn(phys_addr), + PAGE_HYP); + if (err) + return err; + } + + return 0; } /** @@ -420,29 +469,71 @@ void kvm_free_stage2_pgd(struct kvm *kvm) kvm->arch.pgd = NULL; } - -static int stage2_set_pte(struct kvm *kvm, struct kvm_mmu_memory_cache *cache, - phys_addr_t addr, const pte_t *new_pte, bool iomap) +static pmd_t *stage2_get_pmd(struct kvm *kvm, struct kvm_mmu_memory_cache *cache, + phys_addr_t addr) { pgd_t *pgd; pud_t *pud; pmd_t *pmd; - pte_t *pte, old_pte; - /* Create 2nd stage page table mapping - Level 1 */ pgd = kvm->arch.pgd + pgd_index(addr); pud = pud_offset(pgd, addr); if (pud_none(*pud)) { if (!cache) - return 0; /* ignore calls from kvm_set_spte_hva */ + return NULL; pmd = mmu_memory_cache_alloc(cache); pud_populate(NULL, pud, pmd); get_page(virt_to_page(pud)); } - pmd = pmd_offset(pud, addr); + return pmd_offset(pud, addr); +} + +static int stage2_set_pmd_huge(struct kvm *kvm, struct kvm_mmu_memory_cache + *cache, phys_addr_t addr, const pmd_t *new_pmd) +{ + pmd_t *pmd, old_pmd; + + pmd = stage2_get_pmd(kvm, cache, addr); + VM_BUG_ON(!pmd); + + /* + * Mapping in huge pages should only happen through a fault. If a + * page is merged into a transparent huge page, the individual + * subpages of that huge page should be unmapped through MMU + * notifiers before we get here. + * + * Merging of CompoundPages is not supported; they should become + * splitting first, unmapped, merged, and mapped back in on-demand. + */ + VM_BUG_ON(pmd_present(*pmd) && pmd_pfn(*pmd) != pmd_pfn(*new_pmd)); + + old_pmd = *pmd; + kvm_set_pmd(pmd, *new_pmd); + if (pmd_present(old_pmd)) + kvm_tlb_flush_vmid_ipa(kvm, addr); + else + get_page(virt_to_page(pmd)); + return 0; +} + +static int stage2_set_pte(struct kvm *kvm, struct kvm_mmu_memory_cache *cache, + phys_addr_t addr, const pte_t *new_pte, bool iomap) +{ + pmd_t *pmd; + pte_t *pte, old_pte; + + /* Create stage-2 page table mapping - Level 1 */ + pmd = stage2_get_pmd(kvm, cache, addr); + if (!pmd) { + /* + * Ignore calls from kvm_set_spte_hva for unallocated + * address ranges. + */ + return 0; + } - /* Create 2nd stage page table mapping - Level 2 */ + /* Create stage-2 page mappings - Level 2 */ if (pmd_none(*pmd)) { if (!cache) return 0; /* ignore calls from kvm_set_spte_hva */ @@ -507,16 +598,60 @@ out: return ret; } +static bool transparent_hugepage_adjust(pfn_t *pfnp, phys_addr_t *ipap) +{ + pfn_t pfn = *pfnp; + gfn_t gfn = *ipap >> PAGE_SHIFT; + + if (PageTransCompound(pfn_to_page(pfn))) { + unsigned long mask; + /* + * The address we faulted on is backed by a transparent huge + * page. However, because we map the compound huge page and + * not the individual tail page, we need to transfer the + * refcount to the head page. We have to be careful that the + * THP doesn't start to split while we are adjusting the + * refcounts. + * + * We are sure this doesn't happen, because mmu_notifier_retry + * was successful and we are holding the mmu_lock, so if this + * THP is trying to split, it will be blocked in the mmu + * notifier before touching any of the pages, specifically + * before being able to call __split_huge_page_refcount(). + * + * We can therefore safely transfer the refcount from PG_tail + * to PG_head and switch the pfn from a tail page to the head + * page accordingly. + */ + mask = PTRS_PER_PMD - 1; + VM_BUG_ON((gfn & mask) != (pfn & mask)); + if (pfn & mask) { + *ipap &= PMD_MASK; + kvm_release_pfn_clean(pfn); + pfn &= ~mask; + kvm_get_pfn(pfn); + *pfnp = pfn; + } + + return true; + } + + return false; +} + static int user_mem_abort(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa, - gfn_t gfn, struct kvm_memory_slot *memslot, + struct kvm_memory_slot *memslot, unsigned long fault_status) { - pte_t new_pte; - pfn_t pfn; int ret; - bool write_fault, writable; + bool write_fault, writable, hugetlb = false, force_pte = false; unsigned long mmu_seq; + gfn_t gfn = fault_ipa >> PAGE_SHIFT; + unsigned long hva = gfn_to_hva(vcpu->kvm, gfn); + struct kvm *kvm = vcpu->kvm; struct kvm_mmu_memory_cache *memcache = &vcpu->arch.mmu_page_cache; + struct vm_area_struct *vma; + pfn_t pfn; write_fault = kvm_is_write_fault(kvm_vcpu_get_hsr(vcpu)); if (fault_status == FSC_PERM && !write_fault) { @@ -524,6 +659,26 @@ static int user_mem_abort(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa, return -EFAULT; } + /* Let's check if we will get back a huge page backed by hugetlbfs */ + down_read(¤t->mm->mmap_sem); + vma = find_vma_intersection(current->mm, hva, hva + 1); + if (is_vm_hugetlb_page(vma)) { + hugetlb = true; + gfn = (fault_ipa & PMD_MASK) >> PAGE_SHIFT; + } else { + /* + * Pages belonging to VMAs not aligned to the PMD mapping + * granularity cannot be mapped using block descriptors even + * if the pages belong to a THP for the process, because the + * stage-2 block descriptor will cover more than a single THP + * and we loose atomicity for unmapping, updates, and splits + * of the THP or other pages in the stage-2 block range. + */ + if (vma->vm_start & ~PMD_MASK) + force_pte = true; + } + up_read(¤t->mm->mmap_sem); + /* We need minimum second+third level pages */ ret = mmu_topup_memory_cache(memcache, 2, KVM_NR_MEM_OBJS); if (ret) @@ -541,26 +696,40 @@ static int user_mem_abort(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa, */ smp_rmb(); - pfn = gfn_to_pfn_prot(vcpu->kvm, gfn, write_fault, &writable); + pfn = gfn_to_pfn_prot(kvm, gfn, write_fault, &writable); if (is_error_pfn(pfn)) return -EFAULT; - new_pte = pfn_pte(pfn, PAGE_S2); - coherent_icache_guest_page(vcpu->kvm, gfn); - - spin_lock(&vcpu->kvm->mmu_lock); - if (mmu_notifier_retry(vcpu->kvm, mmu_seq)) + spin_lock(&kvm->mmu_lock); + if (mmu_notifier_retry(kvm, mmu_seq)) goto out_unlock; - if (writable) { - kvm_set_s2pte_writable(&new_pte); - kvm_set_pfn_dirty(pfn); + if (!hugetlb && !force_pte) + hugetlb = transparent_hugepage_adjust(&pfn, &fault_ipa); + + if (hugetlb) { + pmd_t new_pmd = pfn_pmd(pfn, PAGE_S2); + new_pmd = pmd_mkhuge(new_pmd); + if (writable) { + kvm_set_s2pmd_writable(&new_pmd); + kvm_set_pfn_dirty(pfn); + } + coherent_icache_guest_page(kvm, hva & PMD_MASK, PMD_SIZE); + ret = stage2_set_pmd_huge(kvm, memcache, fault_ipa, &new_pmd); + } else { + pte_t new_pte = pfn_pte(pfn, PAGE_S2); + if (writable) { + kvm_set_s2pte_writable(&new_pte); + kvm_set_pfn_dirty(pfn); + } + coherent_icache_guest_page(kvm, hva, PAGE_SIZE); + ret = stage2_set_pte(kvm, memcache, fault_ipa, &new_pte, false); } - stage2_set_pte(vcpu->kvm, memcache, fault_ipa, &new_pte, false); + out_unlock: - spin_unlock(&vcpu->kvm->mmu_lock); + spin_unlock(&kvm->mmu_lock); kvm_release_pfn_clean(pfn); - return 0; + return ret; } /** @@ -629,7 +798,7 @@ int kvm_handle_guest_abort(struct kvm_vcpu *vcpu, struct kvm_run *run) memslot = gfn_to_memslot(vcpu->kvm, gfn); - ret = user_mem_abort(vcpu, fault_ipa, gfn, memslot, fault_status); + ret = user_mem_abort(vcpu, fault_ipa, memslot, fault_status); if (ret == 0) ret = 1; out_unlock: diff --git a/arch/arm/kvm/psci.c b/arch/arm/kvm/psci.c index 86a693a02ba3..0881bf169fbc 100644 --- a/arch/arm/kvm/psci.c +++ b/arch/arm/kvm/psci.c @@ -18,6 +18,7 @@ #include <linux/kvm_host.h> #include <linux/wait.h> +#include <asm/cputype.h> #include <asm/kvm_emulate.h> #include <asm/kvm_psci.h> @@ -34,22 +35,30 @@ static void kvm_psci_vcpu_off(struct kvm_vcpu *vcpu) static unsigned long kvm_psci_vcpu_on(struct kvm_vcpu *source_vcpu) { struct kvm *kvm = source_vcpu->kvm; - struct kvm_vcpu *vcpu; + struct kvm_vcpu *vcpu = NULL, *tmp; wait_queue_head_t *wq; unsigned long cpu_id; + unsigned long mpidr; phys_addr_t target_pc; + int i; cpu_id = *vcpu_reg(source_vcpu, 1); if (vcpu_mode_is_32bit(source_vcpu)) cpu_id &= ~((u32) 0); - if (cpu_id >= atomic_read(&kvm->online_vcpus)) + kvm_for_each_vcpu(i, tmp, kvm) { + mpidr = kvm_vcpu_get_mpidr(tmp); + if ((mpidr & MPIDR_HWID_BITMASK) == (cpu_id & MPIDR_HWID_BITMASK)) { + vcpu = tmp; + break; + } + } + + if (!vcpu) return KVM_PSCI_RET_INVAL; target_pc = *vcpu_reg(source_vcpu, 2); - vcpu = kvm_get_vcpu(kvm, cpu_id); - wq = kvm_arch_vcpu_wq(vcpu); if (!waitqueue_active(wq)) return KVM_PSCI_RET_INVAL; @@ -62,6 +71,10 @@ static unsigned long kvm_psci_vcpu_on(struct kvm_vcpu *source_vcpu) vcpu_set_thumb(vcpu); } + /* Propagate caller endianness */ + if (kvm_vcpu_is_be(source_vcpu)) + kvm_vcpu_set_be(vcpu); + *vcpu_pc(vcpu) = target_pc; vcpu->arch.pause = false; smp_mb(); /* Make sure the above is visible */ diff --git a/arch/arm/kvm/reset.c b/arch/arm/kvm/reset.c index c02ba4af599f..f558c073c023 100644 --- a/arch/arm/kvm/reset.c +++ b/arch/arm/kvm/reset.c @@ -30,16 +30,14 @@ #include <kvm/arm_arch_timer.h> /****************************************************************************** - * Cortex-A15 Reset Values + * Cortex-A15 and Cortex-A7 Reset Values */ -static const int a15_max_cpu_idx = 3; - -static struct kvm_regs a15_regs_reset = { +static struct kvm_regs cortexa_regs_reset = { .usr_regs.ARM_cpsr = SVC_MODE | PSR_A_BIT | PSR_I_BIT | PSR_F_BIT, }; -static const struct kvm_irq_level a15_vtimer_irq = { +static const struct kvm_irq_level cortexa_vtimer_irq = { { .irq = 27 }, .level = 1, }; @@ -62,12 +60,11 @@ int kvm_reset_vcpu(struct kvm_vcpu *vcpu) const struct kvm_irq_level *cpu_vtimer_irq; switch (vcpu->arch.target) { + case KVM_ARM_TARGET_CORTEX_A7: case KVM_ARM_TARGET_CORTEX_A15: - if (vcpu->vcpu_id > a15_max_cpu_idx) - return -EINVAL; - reset_regs = &a15_regs_reset; + reset_regs = &cortexa_regs_reset; vcpu->arch.midr = read_cpuid_id(); - cpu_vtimer_irq = &a15_vtimer_irq; + cpu_vtimer_irq = &cortexa_vtimer_irq; break; default: return -ENODEV; diff --git a/arch/arm/mach-at91/Makefile b/arch/arm/mach-at91/Makefile index 3b0a9538093c..90aab2d5a07f 100644 --- a/arch/arm/mach-at91/Makefile +++ b/arch/arm/mach-at91/Makefile @@ -2,7 +2,7 @@ # Makefile for the linux kernel. # -obj-y := irq.o gpio.o setup.o +obj-y := irq.o gpio.o setup.o sysirq_mask.o obj-m := obj-n := obj- := @@ -98,7 +98,6 @@ obj-y += leds.o # Power Management obj-$(CONFIG_PM) += pm.o obj-$(CONFIG_AT91_SLOW_CLOCK) += pm_slowclock.o -obj-$(CONFIG_CPU_IDLE) += cpuidle.o ifeq ($(CONFIG_PM_DEBUG),y) CFLAGS_pm.o += -DDEBUG diff --git a/arch/arm/mach-at91/at91rm9200.c b/arch/arm/mach-at91/at91rm9200.c index 4aad93d54d6f..25805f2f6010 100644 --- a/arch/arm/mach-at91/at91rm9200.c +++ b/arch/arm/mach-at91/at91rm9200.c @@ -27,6 +27,7 @@ #include "generic.h" #include "clock.h" #include "sam9_smc.h" +#include "pm.h" /* -------------------------------------------------------------------- * Clocks @@ -327,6 +328,7 @@ static void __init at91rm9200_ioremap_registers(void) { at91rm9200_ioremap_st(AT91RM9200_BASE_ST); at91_ioremap_ramc(0, AT91RM9200_BASE_MC, 256); + at91_pm_set_standby(at91rm9200_standby); } static void __init at91rm9200_initialize(void) diff --git a/arch/arm/mach-at91/at91sam9260.c b/arch/arm/mach-at91/at91sam9260.c index 5de6074b4f4f..d6a1fa85371d 100644 --- a/arch/arm/mach-at91/at91sam9260.c +++ b/arch/arm/mach-at91/at91sam9260.c @@ -28,6 +28,7 @@ #include "generic.h" #include "clock.h" #include "sam9_smc.h" +#include "pm.h" /* -------------------------------------------------------------------- * Clocks @@ -342,6 +343,7 @@ static void __init at91sam9260_ioremap_registers(void) at91sam926x_ioremap_pit(AT91SAM9260_BASE_PIT); at91sam9_ioremap_smc(0, AT91SAM9260_BASE_SMC); at91_ioremap_matrix(AT91SAM9260_BASE_MATRIX); + at91_pm_set_standby(at91sam9_sdram_standby); } static void __init at91sam9260_initialize(void) @@ -349,6 +351,8 @@ static void __init at91sam9260_initialize(void) arm_pm_idle = at91sam9_idle; arm_pm_restart = at91sam9_alt_restart; + at91_sysirq_mask_rtt(AT91SAM9260_BASE_RTT); + /* Register GPIO subsystem */ at91_gpio_init(at91sam9260_gpio, 3); } diff --git a/arch/arm/mach-at91/at91sam9261.c b/arch/arm/mach-at91/at91sam9261.c index 0e0793241ab7..23ba1d8a1531 100644 --- a/arch/arm/mach-at91/at91sam9261.c +++ b/arch/arm/mach-at91/at91sam9261.c @@ -27,6 +27,7 @@ #include "generic.h" #include "clock.h" #include "sam9_smc.h" +#include "pm.h" /* -------------------------------------------------------------------- * Clocks @@ -284,6 +285,7 @@ static void __init at91sam9261_ioremap_registers(void) at91sam926x_ioremap_pit(AT91SAM9261_BASE_PIT); at91sam9_ioremap_smc(0, AT91SAM9261_BASE_SMC); at91_ioremap_matrix(AT91SAM9261_BASE_MATRIX); + at91_pm_set_standby(at91sam9_sdram_standby); } static void __init at91sam9261_initialize(void) @@ -291,6 +293,8 @@ static void __init at91sam9261_initialize(void) arm_pm_idle = at91sam9_idle; arm_pm_restart = at91sam9_alt_restart; + at91_sysirq_mask_rtt(AT91SAM9261_BASE_RTT); + /* Register GPIO subsystem */ at91_gpio_init(at91sam9261_gpio, 3); } diff --git a/arch/arm/mach-at91/at91sam9261_devices.c b/arch/arm/mach-at91/at91sam9261_devices.c index 629ea5fc95cf..b2a34740146a 100644 --- a/arch/arm/mach-at91/at91sam9261_devices.c +++ b/arch/arm/mach-at91/at91sam9261_devices.c @@ -465,7 +465,7 @@ void __init at91_add_device_spi(struct spi_board_info *devices, int nr_devices) #if defined(CONFIG_FB_ATMEL) || defined(CONFIG_FB_ATMEL_MODULE) static u64 lcdc_dmamask = DMA_BIT_MASK(32); -static struct atmel_lcdfb_info lcdc_data; +static struct atmel_lcdfb_pdata lcdc_data; static struct resource lcdc_resources[] = { [0] = { @@ -498,7 +498,7 @@ static struct platform_device at91_lcdc_device = { .num_resources = ARRAY_SIZE(lcdc_resources), }; -void __init at91_add_device_lcdc(struct atmel_lcdfb_info *data) +void __init at91_add_device_lcdc(struct atmel_lcdfb_pdata *data) { if (!data) { return; @@ -559,7 +559,7 @@ void __init at91_add_device_lcdc(struct atmel_lcdfb_info *data) platform_device_register(&at91_lcdc_device); } #else -void __init at91_add_device_lcdc(struct atmel_lcdfb_info *data) {} +void __init at91_add_device_lcdc(struct atmel_lcdfb_pdata *data) {} #endif diff --git a/arch/arm/mach-at91/at91sam9263.c b/arch/arm/mach-at91/at91sam9263.c index 6ce7d1850893..7eccb0fc57bc 100644 --- a/arch/arm/mach-at91/at91sam9263.c +++ b/arch/arm/mach-at91/at91sam9263.c @@ -26,6 +26,7 @@ #include "generic.h" #include "clock.h" #include "sam9_smc.h" +#include "pm.h" /* -------------------------------------------------------------------- * Clocks @@ -321,6 +322,7 @@ static void __init at91sam9263_ioremap_registers(void) at91sam9_ioremap_smc(0, AT91SAM9263_BASE_SMC0); at91sam9_ioremap_smc(1, AT91SAM9263_BASE_SMC1); at91_ioremap_matrix(AT91SAM9263_BASE_MATRIX); + at91_pm_set_standby(at91sam9_sdram_standby); } static void __init at91sam9263_initialize(void) @@ -328,6 +330,9 @@ static void __init at91sam9263_initialize(void) arm_pm_idle = at91sam9_idle; arm_pm_restart = at91sam9_alt_restart; + at91_sysirq_mask_rtt(AT91SAM9263_BASE_RTT0); + at91_sysirq_mask_rtt(AT91SAM9263_BASE_RTT1); + /* Register GPIO subsystem */ at91_gpio_init(at91sam9263_gpio, 5); } diff --git a/arch/arm/mach-at91/at91sam9263_devices.c b/arch/arm/mach-at91/at91sam9263_devices.c index 858c8aac2daf..4aeadddbc181 100644 --- a/arch/arm/mach-at91/at91sam9263_devices.c +++ b/arch/arm/mach-at91/at91sam9263_devices.c @@ -832,7 +832,7 @@ void __init at91_add_device_can(struct at91_can_data *data) {} #if defined(CONFIG_FB_ATMEL) || defined(CONFIG_FB_ATMEL_MODULE) static u64 lcdc_dmamask = DMA_BIT_MASK(32); -static struct atmel_lcdfb_info lcdc_data; +static struct atmel_lcdfb_pdata lcdc_data; static struct resource lcdc_resources[] = { [0] = { @@ -859,7 +859,7 @@ static struct platform_device at91_lcdc_device = { .num_resources = ARRAY_SIZE(lcdc_resources), }; -void __init at91_add_device_lcdc(struct atmel_lcdfb_info *data) +void __init at91_add_device_lcdc(struct atmel_lcdfb_pdata *data) { if (!data) return; @@ -891,7 +891,7 @@ void __init at91_add_device_lcdc(struct atmel_lcdfb_info *data) platform_device_register(&at91_lcdc_device); } #else -void __init at91_add_device_lcdc(struct atmel_lcdfb_info *data) {} +void __init at91_add_device_lcdc(struct atmel_lcdfb_pdata *data) {} #endif diff --git a/arch/arm/mach-at91/at91sam9g45.c b/arch/arm/mach-at91/at91sam9g45.c index 474ee04d24b9..9405aa08b104 100644 --- a/arch/arm/mach-at91/at91sam9g45.c +++ b/arch/arm/mach-at91/at91sam9g45.c @@ -26,6 +26,7 @@ #include "generic.h" #include "clock.h" #include "sam9_smc.h" +#include "pm.h" /* -------------------------------------------------------------------- * Clocks @@ -370,6 +371,7 @@ static void __init at91sam9g45_ioremap_registers(void) at91sam926x_ioremap_pit(AT91SAM9G45_BASE_PIT); at91sam9_ioremap_smc(0, AT91SAM9G45_BASE_SMC); at91_ioremap_matrix(AT91SAM9G45_BASE_MATRIX); + at91_pm_set_standby(at91_ddr_standby); } static void __init at91sam9g45_initialize(void) @@ -377,6 +379,9 @@ static void __init at91sam9g45_initialize(void) arm_pm_idle = at91sam9_idle; arm_pm_restart = at91sam9g45_restart; + at91_sysirq_mask_rtc(AT91SAM9G45_BASE_RTC); + at91_sysirq_mask_rtt(AT91SAM9G45_BASE_RTT); + /* Register GPIO subsystem */ at91_gpio_init(at91sam9g45_gpio, 5); } diff --git a/arch/arm/mach-at91/at91sam9g45_devices.c b/arch/arm/mach-at91/at91sam9g45_devices.c index acb703e13331..cb36fa872d30 100644 --- a/arch/arm/mach-at91/at91sam9g45_devices.c +++ b/arch/arm/mach-at91/at91sam9g45_devices.c @@ -965,7 +965,7 @@ void __init at91_add_device_isi(struct isi_platform_data *data, #if defined(CONFIG_FB_ATMEL) || defined(CONFIG_FB_ATMEL_MODULE) static u64 lcdc_dmamask = DMA_BIT_MASK(32); -static struct atmel_lcdfb_info lcdc_data; +static struct atmel_lcdfb_pdata lcdc_data; static struct resource lcdc_resources[] = { [0] = { @@ -991,7 +991,7 @@ static struct platform_device at91_lcdc_device = { .num_resources = ARRAY_SIZE(lcdc_resources), }; -void __init at91_add_device_lcdc(struct atmel_lcdfb_info *data) +void __init at91_add_device_lcdc(struct atmel_lcdfb_pdata *data) { if (!data) return; @@ -1037,7 +1037,7 @@ void __init at91_add_device_lcdc(struct atmel_lcdfb_info *data) platform_device_register(&at91_lcdc_device); } #else -void __init at91_add_device_lcdc(struct atmel_lcdfb_info *data) {} +void __init at91_add_device_lcdc(struct atmel_lcdfb_pdata *data) {} #endif diff --git a/arch/arm/mach-at91/at91sam9n12.c b/arch/arm/mach-at91/at91sam9n12.c index 2d895a297739..388ec3aec4b9 100644 --- a/arch/arm/mach-at91/at91sam9n12.c +++ b/arch/arm/mach-at91/at91sam9n12.c @@ -224,7 +224,13 @@ static void __init at91sam9n12_map_io(void) at91_init_sram(0, AT91SAM9N12_SRAM_BASE, AT91SAM9N12_SRAM_SIZE); } +static void __init at91sam9n12_initialize(void) +{ + at91_sysirq_mask_rtc(AT91SAM9N12_BASE_RTC); +} + AT91_SOC_START(at91sam9n12) .map_io = at91sam9n12_map_io, .register_clocks = at91sam9n12_register_clocks, + .init = at91sam9n12_initialize, AT91_SOC_END diff --git a/arch/arm/mach-at91/at91sam9rl.c b/arch/arm/mach-at91/at91sam9rl.c index d4ec0d9a9872..0750ffb7e6b1 100644 --- a/arch/arm/mach-at91/at91sam9rl.c +++ b/arch/arm/mach-at91/at91sam9rl.c @@ -27,6 +27,7 @@ #include "generic.h" #include "clock.h" #include "sam9_smc.h" +#include "pm.h" /* -------------------------------------------------------------------- * Clocks @@ -287,6 +288,7 @@ static void __init at91sam9rl_ioremap_registers(void) at91sam926x_ioremap_pit(AT91SAM9RL_BASE_PIT); at91sam9_ioremap_smc(0, AT91SAM9RL_BASE_SMC); at91_ioremap_matrix(AT91SAM9RL_BASE_MATRIX); + at91_pm_set_standby(at91sam9_sdram_standby); } static void __init at91sam9rl_initialize(void) @@ -294,6 +296,9 @@ static void __init at91sam9rl_initialize(void) arm_pm_idle = at91sam9_idle; arm_pm_restart = at91sam9_alt_restart; + at91_sysirq_mask_rtc(AT91SAM9RL_BASE_RTC); + at91_sysirq_mask_rtt(AT91SAM9RL_BASE_RTT); + /* Register GPIO subsystem */ at91_gpio_init(at91sam9rl_gpio, 4); } diff --git a/arch/arm/mach-at91/at91sam9rl_devices.c b/arch/arm/mach-at91/at91sam9rl_devices.c index 352468f265a9..a698bdab2cce 100644 --- a/arch/arm/mach-at91/at91sam9rl_devices.c +++ b/arch/arm/mach-at91/at91sam9rl_devices.c @@ -498,7 +498,7 @@ void __init at91_add_device_ac97(struct ac97c_platform_data *data) {} #if defined(CONFIG_FB_ATMEL) || defined(CONFIG_FB_ATMEL_MODULE) static u64 lcdc_dmamask = DMA_BIT_MASK(32); -static struct atmel_lcdfb_info lcdc_data; +static struct atmel_lcdfb_pdata lcdc_data; static struct resource lcdc_resources[] = { [0] = { @@ -525,7 +525,7 @@ static struct platform_device at91_lcdc_device = { .num_resources = ARRAY_SIZE(lcdc_resources), }; -void __init at91_add_device_lcdc(struct atmel_lcdfb_info *data) +void __init at91_add_device_lcdc(struct atmel_lcdfb_pdata *data) { if (!data) { return; @@ -557,7 +557,7 @@ void __init at91_add_device_lcdc(struct atmel_lcdfb_info *data) platform_device_register(&at91_lcdc_device); } #else -void __init at91_add_device_lcdc(struct atmel_lcdfb_info *data) {} +void __init at91_add_device_lcdc(struct atmel_lcdfb_pdata *data) {} #endif diff --git a/arch/arm/mach-at91/at91sam9x5.c b/arch/arm/mach-at91/at91sam9x5.c index 916e5a142917..e8a2e075a1b8 100644 --- a/arch/arm/mach-at91/at91sam9x5.c +++ b/arch/arm/mach-at91/at91sam9x5.c @@ -322,6 +322,11 @@ static void __init at91sam9x5_map_io(void) at91_init_sram(0, AT91SAM9X5_SRAM_BASE, AT91SAM9X5_SRAM_SIZE); } +static void __init at91sam9x5_initialize(void) +{ + at91_sysirq_mask_rtc(AT91SAM9X5_BASE_RTC); +} + /* -------------------------------------------------------------------- * Interrupt initialization * -------------------------------------------------------------------- */ @@ -329,4 +334,5 @@ static void __init at91sam9x5_map_io(void) AT91_SOC_START(at91sam9x5) .map_io = at91sam9x5_map_io, .register_clocks = at91sam9x5_register_clocks, + .init = at91sam9x5_initialize, AT91_SOC_END diff --git a/arch/arm/mach-at91/board-sam9260ek.c b/arch/arm/mach-at91/board-sam9260ek.c index 0b153c87521d..f4f8735315da 100644 --- a/arch/arm/mach-at91/board-sam9260ek.c +++ b/arch/arm/mach-at91/board-sam9260ek.c @@ -28,7 +28,7 @@ #include <linux/spi/spi.h> #include <linux/spi/at73c213.h> #include <linux/clk.h> -#include <linux/i2c/at24.h> +#include <linux/platform_data/at24.h> #include <linux/gpio_keys.h> #include <linux/input.h> diff --git a/arch/arm/mach-at91/board-sam9261ek.c b/arch/arm/mach-at91/board-sam9261ek.c index d3437624ca4e..473546b9408b 100644 --- a/arch/arm/mach-at91/board-sam9261ek.c +++ b/arch/arm/mach-at91/board-sam9261ek.c @@ -389,7 +389,7 @@ static struct fb_monspecs at91fb_default_stn_monspecs = { | ATMEL_LCDC_IFWIDTH_4 \ | ATMEL_LCDC_SCANMOD_SINGLE) -static void at91_lcdc_stn_power_control(int on) +static void at91_lcdc_stn_power_control(struct atmel_lcdfb_pdata *pdata, int on) { /* backlight */ if (on) { /* power up */ @@ -401,7 +401,7 @@ static void at91_lcdc_stn_power_control(int on) } } -static struct atmel_lcdfb_info __initdata ek_lcdc_data = { +static struct atmel_lcdfb_pdata __initdata ek_lcdc_data = { .default_bpp = 1, .default_dmacon = ATMEL_LCDC_DMAEN, .default_lcdcon2 = AT91SAM9261_DEFAULT_STN_LCDCON2, @@ -445,7 +445,7 @@ static struct fb_monspecs at91fb_default_tft_monspecs = { | ATMEL_LCDC_DISTYPE_TFT \ | ATMEL_LCDC_CLKMOD_ALWAYSACTIVE) -static void at91_lcdc_tft_power_control(int on) +static void at91_lcdc_tft_power_control(struct atmel_lcdfb_pdata *pdata, int on) { if (on) at91_set_gpio_value(AT91_PIN_PA12, 0); /* power up */ @@ -453,7 +453,7 @@ static void at91_lcdc_tft_power_control(int on) at91_set_gpio_value(AT91_PIN_PA12, 1); /* power down */ } -static struct atmel_lcdfb_info __initdata ek_lcdc_data = { +static struct atmel_lcdfb_pdata __initdata ek_lcdc_data = { .lcdcon_is_backlight = true, .default_bpp = 16, .default_dmacon = ATMEL_LCDC_DMAEN, @@ -465,7 +465,7 @@ static struct atmel_lcdfb_info __initdata ek_lcdc_data = { #endif #else -static struct atmel_lcdfb_info __initdata ek_lcdc_data; +static struct atmel_lcdfb_pdata __initdata ek_lcdc_data; #endif diff --git a/arch/arm/mach-at91/board-sam9263ek.c b/arch/arm/mach-at91/board-sam9263ek.c index 3284df05df14..2f931915c80c 100644 --- a/arch/arm/mach-at91/board-sam9263ek.c +++ b/arch/arm/mach-at91/board-sam9263ek.c @@ -27,7 +27,7 @@ #include <linux/platform_device.h> #include <linux/spi/spi.h> #include <linux/spi/ads7846.h> -#include <linux/i2c/at24.h> +#include <linux/platform_data/at24.h> #include <linux/fb.h> #include <linux/gpio_keys.h> #include <linux/input.h> @@ -275,13 +275,13 @@ static struct fb_monspecs at91fb_default_monspecs = { | ATMEL_LCDC_DISTYPE_TFT \ | ATMEL_LCDC_CLKMOD_ALWAYSACTIVE) -static void at91_lcdc_power_control(int on) +static void at91_lcdc_power_control(struct atmel_lcdfb_pdata *pdata, int on) { at91_set_gpio_value(AT91_PIN_PA30, on); } /* Driver datas */ -static struct atmel_lcdfb_info __initdata ek_lcdc_data = { +static struct atmel_lcdfb_pdata __initdata ek_lcdc_data = { .lcdcon_is_backlight = true, .default_bpp = 16, .default_dmacon = ATMEL_LCDC_DMAEN, @@ -292,7 +292,7 @@ static struct atmel_lcdfb_info __initdata ek_lcdc_data = { }; #else -static struct atmel_lcdfb_info __initdata ek_lcdc_data; +static struct atmel_lcdfb_pdata __initdata ek_lcdc_data; #endif diff --git a/arch/arm/mach-at91/board-sam9m10g45ek.c b/arch/arm/mach-at91/board-sam9m10g45ek.c index 2a94896a1375..ef39078c8ce2 100644 --- a/arch/arm/mach-at91/board-sam9m10g45ek.c +++ b/arch/arm/mach-at91/board-sam9m10g45ek.c @@ -284,7 +284,7 @@ static struct fb_monspecs at91fb_default_monspecs = { | ATMEL_LCDC_CLKMOD_ALWAYSACTIVE) /* Driver datas */ -static struct atmel_lcdfb_info __initdata ek_lcdc_data = { +static struct atmel_lcdfb_pdata __initdata ek_lcdc_data = { .lcdcon_is_backlight = true, .default_bpp = 32, .default_dmacon = ATMEL_LCDC_DMAEN, @@ -295,7 +295,7 @@ static struct atmel_lcdfb_info __initdata ek_lcdc_data = { }; #else -static struct atmel_lcdfb_info __initdata ek_lcdc_data; +static struct atmel_lcdfb_pdata __initdata ek_lcdc_data; #endif diff --git a/arch/arm/mach-at91/board-sam9rlek.c b/arch/arm/mach-at91/board-sam9rlek.c index aa265dcf2128..604eecf6cd70 100644 --- a/arch/arm/mach-at91/board-sam9rlek.c +++ b/arch/arm/mach-at91/board-sam9rlek.c @@ -170,7 +170,7 @@ static struct fb_monspecs at91fb_default_monspecs = { | ATMEL_LCDC_DISTYPE_TFT \ | ATMEL_LCDC_CLKMOD_ALWAYSACTIVE) -static void at91_lcdc_power_control(int on) +static void at91_lcdc_power_control(struct atmel_lcdfb_pdata *pdata, int on) { if (on) at91_set_gpio_value(AT91_PIN_PC1, 0); /* power up */ @@ -179,7 +179,7 @@ static void at91_lcdc_power_control(int on) } /* Driver datas */ -static struct atmel_lcdfb_info __initdata ek_lcdc_data = { +static struct atmel_lcdfb_pdata __initdata ek_lcdc_data = { .lcdcon_is_backlight = true, .default_bpp = 16, .default_dmacon = ATMEL_LCDC_DMAEN, @@ -191,7 +191,7 @@ static struct atmel_lcdfb_info __initdata ek_lcdc_data = { }; #else -static struct atmel_lcdfb_info __initdata ek_lcdc_data; +static struct atmel_lcdfb_pdata __initdata ek_lcdc_data; #endif diff --git a/arch/arm/mach-at91/board.h b/arch/arm/mach-at91/board.h index 4a234fb2ab3b..6c08b341167d 100644 --- a/arch/arm/mach-at91/board.h +++ b/arch/arm/mach-at91/board.h @@ -107,8 +107,8 @@ extern void __init at91_add_device_pwm(u32 mask); extern void __init at91_add_device_ssc(unsigned id, unsigned pins); /* LCD Controller */ -struct atmel_lcdfb_info; -extern void __init at91_add_device_lcdc(struct atmel_lcdfb_info *data); +struct atmel_lcdfb_pdata; +extern void __init at91_add_device_lcdc(struct atmel_lcdfb_pdata *data); /* AC97 */ extern void __init at91_add_device_ac97(struct ac97c_platform_data *data); diff --git a/arch/arm/mach-at91/cpuidle.c b/arch/arm/mach-at91/cpuidle.c deleted file mode 100644 index 4ec6a6d9b9be..000000000000 --- a/arch/arm/mach-at91/cpuidle.c +++ /dev/null @@ -1,68 +0,0 @@ -/* - * based on arch/arm/mach-kirkwood/cpuidle.c - * - * CPU idle support for AT91 SoC - * - * This file is licensed under the terms of the GNU General Public - * License version 2. This program is licensed "as is" without any - * warranty of any kind, whether express or implied. - * - * The cpu idle uses wait-for-interrupt and RAM self refresh in order - * to implement two idle states - - * #1 wait-for-interrupt - * #2 wait-for-interrupt and RAM self refresh - */ - -#include <linux/kernel.h> -#include <linux/init.h> -#include <linux/platform_device.h> -#include <linux/cpuidle.h> -#include <linux/io.h> -#include <linux/export.h> -#include <asm/proc-fns.h> -#include <asm/cpuidle.h> -#include <mach/cpu.h> - -#include "pm.h" - -#define AT91_MAX_STATES 2 - -/* Actual code that puts the SoC in different idle states */ -static int at91_enter_idle(struct cpuidle_device *dev, - struct cpuidle_driver *drv, - int index) -{ - if (cpu_is_at91rm9200()) - at91rm9200_standby(); - else if (cpu_is_at91sam9g45()) - at91sam9g45_standby(); - else if (cpu_is_at91sam9263()) - at91sam9263_standby(); - else - at91sam9_standby(); - - return index; -} - -static struct cpuidle_driver at91_idle_driver = { - .name = "at91_idle", - .owner = THIS_MODULE, - .states[0] = ARM_CPUIDLE_WFI_STATE, - .states[1] = { - .enter = at91_enter_idle, - .exit_latency = 10, - .target_residency = 10000, - .flags = CPUIDLE_FLAG_TIME_VALID, - .name = "RAM_SR", - .desc = "WFI and DDR Self Refresh", - }, - .state_count = AT91_MAX_STATES, -}; - -/* Initialize CPU idle by registering the idle states */ -static int __init at91_init_cpuidle(void) -{ - return cpuidle_register(&at91_idle_driver, NULL); -} - -device_initcall(at91_init_cpuidle); diff --git a/arch/arm/mach-at91/generic.h b/arch/arm/mach-at91/generic.h index dc6e2f5f804d..26dee3ce9397 100644 --- a/arch/arm/mach-at91/generic.h +++ b/arch/arm/mach-at91/generic.h @@ -34,6 +34,8 @@ extern int __init at91_aic_of_init(struct device_node *node, struct device_node *parent); extern int __init at91_aic5_of_init(struct device_node *node, struct device_node *parent); +extern void __init at91_sysirq_mask_rtc(u32 rtc_base); +extern void __init at91_sysirq_mask_rtt(u32 rtt_base); /* Timer */ diff --git a/arch/arm/mach-at91/include/mach/at91sam9n12.h b/arch/arm/mach-at91/include/mach/at91sam9n12.h index d374b87c0459..0151bcf6163c 100644 --- a/arch/arm/mach-at91/include/mach/at91sam9n12.h +++ b/arch/arm/mach-at91/include/mach/at91sam9n12.h @@ -49,6 +49,11 @@ #define AT91SAM9N12_BASE_USART3 0xf8028000 /* + * System Peripherals + */ +#define AT91SAM9N12_BASE_RTC 0xfffffeb0 + +/* * Internal Memory. */ #define AT91SAM9N12_SRAM_BASE 0x00300000 /* Internal SRAM base address */ diff --git a/arch/arm/mach-at91/include/mach/at91sam9x5.h b/arch/arm/mach-at91/include/mach/at91sam9x5.h index c75ee19b58d3..2fc76c49e97c 100644 --- a/arch/arm/mach-at91/include/mach/at91sam9x5.h +++ b/arch/arm/mach-at91/include/mach/at91sam9x5.h @@ -55,6 +55,11 @@ #define AT91SAM9X5_BASE_USART2 0xf8024000 /* + * System Peripherals + */ +#define AT91SAM9X5_BASE_RTC 0xfffffeb0 + +/* * Internal Memory. */ #define AT91SAM9X5_SRAM_BASE 0x00300000 /* Internal SRAM base address */ diff --git a/arch/arm/mach-at91/include/mach/sama5d3.h b/arch/arm/mach-at91/include/mach/sama5d3.h index 31096a8aaf1d..25613d8c6dcd 100644 --- a/arch/arm/mach-at91/include/mach/sama5d3.h +++ b/arch/arm/mach-at91/include/mach/sama5d3.h @@ -73,6 +73,11 @@ #define SAMA5D3_BASE_USART3 0xf8024000 /* + * System Peripherals + */ +#define SAMA5D3_BASE_RTC 0xfffffeb0 + +/* * Internal Memory */ #define SAMA5D3_SRAM_BASE 0x00300000 /* Internal SRAM base address */ diff --git a/arch/arm/mach-at91/pm.c b/arch/arm/mach-at91/pm.c index 15afb5d9271f..9986542e8060 100644 --- a/arch/arm/mach-at91/pm.c +++ b/arch/arm/mach-at91/pm.c @@ -39,6 +39,8 @@ #include "at91_rstc.h" #include "at91_shdwc.h" +static void (*at91_pm_standby)(void); + static void __init show_reset_status(void) { static char reset[] __initdata = "reset"; @@ -266,14 +268,8 @@ static int at91_pm_enter(suspend_state_t state) * For ARM 926 based chips, this requirement is weaker * as at91sam9 can access a RAM in self-refresh mode. */ - if (cpu_is_at91rm9200()) - at91rm9200_standby(); - else if (cpu_is_at91sam9g45()) - at91sam9g45_standby(); - else if (cpu_is_at91sam9263()) - at91sam9263_standby(); - else - at91sam9_standby(); + if (at91_pm_standby) + at91_pm_standby(); break; case PM_SUSPEND_ON: @@ -314,6 +310,18 @@ static const struct platform_suspend_ops at91_pm_ops = { .end = at91_pm_end, }; +static struct platform_device at91_cpuidle_device = { + .name = "cpuidle-at91", +}; + +void at91_pm_set_standby(void (*at91_standby)(void)) +{ + if (at91_standby) { + at91_cpuidle_device.dev.platform_data = at91_standby; + at91_pm_standby = at91_standby; + } +} + static int __init at91_pm_init(void) { #ifdef CONFIG_AT91_SLOW_CLOCK @@ -325,6 +333,9 @@ static int __init at91_pm_init(void) /* AT91RM9200 SDRAM low-power mode cannot be used with self-refresh. */ if (cpu_is_at91rm9200()) at91_ramc_write(0, AT91RM9200_SDRAMC_LPR, 0); + + if (at91_cpuidle_device.dev.platform_data) + platform_device_register(&at91_cpuidle_device); suspend_set_ops(&at91_pm_ops); diff --git a/arch/arm/mach-at91/pm.h b/arch/arm/mach-at91/pm.h index 2f5908f0b8c5..3ed190ce062b 100644 --- a/arch/arm/mach-at91/pm.h +++ b/arch/arm/mach-at91/pm.h @@ -11,9 +11,13 @@ #ifndef __ARCH_ARM_MACH_AT91_PM #define __ARCH_ARM_MACH_AT91_PM +#include <asm/proc-fns.h> + #include <mach/at91_ramc.h> #include <mach/at91rm9200_sdramc.h> +extern void at91_pm_set_standby(void (*at91_standby)(void)); + /* * The AT91RM9200 goes into self-refresh mode with this command, and will * terminate self-refresh automatically on the next SDRAM access. @@ -45,16 +49,18 @@ static inline void at91rm9200_standby(void) /* We manage both DDRAM/SDRAM controllers, we need more than one value to * remember. */ -static inline void at91sam9g45_standby(void) +static inline void at91_ddr_standby(void) { /* Those two values allow us to delay self-refresh activation * to the maximum. */ - u32 lpr0, lpr1; - u32 saved_lpr0, saved_lpr1; + u32 lpr0, lpr1 = 0; + u32 saved_lpr0, saved_lpr1 = 0; - saved_lpr1 = at91_ramc_read(1, AT91_DDRSDRC_LPR); - lpr1 = saved_lpr1 & ~AT91_DDRSDRC_LPCB; - lpr1 |= AT91_DDRSDRC_LPCB_SELF_REFRESH; + if (at91_ramc_base[1]) { + saved_lpr1 = at91_ramc_read(1, AT91_DDRSDRC_LPR); + lpr1 = saved_lpr1 & ~AT91_DDRSDRC_LPCB; + lpr1 |= AT91_DDRSDRC_LPCB_SELF_REFRESH; + } saved_lpr0 = at91_ramc_read(0, AT91_DDRSDRC_LPR); lpr0 = saved_lpr0 & ~AT91_DDRSDRC_LPCB; @@ -62,25 +68,29 @@ static inline void at91sam9g45_standby(void) /* self-refresh mode now */ at91_ramc_write(0, AT91_DDRSDRC_LPR, lpr0); - at91_ramc_write(1, AT91_DDRSDRC_LPR, lpr1); + if (at91_ramc_base[1]) + at91_ramc_write(1, AT91_DDRSDRC_LPR, lpr1); cpu_do_idle(); at91_ramc_write(0, AT91_DDRSDRC_LPR, saved_lpr0); - at91_ramc_write(1, AT91_DDRSDRC_LPR, saved_lpr1); + if (at91_ramc_base[1]) + at91_ramc_write(1, AT91_DDRSDRC_LPR, saved_lpr1); } /* We manage both DDRAM/SDRAM controllers, we need more than one value to * remember. */ -static inline void at91sam9263_standby(void) +static inline void at91sam9_sdram_standby(void) { - u32 lpr0, lpr1; - u32 saved_lpr0, saved_lpr1; + u32 lpr0, lpr1 = 0; + u32 saved_lpr0, saved_lpr1 = 0; - saved_lpr1 = at91_ramc_read(1, AT91_SDRAMC_LPR); - lpr1 = saved_lpr1 & ~AT91_SDRAMC_LPCB; - lpr1 |= AT91_SDRAMC_LPCB_SELF_REFRESH; + if (at91_ramc_base[1]) { + saved_lpr1 = at91_ramc_read(1, AT91_SDRAMC_LPR); + lpr1 = saved_lpr1 & ~AT91_SDRAMC_LPCB; + lpr1 |= AT91_SDRAMC_LPCB_SELF_REFRESH; + } saved_lpr0 = at91_ramc_read(0, AT91_SDRAMC_LPR); lpr0 = saved_lpr0 & ~AT91_SDRAMC_LPCB; @@ -88,27 +98,14 @@ static inline void at91sam9263_standby(void) /* self-refresh mode now */ at91_ramc_write(0, AT91_SDRAMC_LPR, lpr0); - at91_ramc_write(1, AT91_SDRAMC_LPR, lpr1); + if (at91_ramc_base[1]) + at91_ramc_write(1, AT91_SDRAMC_LPR, lpr1); cpu_do_idle(); at91_ramc_write(0, AT91_SDRAMC_LPR, saved_lpr0); - at91_ramc_write(1, AT91_SDRAMC_LPR, saved_lpr1); -} - -static inline void at91sam9_standby(void) -{ - u32 saved_lpr, lpr; - - saved_lpr = at91_ramc_read(0, AT91_SDRAMC_LPR); - - lpr = saved_lpr & ~AT91_SDRAMC_LPCB; - at91_ramc_write(0, AT91_SDRAMC_LPR, lpr | - AT91_SDRAMC_LPCB_SELF_REFRESH); - - cpu_do_idle(); - - at91_ramc_write(0, AT91_SDRAMC_LPR, saved_lpr); + if (at91_ramc_base[1]) + at91_ramc_write(1, AT91_SDRAMC_LPR, saved_lpr1); } #endif diff --git a/arch/arm/mach-at91/sama5d3.c b/arch/arm/mach-at91/sama5d3.c index 401279715ab1..3ea86428ee09 100644 --- a/arch/arm/mach-at91/sama5d3.c +++ b/arch/arm/mach-at91/sama5d3.c @@ -371,7 +371,13 @@ static void __init sama5d3_map_io(void) at91_init_sram(0, SAMA5D3_SRAM_BASE, SAMA5D3_SRAM_SIZE); } +static void __init sama5d3_initialize(void) +{ + at91_sysirq_mask_rtc(SAMA5D3_BASE_RTC); +} + AT91_SOC_START(sama5d3) .map_io = sama5d3_map_io, .register_clocks = sama5d3_register_clocks, + .init = sama5d3_initialize, AT91_SOC_END diff --git a/arch/arm/mach-at91/setup.c b/arch/arm/mach-at91/setup.c index b17fbcf4d9e8..094b3459c288 100644 --- a/arch/arm/mach-at91/setup.c +++ b/arch/arm/mach-at91/setup.c @@ -23,6 +23,7 @@ #include "at91_shdwc.h" #include "soc.h" #include "generic.h" +#include "pm.h" struct at91_init_soc __initdata at91_boot_soc; @@ -376,15 +377,16 @@ static void at91_dt_rstc(void) } static struct of_device_id ramc_ids[] = { - { .compatible = "atmel,at91rm9200-sdramc" }, - { .compatible = "atmel,at91sam9260-sdramc" }, - { .compatible = "atmel,at91sam9g45-ddramc" }, + { .compatible = "atmel,at91rm9200-sdramc", .data = at91rm9200_standby }, + { .compatible = "atmel,at91sam9260-sdramc", .data = at91sam9_sdram_standby }, + { .compatible = "atmel,at91sam9g45-ddramc", .data = at91_ddr_standby }, { /*sentinel*/ } }; static void at91_dt_ramc(void) { struct device_node *np; + const struct of_device_id *of_id; np = of_find_matching_node(NULL, ramc_ids); if (!np) @@ -396,6 +398,12 @@ static void at91_dt_ramc(void) /* the controller may have 2 banks */ at91_ramc_base[1] = of_iomap(np, 1); + of_id = of_match_node(ramc_ids, np); + if (!of_id) + pr_warn("AT91: ramc no standby function available\n"); + else + at91_pm_set_standby(of_id->data); + of_node_put(np); } diff --git a/arch/arm/mach-at91/sysirq_mask.c b/arch/arm/mach-at91/sysirq_mask.c new file mode 100644 index 000000000000..2ba694f9626b --- /dev/null +++ b/arch/arm/mach-at91/sysirq_mask.c @@ -0,0 +1,71 @@ +/* + * sysirq_mask.c - System-interrupt masking + * + * Copyright (C) 2013 Johan Hovold <jhovold@gmail.com> + * + * Functions to disable system interrupts from backup-powered peripherals. + * + * The RTC and RTT-peripherals are generally powered by backup power (VDDBU) + * and are not reset on wake-up, user, watchdog or software reset. This means + * that their interrupts may be enabled during early boot (e.g. after a user + * reset). + * + * As the RTC and RTT share the system-interrupt line with the PIT, an + * interrupt occurring before a handler has been installed would lead to the + * system interrupt being disabled and prevent the system from booting. + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + */ + +#include <linux/io.h> +#include <mach/at91_rtt.h> + +#include "generic.h" + +#define AT91_RTC_IDR 0x24 /* Interrupt Disable Register */ +#define AT91_RTC_IMR 0x28 /* Interrupt Mask Register */ + +void __init at91_sysirq_mask_rtc(u32 rtc_base) +{ + void __iomem *base; + u32 mask; + + base = ioremap(rtc_base, 64); + if (!base) + return; + + mask = readl_relaxed(base + AT91_RTC_IMR); + if (mask) { + pr_info("AT91: Disabling rtc irq\n"); + writel_relaxed(mask, base + AT91_RTC_IDR); + (void)readl_relaxed(base + AT91_RTC_IMR); /* flush */ + } + + iounmap(base); +} + +void __init at91_sysirq_mask_rtt(u32 rtt_base) +{ + void __iomem *base; + void __iomem *reg; + u32 mode; + + base = ioremap(rtt_base, 16); + if (!base) + return; + + reg = base + AT91_RTT_MR; + + mode = readl_relaxed(reg); + if (mode & (AT91_RTT_ALMIEN | AT91_RTT_RTTINCIEN)) { + pr_info("AT91: Disabling rtt irq\n"); + mode &= ~(AT91_RTT_ALMIEN | AT91_RTT_RTTINCIEN); + writel_relaxed(mode, reg); + (void)readl_relaxed(reg); /* flush */ + } + + iounmap(base); +} diff --git a/arch/arm/mach-davinci/Kconfig b/arch/arm/mach-davinci/Kconfig index e026b19b23ea..a075b3e0c5c7 100644 --- a/arch/arm/mach-davinci/Kconfig +++ b/arch/arm/mach-davinci/Kconfig @@ -40,7 +40,6 @@ config ARCH_DAVINCI_DA850 bool "DA850/OMAP-L138/AM18x based system" select ARCH_DAVINCI_DA8XX select ARCH_HAS_CPUFREQ - select CPU_FREQ_TABLE select CP_INTC config ARCH_DAVINCI_DA8XX diff --git a/arch/arm/mach-davinci/board-da830-evm.c b/arch/arm/mach-davinci/board-da830-evm.c index 40f15f133c55..d1f45af7a530 100644 --- a/arch/arm/mach-davinci/board-da830-evm.c +++ b/arch/arm/mach-davinci/board-da830-evm.c @@ -17,7 +17,7 @@ #include <linux/platform_device.h> #include <linux/i2c.h> #include <linux/i2c/pcf857x.h> -#include <linux/i2c/at24.h> +#include <linux/platform_data/at24.h> #include <linux/mtd/mtd.h> #include <linux/mtd/partitions.h> #include <linux/spi/spi.h> diff --git a/arch/arm/mach-davinci/board-da850-evm.c b/arch/arm/mach-davinci/board-da850-evm.c index df16cb88a26b..e0af0eccde8f 100644 --- a/arch/arm/mach-davinci/board-da850-evm.c +++ b/arch/arm/mach-davinci/board-da850-evm.c @@ -18,7 +18,7 @@ #include <linux/init.h> #include <linux/kernel.h> #include <linux/i2c.h> -#include <linux/i2c/at24.h> +#include <linux/platform_data/at24.h> #include <linux/platform_data/pca953x.h> #include <linux/input.h> #include <linux/input/tps6507x-ts.h> diff --git a/arch/arm/mach-davinci/board-dm365-evm.c b/arch/arm/mach-davinci/board-dm365-evm.c index f4a6c18912ea..e08a8684ead2 100644 --- a/arch/arm/mach-davinci/board-dm365-evm.c +++ b/arch/arm/mach-davinci/board-dm365-evm.c @@ -18,7 +18,7 @@ #include <linux/i2c.h> #include <linux/io.h> #include <linux/clk.h> -#include <linux/i2c/at24.h> +#include <linux/platform_data/at24.h> #include <linux/leds.h> #include <linux/mtd/mtd.h> #include <linux/mtd/partitions.h> diff --git a/arch/arm/mach-davinci/board-dm644x-evm.c b/arch/arm/mach-davinci/board-dm644x-evm.c index 9cc32c283b8b..987605b78556 100644 --- a/arch/arm/mach-davinci/board-dm644x-evm.c +++ b/arch/arm/mach-davinci/board-dm644x-evm.c @@ -15,7 +15,7 @@ #include <linux/gpio.h> #include <linux/i2c.h> #include <linux/i2c/pcf857x.h> -#include <linux/i2c/at24.h> +#include <linux/platform_data/at24.h> #include <linux/mtd/mtd.h> #include <linux/mtd/nand.h> #include <linux/mtd/partitions.h> diff --git a/arch/arm/mach-davinci/board-dm646x-evm.c b/arch/arm/mach-davinci/board-dm646x-evm.c index 44b20191a9fe..13d0801fd6b1 100644 --- a/arch/arm/mach-davinci/board-dm646x-evm.c +++ b/arch/arm/mach-davinci/board-dm646x-evm.c @@ -22,7 +22,7 @@ #include <linux/gpio.h> #include <linux/platform_device.h> #include <linux/i2c.h> -#include <linux/i2c/at24.h> +#include <linux/platform_data/at24.h> #include <linux/i2c/pcf857x.h> #include <media/tvp514x.h> diff --git a/arch/arm/mach-davinci/board-mityomapl138.c b/arch/arm/mach-davinci/board-mityomapl138.c index cd0f58730c2b..7aa105b1fd0f 100644 --- a/arch/arm/mach-davinci/board-mityomapl138.c +++ b/arch/arm/mach-davinci/board-mityomapl138.c @@ -15,7 +15,7 @@ #include <linux/mtd/partitions.h> #include <linux/regulator/machine.h> #include <linux/i2c.h> -#include <linux/i2c/at24.h> +#include <linux/platform_data/at24.h> #include <linux/etherdevice.h> #include <linux/spi/spi.h> #include <linux/spi/flash.h> diff --git a/arch/arm/mach-davinci/board-sffsdr.c b/arch/arm/mach-davinci/board-sffsdr.c index d84360148100..41c7c9615791 100644 --- a/arch/arm/mach-davinci/board-sffsdr.c +++ b/arch/arm/mach-davinci/board-sffsdr.c @@ -26,7 +26,7 @@ #include <linux/init.h> #include <linux/platform_device.h> #include <linux/i2c.h> -#include <linux/i2c/at24.h> +#include <linux/platform_data/at24.h> #include <linux/mtd/mtd.h> #include <linux/mtd/nand.h> #include <linux/mtd/partitions.h> diff --git a/arch/arm/mach-exynos/common.c b/arch/arm/mach-exynos/common.c index a4e7ba828810..61d2906ccefb 100644 --- a/arch/arm/mach-exynos/common.c +++ b/arch/arm/mach-exynos/common.c @@ -28,6 +28,7 @@ #include <linux/of_address.h> #include <linux/irqchip/arm-gic.h> #include <linux/irqchip/chained_irq.h> +#include <linux/platform_device.h> #include <asm/proc-fns.h> #include <asm/exception.h> @@ -292,6 +293,16 @@ void exynos5_restart(enum reboot_mode mode, const char *cmd) __raw_writel(val, addr); } +static struct platform_device exynos_cpuidle = { + .name = "exynos_cpuidle", + .id = -1, +}; + +void __init exynos_cpuidle_init(void) +{ + platform_device_register(&exynos_cpuidle); +} + void __init exynos_init_late(void) { if (of_machine_is_compatible("samsung,exynos5440")) diff --git a/arch/arm/mach-exynos/common.h b/arch/arm/mach-exynos/common.h index f0fa2050d08d..ff9b6a9419b0 100644 --- a/arch/arm/mach-exynos/common.h +++ b/arch/arm/mach-exynos/common.h @@ -21,6 +21,7 @@ struct map_desc; void exynos_init_io(void); void exynos4_restart(enum reboot_mode mode, const char *cmd); void exynos5_restart(enum reboot_mode mode, const char *cmd); +void exynos_cpuidle_init(void); void exynos_init_late(void); void exynos_firmware_init(void); diff --git a/arch/arm/mach-exynos/cpuidle.c b/arch/arm/mach-exynos/cpuidle.c index ac139226d63c..ddbfe8709fe7 100644 --- a/arch/arm/mach-exynos/cpuidle.c +++ b/arch/arm/mach-exynos/cpuidle.c @@ -15,6 +15,7 @@ #include <linux/io.h> #include <linux/export.h> #include <linux/time.h> +#include <linux/platform_device.h> #include <asm/proc-fns.h> #include <asm/smp_scu.h> @@ -192,7 +193,7 @@ static void __init exynos5_core_down_clk(void) __raw_writel(tmp, EXYNOS5_PWR_CTRL2); } -static int __init exynos4_init_cpuidle(void) +static int exynos_cpuidle_probe(struct platform_device *pdev) { int cpu_id, ret; struct cpuidle_device *device; @@ -205,7 +206,7 @@ static int __init exynos4_init_cpuidle(void) ret = cpuidle_register_driver(&exynos4_idle_driver); if (ret) { - printk(KERN_ERR "CPUidle failed to register driver\n"); + dev_err(&pdev->dev, "failed to register cpuidle driver\n"); return ret; } @@ -219,11 +220,20 @@ static int __init exynos4_init_cpuidle(void) ret = cpuidle_register_device(device); if (ret) { - printk(KERN_ERR "CPUidle register device failed\n"); + dev_err(&pdev->dev, "failed to register cpuidle device\n"); return ret; } } return 0; } -device_initcall(exynos4_init_cpuidle); + +static struct platform_driver exynos_cpuidle_driver = { + .probe = exynos_cpuidle_probe, + .driver = { + .name = "exynos_cpuidle", + .owner = THIS_MODULE, + }, +}; + +module_platform_driver(exynos_cpuidle_driver); diff --git a/arch/arm/mach-exynos/mach-exynos4-dt.c b/arch/arm/mach-exynos/mach-exynos4-dt.c index 4b8f6e2ca163..4603e6bd424b 100644 --- a/arch/arm/mach-exynos/mach-exynos4-dt.c +++ b/arch/arm/mach-exynos/mach-exynos4-dt.c @@ -21,6 +21,8 @@ static void __init exynos4_dt_machine_init(void) { + exynos_cpuidle_init(); + of_platform_populate(NULL, of_default_bus_match_table, NULL, NULL); } diff --git a/arch/arm/mach-exynos/mach-exynos5-dt.c b/arch/arm/mach-exynos/mach-exynos5-dt.c index 7976ab333192..1fe075a70c1e 100644 --- a/arch/arm/mach-exynos/mach-exynos5-dt.c +++ b/arch/arm/mach-exynos/mach-exynos5-dt.c @@ -43,6 +43,8 @@ static void __init exynos5_dt_machine_init(void) } } + exynos_cpuidle_init(); + of_platform_populate(NULL, of_default_bus_match_table, NULL, NULL); } diff --git a/arch/arm/mach-highbank/Kconfig b/arch/arm/mach-highbank/Kconfig index 08332d841440..0aded64a9ebc 100644 --- a/arch/arm/mach-highbank/Kconfig +++ b/arch/arm/mach-highbank/Kconfig @@ -7,7 +7,7 @@ config ARCH_HIGHBANK select ARCH_SUPPORTS_BIG_ENDIAN select ARCH_WANT_OPTIONAL_GPIOLIB select ARM_AMBA - select ARM_ERRATA_764369 + select ARM_ERRATA_764369 if SMP select ARM_ERRATA_775420 select ARM_ERRATA_798181 if SMP select ARM_GIC diff --git a/arch/arm/mach-imx/Makefile b/arch/arm/mach-imx/Makefile index bbe1f5bb799c..1789e2b31903 100644 --- a/arch/arm/mach-imx/Makefile +++ b/arch/arm/mach-imx/Makefile @@ -102,8 +102,8 @@ obj-$(CONFIG_SOC_IMX6SL) += clk-imx6sl.o mach-imx6sl.o ifeq ($(CONFIG_PM),y) obj-$(CONFIG_SOC_IMX6Q) += pm-imx6q.o headsmp.o -# i.MX6SL reuses pm-imx6q.c -obj-$(CONFIG_SOC_IMX6SL) += pm-imx6q.o +# i.MX6SL reuses i.MX6Q code +obj-$(CONFIG_SOC_IMX6SL) += pm-imx6q.o headsmp.o endif # i.MX5 based machines diff --git a/arch/arm/mach-imx/clk-imx6q.c b/arch/arm/mach-imx/clk-imx6q.c index d756d91fd741..04cfd0fcb0e5 100644 --- a/arch/arm/mach-imx/clk-imx6q.c +++ b/arch/arm/mach-imx/clk-imx6q.c @@ -122,13 +122,14 @@ static struct clk_div_table clk_enet_ref_table[] = { { .val = 1, .div = 10, }, { .val = 2, .div = 5, }, { .val = 3, .div = 4, }, + { /* sentinel */ } }; static struct clk_div_table post_div_table[] = { { .val = 2, .div = 1, }, { .val = 1, .div = 2, }, { .val = 0, .div = 4, }, - { } + { /* sentinel */ } }; static struct clk_div_table video_div_table[] = { @@ -136,7 +137,7 @@ static struct clk_div_table video_div_table[] = { { .val = 1, .div = 2, }, { .val = 2, .div = 1, }, { .val = 3, .div = 4, }, - { } + { /* sentinel */ } }; static void __init imx6q_clocks_init(struct device_node *ccm_node) @@ -298,7 +299,7 @@ static void __init imx6q_clocks_init(struct device_node *ccm_node) clk[asrc_podf] = imx_clk_divider("asrc_podf", "asrc_pred", base + 0x30, 9, 3); clk[spdif_pred] = imx_clk_divider("spdif_pred", "spdif_sel", base + 0x30, 25, 3); clk[spdif_podf] = imx_clk_divider("spdif_podf", "spdif_pred", base + 0x30, 22, 3); - clk[can_root] = imx_clk_divider("can_root", "pll3_usb_otg", base + 0x20, 2, 6); + clk[can_root] = imx_clk_divider("can_root", "pll3_60m", base + 0x20, 2, 6); clk[ecspi_root] = imx_clk_divider("ecspi_root", "pll3_60m", base + 0x38, 19, 6); clk[gpu2d_core_podf] = imx_clk_divider("gpu2d_core_podf", "gpu2d_core_sel", base + 0x18, 23, 3); clk[gpu3d_core_podf] = imx_clk_divider("gpu3d_core_podf", "gpu3d_core_sel", base + 0x18, 26, 3); diff --git a/arch/arm/mach-imx/clk-pllv3.c b/arch/arm/mach-imx/clk-pllv3.c index f6640b6a7b31..61364050fccd 100644 --- a/arch/arm/mach-imx/clk-pllv3.c +++ b/arch/arm/mach-imx/clk-pllv3.c @@ -12,6 +12,7 @@ #include <linux/clk.h> #include <linux/clk-provider.h> +#include <linux/delay.h> #include <linux/io.h> #include <linux/slab.h> #include <linux/jiffies.h> @@ -45,33 +46,49 @@ struct clk_pllv3 { #define to_clk_pllv3(_hw) container_of(_hw, struct clk_pllv3, hw) +static int clk_pllv3_wait_lock(struct clk_pllv3 *pll) +{ + unsigned long timeout = jiffies + msecs_to_jiffies(10); + u32 val = readl_relaxed(pll->base) & BM_PLL_POWER; + + /* No need to wait for lock when pll is not powered up */ + if ((pll->powerup_set && !val) || (!pll->powerup_set && val)) + return 0; + + /* Wait for PLL to lock */ + do { + if (readl_relaxed(pll->base) & BM_PLL_LOCK) + break; + if (time_after(jiffies, timeout)) + break; + usleep_range(50, 500); + } while (1); + + return readl_relaxed(pll->base) & BM_PLL_LOCK ? 0 : -ETIMEDOUT; +} + static int clk_pllv3_prepare(struct clk_hw *hw) { struct clk_pllv3 *pll = to_clk_pllv3(hw); - unsigned long timeout; u32 val; + int ret; val = readl_relaxed(pll->base); - val &= ~BM_PLL_BYPASS; if (pll->powerup_set) val |= BM_PLL_POWER; else val &= ~BM_PLL_POWER; writel_relaxed(val, pll->base); - timeout = jiffies + msecs_to_jiffies(10); - /* Wait for PLL to lock */ - do { - if (readl_relaxed(pll->base) & BM_PLL_LOCK) - break; - if (time_after(jiffies, timeout)) - break; - } while (1); + ret = clk_pllv3_wait_lock(pll); + if (ret) + return ret; - if (readl_relaxed(pll->base) & BM_PLL_LOCK) - return 0; - else - return -ETIMEDOUT; + val = readl_relaxed(pll->base); + val &= ~BM_PLL_BYPASS; + writel_relaxed(val, pll->base); + + return 0; } static void clk_pllv3_unprepare(struct clk_hw *hw) @@ -146,7 +163,7 @@ static int clk_pllv3_set_rate(struct clk_hw *hw, unsigned long rate, val |= div; writel_relaxed(val, pll->base); - return 0; + return clk_pllv3_wait_lock(pll); } static const struct clk_ops clk_pllv3_ops = { @@ -202,7 +219,7 @@ static int clk_pllv3_sys_set_rate(struct clk_hw *hw, unsigned long rate, val |= div; writel_relaxed(val, pll->base); - return 0; + return clk_pllv3_wait_lock(pll); } static const struct clk_ops clk_pllv3_sys_ops = { @@ -276,7 +293,7 @@ static int clk_pllv3_av_set_rate(struct clk_hw *hw, unsigned long rate, writel_relaxed(mfn, pll->base + PLL_NUM_OFFSET); writel_relaxed(mfd, pll->base + PLL_DENOM_OFFSET); - return 0; + return clk_pllv3_wait_lock(pll); } static const struct clk_ops clk_pllv3_av_ops = { diff --git a/arch/arm/mach-imx/common.h b/arch/arm/mach-imx/common.h index 7cbe22d0c6e9..24a7899e36a8 100644 --- a/arch/arm/mach-imx/common.h +++ b/arch/arm/mach-imx/common.h @@ -127,11 +127,6 @@ static inline void imx_smp_prepare(void) {} static inline void imx_scu_standby_enable(void) {} #endif void imx_src_init(void); -#ifdef CONFIG_HAVE_IMX_SRC -void imx_src_prepare_restart(void); -#else -static inline void imx_src_prepare_restart(void) {} -#endif void imx_gpc_init(void); void imx_gpc_pre_suspend(void); void imx_gpc_post_resume(void); diff --git a/arch/arm/mach-imx/mach-imx6q.c b/arch/arm/mach-imx/mach-imx6q.c index 0f9f24116daa..d0cfb225ec9a 100644 --- a/arch/arm/mach-imx/mach-imx6q.c +++ b/arch/arm/mach-imx/mach-imx6q.c @@ -22,7 +22,7 @@ #include <linux/of_address.h> #include <linux/of_irq.h> #include <linux/of_platform.h> -#include <linux/opp.h> +#include <linux/pm_opp.h> #include <linux/phy.h> #include <linux/reboot.h> #include <linux/regmap.h> @@ -176,7 +176,7 @@ static void __init imx6q_opp_check_1p2ghz(struct device *cpu_dev) val = readl_relaxed(base + OCOTP_CFG3); val >>= OCOTP_CFG3_SPEED_SHIFT; if ((val & 0x3) != OCOTP_CFG3_SPEED_1P2GHZ) - if (opp_disable(cpu_dev, 1200000000)) + if (dev_pm_opp_disable(cpu_dev, 1200000000)) pr_warn("failed to disable 1.2 GHz OPP\n"); put_node: diff --git a/arch/arm/mach-imx/mach-pca100.c b/arch/arm/mach-imx/mach-pca100.c index 19bb6441a7d4..c5f95674e9b7 100644 --- a/arch/arm/mach-imx/mach-pca100.c +++ b/arch/arm/mach-imx/mach-pca100.c @@ -20,7 +20,7 @@ #include <linux/platform_device.h> #include <linux/io.h> #include <linux/i2c.h> -#include <linux/i2c/at24.h> +#include <linux/platform_data/at24.h> #include <linux/dma-mapping.h> #include <linux/spi/spi.h> #include <linux/spi/eeprom.h> diff --git a/arch/arm/mach-imx/mach-pcm037.c b/arch/arm/mach-imx/mach-pcm037.c index 45303bd62902..639a3dfb0092 100644 --- a/arch/arm/mach-imx/mach-pcm037.c +++ b/arch/arm/mach-imx/mach-pcm037.c @@ -23,7 +23,7 @@ #include <linux/smsc911x.h> #include <linux/interrupt.h> #include <linux/i2c.h> -#include <linux/i2c/at24.h> +#include <linux/platform_data/at24.h> #include <linux/delay.h> #include <linux/spi/spi.h> #include <linux/irq.h> diff --git a/arch/arm/mach-imx/mach-pcm038.c b/arch/arm/mach-imx/mach-pcm038.c index e805ac273e9c..592ddbe031ac 100644 --- a/arch/arm/mach-imx/mach-pcm038.c +++ b/arch/arm/mach-imx/mach-pcm038.c @@ -18,7 +18,7 @@ */ #include <linux/i2c.h> -#include <linux/i2c/at24.h> +#include <linux/platform_data/at24.h> #include <linux/io.h> #include <linux/mtd/plat-ram.h> #include <linux/mtd/physmap.h> diff --git a/arch/arm/mach-imx/mach-pcm043.c b/arch/arm/mach-imx/mach-pcm043.c index b726cb1c5fdd..ac504b67326b 100644 --- a/arch/arm/mach-imx/mach-pcm043.c +++ b/arch/arm/mach-imx/mach-pcm043.c @@ -24,7 +24,7 @@ #include <linux/interrupt.h> #include <linux/delay.h> #include <linux/i2c.h> -#include <linux/i2c/at24.h> +#include <linux/platform_data/at24.h> #include <linux/usb/otg.h> #include <linux/usb/ulpi.h> diff --git a/arch/arm/mach-imx/mach-vpr200.c b/arch/arm/mach-imx/mach-vpr200.c index 0910761e8280..8825d1217d18 100644 --- a/arch/arm/mach-imx/mach-vpr200.c +++ b/arch/arm/mach-imx/mach-vpr200.c @@ -29,7 +29,7 @@ #include <asm/mach/time.h> #include <linux/i2c.h> -#include <linux/i2c/at24.h> +#include <linux/platform_data/at24.h> #include <linux/mfd/mc13xxx.h> #include "common.h" diff --git a/arch/arm/mach-imx/src.c b/arch/arm/mach-imx/src.c index 4754373e7e7d..45f7f4e0a447 100644 --- a/arch/arm/mach-imx/src.c +++ b/arch/arm/mach-imx/src.c @@ -115,21 +115,6 @@ void imx_set_cpu_arg(int cpu, u32 arg) writel_relaxed(arg, src_base + SRC_GPR1 + cpu * 8 + 4); } -void imx_src_prepare_restart(void) -{ - u32 val; - - /* clear enable bits of secondary cores */ - spin_lock(&scr_lock); - val = readl_relaxed(src_base + SRC_SCR); - val &= ~(0x7 << BP_SRC_SCR_CORE1_ENABLE); - writel_relaxed(val, src_base + SRC_SCR); - spin_unlock(&scr_lock); - - /* clear persistent entry register of primary core */ - writel_relaxed(0, src_base + SRC_GPR1); -} - void __init imx_src_init(void) { struct device_node *np; diff --git a/arch/arm/mach-imx/system.c b/arch/arm/mach-imx/system.c index e6edcd38b282..5e3027d3692f 100644 --- a/arch/arm/mach-imx/system.c +++ b/arch/arm/mach-imx/system.c @@ -42,9 +42,6 @@ void mxc_restart(enum reboot_mode mode, const char *cmd) { unsigned int wcr_enable; - if (cpu_is_imx6q() || cpu_is_imx6dl()) - imx_src_prepare_restart(); - if (wdog_clk) clk_enable(wdog_clk); @@ -55,7 +52,14 @@ void mxc_restart(enum reboot_mode mode, const char *cmd) /* Assert SRS signal */ __raw_writew(wcr_enable, wdog_base); - /* write twice to ensure the request will not get ignored */ + /* + * Due to imx6q errata ERR004346 (WDOG: WDOG SRS bit requires to be + * written twice), we add another two writes to ensure there must be at + * least two writes happen in the same one 32kHz clock period. We save + * the target check here, since the writes shouldn't be a huge burden + * for other platforms. + */ + __raw_writew(wcr_enable, wdog_base); __raw_writew(wcr_enable, wdog_base); /* wait for reset to assert... */ diff --git a/arch/arm/mach-integrator/integrator_cp.c b/arch/arm/mach-integrator/integrator_cp.c index 1df6e7602cad..4fc0a195de01 100644 --- a/arch/arm/mach-integrator/integrator_cp.c +++ b/arch/arm/mach-integrator/integrator_cp.c @@ -198,7 +198,8 @@ static struct mmci_platform_data mmc_data = { static void cp_clcd_enable(struct clcd_fb *fb) { struct fb_var_screeninfo *var = &fb->fb.var; - u32 val = CM_CTRL_STATIC1 | CM_CTRL_STATIC2; + u32 val = CM_CTRL_STATIC1 | CM_CTRL_STATIC2 + | CM_CTRL_LCDEN0 | CM_CTRL_LCDEN1; if (var->bits_per_pixel <= 8 || (var->bits_per_pixel == 16 && var->green.length == 5)) diff --git a/arch/arm/mach-iop13xx/include/mach/adma.h b/arch/arm/mach-iop13xx/include/mach/adma.h index 6d3782d85a9f..a86fd0ed7757 100644 --- a/arch/arm/mach-iop13xx/include/mach/adma.h +++ b/arch/arm/mach-iop13xx/include/mach/adma.h @@ -218,20 +218,6 @@ iop_chan_xor_slot_count(size_t len, int src_cnt, int *slots_per_op) #define iop_chan_pq_slot_count iop_chan_xor_slot_count #define iop_chan_pq_zero_sum_slot_count iop_chan_xor_slot_count -static inline u32 iop_desc_get_dest_addr(struct iop_adma_desc_slot *desc, - struct iop_adma_chan *chan) -{ - struct iop13xx_adma_desc_hw *hw_desc = desc->hw_desc; - return hw_desc->dest_addr; -} - -static inline u32 iop_desc_get_qdest_addr(struct iop_adma_desc_slot *desc, - struct iop_adma_chan *chan) -{ - struct iop13xx_adma_desc_hw *hw_desc = desc->hw_desc; - return hw_desc->q_dest_addr; -} - static inline u32 iop_desc_get_byte_count(struct iop_adma_desc_slot *desc, struct iop_adma_chan *chan) { @@ -350,18 +336,6 @@ iop_desc_init_pq(struct iop_adma_desc_slot *desc, int src_cnt, hw_desc->desc_ctrl = u_desc_ctrl.value; } -static inline int iop_desc_is_pq(struct iop_adma_desc_slot *desc) -{ - struct iop13xx_adma_desc_hw *hw_desc = desc->hw_desc; - union { - u32 value; - struct iop13xx_adma_desc_ctrl field; - } u_desc_ctrl; - - u_desc_ctrl.value = hw_desc->desc_ctrl; - return u_desc_ctrl.field.pq_xfer_en; -} - static inline void iop_desc_init_pq_zero_sum(struct iop_adma_desc_slot *desc, int src_cnt, unsigned long flags) diff --git a/arch/arm/mach-kirkwood/lacie_v2-common.c b/arch/arm/mach-kirkwood/lacie_v2-common.c index 489495976fcd..8e3e4331c380 100644 --- a/arch/arm/mach-kirkwood/lacie_v2-common.c +++ b/arch/arm/mach-kirkwood/lacie_v2-common.c @@ -12,7 +12,7 @@ #include <linux/spi/flash.h> #include <linux/spi/spi.h> #include <linux/i2c.h> -#include <linux/i2c/at24.h> +#include <linux/platform_data/at24.h> #include <linux/gpio.h> #include <asm/mach/time.h> #include <mach/kirkwood.h> diff --git a/arch/arm/mach-mmp/ttc_dkb.c b/arch/arm/mach-mmp/ttc_dkb.c index 702232996c8c..cfadd974f5ce 100644 --- a/arch/arm/mach-mmp/ttc_dkb.c +++ b/arch/arm/mach-mmp/ttc_dkb.c @@ -191,7 +191,6 @@ static struct pxa3xx_nand_platform_data dkb_nand_info = { #define SCLK_SOURCE_SELECT(x) (x << 30) /* 0x0 ~ 0x3 */ /* link config */ #define CFG_DUMBMODE(mode) (mode << 28) /* 0x0 ~ 0x6*/ -#define CFG_GRA_SWAPRB(x) (x << 0) /* 1: rbswap enabled */ static struct mmp_mach_path_config dkb_disp_config[] = { [0] = { .name = "mmp-parallel", @@ -199,8 +198,7 @@ static struct mmp_mach_path_config dkb_disp_config[] = { .output_type = PATH_OUT_PARALLEL, .path_config = CFG_IOPADMODE(0x1) | SCLK_SOURCE_SELECT(0x1), - .link_config = CFG_DUMBMODE(0x2) - | CFG_GRA_SWAPRB(0x1), + .link_config = CFG_DUMBMODE(0x2), }, }; diff --git a/arch/arm/mach-omap1/board-osk.c b/arch/arm/mach-omap1/board-osk.c index a7ce69286688..d68909b095f1 100644 --- a/arch/arm/mach-omap1/board-osk.c +++ b/arch/arm/mach-omap1/board-osk.c @@ -300,7 +300,7 @@ static struct omap_lcd_config osk_lcd_config __initdata = { #ifdef CONFIG_OMAP_OSK_MISTRAL #include <linux/input.h> -#include <linux/i2c/at24.h> +#include <linux/platform_data/at24.h> #include <linux/spi/spi.h> #include <linux/spi/ads7846.h> diff --git a/arch/arm/mach-omap2/Makefile b/arch/arm/mach-omap2/Makefile index e15ac005ef17..1f25f3e99c05 100644 --- a/arch/arm/mach-omap2/Makefile +++ b/arch/arm/mach-omap2/Makefile @@ -40,7 +40,7 @@ omap-4-5-common = omap4-common.o omap-wakeupgen.o obj-$(CONFIG_ARCH_OMAP4) += $(omap-4-5-common) $(smp-y) sleep44xx.o obj-$(CONFIG_SOC_OMAP5) += $(omap-4-5-common) $(smp-y) sleep44xx.o obj-$(CONFIG_SOC_AM43XX) += $(omap-4-5-common) -obj-$(CONFIG_SOC_DRA7XX) += $(omap-4-5-common) $(smp-y) +obj-$(CONFIG_SOC_DRA7XX) += $(omap-4-5-common) $(smp-y) sleep44xx.o plus_sec := $(call as-instr,.arch_extension sec,+sec) AFLAGS_omap-headsmp.o :=-Wa,-march=armv7-a$(plus_sec) diff --git a/arch/arm/mach-omap2/board-cm-t35.c b/arch/arm/mach-omap2/board-cm-t35.c index 33d159e2386e..8dd0ec858cf1 100644 --- a/arch/arm/mach-omap2/board-cm-t35.c +++ b/arch/arm/mach-omap2/board-cm-t35.c @@ -25,7 +25,7 @@ #include <linux/gpio.h> #include <linux/platform_data/gpio-omap.h> -#include <linux/i2c/at24.h> +#include <linux/platform_data/at24.h> #include <linux/i2c/twl.h> #include <linux/regulator/fixed.h> #include <linux/regulator/machine.h> diff --git a/arch/arm/mach-omap2/board-flash.c b/arch/arm/mach-omap2/board-flash.c index fc20a61f6b2a..ac82512b9c8c 100644 --- a/arch/arm/mach-omap2/board-flash.c +++ b/arch/arm/mach-omap2/board-flash.c @@ -142,7 +142,7 @@ __init board_nand_init(struct mtd_partition *nand_parts, u8 nr_parts, u8 cs, board_nand_data.nr_parts = nr_parts; board_nand_data.devsize = nand_type; - board_nand_data.ecc_opt = OMAP_ECC_HAMMING_CODE_DEFAULT; + board_nand_data.ecc_opt = OMAP_ECC_BCH8_CODE_HW; gpmc_nand_init(&board_nand_data, gpmc_t); } #endif /* CONFIG_MTD_NAND_OMAP2 || CONFIG_MTD_NAND_OMAP2_MODULE */ diff --git a/arch/arm/mach-omap2/board-h4.c b/arch/arm/mach-omap2/board-h4.c index 87e41a8b8d46..f7808349a734 100644 --- a/arch/arm/mach-omap2/board-h4.c +++ b/arch/arm/mach-omap2/board-h4.c @@ -20,7 +20,7 @@ #include <linux/delay.h> #include <linux/workqueue.h> #include <linux/i2c.h> -#include <linux/i2c/at24.h> +#include <linux/platform_data/at24.h> #include <linux/input.h> #include <linux/err.h> #include <linux/clk.h> diff --git a/arch/arm/mach-omap2/board-omap3beagle.c b/arch/arm/mach-omap2/board-omap3beagle.c index 8b9cd0690ce7..d6ed819ff15c 100644 --- a/arch/arm/mach-omap2/board-omap3beagle.c +++ b/arch/arm/mach-omap2/board-omap3beagle.c @@ -25,7 +25,7 @@ #include <linux/gpio.h> #include <linux/input.h> #include <linux/gpio_keys.h> -#include <linux/opp.h> +#include <linux/pm_opp.h> #include <linux/cpu.h> #include <linux/mtd/mtd.h> @@ -510,17 +510,17 @@ static int __init beagle_opp_init(void) mpu_dev = get_cpu_device(0); iva_dev = omap_device_get_by_hwmod_name("iva"); - if (IS_ERR(mpu_dev) || IS_ERR(iva_dev)) { + if (!mpu_dev || IS_ERR(iva_dev)) { pr_err("%s: Aiee.. no mpu/dsp devices? %p %p\n", __func__, mpu_dev, iva_dev); return -ENODEV; } /* Enable MPU 1GHz and lower opps */ - r = opp_enable(mpu_dev, 800000000); + r = dev_pm_opp_enable(mpu_dev, 800000000); /* TODO: MPU 1GHz needs SR and ABB */ /* Enable IVA 800MHz and lower opps */ - r |= opp_enable(iva_dev, 660000000); + r |= dev_pm_opp_enable(iva_dev, 660000000); /* TODO: DSP 800MHz needs SR and ABB */ if (r) { pr_err("%s: failed to enable higher opp %d\n", @@ -529,8 +529,8 @@ static int __init beagle_opp_init(void) * Cleanup - disable the higher freqs - we dont care * about the results */ - opp_disable(mpu_dev, 800000000); - opp_disable(iva_dev, 660000000); + dev_pm_opp_disable(mpu_dev, 800000000); + dev_pm_opp_disable(iva_dev, 660000000); } } return 0; diff --git a/arch/arm/mach-omap2/board-omap3stalker.c b/arch/arm/mach-omap2/board-omap3stalker.c index ba8342fef799..119efaf5808a 100644 --- a/arch/arm/mach-omap2/board-omap3stalker.c +++ b/arch/arm/mach-omap2/board-omap3stalker.c @@ -32,7 +32,7 @@ #include <linux/spi/spi.h> #include <linux/interrupt.h> #include <linux/smsc911x.h> -#include <linux/i2c/at24.h> +#include <linux/platform_data/at24.h> #include <linux/usb/phy.h> #include <asm/mach-types.h> diff --git a/arch/arm/mach-omap2/cclock3xxx_data.c b/arch/arm/mach-omap2/cclock3xxx_data.c index 03a2829beb8e..3b05aea56d1f 100644 --- a/arch/arm/mach-omap2/cclock3xxx_data.c +++ b/arch/arm/mach-omap2/cclock3xxx_data.c @@ -381,6 +381,42 @@ static struct clk_hw_omap dpll4_ck_hw = { DEFINE_STRUCT_CLK(dpll4_ck, dpll3_ck_parent_names, dpll4_ck_ops); +static const struct clk_div_table dpll4_mx_ck_div_table[] = { + { .div = 1, .val = 1 }, + { .div = 2, .val = 2 }, + { .div = 3, .val = 3 }, + { .div = 4, .val = 4 }, + { .div = 5, .val = 5 }, + { .div = 6, .val = 6 }, + { .div = 7, .val = 7 }, + { .div = 8, .val = 8 }, + { .div = 9, .val = 9 }, + { .div = 10, .val = 10 }, + { .div = 11, .val = 11 }, + { .div = 12, .val = 12 }, + { .div = 13, .val = 13 }, + { .div = 14, .val = 14 }, + { .div = 15, .val = 15 }, + { .div = 16, .val = 16 }, + { .div = 17, .val = 17 }, + { .div = 18, .val = 18 }, + { .div = 19, .val = 19 }, + { .div = 20, .val = 20 }, + { .div = 21, .val = 21 }, + { .div = 22, .val = 22 }, + { .div = 23, .val = 23 }, + { .div = 24, .val = 24 }, + { .div = 25, .val = 25 }, + { .div = 26, .val = 26 }, + { .div = 27, .val = 27 }, + { .div = 28, .val = 28 }, + { .div = 29, .val = 29 }, + { .div = 30, .val = 30 }, + { .div = 31, .val = 31 }, + { .div = 32, .val = 32 }, + { .div = 0 }, +}; + DEFINE_CLK_DIVIDER(dpll4_m5_ck, "dpll4_ck", &dpll4_ck, 0x0, OMAP_CM_REGADDR(OMAP3430_CAM_MOD, CM_CLKSEL), OMAP3430_CLKSEL_CAM_SHIFT, OMAP3630_CLKSEL_CAM_WIDTH, @@ -524,10 +560,10 @@ static const struct clksel_rate clkout2_src_54m_rates[] = { { .div = 0 } }; -DEFINE_CLK_DIVIDER(dpll4_m3_ck, "dpll4_ck", &dpll4_ck, 0x0, +DEFINE_CLK_DIVIDER_TABLE(dpll4_m3_ck, "dpll4_ck", &dpll4_ck, 0x0, OMAP_CM_REGADDR(OMAP3430_DSS_MOD, CM_CLKSEL), OMAP3430_CLKSEL_TV_SHIFT, OMAP3630_CLKSEL_TV_WIDTH, - CLK_DIVIDER_ONE_BASED, NULL); + 0, dpll4_mx_ck_div_table, NULL); static struct clk dpll4_m3x2_ck; @@ -847,10 +883,10 @@ static struct clk dpll3_m3x2_ck_3630 = { DEFINE_CLK_FIXED_FACTOR(dpll3_x2_ck, "dpll3_ck", &dpll3_ck, 0x0, 2, 1); -DEFINE_CLK_DIVIDER(dpll4_m4_ck, "dpll4_ck", &dpll4_ck, 0x0, +DEFINE_CLK_DIVIDER_TABLE(dpll4_m4_ck, "dpll4_ck", &dpll4_ck, 0x0, OMAP_CM_REGADDR(OMAP3430_DSS_MOD, CM_CLKSEL), OMAP3430_CLKSEL_DSS1_SHIFT, OMAP3630_CLKSEL_DSS1_WIDTH, - CLK_DIVIDER_ONE_BASED, NULL); + 0, dpll4_mx_ck_div_table, NULL); static struct clk dpll4_m4x2_ck; @@ -869,7 +905,8 @@ static struct clk_hw_omap dpll4_m4x2_ck_hw = { .clkdm_name = "dpll4_clkdm", }; -DEFINE_STRUCT_CLK(dpll4_m4x2_ck, dpll4_m4x2_ck_parent_names, dpll4_m5x2_ck_ops); +DEFINE_STRUCT_CLK_FLAGS(dpll4_m4x2_ck, dpll4_m4x2_ck_parent_names, + dpll4_m5x2_ck_ops, CLK_SET_RATE_PARENT); static struct clk dpll4_m4x2_ck_3630 = { .name = "dpll4_m4x2_ck", @@ -877,6 +914,7 @@ static struct clk dpll4_m4x2_ck_3630 = { .parent_names = dpll4_m4x2_ck_parent_names, .num_parents = ARRAY_SIZE(dpll4_m4x2_ck_parent_names), .ops = &dpll4_m5x2_ck_3630_ops, + .flags = CLK_SET_RATE_PARENT, }; DEFINE_CLK_DIVIDER(dpll4_m6_ck, "dpll4_ck", &dpll4_ck, 0x0, @@ -968,8 +1006,9 @@ static struct clk_hw_omap dss1_alwon_fck_3430es1_hw = { .clkdm_name = "dss_clkdm", }; -DEFINE_STRUCT_CLK(dss1_alwon_fck_3430es1, dss1_alwon_fck_3430es1_parent_names, - aes2_ick_ops); +DEFINE_STRUCT_CLK_FLAGS(dss1_alwon_fck_3430es1, + dss1_alwon_fck_3430es1_parent_names, aes2_ick_ops, + CLK_SET_RATE_PARENT); static struct clk dss1_alwon_fck_3430es2; @@ -983,8 +1022,9 @@ static struct clk_hw_omap dss1_alwon_fck_3430es2_hw = { .clkdm_name = "dss_clkdm", }; -DEFINE_STRUCT_CLK(dss1_alwon_fck_3430es2, dss1_alwon_fck_3430es1_parent_names, - aes2_ick_ops); +DEFINE_STRUCT_CLK_FLAGS(dss1_alwon_fck_3430es2, + dss1_alwon_fck_3430es1_parent_names, aes2_ick_ops, + CLK_SET_RATE_PARENT); static struct clk dss2_alwon_fck; diff --git a/arch/arm/mach-omap2/cclock44xx_data.c b/arch/arm/mach-omap2/cclock44xx_data.c index b237950eb8a3..ec0dc0b1755e 100644 --- a/arch/arm/mach-omap2/cclock44xx_data.c +++ b/arch/arm/mach-omap2/cclock44xx_data.c @@ -830,7 +830,8 @@ DEFINE_CLK_GATE(dss_tv_clk, "extalt_clkin_ck", &extalt_clkin_ck, 0x0, OMAP4430_CM_DSS_DSS_CLKCTRL, OMAP4430_OPTFCLKEN_TV_CLK_SHIFT, 0x0, NULL); -DEFINE_CLK_GATE(dss_dss_clk, "dpll_per_m5x2_ck", &dpll_per_m5x2_ck, 0x0, +DEFINE_CLK_GATE(dss_dss_clk, "dpll_per_m5x2_ck", &dpll_per_m5x2_ck, + CLK_SET_RATE_PARENT, OMAP4430_CM_DSS_DSS_CLKCTRL, OMAP4430_OPTFCLKEN_DSSCLK_SHIFT, 0x0, NULL); diff --git a/arch/arm/mach-omap2/gpmc-smsc911x.c b/arch/arm/mach-omap2/gpmc-smsc911x.c index ef990118d32b..2757504a13c4 100644 --- a/arch/arm/mach-omap2/gpmc-smsc911x.c +++ b/arch/arm/mach-omap2/gpmc-smsc911x.c @@ -83,7 +83,7 @@ void __init gpmc_smsc911x_init(struct omap_smsc911x_platform_data *gpmc_cfg) pdev = platform_device_register_resndata(NULL, "smsc911x", gpmc_cfg->id, gpmc_smsc911x_resources, ARRAY_SIZE(gpmc_smsc911x_resources), &gpmc_smsc911x_config, sizeof(gpmc_smsc911x_config)); - if (!pdev) { + if (IS_ERR(pdev)) { pr_err("Unable to register platform device\n"); gpio_free(gpmc_cfg->gpio_reset); goto free2; diff --git a/arch/arm/mach-omap2/gpmc.c b/arch/arm/mach-omap2/gpmc.c index 51525faa0aec..81de56251955 100644 --- a/arch/arm/mach-omap2/gpmc.c +++ b/arch/arm/mach-omap2/gpmc.c @@ -1341,14 +1341,6 @@ static void __maybe_unused gpmc_read_timings_dt(struct device_node *np, #ifdef CONFIG_MTD_NAND -static const char * const nand_ecc_opts[] = { - [OMAP_ECC_HAMMING_CODE_DEFAULT] = "sw", - [OMAP_ECC_HAMMING_CODE_HW] = "hw", - [OMAP_ECC_HAMMING_CODE_HW_ROMCODE] = "hw-romcode", - [OMAP_ECC_BCH4_CODE_HW] = "bch4", - [OMAP_ECC_BCH8_CODE_HW] = "bch8", -}; - static const char * const nand_xfer_types[] = { [NAND_OMAP_PREFETCH_POLLED] = "prefetch-polled", [NAND_OMAP_POLLED] = "polled", @@ -1378,13 +1370,41 @@ static int gpmc_probe_nand_child(struct platform_device *pdev, gpmc_nand_data->cs = val; gpmc_nand_data->of_node = child; - if (!of_property_read_string(child, "ti,nand-ecc-opt", &s)) - for (val = 0; val < ARRAY_SIZE(nand_ecc_opts); val++) - if (!strcasecmp(s, nand_ecc_opts[val])) { - gpmc_nand_data->ecc_opt = val; - break; - } + /* Detect availability of ELM module */ + gpmc_nand_data->elm_of_node = of_parse_phandle(child, "ti,elm-id", 0); + if (gpmc_nand_data->elm_of_node == NULL) + gpmc_nand_data->elm_of_node = + of_parse_phandle(child, "elm_id", 0); + if (gpmc_nand_data->elm_of_node == NULL) + pr_warn("%s: ti,elm-id property not found\n", __func__); + + /* select ecc-scheme for NAND */ + if (of_property_read_string(child, "ti,nand-ecc-opt", &s)) { + pr_err("%s: ti,nand-ecc-opt not found\n", __func__); + return -ENODEV; + } + if (!strcmp(s, "ham1") || !strcmp(s, "sw") || + !strcmp(s, "hw") || !strcmp(s, "hw-romcode")) + gpmc_nand_data->ecc_opt = + OMAP_ECC_HAM1_CODE_HW; + else if (!strcmp(s, "bch4")) + if (gpmc_nand_data->elm_of_node) + gpmc_nand_data->ecc_opt = + OMAP_ECC_BCH4_CODE_HW; + else + gpmc_nand_data->ecc_opt = + OMAP_ECC_BCH4_CODE_HW_DETECTION_SW; + else if (!strcmp(s, "bch8")) + if (gpmc_nand_data->elm_of_node) + gpmc_nand_data->ecc_opt = + OMAP_ECC_BCH8_CODE_HW; + else + gpmc_nand_data->ecc_opt = + OMAP_ECC_BCH8_CODE_HW_DETECTION_SW; + else + pr_err("%s: ti,nand-ecc-opt invalid value\n", __func__); + /* select data transfer mode for NAND controller */ if (!of_property_read_string(child, "ti,nand-xfer-type", &s)) for (val = 0; val < ARRAY_SIZE(nand_xfer_types); val++) if (!strcasecmp(s, nand_xfer_types[val])) { diff --git a/arch/arm/mach-omap2/omap-pm.h b/arch/arm/mach-omap2/omap-pm.h index 67faa7b8fe92..1d777e63e05c 100644 --- a/arch/arm/mach-omap2/omap-pm.h +++ b/arch/arm/mach-omap2/omap-pm.h @@ -17,7 +17,7 @@ #include <linux/device.h> #include <linux/cpufreq.h> #include <linux/clk.h> -#include <linux/opp.h> +#include <linux/pm_opp.h> /* * agent_id values for use with omap_pm_set_min_bus_tput(): diff --git a/arch/arm/mach-omap2/omap_device.c b/arch/arm/mach-omap2/omap_device.c index b69dd9abb50a..53f0735817bb 100644 --- a/arch/arm/mach-omap2/omap_device.c +++ b/arch/arm/mach-omap2/omap_device.c @@ -621,6 +621,7 @@ static int _od_suspend_noirq(struct device *dev) if (!ret && !pm_runtime_status_suspended(dev)) { if (pm_generic_runtime_suspend(dev) == 0) { + pm_runtime_set_suspended(dev); omap_device_idle(pdev); od->flags |= OMAP_DEVICE_SUSPENDED; } @@ -634,10 +635,18 @@ static int _od_resume_noirq(struct device *dev) struct platform_device *pdev = to_platform_device(dev); struct omap_device *od = to_omap_device(pdev); - if ((od->flags & OMAP_DEVICE_SUSPENDED) && - !pm_runtime_status_suspended(dev)) { + if (od->flags & OMAP_DEVICE_SUSPENDED) { od->flags &= ~OMAP_DEVICE_SUSPENDED; omap_device_enable(pdev); + /* + * XXX: we run before core runtime pm has resumed itself. At + * this point in time, we just restore the runtime pm state and + * considering symmetric operations in resume, we donot expect + * to fail. If we failed, something changed in core runtime_pm + * framework OR some device driver messed things up, hence, WARN + */ + WARN(pm_runtime_set_active(dev), + "Could not set %s runtime state active\n", dev_name(dev)); pm_generic_runtime_resume(dev); } diff --git a/arch/arm/mach-omap2/opp.c b/arch/arm/mach-omap2/opp.c index 82fd8c72f750..a358a07e18f2 100644 --- a/arch/arm/mach-omap2/opp.c +++ b/arch/arm/mach-omap2/opp.c @@ -18,7 +18,7 @@ */ #include <linux/module.h> #include <linux/of.h> -#include <linux/opp.h> +#include <linux/pm_opp.h> #include <linux/cpu.h> #include "omap_device.h" @@ -85,14 +85,14 @@ int __init omap_init_opp_table(struct omap_opp_def *opp_def, dev = &oh->od->pdev->dev; } - r = opp_add(dev, opp_def->freq, opp_def->u_volt); + r = dev_pm_opp_add(dev, opp_def->freq, opp_def->u_volt); if (r) { dev_err(dev, "%s: add OPP %ld failed for %s [%d] result=%d\n", __func__, opp_def->freq, opp_def->hwmod_name, i, r); } else { if (!opp_def->default_available) - r = opp_disable(dev, opp_def->freq); + r = dev_pm_opp_disable(dev, opp_def->freq); if (r) dev_err(dev, "%s: disable %ld failed for %s [%d] result=%d\n", __func__, opp_def->freq, diff --git a/arch/arm/mach-omap2/pm.c b/arch/arm/mach-omap2/pm.c index 360b2daf54dd..e1b41416fbf1 100644 --- a/arch/arm/mach-omap2/pm.c +++ b/arch/arm/mach-omap2/pm.c @@ -13,7 +13,7 @@ #include <linux/init.h> #include <linux/io.h> #include <linux/err.h> -#include <linux/opp.h> +#include <linux/pm_opp.h> #include <linux/export.h> #include <linux/suspend.h> #include <linux/cpu.h> @@ -131,7 +131,7 @@ static int __init omap2_set_init_voltage(char *vdd_name, char *clk_name, { struct voltagedomain *voltdm; struct clk *clk; - struct opp *opp; + struct dev_pm_opp *opp; unsigned long freq, bootup_volt; struct device *dev; @@ -172,7 +172,7 @@ static int __init omap2_set_init_voltage(char *vdd_name, char *clk_name, clk_put(clk); rcu_read_lock(); - opp = opp_find_freq_ceil(dev, &freq); + opp = dev_pm_opp_find_freq_ceil(dev, &freq); if (IS_ERR(opp)) { rcu_read_unlock(); pr_err("%s: unable to find boot up OPP for vdd_%s\n", @@ -180,7 +180,7 @@ static int __init omap2_set_init_voltage(char *vdd_name, char *clk_name, goto exit; } - bootup_volt = opp_get_voltage(opp); + bootup_volt = dev_pm_opp_get_voltage(opp); rcu_read_unlock(); if (!bootup_volt) { pr_err("%s: unable to find voltage corresponding to the bootup OPP for vdd_%s\n", diff --git a/arch/arm/mach-omap2/prm44xx_54xx.h b/arch/arm/mach-omap2/prm44xx_54xx.h index a085d9cc1f5d..7a976065e138 100644 --- a/arch/arm/mach-omap2/prm44xx_54xx.h +++ b/arch/arm/mach-omap2/prm44xx_54xx.h @@ -42,7 +42,8 @@ extern u32 omap4_prm_vcvp_read(u8 offset); extern void omap4_prm_vcvp_write(u32 val, u8 offset); extern u32 omap4_prm_vcvp_rmw(u32 mask, u32 bits, u8 offset); -#if defined(CONFIG_ARCH_OMAP4) || defined(CONFIG_SOC_OMAP5) +#if defined(CONFIG_ARCH_OMAP4) || defined(CONFIG_SOC_OMAP5) || \ + defined(CONFIG_SOC_DRA7XX) void omap44xx_prm_reconfigure_io_chain(void); #else static inline void omap44xx_prm_reconfigure_io_chain(void) diff --git a/arch/arm/mach-pxa/Kconfig b/arch/arm/mach-pxa/Kconfig index a8427115ee07..96100dbf5a2e 100644 --- a/arch/arm/mach-pxa/Kconfig +++ b/arch/arm/mach-pxa/Kconfig @@ -615,14 +615,12 @@ endmenu config PXA25x bool select CPU_XSCALE - select CPU_FREQ_TABLE if CPU_FREQ help Select code specific to PXA21x/25x/26x variants config PXA27x bool select CPU_XSCALE - select CPU_FREQ_TABLE if CPU_FREQ help Select code specific to PXA27x variants @@ -635,7 +633,6 @@ config CPU_PXA26x config PXA3xx bool select CPU_XSC3 - select CPU_FREQ_TABLE if CPU_FREQ help Select code specific to PXA3xx variants diff --git a/arch/arm/mach-pxa/cm-x300.c b/arch/arm/mach-pxa/cm-x300.c index f9423493ed36..584439bfa59f 100644 --- a/arch/arm/mach-pxa/cm-x300.c +++ b/arch/arm/mach-pxa/cm-x300.c @@ -310,6 +310,7 @@ static struct platform_pwm_backlight_data cm_x300_backlight_data = { .max_brightness = 100, .dft_brightness = 100, .pwm_period_ns = 10000, + .enable_gpio = -1, }; static struct platform_device cm_x300_backlight_device = { diff --git a/arch/arm/mach-pxa/colibri-pxa270-income.c b/arch/arm/mach-pxa/colibri-pxa270-income.c index 2d4a7b4d5d78..3aa264640c9d 100644 --- a/arch/arm/mach-pxa/colibri-pxa270-income.c +++ b/arch/arm/mach-pxa/colibri-pxa270-income.c @@ -189,6 +189,7 @@ static struct platform_pwm_backlight_data income_backlight_data = { .max_brightness = 0x3ff, .dft_brightness = 0x1ff, .pwm_period_ns = 1000000, + .enable_gpio = -1, }; static struct platform_device income_backlight = { diff --git a/arch/arm/mach-pxa/ezx.c b/arch/arm/mach-pxa/ezx.c index fe2eb8394dff..ab93441e596e 100644 --- a/arch/arm/mach-pxa/ezx.c +++ b/arch/arm/mach-pxa/ezx.c @@ -54,6 +54,7 @@ static struct platform_pwm_backlight_data ezx_backlight_data = { .max_brightness = 1023, .dft_brightness = 1023, .pwm_period_ns = 78770, + .enable_gpio = -1, }; static struct platform_device ezx_backlight_device = { diff --git a/arch/arm/mach-pxa/hx4700.c b/arch/arm/mach-pxa/hx4700.c index 133109ec7332..a7c30eb0c8db 100644 --- a/arch/arm/mach-pxa/hx4700.c +++ b/arch/arm/mach-pxa/hx4700.c @@ -561,6 +561,7 @@ static struct platform_pwm_backlight_data backlight_data = { .max_brightness = 200, .dft_brightness = 100, .pwm_period_ns = 30923, + .enable_gpio = -1, }; static struct platform_device backlight = { diff --git a/arch/arm/mach-pxa/lpd270.c b/arch/arm/mach-pxa/lpd270.c index 1255ee00f3d1..9f6ec167902a 100644 --- a/arch/arm/mach-pxa/lpd270.c +++ b/arch/arm/mach-pxa/lpd270.c @@ -269,6 +269,7 @@ static struct platform_pwm_backlight_data lpd270_backlight_data = { .max_brightness = 1, .dft_brightness = 1, .pwm_period_ns = 78770, + .enable_gpio = -1, }; static struct platform_device lpd270_backlight_device = { diff --git a/arch/arm/mach-pxa/magician.c b/arch/arm/mach-pxa/magician.c index f44532fc648b..fab30d666cc7 100644 --- a/arch/arm/mach-pxa/magician.c +++ b/arch/arm/mach-pxa/magician.c @@ -378,6 +378,7 @@ static struct platform_pwm_backlight_data backlight_data = { .max_brightness = 272, .dft_brightness = 100, .pwm_period_ns = 30923, + .enable_gpio = -1, .init = magician_backlight_init, .notify = magician_backlight_notify, .exit = magician_backlight_exit, diff --git a/arch/arm/mach-pxa/mainstone.c b/arch/arm/mach-pxa/mainstone.c index dd70343c8708..08ccc0718f31 100644 --- a/arch/arm/mach-pxa/mainstone.c +++ b/arch/arm/mach-pxa/mainstone.c @@ -338,6 +338,7 @@ static struct platform_pwm_backlight_data mainstone_backlight_data = { .max_brightness = 1023, .dft_brightness = 1023, .pwm_period_ns = 78770, + .enable_gpio = -1, }; static struct platform_device mainstone_backlight_device = { diff --git a/arch/arm/mach-pxa/mioa701.c b/arch/arm/mach-pxa/mioa701.c index acc9d3cc0762..f70583fee59f 100644 --- a/arch/arm/mach-pxa/mioa701.c +++ b/arch/arm/mach-pxa/mioa701.c @@ -186,6 +186,7 @@ static struct platform_pwm_backlight_data mioa701_backlight_data = { .max_brightness = 100, .dft_brightness = 50, .pwm_period_ns = 4000 * 1024, /* Fl = 250kHz */ + .enable_gpio = -1, }; /* diff --git a/arch/arm/mach-pxa/palm27x.c b/arch/arm/mach-pxa/palm27x.c index 17d4c53017ca..e54a296fb81f 100644 --- a/arch/arm/mach-pxa/palm27x.c +++ b/arch/arm/mach-pxa/palm27x.c @@ -322,6 +322,7 @@ static struct platform_pwm_backlight_data palm27x_backlight_data = { .max_brightness = 0xfe, .dft_brightness = 0x7e, .pwm_period_ns = 3500 * 1024, + .enable_gpio = -1, .init = palm27x_backlight_init, .notify = palm27x_backlight_notify, .exit = palm27x_backlight_exit, diff --git a/arch/arm/mach-pxa/palmtc.c b/arch/arm/mach-pxa/palmtc.c index 100b176f7e88..7691c974ca4b 100644 --- a/arch/arm/mach-pxa/palmtc.c +++ b/arch/arm/mach-pxa/palmtc.c @@ -166,45 +166,12 @@ static inline void palmtc_keys_init(void) {} * Backlight ******************************************************************************/ #if defined(CONFIG_BACKLIGHT_PWM) || defined(CONFIG_BACKLIGHT_PWM_MODULE) -static int palmtc_backlight_init(struct device *dev) -{ - int ret; - - ret = gpio_request(GPIO_NR_PALMTC_BL_POWER, "BL POWER"); - if (ret) - goto err; - ret = gpio_direction_output(GPIO_NR_PALMTC_BL_POWER, 1); - if (ret) - goto err2; - - return 0; - -err2: - gpio_free(GPIO_NR_PALMTC_BL_POWER); -err: - return ret; -} - -static int palmtc_backlight_notify(struct device *dev, int brightness) -{ - /* backlight is on when GPIO16 AF0 is high */ - gpio_set_value(GPIO_NR_PALMTC_BL_POWER, brightness); - return brightness; -} - -static void palmtc_backlight_exit(struct device *dev) -{ - gpio_free(GPIO_NR_PALMTC_BL_POWER); -} - static struct platform_pwm_backlight_data palmtc_backlight_data = { .pwm_id = 1, .max_brightness = PALMTC_MAX_INTENSITY, .dft_brightness = PALMTC_MAX_INTENSITY, .pwm_period_ns = PALMTC_PERIOD_NS, - .init = palmtc_backlight_init, - .notify = palmtc_backlight_notify, - .exit = palmtc_backlight_exit, + .enable_gpio = GPIO_NR_PALMTC_BL_POWER, }; static struct platform_device palmtc_backlight = { diff --git a/arch/arm/mach-pxa/palmte2.c b/arch/arm/mach-pxa/palmte2.c index 0742721ced2d..956fd24ee6fd 100644 --- a/arch/arm/mach-pxa/palmte2.c +++ b/arch/arm/mach-pxa/palmte2.c @@ -165,6 +165,7 @@ static struct platform_pwm_backlight_data palmte2_backlight_data = { .max_brightness = PALMTE2_MAX_INTENSITY, .dft_brightness = PALMTE2_MAX_INTENSITY, .pwm_period_ns = PALMTE2_PERIOD_NS, + .enable_gpio = -1, .init = palmte2_backlight_init, .notify = palmte2_backlight_notify, .exit = palmte2_backlight_exit, diff --git a/arch/arm/mach-pxa/pcm990-baseboard.c b/arch/arm/mach-pxa/pcm990-baseboard.c index 3133ba82c508..9a4e470f162b 100644 --- a/arch/arm/mach-pxa/pcm990-baseboard.c +++ b/arch/arm/mach-pxa/pcm990-baseboard.c @@ -153,6 +153,7 @@ static struct platform_pwm_backlight_data pcm990_backlight_data = { .max_brightness = 1023, .dft_brightness = 1023, .pwm_period_ns = 78770, + .enable_gpio = -1, }; static struct platform_device pcm990_backlight_device = { diff --git a/arch/arm/mach-pxa/raumfeld.c b/arch/arm/mach-pxa/raumfeld.c index 969b0ba7fa70..8386dc30b3e4 100644 --- a/arch/arm/mach-pxa/raumfeld.c +++ b/arch/arm/mach-pxa/raumfeld.c @@ -539,6 +539,7 @@ static struct platform_pwm_backlight_data raumfeld_pwm_backlight_data = { .dft_brightness = 100, /* 10000 ns = 10 ms ^= 100 kHz */ .pwm_period_ns = 10000, + .enable_gpio = -1, }; static struct platform_device raumfeld_pwm_backlight_device = { diff --git a/arch/arm/mach-pxa/stargate2.c b/arch/arm/mach-pxa/stargate2.c index 62aea3e835f3..01de542432a6 100644 --- a/arch/arm/mach-pxa/stargate2.c +++ b/arch/arm/mach-pxa/stargate2.c @@ -27,7 +27,7 @@ #include <linux/i2c/pxa-i2c.h> #include <linux/i2c/pcf857x.h> -#include <linux/i2c/at24.h> +#include <linux/platform_data/at24.h> #include <linux/smc91x.h> #include <linux/gpio.h> #include <linux/leds.h> diff --git a/arch/arm/mach-pxa/tavorevb.c b/arch/arm/mach-pxa/tavorevb.c index 4680efe55345..a71da84e784b 100644 --- a/arch/arm/mach-pxa/tavorevb.c +++ b/arch/arm/mach-pxa/tavorevb.c @@ -175,6 +175,7 @@ static struct platform_pwm_backlight_data tavorevb_backlight_data[] = { .max_brightness = 100, .dft_brightness = 100, .pwm_period_ns = 100000, + .enable_gpio = -1, }, [1] = { /* secondary backlight */ @@ -182,6 +183,7 @@ static struct platform_pwm_backlight_data tavorevb_backlight_data[] = { .max_brightness = 100, .dft_brightness = 100, .pwm_period_ns = 100000, + .enable_gpio = -1, }, }; diff --git a/arch/arm/mach-pxa/viper.c b/arch/arm/mach-pxa/viper.c index 9c363c081d3f..29905b127ad9 100644 --- a/arch/arm/mach-pxa/viper.c +++ b/arch/arm/mach-pxa/viper.c @@ -401,6 +401,7 @@ static struct platform_pwm_backlight_data viper_backlight_data = { .max_brightness = 100, .dft_brightness = 100, .pwm_period_ns = 1000000, + .enable_gpio = -1, .init = viper_backlight_init, .notify = viper_backlight_notify, .exit = viper_backlight_exit, diff --git a/arch/arm/mach-pxa/z2.c b/arch/arm/mach-pxa/z2.c index 2513d8f4931f..e1a121b36cfa 100644 --- a/arch/arm/mach-pxa/z2.c +++ b/arch/arm/mach-pxa/z2.c @@ -206,6 +206,7 @@ static struct platform_pwm_backlight_data z2_backlight_data[] = { .max_brightness = 1023, .dft_brightness = 0, .pwm_period_ns = 1260320, + .enable_gpio = -1, }, [1] = { /* LCD Backlight */ @@ -213,6 +214,7 @@ static struct platform_pwm_backlight_data z2_backlight_data[] = { .max_brightness = 1023, .dft_brightness = 512, .pwm_period_ns = 1260320, + .enable_gpio = -1, }, }; diff --git a/arch/arm/mach-pxa/zylonite.c b/arch/arm/mach-pxa/zylonite.c index 36cf7cf95ec1..77daea478e88 100644 --- a/arch/arm/mach-pxa/zylonite.c +++ b/arch/arm/mach-pxa/zylonite.c @@ -125,6 +125,7 @@ static struct platform_pwm_backlight_data zylonite_backlight_data = { .max_brightness = 100, .dft_brightness = 100, .pwm_period_ns = 10000, + .enable_gpio = -1, }; static struct platform_device zylonite_backlight_device = { diff --git a/arch/arm/mach-s3c24xx/mach-h1940.c b/arch/arm/mach-s3c24xx/mach-h1940.c index 74dd47988b41..952b6a040d1f 100644 --- a/arch/arm/mach-s3c24xx/mach-h1940.c +++ b/arch/arm/mach-s3c24xx/mach-h1940.c @@ -504,6 +504,7 @@ static struct platform_pwm_backlight_data backlight_data = { .dft_brightness = 50, /* tcnt = 0x31 */ .pwm_period_ns = 36296, + .enable_gpio = -1, .init = h1940_backlight_init, .notify = h1940_backlight_notify, .exit = h1940_backlight_exit, diff --git a/arch/arm/mach-s3c24xx/mach-mini2440.c b/arch/arm/mach-s3c24xx/mach-mini2440.c index a83db46320bc..4a18d49a63e0 100644 --- a/arch/arm/mach-s3c24xx/mach-mini2440.c +++ b/arch/arm/mach-s3c24xx/mach-mini2440.c @@ -24,7 +24,7 @@ #include <linux/io.h> #include <linux/serial_core.h> #include <linux/dm9000.h> -#include <linux/i2c/at24.h> +#include <linux/platform_data/at24.h> #include <linux/platform_device.h> #include <linux/gpio_keys.h> #include <linux/i2c.h> diff --git a/arch/arm/mach-s3c24xx/mach-rx1950.c b/arch/arm/mach-s3c24xx/mach-rx1950.c index 206b1f7546d1..034b7fe45c49 100644 --- a/arch/arm/mach-s3c24xx/mach-rx1950.c +++ b/arch/arm/mach-s3c24xx/mach-rx1950.c @@ -522,6 +522,7 @@ static struct platform_pwm_backlight_data rx1950_backlight_data = { .max_brightness = 24, .dft_brightness = 4, .pwm_period_ns = 48000, + .enable_gpio = -1, .init = rx1950_backlight_init, .notify = rx1950_backlight_notify, .exit = rx1950_backlight_exit, diff --git a/arch/arm/mach-s3c64xx/mach-crag6410.c b/arch/arm/mach-s3c64xx/mach-crag6410.c index aca7d16e195d..758e31b26550 100644 --- a/arch/arm/mach-s3c64xx/mach-crag6410.c +++ b/arch/arm/mach-s3c64xx/mach-crag6410.c @@ -114,6 +114,7 @@ static struct platform_pwm_backlight_data crag6410_backlight_data = { .max_brightness = 1000, .dft_brightness = 600, .pwm_period_ns = 100000, /* about 1kHz */ + .enable_gpio = -1, }; static struct platform_device crag6410_backlight_device = { diff --git a/arch/arm/mach-s3c64xx/mach-hmt.c b/arch/arm/mach-s3c64xx/mach-hmt.c index e8064044ef79..614a03a92cf7 100644 --- a/arch/arm/mach-s3c64xx/mach-hmt.c +++ b/arch/arm/mach-s3c64xx/mach-hmt.c @@ -114,6 +114,7 @@ static struct platform_pwm_backlight_data hmt_backlight_data = { .max_brightness = 100 * 256, .dft_brightness = 40 * 256, .pwm_period_ns = 1000000000 / (100 * 256 * 20), + .enable_gpio = -1, .init = hmt_bl_init, .notify = hmt_bl_notify, .exit = hmt_bl_exit, diff --git a/arch/arm/mach-s3c64xx/mach-smartq.c b/arch/arm/mach-s3c64xx/mach-smartq.c index 0f47237be3b2..a6b338fd0470 100644 --- a/arch/arm/mach-s3c64xx/mach-smartq.c +++ b/arch/arm/mach-s3c64xx/mach-smartq.c @@ -151,6 +151,7 @@ static struct platform_pwm_backlight_data smartq_backlight_data = { .max_brightness = 1000, .dft_brightness = 600, .pwm_period_ns = 1000000000 / (1000 * 20), + .enable_gpio = -1, .init = smartq_bl_init, }; diff --git a/arch/arm/mach-s3c64xx/mach-smdk6410.c b/arch/arm/mach-s3c64xx/mach-smdk6410.c index 2a7b32ca5c96..d5ea938cc9a1 100644 --- a/arch/arm/mach-s3c64xx/mach-smdk6410.c +++ b/arch/arm/mach-s3c64xx/mach-smdk6410.c @@ -625,6 +625,7 @@ static struct samsung_bl_gpio_info smdk6410_bl_gpio_info = { static struct platform_pwm_backlight_data smdk6410_bl_data = { .pwm_id = 1, + .enable_gpio = -1, }; static struct s3c_hsotg_plat smdk6410_hsotg_pdata; diff --git a/arch/arm/mach-s5p64x0/mach-smdk6440.c b/arch/arm/mach-s5p64x0/mach-smdk6440.c index 0b00304c1e91..9efdcc03df3b 100644 --- a/arch/arm/mach-s5p64x0/mach-smdk6440.c +++ b/arch/arm/mach-s5p64x0/mach-smdk6440.c @@ -223,6 +223,7 @@ static struct samsung_bl_gpio_info smdk6440_bl_gpio_info = { static struct platform_pwm_backlight_data smdk6440_bl_data = { .pwm_id = 1, + .enable_gpio = -1, }; static void __init smdk6440_map_io(void) diff --git a/arch/arm/mach-s5p64x0/mach-smdk6450.c b/arch/arm/mach-s5p64x0/mach-smdk6450.c index 5949296e88fd..c3cacc067efe 100644 --- a/arch/arm/mach-s5p64x0/mach-smdk6450.c +++ b/arch/arm/mach-s5p64x0/mach-smdk6450.c @@ -242,6 +242,7 @@ static struct samsung_bl_gpio_info smdk6450_bl_gpio_info = { static struct platform_pwm_backlight_data smdk6450_bl_data = { .pwm_id = 1, + .enable_gpio = -1, }; static void __init smdk6450_map_io(void) diff --git a/arch/arm/mach-s5pc100/mach-smdkc100.c b/arch/arm/mach-s5pc100/mach-smdkc100.c index 7c57a221785e..9e256b9fc930 100644 --- a/arch/arm/mach-s5pc100/mach-smdkc100.c +++ b/arch/arm/mach-s5pc100/mach-smdkc100.c @@ -216,6 +216,7 @@ static struct samsung_bl_gpio_info smdkc100_bl_gpio_info = { static struct platform_pwm_backlight_data smdkc100_bl_data = { .pwm_id = 0, + .enable_gpio = -1, }; static void __init smdkc100_map_io(void) diff --git a/arch/arm/mach-s5pv210/mach-smdkv210.c b/arch/arm/mach-s5pv210/mach-smdkv210.c index 6d72bb992e38..f52cc15c2d85 100644 --- a/arch/arm/mach-s5pv210/mach-smdkv210.c +++ b/arch/arm/mach-s5pv210/mach-smdkv210.c @@ -279,6 +279,7 @@ static struct samsung_bl_gpio_info smdkv210_bl_gpio_info = { static struct platform_pwm_backlight_data smdkv210_bl_data = { .pwm_id = 3, .pwm_period_ns = 1000, + .enable_gpio = -1, }; static void __init smdkv210_map_io(void) diff --git a/arch/arm/mach-sa1100/generic.c b/arch/arm/mach-sa1100/generic.c index f25b6119e028..d4ea142c4edd 100644 --- a/arch/arm/mach-sa1100/generic.c +++ b/arch/arm/mach-sa1100/generic.c @@ -42,74 +42,31 @@ EXPORT_SYMBOL(reset_status); /* * This table is setup for a 3.6864MHz Crystal. */ -static const unsigned short cclk_frequency_100khz[NR_FREQS] = { - 590, /* 59.0 MHz */ - 737, /* 73.7 MHz */ - 885, /* 88.5 MHz */ - 1032, /* 103.2 MHz */ - 1180, /* 118.0 MHz */ - 1327, /* 132.7 MHz */ - 1475, /* 147.5 MHz */ - 1622, /* 162.2 MHz */ - 1769, /* 176.9 MHz */ - 1917, /* 191.7 MHz */ - 2064, /* 206.4 MHz */ - 2212, /* 221.2 MHz */ - 2359, /* 235.9 MHz */ - 2507, /* 250.7 MHz */ - 2654, /* 265.4 MHz */ - 2802 /* 280.2 MHz */ +struct cpufreq_frequency_table sa11x0_freq_table[NR_FREQS+1] = { + { .frequency = 59000, /* 59.0 MHz */}, + { .frequency = 73700, /* 73.7 MHz */}, + { .frequency = 88500, /* 88.5 MHz */}, + { .frequency = 103200, /* 103.2 MHz */}, + { .frequency = 118000, /* 118.0 MHz */}, + { .frequency = 132700, /* 132.7 MHz */}, + { .frequency = 147500, /* 147.5 MHz */}, + { .frequency = 162200, /* 162.2 MHz */}, + { .frequency = 176900, /* 176.9 MHz */}, + { .frequency = 191700, /* 191.7 MHz */}, + { .frequency = 206400, /* 206.4 MHz */}, + { .frequency = 221200, /* 221.2 MHz */}, + { .frequency = 235900, /* 235.9 MHz */}, + { .frequency = 250700, /* 250.7 MHz */}, + { .frequency = 265400, /* 265.4 MHz */}, + { .frequency = 280200, /* 280.2 MHz */}, + { .frequency = CPUFREQ_TABLE_END, }, }; -/* rounds up(!) */ -unsigned int sa11x0_freq_to_ppcr(unsigned int khz) -{ - int i; - - khz /= 100; - - for (i = 0; i < NR_FREQS; i++) - if (cclk_frequency_100khz[i] >= khz) - break; - - return i; -} - -unsigned int sa11x0_ppcr_to_freq(unsigned int idx) -{ - unsigned int freq = 0; - if (idx < NR_FREQS) - freq = cclk_frequency_100khz[idx] * 100; - return freq; -} - - -/* make sure that only the "userspace" governor is run -- anything else wouldn't make sense on - * this platform, anyway. - */ -int sa11x0_verify_speed(struct cpufreq_policy *policy) -{ - unsigned int tmp; - if (policy->cpu) - return -EINVAL; - - cpufreq_verify_within_limits(policy, policy->cpuinfo.min_freq, policy->cpuinfo.max_freq); - - /* make sure that at least one frequency is within the policy */ - tmp = cclk_frequency_100khz[sa11x0_freq_to_ppcr(policy->min)] * 100; - if (tmp > policy->max) - policy->max = tmp; - - cpufreq_verify_within_limits(policy, policy->cpuinfo.min_freq, policy->cpuinfo.max_freq); - - return 0; -} - unsigned int sa11x0_getspeed(unsigned int cpu) { if (cpu) return 0; - return cclk_frequency_100khz[PPCR & 0xf] * 100; + return sa11x0_freq_table[PPCR & 0xf].frequency; } /* diff --git a/arch/arm/mach-sa1100/generic.h b/arch/arm/mach-sa1100/generic.h index 9a33695c9492..0d92e119b36b 100644 --- a/arch/arm/mach-sa1100/generic.h +++ b/arch/arm/mach-sa1100/generic.h @@ -3,6 +3,7 @@ * * Author: Nicolas Pitre */ +#include <linux/cpufreq.h> #include <linux/reboot.h> extern void sa1100_timer_init(void); @@ -19,12 +20,8 @@ extern void sa11x0_init_late(void); extern void sa1110_mb_enable(void); extern void sa1110_mb_disable(void); -struct cpufreq_policy; - -extern unsigned int sa11x0_freq_to_ppcr(unsigned int khz); -extern int sa11x0_verify_speed(struct cpufreq_policy *policy); +extern struct cpufreq_frequency_table sa11x0_freq_table[]; extern unsigned int sa11x0_getspeed(unsigned int cpu); -extern unsigned int sa11x0_ppcr_to_freq(unsigned int idx); struct flash_platform_data; struct resource; diff --git a/arch/arm/mach-shmobile/board-armadillo800eva.c b/arch/arm/mach-shmobile/board-armadillo800eva.c index 8bc8e4c58847..958e3cbf0ac2 100644 --- a/arch/arm/mach-shmobile/board-armadillo800eva.c +++ b/arch/arm/mach-shmobile/board-armadillo800eva.c @@ -423,6 +423,7 @@ static struct platform_pwm_backlight_data pwm_backlight_data = { .max_brightness = 255, .dft_brightness = 255, .pwm_period_ns = 33333, /* 30kHz */ + .enable_gpio = -1, }; static struct platform_device pwm_backlight_device = { diff --git a/arch/arm/mach-sti/Kconfig b/arch/arm/mach-sti/Kconfig index 835833e3c4f8..d71654bc8d54 100644 --- a/arch/arm/mach-sti/Kconfig +++ b/arch/arm/mach-sti/Kconfig @@ -12,7 +12,7 @@ menuconfig ARCH_STI select HAVE_ARM_SCU if SMP select ARCH_REQUIRE_GPIOLIB select ARM_ERRATA_754322 - select ARM_ERRATA_764369 + select ARM_ERRATA_764369 if SMP select ARM_ERRATA_775420 select PL310_ERRATA_753970 if CACHE_PL310 select PL310_ERRATA_769419 if CACHE_PL310 @@ -30,7 +30,7 @@ config SOC_STIH415 default y help This enables support for STMicroelectronics Digital Consumer - Electronics family StiH415 parts, primarily targetted at set-top-box + Electronics family StiH415 parts, primarily targeted at set-top-box and other digital audio/video applications using Flattned Device Trees. @@ -39,7 +39,7 @@ config SOC_STIH416 default y help This enables support for STMicroelectronics Digital Consumer - Electronics family StiH416 parts, primarily targetted at set-top-box + Electronics family StiH416 parts, primarily targeted at set-top-box and other digital audio/video applications using Flattened Device Trees. diff --git a/arch/arm/mach-tegra/apbio.c b/arch/arm/mach-tegra/apbio.c index d7aa52ea6cfc..bc471973cf04 100644 --- a/arch/arm/mach-tegra/apbio.c +++ b/arch/arm/mach-tegra/apbio.c @@ -114,7 +114,7 @@ static int do_dma_transfer(unsigned long apb_add, dma_desc->callback = apb_dma_complete; dma_desc->callback_param = NULL; - INIT_COMPLETION(tegra_apb_wait); + reinit_completion(&tegra_apb_wait); dmaengine_submit(dma_desc); dma_async_issue_pending(tegra_apb_dma_chan); diff --git a/arch/arm/mach-tegra/tegra.c b/arch/arm/mach-tegra/tegra.c index ce553d557c31..73368176c6e8 100644 --- a/arch/arm/mach-tegra/tegra.c +++ b/arch/arm/mach-tegra/tegra.c @@ -90,9 +90,9 @@ static void __init tegra_init_cache(void) static void __init tegra_init_early(void) { - tegra_cpu_reset_handler_init(); tegra_apb_io_init(); tegra_init_fuse(); + tegra_cpu_reset_handler_init(); tegra_init_cache(); tegra_powergate_init(); tegra_hotplug_init(); diff --git a/arch/arm/mach-ux500/Kconfig b/arch/arm/mach-ux500/Kconfig index c67f8ad5ccd5..0034d2cd6973 100644 --- a/arch/arm/mach-ux500/Kconfig +++ b/arch/arm/mach-ux500/Kconfig @@ -29,7 +29,6 @@ if ARCH_U8500 config UX500_SOC_DB8500 bool - select CPU_FREQ_TABLE if CPU_FREQ select MFD_DB8500_PRCMU select PINCTRL_DB8500 select PINCTRL_DB8540 diff --git a/arch/arm/mach-vexpress/Kconfig b/arch/arm/mach-vexpress/Kconfig index cbbb81e0e509..4a70be485ff8 100644 --- a/arch/arm/mach-vexpress/Kconfig +++ b/arch/arm/mach-vexpress/Kconfig @@ -65,10 +65,22 @@ config ARCH_VEXPRESS_DCSCB This is needed to provide CPU and cluster power management on RTSM implementing big.LITTLE. +config ARCH_VEXPRESS_SPC + bool "Versatile Express Serial Power Controller (SPC)" + select ARCH_HAS_CPUFREQ + select ARCH_HAS_OPP + select PM_OPP + help + The TC2 (A15x2 A7x3) versatile express core tile integrates a logic + block called Serial Power Controller (SPC) that provides the interface + between the dual cluster test-chip and the M3 microcontroller that + carries out power management. + config ARCH_VEXPRESS_TC2_PM bool "Versatile Express TC2 power management" depends on MCPM select ARM_CCI + select ARCH_VEXPRESS_SPC help Support for CPU and cluster power management on Versatile Express with a TC2 (A15x2 A7x3) big.LITTLE core tile. diff --git a/arch/arm/mach-vexpress/Makefile b/arch/arm/mach-vexpress/Makefile index 505e64ab3eae..0997e0b7494c 100644 --- a/arch/arm/mach-vexpress/Makefile +++ b/arch/arm/mach-vexpress/Makefile @@ -8,7 +8,8 @@ obj-y := v2m.o obj-$(CONFIG_ARCH_VEXPRESS_CA9X4) += ct-ca9x4.o obj-$(CONFIG_ARCH_VEXPRESS_DCSCB) += dcscb.o dcscb_setup.o CFLAGS_dcscb.o += -march=armv7-a -obj-$(CONFIG_ARCH_VEXPRESS_TC2_PM) += tc2_pm.o spc.o +obj-$(CONFIG_ARCH_VEXPRESS_SPC) += spc.o +obj-$(CONFIG_ARCH_VEXPRESS_TC2_PM) += tc2_pm.o CFLAGS_tc2_pm.o += -march=armv7-a obj-$(CONFIG_SMP) += platsmp.o obj-$(CONFIG_HOTPLUG_CPU) += hotplug.o diff --git a/arch/arm/mach-vexpress/spc.c b/arch/arm/mach-vexpress/spc.c index eefb029197ca..033d34dcbd3f 100644 --- a/arch/arm/mach-vexpress/spc.c +++ b/arch/arm/mach-vexpress/spc.c @@ -17,14 +17,31 @@ * GNU General Public License for more details. */ +#include <linux/clk-provider.h> +#include <linux/clkdev.h> +#include <linux/cpu.h> +#include <linux/delay.h> #include <linux/err.h> +#include <linux/interrupt.h> #include <linux/io.h> +#include <linux/platform_device.h> +#include <linux/pm_opp.h> #include <linux/slab.h> +#include <linux/semaphore.h> #include <asm/cacheflush.h> #define SPCLOG "vexpress-spc: " +#define PERF_LVL_A15 0x00 +#define PERF_REQ_A15 0x04 +#define PERF_LVL_A7 0x08 +#define PERF_REQ_A7 0x0c +#define COMMS 0x10 +#define COMMS_REQ 0x14 +#define PWC_STATUS 0x18 +#define PWC_FLAG 0x1c + /* SPC wake-up IRQs status and mask */ #define WAKE_INT_MASK 0x24 #define WAKE_INT_RAW 0x28 @@ -36,12 +53,45 @@ #define A15_BX_ADDR0 0x68 #define A7_BX_ADDR0 0x78 +/* SPC system config interface registers */ +#define SYSCFG_WDATA 0x70 +#define SYSCFG_RDATA 0x74 + +/* A15/A7 OPP virtual register base */ +#define A15_PERFVAL_BASE 0xC10 +#define A7_PERFVAL_BASE 0xC30 + +/* Config interface control bits */ +#define SYSCFG_START (1 << 31) +#define SYSCFG_SCC (6 << 20) +#define SYSCFG_STAT (14 << 20) + /* wake-up interrupt masks */ #define GBL_WAKEUP_INT_MSK (0x3 << 10) /* TC2 static dual-cluster configuration */ #define MAX_CLUSTERS 2 +/* + * Even though the SPC takes max 3-5 ms to complete any OPP/COMMS + * operation, the operation could start just before jiffie is about + * to be incremented. So setting timeout value of 20ms = 2jiffies@100Hz + */ +#define TIMEOUT_US 20000 + +#define MAX_OPPS 8 +#define CA15_DVFS 0 +#define CA7_DVFS 1 +#define SPC_SYS_CFG 2 +#define STAT_COMPLETE(type) ((1 << 0) << (type << 2)) +#define STAT_ERR(type) ((1 << 1) << (type << 2)) +#define RESPONSE_MASK(type) (STAT_COMPLETE(type) | STAT_ERR(type)) + +struct ve_spc_opp { + unsigned long freq; + unsigned long u_volt; +}; + struct ve_spc_drvdata { void __iomem *baseaddr; /* @@ -49,6 +99,12 @@ struct ve_spc_drvdata { * It corresponds to A15 processors MPIDR[15:8] bitfield */ u32 a15_clusid; + uint32_t cur_rsp_mask; + uint32_t cur_rsp_stat; + struct semaphore sem; + struct completion done; + struct ve_spc_opp *opps[MAX_CLUSTERS]; + int num_opps[MAX_CLUSTERS]; }; static struct ve_spc_drvdata *info; @@ -157,8 +213,197 @@ void ve_spc_powerdown(u32 cluster, bool enable) writel_relaxed(enable, info->baseaddr + pwdrn_reg); } -int __init ve_spc_init(void __iomem *baseaddr, u32 a15_clusid) +static int ve_spc_get_performance(int cluster, u32 *freq) +{ + struct ve_spc_opp *opps = info->opps[cluster]; + u32 perf_cfg_reg = 0; + u32 perf; + + perf_cfg_reg = cluster_is_a15(cluster) ? PERF_LVL_A15 : PERF_LVL_A7; + + perf = readl_relaxed(info->baseaddr + perf_cfg_reg); + if (perf >= info->num_opps[cluster]) + return -EINVAL; + + opps += perf; + *freq = opps->freq; + + return 0; +} + +/* find closest match to given frequency in OPP table */ +static int ve_spc_round_performance(int cluster, u32 freq) +{ + int idx, max_opp = info->num_opps[cluster]; + struct ve_spc_opp *opps = info->opps[cluster]; + u32 fmin = 0, fmax = ~0, ftmp; + + freq /= 1000; /* OPP entries in kHz */ + for (idx = 0; idx < max_opp; idx++, opps++) { + ftmp = opps->freq; + if (ftmp >= freq) { + if (ftmp <= fmax) + fmax = ftmp; + } else { + if (ftmp >= fmin) + fmin = ftmp; + } + } + if (fmax != ~0) + return fmax * 1000; + else + return fmin * 1000; +} + +static int ve_spc_find_performance_index(int cluster, u32 freq) +{ + int idx, max_opp = info->num_opps[cluster]; + struct ve_spc_opp *opps = info->opps[cluster]; + + for (idx = 0; idx < max_opp; idx++, opps++) + if (opps->freq == freq) + break; + return (idx == max_opp) ? -EINVAL : idx; +} + +static int ve_spc_waitforcompletion(int req_type) +{ + int ret = wait_for_completion_interruptible_timeout( + &info->done, usecs_to_jiffies(TIMEOUT_US)); + if (ret == 0) + ret = -ETIMEDOUT; + else if (ret > 0) + ret = info->cur_rsp_stat & STAT_COMPLETE(req_type) ? 0 : -EIO; + return ret; +} + +static int ve_spc_set_performance(int cluster, u32 freq) +{ + u32 perf_cfg_reg, perf_stat_reg; + int ret, perf, req_type; + + if (cluster_is_a15(cluster)) { + req_type = CA15_DVFS; + perf_cfg_reg = PERF_LVL_A15; + perf_stat_reg = PERF_REQ_A15; + } else { + req_type = CA7_DVFS; + perf_cfg_reg = PERF_LVL_A7; + perf_stat_reg = PERF_REQ_A7; + } + + perf = ve_spc_find_performance_index(cluster, freq); + + if (perf < 0) + return perf; + + if (down_timeout(&info->sem, usecs_to_jiffies(TIMEOUT_US))) + return -ETIME; + + init_completion(&info->done); + info->cur_rsp_mask = RESPONSE_MASK(req_type); + + writel(perf, info->baseaddr + perf_cfg_reg); + ret = ve_spc_waitforcompletion(req_type); + + info->cur_rsp_mask = 0; + up(&info->sem); + + return ret; +} + +static int ve_spc_read_sys_cfg(int func, int offset, uint32_t *data) +{ + int ret; + + if (down_timeout(&info->sem, usecs_to_jiffies(TIMEOUT_US))) + return -ETIME; + + init_completion(&info->done); + info->cur_rsp_mask = RESPONSE_MASK(SPC_SYS_CFG); + + /* Set the control value */ + writel(SYSCFG_START | func | offset >> 2, info->baseaddr + COMMS); + ret = ve_spc_waitforcompletion(SPC_SYS_CFG); + + if (ret == 0) + *data = readl(info->baseaddr + SYSCFG_RDATA); + + info->cur_rsp_mask = 0; + up(&info->sem); + + return ret; +} + +static irqreturn_t ve_spc_irq_handler(int irq, void *data) +{ + struct ve_spc_drvdata *drv_data = data; + uint32_t status = readl_relaxed(drv_data->baseaddr + PWC_STATUS); + + if (info->cur_rsp_mask & status) { + info->cur_rsp_stat = status; + complete(&drv_data->done); + } + + return IRQ_HANDLED; +} + +/* + * +--------------------------+ + * | 31 20 | 19 0 | + * +--------------------------+ + * | u_volt | freq(kHz) | + * +--------------------------+ + */ +#define MULT_FACTOR 20 +#define VOLT_SHIFT 20 +#define FREQ_MASK (0xFFFFF) +static int ve_spc_populate_opps(uint32_t cluster) { + uint32_t data = 0, off, ret, idx; + struct ve_spc_opp *opps; + + opps = kzalloc(sizeof(*opps) * MAX_OPPS, GFP_KERNEL); + if (!opps) + return -ENOMEM; + + info->opps[cluster] = opps; + + off = cluster_is_a15(cluster) ? A15_PERFVAL_BASE : A7_PERFVAL_BASE; + for (idx = 0; idx < MAX_OPPS; idx++, off += 4, opps++) { + ret = ve_spc_read_sys_cfg(SYSCFG_SCC, off, &data); + if (!ret) { + opps->freq = (data & FREQ_MASK) * MULT_FACTOR; + opps->u_volt = data >> VOLT_SHIFT; + } else { + break; + } + } + info->num_opps[cluster] = idx; + + return ret; +} + +static int ve_init_opp_table(struct device *cpu_dev) +{ + int cluster = topology_physical_package_id(cpu_dev->id); + int idx, ret = 0, max_opp = info->num_opps[cluster]; + struct ve_spc_opp *opps = info->opps[cluster]; + + for (idx = 0; idx < max_opp; idx++, opps++) { + ret = dev_pm_opp_add(cpu_dev, opps->freq * 1000, opps->u_volt); + if (ret) { + dev_warn(cpu_dev, "failed to add opp %lu %lu\n", + opps->freq, opps->u_volt); + return ret; + } + } + return ret; +} + +int __init ve_spc_init(void __iomem *baseaddr, u32 a15_clusid, int irq) +{ + int ret; info = kzalloc(sizeof(*info), GFP_KERNEL); if (!info) { pr_err(SPCLOG "unable to allocate mem\n"); @@ -168,6 +413,25 @@ int __init ve_spc_init(void __iomem *baseaddr, u32 a15_clusid) info->baseaddr = baseaddr; info->a15_clusid = a15_clusid; + if (irq <= 0) { + pr_err(SPCLOG "Invalid IRQ %d\n", irq); + kfree(info); + return -EINVAL; + } + + init_completion(&info->done); + + readl_relaxed(info->baseaddr + PWC_STATUS); + + ret = request_irq(irq, ve_spc_irq_handler, IRQF_TRIGGER_HIGH + | IRQF_ONESHOT, "vexpress-spc", info); + if (ret) { + pr_err(SPCLOG "IRQ %d request failed\n", irq); + kfree(info); + return -ENODEV; + } + + sema_init(&info->sem, 1); /* * Multi-cluster systems may need this data when non-coherent, during * cluster power-up/power-down. Make sure driver info reaches main @@ -178,3 +442,103 @@ int __init ve_spc_init(void __iomem *baseaddr, u32 a15_clusid) return 0; } + +struct clk_spc { + struct clk_hw hw; + int cluster; +}; + +#define to_clk_spc(spc) container_of(spc, struct clk_spc, hw) +static unsigned long spc_recalc_rate(struct clk_hw *hw, + unsigned long parent_rate) +{ + struct clk_spc *spc = to_clk_spc(hw); + u32 freq; + + if (ve_spc_get_performance(spc->cluster, &freq)) + return -EIO; + + return freq * 1000; +} + +static long spc_round_rate(struct clk_hw *hw, unsigned long drate, + unsigned long *parent_rate) +{ + struct clk_spc *spc = to_clk_spc(hw); + + return ve_spc_round_performance(spc->cluster, drate); +} + +static int spc_set_rate(struct clk_hw *hw, unsigned long rate, + unsigned long parent_rate) +{ + struct clk_spc *spc = to_clk_spc(hw); + + return ve_spc_set_performance(spc->cluster, rate / 1000); +} + +static struct clk_ops clk_spc_ops = { + .recalc_rate = spc_recalc_rate, + .round_rate = spc_round_rate, + .set_rate = spc_set_rate, +}; + +static struct clk *ve_spc_clk_register(struct device *cpu_dev) +{ + struct clk_init_data init; + struct clk_spc *spc; + + spc = kzalloc(sizeof(*spc), GFP_KERNEL); + if (!spc) { + pr_err("could not allocate spc clk\n"); + return ERR_PTR(-ENOMEM); + } + + spc->hw.init = &init; + spc->cluster = topology_physical_package_id(cpu_dev->id); + + init.name = dev_name(cpu_dev); + init.ops = &clk_spc_ops; + init.flags = CLK_IS_ROOT | CLK_GET_RATE_NOCACHE; + init.num_parents = 0; + + return devm_clk_register(cpu_dev, &spc->hw); +} + +static int __init ve_spc_clk_init(void) +{ + int cpu; + struct clk *clk; + + if (!info) + return 0; /* Continue only if SPC is initialised */ + + if (ve_spc_populate_opps(0) || ve_spc_populate_opps(1)) { + pr_err("failed to build OPP table\n"); + return -ENODEV; + } + + for_each_possible_cpu(cpu) { + struct device *cpu_dev = get_cpu_device(cpu); + if (!cpu_dev) { + pr_warn("failed to get cpu%d device\n", cpu); + continue; + } + clk = ve_spc_clk_register(cpu_dev); + if (IS_ERR(clk)) { + pr_warn("failed to register cpu%d clock\n", cpu); + continue; + } + if (clk_register_clkdev(clk, NULL, dev_name(cpu_dev))) { + pr_warn("failed to register cpu%d clock lookup\n", cpu); + continue; + } + + if (ve_init_opp_table(cpu_dev)) + pr_warn("failed to initialise cpu%d opp table\n", cpu); + } + + platform_device_register_simple("vexpress-spc-cpufreq", -1, NULL, 0); + return 0; +} +module_init(ve_spc_clk_init); diff --git a/arch/arm/mach-vexpress/spc.h b/arch/arm/mach-vexpress/spc.h index 5f7e4a446a17..dbd44c3720f9 100644 --- a/arch/arm/mach-vexpress/spc.h +++ b/arch/arm/mach-vexpress/spc.h @@ -15,7 +15,7 @@ #ifndef __SPC_H_ #define __SPC_H_ -int __init ve_spc_init(void __iomem *base, u32 a15_clusid); +int __init ve_spc_init(void __iomem *base, u32 a15_clusid, int irq); void ve_spc_global_wakeup_irq(bool set); void ve_spc_cpu_wakeup_irq(u32 cluster, u32 cpu, bool set); void ve_spc_set_resume_addr(u32 cluster, u32 cpu, u32 addr); diff --git a/arch/arm/mach-vexpress/tc2_pm.c b/arch/arm/mach-vexpress/tc2_pm.c index 4eb92ebfd953..05a364c5077a 100644 --- a/arch/arm/mach-vexpress/tc2_pm.c +++ b/arch/arm/mach-vexpress/tc2_pm.c @@ -16,6 +16,7 @@ #include <linux/io.h> #include <linux/kernel.h> #include <linux/of_address.h> +#include <linux/of_irq.h> #include <linux/spinlock.h> #include <linux/errno.h> #include <linux/irqchip/arm-gic.h> @@ -267,7 +268,7 @@ static void __naked tc2_pm_power_up_setup(unsigned int affinity_level) static int __init tc2_pm_init(void) { - int ret; + int ret, irq; void __iomem *scc; u32 a15_cluster_id, a7_cluster_id, sys_info; struct device_node *np; @@ -292,13 +293,15 @@ static int __init tc2_pm_init(void) tc2_nr_cpus[a15_cluster_id] = (sys_info >> 16) & 0xf; tc2_nr_cpus[a7_cluster_id] = (sys_info >> 20) & 0xf; + irq = irq_of_parse_and_map(np, 0); + /* * A subset of the SCC registers is also used to communicate * with the SPC (power controller). We need to be able to * drive it very early in the boot process to power up * processors, so we initialize the SPC driver here. */ - ret = ve_spc_init(scc + SPC_BASE, a15_cluster_id); + ret = ve_spc_init(scc + SPC_BASE, a15_cluster_id, irq); if (ret) return ret; diff --git a/arch/arm/mach-zynq/common.c b/arch/arm/mach-zynq/common.c index 5f252569c689..9a7bd137c8fd 100644 --- a/arch/arm/mach-zynq/common.c +++ b/arch/arm/mach-zynq/common.c @@ -44,6 +44,10 @@ static struct of_device_id zynq_of_bus_ids[] __initdata = { {} }; +static struct platform_device zynq_cpuidle_device = { + .name = "cpuidle-zynq", +}; + /** * zynq_init_machine - System specific initialization, intended to be * called from board specific initialization. @@ -56,6 +60,8 @@ static void __init zynq_init_machine(void) l2x0_of_init(0x02060000, 0xF0F0FFFF); of_platform_bus_probe(NULL, zynq_of_bus_ids, NULL); + + platform_device_register(&zynq_cpuidle_device); } static void __init zynq_timer_init(void) diff --git a/arch/arm/mm/fault-armv.c b/arch/arm/mm/fault-armv.c index 2a5907b5c8d2..ff379ac115df 100644 --- a/arch/arm/mm/fault-armv.c +++ b/arch/arm/mm/fault-armv.c @@ -65,7 +65,7 @@ static int do_adjust_pte(struct vm_area_struct *vma, unsigned long address, return ret; } -#if USE_SPLIT_PTLOCKS +#if USE_SPLIT_PTE_PTLOCKS /* * If we are using split PTE locks, then we need to take the page * lock here. Otherwise we are using shared mm->page_table_lock @@ -84,10 +84,10 @@ static inline void do_pte_unlock(spinlock_t *ptl) { spin_unlock(ptl); } -#else /* !USE_SPLIT_PTLOCKS */ +#else /* !USE_SPLIT_PTE_PTLOCKS */ static inline void do_pte_lock(spinlock_t *ptl) {} static inline void do_pte_unlock(spinlock_t *ptl) {} -#endif /* USE_SPLIT_PTLOCKS */ +#endif /* USE_SPLIT_PTE_PTLOCKS */ static int adjust_pte(struct vm_area_struct *vma, unsigned long address, unsigned long pfn) diff --git a/arch/arm/plat-samsung/dev-backlight.c b/arch/arm/plat-samsung/dev-backlight.c index d51f9565567c..be4ad0b21c08 100644 --- a/arch/arm/plat-samsung/dev-backlight.c +++ b/arch/arm/plat-samsung/dev-backlight.c @@ -70,6 +70,7 @@ static struct samsung_bl_drvdata samsung_dfl_bl_data __initdata = { .max_brightness = 255, .dft_brightness = 255, .pwm_period_ns = 78770, + .enable_gpio = -1, .init = samsung_bl_init, .exit = samsung_bl_exit, }, @@ -121,6 +122,10 @@ void __init samsung_bl_set(struct samsung_bl_gpio_info *gpio_info, samsung_bl_data->lth_brightness = bl_data->lth_brightness; if (bl_data->pwm_period_ns) samsung_bl_data->pwm_period_ns = bl_data->pwm_period_ns; + if (bl_data->enable_gpio >= 0) + samsung_bl_data->enable_gpio = bl_data->enable_gpio; + if (bl_data->enable_gpio_flags) + samsung_bl_data->enable_gpio_flags = bl_data->enable_gpio_flags; if (bl_data->init) samsung_bl_data->init = bl_data->init; if (bl_data->notify) diff --git a/arch/arm/xen/Makefile b/arch/arm/xen/Makefile index 43841033afd3..12969523414c 100644 --- a/arch/arm/xen/Makefile +++ b/arch/arm/xen/Makefile @@ -1 +1 @@ -obj-y := enlighten.o hypercall.o grant-table.o +obj-y := enlighten.o hypercall.o grant-table.o p2m.o mm.o diff --git a/arch/arm/xen/mm.c b/arch/arm/xen/mm.c new file mode 100644 index 000000000000..b0e77de99148 --- /dev/null +++ b/arch/arm/xen/mm.c @@ -0,0 +1,65 @@ +#include <linux/bootmem.h> +#include <linux/gfp.h> +#include <linux/export.h> +#include <linux/slab.h> +#include <linux/types.h> +#include <linux/dma-mapping.h> +#include <linux/vmalloc.h> +#include <linux/swiotlb.h> + +#include <xen/xen.h> +#include <xen/interface/memory.h> +#include <xen/swiotlb-xen.h> + +#include <asm/cacheflush.h> +#include <asm/xen/page.h> +#include <asm/xen/hypercall.h> +#include <asm/xen/interface.h> + +int xen_create_contiguous_region(phys_addr_t pstart, unsigned int order, + unsigned int address_bits, + dma_addr_t *dma_handle) +{ + if (!xen_initial_domain()) + return -EINVAL; + + /* we assume that dom0 is mapped 1:1 for now */ + *dma_handle = pstart; + return 0; +} +EXPORT_SYMBOL_GPL(xen_create_contiguous_region); + +void xen_destroy_contiguous_region(phys_addr_t pstart, unsigned int order) +{ + return; +} +EXPORT_SYMBOL_GPL(xen_destroy_contiguous_region); + +struct dma_map_ops *xen_dma_ops; +EXPORT_SYMBOL_GPL(xen_dma_ops); + +static struct dma_map_ops xen_swiotlb_dma_ops = { + .mapping_error = xen_swiotlb_dma_mapping_error, + .alloc = xen_swiotlb_alloc_coherent, + .free = xen_swiotlb_free_coherent, + .sync_single_for_cpu = xen_swiotlb_sync_single_for_cpu, + .sync_single_for_device = xen_swiotlb_sync_single_for_device, + .sync_sg_for_cpu = xen_swiotlb_sync_sg_for_cpu, + .sync_sg_for_device = xen_swiotlb_sync_sg_for_device, + .map_sg = xen_swiotlb_map_sg_attrs, + .unmap_sg = xen_swiotlb_unmap_sg_attrs, + .map_page = xen_swiotlb_map_page, + .unmap_page = xen_swiotlb_unmap_page, + .dma_supported = xen_swiotlb_dma_supported, + .set_dma_mask = xen_swiotlb_set_dma_mask, +}; + +int __init xen_mm_init(void) +{ + if (!xen_initial_domain()) + return 0; + xen_swiotlb_init(1, false); + xen_dma_ops = &xen_swiotlb_dma_ops; + return 0; +} +arch_initcall(xen_mm_init); diff --git a/arch/arm/xen/p2m.c b/arch/arm/xen/p2m.c new file mode 100644 index 000000000000..23732cdff551 --- /dev/null +++ b/arch/arm/xen/p2m.c @@ -0,0 +1,208 @@ +#include <linux/bootmem.h> +#include <linux/gfp.h> +#include <linux/export.h> +#include <linux/rwlock.h> +#include <linux/slab.h> +#include <linux/types.h> +#include <linux/dma-mapping.h> +#include <linux/vmalloc.h> +#include <linux/swiotlb.h> + +#include <xen/xen.h> +#include <xen/interface/memory.h> +#include <xen/swiotlb-xen.h> + +#include <asm/cacheflush.h> +#include <asm/xen/page.h> +#include <asm/xen/hypercall.h> +#include <asm/xen/interface.h> + +struct xen_p2m_entry { + unsigned long pfn; + unsigned long mfn; + unsigned long nr_pages; + struct rb_node rbnode_mach; + struct rb_node rbnode_phys; +}; + +rwlock_t p2m_lock; +struct rb_root phys_to_mach = RB_ROOT; +static struct rb_root mach_to_phys = RB_ROOT; + +static int xen_add_phys_to_mach_entry(struct xen_p2m_entry *new) +{ + struct rb_node **link = &phys_to_mach.rb_node; + struct rb_node *parent = NULL; + struct xen_p2m_entry *entry; + int rc = 0; + + while (*link) { + parent = *link; + entry = rb_entry(parent, struct xen_p2m_entry, rbnode_phys); + + if (new->mfn == entry->mfn) + goto err_out; + if (new->pfn == entry->pfn) + goto err_out; + + if (new->pfn < entry->pfn) + link = &(*link)->rb_left; + else + link = &(*link)->rb_right; + } + rb_link_node(&new->rbnode_phys, parent, link); + rb_insert_color(&new->rbnode_phys, &phys_to_mach); + goto out; + +err_out: + rc = -EINVAL; + pr_warn("%s: cannot add pfn=%pa -> mfn=%pa: pfn=%pa -> mfn=%pa already exists\n", + __func__, &new->pfn, &new->mfn, &entry->pfn, &entry->mfn); +out: + return rc; +} + +unsigned long __pfn_to_mfn(unsigned long pfn) +{ + struct rb_node *n = phys_to_mach.rb_node; + struct xen_p2m_entry *entry; + unsigned long irqflags; + + read_lock_irqsave(&p2m_lock, irqflags); + while (n) { + entry = rb_entry(n, struct xen_p2m_entry, rbnode_phys); + if (entry->pfn <= pfn && + entry->pfn + entry->nr_pages > pfn) { + read_unlock_irqrestore(&p2m_lock, irqflags); + return entry->mfn + (pfn - entry->pfn); + } + if (pfn < entry->pfn) + n = n->rb_left; + else + n = n->rb_right; + } + read_unlock_irqrestore(&p2m_lock, irqflags); + + return INVALID_P2M_ENTRY; +} +EXPORT_SYMBOL_GPL(__pfn_to_mfn); + +static int xen_add_mach_to_phys_entry(struct xen_p2m_entry *new) +{ + struct rb_node **link = &mach_to_phys.rb_node; + struct rb_node *parent = NULL; + struct xen_p2m_entry *entry; + int rc = 0; + + while (*link) { + parent = *link; + entry = rb_entry(parent, struct xen_p2m_entry, rbnode_mach); + + if (new->mfn == entry->mfn) + goto err_out; + if (new->pfn == entry->pfn) + goto err_out; + + if (new->mfn < entry->mfn) + link = &(*link)->rb_left; + else + link = &(*link)->rb_right; + } + rb_link_node(&new->rbnode_mach, parent, link); + rb_insert_color(&new->rbnode_mach, &mach_to_phys); + goto out; + +err_out: + rc = -EINVAL; + pr_warn("%s: cannot add pfn=%pa -> mfn=%pa: pfn=%pa -> mfn=%pa already exists\n", + __func__, &new->pfn, &new->mfn, &entry->pfn, &entry->mfn); +out: + return rc; +} + +unsigned long __mfn_to_pfn(unsigned long mfn) +{ + struct rb_node *n = mach_to_phys.rb_node; + struct xen_p2m_entry *entry; + unsigned long irqflags; + + read_lock_irqsave(&p2m_lock, irqflags); + while (n) { + entry = rb_entry(n, struct xen_p2m_entry, rbnode_mach); + if (entry->mfn <= mfn && + entry->mfn + entry->nr_pages > mfn) { + read_unlock_irqrestore(&p2m_lock, irqflags); + return entry->pfn + (mfn - entry->mfn); + } + if (mfn < entry->mfn) + n = n->rb_left; + else + n = n->rb_right; + } + read_unlock_irqrestore(&p2m_lock, irqflags); + + return INVALID_P2M_ENTRY; +} +EXPORT_SYMBOL_GPL(__mfn_to_pfn); + +bool __set_phys_to_machine_multi(unsigned long pfn, + unsigned long mfn, unsigned long nr_pages) +{ + int rc; + unsigned long irqflags; + struct xen_p2m_entry *p2m_entry; + struct rb_node *n = phys_to_mach.rb_node; + + if (mfn == INVALID_P2M_ENTRY) { + write_lock_irqsave(&p2m_lock, irqflags); + while (n) { + p2m_entry = rb_entry(n, struct xen_p2m_entry, rbnode_phys); + if (p2m_entry->pfn <= pfn && + p2m_entry->pfn + p2m_entry->nr_pages > pfn) { + rb_erase(&p2m_entry->rbnode_mach, &mach_to_phys); + rb_erase(&p2m_entry->rbnode_phys, &phys_to_mach); + write_unlock_irqrestore(&p2m_lock, irqflags); + kfree(p2m_entry); + return true; + } + if (pfn < p2m_entry->pfn) + n = n->rb_left; + else + n = n->rb_right; + } + write_unlock_irqrestore(&p2m_lock, irqflags); + return true; + } + + p2m_entry = kzalloc(sizeof(struct xen_p2m_entry), GFP_NOWAIT); + if (!p2m_entry) { + pr_warn("cannot allocate xen_p2m_entry\n"); + return false; + } + p2m_entry->pfn = pfn; + p2m_entry->nr_pages = nr_pages; + p2m_entry->mfn = mfn; + + write_lock_irqsave(&p2m_lock, irqflags); + if ((rc = xen_add_phys_to_mach_entry(p2m_entry) < 0) || + (rc = xen_add_mach_to_phys_entry(p2m_entry) < 0)) { + write_unlock_irqrestore(&p2m_lock, irqflags); + return false; + } + write_unlock_irqrestore(&p2m_lock, irqflags); + return true; +} +EXPORT_SYMBOL_GPL(__set_phys_to_machine_multi); + +bool __set_phys_to_machine(unsigned long pfn, unsigned long mfn) +{ + return __set_phys_to_machine_multi(pfn, mfn, 1); +} +EXPORT_SYMBOL_GPL(__set_phys_to_machine); + +int p2m_init(void) +{ + rwlock_init(&p2m_lock); + return 0; +} +arch_initcall(p2m_init); diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig index bb0bf1bfc05d..88c8b6c1341a 100644 --- a/arch/arm64/Kconfig +++ b/arch/arm64/Kconfig @@ -143,7 +143,6 @@ config CPU_BIG_ENDIAN config SMP bool "Symmetric Multi-Processing" - select USE_GENERIC_SMP_HELPERS help This enables support for systems with more than one CPU. If you say N here, the kernel will run on single and @@ -221,6 +220,7 @@ config XEN_DOM0 config XEN bool "Xen guest support on ARM64 (EXPERIMENTAL)" depends on ARM64 && OF + select SWIOTLB_XEN help Say Y if you want to run Linux in a Virtual Machine on Xen on ARM64. diff --git a/arch/arm64/include/asm/dma-mapping.h b/arch/arm64/include/asm/dma-mapping.h index 8d1810001aef..fd0c0c0e447a 100644 --- a/arch/arm64/include/asm/dma-mapping.h +++ b/arch/arm64/include/asm/dma-mapping.h @@ -23,11 +23,15 @@ #include <asm-generic/dma-coherent.h> +#include <xen/xen.h> +#include <asm/xen/hypervisor.h> + #define ARCH_HAS_DMA_GET_REQUIRED_MASK +#define DMA_ERROR_CODE (~(dma_addr_t)0) extern struct dma_map_ops *dma_ops; -static inline struct dma_map_ops *get_dma_ops(struct device *dev) +static inline struct dma_map_ops *__generic_dma_ops(struct device *dev) { if (unlikely(!dev) || !dev->archdata.dma_ops) return dma_ops; @@ -35,6 +39,14 @@ static inline struct dma_map_ops *get_dma_ops(struct device *dev) return dev->archdata.dma_ops; } +static inline struct dma_map_ops *get_dma_ops(struct device *dev) +{ + if (xen_initial_domain()) + return xen_dma_ops; + else + return __generic_dma_ops(dev); +} + #include <asm-generic/dma-mapping-common.h> static inline dma_addr_t phys_to_dma(struct device *dev, phys_addr_t paddr) diff --git a/arch/arm64/include/asm/io.h b/arch/arm64/include/asm/io.h index b56e5b5df881..4cc813eddacb 100644 --- a/arch/arm64/include/asm/io.h +++ b/arch/arm64/include/asm/io.h @@ -22,11 +22,14 @@ #ifdef __KERNEL__ #include <linux/types.h> +#include <linux/blk_types.h> #include <asm/byteorder.h> #include <asm/barrier.h> #include <asm/pgtable.h> +#include <xen/xen.h> + /* * Generic IO read/write. These perform native-endian accesses. */ @@ -263,5 +266,12 @@ extern int devmem_is_allowed(unsigned long pfn); */ #define xlate_dev_kmem_ptr(p) p +struct bio_vec; +extern bool xen_biovec_phys_mergeable(const struct bio_vec *vec1, + const struct bio_vec *vec2); +#define BIOVEC_PHYS_MERGEABLE(vec1, vec2) \ + (__BIOVEC_PHYS_MERGEABLE(vec1, vec2) && \ + (!xen_domain() || xen_biovec_phys_mergeable(vec1, vec2))) + #endif /* __KERNEL__ */ #endif /* __ASM_IO_H */ diff --git a/arch/arm64/include/asm/kvm_arm.h b/arch/arm64/include/asm/kvm_arm.h index a5f28e2720c7..c98ef4771c73 100644 --- a/arch/arm64/include/asm/kvm_arm.h +++ b/arch/arm64/include/asm/kvm_arm.h @@ -63,6 +63,7 @@ * TAC: Trap ACTLR * TSC: Trap SMC * TSW: Trap cache operations by set/way + * TWE: Trap WFE * TWI: Trap WFI * TIDCP: Trap L2CTLR/L2ECTLR * BSU_IS: Upgrade barriers to the inner shareable domain @@ -72,8 +73,9 @@ * FMO: Override CPSR.F and enable signaling with VF * SWIO: Turn set/way invalidates into set/way clean+invalidate */ -#define HCR_GUEST_FLAGS (HCR_TSC | HCR_TSW | HCR_TWI | HCR_VM | HCR_BSU_IS | \ - HCR_FB | HCR_TAC | HCR_AMO | HCR_IMO | HCR_FMO | \ +#define HCR_GUEST_FLAGS (HCR_TSC | HCR_TSW | HCR_TWE | HCR_TWI | HCR_VM | \ + HCR_BSU_IS | HCR_FB | HCR_TAC | \ + HCR_AMO | HCR_IMO | HCR_FMO | \ HCR_SWIO | HCR_TIDCP | HCR_RW) #define HCR_VIRT_EXCP_MASK (HCR_VA | HCR_VI | HCR_VF) @@ -242,4 +244,6 @@ #define ESR_EL2_EC_xABT_xFSR_EXTABT 0x10 +#define ESR_EL2_EC_WFI_ISS_WFE (1 << 0) + #endif /* __ARM64_KVM_ARM_H__ */ diff --git a/arch/arm64/include/asm/kvm_emulate.h b/arch/arm64/include/asm/kvm_emulate.h index eec073875218..dd8ecfc3f995 100644 --- a/arch/arm64/include/asm/kvm_emulate.h +++ b/arch/arm64/include/asm/kvm_emulate.h @@ -177,4 +177,65 @@ static inline u8 kvm_vcpu_trap_get_fault(const struct kvm_vcpu *vcpu) return kvm_vcpu_get_hsr(vcpu) & ESR_EL2_FSC_TYPE; } +static inline unsigned long kvm_vcpu_get_mpidr(struct kvm_vcpu *vcpu) +{ + return vcpu_sys_reg(vcpu, MPIDR_EL1); +} + +static inline void kvm_vcpu_set_be(struct kvm_vcpu *vcpu) +{ + if (vcpu_mode_is_32bit(vcpu)) + *vcpu_cpsr(vcpu) |= COMPAT_PSR_E_BIT; + else + vcpu_sys_reg(vcpu, SCTLR_EL1) |= (1 << 25); +} + +static inline bool kvm_vcpu_is_be(struct kvm_vcpu *vcpu) +{ + if (vcpu_mode_is_32bit(vcpu)) + return !!(*vcpu_cpsr(vcpu) & COMPAT_PSR_E_BIT); + + return !!(vcpu_sys_reg(vcpu, SCTLR_EL1) & (1 << 25)); +} + +static inline unsigned long vcpu_data_guest_to_host(struct kvm_vcpu *vcpu, + unsigned long data, + unsigned int len) +{ + if (kvm_vcpu_is_be(vcpu)) { + switch (len) { + case 1: + return data & 0xff; + case 2: + return be16_to_cpu(data & 0xffff); + case 4: + return be32_to_cpu(data & 0xffffffff); + default: + return be64_to_cpu(data); + } + } + + return data; /* Leave LE untouched */ +} + +static inline unsigned long vcpu_data_host_to_guest(struct kvm_vcpu *vcpu, + unsigned long data, + unsigned int len) +{ + if (kvm_vcpu_is_be(vcpu)) { + switch (len) { + case 1: + return data & 0xff; + case 2: + return cpu_to_be16(data & 0xffff); + case 4: + return cpu_to_be32(data & 0xffffffff); + default: + return cpu_to_be64(data); + } + } + + return data; /* Leave LE untouched */ +} + #endif /* __ARM64_KVM_EMULATE_H__ */ diff --git a/arch/arm64/include/asm/kvm_host.h b/arch/arm64/include/asm/kvm_host.h index 0859a4ddd1e7..5d85a02d1231 100644 --- a/arch/arm64/include/asm/kvm_host.h +++ b/arch/arm64/include/asm/kvm_host.h @@ -36,11 +36,6 @@ #define KVM_VCPU_MAX_FEATURES 2 -/* We don't currently support large pages. */ -#define KVM_HPAGE_GFN_SHIFT(x) 0 -#define KVM_NR_PAGE_SIZES 1 -#define KVM_PAGES_PER_HPAGE(x) (1UL<<31) - struct kvm_vcpu; int kvm_target_cpu(void); int kvm_reset_vcpu(struct kvm_vcpu *vcpu); @@ -151,6 +146,7 @@ struct kvm_vcpu_stat { struct kvm_vcpu_init; int kvm_vcpu_set_target(struct kvm_vcpu *vcpu, const struct kvm_vcpu_init *init); +int kvm_vcpu_preferred_target(struct kvm_vcpu_init *init); unsigned long kvm_arm_num_regs(struct kvm_vcpu *vcpu); int kvm_arm_copy_reg_indices(struct kvm_vcpu *vcpu, u64 __user *indices); struct kvm_one_reg; diff --git a/arch/arm64/include/asm/kvm_mmu.h b/arch/arm64/include/asm/kvm_mmu.h index efe609c6a3c9..680f74e67497 100644 --- a/arch/arm64/include/asm/kvm_mmu.h +++ b/arch/arm64/include/asm/kvm_mmu.h @@ -91,6 +91,7 @@ int kvm_mmu_init(void); void kvm_clear_hyp_idmap(void); #define kvm_set_pte(ptep, pte) set_pte(ptep, pte) +#define kvm_set_pmd(pmdp, pmd) set_pmd(pmdp, pmd) static inline bool kvm_is_write_fault(unsigned long esr) { @@ -116,13 +117,18 @@ static inline void kvm_set_s2pte_writable(pte_t *pte) pte_val(*pte) |= PTE_S2_RDWR; } +static inline void kvm_set_s2pmd_writable(pmd_t *pmd) +{ + pmd_val(*pmd) |= PMD_S2_RDWR; +} + struct kvm; -static inline void coherent_icache_guest_page(struct kvm *kvm, gfn_t gfn) +static inline void coherent_icache_guest_page(struct kvm *kvm, hva_t hva, + unsigned long size) { if (!icache_is_aliasing()) { /* PIPT */ - unsigned long hva = gfn_to_hva(kvm, gfn); - flush_icache_range(hva, hva + PAGE_SIZE); + flush_icache_range(hva, hva + size); } else if (!icache_is_aivivt()) { /* non ASID-tagged VIVT */ /* any kind of VIPT cache */ __flush_icache_all(); diff --git a/arch/arm64/include/asm/pgalloc.h b/arch/arm64/include/asm/pgalloc.h index f214069ec5d5..9bea6e74a001 100644 --- a/arch/arm64/include/asm/pgalloc.h +++ b/arch/arm64/include/asm/pgalloc.h @@ -63,9 +63,12 @@ pte_alloc_one(struct mm_struct *mm, unsigned long addr) struct page *pte; pte = alloc_pages(PGALLOC_GFP, 0); - if (pte) - pgtable_page_ctor(pte); - + if (!pte) + return NULL; + if (!pgtable_page_ctor(pte)) { + __free_page(pte); + return NULL; + } return pte; } diff --git a/arch/arm64/include/asm/pgtable-hwdef.h b/arch/arm64/include/asm/pgtable-hwdef.h index d57e66845c86..755f86143320 100644 --- a/arch/arm64/include/asm/pgtable-hwdef.h +++ b/arch/arm64/include/asm/pgtable-hwdef.h @@ -85,6 +85,8 @@ #define PTE_S2_RDONLY (_AT(pteval_t, 1) << 6) /* HAP[2:1] */ #define PTE_S2_RDWR (_AT(pteval_t, 3) << 6) /* HAP[2:1] */ +#define PMD_S2_RDWR (_AT(pmdval_t, 3) << 6) /* HAP[2:1] */ + /* * Memory Attribute override for Stage-2 (MemAttr[3:0]) */ diff --git a/arch/arm64/include/asm/thread_info.h b/arch/arm64/include/asm/thread_info.h index 23a3c4791d86..720e70b66ffd 100644 --- a/arch/arm64/include/asm/thread_info.h +++ b/arch/arm64/include/asm/thread_info.h @@ -89,12 +89,6 @@ static inline struct thread_info *current_thread_info(void) #endif /* - * We use bit 30 of the preempt_count to indicate that kernel - * preemption is occurring. See <asm/hardirq.h>. - */ -#define PREEMPT_ACTIVE 0x40000000 - -/* * thread information flags: * TIF_SYSCALL_TRACE - syscall trace active * TIF_SIGPENDING - signal pending diff --git a/arch/arm64/include/asm/xen/page-coherent.h b/arch/arm64/include/asm/xen/page-coherent.h new file mode 100644 index 000000000000..2820f1a6eebe --- /dev/null +++ b/arch/arm64/include/asm/xen/page-coherent.h @@ -0,0 +1,47 @@ +#ifndef _ASM_ARM64_XEN_PAGE_COHERENT_H +#define _ASM_ARM64_XEN_PAGE_COHERENT_H + +#include <asm/page.h> +#include <linux/dma-attrs.h> +#include <linux/dma-mapping.h> + +static inline void *xen_alloc_coherent_pages(struct device *hwdev, size_t size, + dma_addr_t *dma_handle, gfp_t flags, + struct dma_attrs *attrs) +{ + return __generic_dma_ops(hwdev)->alloc(hwdev, size, dma_handle, flags, attrs); +} + +static inline void xen_free_coherent_pages(struct device *hwdev, size_t size, + void *cpu_addr, dma_addr_t dma_handle, + struct dma_attrs *attrs) +{ + __generic_dma_ops(hwdev)->free(hwdev, size, cpu_addr, dma_handle, attrs); +} + +static inline void xen_dma_map_page(struct device *hwdev, struct page *page, + unsigned long offset, size_t size, enum dma_data_direction dir, + struct dma_attrs *attrs) +{ + __generic_dma_ops(hwdev)->map_page(hwdev, page, offset, size, dir, attrs); +} + +static inline void xen_dma_unmap_page(struct device *hwdev, dma_addr_t handle, + size_t size, enum dma_data_direction dir, + struct dma_attrs *attrs) +{ + __generic_dma_ops(hwdev)->unmap_page(hwdev, handle, size, dir, attrs); +} + +static inline void xen_dma_sync_single_for_cpu(struct device *hwdev, + dma_addr_t handle, size_t size, enum dma_data_direction dir) +{ + __generic_dma_ops(hwdev)->sync_single_for_cpu(hwdev, handle, size, dir); +} + +static inline void xen_dma_sync_single_for_device(struct device *hwdev, + dma_addr_t handle, size_t size, enum dma_data_direction dir) +{ + __generic_dma_ops(hwdev)->sync_single_for_device(hwdev, handle, size, dir); +} +#endif /* _ASM_ARM64_XEN_PAGE_COHERENT_H */ diff --git a/arch/arm64/kvm/Kconfig b/arch/arm64/kvm/Kconfig index 21e90820bd23..4480ab339a00 100644 --- a/arch/arm64/kvm/Kconfig +++ b/arch/arm64/kvm/Kconfig @@ -21,6 +21,7 @@ config KVM select MMU_NOTIFIER select PREEMPT_NOTIFIERS select ANON_INODES + select HAVE_KVM_CPU_RELAX_INTERCEPT select KVM_MMIO select KVM_ARM_HOST select KVM_ARM_VGIC diff --git a/arch/arm64/kvm/guest.c b/arch/arm64/kvm/guest.c index 2c3ff67a8ecb..3f0731e53274 100644 --- a/arch/arm64/kvm/guest.c +++ b/arch/arm64/kvm/guest.c @@ -248,6 +248,26 @@ int kvm_vcpu_set_target(struct kvm_vcpu *vcpu, return kvm_reset_vcpu(vcpu); } +int kvm_vcpu_preferred_target(struct kvm_vcpu_init *init) +{ + int target = kvm_target_cpu(); + + if (target < 0) + return -ENODEV; + + memset(init, 0, sizeof(*init)); + + /* + * For now, we don't return any features. + * In future, we might use features to return target + * specific features available for the preferred + * target type. + */ + init->target = (__u32)target; + + return 0; +} + int kvm_arch_vcpu_ioctl_get_fpu(struct kvm_vcpu *vcpu, struct kvm_fpu *fpu) { return -EINVAL; diff --git a/arch/arm64/kvm/handle_exit.c b/arch/arm64/kvm/handle_exit.c index 9beaca033437..8da56067c304 100644 --- a/arch/arm64/kvm/handle_exit.c +++ b/arch/arm64/kvm/handle_exit.c @@ -47,21 +47,29 @@ static int handle_smc(struct kvm_vcpu *vcpu, struct kvm_run *run) } /** - * kvm_handle_wfi - handle a wait-for-interrupts instruction executed by a guest + * kvm_handle_wfx - handle a wait-for-interrupts or wait-for-event + * instruction executed by a guest + * * @vcpu: the vcpu pointer * - * Simply call kvm_vcpu_block(), which will halt execution of + * WFE: Yield the CPU and come back to this vcpu when the scheduler + * decides to. + * WFI: Simply call kvm_vcpu_block(), which will halt execution of * world-switches and schedule other host processes until there is an * incoming IRQ or FIQ to the VM. */ -static int kvm_handle_wfi(struct kvm_vcpu *vcpu, struct kvm_run *run) +static int kvm_handle_wfx(struct kvm_vcpu *vcpu, struct kvm_run *run) { - kvm_vcpu_block(vcpu); + if (kvm_vcpu_get_hsr(vcpu) & ESR_EL2_EC_WFI_ISS_WFE) + kvm_vcpu_on_spin(vcpu); + else + kvm_vcpu_block(vcpu); + return 1; } static exit_handle_fn arm_exit_handlers[] = { - [ESR_EL2_EC_WFI] = kvm_handle_wfi, + [ESR_EL2_EC_WFI] = kvm_handle_wfx, [ESR_EL2_EC_CP15_32] = kvm_handle_cp15_32, [ESR_EL2_EC_CP15_64] = kvm_handle_cp15_64, [ESR_EL2_EC_CP14_MR] = kvm_handle_cp14_access, diff --git a/arch/arm64/xen/Makefile b/arch/arm64/xen/Makefile index be240404ba96..74a8d87e542b 100644 --- a/arch/arm64/xen/Makefile +++ b/arch/arm64/xen/Makefile @@ -1,2 +1,2 @@ -xen-arm-y += $(addprefix ../../arm/xen/, enlighten.o grant-table.o) +xen-arm-y += $(addprefix ../../arm/xen/, enlighten.o grant-table.o p2m.o mm.o) obj-y := xen-arm.o hypercall.o diff --git a/arch/avr32/boards/atngw100/evklcd10x.c b/arch/avr32/boards/atngw100/evklcd10x.c index 20388750d564..64919b0da7aa 100644 --- a/arch/avr32/boards/atngw100/evklcd10x.c +++ b/arch/avr32/boards/atngw100/evklcd10x.c @@ -58,7 +58,7 @@ static struct fb_monspecs __initdata atevklcd10x_default_monspecs = { .dclkmax = 28330000, }; -static struct atmel_lcdfb_info __initdata atevklcd10x_lcdc_data = { +static struct atmel_lcdfb_pdata __initdata atevklcd10x_lcdc_data = { .default_bpp = 16, .default_dmacon = ATMEL_LCDC_DMAEN | ATMEL_LCDC_DMA2DEN, .default_lcdcon2 = (ATMEL_LCDC_DISTYPE_TFT @@ -96,7 +96,7 @@ static struct fb_monspecs __initdata atevklcd10x_default_monspecs = { .dclkmax = 7000000, }; -static struct atmel_lcdfb_info __initdata atevklcd10x_lcdc_data = { +static struct atmel_lcdfb_pdata __initdata atevklcd10x_lcdc_data = { .default_bpp = 16, .default_dmacon = ATMEL_LCDC_DMAEN | ATMEL_LCDC_DMA2DEN, .default_lcdcon2 = (ATMEL_LCDC_DISTYPE_TFT @@ -134,7 +134,7 @@ static struct fb_monspecs __initdata atevklcd10x_default_monspecs = { .dclkmax = 6400000, }; -static struct atmel_lcdfb_info __initdata atevklcd10x_lcdc_data = { +static struct atmel_lcdfb_pdata __initdata atevklcd10x_lcdc_data = { .default_bpp = 16, .default_dmacon = ATMEL_LCDC_DMAEN | ATMEL_LCDC_DMA2DEN, .default_lcdcon2 = (ATMEL_LCDC_DISTYPE_TFT @@ -145,7 +145,7 @@ static struct atmel_lcdfb_info __initdata atevklcd10x_lcdc_data = { }; #endif -static void atevklcd10x_lcdc_power_control(int on) +static void atevklcd10x_lcdc_power_control(struct atmel_lcdfb_pdata *pdata, int on) { gpio_set_value(GPIO_PIN_PB(15), on); } diff --git a/arch/avr32/boards/atngw100/mrmt.c b/arch/avr32/boards/atngw100/mrmt.c index 7de083d19b7e..1ba09e4c02b1 100644 --- a/arch/avr32/boards/atngw100/mrmt.c +++ b/arch/avr32/boards/atngw100/mrmt.c @@ -83,7 +83,7 @@ static struct fb_monspecs __initdata lcd_fb_default_monspecs = { .dclkmax = 9260000, }; -static struct atmel_lcdfb_info __initdata rmt_lcdc_data = { +static struct atmel_lcdfb_pdata __initdata rmt_lcdc_data = { .default_bpp = 24, .default_dmacon = ATMEL_LCDC_DMAEN | ATMEL_LCDC_DMA2DEN, .default_lcdcon2 = (ATMEL_LCDC_DISTYPE_TFT @@ -126,7 +126,7 @@ static struct fb_monspecs __initdata lcd_fb_default_monspecs = { .dclkmax = 9260000, }; -static struct atmel_lcdfb_info __initdata rmt_lcdc_data = { +static struct atmel_lcdfb_pdata __initdata rmt_lcdc_data = { .default_bpp = 24, .default_dmacon = ATMEL_LCDC_DMAEN | ATMEL_LCDC_DMA2DEN, .default_lcdcon2 = (ATMEL_LCDC_DISTYPE_TFT diff --git a/arch/avr32/boards/atstk1000/atstk1000.h b/arch/avr32/boards/atstk1000/atstk1000.h index 9392d3252865..653cc09e536c 100644 --- a/arch/avr32/boards/atstk1000/atstk1000.h +++ b/arch/avr32/boards/atstk1000/atstk1000.h @@ -10,7 +10,7 @@ #ifndef __ARCH_AVR32_BOARDS_ATSTK1000_ATSTK1000_H #define __ARCH_AVR32_BOARDS_ATSTK1000_ATSTK1000_H -extern struct atmel_lcdfb_info atstk1000_lcdc_data; +extern struct atmel_lcdfb_pdata atstk1000_lcdc_data; void atstk1000_setup_j2_leds(void); diff --git a/arch/avr32/boards/atstk1000/setup.c b/arch/avr32/boards/atstk1000/setup.c index 2d6b560115d9..b6b88f5e0b43 100644 --- a/arch/avr32/boards/atstk1000/setup.c +++ b/arch/avr32/boards/atstk1000/setup.c @@ -55,7 +55,7 @@ static struct fb_monspecs __initdata atstk1000_default_monspecs = { .dclkmax = 30000000, }; -struct atmel_lcdfb_info __initdata atstk1000_lcdc_data = { +struct atmel_lcdfb_pdata __initdata atstk1000_lcdc_data = { .default_bpp = 24, .default_dmacon = ATMEL_LCDC_DMAEN | ATMEL_LCDC_DMA2DEN, .default_lcdcon2 = (ATMEL_LCDC_DISTYPE_TFT diff --git a/arch/avr32/boards/favr-32/setup.c b/arch/avr32/boards/favr-32/setup.c index 27bd6fbe21cb..7b1f2cd85400 100644 --- a/arch/avr32/boards/favr-32/setup.c +++ b/arch/avr32/boards/favr-32/setup.c @@ -125,7 +125,7 @@ static struct fb_monspecs __initdata favr32_default_monspecs = { .dclkmax = 28000000, }; -struct atmel_lcdfb_info __initdata favr32_lcdc_data = { +struct atmel_lcdfb_pdata __initdata favr32_lcdc_data = { .default_bpp = 16, .default_dmacon = ATMEL_LCDC_DMAEN | ATMEL_LCDC_DMA2DEN, .default_lcdcon2 = (ATMEL_LCDC_DISTYPE_TFT diff --git a/arch/avr32/boards/hammerhead/setup.c b/arch/avr32/boards/hammerhead/setup.c index 9d1efd1cd425..dc0e317f2ecd 100644 --- a/arch/avr32/boards/hammerhead/setup.c +++ b/arch/avr32/boards/hammerhead/setup.c @@ -77,7 +77,7 @@ static struct fb_monspecs __initdata hammerhead_hda350t_monspecs = { .dclkmax = 10000000, }; -struct atmel_lcdfb_info __initdata hammerhead_lcdc_data = { +struct atmel_lcdfb_pdata __initdata hammerhead_lcdc_data = { .default_bpp = 24, .default_dmacon = ATMEL_LCDC_DMAEN | ATMEL_LCDC_DMA2DEN, .default_lcdcon2 = (ATMEL_LCDC_DISTYPE_TFT diff --git a/arch/avr32/boards/merisc/display.c b/arch/avr32/boards/merisc/display.c index 85a543cd4abc..e7683ee7ed40 100644 --- a/arch/avr32/boards/merisc/display.c +++ b/arch/avr32/boards/merisc/display.c @@ -45,7 +45,7 @@ static struct fb_monspecs merisc_fb_monspecs = { .dclkmax = 30000000, }; -struct atmel_lcdfb_info merisc_lcdc_data = { +struct atmel_lcdfb_pdata merisc_lcdc_data = { .default_bpp = 24, .default_dmacon = ATMEL_LCDC_DMAEN | ATMEL_LCDC_DMA2DEN, .default_lcdcon2 = (ATMEL_LCDC_DISTYPE_TFT diff --git a/arch/avr32/boards/mimc200/setup.c b/arch/avr32/boards/mimc200/setup.c index 05358aa5ef7d..1cb8e9cc5cfa 100644 --- a/arch/avr32/boards/mimc200/setup.c +++ b/arch/avr32/boards/mimc200/setup.c @@ -8,7 +8,7 @@ * published by the Free Software Foundation. */ -extern struct atmel_lcdfb_info mimc200_lcdc_data; +extern struct atmel_lcdfb_pdata mimc200_lcdc_data; #include <linux/clk.h> #include <linux/etherdevice.h> @@ -71,7 +71,7 @@ static struct fb_monspecs __initdata mimc200_default_monspecs = { .dclkmax = 25200000, }; -struct atmel_lcdfb_info __initdata mimc200_lcdc_data = { +struct atmel_lcdfb_pdata __initdata mimc200_lcdc_data = { .default_bpp = 16, .default_dmacon = ATMEL_LCDC_DMAEN | ATMEL_LCDC_DMA2DEN, .default_lcdcon2 = (ATMEL_LCDC_DISTYPE_TFT diff --git a/arch/avr32/boot/u-boot/head.S b/arch/avr32/boot/u-boot/head.S index 4488fa27fe94..2ffc298f061b 100644 --- a/arch/avr32/boot/u-boot/head.S +++ b/arch/avr32/boot/u-boot/head.S @@ -8,6 +8,8 @@ * published by the Free Software Foundation. */ #include <asm/setup.h> +#include <asm/thread_info.h> +#include <asm/sysreg.h> /* * The kernel is loaded where we want it to be and all caches @@ -20,11 +22,6 @@ .section .init.text,"ax" .global _start _start: - /* Check if the boot loader actually provided a tag table */ - lddpc r0, magic_number - cp.w r12, r0 - brne no_tag_table - /* Initialize .bss */ lddpc r2, bss_start_addr lddpc r3, end_addr @@ -34,6 +31,25 @@ _start: cp r2, r3 brlo 1b + /* Initialize status register */ + lddpc r0, init_sr + mtsr SYSREG_SR, r0 + + /* Set initial stack pointer */ + lddpc sp, stack_addr + sub sp, -THREAD_SIZE + +#ifdef CONFIG_FRAME_POINTER + /* Mark last stack frame */ + mov lr, 0 + mov r7, 0 +#endif + + /* Check if the boot loader actually provided a tag table */ + lddpc r0, magic_number + cp.w r12, r0 + brne no_tag_table + /* * Save the tag table address for later use. This must be done * _after_ .bss has been initialized... @@ -53,8 +69,15 @@ bss_start_addr: .long __bss_start end_addr: .long _end +init_sr: + .long 0x007f0000 /* Supervisor mode, everything masked */ +stack_addr: + .long init_thread_union +panic_addr: + .long panic no_tag_table: sub r12, pc, (. - 2f) - bral panic + /* branch to panic() which can be far away with that construct */ + lddpc pc, panic_addr 2: .asciz "Boot loader didn't provide correct magic number\n" diff --git a/arch/avr32/include/asm/kprobes.h b/arch/avr32/include/asm/kprobes.h index 996cb656474e..45f563ed73fd 100644 --- a/arch/avr32/include/asm/kprobes.h +++ b/arch/avr32/include/asm/kprobes.h @@ -16,6 +16,7 @@ typedef u16 kprobe_opcode_t; #define BREAKPOINT_INSTRUCTION 0xd673 /* breakpoint */ #define MAX_INSN_SIZE 2 +#define MAX_STACK_SIZE 64 /* 32 would probably be OK */ #define kretprobe_blacklist_size 0 @@ -26,6 +27,19 @@ struct arch_specific_insn { kprobe_opcode_t insn[MAX_INSN_SIZE]; }; +struct prev_kprobe { + struct kprobe *kp; + unsigned int status; +}; + +/* per-cpu kprobe control block */ +struct kprobe_ctlblk { + unsigned int kprobe_status; + struct prev_kprobe prev_kprobe; + struct pt_regs jprobe_saved_regs; + char jprobes_stack[MAX_STACK_SIZE]; +}; + extern int kprobe_fault_handler(struct pt_regs *regs, int trapnr); extern int kprobe_exceptions_notify(struct notifier_block *self, unsigned long val, void *data); diff --git a/arch/avr32/include/asm/pgalloc.h b/arch/avr32/include/asm/pgalloc.h index bc7e8ae479ee..1aba19d68c5e 100644 --- a/arch/avr32/include/asm/pgalloc.h +++ b/arch/avr32/include/asm/pgalloc.h @@ -68,7 +68,10 @@ static inline pgtable_t pte_alloc_one(struct mm_struct *mm, return NULL; page = virt_to_page(pg); - pgtable_page_ctor(page); + if (!pgtable_page_ctor(page)) { + quicklist_free(QUICK_PT, NULL, pg); + return NULL; + } return page; } diff --git a/arch/avr32/include/asm/thread_info.h b/arch/avr32/include/asm/thread_info.h index 6dc62e1f94c7..a978f3fe7c25 100644 --- a/arch/avr32/include/asm/thread_info.h +++ b/arch/avr32/include/asm/thread_info.h @@ -66,8 +66,6 @@ static inline struct thread_info *current_thread_info(void) #endif /* !__ASSEMBLY__ */ -#define PREEMPT_ACTIVE 0x40000000 - /* * Thread information flags * - these are process state flags that various assembly files may need to access diff --git a/arch/avr32/include/uapi/asm/Kbuild b/arch/avr32/include/uapi/asm/Kbuild index 3b85eaddf525..08d8a3d76ea8 100644 --- a/arch/avr32/include/uapi/asm/Kbuild +++ b/arch/avr32/include/uapi/asm/Kbuild @@ -2,35 +2,35 @@ include include/uapi/asm-generic/Kbuild.asm header-y += auxvec.h -header-y += bitsperlong.h header-y += byteorder.h header-y += cachectl.h -header-y += errno.h -header-y += fcntl.h -header-y += ioctl.h -header-y += ioctls.h -header-y += ipcbuf.h -header-y += kvm_para.h -header-y += mman.h header-y += msgbuf.h header-y += param.h -header-y += poll.h header-y += posix_types.h header-y += ptrace.h -header-y += resource.h header-y += sembuf.h header-y += setup.h header-y += shmbuf.h header-y += sigcontext.h -header-y += siginfo.h header-y += signal.h header-y += socket.h header-y += sockios.h header-y += stat.h -header-y += statfs.h header-y += swab.h header-y += termbits.h header-y += termios.h header-y += types.h header-y += unistd.h +generic-y += bitsperlong.h +generic-y += errno.h +generic-y += fcntl.h +generic-y += ioctl.h +generic-y += ioctls.h +generic-y += ipcbuf.h +generic-y += kvm_para.h +generic-y += mman.h generic-y += param.h +generic-y += poll.h +generic-y += resource.h +generic-y += siginfo.h +generic-y += statfs.h diff --git a/arch/avr32/include/uapi/asm/auxvec.h b/arch/avr32/include/uapi/asm/auxvec.h index d5dd435bf8f4..4f02da3ffefa 100644 --- a/arch/avr32/include/uapi/asm/auxvec.h +++ b/arch/avr32/include/uapi/asm/auxvec.h @@ -1,4 +1,4 @@ -#ifndef __ASM_AVR32_AUXVEC_H -#define __ASM_AVR32_AUXVEC_H +#ifndef _UAPI__ASM_AVR32_AUXVEC_H +#define _UAPI__ASM_AVR32_AUXVEC_H -#endif /* __ASM_AVR32_AUXVEC_H */ +#endif /* _UAPI__ASM_AVR32_AUXVEC_H */ diff --git a/arch/avr32/include/uapi/asm/bitsperlong.h b/arch/avr32/include/uapi/asm/bitsperlong.h deleted file mode 100644 index 6dc0bb0c13b2..000000000000 --- a/arch/avr32/include/uapi/asm/bitsperlong.h +++ /dev/null @@ -1 +0,0 @@ -#include <asm-generic/bitsperlong.h> diff --git a/arch/avr32/include/uapi/asm/byteorder.h b/arch/avr32/include/uapi/asm/byteorder.h index 50abc21619a8..71242f0d39c6 100644 --- a/arch/avr32/include/uapi/asm/byteorder.h +++ b/arch/avr32/include/uapi/asm/byteorder.h @@ -1,9 +1,9 @@ /* * AVR32 endian-conversion functions. */ -#ifndef __ASM_AVR32_BYTEORDER_H -#define __ASM_AVR32_BYTEORDER_H +#ifndef _UAPI__ASM_AVR32_BYTEORDER_H +#define _UAPI__ASM_AVR32_BYTEORDER_H #include <linux/byteorder/big_endian.h> -#endif /* __ASM_AVR32_BYTEORDER_H */ +#endif /* _UAPI__ASM_AVR32_BYTEORDER_H */ diff --git a/arch/avr32/include/uapi/asm/cachectl.h b/arch/avr32/include/uapi/asm/cachectl.h index 4faf1ce60061..573a9584dd57 100644 --- a/arch/avr32/include/uapi/asm/cachectl.h +++ b/arch/avr32/include/uapi/asm/cachectl.h @@ -1,5 +1,5 @@ -#ifndef __ASM_AVR32_CACHECTL_H -#define __ASM_AVR32_CACHECTL_H +#ifndef _UAPI__ASM_AVR32_CACHECTL_H +#define _UAPI__ASM_AVR32_CACHECTL_H /* * Operations that can be performed through the cacheflush system call @@ -8,4 +8,4 @@ /* Clean the data cache, then invalidate the icache */ #define CACHE_IFLUSH 0 -#endif /* __ASM_AVR32_CACHECTL_H */ +#endif /* _UAPI__ASM_AVR32_CACHECTL_H */ diff --git a/arch/avr32/include/uapi/asm/errno.h b/arch/avr32/include/uapi/asm/errno.h deleted file mode 100644 index 558a7249f06d..000000000000 --- a/arch/avr32/include/uapi/asm/errno.h +++ /dev/null @@ -1,6 +0,0 @@ -#ifndef __ASM_AVR32_ERRNO_H -#define __ASM_AVR32_ERRNO_H - -#include <asm-generic/errno.h> - -#endif /* __ASM_AVR32_ERRNO_H */ diff --git a/arch/avr32/include/uapi/asm/fcntl.h b/arch/avr32/include/uapi/asm/fcntl.h deleted file mode 100644 index 14c0c4402b11..000000000000 --- a/arch/avr32/include/uapi/asm/fcntl.h +++ /dev/null @@ -1,6 +0,0 @@ -#ifndef __ASM_AVR32_FCNTL_H -#define __ASM_AVR32_FCNTL_H - -#include <asm-generic/fcntl.h> - -#endif /* __ASM_AVR32_FCNTL_H */ diff --git a/arch/avr32/include/uapi/asm/ioctl.h b/arch/avr32/include/uapi/asm/ioctl.h deleted file mode 100644 index c8472c1398ef..000000000000 --- a/arch/avr32/include/uapi/asm/ioctl.h +++ /dev/null @@ -1,6 +0,0 @@ -#ifndef __ASM_AVR32_IOCTL_H -#define __ASM_AVR32_IOCTL_H - -#include <asm-generic/ioctl.h> - -#endif /* __ASM_AVR32_IOCTL_H */ diff --git a/arch/avr32/include/uapi/asm/ioctls.h b/arch/avr32/include/uapi/asm/ioctls.h deleted file mode 100644 index 909cf66feaf5..000000000000 --- a/arch/avr32/include/uapi/asm/ioctls.h +++ /dev/null @@ -1,6 +0,0 @@ -#ifndef __ASM_AVR32_IOCTLS_H -#define __ASM_AVR32_IOCTLS_H - -#include <asm-generic/ioctls.h> - -#endif /* __ASM_AVR32_IOCTLS_H */ diff --git a/arch/avr32/include/uapi/asm/ipcbuf.h b/arch/avr32/include/uapi/asm/ipcbuf.h deleted file mode 100644 index 84c7e51cb6d0..000000000000 --- a/arch/avr32/include/uapi/asm/ipcbuf.h +++ /dev/null @@ -1 +0,0 @@ -#include <asm-generic/ipcbuf.h> diff --git a/arch/avr32/include/uapi/asm/kvm_para.h b/arch/avr32/include/uapi/asm/kvm_para.h deleted file mode 100644 index 14fab8f0b957..000000000000 --- a/arch/avr32/include/uapi/asm/kvm_para.h +++ /dev/null @@ -1 +0,0 @@ -#include <asm-generic/kvm_para.h> diff --git a/arch/avr32/include/uapi/asm/mman.h b/arch/avr32/include/uapi/asm/mman.h deleted file mode 100644 index 8eebf89f5ab1..000000000000 --- a/arch/avr32/include/uapi/asm/mman.h +++ /dev/null @@ -1 +0,0 @@ -#include <asm-generic/mman.h> diff --git a/arch/avr32/include/uapi/asm/msgbuf.h b/arch/avr32/include/uapi/asm/msgbuf.h index ac18bc4da7f7..9eae6effad14 100644 --- a/arch/avr32/include/uapi/asm/msgbuf.h +++ b/arch/avr32/include/uapi/asm/msgbuf.h @@ -1,5 +1,5 @@ -#ifndef __ASM_AVR32_MSGBUF_H -#define __ASM_AVR32_MSGBUF_H +#ifndef _UAPI__ASM_AVR32_MSGBUF_H +#define _UAPI__ASM_AVR32_MSGBUF_H /* * The msqid64_ds structure for i386 architecture. @@ -28,4 +28,4 @@ struct msqid64_ds { unsigned long __unused5; }; -#endif /* __ASM_AVR32_MSGBUF_H */ +#endif /* _UAPI__ASM_AVR32_MSGBUF_H */ diff --git a/arch/avr32/include/uapi/asm/poll.h b/arch/avr32/include/uapi/asm/poll.h deleted file mode 100644 index c98509d3149e..000000000000 --- a/arch/avr32/include/uapi/asm/poll.h +++ /dev/null @@ -1 +0,0 @@ -#include <asm-generic/poll.h> diff --git a/arch/avr32/include/uapi/asm/posix_types.h b/arch/avr32/include/uapi/asm/posix_types.h index 9ba9e749b3f3..5b813a8abf09 100644 --- a/arch/avr32/include/uapi/asm/posix_types.h +++ b/arch/avr32/include/uapi/asm/posix_types.h @@ -5,8 +5,8 @@ * it under the terms of the GNU General Public License version 2 as * published by the Free Software Foundation. */ -#ifndef __ASM_AVR32_POSIX_TYPES_H -#define __ASM_AVR32_POSIX_TYPES_H +#ifndef _UAPI__ASM_AVR32_POSIX_TYPES_H +#define _UAPI__ASM_AVR32_POSIX_TYPES_H /* * This file is generally used by user-level software, so you need to @@ -34,4 +34,4 @@ typedef unsigned short __kernel_old_dev_t; #include <asm-generic/posix_types.h> -#endif /* __ASM_AVR32_POSIX_TYPES_H */ +#endif /* _UAPI__ASM_AVR32_POSIX_TYPES_H */ diff --git a/arch/avr32/include/uapi/asm/resource.h b/arch/avr32/include/uapi/asm/resource.h deleted file mode 100644 index c6dd101472b1..000000000000 --- a/arch/avr32/include/uapi/asm/resource.h +++ /dev/null @@ -1,6 +0,0 @@ -#ifndef __ASM_AVR32_RESOURCE_H -#define __ASM_AVR32_RESOURCE_H - -#include <asm-generic/resource.h> - -#endif /* __ASM_AVR32_RESOURCE_H */ diff --git a/arch/avr32/include/uapi/asm/sembuf.h b/arch/avr32/include/uapi/asm/sembuf.h index e472216e0c97..6c6f7cf1e75a 100644 --- a/arch/avr32/include/uapi/asm/sembuf.h +++ b/arch/avr32/include/uapi/asm/sembuf.h @@ -1,5 +1,5 @@ -#ifndef __ASM_AVR32_SEMBUF_H -#define __ASM_AVR32_SEMBUF_H +#ifndef _UAPI__ASM_AVR32_SEMBUF_H +#define _UAPI__ASM_AVR32_SEMBUF_H /* * The semid64_ds structure for AVR32 architecture. @@ -22,4 +22,4 @@ struct semid64_ds { unsigned long __unused4; }; -#endif /* __ASM_AVR32_SEMBUF_H */ +#endif /* _UAPI__ASM_AVR32_SEMBUF_H */ diff --git a/arch/avr32/include/uapi/asm/setup.h b/arch/avr32/include/uapi/asm/setup.h index e58aa9356faf..a654df7dba46 100644 --- a/arch/avr32/include/uapi/asm/setup.h +++ b/arch/avr32/include/uapi/asm/setup.h @@ -13,5 +13,4 @@ #define COMMAND_LINE_SIZE 256 - #endif /* _UAPI__ASM_AVR32_SETUP_H__ */ diff --git a/arch/avr32/include/uapi/asm/shmbuf.h b/arch/avr32/include/uapi/asm/shmbuf.h index c62fba41739a..b94cf8b60b73 100644 --- a/arch/avr32/include/uapi/asm/shmbuf.h +++ b/arch/avr32/include/uapi/asm/shmbuf.h @@ -1,5 +1,5 @@ -#ifndef __ASM_AVR32_SHMBUF_H -#define __ASM_AVR32_SHMBUF_H +#ifndef _UAPI__ASM_AVR32_SHMBUF_H +#define _UAPI__ASM_AVR32_SHMBUF_H /* * The shmid64_ds structure for i386 architecture. @@ -39,4 +39,4 @@ struct shminfo64 { unsigned long __unused4; }; -#endif /* __ASM_AVR32_SHMBUF_H */ +#endif /* _UAPI__ASM_AVR32_SHMBUF_H */ diff --git a/arch/avr32/include/uapi/asm/sigcontext.h b/arch/avr32/include/uapi/asm/sigcontext.h index e04062b5f39f..27e56bf6377f 100644 --- a/arch/avr32/include/uapi/asm/sigcontext.h +++ b/arch/avr32/include/uapi/asm/sigcontext.h @@ -5,8 +5,8 @@ * it under the terms of the GNU General Public License version 2 as * published by the Free Software Foundation. */ -#ifndef __ASM_AVR32_SIGCONTEXT_H -#define __ASM_AVR32_SIGCONTEXT_H +#ifndef _UAPI__ASM_AVR32_SIGCONTEXT_H +#define _UAPI__ASM_AVR32_SIGCONTEXT_H struct sigcontext { unsigned long oldmask; @@ -31,4 +31,4 @@ struct sigcontext { unsigned long r0; }; -#endif /* __ASM_AVR32_SIGCONTEXT_H */ +#endif /* _UAPI__ASM_AVR32_SIGCONTEXT_H */ diff --git a/arch/avr32/include/uapi/asm/siginfo.h b/arch/avr32/include/uapi/asm/siginfo.h deleted file mode 100644 index 5ee93f40a8a8..000000000000 --- a/arch/avr32/include/uapi/asm/siginfo.h +++ /dev/null @@ -1,6 +0,0 @@ -#ifndef _AVR32_SIGINFO_H -#define _AVR32_SIGINFO_H - -#include <asm-generic/siginfo.h> - -#endif diff --git a/arch/avr32/include/uapi/asm/signal.h b/arch/avr32/include/uapi/asm/signal.h index 1b77a93eff50..ffe8c770cafd 100644 --- a/arch/avr32/include/uapi/asm/signal.h +++ b/arch/avr32/include/uapi/asm/signal.h @@ -118,5 +118,4 @@ typedef struct sigaltstack { size_t ss_size; } stack_t; - #endif /* _UAPI__ASM_AVR32_SIGNAL_H */ diff --git a/arch/avr32/include/uapi/asm/socket.h b/arch/avr32/include/uapi/asm/socket.h index 439936421434..cbf902e4cd9e 100644 --- a/arch/avr32/include/uapi/asm/socket.h +++ b/arch/avr32/include/uapi/asm/socket.h @@ -1,5 +1,5 @@ -#ifndef __ASM_AVR32_SOCKET_H -#define __ASM_AVR32_SOCKET_H +#ifndef _UAPI__ASM_AVR32_SOCKET_H +#define _UAPI__ASM_AVR32_SOCKET_H #include <asm/sockios.h> @@ -78,4 +78,4 @@ #define SO_MAX_PACING_RATE 47 -#endif /* __ASM_AVR32_SOCKET_H */ +#endif /* _UAPI__ASM_AVR32_SOCKET_H */ diff --git a/arch/avr32/include/uapi/asm/sockios.h b/arch/avr32/include/uapi/asm/sockios.h index 0802d742f97d..d04785453532 100644 --- a/arch/avr32/include/uapi/asm/sockios.h +++ b/arch/avr32/include/uapi/asm/sockios.h @@ -1,5 +1,5 @@ -#ifndef __ASM_AVR32_SOCKIOS_H -#define __ASM_AVR32_SOCKIOS_H +#ifndef _UAPI__ASM_AVR32_SOCKIOS_H +#define _UAPI__ASM_AVR32_SOCKIOS_H /* Socket-level I/O control calls. */ #define FIOSETOWN 0x8901 @@ -10,4 +10,4 @@ #define SIOCGSTAMP 0x8906 /* Get stamp (timeval) */ #define SIOCGSTAMPNS 0x8907 /* Get stamp (timespec) */ -#endif /* __ASM_AVR32_SOCKIOS_H */ +#endif /* _UAPI__ASM_AVR32_SOCKIOS_H */ diff --git a/arch/avr32/include/uapi/asm/stat.h b/arch/avr32/include/uapi/asm/stat.h index e72881e10230..c06acef7fce7 100644 --- a/arch/avr32/include/uapi/asm/stat.h +++ b/arch/avr32/include/uapi/asm/stat.h @@ -5,8 +5,8 @@ * it under the terms of the GNU General Public License version 2 as * published by the Free Software Foundation. */ -#ifndef __ASM_AVR32_STAT_H -#define __ASM_AVR32_STAT_H +#ifndef _UAPI__ASM_AVR32_STAT_H +#define _UAPI__ASM_AVR32_STAT_H struct __old_kernel_stat { unsigned short st_dev; @@ -76,4 +76,4 @@ struct stat64 { unsigned long __unused2; }; -#endif /* __ASM_AVR32_STAT_H */ +#endif /* _UAPI__ASM_AVR32_STAT_H */ diff --git a/arch/avr32/include/uapi/asm/statfs.h b/arch/avr32/include/uapi/asm/statfs.h deleted file mode 100644 index 2961bd18c50e..000000000000 --- a/arch/avr32/include/uapi/asm/statfs.h +++ /dev/null @@ -1,6 +0,0 @@ -#ifndef __ASM_AVR32_STATFS_H -#define __ASM_AVR32_STATFS_H - -#include <asm-generic/statfs.h> - -#endif /* __ASM_AVR32_STATFS_H */ diff --git a/arch/avr32/include/uapi/asm/swab.h b/arch/avr32/include/uapi/asm/swab.h index 14cc737bbca6..1a03549e7dc5 100644 --- a/arch/avr32/include/uapi/asm/swab.h +++ b/arch/avr32/include/uapi/asm/swab.h @@ -1,8 +1,8 @@ /* * AVR32 byteswapping functions. */ -#ifndef __ASM_AVR32_SWAB_H -#define __ASM_AVR32_SWAB_H +#ifndef _UAPI__ASM_AVR32_SWAB_H +#define _UAPI__ASM_AVR32_SWAB_H #include <linux/types.h> #include <linux/compiler.h> @@ -32,4 +32,4 @@ static inline __attribute_const__ __u32 __arch_swab32(__u32 val) #define __arch_swab32 __arch_swab32 #endif -#endif /* __ASM_AVR32_SWAB_H */ +#endif /* _UAPI__ASM_AVR32_SWAB_H */ diff --git a/arch/avr32/include/uapi/asm/termbits.h b/arch/avr32/include/uapi/asm/termbits.h index 366adc5ebb10..32789ccb38f8 100644 --- a/arch/avr32/include/uapi/asm/termbits.h +++ b/arch/avr32/include/uapi/asm/termbits.h @@ -1,5 +1,5 @@ -#ifndef __ASM_AVR32_TERMBITS_H -#define __ASM_AVR32_TERMBITS_H +#ifndef _UAPI__ASM_AVR32_TERMBITS_H +#define _UAPI__ASM_AVR32_TERMBITS_H #include <linux/posix_types.h> @@ -193,4 +193,4 @@ struct ktermios { #define TCSADRAIN 1 #define TCSAFLUSH 2 -#endif /* __ASM_AVR32_TERMBITS_H */ +#endif /* _UAPI__ASM_AVR32_TERMBITS_H */ diff --git a/arch/avr32/include/uapi/asm/termios.h b/arch/avr32/include/uapi/asm/termios.h index b8ef8ea63352..c8a0081556c4 100644 --- a/arch/avr32/include/uapi/asm/termios.h +++ b/arch/avr32/include/uapi/asm/termios.h @@ -46,5 +46,4 @@ struct termio { /* ioctl (fd, TIOCSERGETLSR, &result) where result may be as below */ - #endif /* _UAPI__ASM_AVR32_TERMIOS_H */ diff --git a/arch/avr32/include/uapi/asm/types.h b/arch/avr32/include/uapi/asm/types.h index bb34ad349dfc..7c986c4e99b5 100644 --- a/arch/avr32/include/uapi/asm/types.h +++ b/arch/avr32/include/uapi/asm/types.h @@ -5,4 +5,9 @@ * it under the terms of the GNU General Public License version 2 as * published by the Free Software Foundation. */ +#ifndef _UAPI__ASM_AVR32_TYPES_H +#define _UAPI__ASM_AVR32_TYPES_H + #include <asm-generic/int-ll64.h> + +#endif /* _UAPI__ASM_AVR32_TYPES_H */ diff --git a/arch/avr32/include/uapi/asm/unistd.h b/arch/avr32/include/uapi/asm/unistd.h index 3eaa68753adb..8822bf46ddc6 100644 --- a/arch/avr32/include/uapi/asm/unistd.h +++ b/arch/avr32/include/uapi/asm/unistd.h @@ -301,5 +301,4 @@ #define __NR_eventfd 281 #define __NR_setns 283 - #endif /* _UAPI__ASM_AVR32_UNISTD_H */ diff --git a/arch/avr32/kernel/entry-avr32b.S b/arch/avr32/kernel/entry-avr32b.S index 9899d3cc6f03..7301f4806bbe 100644 --- a/arch/avr32/kernel/entry-avr32b.S +++ b/arch/avr32/kernel/entry-avr32b.S @@ -401,9 +401,10 @@ handle_critical: /* We should never get here... */ bad_return: sub r12, pc, (. - 1f) - bral panic + lddpc pc, 2f .align 2 1: .asciz "Return from critical exception!" +2: .long panic .align 1 do_bus_error_write: diff --git a/arch/avr32/kernel/head.S b/arch/avr32/kernel/head.S index 6163bd0acb95..59eae6dfbed2 100644 --- a/arch/avr32/kernel/head.S +++ b/arch/avr32/kernel/head.S @@ -10,33 +10,13 @@ #include <linux/linkage.h> #include <asm/page.h> -#include <asm/thread_info.h> -#include <asm/sysreg.h> .section .init.text,"ax" .global kernel_entry kernel_entry: - /* Initialize status register */ - lddpc r0, init_sr - mtsr SYSREG_SR, r0 - - /* Set initial stack pointer */ - lddpc sp, stack_addr - sub sp, -THREAD_SIZE - -#ifdef CONFIG_FRAME_POINTER - /* Mark last stack frame */ - mov lr, 0 - mov r7, 0 -#endif - /* Start the show */ lddpc pc, kernel_start_addr .align 2 -init_sr: - .long 0x007f0000 /* Supervisor mode, everything masked */ -stack_addr: - .long init_thread_union kernel_start_addr: .long start_kernel diff --git a/arch/avr32/mach-at32ap/at32ap700x.c b/arch/avr32/mach-at32ap/at32ap700x.c index a68f3cf7c3c1..a1f4d1e91b52 100644 --- a/arch/avr32/mach-at32ap/at32ap700x.c +++ b/arch/avr32/mach-at32ap/at32ap700x.c @@ -1439,7 +1439,7 @@ fail: * LCDC * -------------------------------------------------------------------- */ #if defined(CONFIG_CPU_AT32AP7000) || defined(CONFIG_CPU_AT32AP7002) -static struct atmel_lcdfb_info atmel_lcdfb0_data; +static struct atmel_lcdfb_pdata atmel_lcdfb0_data; static struct resource atmel_lcdfb0_resource[] = { { .start = 0xff000000, @@ -1467,12 +1467,12 @@ static struct clk atmel_lcdfb0_pixclk = { }; struct platform_device *__init -at32_add_device_lcdc(unsigned int id, struct atmel_lcdfb_info *data, +at32_add_device_lcdc(unsigned int id, struct atmel_lcdfb_pdata *data, unsigned long fbmem_start, unsigned long fbmem_len, u64 pin_mask) { struct platform_device *pdev; - struct atmel_lcdfb_info *info; + struct atmel_lcdfb_pdata *info; struct fb_monspecs *monspecs; struct fb_videomode *modedb; unsigned int modedb_size; @@ -1529,7 +1529,7 @@ at32_add_device_lcdc(unsigned int id, struct atmel_lcdfb_info *data, } info = pdev->dev.platform_data; - memcpy(info, data, sizeof(struct atmel_lcdfb_info)); + memcpy(info, data, sizeof(struct atmel_lcdfb_pdata)); info->default_monspecs = monspecs; pdev->name = "at32ap-lcdfb"; diff --git a/arch/avr32/mach-at32ap/include/mach/board.h b/arch/avr32/mach-at32ap/include/mach/board.h index d485b0391357..f1a316d52c73 100644 --- a/arch/avr32/mach-at32ap/include/mach/board.h +++ b/arch/avr32/mach-at32ap/include/mach/board.h @@ -44,9 +44,9 @@ struct platform_device * at32_add_device_spi(unsigned int id, struct spi_board_info *b, unsigned int n); void at32_spi_setup_slaves(unsigned int bus_num, struct spi_board_info *b, unsigned int n); -struct atmel_lcdfb_info; +struct atmel_lcdfb_pdata; struct platform_device * -at32_add_device_lcdc(unsigned int id, struct atmel_lcdfb_info *data, +at32_add_device_lcdc(unsigned int id, struct atmel_lcdfb_pdata *data, unsigned long fbmem_start, unsigned long fbmem_len, u64 pin_mask); diff --git a/arch/blackfin/Kconfig b/arch/blackfin/Kconfig index 74314bd8be39..9ceccef9c649 100644 --- a/arch/blackfin/Kconfig +++ b/arch/blackfin/Kconfig @@ -34,7 +34,6 @@ config BLACKFIN select ARCH_WANT_IPC_PARSE_VERSION select GENERIC_ATOMIC64 select GENERIC_IRQ_PROBE - select USE_GENERIC_SMP_HELPERS if SMP select HAVE_NMI_WATCHDOG if NMI_WATCHDOG select GENERIC_SMP_IDLE_THREAD select ARCH_USES_GETTIMEOFFSET if !GENERIC_CLOCKEVENTS @@ -1440,7 +1439,6 @@ source "drivers/cpufreq/Kconfig" config BFIN_CPU_FREQ bool depends on CPU_FREQ - select CPU_FREQ_TABLE default y config CPU_VOLTAGE diff --git a/arch/blackfin/configs/BF609-EZKIT_defconfig b/arch/blackfin/configs/BF609-EZKIT_defconfig index 13eb73231a9a..4ca39ab6b2bf 100644 --- a/arch/blackfin/configs/BF609-EZKIT_defconfig +++ b/arch/blackfin/configs/BF609-EZKIT_defconfig @@ -102,7 +102,7 @@ CONFIG_I2C_CHARDEV=y CONFIG_I2C_BLACKFIN_TWI=y CONFIG_I2C_BLACKFIN_TWI_CLK_KHZ=100 CONFIG_SPI=y -CONFIG_SPI_BFIN6XX=y +CONFIG_SPI_BFIN_V3=y CONFIG_GPIOLIB=y CONFIG_GPIO_SYSFS=y # CONFIG_HWMON is not set diff --git a/arch/blackfin/include/asm/hardirq.h b/arch/blackfin/include/asm/hardirq.h index c078dd78d998..58b54a6d5a16 100644 --- a/arch/blackfin/include/asm/hardirq.h +++ b/arch/blackfin/include/asm/hardirq.h @@ -12,9 +12,6 @@ extern void ack_bad_irq(unsigned int irq); #define ack_bad_irq ack_bad_irq -/* Define until common code gets sane defaults */ -#define HARDIRQ_BITS 9 - #include <asm-generic/hardirq.h> #endif diff --git a/arch/blackfin/include/asm/irq.h b/arch/blackfin/include/asm/irq.h index 4ae1144a4578..2fd04f10cc26 100644 --- a/arch/blackfin/include/asm/irq.h +++ b/arch/blackfin/include/asm/irq.h @@ -23,8 +23,7 @@ /* * pm save bfin pint registers */ -struct bfin_pm_pint_save { - u32 mask_set; +struct adi_pm_pint_save { u32 assign; u32 edge_set; u32 invert_set; diff --git a/arch/blackfin/include/asm/irq_handler.h b/arch/blackfin/include/asm/irq_handler.h index 4fbf83575db1..4b2a992794d7 100644 --- a/arch/blackfin/include/asm/irq_handler.h +++ b/arch/blackfin/include/asm/irq_handler.h @@ -12,11 +12,11 @@ #include <mach/irq.h> /* init functions only */ -extern int __init init_arch_irq(void); +extern int init_arch_irq(void); extern void init_exception_vectors(void); -extern void __init program_IAR(void); +extern void program_IAR(void); #ifdef init_mach_irq -extern void __init init_mach_irq(void); +extern void init_mach_irq(void); #else # define init_mach_irq() #endif diff --git a/arch/blackfin/include/asm/thread_info.h b/arch/blackfin/include/asm/thread_info.h index 3894005337ba..55f473bdad36 100644 --- a/arch/blackfin/include/asm/thread_info.h +++ b/arch/blackfin/include/asm/thread_info.h @@ -88,8 +88,6 @@ static inline struct thread_info *current_thread_info(void) #define TI_CPU 12 #define TI_PREEMPT 16 -#define PREEMPT_ACTIVE 0x4000000 - /* * thread information flag bit numbers */ diff --git a/arch/blackfin/kernel/bfin_gpio.c b/arch/blackfin/kernel/bfin_gpio.c index ed978f1c5cb9..a017359c1826 100644 --- a/arch/blackfin/kernel/bfin_gpio.c +++ b/arch/blackfin/kernel/bfin_gpio.c @@ -11,11 +11,8 @@ #include <linux/err.h> #include <linux/proc_fs.h> #include <linux/seq_file.h> -#include <asm/blackfin.h> -#include <asm/gpio.h> -#include <asm/portmux.h> +#include <linux/gpio.h> #include <linux/irq.h> -#include <asm/irq_handler.h> #if ANOMALY_05000311 || ANOMALY_05000323 enum { @@ -58,19 +55,6 @@ static struct gpio_port_t * const gpio_array[] = { (struct gpio_port_t *) FIO0_FLAG_D, (struct gpio_port_t *) FIO1_FLAG_D, (struct gpio_port_t *) FIO2_FLAG_D, -#elif defined(CONFIG_BF54x) || defined(CONFIG_BF60x) - (struct gpio_port_t *)PORTA_FER, - (struct gpio_port_t *)PORTB_FER, - (struct gpio_port_t *)PORTC_FER, - (struct gpio_port_t *)PORTD_FER, - (struct gpio_port_t *)PORTE_FER, - (struct gpio_port_t *)PORTF_FER, - (struct gpio_port_t *)PORTG_FER, -# if defined(CONFIG_BF54x) - (struct gpio_port_t *)PORTH_FER, - (struct gpio_port_t *)PORTI_FER, - (struct gpio_port_t *)PORTJ_FER, -# endif #else # error no gpio arrays defined #endif @@ -169,12 +153,6 @@ DECLARE_RESERVED_MAP(gpio_irq, GPIO_BANK_NUM); inline int check_gpio(unsigned gpio) { -#if defined(CONFIG_BF54x) - if (gpio == GPIO_PB15 || gpio == GPIO_PC14 || gpio == GPIO_PC15 - || gpio == GPIO_PH14 || gpio == GPIO_PH15 - || gpio == GPIO_PJ14 || gpio == GPIO_PJ15) - return -EINVAL; -#endif if (gpio >= MAX_BLACKFIN_GPIOS) return -EINVAL; return 0; @@ -212,12 +190,6 @@ static void port_setup(unsigned gpio, unsigned short usage) else *port_fer[gpio_bank(gpio)] |= gpio_bit(gpio); SSYNC(); -#elif defined(CONFIG_BF54x) || defined(CONFIG_BF60x) - if (usage == GPIO_USAGE) - gpio_array[gpio_bank(gpio)]->port_fer &= ~gpio_bit(gpio); - else - gpio_array[gpio_bank(gpio)]->port_fer |= gpio_bit(gpio); - SSYNC(); #endif } @@ -255,7 +227,7 @@ static int portmux_group_check(unsigned short per) u16 ident = P_IDENT(per); u16 function = P_FUNCT2MUX(per); s8 offset = port_mux[ident]; - u16 m, pmux, pfunc; + u16 m, pmux, pfunc, mask; if (offset < 0) return 0; @@ -270,10 +242,12 @@ static int portmux_group_check(unsigned short per) continue; if (offset == 1) - pfunc = (pmux >> offset) & 3; + mask = 3; else - pfunc = (pmux >> offset) & 1; - if (pfunc != function) { + mask = 1; + + pfunc = (pmux >> offset) & mask; + if (pfunc != (function & mask)) { pr_err("pin group conflict! request pin %d func %d conflict with pin %d func %d\n", ident, function, m, pfunc); return -EINVAL; @@ -288,43 +262,21 @@ static void portmux_setup(unsigned short per) u16 ident = P_IDENT(per); u16 function = P_FUNCT2MUX(per); s8 offset = port_mux[ident]; - u16 pmux; + u16 pmux, mask; if (offset == -1) return; pmux = bfin_read_PORT_MUX(); - if (offset != 1) - pmux &= ~(1 << offset); + if (offset == 1) + mask = 3; else - pmux &= ~(3 << 1); - pmux |= (function << offset); - bfin_write_PORT_MUX(pmux); -} -#elif defined(CONFIG_BF54x) || defined(CONFIG_BF60x) -inline void portmux_setup(unsigned short per) -{ - u16 ident = P_IDENT(per); - u16 function = P_FUNCT2MUX(per); - u32 pmux; + mask = 1; - pmux = gpio_array[gpio_bank(ident)]->port_mux; + pmux &= ~(mask << offset); + pmux |= ((function & mask) << offset); - pmux &= ~(0x3 << (2 * gpio_sub_n(ident))); - pmux |= (function & 0x3) << (2 * gpio_sub_n(ident)); - - gpio_array[gpio_bank(ident)]->port_mux = pmux; -} - -inline u16 get_portmux(unsigned short per) -{ - u16 ident = P_IDENT(per); - u32 pmux = gpio_array[gpio_bank(ident)]->port_mux; - return (pmux >> (2 * gpio_sub_n(ident)) & 0x3); -} -static int portmux_group_check(unsigned short per) -{ - return 0; + bfin_write_PORT_MUX(pmux); } #elif defined(CONFIG_BF52x) || defined(CONFIG_BF51x) static int portmux_group_check(unsigned short per) @@ -379,7 +331,6 @@ static int portmux_group_check(unsigned short per) } #endif -#if !(defined(CONFIG_BF54x) || defined(CONFIG_BF60x)) /*********************************************************** * * FUNCTIONS: Blackfin General Purpose Ports Access Functions @@ -572,7 +523,7 @@ static const unsigned int sic_iwr_irqs[] = { ************************************************************* * MODIFICATION HISTORY : **************************************************************/ -int gpio_pm_wakeup_ctrl(unsigned gpio, unsigned ctrl) +int bfin_gpio_pm_wakeup_ctrl(unsigned gpio, unsigned ctrl) { unsigned long flags; @@ -591,7 +542,7 @@ int gpio_pm_wakeup_ctrl(unsigned gpio, unsigned ctrl) return 0; } -int bfin_pm_standby_ctrl(unsigned ctrl) +int bfin_gpio_pm_standby_ctrl(unsigned ctrl) { u16 bank, mask, i; @@ -682,53 +633,6 @@ void bfin_gpio_pm_hibernate_restore(void) #endif -#else /* CONFIG_BF54x || CONFIG_BF60x */ -#ifdef CONFIG_PM - -int bfin_pm_standby_ctrl(unsigned ctrl) -{ - return 0; -} - -void bfin_gpio_pm_hibernate_suspend(void) -{ - int i, bank; - - for (i = 0; i < MAX_BLACKFIN_GPIOS; i += GPIO_BANKSIZE) { - bank = gpio_bank(i); - - gpio_bank_saved[bank].fer = gpio_array[bank]->port_fer; - gpio_bank_saved[bank].mux = gpio_array[bank]->port_mux; - gpio_bank_saved[bank].data = gpio_array[bank]->data; - gpio_bank_saved[bank].inen = gpio_array[bank]->inen; - gpio_bank_saved[bank].dir = gpio_array[bank]->dir_set; - } -} - -void bfin_gpio_pm_hibernate_restore(void) -{ - int i, bank; - - for (i = 0; i < MAX_BLACKFIN_GPIOS; i += GPIO_BANKSIZE) { - bank = gpio_bank(i); - - gpio_array[bank]->port_mux = gpio_bank_saved[bank].mux; - gpio_array[bank]->port_fer = gpio_bank_saved[bank].fer; - gpio_array[bank]->inen = gpio_bank_saved[bank].inen; - gpio_array[bank]->data_set = gpio_bank_saved[bank].data - & gpio_bank_saved[bank].dir; - gpio_array[bank]->dir_set = gpio_bank_saved[bank].dir; - } -} -#endif - -unsigned short get_gpio_dir(unsigned gpio) -{ - return (0x01 & (gpio_array[gpio_bank(gpio)]->dir_clear >> gpio_sub_n(gpio))); -} -EXPORT_SYMBOL(get_gpio_dir); - -#endif /* CONFIG_BF54x || CONFIG_BF60x */ /*********************************************************** * @@ -785,11 +689,7 @@ int peripheral_request(unsigned short per, const char *label) * be requested and used by several drivers */ -#if defined(CONFIG_BF54x) || defined(CONFIG_BF60x) - if (!((per & P_MAYSHARE) && get_portmux(per) == P_FUNCT2MUX(per))) { -#else if (!(per & P_MAYSHARE)) { -#endif /* * Allow that the identical pin function can * be requested from the same driver twice @@ -938,12 +838,9 @@ int bfin_gpio_request(unsigned gpio, const char *label) if (unlikely(is_reserved(gpio_irq, gpio, 1))) { printk(KERN_NOTICE "bfin-gpio: GPIO %d is already reserved as gpio-irq!" " (Documentation/blackfin/bfin-gpio-notes.txt)\n", gpio); - } -#if !(defined(CONFIG_BF54x) || defined(CONFIG_BF60x)) - else { /* Reset POLAR setting when acquiring a gpio for the first time */ + } else { /* Reset POLAR setting when acquiring a gpio for the first time */ set_gpio_polar(gpio, 0); } -#endif reserve(gpio, gpio); set_label(gpio, label); @@ -1112,11 +1009,7 @@ void bfin_gpio_irq_free(unsigned gpio) static inline void __bfin_gpio_direction_input(unsigned gpio) { -#if defined(CONFIG_BF54x) || defined(CONFIG_BF60x) - gpio_array[gpio_bank(gpio)]->dir_clear = gpio_bit(gpio); -#else gpio_array[gpio_bank(gpio)]->dir &= ~gpio_bit(gpio); -#endif gpio_array[gpio_bank(gpio)]->inen |= gpio_bit(gpio); } @@ -1140,17 +1033,7 @@ EXPORT_SYMBOL(bfin_gpio_direction_input); void bfin_gpio_irq_prepare(unsigned gpio) { -#if defined(CONFIG_BF54x) || defined(CONFIG_BF60x) - unsigned long flags; -#endif - port_setup(gpio, GPIO_USAGE); - -#if defined(CONFIG_BF54x) || defined(CONFIG_BF60x) - flags = hard_local_irq_save(); - __bfin_gpio_direction_input(gpio); - hard_local_irq_restore(flags); -#endif } void bfin_gpio_set_value(unsigned gpio, int arg) @@ -1175,11 +1058,7 @@ int bfin_gpio_direction_output(unsigned gpio, int value) gpio_array[gpio_bank(gpio)]->inen &= ~gpio_bit(gpio); gpio_set_value(gpio, value); -#if defined(CONFIG_BF54x) || defined(CONFIG_BF60x) - gpio_array[gpio_bank(gpio)]->dir_set = gpio_bit(gpio); -#else gpio_array[gpio_bank(gpio)]->dir |= gpio_bit(gpio); -#endif AWA_DUMMY_READ(dir); hard_local_irq_restore(flags); @@ -1190,9 +1069,6 @@ EXPORT_SYMBOL(bfin_gpio_direction_output); int bfin_gpio_get_value(unsigned gpio) { -#if defined(CONFIG_BF54x) || defined(CONFIG_BF60x) - return (1 & (gpio_array[gpio_bank(gpio)]->data >> gpio_sub_n(gpio))); -#else unsigned long flags; if (unlikely(get_gpio_edge(gpio))) { @@ -1205,7 +1081,6 @@ int bfin_gpio_get_value(unsigned gpio) return ret; } else return get_gpio_data(gpio); -#endif } EXPORT_SYMBOL(bfin_gpio_get_value); diff --git a/arch/blackfin/mach-bf548/Kconfig b/arch/blackfin/mach-bf548/Kconfig index 94acb586832e..334ec7b12188 100644 --- a/arch/blackfin/mach-bf548/Kconfig +++ b/arch/blackfin/mach-bf548/Kconfig @@ -377,40 +377,6 @@ config IRQ_PINT3 endmenu -comment "Pin Interrupt to Port Assignment" -menu "Assignment" - -config PINTx_REASSIGN - bool "Reprogram PINT Assignment" - default y - help - The interrupt assignment registers controls the pin-to-interrupt - assignment in a byte-wide manner. Each option allows you to select - a set of pins (High/Low Byte) of an specific Port being mapped - to one of the four PIN Interrupts IRQ_PINTx. - - You shouldn't change any of these unless you know exactly what you're doing. - Please consult the Blackfin BF54x Processor Hardware Reference Manual. - -config PINT0_ASSIGN - hex "PINT0_ASSIGN" - depends on PINTx_REASSIGN - default 0x00000101 -config PINT1_ASSIGN - hex "PINT1_ASSIGN" - depends on PINTx_REASSIGN - default 0x01010000 -config PINT2_ASSIGN - hex "PINT2_ASSIGN" - depends on PINTx_REASSIGN - default 0x07000101 -config PINT3_ASSIGN - hex "PINT3_ASSIGN" - depends on PINTx_REASSIGN - default 0x02020303 - -endmenu - endmenu endif diff --git a/arch/blackfin/mach-bf548/boards/ezkit.c b/arch/blackfin/mach-bf548/boards/ezkit.c index 372eb54944ef..d495000b81a0 100644 --- a/arch/blackfin/mach-bf548/boards/ezkit.c +++ b/arch/blackfin/mach-bf548/boards/ezkit.c @@ -17,6 +17,9 @@ #include <linux/i2c.h> #include <linux/interrupt.h> #include <linux/usb/musb.h> +#include <linux/pinctrl/machine.h> +#include <linux/pinctrl/pinconf-generic.h> +#include <linux/platform_data/pinctrl-adi2.h> #include <asm/bfin5xx_spi.h> #include <asm/dma.h> #include <asm/gpio.h> @@ -241,6 +244,13 @@ static struct resource bfin_uart0_resources[] = { .end = UART0_RBR+2, .flags = IORESOURCE_MEM, }, +#ifdef CONFIG_EARLY_PRINTK + { + .start = PORTE_FER, + .end = PORTE_FER+2, + .flags = IORESOURCE_REG, + }, +#endif { .start = IRQ_UART0_TX, .end = IRQ_UART0_TX, @@ -289,6 +299,13 @@ static struct resource bfin_uart1_resources[] = { .end = UART1_RBR+2, .flags = IORESOURCE_MEM, }, +#ifdef CONFIG_EARLY_PRINTK + { + .start = PORTH_FER, + .end = PORTH_FER+2, + .flags = IORESOURCE_REG, + }, +#endif { .start = IRQ_UART1_TX, .end = IRQ_UART1_TX, @@ -353,6 +370,13 @@ static struct resource bfin_uart2_resources[] = { .end = UART2_RBR+2, .flags = IORESOURCE_MEM, }, +#ifdef CONFIG_EARLY_PRINTK + { + .start = PORTB_FER, + .end = PORTB_FER+2, + .flags = IORESOURCE_REG, + }, +#endif { .start = IRQ_UART2_TX, .end = IRQ_UART2_TX, @@ -401,6 +425,13 @@ static struct resource bfin_uart3_resources[] = { .end = UART3_RBR+2, .flags = IORESOURCE_MEM, }, +#ifdef CONFIG_EARLY_PRINTK + { + .start = PORTB_FER, + .end = PORTB_FER+2, + .flags = IORESOURCE_REG, + }, +#endif { .start = IRQ_UART3_TX, .end = IRQ_UART3_TX, @@ -1058,6 +1089,411 @@ static const struct ad7877_platform_data bfin_ad7877_ts_info = { }; #endif +#ifdef CONFIG_PINCTRL_ADI2 + +# define ADI_PINT_DEVNAME "adi-gpio-pint" +# define ADI_GPIO_DEVNAME "adi-gpio" +# define ADI_PINCTRL_DEVNAME "pinctrl-adi2" + +static struct platform_device bfin_pinctrl_device = { + .name = ADI_PINCTRL_DEVNAME, + .id = 0, +}; + +static struct resource bfin_pint0_resources[] = { + { + .start = PINT0_MASK_SET, + .end = PINT0_LATCH + 3, + .flags = IORESOURCE_MEM, + }, + { + .start = IRQ_PINT0, + .end = IRQ_PINT0, + .flags = IORESOURCE_IRQ, + }, +}; + +static struct platform_device bfin_pint0_device = { + .name = ADI_PINT_DEVNAME, + .id = 0, + .num_resources = ARRAY_SIZE(bfin_pint0_resources), + .resource = bfin_pint0_resources, +}; + +static struct resource bfin_pint1_resources[] = { + { + .start = PINT1_MASK_SET, + .end = PINT1_LATCH + 3, + .flags = IORESOURCE_MEM, + }, + { + .start = IRQ_PINT1, + .end = IRQ_PINT1, + .flags = IORESOURCE_IRQ, + }, +}; + +static struct platform_device bfin_pint1_device = { + .name = ADI_PINT_DEVNAME, + .id = 1, + .num_resources = ARRAY_SIZE(bfin_pint1_resources), + .resource = bfin_pint1_resources, +}; + +static struct resource bfin_pint2_resources[] = { + { + .start = PINT2_MASK_SET, + .end = PINT2_LATCH + 3, + .flags = IORESOURCE_MEM, + }, + { + .start = IRQ_PINT2, + .end = IRQ_PINT2, + .flags = IORESOURCE_IRQ, + }, +}; + +static struct platform_device bfin_pint2_device = { + .name = ADI_PINT_DEVNAME, + .id = 2, + .num_resources = ARRAY_SIZE(bfin_pint2_resources), + .resource = bfin_pint2_resources, +}; + +static struct resource bfin_pint3_resources[] = { + { + .start = PINT3_MASK_SET, + .end = PINT3_LATCH + 3, + .flags = IORESOURCE_MEM, + }, + { + .start = IRQ_PINT3, + .end = IRQ_PINT3, + .flags = IORESOURCE_IRQ, + }, +}; + +static struct platform_device bfin_pint3_device = { + .name = ADI_PINT_DEVNAME, + .id = 3, + .num_resources = ARRAY_SIZE(bfin_pint3_resources), + .resource = bfin_pint3_resources, +}; + +static struct resource bfin_gpa_resources[] = { + { + .start = PORTA_FER, + .end = PORTA_MUX + 3, + .flags = IORESOURCE_MEM, + }, + { /* optional */ + .start = IRQ_PA0, + .end = IRQ_PA0, + .flags = IORESOURCE_IRQ, + }, +}; + +static struct adi_pinctrl_gpio_platform_data bfin_gpa_pdata = { + .port_gpio_base = GPIO_PA0, /* Optional */ + .port_pin_base = GPIO_PA0, + .port_width = GPIO_BANKSIZE, + .pint_id = 0, /* PINT0 */ + .pint_assign = true, /* PINT upper 16 bit */ + .pint_map = 0, /* mapping mask in PINT */ +}; + +static struct platform_device bfin_gpa_device = { + .name = ADI_GPIO_DEVNAME, + .id = 0, + .num_resources = ARRAY_SIZE(bfin_gpa_resources), + .resource = bfin_gpa_resources, + .dev = { + .platform_data = &bfin_gpa_pdata, /* Passed to driver */ + }, +}; + +static struct resource bfin_gpb_resources[] = { + { + .start = PORTB_FER, + .end = PORTB_MUX + 3, + .flags = IORESOURCE_MEM, + }, + { + .start = IRQ_PB0, + .end = IRQ_PB0, + .flags = IORESOURCE_IRQ, + }, +}; + +static struct adi_pinctrl_gpio_platform_data bfin_gpb_pdata = { + .port_gpio_base = GPIO_PB0, + .port_pin_base = GPIO_PB0, + .port_width = 15, + .pint_id = 0, + .pint_assign = true, + .pint_map = 1, +}; + +static struct platform_device bfin_gpb_device = { + .name = ADI_GPIO_DEVNAME, + .id = 1, + .num_resources = ARRAY_SIZE(bfin_gpb_resources), + .resource = bfin_gpb_resources, + .dev = { + .platform_data = &bfin_gpb_pdata, /* Passed to driver */ + }, +}; + +static struct resource bfin_gpc_resources[] = { + { + .start = PORTC_FER, + .end = PORTC_MUX + 3, + .flags = IORESOURCE_MEM, + }, + { + .start = IRQ_PC0, + .end = IRQ_PC0, + .flags = IORESOURCE_IRQ, + }, +}; + +static struct adi_pinctrl_gpio_platform_data bfin_gpc_pdata = { + .port_gpio_base = GPIO_PC0, + .port_pin_base = GPIO_PC0, + .port_width = 14, + .pint_id = 2, + .pint_assign = true, + .pint_map = 0, +}; + +static struct platform_device bfin_gpc_device = { + .name = ADI_GPIO_DEVNAME, + .id = 2, + .num_resources = ARRAY_SIZE(bfin_gpc_resources), + .resource = bfin_gpc_resources, + .dev = { + .platform_data = &bfin_gpc_pdata, /* Passed to driver */ + }, +}; + +static struct resource bfin_gpd_resources[] = { + { + .start = PORTD_FER, + .end = PORTD_MUX + 3, + .flags = IORESOURCE_MEM, + }, + { + .start = IRQ_PD0, + .end = IRQ_PD0, + .flags = IORESOURCE_IRQ, + }, +}; + +static struct adi_pinctrl_gpio_platform_data bfin_gpd_pdata = { + .port_gpio_base = GPIO_PD0, + .port_pin_base = GPIO_PD0, + .port_width = GPIO_BANKSIZE, + .pint_id = 2, + .pint_assign = false, + .pint_map = 1, +}; + +static struct platform_device bfin_gpd_device = { + .name = ADI_GPIO_DEVNAME, + .id = 3, + .num_resources = ARRAY_SIZE(bfin_gpd_resources), + .resource = bfin_gpd_resources, + .dev = { + .platform_data = &bfin_gpd_pdata, /* Passed to driver */ + }, +}; + +static struct resource bfin_gpe_resources[] = { + { + .start = PORTE_FER, + .end = PORTE_MUX + 3, + .flags = IORESOURCE_MEM, + }, + { + .start = IRQ_PE0, + .end = IRQ_PE0, + .flags = IORESOURCE_IRQ, + }, +}; + +static struct adi_pinctrl_gpio_platform_data bfin_gpe_pdata = { + .port_gpio_base = GPIO_PE0, + .port_pin_base = GPIO_PE0, + .port_width = GPIO_BANKSIZE, + .pint_id = 3, + .pint_assign = true, + .pint_map = 2, +}; + +static struct platform_device bfin_gpe_device = { + .name = ADI_GPIO_DEVNAME, + .id = 4, + .num_resources = ARRAY_SIZE(bfin_gpe_resources), + .resource = bfin_gpe_resources, + .dev = { + .platform_data = &bfin_gpe_pdata, /* Passed to driver */ + }, +}; + +static struct resource bfin_gpf_resources[] = { + { + .start = PORTF_FER, + .end = PORTF_MUX + 3, + .flags = IORESOURCE_MEM, + }, + { + .start = IRQ_PF0, + .end = IRQ_PF0, + .flags = IORESOURCE_IRQ, + }, +}; + +static struct adi_pinctrl_gpio_platform_data bfin_gpf_pdata = { + .port_gpio_base = GPIO_PF0, + .port_pin_base = GPIO_PF0, + .port_width = GPIO_BANKSIZE, + .pint_id = 3, + .pint_assign = false, + .pint_map = 3, +}; + +static struct platform_device bfin_gpf_device = { + .name = ADI_GPIO_DEVNAME, + .id = 5, + .num_resources = ARRAY_SIZE(bfin_gpf_resources), + .resource = bfin_gpf_resources, + .dev = { + .platform_data = &bfin_gpf_pdata, /* Passed to driver */ + }, +}; + +static struct resource bfin_gpg_resources[] = { + { + .start = PORTG_FER, + .end = PORTG_MUX + 3, + .flags = IORESOURCE_MEM, + }, + { + .start = IRQ_PG0, + .end = IRQ_PG0, + .flags = IORESOURCE_IRQ, + }, +}; + +static struct adi_pinctrl_gpio_platform_data bfin_gpg_pdata = { + .port_gpio_base = GPIO_PG0, + .port_pin_base = GPIO_PG0, + .port_width = GPIO_BANKSIZE, + .pint_id = -1, +}; + +static struct platform_device bfin_gpg_device = { + .name = ADI_GPIO_DEVNAME, + .id = 6, + .num_resources = ARRAY_SIZE(bfin_gpg_resources), + .resource = bfin_gpg_resources, + .dev = { + .platform_data = &bfin_gpg_pdata, /* Passed to driver */ + }, +}; + +static struct resource bfin_gph_resources[] = { + { + .start = PORTH_FER, + .end = PORTH_MUX + 3, + .flags = IORESOURCE_MEM, + }, + { + .start = IRQ_PH0, + .end = IRQ_PH0, + .flags = IORESOURCE_IRQ, + }, +}; + +static struct adi_pinctrl_gpio_platform_data bfin_gph_pdata = { + .port_gpio_base = GPIO_PH0, + .port_pin_base = GPIO_PH0, + .port_width = 14, + .pint_id = -1, +}; + +static struct platform_device bfin_gph_device = { + .name = ADI_GPIO_DEVNAME, + .id = 7, + .num_resources = ARRAY_SIZE(bfin_gph_resources), + .resource = bfin_gph_resources, + .dev = { + .platform_data = &bfin_gph_pdata, /* Passed to driver */ + }, +}; + +static struct resource bfin_gpi_resources[] = { + { + .start = PORTI_FER, + .end = PORTI_MUX + 3, + .flags = IORESOURCE_MEM, + }, + { + .start = IRQ_PI0, + .end = IRQ_PI0, + .flags = IORESOURCE_IRQ, + }, +}; + +static struct adi_pinctrl_gpio_platform_data bfin_gpi_pdata = { + .port_gpio_base = GPIO_PI0, + .port_pin_base = GPIO_PI0, + .port_width = GPIO_BANKSIZE, + .pint_id = -1, +}; + +static struct platform_device bfin_gpi_device = { + .name = ADI_GPIO_DEVNAME, + .id = 8, + .num_resources = ARRAY_SIZE(bfin_gpi_resources), + .resource = bfin_gpi_resources, + .dev = { + .platform_data = &bfin_gpi_pdata, /* Passed to driver */ + }, +}; + +static struct resource bfin_gpj_resources[] = { + { + .start = PORTJ_FER, + .end = PORTJ_MUX + 3, + .flags = IORESOURCE_MEM, + }, + { + .start = IRQ_PJ0, + .end = IRQ_PJ0, + .flags = IORESOURCE_IRQ, + }, +}; + +static struct adi_pinctrl_gpio_platform_data bfin_gpj_pdata = { + .port_gpio_base = GPIO_PJ0, + .port_pin_base = GPIO_PJ0, + .port_width = 14, + .pint_id = -1, +}; + +static struct platform_device bfin_gpj_device = { + .name = ADI_GPIO_DEVNAME, + .id = 9, + .num_resources = ARRAY_SIZE(bfin_gpj_resources), + .resource = bfin_gpj_resources, + .dev = { + .platform_data = &bfin_gpj_pdata, /* Passed to driver */ + }, +}; + +#endif + static struct spi_board_info bfin_spi_board_info[] __initdata = { #if defined(CONFIG_MTD_M25P80) \ || defined(CONFIG_MTD_M25P80_MODULE) @@ -1066,7 +1502,7 @@ static struct spi_board_info bfin_spi_board_info[] __initdata = { .modalias = "m25p80", /* Name of spi_driver for this device */ .max_speed_hz = 25000000, /* max spi clock (SCK) speed in HZ */ .bus_num = 0, /* Framework bus number */ - .chip_select = 1, /* SPI_SSEL1*/ + .chip_select = MAX_CTRL_CS + GPIO_PE4, /* SPI_SSEL1*/ .platform_data = &bfin_spi_flash_data, .controller_data = &spi_flash_chip_info, .mode = SPI_MODE_3, @@ -1078,7 +1514,7 @@ static struct spi_board_info bfin_spi_board_info[] __initdata = { .modalias = "ad183x", .max_speed_hz = 3125000, /* max spi clock (SCK) speed in HZ */ .bus_num = 1, - .chip_select = 4, + .chip_select = MAX_CTRL_CS + GPIO_PG6, /* SPI_SSEL2 */ }, #endif #if defined(CONFIG_TOUCHSCREEN_AD7877) || defined(CONFIG_TOUCHSCREEN_AD7877_MODULE) @@ -1088,7 +1524,7 @@ static struct spi_board_info bfin_spi_board_info[] __initdata = { .irq = IRQ_PB4, /* old boards (<=Rev 1.3) use IRQ_PJ11 */ .max_speed_hz = 12500000, /* max spi clock (SCK) speed in HZ */ .bus_num = 0, - .chip_select = 2, + .chip_select = MAX_CTRL_CS + GPIO_PE5, /* SPI_SSEL2 */ }, #endif #if defined(CONFIG_SPI_SPIDEV) || defined(CONFIG_SPI_SPIDEV_MODULE) @@ -1096,7 +1532,7 @@ static struct spi_board_info bfin_spi_board_info[] __initdata = { .modalias = "spidev", .max_speed_hz = 3125000, /* max spi clock (SCK) speed in HZ */ .bus_num = 0, - .chip_select = 1, + .chip_select = MAX_CTRL_CS + GPIO_PE4, /* SPI_SSEL1 */ }, #endif #if defined(CONFIG_INPUT_ADXL34X_SPI) || defined(CONFIG_INPUT_ADXL34X_SPI_MODULE) @@ -1106,7 +1542,7 @@ static struct spi_board_info bfin_spi_board_info[] __initdata = { .irq = IRQ_PC5, .max_speed_hz = 5000000, /* max spi clock (SCK) speed in HZ */ .bus_num = 1, - .chip_select = 2, + .chip_select = MAX_CTRL_CS + GPIO_PG6, /* SPI_SSEL2 */ .mode = SPI_MODE_3, }, #endif @@ -1152,7 +1588,7 @@ static struct resource bfin_spi1_resource[] = { /* SPI controller data */ static struct bfin5xx_spi_master bf54x_spi_master_info0 = { - .num_chipselect = 4, + .num_chipselect = MAX_CTRL_CS + MAX_BLACKFIN_GPIOS, .enable_dma = 1, /* master has the ability to do dma transfer */ .pin_req = {P_SPI0_SCK, P_SPI0_MISO, P_SPI0_MOSI, 0}, }; @@ -1168,7 +1604,7 @@ static struct platform_device bf54x_spi_master0 = { }; static struct bfin5xx_spi_master bf54x_spi_master_info1 = { - .num_chipselect = 4, + .num_chipselect = MAX_CTRL_CS + MAX_BLACKFIN_GPIOS, .enable_dma = 1, /* master has the ability to do dma transfer */ .pin_req = {P_SPI1_SCK, P_SPI1_MISO, P_SPI1_MOSI, 0}, }; @@ -1508,6 +1944,23 @@ static struct platform_device bfin_ac97 = { static struct platform_device *ezkit_devices[] __initdata = { &bfin_dpmc, +#if defined(CONFIG_PINCTRL_ADI2) + &bfin_pinctrl_device, + &bfin_pint0_device, + &bfin_pint1_device, + &bfin_pint2_device, + &bfin_pint3_device, + &bfin_gpa_device, + &bfin_gpb_device, + &bfin_gpc_device, + &bfin_gpd_device, + &bfin_gpe_device, + &bfin_gpf_device, + &bfin_gpg_device, + &bfin_gph_device, + &bfin_gpi_device, + &bfin_gpj_device, +#endif #if defined(CONFIG_RTC_DRV_BFIN) || defined(CONFIG_RTC_DRV_BFIN_MODULE) &rtc_device, @@ -1644,10 +2097,66 @@ static struct platform_device *ezkit_devices[] __initdata = { #endif }; +/* Pin control settings */ +static struct pinctrl_map __initdata bfin_pinmux_map[] = { + /* per-device maps */ + PIN_MAP_MUX_GROUP_DEFAULT("bfin-uart.0", "pinctrl-adi2.0", NULL, "uart0"), + PIN_MAP_MUX_GROUP_DEFAULT("bfin-uart.1", "pinctrl-adi2.0", NULL, "uart1"), +#ifdef CONFIG_BFIN_UART1_CTSRTS + PIN_MAP_MUX_GROUP_DEFAULT("bfin-uart.1", "pinctrl-adi2.0", NULL, "uart1_ctsrts"), +#endif + PIN_MAP_MUX_GROUP_DEFAULT("bfin-uart.2", "pinctrl-adi2.0", NULL, "uart2"), + PIN_MAP_MUX_GROUP_DEFAULT("bfin-uart.3", "pinctrl-adi2.0", NULL, "uart3"), +#ifdef CONFIG_BFIN_UART3_CTSRTS + PIN_MAP_MUX_GROUP_DEFAULT("bfin-uart.3", "pinctrl-adi2.0", NULL, "uart3_ctsrts"), +#endif + PIN_MAP_MUX_GROUP_DEFAULT("bfin_sir.0", "pinctrl-adi2.0", NULL, "uart0"), + PIN_MAP_MUX_GROUP_DEFAULT("bfin_sir.1", "pinctrl-adi2.0", NULL, "uart1"), + PIN_MAP_MUX_GROUP_DEFAULT("bfin_sir.2", "pinctrl-adi2.0", NULL, "uart2"), + PIN_MAP_MUX_GROUP_DEFAULT("bfin_sir.3", "pinctrl-adi2.0", NULL, "uart3"), + PIN_MAP_MUX_GROUP_DEFAULT("bfin-sdh.0", "pinctrl-adi2.0", NULL, "rsi0"), + PIN_MAP_MUX_GROUP_DEFAULT("bfin-spi.0", "pinctrl-adi2.0", NULL, "spi0"), + PIN_MAP_MUX_GROUP_DEFAULT("bfin-spi.1", "pinctrl-adi2.0", NULL, "spi1"), + PIN_MAP_MUX_GROUP_DEFAULT("i2c-bfin-twi.0", "pinctrl-adi2.0", NULL, "twi0"), +#if !defined(CONFIG_BF542) /* The BF542 only has 1 TWI */ + PIN_MAP_MUX_GROUP_DEFAULT("i2c-bfin-twi.1", "pinctrl-adi2.0", NULL, "twi1"), +#endif + PIN_MAP_MUX_GROUP_DEFAULT("bfin-rotary", "pinctrl-adi2.0", NULL, "rotary"), + PIN_MAP_MUX_GROUP_DEFAULT("bfin_can.0", "pinctrl-adi2.0", NULL, "can0"), + PIN_MAP_MUX_GROUP_DEFAULT("bfin_can.1", "pinctrl-adi2.0", NULL, "can1"), + PIN_MAP_MUX_GROUP_DEFAULT("bf54x-lq043", "pinctrl-adi2.0", NULL, "ppi0_24b"), + PIN_MAP_MUX_GROUP_DEFAULT("bfin-i2s.0", "pinctrl-adi2.0", NULL, "sport0"), + PIN_MAP_MUX_GROUP_DEFAULT("bfin-tdm.0", "pinctrl-adi2.0", NULL, "sport0"), + PIN_MAP_MUX_GROUP_DEFAULT("bfin-ac97.0", "pinctrl-adi2.0", NULL, "sport0"), + PIN_MAP_MUX_GROUP_DEFAULT("bfin-i2s.1", "pinctrl-adi2.0", NULL, "sport1"), + PIN_MAP_MUX_GROUP_DEFAULT("bfin-tdm.1", "pinctrl-adi2.0", NULL, "sport1"), + PIN_MAP_MUX_GROUP_DEFAULT("bfin-ac97.1", "pinctrl-adi2.0", NULL, "sport1"), + PIN_MAP_MUX_GROUP_DEFAULT("bfin-i2s.2", "pinctrl-adi2.0", NULL, "sport2"), + PIN_MAP_MUX_GROUP_DEFAULT("bfin-tdm.2", "pinctrl-adi2.0", NULL, "sport2"), + PIN_MAP_MUX_GROUP_DEFAULT("bfin-ac97.2", "pinctrl-adi2.0", NULL, "sport2"), + PIN_MAP_MUX_GROUP_DEFAULT("bfin-i2s.3", "pinctrl-adi2.0", NULL, "sport3"), + PIN_MAP_MUX_GROUP_DEFAULT("bfin-tdm.3", "pinctrl-adi2.0", NULL, "sport3"), + PIN_MAP_MUX_GROUP_DEFAULT("bfin-ac97.3", "pinctrl-adi2.0", NULL, "sport3"), + PIN_MAP_MUX_GROUP_DEFAULT("bfin-sport-uart.0", "pinctrl-adi2.0", NULL, "sport0"), + PIN_MAP_MUX_GROUP_DEFAULT("bfin-sport-uart.1", "pinctrl-adi2.0", NULL, "sport1"), + PIN_MAP_MUX_GROUP_DEFAULT("bfin-sport-uart.2", "pinctrl-adi2.0", NULL, "sport2"), + PIN_MAP_MUX_GROUP_DEFAULT("bfin-sport-uart.3", "pinctrl-adi2.0", NULL, "sport3"), + PIN_MAP_MUX_GROUP_DEFAULT("pata-bf54x", "pinctrl-adi2.0", NULL, "atapi"), +#ifdef CONFIG_BF548_ATAPI_ALTERNATIVE_PORT + PIN_MAP_MUX_GROUP_DEFAULT("pata-bf54x", "pinctrl-adi2.0", NULL, "atapi_alter"), +#endif + PIN_MAP_MUX_GROUP_DEFAULT("bf5xx-nand.0", "pinctrl-adi2.0", NULL, "nfc0"), + PIN_MAP_MUX_GROUP_DEFAULT("bf54x-keys", "pinctrl-adi2.0", NULL, "keys_4x4"), +}; + static int __init ezkit_init(void) { printk(KERN_INFO "%s(): registering device resources\n", __func__); + /* Initialize pinmuxing */ + pinctrl_register_mappings(bfin_pinmux_map, + ARRAY_SIZE(bfin_pinmux_map)); + i2c_register_board_info(0, bfin_i2c_board_info0, ARRAY_SIZE(bfin_i2c_board_info0)); #if !defined(CONFIG_BF542) /* The BF542 only has 1 TWI */ @@ -1679,21 +2188,6 @@ static struct platform_device *ezkit_early_devices[] __initdata = { &bfin_uart3_device, #endif #endif - -#if defined(CONFIG_SERIAL_BFIN_SPORT_CONSOLE) -#ifdef CONFIG_SERIAL_BFIN_SPORT0_UART - &bfin_sport0_uart_device, -#endif -#ifdef CONFIG_SERIAL_BFIN_SPORT1_UART - &bfin_sport1_uart_device, -#endif -#ifdef CONFIG_SERIAL_BFIN_SPORT2_UART - &bfin_sport2_uart_device, -#endif -#ifdef CONFIG_SERIAL_BFIN_SPORT3_UART - &bfin_sport3_uart_device, -#endif -#endif }; void __init native_machine_early_platform_add_devices(void) diff --git a/arch/blackfin/mach-bf548/include/mach/gpio.h b/arch/blackfin/mach-bf548/include/mach/gpio.h index be9edb28f96b..006da1edcf84 100644 --- a/arch/blackfin/mach-bf548/include/mach/gpio.h +++ b/arch/blackfin/mach-bf548/include/mach/gpio.h @@ -194,14 +194,6 @@ struct gpio_port_t { unsigned int port_mux; }; -struct gpio_port_s { - unsigned short fer; - unsigned short data; - unsigned short dir; - unsigned short inen; - unsigned int mux; -}; - #endif #include <mach-common/ports-a.h> diff --git a/arch/blackfin/mach-bf548/include/mach/irq.h b/arch/blackfin/mach-bf548/include/mach/irq.h index 10dc142c518d..cf7cb725cfa2 100644 --- a/arch/blackfin/mach-bf548/include/mach/irq.h +++ b/arch/blackfin/mach-bf548/include/mach/irq.h @@ -433,7 +433,7 @@ #include <linux/types.h> /* - * bfin pint registers layout + * gpio pint registers layout */ struct bfin_pint_regs { u32 mask_set; diff --git a/arch/blackfin/mach-bf609/Kconfig b/arch/blackfin/mach-bf609/Kconfig index 2bcbf94b1edf..b0fca44110b0 100644 --- a/arch/blackfin/mach-bf609/Kconfig +++ b/arch/blackfin/mach-bf609/Kconfig @@ -9,48 +9,6 @@ source "arch/blackfin/mach-bf609/boards/Kconfig" menu "BF609 Specific Configuration" -comment "Pin Interrupt to Port Assignment" -menu "Assignment" - -config PINTx_REASSIGN - bool "Reprogram PINT Assignment" - default y - help - The interrupt assignment registers controls the pin-to-interrupt - assignment in a byte-wide manner. Each option allows you to select - a set of pins (High/Low Byte) of an specific Port being mapped - to one of the four PIN Interrupts IRQ_PINTx. - - You shouldn't change any of these unless you know exactly what you're doing. - Please consult the Blackfin BF60x Processor Hardware Reference Manual. - -config PINT0_ASSIGN - hex "PINT0_ASSIGN" - depends on PINTx_REASSIGN - default 0x00000101 -config PINT1_ASSIGN - hex "PINT1_ASSIGN" - depends on PINTx_REASSIGN - default 0x00000101 -config PINT2_ASSIGN - hex "PINT2_ASSIGN" - depends on PINTx_REASSIGN - default 0x00000101 -config PINT3_ASSIGN - hex "PINT3_ASSIGN" - depends on PINTx_REASSIGN - default 0x00000101 -config PINT4_ASSIGN - hex "PINT3_ASSIGN" - depends on PINTx_REASSIGN - default 0x00000101 -config PINT5_ASSIGN - hex "PINT3_ASSIGN" - depends on PINTx_REASSIGN - default 0x00000101 - -endmenu - config SEC_IRQ_PRIORITY_LEVELS int "SEC interrupt priority levels" default 7 diff --git a/arch/blackfin/mach-bf609/boards/ezkit.c b/arch/blackfin/mach-bf609/boards/ezkit.c index d56a55ad83a7..82beedd953f6 100644 --- a/arch/blackfin/mach-bf609/boards/ezkit.c +++ b/arch/blackfin/mach-bf609/boards/ezkit.c @@ -17,6 +17,9 @@ #include <linux/i2c.h> #include <linux/interrupt.h> #include <linux/usb/musb.h> +#include <linux/pinctrl/machine.h> +#include <linux/pinctrl/pinconf-generic.h> +#include <linux/platform_data/pinctrl-adi2.h> #include <asm/bfin_spi3.h> #include <asm/dma.h> #include <asm/gpio.h> @@ -106,8 +109,6 @@ static struct platform_device bfin_rotary_device = { #include <linux/stmmac.h> #include <linux/phy.h> -static unsigned short pins[] = P_RMII0; - static struct stmmac_mdio_bus_data phy_private_data = { .phy_mask = 1, }; @@ -212,6 +213,18 @@ static struct resource bfin_uart0_resources[] = { .end = UART0_RXDIV+4, .flags = IORESOURCE_MEM, }, +#ifdef CONFIG_EARLY_PRINTK + { + .start = PORTD_FER, + .end = PORTD_FER+2, + .flags = IORESOURCE_REG, + }, + { + .start = PORTD_MUX, + .end = PORTD_MUX+3, + .flags = IORESOURCE_REG, + }, +#endif { .start = IRQ_UART0_TX, .end = IRQ_UART0_TX, @@ -276,6 +289,13 @@ static struct resource bfin_uart1_resources[] = { .end = UART1_RXDIV+4, .flags = IORESOURCE_MEM, }, +#ifdef CONFIG_EARLY_PRINTK + { + .start = PORTG_FER_SET, + .end = PORTG_FER_SET+2, + .flags = IORESOURCE_REG, + }, +#endif { .start = IRQ_UART1_TX, .end = IRQ_UART1_TX, @@ -674,17 +694,12 @@ static struct mtd_partition ezkit_partitions[] = { }, }; -int bf609_nor_flash_init(struct platform_device *dev) +int bf609_nor_flash_init(struct platform_device *pdev) { #define CONFIG_SMC_GCTL_VAL 0x00000010 - const unsigned short pins[] = { - P_A3, P_A4, P_A5, P_A6, P_A7, P_A8, P_A9, P_A10, P_A11, P_A12, - P_A13, P_A14, P_A15, P_A16, P_A17, P_A18, P_A19, P_A20, P_A21, - P_A22, P_A23, P_A24, P_A25, P_NORCK, 0, - }; - - peripheral_request_list(pins, "smc0"); + if (!devm_pinctrl_get_select_default(&pdev->dev)) + return -EBUSY; bfin_write32(SMC_GCTL, CONFIG_SMC_GCTL_VAL); bfin_write32(SMC_B0CTL, 0x01002011); bfin_write32(SMC_B0TIM, 0x08170977); @@ -692,16 +707,9 @@ int bf609_nor_flash_init(struct platform_device *dev) return 0; } -void bf609_nor_flash_exit(struct platform_device *dev) +void bf609_nor_flash_exit(struct platform_device *pdev) { - const unsigned short pins[] = { - P_A3, P_A4, P_A5, P_A6, P_A7, P_A8, P_A9, P_A10, P_A11, P_A12, - P_A13, P_A14, P_A15, P_A16, P_A17, P_A18, P_A19, P_A20, P_A21, - P_A22, P_A23, P_A24, P_A25, P_NORCK, 0, - }; - - peripheral_free_list(pins); - + devm_pinctrl_put(pdev->dev.pins->p); bfin_write32(SMC_GCTL, 0); } @@ -1319,6 +1327,356 @@ static const struct ad7877_platform_data bfin_ad7877_ts_info = { }; #endif +#ifdef CONFIG_PINCTRL_ADI2 + +# define ADI_PINT_DEVNAME "adi-gpio-pint" +# define ADI_GPIO_DEVNAME "adi-gpio" +# define ADI_PINCTRL_DEVNAME "pinctrl-adi2" + +static struct platform_device bfin_pinctrl_device = { + .name = ADI_PINCTRL_DEVNAME, + .id = 0, +}; + +static struct resource bfin_pint0_resources[] = { + { + .start = PINT0_MASK_SET, + .end = PINT0_LATCH + 3, + .flags = IORESOURCE_MEM, + }, + { + .start = IRQ_PINT0, + .end = IRQ_PINT0, + .flags = IORESOURCE_IRQ, + }, +}; + +static struct platform_device bfin_pint0_device = { + .name = ADI_PINT_DEVNAME, + .id = 0, + .num_resources = ARRAY_SIZE(bfin_pint0_resources), + .resource = bfin_pint0_resources, +}; + +static struct resource bfin_pint1_resources[] = { + { + .start = PINT1_MASK_SET, + .end = PINT1_LATCH + 3, + .flags = IORESOURCE_MEM, + }, + { + .start = IRQ_PINT1, + .end = IRQ_PINT1, + .flags = IORESOURCE_IRQ, + }, +}; + +static struct platform_device bfin_pint1_device = { + .name = ADI_PINT_DEVNAME, + .id = 1, + .num_resources = ARRAY_SIZE(bfin_pint1_resources), + .resource = bfin_pint1_resources, +}; + +static struct resource bfin_pint2_resources[] = { + { + .start = PINT2_MASK_SET, + .end = PINT2_LATCH + 3, + .flags = IORESOURCE_MEM, + }, + { + .start = IRQ_PINT2, + .end = IRQ_PINT2, + .flags = IORESOURCE_IRQ, + }, +}; + +static struct platform_device bfin_pint2_device = { + .name = ADI_PINT_DEVNAME, + .id = 2, + .num_resources = ARRAY_SIZE(bfin_pint2_resources), + .resource = bfin_pint2_resources, +}; + +static struct resource bfin_pint3_resources[] = { + { + .start = PINT3_MASK_SET, + .end = PINT3_LATCH + 3, + .flags = IORESOURCE_MEM, + }, + { + .start = IRQ_PINT3, + .end = IRQ_PINT3, + .flags = IORESOURCE_IRQ, + }, +}; + +static struct platform_device bfin_pint3_device = { + .name = ADI_PINT_DEVNAME, + .id = 3, + .num_resources = ARRAY_SIZE(bfin_pint3_resources), + .resource = bfin_pint3_resources, +}; + +static struct resource bfin_pint4_resources[] = { + { + .start = PINT4_MASK_SET, + .end = PINT4_LATCH + 3, + .flags = IORESOURCE_MEM, + }, + { + .start = IRQ_PINT4, + .end = IRQ_PINT4, + .flags = IORESOURCE_IRQ, + }, +}; + +static struct platform_device bfin_pint4_device = { + .name = ADI_PINT_DEVNAME, + .id = 4, + .num_resources = ARRAY_SIZE(bfin_pint4_resources), + .resource = bfin_pint4_resources, +}; + +static struct resource bfin_pint5_resources[] = { + { + .start = PINT5_MASK_SET, + .end = PINT5_LATCH + 3, + .flags = IORESOURCE_MEM, + }, + { + .start = IRQ_PINT5, + .end = IRQ_PINT5, + .flags = IORESOURCE_IRQ, + }, +}; + +static struct platform_device bfin_pint5_device = { + .name = ADI_PINT_DEVNAME, + .id = 5, + .num_resources = ARRAY_SIZE(bfin_pint5_resources), + .resource = bfin_pint5_resources, +}; + +static struct resource bfin_gpa_resources[] = { + { + .start = PORTA_FER, + .end = PORTA_MUX + 3, + .flags = IORESOURCE_MEM, + }, + { /* optional */ + .start = IRQ_PA0, + .end = IRQ_PA0, + .flags = IORESOURCE_IRQ, + }, +}; + +static struct adi_pinctrl_gpio_platform_data bfin_gpa_pdata = { + .port_pin_base = GPIO_PA0, + .port_width = GPIO_BANKSIZE, + .pint_id = 0, /* PINT0 */ + .pint_assign = true, /* PINT upper 16 bit */ + .pint_map = 0, /* mapping mask in PINT */ +}; + +static struct platform_device bfin_gpa_device = { + .name = ADI_GPIO_DEVNAME, + .id = 0, + .num_resources = ARRAY_SIZE(bfin_gpa_resources), + .resource = bfin_gpa_resources, + .dev = { + .platform_data = &bfin_gpa_pdata, /* Passed to driver */ + }, +}; + +static struct resource bfin_gpb_resources[] = { + { + .start = PORTB_FER, + .end = PORTB_MUX + 3, + .flags = IORESOURCE_MEM, + }, + { + .start = IRQ_PB0, + .end = IRQ_PB0, + .flags = IORESOURCE_IRQ, + }, +}; + +static struct adi_pinctrl_gpio_platform_data bfin_gpb_pdata = { + .port_pin_base = GPIO_PB0, + .port_width = GPIO_BANKSIZE, + .pint_id = 0, + .pint_assign = false, + .pint_map = 1, +}; + +static struct platform_device bfin_gpb_device = { + .name = ADI_GPIO_DEVNAME, + .id = 1, + .num_resources = ARRAY_SIZE(bfin_gpb_resources), + .resource = bfin_gpb_resources, + .dev = { + .platform_data = &bfin_gpb_pdata, /* Passed to driver */ + }, +}; + +static struct resource bfin_gpc_resources[] = { + { + .start = PORTC_FER, + .end = PORTC_MUX + 3, + .flags = IORESOURCE_MEM, + }, + { + .start = IRQ_PC0, + .end = IRQ_PC0, + .flags = IORESOURCE_IRQ, + }, +}; + +static struct adi_pinctrl_gpio_platform_data bfin_gpc_pdata = { + .port_pin_base = GPIO_PC0, + .port_width = GPIO_BANKSIZE, + .pint_id = 1, + .pint_assign = false, + .pint_map = 1, +}; + +static struct platform_device bfin_gpc_device = { + .name = ADI_GPIO_DEVNAME, + .id = 2, + .num_resources = ARRAY_SIZE(bfin_gpc_resources), + .resource = bfin_gpc_resources, + .dev = { + .platform_data = &bfin_gpc_pdata, /* Passed to driver */ + }, +}; + +static struct resource bfin_gpd_resources[] = { + { + .start = PORTD_FER, + .end = PORTD_MUX + 3, + .flags = IORESOURCE_MEM, + }, + { + .start = IRQ_PD0, + .end = IRQ_PD0, + .flags = IORESOURCE_IRQ, + }, +}; + +static struct adi_pinctrl_gpio_platform_data bfin_gpd_pdata = { + .port_pin_base = GPIO_PD0, + .port_width = GPIO_BANKSIZE, + .pint_id = 2, + .pint_assign = false, + .pint_map = 1, +}; + +static struct platform_device bfin_gpd_device = { + .name = ADI_GPIO_DEVNAME, + .id = 3, + .num_resources = ARRAY_SIZE(bfin_gpd_resources), + .resource = bfin_gpd_resources, + .dev = { + .platform_data = &bfin_gpd_pdata, /* Passed to driver */ + }, +}; + +static struct resource bfin_gpe_resources[] = { + { + .start = PORTE_FER, + .end = PORTE_MUX + 3, + .flags = IORESOURCE_MEM, + }, + { + .start = IRQ_PE0, + .end = IRQ_PE0, + .flags = IORESOURCE_IRQ, + }, +}; + +static struct adi_pinctrl_gpio_platform_data bfin_gpe_pdata = { + .port_pin_base = GPIO_PE0, + .port_width = GPIO_BANKSIZE, + .pint_id = 3, + .pint_assign = false, + .pint_map = 1, +}; + +static struct platform_device bfin_gpe_device = { + .name = ADI_GPIO_DEVNAME, + .id = 4, + .num_resources = ARRAY_SIZE(bfin_gpe_resources), + .resource = bfin_gpe_resources, + .dev = { + .platform_data = &bfin_gpe_pdata, /* Passed to driver */ + }, +}; + +static struct resource bfin_gpf_resources[] = { + { + .start = PORTF_FER, + .end = PORTF_MUX + 3, + .flags = IORESOURCE_MEM, + }, + { + .start = IRQ_PF0, + .end = IRQ_PF0, + .flags = IORESOURCE_IRQ, + }, +}; + +static struct adi_pinctrl_gpio_platform_data bfin_gpf_pdata = { + .port_pin_base = GPIO_PF0, + .port_width = GPIO_BANKSIZE, + .pint_id = 4, + .pint_assign = false, + .pint_map = 1, +}; + +static struct platform_device bfin_gpf_device = { + .name = ADI_GPIO_DEVNAME, + .id = 5, + .num_resources = ARRAY_SIZE(bfin_gpf_resources), + .resource = bfin_gpf_resources, + .dev = { + .platform_data = &bfin_gpf_pdata, /* Passed to driver */ + }, +}; + +static struct resource bfin_gpg_resources[] = { + { + .start = PORTG_FER, + .end = PORTG_MUX + 3, + .flags = IORESOURCE_MEM, + }, + { + .start = IRQ_PG0, + .end = IRQ_PG0, + .flags = IORESOURCE_IRQ, + }, +}; + +static struct adi_pinctrl_gpio_platform_data bfin_gpg_pdata = { + .port_pin_base = GPIO_PG0, + .port_width = GPIO_BANKSIZE, + .pint_id = 5, + .pint_assign = false, + .pint_map = 1, +}; + +static struct platform_device bfin_gpg_device = { + .name = ADI_GPIO_DEVNAME, + .id = 6, + .num_resources = ARRAY_SIZE(bfin_gpg_resources), + .resource = bfin_gpg_resources, + .dev = { + .platform_data = &bfin_gpg_pdata, /* Passed to driver */ + }, +}; + +#endif + #if defined(CONFIG_KEYBOARD_GPIO) || defined(CONFIG_KEYBOARD_GPIO_MODULE) #include <linux/input.h> #include <linux/gpio_keys.h> @@ -1349,7 +1707,7 @@ static struct spi_board_info bfin_spi_board_info[] __initdata = { .modalias = "m25p80", /* Name of spi_driver for this device */ .max_speed_hz = 25000000, /* max spi clock (SCK) speed in HZ */ .bus_num = 0, /* Framework bus number */ - .chip_select = 1, /* SPI_SSEL1*/ + .chip_select = MAX_CTRL_CS + GPIO_PD11, /* SPI_SSEL1*/ .platform_data = &bfin_spi_flash_data, .controller_data = &spi_flash_chip_info, .mode = SPI_MODE_3, @@ -1362,7 +1720,7 @@ static struct spi_board_info bfin_spi_board_info[] __initdata = { .irq = IRQ_PD9, .max_speed_hz = 12500000, /* max spi clock (SCK) speed in HZ */ .bus_num = 0, - .chip_select = 4, + .chip_select = MAX_CTRL_CS + GPIO_PC15, /* SPI_SSEL4 */ }, #endif #if defined(CONFIG_SPI_SPIDEV) || defined(CONFIG_SPI_SPIDEV_MODULE) @@ -1370,7 +1728,7 @@ static struct spi_board_info bfin_spi_board_info[] __initdata = { .modalias = "spidev", .max_speed_hz = 3125000, /* max spi clock (SCK) speed in HZ */ .bus_num = 0, - .chip_select = 1, + .chip_select = MAX_CTRL_CS + GPIO_PD11, /* SPI_SSEL1*/ .controller_data = &spidev_chip_info, }, #endif @@ -1565,6 +1923,22 @@ static struct platform_device bfin_dpmc = { static struct platform_device *ezkit_devices[] __initdata = { &bfin_dpmc, +#if defined(CONFIG_PINCTRL_ADI2) + &bfin_pinctrl_device, + &bfin_pint0_device, + &bfin_pint1_device, + &bfin_pint2_device, + &bfin_pint3_device, + &bfin_pint4_device, + &bfin_pint5_device, + &bfin_gpa_device, + &bfin_gpb_device, + &bfin_gpc_device, + &bfin_gpd_device, + &bfin_gpe_device, + &bfin_gpf_device, + &bfin_gpg_device, +#endif #if defined(CONFIG_RTC_DRV_BFIN) || defined(CONFIG_RTC_DRV_BFIN_MODULE) &rtc_device, @@ -1681,20 +2055,52 @@ static struct platform_device *ezkit_devices[] __initdata = { }; +/* Pin control settings */ +static struct pinctrl_map __initdata bfin_pinmux_map[] = { + /* per-device maps */ + PIN_MAP_MUX_GROUP_DEFAULT("bfin-uart.0", "pinctrl-adi2.0", NULL, "uart0"), + PIN_MAP_MUX_GROUP_DEFAULT("bfin-uart.1", "pinctrl-adi2.0", NULL, "uart1"), + PIN_MAP_MUX_GROUP_DEFAULT("bfin_sir.0", "pinctrl-adi2.0", NULL, "uart0"), + PIN_MAP_MUX_GROUP_DEFAULT("bfin_sir.1", "pinctrl-adi2.0", NULL, "uart1"), + PIN_MAP_MUX_GROUP_DEFAULT("bfin-sdh.0", "pinctrl-adi2.0", NULL, "rsi0"), + PIN_MAP_MUX_GROUP_DEFAULT("stmmaceth.0", "pinctrl-adi2.0", NULL, "eth0"), + PIN_MAP_MUX_GROUP_DEFAULT("bfin-spi3.0", "pinctrl-adi2.0", NULL, "spi0"), + PIN_MAP_MUX_GROUP_DEFAULT("bfin-spi3.1", "pinctrl-adi2.0", NULL, "spi1"), + PIN_MAP_MUX_GROUP_DEFAULT("i2c-bfin-twi.0", "pinctrl-adi2.0", NULL, "twi0"), + PIN_MAP_MUX_GROUP_DEFAULT("i2c-bfin-twi.1", "pinctrl-adi2.0", NULL, "twi1"), + PIN_MAP_MUX_GROUP_DEFAULT("bfin-rotary", "pinctrl-adi2.0", NULL, "rotary"), + PIN_MAP_MUX_GROUP_DEFAULT("bfin_can.0", "pinctrl-adi2.0", NULL, "can0"), + PIN_MAP_MUX_GROUP_DEFAULT("physmap-flash.0", "pinctrl-adi2.0", NULL, "smc0"), + PIN_MAP_MUX_GROUP_DEFAULT("bf609_nl8048.2", "pinctrl-adi2.0", NULL, "ppi2_16b"), + PIN_MAP_MUX_GROUP_DEFAULT("bfin_display.0", "pinctrl-adi2.0", NULL, "ppi0_16b"), +#if defined(CONFIG_VIDEO_MT9M114) || defined(CONFIG_VIDEO_MT9M114_MODULE) + PIN_MAP_MUX_GROUP_DEFAULT("bfin_capture.0", "pinctrl-adi2.0", NULL, "ppi0_8b"), +#elif defined(CONFIG_VIDEO_VS6624) || defined(CONFIG_VIDEO_VS6624_MODULE) + PIN_MAP_MUX_GROUP_DEFAULT("bfin_capture.0", "pinctrl-adi2.0", NULL, "ppi0_16b"), +#else + PIN_MAP_MUX_GROUP_DEFAULT("bfin_capture.0", "pinctrl-adi2.0", NULL, "ppi0_24b"), +#endif + PIN_MAP_MUX_GROUP_DEFAULT("bfin-i2s.0", "pinctrl-adi2.0", NULL, "sport0"), + PIN_MAP_MUX_GROUP_DEFAULT("bfin-tdm.0", "pinctrl-adi2.0", NULL, "sport0"), + PIN_MAP_MUX_GROUP_DEFAULT("bfin-i2s.1", "pinctrl-adi2.0", NULL, "sport1"), + PIN_MAP_MUX_GROUP_DEFAULT("bfin-tdm.1", "pinctrl-adi2.0", NULL, "sport1"), + PIN_MAP_MUX_GROUP_DEFAULT("bfin-i2s.2", "pinctrl-adi2.0", NULL, "sport2"), + PIN_MAP_MUX_GROUP_DEFAULT("bfin-tdm.2", "pinctrl-adi2.0", NULL, "sport2"), +}; + static int __init ezkit_init(void) { printk(KERN_INFO "%s(): registering device resources\n", __func__); + /* Initialize pinmuxing */ + pinctrl_register_mappings(bfin_pinmux_map, + ARRAY_SIZE(bfin_pinmux_map)); + i2c_register_board_info(0, bfin_i2c_board_info0, ARRAY_SIZE(bfin_i2c_board_info0)); i2c_register_board_info(1, bfin_i2c_board_info1, ARRAY_SIZE(bfin_i2c_board_info1)); -#if defined(CONFIG_STMMAC_ETH) || defined(CONFIG_STMMAC_ETH_MODULE) - if (!peripheral_request_list(pins, "emac0")) - printk(KERN_ERR "%s(): request emac pins failed\n", __func__); -#endif - platform_add_devices(ezkit_devices, ARRAY_SIZE(ezkit_devices)); spi_register_board_info(bfin_spi_board_info, ARRAY_SIZE(bfin_spi_board_info)); @@ -1713,18 +2119,6 @@ static struct platform_device *ezkit_early_devices[] __initdata = { &bfin_uart1_device, #endif #endif - -#if defined(CONFIG_SERIAL_BFIN_SPORT_CONSOLE) -#ifdef CONFIG_SERIAL_BFIN_SPORT0_UART - &bfin_sport0_uart_device, -#endif -#ifdef CONFIG_SERIAL_BFIN_SPORT1_UART - &bfin_sport1_uart_device, -#endif -#ifdef CONFIG_SERIAL_BFIN_SPORT2_UART - &bfin_sport2_uart_device, -#endif -#endif }; void __init native_machine_early_platform_add_devices(void) diff --git a/arch/blackfin/mach-bf609/include/mach/gpio.h b/arch/blackfin/mach-bf609/include/mach/gpio.h index c32c8cc8db2e..07182513e794 100644 --- a/arch/blackfin/mach-bf609/include/mach/gpio.h +++ b/arch/blackfin/mach-bf609/include/mach/gpio.h @@ -152,14 +152,6 @@ struct gpio_port_t { unsigned long revid; }; -struct gpio_port_s { - unsigned short fer; - unsigned short data; - unsigned short dir; - unsigned short inen; - unsigned int mux; -}; - #endif #include <mach-common/ports-a.h> diff --git a/arch/blackfin/mach-bf609/include/mach/irq.h b/arch/blackfin/mach-bf609/include/mach/irq.h index fa0843d5d77a..d1cb6a86f80a 100644 --- a/arch/blackfin/mach-bf609/include/mach/irq.h +++ b/arch/blackfin/mach-bf609/include/mach/irq.h @@ -298,7 +298,7 @@ extern u8 sec_int_priority[]; /* - * bfin pint registers layout + * gpio pint registers layout */ struct bfin_pint_regs { u32 mask_set; diff --git a/arch/blackfin/mach-bf609/include/mach/portmux.h b/arch/blackfin/mach-bf609/include/mach/portmux.h index fe34191eef0b..c48bb71a55ce 100644 --- a/arch/blackfin/mach-bf609/include/mach/portmux.h +++ b/arch/blackfin/mach-bf609/include/mach/portmux.h @@ -19,6 +19,7 @@ #define P_MII0_CRS (P_DEFINED | P_IDENT(GPIO_PC5) | P_FUNCT(0)) #define P_MII0_ERxER (P_DEFINED | P_IDENT(GPIO_PC4) | P_FUNCT(0)) #define P_MII0_TxCLK (P_DEFINED | P_IDENT(GPIO_PB14) | P_FUNCT(0)) +#define P_MII0_PTPPPS (P_DEFINED | P_IDENT(GPIO_PB15) | P_FUNCT(0)) #define P_RMII0 {\ P_MII0_ETxD0, \ @@ -30,6 +31,7 @@ P_MII0_TxCLK, \ P_MII0_PHYINT, \ P_MII0_CRS, \ + P_MII0_PTPPPS, \ P_MII0_MDC, \ P_MII0_MDIO, 0} @@ -44,6 +46,7 @@ #define P_MII1_CRS (P_DEFINED | P_IDENT(GPIO_PE13) | P_FUNCT(0)) #define P_MII1_ERxER (P_DEFINED | P_IDENT(GPIO_PE14) | P_FUNCT(0)) #define P_MII1_TxCLK (P_DEFINED | P_IDENT(GPIO_PG6) | P_FUNCT(0)) +#define P_MII1_PTPPPS (P_DEFINED | P_IDENT(GPIO_PC9) | P_FUNCT(0)) #define P_RMII1 {\ P_MII1_ETxD0, \ @@ -55,6 +58,7 @@ P_MII1_TxCLK, \ P_MII1_PHYINT, \ P_MII1_CRS, \ + P_MII1_PTPPPS, \ P_MII1_MDC, \ P_MII1_MDIO, 0} diff --git a/arch/blackfin/mach-common/ints-priority.c b/arch/blackfin/mach-common/ints-priority.c index d143fd8d2bc5..ca75613231c8 100644 --- a/arch/blackfin/mach-common/ints-priority.c +++ b/arch/blackfin/mach-common/ints-priority.c @@ -704,10 +704,9 @@ static inline void bfin_set_irq_handler(unsigned irq, irq_flow_handler_t handle) __irq_set_handler_locked(irq, handle); } -static DECLARE_BITMAP(gpio_enabled, MAX_BLACKFIN_GPIOS); -extern void bfin_gpio_irq_prepare(unsigned gpio); +#ifdef CONFIG_GPIO_ADI -#if !BFIN_GPIO_PINT +static DECLARE_BITMAP(gpio_enabled, MAX_BLACKFIN_GPIOS); static void bfin_gpio_ack_irq(struct irq_data *d) { @@ -821,15 +820,6 @@ static int bfin_gpio_irq_type(struct irq_data *d, unsigned int type) return 0; } -#ifdef CONFIG_PM -static int bfin_gpio_set_wake(struct irq_data *d, unsigned int state) -{ - return gpio_pm_wakeup_ctrl(irq_to_gpio(d->irq), state); -} -#else -# define bfin_gpio_set_wake NULL -#endif - static void bfin_demux_gpio_block(unsigned int irq) { unsigned int gpio, mask; @@ -896,279 +886,40 @@ void bfin_demux_gpio_irq(unsigned int inta_irq, bfin_demux_gpio_block(irq); } -#else - -#define NR_PINT_BITS 32 -#define IRQ_NOT_AVAIL 0xFF - -#define PINT_2_BANK(x) ((x) >> 5) -#define PINT_2_BIT(x) ((x) & 0x1F) -#define PINT_BIT(x) (1 << (PINT_2_BIT(x))) - -static unsigned char irq2pint_lut[NR_PINTS]; -static unsigned char pint2irq_lut[NR_PINT_SYS_IRQS * NR_PINT_BITS]; - -static struct bfin_pint_regs * const pint[NR_PINT_SYS_IRQS] = { - (struct bfin_pint_regs *)PINT0_MASK_SET, - (struct bfin_pint_regs *)PINT1_MASK_SET, - (struct bfin_pint_regs *)PINT2_MASK_SET, - (struct bfin_pint_regs *)PINT3_MASK_SET, -#ifdef CONFIG_BF60x - (struct bfin_pint_regs *)PINT4_MASK_SET, - (struct bfin_pint_regs *)PINT5_MASK_SET, -#endif -}; - -inline unsigned int get_irq_base(u32 bank, u8 bmap) -{ - unsigned int irq_base; - -#ifndef CONFIG_BF60x - if (bank < 2) { /*PA-PB */ - irq_base = IRQ_PA0 + bmap * 16; - } else { /*PC-PJ */ - irq_base = IRQ_PC0 + bmap * 16; - } -#else - irq_base = IRQ_PA0 + bank * 16 + bmap * 16; -#endif - return irq_base; -} - - /* Whenever PINTx_ASSIGN is altered init_pint_lut() must be executed! */ -void init_pint_lut(void) -{ - u16 bank, bit, irq_base, bit_pos; - u32 pint_assign; - u8 bmap; - - memset(irq2pint_lut, IRQ_NOT_AVAIL, sizeof(irq2pint_lut)); - - for (bank = 0; bank < NR_PINT_SYS_IRQS; bank++) { - - pint_assign = pint[bank]->assign; - - for (bit = 0; bit < NR_PINT_BITS; bit++) { - - bmap = (pint_assign >> ((bit / 8) * 8)) & 0xFF; - - irq_base = get_irq_base(bank, bmap); - - irq_base += (bit % 8) + ((bit / 8) & 1 ? 8 : 0); - bit_pos = bit + bank * NR_PINT_BITS; - - pint2irq_lut[bit_pos] = irq_base - SYS_IRQS; - irq2pint_lut[irq_base - SYS_IRQS] = bit_pos; - } - } -} - -static void bfin_gpio_ack_irq(struct irq_data *d) -{ - u32 pint_val = irq2pint_lut[d->irq - SYS_IRQS]; - u32 pintbit = PINT_BIT(pint_val); - u32 bank = PINT_2_BANK(pint_val); - - if (irqd_get_trigger_type(d) == IRQ_TYPE_EDGE_BOTH) { - if (pint[bank]->invert_set & pintbit) - pint[bank]->invert_clear = pintbit; - else - pint[bank]->invert_set = pintbit; - } - pint[bank]->request = pintbit; - -} - -static void bfin_gpio_mask_ack_irq(struct irq_data *d) -{ - u32 pint_val = irq2pint_lut[d->irq - SYS_IRQS]; - u32 pintbit = PINT_BIT(pint_val); - u32 bank = PINT_2_BANK(pint_val); - - if (irqd_get_trigger_type(d) == IRQ_TYPE_EDGE_BOTH) { - if (pint[bank]->invert_set & pintbit) - pint[bank]->invert_clear = pintbit; - else - pint[bank]->invert_set = pintbit; - } - - pint[bank]->request = pintbit; - pint[bank]->mask_clear = pintbit; -} - -static void bfin_gpio_mask_irq(struct irq_data *d) -{ - u32 pint_val = irq2pint_lut[d->irq - SYS_IRQS]; - - pint[PINT_2_BANK(pint_val)]->mask_clear = PINT_BIT(pint_val); -} - -static void bfin_gpio_unmask_irq(struct irq_data *d) -{ - u32 pint_val = irq2pint_lut[d->irq - SYS_IRQS]; - u32 pintbit = PINT_BIT(pint_val); - u32 bank = PINT_2_BANK(pint_val); - - pint[bank]->mask_set = pintbit; -} - -static unsigned int bfin_gpio_irq_startup(struct irq_data *d) -{ - unsigned int irq = d->irq; - u32 gpionr = irq_to_gpio(irq); - u32 pint_val = irq2pint_lut[irq - SYS_IRQS]; - - if (pint_val == IRQ_NOT_AVAIL) { - printk(KERN_ERR - "GPIO IRQ %d :Not in PINT Assign table " - "Reconfigure Interrupt to Port Assignemt\n", irq); - return -ENODEV; - } - - if (__test_and_set_bit(gpionr, gpio_enabled)) - bfin_gpio_irq_prepare(gpionr); - - bfin_gpio_unmask_irq(d); - - return 0; -} - -static void bfin_gpio_irq_shutdown(struct irq_data *d) -{ - u32 gpionr = irq_to_gpio(d->irq); - - bfin_gpio_mask_irq(d); - __clear_bit(gpionr, gpio_enabled); - bfin_gpio_irq_free(gpionr); -} - -static int bfin_gpio_irq_type(struct irq_data *d, unsigned int type) -{ - unsigned int irq = d->irq; - int ret; - char buf[16]; - u32 gpionr = irq_to_gpio(irq); - u32 pint_val = irq2pint_lut[irq - SYS_IRQS]; - u32 pintbit = PINT_BIT(pint_val); - u32 bank = PINT_2_BANK(pint_val); - - if (pint_val == IRQ_NOT_AVAIL) - return -ENODEV; - - if (type == IRQ_TYPE_PROBE) { - /* only probe unenabled GPIO interrupt lines */ - if (test_bit(gpionr, gpio_enabled)) - return 0; - type = IRQ_TYPE_EDGE_RISING | IRQ_TYPE_EDGE_FALLING; - } - - if (type & (IRQ_TYPE_EDGE_RISING | IRQ_TYPE_EDGE_FALLING | - IRQ_TYPE_LEVEL_HIGH | IRQ_TYPE_LEVEL_LOW)) { - - snprintf(buf, 16, "gpio-irq%d", irq); - ret = bfin_gpio_irq_request(gpionr, buf); - if (ret) - return ret; - - if (__test_and_set_bit(gpionr, gpio_enabled)) - bfin_gpio_irq_prepare(gpionr); - - } else { - __clear_bit(gpionr, gpio_enabled); - return 0; - } - - if ((type & (IRQ_TYPE_EDGE_FALLING | IRQ_TYPE_LEVEL_LOW))) - pint[bank]->invert_set = pintbit; /* low or falling edge denoted by one */ - else - pint[bank]->invert_clear = pintbit; /* high or rising edge denoted by zero */ - - if ((type & (IRQ_TYPE_EDGE_RISING | IRQ_TYPE_EDGE_FALLING)) - == (IRQ_TYPE_EDGE_RISING | IRQ_TYPE_EDGE_FALLING)) { - if (gpio_get_value(gpionr)) - pint[bank]->invert_set = pintbit; - else - pint[bank]->invert_clear = pintbit; - } - - if (type & (IRQ_TYPE_EDGE_RISING | IRQ_TYPE_EDGE_FALLING)) { - pint[bank]->edge_set = pintbit; - bfin_set_irq_handler(irq, handle_edge_irq); - } else { - pint[bank]->edge_clear = pintbit; - bfin_set_irq_handler(irq, handle_level_irq); - } - - return 0; -} - #ifdef CONFIG_PM -static struct bfin_pm_pint_save save_pint_reg[NR_PINT_SYS_IRQS]; -static u32 save_pint_sec_ctl[NR_PINT_SYS_IRQS]; static int bfin_gpio_set_wake(struct irq_data *d, unsigned int state) { - u32 pint_irq; - u32 pint_val = irq2pint_lut[d->irq - SYS_IRQS]; - u32 bank = PINT_2_BANK(pint_val); - - switch (bank) { - case 0: - pint_irq = IRQ_PINT0; - break; - case 2: - pint_irq = IRQ_PINT2; - break; - case 3: - pint_irq = IRQ_PINT3; - break; - case 1: - pint_irq = IRQ_PINT1; - break; -#ifdef CONFIG_BF60x - case 4: - pint_irq = IRQ_PINT4; - break; - case 5: - pint_irq = IRQ_PINT5; - break; -#endif - default: - return -EINVAL; - } + return bfin_gpio_pm_wakeup_ctrl(irq_to_gpio(d->irq), state); +} -#ifndef SEC_GCTL - bfin_internal_set_wake(pint_irq, state); -#endif +#else - return 0; -} +# define bfin_gpio_set_wake NULL -void bfin_pint_suspend(void) -{ - u32 bank; +#endif - for (bank = 0; bank < NR_PINT_SYS_IRQS; bank++) { - save_pint_reg[bank].mask_set = pint[bank]->mask_set; - save_pint_reg[bank].assign = pint[bank]->assign; - save_pint_reg[bank].edge_set = pint[bank]->edge_set; - save_pint_reg[bank].invert_set = pint[bank]->invert_set; - } -} +static struct irq_chip bfin_gpio_irqchip = { + .name = "GPIO", + .irq_ack = bfin_gpio_ack_irq, + .irq_mask = bfin_gpio_mask_irq, + .irq_mask_ack = bfin_gpio_mask_ack_irq, + .irq_unmask = bfin_gpio_unmask_irq, + .irq_disable = bfin_gpio_mask_irq, + .irq_enable = bfin_gpio_unmask_irq, + .irq_set_type = bfin_gpio_irq_type, + .irq_startup = bfin_gpio_irq_startup, + .irq_shutdown = bfin_gpio_irq_shutdown, + .irq_set_wake = bfin_gpio_set_wake, +}; -void bfin_pint_resume(void) -{ - u32 bank; +#endif - for (bank = 0; bank < NR_PINT_SYS_IRQS; bank++) { - pint[bank]->mask_set = save_pint_reg[bank].mask_set; - pint[bank]->assign = save_pint_reg[bank].assign; - pint[bank]->edge_set = save_pint_reg[bank].edge_set; - pint[bank]->invert_set = save_pint_reg[bank].invert_set; - } -} +#ifdef CONFIG_PM #ifdef SEC_GCTL +static u32 save_pint_sec_ctl[NR_PINT_SYS_IRQS]; + static int sec_suspend(void) { u32 bank; @@ -1195,92 +946,10 @@ static struct syscore_ops sec_pm_syscore_ops = { .suspend = sec_suspend, .resume = sec_resume, }; - -#endif -#else -# define bfin_gpio_set_wake NULL -#endif - -void bfin_demux_gpio_irq(unsigned int inta_irq, - struct irq_desc *desc) -{ - u32 bank, pint_val; - u32 request, irq; - u32 level_mask; - int umask = 0; - struct irq_chip *chip = irq_desc_get_chip(desc); - - if (chip->irq_mask_ack) { - chip->irq_mask_ack(&desc->irq_data); - } else { - chip->irq_mask(&desc->irq_data); - if (chip->irq_ack) - chip->irq_ack(&desc->irq_data); - } - - switch (inta_irq) { - case IRQ_PINT0: - bank = 0; - break; - case IRQ_PINT2: - bank = 2; - break; - case IRQ_PINT3: - bank = 3; - break; - case IRQ_PINT1: - bank = 1; - break; -#ifdef CONFIG_BF60x - case IRQ_PINT4: - bank = 4; - break; - case IRQ_PINT5: - bank = 5; - break; #endif - default: - return; - } - - pint_val = bank * NR_PINT_BITS; - - request = pint[bank]->request; - - level_mask = pint[bank]->edge_set & request; - - while (request) { - if (request & 1) { - irq = pint2irq_lut[pint_val] + SYS_IRQS; - if (level_mask & PINT_BIT(pint_val)) { - umask = 1; - chip->irq_unmask(&desc->irq_data); - } - bfin_handle_irq(irq); - } - pint_val++; - request >>= 1; - } - if (!umask) - chip->irq_unmask(&desc->irq_data); -} #endif -static struct irq_chip bfin_gpio_irqchip = { - .name = "GPIO", - .irq_ack = bfin_gpio_ack_irq, - .irq_mask = bfin_gpio_mask_irq, - .irq_mask_ack = bfin_gpio_mask_ack_irq, - .irq_unmask = bfin_gpio_unmask_irq, - .irq_disable = bfin_gpio_mask_irq, - .irq_enable = bfin_gpio_unmask_irq, - .irq_set_type = bfin_gpio_irq_type, - .irq_startup = bfin_gpio_irq_startup, - .irq_shutdown = bfin_gpio_irq_shutdown, - .irq_set_wake = bfin_gpio_set_wake, -}; - void init_exception_vectors(void) { /* cannot program in software: @@ -1331,17 +1000,6 @@ int __init init_arch_irq(void) local_irq_disable(); -#if BFIN_GPIO_PINT -# ifdef CONFIG_PINTx_REASSIGN - pint[0]->assign = CONFIG_PINT0_ASSIGN; - pint[1]->assign = CONFIG_PINT1_ASSIGN; - pint[2]->assign = CONFIG_PINT2_ASSIGN; - pint[3]->assign = CONFIG_PINT3_ASSIGN; -# endif - /* Whenever PINTx_ASSIGN is altered init_pint_lut() must be executed! */ - init_pint_lut(); -#endif - for (irq = 0; irq <= SYS_IRQS; irq++) { if (irq <= IRQ_CORETMR) irq_set_chip(irq, &bfin_core_irqchip); @@ -1349,12 +1007,8 @@ int __init init_arch_irq(void) irq_set_chip(irq, &bfin_internal_irqchip); switch (irq) { -#if BFIN_GPIO_PINT - case IRQ_PINT0: - case IRQ_PINT1: - case IRQ_PINT2: - case IRQ_PINT3: -#elif defined(BF537_FAMILY) +#if !BFIN_GPIO_PINT +#if defined(BF537_FAMILY) case IRQ_PH_INTA_MAC_RX: case IRQ_PF_INTA_PG_INTA: #elif defined(BF533_FAMILY) @@ -1372,6 +1026,7 @@ int __init init_arch_irq(void) #endif irq_set_chained_handler(irq, bfin_demux_gpio_irq); break; +#endif #if defined(CONFIG_BFIN_MAC) || defined(CONFIG_BFIN_MAC_MODULE) case IRQ_MAC_ERROR: irq_set_chained_handler(irq, @@ -1419,10 +1074,12 @@ int __init init_arch_irq(void) handle_level_irq); #endif /* if configured as edge, then will be changed to do_edge_IRQ */ +#ifdef CONFIG_GPIO_ADI for (irq = GPIO_IRQ_BASE; irq < (GPIO_IRQ_BASE + MAX_BLACKFIN_GPIOS); irq++) irq_set_chip_and_handler(irq, &bfin_gpio_irqchip, handle_level_irq); +#endif bfin_write_IMASK(0); CSYNC(); ilat = bfin_read_ILAT(); @@ -1525,19 +1182,6 @@ int __init init_arch_irq(void) local_irq_disable(); -#if BFIN_GPIO_PINT -# ifdef CONFIG_PINTx_REASSIGN - pint[0]->assign = CONFIG_PINT0_ASSIGN; - pint[1]->assign = CONFIG_PINT1_ASSIGN; - pint[2]->assign = CONFIG_PINT2_ASSIGN; - pint[3]->assign = CONFIG_PINT3_ASSIGN; - pint[4]->assign = CONFIG_PINT4_ASSIGN; - pint[5]->assign = CONFIG_PINT5_ASSIGN; -# endif - /* Whenever PINTx_ASSIGN is altered init_pint_lut() must be executed! */ - init_pint_lut(); -#endif - for (irq = 0; irq <= SYS_IRQS; irq++) { if (irq <= IRQ_CORETMR) { irq_set_chip_and_handler(irq, &bfin_core_irqchip, @@ -1546,9 +1190,6 @@ int __init init_arch_irq(void) if (irq == IRQ_CORETMR) irq_set_handler(irq, handle_percpu_irq); #endif - } else if (irq >= BFIN_IRQ(21) && irq <= BFIN_IRQ(26)) { - irq_set_chip(irq, &bfin_sec_irqchip); - irq_set_chained_handler(irq, bfin_demux_gpio_irq); } else if (irq >= BFIN_IRQ(34) && irq <= BFIN_IRQ(37)) { irq_set_chip_and_handler(irq, &bfin_sec_irqchip, handle_percpu_irq); @@ -1563,10 +1204,6 @@ int __init init_arch_irq(void) __irq_set_preflow_handler(irq, bfin_sec_preflow_handler); } } - for (irq = GPIO_IRQ_BASE; - irq < (GPIO_IRQ_BASE + MAX_BLACKFIN_GPIOS); irq++) - irq_set_chip_and_handler(irq, &bfin_gpio_irqchip, - handle_level_irq); bfin_write_IMASK(0); CSYNC(); diff --git a/arch/blackfin/mach-common/pm.c b/arch/blackfin/mach-common/pm.c index 87bfe549ad3f..1387a94bcfd5 100644 --- a/arch/blackfin/mach-common/pm.c +++ b/arch/blackfin/mach-common/pm.c @@ -27,7 +27,7 @@ struct bfin_cpu_pm_fns *bfin_cpu_pm; void bfin_pm_suspend_standby_enter(void) { -#ifndef CONFIG_BF60x +#if !BFIN_GPIO_PINT bfin_pm_standby_setup(); #endif @@ -41,7 +41,7 @@ void bfin_pm_suspend_standby_enter(void) # endif #endif -#ifndef CONFIG_BF60x +#if !BFIN_GPIO_PINT bfin_pm_standby_restore(); #endif @@ -128,6 +128,7 @@ static void flushinv_all_dcache(void) if ((status & 0x3) != 0x3) continue; + /* construct the address using the tag */ addr = (status & 0xFFFFC800) | (subbank << 12) | (set << 5); @@ -140,11 +141,14 @@ static void flushinv_all_dcache(void) int bfin_pm_suspend_mem_enter(void) { - int wakeup, ret; + int ret; +#ifndef CONFIG_BF60x + int wakeup; +#endif unsigned char *memptr = kmalloc(L1_CODE_LENGTH + L1_DATA_A_LENGTH + L1_DATA_B_LENGTH + L1_SCRATCH_LENGTH, - GFP_KERNEL); + GFP_ATOMIC); if (memptr == NULL) { panic("bf53x_suspend_l1_mem malloc failed"); @@ -170,10 +174,8 @@ int bfin_pm_suspend_mem_enter(void) return ret; } +#ifdef CONFIG_GPIO_ADI bfin_gpio_pm_hibernate_suspend(); - -#if BFIN_GPIO_PINT - bfin_pint_suspend(); #endif #if defined(CONFIG_BFIN_EXTMEM_WRITEBACK) || defined(CONFIG_BFIN_L2_WRITEBACK) @@ -194,11 +196,9 @@ int bfin_pm_suspend_mem_enter(void) _enable_icplb(); _enable_dcplb(); -#if BFIN_GPIO_PINT - bfin_pint_resume(); -#endif - +#ifdef CONFIG_GPIO_ADI bfin_gpio_pm_hibernate_restore(); +#endif blackfin_dma_resume(); kfree(memptr); diff --git a/arch/blackfin/mach-common/smp.c b/arch/blackfin/mach-common/smp.c index 82f301c117a5..2bbae0783819 100644 --- a/arch/blackfin/mach-common/smp.c +++ b/arch/blackfin/mach-common/smp.c @@ -146,6 +146,7 @@ static irqreturn_t ipi_handler_int1(int irq, void *dev_instance) platform_clear_ipi(cpu, IRQ_SUPPLE_1); + smp_rmb(); bfin_ipi_data = &__get_cpu_var(bfin_ipi); while ((pending = atomic_xchg(&bfin_ipi_data->bits, 0)) != 0) { msg = 0; @@ -161,18 +162,20 @@ static irqreturn_t ipi_handler_int1(int irq, void *dev_instance) case BFIN_IPI_CALL_FUNC: generic_smp_call_function_interrupt(); break; - case BFIN_IPI_CALL_FUNC_SINGLE: generic_smp_call_function_single_interrupt(); break; - case BFIN_IPI_CPU_STOP: ipi_cpu_stop(cpu); break; + default: + goto out; } atomic_dec(&bfin_ipi_data->count); } while (msg < BITS_PER_LONG); + } +out: return IRQ_HANDLED; } @@ -198,10 +201,11 @@ void send_ipi(const struct cpumask *cpumask, enum ipi_message_type msg) bfin_ipi_data = &per_cpu(bfin_ipi, cpu); atomic_set_mask((1 << msg), &bfin_ipi_data->bits); atomic_inc(&bfin_ipi_data->count); - platform_send_ipi_cpu(cpu, IRQ_SUPPLE_1); } - local_irq_restore(flags); + smp_wmb(); + for_each_cpu(cpu, cpumask) + platform_send_ipi_cpu(cpu, IRQ_SUPPLE_1); } void arch_send_call_function_single_ipi(int cpu) diff --git a/arch/c6x/Kconfig b/arch/c6x/Kconfig index 957dd00ea561..77ea09b8bce1 100644 --- a/arch/c6x/Kconfig +++ b/arch/c6x/Kconfig @@ -36,9 +36,6 @@ config GENERIC_HWEIGHT config GENERIC_BUG def_bool y -config COMMON_CLKDEV - def_bool y - config C6X_BIG_KERNEL bool "Build a big kernel" help @@ -105,10 +102,6 @@ menu "Processor type and features" source "arch/c6x/platforms/Kconfig" -config TMS320C6X_CACHES_ON - bool "L2 cache support" - default y - config KERNEL_RAM_BASE_ADDRESS hex "Virtual address of memory base" default 0xe0000000 if SOC_TMS320C6455 diff --git a/arch/c6x/include/asm/thread_info.h b/arch/c6x/include/asm/thread_info.h index 4c8dc562bd90..d4e9ef87076d 100644 --- a/arch/c6x/include/asm/thread_info.h +++ b/arch/c6x/include/asm/thread_info.h @@ -84,8 +84,6 @@ struct thread_info *current_thread_info(void) #define put_thread_info(ti) put_task_struct((ti)->task) #endif /* __ASSEMBLY__ */ -#define PREEMPT_ACTIVE 0x10000000 - /* * thread information flag bit numbers * - pending work-to-be-done flags are in LSW diff --git a/arch/cris/Kconfig b/arch/cris/Kconfig index 02380bed189c..9c957c81c688 100644 --- a/arch/cris/Kconfig +++ b/arch/cris/Kconfig @@ -130,13 +130,11 @@ config SVINTO_SIM config ETRAXFS bool "ETRAX-FS-V32" - select CPU_FREQ_TABLE if CPU_FREQ help Support CRIS V32. config CRIS_MACH_ARTPEC3 bool "ARTPEC-3" - select CPU_FREQ_TABLE if CPU_FREQ help Support Axis ARTPEC-3. diff --git a/arch/cris/include/asm/hardirq.h b/arch/cris/include/asm/hardirq.h index 17bb12d760b2..04126f7bfab2 100644 --- a/arch/cris/include/asm/hardirq.h +++ b/arch/cris/include/asm/hardirq.h @@ -2,18 +2,6 @@ #define __ASM_HARDIRQ_H #include <asm/irq.h> - -#define HARDIRQ_BITS 8 - -/* - * The hardirq mask has to be large enough to have - * space for potentially all IRQ sources in the system - * nesting on a single CPU: - */ -#if (1 << HARDIRQ_BITS) < NR_IRQS -# error HARDIRQ_BITS is too low! -#endif - #include <asm-generic/hardirq.h> #endif /* __ASM_HARDIRQ_H */ diff --git a/arch/cris/include/asm/pci.h b/arch/cris/include/asm/pci.h index 146da904cdd8..f666734926d5 100644 --- a/arch/cris/include/asm/pci.h +++ b/arch/cris/include/asm/pci.h @@ -11,7 +11,6 @@ #define pcibios_assign_all_busses(void) 1 -extern unsigned long pci_mem_start; #define PCIBIOS_MIN_IO 0x1000 #define PCIBIOS_MIN_MEM 0x10000000 diff --git a/arch/cris/include/asm/pgalloc.h b/arch/cris/include/asm/pgalloc.h index 6da975db112f..235ece437ddd 100644 --- a/arch/cris/include/asm/pgalloc.h +++ b/arch/cris/include/asm/pgalloc.h @@ -32,7 +32,12 @@ static inline pgtable_t pte_alloc_one(struct mm_struct *mm, unsigned long addres { struct page *pte; pte = alloc_pages(GFP_KERNEL|__GFP_REPEAT|__GFP_ZERO, 0); - pgtable_page_ctor(pte); + if (!pte) + return NULL; + if (!pgtable_page_ctor(pte)) { + __free_page(pte); + return NULL; + } return pte; } diff --git a/arch/cris/include/asm/thread_info.h b/arch/cris/include/asm/thread_info.h index 07c8c40c52b3..55dede18c032 100644 --- a/arch/cris/include/asm/thread_info.h +++ b/arch/cris/include/asm/thread_info.h @@ -44,8 +44,6 @@ struct thread_info { #endif -#define PREEMPT_ACTIVE 0x10000000 - /* * macros/functions for gaining access to the thread information structure */ diff --git a/arch/frv/include/asm/thread_info.h b/arch/frv/include/asm/thread_info.h index bebd7eadc772..af29e17c0181 100644 --- a/arch/frv/include/asm/thread_info.h +++ b/arch/frv/include/asm/thread_info.h @@ -52,8 +52,6 @@ struct thread_info { #endif -#define PREEMPT_ACTIVE 0x10000000 - /* * macros/functions for gaining access to the thread information structure */ diff --git a/arch/frv/mb93090-mb00/pci-frv.h b/arch/frv/mb93090-mb00/pci-frv.h index 76c4e73d643d..a7e487fe76ed 100644 --- a/arch/frv/mb93090-mb00/pci-frv.h +++ b/arch/frv/mb93090-mb00/pci-frv.h @@ -30,7 +30,6 @@ void pcibios_resource_survey(void); /* pci-vdk.c */ -extern int __nongpreldata pcibios_last_bus; extern struct pci_ops *__nongpreldata pci_root_ops; /* pci-irq.c */ diff --git a/arch/frv/mb93090-mb00/pci-vdk.c b/arch/frv/mb93090-mb00/pci-vdk.c index deb67843693c..efa5d65b0007 100644 --- a/arch/frv/mb93090-mb00/pci-vdk.c +++ b/arch/frv/mb93090-mb00/pci-vdk.c @@ -25,7 +25,6 @@ unsigned int __nongpreldata pci_probe = 1; -int __nongpreldata pcibios_last_bus = -1; struct pci_ops *__nongpreldata pci_root_ops; /* @@ -220,37 +219,6 @@ static struct pci_ops * __init pci_check_direct(void) } /* - * Discover remaining PCI buses in case there are peer host bridges. - * We use the number of last PCI bus provided by the PCI BIOS. - */ -static void __init pcibios_fixup_peer_bridges(void) -{ - struct pci_bus bus; - struct pci_dev dev; - int n; - u16 l; - - if (pcibios_last_bus <= 0 || pcibios_last_bus >= 0xff) - return; - printk("PCI: Peer bridge fixup\n"); - for (n=0; n <= pcibios_last_bus; n++) { - if (pci_find_bus(0, n)) - continue; - bus.number = n; - bus.ops = pci_root_ops; - dev.bus = &bus; - for(dev.devfn=0; dev.devfn<256; dev.devfn += 8) - if (!pci_read_config_word(&dev, PCI_VENDOR_ID, &l) && - l != 0x0000 && l != 0xffff) { - printk("Found device at %02x:%02x [%04x]\n", n, dev.devfn, l); - printk("PCI: Discovered peer bus %02x\n", n); - pci_scan_bus(n, pci_root_ops, NULL); - break; - } - } -} - -/* * Exceptions for specific devices. Usually work-arounds for fatal design flaws. */ @@ -418,7 +386,6 @@ int __init pcibios_init(void) pci_scan_root_bus(NULL, 0, pci_root_ops, NULL, &resources); pcibios_irq_init(); - pcibios_fixup_peer_bridges(); pcibios_fixup_irqs(); pcibios_resource_survey(); @@ -432,9 +399,6 @@ char * __init pcibios_setup(char *str) if (!strcmp(str, "off")) { pci_probe = 0; return NULL; - } else if (!strncmp(str, "lastbus=", 8)) { - pcibios_last_bus = simple_strtol(str+8, NULL, 0); - return NULL; } return str; } diff --git a/arch/frv/mm/pgalloc.c b/arch/frv/mm/pgalloc.c index f6084bc524e8..41907d25ed38 100644 --- a/arch/frv/mm/pgalloc.c +++ b/arch/frv/mm/pgalloc.c @@ -37,11 +37,15 @@ pgtable_t pte_alloc_one(struct mm_struct *mm, unsigned long address) #else page = alloc_pages(GFP_KERNEL|__GFP_REPEAT, 0); #endif - if (page) { - clear_highpage(page); - pgtable_page_ctor(page); - flush_dcache_page(page); + if (!page) + return NULL; + + clear_highpage(page); + if (!pgtable_page_ctor(page)) { + __free_page(page); + return NULL; } + flush_dcache_page(page); return page; } diff --git a/arch/hexagon/Kconfig b/arch/hexagon/Kconfig index 99041b07e610..09df2608f40a 100644 --- a/arch/hexagon/Kconfig +++ b/arch/hexagon/Kconfig @@ -4,7 +4,6 @@ comment "Linux Kernel Configuration for Hexagon" config HEXAGON def_bool y select HAVE_OPROFILE - select USE_GENERIC_SMP_HELPERS if SMP # Other pending projects/to-do items. # select HAVE_REGS_AND_STACK_ACCESS_API # select HAVE_HW_BREAKPOINT if PERF_EVENTS diff --git a/arch/hexagon/include/asm/pgalloc.h b/arch/hexagon/include/asm/pgalloc.h index 679bf6d66487..4c9d382d7798 100644 --- a/arch/hexagon/include/asm/pgalloc.h +++ b/arch/hexagon/include/asm/pgalloc.h @@ -65,10 +65,12 @@ static inline struct page *pte_alloc_one(struct mm_struct *mm, struct page *pte; pte = alloc_page(GFP_KERNEL | __GFP_REPEAT | __GFP_ZERO); - - if (pte) - pgtable_page_ctor(pte); - + if (!pte) + return NULL; + if (!pgtable_page_ctor(pte)) { + __free_page(pte); + return NULL; + } return pte; } diff --git a/arch/hexagon/include/asm/thread_info.h b/arch/hexagon/include/asm/thread_info.h index f7c32406a711..a59dad3b3695 100644 --- a/arch/hexagon/include/asm/thread_info.h +++ b/arch/hexagon/include/asm/thread_info.h @@ -73,10 +73,6 @@ struct thread_info { #endif /* __ASSEMBLY__ */ -/* looks like "linux/hardirq.h" uses this. */ - -#define PREEMPT_ACTIVE 0x10000000 - #ifndef __ASSEMBLY__ #define INIT_THREAD_INFO(tsk) \ diff --git a/arch/ia64/Kconfig b/arch/ia64/Kconfig index 7740ab10a171..4e4119b0e691 100644 --- a/arch/ia64/Kconfig +++ b/arch/ia64/Kconfig @@ -6,6 +6,7 @@ menu "Processor type and features" config IA64 bool + select ARCH_MIGHT_HAVE_PC_PARPORT select PCI if (!IA64_HP_SIM) select ACPI if (!IA64_HP_SIM) select PM if (!IA64_HP_SIM) @@ -343,7 +344,6 @@ config FORCE_MAX_ZONEORDER config SMP bool "Symmetric multi-processing support" - select USE_GENERIC_SMP_HELPERS help This enables support for systems with more than one CPU. If you have a system with only one CPU, say N. If you have a system with more diff --git a/arch/ia64/hp/common/sba_iommu.c b/arch/ia64/hp/common/sba_iommu.c index d43daf192b21..4c530a82fc46 100644 --- a/arch/ia64/hp/common/sba_iommu.c +++ b/arch/ia64/hp/common/sba_iommu.c @@ -1992,7 +1992,7 @@ sba_connect_bus(struct pci_bus *bus) if (PCI_CONTROLLER(bus)->iommu) return; - handle = PCI_CONTROLLER(bus)->acpi_handle; + handle = acpi_device_handle(PCI_CONTROLLER(bus)->companion); if (!handle) return; diff --git a/arch/ia64/include/asm/kvm_host.h b/arch/ia64/include/asm/kvm_host.h index 989dd3fe8de1..db95f570705f 100644 --- a/arch/ia64/include/asm/kvm_host.h +++ b/arch/ia64/include/asm/kvm_host.h @@ -234,10 +234,6 @@ struct kvm_vm_data { #define KVM_REQ_PTC_G 32 #define KVM_REQ_RESUME 33 -#define KVM_HPAGE_GFN_SHIFT(x) 0 -#define KVM_NR_PAGE_SIZES 1 -#define KVM_PAGES_PER_HPAGE(x) 1 - struct kvm; struct kvm_vcpu; @@ -480,7 +476,7 @@ struct kvm_arch { struct list_head assigned_dev_head; struct iommu_domain *iommu_domain; - int iommu_flags; + bool iommu_noncoherent; unsigned long irq_sources_bitmap; unsigned long irq_states[KVM_IOAPIC_NUM_PINS]; diff --git a/arch/ia64/include/asm/pci.h b/arch/ia64/include/asm/pci.h index 80775f55f03f..71fbaaa495cc 100644 --- a/arch/ia64/include/asm/pci.h +++ b/arch/ia64/include/asm/pci.h @@ -95,7 +95,7 @@ struct iospace_resource { }; struct pci_controller { - void *acpi_handle; + struct acpi_device *companion; void *iommu; int segment; int node; /* nearest node with memory or -1 for global allocation */ diff --git a/arch/ia64/include/asm/pgalloc.h b/arch/ia64/include/asm/pgalloc.h index 96a8d927db28..5767cdfc08db 100644 --- a/arch/ia64/include/asm/pgalloc.h +++ b/arch/ia64/include/asm/pgalloc.h @@ -91,7 +91,10 @@ static inline pgtable_t pte_alloc_one(struct mm_struct *mm, unsigned long addr) if (!pg) return NULL; page = virt_to_page(pg); - pgtable_page_ctor(page); + if (!pgtable_page_ctor(page)) { + quicklist_free(0, NULL, pg); + return NULL; + } return page; } diff --git a/arch/ia64/include/asm/thread_info.h b/arch/ia64/include/asm/thread_info.h index cade13dd0299..5957cf61f898 100644 --- a/arch/ia64/include/asm/thread_info.h +++ b/arch/ia64/include/asm/thread_info.h @@ -11,9 +11,6 @@ #include <asm/processor.h> #include <asm/ptrace.h> -#define PREEMPT_ACTIVE_BIT 30 -#define PREEMPT_ACTIVE (1 << PREEMPT_ACTIVE_BIT) - #ifndef __ASSEMBLY__ /* diff --git a/arch/ia64/include/asm/xen/page-coherent.h b/arch/ia64/include/asm/xen/page-coherent.h new file mode 100644 index 000000000000..96e42f97fa1f --- /dev/null +++ b/arch/ia64/include/asm/xen/page-coherent.h @@ -0,0 +1,38 @@ +#ifndef _ASM_IA64_XEN_PAGE_COHERENT_H +#define _ASM_IA64_XEN_PAGE_COHERENT_H + +#include <asm/page.h> +#include <linux/dma-attrs.h> +#include <linux/dma-mapping.h> + +static inline void *xen_alloc_coherent_pages(struct device *hwdev, size_t size, + dma_addr_t *dma_handle, gfp_t flags, + struct dma_attrs *attrs) +{ + void *vstart = (void*)__get_free_pages(flags, get_order(size)); + *dma_handle = virt_to_phys(vstart); + return vstart; +} + +static inline void xen_free_coherent_pages(struct device *hwdev, size_t size, + void *cpu_addr, dma_addr_t dma_handle, + struct dma_attrs *attrs) +{ + free_pages((unsigned long) cpu_addr, get_order(size)); +} + +static inline void xen_dma_map_page(struct device *hwdev, struct page *page, + unsigned long offset, size_t size, enum dma_data_direction dir, + struct dma_attrs *attrs) { } + +static inline void xen_dma_unmap_page(struct device *hwdev, dma_addr_t handle, + size_t size, enum dma_data_direction dir, + struct dma_attrs *attrs) { } + +static inline void xen_dma_sync_single_for_cpu(struct device *hwdev, + dma_addr_t handle, size_t size, enum dma_data_direction dir) { } + +static inline void xen_dma_sync_single_for_device(struct device *hwdev, + dma_addr_t handle, size_t size, enum dma_data_direction dir) { } + +#endif /* _ASM_IA64_XEN_PAGE_COHERENT_H */ diff --git a/arch/ia64/kernel/acpi.c b/arch/ia64/kernel/acpi.c index 5eb71d22c3d5..59d52e3aef12 100644 --- a/arch/ia64/kernel/acpi.c +++ b/arch/ia64/kernel/acpi.c @@ -882,40 +882,10 @@ __init void prefill_possible_map(void) set_cpu_possible(i, true); } -static int _acpi_map_lsapic(acpi_handle handle, int *pcpu) +static int _acpi_map_lsapic(acpi_handle handle, int physid, int *pcpu) { - struct acpi_buffer buffer = { ACPI_ALLOCATE_BUFFER, NULL }; - union acpi_object *obj; - struct acpi_madt_local_sapic *lsapic; cpumask_t tmp_map; - int cpu, physid; - - if (ACPI_FAILURE(acpi_evaluate_object(handle, "_MAT", NULL, &buffer))) - return -EINVAL; - - if (!buffer.length || !buffer.pointer) - return -EINVAL; - - obj = buffer.pointer; - if (obj->type != ACPI_TYPE_BUFFER) - { - kfree(buffer.pointer); - return -EINVAL; - } - - lsapic = (struct acpi_madt_local_sapic *)obj->buffer.pointer; - - if ((lsapic->header.type != ACPI_MADT_TYPE_LOCAL_SAPIC) || - (!(lsapic->lapic_flags & ACPI_MADT_ENABLED))) { - kfree(buffer.pointer); - return -EINVAL; - } - - physid = ((lsapic->id << 8) | (lsapic->eid)); - - kfree(buffer.pointer); - buffer.length = ACPI_ALLOCATE_BUFFER; - buffer.pointer = NULL; + int cpu; cpumask_complement(&tmp_map, cpu_present_mask); cpu = cpumask_first(&tmp_map); @@ -934,9 +904,9 @@ static int _acpi_map_lsapic(acpi_handle handle, int *pcpu) } /* wrapper to silence section mismatch warning */ -int __ref acpi_map_lsapic(acpi_handle handle, int *pcpu) +int __ref acpi_map_lsapic(acpi_handle handle, int physid, int *pcpu) { - return _acpi_map_lsapic(handle, pcpu); + return _acpi_map_lsapic(handle, physid, pcpu); } EXPORT_SYMBOL(acpi_map_lsapic); diff --git a/arch/ia64/kernel/entry.S b/arch/ia64/kernel/entry.S index 7a53530f22c2..ddea607f948a 100644 --- a/arch/ia64/kernel/entry.S +++ b/arch/ia64/kernel/entry.S @@ -1169,21 +1169,8 @@ skip_rbs_switch: .work_pending: tbit.z p6,p0=r31,TIF_NEED_RESCHED // is resched not needed? (p6) br.cond.sptk.few .notify -#ifdef CONFIG_PREEMPT -(pKStk) dep r21=-1,r0,PREEMPT_ACTIVE_BIT,1 - ;; -(pKStk) st4 [r20]=r21 -#endif - SSM_PSR_I(p0, p6, r2) // enable interrupts - br.call.spnt.many rp=schedule + br.call.spnt.many rp=preempt_schedule_irq .ret9: cmp.eq p6,p0=r0,r0 // p6 <- 1 (re-check) - RSM_PSR_I(p0, r2, r20) // disable interrupts - ;; -#ifdef CONFIG_PREEMPT -(pKStk) adds r20=TI_PRE_COUNT+IA64_TASK_SIZE,r13 - ;; -(pKStk) st4 [r20]=r0 // preempt_count() <- 0 -#endif (pLvSys)br.cond.sptk.few __paravirt_pending_syscall_end br.cond.sptk.many .work_processed_kernel diff --git a/arch/ia64/kernel/kprobes.c b/arch/ia64/kernel/kprobes.c index f8280a766a78..074fde49c9e6 100644 --- a/arch/ia64/kernel/kprobes.c +++ b/arch/ia64/kernel/kprobes.c @@ -947,7 +947,7 @@ int __kprobes kprobe_fault_handler(struct pt_regs *regs, int trapnr) case KPROBE_HIT_SSDONE: /* * We increment the nmissed count for accounting, - * we can also use npre/npostfault count for accouting + * we can also use npre/npostfault count for accounting * these specific fault cases. */ kprobes_inc_nmissed_count(cur); diff --git a/arch/ia64/kernel/perfmon.c b/arch/ia64/kernel/perfmon.c index 5a9ff1c3c3e9..cb592773c78b 100644 --- a/arch/ia64/kernel/perfmon.c +++ b/arch/ia64/kernel/perfmon.c @@ -2166,12 +2166,6 @@ static const struct file_operations pfm_file_ops = { .flush = pfm_flush }; -static int -pfmfs_delete_dentry(const struct dentry *dentry) -{ - return 1; -} - static char *pfmfs_dname(struct dentry *dentry, char *buffer, int buflen) { return dynamic_dname(dentry, buffer, buflen, "pfm:[%lu]", @@ -2179,7 +2173,7 @@ static char *pfmfs_dname(struct dentry *dentry, char *buffer, int buflen) } static const struct dentry_operations pfmfs_dentry_operations = { - .d_delete = pfmfs_delete_dentry, + .d_delete = always_delete_dentry, .d_dname = pfmfs_dname, }; diff --git a/arch/ia64/kvm/kvm-ia64.c b/arch/ia64/kvm/kvm-ia64.c index bdfd8789b376..985bf80c622e 100644 --- a/arch/ia64/kvm/kvm-ia64.c +++ b/arch/ia64/kvm/kvm-ia64.c @@ -1550,12 +1550,13 @@ int kvm_arch_vcpu_fault(struct kvm_vcpu *vcpu, struct vm_fault *vmf) return VM_FAULT_SIGBUS; } -void kvm_arch_free_memslot(struct kvm_memory_slot *free, +void kvm_arch_free_memslot(struct kvm *kvm, struct kvm_memory_slot *free, struct kvm_memory_slot *dont) { } -int kvm_arch_create_memslot(struct kvm_memory_slot *slot, unsigned long npages) +int kvm_arch_create_memslot(struct kvm *kvm, struct kvm_memory_slot *slot, + unsigned long npages) { return 0; } diff --git a/arch/ia64/pci/pci.c b/arch/ia64/pci/pci.c index 2326790b7d8b..9e4938d8ca4d 100644 --- a/arch/ia64/pci/pci.c +++ b/arch/ia64/pci/pci.c @@ -436,9 +436,9 @@ struct pci_bus *pci_acpi_scan_root(struct acpi_pci_root *root) if (!controller) return NULL; - controller->acpi_handle = device->handle; + controller->companion = device; - pxm = acpi_get_pxm(controller->acpi_handle); + pxm = acpi_get_pxm(device->handle); #ifdef CONFIG_NUMA if (pxm >= 0) controller->node = pxm_to_node(pxm); @@ -489,7 +489,7 @@ int pcibios_root_bridge_prepare(struct pci_host_bridge *bridge) { struct pci_controller *controller = bridge->bus->sysdata; - ACPI_HANDLE_SET(&bridge->dev, controller->acpi_handle); + ACPI_COMPANION_SET(&bridge->dev, controller->companion); return 0; } diff --git a/arch/ia64/sn/kernel/io_acpi_init.c b/arch/ia64/sn/kernel/io_acpi_init.c index b1725398b5af..0640739cc20c 100644 --- a/arch/ia64/sn/kernel/io_acpi_init.c +++ b/arch/ia64/sn/kernel/io_acpi_init.c @@ -132,7 +132,7 @@ sn_get_bussoft_ptr(struct pci_bus *bus) struct acpi_resource_vendor_typed *vendor; - handle = PCI_CONTROLLER(bus)->acpi_handle; + handle = acpi_device_handle(PCI_CONTROLLER(bus)->companion); status = acpi_get_vendor_resource(handle, METHOD_NAME__CRS, &sn_uuid, &buffer); if (ACPI_FAILURE(status)) { @@ -360,7 +360,7 @@ sn_acpi_get_pcidev_info(struct pci_dev *dev, struct pcidev_info **pcidev_info, acpi_status status; struct acpi_buffer name_buffer = { ACPI_ALLOCATE_BUFFER, NULL }; - rootbus_handle = PCI_CONTROLLER(dev)->acpi_handle; + rootbus_handle = acpi_device_handle(PCI_CONTROLLER(dev)->companion); status = acpi_evaluate_integer(rootbus_handle, METHOD_NAME__SEG, NULL, &segment); if (ACPI_SUCCESS(status)) { diff --git a/arch/m32r/Kconfig b/arch/m32r/Kconfig index 75661fbf4529..09ef94a8a7c3 100644 --- a/arch/m32r/Kconfig +++ b/arch/m32r/Kconfig @@ -275,7 +275,6 @@ source "kernel/Kconfig.preempt" config SMP bool "Symmetric multi-processing support" - select USE_GENERIC_SMP_HELPERS ---help--- This enables support for systems with more than one CPU. If you have a system with only one CPU, like most personal computers, say N. If diff --git a/arch/m32r/include/asm/hardirq.h b/arch/m32r/include/asm/hardirq.h index 4c31c0ae215e..5f2ac4f64ddf 100644 --- a/arch/m32r/include/asm/hardirq.h +++ b/arch/m32r/include/asm/hardirq.h @@ -3,22 +3,6 @@ #define __ASM_HARDIRQ_H #include <asm/irq.h> - -#if NR_IRQS > 256 -#define HARDIRQ_BITS 9 -#else -#define HARDIRQ_BITS 8 -#endif - -/* - * The hardirq mask has to be large enough to have - * space for potentially all IRQ sources in the system - * nesting on a single CPU: - */ -#if (1 << HARDIRQ_BITS) < NR_IRQS -# error HARDIRQ_BITS is too low! -#endif - #include <asm-generic/hardirq.h> #endif /* __ASM_HARDIRQ_H */ diff --git a/arch/m32r/include/asm/mmu_context.h b/arch/m32r/include/asm/mmu_context.h index a979a4198168..9fc78fc44445 100644 --- a/arch/m32r/include/asm/mmu_context.h +++ b/arch/m32r/include/asm/mmu_context.h @@ -45,7 +45,7 @@ static inline void get_new_mmu_context(struct mm_struct *mm) Flush all TLB and start new cycle. */ local_flush_tlb_all(); /* Fix version if needed. - Note that we avoid version #0 to distingush NO_CONTEXT. */ + Note that we avoid version #0 to distinguish NO_CONTEXT. */ if (!mc) mmu_context_cache = mc = MMU_CONTEXT_FIRST_VERSION; } diff --git a/arch/m32r/include/asm/pgalloc.h b/arch/m32r/include/asm/pgalloc.h index 0fc736198979..2d55a064ccac 100644 --- a/arch/m32r/include/asm/pgalloc.h +++ b/arch/m32r/include/asm/pgalloc.h @@ -43,7 +43,12 @@ static __inline__ pgtable_t pte_alloc_one(struct mm_struct *mm, { struct page *pte = alloc_page(GFP_KERNEL|__GFP_ZERO); - pgtable_page_ctor(pte); + if (!pte) + return NULL; + if (!pgtable_page_ctor(pte)) { + __free_page(pte); + return NULL; + } return pte; } diff --git a/arch/m32r/include/asm/thread_info.h b/arch/m32r/include/asm/thread_info.h index c074f4c2e858..00171703402f 100644 --- a/arch/m32r/include/asm/thread_info.h +++ b/arch/m32r/include/asm/thread_info.h @@ -53,8 +53,6 @@ struct thread_info { #endif -#define PREEMPT_ACTIVE 0x10000000 - #define THREAD_SIZE (PAGE_SIZE << 1) #define THREAD_SIZE_ORDER 1 /* diff --git a/arch/m32r/kernel/entry.S b/arch/m32r/kernel/entry.S index 0c01543f10cd..7c3db9940ce1 100644 --- a/arch/m32r/kernel/entry.S +++ b/arch/m32r/kernel/entry.S @@ -182,13 +182,7 @@ need_resched: ld r4, PSW(sp) ; interrupts off (exception path) ? and3 r4, r4, #0x4000 beqz r4, restore_all - LDIMM (r4, PREEMPT_ACTIVE) - st r4, @(TI_PRE_COUNT, r8) - ENABLE_INTERRUPTS(r4) - bl schedule - ldi r4, #0 - st r4, @(TI_PRE_COUNT, r8) - DISABLE_INTERRUPTS(r4) + bl preempt_schedule_irq bra need_resched #endif diff --git a/arch/m68k/Kconfig b/arch/m68k/Kconfig index 311a300d48cc..75f25a8e3001 100644 --- a/arch/m68k/Kconfig +++ b/arch/m68k/Kconfig @@ -1,6 +1,7 @@ config M68K bool default y + select ARCH_MIGHT_HAVE_PC_PARPORT if ISA select HAVE_IDE select HAVE_AOUT if MMU select HAVE_DEBUG_BUGVERBOSE diff --git a/arch/m68k/include/asm/hardirq.h b/arch/m68k/include/asm/hardirq.h index db30ed276878..6c618529d9b9 100644 --- a/arch/m68k/include/asm/hardirq.h +++ b/arch/m68k/include/asm/hardirq.h @@ -5,17 +5,6 @@ #include <linux/cache.h> #include <asm/irq.h> -#define HARDIRQ_BITS 8 - -/* - * The hardirq mask has to be large enough to have - * space for potentially all IRQ sources in the system - * nesting on a single CPU: - */ -#if (1 << HARDIRQ_BITS) < NR_IRQS -# error HARDIRQ_BITS is too low! -#endif - #ifdef CONFIG_MMU static inline void ack_bad_irq(unsigned int irq) diff --git a/arch/m68k/include/asm/mcf_pgalloc.h b/arch/m68k/include/asm/mcf_pgalloc.h index 313f3dd23cdc..f9924fbcfe42 100644 --- a/arch/m68k/include/asm/mcf_pgalloc.h +++ b/arch/m68k/include/asm/mcf_pgalloc.h @@ -56,6 +56,10 @@ static inline struct page *pte_alloc_one(struct mm_struct *mm, if (!page) return NULL; + if (!pgtable_page_ctor(page)) { + __free_page(page); + return NULL; + } pte = kmap(page); if (pte) { diff --git a/arch/m68k/include/asm/motorola_pgalloc.h b/arch/m68k/include/asm/motorola_pgalloc.h index 2f02f264e694..24bcba496c75 100644 --- a/arch/m68k/include/asm/motorola_pgalloc.h +++ b/arch/m68k/include/asm/motorola_pgalloc.h @@ -29,18 +29,22 @@ static inline void pte_free_kernel(struct mm_struct *mm, pte_t *pte) static inline pgtable_t pte_alloc_one(struct mm_struct *mm, unsigned long address) { - struct page *page = alloc_pages(GFP_KERNEL|__GFP_REPEAT|__GFP_ZERO, 0); + struct page *page; pte_t *pte; + page = alloc_pages(GFP_KERNEL|__GFP_REPEAT|__GFP_ZERO, 0); if(!page) return NULL; + if (!pgtable_page_ctor(page)) { + __free_page(page); + return NULL; + } pte = kmap(page); __flush_page_to_ram(pte); flush_tlb_kernel_page(pte); nocache_page(pte); kunmap(page); - pgtable_page_ctor(page); return page; } diff --git a/arch/m68k/include/asm/sun3_pgalloc.h b/arch/m68k/include/asm/sun3_pgalloc.h index 48d80d5a666f..f868506e3350 100644 --- a/arch/m68k/include/asm/sun3_pgalloc.h +++ b/arch/m68k/include/asm/sun3_pgalloc.h @@ -59,7 +59,10 @@ static inline pgtable_t pte_alloc_one(struct mm_struct *mm, return NULL; clear_highpage(page); - pgtable_page_ctor(page); + if (!pgtable_page_ctor(page)) { + __free_page(page); + return NULL; + } return page; } diff --git a/arch/m68k/include/asm/thread_info.h b/arch/m68k/include/asm/thread_info.h index 126131f94a2c..21a4784ca5a1 100644 --- a/arch/m68k/include/asm/thread_info.h +++ b/arch/m68k/include/asm/thread_info.h @@ -35,8 +35,6 @@ struct thread_info { }; #endif /* __ASSEMBLY__ */ -#define PREEMPT_ACTIVE 0x4000000 - #define INIT_THREAD_INFO(tsk) \ { \ .task = &tsk, \ diff --git a/arch/m68k/kernel/entry.S b/arch/m68k/kernel/entry.S index a78f5649e8de..b54ac7aba850 100644 --- a/arch/m68k/kernel/entry.S +++ b/arch/m68k/kernel/entry.S @@ -45,7 +45,7 @@ .globl system_call, buserr, trap, resume .globl sys_call_table .globl __sys_fork, __sys_clone, __sys_vfork -.globl ret_from_interrupt, bad_interrupt +.globl bad_interrupt .globl auto_irqhandler_fixup .globl user_irqvec_fixup @@ -275,8 +275,6 @@ do_delayed_trace: ENTRY(auto_inthandler) SAVE_ALL_INT GET_CURRENT(%d0) - movel %d0,%a1 - addqb #1,%a1@(TINFO_PREEMPT+1) | put exception # in d0 bfextu %sp@(PT_OFF_FORMATVEC){#4,#10},%d0 subw #VEC_SPUR,%d0 @@ -286,32 +284,13 @@ ENTRY(auto_inthandler) auto_irqhandler_fixup = . + 2 jsr do_IRQ | process the IRQ addql #8,%sp | pop parameters off stack - -ret_from_interrupt: - movel %curptr@(TASK_STACK),%a1 - subqb #1,%a1@(TINFO_PREEMPT+1) - jeq ret_from_last_interrupt -2: RESTORE_ALL - - ALIGN -ret_from_last_interrupt: - moveq #(~ALLOWINT>>8)&0xff,%d0 - andb %sp@(PT_OFF_SR),%d0 - jne 2b - - /* check if we need to do software interrupts */ - tstl irq_stat+CPUSTAT_SOFTIRQ_PENDING - jeq .Lret_from_exception - pea ret_from_exception - jra do_softirq + jra ret_from_exception /* Handler for user defined interrupt vectors */ ENTRY(user_inthandler) SAVE_ALL_INT GET_CURRENT(%d0) - movel %d0,%a1 - addqb #1,%a1@(TINFO_PREEMPT+1) | put exception # in d0 bfextu %sp@(PT_OFF_FORMATVEC){#4,#10},%d0 user_irqvec_fixup = . + 2 @@ -321,29 +300,18 @@ user_irqvec_fixup = . + 2 movel %d0,%sp@- | put vector # on stack jsr do_IRQ | process the IRQ addql #8,%sp | pop parameters off stack - - movel %curptr@(TASK_STACK),%a1 - subqb #1,%a1@(TINFO_PREEMPT+1) - jeq ret_from_last_interrupt - RESTORE_ALL + jra ret_from_exception /* Handler for uninitialized and spurious interrupts */ ENTRY(bad_inthandler) SAVE_ALL_INT GET_CURRENT(%d0) - movel %d0,%a1 - addqb #1,%a1@(TINFO_PREEMPT+1) movel %sp,%sp@- jsr handle_badint addql #4,%sp - - movel %curptr@(TASK_STACK),%a1 - subqb #1,%a1@(TINFO_PREEMPT+1) - jeq ret_from_last_interrupt - RESTORE_ALL - + jra ret_from_exception resume: /* diff --git a/arch/m68k/kernel/ints.c b/arch/m68k/kernel/ints.c index 4d7da384eea0..077d3a70fed1 100644 --- a/arch/m68k/kernel/ints.c +++ b/arch/m68k/kernel/ints.c @@ -58,12 +58,6 @@ void __init init_IRQ(void) { int i; - /* assembly irq entry code relies on this... */ - if (HARDIRQ_MASK != 0x00ff0000) { - extern void hardirq_mask_is_broken(void); - hardirq_mask_is_broken(); - } - for (i = IRQ_AUTO_1; i <= IRQ_AUTO_7; i++) irq_set_chip_and_handler(i, &auto_irq_chip, handle_simple_irq); diff --git a/arch/m68k/platform/68000/entry.S b/arch/m68k/platform/68000/entry.S index 7f91c2fde509..23ac054c6e1a 100644 --- a/arch/m68k/platform/68000/entry.S +++ b/arch/m68k/platform/68000/entry.S @@ -27,7 +27,6 @@ .globl ret_from_exception .globl ret_from_signal .globl sys_call_table -.globl ret_from_interrupt .globl bad_interrupt .globl inthandler1 .globl inthandler2 @@ -137,7 +136,7 @@ inthandler1: movel #65,%sp@- /* put vector # on stack*/ jbsr process_int /* process the IRQ*/ 3: addql #8,%sp /* pop parameters off stack*/ - bra ret_from_interrupt + bra ret_from_exception inthandler2: SAVE_ALL_INT @@ -148,7 +147,7 @@ inthandler2: movel #66,%sp@- /* put vector # on stack*/ jbsr process_int /* process the IRQ*/ 3: addql #8,%sp /* pop parameters off stack*/ - bra ret_from_interrupt + bra ret_from_exception inthandler3: SAVE_ALL_INT @@ -159,7 +158,7 @@ inthandler3: movel #67,%sp@- /* put vector # on stack*/ jbsr process_int /* process the IRQ*/ 3: addql #8,%sp /* pop parameters off stack*/ - bra ret_from_interrupt + bra ret_from_exception inthandler4: SAVE_ALL_INT @@ -170,7 +169,7 @@ inthandler4: movel #68,%sp@- /* put vector # on stack*/ jbsr process_int /* process the IRQ*/ 3: addql #8,%sp /* pop parameters off stack*/ - bra ret_from_interrupt + bra ret_from_exception inthandler5: SAVE_ALL_INT @@ -181,7 +180,7 @@ inthandler5: movel #69,%sp@- /* put vector # on stack*/ jbsr process_int /* process the IRQ*/ 3: addql #8,%sp /* pop parameters off stack*/ - bra ret_from_interrupt + bra ret_from_exception inthandler6: SAVE_ALL_INT @@ -192,7 +191,7 @@ inthandler6: movel #70,%sp@- /* put vector # on stack*/ jbsr process_int /* process the IRQ*/ 3: addql #8,%sp /* pop parameters off stack*/ - bra ret_from_interrupt + bra ret_from_exception inthandler7: SAVE_ALL_INT @@ -203,7 +202,7 @@ inthandler7: movel #71,%sp@- /* put vector # on stack*/ jbsr process_int /* process the IRQ*/ 3: addql #8,%sp /* pop parameters off stack*/ - bra ret_from_interrupt + bra ret_from_exception inthandler: SAVE_ALL_INT @@ -214,23 +213,7 @@ inthandler: movel %d0,%sp@- /* put vector # on stack*/ jbsr process_int /* process the IRQ*/ 3: addql #8,%sp /* pop parameters off stack*/ - bra ret_from_interrupt - -ret_from_interrupt: - jeq 1f -2: - RESTORE_ALL -1: - moveb %sp@(PT_OFF_SR), %d0 - and #7, %d0 - jhi 2b - - /* check if we need to do software interrupts */ - jeq ret_from_exception - - pea ret_from_exception - jra do_softirq - + bra ret_from_exception /* * Handler for uninitialized and spurious interrupts. diff --git a/arch/m68k/platform/68360/entry.S b/arch/m68k/platform/68360/entry.S index 904fd9a4af4e..447c33ef37fd 100644 --- a/arch/m68k/platform/68360/entry.S +++ b/arch/m68k/platform/68360/entry.S @@ -29,7 +29,6 @@ .globl ret_from_exception .globl ret_from_signal .globl sys_call_table -.globl ret_from_interrupt .globl bad_interrupt .globl inthandler @@ -132,26 +131,9 @@ inthandler: movel %sp,%sp@- movel %d0,%sp@- /* put vector # on stack*/ - jbsr do_IRQ /* process the IRQ*/ -3: addql #8,%sp /* pop parameters off stack*/ - bra ret_from_interrupt - -ret_from_interrupt: - jeq 1f -2: - RESTORE_ALL -1: - moveb %sp@(PT_OFF_SR), %d0 - and #7, %d0 - jhi 2b - /* check if we need to do software interrupts */ - - movel irq_stat+CPUSTAT_SOFTIRQ_PENDING,%d0 - jeq ret_from_exception - - pea ret_from_exception - jra do_softirq - + jbsr do_IRQ /* process the IRQ */ + addql #8,%sp /* pop parameters off stack*/ + jra ret_from_exception /* * Handler for uninitialized and spurious interrupts. diff --git a/arch/metag/Kconfig b/arch/metag/Kconfig index 36368eb07e13..e56abd2c1b4f 100644 --- a/arch/metag/Kconfig +++ b/arch/metag/Kconfig @@ -111,7 +111,6 @@ config METAG_META21 config SMP bool "Symmetric multi-processing support" depends on METAG_META21 && METAG_META21_MMU - select USE_GENERIC_SMP_HELPERS help This enables support for systems with more than one thread running Linux. If you have a system with only one thread running Linux, diff --git a/arch/metag/include/asm/pgalloc.h b/arch/metag/include/asm/pgalloc.h index 275d9285141c..3104df0a4822 100644 --- a/arch/metag/include/asm/pgalloc.h +++ b/arch/metag/include/asm/pgalloc.h @@ -52,8 +52,12 @@ static inline pgtable_t pte_alloc_one(struct mm_struct *mm, { struct page *pte; pte = alloc_pages(GFP_KERNEL | __GFP_REPEAT | __GFP_ZERO, 0); - if (pte) - pgtable_page_ctor(pte); + if (!pte) + return NULL; + if (!pgtable_page_ctor(pte)) { + __free_page(pte); + return NULL; + } return pte; } diff --git a/arch/metag/include/asm/thread_info.h b/arch/metag/include/asm/thread_info.h index 7c4a33006142..b19e9c588a16 100644 --- a/arch/metag/include/asm/thread_info.h +++ b/arch/metag/include/asm/thread_info.h @@ -46,8 +46,6 @@ struct thread_info { #endif -#define PREEMPT_ACTIVE 0x10000000 - #ifdef CONFIG_4KSTACKS #define THREAD_SHIFT 12 #else diff --git a/arch/microblaze/Kconfig b/arch/microblaze/Kconfig index 655e1cadf692..e23cccde9c27 100644 --- a/arch/microblaze/Kconfig +++ b/arch/microblaze/Kconfig @@ -1,5 +1,6 @@ config MICROBLAZE def_bool y + select ARCH_MIGHT_HAVE_PC_PARPORT select HAVE_MEMBLOCK select HAVE_MEMBLOCK_NODE_MAP select HAVE_FUNCTION_TRACER diff --git a/arch/microblaze/include/asm/pgalloc.h b/arch/microblaze/include/asm/pgalloc.h index ebd35792482c..7fdf7fabc7d7 100644 --- a/arch/microblaze/include/asm/pgalloc.h +++ b/arch/microblaze/include/asm/pgalloc.h @@ -122,8 +122,13 @@ static inline struct page *pte_alloc_one(struct mm_struct *mm, #endif ptepage = alloc_pages(flags, 0); - if (ptepage) - clear_highpage(ptepage); + if (!ptepage) + return NULL; + clear_highpage(ptepage); + if (!pgtable_page_ctor(ptepage)) { + __free_page(ptepage); + return NULL; + } return ptepage; } @@ -158,8 +163,9 @@ extern inline void pte_free_slow(struct page *ptepage) __free_page(ptepage); } -extern inline void pte_free(struct mm_struct *mm, struct page *ptepage) +static inline void pte_free(struct mm_struct *mm, struct page *ptepage) { + pgtable_page_dtor(ptepage); __free_page(ptepage); } diff --git a/arch/microblaze/include/asm/thread_info.h b/arch/microblaze/include/asm/thread_info.h index de26ea6373de..8c9d36591a03 100644 --- a/arch/microblaze/include/asm/thread_info.h +++ b/arch/microblaze/include/asm/thread_info.h @@ -106,8 +106,6 @@ static inline struct thread_info *current_thread_info(void) /* thread information allocation */ #endif /* __ASSEMBLY__ */ -#define PREEMPT_ACTIVE 0x10000000 - /* * thread information flags * - these are process state flags that various assembly files may diff --git a/arch/mips/Kconfig b/arch/mips/Kconfig index 17cc7ff8458c..650de3976e7a 100644 --- a/arch/mips/Kconfig +++ b/arch/mips/Kconfig @@ -1,6 +1,7 @@ config MIPS bool default y + select ARCH_MIGHT_HAVE_PC_PARPORT select HAVE_CONTEXT_TRACKING select HAVE_GENERIC_DMA_COHERENT select HAVE_IDE @@ -2125,7 +2126,6 @@ source "mm/Kconfig" config SMP bool "Multi-Processing support" depends on SYS_SUPPORTS_SMP - select USE_GENERIC_SMP_HELPERS help This enables support for systems with more than one CPU. If you have a system with only one CPU, like most personal computers, say N. If diff --git a/arch/mips/configs/db1235_defconfig b/arch/mips/configs/db1235_defconfig index e2b4ad55462f..28e49f226dc0 100644 --- a/arch/mips/configs/db1235_defconfig +++ b/arch/mips/configs/db1235_defconfig @@ -351,7 +351,6 @@ CONFIG_USB_OHCI_HCD=y CONFIG_USB_OHCI_HCD_PLATFORM=y CONFIG_USB_STORAGE=y CONFIG_MMC=y -CONFIG_MMC_CLKGATE=y CONFIG_MMC_AU1X=y CONFIG_NEW_LEDS=y CONFIG_LEDS_CLASS=y diff --git a/arch/mips/include/asm/kvm_host.h b/arch/mips/include/asm/kvm_host.h index 4d6fa0bf1305..32966969f2f9 100644 --- a/arch/mips/include/asm/kvm_host.h +++ b/arch/mips/include/asm/kvm_host.h @@ -27,13 +27,6 @@ #define KVM_COALESCED_MMIO_PAGE_OFFSET 1 -/* Don't support huge pages */ -#define KVM_HPAGE_GFN_SHIFT(x) 0 - -/* We don't currently support large pages. */ -#define KVM_NR_PAGE_SIZES 1 -#define KVM_PAGES_PER_HPAGE(x) 1 - /* Special address that contains the comm page, used for reducing # of traps */ diff --git a/arch/mips/include/asm/octeon/cvmx-pip.h b/arch/mips/include/asm/octeon/cvmx-pip.h index a76fe5a57a9f..df69bfd2b006 100644 --- a/arch/mips/include/asm/octeon/cvmx-pip.h +++ b/arch/mips/include/asm/octeon/cvmx-pip.h @@ -192,13 +192,13 @@ typedef struct { /* Number of packets processed by PIP */ uint32_t packets; /* - * Number of indentified L2 multicast packets. Does not + * Number of identified L2 multicast packets. Does not * include broadcast packets. Only includes packets whose * parse mode is SKIP_TO_L2 */ uint32_t multicast_packets; /* - * Number of indentified L2 broadcast packets. Does not + * Number of identified L2 broadcast packets. Does not * include multicast packets. Only includes packets whose * parse mode is SKIP_TO_L2 */ diff --git a/arch/mips/include/asm/pgalloc.h b/arch/mips/include/asm/pgalloc.h index 881d18b4e298..b336037e8768 100644 --- a/arch/mips/include/asm/pgalloc.h +++ b/arch/mips/include/asm/pgalloc.h @@ -80,9 +80,12 @@ static inline struct page *pte_alloc_one(struct mm_struct *mm, struct page *pte; pte = alloc_pages(GFP_KERNEL | __GFP_REPEAT, PTE_ORDER); - if (pte) { - clear_highpage(pte); - pgtable_page_ctor(pte); + if (!pte) + return NULL; + clear_highpage(pte); + if (!pgtable_page_ctor(pte)) { + __free_page(pte); + return NULL; } return pte; } diff --git a/arch/mips/include/asm/thread_info.h b/arch/mips/include/asm/thread_info.h index f9b24bfbdbae..4f58ef6d0eed 100644 --- a/arch/mips/include/asm/thread_info.h +++ b/arch/mips/include/asm/thread_info.h @@ -92,8 +92,6 @@ static inline struct thread_info *current_thread_info(void) #define STACK_WARN (THREAD_SIZE / 8) -#define PREEMPT_ACTIVE 0x10000000 - /* * thread information flags * - these are process state flags that various assembly files may need to diff --git a/arch/mips/kvm/kvm_mips.c b/arch/mips/kvm/kvm_mips.c index a7b044536de4..73b34827826c 100644 --- a/arch/mips/kvm/kvm_mips.c +++ b/arch/mips/kvm/kvm_mips.c @@ -198,12 +198,13 @@ kvm_arch_dev_ioctl(struct file *filp, unsigned int ioctl, unsigned long arg) return -ENOIOCTLCMD; } -void kvm_arch_free_memslot(struct kvm_memory_slot *free, +void kvm_arch_free_memslot(struct kvm *kvm, struct kvm_memory_slot *free, struct kvm_memory_slot *dont) { } -int kvm_arch_create_memslot(struct kvm_memory_slot *slot, unsigned long npages) +int kvm_arch_create_memslot(struct kvm *kvm, struct kvm_memory_slot *slot, + unsigned long npages) { return 0; } diff --git a/arch/mn10300/Kconfig b/arch/mn10300/Kconfig index 6aaa1607001a..8bde9237d13b 100644 --- a/arch/mn10300/Kconfig +++ b/arch/mn10300/Kconfig @@ -181,7 +181,6 @@ endmenu config SMP bool "Symmetric multi-processing support" default y - select USE_GENERIC_SMP_HELPERS depends on MN10300_PROC_MN2WS0038 || MN10300_PROC_MN2WS0050 ---help--- This enables support for systems with more than one CPU. If you have diff --git a/arch/mn10300/include/asm/mmu_context.h b/arch/mn10300/include/asm/mmu_context.h index c67c2b5365a6..75dbe696f830 100644 --- a/arch/mn10300/include/asm/mmu_context.h +++ b/arch/mn10300/include/asm/mmu_context.h @@ -71,7 +71,7 @@ static inline unsigned long allocate_mmu_context(struct mm_struct *mm) local_flush_tlb_all(); /* fix the TLB version if needed (we avoid version #0 so as to - * distingush MMU_NO_CONTEXT) */ + * distinguish MMU_NO_CONTEXT) */ if (!mc) *pmc = mc = MMU_CONTEXT_FIRST_VERSION; } diff --git a/arch/mn10300/include/asm/pci.h b/arch/mn10300/include/asm/pci.h index 6f31cc0f1a87..166323824683 100644 --- a/arch/mn10300/include/asm/pci.h +++ b/arch/mn10300/include/asm/pci.h @@ -44,7 +44,6 @@ extern void unit_pci_init(void); #define pcibios_assign_all_busses() 0 #endif -extern unsigned long pci_mem_start; #define PCIBIOS_MIN_IO 0xBE000004 #define PCIBIOS_MIN_MEM 0xB8000000 diff --git a/arch/mn10300/include/asm/pgalloc.h b/arch/mn10300/include/asm/pgalloc.h index 146bacf193ea..0f25d5fa86f3 100644 --- a/arch/mn10300/include/asm/pgalloc.h +++ b/arch/mn10300/include/asm/pgalloc.h @@ -46,6 +46,7 @@ static inline void pte_free_kernel(struct mm_struct *mm, pte_t *pte) static inline void pte_free(struct mm_struct *mm, struct page *pte) { + pgtable_page_dtor(pte); __free_page(pte); } diff --git a/arch/mn10300/include/asm/thread_info.h b/arch/mn10300/include/asm/thread_info.h index 224b4262486d..bf280eaccd36 100644 --- a/arch/mn10300/include/asm/thread_info.h +++ b/arch/mn10300/include/asm/thread_info.h @@ -16,8 +16,6 @@ #include <asm/page.h> -#define PREEMPT_ACTIVE 0x10000000 - #ifdef CONFIG_4KSTACKS #define THREAD_SIZE (4096) #define THREAD_SIZE_ORDER (0) diff --git a/arch/mn10300/kernel/setup.c b/arch/mn10300/kernel/setup.c index ebac9c11f796..2ad7f32fa122 100644 --- a/arch/mn10300/kernel/setup.c +++ b/arch/mn10300/kernel/setup.c @@ -35,9 +35,6 @@ struct mn10300_cpuinfo boot_cpu_data; -/* For PCI or other memory-mapped resources */ -unsigned long pci_mem_start = 0x18000000; - static char __initdata cmd_line[COMMAND_LINE_SIZE]; char redboot_command_line[COMMAND_LINE_SIZE] = "console=ttyS0,115200 root=/dev/mtdblock3 rw"; diff --git a/arch/mn10300/mm/pgtable.c b/arch/mn10300/mm/pgtable.c index bd9ada693f95..e77a7c728081 100644 --- a/arch/mn10300/mm/pgtable.c +++ b/arch/mn10300/mm/pgtable.c @@ -78,8 +78,13 @@ struct page *pte_alloc_one(struct mm_struct *mm, unsigned long address) #else pte = alloc_pages(GFP_KERNEL|__GFP_REPEAT, 0); #endif - if (pte) - clear_highpage(pte); + if (!pte) + return NULL; + clear_highpage(pte); + if (!pgtable_page_ctor(pte)) { + __free_page(pte); + return NULL; + } return pte; } diff --git a/arch/mn10300/unit-asb2305/pci-asb2305.h b/arch/mn10300/unit-asb2305/pci-asb2305.h index 7fa66a0e4624..9e17aca5a2a1 100644 --- a/arch/mn10300/unit-asb2305/pci-asb2305.h +++ b/arch/mn10300/unit-asb2305/pci-asb2305.h @@ -35,7 +35,6 @@ extern void pcibios_resource_survey(void); /* pci.c */ -extern int pcibios_last_bus; extern struct pci_ops *pci_root_ops; extern struct irq_routing_table *pcibios_get_irq_routing_table(void); diff --git a/arch/mn10300/unit-asb2305/pci.c b/arch/mn10300/unit-asb2305/pci.c index e37fac0461f3..6b4339f8c9c2 100644 --- a/arch/mn10300/unit-asb2305/pci.c +++ b/arch/mn10300/unit-asb2305/pci.c @@ -24,7 +24,6 @@ unsigned int pci_probe = 1; -int pcibios_last_bus = -1; struct pci_ops *pci_root_ops; /* @@ -392,10 +391,6 @@ char *__init pcibios_setup(char *str) if (!strcmp(str, "off")) { pci_probe = 0; return NULL; - - } else if (!strncmp(str, "lastbus=", 8)) { - pcibios_last_bus = simple_strtol(str+8, NULL, 0); - return NULL; } return str; diff --git a/arch/openrisc/Makefile b/arch/openrisc/Makefile index 4739b8302a58..89076a66eee2 100644 --- a/arch/openrisc/Makefile +++ b/arch/openrisc/Makefile @@ -24,7 +24,7 @@ OBJCOPYFLAGS := -O binary -R .note -R .comment -S LDFLAGS_vmlinux := LIBGCC := $(shell $(CC) $(KBUILD_CFLAGS) -print-libgcc-file-name) -KBUILD_CFLAGS += -pipe -ffixed-r10 +KBUILD_CFLAGS += -pipe -ffixed-r10 -D__linux__ ifeq ($(CONFIG_OPENRISC_HAVE_INST_MUL),y) KBUILD_CFLAGS += $(call cc-option,-mhard-mul) diff --git a/arch/openrisc/configs/or1ksim_defconfig b/arch/openrisc/configs/or1ksim_defconfig index ea172bdfa36a..42fe5303a370 100644 --- a/arch/openrisc/configs/or1ksim_defconfig +++ b/arch/openrisc/configs/or1ksim_defconfig @@ -1,9 +1,9 @@ CONFIG_CROSS_COMPILE="or32-linux-" +CONFIG_NO_HZ=y CONFIG_LOG_BUF_SHIFT=14 CONFIG_BLK_DEV_INITRD=y # CONFIG_RD_GZIP is not set CONFIG_EXPERT=y -# CONFIG_SYSCTL_SYSCALL is not set # CONFIG_KALLSYMS is not set # CONFIG_EPOLL is not set # CONFIG_TIMERFD is not set @@ -15,7 +15,6 @@ CONFIG_SLOB=y CONFIG_MODULES=y # CONFIG_BLOCK is not set CONFIG_OPENRISC_BUILTIN_DTB="or1ksim" -CONFIG_NO_HZ=y CONFIG_HZ_100=y CONFIG_NET=y CONFIG_PACKET=y @@ -39,11 +38,8 @@ CONFIG_DEVTMPFS_MOUNT=y # CONFIG_FW_LOADER is not set CONFIG_PROC_DEVICETREE=y CONFIG_NETDEVICES=y -CONFIG_MICREL_PHY=y -CONFIG_NET_ETHERNET=y CONFIG_ETHOC=y -# CONFIG_NETDEV_1000 is not set -# CONFIG_NETDEV_10000 is not set +CONFIG_MICREL_PHY=y # CONFIG_WLAN is not set # CONFIG_INPUT is not set # CONFIG_SERIO is not set @@ -55,11 +51,9 @@ CONFIG_SERIAL_8250_CONSOLE=y CONFIG_SERIAL_OF_PLATFORM=y # CONFIG_HW_RANDOM is not set # CONFIG_HWMON is not set -# CONFIG_MFD_SUPPORT is not set # CONFIG_USB_SUPPORT is not set # CONFIG_DNOTIFY is not set CONFIG_TMPFS=y CONFIG_NFS_FS=y -CONFIG_NFS_V3=y # CONFIG_ENABLE_WARN_DEPRECATED is not set # CONFIG_ENABLE_MUST_CHECK is not set diff --git a/arch/openrisc/include/asm/Kbuild b/arch/openrisc/include/asm/Kbuild index 78405625e799..da1951a22907 100644 --- a/arch/openrisc/include/asm/Kbuild +++ b/arch/openrisc/include/asm/Kbuild @@ -65,6 +65,7 @@ generic-y += trace_clock.h generic-y += types.h generic-y += ucontext.h generic-y += user.h +generic-y += vga.h generic-y += word-at-a-time.h generic-y += xor.h generic-y += preempt.h diff --git a/arch/openrisc/include/asm/pgalloc.h b/arch/openrisc/include/asm/pgalloc.h index 05c39ecd2efd..21484e5b9e9a 100644 --- a/arch/openrisc/include/asm/pgalloc.h +++ b/arch/openrisc/include/asm/pgalloc.h @@ -78,8 +78,13 @@ static inline struct page *pte_alloc_one(struct mm_struct *mm, { struct page *pte; pte = alloc_pages(GFP_KERNEL|__GFP_REPEAT, 0); - if (pte) - clear_page(page_address(pte)); + if (!pte) + return NULL; + clear_page(page_address(pte)); + if (!pgtable_page_ctor(pte)) { + __free_page(pte); + return NULL; + } return pte; } @@ -90,6 +95,7 @@ static inline void pte_free_kernel(struct mm_struct *mm, pte_t *pte) static inline void pte_free(struct mm_struct *mm, struct page *pte) { + pgtable_page_dtor(pte); __free_page(pte); } diff --git a/arch/openrisc/kernel/module.c b/arch/openrisc/kernel/module.c index 10ff50f0202a..ef872ae4c878 100644 --- a/arch/openrisc/kernel/module.c +++ b/arch/openrisc/kernel/module.c @@ -47,12 +47,10 @@ int apply_relocate_add(Elf32_Shdr *sechdrs, *location = value; break; case R_OR32_CONST: - location = (uint16_t *)location + 1; - *((uint16_t *)location) = (uint16_t) (value); + *((uint16_t *)location + 1) = value; break; case R_OR32_CONSTH: - location = (uint16_t *)location + 1; - *((uint16_t *)location) = (uint16_t) (value >> 16); + *((uint16_t *)location + 1) = value >> 16; break; case R_OR32_JUMPTARG: value -= (uint32_t)location; diff --git a/arch/openrisc/kernel/setup.c b/arch/openrisc/kernel/setup.c index 09a769b69572..4fc7ccc0a2cf 100644 --- a/arch/openrisc/kernel/setup.c +++ b/arch/openrisc/kernel/setup.c @@ -40,6 +40,7 @@ #include <linux/device.h> #include <linux/of_platform.h> +#include <asm/sections.h> #include <asm/segment.h> #include <asm/pgtable.h> #include <asm/types.h> @@ -75,7 +76,7 @@ static unsigned long __init setup_memory(void) ram_start_pfn = PFN_UP(memory_start); /* free_ram_start_pfn is first page after kernel */ - free_ram_start_pfn = PFN_UP(__pa(&_end)); + free_ram_start_pfn = PFN_UP(__pa(_end)); ram_end_pfn = PFN_DOWN(memblock_end_of_DRAM()); max_pfn = ram_end_pfn; @@ -207,15 +208,15 @@ void __init setup_cpuinfo(void) * Falls back on built-in device tree in case null pointer is passed. */ -void __init or32_early_setup(unsigned int fdt) +void __init or32_early_setup(void *fdt) { - if (fdt) { - early_init_devtree((void*) fdt); - printk(KERN_INFO "FDT at 0x%08x\n", fdt); - } else { - early_init_devtree(__dtb_start); - printk(KERN_INFO "Compiled-in FDT at %p\n", __dtb_start); + if (fdt) + pr_info("FDT at %p\n", fdt); + else { + fdt = __dtb_start; + pr_info("Compiled-in FDT at %p\n", fdt); } + early_init_devtree(fdt); } static int __init openrisc_device_probe(void) @@ -288,10 +289,10 @@ void __init setup_arch(char **cmdline_p) setup_cpuinfo(); /* process 1's initial memory region is the kernel code/data */ - init_mm.start_code = (unsigned long)&_stext; - init_mm.end_code = (unsigned long)&_etext; - init_mm.end_data = (unsigned long)&_edata; - init_mm.brk = (unsigned long)&_end; + init_mm.start_code = (unsigned long)_stext; + init_mm.end_code = (unsigned long)_etext; + init_mm.end_data = (unsigned long)_edata; + init_mm.brk = (unsigned long)_end; #ifdef CONFIG_BLK_DEV_INITRD initrd_start = (unsigned long)&__initrd_start; diff --git a/arch/openrisc/kernel/vmlinux.h b/arch/openrisc/kernel/vmlinux.h index ee842a2d3f36..70b9ce41835c 100644 --- a/arch/openrisc/kernel/vmlinux.h +++ b/arch/openrisc/kernel/vmlinux.h @@ -1,10 +1,8 @@ #ifndef __OPENRISC_VMLINUX_H_ #define __OPENRISC_VMLINUX_H_ -extern char _stext, _etext, _edata, _end; #ifdef CONFIG_BLK_DEV_INITRD extern char __initrd_start, __initrd_end; -extern char __initramfs_start; #endif extern u32 __dtb_start[]; diff --git a/arch/parisc/Kconfig b/arch/parisc/Kconfig index 7dcde539d61e..b5f1858baf33 100644 --- a/arch/parisc/Kconfig +++ b/arch/parisc/Kconfig @@ -1,6 +1,7 @@ config PARISC def_bool y select ARCH_HAS_DEBUG_STRICT_USER_COPY_CHECKS + select ARCH_MIGHT_HAVE_PC_PARPORT select HAVE_IDE select HAVE_OPROFILE select HAVE_FUNCTION_TRACER if 64BIT @@ -226,7 +227,6 @@ endchoice config SMP bool "Symmetric multi-processing support" - select USE_GENERIC_SMP_HELPERS ---help--- This enables support for systems with more than one CPU. If you have a system with only one CPU, like most personal computers, say N. If diff --git a/arch/parisc/include/asm/pgalloc.h b/arch/parisc/include/asm/pgalloc.h index fc987a1c12a8..f213f5b4c423 100644 --- a/arch/parisc/include/asm/pgalloc.h +++ b/arch/parisc/include/asm/pgalloc.h @@ -121,8 +121,12 @@ static inline pgtable_t pte_alloc_one(struct mm_struct *mm, unsigned long address) { struct page *page = alloc_page(GFP_KERNEL|__GFP_REPEAT|__GFP_ZERO); - if (page) - pgtable_page_ctor(page); + if (!page) + return NULL; + if (!pgtable_page_ctor(page)) { + __free_page(page); + return NULL; + } return page; } diff --git a/arch/parisc/include/asm/socket.h b/arch/parisc/include/asm/socket.h new file mode 100644 index 000000000000..748016cb122d --- /dev/null +++ b/arch/parisc/include/asm/socket.h @@ -0,0 +1,11 @@ +#ifndef _ASM_SOCKET_H +#define _ASM_SOCKET_H + +#include <uapi/asm/socket.h> + +/* O_NONBLOCK clashes with the bits used for socket types. Therefore we + * have to define SOCK_NONBLOCK to a different value here. + */ +#define SOCK_NONBLOCK 0x40000000 + +#endif /* _ASM_SOCKET_H */ diff --git a/arch/parisc/include/asm/thread_info.h b/arch/parisc/include/asm/thread_info.h index bc7cf120106b..d5f97ea3a4e1 100644 --- a/arch/parisc/include/asm/thread_info.h +++ b/arch/parisc/include/asm/thread_info.h @@ -46,9 +46,6 @@ struct thread_info { #define THREAD_SIZE (PAGE_SIZE << THREAD_SIZE_ORDER) #define THREAD_SHIFT (PAGE_SHIFT + THREAD_SIZE_ORDER) -#define PREEMPT_ACTIVE_BIT 28 -#define PREEMPT_ACTIVE (1 << PREEMPT_ACTIVE_BIT) - /* * thread information flags */ diff --git a/arch/parisc/include/asm/uaccess.h b/arch/parisc/include/asm/uaccess.h index 63f4dd0b49c2..4006964d8e12 100644 --- a/arch/parisc/include/asm/uaccess.h +++ b/arch/parisc/include/asm/uaccess.h @@ -4,14 +4,11 @@ /* * User space memory access functions */ -#include <asm/processor.h> #include <asm/page.h> #include <asm/cache.h> #include <asm/errno.h> #include <asm-generic/uaccess-unaligned.h> -#include <linux/sched.h> - #define VERIFY_READ 0 #define VERIFY_WRITE 1 @@ -36,43 +33,12 @@ extern int __get_user_bad(void); extern int __put_kernel_bad(void); extern int __put_user_bad(void); - -/* - * Test whether a block of memory is a valid user space address. - * Returns 0 if the range is valid, nonzero otherwise. - */ -static inline int __range_not_ok(unsigned long addr, unsigned long size, - unsigned long limit) +static inline long access_ok(int type, const void __user * addr, + unsigned long size) { - unsigned long __newaddr = addr + size; - return (__newaddr < addr || __newaddr > limit || size > limit); + return 1; } -/** - * access_ok: - Checks if a user space pointer is valid - * @type: Type of access: %VERIFY_READ or %VERIFY_WRITE. Note that - * %VERIFY_WRITE is a superset of %VERIFY_READ - if it is safe - * to write to a block, it is always safe to read from it. - * @addr: User space pointer to start of block to check - * @size: Size of block to check - * - * Context: User context only. This function may sleep. - * - * Checks if a pointer to a block of memory in user space is valid. - * - * Returns true (nonzero) if the memory block may be valid, false (zero) - * if it is definitely invalid. - * - * Note that, depending on architecture, this function probably just - * checks that the pointer is in the user space range - after calling - * this function, memory access functions may still return -EFAULT. - */ -#define access_ok(type, addr, size) \ -( __chk_user_ptr(addr), \ - !__range_not_ok((unsigned long) (__force void *) (addr), \ - size, user_addr_max()) \ -) - #define put_user __put_user #define get_user __get_user @@ -253,11 +219,7 @@ extern long lstrnlen_user(const char __user *,long); /* * Complex access routines -- macros */ -#ifdef CONFIG_COMPAT -#define user_addr_max() (TASK_SIZE) -#else -#define user_addr_max() (DEFAULT_TASK_SIZE) -#endif +#define user_addr_max() (~0UL) #define strnlen_user lstrnlen_user #define strlen_user(str) lstrnlen_user(str, 0x7fffffffL) diff --git a/arch/parisc/include/uapi/asm/socket.h b/arch/parisc/include/uapi/asm/socket.h index 7c614d01f1fa..f33113a6141e 100644 --- a/arch/parisc/include/uapi/asm/socket.h +++ b/arch/parisc/include/uapi/asm/socket.h @@ -1,5 +1,5 @@ -#ifndef _ASM_SOCKET_H -#define _ASM_SOCKET_H +#ifndef _UAPI_ASM_SOCKET_H +#define _UAPI_ASM_SOCKET_H #include <asm/sockios.h> @@ -77,9 +77,4 @@ #define SO_MAX_PACING_RATE 0x4048 -/* O_NONBLOCK clashes with the bits used for socket types. Therefore we - * have to define SOCK_NONBLOCK to a different value here. - */ -#define SOCK_NONBLOCK 0x40000000 - -#endif /* _ASM_SOCKET_H */ +#endif /* _UAPI_ASM_SOCKET_H */ diff --git a/arch/parisc/lib/memcpy.c b/arch/parisc/lib/memcpy.c index b5507ec06b84..413dc1769299 100644 --- a/arch/parisc/lib/memcpy.c +++ b/arch/parisc/lib/memcpy.c @@ -161,7 +161,7 @@ static inline void prefetch_dst(const void *addr) /* Copy from a not-aligned src to an aligned dst, using shifts. Handles 4 words * per loop. This code is derived from glibc. */ -static inline unsigned long copy_dstaligned(unsigned long dst, +static noinline unsigned long copy_dstaligned(unsigned long dst, unsigned long src, unsigned long len) { /* gcc complains that a2 and a3 may be uninitialized, but actually @@ -276,7 +276,7 @@ handle_store_error: /* Returns PA_MEMCPY_OK, PA_MEMCPY_LOAD_ERROR or PA_MEMCPY_STORE_ERROR. * In case of an access fault the faulty address can be read from the per_cpu * exception data struct. */ -static unsigned long pa_memcpy_internal(void *dstp, const void *srcp, +static noinline unsigned long pa_memcpy_internal(void *dstp, const void *srcp, unsigned long len) { register unsigned long src, dst, t1, t2, t3; @@ -529,7 +529,7 @@ long probe_kernel_read(void *dst, const void *src, size_t size) { unsigned long addr = (unsigned long)src; - if (size < 0 || addr < PAGE_SIZE) + if (addr < PAGE_SIZE) return -EFAULT; /* check for I/O space F_EXTEND(0xfff00000) access as well? */ diff --git a/arch/parisc/mm/fault.c b/arch/parisc/mm/fault.c index 7584a5df0fa4..9d08c71a967e 100644 --- a/arch/parisc/mm/fault.c +++ b/arch/parisc/mm/fault.c @@ -282,16 +282,34 @@ bad_area: #endif switch (code) { case 15: /* Data TLB miss fault/Data page fault */ + /* send SIGSEGV when outside of vma */ + if (!vma || + address < vma->vm_start || address > vma->vm_end) { + si.si_signo = SIGSEGV; + si.si_code = SEGV_MAPERR; + break; + } + + /* send SIGSEGV for wrong permissions */ + if ((vma->vm_flags & acc_type) != acc_type) { + si.si_signo = SIGSEGV; + si.si_code = SEGV_ACCERR; + break; + } + + /* probably address is outside of mapped file */ + /* fall through */ case 17: /* NA data TLB miss / page fault */ case 18: /* Unaligned access - PCXS only */ si.si_signo = SIGBUS; - si.si_code = BUS_ADRERR; + si.si_code = (code == 18) ? BUS_ADRALN : BUS_ADRERR; break; case 16: /* Non-access instruction TLB miss fault */ case 26: /* PCXL: Data memory access rights trap */ default: si.si_signo = SIGSEGV; - si.si_code = SEGV_MAPERR; + si.si_code = (code == 26) ? SEGV_ACCERR : SEGV_MAPERR; + break; } si.si_errno = 0; si.si_addr = (void __user *) address; diff --git a/arch/powerpc/Kconfig b/arch/powerpc/Kconfig index 2f898d63eb96..b44b52c0a8f0 100644 --- a/arch/powerpc/Kconfig +++ b/arch/powerpc/Kconfig @@ -85,6 +85,7 @@ config GENERIC_HWEIGHT config PPC bool default y + select ARCH_MIGHT_HAVE_PC_PARPORT select BINFMT_ELF select OF select OF_EARLY_FLATTREE @@ -106,7 +107,6 @@ config PPC select HAVE_MEMBLOCK_NODE_MAP select HAVE_DMA_ATTRS select HAVE_DMA_API_DEBUG - select USE_GENERIC_SMP_HELPERS if SMP select HAVE_OPROFILE select HAVE_DEBUG_KMEMLEAK select GENERIC_ATOMIC64 if PPC32 diff --git a/arch/powerpc/Makefile b/arch/powerpc/Makefile index 607acf54a425..8a2463670a5b 100644 --- a/arch/powerpc/Makefile +++ b/arch/powerpc/Makefile @@ -111,6 +111,7 @@ endif endif CFLAGS-$(CONFIG_PPC64) := -mtraceback=no -mcall-aixdesc +CFLAGS-$(CONFIG_PPC64) += $(call cc-option,-mabi=elfv1) CFLAGS-$(CONFIG_PPC64) += $(call cc-option,-mcmodel=medium,-mminimal-toc) CFLAGS-$(CONFIG_PPC64) += $(call cc-option,-mno-pointers-to-nested-functions) CFLAGS-$(CONFIG_PPC32) := -ffixed-r2 $(MULTIPLEWORD) diff --git a/arch/powerpc/boot/dts/fsl/b4si-post.dtsi b/arch/powerpc/boot/dts/fsl/b4si-post.dtsi index 4c617bf8cdb2..4f6e48277c46 100644 --- a/arch/powerpc/boot/dts/fsl/b4si-post.dtsi +++ b/arch/powerpc/boot/dts/fsl/b4si-post.dtsi @@ -223,13 +223,13 @@ reg = <0xe2000 0x1000>; }; -/include/ "qoriq-dma-0.dtsi" +/include/ "elo3-dma-0.dtsi" dma@100300 { fsl,iommu-parent = <&pamu0>; fsl,liodn-reg = <&guts 0x580>; /* DMA1LIODNR */ }; -/include/ "qoriq-dma-1.dtsi" +/include/ "elo3-dma-1.dtsi" dma@101300 { fsl,iommu-parent = <&pamu0>; fsl,liodn-reg = <&guts 0x584>; /* DMA2LIODNR */ diff --git a/arch/powerpc/boot/dts/fsl/elo3-dma-0.dtsi b/arch/powerpc/boot/dts/fsl/elo3-dma-0.dtsi new file mode 100644 index 000000000000..3c210e0d5201 --- /dev/null +++ b/arch/powerpc/boot/dts/fsl/elo3-dma-0.dtsi @@ -0,0 +1,82 @@ +/* + * QorIQ Elo3 DMA device tree stub [ controller @ offset 0x100000 ] + * + * Copyright 2013 Freescale Semiconductor Inc. + * + * Redistribution and use in source and binary forms, with or without + * modification, are permitted provided that the following conditions are met: + * * Redistributions of source code must retain the above copyright + * notice, this list of conditions and the following disclaimer. + * * Redistributions in binary form must reproduce the above copyright + * notice, this list of conditions and the following disclaimer in the + * documentation and/or other materials provided with the distribution. + * * Neither the name of Freescale Semiconductor nor the + * names of its contributors may be used to endorse or promote products + * derived from this software without specific prior written permission. + * + * + * ALTERNATIVELY, this software may be distributed under the terms of the + * GNU General Public License ("GPL") as published by the Free Software + * Foundation, either version 2 of that License or (at your option) any + * later version. + * + * THIS SOFTWARE IS PROVIDED BY Freescale Semiconductor ``AS IS'' AND ANY + * EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED + * WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE + * DISCLAIMED. IN NO EVENT SHALL Freescale Semiconductor BE LIABLE FOR ANY + * DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES + * (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; + * LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND + * ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT + * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS + * SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE. + */ + +dma0: dma@100300 { + #address-cells = <1>; + #size-cells = <1>; + compatible = "fsl,elo3-dma"; + reg = <0x100300 0x4>, + <0x100600 0x4>; + ranges = <0x0 0x100100 0x500>; + dma-channel@0 { + compatible = "fsl,eloplus-dma-channel"; + reg = <0x0 0x80>; + interrupts = <28 2 0 0>; + }; + dma-channel@80 { + compatible = "fsl,eloplus-dma-channel"; + reg = <0x80 0x80>; + interrupts = <29 2 0 0>; + }; + dma-channel@100 { + compatible = "fsl,eloplus-dma-channel"; + reg = <0x100 0x80>; + interrupts = <30 2 0 0>; + }; + dma-channel@180 { + compatible = "fsl,eloplus-dma-channel"; + reg = <0x180 0x80>; + interrupts = <31 2 0 0>; + }; + dma-channel@300 { + compatible = "fsl,eloplus-dma-channel"; + reg = <0x300 0x80>; + interrupts = <76 2 0 0>; + }; + dma-channel@380 { + compatible = "fsl,eloplus-dma-channel"; + reg = <0x380 0x80>; + interrupts = <77 2 0 0>; + }; + dma-channel@400 { + compatible = "fsl,eloplus-dma-channel"; + reg = <0x400 0x80>; + interrupts = <78 2 0 0>; + }; + dma-channel@480 { + compatible = "fsl,eloplus-dma-channel"; + reg = <0x480 0x80>; + interrupts = <79 2 0 0>; + }; +}; diff --git a/arch/powerpc/boot/dts/fsl/elo3-dma-1.dtsi b/arch/powerpc/boot/dts/fsl/elo3-dma-1.dtsi new file mode 100644 index 000000000000..cccf3bb38224 --- /dev/null +++ b/arch/powerpc/boot/dts/fsl/elo3-dma-1.dtsi @@ -0,0 +1,82 @@ +/* + * QorIQ Elo3 DMA device tree stub [ controller @ offset 0x101000 ] + * + * Copyright 2013 Freescale Semiconductor Inc. + * + * Redistribution and use in source and binary forms, with or without + * modification, are permitted provided that the following conditions are met: + * * Redistributions of source code must retain the above copyright + * notice, this list of conditions and the following disclaimer. + * * Redistributions in binary form must reproduce the above copyright + * notice, this list of conditions and the following disclaimer in the + * documentation and/or other materials provided with the distribution. + * * Neither the name of Freescale Semiconductor nor the + * names of its contributors may be used to endorse or promote products + * derived from this software without specific prior written permission. + * + * + * ALTERNATIVELY, this software may be distributed under the terms of the + * GNU General Public License ("GPL") as published by the Free Software + * Foundation, either version 2 of that License or (at your option) any + * later version. + * + * THIS SOFTWARE IS PROVIDED BY Freescale Semiconductor ``AS IS'' AND ANY + * EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED + * WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE + * DISCLAIMED. IN NO EVENT SHALL Freescale Semiconductor BE LIABLE FOR ANY + * DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES + * (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; + * LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND + * ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT + * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS + * SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE. + */ + +dma1: dma@101300 { + #address-cells = <1>; + #size-cells = <1>; + compatible = "fsl,elo3-dma"; + reg = <0x101300 0x4>, + <0x101600 0x4>; + ranges = <0x0 0x101100 0x500>; + dma-channel@0 { + compatible = "fsl,eloplus-dma-channel"; + reg = <0x0 0x80>; + interrupts = <32 2 0 0>; + }; + dma-channel@80 { + compatible = "fsl,eloplus-dma-channel"; + reg = <0x80 0x80>; + interrupts = <33 2 0 0>; + }; + dma-channel@100 { + compatible = "fsl,eloplus-dma-channel"; + reg = <0x100 0x80>; + interrupts = <34 2 0 0>; + }; + dma-channel@180 { + compatible = "fsl,eloplus-dma-channel"; + reg = <0x180 0x80>; + interrupts = <35 2 0 0>; + }; + dma-channel@300 { + compatible = "fsl,eloplus-dma-channel"; + reg = <0x300 0x80>; + interrupts = <80 2 0 0>; + }; + dma-channel@380 { + compatible = "fsl,eloplus-dma-channel"; + reg = <0x380 0x80>; + interrupts = <81 2 0 0>; + }; + dma-channel@400 { + compatible = "fsl,eloplus-dma-channel"; + reg = <0x400 0x80>; + interrupts = <82 2 0 0>; + }; + dma-channel@480 { + compatible = "fsl,eloplus-dma-channel"; + reg = <0x480 0x80>; + interrupts = <83 2 0 0>; + }; +}; diff --git a/arch/powerpc/boot/dts/fsl/t4240si-post.dtsi b/arch/powerpc/boot/dts/fsl/t4240si-post.dtsi index 510afa362de1..4143a9733cd0 100644 --- a/arch/powerpc/boot/dts/fsl/t4240si-post.dtsi +++ b/arch/powerpc/boot/dts/fsl/t4240si-post.dtsi @@ -387,8 +387,8 @@ reg = <0xea000 0x4000>; }; -/include/ "qoriq-dma-0.dtsi" -/include/ "qoriq-dma-1.dtsi" +/include/ "elo3-dma-0.dtsi" +/include/ "elo3-dma-1.dtsi" /include/ "qoriq-espi-0.dtsi" spi@110000 { diff --git a/arch/powerpc/configs/pseries_le_defconfig b/arch/powerpc/configs/pseries_le_defconfig new file mode 100644 index 000000000000..62771e0adb7c --- /dev/null +++ b/arch/powerpc/configs/pseries_le_defconfig @@ -0,0 +1,352 @@ +CONFIG_PPC64=y +CONFIG_ALTIVEC=y +CONFIG_VSX=y +CONFIG_SMP=y +CONFIG_NR_CPUS=2048 +CONFIG_CPU_LITTLE_ENDIAN=y +CONFIG_SYSVIPC=y +CONFIG_POSIX_MQUEUE=y +CONFIG_AUDIT=y +CONFIG_AUDITSYSCALL=y +CONFIG_IRQ_DOMAIN_DEBUG=y +CONFIG_NO_HZ=y +CONFIG_HIGH_RES_TIMERS=y +CONFIG_TASKSTATS=y +CONFIG_TASK_DELAY_ACCT=y +CONFIG_TASK_XACCT=y +CONFIG_TASK_IO_ACCOUNTING=y +CONFIG_IKCONFIG=y +CONFIG_IKCONFIG_PROC=y +CONFIG_CGROUPS=y +CONFIG_CGROUP_FREEZER=y +CONFIG_CGROUP_DEVICE=y +CONFIG_CPUSETS=y +CONFIG_CGROUP_CPUACCT=y +CONFIG_BLK_DEV_INITRD=y +# CONFIG_COMPAT_BRK is not set +CONFIG_PROFILING=y +CONFIG_OPROFILE=y +CONFIG_KPROBES=y +CONFIG_JUMP_LABEL=y +CONFIG_MODULES=y +CONFIG_MODULE_UNLOAD=y +CONFIG_MODVERSIONS=y +CONFIG_MODULE_SRCVERSION_ALL=y +CONFIG_PARTITION_ADVANCED=y +CONFIG_PPC_SPLPAR=y +CONFIG_SCANLOG=m +CONFIG_PPC_SMLPAR=y +CONFIG_DTL=y +# CONFIG_PPC_PMAC is not set +CONFIG_RTAS_FLASH=m +CONFIG_IBMEBUS=y +CONFIG_HZ_100=y +CONFIG_BINFMT_MISC=m +CONFIG_PPC_TRANSACTIONAL_MEM=y +CONFIG_KEXEC=y +CONFIG_IRQ_ALL_CPUS=y +CONFIG_MEMORY_HOTPLUG=y +CONFIG_MEMORY_HOTREMOVE=y +CONFIG_CMA=y +CONFIG_PPC_64K_PAGES=y +CONFIG_PPC_SUBPAGE_PROT=y +CONFIG_SCHED_SMT=y +CONFIG_HOTPLUG_PCI=y +CONFIG_HOTPLUG_PCI_RPA=m +CONFIG_HOTPLUG_PCI_RPA_DLPAR=m +CONFIG_PACKET=y +CONFIG_UNIX=y +CONFIG_XFRM_USER=m +CONFIG_NET_KEY=m +CONFIG_INET=y +CONFIG_IP_MULTICAST=y +CONFIG_NET_IPIP=y +CONFIG_SYN_COOKIES=y +CONFIG_INET_AH=m +CONFIG_INET_ESP=m +CONFIG_INET_IPCOMP=m +# CONFIG_IPV6 is not set +CONFIG_NETFILTER=y +CONFIG_NF_CONNTRACK=m +CONFIG_NF_CONNTRACK_EVENTS=y +CONFIG_NF_CT_PROTO_UDPLITE=m +CONFIG_NF_CONNTRACK_FTP=m +CONFIG_NF_CONNTRACK_IRC=m +CONFIG_NF_CONNTRACK_TFTP=m +CONFIG_NF_CT_NETLINK=m +CONFIG_NETFILTER_XT_TARGET_CLASSIFY=m +CONFIG_NETFILTER_XT_TARGET_CONNMARK=m +CONFIG_NETFILTER_XT_TARGET_MARK=m +CONFIG_NETFILTER_XT_TARGET_NFLOG=m +CONFIG_NETFILTER_XT_TARGET_NFQUEUE=m +CONFIG_NETFILTER_XT_TARGET_TCPMSS=m +CONFIG_NETFILTER_XT_MATCH_COMMENT=m +CONFIG_NETFILTER_XT_MATCH_CONNBYTES=m +CONFIG_NETFILTER_XT_MATCH_CONNLIMIT=m +CONFIG_NETFILTER_XT_MATCH_CONNMARK=m +CONFIG_NETFILTER_XT_MATCH_CONNTRACK=m +CONFIG_NETFILTER_XT_MATCH_DCCP=m +CONFIG_NETFILTER_XT_MATCH_DSCP=m +CONFIG_NETFILTER_XT_MATCH_ESP=m +CONFIG_NETFILTER_XT_MATCH_HASHLIMIT=m +CONFIG_NETFILTER_XT_MATCH_HELPER=m +CONFIG_NETFILTER_XT_MATCH_IPRANGE=m +CONFIG_NETFILTER_XT_MATCH_LENGTH=m +CONFIG_NETFILTER_XT_MATCH_LIMIT=m +CONFIG_NETFILTER_XT_MATCH_MAC=m +CONFIG_NETFILTER_XT_MATCH_MARK=m +CONFIG_NETFILTER_XT_MATCH_MULTIPORT=m +CONFIG_NETFILTER_XT_MATCH_OWNER=m +CONFIG_NETFILTER_XT_MATCH_POLICY=m +CONFIG_NETFILTER_XT_MATCH_PKTTYPE=m +CONFIG_NETFILTER_XT_MATCH_QUOTA=m +CONFIG_NETFILTER_XT_MATCH_RATEEST=m +CONFIG_NETFILTER_XT_MATCH_REALM=m +CONFIG_NETFILTER_XT_MATCH_RECENT=m +CONFIG_NETFILTER_XT_MATCH_SCTP=m +CONFIG_NETFILTER_XT_MATCH_STATE=m +CONFIG_NETFILTER_XT_MATCH_STATISTIC=m +CONFIG_NETFILTER_XT_MATCH_STRING=m +CONFIG_NETFILTER_XT_MATCH_TCPMSS=m +CONFIG_NETFILTER_XT_MATCH_TIME=m +CONFIG_NETFILTER_XT_MATCH_U32=m +CONFIG_NF_CONNTRACK_IPV4=m +CONFIG_IP_NF_IPTABLES=m +CONFIG_IP_NF_MATCH_AH=m +CONFIG_IP_NF_MATCH_ECN=m +CONFIG_IP_NF_MATCH_TTL=m +CONFIG_IP_NF_FILTER=m +CONFIG_IP_NF_TARGET_REJECT=m +CONFIG_IP_NF_TARGET_ULOG=m +CONFIG_UEVENT_HELPER_PATH="/sbin/hotplug" +CONFIG_DEVTMPFS=y +CONFIG_DEVTMPFS_MOUNT=y +CONFIG_PROC_DEVICETREE=y +CONFIG_PARPORT=m +CONFIG_PARPORT_PC=m +CONFIG_BLK_DEV_FD=m +CONFIG_BLK_DEV_LOOP=y +CONFIG_BLK_DEV_NBD=m +CONFIG_BLK_DEV_RAM=y +CONFIG_BLK_DEV_RAM_SIZE=65536 +CONFIG_VIRTIO_BLK=m +CONFIG_IDE=y +CONFIG_BLK_DEV_IDECD=y +CONFIG_BLK_DEV_GENERIC=y +CONFIG_BLK_DEV_AMD74XX=y +CONFIG_BLK_DEV_SD=y +CONFIG_CHR_DEV_ST=y +CONFIG_BLK_DEV_SR=y +CONFIG_BLK_DEV_SR_VENDOR=y +CONFIG_CHR_DEV_SG=y +CONFIG_SCSI_MULTI_LUN=y +CONFIG_SCSI_CONSTANTS=y +CONFIG_SCSI_FC_ATTRS=y +CONFIG_SCSI_CXGB3_ISCSI=m +CONFIG_SCSI_CXGB4_ISCSI=m +CONFIG_SCSI_BNX2_ISCSI=m +CONFIG_BE2ISCSI=m +CONFIG_SCSI_MPT2SAS=m +CONFIG_SCSI_IBMVSCSI=y +CONFIG_SCSI_IBMVFC=m +CONFIG_SCSI_SYM53C8XX_2=y +CONFIG_SCSI_SYM53C8XX_DMA_ADDRESSING_MODE=0 +CONFIG_SCSI_IPR=y +CONFIG_SCSI_QLA_FC=m +CONFIG_SCSI_QLA_ISCSI=m +CONFIG_SCSI_LPFC=m +CONFIG_SCSI_VIRTIO=m +CONFIG_SCSI_DH=m +CONFIG_SCSI_DH_RDAC=m +CONFIG_SCSI_DH_ALUA=m +CONFIG_ATA=y +# CONFIG_ATA_SFF is not set +CONFIG_MD=y +CONFIG_BLK_DEV_MD=y +CONFIG_MD_LINEAR=y +CONFIG_MD_RAID0=y +CONFIG_MD_RAID1=y +CONFIG_MD_RAID10=m +CONFIG_MD_RAID456=m +CONFIG_MD_MULTIPATH=m +CONFIG_MD_FAULTY=m +CONFIG_BLK_DEV_DM=y +CONFIG_DM_CRYPT=m +CONFIG_DM_SNAPSHOT=m +CONFIG_DM_MIRROR=m +CONFIG_DM_ZERO=m +CONFIG_DM_MULTIPATH=m +CONFIG_DM_MULTIPATH_QL=m +CONFIG_DM_MULTIPATH_ST=m +CONFIG_DM_UEVENT=y +CONFIG_BONDING=m +CONFIG_DUMMY=m +CONFIG_NETCONSOLE=y +CONFIG_NETPOLL_TRAP=y +CONFIG_TUN=m +CONFIG_VIRTIO_NET=m +CONFIG_VORTEX=y +CONFIG_ACENIC=m +CONFIG_ACENIC_OMIT_TIGON_I=y +CONFIG_PCNET32=y +CONFIG_TIGON3=y +CONFIG_CHELSIO_T1=m +CONFIG_BE2NET=m +CONFIG_S2IO=m +CONFIG_IBMVETH=y +CONFIG_EHEA=y +CONFIG_E100=y +CONFIG_E1000=y +CONFIG_E1000E=y +CONFIG_IXGB=m +CONFIG_IXGBE=m +CONFIG_MLX4_EN=m +CONFIG_MYRI10GE=m +CONFIG_QLGE=m +CONFIG_NETXEN_NIC=m +CONFIG_PPP=m +CONFIG_PPP_BSDCOMP=m +CONFIG_PPP_DEFLATE=m +CONFIG_PPPOE=m +CONFIG_PPP_ASYNC=m +CONFIG_PPP_SYNC_TTY=m +# CONFIG_INPUT_MOUSEDEV_PSAUX is not set +CONFIG_INPUT_EVDEV=m +CONFIG_INPUT_MISC=y +CONFIG_INPUT_PCSPKR=m +# CONFIG_SERIO_SERPORT is not set +CONFIG_SERIAL_8250=y +CONFIG_SERIAL_8250_CONSOLE=y +CONFIG_SERIAL_ICOM=m +CONFIG_SERIAL_JSM=m +CONFIG_HVC_CONSOLE=y +CONFIG_HVC_RTAS=y +CONFIG_HVCS=m +CONFIG_VIRTIO_CONSOLE=m +CONFIG_IBM_BSR=m +CONFIG_GEN_RTC=y +CONFIG_RAW_DRIVER=y +CONFIG_MAX_RAW_DEVS=1024 +CONFIG_FB=y +CONFIG_FIRMWARE_EDID=y +CONFIG_FB_OF=y +CONFIG_FB_MATROX=y +CONFIG_FB_MATROX_MILLENIUM=y +CONFIG_FB_MATROX_MYSTIQUE=y +CONFIG_FB_MATROX_G=y +CONFIG_FB_RADEON=y +CONFIG_FB_IBM_GXT4500=y +CONFIG_LCD_PLATFORM=m +# CONFIG_VGA_CONSOLE is not set +CONFIG_FRAMEBUFFER_CONSOLE=y +CONFIG_LOGO=y +CONFIG_HID_GYRATION=y +CONFIG_HID_PANTHERLORD=y +CONFIG_HID_PETALYNX=y +CONFIG_HID_SAMSUNG=y +CONFIG_HID_SUNPLUS=y +CONFIG_USB_HIDDEV=y +CONFIG_USB=y +CONFIG_USB_MON=m +CONFIG_USB_EHCI_HCD=y +# CONFIG_USB_EHCI_HCD_PPC_OF is not set +CONFIG_USB_OHCI_HCD=y +CONFIG_USB_STORAGE=m +CONFIG_INFINIBAND=m +CONFIG_INFINIBAND_USER_MAD=m +CONFIG_INFINIBAND_USER_ACCESS=m +CONFIG_INFINIBAND_MTHCA=m +CONFIG_INFINIBAND_EHCA=m +CONFIG_INFINIBAND_CXGB3=m +CONFIG_INFINIBAND_CXGB4=m +CONFIG_MLX4_INFINIBAND=m +CONFIG_INFINIBAND_IPOIB=m +CONFIG_INFINIBAND_IPOIB_CM=y +CONFIG_INFINIBAND_SRP=m +CONFIG_INFINIBAND_ISER=m +CONFIG_VIRTIO_PCI=m +CONFIG_VIRTIO_BALLOON=m +CONFIG_EXT2_FS=y +CONFIG_EXT2_FS_XATTR=y +CONFIG_EXT2_FS_POSIX_ACL=y +CONFIG_EXT2_FS_SECURITY=y +CONFIG_EXT2_FS_XIP=y +CONFIG_EXT3_FS=y +CONFIG_EXT3_FS_POSIX_ACL=y +CONFIG_EXT3_FS_SECURITY=y +CONFIG_EXT4_FS=y +CONFIG_EXT4_FS_POSIX_ACL=y +CONFIG_EXT4_FS_SECURITY=y +CONFIG_REISERFS_FS=y +CONFIG_REISERFS_FS_XATTR=y +CONFIG_REISERFS_FS_POSIX_ACL=y +CONFIG_REISERFS_FS_SECURITY=y +CONFIG_JFS_FS=m +CONFIG_JFS_POSIX_ACL=y +CONFIG_JFS_SECURITY=y +CONFIG_XFS_FS=m +CONFIG_XFS_POSIX_ACL=y +CONFIG_BTRFS_FS=m +CONFIG_BTRFS_FS_POSIX_ACL=y +CONFIG_NILFS2_FS=m +CONFIG_AUTOFS4_FS=m +CONFIG_FUSE_FS=m +CONFIG_ISO9660_FS=y +CONFIG_UDF_FS=m +CONFIG_MSDOS_FS=y +CONFIG_VFAT_FS=y +CONFIG_PROC_KCORE=y +CONFIG_TMPFS=y +CONFIG_TMPFS_POSIX_ACL=y +CONFIG_HUGETLBFS=y +CONFIG_CRAMFS=m +CONFIG_SQUASHFS=m +CONFIG_SQUASHFS_XATTR=y +CONFIG_SQUASHFS_LZO=y +CONFIG_SQUASHFS_XZ=y +CONFIG_PSTORE=y +CONFIG_NFS_FS=y +CONFIG_NFS_V3_ACL=y +CONFIG_NFS_V4=y +CONFIG_NFSD=m +CONFIG_NFSD_V3_ACL=y +CONFIG_NFSD_V4=y +CONFIG_CIFS=m +CONFIG_CIFS_XATTR=y +CONFIG_CIFS_POSIX=y +CONFIG_NLS_DEFAULT="utf8" +CONFIG_NLS_CODEPAGE_437=y +CONFIG_NLS_ASCII=y +CONFIG_NLS_ISO8859_1=y +CONFIG_NLS_UTF8=y +CONFIG_CRC_T10DIF=y +CONFIG_MAGIC_SYSRQ=y +CONFIG_DEBUG_KERNEL=y +CONFIG_DEBUG_STACK_USAGE=y +CONFIG_DEBUG_STACKOVERFLOW=y +CONFIG_LOCKUP_DETECTOR=y +CONFIG_LATENCYTOP=y +CONFIG_SCHED_TRACER=y +CONFIG_BLK_DEV_IO_TRACE=y +CONFIG_CODE_PATCHING_SELFTEST=y +CONFIG_FTR_FIXUP_SELFTEST=y +CONFIG_MSI_BITMAP_SELFTEST=y +CONFIG_XMON=y +CONFIG_CRYPTO_TEST=m +CONFIG_CRYPTO_PCBC=m +CONFIG_CRYPTO_HMAC=y +CONFIG_CRYPTO_MICHAEL_MIC=m +CONFIG_CRYPTO_TGR192=m +CONFIG_CRYPTO_WP512=m +CONFIG_CRYPTO_ANUBIS=m +CONFIG_CRYPTO_BLOWFISH=m +CONFIG_CRYPTO_CAST6=m +CONFIG_CRYPTO_KHAZAD=m +CONFIG_CRYPTO_SALSA20=m +CONFIG_CRYPTO_SERPENT=m +CONFIG_CRYPTO_TEA=m +CONFIG_CRYPTO_TWOFISH=m +CONFIG_CRYPTO_LZO=m +# CONFIG_CRYPTO_ANSI_CPRNG is not set +CONFIG_CRYPTO_DEV_NX=y +CONFIG_CRYPTO_DEV_NX_ENCRYPT=m diff --git a/arch/powerpc/include/asm/disassemble.h b/arch/powerpc/include/asm/disassemble.h index 9b198d1b3b2b..856f8deb557a 100644 --- a/arch/powerpc/include/asm/disassemble.h +++ b/arch/powerpc/include/asm/disassemble.h @@ -77,4 +77,8 @@ static inline unsigned int get_d(u32 inst) return inst & 0xffff; } +static inline unsigned int get_oc(u32 inst) +{ + return (inst >> 11) & 0x7fff; +} #endif /* __ASM_PPC_DISASSEMBLE_H__ */ diff --git a/arch/powerpc/include/asm/elf.h b/arch/powerpc/include/asm/elf.h index cc0655a702a7..935b5e7a1436 100644 --- a/arch/powerpc/include/asm/elf.h +++ b/arch/powerpc/include/asm/elf.h @@ -31,6 +31,8 @@ extern unsigned long randomize_et_dyn(unsigned long base); #define ELF_ET_DYN_BASE (randomize_et_dyn(0x20000000)) +#define ELF_CORE_EFLAGS (is_elf2_task() ? 2 : 0) + /* * Our registers are always unsigned longs, whether we're a 32 bit * process or 64 bit, on either a 64 bit or 32 bit kernel. @@ -86,6 +88,8 @@ typedef elf_vrregset_t elf_fpxregset_t; #ifdef __powerpc64__ # define SET_PERSONALITY(ex) \ do { \ + if (((ex).e_flags & 0x3) == 2) \ + set_thread_flag(TIF_ELF2ABI); \ if ((ex).e_ident[EI_CLASS] == ELFCLASS32) \ set_thread_flag(TIF_32BIT); \ else \ diff --git a/arch/powerpc/include/asm/exception-64s.h b/arch/powerpc/include/asm/exception-64s.h index cca12f084842..894662a5d4d5 100644 --- a/arch/powerpc/include/asm/exception-64s.h +++ b/arch/powerpc/include/asm/exception-64s.h @@ -198,12 +198,27 @@ END_FTR_SECTION_NESTED(ftr,ftr,943) cmpwi r10,0; \ bne do_kvm_##n +#ifdef CONFIG_KVM_BOOK3S_HV_POSSIBLE +/* + * If hv is possible, interrupts come into to the hv version + * of the kvmppc_interrupt code, which then jumps to the PR handler, + * kvmppc_interrupt_pr, if the guest is a PR guest. + */ +#define kvmppc_interrupt kvmppc_interrupt_hv +#else +#define kvmppc_interrupt kvmppc_interrupt_pr +#endif + #define __KVM_HANDLER(area, h, n) \ do_kvm_##n: \ BEGIN_FTR_SECTION_NESTED(947) \ ld r10,area+EX_CFAR(r13); \ std r10,HSTATE_CFAR(r13); \ END_FTR_SECTION_NESTED(CPU_FTR_CFAR,CPU_FTR_CFAR,947); \ + BEGIN_FTR_SECTION_NESTED(948) \ + ld r10,area+EX_PPR(r13); \ + std r10,HSTATE_PPR(r13); \ + END_FTR_SECTION_NESTED(CPU_FTR_HAS_PPR,CPU_FTR_HAS_PPR,948); \ ld r10,area+EX_R10(r13); \ stw r9,HSTATE_SCRATCH1(r13); \ ld r9,area+EX_R9(r13); \ @@ -217,6 +232,10 @@ do_kvm_##n: \ ld r10,area+EX_R10(r13); \ beq 89f; \ stw r9,HSTATE_SCRATCH1(r13); \ + BEGIN_FTR_SECTION_NESTED(948) \ + ld r9,area+EX_PPR(r13); \ + std r9,HSTATE_PPR(r13); \ + END_FTR_SECTION_NESTED(CPU_FTR_HAS_PPR,CPU_FTR_HAS_PPR,948); \ ld r9,area+EX_R9(r13); \ std r12,HSTATE_SCRATCH0(r13); \ li r12,n; \ @@ -236,7 +255,7 @@ do_kvm_##n: \ #define KVM_HANDLER_SKIP(area, h, n) #endif -#ifdef CONFIG_KVM_BOOK3S_PR +#ifdef CONFIG_KVM_BOOK3S_PR_POSSIBLE #define KVMTEST_PR(n) __KVMTEST(n) #define KVM_HANDLER_PR(area, h, n) __KVM_HANDLER(area, h, n) #define KVM_HANDLER_PR_SKIP(area, h, n) __KVM_HANDLER_SKIP(area, h, n) diff --git a/arch/powerpc/include/asm/fsl_ifc.h b/arch/powerpc/include/asm/fsl_ifc.h index b8a4b9bc50b3..f49ddb1b2273 100644 --- a/arch/powerpc/include/asm/fsl_ifc.h +++ b/arch/powerpc/include/asm/fsl_ifc.h @@ -93,6 +93,7 @@ #define CSOR_NAND_PGS_512 0x00000000 #define CSOR_NAND_PGS_2K 0x00080000 #define CSOR_NAND_PGS_4K 0x00100000 +#define CSOR_NAND_PGS_8K 0x00180000 /* Spare region Size */ #define CSOR_NAND_SPRZ_MASK 0x0000E000 #define CSOR_NAND_SPRZ_SHIFT 13 @@ -102,6 +103,7 @@ #define CSOR_NAND_SPRZ_210 0x00006000 #define CSOR_NAND_SPRZ_218 0x00008000 #define CSOR_NAND_SPRZ_224 0x0000A000 +#define CSOR_NAND_SPRZ_CSOR_EXT 0x0000C000 /* Pages Per Block */ #define CSOR_NAND_PB_MASK 0x00000700 #define CSOR_NAND_PB_SHIFT 8 diff --git a/arch/powerpc/include/asm/hvcall.h b/arch/powerpc/include/asm/hvcall.h index 0c7f2bfcf134..d8b600b3f058 100644 --- a/arch/powerpc/include/asm/hvcall.h +++ b/arch/powerpc/include/asm/hvcall.h @@ -403,6 +403,8 @@ static inline unsigned long cmo_get_page_size(void) extern long pSeries_enable_reloc_on_exc(void); extern long pSeries_disable_reloc_on_exc(void); +extern long pseries_big_endian_exceptions(void); + #else #define pSeries_enable_reloc_on_exc() do {} while (0) diff --git a/arch/powerpc/include/asm/kvm_asm.h b/arch/powerpc/include/asm/kvm_asm.h index 851bac7afa4b..1bd92fd43cfb 100644 --- a/arch/powerpc/include/asm/kvm_asm.h +++ b/arch/powerpc/include/asm/kvm_asm.h @@ -123,6 +123,8 @@ #define BOOK3S_HFLAG_SLB 0x2 #define BOOK3S_HFLAG_PAIRED_SINGLE 0x4 #define BOOK3S_HFLAG_NATIVE_PS 0x8 +#define BOOK3S_HFLAG_MULTI_PGSIZE 0x10 +#define BOOK3S_HFLAG_NEW_TLBIE 0x20 #define RESUME_FLAG_NV (1<<0) /* Reload guest nonvolatile state? */ #define RESUME_FLAG_HOST (1<<1) /* Resume host? */ @@ -136,6 +138,8 @@ #define KVM_GUEST_MODE_NONE 0 #define KVM_GUEST_MODE_GUEST 1 #define KVM_GUEST_MODE_SKIP 2 +#define KVM_GUEST_MODE_GUEST_HV 3 +#define KVM_GUEST_MODE_HOST_HV 4 #define KVM_INST_FETCH_FAILED -1 diff --git a/arch/powerpc/include/asm/kvm_book3s.h b/arch/powerpc/include/asm/kvm_book3s.h index fa19e2f1a874..4a594b76674d 100644 --- a/arch/powerpc/include/asm/kvm_book3s.h +++ b/arch/powerpc/include/asm/kvm_book3s.h @@ -58,16 +58,18 @@ struct hpte_cache { struct hlist_node list_pte_long; struct hlist_node list_vpte; struct hlist_node list_vpte_long; +#ifdef CONFIG_PPC_BOOK3S_64 + struct hlist_node list_vpte_64k; +#endif struct rcu_head rcu_head; u64 host_vpn; u64 pfn; ulong slot; struct kvmppc_pte pte; + int pagesize; }; struct kvmppc_vcpu_book3s { - struct kvm_vcpu vcpu; - struct kvmppc_book3s_shadow_vcpu *shadow_vcpu; struct kvmppc_sid_map sid_map[SID_MAP_NUM]; struct { u64 esid; @@ -99,6 +101,9 @@ struct kvmppc_vcpu_book3s { struct hlist_head hpte_hash_pte_long[HPTEG_HASH_NUM_PTE_LONG]; struct hlist_head hpte_hash_vpte[HPTEG_HASH_NUM_VPTE]; struct hlist_head hpte_hash_vpte_long[HPTEG_HASH_NUM_VPTE_LONG]; +#ifdef CONFIG_PPC_BOOK3S_64 + struct hlist_head hpte_hash_vpte_64k[HPTEG_HASH_NUM_VPTE_64K]; +#endif int hpte_cache_count; spinlock_t mmu_lock; }; @@ -107,8 +112,9 @@ struct kvmppc_vcpu_book3s { #define CONTEXT_GUEST 1 #define CONTEXT_GUEST_END 2 -#define VSID_REAL 0x0fffffffffc00000ULL -#define VSID_BAT 0x0fffffffffb00000ULL +#define VSID_REAL 0x07ffffffffc00000ULL +#define VSID_BAT 0x07ffffffffb00000ULL +#define VSID_64K 0x0800000000000000ULL #define VSID_1T 0x1000000000000000ULL #define VSID_REAL_DR 0x2000000000000000ULL #define VSID_REAL_IR 0x4000000000000000ULL @@ -118,11 +124,12 @@ extern void kvmppc_mmu_pte_flush(struct kvm_vcpu *vcpu, ulong ea, ulong ea_mask) extern void kvmppc_mmu_pte_vflush(struct kvm_vcpu *vcpu, u64 vp, u64 vp_mask); extern void kvmppc_mmu_pte_pflush(struct kvm_vcpu *vcpu, ulong pa_start, ulong pa_end); extern void kvmppc_set_msr(struct kvm_vcpu *vcpu, u64 new_msr); -extern void kvmppc_set_pvr(struct kvm_vcpu *vcpu, u32 pvr); extern void kvmppc_mmu_book3s_64_init(struct kvm_vcpu *vcpu); extern void kvmppc_mmu_book3s_32_init(struct kvm_vcpu *vcpu); extern void kvmppc_mmu_book3s_hv_init(struct kvm_vcpu *vcpu); -extern int kvmppc_mmu_map_page(struct kvm_vcpu *vcpu, struct kvmppc_pte *pte); +extern int kvmppc_mmu_map_page(struct kvm_vcpu *vcpu, struct kvmppc_pte *pte, + bool iswrite); +extern void kvmppc_mmu_unmap_page(struct kvm_vcpu *vcpu, struct kvmppc_pte *pte); extern int kvmppc_mmu_map_segment(struct kvm_vcpu *vcpu, ulong eaddr); extern void kvmppc_mmu_flush_segment(struct kvm_vcpu *vcpu, ulong eaddr, ulong seg_size); extern void kvmppc_mmu_flush_segments(struct kvm_vcpu *vcpu); @@ -134,6 +141,7 @@ extern long kvmppc_hv_find_lock_hpte(struct kvm *kvm, gva_t eaddr, extern void kvmppc_mmu_hpte_cache_map(struct kvm_vcpu *vcpu, struct hpte_cache *pte); extern struct hpte_cache *kvmppc_mmu_hpte_cache_next(struct kvm_vcpu *vcpu); +extern void kvmppc_mmu_hpte_cache_free(struct hpte_cache *pte); extern void kvmppc_mmu_hpte_destroy(struct kvm_vcpu *vcpu); extern int kvmppc_mmu_hpte_init(struct kvm_vcpu *vcpu); extern void kvmppc_mmu_invalidate_pte(struct kvm_vcpu *vcpu, struct hpte_cache *pte); @@ -151,7 +159,8 @@ extern void kvmppc_set_bat(struct kvm_vcpu *vcpu, struct kvmppc_bat *bat, bool upper, u32 val); extern void kvmppc_giveup_ext(struct kvm_vcpu *vcpu, ulong msr); extern int kvmppc_emulate_paired_single(struct kvm_run *run, struct kvm_vcpu *vcpu); -extern pfn_t kvmppc_gfn_to_pfn(struct kvm_vcpu *vcpu, gfn_t gfn); +extern pfn_t kvmppc_gfn_to_pfn(struct kvm_vcpu *vcpu, gfn_t gfn, bool writing, + bool *writable); extern void kvmppc_add_revmap_chain(struct kvm *kvm, struct revmap_entry *rev, unsigned long *rmap, long pte_index, int realmode); extern void kvmppc_invalidate_hpte(struct kvm *kvm, unsigned long *hptep, @@ -172,6 +181,8 @@ extern long kvmppc_do_h_remove(struct kvm *kvm, unsigned long flags, unsigned long *hpret); extern long kvmppc_hv_get_dirty_log(struct kvm *kvm, struct kvm_memory_slot *memslot, unsigned long *map); +extern void kvmppc_update_lpcr(struct kvm *kvm, unsigned long lpcr, + unsigned long mask); extern void kvmppc_entry_trampoline(void); extern void kvmppc_hv_entry_trampoline(void); @@ -184,11 +195,9 @@ extern int kvmppc_h_pr(struct kvm_vcpu *vcpu, unsigned long cmd); static inline struct kvmppc_vcpu_book3s *to_book3s(struct kvm_vcpu *vcpu) { - return container_of(vcpu, struct kvmppc_vcpu_book3s, vcpu); + return vcpu->arch.book3s; } -extern void kvm_return_point(void); - /* Also add subarch specific defines */ #ifdef CONFIG_KVM_BOOK3S_32_HANDLER @@ -198,203 +207,6 @@ extern void kvm_return_point(void); #include <asm/kvm_book3s_64.h> #endif -#ifdef CONFIG_KVM_BOOK3S_PR - -static inline unsigned long kvmppc_interrupt_offset(struct kvm_vcpu *vcpu) -{ - return to_book3s(vcpu)->hior; -} - -static inline void kvmppc_update_int_pending(struct kvm_vcpu *vcpu, - unsigned long pending_now, unsigned long old_pending) -{ - if (pending_now) - vcpu->arch.shared->int_pending = 1; - else if (old_pending) - vcpu->arch.shared->int_pending = 0; -} - -static inline void kvmppc_set_gpr(struct kvm_vcpu *vcpu, int num, ulong val) -{ - if ( num < 14 ) { - struct kvmppc_book3s_shadow_vcpu *svcpu = svcpu_get(vcpu); - svcpu->gpr[num] = val; - svcpu_put(svcpu); - to_book3s(vcpu)->shadow_vcpu->gpr[num] = val; - } else - vcpu->arch.gpr[num] = val; -} - -static inline ulong kvmppc_get_gpr(struct kvm_vcpu *vcpu, int num) -{ - if ( num < 14 ) { - struct kvmppc_book3s_shadow_vcpu *svcpu = svcpu_get(vcpu); - ulong r = svcpu->gpr[num]; - svcpu_put(svcpu); - return r; - } else - return vcpu->arch.gpr[num]; -} - -static inline void kvmppc_set_cr(struct kvm_vcpu *vcpu, u32 val) -{ - struct kvmppc_book3s_shadow_vcpu *svcpu = svcpu_get(vcpu); - svcpu->cr = val; - svcpu_put(svcpu); - to_book3s(vcpu)->shadow_vcpu->cr = val; -} - -static inline u32 kvmppc_get_cr(struct kvm_vcpu *vcpu) -{ - struct kvmppc_book3s_shadow_vcpu *svcpu = svcpu_get(vcpu); - u32 r; - r = svcpu->cr; - svcpu_put(svcpu); - return r; -} - -static inline void kvmppc_set_xer(struct kvm_vcpu *vcpu, u32 val) -{ - struct kvmppc_book3s_shadow_vcpu *svcpu = svcpu_get(vcpu); - svcpu->xer = val; - to_book3s(vcpu)->shadow_vcpu->xer = val; - svcpu_put(svcpu); -} - -static inline u32 kvmppc_get_xer(struct kvm_vcpu *vcpu) -{ - struct kvmppc_book3s_shadow_vcpu *svcpu = svcpu_get(vcpu); - u32 r; - r = svcpu->xer; - svcpu_put(svcpu); - return r; -} - -static inline void kvmppc_set_ctr(struct kvm_vcpu *vcpu, ulong val) -{ - struct kvmppc_book3s_shadow_vcpu *svcpu = svcpu_get(vcpu); - svcpu->ctr = val; - svcpu_put(svcpu); -} - -static inline ulong kvmppc_get_ctr(struct kvm_vcpu *vcpu) -{ - struct kvmppc_book3s_shadow_vcpu *svcpu = svcpu_get(vcpu); - ulong r; - r = svcpu->ctr; - svcpu_put(svcpu); - return r; -} - -static inline void kvmppc_set_lr(struct kvm_vcpu *vcpu, ulong val) -{ - struct kvmppc_book3s_shadow_vcpu *svcpu = svcpu_get(vcpu); - svcpu->lr = val; - svcpu_put(svcpu); -} - -static inline ulong kvmppc_get_lr(struct kvm_vcpu *vcpu) -{ - struct kvmppc_book3s_shadow_vcpu *svcpu = svcpu_get(vcpu); - ulong r; - r = svcpu->lr; - svcpu_put(svcpu); - return r; -} - -static inline void kvmppc_set_pc(struct kvm_vcpu *vcpu, ulong val) -{ - struct kvmppc_book3s_shadow_vcpu *svcpu = svcpu_get(vcpu); - svcpu->pc = val; - svcpu_put(svcpu); -} - -static inline ulong kvmppc_get_pc(struct kvm_vcpu *vcpu) -{ - struct kvmppc_book3s_shadow_vcpu *svcpu = svcpu_get(vcpu); - ulong r; - r = svcpu->pc; - svcpu_put(svcpu); - return r; -} - -static inline u32 kvmppc_get_last_inst(struct kvm_vcpu *vcpu) -{ - ulong pc = kvmppc_get_pc(vcpu); - struct kvmppc_book3s_shadow_vcpu *svcpu = svcpu_get(vcpu); - u32 r; - - /* Load the instruction manually if it failed to do so in the - * exit path */ - if (svcpu->last_inst == KVM_INST_FETCH_FAILED) - kvmppc_ld(vcpu, &pc, sizeof(u32), &svcpu->last_inst, false); - - r = svcpu->last_inst; - svcpu_put(svcpu); - return r; -} - -/* - * Like kvmppc_get_last_inst(), but for fetching a sc instruction. - * Because the sc instruction sets SRR0 to point to the following - * instruction, we have to fetch from pc - 4. - */ -static inline u32 kvmppc_get_last_sc(struct kvm_vcpu *vcpu) -{ - ulong pc = kvmppc_get_pc(vcpu) - 4; - struct kvmppc_book3s_shadow_vcpu *svcpu = svcpu_get(vcpu); - u32 r; - - /* Load the instruction manually if it failed to do so in the - * exit path */ - if (svcpu->last_inst == KVM_INST_FETCH_FAILED) - kvmppc_ld(vcpu, &pc, sizeof(u32), &svcpu->last_inst, false); - - r = svcpu->last_inst; - svcpu_put(svcpu); - return r; -} - -static inline ulong kvmppc_get_fault_dar(struct kvm_vcpu *vcpu) -{ - struct kvmppc_book3s_shadow_vcpu *svcpu = svcpu_get(vcpu); - ulong r; - r = svcpu->fault_dar; - svcpu_put(svcpu); - return r; -} - -static inline bool kvmppc_critical_section(struct kvm_vcpu *vcpu) -{ - ulong crit_raw = vcpu->arch.shared->critical; - ulong crit_r1 = kvmppc_get_gpr(vcpu, 1); - bool crit; - - /* Truncate crit indicators in 32 bit mode */ - if (!(vcpu->arch.shared->msr & MSR_SF)) { - crit_raw &= 0xffffffff; - crit_r1 &= 0xffffffff; - } - - /* Critical section when crit == r1 */ - crit = (crit_raw == crit_r1); - /* ... and we're in supervisor mode */ - crit = crit && !(vcpu->arch.shared->msr & MSR_PR); - - return crit; -} -#else /* CONFIG_KVM_BOOK3S_PR */ - -static inline unsigned long kvmppc_interrupt_offset(struct kvm_vcpu *vcpu) -{ - return 0; -} - -static inline void kvmppc_update_int_pending(struct kvm_vcpu *vcpu, - unsigned long pending_now, unsigned long old_pending) -{ -} - static inline void kvmppc_set_gpr(struct kvm_vcpu *vcpu, int num, ulong val) { vcpu->arch.gpr[num] = val; @@ -489,12 +301,6 @@ static inline ulong kvmppc_get_fault_dar(struct kvm_vcpu *vcpu) return vcpu->arch.fault_dar; } -static inline bool kvmppc_critical_section(struct kvm_vcpu *vcpu) -{ - return false; -} -#endif - /* Magic register values loaded into r3 and r4 before the 'sc' assembly * instruction for the OSI hypercalls */ #define OSI_SC_MAGIC_R3 0x113724FA diff --git a/arch/powerpc/include/asm/kvm_book3s_32.h b/arch/powerpc/include/asm/kvm_book3s_32.h index ce0ef6ce8f86..c720e0b3238d 100644 --- a/arch/powerpc/include/asm/kvm_book3s_32.h +++ b/arch/powerpc/include/asm/kvm_book3s_32.h @@ -22,7 +22,7 @@ static inline struct kvmppc_book3s_shadow_vcpu *svcpu_get(struct kvm_vcpu *vcpu) { - return to_book3s(vcpu)->shadow_vcpu; + return vcpu->arch.shadow_vcpu; } static inline void svcpu_put(struct kvmppc_book3s_shadow_vcpu *svcpu) diff --git a/arch/powerpc/include/asm/kvm_book3s_64.h b/arch/powerpc/include/asm/kvm_book3s_64.h index 86d638a3b359..bf0fa8b0a883 100644 --- a/arch/powerpc/include/asm/kvm_book3s_64.h +++ b/arch/powerpc/include/asm/kvm_book3s_64.h @@ -20,7 +20,7 @@ #ifndef __ASM_KVM_BOOK3S_64_H__ #define __ASM_KVM_BOOK3S_64_H__ -#ifdef CONFIG_KVM_BOOK3S_PR +#ifdef CONFIG_KVM_BOOK3S_PR_POSSIBLE static inline struct kvmppc_book3s_shadow_vcpu *svcpu_get(struct kvm_vcpu *vcpu) { preempt_disable(); @@ -35,7 +35,7 @@ static inline void svcpu_put(struct kvmppc_book3s_shadow_vcpu *svcpu) #define SPAPR_TCE_SHIFT 12 -#ifdef CONFIG_KVM_BOOK3S_64_HV +#ifdef CONFIG_KVM_BOOK3S_HV_POSSIBLE #define KVM_DEFAULT_HPT_ORDER 24 /* 16MB HPT by default */ extern unsigned long kvm_rma_pages; #endif @@ -278,7 +278,7 @@ static inline int is_vrma_hpte(unsigned long hpte_v) (HPTE_V_1TB_SEG | (VRMA_VSID << (40 - 16))); } -#ifdef CONFIG_KVM_BOOK3S_64_HV +#ifdef CONFIG_KVM_BOOK3S_HV_POSSIBLE /* * Note modification of an HPTE; set the HPTE modified bit * if anyone is interested. @@ -289,6 +289,6 @@ static inline void note_hpte_modification(struct kvm *kvm, if (atomic_read(&kvm->arch.hpte_mod_interest)) rev->guest_rpte |= HPTE_GR_MODIFIED; } -#endif /* CONFIG_KVM_BOOK3S_64_HV */ +#endif /* CONFIG_KVM_BOOK3S_HV_POSSIBLE */ #endif /* __ASM_KVM_BOOK3S_64_H__ */ diff --git a/arch/powerpc/include/asm/kvm_book3s_asm.h b/arch/powerpc/include/asm/kvm_book3s_asm.h index 9039d3c97eec..0bd9348a4db9 100644 --- a/arch/powerpc/include/asm/kvm_book3s_asm.h +++ b/arch/powerpc/include/asm/kvm_book3s_asm.h @@ -83,7 +83,7 @@ struct kvmppc_host_state { u8 restore_hid5; u8 napping; -#ifdef CONFIG_KVM_BOOK3S_64_HV +#ifdef CONFIG_KVM_BOOK3S_HV_POSSIBLE u8 hwthread_req; u8 hwthread_state; u8 host_ipi; @@ -101,6 +101,7 @@ struct kvmppc_host_state { #endif #ifdef CONFIG_PPC_BOOK3S_64 u64 cfar; + u64 ppr; #endif }; @@ -108,14 +109,14 @@ struct kvmppc_book3s_shadow_vcpu { ulong gpr[14]; u32 cr; u32 xer; - - u32 fault_dsisr; - u32 last_inst; ulong ctr; ulong lr; ulong pc; + ulong shadow_srr1; ulong fault_dar; + u32 fault_dsisr; + u32 last_inst; #ifdef CONFIG_PPC_BOOK3S_32 u32 sr[16]; /* Guest SRs */ diff --git a/arch/powerpc/include/asm/kvm_booke.h b/arch/powerpc/include/asm/kvm_booke.h index d3c1eb34c986..dd8f61510dfd 100644 --- a/arch/powerpc/include/asm/kvm_booke.h +++ b/arch/powerpc/include/asm/kvm_booke.h @@ -26,7 +26,12 @@ /* LPIDs we support with this build -- runtime limit may be lower */ #define KVMPPC_NR_LPIDS 64 -#define KVMPPC_INST_EHPRIV 0x7c00021c +#define KVMPPC_INST_EHPRIV 0x7c00021c +#define EHPRIV_OC_SHIFT 11 +/* "ehpriv 1" : ehpriv with OC = 1 is used for debug emulation */ +#define EHPRIV_OC_DEBUG 1 +#define KVMPPC_INST_EHPRIV_DEBUG (KVMPPC_INST_EHPRIV | \ + (EHPRIV_OC_DEBUG << EHPRIV_OC_SHIFT)) static inline void kvmppc_set_gpr(struct kvm_vcpu *vcpu, int num, ulong val) { diff --git a/arch/powerpc/include/asm/kvm_host.h b/arch/powerpc/include/asm/kvm_host.h index 33283532e9d8..237d1d25b448 100644 --- a/arch/powerpc/include/asm/kvm_host.h +++ b/arch/powerpc/include/asm/kvm_host.h @@ -63,20 +63,17 @@ extern void kvm_set_spte_hva(struct kvm *kvm, unsigned long hva, pte_t pte); #endif -/* We don't currently support large pages. */ -#define KVM_HPAGE_GFN_SHIFT(x) 0 -#define KVM_NR_PAGE_SIZES 1 -#define KVM_PAGES_PER_HPAGE(x) (1UL<<31) - #define HPTEG_CACHE_NUM (1 << 15) #define HPTEG_HASH_BITS_PTE 13 #define HPTEG_HASH_BITS_PTE_LONG 12 #define HPTEG_HASH_BITS_VPTE 13 #define HPTEG_HASH_BITS_VPTE_LONG 5 +#define HPTEG_HASH_BITS_VPTE_64K 11 #define HPTEG_HASH_NUM_PTE (1 << HPTEG_HASH_BITS_PTE) #define HPTEG_HASH_NUM_PTE_LONG (1 << HPTEG_HASH_BITS_PTE_LONG) #define HPTEG_HASH_NUM_VPTE (1 << HPTEG_HASH_BITS_VPTE) #define HPTEG_HASH_NUM_VPTE_LONG (1 << HPTEG_HASH_BITS_VPTE_LONG) +#define HPTEG_HASH_NUM_VPTE_64K (1 << HPTEG_HASH_BITS_VPTE_64K) /* Physical Address Mask - allowed range of real mode RAM access */ #define KVM_PAM 0x0fffffffffffffffULL @@ -89,6 +86,9 @@ struct lppaca; struct slb_shadow; struct dtl_entry; +struct kvmppc_vcpu_book3s; +struct kvmppc_book3s_shadow_vcpu; + struct kvm_vm_stat { u32 remote_tlb_flush; }; @@ -224,15 +224,15 @@ struct revmap_entry { #define KVMPPC_GOT_PAGE 0x80 struct kvm_arch_memory_slot { -#ifdef CONFIG_KVM_BOOK3S_64_HV +#ifdef CONFIG_KVM_BOOK3S_HV_POSSIBLE unsigned long *rmap; unsigned long *slot_phys; -#endif /* CONFIG_KVM_BOOK3S_64_HV */ +#endif /* CONFIG_KVM_BOOK3S_HV_POSSIBLE */ }; struct kvm_arch { unsigned int lpid; -#ifdef CONFIG_KVM_BOOK3S_64_HV +#ifdef CONFIG_KVM_BOOK3S_HV_POSSIBLE unsigned long hpt_virt; struct revmap_entry *revmap; unsigned int host_lpid; @@ -256,7 +256,10 @@ struct kvm_arch { cpumask_t need_tlb_flush; struct kvmppc_vcore *vcores[KVM_MAX_VCORES]; int hpt_cma_alloc; -#endif /* CONFIG_KVM_BOOK3S_64_HV */ +#endif /* CONFIG_KVM_BOOK3S_HV_POSSIBLE */ +#ifdef CONFIG_KVM_BOOK3S_PR_POSSIBLE + struct mutex hpt_mutex; +#endif #ifdef CONFIG_PPC_BOOK3S_64 struct list_head spapr_tce_tables; struct list_head rtas_tokens; @@ -267,6 +270,7 @@ struct kvm_arch { #ifdef CONFIG_KVM_XICS struct kvmppc_xics *xics; #endif + struct kvmppc_ops *kvm_ops; }; /* @@ -294,6 +298,10 @@ struct kvmppc_vcore { u64 stolen_tb; u64 preempt_tb; struct kvm_vcpu *runner; + u64 tb_offset; /* guest timebase - host timebase */ + ulong lpcr; + u32 arch_compat; + ulong pcr; }; #define VCORE_ENTRY_COUNT(vc) ((vc)->entry_exit_count & 0xff) @@ -328,6 +336,7 @@ struct kvmppc_pte { bool may_read : 1; bool may_write : 1; bool may_execute : 1; + u8 page_size; /* MMU_PAGE_xxx */ }; struct kvmppc_mmu { @@ -340,7 +349,8 @@ struct kvmppc_mmu { /* book3s */ void (*mtsrin)(struct kvm_vcpu *vcpu, u32 srnum, ulong value); u32 (*mfsrin)(struct kvm_vcpu *vcpu, u32 srnum); - int (*xlate)(struct kvm_vcpu *vcpu, gva_t eaddr, struct kvmppc_pte *pte, bool data); + int (*xlate)(struct kvm_vcpu *vcpu, gva_t eaddr, + struct kvmppc_pte *pte, bool data, bool iswrite); void (*reset_msr)(struct kvm_vcpu *vcpu); void (*tlbie)(struct kvm_vcpu *vcpu, ulong addr, bool large); int (*esid_to_vsid)(struct kvm_vcpu *vcpu, ulong esid, u64 *vsid); @@ -360,6 +370,7 @@ struct kvmppc_slb { bool large : 1; /* PTEs are 16MB */ bool tb : 1; /* 1TB segment */ bool class : 1; + u8 base_page_size; /* MMU_PAGE_xxx */ }; # ifdef CONFIG_PPC_FSL_BOOK3E @@ -377,17 +388,6 @@ struct kvmppc_slb { #define KVMPPC_EPR_USER 1 /* exit to userspace to fill EPR */ #define KVMPPC_EPR_KERNEL 2 /* in-kernel irqchip */ -struct kvmppc_booke_debug_reg { - u32 dbcr0; - u32 dbcr1; - u32 dbcr2; -#ifdef CONFIG_KVM_E500MC - u32 dbcr4; -#endif - u64 iac[KVMPPC_BOOKE_MAX_IAC]; - u64 dac[KVMPPC_BOOKE_MAX_DAC]; -}; - #define KVMPPC_IRQ_DEFAULT 0 #define KVMPPC_IRQ_MPIC 1 #define KVMPPC_IRQ_XICS 2 @@ -402,6 +402,10 @@ struct kvm_vcpu_arch { int slb_max; /* 1 + index of last valid entry in slb[] */ int slb_nr; /* total number of entries in SLB */ struct kvmppc_mmu mmu; + struct kvmppc_vcpu_book3s *book3s; +#endif +#ifdef CONFIG_PPC_BOOK3S_32 + struct kvmppc_book3s_shadow_vcpu *shadow_vcpu; #endif ulong gpr[32]; @@ -463,6 +467,8 @@ struct kvm_vcpu_arch { u32 ctrl; ulong dabr; ulong cfar; + ulong ppr; + ulong shadow_srr1; #endif u32 vrsave; /* also USPRG0 */ u32 mmucr; @@ -498,6 +504,8 @@ struct kvm_vcpu_arch { u64 mmcr[3]; u32 pmc[8]; + u64 siar; + u64 sdar; #ifdef CONFIG_KVM_EXIT_TIMING struct mutex exit_timing_lock; @@ -531,7 +539,10 @@ struct kvm_vcpu_arch { u32 eptcfg; u32 epr; u32 crit_save; - struct kvmppc_booke_debug_reg dbg_reg; + /* guest debug registers*/ + struct debug_reg dbg_reg; + /* hardware visible debug registers when in guest state */ + struct debug_reg shadow_dbg_reg; #endif gpa_t paddr_accessed; gva_t vaddr_accessed; @@ -582,7 +593,7 @@ struct kvm_vcpu_arch { struct kvmppc_icp *icp; /* XICS presentation controller */ #endif -#ifdef CONFIG_KVM_BOOK3S_64_HV +#ifdef CONFIG_KVM_BOOK3S_HV_POSSIBLE struct kvm_vcpu_arch_shared shregs; unsigned long pgfault_addr; diff --git a/arch/powerpc/include/asm/kvm_ppc.h b/arch/powerpc/include/asm/kvm_ppc.h index b15554a26c20..c8317fbf92c4 100644 --- a/arch/powerpc/include/asm/kvm_ppc.h +++ b/arch/powerpc/include/asm/kvm_ppc.h @@ -106,13 +106,6 @@ extern void kvmppc_core_queue_external(struct kvm_vcpu *vcpu, struct kvm_interrupt *irq); extern void kvmppc_core_dequeue_external(struct kvm_vcpu *vcpu); extern void kvmppc_core_flush_tlb(struct kvm_vcpu *vcpu); - -extern int kvmppc_core_emulate_op(struct kvm_run *run, struct kvm_vcpu *vcpu, - unsigned int op, int *advance); -extern int kvmppc_core_emulate_mtspr(struct kvm_vcpu *vcpu, int sprn, - ulong val); -extern int kvmppc_core_emulate_mfspr(struct kvm_vcpu *vcpu, int sprn, - ulong *val); extern int kvmppc_core_check_requests(struct kvm_vcpu *vcpu); extern int kvmppc_booke_init(void); @@ -135,17 +128,17 @@ extern long kvm_vm_ioctl_create_spapr_tce(struct kvm *kvm, struct kvm_create_spapr_tce *args); extern long kvmppc_h_put_tce(struct kvm_vcpu *vcpu, unsigned long liobn, unsigned long ioba, unsigned long tce); -extern long kvm_vm_ioctl_allocate_rma(struct kvm *kvm, - struct kvm_allocate_rma *rma); extern struct kvm_rma_info *kvm_alloc_rma(void); extern void kvm_release_rma(struct kvm_rma_info *ri); extern struct page *kvm_alloc_hpt(unsigned long nr_pages); extern void kvm_release_hpt(struct page *page, unsigned long nr_pages); extern int kvmppc_core_init_vm(struct kvm *kvm); extern void kvmppc_core_destroy_vm(struct kvm *kvm); -extern void kvmppc_core_free_memslot(struct kvm_memory_slot *free, +extern void kvmppc_core_free_memslot(struct kvm *kvm, + struct kvm_memory_slot *free, struct kvm_memory_slot *dont); -extern int kvmppc_core_create_memslot(struct kvm_memory_slot *slot, +extern int kvmppc_core_create_memslot(struct kvm *kvm, + struct kvm_memory_slot *slot, unsigned long npages); extern int kvmppc_core_prepare_memory_region(struct kvm *kvm, struct kvm_memory_slot *memslot, @@ -177,6 +170,72 @@ extern int kvmppc_xics_get_xive(struct kvm *kvm, u32 irq, u32 *server, extern int kvmppc_xics_int_on(struct kvm *kvm, u32 irq); extern int kvmppc_xics_int_off(struct kvm *kvm, u32 irq); +union kvmppc_one_reg { + u32 wval; + u64 dval; + vector128 vval; + u64 vsxval[2]; + struct { + u64 addr; + u64 length; + } vpaval; +}; + +struct kvmppc_ops { + struct module *owner; + int (*get_sregs)(struct kvm_vcpu *vcpu, struct kvm_sregs *sregs); + int (*set_sregs)(struct kvm_vcpu *vcpu, struct kvm_sregs *sregs); + int (*get_one_reg)(struct kvm_vcpu *vcpu, u64 id, + union kvmppc_one_reg *val); + int (*set_one_reg)(struct kvm_vcpu *vcpu, u64 id, + union kvmppc_one_reg *val); + void (*vcpu_load)(struct kvm_vcpu *vcpu, int cpu); + void (*vcpu_put)(struct kvm_vcpu *vcpu); + void (*set_msr)(struct kvm_vcpu *vcpu, u64 msr); + int (*vcpu_run)(struct kvm_run *run, struct kvm_vcpu *vcpu); + struct kvm_vcpu *(*vcpu_create)(struct kvm *kvm, unsigned int id); + void (*vcpu_free)(struct kvm_vcpu *vcpu); + int (*check_requests)(struct kvm_vcpu *vcpu); + int (*get_dirty_log)(struct kvm *kvm, struct kvm_dirty_log *log); + void (*flush_memslot)(struct kvm *kvm, struct kvm_memory_slot *memslot); + int (*prepare_memory_region)(struct kvm *kvm, + struct kvm_memory_slot *memslot, + struct kvm_userspace_memory_region *mem); + void (*commit_memory_region)(struct kvm *kvm, + struct kvm_userspace_memory_region *mem, + const struct kvm_memory_slot *old); + int (*unmap_hva)(struct kvm *kvm, unsigned long hva); + int (*unmap_hva_range)(struct kvm *kvm, unsigned long start, + unsigned long end); + int (*age_hva)(struct kvm *kvm, unsigned long hva); + int (*test_age_hva)(struct kvm *kvm, unsigned long hva); + void (*set_spte_hva)(struct kvm *kvm, unsigned long hva, pte_t pte); + void (*mmu_destroy)(struct kvm_vcpu *vcpu); + void (*free_memslot)(struct kvm_memory_slot *free, + struct kvm_memory_slot *dont); + int (*create_memslot)(struct kvm_memory_slot *slot, + unsigned long npages); + int (*init_vm)(struct kvm *kvm); + void (*destroy_vm)(struct kvm *kvm); + int (*get_smmu_info)(struct kvm *kvm, struct kvm_ppc_smmu_info *info); + int (*emulate_op)(struct kvm_run *run, struct kvm_vcpu *vcpu, + unsigned int inst, int *advance); + int (*emulate_mtspr)(struct kvm_vcpu *vcpu, int sprn, ulong spr_val); + int (*emulate_mfspr)(struct kvm_vcpu *vcpu, int sprn, ulong *spr_val); + void (*fast_vcpu_kick)(struct kvm_vcpu *vcpu); + long (*arch_vm_ioctl)(struct file *filp, unsigned int ioctl, + unsigned long arg); + +}; + +extern struct kvmppc_ops *kvmppc_hv_ops; +extern struct kvmppc_ops *kvmppc_pr_ops; + +static inline bool is_kvmppc_hv_enabled(struct kvm *kvm) +{ + return kvm->arch.kvm_ops == kvmppc_hv_ops; +} + /* * Cuts out inst bits with ordering according to spec. * That means the leftmost bit is zero. All given bits are included. @@ -210,17 +269,6 @@ static inline u32 kvmppc_set_field(u64 inst, int msb, int lsb, int value) return r; } -union kvmppc_one_reg { - u32 wval; - u64 dval; - vector128 vval; - u64 vsxval[2]; - struct { - u64 addr; - u64 length; - } vpaval; -}; - #define one_reg_size(id) \ (1ul << (((id) & KVM_REG_SIZE_MASK) >> KVM_REG_SIZE_SHIFT)) @@ -245,10 +293,10 @@ union kvmppc_one_reg { __v; \ }) -void kvmppc_core_get_sregs(struct kvm_vcpu *vcpu, struct kvm_sregs *sregs); +int kvmppc_core_get_sregs(struct kvm_vcpu *vcpu, struct kvm_sregs *sregs); int kvmppc_core_set_sregs(struct kvm_vcpu *vcpu, struct kvm_sregs *sregs); -void kvmppc_get_sregs_ivor(struct kvm_vcpu *vcpu, struct kvm_sregs *sregs); +int kvmppc_get_sregs_ivor(struct kvm_vcpu *vcpu, struct kvm_sregs *sregs); int kvmppc_set_sregs_ivor(struct kvm_vcpu *vcpu, struct kvm_sregs *sregs); int kvm_vcpu_ioctl_get_one_reg(struct kvm_vcpu *vcpu, struct kvm_one_reg *reg); @@ -260,7 +308,7 @@ void kvmppc_set_pid(struct kvm_vcpu *vcpu, u32 pid); struct openpic; -#ifdef CONFIG_KVM_BOOK3S_64_HV +#ifdef CONFIG_KVM_BOOK3S_HV_POSSIBLE extern void kvm_cma_reserve(void) __init; static inline void kvmppc_set_xics_phys(int cpu, unsigned long addr) { @@ -269,10 +317,10 @@ static inline void kvmppc_set_xics_phys(int cpu, unsigned long addr) static inline u32 kvmppc_get_xics_latch(void) { - u32 xirr = get_paca()->kvm_hstate.saved_xirr; + u32 xirr; + xirr = get_paca()->kvm_hstate.saved_xirr; get_paca()->kvm_hstate.saved_xirr = 0; - return xirr; } @@ -281,7 +329,10 @@ static inline void kvmppc_set_host_ipi(int cpu, u8 host_ipi) paca[cpu].kvm_hstate.host_ipi = host_ipi; } -extern void kvmppc_fast_vcpu_kick(struct kvm_vcpu *vcpu); +static inline void kvmppc_fast_vcpu_kick(struct kvm_vcpu *vcpu) +{ + vcpu->kvm->arch.kvm_ops->fast_vcpu_kick(vcpu); +} #else static inline void __init kvm_cma_reserve(void) diff --git a/arch/powerpc/include/asm/paca.h b/arch/powerpc/include/asm/paca.h index a5954cebbc55..b6ea9e068c13 100644 --- a/arch/powerpc/include/asm/paca.h +++ b/arch/powerpc/include/asm/paca.h @@ -166,7 +166,7 @@ struct paca_struct { struct dtl_entry *dtl_curr; /* pointer corresponding to dtl_ridx */ #ifdef CONFIG_KVM_BOOK3S_HANDLER -#ifdef CONFIG_KVM_BOOK3S_PR +#ifdef CONFIG_KVM_BOOK3S_PR_POSSIBLE /* We use this to store guest state in */ struct kvmppc_book3s_shadow_vcpu shadow_vcpu; #endif diff --git a/arch/powerpc/include/asm/pgalloc-64.h b/arch/powerpc/include/asm/pgalloc-64.h index f65e27b09bd3..16cb92d215d2 100644 --- a/arch/powerpc/include/asm/pgalloc-64.h +++ b/arch/powerpc/include/asm/pgalloc-64.h @@ -91,7 +91,10 @@ static inline pgtable_t pte_alloc_one(struct mm_struct *mm, if (!pte) return NULL; page = virt_to_page(pte); - pgtable_page_ctor(page); + if (!pgtable_page_ctor(page)) { + __free_page(page); + return NULL; + } return page; } diff --git a/arch/powerpc/include/asm/plpar_wrappers.h b/arch/powerpc/include/asm/plpar_wrappers.h index a63b045e707c..12c32c5f533d 100644 --- a/arch/powerpc/include/asm/plpar_wrappers.h +++ b/arch/powerpc/include/asm/plpar_wrappers.h @@ -287,6 +287,32 @@ static inline long disable_reloc_on_exceptions(void) { return plpar_set_mode(0, 3, 0, 0); } +/* + * Take exceptions in big endian mode on this partition + * + * Note: this call has a partition wide scope and can take a while to complete. + * If it returns H_LONG_BUSY_* it should be retried periodically until it + * returns H_SUCCESS. + */ +static inline long enable_big_endian_exceptions(void) +{ + /* mflags = 0: big endian exceptions */ + return plpar_set_mode(0, 4, 0, 0); +} + +/* + * Take exceptions in little endian mode on this partition + * + * Note: this call has a partition wide scope and can take a while to complete. + * If it returns H_LONG_BUSY_* it should be retried periodically until it + * returns H_SUCCESS. + */ +static inline long enable_little_endian_exceptions(void) +{ + /* mflags = 1: little endian exceptions */ + return plpar_set_mode(1, 4, 0, 0); +} + static inline long plapr_set_ciabr(unsigned long ciabr) { return plpar_set_mode(0, 1, ciabr, 0); diff --git a/arch/powerpc/include/asm/processor.h b/arch/powerpc/include/asm/processor.h index 7794b2b04eb2..fc14a38c7ccf 100644 --- a/arch/powerpc/include/asm/processor.h +++ b/arch/powerpc/include/asm/processor.h @@ -208,6 +208,7 @@ struct debug_reg { struct thread_struct { unsigned long ksp; /* Kernel stack pointer */ + #ifdef CONFIG_PPC64 unsigned long ksp_vsid; #endif @@ -221,6 +222,7 @@ struct thread_struct { void *pgdir; /* root of page-table tree */ unsigned long ksp_limit; /* if ksp <= ksp_limit stack overflow */ #endif + /* Debug Registers */ struct debug_reg debug; struct thread_fp_state fp_state; struct thread_fp_state *fp_save_area; diff --git a/arch/powerpc/include/asm/pte-book3e.h b/arch/powerpc/include/asm/pte-book3e.h index 0156702ba24e..576ad88104cb 100644 --- a/arch/powerpc/include/asm/pte-book3e.h +++ b/arch/powerpc/include/asm/pte-book3e.h @@ -40,7 +40,7 @@ #define _PAGE_U1 0x010000 #define _PAGE_U0 0x020000 #define _PAGE_ACCESSED 0x040000 -#define _PAGE_LENDIAN 0x080000 +#define _PAGE_ENDIAN 0x080000 #define _PAGE_GUARDED 0x100000 #define _PAGE_COHERENT 0x200000 /* M: enforce memory coherence */ #define _PAGE_NO_CACHE 0x400000 /* I: cache inhibit */ diff --git a/arch/powerpc/include/asm/reg.h b/arch/powerpc/include/asm/reg.h index 126f6e98f84d..5c45787d551e 100644 --- a/arch/powerpc/include/asm/reg.h +++ b/arch/powerpc/include/asm/reg.h @@ -248,6 +248,7 @@ #define SPRN_TBRU 0x10D /* Time Base Read Upper Register (user, R/O) */ #define SPRN_TBWL 0x11C /* Time Base Lower Register (super, R/W) */ #define SPRN_TBWU 0x11D /* Time Base Upper Register (super, R/W) */ +#define SPRN_TBU40 0x11E /* Timebase upper 40 bits (hyper, R/W) */ #define SPRN_SPURR 0x134 /* Scaled PURR */ #define SPRN_HSPRG0 0x130 /* Hypervisor Scratch 0 */ #define SPRN_HSPRG1 0x131 /* Hypervisor Scratch 1 */ @@ -288,6 +289,7 @@ #define LPCR_ISL (1ul << (63-2)) #define LPCR_VC_SH (63-2) #define LPCR_DPFD_SH (63-11) +#define LPCR_DPFD (7ul << LPCR_DPFD_SH) #define LPCR_VRMASD (0x1ful << (63-16)) #define LPCR_VRMA_L (1ul << (63-12)) #define LPCR_VRMA_LP0 (1ul << (63-15)) @@ -304,6 +306,7 @@ #define LPCR_PECE2 0x00001000 /* machine check etc can cause exit */ #define LPCR_MER 0x00000800 /* Mediated External Exception */ #define LPCR_MER_SH 11 +#define LPCR_TC 0x00000200 /* Translation control */ #define LPCR_LPES 0x0000000c #define LPCR_LPES0 0x00000008 /* LPAR Env selector 0 */ #define LPCR_LPES1 0x00000004 /* LPAR Env selector 1 */ @@ -316,6 +319,10 @@ #define LPID_RSVD 0x3ff /* Reserved LPID for partn switching */ #define SPRN_HMER 0x150 /* Hardware m? error recovery */ #define SPRN_HMEER 0x151 /* Hardware m? enable error recovery */ +#define SPRN_PCR 0x152 /* Processor compatibility register */ +#define PCR_VEC_DIS (1ul << (63-0)) /* Vec. disable (bit NA since POWER8) */ +#define PCR_VSX_DIS (1ul << (63-1)) /* VSX disable (bit NA since POWER8) */ +#define PCR_ARCH_205 0x2 /* Architecture 2.05 */ #define SPRN_HEIR 0x153 /* Hypervisor Emulated Instruction Register */ #define SPRN_TLBINDEXR 0x154 /* P7 TLB control register */ #define SPRN_TLBVPNR 0x155 /* P7 TLB control register */ @@ -425,6 +432,7 @@ #define HID4_RMLS2_SH (63 - 2) /* Real mode limit bottom 2 bits */ #define HID4_LPID5_SH (63 - 6) /* partition ID bottom 4 bits */ #define HID4_RMOR_SH (63 - 22) /* real mode offset (16 bits) */ +#define HID4_RMOR (0xFFFFul << HID4_RMOR_SH) #define HID4_LPES1 (1 << (63-57)) /* LPAR env. sel. bit 1 */ #define HID4_RMLS0_SH (63 - 58) /* Real mode limit top bit */ #define HID4_LPID1_SH 0 /* partition ID top 2 bits */ @@ -1107,6 +1115,13 @@ #define PVR_BE 0x0070 #define PVR_PA6T 0x0090 +/* "Logical" PVR values defined in PAPR, representing architecture levels */ +#define PVR_ARCH_204 0x0f000001 +#define PVR_ARCH_205 0x0f000002 +#define PVR_ARCH_206 0x0f000003 +#define PVR_ARCH_206p 0x0f100003 +#define PVR_ARCH_207 0x0f000004 + /* Macros for setting and retrieving special purpose registers */ #ifndef __ASSEMBLY__ #define mfmsr() ({unsigned long rval; \ diff --git a/arch/powerpc/include/asm/smp.h b/arch/powerpc/include/asm/smp.h index 98da78e0c2c0..084e0807db98 100644 --- a/arch/powerpc/include/asm/smp.h +++ b/arch/powerpc/include/asm/smp.h @@ -33,6 +33,7 @@ extern int boot_cpuid; extern int spinning_secondaries; extern void cpu_die(void); +extern int cpu_to_chip_id(int cpu); #ifdef CONFIG_SMP @@ -112,7 +113,6 @@ static inline struct cpumask *cpu_core_mask(int cpu) } extern int cpu_to_core_id(int cpu); -extern int cpu_to_chip_id(int cpu); /* Since OpenPIC has only 4 IPIs, we use slightly different message numbers. * diff --git a/arch/powerpc/include/asm/thread_info.h b/arch/powerpc/include/asm/thread_info.h index ba7b1973866e..9854c564ac52 100644 --- a/arch/powerpc/include/asm/thread_info.h +++ b/arch/powerpc/include/asm/thread_info.h @@ -82,8 +82,6 @@ static inline struct thread_info *current_thread_info(void) #endif /* __ASSEMBLY__ */ -#define PREEMPT_ACTIVE 0x10000000 - /* * thread information flag bit numbers */ @@ -107,6 +105,9 @@ static inline struct thread_info *current_thread_info(void) #define TIF_EMULATE_STACK_STORE 16 /* Is an instruction emulation for stack store? */ #define TIF_MEMDIE 17 /* is terminating due to OOM killer */ +#if defined(CONFIG_PPC64) +#define TIF_ELF2ABI 18 /* function descriptors must die! */ +#endif /* as above, but as bit values */ #define _TIF_SYSCALL_TRACE (1<<TIF_SYSCALL_TRACE) @@ -185,6 +186,12 @@ static inline bool test_thread_local_flags(unsigned int flags) #define is_32bit_task() (1) #endif +#if defined(CONFIG_PPC64) +#define is_elf2_task() (test_thread_flag(TIF_ELF2ABI)) +#else +#define is_elf2_task() (0) +#endif + #endif /* !__ASSEMBLY__ */ #endif /* __KERNEL__ */ diff --git a/arch/powerpc/include/uapi/asm/kvm.h b/arch/powerpc/include/uapi/asm/kvm.h index 0fb1a6e9ff90..6836ec79a830 100644 --- a/arch/powerpc/include/uapi/asm/kvm.h +++ b/arch/powerpc/include/uapi/asm/kvm.h @@ -27,6 +27,7 @@ #define __KVM_HAVE_PPC_SMT #define __KVM_HAVE_IRQCHIP #define __KVM_HAVE_IRQ_LINE +#define __KVM_HAVE_GUEST_DEBUG struct kvm_regs { __u64 pc; @@ -269,7 +270,24 @@ struct kvm_fpu { __u64 fpr[32]; }; +/* + * Defines for h/w breakpoint, watchpoint (read, write or both) and + * software breakpoint. + * These are used as "type" in KVM_SET_GUEST_DEBUG ioctl and "status" + * for KVM_DEBUG_EXIT. + */ +#define KVMPPC_DEBUG_NONE 0x0 +#define KVMPPC_DEBUG_BREAKPOINT (1UL << 1) +#define KVMPPC_DEBUG_WATCH_WRITE (1UL << 2) +#define KVMPPC_DEBUG_WATCH_READ (1UL << 3) struct kvm_debug_exit_arch { + __u64 address; + /* + * exiting to userspace because of h/w breakpoint, watchpoint + * (read, write or both) and software breakpoint. + */ + __u32 status; + __u32 reserved; }; /* for KVM_SET_GUEST_DEBUG */ @@ -281,10 +299,6 @@ struct kvm_guest_debug_arch { * Type denotes h/w breakpoint, read watchpoint, write * watchpoint or watchpoint (both read and write). */ -#define KVMPPC_DEBUG_NONE 0x0 -#define KVMPPC_DEBUG_BREAKPOINT (1UL << 1) -#define KVMPPC_DEBUG_WATCH_WRITE (1UL << 2) -#define KVMPPC_DEBUG_WATCH_READ (1UL << 3) __u32 type; __u32 reserved; } bp[16]; @@ -429,6 +443,11 @@ struct kvm_get_htab_header { #define KVM_REG_PPC_MMCR0 (KVM_REG_PPC | KVM_REG_SIZE_U64 | 0x10) #define KVM_REG_PPC_MMCR1 (KVM_REG_PPC | KVM_REG_SIZE_U64 | 0x11) #define KVM_REG_PPC_MMCRA (KVM_REG_PPC | KVM_REG_SIZE_U64 | 0x12) +#define KVM_REG_PPC_MMCR2 (KVM_REG_PPC | KVM_REG_SIZE_U64 | 0x13) +#define KVM_REG_PPC_MMCRS (KVM_REG_PPC | KVM_REG_SIZE_U64 | 0x14) +#define KVM_REG_PPC_SIAR (KVM_REG_PPC | KVM_REG_SIZE_U64 | 0x15) +#define KVM_REG_PPC_SDAR (KVM_REG_PPC | KVM_REG_SIZE_U64 | 0x16) +#define KVM_REG_PPC_SIER (KVM_REG_PPC | KVM_REG_SIZE_U64 | 0x17) #define KVM_REG_PPC_PMC1 (KVM_REG_PPC | KVM_REG_SIZE_U32 | 0x18) #define KVM_REG_PPC_PMC2 (KVM_REG_PPC | KVM_REG_SIZE_U32 | 0x19) @@ -499,6 +518,65 @@ struct kvm_get_htab_header { #define KVM_REG_PPC_TLB3PS (KVM_REG_PPC | KVM_REG_SIZE_U32 | 0x9a) #define KVM_REG_PPC_EPTCFG (KVM_REG_PPC | KVM_REG_SIZE_U32 | 0x9b) +/* Timebase offset */ +#define KVM_REG_PPC_TB_OFFSET (KVM_REG_PPC | KVM_REG_SIZE_U64 | 0x9c) + +/* POWER8 registers */ +#define KVM_REG_PPC_SPMC1 (KVM_REG_PPC | KVM_REG_SIZE_U32 | 0x9d) +#define KVM_REG_PPC_SPMC2 (KVM_REG_PPC | KVM_REG_SIZE_U32 | 0x9e) +#define KVM_REG_PPC_IAMR (KVM_REG_PPC | KVM_REG_SIZE_U64 | 0x9f) +#define KVM_REG_PPC_TFHAR (KVM_REG_PPC | KVM_REG_SIZE_U64 | 0xa0) +#define KVM_REG_PPC_TFIAR (KVM_REG_PPC | KVM_REG_SIZE_U64 | 0xa1) +#define KVM_REG_PPC_TEXASR (KVM_REG_PPC | KVM_REG_SIZE_U64 | 0xa2) +#define KVM_REG_PPC_FSCR (KVM_REG_PPC | KVM_REG_SIZE_U64 | 0xa3) +#define KVM_REG_PPC_PSPB (KVM_REG_PPC | KVM_REG_SIZE_U32 | 0xa4) +#define KVM_REG_PPC_EBBHR (KVM_REG_PPC | KVM_REG_SIZE_U64 | 0xa5) +#define KVM_REG_PPC_EBBRR (KVM_REG_PPC | KVM_REG_SIZE_U64 | 0xa6) +#define KVM_REG_PPC_BESCR (KVM_REG_PPC | KVM_REG_SIZE_U64 | 0xa7) +#define KVM_REG_PPC_TAR (KVM_REG_PPC | KVM_REG_SIZE_U64 | 0xa8) +#define KVM_REG_PPC_DPDES (KVM_REG_PPC | KVM_REG_SIZE_U64 | 0xa9) +#define KVM_REG_PPC_DAWR (KVM_REG_PPC | KVM_REG_SIZE_U64 | 0xaa) +#define KVM_REG_PPC_DAWRX (KVM_REG_PPC | KVM_REG_SIZE_U64 | 0xab) +#define KVM_REG_PPC_CIABR (KVM_REG_PPC | KVM_REG_SIZE_U64 | 0xac) +#define KVM_REG_PPC_IC (KVM_REG_PPC | KVM_REG_SIZE_U64 | 0xad) +#define KVM_REG_PPC_VTB (KVM_REG_PPC | KVM_REG_SIZE_U64 | 0xae) +#define KVM_REG_PPC_CSIGR (KVM_REG_PPC | KVM_REG_SIZE_U64 | 0xaf) +#define KVM_REG_PPC_TACR (KVM_REG_PPC | KVM_REG_SIZE_U64 | 0xb0) +#define KVM_REG_PPC_TCSCR (KVM_REG_PPC | KVM_REG_SIZE_U64 | 0xb1) +#define KVM_REG_PPC_PID (KVM_REG_PPC | KVM_REG_SIZE_U64 | 0xb2) +#define KVM_REG_PPC_ACOP (KVM_REG_PPC | KVM_REG_SIZE_U64 | 0xb3) + +#define KVM_REG_PPC_VRSAVE (KVM_REG_PPC | KVM_REG_SIZE_U32 | 0xb4) +#define KVM_REG_PPC_LPCR (KVM_REG_PPC | KVM_REG_SIZE_U32 | 0xb5) +#define KVM_REG_PPC_PPR (KVM_REG_PPC | KVM_REG_SIZE_U64 | 0xb6) + +/* Architecture compatibility level */ +#define KVM_REG_PPC_ARCH_COMPAT (KVM_REG_PPC | KVM_REG_SIZE_U32 | 0xb7) + +/* Transactional Memory checkpointed state: + * This is all GPRs, all VSX regs and a subset of SPRs + */ +#define KVM_REG_PPC_TM (KVM_REG_PPC | 0x80000000) +/* TM GPRs */ +#define KVM_REG_PPC_TM_GPR0 (KVM_REG_PPC_TM | KVM_REG_SIZE_U64 | 0) +#define KVM_REG_PPC_TM_GPR(n) (KVM_REG_PPC_TM_GPR0 + (n)) +#define KVM_REG_PPC_TM_GPR31 (KVM_REG_PPC_TM | KVM_REG_SIZE_U64 | 0x1f) +/* TM VSX */ +#define KVM_REG_PPC_TM_VSR0 (KVM_REG_PPC_TM | KVM_REG_SIZE_U128 | 0x20) +#define KVM_REG_PPC_TM_VSR(n) (KVM_REG_PPC_TM_VSR0 + (n)) +#define KVM_REG_PPC_TM_VSR63 (KVM_REG_PPC_TM | KVM_REG_SIZE_U128 | 0x5f) +/* TM SPRS */ +#define KVM_REG_PPC_TM_CR (KVM_REG_PPC_TM | KVM_REG_SIZE_U64 | 0x60) +#define KVM_REG_PPC_TM_LR (KVM_REG_PPC_TM | KVM_REG_SIZE_U64 | 0x61) +#define KVM_REG_PPC_TM_CTR (KVM_REG_PPC_TM | KVM_REG_SIZE_U64 | 0x62) +#define KVM_REG_PPC_TM_FPSCR (KVM_REG_PPC_TM | KVM_REG_SIZE_U64 | 0x63) +#define KVM_REG_PPC_TM_AMR (KVM_REG_PPC_TM | KVM_REG_SIZE_U64 | 0x64) +#define KVM_REG_PPC_TM_PPR (KVM_REG_PPC_TM | KVM_REG_SIZE_U64 | 0x65) +#define KVM_REG_PPC_TM_VRSAVE (KVM_REG_PPC_TM | KVM_REG_SIZE_U64 | 0x66) +#define KVM_REG_PPC_TM_VSCR (KVM_REG_PPC_TM | KVM_REG_SIZE_U32 | 0x67) +#define KVM_REG_PPC_TM_DSCR (KVM_REG_PPC_TM | KVM_REG_SIZE_U64 | 0x68) +#define KVM_REG_PPC_TM_TAR (KVM_REG_PPC_TM | KVM_REG_SIZE_U64 | 0x69) + /* PPC64 eXternal Interrupt Controller Specification */ #define KVM_DEV_XICS_GRP_SOURCES 1 /* 64-bit source attributes */ diff --git a/arch/powerpc/kernel/asm-offsets.c b/arch/powerpc/kernel/asm-offsets.c index e60a3697932c..2ea5cc033ec8 100644 --- a/arch/powerpc/kernel/asm-offsets.c +++ b/arch/powerpc/kernel/asm-offsets.c @@ -439,7 +439,7 @@ int main(void) DEFINE(VCPU_LR, offsetof(struct kvm_vcpu, arch.lr)); DEFINE(VCPU_CR, offsetof(struct kvm_vcpu, arch.cr)); DEFINE(VCPU_PC, offsetof(struct kvm_vcpu, arch.pc)); -#ifdef CONFIG_KVM_BOOK3S_64_HV +#ifdef CONFIG_KVM_BOOK3S_HV_POSSIBLE DEFINE(VCPU_MSR, offsetof(struct kvm_vcpu, arch.shregs.msr)); DEFINE(VCPU_SRR0, offsetof(struct kvm_vcpu, arch.shregs.srr0)); DEFINE(VCPU_SRR1, offsetof(struct kvm_vcpu, arch.shregs.srr1)); @@ -470,7 +470,7 @@ int main(void) DEFINE(KVM_LPID, offsetof(struct kvm, arch.lpid)); /* book3s */ -#ifdef CONFIG_KVM_BOOK3S_64_HV +#ifdef CONFIG_KVM_BOOK3S_HV_POSSIBLE DEFINE(KVM_SDR1, offsetof(struct kvm, arch.sdr1)); DEFINE(KVM_HOST_LPID, offsetof(struct kvm, arch.host_lpid)); DEFINE(KVM_HOST_LPCR, offsetof(struct kvm, arch.host_lpcr)); @@ -502,6 +502,8 @@ int main(void) DEFINE(VCPU_PRODDED, offsetof(struct kvm_vcpu, arch.prodded)); DEFINE(VCPU_MMCR, offsetof(struct kvm_vcpu, arch.mmcr)); DEFINE(VCPU_PMC, offsetof(struct kvm_vcpu, arch.pmc)); + DEFINE(VCPU_SIAR, offsetof(struct kvm_vcpu, arch.siar)); + DEFINE(VCPU_SDAR, offsetof(struct kvm_vcpu, arch.sdar)); DEFINE(VCPU_SLB, offsetof(struct kvm_vcpu, arch.slb)); DEFINE(VCPU_SLB_MAX, offsetof(struct kvm_vcpu, arch.slb_max)); DEFINE(VCPU_SLB_NR, offsetof(struct kvm_vcpu, arch.slb_nr)); @@ -511,18 +513,22 @@ int main(void) DEFINE(VCPU_TRAP, offsetof(struct kvm_vcpu, arch.trap)); DEFINE(VCPU_PTID, offsetof(struct kvm_vcpu, arch.ptid)); DEFINE(VCPU_CFAR, offsetof(struct kvm_vcpu, arch.cfar)); + DEFINE(VCPU_PPR, offsetof(struct kvm_vcpu, arch.ppr)); + DEFINE(VCPU_SHADOW_SRR1, offsetof(struct kvm_vcpu, arch.shadow_srr1)); DEFINE(VCORE_ENTRY_EXIT, offsetof(struct kvmppc_vcore, entry_exit_count)); DEFINE(VCORE_NAP_COUNT, offsetof(struct kvmppc_vcore, nap_count)); DEFINE(VCORE_IN_GUEST, offsetof(struct kvmppc_vcore, in_guest)); DEFINE(VCORE_NAPPING_THREADS, offsetof(struct kvmppc_vcore, napping_threads)); - DEFINE(VCPU_SVCPU, offsetof(struct kvmppc_vcpu_book3s, shadow_vcpu) - - offsetof(struct kvmppc_vcpu_book3s, vcpu)); + DEFINE(VCORE_TB_OFFSET, offsetof(struct kvmppc_vcore, tb_offset)); + DEFINE(VCORE_LPCR, offsetof(struct kvmppc_vcore, lpcr)); + DEFINE(VCORE_PCR, offsetof(struct kvmppc_vcore, pcr)); DEFINE(VCPU_SLB_E, offsetof(struct kvmppc_slb, orige)); DEFINE(VCPU_SLB_V, offsetof(struct kvmppc_slb, origv)); DEFINE(VCPU_SLB_SIZE, sizeof(struct kvmppc_slb)); #ifdef CONFIG_PPC_BOOK3S_64 -#ifdef CONFIG_KVM_BOOK3S_PR +#ifdef CONFIG_KVM_BOOK3S_PR_POSSIBLE + DEFINE(PACA_SVCPU, offsetof(struct paca_struct, shadow_vcpu)); # define SVCPU_FIELD(x, f) DEFINE(x, offsetof(struct paca_struct, shadow_vcpu.f)) #else # define SVCPU_FIELD(x, f) @@ -574,7 +580,7 @@ int main(void) HSTATE_FIELD(HSTATE_RESTORE_HID5, restore_hid5); HSTATE_FIELD(HSTATE_NAPPING, napping); -#ifdef CONFIG_KVM_BOOK3S_64_HV +#ifdef CONFIG_KVM_BOOK3S_HV_POSSIBLE HSTATE_FIELD(HSTATE_HWTHREAD_REQ, hwthread_req); HSTATE_FIELD(HSTATE_HWTHREAD_STATE, hwthread_state); HSTATE_FIELD(HSTATE_KVM_VCPU, kvm_vcpu); @@ -590,10 +596,11 @@ int main(void) HSTATE_FIELD(HSTATE_DABR, dabr); HSTATE_FIELD(HSTATE_DECEXP, dec_expires); DEFINE(IPI_PRIORITY, IPI_PRIORITY); -#endif /* CONFIG_KVM_BOOK3S_64_HV */ +#endif /* CONFIG_KVM_BOOK3S_HV_POSSIBLE */ #ifdef CONFIG_PPC_BOOK3S_64 HSTATE_FIELD(HSTATE_CFAR, cfar); + HSTATE_FIELD(HSTATE_PPR, ppr); #endif /* CONFIG_PPC_BOOK3S_64 */ #else /* CONFIG_PPC_BOOK3S */ diff --git a/arch/powerpc/kernel/eeh.c b/arch/powerpc/kernel/eeh.c index 1fb331db34c8..4bd687d5e7aa 100644 --- a/arch/powerpc/kernel/eeh.c +++ b/arch/powerpc/kernel/eeh.c @@ -189,14 +189,13 @@ static size_t eeh_gather_pci_data(struct eeh_dev *edev, char * buf, size_t len) } /* If PCI-E capable, dump PCI-E cap 10, and the AER */ - cap = pci_find_capability(dev, PCI_CAP_ID_EXP); - if (cap) { + if (pci_is_pcie(dev)) { n += scnprintf(buf+n, len-n, "pci-e cap10:\n"); printk(KERN_WARNING "EEH: PCI-E capabilities and status follow:\n"); for (i=0; i<=8; i++) { - eeh_ops->read_config(dn, cap+4*i, 4, &cfg); + eeh_ops->read_config(dn, dev->pcie_cap+4*i, 4, &cfg); n += scnprintf(buf+n, len-n, "%02x:%x\n", 4*i, cfg); printk(KERN_WARNING "EEH: PCI-E %02x: %08x\n", i, cfg); } @@ -687,6 +686,15 @@ void eeh_save_bars(struct eeh_dev *edev) for (i = 0; i < 16; i++) eeh_ops->read_config(dn, i * 4, 4, &edev->config_space[i]); + + /* + * For PCI bridges including root port, we need enable bus + * master explicitly. Otherwise, it can't fetch IODA table + * entries correctly. So we cache the bit in advance so that + * we can restore it after reset, either PHB range or PE range. + */ + if (edev->mode & EEH_DEV_BRIDGE) + edev->config_space[1] |= PCI_COMMAND_MASTER; } /** diff --git a/arch/powerpc/kernel/eeh_event.c b/arch/powerpc/kernel/eeh_event.c index d27c5afc90ae..72d748b56c86 100644 --- a/arch/powerpc/kernel/eeh_event.c +++ b/arch/powerpc/kernel/eeh_event.c @@ -74,8 +74,13 @@ static int eeh_event_handler(void * dummy) pe = event->pe; if (pe) { eeh_pe_state_mark(pe, EEH_PE_RECOVERING); - pr_info("EEH: Detected PCI bus error on PHB#%d-PE#%x\n", - pe->phb->global_number, pe->addr); + if (pe->type & EEH_PE_PHB) + pr_info("EEH: Detected error on PHB#%d\n", + pe->phb->global_number); + else + pr_info("EEH: Detected PCI bus error on " + "PHB#%d-PE#%x\n", + pe->phb->global_number, pe->addr); eeh_handle_event(pe); eeh_pe_state_clear(pe, EEH_PE_RECOVERING); } else { diff --git a/arch/powerpc/kernel/exceptions-64s.S b/arch/powerpc/kernel/exceptions-64s.S index 3a9ed6ac224b..9f905e40922e 100644 --- a/arch/powerpc/kernel/exceptions-64s.S +++ b/arch/powerpc/kernel/exceptions-64s.S @@ -126,7 +126,7 @@ BEGIN_FTR_SECTION bgt cr1,. GET_PACA(r13) -#ifdef CONFIG_KVM_BOOK3S_64_HV +#ifdef CONFIG_KVM_BOOK3S_HV_POSSIBLE li r0,KVM_HWTHREAD_IN_KERNEL stb r0,HSTATE_HWTHREAD_STATE(r13) /* Order setting hwthread_state vs. testing hwthread_req */ @@ -425,7 +425,7 @@ data_access_check_stab: mfspr r9,SPRN_DSISR srdi r10,r10,60 rlwimi r10,r9,16,0x20 -#ifdef CONFIG_KVM_BOOK3S_PR +#ifdef CONFIG_KVM_BOOK3S_PR_POSSIBLE lbz r9,HSTATE_IN_GUEST(r13) rlwimi r10,r9,8,0x300 #endif @@ -650,6 +650,32 @@ slb_miss_user_pseries: b . /* prevent spec. execution */ #endif /* __DISABLED__ */ +#ifdef CONFIG_KVM_BOOK3S_64_HANDLER +kvmppc_skip_interrupt: + /* + * Here all GPRs are unchanged from when the interrupt happened + * except for r13, which is saved in SPRG_SCRATCH0. + */ + mfspr r13, SPRN_SRR0 + addi r13, r13, 4 + mtspr SPRN_SRR0, r13 + GET_SCRATCH0(r13) + rfid + b . + +kvmppc_skip_Hinterrupt: + /* + * Here all GPRs are unchanged from when the interrupt happened + * except for r13, which is saved in SPRG_SCRATCH0. + */ + mfspr r13, SPRN_HSRR0 + addi r13, r13, 4 + mtspr SPRN_HSRR0, r13 + GET_SCRATCH0(r13) + hrfid + b . +#endif + /* * Code from here down to __end_handlers is invoked from the * exception prologs above. Because the prologs assemble the diff --git a/arch/powerpc/kernel/idle_power7.S b/arch/powerpc/kernel/idle_power7.S index e11863f4e595..847e40e62fce 100644 --- a/arch/powerpc/kernel/idle_power7.S +++ b/arch/powerpc/kernel/idle_power7.S @@ -84,7 +84,7 @@ _GLOBAL(power7_nap) std r9,_MSR(r1) std r1,PACAR1(r13) -#ifdef CONFIG_KVM_BOOK3S_64_HV +#ifdef CONFIG_KVM_BOOK3S_HV_POSSIBLE /* Tell KVM we're napping */ li r4,KVM_HWTHREAD_IN_NAP stb r4,HSTATE_HWTHREAD_STATE(r13) diff --git a/arch/powerpc/kernel/kprobes.c b/arch/powerpc/kernel/kprobes.c index 2156ea90eb54..90fab64d911d 100644 --- a/arch/powerpc/kernel/kprobes.c +++ b/arch/powerpc/kernel/kprobes.c @@ -429,7 +429,7 @@ int __kprobes kprobe_fault_handler(struct pt_regs *regs, int trapnr) case KPROBE_HIT_SSDONE: /* * We increment the nmissed count for accounting, - * we can also use npre/npostfault count for accouting + * we can also use npre/npostfault count for accounting * these specific fault cases. */ kprobes_inc_nmissed_count(cur); diff --git a/arch/powerpc/kernel/process.c b/arch/powerpc/kernel/process.c index 75c2d1009985..3386d8ab7eb0 100644 --- a/arch/powerpc/kernel/process.c +++ b/arch/powerpc/kernel/process.c @@ -858,17 +858,21 @@ void show_regs(struct pt_regs * regs) printk("MSR: "REG" ", regs->msr); printbits(regs->msr, msr_bits); printk(" CR: %08lx XER: %08lx\n", regs->ccr, regs->xer); -#ifdef CONFIG_PPC64 - printk("SOFTE: %ld\n", regs->softe); -#endif trap = TRAP(regs); if ((regs->trap != 0xc00) && cpu_has_feature(CPU_FTR_CFAR)) - printk("CFAR: "REG"\n", regs->orig_gpr3); - if (trap == 0x300 || trap == 0x600) + printk("CFAR: "REG" ", regs->orig_gpr3); + if (trap == 0x200 || trap == 0x300 || trap == 0x600) #if defined(CONFIG_4xx) || defined(CONFIG_BOOKE) - printk("DEAR: "REG", ESR: "REG"\n", regs->dar, regs->dsisr); + printk("DEAR: "REG" ESR: "REG" ", regs->dar, regs->dsisr); #else - printk("DAR: "REG", DSISR: %08lx\n", regs->dar, regs->dsisr); + printk("DAR: "REG" DSISR: %08lx ", regs->dar, regs->dsisr); +#endif +#ifdef CONFIG_PPC64 + printk("SOFTE: %ld ", regs->softe); +#endif +#ifdef CONFIG_PPC_TRANSACTIONAL_MEM + if (MSR_TM_ACTIVE(regs->msr)) + printk("\nPACATMSCRATCH: %016llx ", get_paca()->tm_scratch); #endif for (i = 0; i < 32; i++) { @@ -887,9 +891,6 @@ void show_regs(struct pt_regs * regs) printk("NIP ["REG"] %pS\n", regs->nip, (void *)regs->nip); printk("LR ["REG"] %pS\n", regs->link, (void *)regs->link); #endif -#ifdef CONFIG_PPC_TRANSACTIONAL_MEM - printk("PACATMSCRATCH [%llx]\n", get_paca()->tm_scratch); -#endif show_stack(current, (unsigned long *) regs->gpr[1]); if (!user_mode(regs)) show_instructions(regs); @@ -1086,25 +1087,45 @@ void start_thread(struct pt_regs *regs, unsigned long start, unsigned long sp) regs->msr = MSR_USER; #else if (!is_32bit_task()) { - unsigned long entry, toc; + unsigned long entry; - /* start is a relocated pointer to the function descriptor for - * the elf _start routine. The first entry in the function - * descriptor is the entry address of _start and the second - * entry is the TOC value we need to use. - */ - __get_user(entry, (unsigned long __user *)start); - __get_user(toc, (unsigned long __user *)start+1); + if (is_elf2_task()) { + /* Look ma, no function descriptors! */ + entry = start; - /* Check whether the e_entry function descriptor entries - * need to be relocated before we can use them. - */ - if (load_addr != 0) { - entry += load_addr; - toc += load_addr; + /* + * Ulrich says: + * The latest iteration of the ABI requires that when + * calling a function (at its global entry point), + * the caller must ensure r12 holds the entry point + * address (so that the function can quickly + * establish addressability). + */ + regs->gpr[12] = start; + /* Make sure that's restored on entry to userspace. */ + set_thread_flag(TIF_RESTOREALL); + } else { + unsigned long toc; + + /* start is a relocated pointer to the function + * descriptor for the elf _start routine. The first + * entry in the function descriptor is the entry + * address of _start and the second entry is the TOC + * value we need to use. + */ + __get_user(entry, (unsigned long __user *)start); + __get_user(toc, (unsigned long __user *)start+1); + + /* Check whether the e_entry function descriptor entries + * need to be relocated before we can use them. + */ + if (load_addr != 0) { + entry += load_addr; + toc += load_addr; + } + regs->gpr[2] = toc; } regs->nip = entry; - regs->gpr[2] = toc; regs->msr = MSR_USER64; } else { regs->nip = start; diff --git a/arch/powerpc/kernel/prom.c b/arch/powerpc/kernel/prom.c index f3a47098fb8e..fa0ad8aafbcc 100644 --- a/arch/powerpc/kernel/prom.c +++ b/arch/powerpc/kernel/prom.c @@ -777,6 +777,26 @@ int of_get_ibm_chip_id(struct device_node *np) return -1; } +/** + * cpu_to_chip_id - Return the cpus chip-id + * @cpu: The logical cpu number. + * + * Return the value of the ibm,chip-id property corresponding to the given + * logical cpu number. If the chip-id can not be found, returns -1. + */ +int cpu_to_chip_id(int cpu) +{ + struct device_node *np; + + np = of_get_cpu_node(cpu, NULL); + if (!np) + return -1; + + of_node_put(np); + return of_get_ibm_chip_id(np); +} +EXPORT_SYMBOL(cpu_to_chip_id); + #ifdef CONFIG_PPC_PSERIES /* * Fix up the uninitialized fields in a new device node: diff --git a/arch/powerpc/kernel/signal_32.c b/arch/powerpc/kernel/signal_32.c index 749778e0a69d..1844298f5ea4 100644 --- a/arch/powerpc/kernel/signal_32.c +++ b/arch/powerpc/kernel/signal_32.c @@ -457,7 +457,15 @@ static int save_user_regs(struct pt_regs *regs, struct mcontext __user *frame, if (copy_vsx_to_user(&frame->mc_vsregs, current)) return 1; msr |= MSR_VSX; - } + } else if (!ctx_has_vsx_region) + /* + * With a small context structure we can't hold the VSX + * registers, hence clear the MSR value to indicate the state + * was not saved. + */ + msr &= ~MSR_VSX; + + #endif /* CONFIG_VSX */ #ifdef CONFIG_SPE /* save spe registers */ diff --git a/arch/powerpc/kernel/signal_64.c b/arch/powerpc/kernel/signal_64.c index b3c615764c9b..e66f67b8b9e6 100644 --- a/arch/powerpc/kernel/signal_64.c +++ b/arch/powerpc/kernel/signal_64.c @@ -701,12 +701,6 @@ badframe: int handle_rt_signal64(int signr, struct k_sigaction *ka, siginfo_t *info, sigset_t *set, struct pt_regs *regs) { - /* Handler is *really* a pointer to the function descriptor for - * the signal routine. The first entry in the function - * descriptor is the entry address of signal and the second - * entry is the TOC value we need to use. - */ - func_descr_t __user *funct_desc_ptr; struct rt_sigframe __user *frame; unsigned long newsp = 0; long err = 0; @@ -766,19 +760,32 @@ int handle_rt_signal64(int signr, struct k_sigaction *ka, siginfo_t *info, goto badframe; regs->link = (unsigned long) &frame->tramp[0]; } - funct_desc_ptr = (func_descr_t __user *) ka->sa.sa_handler; /* Allocate a dummy caller frame for the signal handler. */ newsp = ((unsigned long)frame) - __SIGNAL_FRAMESIZE; err |= put_user(regs->gpr[1], (unsigned long __user *)newsp); /* Set up "regs" so we "return" to the signal handler. */ - err |= get_user(regs->nip, &funct_desc_ptr->entry); + if (is_elf2_task()) { + regs->nip = (unsigned long) ka->sa.sa_handler; + regs->gpr[12] = regs->nip; + } else { + /* Handler is *really* a pointer to the function descriptor for + * the signal routine. The first entry in the function + * descriptor is the entry address of signal and the second + * entry is the TOC value we need to use. + */ + func_descr_t __user *funct_desc_ptr = + (func_descr_t __user *) ka->sa.sa_handler; + + err |= get_user(regs->nip, &funct_desc_ptr->entry); + err |= get_user(regs->gpr[2], &funct_desc_ptr->toc); + } + /* enter the signal handler in native-endian mode */ regs->msr &= ~MSR_LE; regs->msr |= (MSR_KERNEL & MSR_LE); regs->gpr[1] = newsp; - err |= get_user(regs->gpr[2], &funct_desc_ptr->toc); regs->gpr[3] = signr; regs->result = 0; if (ka->sa.sa_flags & SA_SIGINFO) { diff --git a/arch/powerpc/kernel/smp.c b/arch/powerpc/kernel/smp.c index 8e59abc237d7..a3b64f3bf9a2 100644 --- a/arch/powerpc/kernel/smp.c +++ b/arch/powerpc/kernel/smp.c @@ -597,22 +597,6 @@ out: return id; } -/* Return the value of the chip-id property corresponding - * to the given logical cpu. - */ -int cpu_to_chip_id(int cpu) -{ - struct device_node *np; - - np = of_get_cpu_node(cpu, NULL); - if (!np) - return -1; - - of_node_put(np); - return of_get_ibm_chip_id(np); -} -EXPORT_SYMBOL(cpu_to_chip_id); - /* Helper routines for cpu to core mapping */ int cpu_core_index_of_thread(int cpu) { @@ -844,18 +828,6 @@ void __cpu_die(unsigned int cpu) smp_ops->cpu_die(cpu); } -static DEFINE_MUTEX(powerpc_cpu_hotplug_driver_mutex); - -void cpu_hotplug_driver_lock() -{ - mutex_lock(&powerpc_cpu_hotplug_driver_mutex); -} - -void cpu_hotplug_driver_unlock() -{ - mutex_unlock(&powerpc_cpu_hotplug_driver_mutex); -} - void cpu_die(void) { if (ppc_md.cpu_die) diff --git a/arch/powerpc/kernel/time.c b/arch/powerpc/kernel/time.c index 192b051df97e..b3b144121cc9 100644 --- a/arch/powerpc/kernel/time.c +++ b/arch/powerpc/kernel/time.c @@ -213,8 +213,6 @@ static u64 scan_dispatch_log(u64 stop_tb) if (i == be64_to_cpu(vpa->dtl_idx)) return 0; while (i < be64_to_cpu(vpa->dtl_idx)) { - if (dtl_consumer) - dtl_consumer(dtl, i); dtb = be64_to_cpu(dtl->timebase); tb_delta = be32_to_cpu(dtl->enqueue_to_dispatch_time) + be32_to_cpu(dtl->ready_to_enqueue_time); @@ -227,6 +225,8 @@ static u64 scan_dispatch_log(u64 stop_tb) } if (dtb > stop_tb) break; + if (dtl_consumer) + dtl_consumer(dtl, i); stolen += tb_delta; ++i; ++dtl; diff --git a/arch/powerpc/kernel/traps.c b/arch/powerpc/kernel/traps.c index 62c3dd8c69f2..907a472f9a9e 100644 --- a/arch/powerpc/kernel/traps.c +++ b/arch/powerpc/kernel/traps.c @@ -1529,7 +1529,7 @@ static void handle_debug(struct pt_regs *regs, unsigned long debug_status) * back on or not. */ if (DBCR_ACTIVE_EVENTS(current->thread.debug.dbcr0, - current->thread.debug.dbcr1)) + current->thread.debug.dbcr1)) regs->msr |= MSR_DE; else /* Make sure the IDM flag is off */ diff --git a/arch/powerpc/kernel/vdso64/sigtramp.S b/arch/powerpc/kernel/vdso64/sigtramp.S index 45ea281e9a21..542c6f422e4d 100644 --- a/arch/powerpc/kernel/vdso64/sigtramp.S +++ b/arch/powerpc/kernel/vdso64/sigtramp.S @@ -142,6 +142,13 @@ V_FUNCTION_END(__kernel_sigtramp_rt64) /* Size of CR reg in DWARF unwind info. */ #define CRSIZE 4 +/* Offset of CR reg within a full word. */ +#ifdef __LITTLE_ENDIAN__ +#define CROFF 0 +#else +#define CROFF (RSIZE - CRSIZE) +#endif + /* This is the offset of the VMX reg pointer. */ #define VREGS 48*RSIZE+33*8 @@ -181,7 +188,14 @@ V_FUNCTION_END(__kernel_sigtramp_rt64) rsave (31, 31*RSIZE); \ rsave (67, 32*RSIZE); /* ap, used as temp for nip */ \ rsave (65, 36*RSIZE); /* lr */ \ - rsave (70, 38*RSIZE + (RSIZE - CRSIZE)) /* cr */ + rsave (68, 38*RSIZE + CROFF); /* cr fields */ \ + rsave (69, 38*RSIZE + CROFF); \ + rsave (70, 38*RSIZE + CROFF); \ + rsave (71, 38*RSIZE + CROFF); \ + rsave (72, 38*RSIZE + CROFF); \ + rsave (73, 38*RSIZE + CROFF); \ + rsave (74, 38*RSIZE + CROFF); \ + rsave (75, 38*RSIZE + CROFF) /* Describe where the FP regs are saved. */ #define EH_FRAME_FP \ diff --git a/arch/powerpc/kernel/vio.c b/arch/powerpc/kernel/vio.c index e7d0c88f621a..76a64821f4a2 100644 --- a/arch/powerpc/kernel/vio.c +++ b/arch/powerpc/kernel/vio.c @@ -1419,7 +1419,7 @@ struct vio_dev *vio_register_device_node(struct device_node *of_node) /* needed to ensure proper operation of coherent allocations * later, in case driver doesn't set it explicitly */ - dma_set_mask_and_coherent(&viodev->dev, DMA_BIT_MASK(64)); + dma_coerce_mask_and_coherent(&viodev->dev, DMA_BIT_MASK(64)); } /* register with generic device framework */ diff --git a/arch/powerpc/kvm/44x.c b/arch/powerpc/kvm/44x.c index 2f5c6b6d6877..93221e87b911 100644 --- a/arch/powerpc/kvm/44x.c +++ b/arch/powerpc/kvm/44x.c @@ -31,13 +31,13 @@ #include "44x_tlb.h" #include "booke.h" -void kvmppc_core_vcpu_load(struct kvm_vcpu *vcpu, int cpu) +static void kvmppc_core_vcpu_load_44x(struct kvm_vcpu *vcpu, int cpu) { kvmppc_booke_vcpu_load(vcpu, cpu); kvmppc_44x_tlb_load(vcpu); } -void kvmppc_core_vcpu_put(struct kvm_vcpu *vcpu) +static void kvmppc_core_vcpu_put_44x(struct kvm_vcpu *vcpu) { kvmppc_44x_tlb_put(vcpu); kvmppc_booke_vcpu_put(vcpu); @@ -114,29 +114,32 @@ int kvmppc_core_vcpu_translate(struct kvm_vcpu *vcpu, return 0; } -void kvmppc_core_get_sregs(struct kvm_vcpu *vcpu, struct kvm_sregs *sregs) +static int kvmppc_core_get_sregs_44x(struct kvm_vcpu *vcpu, + struct kvm_sregs *sregs) { - kvmppc_get_sregs_ivor(vcpu, sregs); + return kvmppc_get_sregs_ivor(vcpu, sregs); } -int kvmppc_core_set_sregs(struct kvm_vcpu *vcpu, struct kvm_sregs *sregs) +static int kvmppc_core_set_sregs_44x(struct kvm_vcpu *vcpu, + struct kvm_sregs *sregs) { return kvmppc_set_sregs_ivor(vcpu, sregs); } -int kvmppc_get_one_reg(struct kvm_vcpu *vcpu, u64 id, - union kvmppc_one_reg *val) +static int kvmppc_get_one_reg_44x(struct kvm_vcpu *vcpu, u64 id, + union kvmppc_one_reg *val) { return -EINVAL; } -int kvmppc_set_one_reg(struct kvm_vcpu *vcpu, u64 id, - union kvmppc_one_reg *val) +static int kvmppc_set_one_reg_44x(struct kvm_vcpu *vcpu, u64 id, + union kvmppc_one_reg *val) { return -EINVAL; } -struct kvm_vcpu *kvmppc_core_vcpu_create(struct kvm *kvm, unsigned int id) +static struct kvm_vcpu *kvmppc_core_vcpu_create_44x(struct kvm *kvm, + unsigned int id) { struct kvmppc_vcpu_44x *vcpu_44x; struct kvm_vcpu *vcpu; @@ -167,7 +170,7 @@ out: return ERR_PTR(err); } -void kvmppc_core_vcpu_free(struct kvm_vcpu *vcpu) +static void kvmppc_core_vcpu_free_44x(struct kvm_vcpu *vcpu) { struct kvmppc_vcpu_44x *vcpu_44x = to_44x(vcpu); @@ -176,28 +179,53 @@ void kvmppc_core_vcpu_free(struct kvm_vcpu *vcpu) kmem_cache_free(kvm_vcpu_cache, vcpu_44x); } -int kvmppc_core_init_vm(struct kvm *kvm) +static int kvmppc_core_init_vm_44x(struct kvm *kvm) { return 0; } -void kvmppc_core_destroy_vm(struct kvm *kvm) +static void kvmppc_core_destroy_vm_44x(struct kvm *kvm) { } +static struct kvmppc_ops kvm_ops_44x = { + .get_sregs = kvmppc_core_get_sregs_44x, + .set_sregs = kvmppc_core_set_sregs_44x, + .get_one_reg = kvmppc_get_one_reg_44x, + .set_one_reg = kvmppc_set_one_reg_44x, + .vcpu_load = kvmppc_core_vcpu_load_44x, + .vcpu_put = kvmppc_core_vcpu_put_44x, + .vcpu_create = kvmppc_core_vcpu_create_44x, + .vcpu_free = kvmppc_core_vcpu_free_44x, + .mmu_destroy = kvmppc_mmu_destroy_44x, + .init_vm = kvmppc_core_init_vm_44x, + .destroy_vm = kvmppc_core_destroy_vm_44x, + .emulate_op = kvmppc_core_emulate_op_44x, + .emulate_mtspr = kvmppc_core_emulate_mtspr_44x, + .emulate_mfspr = kvmppc_core_emulate_mfspr_44x, +}; + static int __init kvmppc_44x_init(void) { int r; r = kvmppc_booke_init(); if (r) - return r; + goto err_out; + + r = kvm_init(NULL, sizeof(struct kvmppc_vcpu_44x), 0, THIS_MODULE); + if (r) + goto err_out; + kvm_ops_44x.owner = THIS_MODULE; + kvmppc_pr_ops = &kvm_ops_44x; - return kvm_init(NULL, sizeof(struct kvmppc_vcpu_44x), 0, THIS_MODULE); +err_out: + return r; } static void __exit kvmppc_44x_exit(void) { + kvmppc_pr_ops = NULL; kvmppc_booke_exit(); } diff --git a/arch/powerpc/kvm/44x_emulate.c b/arch/powerpc/kvm/44x_emulate.c index 35ec0a8547da..92c9ab4bcfec 100644 --- a/arch/powerpc/kvm/44x_emulate.c +++ b/arch/powerpc/kvm/44x_emulate.c @@ -91,8 +91,8 @@ static int emulate_mfdcr(struct kvm_vcpu *vcpu, int rt, int dcrn) return EMULATE_DONE; } -int kvmppc_core_emulate_op(struct kvm_run *run, struct kvm_vcpu *vcpu, - unsigned int inst, int *advance) +int kvmppc_core_emulate_op_44x(struct kvm_run *run, struct kvm_vcpu *vcpu, + unsigned int inst, int *advance) { int emulated = EMULATE_DONE; int dcrn = get_dcrn(inst); @@ -152,7 +152,7 @@ int kvmppc_core_emulate_op(struct kvm_run *run, struct kvm_vcpu *vcpu, return emulated; } -int kvmppc_core_emulate_mtspr(struct kvm_vcpu *vcpu, int sprn, ulong spr_val) +int kvmppc_core_emulate_mtspr_44x(struct kvm_vcpu *vcpu, int sprn, ulong spr_val) { int emulated = EMULATE_DONE; @@ -172,7 +172,7 @@ int kvmppc_core_emulate_mtspr(struct kvm_vcpu *vcpu, int sprn, ulong spr_val) return emulated; } -int kvmppc_core_emulate_mfspr(struct kvm_vcpu *vcpu, int sprn, ulong *spr_val) +int kvmppc_core_emulate_mfspr_44x(struct kvm_vcpu *vcpu, int sprn, ulong *spr_val) { int emulated = EMULATE_DONE; diff --git a/arch/powerpc/kvm/44x_tlb.c b/arch/powerpc/kvm/44x_tlb.c index ed0385448148..0deef1082e02 100644 --- a/arch/powerpc/kvm/44x_tlb.c +++ b/arch/powerpc/kvm/44x_tlb.c @@ -268,7 +268,7 @@ static void kvmppc_44x_shadow_release(struct kvmppc_vcpu_44x *vcpu_44x, trace_kvm_stlb_inval(stlb_index); } -void kvmppc_mmu_destroy(struct kvm_vcpu *vcpu) +void kvmppc_mmu_destroy_44x(struct kvm_vcpu *vcpu) { struct kvmppc_vcpu_44x *vcpu_44x = to_44x(vcpu); int i; diff --git a/arch/powerpc/kvm/Kconfig b/arch/powerpc/kvm/Kconfig index e593ff257bd3..141b2027189a 100644 --- a/arch/powerpc/kvm/Kconfig +++ b/arch/powerpc/kvm/Kconfig @@ -35,17 +35,20 @@ config KVM_BOOK3S_64_HANDLER bool select KVM_BOOK3S_HANDLER -config KVM_BOOK3S_PR +config KVM_BOOK3S_PR_POSSIBLE bool select KVM_MMIO select MMU_NOTIFIER +config KVM_BOOK3S_HV_POSSIBLE + bool + config KVM_BOOK3S_32 tristate "KVM support for PowerPC book3s_32 processors" depends on PPC_BOOK3S_32 && !SMP && !PTE_64BIT select KVM select KVM_BOOK3S_32_HANDLER - select KVM_BOOK3S_PR + select KVM_BOOK3S_PR_POSSIBLE ---help--- Support running unmodified book3s_32 guest kernels in virtual machines on book3s_32 host processors. @@ -60,6 +63,7 @@ config KVM_BOOK3S_64 depends on PPC_BOOK3S_64 select KVM_BOOK3S_64_HANDLER select KVM + select KVM_BOOK3S_PR_POSSIBLE if !KVM_BOOK3S_HV_POSSIBLE ---help--- Support running unmodified book3s_64 and book3s_32 guest kernels in virtual machines on book3s_64 host processors. @@ -70,8 +74,9 @@ config KVM_BOOK3S_64 If unsure, say N. config KVM_BOOK3S_64_HV - bool "KVM support for POWER7 and PPC970 using hypervisor mode in host" + tristate "KVM support for POWER7 and PPC970 using hypervisor mode in host" depends on KVM_BOOK3S_64 + select KVM_BOOK3S_HV_POSSIBLE select MMU_NOTIFIER select CMA ---help--- @@ -90,9 +95,20 @@ config KVM_BOOK3S_64_HV If unsure, say N. config KVM_BOOK3S_64_PR - def_bool y - depends on KVM_BOOK3S_64 && !KVM_BOOK3S_64_HV - select KVM_BOOK3S_PR + tristate "KVM support without using hypervisor mode in host" + depends on KVM_BOOK3S_64 + select KVM_BOOK3S_PR_POSSIBLE + ---help--- + Support running guest kernels in virtual machines on processors + without using hypervisor mode in the host, by running the + guest in user mode (problem state) and emulating all + privileged instructions and registers. + + This is not as fast as using hypervisor mode, but works on + machines where hypervisor mode is not available or not usable, + and can emulate processors that are different from the host + processor, including emulating 32-bit processors on a 64-bit + host. config KVM_BOOKE_HV bool diff --git a/arch/powerpc/kvm/Makefile b/arch/powerpc/kvm/Makefile index 6646c952c5e3..ce569b6bf4d8 100644 --- a/arch/powerpc/kvm/Makefile +++ b/arch/powerpc/kvm/Makefile @@ -53,41 +53,51 @@ kvm-e500mc-objs := \ e500_emulate.o kvm-objs-$(CONFIG_KVM_E500MC) := $(kvm-e500mc-objs) -kvm-book3s_64-objs-$(CONFIG_KVM_BOOK3S_64_PR) := \ - $(KVM)/coalesced_mmio.o \ +kvm-book3s_64-builtin-objs-$(CONFIG_KVM_BOOK3S_64_HANDLER) := \ + book3s_64_vio_hv.o + +kvm-pr-y := \ fpu.o \ book3s_paired_singles.o \ book3s_pr.o \ book3s_pr_papr.o \ - book3s_64_vio_hv.o \ book3s_emulate.o \ book3s_interrupts.o \ book3s_mmu_hpte.o \ book3s_64_mmu_host.o \ book3s_64_mmu.o \ book3s_32_mmu.o -kvm-book3s_64-builtin-objs-$(CONFIG_KVM_BOOK3S_64_PR) := \ + +ifdef CONFIG_KVM_BOOK3S_PR_POSSIBLE +kvm-book3s_64-module-objs := \ + $(KVM)/coalesced_mmio.o + +kvm-book3s_64-builtin-objs-$(CONFIG_KVM_BOOK3S_64_HANDLER) += \ book3s_rmhandlers.o +endif -kvm-book3s_64-objs-$(CONFIG_KVM_BOOK3S_64_HV) := \ +kvm-hv-y += \ book3s_hv.o \ book3s_hv_interrupts.o \ book3s_64_mmu_hv.o + kvm-book3s_64-builtin-xics-objs-$(CONFIG_KVM_XICS) := \ book3s_hv_rm_xics.o -kvm-book3s_64-builtin-objs-$(CONFIG_KVM_BOOK3S_64_HV) := \ + +ifdef CONFIG_KVM_BOOK3S_HV_POSSIBLE +kvm-book3s_64-builtin-objs-$(CONFIG_KVM_BOOK3S_64_HANDLER) += \ book3s_hv_rmhandlers.o \ book3s_hv_rm_mmu.o \ - book3s_64_vio_hv.o \ book3s_hv_ras.o \ book3s_hv_builtin.o \ book3s_hv_cma.o \ $(kvm-book3s_64-builtin-xics-objs-y) +endif kvm-book3s_64-objs-$(CONFIG_KVM_XICS) += \ book3s_xics.o -kvm-book3s_64-module-objs := \ +kvm-book3s_64-module-objs += \ $(KVM)/kvm_main.o \ $(KVM)/eventfd.o \ powerpc.o \ @@ -123,4 +133,7 @@ obj-$(CONFIG_KVM_E500MC) += kvm.o obj-$(CONFIG_KVM_BOOK3S_64) += kvm.o obj-$(CONFIG_KVM_BOOK3S_32) += kvm.o +obj-$(CONFIG_KVM_BOOK3S_64_PR) += kvm-pr.o +obj-$(CONFIG_KVM_BOOK3S_64_HV) += kvm-hv.o + obj-y += $(kvm-book3s_64-builtin-objs-y) diff --git a/arch/powerpc/kvm/book3s.c b/arch/powerpc/kvm/book3s.c index 700df6f1d32c..8912608b7e1b 100644 --- a/arch/powerpc/kvm/book3s.c +++ b/arch/powerpc/kvm/book3s.c @@ -34,6 +34,7 @@ #include <linux/vmalloc.h> #include <linux/highmem.h> +#include "book3s.h" #include "trace.h" #define VCPU_STAT(x) offsetof(struct kvm_vcpu, stat.x), KVM_STAT_VCPU @@ -69,6 +70,50 @@ void kvmppc_core_load_guest_debugstate(struct kvm_vcpu *vcpu) { } +static inline unsigned long kvmppc_interrupt_offset(struct kvm_vcpu *vcpu) +{ + if (!is_kvmppc_hv_enabled(vcpu->kvm)) + return to_book3s(vcpu)->hior; + return 0; +} + +static inline void kvmppc_update_int_pending(struct kvm_vcpu *vcpu, + unsigned long pending_now, unsigned long old_pending) +{ + if (is_kvmppc_hv_enabled(vcpu->kvm)) + return; + if (pending_now) + vcpu->arch.shared->int_pending = 1; + else if (old_pending) + vcpu->arch.shared->int_pending = 0; +} + +static inline bool kvmppc_critical_section(struct kvm_vcpu *vcpu) +{ + ulong crit_raw; + ulong crit_r1; + bool crit; + + if (is_kvmppc_hv_enabled(vcpu->kvm)) + return false; + + crit_raw = vcpu->arch.shared->critical; + crit_r1 = kvmppc_get_gpr(vcpu, 1); + + /* Truncate crit indicators in 32 bit mode */ + if (!(vcpu->arch.shared->msr & MSR_SF)) { + crit_raw &= 0xffffffff; + crit_r1 &= 0xffffffff; + } + + /* Critical section when crit == r1 */ + crit = (crit_raw == crit_r1); + /* ... and we're in supervisor mode */ + crit = crit && !(vcpu->arch.shared->msr & MSR_PR); + + return crit; +} + void kvmppc_inject_interrupt(struct kvm_vcpu *vcpu, int vec, u64 flags) { vcpu->arch.shared->srr0 = kvmppc_get_pc(vcpu); @@ -126,28 +171,32 @@ void kvmppc_book3s_queue_irqprio(struct kvm_vcpu *vcpu, unsigned int vec) printk(KERN_INFO "Queueing interrupt %x\n", vec); #endif } - +EXPORT_SYMBOL_GPL(kvmppc_book3s_queue_irqprio); void kvmppc_core_queue_program(struct kvm_vcpu *vcpu, ulong flags) { /* might as well deliver this straight away */ kvmppc_inject_interrupt(vcpu, BOOK3S_INTERRUPT_PROGRAM, flags); } +EXPORT_SYMBOL_GPL(kvmppc_core_queue_program); void kvmppc_core_queue_dec(struct kvm_vcpu *vcpu) { kvmppc_book3s_queue_irqprio(vcpu, BOOK3S_INTERRUPT_DECREMENTER); } +EXPORT_SYMBOL_GPL(kvmppc_core_queue_dec); int kvmppc_core_pending_dec(struct kvm_vcpu *vcpu) { return test_bit(BOOK3S_IRQPRIO_DECREMENTER, &vcpu->arch.pending_exceptions); } +EXPORT_SYMBOL_GPL(kvmppc_core_pending_dec); void kvmppc_core_dequeue_dec(struct kvm_vcpu *vcpu) { kvmppc_book3s_dequeue_irqprio(vcpu, BOOK3S_INTERRUPT_DECREMENTER); } +EXPORT_SYMBOL_GPL(kvmppc_core_dequeue_dec); void kvmppc_core_queue_external(struct kvm_vcpu *vcpu, struct kvm_interrupt *irq) @@ -285,8 +334,10 @@ int kvmppc_core_prepare_to_enter(struct kvm_vcpu *vcpu) return 0; } +EXPORT_SYMBOL_GPL(kvmppc_core_prepare_to_enter); -pfn_t kvmppc_gfn_to_pfn(struct kvm_vcpu *vcpu, gfn_t gfn) +pfn_t kvmppc_gfn_to_pfn(struct kvm_vcpu *vcpu, gfn_t gfn, bool writing, + bool *writable) { ulong mp_pa = vcpu->arch.magic_page_pa; @@ -302,20 +353,23 @@ pfn_t kvmppc_gfn_to_pfn(struct kvm_vcpu *vcpu, gfn_t gfn) pfn = (pfn_t)virt_to_phys((void*)shared_page) >> PAGE_SHIFT; get_page(pfn_to_page(pfn)); + if (writable) + *writable = true; return pfn; } - return gfn_to_pfn(vcpu->kvm, gfn); + return gfn_to_pfn_prot(vcpu->kvm, gfn, writing, writable); } +EXPORT_SYMBOL_GPL(kvmppc_gfn_to_pfn); static int kvmppc_xlate(struct kvm_vcpu *vcpu, ulong eaddr, bool data, - struct kvmppc_pte *pte) + bool iswrite, struct kvmppc_pte *pte) { int relocated = (vcpu->arch.shared->msr & (data ? MSR_DR : MSR_IR)); int r; if (relocated) { - r = vcpu->arch.mmu.xlate(vcpu, eaddr, pte, data); + r = vcpu->arch.mmu.xlate(vcpu, eaddr, pte, data, iswrite); } else { pte->eaddr = eaddr; pte->raddr = eaddr & KVM_PAM; @@ -361,7 +415,7 @@ int kvmppc_st(struct kvm_vcpu *vcpu, ulong *eaddr, int size, void *ptr, vcpu->stat.st++; - if (kvmppc_xlate(vcpu, *eaddr, data, &pte)) + if (kvmppc_xlate(vcpu, *eaddr, data, true, &pte)) return -ENOENT; *eaddr = pte.raddr; @@ -374,6 +428,7 @@ int kvmppc_st(struct kvm_vcpu *vcpu, ulong *eaddr, int size, void *ptr, return EMULATE_DONE; } +EXPORT_SYMBOL_GPL(kvmppc_st); int kvmppc_ld(struct kvm_vcpu *vcpu, ulong *eaddr, int size, void *ptr, bool data) @@ -383,7 +438,7 @@ int kvmppc_ld(struct kvm_vcpu *vcpu, ulong *eaddr, int size, void *ptr, vcpu->stat.ld++; - if (kvmppc_xlate(vcpu, *eaddr, data, &pte)) + if (kvmppc_xlate(vcpu, *eaddr, data, false, &pte)) goto nopte; *eaddr = pte.raddr; @@ -404,6 +459,7 @@ nopte: mmio: return EMULATE_DO_MMIO; } +EXPORT_SYMBOL_GPL(kvmppc_ld); int kvm_arch_vcpu_setup(struct kvm_vcpu *vcpu) { @@ -419,6 +475,18 @@ void kvmppc_subarch_vcpu_uninit(struct kvm_vcpu *vcpu) { } +int kvm_arch_vcpu_ioctl_get_sregs(struct kvm_vcpu *vcpu, + struct kvm_sregs *sregs) +{ + return vcpu->kvm->arch.kvm_ops->get_sregs(vcpu, sregs); +} + +int kvm_arch_vcpu_ioctl_set_sregs(struct kvm_vcpu *vcpu, + struct kvm_sregs *sregs) +{ + return vcpu->kvm->arch.kvm_ops->set_sregs(vcpu, sregs); +} + int kvm_arch_vcpu_ioctl_get_regs(struct kvm_vcpu *vcpu, struct kvm_regs *regs) { int i; @@ -495,8 +563,7 @@ int kvm_vcpu_ioctl_get_one_reg(struct kvm_vcpu *vcpu, struct kvm_one_reg *reg) if (size > sizeof(val)) return -EINVAL; - r = kvmppc_get_one_reg(vcpu, reg->id, &val); - + r = vcpu->kvm->arch.kvm_ops->get_one_reg(vcpu, reg->id, &val); if (r == -EINVAL) { r = 0; switch (reg->id) { @@ -528,6 +595,9 @@ int kvm_vcpu_ioctl_get_one_reg(struct kvm_vcpu *vcpu, struct kvm_one_reg *reg) } val = get_reg_val(reg->id, vcpu->arch.vscr.u[3]); break; + case KVM_REG_PPC_VRSAVE: + val = get_reg_val(reg->id, vcpu->arch.vrsave); + break; #endif /* CONFIG_ALTIVEC */ case KVM_REG_PPC_DEBUG_INST: { u32 opcode = INS_TW; @@ -572,8 +642,7 @@ int kvm_vcpu_ioctl_set_one_reg(struct kvm_vcpu *vcpu, struct kvm_one_reg *reg) if (copy_from_user(&val, (char __user *)(unsigned long)reg->addr, size)) return -EFAULT; - r = kvmppc_set_one_reg(vcpu, reg->id, &val); - + r = vcpu->kvm->arch.kvm_ops->set_one_reg(vcpu, reg->id, &val); if (r == -EINVAL) { r = 0; switch (reg->id) { @@ -605,6 +674,13 @@ int kvm_vcpu_ioctl_set_one_reg(struct kvm_vcpu *vcpu, struct kvm_one_reg *reg) } vcpu->arch.vscr.u[3] = set_reg_val(reg->id, val); break; + case KVM_REG_PPC_VRSAVE: + if (!cpu_has_feature(CPU_FTR_ALTIVEC)) { + r = -ENXIO; + break; + } + vcpu->arch.vrsave = set_reg_val(reg->id, val); + break; #endif /* CONFIG_ALTIVEC */ #ifdef CONFIG_KVM_XICS case KVM_REG_PPC_ICP_STATE: @@ -625,6 +701,27 @@ int kvm_vcpu_ioctl_set_one_reg(struct kvm_vcpu *vcpu, struct kvm_one_reg *reg) return r; } +void kvmppc_core_vcpu_load(struct kvm_vcpu *vcpu, int cpu) +{ + vcpu->kvm->arch.kvm_ops->vcpu_load(vcpu, cpu); +} + +void kvmppc_core_vcpu_put(struct kvm_vcpu *vcpu) +{ + vcpu->kvm->arch.kvm_ops->vcpu_put(vcpu); +} + +void kvmppc_set_msr(struct kvm_vcpu *vcpu, u64 msr) +{ + vcpu->kvm->arch.kvm_ops->set_msr(vcpu, msr); +} +EXPORT_SYMBOL_GPL(kvmppc_set_msr); + +int kvmppc_vcpu_run(struct kvm_run *kvm_run, struct kvm_vcpu *vcpu) +{ + return vcpu->kvm->arch.kvm_ops->vcpu_run(kvm_run, vcpu); +} + int kvm_arch_vcpu_ioctl_translate(struct kvm_vcpu *vcpu, struct kvm_translation *tr) { @@ -644,3 +741,141 @@ void kvmppc_decrementer_func(unsigned long data) kvmppc_core_queue_dec(vcpu); kvm_vcpu_kick(vcpu); } + +struct kvm_vcpu *kvmppc_core_vcpu_create(struct kvm *kvm, unsigned int id) +{ + return kvm->arch.kvm_ops->vcpu_create(kvm, id); +} + +void kvmppc_core_vcpu_free(struct kvm_vcpu *vcpu) +{ + vcpu->kvm->arch.kvm_ops->vcpu_free(vcpu); +} + +int kvmppc_core_check_requests(struct kvm_vcpu *vcpu) +{ + return vcpu->kvm->arch.kvm_ops->check_requests(vcpu); +} + +int kvm_vm_ioctl_get_dirty_log(struct kvm *kvm, struct kvm_dirty_log *log) +{ + return kvm->arch.kvm_ops->get_dirty_log(kvm, log); +} + +void kvmppc_core_free_memslot(struct kvm *kvm, struct kvm_memory_slot *free, + struct kvm_memory_slot *dont) +{ + kvm->arch.kvm_ops->free_memslot(free, dont); +} + +int kvmppc_core_create_memslot(struct kvm *kvm, struct kvm_memory_slot *slot, + unsigned long npages) +{ + return kvm->arch.kvm_ops->create_memslot(slot, npages); +} + +void kvmppc_core_flush_memslot(struct kvm *kvm, struct kvm_memory_slot *memslot) +{ + kvm->arch.kvm_ops->flush_memslot(kvm, memslot); +} + +int kvmppc_core_prepare_memory_region(struct kvm *kvm, + struct kvm_memory_slot *memslot, + struct kvm_userspace_memory_region *mem) +{ + return kvm->arch.kvm_ops->prepare_memory_region(kvm, memslot, mem); +} + +void kvmppc_core_commit_memory_region(struct kvm *kvm, + struct kvm_userspace_memory_region *mem, + const struct kvm_memory_slot *old) +{ + kvm->arch.kvm_ops->commit_memory_region(kvm, mem, old); +} + +int kvm_unmap_hva(struct kvm *kvm, unsigned long hva) +{ + return kvm->arch.kvm_ops->unmap_hva(kvm, hva); +} +EXPORT_SYMBOL_GPL(kvm_unmap_hva); + +int kvm_unmap_hva_range(struct kvm *kvm, unsigned long start, unsigned long end) +{ + return kvm->arch.kvm_ops->unmap_hva_range(kvm, start, end); +} + +int kvm_age_hva(struct kvm *kvm, unsigned long hva) +{ + return kvm->arch.kvm_ops->age_hva(kvm, hva); +} + +int kvm_test_age_hva(struct kvm *kvm, unsigned long hva) +{ + return kvm->arch.kvm_ops->test_age_hva(kvm, hva); +} + +void kvm_set_spte_hva(struct kvm *kvm, unsigned long hva, pte_t pte) +{ + kvm->arch.kvm_ops->set_spte_hva(kvm, hva, pte); +} + +void kvmppc_mmu_destroy(struct kvm_vcpu *vcpu) +{ + vcpu->kvm->arch.kvm_ops->mmu_destroy(vcpu); +} + +int kvmppc_core_init_vm(struct kvm *kvm) +{ + +#ifdef CONFIG_PPC64 + INIT_LIST_HEAD(&kvm->arch.spapr_tce_tables); + INIT_LIST_HEAD(&kvm->arch.rtas_tokens); +#endif + + return kvm->arch.kvm_ops->init_vm(kvm); +} + +void kvmppc_core_destroy_vm(struct kvm *kvm) +{ + kvm->arch.kvm_ops->destroy_vm(kvm); + +#ifdef CONFIG_PPC64 + kvmppc_rtas_tokens_free(kvm); + WARN_ON(!list_empty(&kvm->arch.spapr_tce_tables)); +#endif +} + +int kvmppc_core_check_processor_compat(void) +{ + /* + * We always return 0 for book3s. We check + * for compatability while loading the HV + * or PR module + */ + return 0; +} + +static int kvmppc_book3s_init(void) +{ + int r; + + r = kvm_init(NULL, sizeof(struct kvm_vcpu), 0, THIS_MODULE); + if (r) + return r; +#ifdef CONFIG_KVM_BOOK3S_32 + r = kvmppc_book3s_init_pr(); +#endif + return r; + +} + +static void kvmppc_book3s_exit(void) +{ +#ifdef CONFIG_KVM_BOOK3S_32 + kvmppc_book3s_exit_pr(); +#endif + kvm_exit(); +} + +module_init(kvmppc_book3s_init); +module_exit(kvmppc_book3s_exit); diff --git a/arch/powerpc/kvm/book3s.h b/arch/powerpc/kvm/book3s.h new file mode 100644 index 000000000000..4bf956cf94d6 --- /dev/null +++ b/arch/powerpc/kvm/book3s.h @@ -0,0 +1,34 @@ +/* + * Copyright IBM Corporation, 2013 + * Author Aneesh Kumar K.V <aneesh.kumar@linux.vnet.ibm.com> + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public License as + * published by the Free Software Foundation; either version 2 of the + * License or (at your optional) any later version of the license. + * + */ + +#ifndef __POWERPC_KVM_BOOK3S_H__ +#define __POWERPC_KVM_BOOK3S_H__ + +extern void kvmppc_core_flush_memslot_hv(struct kvm *kvm, + struct kvm_memory_slot *memslot); +extern int kvm_unmap_hva_hv(struct kvm *kvm, unsigned long hva); +extern int kvm_unmap_hva_range_hv(struct kvm *kvm, unsigned long start, + unsigned long end); +extern int kvm_age_hva_hv(struct kvm *kvm, unsigned long hva); +extern int kvm_test_age_hva_hv(struct kvm *kvm, unsigned long hva); +extern void kvm_set_spte_hva_hv(struct kvm *kvm, unsigned long hva, pte_t pte); + +extern void kvmppc_mmu_destroy_pr(struct kvm_vcpu *vcpu); +extern int kvmppc_core_emulate_op_pr(struct kvm_run *run, struct kvm_vcpu *vcpu, + unsigned int inst, int *advance); +extern int kvmppc_core_emulate_mtspr_pr(struct kvm_vcpu *vcpu, + int sprn, ulong spr_val); +extern int kvmppc_core_emulate_mfspr_pr(struct kvm_vcpu *vcpu, + int sprn, ulong *spr_val); +extern int kvmppc_book3s_init_pr(void); +extern void kvmppc_book3s_exit_pr(void); + +#endif diff --git a/arch/powerpc/kvm/book3s_32_mmu.c b/arch/powerpc/kvm/book3s_32_mmu.c index c8cefdd15fd8..76a64ce6a5b6 100644 --- a/arch/powerpc/kvm/book3s_32_mmu.c +++ b/arch/powerpc/kvm/book3s_32_mmu.c @@ -84,7 +84,8 @@ static inline bool sr_nx(u32 sr_raw) } static int kvmppc_mmu_book3s_32_xlate_bat(struct kvm_vcpu *vcpu, gva_t eaddr, - struct kvmppc_pte *pte, bool data); + struct kvmppc_pte *pte, bool data, + bool iswrite); static int kvmppc_mmu_book3s_32_esid_to_vsid(struct kvm_vcpu *vcpu, ulong esid, u64 *vsid); @@ -99,7 +100,7 @@ static u64 kvmppc_mmu_book3s_32_ea_to_vp(struct kvm_vcpu *vcpu, gva_t eaddr, u64 vsid; struct kvmppc_pte pte; - if (!kvmppc_mmu_book3s_32_xlate_bat(vcpu, eaddr, &pte, data)) + if (!kvmppc_mmu_book3s_32_xlate_bat(vcpu, eaddr, &pte, data, false)) return pte.vpage; kvmppc_mmu_book3s_32_esid_to_vsid(vcpu, eaddr >> SID_SHIFT, &vsid); @@ -111,10 +112,11 @@ static void kvmppc_mmu_book3s_32_reset_msr(struct kvm_vcpu *vcpu) kvmppc_set_msr(vcpu, 0); } -static hva_t kvmppc_mmu_book3s_32_get_pteg(struct kvmppc_vcpu_book3s *vcpu_book3s, +static hva_t kvmppc_mmu_book3s_32_get_pteg(struct kvm_vcpu *vcpu, u32 sre, gva_t eaddr, bool primary) { + struct kvmppc_vcpu_book3s *vcpu_book3s = to_book3s(vcpu); u32 page, hash, pteg, htabmask; hva_t r; @@ -132,7 +134,7 @@ static hva_t kvmppc_mmu_book3s_32_get_pteg(struct kvmppc_vcpu_book3s *vcpu_book3 kvmppc_get_pc(&vcpu_book3s->vcpu), eaddr, vcpu_book3s->sdr1, pteg, sr_vsid(sre)); - r = gfn_to_hva(vcpu_book3s->vcpu.kvm, pteg >> PAGE_SHIFT); + r = gfn_to_hva(vcpu->kvm, pteg >> PAGE_SHIFT); if (kvm_is_error_hva(r)) return r; return r | (pteg & ~PAGE_MASK); @@ -145,7 +147,8 @@ static u32 kvmppc_mmu_book3s_32_get_ptem(u32 sre, gva_t eaddr, bool primary) } static int kvmppc_mmu_book3s_32_xlate_bat(struct kvm_vcpu *vcpu, gva_t eaddr, - struct kvmppc_pte *pte, bool data) + struct kvmppc_pte *pte, bool data, + bool iswrite) { struct kvmppc_vcpu_book3s *vcpu_book3s = to_book3s(vcpu); struct kvmppc_bat *bat; @@ -186,8 +189,7 @@ static int kvmppc_mmu_book3s_32_xlate_bat(struct kvm_vcpu *vcpu, gva_t eaddr, printk(KERN_INFO "BAT is not readable!\n"); continue; } - if (!pte->may_write) { - /* let's treat r/o BATs as not-readable for now */ + if (iswrite && !pte->may_write) { dprintk_pte("BAT is read-only!\n"); continue; } @@ -201,9 +203,8 @@ static int kvmppc_mmu_book3s_32_xlate_bat(struct kvm_vcpu *vcpu, gva_t eaddr, static int kvmppc_mmu_book3s_32_xlate_pte(struct kvm_vcpu *vcpu, gva_t eaddr, struct kvmppc_pte *pte, bool data, - bool primary) + bool iswrite, bool primary) { - struct kvmppc_vcpu_book3s *vcpu_book3s = to_book3s(vcpu); u32 sre; hva_t ptegp; u32 pteg[16]; @@ -218,7 +219,7 @@ static int kvmppc_mmu_book3s_32_xlate_pte(struct kvm_vcpu *vcpu, gva_t eaddr, pte->vpage = kvmppc_mmu_book3s_32_ea_to_vp(vcpu, eaddr, data); - ptegp = kvmppc_mmu_book3s_32_get_pteg(vcpu_book3s, sre, eaddr, primary); + ptegp = kvmppc_mmu_book3s_32_get_pteg(vcpu, sre, eaddr, primary); if (kvm_is_error_hva(ptegp)) { printk(KERN_INFO "KVM: Invalid PTEG!\n"); goto no_page_found; @@ -258,9 +259,6 @@ static int kvmppc_mmu_book3s_32_xlate_pte(struct kvm_vcpu *vcpu, gva_t eaddr, break; } - if ( !pte->may_read ) - continue; - dprintk_pte("MMU: Found PTE -> %x %x - %x\n", pteg[i], pteg[i+1], pp); found = 1; @@ -271,19 +269,23 @@ static int kvmppc_mmu_book3s_32_xlate_pte(struct kvm_vcpu *vcpu, gva_t eaddr, /* Update PTE C and A bits, so the guest's swapper knows we used the page */ if (found) { - u32 oldpte = pteg[i+1]; - - if (pte->may_read) - pteg[i+1] |= PTEG_FLAG_ACCESSED; - if (pte->may_write) - pteg[i+1] |= PTEG_FLAG_DIRTY; - else - dprintk_pte("KVM: Mapping read-only page!\n"); - - /* Write back into the PTEG */ - if (pteg[i+1] != oldpte) - copy_to_user((void __user *)ptegp, pteg, sizeof(pteg)); - + u32 pte_r = pteg[i+1]; + char __user *addr = (char __user *) &pteg[i+1]; + + /* + * Use single-byte writes to update the HPTE, to + * conform to what real hardware does. + */ + if (pte->may_read && !(pte_r & PTEG_FLAG_ACCESSED)) { + pte_r |= PTEG_FLAG_ACCESSED; + put_user(pte_r >> 8, addr + 2); + } + if (iswrite && pte->may_write && !(pte_r & PTEG_FLAG_DIRTY)) { + pte_r |= PTEG_FLAG_DIRTY; + put_user(pte_r, addr + 3); + } + if (!pte->may_read || (iswrite && !pte->may_write)) + return -EPERM; return 0; } @@ -302,12 +304,14 @@ no_page_found: } static int kvmppc_mmu_book3s_32_xlate(struct kvm_vcpu *vcpu, gva_t eaddr, - struct kvmppc_pte *pte, bool data) + struct kvmppc_pte *pte, bool data, + bool iswrite) { int r; ulong mp_ea = vcpu->arch.magic_page_ea; pte->eaddr = eaddr; + pte->page_size = MMU_PAGE_4K; /* Magic page override */ if (unlikely(mp_ea) && @@ -323,11 +327,13 @@ static int kvmppc_mmu_book3s_32_xlate(struct kvm_vcpu *vcpu, gva_t eaddr, return 0; } - r = kvmppc_mmu_book3s_32_xlate_bat(vcpu, eaddr, pte, data); + r = kvmppc_mmu_book3s_32_xlate_bat(vcpu, eaddr, pte, data, iswrite); if (r < 0) - r = kvmppc_mmu_book3s_32_xlate_pte(vcpu, eaddr, pte, data, true); + r = kvmppc_mmu_book3s_32_xlate_pte(vcpu, eaddr, pte, + data, iswrite, true); if (r < 0) - r = kvmppc_mmu_book3s_32_xlate_pte(vcpu, eaddr, pte, data, false); + r = kvmppc_mmu_book3s_32_xlate_pte(vcpu, eaddr, pte, + data, iswrite, false); return r; } @@ -347,7 +353,12 @@ static void kvmppc_mmu_book3s_32_mtsrin(struct kvm_vcpu *vcpu, u32 srnum, static void kvmppc_mmu_book3s_32_tlbie(struct kvm_vcpu *vcpu, ulong ea, bool large) { - kvmppc_mmu_pte_flush(vcpu, ea, 0x0FFFF000); + int i; + struct kvm_vcpu *v; + + /* flush this VA on all cpus */ + kvm_for_each_vcpu(i, v, vcpu->kvm) + kvmppc_mmu_pte_flush(v, ea, 0x0FFFF000); } static int kvmppc_mmu_book3s_32_esid_to_vsid(struct kvm_vcpu *vcpu, ulong esid, diff --git a/arch/powerpc/kvm/book3s_32_mmu_host.c b/arch/powerpc/kvm/book3s_32_mmu_host.c index 00e619bf608e..3a0abd2e5a15 100644 --- a/arch/powerpc/kvm/book3s_32_mmu_host.c +++ b/arch/powerpc/kvm/book3s_32_mmu_host.c @@ -138,7 +138,8 @@ static u32 *kvmppc_mmu_get_pteg(struct kvm_vcpu *vcpu, u32 vsid, u32 eaddr, extern char etext[]; -int kvmppc_mmu_map_page(struct kvm_vcpu *vcpu, struct kvmppc_pte *orig_pte) +int kvmppc_mmu_map_page(struct kvm_vcpu *vcpu, struct kvmppc_pte *orig_pte, + bool iswrite) { pfn_t hpaddr; u64 vpn; @@ -152,9 +153,11 @@ int kvmppc_mmu_map_page(struct kvm_vcpu *vcpu, struct kvmppc_pte *orig_pte) bool evict = false; struct hpte_cache *pte; int r = 0; + bool writable; /* Get host physical address for gpa */ - hpaddr = kvmppc_gfn_to_pfn(vcpu, orig_pte->raddr >> PAGE_SHIFT); + hpaddr = kvmppc_gfn_to_pfn(vcpu, orig_pte->raddr >> PAGE_SHIFT, + iswrite, &writable); if (is_error_noslot_pfn(hpaddr)) { printk(KERN_INFO "Couldn't get guest page for gfn %lx!\n", orig_pte->eaddr); @@ -204,7 +207,7 @@ next_pteg: (primary ? 0 : PTE_SEC); pteg1 = hpaddr | PTE_M | PTE_R | PTE_C; - if (orig_pte->may_write) { + if (orig_pte->may_write && writable) { pteg1 |= PP_RWRW; mark_page_dirty(vcpu->kvm, orig_pte->raddr >> PAGE_SHIFT); } else { @@ -259,6 +262,11 @@ out: return r; } +void kvmppc_mmu_unmap_page(struct kvm_vcpu *vcpu, struct kvmppc_pte *pte) +{ + kvmppc_mmu_pte_vflush(vcpu, pte->vpage, 0xfffffffffULL); +} + static struct kvmppc_sid_map *create_sid_map(struct kvm_vcpu *vcpu, u64 gvsid) { struct kvmppc_sid_map *map; @@ -341,7 +349,7 @@ void kvmppc_mmu_flush_segments(struct kvm_vcpu *vcpu) svcpu_put(svcpu); } -void kvmppc_mmu_destroy(struct kvm_vcpu *vcpu) +void kvmppc_mmu_destroy_pr(struct kvm_vcpu *vcpu) { int i; diff --git a/arch/powerpc/kvm/book3s_64_mmu.c b/arch/powerpc/kvm/book3s_64_mmu.c index 7e345e00661a..83da1f868fd5 100644 --- a/arch/powerpc/kvm/book3s_64_mmu.c +++ b/arch/powerpc/kvm/book3s_64_mmu.c @@ -107,9 +107,20 @@ static u64 kvmppc_mmu_book3s_64_ea_to_vp(struct kvm_vcpu *vcpu, gva_t eaddr, return kvmppc_slb_calc_vpn(slb, eaddr); } +static int mmu_pagesize(int mmu_pg) +{ + switch (mmu_pg) { + case MMU_PAGE_64K: + return 16; + case MMU_PAGE_16M: + return 24; + } + return 12; +} + static int kvmppc_mmu_book3s_64_get_pagesize(struct kvmppc_slb *slbe) { - return slbe->large ? 24 : 12; + return mmu_pagesize(slbe->base_page_size); } static u32 kvmppc_mmu_book3s_64_get_page(struct kvmppc_slb *slbe, gva_t eaddr) @@ -119,11 +130,11 @@ static u32 kvmppc_mmu_book3s_64_get_page(struct kvmppc_slb *slbe, gva_t eaddr) return ((eaddr & kvmppc_slb_offset_mask(slbe)) >> p); } -static hva_t kvmppc_mmu_book3s_64_get_pteg( - struct kvmppc_vcpu_book3s *vcpu_book3s, +static hva_t kvmppc_mmu_book3s_64_get_pteg(struct kvm_vcpu *vcpu, struct kvmppc_slb *slbe, gva_t eaddr, bool second) { + struct kvmppc_vcpu_book3s *vcpu_book3s = to_book3s(vcpu); u64 hash, pteg, htabsize; u32 ssize; hva_t r; @@ -148,10 +159,10 @@ static hva_t kvmppc_mmu_book3s_64_get_pteg( /* When running a PAPR guest, SDR1 contains a HVA address instead of a GPA */ - if (vcpu_book3s->vcpu.arch.papr_enabled) + if (vcpu->arch.papr_enabled) r = pteg; else - r = gfn_to_hva(vcpu_book3s->vcpu.kvm, pteg >> PAGE_SHIFT); + r = gfn_to_hva(vcpu->kvm, pteg >> PAGE_SHIFT); if (kvm_is_error_hva(r)) return r; @@ -166,18 +177,38 @@ static u64 kvmppc_mmu_book3s_64_get_avpn(struct kvmppc_slb *slbe, gva_t eaddr) avpn = kvmppc_mmu_book3s_64_get_page(slbe, eaddr); avpn |= slbe->vsid << (kvmppc_slb_sid_shift(slbe) - p); - if (p < 24) - avpn >>= ((80 - p) - 56) - 8; + if (p < 16) + avpn >>= ((80 - p) - 56) - 8; /* 16 - p */ else - avpn <<= 8; + avpn <<= p - 16; return avpn; } +/* + * Return page size encoded in the second word of a HPTE, or + * -1 for an invalid encoding for the base page size indicated by + * the SLB entry. This doesn't handle mixed pagesize segments yet. + */ +static int decode_pagesize(struct kvmppc_slb *slbe, u64 r) +{ + switch (slbe->base_page_size) { + case MMU_PAGE_64K: + if ((r & 0xf000) == 0x1000) + return MMU_PAGE_64K; + break; + case MMU_PAGE_16M: + if ((r & 0xff000) == 0) + return MMU_PAGE_16M; + break; + } + return -1; +} + static int kvmppc_mmu_book3s_64_xlate(struct kvm_vcpu *vcpu, gva_t eaddr, - struct kvmppc_pte *gpte, bool data) + struct kvmppc_pte *gpte, bool data, + bool iswrite) { - struct kvmppc_vcpu_book3s *vcpu_book3s = to_book3s(vcpu); struct kvmppc_slb *slbe; hva_t ptegp; u64 pteg[16]; @@ -189,6 +220,7 @@ static int kvmppc_mmu_book3s_64_xlate(struct kvm_vcpu *vcpu, gva_t eaddr, u8 pp, key = 0; bool found = false; bool second = false; + int pgsize; ulong mp_ea = vcpu->arch.magic_page_ea; /* Magic page override */ @@ -202,6 +234,7 @@ static int kvmppc_mmu_book3s_64_xlate(struct kvm_vcpu *vcpu, gva_t eaddr, gpte->may_execute = true; gpte->may_read = true; gpte->may_write = true; + gpte->page_size = MMU_PAGE_4K; return 0; } @@ -222,8 +255,12 @@ static int kvmppc_mmu_book3s_64_xlate(struct kvm_vcpu *vcpu, gva_t eaddr, v_mask = SLB_VSID_B | HPTE_V_AVPN | HPTE_V_LARGE | HPTE_V_VALID | HPTE_V_SECONDARY; + pgsize = slbe->large ? MMU_PAGE_16M : MMU_PAGE_4K; + + mutex_lock(&vcpu->kvm->arch.hpt_mutex); + do_second: - ptegp = kvmppc_mmu_book3s_64_get_pteg(vcpu_book3s, slbe, eaddr, second); + ptegp = kvmppc_mmu_book3s_64_get_pteg(vcpu, slbe, eaddr, second); if (kvm_is_error_hva(ptegp)) goto no_page_found; @@ -240,6 +277,13 @@ do_second: for (i=0; i<16; i+=2) { /* Check all relevant fields of 1st dword */ if ((pteg[i] & v_mask) == v_val) { + /* If large page bit is set, check pgsize encoding */ + if (slbe->large && + (vcpu->arch.hflags & BOOK3S_HFLAG_MULTI_PGSIZE)) { + pgsize = decode_pagesize(slbe, pteg[i+1]); + if (pgsize < 0) + continue; + } found = true; break; } @@ -256,13 +300,15 @@ do_second: v = pteg[i]; r = pteg[i+1]; pp = (r & HPTE_R_PP) | key; - eaddr_mask = 0xFFF; + if (r & HPTE_R_PP0) + pp |= 8; gpte->eaddr = eaddr; gpte->vpage = kvmppc_mmu_book3s_64_ea_to_vp(vcpu, eaddr, data); - if (slbe->large) - eaddr_mask = 0xFFFFFF; + + eaddr_mask = (1ull << mmu_pagesize(pgsize)) - 1; gpte->raddr = (r & HPTE_R_RPN & ~eaddr_mask) | (eaddr & eaddr_mask); + gpte->page_size = pgsize; gpte->may_execute = ((r & HPTE_R_N) ? false : true); gpte->may_read = false; gpte->may_write = false; @@ -277,6 +323,7 @@ do_second: case 3: case 5: case 7: + case 10: gpte->may_read = true; break; } @@ -287,30 +334,37 @@ do_second: /* Update PTE R and C bits, so the guest's swapper knows we used the * page */ - if (gpte->may_read) { - /* Set the accessed flag */ + if (gpte->may_read && !(r & HPTE_R_R)) { + /* + * Set the accessed flag. + * We have to write this back with a single byte write + * because another vcpu may be accessing this on + * non-PAPR platforms such as mac99, and this is + * what real hardware does. + */ + char __user *addr = (char __user *) &pteg[i+1]; r |= HPTE_R_R; + put_user(r >> 8, addr + 6); } - if (data && gpte->may_write) { - /* Set the dirty flag -- XXX even if not writing */ + if (iswrite && gpte->may_write && !(r & HPTE_R_C)) { + /* Set the dirty flag */ + /* Use a single byte write */ + char __user *addr = (char __user *) &pteg[i+1]; r |= HPTE_R_C; + put_user(r, addr + 7); } - /* Write back into the PTEG */ - if (pteg[i+1] != r) { - pteg[i+1] = r; - copy_to_user((void __user *)ptegp, pteg, sizeof(pteg)); - } + mutex_unlock(&vcpu->kvm->arch.hpt_mutex); - if (!gpte->may_read) + if (!gpte->may_read || (iswrite && !gpte->may_write)) return -EPERM; return 0; no_page_found: + mutex_unlock(&vcpu->kvm->arch.hpt_mutex); return -ENOENT; no_seg_found: - dprintk("KVM MMU: Trigger segment fault\n"); return -EINVAL; } @@ -345,6 +399,21 @@ static void kvmppc_mmu_book3s_64_slbmte(struct kvm_vcpu *vcpu, u64 rs, u64 rb) slbe->nx = (rs & SLB_VSID_N) ? 1 : 0; slbe->class = (rs & SLB_VSID_C) ? 1 : 0; + slbe->base_page_size = MMU_PAGE_4K; + if (slbe->large) { + if (vcpu->arch.hflags & BOOK3S_HFLAG_MULTI_PGSIZE) { + switch (rs & SLB_VSID_LP) { + case SLB_VSID_LP_00: + slbe->base_page_size = MMU_PAGE_16M; + break; + case SLB_VSID_LP_01: + slbe->base_page_size = MMU_PAGE_64K; + break; + } + } else + slbe->base_page_size = MMU_PAGE_16M; + } + slbe->orige = rb & (ESID_MASK | SLB_ESID_V); slbe->origv = rs; @@ -460,14 +529,45 @@ static void kvmppc_mmu_book3s_64_tlbie(struct kvm_vcpu *vcpu, ulong va, bool large) { u64 mask = 0xFFFFFFFFFULL; + long i; + struct kvm_vcpu *v; dprintk("KVM MMU: tlbie(0x%lx)\n", va); - if (large) - mask = 0xFFFFFF000ULL; - kvmppc_mmu_pte_vflush(vcpu, va >> 12, mask); + /* + * The tlbie instruction changed behaviour starting with + * POWER6. POWER6 and later don't have the large page flag + * in the instruction but in the RB value, along with bits + * indicating page and segment sizes. + */ + if (vcpu->arch.hflags & BOOK3S_HFLAG_NEW_TLBIE) { + /* POWER6 or later */ + if (va & 1) { /* L bit */ + if ((va & 0xf000) == 0x1000) + mask = 0xFFFFFFFF0ULL; /* 64k page */ + else + mask = 0xFFFFFF000ULL; /* 16M page */ + } + } else { + /* older processors, e.g. PPC970 */ + if (large) + mask = 0xFFFFFF000ULL; + } + /* flush this VA on all vcpus */ + kvm_for_each_vcpu(i, v, vcpu->kvm) + kvmppc_mmu_pte_vflush(v, va >> 12, mask); } +#ifdef CONFIG_PPC_64K_PAGES +static int segment_contains_magic_page(struct kvm_vcpu *vcpu, ulong esid) +{ + ulong mp_ea = vcpu->arch.magic_page_ea; + + return mp_ea && !(vcpu->arch.shared->msr & MSR_PR) && + (mp_ea >> SID_SHIFT) == esid; +} +#endif + static int kvmppc_mmu_book3s_64_esid_to_vsid(struct kvm_vcpu *vcpu, ulong esid, u64 *vsid) { @@ -475,11 +575,13 @@ static int kvmppc_mmu_book3s_64_esid_to_vsid(struct kvm_vcpu *vcpu, ulong esid, struct kvmppc_slb *slb; u64 gvsid = esid; ulong mp_ea = vcpu->arch.magic_page_ea; + int pagesize = MMU_PAGE_64K; if (vcpu->arch.shared->msr & (MSR_DR|MSR_IR)) { slb = kvmppc_mmu_book3s_64_find_slbe(vcpu, ea); if (slb) { gvsid = slb->vsid; + pagesize = slb->base_page_size; if (slb->tb) { gvsid <<= SID_SHIFT_1T - SID_SHIFT; gvsid |= esid & ((1ul << (SID_SHIFT_1T - SID_SHIFT)) - 1); @@ -490,28 +592,41 @@ static int kvmppc_mmu_book3s_64_esid_to_vsid(struct kvm_vcpu *vcpu, ulong esid, switch (vcpu->arch.shared->msr & (MSR_DR|MSR_IR)) { case 0: - *vsid = VSID_REAL | esid; + gvsid = VSID_REAL | esid; break; case MSR_IR: - *vsid = VSID_REAL_IR | gvsid; + gvsid |= VSID_REAL_IR; break; case MSR_DR: - *vsid = VSID_REAL_DR | gvsid; + gvsid |= VSID_REAL_DR; break; case MSR_DR|MSR_IR: if (!slb) goto no_slb; - *vsid = gvsid; break; default: BUG(); break; } +#ifdef CONFIG_PPC_64K_PAGES + /* + * Mark this as a 64k segment if the host is using + * 64k pages, the host MMU supports 64k pages and + * the guest segment page size is >= 64k, + * but not if this segment contains the magic page. + */ + if (pagesize >= MMU_PAGE_64K && + mmu_psize_defs[MMU_PAGE_64K].shift && + !segment_contains_magic_page(vcpu, esid)) + gvsid |= VSID_64K; +#endif + if (vcpu->arch.shared->msr & MSR_PR) - *vsid |= VSID_PR; + gvsid |= VSID_PR; + *vsid = gvsid; return 0; no_slb: diff --git a/arch/powerpc/kvm/book3s_64_mmu_host.c b/arch/powerpc/kvm/book3s_64_mmu_host.c index e5240524bf6c..0d513af62bba 100644 --- a/arch/powerpc/kvm/book3s_64_mmu_host.c +++ b/arch/powerpc/kvm/book3s_64_mmu_host.c @@ -27,14 +27,14 @@ #include <asm/machdep.h> #include <asm/mmu_context.h> #include <asm/hw_irq.h> -#include "trace.h" +#include "trace_pr.h" #define PTE_SIZE 12 void kvmppc_mmu_invalidate_pte(struct kvm_vcpu *vcpu, struct hpte_cache *pte) { ppc_md.hpte_invalidate(pte->slot, pte->host_vpn, - MMU_PAGE_4K, MMU_PAGE_4K, MMU_SEGSIZE_256M, + pte->pagesize, pte->pagesize, MMU_SEGSIZE_256M, false); } @@ -78,7 +78,8 @@ static struct kvmppc_sid_map *find_sid_vsid(struct kvm_vcpu *vcpu, u64 gvsid) return NULL; } -int kvmppc_mmu_map_page(struct kvm_vcpu *vcpu, struct kvmppc_pte *orig_pte) +int kvmppc_mmu_map_page(struct kvm_vcpu *vcpu, struct kvmppc_pte *orig_pte, + bool iswrite) { unsigned long vpn; pfn_t hpaddr; @@ -90,16 +91,26 @@ int kvmppc_mmu_map_page(struct kvm_vcpu *vcpu, struct kvmppc_pte *orig_pte) int attempt = 0; struct kvmppc_sid_map *map; int r = 0; + int hpsize = MMU_PAGE_4K; + bool writable; + unsigned long mmu_seq; + struct kvm *kvm = vcpu->kvm; + struct hpte_cache *cpte; + unsigned long gfn = orig_pte->raddr >> PAGE_SHIFT; + unsigned long pfn; + + /* used to check for invalidations in progress */ + mmu_seq = kvm->mmu_notifier_seq; + smp_rmb(); /* Get host physical address for gpa */ - hpaddr = kvmppc_gfn_to_pfn(vcpu, orig_pte->raddr >> PAGE_SHIFT); - if (is_error_noslot_pfn(hpaddr)) { - printk(KERN_INFO "Couldn't get guest page for gfn %lx!\n", orig_pte->eaddr); + pfn = kvmppc_gfn_to_pfn(vcpu, gfn, iswrite, &writable); + if (is_error_noslot_pfn(pfn)) { + printk(KERN_INFO "Couldn't get guest page for gfn %lx!\n", gfn); r = -EINVAL; goto out; } - hpaddr <<= PAGE_SHIFT; - hpaddr |= orig_pte->raddr & (~0xfffULL & ~PAGE_MASK); + hpaddr = pfn << PAGE_SHIFT; /* and write the mapping ea -> hpa into the pt */ vcpu->arch.mmu.esid_to_vsid(vcpu, orig_pte->eaddr >> SID_SHIFT, &vsid); @@ -117,20 +128,39 @@ int kvmppc_mmu_map_page(struct kvm_vcpu *vcpu, struct kvmppc_pte *orig_pte) goto out; } - vsid = map->host_vsid; - vpn = hpt_vpn(orig_pte->eaddr, vsid, MMU_SEGSIZE_256M); + vpn = hpt_vpn(orig_pte->eaddr, map->host_vsid, MMU_SEGSIZE_256M); - if (!orig_pte->may_write) - rflags |= HPTE_R_PP; - else - mark_page_dirty(vcpu->kvm, orig_pte->raddr >> PAGE_SHIFT); + kvm_set_pfn_accessed(pfn); + if (!orig_pte->may_write || !writable) + rflags |= PP_RXRX; + else { + mark_page_dirty(vcpu->kvm, gfn); + kvm_set_pfn_dirty(pfn); + } if (!orig_pte->may_execute) rflags |= HPTE_R_N; else - kvmppc_mmu_flush_icache(hpaddr >> PAGE_SHIFT); + kvmppc_mmu_flush_icache(pfn); + + /* + * Use 64K pages if possible; otherwise, on 64K page kernels, + * we need to transfer 4 more bits from guest real to host real addr. + */ + if (vsid & VSID_64K) + hpsize = MMU_PAGE_64K; + else + hpaddr |= orig_pte->raddr & (~0xfffULL & ~PAGE_MASK); + + hash = hpt_hash(vpn, mmu_psize_defs[hpsize].shift, MMU_SEGSIZE_256M); - hash = hpt_hash(vpn, PTE_SIZE, MMU_SEGSIZE_256M); + cpte = kvmppc_mmu_hpte_cache_next(vcpu); + + spin_lock(&kvm->mmu_lock); + if (!cpte || mmu_notifier_retry(kvm, mmu_seq)) { + r = -EAGAIN; + goto out_unlock; + } map_again: hpteg = ((hash & htab_hash_mask) * HPTES_PER_GROUP); @@ -139,11 +169,11 @@ map_again: if (attempt > 1) if (ppc_md.hpte_remove(hpteg) < 0) { r = -1; - goto out; + goto out_unlock; } ret = ppc_md.hpte_insert(hpteg, vpn, hpaddr, rflags, vflags, - MMU_PAGE_4K, MMU_PAGE_4K, MMU_SEGSIZE_256M); + hpsize, hpsize, MMU_SEGSIZE_256M); if (ret < 0) { /* If we couldn't map a primary PTE, try a secondary */ @@ -152,8 +182,6 @@ map_again: attempt++; goto map_again; } else { - struct hpte_cache *pte = kvmppc_mmu_hpte_cache_next(vcpu); - trace_kvm_book3s_64_mmu_map(rflags, hpteg, vpn, hpaddr, orig_pte); @@ -164,19 +192,37 @@ map_again: hpteg = ((hash & htab_hash_mask) * HPTES_PER_GROUP); } - pte->slot = hpteg + (ret & 7); - pte->host_vpn = vpn; - pte->pte = *orig_pte; - pte->pfn = hpaddr >> PAGE_SHIFT; + cpte->slot = hpteg + (ret & 7); + cpte->host_vpn = vpn; + cpte->pte = *orig_pte; + cpte->pfn = pfn; + cpte->pagesize = hpsize; - kvmppc_mmu_hpte_cache_map(vcpu, pte); + kvmppc_mmu_hpte_cache_map(vcpu, cpte); + cpte = NULL; } - kvm_release_pfn_clean(hpaddr >> PAGE_SHIFT); + +out_unlock: + spin_unlock(&kvm->mmu_lock); + kvm_release_pfn_clean(pfn); + if (cpte) + kvmppc_mmu_hpte_cache_free(cpte); out: return r; } +void kvmppc_mmu_unmap_page(struct kvm_vcpu *vcpu, struct kvmppc_pte *pte) +{ + u64 mask = 0xfffffffffULL; + u64 vsid; + + vcpu->arch.mmu.esid_to_vsid(vcpu, pte->eaddr >> SID_SHIFT, &vsid); + if (vsid & VSID_64K) + mask = 0xffffffff0ULL; + kvmppc_mmu_pte_vflush(vcpu, pte->vpage, mask); +} + static struct kvmppc_sid_map *create_sid_map(struct kvm_vcpu *vcpu, u64 gvsid) { struct kvmppc_sid_map *map; @@ -291,6 +337,12 @@ int kvmppc_mmu_map_segment(struct kvm_vcpu *vcpu, ulong eaddr) slb_vsid &= ~SLB_VSID_KP; slb_esid |= slb_index; +#ifdef CONFIG_PPC_64K_PAGES + /* Set host segment base page size to 64K if possible */ + if (gvsid & VSID_64K) + slb_vsid |= mmu_psize_defs[MMU_PAGE_64K].sllp; +#endif + svcpu->slb[slb_index].esid = slb_esid; svcpu->slb[slb_index].vsid = slb_vsid; @@ -326,7 +378,7 @@ void kvmppc_mmu_flush_segments(struct kvm_vcpu *vcpu) svcpu_put(svcpu); } -void kvmppc_mmu_destroy(struct kvm_vcpu *vcpu) +void kvmppc_mmu_destroy_pr(struct kvm_vcpu *vcpu) { kvmppc_mmu_hpte_destroy(vcpu); __destroy_context(to_book3s(vcpu)->context_id[0]); diff --git a/arch/powerpc/kvm/book3s_64_mmu_hv.c b/arch/powerpc/kvm/book3s_64_mmu_hv.c index 043eec8461e7..f3ff587a8b7d 100644 --- a/arch/powerpc/kvm/book3s_64_mmu_hv.c +++ b/arch/powerpc/kvm/book3s_64_mmu_hv.c @@ -260,10 +260,6 @@ int kvmppc_mmu_hv_init(void) return 0; } -void kvmppc_mmu_destroy(struct kvm_vcpu *vcpu) -{ -} - static void kvmppc_mmu_book3s_64_hv_reset_msr(struct kvm_vcpu *vcpu) { kvmppc_set_msr(vcpu, MSR_SF | MSR_ME); @@ -451,7 +447,7 @@ static unsigned long kvmppc_mmu_get_real_addr(unsigned long v, unsigned long r, } static int kvmppc_mmu_book3s_64_hv_xlate(struct kvm_vcpu *vcpu, gva_t eaddr, - struct kvmppc_pte *gpte, bool data) + struct kvmppc_pte *gpte, bool data, bool iswrite) { struct kvm *kvm = vcpu->kvm; struct kvmppc_slb *slbe; @@ -906,21 +902,22 @@ static int kvm_unmap_rmapp(struct kvm *kvm, unsigned long *rmapp, return 0; } -int kvm_unmap_hva(struct kvm *kvm, unsigned long hva) +int kvm_unmap_hva_hv(struct kvm *kvm, unsigned long hva) { if (kvm->arch.using_mmu_notifiers) kvm_handle_hva(kvm, hva, kvm_unmap_rmapp); return 0; } -int kvm_unmap_hva_range(struct kvm *kvm, unsigned long start, unsigned long end) +int kvm_unmap_hva_range_hv(struct kvm *kvm, unsigned long start, unsigned long end) { if (kvm->arch.using_mmu_notifiers) kvm_handle_hva_range(kvm, start, end, kvm_unmap_rmapp); return 0; } -void kvmppc_core_flush_memslot(struct kvm *kvm, struct kvm_memory_slot *memslot) +void kvmppc_core_flush_memslot_hv(struct kvm *kvm, + struct kvm_memory_slot *memslot) { unsigned long *rmapp; unsigned long gfn; @@ -994,7 +991,7 @@ static int kvm_age_rmapp(struct kvm *kvm, unsigned long *rmapp, return ret; } -int kvm_age_hva(struct kvm *kvm, unsigned long hva) +int kvm_age_hva_hv(struct kvm *kvm, unsigned long hva) { if (!kvm->arch.using_mmu_notifiers) return 0; @@ -1032,14 +1029,14 @@ static int kvm_test_age_rmapp(struct kvm *kvm, unsigned long *rmapp, return ret; } -int kvm_test_age_hva(struct kvm *kvm, unsigned long hva) +int kvm_test_age_hva_hv(struct kvm *kvm, unsigned long hva) { if (!kvm->arch.using_mmu_notifiers) return 0; return kvm_handle_hva(kvm, hva, kvm_test_age_rmapp); } -void kvm_set_spte_hva(struct kvm *kvm, unsigned long hva, pte_t pte) +void kvm_set_spte_hva_hv(struct kvm *kvm, unsigned long hva, pte_t pte) { if (!kvm->arch.using_mmu_notifiers) return; @@ -1512,9 +1509,8 @@ static ssize_t kvm_htab_write(struct file *file, const char __user *buf, kvm->arch.vrma_slb_v = senc | SLB_VSID_B_1T | (VRMA_VSID << SLB_VSID_SHIFT_1T); - lpcr = kvm->arch.lpcr & ~LPCR_VRMASD; - lpcr |= senc << (LPCR_VRMASD_SH - 4); - kvm->arch.lpcr = lpcr; + lpcr = senc << (LPCR_VRMASD_SH - 4); + kvmppc_update_lpcr(kvm, lpcr, LPCR_VRMASD); rma_setup = 1; } ++i; diff --git a/arch/powerpc/kvm/book3s_64_vio_hv.c b/arch/powerpc/kvm/book3s_64_vio_hv.c index 30c2f3b134c6..2c25f5412bdb 100644 --- a/arch/powerpc/kvm/book3s_64_vio_hv.c +++ b/arch/powerpc/kvm/book3s_64_vio_hv.c @@ -74,3 +74,4 @@ long kvmppc_h_put_tce(struct kvm_vcpu *vcpu, unsigned long liobn, /* Didn't find the liobn, punt it to userspace */ return H_TOO_HARD; } +EXPORT_SYMBOL_GPL(kvmppc_h_put_tce); diff --git a/arch/powerpc/kvm/book3s_emulate.c b/arch/powerpc/kvm/book3s_emulate.c index 360ce68c9809..99d40f8977e8 100644 --- a/arch/powerpc/kvm/book3s_emulate.c +++ b/arch/powerpc/kvm/book3s_emulate.c @@ -86,8 +86,8 @@ static bool spr_allowed(struct kvm_vcpu *vcpu, enum priv_level level) return true; } -int kvmppc_core_emulate_op(struct kvm_run *run, struct kvm_vcpu *vcpu, - unsigned int inst, int *advance) +int kvmppc_core_emulate_op_pr(struct kvm_run *run, struct kvm_vcpu *vcpu, + unsigned int inst, int *advance) { int emulated = EMULATE_DONE; int rt = get_rt(inst); @@ -172,7 +172,7 @@ int kvmppc_core_emulate_op(struct kvm_run *run, struct kvm_vcpu *vcpu, vcpu->arch.mmu.tlbie(vcpu, addr, large); break; } -#ifdef CONFIG_KVM_BOOK3S_64_PR +#ifdef CONFIG_PPC_BOOK3S_64 case OP_31_XOP_FAKE_SC1: { /* SC 1 papr hypercalls */ @@ -267,12 +267,9 @@ int kvmppc_core_emulate_op(struct kvm_run *run, struct kvm_vcpu *vcpu, r = kvmppc_st(vcpu, &addr, 32, zeros, true); if ((r == -ENOENT) || (r == -EPERM)) { - struct kvmppc_book3s_shadow_vcpu *svcpu; - - svcpu = svcpu_get(vcpu); *advance = 0; vcpu->arch.shared->dar = vaddr; - svcpu->fault_dar = vaddr; + vcpu->arch.fault_dar = vaddr; dsisr = DSISR_ISSTORE; if (r == -ENOENT) @@ -281,8 +278,7 @@ int kvmppc_core_emulate_op(struct kvm_run *run, struct kvm_vcpu *vcpu, dsisr |= DSISR_PROTFAULT; vcpu->arch.shared->dsisr = dsisr; - svcpu->fault_dsisr = dsisr; - svcpu_put(svcpu); + vcpu->arch.fault_dsisr = dsisr; kvmppc_book3s_queue_irqprio(vcpu, BOOK3S_INTERRUPT_DATA_STORAGE); @@ -349,7 +345,7 @@ static struct kvmppc_bat *kvmppc_find_bat(struct kvm_vcpu *vcpu, int sprn) return bat; } -int kvmppc_core_emulate_mtspr(struct kvm_vcpu *vcpu, int sprn, ulong spr_val) +int kvmppc_core_emulate_mtspr_pr(struct kvm_vcpu *vcpu, int sprn, ulong spr_val) { int emulated = EMULATE_DONE; @@ -472,7 +468,7 @@ unprivileged: return emulated; } -int kvmppc_core_emulate_mfspr(struct kvm_vcpu *vcpu, int sprn, ulong *spr_val) +int kvmppc_core_emulate_mfspr_pr(struct kvm_vcpu *vcpu, int sprn, ulong *spr_val) { int emulated = EMULATE_DONE; diff --git a/arch/powerpc/kvm/book3s_exports.c b/arch/powerpc/kvm/book3s_exports.c index 7057a02f0906..852989a9bad3 100644 --- a/arch/powerpc/kvm/book3s_exports.c +++ b/arch/powerpc/kvm/book3s_exports.c @@ -20,9 +20,10 @@ #include <linux/export.h> #include <asm/kvm_book3s.h> -#ifdef CONFIG_KVM_BOOK3S_64_HV +#ifdef CONFIG_KVM_BOOK3S_HV_POSSIBLE EXPORT_SYMBOL_GPL(kvmppc_hv_entry_trampoline); -#else +#endif +#ifdef CONFIG_KVM_BOOK3S_PR_POSSIBLE EXPORT_SYMBOL_GPL(kvmppc_entry_trampoline); EXPORT_SYMBOL_GPL(kvmppc_load_up_fpu); #ifdef CONFIG_ALTIVEC diff --git a/arch/powerpc/kvm/book3s_hv.c b/arch/powerpc/kvm/book3s_hv.c index 62a2b5ab08ed..072287f1c3bc 100644 --- a/arch/powerpc/kvm/book3s_hv.c +++ b/arch/powerpc/kvm/book3s_hv.c @@ -52,6 +52,9 @@ #include <linux/vmalloc.h> #include <linux/highmem.h> #include <linux/hugetlb.h> +#include <linux/module.h> + +#include "book3s.h" /* #define EXIT_DEBUG */ /* #define EXIT_DEBUG_SIMPLE */ @@ -66,7 +69,7 @@ static void kvmppc_end_cede(struct kvm_vcpu *vcpu); static int kvmppc_hv_setup_htab_rma(struct kvm_vcpu *vcpu); -void kvmppc_fast_vcpu_kick(struct kvm_vcpu *vcpu) +static void kvmppc_fast_vcpu_kick_hv(struct kvm_vcpu *vcpu) { int me; int cpu = vcpu->cpu; @@ -125,7 +128,7 @@ void kvmppc_fast_vcpu_kick(struct kvm_vcpu *vcpu) * purely defensive; they should never fail.) */ -void kvmppc_core_vcpu_load(struct kvm_vcpu *vcpu, int cpu) +static void kvmppc_core_vcpu_load_hv(struct kvm_vcpu *vcpu, int cpu) { struct kvmppc_vcore *vc = vcpu->arch.vcore; @@ -143,7 +146,7 @@ void kvmppc_core_vcpu_load(struct kvm_vcpu *vcpu, int cpu) spin_unlock(&vcpu->arch.tbacct_lock); } -void kvmppc_core_vcpu_put(struct kvm_vcpu *vcpu) +static void kvmppc_core_vcpu_put_hv(struct kvm_vcpu *vcpu) { struct kvmppc_vcore *vc = vcpu->arch.vcore; @@ -155,17 +158,46 @@ void kvmppc_core_vcpu_put(struct kvm_vcpu *vcpu) spin_unlock(&vcpu->arch.tbacct_lock); } -void kvmppc_set_msr(struct kvm_vcpu *vcpu, u64 msr) +static void kvmppc_set_msr_hv(struct kvm_vcpu *vcpu, u64 msr) { vcpu->arch.shregs.msr = msr; kvmppc_end_cede(vcpu); } -void kvmppc_set_pvr(struct kvm_vcpu *vcpu, u32 pvr) +void kvmppc_set_pvr_hv(struct kvm_vcpu *vcpu, u32 pvr) { vcpu->arch.pvr = pvr; } +int kvmppc_set_arch_compat(struct kvm_vcpu *vcpu, u32 arch_compat) +{ + unsigned long pcr = 0; + struct kvmppc_vcore *vc = vcpu->arch.vcore; + + if (arch_compat) { + if (!cpu_has_feature(CPU_FTR_ARCH_206)) + return -EINVAL; /* 970 has no compat mode support */ + + switch (arch_compat) { + case PVR_ARCH_205: + pcr = PCR_ARCH_205; + break; + case PVR_ARCH_206: + case PVR_ARCH_206p: + break; + default: + return -EINVAL; + } + } + + spin_lock(&vc->lock); + vc->arch_compat = arch_compat; + vc->pcr = pcr; + spin_unlock(&vc->lock); + + return 0; +} + void kvmppc_dump_regs(struct kvm_vcpu *vcpu) { int r; @@ -195,7 +227,7 @@ void kvmppc_dump_regs(struct kvm_vcpu *vcpu) pr_err(" ESID = %.16llx VSID = %.16llx\n", vcpu->arch.slb[r].orige, vcpu->arch.slb[r].origv); pr_err("lpcr = %.16lx sdr1 = %.16lx last_inst = %.8x\n", - vcpu->kvm->arch.lpcr, vcpu->kvm->arch.sdr1, + vcpu->arch.vcore->lpcr, vcpu->kvm->arch.sdr1, vcpu->arch.last_inst); } @@ -489,7 +521,7 @@ static void kvmppc_create_dtl_entry(struct kvm_vcpu *vcpu, memset(dt, 0, sizeof(struct dtl_entry)); dt->dispatch_reason = 7; dt->processor_id = vc->pcpu + vcpu->arch.ptid; - dt->timebase = now; + dt->timebase = now + vc->tb_offset; dt->enqueue_to_dispatch_time = stolen; dt->srr0 = kvmppc_get_pc(vcpu); dt->srr1 = vcpu->arch.shregs.msr; @@ -538,6 +570,15 @@ int kvmppc_pseries_do_hcall(struct kvm_vcpu *vcpu) } break; case H_CONFER: + target = kvmppc_get_gpr(vcpu, 4); + if (target == -1) + break; + tvcpu = kvmppc_find_vcpu(vcpu->kvm, target); + if (!tvcpu) { + ret = H_PARAMETER; + break; + } + kvm_vcpu_yield_to(tvcpu); break; case H_REGISTER_VPA: ret = do_h_register_vpa(vcpu, kvmppc_get_gpr(vcpu, 4), @@ -576,8 +617,8 @@ int kvmppc_pseries_do_hcall(struct kvm_vcpu *vcpu) return RESUME_GUEST; } -static int kvmppc_handle_exit(struct kvm_run *run, struct kvm_vcpu *vcpu, - struct task_struct *tsk) +static int kvmppc_handle_exit_hv(struct kvm_run *run, struct kvm_vcpu *vcpu, + struct task_struct *tsk) { int r = RESUME_HOST; @@ -671,16 +712,16 @@ static int kvmppc_handle_exit(struct kvm_run *run, struct kvm_vcpu *vcpu, printk(KERN_EMERG "trap=0x%x | pc=0x%lx | msr=0x%llx\n", vcpu->arch.trap, kvmppc_get_pc(vcpu), vcpu->arch.shregs.msr); + run->hw.hardware_exit_reason = vcpu->arch.trap; r = RESUME_HOST; - BUG(); break; } return r; } -int kvm_arch_vcpu_ioctl_get_sregs(struct kvm_vcpu *vcpu, - struct kvm_sregs *sregs) +static int kvm_arch_vcpu_ioctl_get_sregs_hv(struct kvm_vcpu *vcpu, + struct kvm_sregs *sregs) { int i; @@ -694,12 +735,12 @@ int kvm_arch_vcpu_ioctl_get_sregs(struct kvm_vcpu *vcpu, return 0; } -int kvm_arch_vcpu_ioctl_set_sregs(struct kvm_vcpu *vcpu, - struct kvm_sregs *sregs) +static int kvm_arch_vcpu_ioctl_set_sregs_hv(struct kvm_vcpu *vcpu, + struct kvm_sregs *sregs) { int i, j; - kvmppc_set_pvr(vcpu, sregs->pvr); + kvmppc_set_pvr_hv(vcpu, sregs->pvr); j = 0; for (i = 0; i < vcpu->arch.slb_nr; i++) { @@ -714,7 +755,23 @@ int kvm_arch_vcpu_ioctl_set_sregs(struct kvm_vcpu *vcpu, return 0; } -int kvmppc_get_one_reg(struct kvm_vcpu *vcpu, u64 id, union kvmppc_one_reg *val) +static void kvmppc_set_lpcr(struct kvm_vcpu *vcpu, u64 new_lpcr) +{ + struct kvmppc_vcore *vc = vcpu->arch.vcore; + u64 mask; + + spin_lock(&vc->lock); + /* + * Userspace can only modify DPFD (default prefetch depth), + * ILE (interrupt little-endian) and TC (translation control). + */ + mask = LPCR_DPFD | LPCR_ILE | LPCR_TC; + vc->lpcr = (vc->lpcr & ~mask) | (new_lpcr & mask); + spin_unlock(&vc->lock); +} + +static int kvmppc_get_one_reg_hv(struct kvm_vcpu *vcpu, u64 id, + union kvmppc_one_reg *val) { int r = 0; long int i; @@ -749,6 +806,12 @@ int kvmppc_get_one_reg(struct kvm_vcpu *vcpu, u64 id, union kvmppc_one_reg *val) i = id - KVM_REG_PPC_PMC1; *val = get_reg_val(id, vcpu->arch.pmc[i]); break; + case KVM_REG_PPC_SIAR: + *val = get_reg_val(id, vcpu->arch.siar); + break; + case KVM_REG_PPC_SDAR: + *val = get_reg_val(id, vcpu->arch.sdar); + break; #ifdef CONFIG_VSX case KVM_REG_PPC_FPR0 ... KVM_REG_PPC_FPR31: if (cpu_has_feature(CPU_FTR_VSX)) { @@ -787,6 +850,18 @@ int kvmppc_get_one_reg(struct kvm_vcpu *vcpu, u64 id, union kvmppc_one_reg *val) val->vpaval.length = vcpu->arch.dtl.len; spin_unlock(&vcpu->arch.vpa_update_lock); break; + case KVM_REG_PPC_TB_OFFSET: + *val = get_reg_val(id, vcpu->arch.vcore->tb_offset); + break; + case KVM_REG_PPC_LPCR: + *val = get_reg_val(id, vcpu->arch.vcore->lpcr); + break; + case KVM_REG_PPC_PPR: + *val = get_reg_val(id, vcpu->arch.ppr); + break; + case KVM_REG_PPC_ARCH_COMPAT: + *val = get_reg_val(id, vcpu->arch.vcore->arch_compat); + break; default: r = -EINVAL; break; @@ -795,7 +870,8 @@ int kvmppc_get_one_reg(struct kvm_vcpu *vcpu, u64 id, union kvmppc_one_reg *val) return r; } -int kvmppc_set_one_reg(struct kvm_vcpu *vcpu, u64 id, union kvmppc_one_reg *val) +static int kvmppc_set_one_reg_hv(struct kvm_vcpu *vcpu, u64 id, + union kvmppc_one_reg *val) { int r = 0; long int i; @@ -833,6 +909,12 @@ int kvmppc_set_one_reg(struct kvm_vcpu *vcpu, u64 id, union kvmppc_one_reg *val) i = id - KVM_REG_PPC_PMC1; vcpu->arch.pmc[i] = set_reg_val(id, *val); break; + case KVM_REG_PPC_SIAR: + vcpu->arch.siar = set_reg_val(id, *val); + break; + case KVM_REG_PPC_SDAR: + vcpu->arch.sdar = set_reg_val(id, *val); + break; #ifdef CONFIG_VSX case KVM_REG_PPC_FPR0 ... KVM_REG_PPC_FPR31: if (cpu_has_feature(CPU_FTR_VSX)) { @@ -880,6 +962,20 @@ int kvmppc_set_one_reg(struct kvm_vcpu *vcpu, u64 id, union kvmppc_one_reg *val) len -= len % sizeof(struct dtl_entry); r = set_vpa(vcpu, &vcpu->arch.dtl, addr, len); break; + case KVM_REG_PPC_TB_OFFSET: + /* round up to multiple of 2^24 */ + vcpu->arch.vcore->tb_offset = + ALIGN(set_reg_val(id, *val), 1UL << 24); + break; + case KVM_REG_PPC_LPCR: + kvmppc_set_lpcr(vcpu, set_reg_val(id, *val)); + break; + case KVM_REG_PPC_PPR: + vcpu->arch.ppr = set_reg_val(id, *val); + break; + case KVM_REG_PPC_ARCH_COMPAT: + r = kvmppc_set_arch_compat(vcpu, set_reg_val(id, *val)); + break; default: r = -EINVAL; break; @@ -888,14 +984,8 @@ int kvmppc_set_one_reg(struct kvm_vcpu *vcpu, u64 id, union kvmppc_one_reg *val) return r; } -int kvmppc_core_check_processor_compat(void) -{ - if (cpu_has_feature(CPU_FTR_HVMODE)) - return 0; - return -EIO; -} - -struct kvm_vcpu *kvmppc_core_vcpu_create(struct kvm *kvm, unsigned int id) +static struct kvm_vcpu *kvmppc_core_vcpu_create_hv(struct kvm *kvm, + unsigned int id) { struct kvm_vcpu *vcpu; int err = -EINVAL; @@ -919,8 +1009,7 @@ struct kvm_vcpu *kvmppc_core_vcpu_create(struct kvm *kvm, unsigned int id) vcpu->arch.mmcr[0] = MMCR0_FC; vcpu->arch.ctrl = CTRL_RUNLATCH; /* default to host PVR, since we can't spoof it */ - vcpu->arch.pvr = mfspr(SPRN_PVR); - kvmppc_set_pvr(vcpu, vcpu->arch.pvr); + kvmppc_set_pvr_hv(vcpu, mfspr(SPRN_PVR)); spin_lock_init(&vcpu->arch.vpa_update_lock); spin_lock_init(&vcpu->arch.tbacct_lock); vcpu->arch.busy_preempt = TB_NIL; @@ -940,6 +1029,7 @@ struct kvm_vcpu *kvmppc_core_vcpu_create(struct kvm *kvm, unsigned int id) spin_lock_init(&vcore->lock); init_waitqueue_head(&vcore->wq); vcore->preempt_tb = TB_NIL; + vcore->lpcr = kvm->arch.lpcr; } kvm->arch.vcores[core] = vcore; kvm->arch.online_vcores++; @@ -972,7 +1062,7 @@ static void unpin_vpa(struct kvm *kvm, struct kvmppc_vpa *vpa) vpa->dirty); } -void kvmppc_core_vcpu_free(struct kvm_vcpu *vcpu) +static void kvmppc_core_vcpu_free_hv(struct kvm_vcpu *vcpu) { spin_lock(&vcpu->arch.vpa_update_lock); unpin_vpa(vcpu->kvm, &vcpu->arch.dtl); @@ -983,6 +1073,12 @@ void kvmppc_core_vcpu_free(struct kvm_vcpu *vcpu) kmem_cache_free(kvm_vcpu_cache, vcpu); } +static int kvmppc_core_check_requests_hv(struct kvm_vcpu *vcpu) +{ + /* Indicate we want to get back into the guest */ + return 1; +} + static void kvmppc_set_timer(struct kvm_vcpu *vcpu) { unsigned long dec_nsec, now; @@ -1264,8 +1360,8 @@ static void kvmppc_run_core(struct kvmppc_vcore *vc) ret = RESUME_GUEST; if (vcpu->arch.trap) - ret = kvmppc_handle_exit(vcpu->arch.kvm_run, vcpu, - vcpu->arch.run_task); + ret = kvmppc_handle_exit_hv(vcpu->arch.kvm_run, vcpu, + vcpu->arch.run_task); vcpu->arch.ret = ret; vcpu->arch.trap = 0; @@ -1424,7 +1520,7 @@ static int kvmppc_run_vcpu(struct kvm_run *kvm_run, struct kvm_vcpu *vcpu) return vcpu->arch.ret; } -int kvmppc_vcpu_run(struct kvm_run *run, struct kvm_vcpu *vcpu) +static int kvmppc_vcpu_run_hv(struct kvm_run *run, struct kvm_vcpu *vcpu) { int r; int srcu_idx; @@ -1546,7 +1642,8 @@ static const struct file_operations kvm_rma_fops = { .release = kvm_rma_release, }; -long kvm_vm_ioctl_allocate_rma(struct kvm *kvm, struct kvm_allocate_rma *ret) +static long kvm_vm_ioctl_allocate_rma(struct kvm *kvm, + struct kvm_allocate_rma *ret) { long fd; struct kvm_rma_info *ri; @@ -1592,7 +1689,8 @@ static void kvmppc_add_seg_page_size(struct kvm_ppc_one_seg_page_size **sps, (*sps)++; } -int kvm_vm_ioctl_get_smmu_info(struct kvm *kvm, struct kvm_ppc_smmu_info *info) +static int kvm_vm_ioctl_get_smmu_info_hv(struct kvm *kvm, + struct kvm_ppc_smmu_info *info) { struct kvm_ppc_one_seg_page_size *sps; @@ -1613,7 +1711,8 @@ int kvm_vm_ioctl_get_smmu_info(struct kvm *kvm, struct kvm_ppc_smmu_info *info) /* * Get (and clear) the dirty memory log for a memory slot. */ -int kvm_vm_ioctl_get_dirty_log(struct kvm *kvm, struct kvm_dirty_log *log) +static int kvm_vm_ioctl_get_dirty_log_hv(struct kvm *kvm, + struct kvm_dirty_log *log) { struct kvm_memory_slot *memslot; int r; @@ -1667,8 +1766,8 @@ static void unpin_slot(struct kvm_memory_slot *memslot) } } -void kvmppc_core_free_memslot(struct kvm_memory_slot *free, - struct kvm_memory_slot *dont) +static void kvmppc_core_free_memslot_hv(struct kvm_memory_slot *free, + struct kvm_memory_slot *dont) { if (!dont || free->arch.rmap != dont->arch.rmap) { vfree(free->arch.rmap); @@ -1681,8 +1780,8 @@ void kvmppc_core_free_memslot(struct kvm_memory_slot *free, } } -int kvmppc_core_create_memslot(struct kvm_memory_slot *slot, - unsigned long npages) +static int kvmppc_core_create_memslot_hv(struct kvm_memory_slot *slot, + unsigned long npages) { slot->arch.rmap = vzalloc(npages * sizeof(*slot->arch.rmap)); if (!slot->arch.rmap) @@ -1692,9 +1791,9 @@ int kvmppc_core_create_memslot(struct kvm_memory_slot *slot, return 0; } -int kvmppc_core_prepare_memory_region(struct kvm *kvm, - struct kvm_memory_slot *memslot, - struct kvm_userspace_memory_region *mem) +static int kvmppc_core_prepare_memory_region_hv(struct kvm *kvm, + struct kvm_memory_slot *memslot, + struct kvm_userspace_memory_region *mem) { unsigned long *phys; @@ -1710,9 +1809,9 @@ int kvmppc_core_prepare_memory_region(struct kvm *kvm, return 0; } -void kvmppc_core_commit_memory_region(struct kvm *kvm, - struct kvm_userspace_memory_region *mem, - const struct kvm_memory_slot *old) +static void kvmppc_core_commit_memory_region_hv(struct kvm *kvm, + struct kvm_userspace_memory_region *mem, + const struct kvm_memory_slot *old) { unsigned long npages = mem->memory_size >> PAGE_SHIFT; struct kvm_memory_slot *memslot; @@ -1729,6 +1828,37 @@ void kvmppc_core_commit_memory_region(struct kvm *kvm, } } +/* + * Update LPCR values in kvm->arch and in vcores. + * Caller must hold kvm->lock. + */ +void kvmppc_update_lpcr(struct kvm *kvm, unsigned long lpcr, unsigned long mask) +{ + long int i; + u32 cores_done = 0; + + if ((kvm->arch.lpcr & mask) == lpcr) + return; + + kvm->arch.lpcr = (kvm->arch.lpcr & ~mask) | lpcr; + + for (i = 0; i < KVM_MAX_VCORES; ++i) { + struct kvmppc_vcore *vc = kvm->arch.vcores[i]; + if (!vc) + continue; + spin_lock(&vc->lock); + vc->lpcr = (vc->lpcr & ~mask) | lpcr; + spin_unlock(&vc->lock); + if (++cores_done >= kvm->arch.online_vcores) + break; + } +} + +static void kvmppc_mmu_destroy_hv(struct kvm_vcpu *vcpu) +{ + return; +} + static int kvmppc_hv_setup_htab_rma(struct kvm_vcpu *vcpu) { int err = 0; @@ -1737,7 +1867,8 @@ static int kvmppc_hv_setup_htab_rma(struct kvm_vcpu *vcpu) unsigned long hva; struct kvm_memory_slot *memslot; struct vm_area_struct *vma; - unsigned long lpcr, senc; + unsigned long lpcr = 0, senc; + unsigned long lpcr_mask = 0; unsigned long psize, porder; unsigned long rma_size; unsigned long rmls; @@ -1802,9 +1933,9 @@ static int kvmppc_hv_setup_htab_rma(struct kvm_vcpu *vcpu) senc = slb_pgsize_encoding(psize); kvm->arch.vrma_slb_v = senc | SLB_VSID_B_1T | (VRMA_VSID << SLB_VSID_SHIFT_1T); - lpcr = kvm->arch.lpcr & ~LPCR_VRMASD; - lpcr |= senc << (LPCR_VRMASD_SH - 4); - kvm->arch.lpcr = lpcr; + lpcr_mask = LPCR_VRMASD; + /* the -4 is to account for senc values starting at 0x10 */ + lpcr = senc << (LPCR_VRMASD_SH - 4); /* Create HPTEs in the hash page table for the VRMA */ kvmppc_map_vrma(vcpu, memslot, porder); @@ -1825,23 +1956,21 @@ static int kvmppc_hv_setup_htab_rma(struct kvm_vcpu *vcpu) kvm->arch.rma = ri; /* Update LPCR and RMOR */ - lpcr = kvm->arch.lpcr; if (cpu_has_feature(CPU_FTR_ARCH_201)) { /* PPC970; insert RMLS value (split field) in HID4 */ - lpcr &= ~((1ul << HID4_RMLS0_SH) | - (3ul << HID4_RMLS2_SH)); - lpcr |= ((rmls >> 2) << HID4_RMLS0_SH) | + lpcr_mask = (1ul << HID4_RMLS0_SH) | + (3ul << HID4_RMLS2_SH) | HID4_RMOR; + lpcr = ((rmls >> 2) << HID4_RMLS0_SH) | ((rmls & 3) << HID4_RMLS2_SH); /* RMOR is also in HID4 */ lpcr |= ((ri->base_pfn >> (26 - PAGE_SHIFT)) & 0xffff) << HID4_RMOR_SH; } else { /* POWER7 */ - lpcr &= ~(LPCR_VPM0 | LPCR_VRMA_L); - lpcr |= rmls << LPCR_RMLS_SH; + lpcr_mask = LPCR_VPM0 | LPCR_VRMA_L | LPCR_RMLS; + lpcr = rmls << LPCR_RMLS_SH; kvm->arch.rmor = ri->base_pfn << PAGE_SHIFT; } - kvm->arch.lpcr = lpcr; pr_info("KVM: Using RMO at %lx size %lx (LPCR = %lx)\n", ri->base_pfn << PAGE_SHIFT, rma_size, lpcr); @@ -1860,6 +1989,8 @@ static int kvmppc_hv_setup_htab_rma(struct kvm_vcpu *vcpu) } } + kvmppc_update_lpcr(kvm, lpcr, lpcr_mask); + /* Order updates to kvm->arch.lpcr etc. vs. rma_setup_done */ smp_wmb(); kvm->arch.rma_setup_done = 1; @@ -1875,7 +2006,7 @@ static int kvmppc_hv_setup_htab_rma(struct kvm_vcpu *vcpu) goto out_srcu; } -int kvmppc_core_init_vm(struct kvm *kvm) +static int kvmppc_core_init_vm_hv(struct kvm *kvm) { unsigned long lpcr, lpid; @@ -1893,9 +2024,6 @@ int kvmppc_core_init_vm(struct kvm *kvm) */ cpumask_setall(&kvm->arch.need_tlb_flush); - INIT_LIST_HEAD(&kvm->arch.spapr_tce_tables); - INIT_LIST_HEAD(&kvm->arch.rtas_tokens); - kvm->arch.rma = NULL; kvm->arch.host_sdr1 = mfspr(SPRN_SDR1); @@ -1931,61 +2059,162 @@ int kvmppc_core_init_vm(struct kvm *kvm) return 0; } -void kvmppc_core_destroy_vm(struct kvm *kvm) +static void kvmppc_free_vcores(struct kvm *kvm) +{ + long int i; + + for (i = 0; i < KVM_MAX_VCORES; ++i) + kfree(kvm->arch.vcores[i]); + kvm->arch.online_vcores = 0; +} + +static void kvmppc_core_destroy_vm_hv(struct kvm *kvm) { uninhibit_secondary_onlining(); + kvmppc_free_vcores(kvm); if (kvm->arch.rma) { kvm_release_rma(kvm->arch.rma); kvm->arch.rma = NULL; } - kvmppc_rtas_tokens_free(kvm); - kvmppc_free_hpt(kvm); - WARN_ON(!list_empty(&kvm->arch.spapr_tce_tables)); } -/* These are stubs for now */ -void kvmppc_mmu_pte_pflush(struct kvm_vcpu *vcpu, ulong pa_start, ulong pa_end) +/* We don't need to emulate any privileged instructions or dcbz */ +static int kvmppc_core_emulate_op_hv(struct kvm_run *run, struct kvm_vcpu *vcpu, + unsigned int inst, int *advance) { + return EMULATE_FAIL; } -/* We don't need to emulate any privileged instructions or dcbz */ -int kvmppc_core_emulate_op(struct kvm_run *run, struct kvm_vcpu *vcpu, - unsigned int inst, int *advance) +static int kvmppc_core_emulate_mtspr_hv(struct kvm_vcpu *vcpu, int sprn, + ulong spr_val) { return EMULATE_FAIL; } -int kvmppc_core_emulate_mtspr(struct kvm_vcpu *vcpu, int sprn, ulong spr_val) +static int kvmppc_core_emulate_mfspr_hv(struct kvm_vcpu *vcpu, int sprn, + ulong *spr_val) { return EMULATE_FAIL; } -int kvmppc_core_emulate_mfspr(struct kvm_vcpu *vcpu, int sprn, ulong *spr_val) +static int kvmppc_core_check_processor_compat_hv(void) { - return EMULATE_FAIL; + if (!cpu_has_feature(CPU_FTR_HVMODE)) + return -EIO; + return 0; } -static int kvmppc_book3s_hv_init(void) +static long kvm_arch_vm_ioctl_hv(struct file *filp, + unsigned int ioctl, unsigned long arg) { - int r; + struct kvm *kvm __maybe_unused = filp->private_data; + void __user *argp = (void __user *)arg; + long r; - r = kvm_init(NULL, sizeof(struct kvm_vcpu), 0, THIS_MODULE); + switch (ioctl) { - if (r) + case KVM_ALLOCATE_RMA: { + struct kvm_allocate_rma rma; + struct kvm *kvm = filp->private_data; + + r = kvm_vm_ioctl_allocate_rma(kvm, &rma); + if (r >= 0 && copy_to_user(argp, &rma, sizeof(rma))) + r = -EFAULT; + break; + } + + case KVM_PPC_ALLOCATE_HTAB: { + u32 htab_order; + + r = -EFAULT; + if (get_user(htab_order, (u32 __user *)argp)) + break; + r = kvmppc_alloc_reset_hpt(kvm, &htab_order); + if (r) + break; + r = -EFAULT; + if (put_user(htab_order, (u32 __user *)argp)) + break; + r = 0; + break; + } + + case KVM_PPC_GET_HTAB_FD: { + struct kvm_get_htab_fd ghf; + + r = -EFAULT; + if (copy_from_user(&ghf, argp, sizeof(ghf))) + break; + r = kvm_vm_ioctl_get_htab_fd(kvm, &ghf); + break; + } + + default: + r = -ENOTTY; + } + + return r; +} + +static struct kvmppc_ops kvm_ops_hv = { + .get_sregs = kvm_arch_vcpu_ioctl_get_sregs_hv, + .set_sregs = kvm_arch_vcpu_ioctl_set_sregs_hv, + .get_one_reg = kvmppc_get_one_reg_hv, + .set_one_reg = kvmppc_set_one_reg_hv, + .vcpu_load = kvmppc_core_vcpu_load_hv, + .vcpu_put = kvmppc_core_vcpu_put_hv, + .set_msr = kvmppc_set_msr_hv, + .vcpu_run = kvmppc_vcpu_run_hv, + .vcpu_create = kvmppc_core_vcpu_create_hv, + .vcpu_free = kvmppc_core_vcpu_free_hv, + .check_requests = kvmppc_core_check_requests_hv, + .get_dirty_log = kvm_vm_ioctl_get_dirty_log_hv, + .flush_memslot = kvmppc_core_flush_memslot_hv, + .prepare_memory_region = kvmppc_core_prepare_memory_region_hv, + .commit_memory_region = kvmppc_core_commit_memory_region_hv, + .unmap_hva = kvm_unmap_hva_hv, + .unmap_hva_range = kvm_unmap_hva_range_hv, + .age_hva = kvm_age_hva_hv, + .test_age_hva = kvm_test_age_hva_hv, + .set_spte_hva = kvm_set_spte_hva_hv, + .mmu_destroy = kvmppc_mmu_destroy_hv, + .free_memslot = kvmppc_core_free_memslot_hv, + .create_memslot = kvmppc_core_create_memslot_hv, + .init_vm = kvmppc_core_init_vm_hv, + .destroy_vm = kvmppc_core_destroy_vm_hv, + .get_smmu_info = kvm_vm_ioctl_get_smmu_info_hv, + .emulate_op = kvmppc_core_emulate_op_hv, + .emulate_mtspr = kvmppc_core_emulate_mtspr_hv, + .emulate_mfspr = kvmppc_core_emulate_mfspr_hv, + .fast_vcpu_kick = kvmppc_fast_vcpu_kick_hv, + .arch_vm_ioctl = kvm_arch_vm_ioctl_hv, +}; + +static int kvmppc_book3s_init_hv(void) +{ + int r; + /* + * FIXME!! Do we need to check on all cpus ? + */ + r = kvmppc_core_check_processor_compat_hv(); + if (r < 0) return r; - r = kvmppc_mmu_hv_init(); + kvm_ops_hv.owner = THIS_MODULE; + kvmppc_hv_ops = &kvm_ops_hv; + r = kvmppc_mmu_hv_init(); return r; } -static void kvmppc_book3s_hv_exit(void) +static void kvmppc_book3s_exit_hv(void) { - kvm_exit(); + kvmppc_hv_ops = NULL; } -module_init(kvmppc_book3s_hv_init); -module_exit(kvmppc_book3s_hv_exit); +module_init(kvmppc_book3s_init_hv); +module_exit(kvmppc_book3s_exit_hv); +MODULE_LICENSE("GPL"); diff --git a/arch/powerpc/kvm/book3s_hv_interrupts.S b/arch/powerpc/kvm/book3s_hv_interrupts.S index 37f1cc417ca0..928142c64cb0 100644 --- a/arch/powerpc/kvm/book3s_hv_interrupts.S +++ b/arch/powerpc/kvm/book3s_hv_interrupts.S @@ -158,9 +158,6 @@ END_FTR_SECTION_IFSET(CPU_FTR_ARCH_201) * Interrupts are enabled again at this point. */ -.global kvmppc_handler_highmem -kvmppc_handler_highmem: - /* * Register usage at this point: * diff --git a/arch/powerpc/kvm/book3s_hv_rmhandlers.S b/arch/powerpc/kvm/book3s_hv_rmhandlers.S index c71103b8a748..bc8de75b1925 100644 --- a/arch/powerpc/kvm/book3s_hv_rmhandlers.S +++ b/arch/powerpc/kvm/book3s_hv_rmhandlers.S @@ -33,30 +33,6 @@ #error Need to fix lppaca and SLB shadow accesses in little endian mode #endif -/***************************************************************************** - * * - * Real Mode handlers that need to be in the linear mapping * - * * - ****************************************************************************/ - - .globl kvmppc_skip_interrupt -kvmppc_skip_interrupt: - mfspr r13,SPRN_SRR0 - addi r13,r13,4 - mtspr SPRN_SRR0,r13 - GET_SCRATCH0(r13) - rfid - b . - - .globl kvmppc_skip_Hinterrupt -kvmppc_skip_Hinterrupt: - mfspr r13,SPRN_HSRR0 - addi r13,r13,4 - mtspr SPRN_HSRR0,r13 - GET_SCRATCH0(r13) - hrfid - b . - /* * Call kvmppc_hv_entry in real mode. * Must be called with interrupts hard-disabled. @@ -66,8 +42,11 @@ kvmppc_skip_Hinterrupt: * LR = return address to continue at after eventually re-enabling MMU */ _GLOBAL(kvmppc_hv_entry_trampoline) + mflr r0 + std r0, PPC_LR_STKOFF(r1) + stdu r1, -112(r1) mfmsr r10 - LOAD_REG_ADDR(r5, kvmppc_hv_entry) + LOAD_REG_ADDR(r5, kvmppc_call_hv_entry) li r0,MSR_RI andc r0,r10,r0 li r6,MSR_IR | MSR_DR @@ -77,11 +56,103 @@ _GLOBAL(kvmppc_hv_entry_trampoline) mtsrr1 r6 RFI -/****************************************************************************** - * * - * Entry code * - * * - *****************************************************************************/ +kvmppc_call_hv_entry: + bl kvmppc_hv_entry + + /* Back from guest - restore host state and return to caller */ + + /* Restore host DABR and DABRX */ + ld r5,HSTATE_DABR(r13) + li r6,7 + mtspr SPRN_DABR,r5 + mtspr SPRN_DABRX,r6 + + /* Restore SPRG3 */ + ld r3,PACA_SPRG3(r13) + mtspr SPRN_SPRG3,r3 + + /* + * Reload DEC. HDEC interrupts were disabled when + * we reloaded the host's LPCR value. + */ + ld r3, HSTATE_DECEXP(r13) + mftb r4 + subf r4, r4, r3 + mtspr SPRN_DEC, r4 + + /* Reload the host's PMU registers */ + ld r3, PACALPPACAPTR(r13) /* is the host using the PMU? */ + lbz r4, LPPACA_PMCINUSE(r3) + cmpwi r4, 0 + beq 23f /* skip if not */ + lwz r3, HSTATE_PMC(r13) + lwz r4, HSTATE_PMC + 4(r13) + lwz r5, HSTATE_PMC + 8(r13) + lwz r6, HSTATE_PMC + 12(r13) + lwz r8, HSTATE_PMC + 16(r13) + lwz r9, HSTATE_PMC + 20(r13) +BEGIN_FTR_SECTION + lwz r10, HSTATE_PMC + 24(r13) + lwz r11, HSTATE_PMC + 28(r13) +END_FTR_SECTION_IFSET(CPU_FTR_ARCH_201) + mtspr SPRN_PMC1, r3 + mtspr SPRN_PMC2, r4 + mtspr SPRN_PMC3, r5 + mtspr SPRN_PMC4, r6 + mtspr SPRN_PMC5, r8 + mtspr SPRN_PMC6, r9 +BEGIN_FTR_SECTION + mtspr SPRN_PMC7, r10 + mtspr SPRN_PMC8, r11 +END_FTR_SECTION_IFSET(CPU_FTR_ARCH_201) + ld r3, HSTATE_MMCR(r13) + ld r4, HSTATE_MMCR + 8(r13) + ld r5, HSTATE_MMCR + 16(r13) + mtspr SPRN_MMCR1, r4 + mtspr SPRN_MMCRA, r5 + mtspr SPRN_MMCR0, r3 + isync +23: + + /* + * For external and machine check interrupts, we need + * to call the Linux handler to process the interrupt. + * We do that by jumping to absolute address 0x500 for + * external interrupts, or the machine_check_fwnmi label + * for machine checks (since firmware might have patched + * the vector area at 0x200). The [h]rfid at the end of the + * handler will return to the book3s_hv_interrupts.S code. + * For other interrupts we do the rfid to get back + * to the book3s_hv_interrupts.S code here. + */ + ld r8, 112+PPC_LR_STKOFF(r1) + addi r1, r1, 112 + ld r7, HSTATE_HOST_MSR(r13) + + cmpwi cr1, r12, BOOK3S_INTERRUPT_MACHINE_CHECK + cmpwi r12, BOOK3S_INTERRUPT_EXTERNAL +BEGIN_FTR_SECTION + beq 11f +END_FTR_SECTION_IFSET(CPU_FTR_ARCH_206) + + /* RFI into the highmem handler, or branch to interrupt handler */ + mfmsr r6 + li r0, MSR_RI + andc r6, r6, r0 + mtmsrd r6, 1 /* Clear RI in MSR */ + mtsrr0 r8 + mtsrr1 r7 + beqa 0x500 /* external interrupt (PPC970) */ + beq cr1, 13f /* machine check */ + RFI + + /* On POWER7, we have external interrupts set to use HSRR0/1 */ +11: mtspr SPRN_HSRR0, r8 + mtspr SPRN_HSRR1, r7 + ba 0x500 + +13: b machine_check_fwnmi + /* * We come in here when wakened from nap mode on a secondary hw thread. @@ -137,7 +208,7 @@ kvm_start_guest: cmpdi r4,0 /* if we have no vcpu to run, go back to sleep */ beq kvm_no_guest - b kvmppc_hv_entry + b 30f 27: /* XXX should handle hypervisor maintenance interrupts etc. here */ b kvm_no_guest @@ -147,6 +218,57 @@ kvm_start_guest: stw r8,HSTATE_SAVED_XIRR(r13) b kvm_no_guest +30: bl kvmppc_hv_entry + + /* Back from the guest, go back to nap */ + /* Clear our vcpu pointer so we don't come back in early */ + li r0, 0 + std r0, HSTATE_KVM_VCPU(r13) + lwsync + /* Clear any pending IPI - we're an offline thread */ + ld r5, HSTATE_XICS_PHYS(r13) + li r7, XICS_XIRR + lwzcix r3, r5, r7 /* ack any pending interrupt */ + rlwinm. r0, r3, 0, 0xffffff /* any pending? */ + beq 37f + sync + li r0, 0xff + li r6, XICS_MFRR + stbcix r0, r5, r6 /* clear the IPI */ + stwcix r3, r5, r7 /* EOI it */ +37: sync + + /* increment the nap count and then go to nap mode */ + ld r4, HSTATE_KVM_VCORE(r13) + addi r4, r4, VCORE_NAP_COUNT + lwsync /* make previous updates visible */ +51: lwarx r3, 0, r4 + addi r3, r3, 1 + stwcx. r3, 0, r4 + bne 51b + +kvm_no_guest: + li r0, KVM_HWTHREAD_IN_NAP + stb r0, HSTATE_HWTHREAD_STATE(r13) + li r3, LPCR_PECE0 + mfspr r4, SPRN_LPCR + rlwimi r4, r3, 0, LPCR_PECE0 | LPCR_PECE1 + mtspr SPRN_LPCR, r4 + isync + std r0, HSTATE_SCRATCH0(r13) + ptesync + ld r0, HSTATE_SCRATCH0(r13) +1: cmpd r0, r0 + bne 1b + nap + b . + +/****************************************************************************** + * * + * Entry code * + * * + *****************************************************************************/ + .global kvmppc_hv_entry kvmppc_hv_entry: @@ -159,7 +281,8 @@ kvmppc_hv_entry: * all other volatile GPRS = free */ mflr r0 - std r0, HSTATE_VMHANDLER(r13) + std r0, PPC_LR_STKOFF(r1) + stdu r1, -112(r1) /* Set partition DABR */ /* Do this before re-enabling PMU to avoid P7 DABR corruption bug */ @@ -200,8 +323,12 @@ END_FTR_SECTION_IFSET(CPU_FTR_ARCH_201) ld r3, VCPU_MMCR(r4) ld r5, VCPU_MMCR + 8(r4) ld r6, VCPU_MMCR + 16(r4) + ld r7, VCPU_SIAR(r4) + ld r8, VCPU_SDAR(r4) mtspr SPRN_MMCR1, r5 mtspr SPRN_MMCRA, r6 + mtspr SPRN_SIAR, r7 + mtspr SPRN_SDAR, r8 mtspr SPRN_MMCR0, r3 isync @@ -254,22 +381,15 @@ END_FTR_SECTION_IFSET(CPU_FTR_ARCH_206) /* Save R1 in the PACA */ std r1, HSTATE_HOST_R1(r13) - /* Increment yield count if they have a VPA */ - ld r3, VCPU_VPA(r4) - cmpdi r3, 0 - beq 25f - lwz r5, LPPACA_YIELDCOUNT(r3) - addi r5, r5, 1 - stw r5, LPPACA_YIELDCOUNT(r3) - li r6, 1 - stb r6, VCPU_VPA_DIRTY(r4) -25: /* Load up DAR and DSISR */ ld r5, VCPU_DAR(r4) lwz r6, VCPU_DSISR(r4) mtspr SPRN_DAR, r5 mtspr SPRN_DSISR, r6 + li r6, KVM_GUEST_MODE_HOST_HV + stb r6, HSTATE_IN_GUEST(r13) + BEGIN_FTR_SECTION /* Restore AMR and UAMOR, set AMOR to all 1s */ ld r5,VCPU_AMR(r4) @@ -343,7 +463,28 @@ END_FTR_SECTION_IFSET(CPU_FTR_ARCH_201) bdnz 28b ptesync -22: li r0,1 + /* Add timebase offset onto timebase */ +22: ld r8,VCORE_TB_OFFSET(r5) + cmpdi r8,0 + beq 37f + mftb r6 /* current host timebase */ + add r8,r8,r6 + mtspr SPRN_TBU40,r8 /* update upper 40 bits */ + mftb r7 /* check if lower 24 bits overflowed */ + clrldi r6,r6,40 + clrldi r7,r7,40 + cmpld r7,r6 + bge 37f + addis r8,r8,0x100 /* if so, increment upper 40 bits */ + mtspr SPRN_TBU40,r8 + + /* Load guest PCR value to select appropriate compat mode */ +37: ld r7, VCORE_PCR(r5) + cmpdi r7, 0 + beq 38f + mtspr SPRN_PCR, r7 +38: + li r0,1 stb r0,VCORE_IN_GUEST(r5) /* signal secondaries to continue */ b 10f @@ -353,12 +494,22 @@ END_FTR_SECTION_IFSET(CPU_FTR_ARCH_201) beq 20b /* Set LPCR and RMOR. */ -10: ld r8,KVM_LPCR(r9) +10: ld r8,VCORE_LPCR(r5) mtspr SPRN_LPCR,r8 ld r8,KVM_RMOR(r9) mtspr SPRN_RMOR,r8 isync + /* Increment yield count if they have a VPA */ + ld r3, VCPU_VPA(r4) + cmpdi r3, 0 + beq 25f + lwz r5, LPPACA_YIELDCOUNT(r3) + addi r5, r5, 1 + stw r5, LPPACA_YIELDCOUNT(r3) + li r6, 1 + stb r6, VCPU_VPA_DIRTY(r4) +25: /* Check if HDEC expires soon */ mfspr r3,SPRN_HDEC cmpwi r3,10 @@ -405,7 +556,8 @@ toc_tlbie_lock: bne 24b isync - ld r7,KVM_LPCR(r9) /* use kvm->arch.lpcr to store HID4 */ + ld r5,HSTATE_KVM_VCORE(r13) + ld r7,VCORE_LPCR(r5) /* use vcore->lpcr to store HID4 */ li r0,0x18f rotldi r0,r0,HID4_LPID5_SH /* all lpid bits in HID4 = 1 */ or r0,r7,r0 @@ -541,7 +693,7 @@ fast_guest_return: mtspr SPRN_HSRR1,r11 /* Activate guest mode, so faults get handled by KVM */ - li r9, KVM_GUEST_MODE_GUEST + li r9, KVM_GUEST_MODE_GUEST_HV stb r9, HSTATE_IN_GUEST(r13) /* Enter guest */ @@ -550,13 +702,15 @@ BEGIN_FTR_SECTION ld r5, VCPU_CFAR(r4) mtspr SPRN_CFAR, r5 END_FTR_SECTION_IFSET(CPU_FTR_CFAR) +BEGIN_FTR_SECTION + ld r0, VCPU_PPR(r4) +END_FTR_SECTION_IFSET(CPU_FTR_HAS_PPR) ld r5, VCPU_LR(r4) lwz r6, VCPU_CR(r4) mtlr r5 mtcr r6 - ld r0, VCPU_GPR(R0)(r4) ld r1, VCPU_GPR(R1)(r4) ld r2, VCPU_GPR(R2)(r4) ld r3, VCPU_GPR(R3)(r4) @@ -570,6 +724,10 @@ END_FTR_SECTION_IFSET(CPU_FTR_CFAR) ld r12, VCPU_GPR(R12)(r4) ld r13, VCPU_GPR(R13)(r4) +BEGIN_FTR_SECTION + mtspr SPRN_PPR, r0 +END_FTR_SECTION_IFSET(CPU_FTR_HAS_PPR) + ld r0, VCPU_GPR(R0)(r4) ld r4, VCPU_GPR(R4)(r4) hrfid @@ -584,8 +742,8 @@ END_FTR_SECTION_IFSET(CPU_FTR_CFAR) /* * We come here from the first-level interrupt handlers. */ - .globl kvmppc_interrupt -kvmppc_interrupt: + .globl kvmppc_interrupt_hv +kvmppc_interrupt_hv: /* * Register contents: * R12 = interrupt vector @@ -595,6 +753,19 @@ kvmppc_interrupt: */ /* abuse host_r2 as third scratch area; we get r2 from PACATOC(r13) */ std r9, HSTATE_HOST_R2(r13) + + lbz r9, HSTATE_IN_GUEST(r13) + cmpwi r9, KVM_GUEST_MODE_HOST_HV + beq kvmppc_bad_host_intr +#ifdef CONFIG_KVM_BOOK3S_PR_POSSIBLE + cmpwi r9, KVM_GUEST_MODE_GUEST + ld r9, HSTATE_HOST_R2(r13) + beq kvmppc_interrupt_pr +#endif + /* We're now back in the host but in guest MMU context */ + li r9, KVM_GUEST_MODE_HOST_HV + stb r9, HSTATE_IN_GUEST(r13) + ld r9, HSTATE_KVM_VCPU(r13) /* Save registers */ @@ -620,6 +791,10 @@ BEGIN_FTR_SECTION ld r3, HSTATE_CFAR(r13) std r3, VCPU_CFAR(r9) END_FTR_SECTION_IFSET(CPU_FTR_CFAR) +BEGIN_FTR_SECTION + ld r4, HSTATE_PPR(r13) + std r4, VCPU_PPR(r9) +END_FTR_SECTION_IFSET(CPU_FTR_HAS_PPR) /* Restore R1/R2 so we can handle faults */ ld r1, HSTATE_HOST_R1(r13) @@ -642,10 +817,6 @@ END_FTR_SECTION_IFSET(CPU_FTR_CFAR) std r3, VCPU_GPR(R13)(r9) std r4, VCPU_LR(r9) - /* Unset guest mode */ - li r0, KVM_GUEST_MODE_NONE - stb r0, HSTATE_IN_GUEST(r13) - stw r12,VCPU_TRAP(r9) /* Save HEIR (HV emulation assist reg) in last_inst @@ -696,46 +867,11 @@ END_FTR_SECTION_IFCLR(CPU_FTR_ARCH_206) * set, we know the host wants us out so let's do it now */ do_ext_interrupt: - lbz r0, HSTATE_HOST_IPI(r13) - cmpwi r0, 0 - bne ext_interrupt_to_host - - /* Now read the interrupt from the ICP */ - ld r5, HSTATE_XICS_PHYS(r13) - li r7, XICS_XIRR - cmpdi r5, 0 - beq- ext_interrupt_to_host - lwzcix r3, r5, r7 - rlwinm. r0, r3, 0, 0xffffff - sync - beq 3f /* if nothing pending in the ICP */ - - /* We found something in the ICP... - * - * If it's not an IPI, stash it in the PACA and return to - * the host, we don't (yet) handle directing real external - * interrupts directly to the guest - */ - cmpwi r0, XICS_IPI - bne ext_stash_for_host - - /* It's an IPI, clear the MFRR and EOI it */ - li r0, 0xff - li r6, XICS_MFRR - stbcix r0, r5, r6 /* clear the IPI */ - stwcix r3, r5, r7 /* EOI it */ - sync - - /* We need to re-check host IPI now in case it got set in the - * meantime. If it's clear, we bounce the interrupt to the - * guest - */ - lbz r0, HSTATE_HOST_IPI(r13) - cmpwi r0, 0 - bne- 1f + bl kvmppc_read_intr + cmpdi r3, 0 + bgt ext_interrupt_to_host /* Allright, looks like an IPI for the guest, we need to set MER */ -3: /* Check if any CPU is heading out to the host, if so head out too */ ld r5, HSTATE_KVM_VCORE(r13) lwz r0, VCORE_ENTRY_EXIT(r5) @@ -764,27 +900,9 @@ do_ext_interrupt: mtspr SPRN_LPCR, r8 b fast_guest_return - /* We raced with the host, we need to resend that IPI, bummer */ -1: li r0, IPI_PRIORITY - stbcix r0, r5, r6 /* set the IPI */ - sync - b ext_interrupt_to_host - -ext_stash_for_host: - /* It's not an IPI and it's for the host, stash it in the PACA - * before exit, it will be picked up by the host ICP driver - */ - stw r3, HSTATE_SAVED_XIRR(r13) ext_interrupt_to_host: guest_exit_cont: /* r9 = vcpu, r12 = trap, r13 = paca */ - /* Save DEC */ - mfspr r5,SPRN_DEC - mftb r6 - extsw r5,r5 - add r5,r5,r6 - std r5,VCPU_DEC_EXPIRES(r9) - /* Save more register state */ mfdar r6 mfdsisr r7 @@ -954,7 +1072,30 @@ END_FTR_SECTION_IFSET(CPU_FTR_ARCH_201) mtspr SPRN_SDR1,r6 /* switch to partition page table */ mtspr SPRN_LPID,r7 isync - li r0,0 + + /* Subtract timebase offset from timebase */ + ld r8,VCORE_TB_OFFSET(r5) + cmpdi r8,0 + beq 17f + mftb r6 /* current host timebase */ + subf r8,r8,r6 + mtspr SPRN_TBU40,r8 /* update upper 40 bits */ + mftb r7 /* check if lower 24 bits overflowed */ + clrldi r6,r6,40 + clrldi r7,r7,40 + cmpld r7,r6 + bge 17f + addis r8,r8,0x100 /* if so, increment upper 40 bits */ + mtspr SPRN_TBU40,r8 + + /* Reset PCR */ +17: ld r0, VCORE_PCR(r5) + cmpdi r0, 0 + beq 18f + li r0, 0 + mtspr SPRN_PCR, r0 +18: + /* Signal secondary CPUs to continue */ stb r0,VCORE_IN_GUEST(r5) lis r8,0x7fff /* MAX_INT@h */ mtspr SPRN_HDEC,r8 @@ -1052,6 +1193,13 @@ END_FTR_SECTION_IFSET(CPU_FTR_ARCH_201) 1: addi r8,r8,16 .endr + /* Save DEC */ + mfspr r5,SPRN_DEC + mftb r6 + extsw r5,r5 + add r5,r5,r6 + std r5,VCPU_DEC_EXPIRES(r9) + /* Save and reset AMR and UAMOR before turning on the MMU */ BEGIN_FTR_SECTION mfspr r5,SPRN_AMR @@ -1062,6 +1210,10 @@ BEGIN_FTR_SECTION mtspr SPRN_AMR,r6 END_FTR_SECTION_IFSET(CPU_FTR_ARCH_206) + /* Unset guest mode */ + li r0, KVM_GUEST_MODE_NONE + stb r0, HSTATE_IN_GUEST(r13) + /* Switch DSCR back to host value */ BEGIN_FTR_SECTION mfspr r8, SPRN_DSCR @@ -1134,9 +1286,13 @@ END_FTR_SECTION_IFSET(CPU_FTR_ARCH_206) std r3, VCPU_MMCR(r9) /* if not, set saved MMCR0 to FC */ b 22f 21: mfspr r5, SPRN_MMCR1 + mfspr r7, SPRN_SIAR + mfspr r8, SPRN_SDAR std r4, VCPU_MMCR(r9) std r5, VCPU_MMCR + 8(r9) std r6, VCPU_MMCR + 16(r9) + std r7, VCPU_SIAR(r9) + std r8, VCPU_SDAR(r9) mfspr r3, SPRN_PMC1 mfspr r4, SPRN_PMC2 mfspr r5, SPRN_PMC3 @@ -1158,103 +1314,30 @@ BEGIN_FTR_SECTION stw r11, VCPU_PMC + 28(r9) END_FTR_SECTION_IFSET(CPU_FTR_ARCH_201) 22: + ld r0, 112+PPC_LR_STKOFF(r1) + addi r1, r1, 112 + mtlr r0 + blr +secondary_too_late: + ld r5,HSTATE_KVM_VCORE(r13) + HMT_LOW +13: lbz r3,VCORE_IN_GUEST(r5) + cmpwi r3,0 + bne 13b + HMT_MEDIUM + li r0, KVM_GUEST_MODE_NONE + stb r0, HSTATE_IN_GUEST(r13) + ld r11,PACA_SLBSHADOWPTR(r13) - /* Secondary threads go off to take a nap on POWER7 */ -BEGIN_FTR_SECTION - lwz r0,VCPU_PTID(r9) - cmpwi r0,0 - bne secondary_nap -END_FTR_SECTION_IFSET(CPU_FTR_ARCH_206) - - /* Restore host DABR and DABRX */ - ld r5,HSTATE_DABR(r13) - li r6,7 - mtspr SPRN_DABR,r5 - mtspr SPRN_DABRX,r6 - - /* Restore SPRG3 */ - ld r3,PACA_SPRG3(r13) - mtspr SPRN_SPRG3,r3 - - /* - * Reload DEC. HDEC interrupts were disabled when - * we reloaded the host's LPCR value. - */ - ld r3, HSTATE_DECEXP(r13) - mftb r4 - subf r4, r4, r3 - mtspr SPRN_DEC, r4 - - /* Reload the host's PMU registers */ - ld r3, PACALPPACAPTR(r13) /* is the host using the PMU? */ - lbz r4, LPPACA_PMCINUSE(r3) - cmpwi r4, 0 - beq 23f /* skip if not */ - lwz r3, HSTATE_PMC(r13) - lwz r4, HSTATE_PMC + 4(r13) - lwz r5, HSTATE_PMC + 8(r13) - lwz r6, HSTATE_PMC + 12(r13) - lwz r8, HSTATE_PMC + 16(r13) - lwz r9, HSTATE_PMC + 20(r13) -BEGIN_FTR_SECTION - lwz r10, HSTATE_PMC + 24(r13) - lwz r11, HSTATE_PMC + 28(r13) -END_FTR_SECTION_IFSET(CPU_FTR_ARCH_201) - mtspr SPRN_PMC1, r3 - mtspr SPRN_PMC2, r4 - mtspr SPRN_PMC3, r5 - mtspr SPRN_PMC4, r6 - mtspr SPRN_PMC5, r8 - mtspr SPRN_PMC6, r9 -BEGIN_FTR_SECTION - mtspr SPRN_PMC7, r10 - mtspr SPRN_PMC8, r11 -END_FTR_SECTION_IFSET(CPU_FTR_ARCH_201) - ld r3, HSTATE_MMCR(r13) - ld r4, HSTATE_MMCR + 8(r13) - ld r5, HSTATE_MMCR + 16(r13) - mtspr SPRN_MMCR1, r4 - mtspr SPRN_MMCRA, r5 - mtspr SPRN_MMCR0, r3 - isync -23: - /* - * For external and machine check interrupts, we need - * to call the Linux handler to process the interrupt. - * We do that by jumping to absolute address 0x500 for - * external interrupts, or the machine_check_fwnmi label - * for machine checks (since firmware might have patched - * the vector area at 0x200). The [h]rfid at the end of the - * handler will return to the book3s_hv_interrupts.S code. - * For other interrupts we do the rfid to get back - * to the book3s_hv_interrupts.S code here. - */ - ld r8, HSTATE_VMHANDLER(r13) - ld r7, HSTATE_HOST_MSR(r13) - - cmpwi cr1, r12, BOOK3S_INTERRUPT_MACHINE_CHECK - cmpwi r12, BOOK3S_INTERRUPT_EXTERNAL -BEGIN_FTR_SECTION - beq 11f -END_FTR_SECTION_IFSET(CPU_FTR_ARCH_206) - - /* RFI into the highmem handler, or branch to interrupt handler */ - mfmsr r6 - li r0, MSR_RI - andc r6, r6, r0 - mtmsrd r6, 1 /* Clear RI in MSR */ - mtsrr0 r8 - mtsrr1 r7 - beqa 0x500 /* external interrupt (PPC970) */ - beq cr1, 13f /* machine check */ - RFI - - /* On POWER7, we have external interrupts set to use HSRR0/1 */ -11: mtspr SPRN_HSRR0, r8 - mtspr SPRN_HSRR1, r7 - ba 0x500 - -13: b machine_check_fwnmi + .rept SLB_NUM_BOLTED + ld r5,SLBSHADOW_SAVEAREA(r11) + ld r6,SLBSHADOW_SAVEAREA+8(r11) + andis. r7,r5,SLB_ESID_V@h + beq 1f + slbmte r6,r5 +1: addi r11,r11,16 + .endr + b 22b /* * Check whether an HDSI is an HPTE not found fault or something else. @@ -1333,7 +1416,7 @@ fast_interrupt_c_return: stw r8, VCPU_LAST_INST(r9) /* Unset guest mode. */ - li r0, KVM_GUEST_MODE_NONE + li r0, KVM_GUEST_MODE_HOST_HV stb r0, HSTATE_IN_GUEST(r13) b guest_exit_cont @@ -1701,67 +1784,70 @@ machine_check_realmode: rotldi r11, r11, 63 b fast_interrupt_c_return -secondary_too_late: - ld r5,HSTATE_KVM_VCORE(r13) - HMT_LOW -13: lbz r3,VCORE_IN_GUEST(r5) - cmpwi r3,0 - bne 13b - HMT_MEDIUM - ld r11,PACA_SLBSHADOWPTR(r13) - - .rept SLB_NUM_BOLTED - ld r5,SLBSHADOW_SAVEAREA(r11) - ld r6,SLBSHADOW_SAVEAREA+8(r11) - andis. r7,r5,SLB_ESID_V@h - beq 1f - slbmte r6,r5 -1: addi r11,r11,16 - .endr +/* + * Determine what sort of external interrupt is pending (if any). + * Returns: + * 0 if no interrupt is pending + * 1 if an interrupt is pending that needs to be handled by the host + * -1 if there was a guest wakeup IPI (which has now been cleared) + */ +kvmppc_read_intr: + /* see if a host IPI is pending */ + li r3, 1 + lbz r0, HSTATE_HOST_IPI(r13) + cmpwi r0, 0 + bne 1f -secondary_nap: - /* Clear our vcpu pointer so we don't come back in early */ - li r0, 0 - std r0, HSTATE_KVM_VCPU(r13) - lwsync - /* Clear any pending IPI - assume we're a secondary thread */ - ld r5, HSTATE_XICS_PHYS(r13) + /* Now read the interrupt from the ICP */ + ld r6, HSTATE_XICS_PHYS(r13) li r7, XICS_XIRR - lwzcix r3, r5, r7 /* ack any pending interrupt */ - rlwinm. r0, r3, 0, 0xffffff /* any pending? */ - beq 37f + cmpdi r6, 0 + beq- 1f + lwzcix r0, r6, r7 + rlwinm. r3, r0, 0, 0xffffff sync - li r0, 0xff - li r6, XICS_MFRR - stbcix r0, r5, r6 /* clear the IPI */ - stwcix r3, r5, r7 /* EOI it */ -37: sync + beq 1f /* if nothing pending in the ICP */ - /* increment the nap count and then go to nap mode */ - ld r4, HSTATE_KVM_VCORE(r13) - addi r4, r4, VCORE_NAP_COUNT - lwsync /* make previous updates visible */ -51: lwarx r3, 0, r4 - addi r3, r3, 1 - stwcx. r3, 0, r4 - bne 51b + /* We found something in the ICP... + * + * If it's not an IPI, stash it in the PACA and return to + * the host, we don't (yet) handle directing real external + * interrupts directly to the guest + */ + cmpwi r3, XICS_IPI /* if there is, is it an IPI? */ + li r3, 1 + bne 42f -kvm_no_guest: - li r0, KVM_HWTHREAD_IN_NAP - stb r0, HSTATE_HWTHREAD_STATE(r13) + /* It's an IPI, clear the MFRR and EOI it */ + li r3, 0xff + li r8, XICS_MFRR + stbcix r3, r6, r8 /* clear the IPI */ + stwcix r0, r6, r7 /* EOI it */ + sync - li r3, LPCR_PECE0 - mfspr r4, SPRN_LPCR - rlwimi r4, r3, 0, LPCR_PECE0 | LPCR_PECE1 - mtspr SPRN_LPCR, r4 - isync - std r0, HSTATE_SCRATCH0(r13) - ptesync - ld r0, HSTATE_SCRATCH0(r13) -1: cmpd r0, r0 - bne 1b - nap - b . + /* We need to re-check host IPI now in case it got set in the + * meantime. If it's clear, we bounce the interrupt to the + * guest + */ + lbz r0, HSTATE_HOST_IPI(r13) + cmpwi r0, 0 + bne- 43f + + /* OK, it's an IPI for us */ + li r3, -1 +1: blr + +42: /* It's not an IPI and it's for the host, stash it in the PACA + * before exit, it will be picked up by the host ICP driver + */ + stw r0, HSTATE_SAVED_XIRR(r13) + b 1b + +43: /* We raced with the host, we need to resend that IPI, bummer */ + li r0, IPI_PRIORITY + stbcix r0, r6, r8 /* set the IPI */ + sync + b 1b /* * Save away FP, VMX and VSX registers. @@ -1879,3 +1965,11 @@ END_FTR_SECTION_IFSET(CPU_FTR_ALTIVEC) lwz r7,VCPU_VRSAVE(r4) mtspr SPRN_VRSAVE,r7 blr + +/* + * We come here if we get any exception or interrupt while we are + * executing host real mode code while in guest MMU context. + * For now just spin, but we should do something better. + */ +kvmppc_bad_host_intr: + b . diff --git a/arch/powerpc/kvm/book3s_interrupts.S b/arch/powerpc/kvm/book3s_interrupts.S index 17cfae5497a3..f4dd041c14ea 100644 --- a/arch/powerpc/kvm/book3s_interrupts.S +++ b/arch/powerpc/kvm/book3s_interrupts.S @@ -26,8 +26,12 @@ #if defined(CONFIG_PPC_BOOK3S_64) #define FUNC(name) GLUE(.,name) +#define GET_SHADOW_VCPU(reg) addi reg, r13, PACA_SVCPU + #elif defined(CONFIG_PPC_BOOK3S_32) #define FUNC(name) name +#define GET_SHADOW_VCPU(reg) lwz reg, (THREAD + THREAD_KVM_SVCPU)(r2) + #endif /* CONFIG_PPC_BOOK3S_XX */ #define VCPU_LOAD_NVGPRS(vcpu) \ @@ -87,8 +91,14 @@ kvm_start_entry: VCPU_LOAD_NVGPRS(r4) kvm_start_lightweight: + /* Copy registers into shadow vcpu so we can access them in real mode */ + GET_SHADOW_VCPU(r3) + bl FUNC(kvmppc_copy_to_svcpu) + nop + REST_GPR(4, r1) #ifdef CONFIG_PPC_BOOK3S_64 + /* Get the dcbz32 flag */ PPC_LL r3, VCPU_HFLAGS(r4) rldicl r3, r3, 0, 63 /* r3 &= 1 */ stb r3, HSTATE_RESTORE_HID5(r13) @@ -111,9 +121,6 @@ kvm_start_lightweight: * */ -.global kvmppc_handler_highmem -kvmppc_handler_highmem: - /* * Register usage at this point: * @@ -125,18 +132,31 @@ kvmppc_handler_highmem: * */ - /* R7 = vcpu */ - PPC_LL r7, GPR4(r1) + /* Transfer reg values from shadow vcpu back to vcpu struct */ + /* On 64-bit, interrupts are still off at this point */ + PPC_LL r3, GPR4(r1) /* vcpu pointer */ + GET_SHADOW_VCPU(r4) + bl FUNC(kvmppc_copy_from_svcpu) + nop #ifdef CONFIG_PPC_BOOK3S_64 + /* Re-enable interrupts */ + ld r3, HSTATE_HOST_MSR(r13) + ori r3, r3, MSR_EE + MTMSR_EERI(r3) + /* * Reload kernel SPRG3 value. * No need to save guest value as usermode can't modify SPRG3. */ ld r3, PACA_SPRG3(r13) mtspr SPRN_SPRG3, r3 + #endif /* CONFIG_PPC_BOOK3S_64 */ + /* R7 = vcpu */ + PPC_LL r7, GPR4(r1) + PPC_STL r14, VCPU_GPR(R14)(r7) PPC_STL r15, VCPU_GPR(R15)(r7) PPC_STL r16, VCPU_GPR(R16)(r7) @@ -161,7 +181,7 @@ kvmppc_handler_highmem: /* Restore r3 (kvm_run) and r4 (vcpu) */ REST_2GPRS(3, r1) - bl FUNC(kvmppc_handle_exit) + bl FUNC(kvmppc_handle_exit_pr) /* If RESUME_GUEST, get back in the loop */ cmpwi r3, RESUME_GUEST diff --git a/arch/powerpc/kvm/book3s_mmu_hpte.c b/arch/powerpc/kvm/book3s_mmu_hpte.c index da8b13c4b776..5a1ab1250a05 100644 --- a/arch/powerpc/kvm/book3s_mmu_hpte.c +++ b/arch/powerpc/kvm/book3s_mmu_hpte.c @@ -28,7 +28,7 @@ #include <asm/mmu_context.h> #include <asm/hw_irq.h> -#include "trace.h" +#include "trace_pr.h" #define PTE_SIZE 12 @@ -56,6 +56,14 @@ static inline u64 kvmppc_mmu_hash_vpte_long(u64 vpage) HPTEG_HASH_BITS_VPTE_LONG); } +#ifdef CONFIG_PPC_BOOK3S_64 +static inline u64 kvmppc_mmu_hash_vpte_64k(u64 vpage) +{ + return hash_64((vpage & 0xffffffff0ULL) >> 4, + HPTEG_HASH_BITS_VPTE_64K); +} +#endif + void kvmppc_mmu_hpte_cache_map(struct kvm_vcpu *vcpu, struct hpte_cache *pte) { u64 index; @@ -83,6 +91,15 @@ void kvmppc_mmu_hpte_cache_map(struct kvm_vcpu *vcpu, struct hpte_cache *pte) hlist_add_head_rcu(&pte->list_vpte_long, &vcpu3s->hpte_hash_vpte_long[index]); +#ifdef CONFIG_PPC_BOOK3S_64 + /* Add to vPTE_64k list */ + index = kvmppc_mmu_hash_vpte_64k(pte->pte.vpage); + hlist_add_head_rcu(&pte->list_vpte_64k, + &vcpu3s->hpte_hash_vpte_64k[index]); +#endif + + vcpu3s->hpte_cache_count++; + spin_unlock(&vcpu3s->mmu_lock); } @@ -113,10 +130,13 @@ static void invalidate_pte(struct kvm_vcpu *vcpu, struct hpte_cache *pte) hlist_del_init_rcu(&pte->list_pte_long); hlist_del_init_rcu(&pte->list_vpte); hlist_del_init_rcu(&pte->list_vpte_long); +#ifdef CONFIG_PPC_BOOK3S_64 + hlist_del_init_rcu(&pte->list_vpte_64k); +#endif + vcpu3s->hpte_cache_count--; spin_unlock(&vcpu3s->mmu_lock); - vcpu3s->hpte_cache_count--; call_rcu(&pte->rcu_head, free_pte_rcu); } @@ -219,6 +239,29 @@ static void kvmppc_mmu_pte_vflush_short(struct kvm_vcpu *vcpu, u64 guest_vp) rcu_read_unlock(); } +#ifdef CONFIG_PPC_BOOK3S_64 +/* Flush with mask 0xffffffff0 */ +static void kvmppc_mmu_pte_vflush_64k(struct kvm_vcpu *vcpu, u64 guest_vp) +{ + struct kvmppc_vcpu_book3s *vcpu3s = to_book3s(vcpu); + struct hlist_head *list; + struct hpte_cache *pte; + u64 vp_mask = 0xffffffff0ULL; + + list = &vcpu3s->hpte_hash_vpte_64k[ + kvmppc_mmu_hash_vpte_64k(guest_vp)]; + + rcu_read_lock(); + + /* Check the list for matching entries and invalidate */ + hlist_for_each_entry_rcu(pte, list, list_vpte_64k) + if ((pte->pte.vpage & vp_mask) == guest_vp) + invalidate_pte(vcpu, pte); + + rcu_read_unlock(); +} +#endif + /* Flush with mask 0xffffff000 */ static void kvmppc_mmu_pte_vflush_long(struct kvm_vcpu *vcpu, u64 guest_vp) { @@ -249,6 +292,11 @@ void kvmppc_mmu_pte_vflush(struct kvm_vcpu *vcpu, u64 guest_vp, u64 vp_mask) case 0xfffffffffULL: kvmppc_mmu_pte_vflush_short(vcpu, guest_vp); break; +#ifdef CONFIG_PPC_BOOK3S_64 + case 0xffffffff0ULL: + kvmppc_mmu_pte_vflush_64k(vcpu, guest_vp); + break; +#endif case 0xffffff000ULL: kvmppc_mmu_pte_vflush_long(vcpu, guest_vp); break; @@ -285,15 +333,19 @@ struct hpte_cache *kvmppc_mmu_hpte_cache_next(struct kvm_vcpu *vcpu) struct kvmppc_vcpu_book3s *vcpu3s = to_book3s(vcpu); struct hpte_cache *pte; - pte = kmem_cache_zalloc(hpte_cache, GFP_KERNEL); - vcpu3s->hpte_cache_count++; - if (vcpu3s->hpte_cache_count == HPTEG_CACHE_NUM) kvmppc_mmu_pte_flush_all(vcpu); + pte = kmem_cache_zalloc(hpte_cache, GFP_KERNEL); + return pte; } +void kvmppc_mmu_hpte_cache_free(struct hpte_cache *pte) +{ + kmem_cache_free(hpte_cache, pte); +} + void kvmppc_mmu_hpte_destroy(struct kvm_vcpu *vcpu) { kvmppc_mmu_pte_flush(vcpu, 0, 0); @@ -320,6 +372,10 @@ int kvmppc_mmu_hpte_init(struct kvm_vcpu *vcpu) ARRAY_SIZE(vcpu3s->hpte_hash_vpte)); kvmppc_mmu_hpte_init_hash(vcpu3s->hpte_hash_vpte_long, ARRAY_SIZE(vcpu3s->hpte_hash_vpte_long)); +#ifdef CONFIG_PPC_BOOK3S_64 + kvmppc_mmu_hpte_init_hash(vcpu3s->hpte_hash_vpte_64k, + ARRAY_SIZE(vcpu3s->hpte_hash_vpte_64k)); +#endif spin_lock_init(&vcpu3s->mmu_lock); diff --git a/arch/powerpc/kvm/book3s_pr.c b/arch/powerpc/kvm/book3s_pr.c index c0b48f96a91c..fe14ca3dd171 100644 --- a/arch/powerpc/kvm/book3s_pr.c +++ b/arch/powerpc/kvm/book3s_pr.c @@ -40,8 +40,12 @@ #include <linux/sched.h> #include <linux/vmalloc.h> #include <linux/highmem.h> +#include <linux/module.h> -#include "trace.h" +#include "book3s.h" + +#define CREATE_TRACE_POINTS +#include "trace_pr.h" /* #define EXIT_DEBUG */ /* #define DEBUG_EXT */ @@ -56,29 +60,25 @@ static int kvmppc_handle_ext(struct kvm_vcpu *vcpu, unsigned int exit_nr, #define HW_PAGE_SIZE PAGE_SIZE #endif -void kvmppc_core_vcpu_load(struct kvm_vcpu *vcpu, int cpu) +static void kvmppc_core_vcpu_load_pr(struct kvm_vcpu *vcpu, int cpu) { #ifdef CONFIG_PPC_BOOK3S_64 struct kvmppc_book3s_shadow_vcpu *svcpu = svcpu_get(vcpu); memcpy(svcpu->slb, to_book3s(vcpu)->slb_shadow, sizeof(svcpu->slb)); - memcpy(&get_paca()->shadow_vcpu, to_book3s(vcpu)->shadow_vcpu, - sizeof(get_paca()->shadow_vcpu)); svcpu->slb_max = to_book3s(vcpu)->slb_shadow_max; svcpu_put(svcpu); #endif vcpu->cpu = smp_processor_id(); #ifdef CONFIG_PPC_BOOK3S_32 - current->thread.kvm_shadow_vcpu = to_book3s(vcpu)->shadow_vcpu; + current->thread.kvm_shadow_vcpu = vcpu->arch.shadow_vcpu; #endif } -void kvmppc_core_vcpu_put(struct kvm_vcpu *vcpu) +static void kvmppc_core_vcpu_put_pr(struct kvm_vcpu *vcpu) { #ifdef CONFIG_PPC_BOOK3S_64 struct kvmppc_book3s_shadow_vcpu *svcpu = svcpu_get(vcpu); memcpy(to_book3s(vcpu)->slb_shadow, svcpu->slb, sizeof(svcpu->slb)); - memcpy(to_book3s(vcpu)->shadow_vcpu, &get_paca()->shadow_vcpu, - sizeof(get_paca()->shadow_vcpu)); to_book3s(vcpu)->slb_shadow_max = svcpu->slb_max; svcpu_put(svcpu); #endif @@ -87,7 +87,61 @@ void kvmppc_core_vcpu_put(struct kvm_vcpu *vcpu) vcpu->cpu = -1; } -int kvmppc_core_check_requests(struct kvm_vcpu *vcpu) +/* Copy data needed by real-mode code from vcpu to shadow vcpu */ +void kvmppc_copy_to_svcpu(struct kvmppc_book3s_shadow_vcpu *svcpu, + struct kvm_vcpu *vcpu) +{ + svcpu->gpr[0] = vcpu->arch.gpr[0]; + svcpu->gpr[1] = vcpu->arch.gpr[1]; + svcpu->gpr[2] = vcpu->arch.gpr[2]; + svcpu->gpr[3] = vcpu->arch.gpr[3]; + svcpu->gpr[4] = vcpu->arch.gpr[4]; + svcpu->gpr[5] = vcpu->arch.gpr[5]; + svcpu->gpr[6] = vcpu->arch.gpr[6]; + svcpu->gpr[7] = vcpu->arch.gpr[7]; + svcpu->gpr[8] = vcpu->arch.gpr[8]; + svcpu->gpr[9] = vcpu->arch.gpr[9]; + svcpu->gpr[10] = vcpu->arch.gpr[10]; + svcpu->gpr[11] = vcpu->arch.gpr[11]; + svcpu->gpr[12] = vcpu->arch.gpr[12]; + svcpu->gpr[13] = vcpu->arch.gpr[13]; + svcpu->cr = vcpu->arch.cr; + svcpu->xer = vcpu->arch.xer; + svcpu->ctr = vcpu->arch.ctr; + svcpu->lr = vcpu->arch.lr; + svcpu->pc = vcpu->arch.pc; +} + +/* Copy data touched by real-mode code from shadow vcpu back to vcpu */ +void kvmppc_copy_from_svcpu(struct kvm_vcpu *vcpu, + struct kvmppc_book3s_shadow_vcpu *svcpu) +{ + vcpu->arch.gpr[0] = svcpu->gpr[0]; + vcpu->arch.gpr[1] = svcpu->gpr[1]; + vcpu->arch.gpr[2] = svcpu->gpr[2]; + vcpu->arch.gpr[3] = svcpu->gpr[3]; + vcpu->arch.gpr[4] = svcpu->gpr[4]; + vcpu->arch.gpr[5] = svcpu->gpr[5]; + vcpu->arch.gpr[6] = svcpu->gpr[6]; + vcpu->arch.gpr[7] = svcpu->gpr[7]; + vcpu->arch.gpr[8] = svcpu->gpr[8]; + vcpu->arch.gpr[9] = svcpu->gpr[9]; + vcpu->arch.gpr[10] = svcpu->gpr[10]; + vcpu->arch.gpr[11] = svcpu->gpr[11]; + vcpu->arch.gpr[12] = svcpu->gpr[12]; + vcpu->arch.gpr[13] = svcpu->gpr[13]; + vcpu->arch.cr = svcpu->cr; + vcpu->arch.xer = svcpu->xer; + vcpu->arch.ctr = svcpu->ctr; + vcpu->arch.lr = svcpu->lr; + vcpu->arch.pc = svcpu->pc; + vcpu->arch.shadow_srr1 = svcpu->shadow_srr1; + vcpu->arch.fault_dar = svcpu->fault_dar; + vcpu->arch.fault_dsisr = svcpu->fault_dsisr; + vcpu->arch.last_inst = svcpu->last_inst; +} + +static int kvmppc_core_check_requests_pr(struct kvm_vcpu *vcpu) { int r = 1; /* Indicate we want to get back into the guest */ @@ -100,44 +154,69 @@ int kvmppc_core_check_requests(struct kvm_vcpu *vcpu) } /************* MMU Notifiers *************/ +static void do_kvm_unmap_hva(struct kvm *kvm, unsigned long start, + unsigned long end) +{ + long i; + struct kvm_vcpu *vcpu; + struct kvm_memslots *slots; + struct kvm_memory_slot *memslot; + + slots = kvm_memslots(kvm); + kvm_for_each_memslot(memslot, slots) { + unsigned long hva_start, hva_end; + gfn_t gfn, gfn_end; + + hva_start = max(start, memslot->userspace_addr); + hva_end = min(end, memslot->userspace_addr + + (memslot->npages << PAGE_SHIFT)); + if (hva_start >= hva_end) + continue; + /* + * {gfn(page) | page intersects with [hva_start, hva_end)} = + * {gfn, gfn+1, ..., gfn_end-1}. + */ + gfn = hva_to_gfn_memslot(hva_start, memslot); + gfn_end = hva_to_gfn_memslot(hva_end + PAGE_SIZE - 1, memslot); + kvm_for_each_vcpu(i, vcpu, kvm) + kvmppc_mmu_pte_pflush(vcpu, gfn << PAGE_SHIFT, + gfn_end << PAGE_SHIFT); + } +} -int kvm_unmap_hva(struct kvm *kvm, unsigned long hva) +static int kvm_unmap_hva_pr(struct kvm *kvm, unsigned long hva) { trace_kvm_unmap_hva(hva); - /* - * Flush all shadow tlb entries everywhere. This is slow, but - * we are 100% sure that we catch the to be unmapped page - */ - kvm_flush_remote_tlbs(kvm); + do_kvm_unmap_hva(kvm, hva, hva + PAGE_SIZE); return 0; } -int kvm_unmap_hva_range(struct kvm *kvm, unsigned long start, unsigned long end) +static int kvm_unmap_hva_range_pr(struct kvm *kvm, unsigned long start, + unsigned long end) { - /* kvm_unmap_hva flushes everything anyways */ - kvm_unmap_hva(kvm, start); + do_kvm_unmap_hva(kvm, start, end); return 0; } -int kvm_age_hva(struct kvm *kvm, unsigned long hva) +static int kvm_age_hva_pr(struct kvm *kvm, unsigned long hva) { /* XXX could be more clever ;) */ return 0; } -int kvm_test_age_hva(struct kvm *kvm, unsigned long hva) +static int kvm_test_age_hva_pr(struct kvm *kvm, unsigned long hva) { /* XXX could be more clever ;) */ return 0; } -void kvm_set_spte_hva(struct kvm *kvm, unsigned long hva, pte_t pte) +static void kvm_set_spte_hva_pr(struct kvm *kvm, unsigned long hva, pte_t pte) { /* The page will get remapped properly on its next fault */ - kvm_unmap_hva(kvm, hva); + do_kvm_unmap_hva(kvm, hva, hva + PAGE_SIZE); } /*****************************************/ @@ -159,7 +238,7 @@ static void kvmppc_recalc_shadow_msr(struct kvm_vcpu *vcpu) vcpu->arch.shadow_msr = smsr; } -void kvmppc_set_msr(struct kvm_vcpu *vcpu, u64 msr) +static void kvmppc_set_msr_pr(struct kvm_vcpu *vcpu, u64 msr) { ulong old_msr = vcpu->arch.shared->msr; @@ -219,7 +298,7 @@ void kvmppc_set_msr(struct kvm_vcpu *vcpu, u64 msr) kvmppc_handle_ext(vcpu, BOOK3S_INTERRUPT_FP_UNAVAIL, MSR_FP); } -void kvmppc_set_pvr(struct kvm_vcpu *vcpu, u32 pvr) +void kvmppc_set_pvr_pr(struct kvm_vcpu *vcpu, u32 pvr) { u32 host_pvr; @@ -256,6 +335,23 @@ void kvmppc_set_pvr(struct kvm_vcpu *vcpu, u32 pvr) if (!strcmp(cur_cpu_spec->platform, "ppc-cell-be")) to_book3s(vcpu)->msr_mask &= ~(MSR_FE0 | MSR_FE1); + /* + * If they're asking for POWER6 or later, set the flag + * indicating that we can do multiple large page sizes + * and 1TB segments. + * Also set the flag that indicates that tlbie has the large + * page bit in the RB operand instead of the instruction. + */ + switch (PVR_VER(pvr)) { + case PVR_POWER6: + case PVR_POWER7: + case PVR_POWER7p: + case PVR_POWER8: + vcpu->arch.hflags |= BOOK3S_HFLAG_MULTI_PGSIZE | + BOOK3S_HFLAG_NEW_TLBIE; + break; + } + #ifdef CONFIG_PPC_BOOK3S_32 /* 32 bit Book3S always has 32 byte dcbz */ vcpu->arch.hflags |= BOOK3S_HFLAG_DCBZ32; @@ -334,6 +430,7 @@ int kvmppc_handle_pagefault(struct kvm_run *run, struct kvm_vcpu *vcpu, ulong eaddr, int vec) { bool data = (vec == BOOK3S_INTERRUPT_DATA_STORAGE); + bool iswrite = false; int r = RESUME_GUEST; int relocated; int page_found = 0; @@ -344,10 +441,12 @@ int kvmppc_handle_pagefault(struct kvm_run *run, struct kvm_vcpu *vcpu, u64 vsid; relocated = data ? dr : ir; + if (data && (vcpu->arch.fault_dsisr & DSISR_ISSTORE)) + iswrite = true; /* Resolve real address if translation turned on */ if (relocated) { - page_found = vcpu->arch.mmu.xlate(vcpu, eaddr, &pte, data); + page_found = vcpu->arch.mmu.xlate(vcpu, eaddr, &pte, data, iswrite); } else { pte.may_execute = true; pte.may_read = true; @@ -355,6 +454,7 @@ int kvmppc_handle_pagefault(struct kvm_run *run, struct kvm_vcpu *vcpu, pte.raddr = eaddr & KVM_PAM; pte.eaddr = eaddr; pte.vpage = eaddr >> 12; + pte.page_size = MMU_PAGE_64K; } switch (vcpu->arch.shared->msr & (MSR_DR|MSR_IR)) { @@ -388,22 +488,18 @@ int kvmppc_handle_pagefault(struct kvm_run *run, struct kvm_vcpu *vcpu, if (page_found == -ENOENT) { /* Page not found in guest PTE entries */ - struct kvmppc_book3s_shadow_vcpu *svcpu = svcpu_get(vcpu); vcpu->arch.shared->dar = kvmppc_get_fault_dar(vcpu); - vcpu->arch.shared->dsisr = svcpu->fault_dsisr; + vcpu->arch.shared->dsisr = vcpu->arch.fault_dsisr; vcpu->arch.shared->msr |= - (svcpu->shadow_srr1 & 0x00000000f8000000ULL); - svcpu_put(svcpu); + vcpu->arch.shadow_srr1 & 0x00000000f8000000ULL; kvmppc_book3s_queue_irqprio(vcpu, vec); } else if (page_found == -EPERM) { /* Storage protection */ - struct kvmppc_book3s_shadow_vcpu *svcpu = svcpu_get(vcpu); vcpu->arch.shared->dar = kvmppc_get_fault_dar(vcpu); - vcpu->arch.shared->dsisr = svcpu->fault_dsisr & ~DSISR_NOHPTE; + vcpu->arch.shared->dsisr = vcpu->arch.fault_dsisr & ~DSISR_NOHPTE; vcpu->arch.shared->dsisr |= DSISR_PROTFAULT; vcpu->arch.shared->msr |= - svcpu->shadow_srr1 & 0x00000000f8000000ULL; - svcpu_put(svcpu); + vcpu->arch.shadow_srr1 & 0x00000000f8000000ULL; kvmppc_book3s_queue_irqprio(vcpu, vec); } else if (page_found == -EINVAL) { /* Page not found in guest SLB */ @@ -411,12 +507,20 @@ int kvmppc_handle_pagefault(struct kvm_run *run, struct kvm_vcpu *vcpu, kvmppc_book3s_queue_irqprio(vcpu, vec + 0x80); } else if (!is_mmio && kvmppc_visible_gfn(vcpu, pte.raddr >> PAGE_SHIFT)) { + if (data && !(vcpu->arch.fault_dsisr & DSISR_NOHPTE)) { + /* + * There is already a host HPTE there, presumably + * a read-only one for a page the guest thinks + * is writable, so get rid of it first. + */ + kvmppc_mmu_unmap_page(vcpu, &pte); + } /* The guest's PTE is not mapped yet. Map on the host */ - kvmppc_mmu_map_page(vcpu, &pte); + kvmppc_mmu_map_page(vcpu, &pte, iswrite); if (data) vcpu->stat.sp_storage++; else if (vcpu->arch.mmu.is_dcbz32(vcpu) && - (!(vcpu->arch.hflags & BOOK3S_HFLAG_DCBZ32))) + (!(vcpu->arch.hflags & BOOK3S_HFLAG_DCBZ32))) kvmppc_patch_dcbz(vcpu, &pte); } else { /* MMIO */ @@ -619,13 +723,15 @@ static void kvmppc_handle_lost_ext(struct kvm_vcpu *vcpu) if (lost_ext & MSR_FP) kvmppc_load_up_fpu(); +#ifdef CONFIG_ALTIVEC if (lost_ext & MSR_VEC) kvmppc_load_up_altivec(); +#endif current->thread.regs->msr |= lost_ext; } -int kvmppc_handle_exit(struct kvm_run *run, struct kvm_vcpu *vcpu, - unsigned int exit_nr) +int kvmppc_handle_exit_pr(struct kvm_run *run, struct kvm_vcpu *vcpu, + unsigned int exit_nr) { int r = RESUME_HOST; int s; @@ -643,25 +749,32 @@ int kvmppc_handle_exit(struct kvm_run *run, struct kvm_vcpu *vcpu, switch (exit_nr) { case BOOK3S_INTERRUPT_INST_STORAGE: { - struct kvmppc_book3s_shadow_vcpu *svcpu = svcpu_get(vcpu); - ulong shadow_srr1 = svcpu->shadow_srr1; + ulong shadow_srr1 = vcpu->arch.shadow_srr1; vcpu->stat.pf_instruc++; #ifdef CONFIG_PPC_BOOK3S_32 /* We set segments as unused segments when invalidating them. So * treat the respective fault as segment fault. */ - if (svcpu->sr[kvmppc_get_pc(vcpu) >> SID_SHIFT] == SR_INVALID) { - kvmppc_mmu_map_segment(vcpu, kvmppc_get_pc(vcpu)); - r = RESUME_GUEST; + { + struct kvmppc_book3s_shadow_vcpu *svcpu; + u32 sr; + + svcpu = svcpu_get(vcpu); + sr = svcpu->sr[kvmppc_get_pc(vcpu) >> SID_SHIFT]; svcpu_put(svcpu); - break; + if (sr == SR_INVALID) { + kvmppc_mmu_map_segment(vcpu, kvmppc_get_pc(vcpu)); + r = RESUME_GUEST; + break; + } } #endif - svcpu_put(svcpu); /* only care about PTEG not found errors, but leave NX alone */ if (shadow_srr1 & 0x40000000) { + int idx = srcu_read_lock(&vcpu->kvm->srcu); r = kvmppc_handle_pagefault(run, vcpu, kvmppc_get_pc(vcpu), exit_nr); + srcu_read_unlock(&vcpu->kvm->srcu, idx); vcpu->stat.sp_instruc++; } else if (vcpu->arch.mmu.is_dcbz32(vcpu) && (!(vcpu->arch.hflags & BOOK3S_HFLAG_DCBZ32))) { @@ -682,25 +795,36 @@ int kvmppc_handle_exit(struct kvm_run *run, struct kvm_vcpu *vcpu, case BOOK3S_INTERRUPT_DATA_STORAGE: { ulong dar = kvmppc_get_fault_dar(vcpu); - struct kvmppc_book3s_shadow_vcpu *svcpu = svcpu_get(vcpu); - u32 fault_dsisr = svcpu->fault_dsisr; + u32 fault_dsisr = vcpu->arch.fault_dsisr; vcpu->stat.pf_storage++; #ifdef CONFIG_PPC_BOOK3S_32 /* We set segments as unused segments when invalidating them. So * treat the respective fault as segment fault. */ - if ((svcpu->sr[dar >> SID_SHIFT]) == SR_INVALID) { - kvmppc_mmu_map_segment(vcpu, dar); - r = RESUME_GUEST; + { + struct kvmppc_book3s_shadow_vcpu *svcpu; + u32 sr; + + svcpu = svcpu_get(vcpu); + sr = svcpu->sr[dar >> SID_SHIFT]; svcpu_put(svcpu); - break; + if (sr == SR_INVALID) { + kvmppc_mmu_map_segment(vcpu, dar); + r = RESUME_GUEST; + break; + } } #endif - svcpu_put(svcpu); - /* The only case we need to handle is missing shadow PTEs */ - if (fault_dsisr & DSISR_NOHPTE) { + /* + * We need to handle missing shadow PTEs, and + * protection faults due to us mapping a page read-only + * when the guest thinks it is writable. + */ + if (fault_dsisr & (DSISR_NOHPTE | DSISR_PROTFAULT)) { + int idx = srcu_read_lock(&vcpu->kvm->srcu); r = kvmppc_handle_pagefault(run, vcpu, dar, exit_nr); + srcu_read_unlock(&vcpu->kvm->srcu, idx); } else { vcpu->arch.shared->dar = dar; vcpu->arch.shared->dsisr = fault_dsisr; @@ -743,13 +867,10 @@ int kvmppc_handle_exit(struct kvm_run *run, struct kvm_vcpu *vcpu, case BOOK3S_INTERRUPT_H_EMUL_ASSIST: { enum emulation_result er; - struct kvmppc_book3s_shadow_vcpu *svcpu; ulong flags; program_interrupt: - svcpu = svcpu_get(vcpu); - flags = svcpu->shadow_srr1 & 0x1f0000ull; - svcpu_put(svcpu); + flags = vcpu->arch.shadow_srr1 & 0x1f0000ull; if (vcpu->arch.shared->msr & MSR_PR) { #ifdef EXIT_DEBUG @@ -798,7 +919,7 @@ program_interrupt: ulong cmd = kvmppc_get_gpr(vcpu, 3); int i; -#ifdef CONFIG_KVM_BOOK3S_64_PR +#ifdef CONFIG_PPC_BOOK3S_64 if (kvmppc_h_pr(vcpu, cmd) == EMULATE_DONE) { r = RESUME_GUEST; break; @@ -881,9 +1002,7 @@ program_interrupt: break; default: { - struct kvmppc_book3s_shadow_vcpu *svcpu = svcpu_get(vcpu); - ulong shadow_srr1 = svcpu->shadow_srr1; - svcpu_put(svcpu); + ulong shadow_srr1 = vcpu->arch.shadow_srr1; /* Ugh - bork here! What did we get? */ printk(KERN_EMERG "exit_nr=0x%x | pc=0x%lx | msr=0x%lx\n", exit_nr, kvmppc_get_pc(vcpu), shadow_srr1); @@ -920,8 +1039,8 @@ program_interrupt: return r; } -int kvm_arch_vcpu_ioctl_get_sregs(struct kvm_vcpu *vcpu, - struct kvm_sregs *sregs) +static int kvm_arch_vcpu_ioctl_get_sregs_pr(struct kvm_vcpu *vcpu, + struct kvm_sregs *sregs) { struct kvmppc_vcpu_book3s *vcpu3s = to_book3s(vcpu); int i; @@ -947,13 +1066,13 @@ int kvm_arch_vcpu_ioctl_get_sregs(struct kvm_vcpu *vcpu, return 0; } -int kvm_arch_vcpu_ioctl_set_sregs(struct kvm_vcpu *vcpu, - struct kvm_sregs *sregs) +static int kvm_arch_vcpu_ioctl_set_sregs_pr(struct kvm_vcpu *vcpu, + struct kvm_sregs *sregs) { struct kvmppc_vcpu_book3s *vcpu3s = to_book3s(vcpu); int i; - kvmppc_set_pvr(vcpu, sregs->pvr); + kvmppc_set_pvr_pr(vcpu, sregs->pvr); vcpu3s->sdr1 = sregs->u.s.sdr1; if (vcpu->arch.hflags & BOOK3S_HFLAG_SLB) { @@ -983,7 +1102,8 @@ int kvm_arch_vcpu_ioctl_set_sregs(struct kvm_vcpu *vcpu, return 0; } -int kvmppc_get_one_reg(struct kvm_vcpu *vcpu, u64 id, union kvmppc_one_reg *val) +static int kvmppc_get_one_reg_pr(struct kvm_vcpu *vcpu, u64 id, + union kvmppc_one_reg *val) { int r = 0; @@ -1012,7 +1132,8 @@ int kvmppc_get_one_reg(struct kvm_vcpu *vcpu, u64 id, union kvmppc_one_reg *val) return r; } -int kvmppc_set_one_reg(struct kvm_vcpu *vcpu, u64 id, union kvmppc_one_reg *val) +static int kvmppc_set_one_reg_pr(struct kvm_vcpu *vcpu, u64 id, + union kvmppc_one_reg *val) { int r = 0; @@ -1042,28 +1163,30 @@ int kvmppc_set_one_reg(struct kvm_vcpu *vcpu, u64 id, union kvmppc_one_reg *val) return r; } -int kvmppc_core_check_processor_compat(void) -{ - return 0; -} - -struct kvm_vcpu *kvmppc_core_vcpu_create(struct kvm *kvm, unsigned int id) +static struct kvm_vcpu *kvmppc_core_vcpu_create_pr(struct kvm *kvm, + unsigned int id) { struct kvmppc_vcpu_book3s *vcpu_book3s; struct kvm_vcpu *vcpu; int err = -ENOMEM; unsigned long p; - vcpu_book3s = vzalloc(sizeof(struct kvmppc_vcpu_book3s)); - if (!vcpu_book3s) + vcpu = kmem_cache_zalloc(kvm_vcpu_cache, GFP_KERNEL); + if (!vcpu) goto out; - vcpu_book3s->shadow_vcpu = - kzalloc(sizeof(*vcpu_book3s->shadow_vcpu), GFP_KERNEL); - if (!vcpu_book3s->shadow_vcpu) + vcpu_book3s = vzalloc(sizeof(struct kvmppc_vcpu_book3s)); + if (!vcpu_book3s) goto free_vcpu; + vcpu->arch.book3s = vcpu_book3s; + +#ifdef CONFIG_KVM_BOOK3S_32 + vcpu->arch.shadow_vcpu = + kzalloc(sizeof(*vcpu->arch.shadow_vcpu), GFP_KERNEL); + if (!vcpu->arch.shadow_vcpu) + goto free_vcpu3s; +#endif - vcpu = &vcpu_book3s->vcpu; err = kvm_vcpu_init(vcpu, kvm, id); if (err) goto free_shadow_vcpu; @@ -1076,13 +1199,19 @@ struct kvm_vcpu *kvmppc_core_vcpu_create(struct kvm *kvm, unsigned int id) vcpu->arch.shared = (void *)(p + PAGE_SIZE - 4096); #ifdef CONFIG_PPC_BOOK3S_64 - /* default to book3s_64 (970fx) */ + /* + * Default to the same as the host if we're on sufficiently + * recent machine that we have 1TB segments; + * otherwise default to PPC970FX. + */ vcpu->arch.pvr = 0x3C0301; + if (mmu_has_feature(MMU_FTR_1T_SEGMENT)) + vcpu->arch.pvr = mfspr(SPRN_PVR); #else /* default to book3s_32 (750) */ vcpu->arch.pvr = 0x84202; #endif - kvmppc_set_pvr(vcpu, vcpu->arch.pvr); + kvmppc_set_pvr_pr(vcpu, vcpu->arch.pvr); vcpu->arch.slb_nr = 64; vcpu->arch.shadow_msr = MSR_USER64; @@ -1096,24 +1225,31 @@ struct kvm_vcpu *kvmppc_core_vcpu_create(struct kvm *kvm, unsigned int id) uninit_vcpu: kvm_vcpu_uninit(vcpu); free_shadow_vcpu: - kfree(vcpu_book3s->shadow_vcpu); -free_vcpu: +#ifdef CONFIG_KVM_BOOK3S_32 + kfree(vcpu->arch.shadow_vcpu); +free_vcpu3s: +#endif vfree(vcpu_book3s); +free_vcpu: + kmem_cache_free(kvm_vcpu_cache, vcpu); out: return ERR_PTR(err); } -void kvmppc_core_vcpu_free(struct kvm_vcpu *vcpu) +static void kvmppc_core_vcpu_free_pr(struct kvm_vcpu *vcpu) { struct kvmppc_vcpu_book3s *vcpu_book3s = to_book3s(vcpu); free_page((unsigned long)vcpu->arch.shared & PAGE_MASK); kvm_vcpu_uninit(vcpu); - kfree(vcpu_book3s->shadow_vcpu); +#ifdef CONFIG_KVM_BOOK3S_32 + kfree(vcpu->arch.shadow_vcpu); +#endif vfree(vcpu_book3s); + kmem_cache_free(kvm_vcpu_cache, vcpu); } -int kvmppc_vcpu_run(struct kvm_run *kvm_run, struct kvm_vcpu *vcpu) +static int kvmppc_vcpu_run_pr(struct kvm_run *kvm_run, struct kvm_vcpu *vcpu) { int ret; struct thread_fp_state fp; @@ -1216,8 +1352,8 @@ out: /* * Get (and clear) the dirty memory log for a memory slot. */ -int kvm_vm_ioctl_get_dirty_log(struct kvm *kvm, - struct kvm_dirty_log *log) +static int kvm_vm_ioctl_get_dirty_log_pr(struct kvm *kvm, + struct kvm_dirty_log *log) { struct kvm_memory_slot *memslot; struct kvm_vcpu *vcpu; @@ -1252,67 +1388,100 @@ out: return r; } -#ifdef CONFIG_PPC64 -int kvm_vm_ioctl_get_smmu_info(struct kvm *kvm, struct kvm_ppc_smmu_info *info) +static void kvmppc_core_flush_memslot_pr(struct kvm *kvm, + struct kvm_memory_slot *memslot) { - info->flags = KVM_PPC_1T_SEGMENTS; - - /* SLB is always 64 entries */ - info->slb_size = 64; - - /* Standard 4k base page size segment */ - info->sps[0].page_shift = 12; - info->sps[0].slb_enc = 0; - info->sps[0].enc[0].page_shift = 12; - info->sps[0].enc[0].pte_enc = 0; - - /* Standard 16M large page size segment */ - info->sps[1].page_shift = 24; - info->sps[1].slb_enc = SLB_VSID_L; - info->sps[1].enc[0].page_shift = 24; - info->sps[1].enc[0].pte_enc = 0; + return; +} +static int kvmppc_core_prepare_memory_region_pr(struct kvm *kvm, + struct kvm_memory_slot *memslot, + struct kvm_userspace_memory_region *mem) +{ return 0; } -#endif /* CONFIG_PPC64 */ -void kvmppc_core_free_memslot(struct kvm_memory_slot *free, - struct kvm_memory_slot *dont) +static void kvmppc_core_commit_memory_region_pr(struct kvm *kvm, + struct kvm_userspace_memory_region *mem, + const struct kvm_memory_slot *old) { + return; } -int kvmppc_core_create_memslot(struct kvm_memory_slot *slot, - unsigned long npages) +static void kvmppc_core_free_memslot_pr(struct kvm_memory_slot *free, + struct kvm_memory_slot *dont) { - return 0; + return; } -int kvmppc_core_prepare_memory_region(struct kvm *kvm, - struct kvm_memory_slot *memslot, - struct kvm_userspace_memory_region *mem) +static int kvmppc_core_create_memslot_pr(struct kvm_memory_slot *slot, + unsigned long npages) { return 0; } -void kvmppc_core_commit_memory_region(struct kvm *kvm, - struct kvm_userspace_memory_region *mem, - const struct kvm_memory_slot *old) + +#ifdef CONFIG_PPC64 +static int kvm_vm_ioctl_get_smmu_info_pr(struct kvm *kvm, + struct kvm_ppc_smmu_info *info) { -} + long int i; + struct kvm_vcpu *vcpu; + + info->flags = 0; + + /* SLB is always 64 entries */ + info->slb_size = 64; + + /* Standard 4k base page size segment */ + info->sps[0].page_shift = 12; + info->sps[0].slb_enc = 0; + info->sps[0].enc[0].page_shift = 12; + info->sps[0].enc[0].pte_enc = 0; + + /* + * 64k large page size. + * We only want to put this in if the CPUs we're emulating + * support it, but unfortunately we don't have a vcpu easily + * to hand here to test. Just pick the first vcpu, and if + * that doesn't exist yet, report the minimum capability, + * i.e., no 64k pages. + * 1T segment support goes along with 64k pages. + */ + i = 1; + vcpu = kvm_get_vcpu(kvm, 0); + if (vcpu && (vcpu->arch.hflags & BOOK3S_HFLAG_MULTI_PGSIZE)) { + info->flags = KVM_PPC_1T_SEGMENTS; + info->sps[i].page_shift = 16; + info->sps[i].slb_enc = SLB_VSID_L | SLB_VSID_LP_01; + info->sps[i].enc[0].page_shift = 16; + info->sps[i].enc[0].pte_enc = 1; + ++i; + } + + /* Standard 16M large page size segment */ + info->sps[i].page_shift = 24; + info->sps[i].slb_enc = SLB_VSID_L; + info->sps[i].enc[0].page_shift = 24; + info->sps[i].enc[0].pte_enc = 0; -void kvmppc_core_flush_memslot(struct kvm *kvm, struct kvm_memory_slot *memslot) + return 0; +} +#else +static int kvm_vm_ioctl_get_smmu_info_pr(struct kvm *kvm, + struct kvm_ppc_smmu_info *info) { + /* We should not get called */ + BUG(); } +#endif /* CONFIG_PPC64 */ static unsigned int kvm_global_user_count = 0; static DEFINE_SPINLOCK(kvm_global_user_count_lock); -int kvmppc_core_init_vm(struct kvm *kvm) +static int kvmppc_core_init_vm_pr(struct kvm *kvm) { -#ifdef CONFIG_PPC64 - INIT_LIST_HEAD(&kvm->arch.spapr_tce_tables); - INIT_LIST_HEAD(&kvm->arch.rtas_tokens); -#endif + mutex_init(&kvm->arch.hpt_mutex); if (firmware_has_feature(FW_FEATURE_SET_MODE)) { spin_lock(&kvm_global_user_count_lock); @@ -1323,7 +1492,7 @@ int kvmppc_core_init_vm(struct kvm *kvm) return 0; } -void kvmppc_core_destroy_vm(struct kvm *kvm) +static void kvmppc_core_destroy_vm_pr(struct kvm *kvm) { #ifdef CONFIG_PPC64 WARN_ON(!list_empty(&kvm->arch.spapr_tce_tables)); @@ -1338,26 +1507,81 @@ void kvmppc_core_destroy_vm(struct kvm *kvm) } } -static int kvmppc_book3s_init(void) +static int kvmppc_core_check_processor_compat_pr(void) { - int r; + /* we are always compatible */ + return 0; +} - r = kvm_init(NULL, sizeof(struct kvmppc_vcpu_book3s), 0, - THIS_MODULE); +static long kvm_arch_vm_ioctl_pr(struct file *filp, + unsigned int ioctl, unsigned long arg) +{ + return -ENOTTY; +} - if (r) +static struct kvmppc_ops kvm_ops_pr = { + .get_sregs = kvm_arch_vcpu_ioctl_get_sregs_pr, + .set_sregs = kvm_arch_vcpu_ioctl_set_sregs_pr, + .get_one_reg = kvmppc_get_one_reg_pr, + .set_one_reg = kvmppc_set_one_reg_pr, + .vcpu_load = kvmppc_core_vcpu_load_pr, + .vcpu_put = kvmppc_core_vcpu_put_pr, + .set_msr = kvmppc_set_msr_pr, + .vcpu_run = kvmppc_vcpu_run_pr, + .vcpu_create = kvmppc_core_vcpu_create_pr, + .vcpu_free = kvmppc_core_vcpu_free_pr, + .check_requests = kvmppc_core_check_requests_pr, + .get_dirty_log = kvm_vm_ioctl_get_dirty_log_pr, + .flush_memslot = kvmppc_core_flush_memslot_pr, + .prepare_memory_region = kvmppc_core_prepare_memory_region_pr, + .commit_memory_region = kvmppc_core_commit_memory_region_pr, + .unmap_hva = kvm_unmap_hva_pr, + .unmap_hva_range = kvm_unmap_hva_range_pr, + .age_hva = kvm_age_hva_pr, + .test_age_hva = kvm_test_age_hva_pr, + .set_spte_hva = kvm_set_spte_hva_pr, + .mmu_destroy = kvmppc_mmu_destroy_pr, + .free_memslot = kvmppc_core_free_memslot_pr, + .create_memslot = kvmppc_core_create_memslot_pr, + .init_vm = kvmppc_core_init_vm_pr, + .destroy_vm = kvmppc_core_destroy_vm_pr, + .get_smmu_info = kvm_vm_ioctl_get_smmu_info_pr, + .emulate_op = kvmppc_core_emulate_op_pr, + .emulate_mtspr = kvmppc_core_emulate_mtspr_pr, + .emulate_mfspr = kvmppc_core_emulate_mfspr_pr, + .fast_vcpu_kick = kvm_vcpu_kick, + .arch_vm_ioctl = kvm_arch_vm_ioctl_pr, +}; + + +int kvmppc_book3s_init_pr(void) +{ + int r; + + r = kvmppc_core_check_processor_compat_pr(); + if (r < 0) return r; - r = kvmppc_mmu_hpte_sysinit(); + kvm_ops_pr.owner = THIS_MODULE; + kvmppc_pr_ops = &kvm_ops_pr; + r = kvmppc_mmu_hpte_sysinit(); return r; } -static void kvmppc_book3s_exit(void) +void kvmppc_book3s_exit_pr(void) { + kvmppc_pr_ops = NULL; kvmppc_mmu_hpte_sysexit(); - kvm_exit(); } -module_init(kvmppc_book3s_init); -module_exit(kvmppc_book3s_exit); +/* + * We only support separate modules for book3s 64 + */ +#ifdef CONFIG_PPC_BOOK3S_64 + +module_init(kvmppc_book3s_init_pr); +module_exit(kvmppc_book3s_exit_pr); + +MODULE_LICENSE("GPL"); +#endif diff --git a/arch/powerpc/kvm/book3s_pr_papr.c b/arch/powerpc/kvm/book3s_pr_papr.c index da0e0bc268bd..5efa97b993d8 100644 --- a/arch/powerpc/kvm/book3s_pr_papr.c +++ b/arch/powerpc/kvm/book3s_pr_papr.c @@ -21,6 +21,8 @@ #include <asm/kvm_ppc.h> #include <asm/kvm_book3s.h> +#define HPTE_SIZE 16 /* bytes per HPT entry */ + static unsigned long get_pteg_addr(struct kvm_vcpu *vcpu, long pte_index) { struct kvmppc_vcpu_book3s *vcpu_book3s = to_book3s(vcpu); @@ -40,32 +42,41 @@ static int kvmppc_h_pr_enter(struct kvm_vcpu *vcpu) long pte_index = kvmppc_get_gpr(vcpu, 5); unsigned long pteg[2 * 8]; unsigned long pteg_addr, i, *hpte; + long int ret; + i = pte_index & 7; pte_index &= ~7UL; pteg_addr = get_pteg_addr(vcpu, pte_index); + mutex_lock(&vcpu->kvm->arch.hpt_mutex); copy_from_user(pteg, (void __user *)pteg_addr, sizeof(pteg)); hpte = pteg; + ret = H_PTEG_FULL; if (likely((flags & H_EXACT) == 0)) { - pte_index &= ~7UL; for (i = 0; ; ++i) { if (i == 8) - return H_PTEG_FULL; + goto done; if ((*hpte & HPTE_V_VALID) == 0) break; hpte += 2; } } else { - i = kvmppc_get_gpr(vcpu, 5) & 7UL; hpte += i * 2; + if (*hpte & HPTE_V_VALID) + goto done; } hpte[0] = kvmppc_get_gpr(vcpu, 6); hpte[1] = kvmppc_get_gpr(vcpu, 7); - copy_to_user((void __user *)pteg_addr, pteg, sizeof(pteg)); - kvmppc_set_gpr(vcpu, 3, H_SUCCESS); + pteg_addr += i * HPTE_SIZE; + copy_to_user((void __user *)pteg_addr, hpte, HPTE_SIZE); kvmppc_set_gpr(vcpu, 4, pte_index | i); + ret = H_SUCCESS; + + done: + mutex_unlock(&vcpu->kvm->arch.hpt_mutex); + kvmppc_set_gpr(vcpu, 3, ret); return EMULATE_DONE; } @@ -77,26 +88,31 @@ static int kvmppc_h_pr_remove(struct kvm_vcpu *vcpu) unsigned long avpn = kvmppc_get_gpr(vcpu, 6); unsigned long v = 0, pteg, rb; unsigned long pte[2]; + long int ret; pteg = get_pteg_addr(vcpu, pte_index); + mutex_lock(&vcpu->kvm->arch.hpt_mutex); copy_from_user(pte, (void __user *)pteg, sizeof(pte)); + ret = H_NOT_FOUND; if ((pte[0] & HPTE_V_VALID) == 0 || ((flags & H_AVPN) && (pte[0] & ~0x7fUL) != avpn) || - ((flags & H_ANDCOND) && (pte[0] & avpn) != 0)) { - kvmppc_set_gpr(vcpu, 3, H_NOT_FOUND); - return EMULATE_DONE; - } + ((flags & H_ANDCOND) && (pte[0] & avpn) != 0)) + goto done; copy_to_user((void __user *)pteg, &v, sizeof(v)); rb = compute_tlbie_rb(pte[0], pte[1], pte_index); vcpu->arch.mmu.tlbie(vcpu, rb, rb & 1 ? true : false); - kvmppc_set_gpr(vcpu, 3, H_SUCCESS); + ret = H_SUCCESS; kvmppc_set_gpr(vcpu, 4, pte[0]); kvmppc_set_gpr(vcpu, 5, pte[1]); + done: + mutex_unlock(&vcpu->kvm->arch.hpt_mutex); + kvmppc_set_gpr(vcpu, 3, ret); + return EMULATE_DONE; } @@ -124,6 +140,7 @@ static int kvmppc_h_pr_bulk_remove(struct kvm_vcpu *vcpu) int paramnr = 4; int ret = H_SUCCESS; + mutex_lock(&vcpu->kvm->arch.hpt_mutex); for (i = 0; i < H_BULK_REMOVE_MAX_BATCH; i++) { unsigned long tsh = kvmppc_get_gpr(vcpu, paramnr+(2*i)); unsigned long tsl = kvmppc_get_gpr(vcpu, paramnr+(2*i)+1); @@ -172,6 +189,7 @@ static int kvmppc_h_pr_bulk_remove(struct kvm_vcpu *vcpu) } kvmppc_set_gpr(vcpu, paramnr+(2*i), tsh); } + mutex_unlock(&vcpu->kvm->arch.hpt_mutex); kvmppc_set_gpr(vcpu, 3, ret); return EMULATE_DONE; @@ -184,15 +202,16 @@ static int kvmppc_h_pr_protect(struct kvm_vcpu *vcpu) unsigned long avpn = kvmppc_get_gpr(vcpu, 6); unsigned long rb, pteg, r, v; unsigned long pte[2]; + long int ret; pteg = get_pteg_addr(vcpu, pte_index); + mutex_lock(&vcpu->kvm->arch.hpt_mutex); copy_from_user(pte, (void __user *)pteg, sizeof(pte)); + ret = H_NOT_FOUND; if ((pte[0] & HPTE_V_VALID) == 0 || - ((flags & H_AVPN) && (pte[0] & ~0x7fUL) != avpn)) { - kvmppc_set_gpr(vcpu, 3, H_NOT_FOUND); - return EMULATE_DONE; - } + ((flags & H_AVPN) && (pte[0] & ~0x7fUL) != avpn)) + goto done; v = pte[0]; r = pte[1]; @@ -207,8 +226,11 @@ static int kvmppc_h_pr_protect(struct kvm_vcpu *vcpu) rb = compute_tlbie_rb(v, r, pte_index); vcpu->arch.mmu.tlbie(vcpu, rb, rb & 1 ? true : false); copy_to_user((void __user *)pteg, pte, sizeof(pte)); + ret = H_SUCCESS; - kvmppc_set_gpr(vcpu, 3, H_SUCCESS); + done: + mutex_unlock(&vcpu->kvm->arch.hpt_mutex); + kvmppc_set_gpr(vcpu, 3, ret); return EMULATE_DONE; } diff --git a/arch/powerpc/kvm/book3s_rmhandlers.S b/arch/powerpc/kvm/book3s_rmhandlers.S index 8f7633e3afb8..a38c4c9edab8 100644 --- a/arch/powerpc/kvm/book3s_rmhandlers.S +++ b/arch/powerpc/kvm/book3s_rmhandlers.S @@ -38,32 +38,6 @@ #define FUNC(name) GLUE(.,name) - .globl kvmppc_skip_interrupt -kvmppc_skip_interrupt: - /* - * Here all GPRs are unchanged from when the interrupt happened - * except for r13, which is saved in SPRG_SCRATCH0. - */ - mfspr r13, SPRN_SRR0 - addi r13, r13, 4 - mtspr SPRN_SRR0, r13 - GET_SCRATCH0(r13) - rfid - b . - - .globl kvmppc_skip_Hinterrupt -kvmppc_skip_Hinterrupt: - /* - * Here all GPRs are unchanged from when the interrupt happened - * except for r13, which is saved in SPRG_SCRATCH0. - */ - mfspr r13, SPRN_HSRR0 - addi r13, r13, 4 - mtspr SPRN_HSRR0, r13 - GET_SCRATCH0(r13) - hrfid - b . - #elif defined(CONFIG_PPC_BOOK3S_32) #define FUNC(name) name @@ -179,11 +153,15 @@ _GLOBAL(kvmppc_entry_trampoline) li r6, MSR_IR | MSR_DR andc r6, r5, r6 /* Clear DR and IR in MSR value */ +#ifdef CONFIG_PPC_BOOK3S_32 /* * Set EE in HOST_MSR so that it's enabled when we get into our - * C exit handler function + * C exit handler function. On 64-bit we delay enabling + * interrupts until we have finished transferring stuff + * to or from the PACA. */ ori r5, r5, MSR_EE +#endif mtsrr0 r7 mtsrr1 r6 RFI diff --git a/arch/powerpc/kvm/book3s_rtas.c b/arch/powerpc/kvm/book3s_rtas.c index 3219ba895246..cf95cdef73c9 100644 --- a/arch/powerpc/kvm/book3s_rtas.c +++ b/arch/powerpc/kvm/book3s_rtas.c @@ -260,6 +260,7 @@ fail: */ return rc; } +EXPORT_SYMBOL_GPL(kvmppc_rtas_hcall); void kvmppc_rtas_tokens_free(struct kvm *kvm) { diff --git a/arch/powerpc/kvm/book3s_segment.S b/arch/powerpc/kvm/book3s_segment.S index 1abe4788191a..bc50c97751d3 100644 --- a/arch/powerpc/kvm/book3s_segment.S +++ b/arch/powerpc/kvm/book3s_segment.S @@ -161,8 +161,8 @@ kvmppc_handler_trampoline_enter_end: .global kvmppc_handler_trampoline_exit kvmppc_handler_trampoline_exit: -.global kvmppc_interrupt -kvmppc_interrupt: +.global kvmppc_interrupt_pr +kvmppc_interrupt_pr: /* Register usage at this point: * diff --git a/arch/powerpc/kvm/book3s_xics.c b/arch/powerpc/kvm/book3s_xics.c index a3a5cb8ee7ea..02a17dcf1610 100644 --- a/arch/powerpc/kvm/book3s_xics.c +++ b/arch/powerpc/kvm/book3s_xics.c @@ -818,7 +818,7 @@ int kvmppc_xics_hcall(struct kvm_vcpu *vcpu, u32 req) } /* Check for real mode returning too hard */ - if (xics->real_mode) + if (xics->real_mode && is_kvmppc_hv_enabled(vcpu->kvm)) return kvmppc_xics_rm_complete(vcpu, req); switch (req) { @@ -840,6 +840,7 @@ int kvmppc_xics_hcall(struct kvm_vcpu *vcpu, u32 req) return rc; } +EXPORT_SYMBOL_GPL(kvmppc_xics_hcall); /* -- Initialisation code etc. -- */ @@ -1250,13 +1251,13 @@ static int kvmppc_xics_create(struct kvm_device *dev, u32 type) xics_debugfs_init(xics); -#ifdef CONFIG_KVM_BOOK3S_64_HV +#ifdef CONFIG_KVM_BOOK3S_HV_POSSIBLE if (cpu_has_feature(CPU_FTR_ARCH_206)) { /* Enable real mode support */ xics->real_mode = ENABLE_REALMODE; xics->real_mode_dbg = DEBUG_REALMODE; } -#endif /* CONFIG_KVM_BOOK3S_64_HV */ +#endif /* CONFIG_KVM_BOOK3S_HV_POSSIBLE */ return 0; } diff --git a/arch/powerpc/kvm/booke.c b/arch/powerpc/kvm/booke.c index 5133199f6cb7..53e65a210b9a 100644 --- a/arch/powerpc/kvm/booke.c +++ b/arch/powerpc/kvm/booke.c @@ -40,7 +40,9 @@ #include "timing.h" #include "booke.h" -#include "trace.h" + +#define CREATE_TRACE_POINTS +#include "trace_booke.h" unsigned long kvmppc_booke_handlers; @@ -133,6 +135,29 @@ static void kvmppc_vcpu_sync_fpu(struct kvm_vcpu *vcpu) #endif } +static void kvmppc_vcpu_sync_debug(struct kvm_vcpu *vcpu) +{ + /* Synchronize guest's desire to get debug interrupts into shadow MSR */ +#ifndef CONFIG_KVM_BOOKE_HV + vcpu->arch.shadow_msr &= ~MSR_DE; + vcpu->arch.shadow_msr |= vcpu->arch.shared->msr & MSR_DE; +#endif + + /* Force enable debug interrupts when user space wants to debug */ + if (vcpu->guest_debug) { +#ifdef CONFIG_KVM_BOOKE_HV + /* + * Since there is no shadow MSR, sync MSR_DE into the guest + * visible MSR. + */ + vcpu->arch.shared->msr |= MSR_DE; +#else + vcpu->arch.shadow_msr |= MSR_DE; + vcpu->arch.shared->msr &= ~MSR_DE; +#endif + } +} + /* * Helper function for "full" MSR writes. No need to call this if only * EE/CE/ME/DE/RI are changing. @@ -150,6 +175,7 @@ void kvmppc_set_msr(struct kvm_vcpu *vcpu, u32 new_msr) kvmppc_mmu_msr_notify(vcpu, old_msr); kvmppc_vcpu_sync_spe(vcpu); kvmppc_vcpu_sync_fpu(vcpu); + kvmppc_vcpu_sync_debug(vcpu); } static void kvmppc_booke_queue_irqprio(struct kvm_vcpu *vcpu, @@ -655,6 +681,7 @@ int kvmppc_core_check_requests(struct kvm_vcpu *vcpu) int kvmppc_vcpu_run(struct kvm_run *kvm_run, struct kvm_vcpu *vcpu) { int ret, s; + struct thread_struct thread; #ifdef CONFIG_PPC_FPU struct thread_fp_state fp; int fpexc_mode; @@ -695,6 +722,12 @@ int kvmppc_vcpu_run(struct kvm_run *kvm_run, struct kvm_vcpu *vcpu) kvmppc_load_guest_fp(vcpu); #endif + /* Switch to guest debug context */ + thread.debug = vcpu->arch.shadow_dbg_reg; + switch_booke_debug_regs(&thread); + thread.debug = current->thread.debug; + current->thread.debug = vcpu->arch.shadow_dbg_reg; + kvmppc_fix_ee_before_entry(); ret = __kvmppc_vcpu_run(kvm_run, vcpu); @@ -702,6 +735,10 @@ int kvmppc_vcpu_run(struct kvm_run *kvm_run, struct kvm_vcpu *vcpu) /* No need for kvm_guest_exit. It's done in handle_exit. We also get here with interrupts enabled. */ + /* Switch back to user space debug context */ + switch_booke_debug_regs(&thread); + current->thread.debug = thread.debug; + #ifdef CONFIG_PPC_FPU kvmppc_save_guest_fp(vcpu); @@ -757,6 +794,30 @@ static int emulation_exit(struct kvm_run *run, struct kvm_vcpu *vcpu) } } +static int kvmppc_handle_debug(struct kvm_run *run, struct kvm_vcpu *vcpu) +{ + struct debug_reg *dbg_reg = &(vcpu->arch.shadow_dbg_reg); + u32 dbsr = vcpu->arch.dbsr; + + run->debug.arch.status = 0; + run->debug.arch.address = vcpu->arch.pc; + + if (dbsr & (DBSR_IAC1 | DBSR_IAC2 | DBSR_IAC3 | DBSR_IAC4)) { + run->debug.arch.status |= KVMPPC_DEBUG_BREAKPOINT; + } else { + if (dbsr & (DBSR_DAC1W | DBSR_DAC2W)) + run->debug.arch.status |= KVMPPC_DEBUG_WATCH_WRITE; + else if (dbsr & (DBSR_DAC1R | DBSR_DAC2R)) + run->debug.arch.status |= KVMPPC_DEBUG_WATCH_READ; + if (dbsr & (DBSR_DAC1R | DBSR_DAC1W)) + run->debug.arch.address = dbg_reg->dac1; + else if (dbsr & (DBSR_DAC2R | DBSR_DAC2W)) + run->debug.arch.address = dbg_reg->dac2; + } + + return RESUME_HOST; +} + static void kvmppc_fill_pt_regs(struct pt_regs *regs) { ulong r1, ip, msr, lr; @@ -817,6 +878,11 @@ static void kvmppc_restart_interrupt(struct kvm_vcpu *vcpu, case BOOKE_INTERRUPT_CRITICAL: unknown_exception(®s); break; + case BOOKE_INTERRUPT_DEBUG: + /* Save DBSR before preemption is enabled */ + vcpu->arch.dbsr = mfspr(SPRN_DBSR); + kvmppc_clear_dbsr(); + break; } } @@ -1134,18 +1200,10 @@ int kvmppc_handle_exit(struct kvm_run *run, struct kvm_vcpu *vcpu, } case BOOKE_INTERRUPT_DEBUG: { - u32 dbsr; - - vcpu->arch.pc = mfspr(SPRN_CSRR0); - - /* clear IAC events in DBSR register */ - dbsr = mfspr(SPRN_DBSR); - dbsr &= DBSR_IAC1 | DBSR_IAC2 | DBSR_IAC3 | DBSR_IAC4; - mtspr(SPRN_DBSR, dbsr); - - run->exit_reason = KVM_EXIT_DEBUG; + r = kvmppc_handle_debug(run, vcpu); + if (r == RESUME_HOST) + run->exit_reason = KVM_EXIT_DEBUG; kvmppc_account_exit(vcpu, DEBUG_EXITS); - r = RESUME_HOST; break; } @@ -1196,7 +1254,7 @@ int kvm_arch_vcpu_setup(struct kvm_vcpu *vcpu) kvmppc_set_msr(vcpu, 0); #ifndef CONFIG_KVM_BOOKE_HV - vcpu->arch.shadow_msr = MSR_USER | MSR_DE | MSR_IS | MSR_DS; + vcpu->arch.shadow_msr = MSR_USER | MSR_IS | MSR_DS; vcpu->arch.shadow_pid = 1; vcpu->arch.shared->msr = 0; #endif @@ -1358,7 +1416,7 @@ static int set_sregs_arch206(struct kvm_vcpu *vcpu, return 0; } -void kvmppc_get_sregs_ivor(struct kvm_vcpu *vcpu, struct kvm_sregs *sregs) +int kvmppc_get_sregs_ivor(struct kvm_vcpu *vcpu, struct kvm_sregs *sregs) { sregs->u.e.features |= KVM_SREGS_E_IVOR; @@ -1378,6 +1436,7 @@ void kvmppc_get_sregs_ivor(struct kvm_vcpu *vcpu, struct kvm_sregs *sregs) sregs->u.e.ivor_low[13] = vcpu->arch.ivor[BOOKE_IRQPRIO_DTLB_MISS]; sregs->u.e.ivor_low[14] = vcpu->arch.ivor[BOOKE_IRQPRIO_ITLB_MISS]; sregs->u.e.ivor_low[15] = vcpu->arch.ivor[BOOKE_IRQPRIO_DEBUG]; + return 0; } int kvmppc_set_sregs_ivor(struct kvm_vcpu *vcpu, struct kvm_sregs *sregs) @@ -1412,8 +1471,7 @@ int kvm_arch_vcpu_ioctl_get_sregs(struct kvm_vcpu *vcpu, get_sregs_base(vcpu, sregs); get_sregs_arch206(vcpu, sregs); - kvmppc_core_get_sregs(vcpu, sregs); - return 0; + return vcpu->kvm->arch.kvm_ops->get_sregs(vcpu, sregs); } int kvm_arch_vcpu_ioctl_set_sregs(struct kvm_vcpu *vcpu, @@ -1432,7 +1490,7 @@ int kvm_arch_vcpu_ioctl_set_sregs(struct kvm_vcpu *vcpu, if (ret < 0) return ret; - return kvmppc_core_set_sregs(vcpu, sregs); + return vcpu->kvm->arch.kvm_ops->set_sregs(vcpu, sregs); } int kvm_vcpu_ioctl_get_one_reg(struct kvm_vcpu *vcpu, struct kvm_one_reg *reg) @@ -1440,7 +1498,6 @@ int kvm_vcpu_ioctl_get_one_reg(struct kvm_vcpu *vcpu, struct kvm_one_reg *reg) int r = 0; union kvmppc_one_reg val; int size; - long int i; size = one_reg_size(reg->id); if (size > sizeof(val)) @@ -1448,16 +1505,24 @@ int kvm_vcpu_ioctl_get_one_reg(struct kvm_vcpu *vcpu, struct kvm_one_reg *reg) switch (reg->id) { case KVM_REG_PPC_IAC1: + val = get_reg_val(reg->id, vcpu->arch.dbg_reg.iac1); + break; case KVM_REG_PPC_IAC2: + val = get_reg_val(reg->id, vcpu->arch.dbg_reg.iac2); + break; +#if CONFIG_PPC_ADV_DEBUG_IACS > 2 case KVM_REG_PPC_IAC3: + val = get_reg_val(reg->id, vcpu->arch.dbg_reg.iac3); + break; case KVM_REG_PPC_IAC4: - i = reg->id - KVM_REG_PPC_IAC1; - val = get_reg_val(reg->id, vcpu->arch.dbg_reg.iac[i]); + val = get_reg_val(reg->id, vcpu->arch.dbg_reg.iac4); break; +#endif case KVM_REG_PPC_DAC1: + val = get_reg_val(reg->id, vcpu->arch.dbg_reg.dac1); + break; case KVM_REG_PPC_DAC2: - i = reg->id - KVM_REG_PPC_DAC1; - val = get_reg_val(reg->id, vcpu->arch.dbg_reg.dac[i]); + val = get_reg_val(reg->id, vcpu->arch.dbg_reg.dac2); break; case KVM_REG_PPC_EPR: { u32 epr = get_guest_epr(vcpu); @@ -1476,10 +1541,13 @@ int kvm_vcpu_ioctl_get_one_reg(struct kvm_vcpu *vcpu, struct kvm_one_reg *reg) val = get_reg_val(reg->id, vcpu->arch.tsr); break; case KVM_REG_PPC_DEBUG_INST: - val = get_reg_val(reg->id, KVMPPC_INST_EHPRIV); + val = get_reg_val(reg->id, KVMPPC_INST_EHPRIV_DEBUG); + break; + case KVM_REG_PPC_VRSAVE: + val = get_reg_val(reg->id, vcpu->arch.vrsave); break; default: - r = kvmppc_get_one_reg(vcpu, reg->id, &val); + r = vcpu->kvm->arch.kvm_ops->get_one_reg(vcpu, reg->id, &val); break; } @@ -1497,7 +1565,6 @@ int kvm_vcpu_ioctl_set_one_reg(struct kvm_vcpu *vcpu, struct kvm_one_reg *reg) int r = 0; union kvmppc_one_reg val; int size; - long int i; size = one_reg_size(reg->id); if (size > sizeof(val)) @@ -1508,16 +1575,24 @@ int kvm_vcpu_ioctl_set_one_reg(struct kvm_vcpu *vcpu, struct kvm_one_reg *reg) switch (reg->id) { case KVM_REG_PPC_IAC1: + vcpu->arch.dbg_reg.iac1 = set_reg_val(reg->id, val); + break; case KVM_REG_PPC_IAC2: + vcpu->arch.dbg_reg.iac2 = set_reg_val(reg->id, val); + break; +#if CONFIG_PPC_ADV_DEBUG_IACS > 2 case KVM_REG_PPC_IAC3: + vcpu->arch.dbg_reg.iac3 = set_reg_val(reg->id, val); + break; case KVM_REG_PPC_IAC4: - i = reg->id - KVM_REG_PPC_IAC1; - vcpu->arch.dbg_reg.iac[i] = set_reg_val(reg->id, val); + vcpu->arch.dbg_reg.iac4 = set_reg_val(reg->id, val); break; +#endif case KVM_REG_PPC_DAC1: + vcpu->arch.dbg_reg.dac1 = set_reg_val(reg->id, val); + break; case KVM_REG_PPC_DAC2: - i = reg->id - KVM_REG_PPC_DAC1; - vcpu->arch.dbg_reg.dac[i] = set_reg_val(reg->id, val); + vcpu->arch.dbg_reg.dac2 = set_reg_val(reg->id, val); break; case KVM_REG_PPC_EPR: { u32 new_epr = set_reg_val(reg->id, val); @@ -1551,20 +1626,17 @@ int kvm_vcpu_ioctl_set_one_reg(struct kvm_vcpu *vcpu, struct kvm_one_reg *reg) kvmppc_set_tcr(vcpu, tcr); break; } + case KVM_REG_PPC_VRSAVE: + vcpu->arch.vrsave = set_reg_val(reg->id, val); + break; default: - r = kvmppc_set_one_reg(vcpu, reg->id, &val); + r = vcpu->kvm->arch.kvm_ops->set_one_reg(vcpu, reg->id, &val); break; } return r; } -int kvm_arch_vcpu_ioctl_set_guest_debug(struct kvm_vcpu *vcpu, - struct kvm_guest_debug *dbg) -{ - return -EINVAL; -} - int kvm_arch_vcpu_ioctl_get_fpu(struct kvm_vcpu *vcpu, struct kvm_fpu *fpu) { return -ENOTSUPP; @@ -1589,12 +1661,12 @@ int kvm_vm_ioctl_get_dirty_log(struct kvm *kvm, struct kvm_dirty_log *log) return -ENOTSUPP; } -void kvmppc_core_free_memslot(struct kvm_memory_slot *free, +void kvmppc_core_free_memslot(struct kvm *kvm, struct kvm_memory_slot *free, struct kvm_memory_slot *dont) { } -int kvmppc_core_create_memslot(struct kvm_memory_slot *slot, +int kvmppc_core_create_memslot(struct kvm *kvm, struct kvm_memory_slot *slot, unsigned long npages) { return 0; @@ -1670,6 +1742,157 @@ void kvmppc_decrementer_func(unsigned long data) kvmppc_set_tsr_bits(vcpu, TSR_DIS); } +static int kvmppc_booke_add_breakpoint(struct debug_reg *dbg_reg, + uint64_t addr, int index) +{ + switch (index) { + case 0: + dbg_reg->dbcr0 |= DBCR0_IAC1; + dbg_reg->iac1 = addr; + break; + case 1: + dbg_reg->dbcr0 |= DBCR0_IAC2; + dbg_reg->iac2 = addr; + break; +#if CONFIG_PPC_ADV_DEBUG_IACS > 2 + case 2: + dbg_reg->dbcr0 |= DBCR0_IAC3; + dbg_reg->iac3 = addr; + break; + case 3: + dbg_reg->dbcr0 |= DBCR0_IAC4; + dbg_reg->iac4 = addr; + break; +#endif + default: + return -EINVAL; + } + + dbg_reg->dbcr0 |= DBCR0_IDM; + return 0; +} + +static int kvmppc_booke_add_watchpoint(struct debug_reg *dbg_reg, uint64_t addr, + int type, int index) +{ + switch (index) { + case 0: + if (type & KVMPPC_DEBUG_WATCH_READ) + dbg_reg->dbcr0 |= DBCR0_DAC1R; + if (type & KVMPPC_DEBUG_WATCH_WRITE) + dbg_reg->dbcr0 |= DBCR0_DAC1W; + dbg_reg->dac1 = addr; + break; + case 1: + if (type & KVMPPC_DEBUG_WATCH_READ) + dbg_reg->dbcr0 |= DBCR0_DAC2R; + if (type & KVMPPC_DEBUG_WATCH_WRITE) + dbg_reg->dbcr0 |= DBCR0_DAC2W; + dbg_reg->dac2 = addr; + break; + default: + return -EINVAL; + } + + dbg_reg->dbcr0 |= DBCR0_IDM; + return 0; +} +void kvm_guest_protect_msr(struct kvm_vcpu *vcpu, ulong prot_bitmap, bool set) +{ + /* XXX: Add similar MSR protection for BookE-PR */ +#ifdef CONFIG_KVM_BOOKE_HV + BUG_ON(prot_bitmap & ~(MSRP_UCLEP | MSRP_DEP | MSRP_PMMP)); + if (set) { + if (prot_bitmap & MSR_UCLE) + vcpu->arch.shadow_msrp |= MSRP_UCLEP; + if (prot_bitmap & MSR_DE) + vcpu->arch.shadow_msrp |= MSRP_DEP; + if (prot_bitmap & MSR_PMM) + vcpu->arch.shadow_msrp |= MSRP_PMMP; + } else { + if (prot_bitmap & MSR_UCLE) + vcpu->arch.shadow_msrp &= ~MSRP_UCLEP; + if (prot_bitmap & MSR_DE) + vcpu->arch.shadow_msrp &= ~MSRP_DEP; + if (prot_bitmap & MSR_PMM) + vcpu->arch.shadow_msrp &= ~MSRP_PMMP; + } +#endif +} + +int kvm_arch_vcpu_ioctl_set_guest_debug(struct kvm_vcpu *vcpu, + struct kvm_guest_debug *dbg) +{ + struct debug_reg *dbg_reg; + int n, b = 0, w = 0; + + if (!(dbg->control & KVM_GUESTDBG_ENABLE)) { + vcpu->arch.shadow_dbg_reg.dbcr0 = 0; + vcpu->guest_debug = 0; + kvm_guest_protect_msr(vcpu, MSR_DE, false); + return 0; + } + + kvm_guest_protect_msr(vcpu, MSR_DE, true); + vcpu->guest_debug = dbg->control; + vcpu->arch.shadow_dbg_reg.dbcr0 = 0; + /* Set DBCR0_EDM in guest visible DBCR0 register. */ + vcpu->arch.dbg_reg.dbcr0 = DBCR0_EDM; + + if (vcpu->guest_debug & KVM_GUESTDBG_SINGLESTEP) + vcpu->arch.shadow_dbg_reg.dbcr0 |= DBCR0_IDM | DBCR0_IC; + + /* Code below handles only HW breakpoints */ + dbg_reg = &(vcpu->arch.shadow_dbg_reg); + +#ifdef CONFIG_KVM_BOOKE_HV + /* + * On BookE-HV (e500mc) the guest is always executed with MSR.GS=1 + * DBCR1 and DBCR2 are set to trigger debug events when MSR.PR is 0 + */ + dbg_reg->dbcr1 = 0; + dbg_reg->dbcr2 = 0; +#else + /* + * On BookE-PR (e500v2) the guest is always executed with MSR.PR=1 + * We set DBCR1 and DBCR2 to only trigger debug events when MSR.PR + * is set. + */ + dbg_reg->dbcr1 = DBCR1_IAC1US | DBCR1_IAC2US | DBCR1_IAC3US | + DBCR1_IAC4US; + dbg_reg->dbcr2 = DBCR2_DAC1US | DBCR2_DAC2US; +#endif + + if (!(vcpu->guest_debug & KVM_GUESTDBG_USE_HW_BP)) + return 0; + + for (n = 0; n < (KVMPPC_BOOKE_IAC_NUM + KVMPPC_BOOKE_DAC_NUM); n++) { + uint64_t addr = dbg->arch.bp[n].addr; + uint32_t type = dbg->arch.bp[n].type; + + if (type == KVMPPC_DEBUG_NONE) + continue; + + if (type & !(KVMPPC_DEBUG_WATCH_READ | + KVMPPC_DEBUG_WATCH_WRITE | + KVMPPC_DEBUG_BREAKPOINT)) + return -EINVAL; + + if (type & KVMPPC_DEBUG_BREAKPOINT) { + /* Setting H/W breakpoint */ + if (kvmppc_booke_add_breakpoint(dbg_reg, addr, b++)) + return -EINVAL; + } else { + /* Setting H/W watchpoint */ + if (kvmppc_booke_add_watchpoint(dbg_reg, addr, + type, w++)) + return -EINVAL; + } + } + + return 0; +} + void kvmppc_booke_vcpu_load(struct kvm_vcpu *vcpu, int cpu) { vcpu->cpu = smp_processor_id(); @@ -1680,6 +1903,44 @@ void kvmppc_booke_vcpu_put(struct kvm_vcpu *vcpu) { current->thread.kvm_vcpu = NULL; vcpu->cpu = -1; + + /* Clear pending debug event in DBSR */ + kvmppc_clear_dbsr(); +} + +void kvmppc_mmu_destroy(struct kvm_vcpu *vcpu) +{ + vcpu->kvm->arch.kvm_ops->mmu_destroy(vcpu); +} + +int kvmppc_core_init_vm(struct kvm *kvm) +{ + return kvm->arch.kvm_ops->init_vm(kvm); +} + +struct kvm_vcpu *kvmppc_core_vcpu_create(struct kvm *kvm, unsigned int id) +{ + return kvm->arch.kvm_ops->vcpu_create(kvm, id); +} + +void kvmppc_core_vcpu_free(struct kvm_vcpu *vcpu) +{ + vcpu->kvm->arch.kvm_ops->vcpu_free(vcpu); +} + +void kvmppc_core_destroy_vm(struct kvm *kvm) +{ + kvm->arch.kvm_ops->destroy_vm(kvm); +} + +void kvmppc_core_vcpu_load(struct kvm_vcpu *vcpu, int cpu) +{ + vcpu->kvm->arch.kvm_ops->vcpu_load(vcpu, cpu); +} + +void kvmppc_core_vcpu_put(struct kvm_vcpu *vcpu) +{ + vcpu->kvm->arch.kvm_ops->vcpu_put(vcpu); } int __init kvmppc_booke_init(void) diff --git a/arch/powerpc/kvm/booke.h b/arch/powerpc/kvm/booke.h index 5fd1ba693579..09bfd9bc7cf8 100644 --- a/arch/powerpc/kvm/booke.h +++ b/arch/powerpc/kvm/booke.h @@ -99,6 +99,30 @@ enum int_class { void kvmppc_set_pending_interrupt(struct kvm_vcpu *vcpu, enum int_class type); +extern void kvmppc_mmu_destroy_44x(struct kvm_vcpu *vcpu); +extern int kvmppc_core_emulate_op_44x(struct kvm_run *run, struct kvm_vcpu *vcpu, + unsigned int inst, int *advance); +extern int kvmppc_core_emulate_mtspr_44x(struct kvm_vcpu *vcpu, int sprn, + ulong spr_val); +extern int kvmppc_core_emulate_mfspr_44x(struct kvm_vcpu *vcpu, int sprn, + ulong *spr_val); +extern void kvmppc_mmu_destroy_e500(struct kvm_vcpu *vcpu); +extern int kvmppc_core_emulate_op_e500(struct kvm_run *run, + struct kvm_vcpu *vcpu, + unsigned int inst, int *advance); +extern int kvmppc_core_emulate_mtspr_e500(struct kvm_vcpu *vcpu, int sprn, + ulong spr_val); +extern int kvmppc_core_emulate_mfspr_e500(struct kvm_vcpu *vcpu, int sprn, + ulong *spr_val); +extern void kvmppc_mmu_destroy_e500(struct kvm_vcpu *vcpu); +extern int kvmppc_core_emulate_op_e500(struct kvm_run *run, + struct kvm_vcpu *vcpu, + unsigned int inst, int *advance); +extern int kvmppc_core_emulate_mtspr_e500(struct kvm_vcpu *vcpu, int sprn, + ulong spr_val); +extern int kvmppc_core_emulate_mfspr_e500(struct kvm_vcpu *vcpu, int sprn, + ulong *spr_val); + /* * Load up guest vcpu FP state if it's needed. * It also set the MSR_FP in thread so that host know @@ -129,4 +153,9 @@ static inline void kvmppc_save_guest_fp(struct kvm_vcpu *vcpu) giveup_fpu(current); #endif } + +static inline void kvmppc_clear_dbsr(void) +{ + mtspr(SPRN_DBSR, mfspr(SPRN_DBSR)); +} #endif /* __KVM_BOOKE_H__ */ diff --git a/arch/powerpc/kvm/e500.c b/arch/powerpc/kvm/e500.c index ce6b73c29612..497b142f651c 100644 --- a/arch/powerpc/kvm/e500.c +++ b/arch/powerpc/kvm/e500.c @@ -305,7 +305,7 @@ void kvmppc_core_load_guest_debugstate(struct kvm_vcpu *vcpu) { } -void kvmppc_core_vcpu_load(struct kvm_vcpu *vcpu, int cpu) +static void kvmppc_core_vcpu_load_e500(struct kvm_vcpu *vcpu, int cpu) { kvmppc_booke_vcpu_load(vcpu, cpu); @@ -313,7 +313,7 @@ void kvmppc_core_vcpu_load(struct kvm_vcpu *vcpu, int cpu) kvmppc_e500_recalc_shadow_pid(to_e500(vcpu)); } -void kvmppc_core_vcpu_put(struct kvm_vcpu *vcpu) +static void kvmppc_core_vcpu_put_e500(struct kvm_vcpu *vcpu) { #ifdef CONFIG_SPE if (vcpu->arch.shadow_msr & MSR_SPE) @@ -367,7 +367,8 @@ int kvmppc_core_vcpu_setup(struct kvm_vcpu *vcpu) return 0; } -void kvmppc_core_get_sregs(struct kvm_vcpu *vcpu, struct kvm_sregs *sregs) +static int kvmppc_core_get_sregs_e500(struct kvm_vcpu *vcpu, + struct kvm_sregs *sregs) { struct kvmppc_vcpu_e500 *vcpu_e500 = to_e500(vcpu); @@ -388,9 +389,11 @@ void kvmppc_core_get_sregs(struct kvm_vcpu *vcpu, struct kvm_sregs *sregs) kvmppc_get_sregs_ivor(vcpu, sregs); kvmppc_get_sregs_e500_tlb(vcpu, sregs); + return 0; } -int kvmppc_core_set_sregs(struct kvm_vcpu *vcpu, struct kvm_sregs *sregs) +static int kvmppc_core_set_sregs_e500(struct kvm_vcpu *vcpu, + struct kvm_sregs *sregs) { struct kvmppc_vcpu_e500 *vcpu_e500 = to_e500(vcpu); int ret; @@ -425,21 +428,22 @@ int kvmppc_core_set_sregs(struct kvm_vcpu *vcpu, struct kvm_sregs *sregs) return kvmppc_set_sregs_ivor(vcpu, sregs); } -int kvmppc_get_one_reg(struct kvm_vcpu *vcpu, u64 id, - union kvmppc_one_reg *val) +static int kvmppc_get_one_reg_e500(struct kvm_vcpu *vcpu, u64 id, + union kvmppc_one_reg *val) { int r = kvmppc_get_one_reg_e500_tlb(vcpu, id, val); return r; } -int kvmppc_set_one_reg(struct kvm_vcpu *vcpu, u64 id, - union kvmppc_one_reg *val) +static int kvmppc_set_one_reg_e500(struct kvm_vcpu *vcpu, u64 id, + union kvmppc_one_reg *val) { int r = kvmppc_get_one_reg_e500_tlb(vcpu, id, val); return r; } -struct kvm_vcpu *kvmppc_core_vcpu_create(struct kvm *kvm, unsigned int id) +static struct kvm_vcpu *kvmppc_core_vcpu_create_e500(struct kvm *kvm, + unsigned int id) { struct kvmppc_vcpu_e500 *vcpu_e500; struct kvm_vcpu *vcpu; @@ -481,7 +485,7 @@ out: return ERR_PTR(err); } -void kvmppc_core_vcpu_free(struct kvm_vcpu *vcpu) +static void kvmppc_core_vcpu_free_e500(struct kvm_vcpu *vcpu) { struct kvmppc_vcpu_e500 *vcpu_e500 = to_e500(vcpu); @@ -492,15 +496,32 @@ void kvmppc_core_vcpu_free(struct kvm_vcpu *vcpu) kmem_cache_free(kvm_vcpu_cache, vcpu_e500); } -int kvmppc_core_init_vm(struct kvm *kvm) +static int kvmppc_core_init_vm_e500(struct kvm *kvm) { return 0; } -void kvmppc_core_destroy_vm(struct kvm *kvm) +static void kvmppc_core_destroy_vm_e500(struct kvm *kvm) { } +static struct kvmppc_ops kvm_ops_e500 = { + .get_sregs = kvmppc_core_get_sregs_e500, + .set_sregs = kvmppc_core_set_sregs_e500, + .get_one_reg = kvmppc_get_one_reg_e500, + .set_one_reg = kvmppc_set_one_reg_e500, + .vcpu_load = kvmppc_core_vcpu_load_e500, + .vcpu_put = kvmppc_core_vcpu_put_e500, + .vcpu_create = kvmppc_core_vcpu_create_e500, + .vcpu_free = kvmppc_core_vcpu_free_e500, + .mmu_destroy = kvmppc_mmu_destroy_e500, + .init_vm = kvmppc_core_init_vm_e500, + .destroy_vm = kvmppc_core_destroy_vm_e500, + .emulate_op = kvmppc_core_emulate_op_e500, + .emulate_mtspr = kvmppc_core_emulate_mtspr_e500, + .emulate_mfspr = kvmppc_core_emulate_mfspr_e500, +}; + static int __init kvmppc_e500_init(void) { int r, i; @@ -512,11 +533,11 @@ static int __init kvmppc_e500_init(void) r = kvmppc_core_check_processor_compat(); if (r) - return r; + goto err_out; r = kvmppc_booke_init(); if (r) - return r; + goto err_out; /* copy extra E500 exception handlers */ ivor[0] = mfspr(SPRN_IVOR32); @@ -534,11 +555,19 @@ static int __init kvmppc_e500_init(void) flush_icache_range(kvmppc_booke_handlers, kvmppc_booke_handlers + ivor[max_ivor] + handler_len); - return kvm_init(NULL, sizeof(struct kvmppc_vcpu_e500), 0, THIS_MODULE); + r = kvm_init(NULL, sizeof(struct kvmppc_vcpu_e500), 0, THIS_MODULE); + if (r) + goto err_out; + kvm_ops_e500.owner = THIS_MODULE; + kvmppc_pr_ops = &kvm_ops_e500; + +err_out: + return r; } static void __exit kvmppc_e500_exit(void) { + kvmppc_pr_ops = NULL; kvmppc_booke_exit(); } diff --git a/arch/powerpc/kvm/e500.h b/arch/powerpc/kvm/e500.h index c2e5e98453a6..4fd9650eb018 100644 --- a/arch/powerpc/kvm/e500.h +++ b/arch/powerpc/kvm/e500.h @@ -117,7 +117,7 @@ static inline struct kvmppc_vcpu_e500 *to_e500(struct kvm_vcpu *vcpu) #define E500_TLB_USER_PERM_MASK (MAS3_UX|MAS3_UR|MAS3_UW) #define E500_TLB_SUPER_PERM_MASK (MAS3_SX|MAS3_SR|MAS3_SW) #define MAS2_ATTRIB_MASK \ - (MAS2_X0 | MAS2_X1) + (MAS2_X0 | MAS2_X1 | MAS2_E | MAS2_G) #define MAS3_ATTRIB_MASK \ (MAS3_U0 | MAS3_U1 | MAS3_U2 | MAS3_U3 \ | E500_TLB_USER_PERM_MASK | E500_TLB_SUPER_PERM_MASK) diff --git a/arch/powerpc/kvm/e500_emulate.c b/arch/powerpc/kvm/e500_emulate.c index b10a01243abd..89b7f821f6c4 100644 --- a/arch/powerpc/kvm/e500_emulate.c +++ b/arch/powerpc/kvm/e500_emulate.c @@ -26,6 +26,7 @@ #define XOP_TLBRE 946 #define XOP_TLBWE 978 #define XOP_TLBILX 18 +#define XOP_EHPRIV 270 #ifdef CONFIG_KVM_E500MC static int dbell2prio(ulong param) @@ -82,8 +83,28 @@ static int kvmppc_e500_emul_msgsnd(struct kvm_vcpu *vcpu, int rb) } #endif -int kvmppc_core_emulate_op(struct kvm_run *run, struct kvm_vcpu *vcpu, - unsigned int inst, int *advance) +static int kvmppc_e500_emul_ehpriv(struct kvm_run *run, struct kvm_vcpu *vcpu, + unsigned int inst, int *advance) +{ + int emulated = EMULATE_DONE; + + switch (get_oc(inst)) { + case EHPRIV_OC_DEBUG: + run->exit_reason = KVM_EXIT_DEBUG; + run->debug.arch.address = vcpu->arch.pc; + run->debug.arch.status = 0; + kvmppc_account_exit(vcpu, DEBUG_EXITS); + emulated = EMULATE_EXIT_USER; + *advance = 0; + break; + default: + emulated = EMULATE_FAIL; + } + return emulated; +} + +int kvmppc_core_emulate_op_e500(struct kvm_run *run, struct kvm_vcpu *vcpu, + unsigned int inst, int *advance) { int emulated = EMULATE_DONE; int ra = get_ra(inst); @@ -130,6 +151,11 @@ int kvmppc_core_emulate_op(struct kvm_run *run, struct kvm_vcpu *vcpu, emulated = kvmppc_e500_emul_tlbivax(vcpu, ea); break; + case XOP_EHPRIV: + emulated = kvmppc_e500_emul_ehpriv(run, vcpu, inst, + advance); + break; + default: emulated = EMULATE_FAIL; } @@ -146,7 +172,7 @@ int kvmppc_core_emulate_op(struct kvm_run *run, struct kvm_vcpu *vcpu, return emulated; } -int kvmppc_core_emulate_mtspr(struct kvm_vcpu *vcpu, int sprn, ulong spr_val) +int kvmppc_core_emulate_mtspr_e500(struct kvm_vcpu *vcpu, int sprn, ulong spr_val) { struct kvmppc_vcpu_e500 *vcpu_e500 = to_e500(vcpu); int emulated = EMULATE_DONE; @@ -237,7 +263,7 @@ int kvmppc_core_emulate_mtspr(struct kvm_vcpu *vcpu, int sprn, ulong spr_val) return emulated; } -int kvmppc_core_emulate_mfspr(struct kvm_vcpu *vcpu, int sprn, ulong *spr_val) +int kvmppc_core_emulate_mfspr_e500(struct kvm_vcpu *vcpu, int sprn, ulong *spr_val) { struct kvmppc_vcpu_e500 *vcpu_e500 = to_e500(vcpu); int emulated = EMULATE_DONE; diff --git a/arch/powerpc/kvm/e500_mmu.c b/arch/powerpc/kvm/e500_mmu.c index 6d6f153b6c1d..ebca6b88ea5e 100644 --- a/arch/powerpc/kvm/e500_mmu.c +++ b/arch/powerpc/kvm/e500_mmu.c @@ -32,7 +32,7 @@ #include <asm/kvm_ppc.h> #include "e500.h" -#include "trace.h" +#include "trace_booke.h" #include "timing.h" #include "e500_mmu_host.h" @@ -536,7 +536,7 @@ gpa_t kvmppc_mmu_xlate(struct kvm_vcpu *vcpu, unsigned int index, return get_tlb_raddr(gtlbe) | (eaddr & pgmask); } -void kvmppc_mmu_destroy(struct kvm_vcpu *vcpu) +void kvmppc_mmu_destroy_e500(struct kvm_vcpu *vcpu) { } diff --git a/arch/powerpc/kvm/e500_mmu_host.c b/arch/powerpc/kvm/e500_mmu_host.c index c65593abae8e..ecf2247b13be 100644 --- a/arch/powerpc/kvm/e500_mmu_host.c +++ b/arch/powerpc/kvm/e500_mmu_host.c @@ -32,10 +32,11 @@ #include <asm/kvm_ppc.h> #include "e500.h" -#include "trace.h" #include "timing.h" #include "e500_mmu_host.h" +#include "trace_booke.h" + #define to_htlb1_esel(esel) (host_tlb_params[1].entries - (esel) - 1) static struct kvmppc_e500_tlb_params host_tlb_params[E500_TLB_NUM]; @@ -253,6 +254,9 @@ static inline void kvmppc_e500_ref_setup(struct tlbe_ref *ref, ref->pfn = pfn; ref->flags |= E500_TLB_VALID; + /* Mark the page accessed */ + kvm_set_pfn_accessed(pfn); + if (tlbe_is_writable(gtlbe)) kvm_set_pfn_dirty(pfn); } diff --git a/arch/powerpc/kvm/e500mc.c b/arch/powerpc/kvm/e500mc.c index 19c8379575f7..4132cd2fc171 100644 --- a/arch/powerpc/kvm/e500mc.c +++ b/arch/powerpc/kvm/e500mc.c @@ -110,7 +110,7 @@ void kvmppc_mmu_msr_notify(struct kvm_vcpu *vcpu, u32 old_msr) static DEFINE_PER_CPU(struct kvm_vcpu *, last_vcpu_on_cpu); -void kvmppc_core_vcpu_load(struct kvm_vcpu *vcpu, int cpu) +static void kvmppc_core_vcpu_load_e500mc(struct kvm_vcpu *vcpu, int cpu) { struct kvmppc_vcpu_e500 *vcpu_e500 = to_e500(vcpu); @@ -147,7 +147,7 @@ void kvmppc_core_vcpu_load(struct kvm_vcpu *vcpu, int cpu) kvmppc_load_guest_fp(vcpu); } -void kvmppc_core_vcpu_put(struct kvm_vcpu *vcpu) +static void kvmppc_core_vcpu_put_e500mc(struct kvm_vcpu *vcpu) { vcpu->arch.eplc = mfspr(SPRN_EPLC); vcpu->arch.epsc = mfspr(SPRN_EPSC); @@ -204,7 +204,8 @@ int kvmppc_core_vcpu_setup(struct kvm_vcpu *vcpu) return 0; } -void kvmppc_core_get_sregs(struct kvm_vcpu *vcpu, struct kvm_sregs *sregs) +static int kvmppc_core_get_sregs_e500mc(struct kvm_vcpu *vcpu, + struct kvm_sregs *sregs) { struct kvmppc_vcpu_e500 *vcpu_e500 = to_e500(vcpu); @@ -224,10 +225,11 @@ void kvmppc_core_get_sregs(struct kvm_vcpu *vcpu, struct kvm_sregs *sregs) sregs->u.e.ivor_high[4] = vcpu->arch.ivor[BOOKE_IRQPRIO_DBELL]; sregs->u.e.ivor_high[5] = vcpu->arch.ivor[BOOKE_IRQPRIO_DBELL_CRIT]; - kvmppc_get_sregs_ivor(vcpu, sregs); + return kvmppc_get_sregs_ivor(vcpu, sregs); } -int kvmppc_core_set_sregs(struct kvm_vcpu *vcpu, struct kvm_sregs *sregs) +static int kvmppc_core_set_sregs_e500mc(struct kvm_vcpu *vcpu, + struct kvm_sregs *sregs) { struct kvmppc_vcpu_e500 *vcpu_e500 = to_e500(vcpu); int ret; @@ -260,21 +262,22 @@ int kvmppc_core_set_sregs(struct kvm_vcpu *vcpu, struct kvm_sregs *sregs) return kvmppc_set_sregs_ivor(vcpu, sregs); } -int kvmppc_get_one_reg(struct kvm_vcpu *vcpu, u64 id, - union kvmppc_one_reg *val) +static int kvmppc_get_one_reg_e500mc(struct kvm_vcpu *vcpu, u64 id, + union kvmppc_one_reg *val) { int r = kvmppc_get_one_reg_e500_tlb(vcpu, id, val); return r; } -int kvmppc_set_one_reg(struct kvm_vcpu *vcpu, u64 id, - union kvmppc_one_reg *val) +static int kvmppc_set_one_reg_e500mc(struct kvm_vcpu *vcpu, u64 id, + union kvmppc_one_reg *val) { int r = kvmppc_set_one_reg_e500_tlb(vcpu, id, val); return r; } -struct kvm_vcpu *kvmppc_core_vcpu_create(struct kvm *kvm, unsigned int id) +static struct kvm_vcpu *kvmppc_core_vcpu_create_e500mc(struct kvm *kvm, + unsigned int id) { struct kvmppc_vcpu_e500 *vcpu_e500; struct kvm_vcpu *vcpu; @@ -315,7 +318,7 @@ out: return ERR_PTR(err); } -void kvmppc_core_vcpu_free(struct kvm_vcpu *vcpu) +static void kvmppc_core_vcpu_free_e500mc(struct kvm_vcpu *vcpu) { struct kvmppc_vcpu_e500 *vcpu_e500 = to_e500(vcpu); @@ -325,7 +328,7 @@ void kvmppc_core_vcpu_free(struct kvm_vcpu *vcpu) kmem_cache_free(kvm_vcpu_cache, vcpu_e500); } -int kvmppc_core_init_vm(struct kvm *kvm) +static int kvmppc_core_init_vm_e500mc(struct kvm *kvm) { int lpid; @@ -337,27 +340,52 @@ int kvmppc_core_init_vm(struct kvm *kvm) return 0; } -void kvmppc_core_destroy_vm(struct kvm *kvm) +static void kvmppc_core_destroy_vm_e500mc(struct kvm *kvm) { kvmppc_free_lpid(kvm->arch.lpid); } +static struct kvmppc_ops kvm_ops_e500mc = { + .get_sregs = kvmppc_core_get_sregs_e500mc, + .set_sregs = kvmppc_core_set_sregs_e500mc, + .get_one_reg = kvmppc_get_one_reg_e500mc, + .set_one_reg = kvmppc_set_one_reg_e500mc, + .vcpu_load = kvmppc_core_vcpu_load_e500mc, + .vcpu_put = kvmppc_core_vcpu_put_e500mc, + .vcpu_create = kvmppc_core_vcpu_create_e500mc, + .vcpu_free = kvmppc_core_vcpu_free_e500mc, + .mmu_destroy = kvmppc_mmu_destroy_e500, + .init_vm = kvmppc_core_init_vm_e500mc, + .destroy_vm = kvmppc_core_destroy_vm_e500mc, + .emulate_op = kvmppc_core_emulate_op_e500, + .emulate_mtspr = kvmppc_core_emulate_mtspr_e500, + .emulate_mfspr = kvmppc_core_emulate_mfspr_e500, +}; + static int __init kvmppc_e500mc_init(void) { int r; r = kvmppc_booke_init(); if (r) - return r; + goto err_out; kvmppc_init_lpid(64); kvmppc_claim_lpid(0); /* host */ - return kvm_init(NULL, sizeof(struct kvmppc_vcpu_e500), 0, THIS_MODULE); + r = kvm_init(NULL, sizeof(struct kvmppc_vcpu_e500), 0, THIS_MODULE); + if (r) + goto err_out; + kvm_ops_e500mc.owner = THIS_MODULE; + kvmppc_pr_ops = &kvm_ops_e500mc; + +err_out: + return r; } static void __exit kvmppc_e500mc_exit(void) { + kvmppc_pr_ops = NULL; kvmppc_booke_exit(); } diff --git a/arch/powerpc/kvm/emulate.c b/arch/powerpc/kvm/emulate.c index 751cd45f65a0..2f9a0873b44f 100644 --- a/arch/powerpc/kvm/emulate.c +++ b/arch/powerpc/kvm/emulate.c @@ -130,8 +130,8 @@ static int kvmppc_emulate_mtspr(struct kvm_vcpu *vcpu, int sprn, int rs) case SPRN_PIR: break; default: - emulated = kvmppc_core_emulate_mtspr(vcpu, sprn, - spr_val); + emulated = vcpu->kvm->arch.kvm_ops->emulate_mtspr(vcpu, sprn, + spr_val); if (emulated == EMULATE_FAIL) printk(KERN_INFO "mtspr: unknown spr " "0x%x\n", sprn); @@ -191,8 +191,8 @@ static int kvmppc_emulate_mfspr(struct kvm_vcpu *vcpu, int sprn, int rt) spr_val = kvmppc_get_dec(vcpu, get_tb()); break; default: - emulated = kvmppc_core_emulate_mfspr(vcpu, sprn, - &spr_val); + emulated = vcpu->kvm->arch.kvm_ops->emulate_mfspr(vcpu, sprn, + &spr_val); if (unlikely(emulated == EMULATE_FAIL)) { printk(KERN_INFO "mfspr: unknown spr " "0x%x\n", sprn); @@ -464,7 +464,8 @@ int kvmppc_emulate_instruction(struct kvm_run *run, struct kvm_vcpu *vcpu) } if (emulated == EMULATE_FAIL) { - emulated = kvmppc_core_emulate_op(run, vcpu, inst, &advance); + emulated = vcpu->kvm->arch.kvm_ops->emulate_op(run, vcpu, inst, + &advance); if (emulated == EMULATE_AGAIN) { advance = 0; } else if (emulated == EMULATE_FAIL) { @@ -483,3 +484,4 @@ int kvmppc_emulate_instruction(struct kvm_run *run, struct kvm_vcpu *vcpu) return emulated; } +EXPORT_SYMBOL_GPL(kvmppc_emulate_instruction); diff --git a/arch/powerpc/kvm/powerpc.c b/arch/powerpc/kvm/powerpc.c index 07c0106fab76..9ae97686e9f4 100644 --- a/arch/powerpc/kvm/powerpc.c +++ b/arch/powerpc/kvm/powerpc.c @@ -26,6 +26,7 @@ #include <linux/fs.h> #include <linux/slab.h> #include <linux/file.h> +#include <linux/module.h> #include <asm/cputable.h> #include <asm/uaccess.h> #include <asm/kvm_ppc.h> @@ -39,6 +40,12 @@ #define CREATE_TRACE_POINTS #include "trace.h" +struct kvmppc_ops *kvmppc_hv_ops; +EXPORT_SYMBOL_GPL(kvmppc_hv_ops); +struct kvmppc_ops *kvmppc_pr_ops; +EXPORT_SYMBOL_GPL(kvmppc_pr_ops); + + int kvm_arch_vcpu_runnable(struct kvm_vcpu *v) { return !!(v->arch.pending_exceptions) || @@ -50,7 +57,6 @@ int kvm_arch_vcpu_should_kick(struct kvm_vcpu *vcpu) return 1; } -#ifndef CONFIG_KVM_BOOK3S_64_HV /* * Common checks before entering the guest world. Call with interrupts * disabled. @@ -125,7 +131,7 @@ int kvmppc_prepare_to_enter(struct kvm_vcpu *vcpu) return r; } -#endif /* CONFIG_KVM_BOOK3S_64_HV */ +EXPORT_SYMBOL_GPL(kvmppc_prepare_to_enter); int kvmppc_kvm_pv(struct kvm_vcpu *vcpu) { @@ -179,6 +185,7 @@ int kvmppc_kvm_pv(struct kvm_vcpu *vcpu) return r; } +EXPORT_SYMBOL_GPL(kvmppc_kvm_pv); int kvmppc_sanity_check(struct kvm_vcpu *vcpu) { @@ -192,11 +199,9 @@ int kvmppc_sanity_check(struct kvm_vcpu *vcpu) if ((vcpu->arch.cpu_type != KVM_CPU_3S_64) && vcpu->arch.papr_enabled) goto out; -#ifdef CONFIG_KVM_BOOK3S_64_HV /* HV KVM can only do PAPR mode for now */ - if (!vcpu->arch.papr_enabled) + if (!vcpu->arch.papr_enabled && is_kvmppc_hv_enabled(vcpu->kvm)) goto out; -#endif #ifdef CONFIG_KVM_BOOKE_HV if (!cpu_has_feature(CPU_FTR_EMB_HV)) @@ -209,6 +214,7 @@ out: vcpu->arch.sane = r; return r ? 0 : -EINVAL; } +EXPORT_SYMBOL_GPL(kvmppc_sanity_check); int kvmppc_emulate_mmio(struct kvm_run *run, struct kvm_vcpu *vcpu) { @@ -243,6 +249,7 @@ int kvmppc_emulate_mmio(struct kvm_run *run, struct kvm_vcpu *vcpu) return r; } +EXPORT_SYMBOL_GPL(kvmppc_emulate_mmio); int kvm_arch_hardware_enable(void *garbage) { @@ -269,10 +276,35 @@ void kvm_arch_check_processor_compat(void *rtn) int kvm_arch_init_vm(struct kvm *kvm, unsigned long type) { - if (type) - return -EINVAL; - + struct kvmppc_ops *kvm_ops = NULL; + /* + * if we have both HV and PR enabled, default is HV + */ + if (type == 0) { + if (kvmppc_hv_ops) + kvm_ops = kvmppc_hv_ops; + else + kvm_ops = kvmppc_pr_ops; + if (!kvm_ops) + goto err_out; + } else if (type == KVM_VM_PPC_HV) { + if (!kvmppc_hv_ops) + goto err_out; + kvm_ops = kvmppc_hv_ops; + } else if (type == KVM_VM_PPC_PR) { + if (!kvmppc_pr_ops) + goto err_out; + kvm_ops = kvmppc_pr_ops; + } else + goto err_out; + + if (kvm_ops->owner && !try_module_get(kvm_ops->owner)) + return -ENOENT; + + kvm->arch.kvm_ops = kvm_ops; return kvmppc_core_init_vm(kvm); +err_out: + return -EINVAL; } void kvm_arch_destroy_vm(struct kvm *kvm) @@ -292,6 +324,9 @@ void kvm_arch_destroy_vm(struct kvm *kvm) kvmppc_core_destroy_vm(kvm); mutex_unlock(&kvm->lock); + + /* drop the module reference */ + module_put(kvm->arch.kvm_ops->owner); } void kvm_arch_sync_events(struct kvm *kvm) @@ -301,6 +336,10 @@ void kvm_arch_sync_events(struct kvm *kvm) int kvm_dev_ioctl_check_extension(long ext) { int r; + /* FIXME!! + * Should some of this be vm ioctl ? is it possible now ? + */ + int hv_enabled = kvmppc_hv_ops ? 1 : 0; switch (ext) { #ifdef CONFIG_BOOKE @@ -320,22 +359,26 @@ int kvm_dev_ioctl_check_extension(long ext) case KVM_CAP_DEVICE_CTRL: r = 1; break; -#ifndef CONFIG_KVM_BOOK3S_64_HV case KVM_CAP_PPC_PAIRED_SINGLES: case KVM_CAP_PPC_OSI: case KVM_CAP_PPC_GET_PVINFO: #if defined(CONFIG_KVM_E500V2) || defined(CONFIG_KVM_E500MC) case KVM_CAP_SW_TLB: #endif -#ifdef CONFIG_KVM_MPIC - case KVM_CAP_IRQ_MPIC: -#endif - r = 1; + /* We support this only for PR */ + r = !hv_enabled; break; +#ifdef CONFIG_KVM_MMIO case KVM_CAP_COALESCED_MMIO: r = KVM_COALESCED_MMIO_PAGE_OFFSET; break; #endif +#ifdef CONFIG_KVM_MPIC + case KVM_CAP_IRQ_MPIC: + r = 1; + break; +#endif + #ifdef CONFIG_PPC_BOOK3S_64 case KVM_CAP_SPAPR_TCE: case KVM_CAP_PPC_ALLOC_HTAB: @@ -346,32 +389,37 @@ int kvm_dev_ioctl_check_extension(long ext) r = 1; break; #endif /* CONFIG_PPC_BOOK3S_64 */ -#ifdef CONFIG_KVM_BOOK3S_64_HV +#ifdef CONFIG_KVM_BOOK3S_HV_POSSIBLE case KVM_CAP_PPC_SMT: - r = threads_per_core; + if (hv_enabled) + r = threads_per_core; + else + r = 0; break; case KVM_CAP_PPC_RMA: - r = 1; + r = hv_enabled; /* PPC970 requires an RMA */ - if (cpu_has_feature(CPU_FTR_ARCH_201)) + if (r && cpu_has_feature(CPU_FTR_ARCH_201)) r = 2; break; #endif case KVM_CAP_SYNC_MMU: -#ifdef CONFIG_KVM_BOOK3S_64_HV - r = cpu_has_feature(CPU_FTR_ARCH_206) ? 1 : 0; +#ifdef CONFIG_KVM_BOOK3S_HV_POSSIBLE + if (hv_enabled) + r = cpu_has_feature(CPU_FTR_ARCH_206) ? 1 : 0; + else + r = 0; #elif defined(KVM_ARCH_WANT_MMU_NOTIFIER) r = 1; #else r = 0; - break; #endif -#ifdef CONFIG_KVM_BOOK3S_64_HV + break; +#ifdef CONFIG_KVM_BOOK3S_HV_POSSIBLE case KVM_CAP_PPC_HTAB_FD: - r = 1; + r = hv_enabled; break; #endif - break; case KVM_CAP_NR_VCPUS: /* * Recommending a number of CPUs is somewhat arbitrary; we @@ -379,11 +427,10 @@ int kvm_dev_ioctl_check_extension(long ext) * will have secondary threads "offline"), and for other KVM * implementations just count online CPUs. */ -#ifdef CONFIG_KVM_BOOK3S_64_HV - r = num_present_cpus(); -#else - r = num_online_cpus(); -#endif + if (hv_enabled) + r = num_present_cpus(); + else + r = num_online_cpus(); break; case KVM_CAP_MAX_VCPUS: r = KVM_MAX_VCPUS; @@ -407,15 +454,16 @@ long kvm_arch_dev_ioctl(struct file *filp, return -EINVAL; } -void kvm_arch_free_memslot(struct kvm_memory_slot *free, +void kvm_arch_free_memslot(struct kvm *kvm, struct kvm_memory_slot *free, struct kvm_memory_slot *dont) { - kvmppc_core_free_memslot(free, dont); + kvmppc_core_free_memslot(kvm, free, dont); } -int kvm_arch_create_memslot(struct kvm_memory_slot *slot, unsigned long npages) +int kvm_arch_create_memslot(struct kvm *kvm, struct kvm_memory_slot *slot, + unsigned long npages) { - return kvmppc_core_create_memslot(slot, npages); + return kvmppc_core_create_memslot(kvm, slot, npages); } void kvm_arch_memslots_updated(struct kvm *kvm) @@ -659,6 +707,7 @@ int kvmppc_handle_load(struct kvm_run *run, struct kvm_vcpu *vcpu, return EMULATE_DO_MMIO; } +EXPORT_SYMBOL_GPL(kvmppc_handle_load); /* Same as above, but sign extends */ int kvmppc_handle_loads(struct kvm_run *run, struct kvm_vcpu *vcpu, @@ -720,6 +769,7 @@ int kvmppc_handle_store(struct kvm_run *run, struct kvm_vcpu *vcpu, return EMULATE_DO_MMIO; } +EXPORT_SYMBOL_GPL(kvmppc_handle_store); int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu, struct kvm_run *run) { @@ -1024,52 +1074,12 @@ long kvm_arch_vm_ioctl(struct file *filp, r = kvm_vm_ioctl_create_spapr_tce(kvm, &create_tce); goto out; } -#endif /* CONFIG_PPC_BOOK3S_64 */ - -#ifdef CONFIG_KVM_BOOK3S_64_HV - case KVM_ALLOCATE_RMA: { - struct kvm_allocate_rma rma; - struct kvm *kvm = filp->private_data; - - r = kvm_vm_ioctl_allocate_rma(kvm, &rma); - if (r >= 0 && copy_to_user(argp, &rma, sizeof(rma))) - r = -EFAULT; - break; - } - - case KVM_PPC_ALLOCATE_HTAB: { - u32 htab_order; - - r = -EFAULT; - if (get_user(htab_order, (u32 __user *)argp)) - break; - r = kvmppc_alloc_reset_hpt(kvm, &htab_order); - if (r) - break; - r = -EFAULT; - if (put_user(htab_order, (u32 __user *)argp)) - break; - r = 0; - break; - } - - case KVM_PPC_GET_HTAB_FD: { - struct kvm_get_htab_fd ghf; - - r = -EFAULT; - if (copy_from_user(&ghf, argp, sizeof(ghf))) - break; - r = kvm_vm_ioctl_get_htab_fd(kvm, &ghf); - break; - } -#endif /* CONFIG_KVM_BOOK3S_64_HV */ - -#ifdef CONFIG_PPC_BOOK3S_64 case KVM_PPC_GET_SMMU_INFO: { struct kvm_ppc_smmu_info info; + struct kvm *kvm = filp->private_data; memset(&info, 0, sizeof(info)); - r = kvm_vm_ioctl_get_smmu_info(kvm, &info); + r = kvm->arch.kvm_ops->get_smmu_info(kvm, &info); if (r >= 0 && copy_to_user(argp, &info, sizeof(info))) r = -EFAULT; break; @@ -1080,11 +1090,15 @@ long kvm_arch_vm_ioctl(struct file *filp, r = kvm_vm_ioctl_rtas_define_token(kvm, argp); break; } -#endif /* CONFIG_PPC_BOOK3S_64 */ + default: { + struct kvm *kvm = filp->private_data; + r = kvm->arch.kvm_ops->arch_vm_ioctl(filp, ioctl, arg); + } +#else /* CONFIG_PPC_BOOK3S_64 */ default: r = -ENOTTY; +#endif } - out: return r; } @@ -1106,22 +1120,26 @@ long kvmppc_alloc_lpid(void) return lpid; } +EXPORT_SYMBOL_GPL(kvmppc_alloc_lpid); void kvmppc_claim_lpid(long lpid) { set_bit(lpid, lpid_inuse); } +EXPORT_SYMBOL_GPL(kvmppc_claim_lpid); void kvmppc_free_lpid(long lpid) { clear_bit(lpid, lpid_inuse); } +EXPORT_SYMBOL_GPL(kvmppc_free_lpid); void kvmppc_init_lpid(unsigned long nr_lpids_param) { nr_lpids = min_t(unsigned long, KVMPPC_NR_LPIDS, nr_lpids_param); memset(lpid_inuse, 0, sizeof(lpid_inuse)); } +EXPORT_SYMBOL_GPL(kvmppc_init_lpid); int kvm_arch_init(void *opaque) { @@ -1130,4 +1148,5 @@ int kvm_arch_init(void *opaque) void kvm_arch_exit(void) { + } diff --git a/arch/powerpc/kvm/trace.h b/arch/powerpc/kvm/trace.h index e326489a5420..2e0e67ef3544 100644 --- a/arch/powerpc/kvm/trace.h +++ b/arch/powerpc/kvm/trace.h @@ -31,126 +31,6 @@ TRACE_EVENT(kvm_ppc_instr, __entry->inst, __entry->pc, __entry->emulate) ); -#ifdef CONFIG_PPC_BOOK3S -#define kvm_trace_symbol_exit \ - {0x100, "SYSTEM_RESET"}, \ - {0x200, "MACHINE_CHECK"}, \ - {0x300, "DATA_STORAGE"}, \ - {0x380, "DATA_SEGMENT"}, \ - {0x400, "INST_STORAGE"}, \ - {0x480, "INST_SEGMENT"}, \ - {0x500, "EXTERNAL"}, \ - {0x501, "EXTERNAL_LEVEL"}, \ - {0x502, "EXTERNAL_HV"}, \ - {0x600, "ALIGNMENT"}, \ - {0x700, "PROGRAM"}, \ - {0x800, "FP_UNAVAIL"}, \ - {0x900, "DECREMENTER"}, \ - {0x980, "HV_DECREMENTER"}, \ - {0xc00, "SYSCALL"}, \ - {0xd00, "TRACE"}, \ - {0xe00, "H_DATA_STORAGE"}, \ - {0xe20, "H_INST_STORAGE"}, \ - {0xe40, "H_EMUL_ASSIST"}, \ - {0xf00, "PERFMON"}, \ - {0xf20, "ALTIVEC"}, \ - {0xf40, "VSX"} -#else -#define kvm_trace_symbol_exit \ - {0, "CRITICAL"}, \ - {1, "MACHINE_CHECK"}, \ - {2, "DATA_STORAGE"}, \ - {3, "INST_STORAGE"}, \ - {4, "EXTERNAL"}, \ - {5, "ALIGNMENT"}, \ - {6, "PROGRAM"}, \ - {7, "FP_UNAVAIL"}, \ - {8, "SYSCALL"}, \ - {9, "AP_UNAVAIL"}, \ - {10, "DECREMENTER"}, \ - {11, "FIT"}, \ - {12, "WATCHDOG"}, \ - {13, "DTLB_MISS"}, \ - {14, "ITLB_MISS"}, \ - {15, "DEBUG"}, \ - {32, "SPE_UNAVAIL"}, \ - {33, "SPE_FP_DATA"}, \ - {34, "SPE_FP_ROUND"}, \ - {35, "PERFORMANCE_MONITOR"}, \ - {36, "DOORBELL"}, \ - {37, "DOORBELL_CRITICAL"}, \ - {38, "GUEST_DBELL"}, \ - {39, "GUEST_DBELL_CRIT"}, \ - {40, "HV_SYSCALL"}, \ - {41, "HV_PRIV"} -#endif - -TRACE_EVENT(kvm_exit, - TP_PROTO(unsigned int exit_nr, struct kvm_vcpu *vcpu), - TP_ARGS(exit_nr, vcpu), - - TP_STRUCT__entry( - __field( unsigned int, exit_nr ) - __field( unsigned long, pc ) - __field( unsigned long, msr ) - __field( unsigned long, dar ) -#ifdef CONFIG_KVM_BOOK3S_PR - __field( unsigned long, srr1 ) -#endif - __field( unsigned long, last_inst ) - ), - - TP_fast_assign( -#ifdef CONFIG_KVM_BOOK3S_PR - struct kvmppc_book3s_shadow_vcpu *svcpu; -#endif - __entry->exit_nr = exit_nr; - __entry->pc = kvmppc_get_pc(vcpu); - __entry->dar = kvmppc_get_fault_dar(vcpu); - __entry->msr = vcpu->arch.shared->msr; -#ifdef CONFIG_KVM_BOOK3S_PR - svcpu = svcpu_get(vcpu); - __entry->srr1 = svcpu->shadow_srr1; - svcpu_put(svcpu); -#endif - __entry->last_inst = vcpu->arch.last_inst; - ), - - TP_printk("exit=%s" - " | pc=0x%lx" - " | msr=0x%lx" - " | dar=0x%lx" -#ifdef CONFIG_KVM_BOOK3S_PR - " | srr1=0x%lx" -#endif - " | last_inst=0x%lx" - , - __print_symbolic(__entry->exit_nr, kvm_trace_symbol_exit), - __entry->pc, - __entry->msr, - __entry->dar, -#ifdef CONFIG_KVM_BOOK3S_PR - __entry->srr1, -#endif - __entry->last_inst - ) -); - -TRACE_EVENT(kvm_unmap_hva, - TP_PROTO(unsigned long hva), - TP_ARGS(hva), - - TP_STRUCT__entry( - __field( unsigned long, hva ) - ), - - TP_fast_assign( - __entry->hva = hva; - ), - - TP_printk("unmap hva 0x%lx\n", __entry->hva) -); - TRACE_EVENT(kvm_stlb_inval, TP_PROTO(unsigned int stlb_index), TP_ARGS(stlb_index), @@ -236,315 +116,6 @@ TRACE_EVENT(kvm_check_requests, __entry->cpu_nr, __entry->requests) ); - -/************************************************************************* - * Book3S trace points * - *************************************************************************/ - -#ifdef CONFIG_KVM_BOOK3S_PR - -TRACE_EVENT(kvm_book3s_reenter, - TP_PROTO(int r, struct kvm_vcpu *vcpu), - TP_ARGS(r, vcpu), - - TP_STRUCT__entry( - __field( unsigned int, r ) - __field( unsigned long, pc ) - ), - - TP_fast_assign( - __entry->r = r; - __entry->pc = kvmppc_get_pc(vcpu); - ), - - TP_printk("reentry r=%d | pc=0x%lx", __entry->r, __entry->pc) -); - -#ifdef CONFIG_PPC_BOOK3S_64 - -TRACE_EVENT(kvm_book3s_64_mmu_map, - TP_PROTO(int rflags, ulong hpteg, ulong va, pfn_t hpaddr, - struct kvmppc_pte *orig_pte), - TP_ARGS(rflags, hpteg, va, hpaddr, orig_pte), - - TP_STRUCT__entry( - __field( unsigned char, flag_w ) - __field( unsigned char, flag_x ) - __field( unsigned long, eaddr ) - __field( unsigned long, hpteg ) - __field( unsigned long, va ) - __field( unsigned long long, vpage ) - __field( unsigned long, hpaddr ) - ), - - TP_fast_assign( - __entry->flag_w = ((rflags & HPTE_R_PP) == 3) ? '-' : 'w'; - __entry->flag_x = (rflags & HPTE_R_N) ? '-' : 'x'; - __entry->eaddr = orig_pte->eaddr; - __entry->hpteg = hpteg; - __entry->va = va; - __entry->vpage = orig_pte->vpage; - __entry->hpaddr = hpaddr; - ), - - TP_printk("KVM: %c%c Map 0x%lx: [%lx] 0x%lx (0x%llx) -> %lx", - __entry->flag_w, __entry->flag_x, __entry->eaddr, - __entry->hpteg, __entry->va, __entry->vpage, __entry->hpaddr) -); - -#endif /* CONFIG_PPC_BOOK3S_64 */ - -TRACE_EVENT(kvm_book3s_mmu_map, - TP_PROTO(struct hpte_cache *pte), - TP_ARGS(pte), - - TP_STRUCT__entry( - __field( u64, host_vpn ) - __field( u64, pfn ) - __field( ulong, eaddr ) - __field( u64, vpage ) - __field( ulong, raddr ) - __field( int, flags ) - ), - - TP_fast_assign( - __entry->host_vpn = pte->host_vpn; - __entry->pfn = pte->pfn; - __entry->eaddr = pte->pte.eaddr; - __entry->vpage = pte->pte.vpage; - __entry->raddr = pte->pte.raddr; - __entry->flags = (pte->pte.may_read ? 0x4 : 0) | - (pte->pte.may_write ? 0x2 : 0) | - (pte->pte.may_execute ? 0x1 : 0); - ), - - TP_printk("Map: hvpn=%llx pfn=%llx ea=%lx vp=%llx ra=%lx [%x]", - __entry->host_vpn, __entry->pfn, __entry->eaddr, - __entry->vpage, __entry->raddr, __entry->flags) -); - -TRACE_EVENT(kvm_book3s_mmu_invalidate, - TP_PROTO(struct hpte_cache *pte), - TP_ARGS(pte), - - TP_STRUCT__entry( - __field( u64, host_vpn ) - __field( u64, pfn ) - __field( ulong, eaddr ) - __field( u64, vpage ) - __field( ulong, raddr ) - __field( int, flags ) - ), - - TP_fast_assign( - __entry->host_vpn = pte->host_vpn; - __entry->pfn = pte->pfn; - __entry->eaddr = pte->pte.eaddr; - __entry->vpage = pte->pte.vpage; - __entry->raddr = pte->pte.raddr; - __entry->flags = (pte->pte.may_read ? 0x4 : 0) | - (pte->pte.may_write ? 0x2 : 0) | - (pte->pte.may_execute ? 0x1 : 0); - ), - - TP_printk("Flush: hva=%llx pfn=%llx ea=%lx vp=%llx ra=%lx [%x]", - __entry->host_vpn, __entry->pfn, __entry->eaddr, - __entry->vpage, __entry->raddr, __entry->flags) -); - -TRACE_EVENT(kvm_book3s_mmu_flush, - TP_PROTO(const char *type, struct kvm_vcpu *vcpu, unsigned long long p1, - unsigned long long p2), - TP_ARGS(type, vcpu, p1, p2), - - TP_STRUCT__entry( - __field( int, count ) - __field( unsigned long long, p1 ) - __field( unsigned long long, p2 ) - __field( const char *, type ) - ), - - TP_fast_assign( - __entry->count = to_book3s(vcpu)->hpte_cache_count; - __entry->p1 = p1; - __entry->p2 = p2; - __entry->type = type; - ), - - TP_printk("Flush %d %sPTEs: %llx - %llx", - __entry->count, __entry->type, __entry->p1, __entry->p2) -); - -TRACE_EVENT(kvm_book3s_slb_found, - TP_PROTO(unsigned long long gvsid, unsigned long long hvsid), - TP_ARGS(gvsid, hvsid), - - TP_STRUCT__entry( - __field( unsigned long long, gvsid ) - __field( unsigned long long, hvsid ) - ), - - TP_fast_assign( - __entry->gvsid = gvsid; - __entry->hvsid = hvsid; - ), - - TP_printk("%llx -> %llx", __entry->gvsid, __entry->hvsid) -); - -TRACE_EVENT(kvm_book3s_slb_fail, - TP_PROTO(u16 sid_map_mask, unsigned long long gvsid), - TP_ARGS(sid_map_mask, gvsid), - - TP_STRUCT__entry( - __field( unsigned short, sid_map_mask ) - __field( unsigned long long, gvsid ) - ), - - TP_fast_assign( - __entry->sid_map_mask = sid_map_mask; - __entry->gvsid = gvsid; - ), - - TP_printk("%x/%x: %llx", __entry->sid_map_mask, - SID_MAP_MASK - __entry->sid_map_mask, __entry->gvsid) -); - -TRACE_EVENT(kvm_book3s_slb_map, - TP_PROTO(u16 sid_map_mask, unsigned long long gvsid, - unsigned long long hvsid), - TP_ARGS(sid_map_mask, gvsid, hvsid), - - TP_STRUCT__entry( - __field( unsigned short, sid_map_mask ) - __field( unsigned long long, guest_vsid ) - __field( unsigned long long, host_vsid ) - ), - - TP_fast_assign( - __entry->sid_map_mask = sid_map_mask; - __entry->guest_vsid = gvsid; - __entry->host_vsid = hvsid; - ), - - TP_printk("%x: %llx -> %llx", __entry->sid_map_mask, - __entry->guest_vsid, __entry->host_vsid) -); - -TRACE_EVENT(kvm_book3s_slbmte, - TP_PROTO(u64 slb_vsid, u64 slb_esid), - TP_ARGS(slb_vsid, slb_esid), - - TP_STRUCT__entry( - __field( u64, slb_vsid ) - __field( u64, slb_esid ) - ), - - TP_fast_assign( - __entry->slb_vsid = slb_vsid; - __entry->slb_esid = slb_esid; - ), - - TP_printk("%llx, %llx", __entry->slb_vsid, __entry->slb_esid) -); - -#endif /* CONFIG_PPC_BOOK3S */ - - -/************************************************************************* - * Book3E trace points * - *************************************************************************/ - -#ifdef CONFIG_BOOKE - -TRACE_EVENT(kvm_booke206_stlb_write, - TP_PROTO(__u32 mas0, __u32 mas8, __u32 mas1, __u64 mas2, __u64 mas7_3), - TP_ARGS(mas0, mas8, mas1, mas2, mas7_3), - - TP_STRUCT__entry( - __field( __u32, mas0 ) - __field( __u32, mas8 ) - __field( __u32, mas1 ) - __field( __u64, mas2 ) - __field( __u64, mas7_3 ) - ), - - TP_fast_assign( - __entry->mas0 = mas0; - __entry->mas8 = mas8; - __entry->mas1 = mas1; - __entry->mas2 = mas2; - __entry->mas7_3 = mas7_3; - ), - - TP_printk("mas0=%x mas8=%x mas1=%x mas2=%llx mas7_3=%llx", - __entry->mas0, __entry->mas8, __entry->mas1, - __entry->mas2, __entry->mas7_3) -); - -TRACE_EVENT(kvm_booke206_gtlb_write, - TP_PROTO(__u32 mas0, __u32 mas1, __u64 mas2, __u64 mas7_3), - TP_ARGS(mas0, mas1, mas2, mas7_3), - - TP_STRUCT__entry( - __field( __u32, mas0 ) - __field( __u32, mas1 ) - __field( __u64, mas2 ) - __field( __u64, mas7_3 ) - ), - - TP_fast_assign( - __entry->mas0 = mas0; - __entry->mas1 = mas1; - __entry->mas2 = mas2; - __entry->mas7_3 = mas7_3; - ), - - TP_printk("mas0=%x mas1=%x mas2=%llx mas7_3=%llx", - __entry->mas0, __entry->mas1, - __entry->mas2, __entry->mas7_3) -); - -TRACE_EVENT(kvm_booke206_ref_release, - TP_PROTO(__u64 pfn, __u32 flags), - TP_ARGS(pfn, flags), - - TP_STRUCT__entry( - __field( __u64, pfn ) - __field( __u32, flags ) - ), - - TP_fast_assign( - __entry->pfn = pfn; - __entry->flags = flags; - ), - - TP_printk("pfn=%llx flags=%x", - __entry->pfn, __entry->flags) -); - -TRACE_EVENT(kvm_booke_queue_irqprio, - TP_PROTO(struct kvm_vcpu *vcpu, unsigned int priority), - TP_ARGS(vcpu, priority), - - TP_STRUCT__entry( - __field( __u32, cpu_nr ) - __field( __u32, priority ) - __field( unsigned long, pending ) - ), - - TP_fast_assign( - __entry->cpu_nr = vcpu->vcpu_id; - __entry->priority = priority; - __entry->pending = vcpu->arch.pending_exceptions; - ), - - TP_printk("vcpu=%x prio=%x pending=%lx", - __entry->cpu_nr, __entry->priority, __entry->pending) -); - -#endif - #endif /* _TRACE_KVM_H */ /* This part must be outside protection */ diff --git a/arch/powerpc/kvm/trace_booke.h b/arch/powerpc/kvm/trace_booke.h new file mode 100644 index 000000000000..f7537cf26ce7 --- /dev/null +++ b/arch/powerpc/kvm/trace_booke.h @@ -0,0 +1,177 @@ +#if !defined(_TRACE_KVM_BOOKE_H) || defined(TRACE_HEADER_MULTI_READ) +#define _TRACE_KVM_BOOKE_H + +#include <linux/tracepoint.h> + +#undef TRACE_SYSTEM +#define TRACE_SYSTEM kvm_booke +#define TRACE_INCLUDE_PATH . +#define TRACE_INCLUDE_FILE trace_booke + +#define kvm_trace_symbol_exit \ + {0, "CRITICAL"}, \ + {1, "MACHINE_CHECK"}, \ + {2, "DATA_STORAGE"}, \ + {3, "INST_STORAGE"}, \ + {4, "EXTERNAL"}, \ + {5, "ALIGNMENT"}, \ + {6, "PROGRAM"}, \ + {7, "FP_UNAVAIL"}, \ + {8, "SYSCALL"}, \ + {9, "AP_UNAVAIL"}, \ + {10, "DECREMENTER"}, \ + {11, "FIT"}, \ + {12, "WATCHDOG"}, \ + {13, "DTLB_MISS"}, \ + {14, "ITLB_MISS"}, \ + {15, "DEBUG"}, \ + {32, "SPE_UNAVAIL"}, \ + {33, "SPE_FP_DATA"}, \ + {34, "SPE_FP_ROUND"}, \ + {35, "PERFORMANCE_MONITOR"}, \ + {36, "DOORBELL"}, \ + {37, "DOORBELL_CRITICAL"}, \ + {38, "GUEST_DBELL"}, \ + {39, "GUEST_DBELL_CRIT"}, \ + {40, "HV_SYSCALL"}, \ + {41, "HV_PRIV"} + +TRACE_EVENT(kvm_exit, + TP_PROTO(unsigned int exit_nr, struct kvm_vcpu *vcpu), + TP_ARGS(exit_nr, vcpu), + + TP_STRUCT__entry( + __field( unsigned int, exit_nr ) + __field( unsigned long, pc ) + __field( unsigned long, msr ) + __field( unsigned long, dar ) + __field( unsigned long, last_inst ) + ), + + TP_fast_assign( + __entry->exit_nr = exit_nr; + __entry->pc = kvmppc_get_pc(vcpu); + __entry->dar = kvmppc_get_fault_dar(vcpu); + __entry->msr = vcpu->arch.shared->msr; + __entry->last_inst = vcpu->arch.last_inst; + ), + + TP_printk("exit=%s" + " | pc=0x%lx" + " | msr=0x%lx" + " | dar=0x%lx" + " | last_inst=0x%lx" + , + __print_symbolic(__entry->exit_nr, kvm_trace_symbol_exit), + __entry->pc, + __entry->msr, + __entry->dar, + __entry->last_inst + ) +); + +TRACE_EVENT(kvm_unmap_hva, + TP_PROTO(unsigned long hva), + TP_ARGS(hva), + + TP_STRUCT__entry( + __field( unsigned long, hva ) + ), + + TP_fast_assign( + __entry->hva = hva; + ), + + TP_printk("unmap hva 0x%lx\n", __entry->hva) +); + +TRACE_EVENT(kvm_booke206_stlb_write, + TP_PROTO(__u32 mas0, __u32 mas8, __u32 mas1, __u64 mas2, __u64 mas7_3), + TP_ARGS(mas0, mas8, mas1, mas2, mas7_3), + + TP_STRUCT__entry( + __field( __u32, mas0 ) + __field( __u32, mas8 ) + __field( __u32, mas1 ) + __field( __u64, mas2 ) + __field( __u64, mas7_3 ) + ), + + TP_fast_assign( + __entry->mas0 = mas0; + __entry->mas8 = mas8; + __entry->mas1 = mas1; + __entry->mas2 = mas2; + __entry->mas7_3 = mas7_3; + ), + + TP_printk("mas0=%x mas8=%x mas1=%x mas2=%llx mas7_3=%llx", + __entry->mas0, __entry->mas8, __entry->mas1, + __entry->mas2, __entry->mas7_3) +); + +TRACE_EVENT(kvm_booke206_gtlb_write, + TP_PROTO(__u32 mas0, __u32 mas1, __u64 mas2, __u64 mas7_3), + TP_ARGS(mas0, mas1, mas2, mas7_3), + + TP_STRUCT__entry( + __field( __u32, mas0 ) + __field( __u32, mas1 ) + __field( __u64, mas2 ) + __field( __u64, mas7_3 ) + ), + + TP_fast_assign( + __entry->mas0 = mas0; + __entry->mas1 = mas1; + __entry->mas2 = mas2; + __entry->mas7_3 = mas7_3; + ), + + TP_printk("mas0=%x mas1=%x mas2=%llx mas7_3=%llx", + __entry->mas0, __entry->mas1, + __entry->mas2, __entry->mas7_3) +); + +TRACE_EVENT(kvm_booke206_ref_release, + TP_PROTO(__u64 pfn, __u32 flags), + TP_ARGS(pfn, flags), + + TP_STRUCT__entry( + __field( __u64, pfn ) + __field( __u32, flags ) + ), + + TP_fast_assign( + __entry->pfn = pfn; + __entry->flags = flags; + ), + + TP_printk("pfn=%llx flags=%x", + __entry->pfn, __entry->flags) +); + +TRACE_EVENT(kvm_booke_queue_irqprio, + TP_PROTO(struct kvm_vcpu *vcpu, unsigned int priority), + TP_ARGS(vcpu, priority), + + TP_STRUCT__entry( + __field( __u32, cpu_nr ) + __field( __u32, priority ) + __field( unsigned long, pending ) + ), + + TP_fast_assign( + __entry->cpu_nr = vcpu->vcpu_id; + __entry->priority = priority; + __entry->pending = vcpu->arch.pending_exceptions; + ), + + TP_printk("vcpu=%x prio=%x pending=%lx", + __entry->cpu_nr, __entry->priority, __entry->pending) +); + +#endif + +/* This part must be outside protection */ +#include <trace/define_trace.h> diff --git a/arch/powerpc/kvm/trace_pr.h b/arch/powerpc/kvm/trace_pr.h new file mode 100644 index 000000000000..8b22e4748344 --- /dev/null +++ b/arch/powerpc/kvm/trace_pr.h @@ -0,0 +1,297 @@ + +#if !defined(_TRACE_KVM_PR_H) || defined(TRACE_HEADER_MULTI_READ) +#define _TRACE_KVM_PR_H + +#include <linux/tracepoint.h> + +#undef TRACE_SYSTEM +#define TRACE_SYSTEM kvm_pr +#define TRACE_INCLUDE_PATH . +#define TRACE_INCLUDE_FILE trace_pr + +#define kvm_trace_symbol_exit \ + {0x100, "SYSTEM_RESET"}, \ + {0x200, "MACHINE_CHECK"}, \ + {0x300, "DATA_STORAGE"}, \ + {0x380, "DATA_SEGMENT"}, \ + {0x400, "INST_STORAGE"}, \ + {0x480, "INST_SEGMENT"}, \ + {0x500, "EXTERNAL"}, \ + {0x501, "EXTERNAL_LEVEL"}, \ + {0x502, "EXTERNAL_HV"}, \ + {0x600, "ALIGNMENT"}, \ + {0x700, "PROGRAM"}, \ + {0x800, "FP_UNAVAIL"}, \ + {0x900, "DECREMENTER"}, \ + {0x980, "HV_DECREMENTER"}, \ + {0xc00, "SYSCALL"}, \ + {0xd00, "TRACE"}, \ + {0xe00, "H_DATA_STORAGE"}, \ + {0xe20, "H_INST_STORAGE"}, \ + {0xe40, "H_EMUL_ASSIST"}, \ + {0xf00, "PERFMON"}, \ + {0xf20, "ALTIVEC"}, \ + {0xf40, "VSX"} + +TRACE_EVENT(kvm_book3s_reenter, + TP_PROTO(int r, struct kvm_vcpu *vcpu), + TP_ARGS(r, vcpu), + + TP_STRUCT__entry( + __field( unsigned int, r ) + __field( unsigned long, pc ) + ), + + TP_fast_assign( + __entry->r = r; + __entry->pc = kvmppc_get_pc(vcpu); + ), + + TP_printk("reentry r=%d | pc=0x%lx", __entry->r, __entry->pc) +); + +#ifdef CONFIG_PPC_BOOK3S_64 + +TRACE_EVENT(kvm_book3s_64_mmu_map, + TP_PROTO(int rflags, ulong hpteg, ulong va, pfn_t hpaddr, + struct kvmppc_pte *orig_pte), + TP_ARGS(rflags, hpteg, va, hpaddr, orig_pte), + + TP_STRUCT__entry( + __field( unsigned char, flag_w ) + __field( unsigned char, flag_x ) + __field( unsigned long, eaddr ) + __field( unsigned long, hpteg ) + __field( unsigned long, va ) + __field( unsigned long long, vpage ) + __field( unsigned long, hpaddr ) + ), + + TP_fast_assign( + __entry->flag_w = ((rflags & HPTE_R_PP) == 3) ? '-' : 'w'; + __entry->flag_x = (rflags & HPTE_R_N) ? '-' : 'x'; + __entry->eaddr = orig_pte->eaddr; + __entry->hpteg = hpteg; + __entry->va = va; + __entry->vpage = orig_pte->vpage; + __entry->hpaddr = hpaddr; + ), + + TP_printk("KVM: %c%c Map 0x%lx: [%lx] 0x%lx (0x%llx) -> %lx", + __entry->flag_w, __entry->flag_x, __entry->eaddr, + __entry->hpteg, __entry->va, __entry->vpage, __entry->hpaddr) +); + +#endif /* CONFIG_PPC_BOOK3S_64 */ + +TRACE_EVENT(kvm_book3s_mmu_map, + TP_PROTO(struct hpte_cache *pte), + TP_ARGS(pte), + + TP_STRUCT__entry( + __field( u64, host_vpn ) + __field( u64, pfn ) + __field( ulong, eaddr ) + __field( u64, vpage ) + __field( ulong, raddr ) + __field( int, flags ) + ), + + TP_fast_assign( + __entry->host_vpn = pte->host_vpn; + __entry->pfn = pte->pfn; + __entry->eaddr = pte->pte.eaddr; + __entry->vpage = pte->pte.vpage; + __entry->raddr = pte->pte.raddr; + __entry->flags = (pte->pte.may_read ? 0x4 : 0) | + (pte->pte.may_write ? 0x2 : 0) | + (pte->pte.may_execute ? 0x1 : 0); + ), + + TP_printk("Map: hvpn=%llx pfn=%llx ea=%lx vp=%llx ra=%lx [%x]", + __entry->host_vpn, __entry->pfn, __entry->eaddr, + __entry->vpage, __entry->raddr, __entry->flags) +); + +TRACE_EVENT(kvm_book3s_mmu_invalidate, + TP_PROTO(struct hpte_cache *pte), + TP_ARGS(pte), + + TP_STRUCT__entry( + __field( u64, host_vpn ) + __field( u64, pfn ) + __field( ulong, eaddr ) + __field( u64, vpage ) + __field( ulong, raddr ) + __field( int, flags ) + ), + + TP_fast_assign( + __entry->host_vpn = pte->host_vpn; + __entry->pfn = pte->pfn; + __entry->eaddr = pte->pte.eaddr; + __entry->vpage = pte->pte.vpage; + __entry->raddr = pte->pte.raddr; + __entry->flags = (pte->pte.may_read ? 0x4 : 0) | + (pte->pte.may_write ? 0x2 : 0) | + (pte->pte.may_execute ? 0x1 : 0); + ), + + TP_printk("Flush: hva=%llx pfn=%llx ea=%lx vp=%llx ra=%lx [%x]", + __entry->host_vpn, __entry->pfn, __entry->eaddr, + __entry->vpage, __entry->raddr, __entry->flags) +); + +TRACE_EVENT(kvm_book3s_mmu_flush, + TP_PROTO(const char *type, struct kvm_vcpu *vcpu, unsigned long long p1, + unsigned long long p2), + TP_ARGS(type, vcpu, p1, p2), + + TP_STRUCT__entry( + __field( int, count ) + __field( unsigned long long, p1 ) + __field( unsigned long long, p2 ) + __field( const char *, type ) + ), + + TP_fast_assign( + __entry->count = to_book3s(vcpu)->hpte_cache_count; + __entry->p1 = p1; + __entry->p2 = p2; + __entry->type = type; + ), + + TP_printk("Flush %d %sPTEs: %llx - %llx", + __entry->count, __entry->type, __entry->p1, __entry->p2) +); + +TRACE_EVENT(kvm_book3s_slb_found, + TP_PROTO(unsigned long long gvsid, unsigned long long hvsid), + TP_ARGS(gvsid, hvsid), + + TP_STRUCT__entry( + __field( unsigned long long, gvsid ) + __field( unsigned long long, hvsid ) + ), + + TP_fast_assign( + __entry->gvsid = gvsid; + __entry->hvsid = hvsid; + ), + + TP_printk("%llx -> %llx", __entry->gvsid, __entry->hvsid) +); + +TRACE_EVENT(kvm_book3s_slb_fail, + TP_PROTO(u16 sid_map_mask, unsigned long long gvsid), + TP_ARGS(sid_map_mask, gvsid), + + TP_STRUCT__entry( + __field( unsigned short, sid_map_mask ) + __field( unsigned long long, gvsid ) + ), + + TP_fast_assign( + __entry->sid_map_mask = sid_map_mask; + __entry->gvsid = gvsid; + ), + + TP_printk("%x/%x: %llx", __entry->sid_map_mask, + SID_MAP_MASK - __entry->sid_map_mask, __entry->gvsid) +); + +TRACE_EVENT(kvm_book3s_slb_map, + TP_PROTO(u16 sid_map_mask, unsigned long long gvsid, + unsigned long long hvsid), + TP_ARGS(sid_map_mask, gvsid, hvsid), + + TP_STRUCT__entry( + __field( unsigned short, sid_map_mask ) + __field( unsigned long long, guest_vsid ) + __field( unsigned long long, host_vsid ) + ), + + TP_fast_assign( + __entry->sid_map_mask = sid_map_mask; + __entry->guest_vsid = gvsid; + __entry->host_vsid = hvsid; + ), + + TP_printk("%x: %llx -> %llx", __entry->sid_map_mask, + __entry->guest_vsid, __entry->host_vsid) +); + +TRACE_EVENT(kvm_book3s_slbmte, + TP_PROTO(u64 slb_vsid, u64 slb_esid), + TP_ARGS(slb_vsid, slb_esid), + + TP_STRUCT__entry( + __field( u64, slb_vsid ) + __field( u64, slb_esid ) + ), + + TP_fast_assign( + __entry->slb_vsid = slb_vsid; + __entry->slb_esid = slb_esid; + ), + + TP_printk("%llx, %llx", __entry->slb_vsid, __entry->slb_esid) +); + +TRACE_EVENT(kvm_exit, + TP_PROTO(unsigned int exit_nr, struct kvm_vcpu *vcpu), + TP_ARGS(exit_nr, vcpu), + + TP_STRUCT__entry( + __field( unsigned int, exit_nr ) + __field( unsigned long, pc ) + __field( unsigned long, msr ) + __field( unsigned long, dar ) + __field( unsigned long, srr1 ) + __field( unsigned long, last_inst ) + ), + + TP_fast_assign( + __entry->exit_nr = exit_nr; + __entry->pc = kvmppc_get_pc(vcpu); + __entry->dar = kvmppc_get_fault_dar(vcpu); + __entry->msr = vcpu->arch.shared->msr; + __entry->srr1 = vcpu->arch.shadow_srr1; + __entry->last_inst = vcpu->arch.last_inst; + ), + + TP_printk("exit=%s" + " | pc=0x%lx" + " | msr=0x%lx" + " | dar=0x%lx" + " | srr1=0x%lx" + " | last_inst=0x%lx" + , + __print_symbolic(__entry->exit_nr, kvm_trace_symbol_exit), + __entry->pc, + __entry->msr, + __entry->dar, + __entry->srr1, + __entry->last_inst + ) +); + +TRACE_EVENT(kvm_unmap_hva, + TP_PROTO(unsigned long hva), + TP_ARGS(hva), + + TP_STRUCT__entry( + __field( unsigned long, hva ) + ), + + TP_fast_assign( + __entry->hva = hva; + ), + + TP_printk("unmap hva 0x%lx\n", __entry->hva) +); + +#endif /* _TRACE_KVM_H */ + +/* This part must be outside protection */ +#include <trace/define_trace.h> diff --git a/arch/powerpc/mm/gup.c b/arch/powerpc/mm/gup.c index 6936547018b8..c5f734e20b0f 100644 --- a/arch/powerpc/mm/gup.c +++ b/arch/powerpc/mm/gup.c @@ -123,6 +123,7 @@ int __get_user_pages_fast(unsigned long start, int nr_pages, int write, struct mm_struct *mm = current->mm; unsigned long addr, len, end; unsigned long next; + unsigned long flags; pgd_t *pgdp; int nr = 0; @@ -156,7 +157,7 @@ int __get_user_pages_fast(unsigned long start, int nr_pages, int write, * So long as we atomically load page table pointers versus teardown, * we can follow the address down to the the page and take a ref on it. */ - local_irq_disable(); + local_irq_save(flags); pgdp = pgd_offset(mm, addr); do { @@ -179,7 +180,7 @@ int __get_user_pages_fast(unsigned long start, int nr_pages, int write, break; } while (pgdp++, addr = next, addr != end); - local_irq_enable(); + local_irq_restore(flags); return nr; } diff --git a/arch/powerpc/mm/pgtable_32.c b/arch/powerpc/mm/pgtable_32.c index 6c856fb8c15b..5b9601715289 100644 --- a/arch/powerpc/mm/pgtable_32.c +++ b/arch/powerpc/mm/pgtable_32.c @@ -121,7 +121,10 @@ pgtable_t pte_alloc_one(struct mm_struct *mm, unsigned long address) ptepage = alloc_pages(flags, 0); if (!ptepage) return NULL; - pgtable_page_ctor(ptepage); + if (!pgtable_page_ctor(ptepage)) { + __free_page(ptepage); + return NULL; + } return ptepage; } diff --git a/arch/powerpc/mm/pgtable_64.c b/arch/powerpc/mm/pgtable_64.c index 536eec72c0f7..9d95786aa80f 100644 --- a/arch/powerpc/mm/pgtable_64.c +++ b/arch/powerpc/mm/pgtable_64.c @@ -378,6 +378,10 @@ static pte_t *__alloc_for_cache(struct mm_struct *mm, int kernel) __GFP_REPEAT | __GFP_ZERO); if (!page) return NULL; + if (!kernel && !pgtable_page_ctor(page)) { + __free_page(page); + return NULL; + } ret = page_address(page); spin_lock(&mm->page_table_lock); @@ -392,9 +396,6 @@ static pte_t *__alloc_for_cache(struct mm_struct *mm, int kernel) } spin_unlock(&mm->page_table_lock); - if (!kernel) - pgtable_page_ctor(page); - return (pte_t *)ret; } diff --git a/arch/powerpc/mm/slice.c b/arch/powerpc/mm/slice.c index 3e99c149271a..7ce9cf3b6988 100644 --- a/arch/powerpc/mm/slice.c +++ b/arch/powerpc/mm/slice.c @@ -258,7 +258,7 @@ static bool slice_scan_available(unsigned long addr, slice = GET_HIGH_SLICE_INDEX(addr); *boundary_addr = (slice + end) ? ((slice + end) << SLICE_HIGH_SHIFT) : SLICE_LOW_TOP; - return !!(available.high_slices & (1u << slice)); + return !!(available.high_slices & (1ul << slice)); } } diff --git a/arch/powerpc/platforms/Kconfig.cputype b/arch/powerpc/platforms/Kconfig.cputype index c2a566fb8bb8..132f8726a257 100644 --- a/arch/powerpc/platforms/Kconfig.cputype +++ b/arch/powerpc/platforms/Kconfig.cputype @@ -403,3 +403,14 @@ config PPC_DOORBELL default n endmenu + +config CPU_LITTLE_ENDIAN + bool "Build little endian kernel" + default n + help + This option selects whether a big endian or little endian kernel will + be built. + + Note that if cross compiling a little endian kernel, + CROSS_COMPILE must point to a toolchain capable of targeting + little endian powerpc. diff --git a/arch/powerpc/platforms/powermac/low_i2c.c b/arch/powerpc/platforms/powermac/low_i2c.c index fc536f2971c0..7553b6a77c64 100644 --- a/arch/powerpc/platforms/powermac/low_i2c.c +++ b/arch/powerpc/platforms/powermac/low_i2c.c @@ -452,7 +452,7 @@ static int kw_i2c_xfer(struct pmac_i2c_bus *bus, u8 addrdir, int subsize, */ if (use_irq) { /* Clear completion */ - INIT_COMPLETION(host->complete); + reinit_completion(&host->complete); /* Ack stale interrupts */ kw_write_reg(reg_isr, kw_read_reg(reg_isr)); /* Arm timeout */ @@ -717,7 +717,7 @@ static int pmu_i2c_xfer(struct pmac_i2c_bus *bus, u8 addrdir, int subsize, return -EINVAL; } - INIT_COMPLETION(comp); + reinit_completion(&comp); req->data[0] = PMU_I2C_CMD; req->reply[0] = 0xff; req->nbytes = sizeof(struct pmu_i2c_hdr) + 1; @@ -748,7 +748,7 @@ static int pmu_i2c_xfer(struct pmac_i2c_bus *bus, u8 addrdir, int subsize, hdr->bus = PMU_I2C_BUS_STATUS; - INIT_COMPLETION(comp); + reinit_completion(&comp); req->data[0] = PMU_I2C_CMD; req->reply[0] = 0xff; req->nbytes = 2; diff --git a/arch/powerpc/platforms/powernv/rng.c b/arch/powerpc/platforms/powernv/rng.c index 8844628915dc..1cb160dc1609 100644 --- a/arch/powerpc/platforms/powernv/rng.c +++ b/arch/powerpc/platforms/powernv/rng.c @@ -19,6 +19,7 @@ #include <asm/io.h> #include <asm/prom.h> #include <asm/machdep.h> +#include <asm/smp.h> struct powernv_rng { diff --git a/arch/powerpc/platforms/pseries/dlpar.c b/arch/powerpc/platforms/pseries/dlpar.c index 7cfdaae1721a..a8fe5aa3d34f 100644 --- a/arch/powerpc/platforms/pseries/dlpar.c +++ b/arch/powerpc/platforms/pseries/dlpar.c @@ -404,46 +404,38 @@ static ssize_t dlpar_cpu_probe(const char *buf, size_t count) unsigned long drc_index; int rc; - cpu_hotplug_driver_lock(); rc = strict_strtoul(buf, 0, &drc_index); - if (rc) { - rc = -EINVAL; - goto out; - } + if (rc) + return -EINVAL; parent = of_find_node_by_path("/cpus"); - if (!parent) { - rc = -ENODEV; - goto out; - } + if (!parent) + return -ENODEV; dn = dlpar_configure_connector(drc_index, parent); - if (!dn) { - rc = -EINVAL; - goto out; - } + if (!dn) + return -EINVAL; of_node_put(parent); rc = dlpar_acquire_drc(drc_index); if (rc) { dlpar_free_cc_nodes(dn); - rc = -EINVAL; - goto out; + return -EINVAL; } rc = dlpar_attach_node(dn); if (rc) { dlpar_release_drc(drc_index); dlpar_free_cc_nodes(dn); - goto out; + return rc; } rc = dlpar_online_cpu(dn); -out: - cpu_hotplug_driver_unlock(); + if (rc) + return rc; - return rc ? rc : count; + return count; } static int dlpar_offline_cpu(struct device_node *dn) @@ -516,30 +508,27 @@ static ssize_t dlpar_cpu_release(const char *buf, size_t count) return -EINVAL; } - cpu_hotplug_driver_lock(); rc = dlpar_offline_cpu(dn); if (rc) { of_node_put(dn); - rc = -EINVAL; - goto out; + return -EINVAL; } rc = dlpar_release_drc(*drc_index); if (rc) { of_node_put(dn); - goto out; + return rc; } rc = dlpar_detach_node(dn); if (rc) { dlpar_acquire_drc(*drc_index); - goto out; + return rc; } of_node_put(dn); -out: - cpu_hotplug_driver_unlock(); - return rc ? rc : count; + + return count; } static int __init pseries_dlpar_init(void) diff --git a/arch/powerpc/platforms/pseries/eeh_pseries.c b/arch/powerpc/platforms/pseries/eeh_pseries.c index 7fbc25b1813f..ccb633e077b1 100644 --- a/arch/powerpc/platforms/pseries/eeh_pseries.c +++ b/arch/powerpc/platforms/pseries/eeh_pseries.c @@ -189,8 +189,9 @@ static void *pseries_eeh_of_probe(struct device_node *dn, void *flag) struct eeh_dev *edev; struct eeh_pe pe; struct pci_dn *pdn = PCI_DN(dn); - const u32 *class_code, *vendor_id, *device_id; - const u32 *regs; + const __be32 *classp, *vendorp, *devicep; + u32 class_code; + const __be32 *regs; u32 pcie_flags; int enable = 0; int ret; @@ -201,22 +202,24 @@ static void *pseries_eeh_of_probe(struct device_node *dn, void *flag) return NULL; /* Retrieve class/vendor/device IDs */ - class_code = of_get_property(dn, "class-code", NULL); - vendor_id = of_get_property(dn, "vendor-id", NULL); - device_id = of_get_property(dn, "device-id", NULL); + classp = of_get_property(dn, "class-code", NULL); + vendorp = of_get_property(dn, "vendor-id", NULL); + devicep = of_get_property(dn, "device-id", NULL); /* Skip for bad OF node or PCI-ISA bridge */ - if (!class_code || !vendor_id || !device_id) + if (!classp || !vendorp || !devicep) return NULL; if (dn->type && !strcmp(dn->type, "isa")) return NULL; + class_code = of_read_number(classp, 1); + /* * Update class code and mode of eeh device. We need * correctly reflects that current device is root port * or PCIe switch downstream port. */ - edev->class_code = *class_code; + edev->class_code = class_code; edev->pcie_cap = pseries_eeh_find_cap(dn, PCI_CAP_ID_EXP); edev->mode &= 0xFFFFFF00; if ((edev->class_code >> 8) == PCI_CLASS_BRIDGE_PCI) { @@ -243,12 +246,12 @@ static void *pseries_eeh_of_probe(struct device_node *dn, void *flag) /* Initialize the fake PE */ memset(&pe, 0, sizeof(struct eeh_pe)); pe.phb = edev->phb; - pe.config_addr = regs[0]; + pe.config_addr = of_read_number(regs, 1); /* Enable EEH on the device */ ret = eeh_ops->set_option(&pe, EEH_OPT_ENABLE); if (!ret) { - edev->config_addr = regs[0]; + edev->config_addr = of_read_number(regs, 1); /* Retrieve PE address */ edev->pe_config_addr = eeh_ops->get_pe_addr(&pe); pe.addr = edev->pe_config_addr; diff --git a/arch/powerpc/platforms/pseries/lpar.c b/arch/powerpc/platforms/pseries/lpar.c index 356bc75ca74f..4fca3def9db9 100644 --- a/arch/powerpc/platforms/pseries/lpar.c +++ b/arch/powerpc/platforms/pseries/lpar.c @@ -245,6 +245,23 @@ static void pSeries_lpar_hptab_clear(void) &(ptes[j].pteh), &(ptes[j].ptel)); } } + +#ifdef __LITTLE_ENDIAN__ + /* Reset exceptions to big endian */ + if (firmware_has_feature(FW_FEATURE_SET_MODE)) { + long rc; + + rc = pseries_big_endian_exceptions(); + /* + * At this point it is unlikely panic() will get anything + * out to the user, but at least this will stop us from + * continuing on further and creating an even more + * difficult to debug situation. + */ + if (rc) + panic("Could not enable big endian exceptions"); + } +#endif } /* diff --git a/arch/powerpc/platforms/pseries/nvram.c b/arch/powerpc/platforms/pseries/nvram.c index 057fc894be51..7bfaf58d4664 100644 --- a/arch/powerpc/platforms/pseries/nvram.c +++ b/arch/powerpc/platforms/pseries/nvram.c @@ -31,7 +31,7 @@ #define NVRW_CNT 0x20 /* - * Set oops header version to distingush between old and new format header. + * Set oops header version to distinguish between old and new format header. * lnx,oops-log partition max size is 4000, header version > 4000 will * help in identifying new header. */ diff --git a/arch/powerpc/platforms/pseries/rng.c b/arch/powerpc/platforms/pseries/rng.c index a702f1c08242..72a102758d4e 100644 --- a/arch/powerpc/platforms/pseries/rng.c +++ b/arch/powerpc/platforms/pseries/rng.c @@ -13,6 +13,7 @@ #include <linux/of.h> #include <asm/archrandom.h> #include <asm/machdep.h> +#include <asm/plpar_wrappers.h> static int pseries_get_random_long(unsigned long *v) diff --git a/arch/powerpc/platforms/pseries/setup.c b/arch/powerpc/platforms/pseries/setup.c index 1f97e2b87a62..c1f190858701 100644 --- a/arch/powerpc/platforms/pseries/setup.c +++ b/arch/powerpc/platforms/pseries/setup.c @@ -442,6 +442,32 @@ static void pSeries_machine_kexec(struct kimage *image) } #endif +#ifdef __LITTLE_ENDIAN__ +long pseries_big_endian_exceptions(void) +{ + long rc; + + while (1) { + rc = enable_big_endian_exceptions(); + if (!H_IS_LONG_BUSY(rc)) + return rc; + mdelay(get_longbusy_msecs(rc)); + } +} + +static long pseries_little_endian_exceptions(void) +{ + long rc; + + while (1) { + rc = enable_little_endian_exceptions(); + if (!H_IS_LONG_BUSY(rc)) + return rc; + mdelay(get_longbusy_msecs(rc)); + } +} +#endif + static void __init pSeries_setup_arch(void) { panic_timeout = 10; @@ -698,6 +724,22 @@ static int __init pSeries_probe(void) /* Now try to figure out if we are running on LPAR */ of_scan_flat_dt(pseries_probe_fw_features, NULL); +#ifdef __LITTLE_ENDIAN__ + if (firmware_has_feature(FW_FEATURE_SET_MODE)) { + long rc; + /* + * Tell the hypervisor that we want our exceptions to + * be taken in little endian mode. If this fails we don't + * want to use BUG() because it will trigger an exception. + */ + rc = pseries_little_endian_exceptions(); + if (rc) { + ppc_md.progress("H_SET_MODE LE exception fail", 0); + panic("Could not enable little endian exceptions"); + } + } +#endif + if (firmware_has_feature(FW_FEATURE_LPAR)) hpte_init_lpar(); else diff --git a/arch/powerpc/platforms/pseries/suspend.c b/arch/powerpc/platforms/pseries/suspend.c index 5f997e79d570..16a255255d30 100644 --- a/arch/powerpc/platforms/pseries/suspend.c +++ b/arch/powerpc/platforms/pseries/suspend.c @@ -106,7 +106,7 @@ static int pseries_prepare_late(void) atomic_set(&suspend_data.done, 0); atomic_set(&suspend_data.error, 0); suspend_data.complete = &suspend_work; - INIT_COMPLETION(suspend_work); + reinit_completion(&suspend_work); return 0; } diff --git a/arch/powerpc/platforms/wsp/chroma.c b/arch/powerpc/platforms/wsp/chroma.c index 8ef53bc2e70e..aaa46b353715 100644 --- a/arch/powerpc/platforms/wsp/chroma.c +++ b/arch/powerpc/platforms/wsp/chroma.c @@ -15,6 +15,7 @@ #include <linux/of.h> #include <linux/smp.h> #include <linux/time.h> +#include <linux/of_fdt.h> #include <asm/machdep.h> #include <asm/udbg.h> diff --git a/arch/powerpc/platforms/wsp/h8.c b/arch/powerpc/platforms/wsp/h8.c index d18e6cc19df3..a3c87f395750 100644 --- a/arch/powerpc/platforms/wsp/h8.c +++ b/arch/powerpc/platforms/wsp/h8.c @@ -10,6 +10,7 @@ #include <linux/kernel.h> #include <linux/of.h> #include <linux/io.h> +#include <linux/of_address.h> #include "wsp.h" diff --git a/arch/powerpc/platforms/wsp/ics.c b/arch/powerpc/platforms/wsp/ics.c index 2d3b1dd9571d..9cd92e645028 100644 --- a/arch/powerpc/platforms/wsp/ics.c +++ b/arch/powerpc/platforms/wsp/ics.c @@ -18,6 +18,8 @@ #include <linux/smp.h> #include <linux/spinlock.h> #include <linux/types.h> +#include <linux/of_address.h> +#include <linux/of_irq.h> #include <asm/io.h> #include <asm/irq.h> diff --git a/arch/powerpc/platforms/wsp/opb_pic.c b/arch/powerpc/platforms/wsp/opb_pic.c index cb565bf93650..3f6729807938 100644 --- a/arch/powerpc/platforms/wsp/opb_pic.c +++ b/arch/powerpc/platforms/wsp/opb_pic.c @@ -15,6 +15,8 @@ #include <linux/of.h> #include <linux/slab.h> #include <linux/time.h> +#include <linux/of_address.h> +#include <linux/of_irq.h> #include <asm/reg_a2.h> #include <asm/irq.h> diff --git a/arch/powerpc/platforms/wsp/psr2.c b/arch/powerpc/platforms/wsp/psr2.c index 508ec8282b96..a87b414c766a 100644 --- a/arch/powerpc/platforms/wsp/psr2.c +++ b/arch/powerpc/platforms/wsp/psr2.c @@ -15,6 +15,7 @@ #include <linux/of.h> #include <linux/smp.h> #include <linux/time.h> +#include <linux/of_fdt.h> #include <asm/machdep.h> #include <asm/udbg.h> diff --git a/arch/powerpc/platforms/wsp/scom_wsp.c b/arch/powerpc/platforms/wsp/scom_wsp.c index 8928507affea..6538b4de34fc 100644 --- a/arch/powerpc/platforms/wsp/scom_wsp.c +++ b/arch/powerpc/platforms/wsp/scom_wsp.c @@ -14,6 +14,7 @@ #include <linux/of.h> #include <linux/spinlock.h> #include <linux/types.h> +#include <linux/of_address.h> #include <asm/cputhreads.h> #include <asm/reg_a2.h> diff --git a/arch/powerpc/platforms/wsp/wsp.c b/arch/powerpc/platforms/wsp/wsp.c index ddb6efe88914..58cd1f00e1ef 100644 --- a/arch/powerpc/platforms/wsp/wsp.c +++ b/arch/powerpc/platforms/wsp/wsp.c @@ -13,6 +13,7 @@ #include <linux/smp.h> #include <linux/delay.h> #include <linux/time.h> +#include <linux/of_address.h> #include <asm/scom.h> diff --git a/arch/powerpc/sysdev/fsl_pci.c b/arch/powerpc/sysdev/fsl_pci.c index 21039634d1d0..4dfd61df8aba 100644 --- a/arch/powerpc/sysdev/fsl_pci.c +++ b/arch/powerpc/sysdev/fsl_pci.c @@ -45,7 +45,7 @@ static void quirk_fsl_pcie_early(struct pci_dev *dev) u8 hdr_type; /* if we aren't a PCIe don't bother */ - if (!pci_find_capability(dev, PCI_CAP_ID_EXP)) + if (!pci_is_pcie(dev)) return; /* if we aren't in host mode don't bother */ diff --git a/arch/s390/Kconfig b/arch/s390/Kconfig index f75d7e517927..314fced4fc14 100644 --- a/arch/s390/Kconfig +++ b/arch/s390/Kconfig @@ -141,7 +141,6 @@ config S390 select OLD_SIGACTION select OLD_SIGSUSPEND3 select SYSCTL_EXCEPTION_TRACE - select USE_GENERIC_SMP_HELPERS if SMP select VIRT_CPU_ACCOUNTING select VIRT_TO_BUS diff --git a/arch/s390/boot/Makefile b/arch/s390/boot/Makefile index f2737a005afc..9a42ecec5647 100644 --- a/arch/s390/boot/Makefile +++ b/arch/s390/boot/Makefile @@ -21,6 +21,6 @@ $(obj)/bzImage: $(obj)/compressed/vmlinux FORCE $(obj)/compressed/vmlinux: FORCE $(Q)$(MAKE) $(build)=$(obj)/compressed $@ -install: $(CONFIGURE) $(obj)/image - sh -x $(srctree)/$(obj)/install.sh $(KERNELRELEASE) $(obj)/image \ +install: $(CONFIGURE) $(obj)/bzImage + sh -x $(srctree)/$(obj)/install.sh $(KERNELRELEASE) $(obj)/bzImage \ System.map "$(INSTALL_PATH)" diff --git a/arch/s390/include/asm/ctl_reg.h b/arch/s390/include/asm/ctl_reg.h index 9b69c0befdca..4e63f1a13600 100644 --- a/arch/s390/include/asm/ctl_reg.h +++ b/arch/s390/include/asm/ctl_reg.h @@ -7,6 +7,8 @@ #ifndef __ASM_CTL_REG_H #define __ASM_CTL_REG_H +#include <linux/bug.h> + #ifdef CONFIG_64BIT # define __CTL_LOAD "lctlg" # define __CTL_STORE "stctg" diff --git a/arch/s390/include/asm/eadm.h b/arch/s390/include/asm/eadm.h index dc9200ca32ed..67026300c88e 100644 --- a/arch/s390/include/asm/eadm.h +++ b/arch/s390/include/asm/eadm.h @@ -111,18 +111,7 @@ struct scm_driver { int scm_driver_register(struct scm_driver *scmdrv); void scm_driver_unregister(struct scm_driver *scmdrv); -int scm_start_aob(struct aob *aob); +int eadm_start_aob(struct aob *aob); void scm_irq_handler(struct aob *aob, int error); -struct eadm_ops { - int (*eadm_start) (struct aob *aob); - struct module *owner; -}; - -int scm_get_ref(void); -void scm_put_ref(void); - -void register_eadm_ops(struct eadm_ops *ops); -void unregister_eadm_ops(struct eadm_ops *ops); - #endif /* _ASM_S390_EADM_H */ diff --git a/arch/s390/include/asm/hardirq.h b/arch/s390/include/asm/hardirq.h index a908d2941c5d..b7eabaaeffbd 100644 --- a/arch/s390/include/asm/hardirq.h +++ b/arch/s390/include/asm/hardirq.h @@ -18,8 +18,6 @@ #define __ARCH_HAS_DO_SOFTIRQ #define __ARCH_IRQ_EXIT_IRQS_DISABLED -#define HARDIRQ_BITS 8 - static inline void ack_bad_irq(unsigned int irq) { printk(KERN_CRIT "unexpected IRQ trap at vector %02x\n", irq); diff --git a/arch/s390/include/asm/kvm_host.h b/arch/s390/include/asm/kvm_host.h index e87ecaa2c569..d5bc3750616e 100644 --- a/arch/s390/include/asm/kvm_host.h +++ b/arch/s390/include/asm/kvm_host.h @@ -38,13 +38,6 @@ struct sca_block { struct sca_entry cpu[64]; } __attribute__((packed)); -#define KVM_NR_PAGE_SIZES 2 -#define KVM_HPAGE_GFN_SHIFT(x) (((x) - 1) * 8) -#define KVM_HPAGE_SHIFT(x) (PAGE_SHIFT + KVM_HPAGE_GFN_SHIFT(x)) -#define KVM_HPAGE_SIZE(x) (1UL << KVM_HPAGE_SHIFT(x)) -#define KVM_HPAGE_MASK(x) (~(KVM_HPAGE_SIZE(x) - 1)) -#define KVM_PAGES_PER_HPAGE(x) (KVM_HPAGE_SIZE(x) / PAGE_SIZE) - #define CPUSTAT_STOPPED 0x80000000 #define CPUSTAT_WAIT 0x10000000 #define CPUSTAT_ECALL_PEND 0x08000000 @@ -220,7 +213,6 @@ struct kvm_s390_interrupt_info { /* for local_interrupt.action_flags */ #define ACTION_STORE_ON_STOP (1<<0) #define ACTION_STOP_ON_STOP (1<<1) -#define ACTION_RELOADVCPU_ON_STOP (1<<2) struct kvm_s390_local_interrupt { spinlock_t lock; diff --git a/arch/s390/include/asm/pci.h b/arch/s390/include/asm/pci.h index 1cc185da9d38..c129ab2ac731 100644 --- a/arch/s390/include/asm/pci.h +++ b/arch/s390/include/asm/pci.h @@ -63,9 +63,10 @@ enum zpci_state { }; struct zpci_bar_struct { + struct resource *res; /* bus resource */ u32 val; /* bar start & 3 flag bits */ - u8 size; /* order 2 exponent */ u16 map_idx; /* index into bar mapping array */ + u8 size; /* order 2 exponent */ }; /* Private data per function */ @@ -97,6 +98,7 @@ struct zpci_dev { unsigned long iommu_pages; unsigned int next_bit; + char res_name[16]; struct zpci_bar_struct bars[PCI_BAR_COUNT]; u64 start_dma; /* Start of available DMA addresses */ @@ -122,12 +124,10 @@ static inline bool zdev_enabled(struct zpci_dev *zdev) Prototypes ----------------------------------------------------------------------------- */ /* Base stuff */ -struct zpci_dev *zpci_alloc_device(void); int zpci_create_device(struct zpci_dev *); int zpci_enable_device(struct zpci_dev *); int zpci_disable_device(struct zpci_dev *); void zpci_stop_device(struct zpci_dev *); -void zpci_free_device(struct zpci_dev *); int zpci_register_ioat(struct zpci_dev *, u8, u64, u64, u64); int zpci_unregister_ioat(struct zpci_dev *, u8); diff --git a/arch/s390/include/asm/sclp.h b/arch/s390/include/asm/sclp.h index 7dc7f9c63b65..30ef748bc161 100644 --- a/arch/s390/include/asm/sclp.h +++ b/arch/s390/include/asm/sclp.h @@ -43,7 +43,6 @@ struct sclp_cpu_info { int sclp_get_cpu_info(struct sclp_cpu_info *info); int sclp_cpu_configure(u8 cpu); int sclp_cpu_deconfigure(u8 cpu); -void sclp_facilities_detect(void); unsigned long long sclp_get_rnmax(void); unsigned long long sclp_get_rzm(void); int sclp_sdias_blk_count(void); @@ -57,5 +56,7 @@ bool sclp_has_vt220(void); int sclp_pci_configure(u32 fid); int sclp_pci_deconfigure(u32 fid); int memcpy_hsa(void *dest, unsigned long src, size_t count, int mode); +unsigned long sclp_get_hsa_size(void); +void sclp_early_detect(void); #endif /* _ASM_S390_SCLP_H */ diff --git a/arch/s390/include/asm/setup.h b/arch/s390/include/asm/setup.h index df802ee14af6..94cfbe442f12 100644 --- a/arch/s390/include/asm/setup.h +++ b/arch/s390/include/asm/setup.h @@ -107,9 +107,6 @@ void create_mem_hole(struct mem_chunk mem_chunk[], unsigned long addr, #define MACHINE_HAS_RRBM (S390_lowcore.machine_flags & MACHINE_FLAG_RRBM) #endif /* CONFIG_64BIT */ -#define ZFCPDUMP_HSA_SIZE (32UL<<20) -#define ZFCPDUMP_HSA_SIZE_MAX (64UL<<20) - /* * Console mode. Override with conmode= */ diff --git a/arch/s390/include/asm/thread_info.h b/arch/s390/include/asm/thread_info.h index eb5f64d26d06..10e0fcd3633d 100644 --- a/arch/s390/include/asm/thread_info.h +++ b/arch/s390/include/asm/thread_info.h @@ -111,6 +111,4 @@ static inline struct thread_info *current_thread_info(void) #define is_32bit_task() (1) #endif -#define PREEMPT_ACTIVE 0x4000000 - #endif /* _ASM_THREAD_INFO_H */ diff --git a/arch/s390/kernel/crash_dump.c b/arch/s390/kernel/crash_dump.c index f45b2ab0cb81..d7658c4b2ed5 100644 --- a/arch/s390/kernel/crash_dump.c +++ b/arch/s390/kernel/crash_dump.c @@ -95,7 +95,7 @@ static void *elfcorehdr_newmem; /* * Copy one page from zfcpdump "oldmem" * - * For pages below ZFCPDUMP_HSA_SIZE memory from the HSA is copied. Otherwise + * For pages below HSA size memory from the HSA is copied. Otherwise * real memory copy is used. */ static ssize_t copy_oldmem_page_zfcpdump(char *buf, size_t csize, @@ -103,7 +103,7 @@ static ssize_t copy_oldmem_page_zfcpdump(char *buf, size_t csize, { int rc; - if (src < ZFCPDUMP_HSA_SIZE) { + if (src < sclp_get_hsa_size()) { rc = memcpy_hsa(buf, src, csize, userbuf); } else { if (userbuf) @@ -188,18 +188,19 @@ static int remap_oldmem_pfn_range_kdump(struct vm_area_struct *vma, /* * Remap "oldmem" for zfcpdump * - * We only map available memory above ZFCPDUMP_HSA_SIZE. Memory below - * ZFCPDUMP_HSA_SIZE is read on demand using the copy_oldmem_page() function. + * We only map available memory above HSA size. Memory below HSA size + * is read on demand using the copy_oldmem_page() function. */ static int remap_oldmem_pfn_range_zfcpdump(struct vm_area_struct *vma, unsigned long from, unsigned long pfn, unsigned long size, pgprot_t prot) { + unsigned long hsa_end = sclp_get_hsa_size(); unsigned long size_hsa; - if (pfn < ZFCPDUMP_HSA_SIZE >> PAGE_SHIFT) { - size_hsa = min(size, ZFCPDUMP_HSA_SIZE - (pfn << PAGE_SHIFT)); + if (pfn < hsa_end >> PAGE_SHIFT) { + size_hsa = min(size, hsa_end - (pfn << PAGE_SHIFT)); if (size == size_hsa) return 0; size -= size_hsa; @@ -238,9 +239,9 @@ int copy_from_oldmem(void *dest, void *src, size_t count) return rc; } } else { - if ((unsigned long) src < ZFCPDUMP_HSA_SIZE) { - copied = min(count, - ZFCPDUMP_HSA_SIZE - (unsigned long) src); + unsigned long hsa_end = sclp_get_hsa_size(); + if ((unsigned long) src < hsa_end) { + copied = min(count, hsa_end - (unsigned long) src); rc = memcpy_hsa(dest, (unsigned long) src, copied, 0); if (rc) return rc; @@ -580,6 +581,9 @@ int elfcorehdr_alloc(unsigned long long *addr, unsigned long long *size) /* If elfcorehdr= has been passed via cmdline, we use that one */ if (elfcorehdr_addr != ELFCORE_ADDR_MAX) return 0; + /* If we cannot get HSA size for zfcpdump return error */ + if (ipl_info.type == IPL_TYPE_FCP_DUMP && !sclp_get_hsa_size()) + return -ENODEV; mem_chunk_cnt = get_mem_chunk_cnt(); alloc_size = 0x1000 + get_cpu_cnt() * 0x300 + diff --git a/arch/s390/kernel/early.c b/arch/s390/kernel/early.c index 96543ac400a7..fca20b5fe79e 100644 --- a/arch/s390/kernel/early.c +++ b/arch/s390/kernel/early.c @@ -483,7 +483,7 @@ void __init startup_init(void) detect_diag44(); detect_machine_facilities(); setup_topology(); - sclp_facilities_detect(); + sclp_early_detect(); #ifdef CONFIG_DYNAMIC_FTRACE S390_lowcore.ftrace_func = (unsigned long)ftrace_caller; #endif diff --git a/arch/s390/kernel/kprobes.c b/arch/s390/kernel/kprobes.c index 59a9c35c4598..bc71a7b95af5 100644 --- a/arch/s390/kernel/kprobes.c +++ b/arch/s390/kernel/kprobes.c @@ -680,7 +680,7 @@ static int __kprobes kprobe_trap_handler(struct pt_regs *regs, int trapnr) case KPROBE_HIT_SSDONE: /* * We increment the nmissed count for accounting, - * we can also use npre/npostfault count for accouting + * we can also use npre/npostfault count for accounting * these specific fault cases. */ kprobes_inc_nmissed_count(p); diff --git a/arch/s390/kernel/setup.c b/arch/s390/kernel/setup.c index ffe1c53264a7..4444875266ee 100644 --- a/arch/s390/kernel/setup.c +++ b/arch/s390/kernel/setup.c @@ -471,8 +471,9 @@ static void __init setup_memory_end(void) #ifdef CONFIG_ZFCPDUMP - if (ipl_info.type == IPL_TYPE_FCP_DUMP && !OLDMEM_BASE) { - memory_end = ZFCPDUMP_HSA_SIZE; + if (ipl_info.type == IPL_TYPE_FCP_DUMP && + !OLDMEM_BASE && sclp_get_hsa_size()) { + memory_end = sclp_get_hsa_size(); memory_end_set = 1; } #endif @@ -586,7 +587,7 @@ static unsigned long __init find_crash_base(unsigned long crash_size, crash_base = (chunk->addr + chunk->size) - crash_size; if (crash_base < crash_size) continue; - if (crash_base < ZFCPDUMP_HSA_SIZE_MAX) + if (crash_base < sclp_get_hsa_size()) continue; if (crash_base < (unsigned long) INITRD_START + INITRD_SIZE) continue; diff --git a/arch/s390/kvm/diag.c b/arch/s390/kvm/diag.c index 3a74d8af0d69..78d967f180f4 100644 --- a/arch/s390/kvm/diag.c +++ b/arch/s390/kvm/diag.c @@ -107,14 +107,13 @@ static int __diag_ipl_functions(struct kvm_vcpu *vcpu) static int __diag_virtio_hypercall(struct kvm_vcpu *vcpu) { - int ret, idx; + int ret; /* No virtio-ccw notification? Get out quickly. */ if (!vcpu->kvm->arch.css_support || (vcpu->run->s.regs.gprs[1] != KVM_S390_VIRTIO_CCW_NOTIFY)) return -EOPNOTSUPP; - idx = srcu_read_lock(&vcpu->kvm->srcu); /* * The layout is as follows: * - gpr 2 contains the subchannel id (passed as addr) @@ -125,7 +124,6 @@ static int __diag_virtio_hypercall(struct kvm_vcpu *vcpu) vcpu->run->s.regs.gprs[2], 8, &vcpu->run->s.regs.gprs[3], vcpu->run->s.regs.gprs[4]); - srcu_read_unlock(&vcpu->kvm->srcu, idx); /* * Return cookie in gpr 2, but don't overwrite the register if the diff --git a/arch/s390/kvm/gaccess.h b/arch/s390/kvm/gaccess.h index 99d789e8a018..374a439ccc60 100644 --- a/arch/s390/kvm/gaccess.h +++ b/arch/s390/kvm/gaccess.h @@ -18,20 +18,27 @@ #include <asm/uaccess.h> #include "kvm-s390.h" +/* Convert real to absolute address by applying the prefix of the CPU */ +static inline unsigned long kvm_s390_real_to_abs(struct kvm_vcpu *vcpu, + unsigned long gaddr) +{ + unsigned long prefix = vcpu->arch.sie_block->prefix; + if (gaddr < 2 * PAGE_SIZE) + gaddr += prefix; + else if (gaddr >= prefix && gaddr < prefix + 2 * PAGE_SIZE) + gaddr -= prefix; + return gaddr; +} + static inline void __user *__gptr_to_uptr(struct kvm_vcpu *vcpu, void __user *gptr, int prefixing) { - unsigned long prefix = vcpu->arch.sie_block->prefix; unsigned long gaddr = (unsigned long) gptr; unsigned long uaddr; - if (prefixing) { - if (gaddr < 2 * PAGE_SIZE) - gaddr += prefix; - else if ((gaddr >= prefix) && (gaddr < prefix + 2 * PAGE_SIZE)) - gaddr -= prefix; - } + if (prefixing) + gaddr = kvm_s390_real_to_abs(vcpu, gaddr); uaddr = gmap_fault(gaddr, vcpu->arch.gmap); if (IS_ERR_VALUE(uaddr)) uaddr = -EFAULT; diff --git a/arch/s390/kvm/intercept.c b/arch/s390/kvm/intercept.c index 5ee56e5acc23..5ddbbde6f65c 100644 --- a/arch/s390/kvm/intercept.c +++ b/arch/s390/kvm/intercept.c @@ -62,12 +62,6 @@ static int handle_stop(struct kvm_vcpu *vcpu) trace_kvm_s390_stop_request(vcpu->arch.local_int.action_bits); - if (vcpu->arch.local_int.action_bits & ACTION_RELOADVCPU_ON_STOP) { - vcpu->arch.local_int.action_bits &= ~ACTION_RELOADVCPU_ON_STOP; - rc = SIE_INTERCEPT_RERUNVCPU; - vcpu->run->exit_reason = KVM_EXIT_INTR; - } - if (vcpu->arch.local_int.action_bits & ACTION_STOP_ON_STOP) { atomic_set_mask(CPUSTAT_STOPPED, &vcpu->arch.sie_block->cpuflags); diff --git a/arch/s390/kvm/interrupt.c b/arch/s390/kvm/interrupt.c index 7f1f7ac5cf7f..5f79d2d79ca7 100644 --- a/arch/s390/kvm/interrupt.c +++ b/arch/s390/kvm/interrupt.c @@ -436,6 +436,7 @@ int kvm_s390_handle_wait(struct kvm_vcpu *vcpu) hrtimer_start(&vcpu->arch.ckc_timer, ktime_set (0, sltime) , HRTIMER_MODE_REL); VCPU_EVENT(vcpu, 5, "enabled wait via clock comparator: %llx ns", sltime); no_timer: + srcu_read_unlock(&vcpu->kvm->srcu, vcpu->srcu_idx); spin_lock(&vcpu->arch.local_int.float_int->lock); spin_lock_bh(&vcpu->arch.local_int.lock); add_wait_queue(&vcpu->wq, &wait); @@ -455,6 +456,8 @@ no_timer: remove_wait_queue(&vcpu->wq, &wait); spin_unlock_bh(&vcpu->arch.local_int.lock); spin_unlock(&vcpu->arch.local_int.float_int->lock); + vcpu->srcu_idx = srcu_read_lock(&vcpu->kvm->srcu); + hrtimer_try_to_cancel(&vcpu->arch.ckc_timer); return 0; } diff --git a/arch/s390/kvm/kvm-s390.c b/arch/s390/kvm/kvm-s390.c index ed8064cb5c49..569494e01ec6 100644 --- a/arch/s390/kvm/kvm-s390.c +++ b/arch/s390/kvm/kvm-s390.c @@ -695,9 +695,9 @@ static int kvm_s390_handle_requests(struct kvm_vcpu *vcpu) return 0; } -static int __vcpu_run(struct kvm_vcpu *vcpu) +static int vcpu_pre_run(struct kvm_vcpu *vcpu) { - int rc; + int rc, cpuflags; memcpy(&vcpu->arch.sie_block->gg14, &vcpu->run->s.regs.gprs[14], 16); @@ -715,28 +715,24 @@ static int __vcpu_run(struct kvm_vcpu *vcpu) return rc; vcpu->arch.sie_block->icptcode = 0; - VCPU_EVENT(vcpu, 6, "entering sie flags %x", - atomic_read(&vcpu->arch.sie_block->cpuflags)); - trace_kvm_s390_sie_enter(vcpu, - atomic_read(&vcpu->arch.sie_block->cpuflags)); + cpuflags = atomic_read(&vcpu->arch.sie_block->cpuflags); + VCPU_EVENT(vcpu, 6, "entering sie flags %x", cpuflags); + trace_kvm_s390_sie_enter(vcpu, cpuflags); - /* - * As PF_VCPU will be used in fault handler, between guest_enter - * and guest_exit should be no uaccess. - */ - preempt_disable(); - kvm_guest_enter(); - preempt_enable(); - rc = sie64a(vcpu->arch.sie_block, vcpu->run->s.regs.gprs); - kvm_guest_exit(); + return 0; +} + +static int vcpu_post_run(struct kvm_vcpu *vcpu, int exit_reason) +{ + int rc; VCPU_EVENT(vcpu, 6, "exit sie icptcode %d", vcpu->arch.sie_block->icptcode); trace_kvm_s390_sie_exit(vcpu, vcpu->arch.sie_block->icptcode); - if (rc > 0) + if (exit_reason >= 0) { rc = 0; - if (rc < 0) { + } else { if (kvm_is_ucontrol(vcpu->kvm)) { rc = SIE_INTERCEPT_UCONTROL; } else { @@ -747,6 +743,49 @@ static int __vcpu_run(struct kvm_vcpu *vcpu) } memcpy(&vcpu->run->s.regs.gprs[14], &vcpu->arch.sie_block->gg14, 16); + + if (rc == 0) { + if (kvm_is_ucontrol(vcpu->kvm)) + rc = -EOPNOTSUPP; + else + rc = kvm_handle_sie_intercept(vcpu); + } + + return rc; +} + +static int __vcpu_run(struct kvm_vcpu *vcpu) +{ + int rc, exit_reason; + + /* + * We try to hold kvm->srcu during most of vcpu_run (except when run- + * ning the guest), so that memslots (and other stuff) are protected + */ + vcpu->srcu_idx = srcu_read_lock(&vcpu->kvm->srcu); + + do { + rc = vcpu_pre_run(vcpu); + if (rc) + break; + + srcu_read_unlock(&vcpu->kvm->srcu, vcpu->srcu_idx); + /* + * As PF_VCPU will be used in fault handler, between + * guest_enter and guest_exit should be no uaccess. + */ + preempt_disable(); + kvm_guest_enter(); + preempt_enable(); + exit_reason = sie64a(vcpu->arch.sie_block, + vcpu->run->s.regs.gprs); + kvm_guest_exit(); + vcpu->srcu_idx = srcu_read_lock(&vcpu->kvm->srcu); + + rc = vcpu_post_run(vcpu, exit_reason); + } while (!signal_pending(current) && !rc); + + srcu_read_unlock(&vcpu->kvm->srcu, vcpu->srcu_idx); return rc; } @@ -755,7 +794,6 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run) int rc; sigset_t sigsaved; -rerun_vcpu: if (vcpu->sigset_active) sigprocmask(SIG_SETMASK, &vcpu->sigset, &sigsaved); @@ -788,19 +826,7 @@ rerun_vcpu: } might_fault(); - - do { - rc = __vcpu_run(vcpu); - if (rc) - break; - if (kvm_is_ucontrol(vcpu->kvm)) - rc = -EOPNOTSUPP; - else - rc = kvm_handle_sie_intercept(vcpu); - } while (!signal_pending(current) && !rc); - - if (rc == SIE_INTERCEPT_RERUNVCPU) - goto rerun_vcpu; + rc = __vcpu_run(vcpu); if (signal_pending(current) && !rc) { kvm_run->exit_reason = KVM_EXIT_INTR; @@ -958,6 +984,7 @@ long kvm_arch_vcpu_ioctl(struct file *filp, { struct kvm_vcpu *vcpu = filp->private_data; void __user *argp = (void __user *)arg; + int idx; long r; switch (ioctl) { @@ -971,7 +998,9 @@ long kvm_arch_vcpu_ioctl(struct file *filp, break; } case KVM_S390_STORE_STATUS: + idx = srcu_read_lock(&vcpu->kvm->srcu); r = kvm_s390_vcpu_store_status(vcpu, arg); + srcu_read_unlock(&vcpu->kvm->srcu, idx); break; case KVM_S390_SET_INITIAL_PSW: { psw_t psw; @@ -1067,12 +1096,13 @@ int kvm_arch_vcpu_fault(struct kvm_vcpu *vcpu, struct vm_fault *vmf) return VM_FAULT_SIGBUS; } -void kvm_arch_free_memslot(struct kvm_memory_slot *free, +void kvm_arch_free_memslot(struct kvm *kvm, struct kvm_memory_slot *free, struct kvm_memory_slot *dont) { } -int kvm_arch_create_memslot(struct kvm_memory_slot *slot, unsigned long npages) +int kvm_arch_create_memslot(struct kvm *kvm, struct kvm_memory_slot *slot, + unsigned long npages) { return 0; } diff --git a/arch/s390/kvm/kvm-s390.h b/arch/s390/kvm/kvm-s390.h index dc99f1ca4267..b44912a32949 100644 --- a/arch/s390/kvm/kvm-s390.h +++ b/arch/s390/kvm/kvm-s390.h @@ -28,8 +28,7 @@ typedef int (*intercept_handler_t)(struct kvm_vcpu *vcpu); extern unsigned long *vfacilities; /* negativ values are error codes, positive values for internal conditions */ -#define SIE_INTERCEPT_RERUNVCPU (1<<0) -#define SIE_INTERCEPT_UCONTROL (1<<1) +#define SIE_INTERCEPT_UCONTROL (1<<0) int kvm_handle_sie_intercept(struct kvm_vcpu *vcpu); #define VM_EVENT(d_kvm, d_loglevel, d_string, d_args...)\ @@ -91,8 +90,10 @@ static inline void kvm_s390_get_base_disp_sse(struct kvm_vcpu *vcpu, static inline void kvm_s390_get_regs_rre(struct kvm_vcpu *vcpu, int *r1, int *r2) { - *r1 = (vcpu->arch.sie_block->ipb & 0x00f00000) >> 20; - *r2 = (vcpu->arch.sie_block->ipb & 0x000f0000) >> 16; + if (r1) + *r1 = (vcpu->arch.sie_block->ipb & 0x00f00000) >> 20; + if (r2) + *r2 = (vcpu->arch.sie_block->ipb & 0x000f0000) >> 16; } static inline u64 kvm_s390_get_base_disp_rsy(struct kvm_vcpu *vcpu) diff --git a/arch/s390/kvm/priv.c b/arch/s390/kvm/priv.c index 59200ee275e5..2440602e6df1 100644 --- a/arch/s390/kvm/priv.c +++ b/arch/s390/kvm/priv.c @@ -30,6 +30,38 @@ #include "kvm-s390.h" #include "trace.h" +/* Handle SCK (SET CLOCK) interception */ +static int handle_set_clock(struct kvm_vcpu *vcpu) +{ + struct kvm_vcpu *cpup; + s64 hostclk, val; + u64 op2; + int i; + + if (vcpu->arch.sie_block->gpsw.mask & PSW_MASK_PSTATE) + return kvm_s390_inject_program_int(vcpu, PGM_PRIVILEGED_OP); + + op2 = kvm_s390_get_base_disp_s(vcpu); + if (op2 & 7) /* Operand must be on a doubleword boundary */ + return kvm_s390_inject_program_int(vcpu, PGM_SPECIFICATION); + if (get_guest(vcpu, val, (u64 __user *) op2)) + return kvm_s390_inject_program_int(vcpu, PGM_ADDRESSING); + + if (store_tod_clock(&hostclk)) { + kvm_s390_set_psw_cc(vcpu, 3); + return 0; + } + val = (val - hostclk) & ~0x3fUL; + + mutex_lock(&vcpu->kvm->lock); + kvm_for_each_vcpu(i, cpup, vcpu->kvm) + cpup->arch.sie_block->epoch = val; + mutex_unlock(&vcpu->kvm->lock); + + kvm_s390_set_psw_cc(vcpu, 0); + return 0; +} + static int handle_set_prefix(struct kvm_vcpu *vcpu) { u64 operand2; @@ -128,6 +160,33 @@ static int handle_skey(struct kvm_vcpu *vcpu) return 0; } +static int handle_test_block(struct kvm_vcpu *vcpu) +{ + unsigned long hva; + gpa_t addr; + int reg2; + + if (vcpu->arch.sie_block->gpsw.mask & PSW_MASK_PSTATE) + return kvm_s390_inject_program_int(vcpu, PGM_PRIVILEGED_OP); + + kvm_s390_get_regs_rre(vcpu, NULL, ®2); + addr = vcpu->run->s.regs.gprs[reg2] & PAGE_MASK; + addr = kvm_s390_real_to_abs(vcpu, addr); + + hva = gfn_to_hva(vcpu->kvm, gpa_to_gfn(addr)); + if (kvm_is_error_hva(hva)) + return kvm_s390_inject_program_int(vcpu, PGM_ADDRESSING); + /* + * We don't expect errors on modern systems, and do not care + * about storage keys (yet), so let's just clear the page. + */ + if (clear_user((void __user *)hva, PAGE_SIZE) != 0) + return -EFAULT; + kvm_s390_set_psw_cc(vcpu, 0); + vcpu->run->s.regs.gprs[0] = 0; + return 0; +} + static int handle_tpi(struct kvm_vcpu *vcpu) { struct kvm_s390_interrupt_info *inti; @@ -438,12 +497,14 @@ out_exception: static const intercept_handler_t b2_handlers[256] = { [0x02] = handle_stidp, + [0x04] = handle_set_clock, [0x10] = handle_set_prefix, [0x11] = handle_store_prefix, [0x12] = handle_store_cpu_address, [0x29] = handle_skey, [0x2a] = handle_skey, [0x2b] = handle_skey, + [0x2c] = handle_test_block, [0x30] = handle_io_inst, [0x31] = handle_io_inst, [0x32] = handle_io_inst, diff --git a/arch/s390/mm/pgtable.c b/arch/s390/mm/pgtable.c index 0a2e5e086749..e794c88f699a 100644 --- a/arch/s390/mm/pgtable.c +++ b/arch/s390/mm/pgtable.c @@ -772,7 +772,11 @@ static inline unsigned long *page_table_alloc_pgste(struct mm_struct *mm, __free_page(page); return NULL; } - pgtable_page_ctor(page); + if (!pgtable_page_ctor(page)) { + kfree(mp); + __free_page(page); + return NULL; + } mp->vmaddr = vmaddr & PMD_MASK; INIT_LIST_HEAD(&mp->mapper); page->index = (unsigned long) mp; @@ -902,7 +906,10 @@ unsigned long *page_table_alloc(struct mm_struct *mm, unsigned long vmaddr) page = alloc_page(GFP_KERNEL|__GFP_REPEAT); if (!page) return NULL; - pgtable_page_ctor(page); + if (!pgtable_page_ctor(page)) { + __free_page(page); + return NULL; + } atomic_set(&page->_mapcount, 1); table = (unsigned long *) page_to_phys(page); clear_table(table, _PAGE_INVALID, PAGE_SIZE); @@ -1244,11 +1251,11 @@ void pgtable_trans_huge_deposit(struct mm_struct *mm, pmd_t *pmdp, assert_spin_locked(&mm->page_table_lock); /* FIFO */ - if (!mm->pmd_huge_pte) + if (!pmd_huge_pte(mm, pmdp)) INIT_LIST_HEAD(lh); else - list_add(lh, (struct list_head *) mm->pmd_huge_pte); - mm->pmd_huge_pte = pgtable; + list_add(lh, (struct list_head *) pmd_huge_pte(mm, pmdp)); + pmd_huge_pte(mm, pmdp) = pgtable; } pgtable_t pgtable_trans_huge_withdraw(struct mm_struct *mm, pmd_t *pmdp) @@ -1260,12 +1267,12 @@ pgtable_t pgtable_trans_huge_withdraw(struct mm_struct *mm, pmd_t *pmdp) assert_spin_locked(&mm->page_table_lock); /* FIFO */ - pgtable = mm->pmd_huge_pte; + pgtable = pmd_huge_pte(mm, pmdp); lh = (struct list_head *) pgtable; if (list_empty(lh)) - mm->pmd_huge_pte = NULL; + pmd_huge_pte(mm, pmdp) = NULL; else { - mm->pmd_huge_pte = (pgtable_t) lh->next; + pmd_huge_pte(mm, pmdp) = (pgtable_t) lh->next; list_del(lh); } ptep = (pte_t *) pgtable; diff --git a/arch/s390/pci/pci.c b/arch/s390/pci/pci.c index 0c9a17780e4b..bf7c73d71eef 100644 --- a/arch/s390/pci/pci.c +++ b/arch/s390/pci/pci.c @@ -530,20 +530,6 @@ static void zpci_unmap_resources(struct zpci_dev *zdev) } } -struct zpci_dev *zpci_alloc_device(void) -{ - struct zpci_dev *zdev; - - /* Alloc memory for our private pci device data */ - zdev = kzalloc(sizeof(*zdev), GFP_KERNEL); - return zdev ? : ERR_PTR(-ENOMEM); -} - -void zpci_free_device(struct zpci_dev *zdev) -{ - kfree(zdev); -} - int pcibios_add_platform_entries(struct pci_dev *pdev) { return zpci_sysfs_add_device(&pdev->dev); @@ -579,37 +565,6 @@ static void zpci_irq_exit(void) unregister_adapter_interrupt(&zpci_airq); } -static struct resource *zpci_alloc_bus_resource(unsigned long start, unsigned long size, - unsigned long flags, int domain) -{ - struct resource *r; - char *name; - int rc; - - r = kzalloc(sizeof(*r), GFP_KERNEL); - if (!r) - return ERR_PTR(-ENOMEM); - r->start = start; - r->end = r->start + size - 1; - r->flags = flags; - r->parent = &iomem_resource; - name = kmalloc(18, GFP_KERNEL); - if (!name) { - kfree(r); - return ERR_PTR(-ENOMEM); - } - sprintf(name, "PCI Bus: %04x:%02x", domain, ZPCI_BUS_NR); - r->name = name; - - rc = request_resource(&iomem_resource, r); - if (rc) { - kfree(r->name); - kfree(r); - return ERR_PTR(-ENOMEM); - } - return r; -} - static int zpci_alloc_iomap(struct zpci_dev *zdev) { int entry; @@ -633,6 +588,82 @@ static void zpci_free_iomap(struct zpci_dev *zdev, int entry) spin_unlock(&zpci_iomap_lock); } +static struct resource *__alloc_res(struct zpci_dev *zdev, unsigned long start, + unsigned long size, unsigned long flags) +{ + struct resource *r; + + r = kzalloc(sizeof(*r), GFP_KERNEL); + if (!r) + return NULL; + + r->start = start; + r->end = r->start + size - 1; + r->flags = flags; + r->name = zdev->res_name; + + if (request_resource(&iomem_resource, r)) { + kfree(r); + return NULL; + } + return r; +} + +static int zpci_setup_bus_resources(struct zpci_dev *zdev, + struct list_head *resources) +{ + unsigned long addr, size, flags; + struct resource *res; + int i, entry; + + snprintf(zdev->res_name, sizeof(zdev->res_name), + "PCI Bus %04x:%02x", zdev->domain, ZPCI_BUS_NR); + + for (i = 0; i < PCI_BAR_COUNT; i++) { + if (!zdev->bars[i].size) + continue; + entry = zpci_alloc_iomap(zdev); + if (entry < 0) + return entry; + zdev->bars[i].map_idx = entry; + + /* only MMIO is supported */ + flags = IORESOURCE_MEM; + if (zdev->bars[i].val & 8) + flags |= IORESOURCE_PREFETCH; + if (zdev->bars[i].val & 4) + flags |= IORESOURCE_MEM_64; + + addr = ZPCI_IOMAP_ADDR_BASE + ((u64) entry << 48); + + size = 1UL << zdev->bars[i].size; + + res = __alloc_res(zdev, addr, size, flags); + if (!res) { + zpci_free_iomap(zdev, entry); + return -ENOMEM; + } + zdev->bars[i].res = res; + pci_add_resource(resources, res); + } + + return 0; +} + +static void zpci_cleanup_bus_resources(struct zpci_dev *zdev) +{ + int i; + + for (i = 0; i < PCI_BAR_COUNT; i++) { + if (!zdev->bars[i].size) + continue; + + zpci_free_iomap(zdev, zdev->bars[i].map_idx); + release_resource(zdev->bars[i].res); + kfree(zdev->bars[i].res); + } +} + int pcibios_add_device(struct pci_dev *pdev) { struct zpci_dev *zdev = get_zdev(pdev); @@ -729,52 +760,6 @@ struct dev_pm_ops pcibios_pm_ops = { }; #endif /* CONFIG_HIBERNATE_CALLBACKS */ -static int zpci_scan_bus(struct zpci_dev *zdev) -{ - struct resource *res; - LIST_HEAD(resources); - int i; - - /* allocate mapping entry for each used bar */ - for (i = 0; i < PCI_BAR_COUNT; i++) { - unsigned long addr, size, flags; - int entry; - - if (!zdev->bars[i].size) - continue; - entry = zpci_alloc_iomap(zdev); - if (entry < 0) - return entry; - zdev->bars[i].map_idx = entry; - - /* only MMIO is supported */ - flags = IORESOURCE_MEM; - if (zdev->bars[i].val & 8) - flags |= IORESOURCE_PREFETCH; - if (zdev->bars[i].val & 4) - flags |= IORESOURCE_MEM_64; - - addr = ZPCI_IOMAP_ADDR_BASE + ((u64) entry << 48); - - size = 1UL << zdev->bars[i].size; - - res = zpci_alloc_bus_resource(addr, size, flags, zdev->domain); - if (IS_ERR(res)) { - zpci_free_iomap(zdev, entry); - return PTR_ERR(res); - } - pci_add_resource(&resources, res); - } - - zdev->bus = pci_scan_root_bus(NULL, ZPCI_BUS_NR, &pci_root_ops, - zdev, &resources); - if (!zdev->bus) - return -EIO; - - zdev->bus->max_bus_speed = zdev->max_bus_speed; - return 0; -} - static int zpci_alloc_domain(struct zpci_dev *zdev) { spin_lock(&zpci_domain_lock); @@ -795,6 +780,41 @@ static void zpci_free_domain(struct zpci_dev *zdev) spin_unlock(&zpci_domain_lock); } +void pcibios_remove_bus(struct pci_bus *bus) +{ + struct zpci_dev *zdev = get_zdev_by_bus(bus); + + zpci_exit_slot(zdev); + zpci_cleanup_bus_resources(zdev); + zpci_free_domain(zdev); + + spin_lock(&zpci_list_lock); + list_del(&zdev->entry); + spin_unlock(&zpci_list_lock); + + kfree(zdev); +} + +static int zpci_scan_bus(struct zpci_dev *zdev) +{ + LIST_HEAD(resources); + int ret; + + ret = zpci_setup_bus_resources(zdev, &resources); + if (ret) + return ret; + + zdev->bus = pci_scan_root_bus(NULL, ZPCI_BUS_NR, &pci_root_ops, + zdev, &resources); + if (!zdev->bus) { + zpci_cleanup_bus_resources(zdev); + return -EIO; + } + + zdev->bus->max_bus_speed = zdev->max_bus_speed; + return 0; +} + int zpci_enable_device(struct zpci_dev *zdev) { int rc; diff --git a/arch/s390/pci/pci_clp.c b/arch/s390/pci/pci_clp.c index 84147984224a..c747394029ee 100644 --- a/arch/s390/pci/pci_clp.c +++ b/arch/s390/pci/pci_clp.c @@ -155,9 +155,9 @@ int clp_add_pci_device(u32 fid, u32 fh, int configured) int rc; zpci_dbg(3, "add fid:%x, fh:%x, c:%d\n", fid, fh, configured); - zdev = zpci_alloc_device(); - if (IS_ERR(zdev)) - return PTR_ERR(zdev); + zdev = kzalloc(sizeof(*zdev), GFP_KERNEL); + if (!zdev) + return -ENOMEM; zdev->fh = fh; zdev->fid = fid; @@ -178,7 +178,7 @@ int clp_add_pci_device(u32 fid, u32 fh, int configured) return 0; error: - zpci_free_device(zdev); + kfree(zdev); return rc; } diff --git a/arch/s390/pci/pci_event.c b/arch/s390/pci/pci_event.c index 278e671ec9ac..800f064b0da7 100644 --- a/arch/s390/pci/pci_event.c +++ b/arch/s390/pci/pci_event.c @@ -11,6 +11,7 @@ #include <linux/kernel.h> #include <linux/pci.h> #include <asm/pci_debug.h> +#include <asm/sclp.h> /* Content Code Description for PCI Function Error */ struct zpci_ccdf_err { @@ -42,10 +43,27 @@ struct zpci_ccdf_avail { u16 pec; /* PCI event code */ } __packed; -static void zpci_event_log_avail(struct zpci_ccdf_avail *ccdf) +void zpci_event_error(void *data) { + struct zpci_ccdf_err *ccdf = data; + struct zpci_dev *zdev = get_zdev_by_fid(ccdf->fid); + + zpci_err("error CCDF:\n"); + zpci_err_hex(ccdf, sizeof(*ccdf)); + + if (!zdev) + return; + + pr_err("%s: Event 0x%x reports an error for PCI function 0x%x\n", + pci_name(zdev->pdev), ccdf->pec, ccdf->fid); +} + +void zpci_event_availability(void *data) +{ + struct zpci_ccdf_avail *ccdf = data; struct zpci_dev *zdev = get_zdev_by_fid(ccdf->fid); struct pci_dev *pdev = zdev ? zdev->pdev : NULL; + int ret; pr_info("%s: Event 0x%x reconfigured PCI function 0x%x\n", pdev ? pci_name(pdev) : "n/a", ccdf->pec, ccdf->fid); @@ -53,36 +71,47 @@ static void zpci_event_log_avail(struct zpci_ccdf_avail *ccdf) zpci_err_hex(ccdf, sizeof(*ccdf)); switch (ccdf->pec) { - case 0x0301: - zpci_enable_device(zdev); + case 0x0301: /* Standby -> Configured */ + if (!zdev || zdev->state == ZPCI_FN_STATE_CONFIGURED) + break; + zdev->state = ZPCI_FN_STATE_CONFIGURED; + ret = zpci_enable_device(zdev); + if (ret) + break; + pci_rescan_bus(zdev->bus); break; - case 0x0302: + case 0x0302: /* Reserved -> Standby */ clp_add_pci_device(ccdf->fid, ccdf->fh, 0); break; - case 0x0306: + case 0x0303: /* Deconfiguration requested */ + if (pdev) + pci_stop_and_remove_bus_device(pdev); + + ret = zpci_disable_device(zdev); + if (ret) + break; + + ret = sclp_pci_deconfigure(zdev->fid); + zpci_dbg(3, "deconf fid:%x, rc:%d\n", zdev->fid, ret); + if (!ret) + zdev->state = ZPCI_FN_STATE_STANDBY; + + break; + case 0x0304: /* Configured -> Standby */ + if (pdev) + pci_stop_and_remove_bus_device(pdev); + + zpci_disable_device(zdev); + zdev->state = ZPCI_FN_STATE_STANDBY; + break; + case 0x0306: /* 0x308 or 0x302 for multiple devices */ clp_rescan_pci_devices(); break; + case 0x0308: /* Standby -> Reserved */ + pci_stop_root_bus(zdev->bus); + pci_remove_root_bus(zdev->bus); + break; default: break; } } - -void zpci_event_error(void *data) -{ - struct zpci_ccdf_err *ccdf = data; - struct zpci_dev *zdev = get_zdev_by_fid(ccdf->fid); - - zpci_err("error CCDF:\n"); - zpci_err_hex(ccdf, sizeof(*ccdf)); - - if (!zdev) - return; - - pr_err("%s: Event 0x%x reports an error for PCI function 0x%x\n", - pci_name(zdev->pdev), ccdf->pec, ccdf->fid); -} - -void zpci_event_availability(void *data) -{ - zpci_event_log_avail(data); -} diff --git a/arch/score/include/asm/pgalloc.h b/arch/score/include/asm/pgalloc.h index 716b3fd1d863..2e067657db98 100644 --- a/arch/score/include/asm/pgalloc.h +++ b/arch/score/include/asm/pgalloc.h @@ -54,9 +54,12 @@ static inline struct page *pte_alloc_one(struct mm_struct *mm, struct page *pte; pte = alloc_pages(GFP_KERNEL | __GFP_REPEAT, PTE_ORDER); - if (pte) { - clear_highpage(pte); - pgtable_page_ctor(pte); + if (!pte) + return NULL; + clear_highpage(pte); + if (!pgtable_page_ctor(pte)) { + __free_page(pte); + return NULL; } return pte; } diff --git a/arch/score/include/asm/thread_info.h b/arch/score/include/asm/thread_info.h index 1425cc034872..656b7ada9326 100644 --- a/arch/score/include/asm/thread_info.h +++ b/arch/score/include/asm/thread_info.h @@ -72,8 +72,6 @@ register struct thread_info *__current_thread_info __asm__("r28"); #endif /* !__ASSEMBLY__ */ -#define PREEMPT_ACTIVE 0x10000000 - /* * thread information flags * - these are process state flags that various assembly files may need to diff --git a/arch/sh/Kconfig b/arch/sh/Kconfig index 224f4bc9925e..9b0979f4df7a 100644 --- a/arch/sh/Kconfig +++ b/arch/sh/Kconfig @@ -1,5 +1,6 @@ config SUPERH def_bool y + select ARCH_MIGHT_HAVE_PC_PARPORT select EXPERT select CLKDEV_LOOKUP select HAVE_IDE if HAS_IOPORT @@ -711,7 +712,6 @@ config CC_STACKPROTECTOR config SMP bool "Symmetric multi-processing support" depends on SYS_SUPPORTS_SMP - select USE_GENERIC_SMP_HELPERS ---help--- This enables support for systems with more than one CPU. If you have a system with only one CPU, like most personal computers, say N. If diff --git a/arch/sh/boards/mach-ecovec24/setup.c b/arch/sh/boards/mach-ecovec24/setup.c index 1fa8be409771..122f737a901f 100644 --- a/arch/sh/boards/mach-ecovec24/setup.c +++ b/arch/sh/boards/mach-ecovec24/setup.c @@ -15,6 +15,7 @@ #include <linux/mmc/sh_mmcif.h> #include <linux/mmc/sh_mobile_sdhi.h> #include <linux/mtd/physmap.h> +#include <linux/mfd/tmio.h> #include <linux/gpio.h> #include <linux/interrupt.h> #include <linux/io.h> diff --git a/arch/sh/include/asm/mmu_context.h b/arch/sh/include/asm/mmu_context.h index 21c5088788da..b9d9489a5012 100644 --- a/arch/sh/include/asm/mmu_context.h +++ b/arch/sh/include/asm/mmu_context.h @@ -81,7 +81,7 @@ static inline void get_mmu_context(struct mm_struct *mm, unsigned int cpu) /* * Fix version; Note that we avoid version #0 - * to distingush NO_CONTEXT. + * to distinguish NO_CONTEXT. */ if (!asid) asid = MMU_CONTEXT_FIRST_VERSION; diff --git a/arch/sh/include/asm/pgalloc.h b/arch/sh/include/asm/pgalloc.h index 8c00785c60d5..a33673b3687d 100644 --- a/arch/sh/include/asm/pgalloc.h +++ b/arch/sh/include/asm/pgalloc.h @@ -47,7 +47,10 @@ static inline pgtable_t pte_alloc_one(struct mm_struct *mm, if (!pg) return NULL; page = virt_to_page(pg); - pgtable_page_ctor(page); + if (!pgtable_page_ctor(page)) { + quicklist_free(QUICK_PT, NULL, pg); + return NULL; + } return page; } diff --git a/arch/sh/include/asm/thread_info.h b/arch/sh/include/asm/thread_info.h index 45a93669289d..ad27ffa65e2e 100644 --- a/arch/sh/include/asm/thread_info.h +++ b/arch/sh/include/asm/thread_info.h @@ -41,8 +41,6 @@ struct thread_info { #endif -#define PREEMPT_ACTIVE 0x10000000 - #if defined(CONFIG_4KSTACKS) #define THREAD_SHIFT 12 #else diff --git a/arch/sh/kernel/entry-common.S b/arch/sh/kernel/entry-common.S index 9b6e4beeb296..ca46834294b7 100644 --- a/arch/sh/kernel/entry-common.S +++ b/arch/sh/kernel/entry-common.S @@ -108,7 +108,7 @@ need_resched: and #(0xf0>>1), r0 ! interrupts off (exception path)? cmp/eq #(0xf0>>1), r0 bt noresched - mov.l 3f, r0 + mov.l 1f, r0 jsr @r0 ! call preempt_schedule_irq nop bra need_resched @@ -119,9 +119,7 @@ noresched: nop .align 2 -1: .long PREEMPT_ACTIVE -2: .long schedule -3: .long preempt_schedule_irq +1: .long preempt_schedule_irq #endif ENTRY(resume_userspace) diff --git a/arch/sparc/Kconfig b/arch/sparc/Kconfig index 78c4fdb91bc5..d4f7a6a163dc 100644 --- a/arch/sparc/Kconfig +++ b/arch/sparc/Kconfig @@ -12,6 +12,7 @@ config 64BIT config SPARC bool default y + select ARCH_MIGHT_HAVE_PC_PARPORT if SPARC64 && PCI select OF select OF_PROMTREE select HAVE_IDE @@ -28,7 +29,6 @@ config SPARC select HAVE_ARCH_JUMP_LABEL select GENERIC_IRQ_SHOW select ARCH_WANT_IPC_PARSE_VERSION - select USE_GENERIC_SMP_HELPERS if SMP select GENERIC_PCI_IOMAP select HAVE_NMI_WATCHDOG if SPARC64 select HAVE_BPF_JIT @@ -64,6 +64,7 @@ config SPARC64 select HAVE_DYNAMIC_FTRACE select HAVE_FTRACE_MCOUNT_RECORD select HAVE_SYSCALL_TRACEPOINTS + select HAVE_CONTEXT_TRACKING select HAVE_DEBUG_KMEMLEAK select RTC_DRV_CMOS select RTC_DRV_BQ4802 diff --git a/arch/sparc/include/asm/hardirq_32.h b/arch/sparc/include/asm/hardirq_32.h index 162007643cdc..ee93923b7f82 100644 --- a/arch/sparc/include/asm/hardirq_32.h +++ b/arch/sparc/include/asm/hardirq_32.h @@ -7,7 +7,6 @@ #ifndef __SPARC_HARDIRQ_H #define __SPARC_HARDIRQ_H -#define HARDIRQ_BITS 8 #include <asm-generic/hardirq.h> #endif /* __SPARC_HARDIRQ_H */ diff --git a/arch/sparc/include/asm/hardirq_64.h b/arch/sparc/include/asm/hardirq_64.h index 7c29fd1a87aa..f478ff1ddd02 100644 --- a/arch/sparc/include/asm/hardirq_64.h +++ b/arch/sparc/include/asm/hardirq_64.h @@ -14,6 +14,4 @@ void ack_bad_irq(unsigned int irq); -#define HARDIRQ_BITS 8 - #endif /* !(__SPARC64_HARDIRQ_H) */ diff --git a/arch/sparc/include/asm/mmu_64.h b/arch/sparc/include/asm/mmu_64.h index 76092c4dd277..f668797ae234 100644 --- a/arch/sparc/include/asm/mmu_64.h +++ b/arch/sparc/include/asm/mmu_64.h @@ -93,7 +93,6 @@ typedef struct { spinlock_t lock; unsigned long sparc64_ctx_val; unsigned long huge_pte_count; - struct page *pgtable_page; struct tsb_config tsb_block[MM_NUM_TSBS]; struct hv_tsb_descr tsb_descr[MM_NUM_TSBS]; } mm_context_t; diff --git a/arch/sparc/include/asm/page_64.h b/arch/sparc/include/asm/page_64.h index e15538899f3d..aac53fcea807 100644 --- a/arch/sparc/include/asm/page_64.h +++ b/arch/sparc/include/asm/page_64.h @@ -15,7 +15,10 @@ #define DCACHE_ALIASING_POSSIBLE #endif -#define HPAGE_SHIFT 22 +#define HPAGE_SHIFT 23 +#define REAL_HPAGE_SHIFT 22 + +#define REAL_HPAGE_SIZE (_AC(1,UL) << REAL_HPAGE_SHIFT) #if defined(CONFIG_HUGETLB_PAGE) || defined(CONFIG_TRANSPARENT_HUGEPAGE) #define HPAGE_SIZE (_AC(1,UL) << HPAGE_SHIFT) @@ -53,8 +56,8 @@ extern void copy_user_page(void *to, void *from, unsigned long vaddr, struct pag /* These are used to make use of C type-checking.. */ typedef struct { unsigned long pte; } pte_t; typedef struct { unsigned long iopte; } iopte_t; -typedef struct { unsigned int pmd; } pmd_t; -typedef struct { unsigned int pgd; } pgd_t; +typedef struct { unsigned long pmd; } pmd_t; +typedef struct { unsigned long pgd; } pgd_t; typedef struct { unsigned long pgprot; } pgprot_t; #define pte_val(x) ((x).pte) @@ -73,8 +76,8 @@ typedef struct { unsigned long pgprot; } pgprot_t; /* .. while these make it easier on the compiler */ typedef unsigned long pte_t; typedef unsigned long iopte_t; -typedef unsigned int pmd_t; -typedef unsigned int pgd_t; +typedef unsigned long pmd_t; +typedef unsigned long pgd_t; typedef unsigned long pgprot_t; #define pte_val(x) (x) @@ -93,18 +96,44 @@ typedef unsigned long pgprot_t; typedef pte_t *pgtable_t; +/* These two values define the virtual address space range in which we + * must forbid 64-bit user processes from making mappings. It used to + * represent precisely the virtual address space hole present in most + * early sparc64 chips including UltraSPARC-I. But now it also is + * further constrained by the limits of our page tables, which is + * 43-bits of virtual address. + */ +#define SPARC64_VA_HOLE_TOP _AC(0xfffffc0000000000,UL) +#define SPARC64_VA_HOLE_BOTTOM _AC(0x0000040000000000,UL) + +/* The next two defines specify the actual exclusion region we + * enforce, wherein we use a 4GB red zone on each side of the VA hole. + */ +#define VA_EXCLUDE_START (SPARC64_VA_HOLE_BOTTOM - (1UL << 32UL)) +#define VA_EXCLUDE_END (SPARC64_VA_HOLE_TOP + (1UL << 32UL)) + #define TASK_UNMAPPED_BASE (test_thread_flag(TIF_32BIT) ? \ - (_AC(0x0000000070000000,UL)) : \ - (_AC(0xfffff80000000000,UL) + (1UL << 32UL))) + _AC(0x0000000070000000,UL) : \ + VA_EXCLUDE_END) #include <asm-generic/memory_model.h> +#define PAGE_OFFSET_BY_BITS(X) (-(_AC(1,UL) << (X))) +extern unsigned long PAGE_OFFSET; + #endif /* !(__ASSEMBLY__) */ -/* We used to stick this into a hard-coded global register (%g4) - * but that does not make sense anymore. +/* The maximum number of physical memory address bits we support, this + * is used to size various tables used to manage kernel TLB misses and + * also the sparsemem code. + */ +#define MAX_PHYS_ADDRESS_BITS 47 + +/* These two shift counts are used when indexing sparc64_valid_addr_bitmap + * and kpte_linear_bitmap. */ -#define PAGE_OFFSET _AC(0xFFFFF80000000000,UL) +#define ILOG2_4MB 22 +#define ILOG2_256MB 28 #ifndef __ASSEMBLY__ diff --git a/arch/sparc/include/asm/pgtable_64.h b/arch/sparc/include/asm/pgtable_64.h index 36760317814f..8358dc144959 100644 --- a/arch/sparc/include/asm/pgtable_64.h +++ b/arch/sparc/include/asm/pgtable_64.h @@ -48,18 +48,18 @@ /* PMD_SHIFT determines the size of the area a second-level page * table can map */ -#define PMD_SHIFT (PAGE_SHIFT + (PAGE_SHIFT-4)) +#define PMD_SHIFT (PAGE_SHIFT + (PAGE_SHIFT-3)) #define PMD_SIZE (_AC(1,UL) << PMD_SHIFT) #define PMD_MASK (~(PMD_SIZE-1)) -#define PMD_BITS (PAGE_SHIFT - 2) +#define PMD_BITS (PAGE_SHIFT - 3) /* PGDIR_SHIFT determines what a third-level page table entry can map */ -#define PGDIR_SHIFT (PAGE_SHIFT + (PAGE_SHIFT-4) + PMD_BITS) +#define PGDIR_SHIFT (PAGE_SHIFT + (PAGE_SHIFT-3) + PMD_BITS) #define PGDIR_SIZE (_AC(1,UL) << PGDIR_SHIFT) #define PGDIR_MASK (~(PGDIR_SIZE-1)) -#define PGDIR_BITS (PAGE_SHIFT - 2) +#define PGDIR_BITS (PAGE_SHIFT - 3) -#if (PGDIR_SHIFT + PGDIR_BITS) != 44 +#if (PGDIR_SHIFT + PGDIR_BITS) != 43 #error Page table parameters do not cover virtual address space properly. #endif @@ -67,35 +67,12 @@ #error PMD_SHIFT must equal HPAGE_SHIFT for transparent huge pages. #endif -/* PMDs point to PTE tables which are 4K aligned. */ -#define PMD_PADDR _AC(0xfffffffe,UL) -#define PMD_PADDR_SHIFT _AC(11,UL) - -#define PMD_ISHUGE _AC(0x00000001,UL) - -/* This is the PMD layout when PMD_ISHUGE is set. With 4MB huge - * pages, this frees up a bunch of bits in the layout that we can - * use for the protection settings and software metadata. - */ -#define PMD_HUGE_PADDR _AC(0xfffff800,UL) -#define PMD_HUGE_PROTBITS _AC(0x000007ff,UL) -#define PMD_HUGE_PRESENT _AC(0x00000400,UL) -#define PMD_HUGE_WRITE _AC(0x00000200,UL) -#define PMD_HUGE_DIRTY _AC(0x00000100,UL) -#define PMD_HUGE_ACCESSED _AC(0x00000080,UL) -#define PMD_HUGE_EXEC _AC(0x00000040,UL) -#define PMD_HUGE_SPLITTING _AC(0x00000020,UL) - -/* PGDs point to PMD tables which are 8K aligned. */ -#define PGD_PADDR _AC(0xfffffffc,UL) -#define PGD_PADDR_SHIFT _AC(11,UL) - #ifndef __ASSEMBLY__ #include <linux/sched.h> /* Entries per page directory level. */ -#define PTRS_PER_PTE (1UL << (PAGE_SHIFT-4)) +#define PTRS_PER_PTE (1UL << (PAGE_SHIFT-3)) #define PTRS_PER_PMD (1UL << PMD_BITS) #define PTRS_PER_PGD (1UL << PGDIR_BITS) @@ -112,6 +89,7 @@ #define _PAGE_VALID _AC(0x8000000000000000,UL) /* Valid TTE */ #define _PAGE_R _AC(0x8000000000000000,UL) /* Keep ref bit uptodate*/ #define _PAGE_SPECIAL _AC(0x0200000000000000,UL) /* Special page */ +#define _PAGE_PMD_HUGE _AC(0x0100000000000000,UL) /* Huge page */ /* Advertise support for _PAGE_SPECIAL */ #define __HAVE_ARCH_PTE_SPECIAL @@ -125,6 +103,7 @@ #define _PAGE_IE_4U _AC(0x0800000000000000,UL) /* Invert Endianness */ #define _PAGE_SOFT2_4U _AC(0x07FC000000000000,UL) /* Software bits, set 2 */ #define _PAGE_SPECIAL_4U _AC(0x0200000000000000,UL) /* Special page */ +#define _PAGE_PMD_HUGE_4U _AC(0x0100000000000000,UL) /* Huge page */ #define _PAGE_RES1_4U _AC(0x0002000000000000,UL) /* Reserved */ #define _PAGE_SZ32MB_4U _AC(0x0001000000000000,UL) /* (Panther) 32MB page */ #define _PAGE_SZ256MB_4U _AC(0x2001000000000000,UL) /* (Panther) 256MB page */ @@ -155,6 +134,7 @@ #define _PAGE_READ_4V _AC(0x0800000000000000,UL) /* Readable SW Bit */ #define _PAGE_WRITE_4V _AC(0x0400000000000000,UL) /* Writable SW Bit */ #define _PAGE_SPECIAL_4V _AC(0x0200000000000000,UL) /* Special page */ +#define _PAGE_PMD_HUGE_4V _AC(0x0100000000000000,UL) /* Huge page */ #define _PAGE_PADDR_4V _AC(0x00FFFFFFFFFFE000,UL) /* paddr[55:13] */ #define _PAGE_IE_4V _AC(0x0000000000001000,UL) /* Invert Endianness */ #define _PAGE_E_4V _AC(0x0000000000000800,UL) /* side-Effect */ @@ -180,6 +160,10 @@ #define _PAGE_SZBITS_4U _PAGE_SZ8K_4U #define _PAGE_SZBITS_4V _PAGE_SZ8K_4V +#if REAL_HPAGE_SHIFT != 22 +#error REAL_HPAGE_SHIFT and _PAGE_SZHUGE_foo must match up +#endif + #define _PAGE_SZHUGE_4U _PAGE_SZ4MB_4U #define _PAGE_SZHUGE_4V _PAGE_SZ4MB_4V @@ -239,16 +223,13 @@ static inline pte_t pfn_pte(unsigned long pfn, pgprot_t prot) #define mk_pte(page, pgprot) pfn_pte(page_to_pfn(page), (pgprot)) #ifdef CONFIG_TRANSPARENT_HUGEPAGE -extern pmd_t pfn_pmd(unsigned long page_nr, pgprot_t pgprot); -#define mk_pmd(page, pgprot) pfn_pmd(page_to_pfn(page), (pgprot)) - -extern pmd_t pmd_modify(pmd_t pmd, pgprot_t newprot); - -static inline pmd_t pmd_mkhuge(pmd_t pmd) +static inline pmd_t pfn_pmd(unsigned long page_nr, pgprot_t pgprot) { - /* Do nothing, mk_pmd() does this part. */ - return pmd; + pte_t pte = pfn_pte(page_nr, pgprot); + + return __pmd(pte_val(pte)); } +#define mk_pmd(page, pgprot) pfn_pmd(page_to_pfn(page), (pgprot)) #endif /* This one can be done with two shifts. */ @@ -309,14 +290,25 @@ static inline pte_t pte_modify(pte_t pte, pgprot_t prot) : "=r" (mask), "=r" (tmp) : "i" (_PAGE_PADDR_4U | _PAGE_MODIFIED_4U | _PAGE_ACCESSED_4U | _PAGE_CP_4U | _PAGE_CV_4U | _PAGE_E_4U | _PAGE_PRESENT_4U | - _PAGE_SPECIAL), + _PAGE_SPECIAL | _PAGE_PMD_HUGE | _PAGE_SZALL_4U), "i" (_PAGE_PADDR_4V | _PAGE_MODIFIED_4V | _PAGE_ACCESSED_4V | _PAGE_CP_4V | _PAGE_CV_4V | _PAGE_E_4V | _PAGE_PRESENT_4V | - _PAGE_SPECIAL)); + _PAGE_SPECIAL | _PAGE_PMD_HUGE | _PAGE_SZALL_4V)); return __pte((pte_val(pte) & mask) | (pgprot_val(prot) & ~mask)); } +#ifdef CONFIG_TRANSPARENT_HUGEPAGE +static inline pmd_t pmd_modify(pmd_t pmd, pgprot_t newprot) +{ + pte_t pte = __pte(pmd_val(pmd)); + + pte = pte_modify(pte, newprot); + + return __pmd(pte_val(pte)); +} +#endif + static inline pte_t pgoff_to_pte(unsigned long off) { off <<= PAGE_SHIFT; @@ -357,7 +349,7 @@ static inline pgprot_t pgprot_noncached(pgprot_t prot) */ #define pgprot_noncached pgprot_noncached -#ifdef CONFIG_HUGETLB_PAGE +#if defined(CONFIG_HUGETLB_PAGE) || defined(CONFIG_TRANSPARENT_HUGEPAGE) static inline pte_t pte_mkhuge(pte_t pte) { unsigned long mask; @@ -375,6 +367,17 @@ static inline pte_t pte_mkhuge(pte_t pte) return __pte(pte_val(pte) | mask); } +#ifdef CONFIG_TRANSPARENT_HUGEPAGE +static inline pmd_t pmd_mkhuge(pmd_t pmd) +{ + pte_t pte = __pte(pmd_val(pmd)); + + pte = pte_mkhuge(pte); + pte_val(pte) |= _PAGE_PMD_HUGE; + + return __pmd(pte_val(pte)); +} +#endif #endif static inline pte_t pte_mkdirty(pte_t pte) @@ -626,91 +629,130 @@ static inline unsigned long pte_special(pte_t pte) return pte_val(pte) & _PAGE_SPECIAL; } -static inline int pmd_large(pmd_t pmd) +static inline unsigned long pmd_large(pmd_t pmd) { - return (pmd_val(pmd) & (PMD_ISHUGE | PMD_HUGE_PRESENT)) == - (PMD_ISHUGE | PMD_HUGE_PRESENT); + pte_t pte = __pte(pmd_val(pmd)); + + return (pte_val(pte) & _PAGE_PMD_HUGE) && pte_present(pte); } #ifdef CONFIG_TRANSPARENT_HUGEPAGE -static inline int pmd_young(pmd_t pmd) +static inline unsigned long pmd_young(pmd_t pmd) { - return pmd_val(pmd) & PMD_HUGE_ACCESSED; + pte_t pte = __pte(pmd_val(pmd)); + + return pte_young(pte); } -static inline int pmd_write(pmd_t pmd) +static inline unsigned long pmd_write(pmd_t pmd) { - return pmd_val(pmd) & PMD_HUGE_WRITE; + pte_t pte = __pte(pmd_val(pmd)); + + return pte_write(pte); } static inline unsigned long pmd_pfn(pmd_t pmd) { - unsigned long val = pmd_val(pmd) & PMD_HUGE_PADDR; + pte_t pte = __pte(pmd_val(pmd)); - return val >> (PAGE_SHIFT - PMD_PADDR_SHIFT); + return pte_pfn(pte); } -static inline int pmd_trans_splitting(pmd_t pmd) +static inline unsigned long pmd_trans_huge(pmd_t pmd) { - return (pmd_val(pmd) & (PMD_ISHUGE|PMD_HUGE_SPLITTING)) == - (PMD_ISHUGE|PMD_HUGE_SPLITTING); + pte_t pte = __pte(pmd_val(pmd)); + + return pte_val(pte) & _PAGE_PMD_HUGE; } -static inline int pmd_trans_huge(pmd_t pmd) +static inline unsigned long pmd_trans_splitting(pmd_t pmd) { - return pmd_val(pmd) & PMD_ISHUGE; + pte_t pte = __pte(pmd_val(pmd)); + + return pmd_trans_huge(pmd) && pte_special(pte); } #define has_transparent_hugepage() 1 static inline pmd_t pmd_mkold(pmd_t pmd) { - pmd_val(pmd) &= ~PMD_HUGE_ACCESSED; - return pmd; + pte_t pte = __pte(pmd_val(pmd)); + + pte = pte_mkold(pte); + + return __pmd(pte_val(pte)); } static inline pmd_t pmd_wrprotect(pmd_t pmd) { - pmd_val(pmd) &= ~PMD_HUGE_WRITE; - return pmd; + pte_t pte = __pte(pmd_val(pmd)); + + pte = pte_wrprotect(pte); + + return __pmd(pte_val(pte)); } static inline pmd_t pmd_mkdirty(pmd_t pmd) { - pmd_val(pmd) |= PMD_HUGE_DIRTY; - return pmd; + pte_t pte = __pte(pmd_val(pmd)); + + pte = pte_mkdirty(pte); + + return __pmd(pte_val(pte)); } static inline pmd_t pmd_mkyoung(pmd_t pmd) { - pmd_val(pmd) |= PMD_HUGE_ACCESSED; - return pmd; + pte_t pte = __pte(pmd_val(pmd)); + + pte = pte_mkyoung(pte); + + return __pmd(pte_val(pte)); } static inline pmd_t pmd_mkwrite(pmd_t pmd) { - pmd_val(pmd) |= PMD_HUGE_WRITE; - return pmd; + pte_t pte = __pte(pmd_val(pmd)); + + pte = pte_mkwrite(pte); + + return __pmd(pte_val(pte)); } static inline pmd_t pmd_mknotpresent(pmd_t pmd) { - pmd_val(pmd) &= ~PMD_HUGE_PRESENT; + unsigned long mask; + + if (tlb_type == hypervisor) + mask = _PAGE_PRESENT_4V; + else + mask = _PAGE_PRESENT_4U; + + pmd_val(pmd) &= ~mask; + return pmd; } static inline pmd_t pmd_mksplitting(pmd_t pmd) { - pmd_val(pmd) |= PMD_HUGE_SPLITTING; - return pmd; + pte_t pte = __pte(pmd_val(pmd)); + + pte = pte_mkspecial(pte); + + return __pmd(pte_val(pte)); } -extern pgprot_t pmd_pgprot(pmd_t entry); +static inline pgprot_t pmd_pgprot(pmd_t entry) +{ + unsigned long val = pmd_val(entry); + + return __pgprot(val); +} #endif static inline int pmd_present(pmd_t pmd) { - return pmd_val(pmd) != 0U; + return pmd_val(pmd) != 0UL; } #define pmd_none(pmd) (!pmd_val(pmd)) @@ -728,33 +770,32 @@ static inline void set_pmd_at(struct mm_struct *mm, unsigned long addr, static inline void pmd_set(struct mm_struct *mm, pmd_t *pmdp, pte_t *ptep) { - unsigned long val = __pa((unsigned long) (ptep)) >> PMD_PADDR_SHIFT; + unsigned long val = __pa((unsigned long) (ptep)); pmd_val(*pmdp) = val; } #define pud_set(pudp, pmdp) \ - (pud_val(*(pudp)) = (__pa((unsigned long) (pmdp)) >> PGD_PADDR_SHIFT)) + (pud_val(*(pudp)) = (__pa((unsigned long) (pmdp)))) static inline unsigned long __pmd_page(pmd_t pmd) { - unsigned long paddr = (unsigned long) pmd_val(pmd); -#ifdef CONFIG_TRANSPARENT_HUGEPAGE - if (pmd_val(pmd) & PMD_ISHUGE) - paddr &= PMD_HUGE_PADDR; -#endif - paddr <<= PMD_PADDR_SHIFT; - return ((unsigned long) __va(paddr)); + pte_t pte = __pte(pmd_val(pmd)); + unsigned long pfn; + + pfn = pte_pfn(pte); + + return ((unsigned long) __va(pfn << PAGE_SHIFT)); } #define pmd_page(pmd) virt_to_page((void *)__pmd_page(pmd)) #define pud_page_vaddr(pud) \ - ((unsigned long) __va((((unsigned long)pud_val(pud))<<PGD_PADDR_SHIFT))) + ((unsigned long) __va(pud_val(pud))) #define pud_page(pud) virt_to_page((void *)pud_page_vaddr(pud)) #define pmd_bad(pmd) (0) -#define pmd_clear(pmdp) (pmd_val(*(pmdp)) = 0U) +#define pmd_clear(pmdp) (pmd_val(*(pmdp)) = 0UL) #define pud_none(pud) (!pud_val(pud)) #define pud_bad(pud) (0) #define pud_present(pud) (pud_val(pud) != 0U) -#define pud_clear(pudp) (pud_val(*(pudp)) = 0U) +#define pud_clear(pudp) (pud_val(*(pudp)) = 0UL) /* Same in both SUN4V and SUN4U. */ #define pte_none(pte) (!pte_val(pte)) @@ -789,7 +830,7 @@ static inline pmd_t pmdp_get_and_clear(struct mm_struct *mm, pmd_t *pmdp) { pmd_t pmd = *pmdp; - set_pmd_at(mm, addr, pmdp, __pmd(0U)); + set_pmd_at(mm, addr, pmdp, __pmd(0UL)); return pmd; } @@ -837,8 +878,8 @@ static inline void __set_pte_at(struct mm_struct *mm, unsigned long addr, }) #endif -extern pgd_t swapper_pg_dir[2048]; -extern pmd_t swapper_low_pmd_dir[2048]; +extern pgd_t swapper_pg_dir[PTRS_PER_PGD]; +extern pmd_t swapper_low_pmd_dir[PTRS_PER_PMD]; extern void paging_init(void); extern unsigned long find_ecache_flush_span(unsigned long size); diff --git a/arch/sparc/include/asm/sparsemem.h b/arch/sparc/include/asm/sparsemem.h index b99d4e4b6d28..e5e1752d5d78 100644 --- a/arch/sparc/include/asm/sparsemem.h +++ b/arch/sparc/include/asm/sparsemem.h @@ -3,9 +3,11 @@ #ifdef __KERNEL__ +#include <asm/page.h> + #define SECTION_SIZE_BITS 30 -#define MAX_PHYSADDR_BITS 42 -#define MAX_PHYSMEM_BITS 42 +#define MAX_PHYSADDR_BITS MAX_PHYS_ADDRESS_BITS +#define MAX_PHYSMEM_BITS MAX_PHYS_ADDRESS_BITS #endif /* !(__KERNEL__) */ diff --git a/arch/sparc/include/asm/thread_info_32.h b/arch/sparc/include/asm/thread_info_32.h index dd3807599bb9..96efa7adc223 100644 --- a/arch/sparc/include/asm/thread_info_32.h +++ b/arch/sparc/include/asm/thread_info_32.h @@ -105,8 +105,6 @@ register struct thread_info *current_thread_info_reg asm("g6"); #define TI_W_SAVED 0x250 /* #define TI_RESTART_BLOCK 0x25n */ /* Nobody cares */ -#define PREEMPT_ACTIVE 0x4000000 - /* * thread information flag bit numbers */ diff --git a/arch/sparc/include/asm/thread_info_64.h b/arch/sparc/include/asm/thread_info_64.h index d5e504251079..a5f01ac6d0f1 100644 --- a/arch/sparc/include/asm/thread_info_64.h +++ b/arch/sparc/include/asm/thread_info_64.h @@ -111,8 +111,6 @@ struct thread_info { #define THREAD_SHIFT PAGE_SHIFT #endif /* PAGE_SHIFT == 13 */ -#define PREEMPT_ACTIVE 0x10000000 - /* * macros/functions for gaining access to the thread information structure */ @@ -192,7 +190,7 @@ register struct thread_info *current_thread_info_reg asm("g6"); #define TIF_UNALIGNED 5 /* allowed to do unaligned accesses */ /* flag bit 6 is available */ #define TIF_32BIT 7 /* 32-bit binary */ -/* flag bit 8 is available */ +#define TIF_NOHZ 8 /* in adaptive nohz mode */ #define TIF_SECCOMP 9 /* secure computing */ #define TIF_SYSCALL_AUDIT 10 /* syscall auditing active */ #define TIF_SYSCALL_TRACEPOINT 11 /* syscall tracepoint instrumentation */ @@ -210,6 +208,7 @@ register struct thread_info *current_thread_info_reg asm("g6"); #define _TIF_NEED_RESCHED (1<<TIF_NEED_RESCHED) #define _TIF_UNALIGNED (1<<TIF_UNALIGNED) #define _TIF_32BIT (1<<TIF_32BIT) +#define _TIF_NOHZ (1<<TIF_NOHZ) #define _TIF_SECCOMP (1<<TIF_SECCOMP) #define _TIF_SYSCALL_AUDIT (1<<TIF_SYSCALL_AUDIT) #define _TIF_SYSCALL_TRACEPOINT (1<<TIF_SYSCALL_TRACEPOINT) diff --git a/arch/sparc/include/asm/tlbflush_64.h b/arch/sparc/include/asm/tlbflush_64.h index f0d6a9700f4c..3c3c89f52643 100644 --- a/arch/sparc/include/asm/tlbflush_64.h +++ b/arch/sparc/include/asm/tlbflush_64.h @@ -1,7 +1,6 @@ #ifndef _SPARC64_TLBFLUSH_H #define _SPARC64_TLBFLUSH_H -#include <linux/mm.h> #include <asm/mmu_context.h> /* TSB flush operations. */ diff --git a/arch/sparc/include/asm/tsb.h b/arch/sparc/include/asm/tsb.h index e696432b950d..2230f80d9fe3 100644 --- a/arch/sparc/include/asm/tsb.h +++ b/arch/sparc/include/asm/tsb.h @@ -142,98 +142,39 @@ extern struct tsb_phys_patch_entry __tsb_phys_patch, __tsb_phys_patch_end; or REG1, %lo(swapper_pg_dir), REG1; \ sllx VADDR, 64 - (PGDIR_SHIFT + PGDIR_BITS), REG2; \ srlx REG2, 64 - PAGE_SHIFT, REG2; \ - andn REG2, 0x3, REG2; \ - lduw [REG1 + REG2], REG1; \ + andn REG2, 0x7, REG2; \ + ldx [REG1 + REG2], REG1; \ brz,pn REG1, FAIL_LABEL; \ sllx VADDR, 64 - (PMD_SHIFT + PMD_BITS), REG2; \ srlx REG2, 64 - PAGE_SHIFT, REG2; \ - sllx REG1, PGD_PADDR_SHIFT, REG1; \ - andn REG2, 0x3, REG2; \ - lduwa [REG1 + REG2] ASI_PHYS_USE_EC, REG1; \ + andn REG2, 0x7, REG2; \ + ldxa [REG1 + REG2] ASI_PHYS_USE_EC, REG1; \ brz,pn REG1, FAIL_LABEL; \ sllx VADDR, 64 - PMD_SHIFT, REG2; \ - srlx REG2, 64 - (PAGE_SHIFT - 1), REG2; \ - sllx REG1, PMD_PADDR_SHIFT, REG1; \ + srlx REG2, 64 - PAGE_SHIFT, REG2; \ andn REG2, 0x7, REG2; \ add REG1, REG2, REG1; - /* These macros exists only to make the PMD translator below - * easier to read. It hides the ELF section switch for the - * sun4v code patching. - */ -#define OR_PTE_BIT_1INSN(REG, NAME) \ -661: or REG, _PAGE_##NAME##_4U, REG; \ - .section .sun4v_1insn_patch, "ax"; \ - .word 661b; \ - or REG, _PAGE_##NAME##_4V, REG; \ - .previous; - -#define OR_PTE_BIT_2INSN(REG, TMP, NAME) \ -661: sethi %hi(_PAGE_##NAME##_4U), TMP; \ - or REG, TMP, REG; \ - .section .sun4v_2insn_patch, "ax"; \ - .word 661b; \ - mov -1, TMP; \ - or REG, _PAGE_##NAME##_4V, REG; \ - .previous; - - /* Load into REG the PTE value for VALID, CACHE, and SZHUGE. */ -#define BUILD_PTE_VALID_SZHUGE_CACHE(REG) \ -661: sethi %uhi(_PAGE_VALID|_PAGE_SZHUGE_4U), REG; \ - .section .sun4v_1insn_patch, "ax"; \ - .word 661b; \ - sethi %uhi(_PAGE_VALID), REG; \ - .previous; \ - sllx REG, 32, REG; \ -661: or REG, _PAGE_CP_4U|_PAGE_CV_4U, REG; \ - .section .sun4v_1insn_patch, "ax"; \ - .word 661b; \ - or REG, _PAGE_CP_4V|_PAGE_CV_4V|_PAGE_SZHUGE_4V, REG; \ - .previous; - /* PMD has been loaded into REG1, interpret the value, seeing * if it is a HUGE PMD or a normal one. If it is not valid * then jump to FAIL_LABEL. If it is a HUGE PMD, and it * translates to a valid PTE, branch to PTE_LABEL. * - * We translate the PMD by hand, one bit at a time, - * constructing the huge PTE. - * - * So we construct the PTE in REG2 as follows: - * - * 1) Extract the PMD PFN from REG1 and place it into REG2. - * - * 2) Translate PMD protection bits in REG1 into REG2, one bit - * at a time using andcc tests on REG1 and OR's into REG2. - * - * Only two bits to be concerned with here, EXEC and WRITE. - * Now REG1 is freed up and we can use it as a temporary. - * - * 3) Construct the VALID, CACHE, and page size PTE bits in - * REG1, OR with REG2 to form final PTE. + * We have to propagate the 4MB bit of the virtual address + * because we are fabricating 8MB pages using 4MB hw pages. */ #ifdef CONFIG_TRANSPARENT_HUGEPAGE #define USER_PGTABLE_CHECK_PMD_HUGE(VADDR, REG1, REG2, FAIL_LABEL, PTE_LABEL) \ - brz,pn REG1, FAIL_LABEL; \ - andcc REG1, PMD_ISHUGE, %g0; \ - be,pt %xcc, 700f; \ - and REG1, PMD_HUGE_PRESENT|PMD_HUGE_ACCESSED, REG2; \ - cmp REG2, PMD_HUGE_PRESENT|PMD_HUGE_ACCESSED; \ - bne,pn %xcc, FAIL_LABEL; \ - andn REG1, PMD_HUGE_PROTBITS, REG2; \ - sllx REG2, PMD_PADDR_SHIFT, REG2; \ - /* REG2 now holds PFN << PAGE_SHIFT */ \ - andcc REG1, PMD_HUGE_WRITE, %g0; \ - bne,a,pt %xcc, 1f; \ - OR_PTE_BIT_1INSN(REG2, W); \ -1: andcc REG1, PMD_HUGE_EXEC, %g0; \ - be,pt %xcc, 1f; \ - nop; \ - OR_PTE_BIT_2INSN(REG2, REG1, EXEC); \ - /* REG1 can now be clobbered, build final PTE */ \ -1: BUILD_PTE_VALID_SZHUGE_CACHE(REG1); \ - ba,pt %xcc, PTE_LABEL; \ - or REG1, REG2, REG1; \ + brz,pn REG1, FAIL_LABEL; \ + sethi %uhi(_PAGE_PMD_HUGE), REG2; \ + sllx REG2, 32, REG2; \ + andcc REG1, REG2, %g0; \ + be,pt %xcc, 700f; \ + sethi %hi(4 * 1024 * 1024), REG2; \ + andn REG1, REG2, REG1; \ + and VADDR, REG2, REG2; \ + brlz,pt REG1, PTE_LABEL; \ + or REG1, REG2, REG1; \ 700: #else #define USER_PGTABLE_CHECK_PMD_HUGE(VADDR, REG1, REG2, FAIL_LABEL, PTE_LABEL) \ @@ -253,18 +194,16 @@ extern struct tsb_phys_patch_entry __tsb_phys_patch, __tsb_phys_patch_end; #define USER_PGTABLE_WALK_TL1(VADDR, PHYS_PGD, REG1, REG2, FAIL_LABEL) \ sllx VADDR, 64 - (PGDIR_SHIFT + PGDIR_BITS), REG2; \ srlx REG2, 64 - PAGE_SHIFT, REG2; \ - andn REG2, 0x3, REG2; \ - lduwa [PHYS_PGD + REG2] ASI_PHYS_USE_EC, REG1; \ + andn REG2, 0x7, REG2; \ + ldxa [PHYS_PGD + REG2] ASI_PHYS_USE_EC, REG1; \ brz,pn REG1, FAIL_LABEL; \ sllx VADDR, 64 - (PMD_SHIFT + PMD_BITS), REG2; \ srlx REG2, 64 - PAGE_SHIFT, REG2; \ - sllx REG1, PGD_PADDR_SHIFT, REG1; \ - andn REG2, 0x3, REG2; \ - lduwa [REG1 + REG2] ASI_PHYS_USE_EC, REG1; \ + andn REG2, 0x7, REG2; \ + ldxa [REG1 + REG2] ASI_PHYS_USE_EC, REG1; \ USER_PGTABLE_CHECK_PMD_HUGE(VADDR, REG1, REG2, FAIL_LABEL, 800f) \ sllx VADDR, 64 - PMD_SHIFT, REG2; \ - srlx REG2, 64 - (PAGE_SHIFT - 1), REG2; \ - sllx REG1, PMD_PADDR_SHIFT, REG1; \ + srlx REG2, 64 - PAGE_SHIFT, REG2; \ andn REG2, 0x7, REG2; \ add REG1, REG2, REG1; \ ldxa [REG1] ASI_PHYS_USE_EC, REG1; \ diff --git a/arch/sparc/kernel/entry.h b/arch/sparc/kernel/entry.h index 9c179fbfb219..140966fbd303 100644 --- a/arch/sparc/kernel/entry.h +++ b/arch/sparc/kernel/entry.h @@ -88,7 +88,6 @@ extern asmlinkage void syscall_trace_leave(struct pt_regs *regs); extern void bad_trap_tl1(struct pt_regs *regs, long lvl); -extern void do_fpe_common(struct pt_regs *regs); extern void do_fpieee(struct pt_regs *regs); extern void do_fpother(struct pt_regs *regs); extern void do_tof(struct pt_regs *regs); diff --git a/arch/sparc/kernel/kgdb_64.c b/arch/sparc/kernel/kgdb_64.c index 53c0a82e6030..60b19f50c80a 100644 --- a/arch/sparc/kernel/kgdb_64.c +++ b/arch/sparc/kernel/kgdb_64.c @@ -159,11 +159,12 @@ int kgdb_arch_handle_exception(int e_vector, int signo, int err_code, asmlinkage void kgdb_trap(unsigned long trap_level, struct pt_regs *regs) { + enum ctx_state prev_state = exception_enter(); unsigned long flags; if (user_mode(regs)) { bad_trap(regs, trap_level); - return; + goto out; } flushw_all(); @@ -171,6 +172,8 @@ asmlinkage void kgdb_trap(unsigned long trap_level, struct pt_regs *regs) local_irq_save(flags); kgdb_handle_exception(0x172, SIGTRAP, 0, regs); local_irq_restore(flags); +out: + exception_exit(prev_state); } int kgdb_arch_init(void) diff --git a/arch/sparc/kernel/kprobes.c b/arch/sparc/kernel/kprobes.c index e72212148d2a..1b0973503197 100644 --- a/arch/sparc/kernel/kprobes.c +++ b/arch/sparc/kernel/kprobes.c @@ -8,6 +8,7 @@ #include <linux/module.h> #include <linux/kdebug.h> #include <linux/slab.h> +#include <linux/context_tracking.h> #include <asm/signal.h> #include <asm/cacheflush.h> #include <asm/uaccess.h> @@ -349,7 +350,7 @@ int __kprobes kprobe_fault_handler(struct pt_regs *regs, int trapnr) case KPROBE_HIT_SSDONE: /* * We increment the nmissed count for accounting, - * we can also use npre/npostfault count for accouting + * we can also use npre/npostfault count for accounting * these specific fault cases. */ kprobes_inc_nmissed_count(cur); @@ -418,12 +419,14 @@ int __kprobes kprobe_exceptions_notify(struct notifier_block *self, asmlinkage void __kprobes kprobe_trap(unsigned long trap_level, struct pt_regs *regs) { + enum ctx_state prev_state = exception_enter(); + BUG_ON(trap_level != 0x170 && trap_level != 0x171); if (user_mode(regs)) { local_irq_enable(); bad_trap(regs, trap_level); - return; + goto out; } /* trap_level == 0x170 --> ta 0x70 @@ -433,6 +436,8 @@ asmlinkage void __kprobes kprobe_trap(unsigned long trap_level, (trap_level == 0x170) ? "debug" : "debug_2", regs, 0, trap_level, SIGTRAP) != NOTIFY_STOP) bad_trap(regs, trap_level); +out: + exception_exit(prev_state); } /* Jprobes support. */ diff --git a/arch/sparc/kernel/ktlb.S b/arch/sparc/kernel/ktlb.S index fde5a419cf27..542e96ac4d39 100644 --- a/arch/sparc/kernel/ktlb.S +++ b/arch/sparc/kernel/ktlb.S @@ -153,12 +153,19 @@ kvmap_dtlb_tsb4m_miss: /* Clear the PAGE_OFFSET top virtual bits, shift * down to get PFN, and make sure PFN is in range. */ - sllx %g4, 21, %g5 +661: sllx %g4, 0, %g5 + .section .page_offset_shift_patch, "ax" + .word 661b + .previous /* Check to see if we know about valid memory at the 4MB * chunk this physical address will reside within. */ - srlx %g5, 21 + 41, %g2 +661: srlx %g5, MAX_PHYS_ADDRESS_BITS, %g2 + .section .page_offset_shift_patch, "ax" + .word 661b + .previous + brnz,pn %g2, kvmap_dtlb_longpath nop @@ -176,7 +183,11 @@ valid_addr_bitmap_patch: or %g7, %lo(sparc64_valid_addr_bitmap), %g7 .previous - srlx %g5, 21 + 22, %g2 +661: srlx %g5, ILOG2_4MB, %g2 + .section .page_offset_shift_patch, "ax" + .word 661b + .previous + srlx %g2, 6, %g5 and %g2, 63, %g2 sllx %g5, 3, %g5 @@ -189,9 +200,18 @@ valid_addr_bitmap_patch: 2: sethi %hi(kpte_linear_bitmap), %g2 /* Get the 256MB physical address index. */ - sllx %g4, 21, %g5 +661: sllx %g4, 0, %g5 + .section .page_offset_shift_patch, "ax" + .word 661b + .previous + or %g2, %lo(kpte_linear_bitmap), %g2 - srlx %g5, 21 + 28, %g5 + +661: srlx %g5, ILOG2_256MB, %g5 + .section .page_offset_shift_patch, "ax" + .word 661b + .previous + and %g5, (32 - 1), %g7 /* Divide by 32 to get the offset into the bitmask. */ diff --git a/arch/sparc/kernel/pci.c b/arch/sparc/kernel/pci.c index bc4d3f5d2e5d..cb021453de2a 100644 --- a/arch/sparc/kernel/pci.c +++ b/arch/sparc/kernel/pci.c @@ -398,8 +398,8 @@ static void apb_fake_ranges(struct pci_dev *dev, apb_calc_first_last(map, &first, &last); res = bus->resource[1]; res->flags = IORESOURCE_MEM; - region.start = (first << 21); - region.end = (last << 21) + ((1 << 21) - 1); + region.start = (first << 29); + region.end = (last << 29) + ((1 << 29) - 1); pcibios_bus_to_resource(dev, res, ®ion); } diff --git a/arch/sparc/kernel/process_64.c b/arch/sparc/kernel/process_64.c index baebab215492..32a280ec38c1 100644 --- a/arch/sparc/kernel/process_64.c +++ b/arch/sparc/kernel/process_64.c @@ -31,6 +31,7 @@ #include <linux/elfcore.h> #include <linux/sysrq.h> #include <linux/nmi.h> +#include <linux/context_tracking.h> #include <asm/uaccess.h> #include <asm/page.h> @@ -557,6 +558,7 @@ void fault_in_user_windows(void) barf: set_thread_wsaved(window + 1); + user_exit(); do_exit(SIGILL); } diff --git a/arch/sparc/kernel/ptrace_64.c b/arch/sparc/kernel/ptrace_64.c index 773c1f2983ce..c13c9f25d83a 100644 --- a/arch/sparc/kernel/ptrace_64.c +++ b/arch/sparc/kernel/ptrace_64.c @@ -27,6 +27,7 @@ #include <trace/syscall.h> #include <linux/compat.h> #include <linux/elf.h> +#include <linux/context_tracking.h> #include <asm/asi.h> #include <asm/pgtable.h> @@ -1066,6 +1067,9 @@ asmlinkage int syscall_trace_enter(struct pt_regs *regs) /* do the secure computing check first */ secure_computing_strict(regs->u_regs[UREG_G1]); + if (test_thread_flag(TIF_NOHZ)) + user_exit(); + if (test_thread_flag(TIF_SYSCALL_TRACE)) ret = tracehook_report_syscall_entry(regs); @@ -1086,6 +1090,9 @@ asmlinkage int syscall_trace_enter(struct pt_regs *regs) asmlinkage void syscall_trace_leave(struct pt_regs *regs) { + if (test_thread_flag(TIF_NOHZ)) + user_exit(); + audit_syscall_exit(regs); if (unlikely(test_thread_flag(TIF_SYSCALL_TRACEPOINT))) @@ -1093,4 +1100,7 @@ asmlinkage void syscall_trace_leave(struct pt_regs *regs) if (test_thread_flag(TIF_SYSCALL_TRACE)) tracehook_report_syscall_exit(regs, 0); + + if (test_thread_flag(TIF_NOHZ)) + user_enter(); } diff --git a/arch/sparc/kernel/rtrap_64.S b/arch/sparc/kernel/rtrap_64.S index afa2a9e3d0a0..39f0c662f4c8 100644 --- a/arch/sparc/kernel/rtrap_64.S +++ b/arch/sparc/kernel/rtrap_64.S @@ -18,10 +18,16 @@ #define RTRAP_PSTATE_IRQOFF (PSTATE_TSO|PSTATE_PEF|PSTATE_PRIV) #define RTRAP_PSTATE_AG_IRQOFF (PSTATE_TSO|PSTATE_PEF|PSTATE_PRIV|PSTATE_AG) +#ifdef CONFIG_CONTEXT_TRACKING +# define SCHEDULE_USER schedule_user +#else +# define SCHEDULE_USER schedule +#endif + .text .align 32 __handle_preemption: - call schedule + call SCHEDULE_USER wrpr %g0, RTRAP_PSTATE, %pstate ba,pt %xcc, __handle_preemption_continue wrpr %g0, RTRAP_PSTATE_IRQOFF, %pstate @@ -306,12 +312,10 @@ to_kernel: nop cmp %l4, 0 bne,pn %xcc, kern_fpucheck - sethi %hi(PREEMPT_ACTIVE), %l6 - stw %l6, [%g6 + TI_PRE_COUNT] - call schedule + nop + call preempt_schedule_irq nop ba,pt %xcc, rtrap - stw %g0, [%g6 + TI_PRE_COUNT] #endif kern_fpucheck: ldub [%g6 + TI_FPDEPTH], %l5 brz,pt %l5, rt_continue diff --git a/arch/sparc/kernel/signal_64.c b/arch/sparc/kernel/signal_64.c index 35923e8abd82..cd91d010e6d3 100644 --- a/arch/sparc/kernel/signal_64.c +++ b/arch/sparc/kernel/signal_64.c @@ -23,6 +23,7 @@ #include <linux/tty.h> #include <linux/binfmts.h> #include <linux/bitops.h> +#include <linux/context_tracking.h> #include <asm/uaccess.h> #include <asm/ptrace.h> @@ -43,6 +44,7 @@ asmlinkage void sparc64_set_context(struct pt_regs *regs) { struct ucontext __user *ucp = (struct ucontext __user *) regs->u_regs[UREG_I0]; + enum ctx_state prev_state = exception_enter(); mc_gregset_t __user *grp; unsigned long pc, npc, tstate; unsigned long fp, i7; @@ -129,16 +131,19 @@ asmlinkage void sparc64_set_context(struct pt_regs *regs) } if (err) goto do_sigsegv; - +out: + exception_exit(prev_state); return; do_sigsegv: force_sig(SIGSEGV, current); + goto out; } asmlinkage void sparc64_get_context(struct pt_regs *regs) { struct ucontext __user *ucp = (struct ucontext __user *) regs->u_regs[UREG_I0]; + enum ctx_state prev_state = exception_enter(); mc_gregset_t __user *grp; mcontext_t __user *mcp; unsigned long fp, i7; @@ -220,10 +225,12 @@ asmlinkage void sparc64_get_context(struct pt_regs *regs) } if (err) goto do_sigsegv; - +out: + exception_exit(prev_state); return; do_sigsegv: force_sig(SIGSEGV, current); + goto out; } struct rt_signal_frame { @@ -528,11 +535,13 @@ static void do_signal(struct pt_regs *regs, unsigned long orig_i0) void do_notify_resume(struct pt_regs *regs, unsigned long orig_i0, unsigned long thread_info_flags) { + user_exit(); if (thread_info_flags & _TIF_SIGPENDING) do_signal(regs, orig_i0); if (thread_info_flags & _TIF_NOTIFY_RESUME) { clear_thread_flag(TIF_NOTIFY_RESUME); tracehook_notify_resume(regs); } + user_enter(); } diff --git a/arch/sparc/kernel/smp_64.c b/arch/sparc/kernel/smp_64.c index e142545244f2..b66a5338231e 100644 --- a/arch/sparc/kernel/smp_64.c +++ b/arch/sparc/kernel/smp_64.c @@ -1399,8 +1399,13 @@ void __init smp_cpus_done(unsigned int max_cpus) void smp_send_reschedule(int cpu) { - xcall_deliver((u64) &xcall_receive_signal, 0, 0, - cpumask_of(cpu)); + if (cpu == smp_processor_id()) { + WARN_ON_ONCE(preemptible()); + set_softint(1 << PIL_SMP_RECEIVE_SIGNAL); + } else { + xcall_deliver((u64) &xcall_receive_signal, + 0, 0, cpumask_of(cpu)); + } } void __irq_entry smp_receive_signal_client(int irq, struct pt_regs *regs) diff --git a/arch/sparc/kernel/sun4v_tlb_miss.S b/arch/sparc/kernel/sun4v_tlb_miss.S index bde867fd71e8..e0c09bf85610 100644 --- a/arch/sparc/kernel/sun4v_tlb_miss.S +++ b/arch/sparc/kernel/sun4v_tlb_miss.S @@ -182,7 +182,7 @@ sun4v_tsb_miss_common: cmp %g5, -1 be,pt %xcc, 80f nop - COMPUTE_TSB_PTR(%g5, %g4, HPAGE_SHIFT, %g2, %g7) + COMPUTE_TSB_PTR(%g5, %g4, REAL_HPAGE_SHIFT, %g2, %g7) /* That clobbered %g2, reload it. */ ldxa [%g0] ASI_SCRATCHPAD, %g2 diff --git a/arch/sparc/kernel/sys_sparc_64.c b/arch/sparc/kernel/sys_sparc_64.c index 51561b8b15ba..beb0b5a5f21f 100644 --- a/arch/sparc/kernel/sys_sparc_64.c +++ b/arch/sparc/kernel/sys_sparc_64.c @@ -24,6 +24,7 @@ #include <linux/personality.h> #include <linux/random.h> #include <linux/export.h> +#include <linux/context_tracking.h> #include <asm/uaccess.h> #include <asm/utrap.h> @@ -39,9 +40,6 @@ asmlinkage unsigned long sys_getpagesize(void) return PAGE_SIZE; } -#define VA_EXCLUDE_START (0x0000080000000000UL - (1UL << 32UL)) -#define VA_EXCLUDE_END (0xfffff80000000000UL + (1UL << 32UL)) - /* Does addr --> addr+len fall within 4GB of the VA-space hole or * overflow past the end of the 64-bit address space? */ @@ -499,6 +497,7 @@ asmlinkage unsigned long c_sys_nis_syscall(struct pt_regs *regs) asmlinkage void sparc_breakpoint(struct pt_regs *regs) { + enum ctx_state prev_state = exception_enter(); siginfo_t info; if (test_thread_flag(TIF_32BIT)) { @@ -517,6 +516,7 @@ asmlinkage void sparc_breakpoint(struct pt_regs *regs) #ifdef DEBUG_SPARC_BREAKPOINT printk ("TRAP: Returning to space: PC=%lx nPC=%lx\n", regs->tpc, regs->tnpc); #endif + exception_exit(prev_state); } extern void check_pending(int signum); diff --git a/arch/sparc/kernel/syscalls.S b/arch/sparc/kernel/syscalls.S index d950197a17e1..87729fff13b9 100644 --- a/arch/sparc/kernel/syscalls.S +++ b/arch/sparc/kernel/syscalls.S @@ -52,7 +52,7 @@ sys32_rt_sigreturn: #endif .align 32 1: ldx [%g6 + TI_FLAGS], %l5 - andcc %l5, (_TIF_SYSCALL_TRACE|_TIF_SECCOMP|_TIF_SYSCALL_AUDIT|_TIF_SYSCALL_TRACEPOINT), %g0 + andcc %l5, (_TIF_SYSCALL_TRACE|_TIF_SECCOMP|_TIF_SYSCALL_AUDIT|_TIF_SYSCALL_TRACEPOINT|_TIF_NOHZ), %g0 be,pt %icc, rtrap nop call syscall_trace_leave @@ -184,7 +184,7 @@ linux_sparc_syscall32: srl %i3, 0, %o3 ! IEU0 srl %i2, 0, %o2 ! IEU0 Group - andcc %l0, (_TIF_SYSCALL_TRACE|_TIF_SECCOMP|_TIF_SYSCALL_AUDIT|_TIF_SYSCALL_TRACEPOINT), %g0 + andcc %l0, (_TIF_SYSCALL_TRACE|_TIF_SECCOMP|_TIF_SYSCALL_AUDIT|_TIF_SYSCALL_TRACEPOINT|_TIF_NOHZ), %g0 bne,pn %icc, linux_syscall_trace32 ! CTI mov %i0, %l5 ! IEU1 5: call %l7 ! CTI Group brk forced @@ -207,7 +207,7 @@ linux_sparc_syscall: mov %i3, %o3 ! IEU1 mov %i4, %o4 ! IEU0 Group - andcc %l0, (_TIF_SYSCALL_TRACE|_TIF_SECCOMP|_TIF_SYSCALL_AUDIT|_TIF_SYSCALL_TRACEPOINT), %g0 + andcc %l0, (_TIF_SYSCALL_TRACE|_TIF_SECCOMP|_TIF_SYSCALL_AUDIT|_TIF_SYSCALL_TRACEPOINT|_TIF_NOHZ), %g0 bne,pn %icc, linux_syscall_trace ! CTI Group mov %i0, %l5 ! IEU0 2: call %l7 ! CTI Group brk forced @@ -223,7 +223,7 @@ ret_sys_call: cmp %o0, -ERESTART_RESTARTBLOCK bgeu,pn %xcc, 1f - andcc %l0, (_TIF_SYSCALL_TRACE|_TIF_SECCOMP|_TIF_SYSCALL_AUDIT|_TIF_SYSCALL_TRACEPOINT), %g0 + andcc %l0, (_TIF_SYSCALL_TRACE|_TIF_SECCOMP|_TIF_SYSCALL_AUDIT|_TIF_SYSCALL_TRACEPOINT|_TIF_NOHZ), %g0 ldx [%sp + PTREGS_OFF + PT_V9_TNPC], %l1 ! pc = npc 2: diff --git a/arch/sparc/kernel/traps_64.c b/arch/sparc/kernel/traps_64.c index b3f833ab90eb..4ced92f05358 100644 --- a/arch/sparc/kernel/traps_64.c +++ b/arch/sparc/kernel/traps_64.c @@ -20,6 +20,7 @@ #include <linux/ftrace.h> #include <linux/reboot.h> #include <linux/gfp.h> +#include <linux/context_tracking.h> #include <asm/smp.h> #include <asm/delay.h> @@ -186,11 +187,12 @@ EXPORT_SYMBOL_GPL(unregister_dimm_printer); void spitfire_insn_access_exception(struct pt_regs *regs, unsigned long sfsr, unsigned long sfar) { + enum ctx_state prev_state = exception_enter(); siginfo_t info; if (notify_die(DIE_TRAP, "instruction access exception", regs, 0, 0x8, SIGTRAP) == NOTIFY_STOP) - return; + goto out; if (regs->tstate & TSTATE_PRIV) { printk("spitfire_insn_access_exception: SFSR[%016lx] " @@ -207,6 +209,8 @@ void spitfire_insn_access_exception(struct pt_regs *regs, unsigned long sfsr, un info.si_addr = (void __user *)regs->tpc; info.si_trapno = 0; force_sig_info(SIGSEGV, &info, current); +out: + exception_exit(prev_state); } void spitfire_insn_access_exception_tl1(struct pt_regs *regs, unsigned long sfsr, unsigned long sfar) @@ -260,11 +264,12 @@ void sun4v_insn_access_exception_tl1(struct pt_regs *regs, unsigned long addr, u void spitfire_data_access_exception(struct pt_regs *regs, unsigned long sfsr, unsigned long sfar) { + enum ctx_state prev_state = exception_enter(); siginfo_t info; if (notify_die(DIE_TRAP, "data access exception", regs, 0, 0x30, SIGTRAP) == NOTIFY_STOP) - return; + goto out; if (regs->tstate & TSTATE_PRIV) { /* Test if this comes from uaccess places. */ @@ -280,7 +285,7 @@ void spitfire_data_access_exception(struct pt_regs *regs, unsigned long sfsr, un #endif regs->tpc = entry->fixup; regs->tnpc = regs->tpc + 4; - return; + goto out; } /* Shit... */ printk("spitfire_data_access_exception: SFSR[%016lx] " @@ -294,6 +299,8 @@ void spitfire_data_access_exception(struct pt_regs *regs, unsigned long sfsr, un info.si_addr = (void __user *)sfar; info.si_trapno = 0; force_sig_info(SIGSEGV, &info, current); +out: + exception_exit(prev_state); } void spitfire_data_access_exception_tl1(struct pt_regs *regs, unsigned long sfsr, unsigned long sfar) @@ -1994,6 +2001,7 @@ static void sun4v_log_error(struct pt_regs *regs, struct sun4v_error_entry *ent, */ void sun4v_resum_error(struct pt_regs *regs, unsigned long offset) { + enum ctx_state prev_state = exception_enter(); struct sun4v_error_entry *ent, local_copy; struct trap_per_cpu *tb; unsigned long paddr; @@ -2022,12 +2030,14 @@ void sun4v_resum_error(struct pt_regs *regs, unsigned long offset) pr_info("Shutdown request, %u seconds...\n", local_copy.err_secs); orderly_poweroff(true); - return; + goto out; } sun4v_log_error(regs, &local_copy, cpu, KERN_ERR "RESUMABLE ERROR", &sun4v_resum_oflow_cnt); +out: + exception_exit(prev_state); } /* If we try to printk() we'll probably make matters worse, by trying @@ -2152,7 +2162,7 @@ void hypervisor_tlbop_error_xcall(unsigned long err, unsigned long op) err, op); } -void do_fpe_common(struct pt_regs *regs) +static void do_fpe_common(struct pt_regs *regs) { if (regs->tstate & TSTATE_PRIV) { regs->tpc = regs->tnpc; @@ -2188,23 +2198,28 @@ void do_fpe_common(struct pt_regs *regs) void do_fpieee(struct pt_regs *regs) { + enum ctx_state prev_state = exception_enter(); + if (notify_die(DIE_TRAP, "fpu exception ieee", regs, 0, 0x24, SIGFPE) == NOTIFY_STOP) - return; + goto out; do_fpe_common(regs); +out: + exception_exit(prev_state); } extern int do_mathemu(struct pt_regs *, struct fpustate *, bool); void do_fpother(struct pt_regs *regs) { + enum ctx_state prev_state = exception_enter(); struct fpustate *f = FPUSTATE; int ret = 0; if (notify_die(DIE_TRAP, "fpu exception other", regs, 0, 0x25, SIGFPE) == NOTIFY_STOP) - return; + goto out; switch ((current_thread_info()->xfsr[0] & 0x1c000)) { case (2 << 14): /* unfinished_FPop */ @@ -2213,17 +2228,20 @@ void do_fpother(struct pt_regs *regs) break; } if (ret) - return; + goto out; do_fpe_common(regs); +out: + exception_exit(prev_state); } void do_tof(struct pt_regs *regs) { + enum ctx_state prev_state = exception_enter(); siginfo_t info; if (notify_die(DIE_TRAP, "tagged arithmetic overflow", regs, 0, 0x26, SIGEMT) == NOTIFY_STOP) - return; + goto out; if (regs->tstate & TSTATE_PRIV) die_if_kernel("Penguin overflow trap from kernel mode", regs); @@ -2237,15 +2255,18 @@ void do_tof(struct pt_regs *regs) info.si_addr = (void __user *)regs->tpc; info.si_trapno = 0; force_sig_info(SIGEMT, &info, current); +out: + exception_exit(prev_state); } void do_div0(struct pt_regs *regs) { + enum ctx_state prev_state = exception_enter(); siginfo_t info; if (notify_die(DIE_TRAP, "integer division by zero", regs, 0, 0x28, SIGFPE) == NOTIFY_STOP) - return; + goto out; if (regs->tstate & TSTATE_PRIV) die_if_kernel("TL0: Kernel divide by zero.", regs); @@ -2259,6 +2280,8 @@ void do_div0(struct pt_regs *regs) info.si_addr = (void __user *)regs->tpc; info.si_trapno = 0; force_sig_info(SIGFPE, &info, current); +out: + exception_exit(prev_state); } static void instruction_dump(unsigned int *pc) @@ -2415,6 +2438,7 @@ extern int handle_ldf_stq(u32 insn, struct pt_regs *regs); void do_illegal_instruction(struct pt_regs *regs) { + enum ctx_state prev_state = exception_enter(); unsigned long pc = regs->tpc; unsigned long tstate = regs->tstate; u32 insn; @@ -2422,7 +2446,7 @@ void do_illegal_instruction(struct pt_regs *regs) if (notify_die(DIE_TRAP, "illegal instruction", regs, 0, 0x10, SIGILL) == NOTIFY_STOP) - return; + goto out; if (tstate & TSTATE_PRIV) die_if_kernel("Kernel illegal instruction", regs); @@ -2431,14 +2455,14 @@ void do_illegal_instruction(struct pt_regs *regs) if (get_user(insn, (u32 __user *) pc) != -EFAULT) { if ((insn & 0xc1ffc000) == 0x81700000) /* POPC */ { if (handle_popc(insn, regs)) - return; + goto out; } else if ((insn & 0xc1580000) == 0xc1100000) /* LDQ/STQ */ { if (handle_ldf_stq(insn, regs)) - return; + goto out; } else if (tlb_type == hypervisor) { if ((insn & VIS_OPCODE_MASK) == VIS_OPCODE_VAL) { if (!vis_emul(regs, insn)) - return; + goto out; } else { struct fpustate *f = FPUSTATE; @@ -2448,7 +2472,7 @@ void do_illegal_instruction(struct pt_regs *regs) * Trap in the %fsr to unimplemented_FPop. */ if (do_mathemu(regs, f, true)) - return; + goto out; } } } @@ -2458,21 +2482,24 @@ void do_illegal_instruction(struct pt_regs *regs) info.si_addr = (void __user *)pc; info.si_trapno = 0; force_sig_info(SIGILL, &info, current); +out: + exception_exit(prev_state); } extern void kernel_unaligned_trap(struct pt_regs *regs, unsigned int insn); void mem_address_unaligned(struct pt_regs *regs, unsigned long sfar, unsigned long sfsr) { + enum ctx_state prev_state = exception_enter(); siginfo_t info; if (notify_die(DIE_TRAP, "memory address unaligned", regs, 0, 0x34, SIGSEGV) == NOTIFY_STOP) - return; + goto out; if (regs->tstate & TSTATE_PRIV) { kernel_unaligned_trap(regs, *((unsigned int *)regs->tpc)); - return; + goto out; } info.si_signo = SIGBUS; info.si_errno = 0; @@ -2480,6 +2507,8 @@ void mem_address_unaligned(struct pt_regs *regs, unsigned long sfar, unsigned lo info.si_addr = (void __user *)sfar; info.si_trapno = 0; force_sig_info(SIGBUS, &info, current); +out: + exception_exit(prev_state); } void sun4v_do_mna(struct pt_regs *regs, unsigned long addr, unsigned long type_ctx) @@ -2504,11 +2533,12 @@ void sun4v_do_mna(struct pt_regs *regs, unsigned long addr, unsigned long type_c void do_privop(struct pt_regs *regs) { + enum ctx_state prev_state = exception_enter(); siginfo_t info; if (notify_die(DIE_TRAP, "privileged operation", regs, 0, 0x11, SIGILL) == NOTIFY_STOP) - return; + goto out; if (test_thread_flag(TIF_32BIT)) { regs->tpc &= 0xffffffff; @@ -2520,6 +2550,8 @@ void do_privop(struct pt_regs *regs) info.si_addr = (void __user *)regs->tpc; info.si_trapno = 0; force_sig_info(SIGILL, &info, current); +out: + exception_exit(prev_state); } void do_privact(struct pt_regs *regs) @@ -2530,99 +2562,116 @@ void do_privact(struct pt_regs *regs) /* Trap level 1 stuff or other traps we should never see... */ void do_cee(struct pt_regs *regs) { + exception_enter(); die_if_kernel("TL0: Cache Error Exception", regs); } void do_cee_tl1(struct pt_regs *regs) { + exception_enter(); dump_tl1_traplog((struct tl1_traplog *)(regs + 1)); die_if_kernel("TL1: Cache Error Exception", regs); } void do_dae_tl1(struct pt_regs *regs) { + exception_enter(); dump_tl1_traplog((struct tl1_traplog *)(regs + 1)); die_if_kernel("TL1: Data Access Exception", regs); } void do_iae_tl1(struct pt_regs *regs) { + exception_enter(); dump_tl1_traplog((struct tl1_traplog *)(regs + 1)); die_if_kernel("TL1: Instruction Access Exception", regs); } void do_div0_tl1(struct pt_regs *regs) { + exception_enter(); dump_tl1_traplog((struct tl1_traplog *)(regs + 1)); die_if_kernel("TL1: DIV0 Exception", regs); } void do_fpdis_tl1(struct pt_regs *regs) { + exception_enter(); dump_tl1_traplog((struct tl1_traplog *)(regs + 1)); die_if_kernel("TL1: FPU Disabled", regs); } void do_fpieee_tl1(struct pt_regs *regs) { + exception_enter(); dump_tl1_traplog((struct tl1_traplog *)(regs + 1)); die_if_kernel("TL1: FPU IEEE Exception", regs); } void do_fpother_tl1(struct pt_regs *regs) { + exception_enter(); dump_tl1_traplog((struct tl1_traplog *)(regs + 1)); die_if_kernel("TL1: FPU Other Exception", regs); } void do_ill_tl1(struct pt_regs *regs) { + exception_enter(); dump_tl1_traplog((struct tl1_traplog *)(regs + 1)); die_if_kernel("TL1: Illegal Instruction Exception", regs); } void do_irq_tl1(struct pt_regs *regs) { + exception_enter(); dump_tl1_traplog((struct tl1_traplog *)(regs + 1)); die_if_kernel("TL1: IRQ Exception", regs); } void do_lddfmna_tl1(struct pt_regs *regs) { + exception_enter(); dump_tl1_traplog((struct tl1_traplog *)(regs + 1)); die_if_kernel("TL1: LDDF Exception", regs); } void do_stdfmna_tl1(struct pt_regs *regs) { + exception_enter(); dump_tl1_traplog((struct tl1_traplog *)(regs + 1)); die_if_kernel("TL1: STDF Exception", regs); } void do_paw(struct pt_regs *regs) { + exception_enter(); die_if_kernel("TL0: Phys Watchpoint Exception", regs); } void do_paw_tl1(struct pt_regs *regs) { + exception_enter(); dump_tl1_traplog((struct tl1_traplog *)(regs + 1)); die_if_kernel("TL1: Phys Watchpoint Exception", regs); } void do_vaw(struct pt_regs *regs) { + exception_enter(); die_if_kernel("TL0: Virt Watchpoint Exception", regs); } void do_vaw_tl1(struct pt_regs *regs) { + exception_enter(); dump_tl1_traplog((struct tl1_traplog *)(regs + 1)); die_if_kernel("TL1: Virt Watchpoint Exception", regs); } void do_tof_tl1(struct pt_regs *regs) { + exception_enter(); dump_tl1_traplog((struct tl1_traplog *)(regs + 1)); die_if_kernel("TL1: Tag Overflow Exception", regs); } diff --git a/arch/sparc/kernel/tsb.S b/arch/sparc/kernel/tsb.S index a313e4a9399b..14158d40ba76 100644 --- a/arch/sparc/kernel/tsb.S +++ b/arch/sparc/kernel/tsb.S @@ -75,7 +75,7 @@ tsb_miss_page_table_walk: mov 512, %g7 andn %g5, 0x7, %g5 sllx %g7, %g6, %g7 - srlx %g4, HPAGE_SHIFT, %g6 + srlx %g4, REAL_HPAGE_SHIFT, %g6 sub %g7, 1, %g7 and %g6, %g7, %g6 sllx %g6, 4, %g6 diff --git a/arch/sparc/kernel/unaligned_64.c b/arch/sparc/kernel/unaligned_64.c index 8201c25e7669..3c1a7cb31579 100644 --- a/arch/sparc/kernel/unaligned_64.c +++ b/arch/sparc/kernel/unaligned_64.c @@ -21,9 +21,12 @@ #include <linux/bitops.h> #include <linux/perf_event.h> #include <linux/ratelimit.h> +#include <linux/context_tracking.h> #include <asm/fpumacro.h> #include <asm/cacheflush.h> +#include "entry.h" + enum direction { load, /* ld, ldd, ldh, ldsh */ store, /* st, std, sth, stsh */ @@ -418,9 +421,6 @@ int handle_popc(u32 insn, struct pt_regs *regs) extern void do_fpother(struct pt_regs *regs); extern void do_privact(struct pt_regs *regs); -extern void spitfire_data_access_exception(struct pt_regs *regs, - unsigned long sfsr, - unsigned long sfar); extern void sun4v_data_access_exception(struct pt_regs *regs, unsigned long addr, unsigned long type_ctx); @@ -578,6 +578,7 @@ void handle_ld_nf(u32 insn, struct pt_regs *regs) void handle_lddfmna(struct pt_regs *regs, unsigned long sfar, unsigned long sfsr) { + enum ctx_state prev_state = exception_enter(); unsigned long pc = regs->tpc; unsigned long tstate = regs->tstate; u32 insn; @@ -632,13 +633,16 @@ daex: sun4v_data_access_exception(regs, sfar, sfsr); else spitfire_data_access_exception(regs, sfsr, sfar); - return; + goto out; } advance(regs); +out: + exception_exit(prev_state); } void handle_stdfmna(struct pt_regs *regs, unsigned long sfar, unsigned long sfsr) { + enum ctx_state prev_state = exception_enter(); unsigned long pc = regs->tpc; unsigned long tstate = regs->tstate; u32 insn; @@ -680,7 +684,9 @@ daex: sun4v_data_access_exception(regs, sfar, sfsr); else spitfire_data_access_exception(regs, sfsr, sfar); - return; + goto out; } advance(regs); +out: + exception_exit(prev_state); } diff --git a/arch/sparc/kernel/vmlinux.lds.S b/arch/sparc/kernel/vmlinux.lds.S index 0bacceb19150..932ff90fd760 100644 --- a/arch/sparc/kernel/vmlinux.lds.S +++ b/arch/sparc/kernel/vmlinux.lds.S @@ -122,6 +122,11 @@ SECTIONS *(.swapper_4m_tsb_phys_patch) __swapper_4m_tsb_phys_patch_end = .; } + .page_offset_shift_patch : { + __page_offset_shift_patch = .; + *(.page_offset_shift_patch) + __page_offset_shift_patch_end = .; + } .popc_3insn_patch : { __popc_3insn_patch = .; *(.popc_3insn_patch) diff --git a/arch/sparc/lib/clear_page.S b/arch/sparc/lib/clear_page.S index 77e531f6c2a7..46272dfc26e8 100644 --- a/arch/sparc/lib/clear_page.S +++ b/arch/sparc/lib/clear_page.S @@ -37,10 +37,10 @@ _clear_page: /* %o0=dest */ .globl clear_user_page clear_user_page: /* %o0=dest, %o1=vaddr */ lduw [%g6 + TI_PRE_COUNT], %o2 - sethi %uhi(PAGE_OFFSET), %g2 + sethi %hi(PAGE_OFFSET), %g2 sethi %hi(PAGE_SIZE), %o4 - sllx %g2, 32, %g2 + ldx [%g2 + %lo(PAGE_OFFSET)], %g2 sethi %hi(PAGE_KERNEL_LOCKED), %g3 ldx [%g3 + %lo(PAGE_KERNEL_LOCKED)], %g3 diff --git a/arch/sparc/lib/copy_page.S b/arch/sparc/lib/copy_page.S index 4d2df328e514..dd16c61f3263 100644 --- a/arch/sparc/lib/copy_page.S +++ b/arch/sparc/lib/copy_page.S @@ -46,10 +46,10 @@ .type copy_user_page,#function copy_user_page: /* %o0=dest, %o1=src, %o2=vaddr */ lduw [%g6 + TI_PRE_COUNT], %o4 - sethi %uhi(PAGE_OFFSET), %g2 + sethi %hi(PAGE_OFFSET), %g2 sethi %hi(PAGE_SIZE), %o3 - sllx %g2, 32, %g2 + ldx [%g2 + %lo(PAGE_OFFSET)], %g2 sethi %hi(PAGE_KERNEL_LOCKED), %g3 ldx [%g3 + %lo(PAGE_KERNEL_LOCKED)], %g3 diff --git a/arch/sparc/mm/fault_64.c b/arch/sparc/mm/fault_64.c index 2ebec263d685..69bb818fdd79 100644 --- a/arch/sparc/mm/fault_64.c +++ b/arch/sparc/mm/fault_64.c @@ -21,6 +21,7 @@ #include <linux/kprobes.h> #include <linux/kdebug.h> #include <linux/percpu.h> +#include <linux/context_tracking.h> #include <asm/page.h> #include <asm/pgtable.h> @@ -272,6 +273,7 @@ static void noinline __kprobes bogus_32bit_fault_address(struct pt_regs *regs, asmlinkage void __kprobes do_sparc64_fault(struct pt_regs *regs) { + enum ctx_state prev_state = exception_enter(); struct mm_struct *mm = current->mm; struct vm_area_struct *vma; unsigned int insn = 0; @@ -282,7 +284,7 @@ asmlinkage void __kprobes do_sparc64_fault(struct pt_regs *regs) fault_code = get_thread_fault_code(); if (notify_page_fault(regs)) - return; + goto exit_exception; si_code = SEGV_MAPERR; address = current_thread_info()->fault_address; @@ -313,7 +315,7 @@ asmlinkage void __kprobes do_sparc64_fault(struct pt_regs *regs) /* Valid, no problems... */ } else { bad_kernel_pc(regs, address); - return; + goto exit_exception; } } else flags |= FAULT_FLAG_USER; @@ -430,7 +432,7 @@ good_area: fault = handle_mm_fault(mm, vma, address, flags); if ((fault & VM_FAULT_RETRY) && fatal_signal_pending(current)) - return; + goto exit_exception; if (unlikely(fault & VM_FAULT_ERROR)) { if (fault & VM_FAULT_OOM) @@ -482,6 +484,8 @@ good_area: } #endif +exit_exception: + exception_exit(prev_state); return; /* @@ -494,7 +498,7 @@ bad_area: handle_kernel_fault: do_kernel_fault(regs, si_code, fault_code, insn, address); - return; + goto exit_exception; /* * We ran out of memory, or some other thing happened to us that made @@ -505,7 +509,7 @@ out_of_memory: up_read(&mm->mmap_sem); if (!(regs->tstate & TSTATE_PRIV)) { pagefault_out_of_memory(); - return; + goto exit_exception; } goto handle_kernel_fault; diff --git a/arch/sparc/mm/gup.c b/arch/sparc/mm/gup.c index 01ee23dd724d..c4d3da68b800 100644 --- a/arch/sparc/mm/gup.c +++ b/arch/sparc/mm/gup.c @@ -71,13 +71,12 @@ static int gup_huge_pmd(pmd_t *pmdp, pmd_t pmd, unsigned long addr, int *nr) { struct page *head, *page, *tail; - u32 mask; int refs; - mask = PMD_HUGE_PRESENT; - if (write) - mask |= PMD_HUGE_WRITE; - if ((pmd_val(pmd) & mask) != mask) + if (!pmd_large(pmd)) + return 0; + + if (write && !pmd_write(pmd)) return 0; refs = 0; diff --git a/arch/sparc/mm/hugetlbpage.c b/arch/sparc/mm/hugetlbpage.c index 96399646570a..30963178d7e9 100644 --- a/arch/sparc/mm/hugetlbpage.c +++ b/arch/sparc/mm/hugetlbpage.c @@ -21,8 +21,6 @@ /* Slightly simplified from the non-hugepage variant because by * definition we don't have to worry about any page coloring stuff */ -#define VA_EXCLUDE_START (0x0000080000000000UL - (1UL << 32UL)) -#define VA_EXCLUDE_END (0xfffff80000000000UL + (1UL << 32UL)) static unsigned long hugetlb_get_unmapped_area_bottomup(struct file *filp, unsigned long addr, diff --git a/arch/sparc/mm/init_64.c b/arch/sparc/mm/init_64.c index ed82edad1a39..5322e530d09c 100644 --- a/arch/sparc/mm/init_64.c +++ b/arch/sparc/mm/init_64.c @@ -354,7 +354,7 @@ void update_mmu_cache(struct vm_area_struct *vma, unsigned long address, pte_t * #if defined(CONFIG_HUGETLB_PAGE) || defined(CONFIG_TRANSPARENT_HUGEPAGE) if (mm->context.huge_pte_count && is_hugetlb_pte(pte)) - __update_mmu_tsb_insert(mm, MM_TSB_HUGE, HPAGE_SHIFT, + __update_mmu_tsb_insert(mm, MM_TSB_HUGE, REAL_HPAGE_SHIFT, address, pte_val(pte)); else #endif @@ -1557,6 +1557,96 @@ unsigned long __init find_ecache_flush_span(unsigned long size) return ~0UL; } +unsigned long PAGE_OFFSET; +EXPORT_SYMBOL(PAGE_OFFSET); + +static void __init page_offset_shift_patch_one(unsigned int *insn, unsigned long phys_bits) +{ + unsigned long final_shift; + unsigned int val = *insn; + unsigned int cnt; + + /* We are patching in ilog2(max_supported_phys_address), and + * we are doing so in a manner similar to a relocation addend. + * That is, we are adding the shift value to whatever value + * is in the shift instruction count field already. + */ + cnt = (val & 0x3f); + val &= ~0x3f; + + /* If we are trying to shift >= 64 bits, clear the destination + * register. This can happen when phys_bits ends up being equal + * to MAX_PHYS_ADDRESS_BITS. + */ + final_shift = (cnt + (64 - phys_bits)); + if (final_shift >= 64) { + unsigned int rd = (val >> 25) & 0x1f; + + val = 0x80100000 | (rd << 25); + } else { + val |= final_shift; + } + *insn = val; + + __asm__ __volatile__("flush %0" + : /* no outputs */ + : "r" (insn)); +} + +static void __init page_offset_shift_patch(unsigned long phys_bits) +{ + extern unsigned int __page_offset_shift_patch; + extern unsigned int __page_offset_shift_patch_end; + unsigned int *p; + + p = &__page_offset_shift_patch; + while (p < &__page_offset_shift_patch_end) { + unsigned int *insn = (unsigned int *)(unsigned long)*p; + + page_offset_shift_patch_one(insn, phys_bits); + + p++; + } +} + +static void __init setup_page_offset(void) +{ + unsigned long max_phys_bits = 40; + + if (tlb_type == cheetah || tlb_type == cheetah_plus) { + max_phys_bits = 42; + } else if (tlb_type == hypervisor) { + switch (sun4v_chip_type) { + case SUN4V_CHIP_NIAGARA1: + case SUN4V_CHIP_NIAGARA2: + max_phys_bits = 39; + break; + case SUN4V_CHIP_NIAGARA3: + max_phys_bits = 43; + break; + case SUN4V_CHIP_NIAGARA4: + case SUN4V_CHIP_NIAGARA5: + case SUN4V_CHIP_SPARC64X: + default: + max_phys_bits = 47; + break; + } + } + + if (max_phys_bits > MAX_PHYS_ADDRESS_BITS) { + prom_printf("MAX_PHYS_ADDRESS_BITS is too small, need %lu\n", + max_phys_bits); + prom_halt(); + } + + PAGE_OFFSET = PAGE_OFFSET_BY_BITS(max_phys_bits); + + pr_info("PAGE_OFFSET is 0x%016lx (max_phys_bits == %lu)\n", + PAGE_OFFSET, max_phys_bits); + + page_offset_shift_patch(max_phys_bits); +} + static void __init tsb_phys_patch(void) { struct tsb_ldquad_phys_patch_entry *pquad; @@ -1722,7 +1812,7 @@ static void __init sun4v_linear_pte_xor_finalize(void) #ifndef CONFIG_DEBUG_PAGEALLOC if (cpu_pgsz_mask & HV_PGSZ_MASK_256MB) { kern_linear_pte_xor[1] = (_PAGE_VALID | _PAGE_SZ256MB_4V) ^ - 0xfffff80000000000UL; + PAGE_OFFSET; kern_linear_pte_xor[1] |= (_PAGE_CP_4V | _PAGE_CV_4V | _PAGE_P_4V | _PAGE_W_4V); } else { @@ -1731,7 +1821,7 @@ static void __init sun4v_linear_pte_xor_finalize(void) if (cpu_pgsz_mask & HV_PGSZ_MASK_2GB) { kern_linear_pte_xor[2] = (_PAGE_VALID | _PAGE_SZ2GB_4V) ^ - 0xfffff80000000000UL; + PAGE_OFFSET; kern_linear_pte_xor[2] |= (_PAGE_CP_4V | _PAGE_CV_4V | _PAGE_P_4V | _PAGE_W_4V); } else { @@ -1740,7 +1830,7 @@ static void __init sun4v_linear_pte_xor_finalize(void) if (cpu_pgsz_mask & HV_PGSZ_MASK_16GB) { kern_linear_pte_xor[3] = (_PAGE_VALID | _PAGE_SZ16GB_4V) ^ - 0xfffff80000000000UL; + PAGE_OFFSET; kern_linear_pte_xor[3] |= (_PAGE_CP_4V | _PAGE_CV_4V | _PAGE_P_4V | _PAGE_W_4V); } else { @@ -1752,7 +1842,7 @@ static void __init sun4v_linear_pte_xor_finalize(void) /* paging_init() sets up the page tables */ static unsigned long last_valid_pfn; -pgd_t swapper_pg_dir[2048]; +pgd_t swapper_pg_dir[PTRS_PER_PGD]; static void sun4u_pgprot_init(void); static void sun4v_pgprot_init(void); @@ -1763,6 +1853,8 @@ void __init paging_init(void) unsigned long real_end, i; int node; + setup_page_offset(); + /* These build time checkes make sure that the dcache_dirty_cpu() * page->flags usage will work. * @@ -2261,10 +2353,10 @@ static void __init sun4u_pgprot_init(void) __ACCESS_BITS_4U | _PAGE_E_4U); #ifdef CONFIG_DEBUG_PAGEALLOC - kern_linear_pte_xor[0] = _PAGE_VALID ^ 0xfffff80000000000UL; + kern_linear_pte_xor[0] = _PAGE_VALID ^ PAGE_OFFSET; #else kern_linear_pte_xor[0] = (_PAGE_VALID | _PAGE_SZ4MB_4U) ^ - 0xfffff80000000000UL; + PAGE_OFFSET; #endif kern_linear_pte_xor[0] |= (_PAGE_CP_4U | _PAGE_CV_4U | _PAGE_P_4U | _PAGE_W_4U); @@ -2308,10 +2400,10 @@ static void __init sun4v_pgprot_init(void) _PAGE_CACHE = _PAGE_CACHE_4V; #ifdef CONFIG_DEBUG_PAGEALLOC - kern_linear_pte_xor[0] = _PAGE_VALID ^ 0xfffff80000000000UL; + kern_linear_pte_xor[0] = _PAGE_VALID ^ PAGE_OFFSET; #else kern_linear_pte_xor[0] = (_PAGE_VALID | _PAGE_SZ4MB_4V) ^ - 0xfffff80000000000UL; + PAGE_OFFSET; #endif kern_linear_pte_xor[0] |= (_PAGE_CP_4V | _PAGE_CV_4V | _PAGE_P_4V | _PAGE_W_4V); @@ -2455,53 +2547,13 @@ void __flush_tlb_all(void) : : "r" (pstate)); } -static pte_t *get_from_cache(struct mm_struct *mm) -{ - struct page *page; - pte_t *ret; - - spin_lock(&mm->page_table_lock); - page = mm->context.pgtable_page; - ret = NULL; - if (page) { - void *p = page_address(page); - - mm->context.pgtable_page = NULL; - - ret = (pte_t *) (p + (PAGE_SIZE / 2)); - } - spin_unlock(&mm->page_table_lock); - - return ret; -} - -static struct page *__alloc_for_cache(struct mm_struct *mm) -{ - struct page *page = alloc_page(GFP_KERNEL | __GFP_NOTRACK | - __GFP_REPEAT | __GFP_ZERO); - - if (page) { - spin_lock(&mm->page_table_lock); - if (!mm->context.pgtable_page) { - atomic_set(&page->_count, 2); - mm->context.pgtable_page = page; - } - spin_unlock(&mm->page_table_lock); - } - return page; -} - pte_t *pte_alloc_one_kernel(struct mm_struct *mm, unsigned long address) { - struct page *page; - pte_t *pte; - - pte = get_from_cache(mm); - if (pte) - return pte; + struct page *page = alloc_page(GFP_KERNEL | __GFP_NOTRACK | + __GFP_REPEAT | __GFP_ZERO); + pte_t *pte = NULL; - page = __alloc_for_cache(mm); if (page) pte = (pte_t *) page_address(page); @@ -2511,36 +2563,28 @@ pte_t *pte_alloc_one_kernel(struct mm_struct *mm, pgtable_t pte_alloc_one(struct mm_struct *mm, unsigned long address) { - struct page *page; - pte_t *pte; - - pte = get_from_cache(mm); - if (pte) - return pte; - - page = __alloc_for_cache(mm); - if (page) { - pgtable_page_ctor(page); - pte = (pte_t *) page_address(page); + struct page *page = alloc_page(GFP_KERNEL | __GFP_NOTRACK | + __GFP_REPEAT | __GFP_ZERO); + if (!page) + return NULL; + if (!pgtable_page_ctor(page)) { + free_hot_cold_page(page, 0); + return NULL; } - - return pte; + return (pte_t *) page_address(page); } void pte_free_kernel(struct mm_struct *mm, pte_t *pte) { - struct page *page = virt_to_page(pte); - if (put_page_testzero(page)) - free_hot_cold_page(page, 0); + free_page((unsigned long)pte); } static void __pte_free(pgtable_t pte) { struct page *page = virt_to_page(pte); - if (put_page_testzero(page)) { - pgtable_page_dtor(page); - free_hot_cold_page(page, 0); - } + + pgtable_page_dtor(page); + __free_page(page); } void pte_free(struct mm_struct *mm, pgtable_t pte) @@ -2557,124 +2601,27 @@ void pgtable_free(void *table, bool is_page) } #ifdef CONFIG_TRANSPARENT_HUGEPAGE -static pmd_t pmd_set_protbits(pmd_t pmd, pgprot_t pgprot, bool for_modify) -{ - if (pgprot_val(pgprot) & _PAGE_VALID) - pmd_val(pmd) |= PMD_HUGE_PRESENT; - if (tlb_type == hypervisor) { - if (pgprot_val(pgprot) & _PAGE_WRITE_4V) - pmd_val(pmd) |= PMD_HUGE_WRITE; - if (pgprot_val(pgprot) & _PAGE_EXEC_4V) - pmd_val(pmd) |= PMD_HUGE_EXEC; - - if (!for_modify) { - if (pgprot_val(pgprot) & _PAGE_ACCESSED_4V) - pmd_val(pmd) |= PMD_HUGE_ACCESSED; - if (pgprot_val(pgprot) & _PAGE_MODIFIED_4V) - pmd_val(pmd) |= PMD_HUGE_DIRTY; - } - } else { - if (pgprot_val(pgprot) & _PAGE_WRITE_4U) - pmd_val(pmd) |= PMD_HUGE_WRITE; - if (pgprot_val(pgprot) & _PAGE_EXEC_4U) - pmd_val(pmd) |= PMD_HUGE_EXEC; - - if (!for_modify) { - if (pgprot_val(pgprot) & _PAGE_ACCESSED_4U) - pmd_val(pmd) |= PMD_HUGE_ACCESSED; - if (pgprot_val(pgprot) & _PAGE_MODIFIED_4U) - pmd_val(pmd) |= PMD_HUGE_DIRTY; - } - } - - return pmd; -} - -pmd_t pfn_pmd(unsigned long page_nr, pgprot_t pgprot) -{ - pmd_t pmd; - - pmd_val(pmd) = (page_nr << ((PAGE_SHIFT - PMD_PADDR_SHIFT))); - pmd_val(pmd) |= PMD_ISHUGE; - pmd = pmd_set_protbits(pmd, pgprot, false); - return pmd; -} - -pmd_t pmd_modify(pmd_t pmd, pgprot_t newprot) -{ - pmd_val(pmd) &= ~(PMD_HUGE_PRESENT | - PMD_HUGE_WRITE | - PMD_HUGE_EXEC); - pmd = pmd_set_protbits(pmd, newprot, true); - return pmd; -} - -pgprot_t pmd_pgprot(pmd_t entry) -{ - unsigned long pte = 0; - - if (pmd_val(entry) & PMD_HUGE_PRESENT) - pte |= _PAGE_VALID; - - if (tlb_type == hypervisor) { - if (pmd_val(entry) & PMD_HUGE_PRESENT) - pte |= _PAGE_PRESENT_4V; - if (pmd_val(entry) & PMD_HUGE_EXEC) - pte |= _PAGE_EXEC_4V; - if (pmd_val(entry) & PMD_HUGE_WRITE) - pte |= _PAGE_W_4V; - if (pmd_val(entry) & PMD_HUGE_ACCESSED) - pte |= _PAGE_ACCESSED_4V; - if (pmd_val(entry) & PMD_HUGE_DIRTY) - pte |= _PAGE_MODIFIED_4V; - pte |= _PAGE_CP_4V|_PAGE_CV_4V; - } else { - if (pmd_val(entry) & PMD_HUGE_PRESENT) - pte |= _PAGE_PRESENT_4U; - if (pmd_val(entry) & PMD_HUGE_EXEC) - pte |= _PAGE_EXEC_4U; - if (pmd_val(entry) & PMD_HUGE_WRITE) - pte |= _PAGE_W_4U; - if (pmd_val(entry) & PMD_HUGE_ACCESSED) - pte |= _PAGE_ACCESSED_4U; - if (pmd_val(entry) & PMD_HUGE_DIRTY) - pte |= _PAGE_MODIFIED_4U; - pte |= _PAGE_CP_4U|_PAGE_CV_4U; - } - - return __pgprot(pte); -} - void update_mmu_cache_pmd(struct vm_area_struct *vma, unsigned long addr, pmd_t *pmd) { unsigned long pte, flags; struct mm_struct *mm; pmd_t entry = *pmd; - pgprot_t prot; if (!pmd_large(entry) || !pmd_young(entry)) return; - pte = (pmd_val(entry) & ~PMD_HUGE_PROTBITS); - pte <<= PMD_PADDR_SHIFT; - pte |= _PAGE_VALID; - - prot = pmd_pgprot(entry); - - if (tlb_type == hypervisor) - pgprot_val(prot) |= _PAGE_SZHUGE_4V; - else - pgprot_val(prot) |= _PAGE_SZHUGE_4U; + pte = pmd_val(entry); - pte |= pgprot_val(prot); + /* We are fabricating 8MB pages using 4MB real hw pages. */ + pte |= (addr & (1UL << REAL_HPAGE_SHIFT)); mm = vma->vm_mm; spin_lock_irqsave(&mm->context.lock, flags); if (mm->context.tsb_block[MM_TSB_HUGE].tsb != NULL) - __update_mmu_tsb_insert(mm, MM_TSB_HUGE, HPAGE_SHIFT, + __update_mmu_tsb_insert(mm, MM_TSB_HUGE, REAL_HPAGE_SHIFT, addr, pte); spin_unlock_irqrestore(&mm->context.lock, flags); diff --git a/arch/sparc/mm/init_64.h b/arch/sparc/mm/init_64.h index 0661aa606dec..5d3782deb403 100644 --- a/arch/sparc/mm/init_64.h +++ b/arch/sparc/mm/init_64.h @@ -1,11 +1,13 @@ #ifndef _SPARC64_MM_INIT_H #define _SPARC64_MM_INIT_H +#include <asm/page.h> + /* Most of the symbols in this file are defined in init.c and * marked non-static so that assembler code can get at them. */ -#define MAX_PHYS_ADDRESS (1UL << 41UL) +#define MAX_PHYS_ADDRESS (1UL << MAX_PHYS_ADDRESS_BITS) #define KPTE_BITMAP_CHUNK_SZ (256UL * 1024UL * 1024UL) #define KPTE_BITMAP_BYTES \ ((MAX_PHYS_ADDRESS / KPTE_BITMAP_CHUNK_SZ) / 4) diff --git a/arch/sparc/mm/srmmu.c b/arch/sparc/mm/srmmu.c index 5d721df48a72..869023abe5a4 100644 --- a/arch/sparc/mm/srmmu.c +++ b/arch/sparc/mm/srmmu.c @@ -345,7 +345,10 @@ pgtable_t pte_alloc_one(struct mm_struct *mm, unsigned long address) if ((pte = (unsigned long)pte_alloc_one_kernel(mm, address)) == 0) return NULL; page = pfn_to_page(__nocache_pa(pte) >> PAGE_SHIFT); - pgtable_page_ctor(page); + if (!pgtable_page_ctor(page)) { + __free_page(page); + return NULL; + } return page; } diff --git a/arch/sparc/mm/tlb.c b/arch/sparc/mm/tlb.c index 7a91f288c708..ad3bf4b4324d 100644 --- a/arch/sparc/mm/tlb.c +++ b/arch/sparc/mm/tlb.c @@ -161,8 +161,8 @@ void set_pmd_at(struct mm_struct *mm, unsigned long addr, if (mm == &init_mm) return; - if ((pmd_val(pmd) ^ pmd_val(orig)) & PMD_ISHUGE) { - if (pmd_val(pmd) & PMD_ISHUGE) + if ((pmd_val(pmd) ^ pmd_val(orig)) & _PAGE_PMD_HUGE) { + if (pmd_val(pmd) & _PAGE_PMD_HUGE) mm->context.huge_pte_count++; else mm->context.huge_pte_count--; @@ -178,13 +178,16 @@ void set_pmd_at(struct mm_struct *mm, unsigned long addr, } if (!pmd_none(orig)) { - bool exec = ((pmd_val(orig) & PMD_HUGE_EXEC) != 0); + pte_t orig_pte = __pte(pmd_val(orig)); + bool exec = pte_exec(orig_pte); addr &= HPAGE_MASK; - if (pmd_val(orig) & PMD_ISHUGE) + if (pmd_trans_huge(orig)) { tlb_batch_add_one(mm, addr, exec); - else + tlb_batch_add_one(mm, addr + REAL_HPAGE_SIZE, exec); + } else { tlb_batch_pmd_scan(mm, addr, orig, exec); + } } } @@ -196,11 +199,11 @@ void pgtable_trans_huge_deposit(struct mm_struct *mm, pmd_t *pmdp, assert_spin_locked(&mm->page_table_lock); /* FIFO */ - if (!mm->pmd_huge_pte) + if (!pmd_huge_pte(mm, pmdp)) INIT_LIST_HEAD(lh); else - list_add(lh, (struct list_head *) mm->pmd_huge_pte); - mm->pmd_huge_pte = pgtable; + list_add(lh, (struct list_head *) pmd_huge_pte(mm, pmdp)); + pmd_huge_pte(mm, pmdp) = pgtable; } pgtable_t pgtable_trans_huge_withdraw(struct mm_struct *mm, pmd_t *pmdp) @@ -211,12 +214,12 @@ pgtable_t pgtable_trans_huge_withdraw(struct mm_struct *mm, pmd_t *pmdp) assert_spin_locked(&mm->page_table_lock); /* FIFO */ - pgtable = mm->pmd_huge_pte; + pgtable = pmd_huge_pte(mm, pmdp); lh = (struct list_head *) pgtable; if (list_empty(lh)) - mm->pmd_huge_pte = NULL; + pmd_huge_pte(mm, pmdp) = NULL; else { - mm->pmd_huge_pte = (pgtable_t) lh->next; + pmd_huge_pte(mm, pmdp) = (pgtable_t) lh->next; list_del(lh); } pte_val(pgtable[0]) = 0; diff --git a/arch/sparc/mm/tsb.c b/arch/sparc/mm/tsb.c index 2cc3bce5ee91..3b3a360b429a 100644 --- a/arch/sparc/mm/tsb.c +++ b/arch/sparc/mm/tsb.c @@ -87,7 +87,7 @@ void flush_tsb_user(struct tlb_batch *tb) nentries = mm->context.tsb_block[MM_TSB_HUGE].tsb_nentries; if (tlb_type == cheetah_plus || tlb_type == hypervisor) base = __pa(base); - __flush_tsb_one(tb, HPAGE_SHIFT, base, nentries); + __flush_tsb_one(tb, REAL_HPAGE_SHIFT, base, nentries); } #endif spin_unlock_irqrestore(&mm->context.lock, flags); @@ -111,7 +111,7 @@ void flush_tsb_user_page(struct mm_struct *mm, unsigned long vaddr) nentries = mm->context.tsb_block[MM_TSB_HUGE].tsb_nentries; if (tlb_type == cheetah_plus || tlb_type == hypervisor) base = __pa(base); - __flush_tsb_one_entry(base, vaddr, HPAGE_SHIFT, nentries); + __flush_tsb_one_entry(base, vaddr, REAL_HPAGE_SHIFT, nentries); } #endif spin_unlock_irqrestore(&mm->context.lock, flags); @@ -472,8 +472,6 @@ int init_new_context(struct task_struct *tsk, struct mm_struct *mm) mm->context.huge_pte_count = 0; #endif - mm->context.pgtable_page = NULL; - /* copy_mm() copies over the parent's mm_struct before calling * us, so we need to zero out the TSB pointer or else tsb_grow() * will be confused and think there is an older TSB to free up. @@ -512,17 +510,10 @@ static void tsb_destroy_one(struct tsb_config *tp) void destroy_context(struct mm_struct *mm) { unsigned long flags, i; - struct page *page; for (i = 0; i < MM_NUM_TSBS; i++) tsb_destroy_one(&mm->context.tsb_block[i]); - page = mm->context.pgtable_page; - if (page && put_page_testzero(page)) { - pgtable_page_dtor(page); - free_hot_cold_page(page, 0); - } - spin_lock_irqsave(&ctx_alloc_lock, flags); if (CTX_VALID(mm->context)) { diff --git a/arch/sparc/mm/ultra.S b/arch/sparc/mm/ultra.S index 432aa0cb1b38..b4f4733abc6e 100644 --- a/arch/sparc/mm/ultra.S +++ b/arch/sparc/mm/ultra.S @@ -153,10 +153,10 @@ __spitfire_flush_tlb_mm_slow: .globl __flush_icache_page __flush_icache_page: /* %o0 = phys_page */ srlx %o0, PAGE_SHIFT, %o0 - sethi %uhi(PAGE_OFFSET), %g1 + sethi %hi(PAGE_OFFSET), %g1 sllx %o0, PAGE_SHIFT, %o0 sethi %hi(PAGE_SIZE), %g2 - sllx %g1, 32, %g1 + ldx [%g1 + %lo(PAGE_OFFSET)], %g1 add %o0, %g1, %o0 1: subcc %g2, 32, %g2 bne,pt %icc, 1b @@ -178,8 +178,8 @@ __flush_icache_page: /* %o0 = phys_page */ .align 64 .globl __flush_dcache_page __flush_dcache_page: /* %o0=kaddr, %o1=flush_icache */ - sethi %uhi(PAGE_OFFSET), %g1 - sllx %g1, 32, %g1 + sethi %hi(PAGE_OFFSET), %g1 + ldx [%g1 + %lo(PAGE_OFFSET)], %g1 sub %o0, %g1, %o0 ! physical address srlx %o0, 11, %o0 ! make D-cache TAG sethi %hi(1 << 14), %o2 ! D-cache size @@ -287,8 +287,8 @@ __cheetah_flush_tlb_pending: /* 27 insns */ #ifdef DCACHE_ALIASING_POSSIBLE __cheetah_flush_dcache_page: /* 11 insns */ - sethi %uhi(PAGE_OFFSET), %g1 - sllx %g1, 32, %g1 + sethi %hi(PAGE_OFFSET), %g1 + ldx [%g1 + %lo(PAGE_OFFSET)], %g1 sub %o0, %g1, %o0 sethi %hi(PAGE_SIZE), %o4 1: subcc %o4, (1 << 5), %o4 diff --git a/arch/tile/Kconfig b/arch/tile/Kconfig index d45a2c48f185..b3692ce78f90 100644 --- a/arch/tile/Kconfig +++ b/arch/tile/Kconfig @@ -8,7 +8,6 @@ config TILE select HAVE_KVM if !TILEGX select GENERIC_FIND_FIRST_BIT select SYSCTL_EXCEPTION_TRACE - select USE_GENERIC_SMP_HELPERS select CC_OPTIMIZE_FOR_SIZE select HAVE_DEBUG_KMEMLEAK select GENERIC_IRQ_PROBE diff --git a/arch/tile/include/asm/hardirq.h b/arch/tile/include/asm/hardirq.h index 822390f9a154..54110af23985 100644 --- a/arch/tile/include/asm/hardirq.h +++ b/arch/tile/include/asm/hardirq.h @@ -42,6 +42,4 @@ DECLARE_PER_CPU(irq_cpustat_t, irq_stat); #include <linux/irq_cpustat.h> /* Standard mappings for irq_cpustat_t above */ -#define HARDIRQ_BITS 8 - #endif /* _ASM_TILE_HARDIRQ_H */ diff --git a/arch/tile/include/asm/thread_info.h b/arch/tile/include/asm/thread_info.h index b8aa6df3e102..729aa107f64e 100644 --- a/arch/tile/include/asm/thread_info.h +++ b/arch/tile/include/asm/thread_info.h @@ -113,8 +113,6 @@ extern void _cpu_idle(void); #endif /* !__ASSEMBLY__ */ -#define PREEMPT_ACTIVE 0x10000000 - /* * Thread information flags that various assembly files may need to access. * Keep flags accessed frequently in low bits, particular since it makes diff --git a/arch/tile/kernel/pci.c b/arch/tile/kernel/pci.c index b7180e6e900d..c45593db7718 100644 --- a/arch/tile/kernel/pci.c +++ b/arch/tile/kernel/pci.c @@ -251,15 +251,12 @@ static void fixup_read_and_payload_sizes(void) /* Scan for the smallest maximum payload size. */ for_each_pci_dev(dev) { u32 devcap; - int max_payload; if (!pci_is_pcie(dev)) continue; - pcie_capability_read_dword(dev, PCI_EXP_DEVCAP, &devcap); - max_payload = devcap & PCI_EXP_DEVCAP_PAYLOAD; - if (max_payload < smallest_max_payload) - smallest_max_payload = max_payload; + if (dev->pcie_mpss < smallest_max_payload) + smallest_max_payload = dev->pcie_mpss; } /* Now, set the max_payload_size for all devices to that value. */ diff --git a/arch/tile/mm/pgtable.c b/arch/tile/mm/pgtable.c index 4fd9ec0b58ed..5e86eac4bfae 100644 --- a/arch/tile/mm/pgtable.c +++ b/arch/tile/mm/pgtable.c @@ -241,6 +241,11 @@ struct page *pgtable_alloc_one(struct mm_struct *mm, unsigned long address, if (p == NULL) return NULL; + if (!pgtable_page_ctor(p)) { + __free_pages(p, L2_USER_PGTABLE_ORDER); + return NULL; + } + /* * Make every page have a page_count() of one, not just the first. * We don't use __GFP_COMP since it doesn't look like it works @@ -251,7 +256,6 @@ struct page *pgtable_alloc_one(struct mm_struct *mm, unsigned long address, inc_zone_page_state(p+i, NR_PAGETABLE); } - pgtable_page_ctor(p); return p; } diff --git a/arch/um/Kconfig.char b/arch/um/Kconfig.char index b9d7c4276682..f10738d68b2d 100644 --- a/arch/um/Kconfig.char +++ b/arch/um/Kconfig.char @@ -6,10 +6,6 @@ config STDERR_CONSOLE help console driver which dumps all printk messages to stderr. -config STDIO_CONSOLE - bool - default y - config SSL bool "Virtual serial line" help diff --git a/arch/um/Kconfig.common b/arch/um/Kconfig.common index 8ddea1f8006a..21ca44c4f6d5 100644 --- a/arch/um/Kconfig.common +++ b/arch/um/Kconfig.common @@ -1,8 +1,3 @@ -config DEFCONFIG_LIST - string - option defconfig_list - default "arch/$ARCH/defconfig" - config UML bool default y diff --git a/arch/um/Makefile b/arch/um/Makefile index 133f7de2a13d..48d92bbe62e9 100644 --- a/arch/um/Makefile +++ b/arch/um/Makefile @@ -6,6 +6,17 @@ # Licensed under the GPL # +# select defconfig based on actual architecture +ifeq ($(SUBARCH),x86) + ifeq ($(shell uname -m),x86_64) + KBUILD_DEFCONFIG := x86_64_defconfig + else + KBUILD_DEFCONFIG := i386_defconfig + endif +else + KBUILD_DEFCONFIG := $(SUBARCH)_defconfig +endif + ARCH_DIR := arch/um OS := $(shell uname -s) # We require bash because the vmlinux link and loader script cpp use bash diff --git a/arch/um/configs/i386_defconfig b/arch/um/configs/i386_defconfig new file mode 100644 index 000000000000..a12bf68c9f3a --- /dev/null +++ b/arch/um/configs/i386_defconfig @@ -0,0 +1,76 @@ +CONFIG_3_LEVEL_PGTABLES=y +# CONFIG_COMPACTION is not set +CONFIG_BINFMT_MISC=m +CONFIG_HOSTFS=y +CONFIG_MAGIC_SYSRQ=y +CONFIG_KERNEL_STACK_ORDER=1 +CONFIG_SYSVIPC=y +CONFIG_POSIX_MQUEUE=y +CONFIG_NO_HZ=y +CONFIG_HIGH_RES_TIMERS=y +CONFIG_BSD_PROCESS_ACCT=y +CONFIG_IKCONFIG=y +CONFIG_IKCONFIG_PROC=y +CONFIG_LOG_BUF_SHIFT=14 +CONFIG_CGROUPS=y +CONFIG_CGROUP_FREEZER=y +CONFIG_CGROUP_DEVICE=y +CONFIG_CPUSETS=y +CONFIG_CGROUP_CPUACCT=y +CONFIG_RESOURCE_COUNTERS=y +CONFIG_CGROUP_SCHED=y +CONFIG_BLK_CGROUP=y +# CONFIG_PID_NS is not set +CONFIG_SYSFS_DEPRECATED=y +CONFIG_CC_OPTIMIZE_FOR_SIZE=y +CONFIG_SLAB=y +CONFIG_MODULES=y +CONFIG_MODULE_UNLOAD=y +# CONFIG_BLK_DEV_BSG is not set +CONFIG_IOSCHED_CFQ=m +CONFIG_SSL=y +CONFIG_NULL_CHAN=y +CONFIG_PORT_CHAN=y +CONFIG_PTY_CHAN=y +CONFIG_TTY_CHAN=y +CONFIG_XTERM_CHAN=y +CONFIG_CON_CHAN="pts" +CONFIG_SSL_CHAN="pts" +CONFIG_UML_SOUND=m +CONFIG_UEVENT_HELPER_PATH="/sbin/hotplug" +CONFIG_DEVTMPFS=y +CONFIG_DEVTMPFS_MOUNT=y +CONFIG_BLK_DEV_UBD=y +CONFIG_BLK_DEV_LOOP=m +CONFIG_BLK_DEV_NBD=m +CONFIG_DUMMY=m +CONFIG_TUN=m +CONFIG_PPP=m +CONFIG_SLIP=m +CONFIG_LEGACY_PTY_COUNT=32 +# CONFIG_HW_RANDOM is not set +CONFIG_UML_RANDOM=y +CONFIG_NET=y +CONFIG_PACKET=y +CONFIG_UNIX=y +CONFIG_INET=y +# CONFIG_INET_LRO is not set +# CONFIG_IPV6 is not set +CONFIG_UML_NET=y +CONFIG_UML_NET_ETHERTAP=y +CONFIG_UML_NET_TUNTAP=y +CONFIG_UML_NET_SLIP=y +CONFIG_UML_NET_DAEMON=y +CONFIG_UML_NET_MCAST=y +CONFIG_UML_NET_SLIRP=y +CONFIG_EXT4_FS=y +CONFIG_REISERFS_FS=y +CONFIG_QUOTA=y +CONFIG_AUTOFS4_FS=m +CONFIG_ISO9660_FS=m +CONFIG_JOLIET=y +CONFIG_PROC_KCORE=y +CONFIG_TMPFS=y +CONFIG_NLS=y +CONFIG_DEBUG_INFO=y +CONFIG_DEBUG_KERNEL=y diff --git a/arch/um/configs/x86_64_defconfig b/arch/um/configs/x86_64_defconfig new file mode 100644 index 000000000000..3aab117bd553 --- /dev/null +++ b/arch/um/configs/x86_64_defconfig @@ -0,0 +1,75 @@ +# CONFIG_COMPACTION is not set +CONFIG_BINFMT_MISC=m +CONFIG_HOSTFS=y +CONFIG_MAGIC_SYSRQ=y +CONFIG_SYSVIPC=y +CONFIG_POSIX_MQUEUE=y +CONFIG_NO_HZ=y +CONFIG_HIGH_RES_TIMERS=y +CONFIG_BSD_PROCESS_ACCT=y +CONFIG_IKCONFIG=y +CONFIG_IKCONFIG_PROC=y +CONFIG_LOG_BUF_SHIFT=14 +CONFIG_CGROUPS=y +CONFIG_CGROUP_FREEZER=y +CONFIG_CGROUP_DEVICE=y +CONFIG_CPUSETS=y +CONFIG_CGROUP_CPUACCT=y +CONFIG_RESOURCE_COUNTERS=y +CONFIG_CGROUP_SCHED=y +CONFIG_BLK_CGROUP=y +# CONFIG_PID_NS is not set +CONFIG_SYSFS_DEPRECATED=y +CONFIG_CC_OPTIMIZE_FOR_SIZE=y +CONFIG_SLAB=y +CONFIG_MODULES=y +CONFIG_MODULE_UNLOAD=y +# CONFIG_BLK_DEV_BSG is not set +CONFIG_IOSCHED_CFQ=m +CONFIG_SSL=y +CONFIG_NULL_CHAN=y +CONFIG_PORT_CHAN=y +CONFIG_PTY_CHAN=y +CONFIG_TTY_CHAN=y +CONFIG_XTERM_CHAN=y +CONFIG_CON_CHAN="pts" +CONFIG_SSL_CHAN="pts" +CONFIG_UML_SOUND=m +CONFIG_UEVENT_HELPER_PATH="/sbin/hotplug" +CONFIG_DEVTMPFS=y +CONFIG_DEVTMPFS_MOUNT=y +CONFIG_BLK_DEV_UBD=y +CONFIG_BLK_DEV_LOOP=m +CONFIG_BLK_DEV_NBD=m +CONFIG_DUMMY=m +CONFIG_TUN=m +CONFIG_PPP=m +CONFIG_SLIP=m +CONFIG_LEGACY_PTY_COUNT=32 +# CONFIG_HW_RANDOM is not set +CONFIG_UML_RANDOM=y +CONFIG_NET=y +CONFIG_PACKET=y +CONFIG_UNIX=y +CONFIG_INET=y +# CONFIG_INET_LRO is not set +# CONFIG_IPV6 is not set +CONFIG_UML_NET=y +CONFIG_UML_NET_ETHERTAP=y +CONFIG_UML_NET_TUNTAP=y +CONFIG_UML_NET_SLIP=y +CONFIG_UML_NET_DAEMON=y +CONFIG_UML_NET_MCAST=y +CONFIG_UML_NET_SLIRP=y +CONFIG_EXT4_FS=y +CONFIG_REISERFS_FS=y +CONFIG_QUOTA=y +CONFIG_AUTOFS4_FS=m +CONFIG_ISO9660_FS=m +CONFIG_JOLIET=y +CONFIG_PROC_KCORE=y +CONFIG_TMPFS=y +CONFIG_NLS=y +CONFIG_DEBUG_INFO=y +CONFIG_FRAME_WARN=1024 +CONFIG_DEBUG_KERNEL=y diff --git a/arch/um/defconfig b/arch/um/defconfig deleted file mode 100644 index 2665e6b683f5..000000000000 --- a/arch/um/defconfig +++ /dev/null @@ -1,899 +0,0 @@ -# -# Automatically generated file; DO NOT EDIT. -# User Mode Linux/i386 3.3.0 Kernel Configuration -# -CONFIG_DEFCONFIG_LIST="arch/$ARCH/defconfig" -CONFIG_UML=y -CONFIG_MMU=y -CONFIG_NO_IOMEM=y -# CONFIG_TRACE_IRQFLAGS_SUPPORT is not set -CONFIG_LOCKDEP_SUPPORT=y -# CONFIG_STACKTRACE_SUPPORT is not set -CONFIG_GENERIC_CALIBRATE_DELAY=y -CONFIG_GENERIC_BUG=y -CONFIG_GENERIC_CLOCKEVENTS=y -CONFIG_HZ=100 - -# -# UML-specific options -# - -# -# Host processor type and features -# -# CONFIG_M486 is not set -# CONFIG_M586 is not set -# CONFIG_M586TSC is not set -# CONFIG_M586MMX is not set -CONFIG_M686=y -# CONFIG_MPENTIUMII is not set -# CONFIG_MPENTIUMIII is not set -# CONFIG_MPENTIUMM is not set -# CONFIG_MPENTIUM4 is not set -# CONFIG_MK6 is not set -# CONFIG_MK7 is not set -# CONFIG_MK8 is not set -# CONFIG_MCRUSOE is not set -# CONFIG_MEFFICEON is not set -# CONFIG_MWINCHIPC6 is not set -# CONFIG_MWINCHIP3D is not set -# CONFIG_MELAN is not set -# CONFIG_MGEODEGX1 is not set -# CONFIG_MGEODE_LX is not set -# CONFIG_MCYRIXIII is not set -# CONFIG_MVIAC3_2 is not set -# CONFIG_MVIAC7 is not set -# CONFIG_MCORE2 is not set -# CONFIG_MATOM is not set -# CONFIG_X86_GENERIC is not set -CONFIG_X86_INTERNODE_CACHE_SHIFT=5 -CONFIG_X86_CMPXCHG=y -CONFIG_X86_L1_CACHE_SHIFT=5 -CONFIG_X86_XADD=y -CONFIG_X86_PPRO_FENCE=y -CONFIG_X86_WP_WORKS_OK=y -CONFIG_X86_INVLPG=y -CONFIG_X86_BSWAP=y -CONFIG_X86_POPAD_OK=y -CONFIG_X86_USE_PPRO_CHECKSUM=y -CONFIG_X86_TSC=y -CONFIG_X86_CMPXCHG64=y -CONFIG_X86_CMOV=y -CONFIG_X86_MINIMUM_CPU_FAMILY=5 -CONFIG_CPU_SUP_INTEL=y -CONFIG_CPU_SUP_CYRIX_32=y -CONFIG_CPU_SUP_AMD=y -CONFIG_CPU_SUP_CENTAUR=y -CONFIG_CPU_SUP_TRANSMETA_32=y -CONFIG_CPU_SUP_UMC_32=y -CONFIG_UML_X86=y -# CONFIG_64BIT is not set -CONFIG_X86_32=y -# CONFIG_X86_64 is not set -# CONFIG_RWSEM_XCHGADD_ALGORITHM is not set -CONFIG_RWSEM_GENERIC_SPINLOCK=y -# CONFIG_3_LEVEL_PGTABLES is not set -CONFIG_ARCH_HAS_SC_SIGNALS=y -CONFIG_ARCH_REUSE_HOST_VSYSCALL_AREA=y -CONFIG_GENERIC_HWEIGHT=y -# CONFIG_STATIC_LINK is not set -CONFIG_SELECT_MEMORY_MODEL=y -CONFIG_FLATMEM_MANUAL=y -CONFIG_FLATMEM=y -CONFIG_FLAT_NODE_MEM_MAP=y -CONFIG_PAGEFLAGS_EXTENDED=y -CONFIG_SPLIT_PTLOCK_CPUS=4 -# CONFIG_COMPACTION is not set -# CONFIG_PHYS_ADDR_T_64BIT is not set -CONFIG_ZONE_DMA_FLAG=0 -CONFIG_VIRT_TO_BUS=y -# CONFIG_KSM is not set -CONFIG_DEFAULT_MMAP_MIN_ADDR=4096 -CONFIG_NEED_PER_CPU_KM=y -# CONFIG_CLEANCACHE is not set -CONFIG_TICK_ONESHOT=y -CONFIG_NO_HZ=y -CONFIG_HIGH_RES_TIMERS=y -CONFIG_GENERIC_CLOCKEVENTS_BUILD=y -CONFIG_LD_SCRIPT_DYN=y -CONFIG_BINFMT_ELF=y -CONFIG_CORE_DUMP_DEFAULT_ELF_HEADERS=y -CONFIG_HAVE_AOUT=y -# CONFIG_BINFMT_AOUT is not set -CONFIG_BINFMT_MISC=m -CONFIG_HOSTFS=y -# CONFIG_HPPFS is not set -CONFIG_MCONSOLE=y -CONFIG_MAGIC_SYSRQ=y -CONFIG_KERNEL_STACK_ORDER=0 -# CONFIG_MMAPPER is not set -CONFIG_NO_DMA=y - -# -# General setup -# -CONFIG_EXPERIMENTAL=y -CONFIG_BROKEN_ON_SMP=y -CONFIG_INIT_ENV_ARG_LIMIT=128 -CONFIG_CROSS_COMPILE="" -CONFIG_LOCALVERSION="" -CONFIG_LOCALVERSION_AUTO=y -CONFIG_DEFAULT_HOSTNAME="(none)" -CONFIG_SWAP=y -CONFIG_SYSVIPC=y -CONFIG_SYSVIPC_SYSCTL=y -CONFIG_POSIX_MQUEUE=y -CONFIG_POSIX_MQUEUE_SYSCTL=y -CONFIG_BSD_PROCESS_ACCT=y -# CONFIG_BSD_PROCESS_ACCT_V3 is not set -# CONFIG_FHANDLE is not set -# CONFIG_TASKSTATS is not set -# CONFIG_AUDIT is not set - -# -# IRQ subsystem -# -CONFIG_GENERIC_IRQ_SHOW=y - -# -# RCU Subsystem -# -CONFIG_TINY_RCU=y -# CONFIG_PREEMPT_RCU is not set -# CONFIG_RCU_TRACE is not set -# CONFIG_TREE_RCU_TRACE is not set -CONFIG_IKCONFIG=y -CONFIG_IKCONFIG_PROC=y -CONFIG_LOG_BUF_SHIFT=14 -CONFIG_CGROUPS=y -# CONFIG_CGROUP_DEBUG is not set -CONFIG_CGROUP_FREEZER=y -CONFIG_CGROUP_DEVICE=y -CONFIG_CPUSETS=y -CONFIG_PROC_PID_CPUSET=y -CONFIG_CGROUP_CPUACCT=y -CONFIG_RESOURCE_COUNTERS=y -CONFIG_CGROUP_MEMCG=y -CONFIG_CGROUP_MEMCG_SWAP=y -# CONFIG_CGROUP_MEMCG_SWAP_ENABLED is not set -# CONFIG_CGROUP_MEMCG_KMEM is not set -CONFIG_CGROUP_SCHED=y -CONFIG_FAIR_GROUP_SCHED=y -# CONFIG_CFS_BANDWIDTH is not set -# CONFIG_RT_GROUP_SCHED is not set -CONFIG_BLK_CGROUP=y -# CONFIG_DEBUG_BLK_CGROUP is not set -# CONFIG_CHECKPOINT_RESTORE is not set -CONFIG_NAMESPACES=y -CONFIG_UTS_NS=y -CONFIG_IPC_NS=y -# CONFIG_USER_NS is not set -# CONFIG_PID_NS is not set -CONFIG_NET_NS=y -# CONFIG_SCHED_AUTOGROUP is not set -CONFIG_MM_OWNER=y -CONFIG_SYSFS_DEPRECATED=y -# CONFIG_SYSFS_DEPRECATED_V2 is not set -# CONFIG_RELAY is not set -# CONFIG_BLK_DEV_INITRD is not set -CONFIG_CC_OPTIMIZE_FOR_SIZE=y -CONFIG_SYSCTL=y -CONFIG_ANON_INODES=y -# CONFIG_EXPERT is not set -CONFIG_UID16=y -# CONFIG_SYSCTL_SYSCALL is not set -CONFIG_KALLSYMS=y -# CONFIG_KALLSYMS_ALL is not set -CONFIG_HOTPLUG=y -CONFIG_PRINTK=y -CONFIG_BUG=y -CONFIG_ELF_CORE=y -CONFIG_BASE_FULL=y -CONFIG_FUTEX=y -CONFIG_EPOLL=y -CONFIG_SIGNALFD=y -CONFIG_TIMERFD=y -CONFIG_EVENTFD=y -CONFIG_SHMEM=y -CONFIG_AIO=y -# CONFIG_EMBEDDED is not set - -# -# Kernel Performance Events And Counters -# -CONFIG_VM_EVENT_COUNTERS=y -CONFIG_COMPAT_BRK=y -CONFIG_SLAB=y -# CONFIG_SLUB is not set -# CONFIG_PROFILING is not set - -# -# GCOV-based kernel profiling -# -# CONFIG_HAVE_GENERIC_DMA_COHERENT is not set -CONFIG_SLABINFO=y -CONFIG_RT_MUTEXES=y -CONFIG_BASE_SMALL=0 -CONFIG_MODULES=y -# CONFIG_MODULE_FORCE_LOAD is not set -CONFIG_MODULE_UNLOAD=y -# CONFIG_MODULE_FORCE_UNLOAD is not set -# CONFIG_MODVERSIONS is not set -# CONFIG_MODULE_SRCVERSION_ALL is not set -CONFIG_BLOCK=y -CONFIG_LBDAF=y -# CONFIG_BLK_DEV_BSG is not set -# CONFIG_BLK_DEV_BSGLIB is not set -# CONFIG_BLK_DEV_INTEGRITY is not set - -# -# Partition Types -# -# CONFIG_PARTITION_ADVANCED is not set -CONFIG_MSDOS_PARTITION=y - -# -# IO Schedulers -# -CONFIG_IOSCHED_NOOP=y -CONFIG_IOSCHED_DEADLINE=y -CONFIG_IOSCHED_CFQ=m -# CONFIG_CFQ_GROUP_IOSCHED is not set -CONFIG_DEFAULT_DEADLINE=y -# CONFIG_DEFAULT_CFQ is not set -# CONFIG_DEFAULT_NOOP is not set -CONFIG_DEFAULT_IOSCHED="deadline" -# CONFIG_INLINE_SPIN_TRYLOCK is not set -# CONFIG_INLINE_SPIN_TRYLOCK_BH is not set -# CONFIG_INLINE_SPIN_LOCK is not set -# CONFIG_INLINE_SPIN_LOCK_BH is not set -# CONFIG_INLINE_SPIN_LOCK_IRQ is not set -# CONFIG_INLINE_SPIN_LOCK_IRQSAVE is not set -CONFIG_INLINE_SPIN_UNLOCK=y -# CONFIG_INLINE_SPIN_UNLOCK_BH is not set -CONFIG_INLINE_SPIN_UNLOCK_IRQ=y -# CONFIG_INLINE_SPIN_UNLOCK_IRQRESTORE is not set -# CONFIG_INLINE_READ_TRYLOCK is not set -# CONFIG_INLINE_READ_LOCK is not set -# CONFIG_INLINE_READ_LOCK_BH is not set -# CONFIG_INLINE_READ_LOCK_IRQ is not set -# CONFIG_INLINE_READ_LOCK_IRQSAVE is not set -CONFIG_INLINE_READ_UNLOCK=y -# CONFIG_INLINE_READ_UNLOCK_BH is not set -CONFIG_INLINE_READ_UNLOCK_IRQ=y -# CONFIG_INLINE_READ_UNLOCK_IRQRESTORE is not set -# CONFIG_INLINE_WRITE_TRYLOCK is not set -# CONFIG_INLINE_WRITE_LOCK is not set -# CONFIG_INLINE_WRITE_LOCK_BH is not set -# CONFIG_INLINE_WRITE_LOCK_IRQ is not set -# CONFIG_INLINE_WRITE_LOCK_IRQSAVE is not set -CONFIG_INLINE_WRITE_UNLOCK=y -# CONFIG_INLINE_WRITE_UNLOCK_BH is not set -CONFIG_INLINE_WRITE_UNLOCK_IRQ=y -# CONFIG_INLINE_WRITE_UNLOCK_IRQRESTORE is not set -# CONFIG_MUTEX_SPIN_ON_OWNER is not set -CONFIG_FREEZER=y - -# -# UML Character Devices -# -CONFIG_STDERR_CONSOLE=y -CONFIG_STDIO_CONSOLE=y -CONFIG_SSL=y -CONFIG_NULL_CHAN=y -CONFIG_PORT_CHAN=y -CONFIG_PTY_CHAN=y -CONFIG_TTY_CHAN=y -CONFIG_XTERM_CHAN=y -# CONFIG_NOCONFIG_CHAN is not set -CONFIG_CON_ZERO_CHAN="fd:0,fd:1" -CONFIG_CON_CHAN="xterm" -CONFIG_SSL_CHAN="pts" -CONFIG_UML_SOUND=m -CONFIG_SOUND=m -CONFIG_SOUND_OSS_CORE=y -CONFIG_HOSTAUDIO=m - -# -# Device Drivers -# - -# -# Generic Driver Options -# -CONFIG_UEVENT_HELPER_PATH="/sbin/hotplug" -CONFIG_DEVTMPFS=y -CONFIG_DEVTMPFS_MOUNT=y -CONFIG_STANDALONE=y -CONFIG_PREVENT_FIRMWARE_BUILD=y -CONFIG_FW_LOADER=y -CONFIG_FIRMWARE_IN_KERNEL=y -CONFIG_EXTRA_FIRMWARE="" -# CONFIG_DEBUG_DRIVER is not set -# CONFIG_DEBUG_DEVRES is not set -# CONFIG_SYS_HYPERVISOR is not set -CONFIG_GENERIC_CPU_DEVICES=y -# CONFIG_DMA_SHARED_BUFFER is not set -# CONFIG_CONNECTOR is not set -# CONFIG_MTD is not set -CONFIG_BLK_DEV=y -CONFIG_BLK_DEV_UBD=y -# CONFIG_BLK_DEV_UBD_SYNC is not set -CONFIG_BLK_DEV_COW_COMMON=y -CONFIG_BLK_DEV_LOOP=m -CONFIG_BLK_DEV_LOOP_MIN_COUNT=8 -# CONFIG_BLK_DEV_CRYPTOLOOP is not set - -# -# DRBD disabled because PROC_FS, INET or CONNECTOR not selected -# -CONFIG_BLK_DEV_NBD=m -# CONFIG_BLK_DEV_RAM is not set -# CONFIG_ATA_OVER_ETH is not set -# CONFIG_BLK_DEV_RBD is not set - -# -# Misc devices -# -# CONFIG_ENCLOSURE_SERVICES is not set -# CONFIG_C2PORT is not set - -# -# EEPROM support -# -# CONFIG_EEPROM_93CX6 is not set - -# -# Texas Instruments shared transport line discipline -# - -# -# Altera FPGA firmware download module -# - -# -# SCSI device support -# -CONFIG_SCSI_MOD=y -# CONFIG_RAID_ATTRS is not set -# CONFIG_SCSI is not set -# CONFIG_SCSI_DMA is not set -# CONFIG_SCSI_NETLINK is not set -# CONFIG_MD is not set -CONFIG_NETDEVICES=y -CONFIG_NET_CORE=y -# CONFIG_BONDING is not set -CONFIG_DUMMY=m -# CONFIG_EQUALIZER is not set -# CONFIG_MII is not set -# CONFIG_NET_TEAM is not set -# CONFIG_MACVLAN is not set -# CONFIG_NETCONSOLE is not set -# CONFIG_NETPOLL is not set -# CONFIG_NET_POLL_CONTROLLER is not set -CONFIG_TUN=m -# CONFIG_VETH is not set - -# -# CAIF transport drivers -# -CONFIG_ETHERNET=y -CONFIG_NET_VENDOR_CHELSIO=y -CONFIG_NET_VENDOR_INTEL=y -CONFIG_NET_VENDOR_I825XX=y -CONFIG_NET_VENDOR_MARVELL=y -CONFIG_NET_VENDOR_NATSEMI=y -CONFIG_NET_VENDOR_8390=y -# CONFIG_PHYLIB is not set -CONFIG_PPP=m -# CONFIG_PPP_BSDCOMP is not set -# CONFIG_PPP_DEFLATE is not set -# CONFIG_PPP_FILTER is not set -# CONFIG_PPP_MPPE is not set -# CONFIG_PPP_MULTILINK is not set -# CONFIG_PPPOE is not set -# CONFIG_PPP_ASYNC is not set -# CONFIG_PPP_SYNC_TTY is not set -CONFIG_SLIP=m -CONFIG_SLHC=m -# CONFIG_SLIP_COMPRESSED is not set -# CONFIG_SLIP_SMART is not set -# CONFIG_SLIP_MODE_SLIP6 is not set -CONFIG_WLAN=y -# CONFIG_HOSTAP is not set - -# -# Enable WiMAX (Networking options) to see the WiMAX drivers -# -# CONFIG_WAN is not set - -# -# Character devices -# -CONFIG_UNIX98_PTYS=y -# CONFIG_DEVPTS_MULTIPLE_INSTANCES is not set -CONFIG_LEGACY_PTYS=y -CONFIG_LEGACY_PTY_COUNT=32 -# CONFIG_N_GSM is not set -# CONFIG_TRACE_SINK is not set -CONFIG_DEVKMEM=y -# CONFIG_HW_RANDOM is not set -CONFIG_UML_RANDOM=y -# CONFIG_R3964 is not set -# CONFIG_NSC_GPIO is not set -# CONFIG_RAW_DRIVER is not set - -# -# PPS support -# -# CONFIG_PPS is not set - -# -# PPS generators support -# - -# -# PTP clock support -# - -# -# Enable Device Drivers -> PPS to see the PTP clock options. -# -# CONFIG_POWER_SUPPLY is not set -# CONFIG_THERMAL is not set -# CONFIG_WATCHDOG is not set -# CONFIG_REGULATOR is not set -CONFIG_SOUND_OSS_CORE_PRECLAIM=y -# CONFIG_MEMSTICK is not set -# CONFIG_NEW_LEDS is not set -# CONFIG_ACCESSIBILITY is not set -# CONFIG_AUXDISPLAY is not set -# CONFIG_UIO is not set - -# -# Virtio drivers -# -# CONFIG_VIRTIO_BALLOON is not set - -# -# Microsoft Hyper-V guest support -# -# CONFIG_STAGING is not set - -# -# Hardware Spinlock drivers -# -CONFIG_IOMMU_SUPPORT=y -# CONFIG_VIRT_DRIVERS is not set -# CONFIG_PM_DEVFREQ is not set -CONFIG_NET=y - -# -# Networking options -# -CONFIG_PACKET=y -CONFIG_UNIX=y -# CONFIG_UNIX_DIAG is not set -CONFIG_XFRM=y -# CONFIG_XFRM_USER is not set -# CONFIG_XFRM_SUB_POLICY is not set -# CONFIG_XFRM_MIGRATE is not set -# CONFIG_XFRM_STATISTICS is not set -# CONFIG_NET_KEY is not set -CONFIG_INET=y -# CONFIG_IP_MULTICAST is not set -# CONFIG_IP_ADVANCED_ROUTER is not set -# CONFIG_IP_PNP is not set -# CONFIG_NET_IPIP is not set -# CONFIG_NET_IPGRE_DEMUX is not set -# CONFIG_ARPD is not set -# CONFIG_SYN_COOKIES is not set -# CONFIG_INET_AH is not set -# CONFIG_INET_ESP is not set -# CONFIG_INET_IPCOMP is not set -# CONFIG_INET_XFRM_TUNNEL is not set -# CONFIG_INET_TUNNEL is not set -CONFIG_INET_XFRM_MODE_TRANSPORT=y -CONFIG_INET_XFRM_MODE_TUNNEL=y -CONFIG_INET_XFRM_MODE_BEET=y -# CONFIG_INET_LRO is not set -CONFIG_INET_DIAG=y -CONFIG_INET_TCP_DIAG=y -# CONFIG_INET_UDP_DIAG is not set -# CONFIG_TCP_CONG_ADVANCED is not set -CONFIG_TCP_CONG_CUBIC=y -CONFIG_DEFAULT_TCP_CONG="cubic" -# CONFIG_TCP_MD5SIG is not set -# CONFIG_IPV6 is not set -# CONFIG_NETWORK_SECMARK is not set -# CONFIG_NETWORK_PHY_TIMESTAMPING is not set -# CONFIG_NETFILTER is not set -# CONFIG_IP_DCCP is not set -# CONFIG_IP_SCTP is not set -# CONFIG_RDS is not set -# CONFIG_TIPC is not set -# CONFIG_ATM is not set -# CONFIG_L2TP is not set -# CONFIG_BRIDGE is not set -# CONFIG_NET_DSA is not set -# CONFIG_VLAN_8021Q is not set -# CONFIG_DECNET is not set -# CONFIG_LLC2 is not set -# CONFIG_IPX is not set -# CONFIG_ATALK is not set -# CONFIG_X25 is not set -# CONFIG_LAPB is not set -# CONFIG_ECONET is not set -# CONFIG_WAN_ROUTER is not set -# CONFIG_PHONET is not set -# CONFIG_IEEE802154 is not set -# CONFIG_NET_SCHED is not set -# CONFIG_DCB is not set -# CONFIG_BATMAN_ADV is not set -# CONFIG_OPENVSWITCH is not set -# CONFIG_NETPRIO_CGROUP is not set -CONFIG_BQL=y - -# -# Network testing -# -# CONFIG_NET_PKTGEN is not set -# CONFIG_HAMRADIO is not set -# CONFIG_CAN is not set -# CONFIG_IRDA is not set -# CONFIG_BT is not set -# CONFIG_AF_RXRPC is not set -CONFIG_WIRELESS=y -# CONFIG_CFG80211 is not set -# CONFIG_LIB80211 is not set - -# -# CFG80211 needs to be enabled for MAC80211 -# -# CONFIG_WIMAX is not set -# CONFIG_RFKILL is not set -# CONFIG_NET_9P is not set -# CONFIG_CAIF is not set -# CONFIG_CEPH_LIB is not set -# CONFIG_NFC is not set - -# -# UML Network Devices -# -CONFIG_UML_NET=y -CONFIG_UML_NET_ETHERTAP=y -CONFIG_UML_NET_TUNTAP=y -CONFIG_UML_NET_SLIP=y -CONFIG_UML_NET_DAEMON=y -# CONFIG_UML_NET_VDE is not set -CONFIG_UML_NET_MCAST=y -# CONFIG_UML_NET_PCAP is not set -CONFIG_UML_NET_SLIRP=y - -# -# File systems -# -# CONFIG_EXT2_FS is not set -# CONFIG_EXT3_FS is not set -CONFIG_EXT4_FS=y -CONFIG_EXT4_USE_FOR_EXT23=y -CONFIG_EXT4_FS_XATTR=y -# CONFIG_EXT4_FS_POSIX_ACL is not set -# CONFIG_EXT4_FS_SECURITY is not set -# CONFIG_EXT4_DEBUG is not set -CONFIG_JBD2=y -CONFIG_FS_MBCACHE=y -CONFIG_REISERFS_FS=y -# CONFIG_REISERFS_CHECK is not set -# CONFIG_REISERFS_PROC_INFO is not set -# CONFIG_REISERFS_FS_XATTR is not set -# CONFIG_JFS_FS is not set -# CONFIG_XFS_FS is not set -# CONFIG_GFS2_FS is not set -# CONFIG_BTRFS_FS is not set -# CONFIG_NILFS2_FS is not set -# CONFIG_FS_POSIX_ACL is not set -CONFIG_FILE_LOCKING=y -CONFIG_FSNOTIFY=y -CONFIG_DNOTIFY=y -CONFIG_INOTIFY_USER=y -# CONFIG_FANOTIFY is not set -CONFIG_QUOTA=y -# CONFIG_QUOTA_NETLINK_INTERFACE is not set -CONFIG_PRINT_QUOTA_WARNING=y -# CONFIG_QUOTA_DEBUG is not set -# CONFIG_QFMT_V1 is not set -# CONFIG_QFMT_V2 is not set -CONFIG_QUOTACTL=y -CONFIG_AUTOFS4_FS=m -# CONFIG_FUSE_FS is not set - -# -# Caches -# -# CONFIG_FSCACHE is not set - -# -# CD-ROM/DVD Filesystems -# -CONFIG_ISO9660_FS=m -CONFIG_JOLIET=y -# CONFIG_ZISOFS is not set -# CONFIG_UDF_FS is not set - -# -# DOS/FAT/NT Filesystems -# -# CONFIG_MSDOS_FS is not set -# CONFIG_VFAT_FS is not set -# CONFIG_NTFS_FS is not set - -# -# Pseudo filesystems -# -CONFIG_PROC_FS=y -CONFIG_PROC_KCORE=y -CONFIG_PROC_SYSCTL=y -CONFIG_PROC_PAGE_MONITOR=y -CONFIG_SYSFS=y -CONFIG_TMPFS=y -# CONFIG_TMPFS_POSIX_ACL is not set -# CONFIG_TMPFS_XATTR is not set -# CONFIG_HUGETLB_PAGE is not set -# CONFIG_CONFIGFS_FS is not set -CONFIG_MISC_FILESYSTEMS=y -# CONFIG_ADFS_FS is not set -# CONFIG_AFFS_FS is not set -# CONFIG_HFS_FS is not set -# CONFIG_HFSPLUS_FS is not set -# CONFIG_BEFS_FS is not set -# CONFIG_BFS_FS is not set -# CONFIG_EFS_FS is not set -# CONFIG_LOGFS is not set -# CONFIG_CRAMFS is not set -# CONFIG_SQUASHFS is not set -# CONFIG_VXFS_FS is not set -# CONFIG_MINIX_FS is not set -# CONFIG_OMFS_FS is not set -# CONFIG_HPFS_FS is not set -# CONFIG_QNX4FS_FS is not set -# CONFIG_ROMFS_FS is not set -# CONFIG_PSTORE is not set -# CONFIG_SYSV_FS is not set -# CONFIG_UFS_FS is not set -CONFIG_NETWORK_FILESYSTEMS=y -# CONFIG_NFS_FS is not set -# CONFIG_NFSD is not set -# CONFIG_CEPH_FS is not set -# CONFIG_CIFS is not set -# CONFIG_NCP_FS is not set -# CONFIG_CODA_FS is not set -# CONFIG_AFS_FS is not set -CONFIG_NLS=y -CONFIG_NLS_DEFAULT="iso8859-1" -# CONFIG_NLS_CODEPAGE_437 is not set -# CONFIG_NLS_CODEPAGE_737 is not set -# CONFIG_NLS_CODEPAGE_775 is not set -# CONFIG_NLS_CODEPAGE_850 is not set -# CONFIG_NLS_CODEPAGE_852 is not set -# CONFIG_NLS_CODEPAGE_855 is not set -# CONFIG_NLS_CODEPAGE_857 is not set -# CONFIG_NLS_CODEPAGE_860 is not set -# CONFIG_NLS_CODEPAGE_861 is not set -# CONFIG_NLS_CODEPAGE_862 is not set -# CONFIG_NLS_CODEPAGE_863 is not set -# CONFIG_NLS_CODEPAGE_864 is not set -# CONFIG_NLS_CODEPAGE_865 is not set -# CONFIG_NLS_CODEPAGE_866 is not set -# CONFIG_NLS_CODEPAGE_869 is not set -# CONFIG_NLS_CODEPAGE_936 is not set -# CONFIG_NLS_CODEPAGE_950 is not set -# CONFIG_NLS_CODEPAGE_932 is not set -# CONFIG_NLS_CODEPAGE_949 is not set -# CONFIG_NLS_CODEPAGE_874 is not set -# CONFIG_NLS_ISO8859_8 is not set -# CONFIG_NLS_CODEPAGE_1250 is not set -# CONFIG_NLS_CODEPAGE_1251 is not set -# CONFIG_NLS_ASCII is not set -# CONFIG_NLS_ISO8859_1 is not set -# CONFIG_NLS_ISO8859_2 is not set -# CONFIG_NLS_ISO8859_3 is not set -# CONFIG_NLS_ISO8859_4 is not set -# CONFIG_NLS_ISO8859_5 is not set -# CONFIG_NLS_ISO8859_6 is not set -# CONFIG_NLS_ISO8859_7 is not set -# CONFIG_NLS_ISO8859_9 is not set -# CONFIG_NLS_ISO8859_13 is not set -# CONFIG_NLS_ISO8859_14 is not set -# CONFIG_NLS_ISO8859_15 is not set -# CONFIG_NLS_KOI8_R is not set -# CONFIG_NLS_KOI8_U is not set -# CONFIG_NLS_UTF8 is not set - -# -# Security options -# -# CONFIG_KEYS is not set -# CONFIG_SECURITY_DMESG_RESTRICT is not set -# CONFIG_SECURITY is not set -# CONFIG_SECURITYFS is not set -CONFIG_DEFAULT_SECURITY_DAC=y -CONFIG_DEFAULT_SECURITY="" -CONFIG_CRYPTO=y - -# -# Crypto core or helper -# -# CONFIG_CRYPTO_FIPS is not set -CONFIG_CRYPTO_ALGAPI=m -CONFIG_CRYPTO_ALGAPI2=m -CONFIG_CRYPTO_RNG=m -CONFIG_CRYPTO_RNG2=m -# CONFIG_CRYPTO_MANAGER is not set -# CONFIG_CRYPTO_MANAGER2 is not set -# CONFIG_CRYPTO_USER is not set -# CONFIG_CRYPTO_GF128MUL is not set -# CONFIG_CRYPTO_NULL is not set -# CONFIG_CRYPTO_CRYPTD is not set -# CONFIG_CRYPTO_AUTHENC is not set -# CONFIG_CRYPTO_TEST is not set - -# -# Authenticated Encryption with Associated Data -# -# CONFIG_CRYPTO_CCM is not set -# CONFIG_CRYPTO_GCM is not set -# CONFIG_CRYPTO_SEQIV is not set - -# -# Block modes -# -# CONFIG_CRYPTO_CBC is not set -# CONFIG_CRYPTO_CTR is not set -# CONFIG_CRYPTO_CTS is not set -# CONFIG_CRYPTO_ECB is not set -# CONFIG_CRYPTO_LRW is not set -# CONFIG_CRYPTO_PCBC is not set -# CONFIG_CRYPTO_XTS is not set - -# -# Hash modes -# -# CONFIG_CRYPTO_HMAC is not set -# CONFIG_CRYPTO_XCBC is not set -# CONFIG_CRYPTO_VMAC is not set - -# -# Digest -# -# CONFIG_CRYPTO_CRC32C is not set -# CONFIG_CRYPTO_GHASH is not set -# CONFIG_CRYPTO_MD4 is not set -# CONFIG_CRYPTO_MD5 is not set -# CONFIG_CRYPTO_MICHAEL_MIC is not set -# CONFIG_CRYPTO_RMD128 is not set -# CONFIG_CRYPTO_RMD160 is not set -# CONFIG_CRYPTO_RMD256 is not set -# CONFIG_CRYPTO_RMD320 is not set -# CONFIG_CRYPTO_SHA1 is not set -# CONFIG_CRYPTO_SHA256 is not set -# CONFIG_CRYPTO_SHA512 is not set -# CONFIG_CRYPTO_TGR192 is not set -# CONFIG_CRYPTO_WP512 is not set - -# -# Ciphers -# -CONFIG_CRYPTO_AES=m -# CONFIG_CRYPTO_AES_586 is not set -# CONFIG_CRYPTO_ANUBIS is not set -# CONFIG_CRYPTO_ARC4 is not set -# CONFIG_CRYPTO_BLOWFISH is not set -# CONFIG_CRYPTO_CAMELLIA is not set -# CONFIG_CRYPTO_CAST5 is not set -# CONFIG_CRYPTO_CAST6 is not set -# CONFIG_CRYPTO_DES is not set -# CONFIG_CRYPTO_FCRYPT is not set -# CONFIG_CRYPTO_KHAZAD is not set -# CONFIG_CRYPTO_SALSA20 is not set -# CONFIG_CRYPTO_SALSA20_586 is not set -# CONFIG_CRYPTO_SEED is not set -# CONFIG_CRYPTO_SERPENT is not set -# CONFIG_CRYPTO_TEA is not set -# CONFIG_CRYPTO_TWOFISH is not set -# CONFIG_CRYPTO_TWOFISH_586 is not set - -# -# Compression -# -# CONFIG_CRYPTO_DEFLATE is not set -# CONFIG_CRYPTO_ZLIB is not set -# CONFIG_CRYPTO_LZO is not set - -# -# Random Number Generation -# -CONFIG_CRYPTO_ANSI_CPRNG=m -# CONFIG_CRYPTO_USER_API_HASH is not set -# CONFIG_CRYPTO_USER_API_SKCIPHER is not set -CONFIG_CRYPTO_HW=y -# CONFIG_BINARY_PRINTF is not set - -# -# Library routines -# -CONFIG_BITREVERSE=y -CONFIG_GENERIC_FIND_FIRST_BIT=y -CONFIG_GENERIC_IO=y -# CONFIG_CRC_CCITT is not set -CONFIG_CRC16=y -# CONFIG_CRC_T10DIF is not set -# CONFIG_CRC_ITU_T is not set -CONFIG_CRC32=y -# CONFIG_CRC7 is not set -# CONFIG_LIBCRC32C is not set -# CONFIG_CRC8 is not set -# CONFIG_XZ_DEC is not set -# CONFIG_XZ_DEC_BCJ is not set -CONFIG_DQL=y -CONFIG_NLATTR=y -# CONFIG_AVERAGE is not set -# CONFIG_CORDIC is not set - -# -# Kernel hacking -# -# CONFIG_PRINTK_TIME is not set -CONFIG_DEFAULT_MESSAGE_LOGLEVEL=4 -CONFIG_ENABLE_WARN_DEPRECATED=y -CONFIG_ENABLE_MUST_CHECK=y -CONFIG_FRAME_WARN=1024 -# CONFIG_STRIP_ASM_SYMS is not set -# CONFIG_UNUSED_SYMBOLS is not set -# CONFIG_DEBUG_FS is not set -# CONFIG_DEBUG_SECTION_MISMATCH is not set -CONFIG_DEBUG_KERNEL=y -# CONFIG_DEBUG_SHIRQ is not set -# CONFIG_LOCKUP_DETECTOR is not set -# CONFIG_HARDLOCKUP_DETECTOR is not set -# CONFIG_DETECT_HUNG_TASK is not set -CONFIG_SCHED_DEBUG=y -# CONFIG_SCHEDSTATS is not set -# CONFIG_TIMER_STATS is not set -# CONFIG_DEBUG_OBJECTS is not set -# CONFIG_DEBUG_SLAB is not set -# CONFIG_DEBUG_RT_MUTEXES is not set -# CONFIG_RT_MUTEX_TESTER is not set -# CONFIG_DEBUG_SPINLOCK is not set -# CONFIG_DEBUG_MUTEXES is not set -# CONFIG_SPARSE_RCU_POINTER is not set -# CONFIG_DEBUG_ATOMIC_SLEEP is not set -# CONFIG_DEBUG_LOCKING_API_SELFTESTS is not set -# CONFIG_DEBUG_STACK_USAGE is not set -# CONFIG_DEBUG_KOBJECT is not set -CONFIG_DEBUG_BUGVERBOSE=y -CONFIG_DEBUG_INFO=y -# CONFIG_DEBUG_INFO_REDUCED is not set -# CONFIG_DEBUG_VM is not set -# CONFIG_DEBUG_WRITECOUNT is not set -CONFIG_DEBUG_MEMORY_INIT=y -# CONFIG_DEBUG_LIST is not set -# CONFIG_TEST_LIST_SORT is not set -# CONFIG_DEBUG_SG is not set -# CONFIG_DEBUG_NOTIFIERS is not set -# CONFIG_DEBUG_CREDENTIALS is not set -CONFIG_FRAME_POINTER=y -# CONFIG_BOOT_PRINTK_DELAY is not set -# CONFIG_RCU_TORTURE_TEST is not set -# CONFIG_BACKTRACE_SELF_TEST is not set -# CONFIG_DEBUG_BLOCK_EXT_DEVT is not set -# CONFIG_DEBUG_FORCE_WEAK_PER_CPU is not set -# CONFIG_FAULT_INJECTION is not set -# CONFIG_SYSCTL_SYSCALL_CHECK is not set -# CONFIG_DEBUG_PAGEALLOC is not set -# CONFIG_ATOMIC64_SELFTEST is not set -# CONFIG_SAMPLES is not set -# CONFIG_TEST_KSTRTOX is not set -# CONFIG_GPROF is not set -# CONFIG_GCOV is not set -CONFIG_EARLY_PRINTK=y diff --git a/arch/um/drivers/mconsole_kern.c b/arch/um/drivers/mconsole_kern.c index 3df3bd544492..29880c9b324e 100644 --- a/arch/um/drivers/mconsole_kern.c +++ b/arch/um/drivers/mconsole_kern.c @@ -645,11 +645,9 @@ void mconsole_sysrq(struct mc_request *req) static void stack_proc(void *arg) { - struct task_struct *from = current, *to = arg; + struct task_struct *task = arg; - to->thread.saved_task = from; - rcu_user_hooks_switch(from, to); - switch_to(from, to, from); + show_stack(task, NULL); } /* diff --git a/arch/um/include/asm/processor-generic.h b/arch/um/include/asm/processor-generic.h index c03cd5a02364..d89b02bb6262 100644 --- a/arch/um/include/asm/processor-generic.h +++ b/arch/um/include/asm/processor-generic.h @@ -19,8 +19,8 @@ struct task_struct; struct mm_struct; struct thread_struct { - struct task_struct *saved_task; struct pt_regs regs; + struct pt_regs *segv_regs; int singlestep_syscall; void *fault_addr; jmp_buf *fault_catcher; diff --git a/arch/um/include/asm/thread_info.h b/arch/um/include/asm/thread_info.h index 2c8eeb2df8b4..1c5b2a83046a 100644 --- a/arch/um/include/asm/thread_info.h +++ b/arch/um/include/asm/thread_info.h @@ -60,8 +60,6 @@ static inline struct thread_info *current_thread_info(void) #endif -#define PREEMPT_ACTIVE 0x10000000 - #define TIF_SYSCALL_TRACE 0 /* syscall trace active */ #define TIF_SIGPENDING 1 /* signal pending */ #define TIF_NEED_RESCHED 2 /* rescheduling necessary */ diff --git a/arch/um/include/shared/as-layout.h b/arch/um/include/shared/as-layout.h index 694c792bab4e..41c8c774ec10 100644 --- a/arch/um/include/shared/as-layout.h +++ b/arch/um/include/shared/as-layout.h @@ -44,7 +44,6 @@ struct cpu_task { extern struct cpu_task cpu_tasks[]; -extern unsigned long low_physmem; extern unsigned long high_physmem; extern unsigned long uml_physmem; extern unsigned long uml_reserved; @@ -52,8 +51,6 @@ extern unsigned long end_vm; extern unsigned long start_vm; extern unsigned long long highmem; -extern unsigned long _stext, _etext, _sdata, _edata, __bss_start, _end; -extern unsigned long _unprotected_end; extern unsigned long brk_start; extern unsigned long host_task_size; diff --git a/arch/um/include/shared/os.h b/arch/um/include/shared/os.h index 021104d98cb3..75298d3358e7 100644 --- a/arch/um/include/shared/os.h +++ b/arch/um/include/shared/os.h @@ -227,6 +227,7 @@ extern void block_signals(void); extern void unblock_signals(void); extern int get_signals(void); extern int set_signals(int enable); +extern int os_is_signal_stack(void); /* util.c */ extern void stack_protections(unsigned long address); diff --git a/arch/um/kernel/mem.c b/arch/um/kernel/mem.c index 7ddb64baf327..8636e905426f 100644 --- a/arch/um/kernel/mem.c +++ b/arch/um/kernel/mem.c @@ -279,8 +279,12 @@ pgtable_t pte_alloc_one(struct mm_struct *mm, unsigned long address) struct page *pte; pte = alloc_page(GFP_KERNEL|__GFP_REPEAT|__GFP_ZERO); - if (pte) - pgtable_page_ctor(pte); + if (!pte) + return NULL; + if (!pgtable_page_ctor(pte)) { + __free_page(pte); + return NULL; + } return pte; } diff --git a/arch/um/kernel/process.c b/arch/um/kernel/process.c index bbcef522bcb1..eecc4142764c 100644 --- a/arch/um/kernel/process.c +++ b/arch/um/kernel/process.c @@ -82,19 +82,8 @@ void *__switch_to(struct task_struct *from, struct task_struct *to) to->thread.prev_sched = from; set_current(to); - do { - current->thread.saved_task = NULL; - - switch_threads(&from->thread.switch_buf, - &to->thread.switch_buf); - - arch_switch_to(current); - - if (current->thread.saved_task) - show_regs(&(current->thread.regs)); - to = current->thread.saved_task; - from = current; - } while (current->thread.saved_task); + switch_threads(&from->thread.switch_buf, &to->thread.switch_buf); + arch_switch_to(current); return current->thread.prev_sched; } diff --git a/arch/um/kernel/sysrq.c b/arch/um/kernel/sysrq.c index 0dc4d1c6f98a..4d6fdf68edf3 100644 --- a/arch/um/kernel/sysrq.c +++ b/arch/um/kernel/sysrq.c @@ -1,6 +1,10 @@ /* * Copyright (C) 2001 - 2007 Jeff Dike (jdike@{addtoit,linux.intel}.com) - * Licensed under the GPL + * Copyright (C) 2013 Richard Weinberger <richrd@nod.at> + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. */ #include <linux/kallsyms.h> @@ -8,59 +12,87 @@ #include <linux/module.h> #include <linux/sched.h> #include <asm/sysrq.h> +#include <os.h> -/* Catch non-i386 SUBARCH's. */ -#if !defined(CONFIG_UML_X86) || defined(CONFIG_64BIT) -void show_trace(struct task_struct *task, unsigned long * stack) +struct stack_frame { + struct stack_frame *next_frame; + unsigned long return_address; +}; + +static void print_stack_trace(unsigned long *sp, unsigned long bp) { + int reliable; unsigned long addr; + struct stack_frame *frame = (struct stack_frame *)bp; - if (!stack) { - stack = (unsigned long*) &stack; - WARN_ON(1); - } - - printk(KERN_INFO "Call Trace: \n"); - while (((long) stack & (THREAD_SIZE-1)) != 0) { - addr = *stack; + printk(KERN_INFO "Call Trace:\n"); + while (((long) sp & (THREAD_SIZE-1)) != 0) { + addr = *sp; if (__kernel_text_address(addr)) { - printk(KERN_INFO "%08lx: [<%08lx>]", - (unsigned long) stack, addr); - print_symbol(KERN_CONT " %s", addr); + reliable = 0; + if ((unsigned long) sp == bp + sizeof(long)) { + frame = frame ? frame->next_frame : NULL; + bp = (unsigned long)frame; + reliable = 1; + } + + printk(KERN_INFO " [<%08lx>]", addr); + printk(KERN_CONT " %s", reliable ? "" : "? "); + print_symbol(KERN_CONT "%s", addr); printk(KERN_CONT "\n"); } - stack++; + sp++; } printk(KERN_INFO "\n"); } -#endif -/*Stolen from arch/i386/kernel/traps.c */ -static const int kstack_depth_to_print = 24; +static unsigned long get_frame_pointer(struct task_struct *task, + struct pt_regs *segv_regs) +{ + if (!task || task == current) + return segv_regs ? PT_REGS_BP(segv_regs) : current_bp(); + else + return KSTK_EBP(task); +} -/* This recently started being used in arch-independent code too, as in - * kernel/sched/core.c.*/ -void show_stack(struct task_struct *task, unsigned long *esp) +static unsigned long *get_stack_pointer(struct task_struct *task, + struct pt_regs *segv_regs) { - unsigned long *stack; + if (!task || task == current) + return segv_regs ? (unsigned long *)PT_REGS_SP(segv_regs) : current_sp(); + else + return (unsigned long *)KSTK_ESP(task); +} + +void show_stack(struct task_struct *task, unsigned long *stack) +{ + unsigned long *sp = stack, bp = 0; + struct pt_regs *segv_regs = current->thread.segv_regs; int i; - if (esp == NULL) { - if (task != current && task != NULL) { - esp = (unsigned long *) KSTK_ESP(task); - } else { - esp = (unsigned long *) &esp; - } + if (!segv_regs && os_is_signal_stack()) { + printk(KERN_ERR "Received SIGSEGV in SIGSEGV handler," + " aborting stack trace!\n"); + return; } - stack = esp; - for (i = 0; i < kstack_depth_to_print; i++) { +#ifdef CONFIG_FRAME_POINTER + bp = get_frame_pointer(task, segv_regs); +#endif + + if (!stack) + sp = get_stack_pointer(task, segv_regs); + + printk(KERN_INFO "Stack:\n"); + stack = sp; + for (i = 0; i < 3 * STACKSLOTS_PER_LINE; i++) { if (kstack_end(stack)) break; - if (i && ((i % 8) == 0)) - printk(KERN_INFO " "); - printk(KERN_CONT "%08lx ", *stack++); + if (i && ((i % STACKSLOTS_PER_LINE) == 0)) + printk(KERN_CONT "\n"); + printk(KERN_CONT " %08lx", *stack++); } + printk(KERN_CONT "\n"); - show_trace(task, esp); + print_stack_trace(sp, bp); } diff --git a/arch/um/kernel/trap.c b/arch/um/kernel/trap.c index 5c3aef74237f..974b87474a99 100644 --- a/arch/um/kernel/trap.c +++ b/arch/um/kernel/trap.c @@ -206,9 +206,12 @@ unsigned long segv(struct faultinfo fi, unsigned long ip, int is_user, int is_write = FAULT_WRITE(fi); unsigned long address = FAULT_ADDRESS(fi); + if (regs) + current->thread.segv_regs = container_of(regs, struct pt_regs, regs); + if (!is_user && (address >= start_vm) && (address < end_vm)) { flush_tlb_kernel_vm(); - return 0; + goto out; } else if (current->mm == NULL) { show_regs(container_of(regs, struct pt_regs, regs)); @@ -230,7 +233,7 @@ unsigned long segv(struct faultinfo fi, unsigned long ip, int is_user, catcher = current->thread.fault_catcher; if (!err) - return 0; + goto out; else if (catcher != NULL) { current->thread.fault_addr = (void *) address; UML_LONGJMP(catcher, 1); @@ -238,7 +241,7 @@ unsigned long segv(struct faultinfo fi, unsigned long ip, int is_user, else if (current->thread.fault_addr != NULL) panic("fault_addr set but no fault catcher"); else if (!is_user && arch_fixup(ip, regs)) - return 0; + goto out; if (!is_user) { show_regs(container_of(regs, struct pt_regs, regs)); @@ -262,6 +265,11 @@ unsigned long segv(struct faultinfo fi, unsigned long ip, int is_user, current->thread.arch.faultinfo = fi; force_sig_info(SIGSEGV, &si, current); } + +out: + if (regs) + current->thread.segv_regs = NULL; + return 0; } diff --git a/arch/um/kernel/um_arch.c b/arch/um/kernel/um_arch.c index 87df5e3acc26..016adf0985d5 100644 --- a/arch/um/kernel/um_arch.c +++ b/arch/um/kernel/um_arch.c @@ -13,6 +13,7 @@ #include <linux/sched.h> #include <asm/pgtable.h> #include <asm/processor.h> +#include <asm/sections.h> #include <asm/setup.h> #include <as-layout.h> #include <arch.h> @@ -234,7 +235,6 @@ static int panic_exit(struct notifier_block *self, unsigned long unused1, void *unused2) { bust_spinlocks(1); - show_regs(&(current->thread.regs)); bust_spinlocks(0); uml_exitcode = 1; os_dump_core(); diff --git a/arch/um/os-Linux/signal.c b/arch/um/os-Linux/signal.c index 905924b773d3..7b605e4dfffa 100644 --- a/arch/um/os-Linux/signal.c +++ b/arch/um/os-Linux/signal.c @@ -304,3 +304,11 @@ int set_signals(int enable) return ret; } + +int os_is_signal_stack(void) +{ + stack_t ss; + sigaltstack(NULL, &ss); + + return ss.ss_flags & SS_ONSTACK; +} diff --git a/arch/unicore32/Kconfig b/arch/unicore32/Kconfig index 82cdd8906f3d..a7ba27b2752b 100644 --- a/arch/unicore32/Kconfig +++ b/arch/unicore32/Kconfig @@ -1,5 +1,6 @@ config UNICORE32 def_bool y + select ARCH_MIGHT_HAVE_PC_PARPORT select HAVE_MEMBLOCK select HAVE_GENERIC_DMA_COHERENT select HAVE_DMA_ATTRS diff --git a/arch/unicore32/include/asm/pgalloc.h b/arch/unicore32/include/asm/pgalloc.h index 0213e373a895..2e02d1356fdf 100644 --- a/arch/unicore32/include/asm/pgalloc.h +++ b/arch/unicore32/include/asm/pgalloc.h @@ -51,12 +51,14 @@ pte_alloc_one(struct mm_struct *mm, unsigned long addr) struct page *pte; pte = alloc_pages(PGALLOC_GFP, 0); - if (pte) { - if (!PageHighMem(pte)) { - void *page = page_address(pte); - clean_dcache_area(page, PTRS_PER_PTE * sizeof(pte_t)); - } - pgtable_page_ctor(pte); + if (!pte) + return NULL; + if (!PageHighMem(pte)) { + void *page = page_address(pte); + clean_dcache_area(page, PTRS_PER_PTE * sizeof(pte_t)); + } + if (!pgtable_page_ctor(pte)) { + __free_page(pte); } return pte; diff --git a/arch/unicore32/include/asm/thread_info.h b/arch/unicore32/include/asm/thread_info.h index 818b4a1edb5b..af36d8eabdf1 100644 --- a/arch/unicore32/include/asm/thread_info.h +++ b/arch/unicore32/include/asm/thread_info.h @@ -118,12 +118,6 @@ static inline struct thread_info *current_thread_info(void) #endif /* - * We use bit 30 of the preempt_count to indicate that kernel - * preemption is occurring. See <asm/hardirq.h>. - */ -#define PREEMPT_ACTIVE 0x40000000 - -/* * thread information flags: * TIF_SYSCALL_TRACE - syscall trace active * TIF_SIGPENDING - signal pending diff --git a/arch/unicore32/kernel/puv3-nb0916.c b/arch/unicore32/kernel/puv3-nb0916.c index 181108b8ecce..0c6618e71897 100644 --- a/arch/unicore32/kernel/puv3-nb0916.c +++ b/arch/unicore32/kernel/puv3-nb0916.c @@ -54,6 +54,7 @@ static struct platform_pwm_backlight_data nb0916_backlight_data = { .max_brightness = 100, .dft_brightness = 100, .pwm_period_ns = 70 * 1024, + .enable_gpio = -1, }; static struct gpio_keys_button nb0916_gpio_keys[] = { diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig index 725e1573ea85..e903c71f7e69 100644 --- a/arch/x86/Kconfig +++ b/arch/x86/Kconfig @@ -22,6 +22,7 @@ config X86_64 config X86 def_bool y select ARCH_HAS_DEBUG_STRICT_USER_COPY_CHECKS + select ARCH_MIGHT_HAVE_PC_PARPORT select HAVE_AOUT if X86_32 select HAVE_UNSTABLE_SCHED_CLOCK select ARCH_SUPPORTS_NUMA_BALANCING @@ -90,7 +91,6 @@ config X86 select GENERIC_IRQ_SHOW select GENERIC_CLOCKEVENTS_MIN_ADJUST select IRQ_FORCED_THREADING - select USE_GENERIC_SMP_HELPERS if SMP select HAVE_BPF_JIT if X86_64 select HAVE_ARCH_TRANSPARENT_HUGEPAGE select CLKEVT_I8253 @@ -255,10 +255,6 @@ config ARCH_HWEIGHT_CFLAGS default "-fcall-saved-ecx -fcall-saved-edx" if X86_32 default "-fcall-saved-rdi -fcall-saved-rsi -fcall-saved-rdx -fcall-saved-rcx -fcall-saved-r8 -fcall-saved-r9 -fcall-saved-r10 -fcall-saved-r11" if X86_64 -config ARCH_CPU_PROBE_RELEASE - def_bool y - depends on HOTPLUG_CPU - config ARCH_SUPPORTS_UPROBES def_bool y @@ -639,10 +635,10 @@ config PARAVIRT_SPINLOCKS spinlock implementation with something virtualization-friendly (for example, block the virtual CPU rather than spinning). - Unfortunately the downside is an up to 5% performance hit on - native kernels, with various workloads. + It has a minimal impact on native kernels and gives a nice performance + benefit on paravirtualized KVM / Xen kernels. - If you are unsure how to answer this question, answer N. + If you are unsure how to answer this question, answer Y. source "arch/x86/xen/Kconfig" @@ -1889,6 +1885,10 @@ config USE_PERCPU_NUMA_NODE_ID def_bool y depends on NUMA +config ARCH_ENABLE_SPLIT_PMD_PTLOCK + def_bool y + depends on X86_64 || X86_PAE + menu "Power management and ACPI options" config ARCH_HIBERNATION_HEADER diff --git a/arch/x86/include/asm/acpi.h b/arch/x86/include/asm/acpi.h index b1977bad5435..c8c1e700c26e 100644 --- a/arch/x86/include/asm/acpi.h +++ b/arch/x86/include/asm/acpi.h @@ -26,6 +26,7 @@ #include <acpi/pdc_intel.h> #include <asm/numa.h> +#include <asm/fixmap.h> #include <asm/processor.h> #include <asm/mmu.h> #include <asm/mpspec.h> diff --git a/arch/x86/include/asm/desc.h b/arch/x86/include/asm/desc.h index b90e5dfeee46..50d033a8947d 100644 --- a/arch/x86/include/asm/desc.h +++ b/arch/x86/include/asm/desc.h @@ -327,10 +327,25 @@ static inline void write_trace_idt_entry(int entry, const gate_desc *gate) { write_idt_entry(trace_idt_table, entry, gate); } + +static inline void _trace_set_gate(int gate, unsigned type, void *addr, + unsigned dpl, unsigned ist, unsigned seg) +{ + gate_desc s; + + pack_gate(&s, type, (unsigned long)addr, dpl, ist, seg); + /* + * does not need to be atomic because it is only done once at + * setup time + */ + write_trace_idt_entry(gate, &s); +} #else static inline void write_trace_idt_entry(int entry, const gate_desc *gate) { } + +#define _trace_set_gate(gate, type, addr, dpl, ist, seg) #endif static inline void _set_gate(int gate, unsigned type, void *addr, @@ -353,11 +368,14 @@ static inline void _set_gate(int gate, unsigned type, void *addr, * Pentium F0 0F bugfix can have resulted in the mapped * IDT being write-protected. */ -static inline void set_intr_gate(unsigned int n, void *addr) -{ - BUG_ON((unsigned)n > 0xFF); - _set_gate(n, GATE_INTERRUPT, addr, 0, 0, __KERNEL_CS); -} +#define set_intr_gate(n, addr) \ + do { \ + BUG_ON((unsigned)n > 0xFF); \ + _set_gate(n, GATE_INTERRUPT, (void *)addr, 0, 0, \ + __KERNEL_CS); \ + _trace_set_gate(n, GATE_INTERRUPT, (void *)trace_##addr,\ + 0, 0, __KERNEL_CS); \ + } while (0) extern int first_system_vector; /* used_vectors is BITMAP for irq is not managed by percpu vector_irq */ @@ -374,37 +392,10 @@ static inline void alloc_system_vector(int vector) } } -#ifdef CONFIG_TRACING -static inline void trace_set_intr_gate(unsigned int gate, void *addr) -{ - gate_desc s; - - pack_gate(&s, GATE_INTERRUPT, (unsigned long)addr, 0, 0, __KERNEL_CS); - write_idt_entry(trace_idt_table, gate, &s); -} - -static inline void __trace_alloc_intr_gate(unsigned int n, void *addr) -{ - trace_set_intr_gate(n, addr); -} -#else -static inline void trace_set_intr_gate(unsigned int gate, void *addr) -{ -} - -#define __trace_alloc_intr_gate(n, addr) -#endif - -static inline void __alloc_intr_gate(unsigned int n, void *addr) -{ - set_intr_gate(n, addr); -} - #define alloc_intr_gate(n, addr) \ do { \ alloc_system_vector(n); \ - __alloc_intr_gate(n, addr); \ - __trace_alloc_intr_gate(n, trace_##addr); \ + set_intr_gate(n, addr); \ } while (0) /* diff --git a/arch/x86/include/asm/hw_irq.h b/arch/x86/include/asm/hw_irq.h index 92b3bae08b74..cba45d99ac1a 100644 --- a/arch/x86/include/asm/hw_irq.h +++ b/arch/x86/include/asm/hw_irq.h @@ -187,6 +187,9 @@ extern __visible void smp_invalidate_interrupt(struct pt_regs *); #endif extern void (*__initconst interrupt[NR_VECTORS-FIRST_EXTERNAL_VECTOR])(void); +#ifdef CONFIG_TRACING +#define trace_interrupt interrupt +#endif typedef int vector_irq_t[NR_VECTORS]; DECLARE_PER_CPU(vector_irq_t, vector_irq); diff --git a/arch/x86/include/asm/kdebug.h b/arch/x86/include/asm/kdebug.h index 2c37aadcbc35..32ce71375b21 100644 --- a/arch/x86/include/asm/kdebug.h +++ b/arch/x86/include/asm/kdebug.h @@ -21,7 +21,7 @@ enum die_val { DIE_NMIUNKNOWN, }; -extern void printk_address(unsigned long address, int reliable); +extern void printk_address(unsigned long address); extern void die(const char *, struct pt_regs *,long); extern int __must_check __die(const char *, struct pt_regs *, long); extern void show_trace(struct task_struct *t, struct pt_regs *regs, diff --git a/arch/x86/include/asm/kvm_emulate.h b/arch/x86/include/asm/kvm_emulate.h index 15f960c06ff7..24ec1216596e 100644 --- a/arch/x86/include/asm/kvm_emulate.h +++ b/arch/x86/include/asm/kvm_emulate.h @@ -274,13 +274,17 @@ struct x86_emulate_ctxt { bool guest_mode; /* guest running a nested guest */ bool perm_ok; /* do not check permissions if true */ - bool only_vendor_specific_insn; + bool ud; /* inject an #UD if host doesn't support insn */ bool have_exception; struct x86_exception exception; - /* decode cache */ - u8 twobyte; + /* + * decode cache + */ + + /* current opcode length in bytes */ + u8 opcode_len; u8 b; u8 intercept; u8 lock_prefix; diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h index c76ff74a98f2..ae5d7830855c 100644 --- a/arch/x86/include/asm/kvm_host.h +++ b/arch/x86/include/asm/kvm_host.h @@ -79,6 +79,13 @@ #define KVM_HPAGE_MASK(x) (~(KVM_HPAGE_SIZE(x) - 1)) #define KVM_PAGES_PER_HPAGE(x) (KVM_HPAGE_SIZE(x) / PAGE_SIZE) +static inline gfn_t gfn_to_index(gfn_t gfn, gfn_t base_gfn, int level) +{ + /* KVM_HPAGE_GFN_SHIFT(PT_PAGE_TABLE_LEVEL) must be 0. */ + return (gfn >> KVM_HPAGE_GFN_SHIFT(level)) - + (base_gfn >> KVM_HPAGE_GFN_SHIFT(level)); +} + #define SELECTOR_TI_MASK (1 << 2) #define SELECTOR_RPL_MASK 0x03 @@ -253,7 +260,6 @@ struct kvm_pio_request { * mode. */ struct kvm_mmu { - void (*new_cr3)(struct kvm_vcpu *vcpu); void (*set_cr3)(struct kvm_vcpu *vcpu, unsigned long root); unsigned long (*get_cr3)(struct kvm_vcpu *vcpu); u64 (*get_pdptr)(struct kvm_vcpu *vcpu, int index); @@ -261,7 +267,6 @@ struct kvm_mmu { bool prefault); void (*inject_page_fault)(struct kvm_vcpu *vcpu, struct x86_exception *fault); - void (*free)(struct kvm_vcpu *vcpu); gpa_t (*gva_to_gpa)(struct kvm_vcpu *vcpu, gva_t gva, u32 access, struct x86_exception *exception); gpa_t (*translate_gpa)(struct kvm_vcpu *vcpu, gpa_t gpa, u32 access); @@ -389,6 +394,8 @@ struct kvm_vcpu_arch { struct fpu guest_fpu; u64 xcr0; + u64 guest_supported_xcr0; + u32 guest_xstate_size; struct kvm_pio_request pio; void *pio_data; @@ -557,7 +564,9 @@ struct kvm_arch { struct list_head assigned_dev_head; struct iommu_domain *iommu_domain; - int iommu_flags; + bool iommu_noncoherent; +#define __KVM_HAVE_ARCH_NONCOHERENT_DMA + atomic_t noncoherent_dma_count; struct kvm_pic *vpic; struct kvm_ioapic *vioapic; struct kvm_pit *vpit; @@ -780,11 +789,11 @@ void kvm_mmu_module_exit(void); void kvm_mmu_destroy(struct kvm_vcpu *vcpu); int kvm_mmu_create(struct kvm_vcpu *vcpu); -int kvm_mmu_setup(struct kvm_vcpu *vcpu); +void kvm_mmu_setup(struct kvm_vcpu *vcpu); void kvm_mmu_set_mask_ptes(u64 user_mask, u64 accessed_mask, u64 dirty_mask, u64 nx_mask, u64 x_mask); -int kvm_mmu_reset_context(struct kvm_vcpu *vcpu); +void kvm_mmu_reset_context(struct kvm_vcpu *vcpu); void kvm_mmu_slot_remove_write_access(struct kvm *kvm, int slot); void kvm_mmu_write_protect_pt_masked(struct kvm *kvm, struct kvm_memory_slot *slot, @@ -922,13 +931,11 @@ int kvm_emulate_hypercall(struct kvm_vcpu *vcpu); int kvm_mmu_page_fault(struct kvm_vcpu *vcpu, gva_t gva, u32 error_code, void *insn, int insn_len); void kvm_mmu_invlpg(struct kvm_vcpu *vcpu, gva_t gva); +void kvm_mmu_new_cr3(struct kvm_vcpu *vcpu); void kvm_enable_tdp(void); void kvm_disable_tdp(void); -int complete_pio(struct kvm_vcpu *vcpu); -bool kvm_check_iopl(struct kvm_vcpu *vcpu); - static inline gpa_t translate_gpa(struct kvm_vcpu *vcpu, gpa_t gpa, u32 access) { return gpa; diff --git a/arch/x86/include/asm/mpspec.h b/arch/x86/include/asm/mpspec.h index 626cf70082d7..3142a94c7b4b 100644 --- a/arch/x86/include/asm/mpspec.h +++ b/arch/x86/include/asm/mpspec.h @@ -94,7 +94,7 @@ static inline void early_reserve_e820_mpc_new(void) { } #define default_get_smp_config x86_init_uint_noop #endif -void generic_processor_info(int apicid, int version); +int generic_processor_info(int apicid, int version); #ifdef CONFIG_ACPI extern void mp_register_ioapic(int id, u32 address, u32 gsi_base); extern void mp_override_legacy_irq(u8 bus_irq, u8 polarity, u8 trigger, diff --git a/arch/x86/include/asm/msr.h b/arch/x86/include/asm/msr.h index cb7502852acb..e139b13f2a33 100644 --- a/arch/x86/include/asm/msr.h +++ b/arch/x86/include/asm/msr.h @@ -218,10 +218,14 @@ void msrs_free(struct msr *msrs); #ifdef CONFIG_SMP int rdmsr_on_cpu(unsigned int cpu, u32 msr_no, u32 *l, u32 *h); int wrmsr_on_cpu(unsigned int cpu, u32 msr_no, u32 l, u32 h); +int rdmsrl_on_cpu(unsigned int cpu, u32 msr_no, u64 *q); +int wrmsrl_on_cpu(unsigned int cpu, u32 msr_no, u64 q); void rdmsr_on_cpus(const struct cpumask *mask, u32 msr_no, struct msr *msrs); void wrmsr_on_cpus(const struct cpumask *mask, u32 msr_no, struct msr *msrs); int rdmsr_safe_on_cpu(unsigned int cpu, u32 msr_no, u32 *l, u32 *h); int wrmsr_safe_on_cpu(unsigned int cpu, u32 msr_no, u32 l, u32 h); +int rdmsrl_safe_on_cpu(unsigned int cpu, u32 msr_no, u64 *q); +int wrmsrl_safe_on_cpu(unsigned int cpu, u32 msr_no, u64 q); int rdmsr_safe_regs_on_cpu(unsigned int cpu, u32 regs[8]); int wrmsr_safe_regs_on_cpu(unsigned int cpu, u32 regs[8]); #else /* CONFIG_SMP */ @@ -235,6 +239,16 @@ static inline int wrmsr_on_cpu(unsigned int cpu, u32 msr_no, u32 l, u32 h) wrmsr(msr_no, l, h); return 0; } +static inline int rdmsrl_on_cpu(unsigned int cpu, u32 msr_no, u64 *q) +{ + rdmsrl(msr_no, *q); + return 0; +} +static inline int wrmsrl_on_cpu(unsigned int cpu, u32 msr_no, u64 q) +{ + wrmsrl(msr_no, q); + return 0; +} static inline void rdmsr_on_cpus(const struct cpumask *m, u32 msr_no, struct msr *msrs) { @@ -254,6 +268,14 @@ static inline int wrmsr_safe_on_cpu(unsigned int cpu, u32 msr_no, u32 l, u32 h) { return wrmsr_safe(msr_no, l, h); } +static inline int rdmsrl_safe_on_cpu(unsigned int cpu, u32 msr_no, u64 *q) +{ + return rdmsrl_safe(msr_no, q); +} +static inline int wrmsrl_safe_on_cpu(unsigned int cpu, u32 msr_no, u64 q) +{ + return wrmsrl_safe(msr_no, q); +} static inline int rdmsr_safe_regs_on_cpu(unsigned int cpu, u32 regs[8]) { return rdmsr_safe_regs(regs); diff --git a/arch/x86/include/asm/pci.h b/arch/x86/include/asm/pci.h index 7d7443283a9d..947b5c417e83 100644 --- a/arch/x86/include/asm/pci.h +++ b/arch/x86/include/asm/pci.h @@ -15,7 +15,7 @@ struct pci_sysdata { int domain; /* PCI domain */ int node; /* NUMA node */ #ifdef CONFIG_ACPI - void *acpi; /* ACPI-specific data */ + struct acpi_device *companion; /* ACPI companion device */ #endif #ifdef CONFIG_X86_64 void *iommu; /* IOMMU private data */ diff --git a/arch/x86/include/asm/pgalloc.h b/arch/x86/include/asm/pgalloc.h index b4389a468fb6..c4412e972bbd 100644 --- a/arch/x86/include/asm/pgalloc.h +++ b/arch/x86/include/asm/pgalloc.h @@ -80,12 +80,21 @@ static inline void pmd_populate(struct mm_struct *mm, pmd_t *pmd, #if PAGETABLE_LEVELS > 2 static inline pmd_t *pmd_alloc_one(struct mm_struct *mm, unsigned long addr) { - return (pmd_t *)get_zeroed_page(GFP_KERNEL|__GFP_REPEAT); + struct page *page; + page = alloc_pages(GFP_KERNEL | __GFP_REPEAT | __GFP_ZERO, 0); + if (!page) + return NULL; + if (!pgtable_pmd_page_ctor(page)) { + __free_pages(page, 0); + return NULL; + } + return (pmd_t *)page_address(page); } static inline void pmd_free(struct mm_struct *mm, pmd_t *pmd) { BUG_ON((unsigned long)pmd & (PAGE_SIZE-1)); + pgtable_pmd_page_dtor(virt_to_page(pmd)); free_page((unsigned long)pmd); } diff --git a/arch/x86/include/asm/pvclock.h b/arch/x86/include/asm/pvclock.h index be8269b00e2a..d6b078e9fa28 100644 --- a/arch/x86/include/asm/pvclock.h +++ b/arch/x86/include/asm/pvclock.h @@ -14,6 +14,8 @@ void pvclock_read_wallclock(struct pvclock_wall_clock *wall, struct timespec *ts); void pvclock_resume(void); +void pvclock_touch_watchdogs(void); + /* * Scale a 64-bit delta by scaling and multiplying by a 32-bit fraction, * yielding a 64-bit result. diff --git a/arch/x86/include/asm/segment.h b/arch/x86/include/asm/segment.h index c48a95035a77..6f1c3a8a33ab 100644 --- a/arch/x86/include/asm/segment.h +++ b/arch/x86/include/asm/segment.h @@ -214,6 +214,9 @@ #ifdef __KERNEL__ #ifndef __ASSEMBLY__ extern const char early_idt_handlers[NUM_EXCEPTION_VECTORS][2+2+5]; +#ifdef CONFIG_TRACING +#define trace_early_idt_handlers early_idt_handlers +#endif /* * Load a segment. Fall back on loading the zero diff --git a/arch/x86/include/asm/thread_info.h b/arch/x86/include/asm/thread_info.h index c46a46be1ec6..3ba3de457d05 100644 --- a/arch/x86/include/asm/thread_info.h +++ b/arch/x86/include/asm/thread_info.h @@ -153,8 +153,6 @@ struct thread_info { #define _TIF_WORK_CTXSW_PREV (_TIF_WORK_CTXSW|_TIF_USER_RETURN_NOTIFY) #define _TIF_WORK_CTXSW_NEXT (_TIF_WORK_CTXSW) -#define PREEMPT_ACTIVE 0x10000000 - #ifdef CONFIG_X86_32 #define STACK_WARN (THREAD_SIZE/8) diff --git a/arch/x86/include/asm/trace/exceptions.h b/arch/x86/include/asm/trace/exceptions.h new file mode 100644 index 000000000000..2fbc66c7885b --- /dev/null +++ b/arch/x86/include/asm/trace/exceptions.h @@ -0,0 +1,52 @@ +#undef TRACE_SYSTEM +#define TRACE_SYSTEM exceptions + +#if !defined(_TRACE_PAGE_FAULT_H) || defined(TRACE_HEADER_MULTI_READ) +#define _TRACE_PAGE_FAULT_H + +#include <linux/tracepoint.h> + +extern void trace_irq_vector_regfunc(void); +extern void trace_irq_vector_unregfunc(void); + +DECLARE_EVENT_CLASS(x86_exceptions, + + TP_PROTO(unsigned long address, struct pt_regs *regs, + unsigned long error_code), + + TP_ARGS(address, regs, error_code), + + TP_STRUCT__entry( + __field( unsigned long, address ) + __field( unsigned long, ip ) + __field( unsigned long, error_code ) + ), + + TP_fast_assign( + __entry->address = address; + __entry->ip = regs->ip; + __entry->error_code = error_code; + ), + + TP_printk("address=%pf ip=%pf error_code=0x%lx", + (void *)__entry->address, (void *)__entry->ip, + __entry->error_code) ); + +#define DEFINE_PAGE_FAULT_EVENT(name) \ +DEFINE_EVENT_FN(x86_exceptions, name, \ + TP_PROTO(unsigned long address, struct pt_regs *regs, \ + unsigned long error_code), \ + TP_ARGS(address, regs, error_code), \ + trace_irq_vector_regfunc, \ + trace_irq_vector_unregfunc); + +DEFINE_PAGE_FAULT_EVENT(page_fault_user); +DEFINE_PAGE_FAULT_EVENT(page_fault_kernel); + +#undef TRACE_INCLUDE_PATH +#define TRACE_INCLUDE_PATH . +#define TRACE_INCLUDE_FILE exceptions +#endif /* _TRACE_PAGE_FAULT_H */ + +/* This part must be outside protection */ +#include <trace/define_trace.h> diff --git a/arch/x86/include/asm/traps.h b/arch/x86/include/asm/traps.h index 7036cb60cd87..58d66fe06b61 100644 --- a/arch/x86/include/asm/traps.h +++ b/arch/x86/include/asm/traps.h @@ -37,6 +37,23 @@ asmlinkage void machine_check(void); #endif /* CONFIG_X86_MCE */ asmlinkage void simd_coprocessor_error(void); +#ifdef CONFIG_TRACING +asmlinkage void trace_page_fault(void); +#define trace_divide_error divide_error +#define trace_bounds bounds +#define trace_invalid_op invalid_op +#define trace_device_not_available device_not_available +#define trace_coprocessor_segment_overrun coprocessor_segment_overrun +#define trace_invalid_TSS invalid_TSS +#define trace_segment_not_present segment_not_present +#define trace_general_protection general_protection +#define trace_spurious_interrupt_bug spurious_interrupt_bug +#define trace_coprocessor_error coprocessor_error +#define trace_alignment_check alignment_check +#define trace_simd_coprocessor_error simd_coprocessor_error +#define trace_async_page_fault async_page_fault +#endif + dotraplinkage void do_divide_error(struct pt_regs *, long); dotraplinkage void do_debug(struct pt_regs *, long); dotraplinkage void do_nmi(struct pt_regs *, long); @@ -55,6 +72,9 @@ asmlinkage __kprobes struct pt_regs *sync_regs(struct pt_regs *); #endif dotraplinkage void do_general_protection(struct pt_regs *, long); dotraplinkage void do_page_fault(struct pt_regs *, unsigned long); +#ifdef CONFIG_TRACING +dotraplinkage void trace_do_page_fault(struct pt_regs *, unsigned long); +#endif dotraplinkage void do_spurious_interrupt_bug(struct pt_regs *, long); dotraplinkage void do_coprocessor_error(struct pt_regs *, long); dotraplinkage void do_alignment_check(struct pt_regs *, long); diff --git a/arch/x86/include/asm/x86_init.h b/arch/x86/include/asm/x86_init.h index 828a1565ba57..0f1be11e43d2 100644 --- a/arch/x86/include/asm/x86_init.h +++ b/arch/x86/include/asm/x86_init.h @@ -172,6 +172,7 @@ struct x86_platform_ops { struct pci_dev; struct msi_msg; +struct msi_desc; struct x86_msi_ops { int (*setup_msi_irqs)(struct pci_dev *dev, int nvec, int type); @@ -182,6 +183,8 @@ struct x86_msi_ops { void (*teardown_msi_irqs)(struct pci_dev *dev); void (*restore_msi_irqs)(struct pci_dev *dev, int irq); int (*setup_hpet_msi)(unsigned int irq, unsigned int id); + u32 (*msi_mask_irq)(struct msi_desc *desc, u32 mask, u32 flag); + u32 (*msix_mask_irq)(struct msi_desc *desc, u32 flag); }; struct IO_APIC_route_entry; diff --git a/arch/x86/include/asm/xen/page-coherent.h b/arch/x86/include/asm/xen/page-coherent.h new file mode 100644 index 000000000000..7f02fe4e2c7b --- /dev/null +++ b/arch/x86/include/asm/xen/page-coherent.h @@ -0,0 +1,38 @@ +#ifndef _ASM_X86_XEN_PAGE_COHERENT_H +#define _ASM_X86_XEN_PAGE_COHERENT_H + +#include <asm/page.h> +#include <linux/dma-attrs.h> +#include <linux/dma-mapping.h> + +static inline void *xen_alloc_coherent_pages(struct device *hwdev, size_t size, + dma_addr_t *dma_handle, gfp_t flags, + struct dma_attrs *attrs) +{ + void *vstart = (void*)__get_free_pages(flags, get_order(size)); + *dma_handle = virt_to_phys(vstart); + return vstart; +} + +static inline void xen_free_coherent_pages(struct device *hwdev, size_t size, + void *cpu_addr, dma_addr_t dma_handle, + struct dma_attrs *attrs) +{ + free_pages((unsigned long) cpu_addr, get_order(size)); +} + +static inline void xen_dma_map_page(struct device *hwdev, struct page *page, + unsigned long offset, size_t size, enum dma_data_direction dir, + struct dma_attrs *attrs) { } + +static inline void xen_dma_unmap_page(struct device *hwdev, dma_addr_t handle, + size_t size, enum dma_data_direction dir, + struct dma_attrs *attrs) { } + +static inline void xen_dma_sync_single_for_cpu(struct device *hwdev, + dma_addr_t handle, size_t size, enum dma_data_direction dir) { } + +static inline void xen_dma_sync_single_for_device(struct device *hwdev, + dma_addr_t handle, size_t size, enum dma_data_direction dir) { } + +#endif /* _ASM_X86_XEN_PAGE_COHERENT_H */ diff --git a/arch/x86/include/uapi/asm/kvm.h b/arch/x86/include/uapi/asm/kvm.h index 5d9a3033b3d7..d3a87780c70b 100644 --- a/arch/x86/include/uapi/asm/kvm.h +++ b/arch/x86/include/uapi/asm/kvm.h @@ -211,9 +211,9 @@ struct kvm_cpuid_entry2 { __u32 padding[3]; }; -#define KVM_CPUID_FLAG_SIGNIFCANT_INDEX 1 -#define KVM_CPUID_FLAG_STATEFUL_FUNC 2 -#define KVM_CPUID_FLAG_STATE_READ_NEXT 4 +#define KVM_CPUID_FLAG_SIGNIFCANT_INDEX BIT(0) +#define KVM_CPUID_FLAG_STATEFUL_FUNC BIT(1) +#define KVM_CPUID_FLAG_STATE_READ_NEXT BIT(2) /* for KVM_SET_CPUID2 */ struct kvm_cpuid2 { diff --git a/arch/x86/include/uapi/asm/msr-index.h b/arch/x86/include/uapi/asm/msr-index.h index bb0465090ae5..37813b5ddc37 100644 --- a/arch/x86/include/uapi/asm/msr-index.h +++ b/arch/x86/include/uapi/asm/msr-index.h @@ -147,6 +147,8 @@ #define MSR_PP1_ENERGY_STATUS 0x00000641 #define MSR_PP1_POLICY 0x00000642 +#define MSR_CORE_C1_RES 0x00000660 + #define MSR_AMD64_MC0_MASK 0xc0010044 #define MSR_IA32_MCx_CTL(x) (MSR_IA32_MC0_CTL + 4*(x)) @@ -536,6 +538,7 @@ /* MSR_IA32_VMX_MISC bits */ #define MSR_IA32_VMX_MISC_VMWRITE_SHADOW_RO_FIELDS (1ULL << 29) +#define MSR_IA32_VMX_MISC_PREEMPTION_TIMER_SCALE 0x1F /* AMD-V MSRs */ #define MSR_VM_CR 0xc0010114 diff --git a/arch/x86/kernel/acpi/boot.c b/arch/x86/kernel/acpi/boot.c index 40c76604199f..6c0b43bd024b 100644 --- a/arch/x86/kernel/acpi/boot.c +++ b/arch/x86/kernel/acpi/boot.c @@ -189,24 +189,31 @@ static int __init acpi_parse_madt(struct acpi_table_header *table) return 0; } -static void acpi_register_lapic(int id, u8 enabled) +/** + * acpi_register_lapic - register a local apic and generates a logic cpu number + * @id: local apic id to register + * @enabled: this cpu is enabled or not + * + * Returns the logic cpu number which maps to the local apic + */ +static int acpi_register_lapic(int id, u8 enabled) { unsigned int ver = 0; if (id >= MAX_LOCAL_APIC) { printk(KERN_INFO PREFIX "skipped apicid that is too big\n"); - return; + return -EINVAL; } if (!enabled) { ++disabled_cpus; - return; + return -EINVAL; } if (boot_cpu_physical_apicid != -1U) ver = apic_version[boot_cpu_physical_apicid]; - generic_processor_info(id, ver); + return generic_processor_info(id, ver); } static int __init @@ -614,84 +621,27 @@ static void acpi_map_cpu2node(acpi_handle handle, int cpu, int physid) #endif } -static int _acpi_map_lsapic(acpi_handle handle, int *pcpu) +static int _acpi_map_lsapic(acpi_handle handle, int physid, int *pcpu) { - struct acpi_buffer buffer = { ACPI_ALLOCATE_BUFFER, NULL }; - union acpi_object *obj; - struct acpi_madt_local_apic *lapic; - cpumask_var_t tmp_map, new_map; - u8 physid; int cpu; - int retval = -ENOMEM; - - if (ACPI_FAILURE(acpi_evaluate_object(handle, "_MAT", NULL, &buffer))) - return -EINVAL; - - if (!buffer.length || !buffer.pointer) - return -EINVAL; - - obj = buffer.pointer; - if (obj->type != ACPI_TYPE_BUFFER || - obj->buffer.length < sizeof(*lapic)) { - kfree(buffer.pointer); - return -EINVAL; - } - lapic = (struct acpi_madt_local_apic *)obj->buffer.pointer; - - if (lapic->header.type != ACPI_MADT_TYPE_LOCAL_APIC || - !(lapic->lapic_flags & ACPI_MADT_ENABLED)) { - kfree(buffer.pointer); - return -EINVAL; - } - - physid = lapic->id; - - kfree(buffer.pointer); - buffer.length = ACPI_ALLOCATE_BUFFER; - buffer.pointer = NULL; - lapic = NULL; - - if (!alloc_cpumask_var(&tmp_map, GFP_KERNEL)) - goto out; - - if (!alloc_cpumask_var(&new_map, GFP_KERNEL)) - goto free_tmp_map; - - cpumask_copy(tmp_map, cpu_present_mask); - acpi_register_lapic(physid, ACPI_MADT_ENABLED); - - /* - * If acpi_register_lapic successfully generates a new logical cpu - * number, then the following will get us exactly what was mapped - */ - cpumask_andnot(new_map, cpu_present_mask, tmp_map); - if (cpumask_empty(new_map)) { - printk ("Unable to map lapic to logical cpu number\n"); - retval = -EINVAL; - goto free_new_map; + cpu = acpi_register_lapic(physid, ACPI_MADT_ENABLED); + if (cpu < 0) { + pr_info(PREFIX "Unable to map lapic to logical cpu number\n"); + return cpu; } acpi_processor_set_pdc(handle); - - cpu = cpumask_first(new_map); acpi_map_cpu2node(handle, cpu, physid); *pcpu = cpu; - retval = 0; - -free_new_map: - free_cpumask_var(new_map); -free_tmp_map: - free_cpumask_var(tmp_map); -out: - return retval; + return 0; } /* wrapper to silence section mismatch warning */ -int __ref acpi_map_lsapic(acpi_handle handle, int *pcpu) +int __ref acpi_map_lsapic(acpi_handle handle, int physid, int *pcpu) { - return _acpi_map_lsapic(handle, pcpu); + return _acpi_map_lsapic(handle, physid, pcpu); } EXPORT_SYMBOL(acpi_map_lsapic); @@ -745,7 +695,7 @@ static int __init acpi_parse_sbf(struct acpi_table_header *table) #ifdef CONFIG_HPET_TIMER #include <asm/hpet.h> -static struct __initdata resource *hpet_res; +static struct resource *hpet_res __initdata; static int __init acpi_parse_hpet(struct acpi_table_header *table) { diff --git a/arch/x86/kernel/acpi/sleep.c b/arch/x86/kernel/acpi/sleep.c index 33120100ff5e..3a2ae4c88948 100644 --- a/arch/x86/kernel/acpi/sleep.c +++ b/arch/x86/kernel/acpi/sleep.c @@ -26,6 +26,17 @@ static char temp_stack[4096]; #endif /** + * x86_acpi_enter_sleep_state - enter sleep state + * @state: Sleep state to enter. + * + * Wrapper around acpi_enter_sleep_state() to be called by assmebly. + */ +acpi_status asmlinkage x86_acpi_enter_sleep_state(u8 state) +{ + return acpi_enter_sleep_state(state); +} + +/** * x86_acpi_suspend_lowlevel - save kernel state * * Create an identity mapped page table and copy the wakeup routine to diff --git a/arch/x86/kernel/acpi/sleep.h b/arch/x86/kernel/acpi/sleep.h index c9c2c982d5e4..65c7b606b606 100644 --- a/arch/x86/kernel/acpi/sleep.h +++ b/arch/x86/kernel/acpi/sleep.h @@ -17,3 +17,5 @@ extern void wakeup_long64(void); extern void do_suspend_lowlevel(void); extern int x86_acpi_suspend_lowlevel(void); + +acpi_status asmlinkage x86_acpi_enter_sleep_state(u8 state); diff --git a/arch/x86/kernel/acpi/wakeup_32.S b/arch/x86/kernel/acpi/wakeup_32.S index d1daa66ab162..665c6b7d2ea9 100644 --- a/arch/x86/kernel/acpi/wakeup_32.S +++ b/arch/x86/kernel/acpi/wakeup_32.S @@ -73,7 +73,7 @@ ENTRY(do_suspend_lowlevel) call save_processor_state call save_registers pushl $3 - call acpi_enter_sleep_state + call x86_acpi_enter_sleep_state addl $4, %esp # In case of S3 failure, we'll emerge here. Jump diff --git a/arch/x86/kernel/acpi/wakeup_64.S b/arch/x86/kernel/acpi/wakeup_64.S index 8ea5164cbd04..ae693b51ed8e 100644 --- a/arch/x86/kernel/acpi/wakeup_64.S +++ b/arch/x86/kernel/acpi/wakeup_64.S @@ -73,7 +73,7 @@ ENTRY(do_suspend_lowlevel) addq $8, %rsp movl $3, %edi xorl %eax, %eax - call acpi_enter_sleep_state + call x86_acpi_enter_sleep_state /* in case something went wrong, restore the machine status and go on */ jmp resume_point diff --git a/arch/x86/kernel/alternative.c b/arch/x86/kernel/alternative.c index 15e8563e5c24..df94598ad05a 100644 --- a/arch/x86/kernel/alternative.c +++ b/arch/x86/kernel/alternative.c @@ -402,17 +402,6 @@ void alternatives_enable_smp(void) { struct smp_alt_module *mod; -#ifdef CONFIG_LOCKDEP - /* - * Older binutils section handling bug prevented - * alternatives-replacement from working reliably. - * - * If this still occurs then you should see a hang - * or crash shortly after this line: - */ - pr_info("lockdep: fixing up alternatives\n"); -#endif - /* Why bother if there are no other CPUs? */ BUG_ON(num_possible_cpus() == 1); diff --git a/arch/x86/kernel/apic/apic.c b/arch/x86/kernel/apic/apic.c index a7eb82d9b012..d278736bf774 100644 --- a/arch/x86/kernel/apic/apic.c +++ b/arch/x86/kernel/apic/apic.c @@ -62,6 +62,7 @@ unsigned disabled_cpus; /* Processor that is doing the boot up */ unsigned int boot_cpu_physical_apicid = -1U; +EXPORT_SYMBOL_GPL(boot_cpu_physical_apicid); /* * The highest APIC ID seen during enumeration. @@ -2107,7 +2108,7 @@ void disconnect_bsp_APIC(int virt_wire_setup) apic_write(APIC_LVT1, value); } -void generic_processor_info(int apicid, int version) +int generic_processor_info(int apicid, int version) { int cpu, max = nr_cpu_ids; bool boot_cpu_detected = physid_isset(boot_cpu_physical_apicid, @@ -2127,7 +2128,7 @@ void generic_processor_info(int apicid, int version) " Processor %d/0x%x ignored.\n", max, thiscpu, apicid); disabled_cpus++; - return; + return -ENODEV; } if (num_processors >= nr_cpu_ids) { @@ -2138,7 +2139,7 @@ void generic_processor_info(int apicid, int version) " Processor %d/0x%x ignored.\n", max, thiscpu, apicid); disabled_cpus++; - return; + return -EINVAL; } num_processors++; @@ -2183,6 +2184,8 @@ void generic_processor_info(int apicid, int version) #endif set_cpu_possible(cpu, true); set_cpu_present(cpu, true); + + return cpu; } int hard_smp_processor_id(void) diff --git a/arch/x86/kernel/cpu/amd.c b/arch/x86/kernel/cpu/amd.c index 3daece79a142..bca023bdd6b2 100644 --- a/arch/x86/kernel/cpu/amd.c +++ b/arch/x86/kernel/cpu/amd.c @@ -339,7 +339,7 @@ static void amd_get_topology(struct cpuinfo_x86 *c) #endif /* - * On a AMD dual core setup the lower bits of the APIC id distingush the cores. + * On a AMD dual core setup the lower bits of the APIC id distinguish the cores. * Assumes number of cores is a power of two. */ static void amd_detect_cmp(struct cpuinfo_x86 *c) diff --git a/arch/x86/kernel/cpu/intel_cacheinfo.c b/arch/x86/kernel/cpu/intel_cacheinfo.c index 1414c90feaba..0641113e2965 100644 --- a/arch/x86/kernel/cpu/intel_cacheinfo.c +++ b/arch/x86/kernel/cpu/intel_cacheinfo.c @@ -1,5 +1,5 @@ /* - * Routines to indentify caches on Intel CPU. + * Routines to identify caches on Intel CPU. * * Changes: * Venkatesh Pallipadi : Adding cache identification through cpuid(4) diff --git a/arch/x86/kernel/cpu/scattered.c b/arch/x86/kernel/cpu/scattered.c index f2cc63e9cf08..b6f794aa1693 100644 --- a/arch/x86/kernel/cpu/scattered.c +++ b/arch/x86/kernel/cpu/scattered.c @@ -1,5 +1,5 @@ /* - * Routines to indentify additional cpu features that are scattered in + * Routines to identify additional cpu features that are scattered in * cpuid space. */ #include <linux/cpu.h> diff --git a/arch/x86/kernel/dumpstack.c b/arch/x86/kernel/dumpstack.c index deb6421c9e69..d9c12d3022a7 100644 --- a/arch/x86/kernel/dumpstack.c +++ b/arch/x86/kernel/dumpstack.c @@ -25,12 +25,17 @@ unsigned int code_bytes = 64; int kstack_depth_to_print = 3 * STACKSLOTS_PER_LINE; static int die_counter; -void printk_address(unsigned long address, int reliable) +static void printk_stack_address(unsigned long address, int reliable) { pr_cont(" [<%p>] %s%pB\n", (void *)address, reliable ? "" : "? ", (void *)address); } +void printk_address(unsigned long address) +{ + pr_cont(" [<%p>] %pS\n", (void *)address, (void *)address); +} + #ifdef CONFIG_FUNCTION_GRAPH_TRACER static void print_ftrace_graph_addr(unsigned long addr, void *data, @@ -151,7 +156,7 @@ static void print_trace_address(void *data, unsigned long addr, int reliable) { touch_nmi_watchdog(); printk(data); - printk_address(addr, reliable); + printk_stack_address(addr, reliable); } static const struct stacktrace_ops print_trace_ops = { @@ -281,7 +286,7 @@ int __kprobes __die(const char *str, struct pt_regs *regs, long err) #else /* Executive summary in case the oops scrolled away */ printk(KERN_ALERT "RIP "); - printk_address(regs->ip, 1); + printk_address(regs->ip); printk(" RSP <%016lx>\n", regs->sp); #endif return 0; diff --git a/arch/x86/kernel/early-quirks.c b/arch/x86/kernel/early-quirks.c index b3cd3ebae077..96f958d8cd45 100644 --- a/arch/x86/kernel/early-quirks.c +++ b/arch/x86/kernel/early-quirks.c @@ -313,6 +313,16 @@ static size_t __init gen6_stolen_size(int num, int slot, int func) return gmch_ctrl << 25; /* 32 MB units */ } +static inline size_t gen8_stolen_size(int num, int slot, int func) +{ + u16 gmch_ctrl; + + gmch_ctrl = read_pci_config_16(num, slot, func, SNB_GMCH_CTRL); + gmch_ctrl >>= BDW_GMCH_GMS_SHIFT; + gmch_ctrl &= BDW_GMCH_GMS_MASK; + return gmch_ctrl << 25; /* 32 MB units */ +} + typedef size_t (*stolen_size_fn)(int num, int slot, int func); static struct pci_device_id intel_stolen_ids[] __initdata = { @@ -336,6 +346,8 @@ static struct pci_device_id intel_stolen_ids[] __initdata = { INTEL_IVB_D_IDS(gen6_stolen_size), INTEL_HSW_D_IDS(gen6_stolen_size), INTEL_HSW_M_IDS(gen6_stolen_size), + INTEL_BDW_M_IDS(gen8_stolen_size), + INTEL_BDW_D_IDS(gen8_stolen_size) }; static void __init intel_graphics_stolen(int num, int slot, int func) diff --git a/arch/x86/kernel/entry_32.S b/arch/x86/kernel/entry_32.S index fd1bc1b15e6d..51e2988c5728 100644 --- a/arch/x86/kernel/entry_32.S +++ b/arch/x86/kernel/entry_32.S @@ -1244,6 +1244,16 @@ return_to_handler: */ .pushsection .kprobes.text, "ax" +#ifdef CONFIG_TRACING +ENTRY(trace_page_fault) + RING0_EC_FRAME + ASM_CLAC + pushl_cfi $trace_do_page_fault + jmp error_code + CFI_ENDPROC +END(trace_page_fault) +#endif + ENTRY(page_fault) RING0_EC_FRAME ASM_CLAC diff --git a/arch/x86/kernel/entry_64.S b/arch/x86/kernel/entry_64.S index 603be7c70675..e21b0785a85b 100644 --- a/arch/x86/kernel/entry_64.S +++ b/arch/x86/kernel/entry_64.S @@ -1278,6 +1278,17 @@ ENTRY(\sym) END(\sym) .endm +#ifdef CONFIG_TRACING +.macro trace_errorentry sym do_sym +errorentry trace(\sym) trace(\do_sym) +errorentry \sym \do_sym +.endm +#else +.macro trace_errorentry sym do_sym +errorentry \sym \do_sym +.endm +#endif + /* error code is on the stack already */ .macro paranoiderrorentry sym do_sym ENTRY(\sym) @@ -1480,7 +1491,7 @@ zeroentry xen_int3 do_int3 errorentry xen_stack_segment do_stack_segment #endif errorentry general_protection do_general_protection -errorentry page_fault do_page_fault +trace_errorentry page_fault do_page_fault #ifdef CONFIG_KVM_GUEST errorentry async_page_fault do_async_page_fault #endif diff --git a/arch/x86/kernel/ftrace.c b/arch/x86/kernel/ftrace.c index 42a392a9fd02..d4bdd253fea7 100644 --- a/arch/x86/kernel/ftrace.c +++ b/arch/x86/kernel/ftrace.c @@ -248,6 +248,15 @@ int ftrace_update_ftrace_func(ftrace_func_t func) return ret; } +static int is_ftrace_caller(unsigned long ip) +{ + if (ip == (unsigned long)(&ftrace_call) || + ip == (unsigned long)(&ftrace_regs_call)) + return 1; + + return 0; +} + /* * A breakpoint was added to the code address we are about to * modify, and this is the handle that will just skip over it. @@ -257,10 +266,13 @@ int ftrace_update_ftrace_func(ftrace_func_t func) */ int ftrace_int3_handler(struct pt_regs *regs) { + unsigned long ip; + if (WARN_ON_ONCE(!regs)) return 0; - if (!ftrace_location(regs->ip - 1)) + ip = regs->ip - 1; + if (!ftrace_location(ip) && !is_ftrace_caller(ip)) return 0; regs->ip += MCOUNT_INSN_SIZE - 1; diff --git a/arch/x86/kernel/head64.c b/arch/x86/kernel/head64.c index 1be8e43b669e..85126ccbdf6b 100644 --- a/arch/x86/kernel/head64.c +++ b/arch/x86/kernel/head64.c @@ -162,7 +162,7 @@ asmlinkage void __init x86_64_start_kernel(char * real_mode_data) clear_bss(); for (i = 0; i < NUM_EXCEPTION_VECTORS; i++) - set_intr_gate(i, &early_idt_handlers[i]); + set_intr_gate(i, early_idt_handlers[i]); load_idt((const struct desc_ptr *)&idt_descr); copy_bootdata(__va(real_mode_data)); diff --git a/arch/x86/kernel/kvm.c b/arch/x86/kernel/kvm.c index b2046e4d0b59..6dd802c6d780 100644 --- a/arch/x86/kernel/kvm.c +++ b/arch/x86/kernel/kvm.c @@ -464,7 +464,7 @@ static struct notifier_block kvm_cpu_notifier = { static void __init kvm_apf_trap_init(void) { - set_intr_gate(14, &async_page_fault); + set_intr_gate(14, async_page_fault); } void __init kvm_guest_init(void) diff --git a/arch/x86/kernel/kvmclock.c b/arch/x86/kernel/kvmclock.c index 1570e0741344..e6041094ff26 100644 --- a/arch/x86/kernel/kvmclock.c +++ b/arch/x86/kernel/kvmclock.c @@ -139,6 +139,7 @@ bool kvm_check_and_clear_guest_paused(void) src = &hv_clock[cpu].pvti; if ((src->flags & PVCLOCK_GUEST_STOPPED) != 0) { src->flags &= ~PVCLOCK_GUEST_STOPPED; + pvclock_touch_watchdogs(); ret = true; } diff --git a/arch/x86/kernel/microcode_amd.c b/arch/x86/kernel/microcode_amd.c index af99f71aeb7f..c3d4cc972eca 100644 --- a/arch/x86/kernel/microcode_amd.c +++ b/arch/x86/kernel/microcode_amd.c @@ -431,7 +431,7 @@ static enum ucode_state request_microcode_amd(int cpu, struct device *device, snprintf(fw_name, sizeof(fw_name), "amd-ucode/microcode_amd_fam%.2xh.bin", c->x86); if (request_firmware(&fw, (const char *)fw_name, device)) { - pr_err("failed to load file %s\n", fw_name); + pr_debug("failed to load file %s\n", fw_name); goto out; } diff --git a/arch/x86/kernel/process_64.c b/arch/x86/kernel/process_64.c index 10fe4c189621..9c0280f93d05 100644 --- a/arch/x86/kernel/process_64.c +++ b/arch/x86/kernel/process_64.c @@ -63,7 +63,7 @@ void __show_regs(struct pt_regs *regs, int all) unsigned int ds, cs, es; printk(KERN_DEFAULT "RIP: %04lx:[<%016lx>] ", regs->cs & 0xffff, regs->ip); - printk_address(regs->ip, 1); + printk_address(regs->ip); printk(KERN_DEFAULT "RSP: %04lx:%016lx EFLAGS: %08lx\n", regs->ss, regs->sp, regs->flags); printk(KERN_DEFAULT "RAX: %016lx RBX: %016lx RCX: %016lx\n", diff --git a/arch/x86/kernel/pvclock.c b/arch/x86/kernel/pvclock.c index a16bae3f83b3..2f355d229a58 100644 --- a/arch/x86/kernel/pvclock.c +++ b/arch/x86/kernel/pvclock.c @@ -43,6 +43,14 @@ unsigned long pvclock_tsc_khz(struct pvclock_vcpu_time_info *src) return pv_tsc_khz; } +void pvclock_touch_watchdogs(void) +{ + touch_softlockup_watchdog_sync(); + clocksource_touch_watchdog(); + rcu_cpu_stall_reset(); + reset_hung_task_detector(); +} + static atomic64_t last_value = ATOMIC64_INIT(0); void pvclock_resume(void) @@ -74,6 +82,11 @@ cycle_t pvclock_clocksource_read(struct pvclock_vcpu_time_info *src) version = __pvclock_read_cycles(src, &ret, &flags); } while ((src->version & 1) || version != src->version); + if (unlikely((flags & PVCLOCK_GUEST_STOPPED) != 0)) { + src->flags &= ~PVCLOCK_GUEST_STOPPED; + pvclock_touch_watchdogs(); + } + if ((valid_flags & PVCLOCK_TSC_STABLE_BIT) && (flags & PVCLOCK_TSC_STABLE_BIT)) return ret; diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c index 2a165580fa16..85dc05a3aa02 100644 --- a/arch/x86/kernel/smpboot.c +++ b/arch/x86/kernel/smpboot.c @@ -81,27 +81,6 @@ /* State of each CPU */ DEFINE_PER_CPU(int, cpu_state) = { 0 }; -#ifdef CONFIG_HOTPLUG_CPU -/* - * We need this for trampoline_base protection from concurrent accesses when - * off- and onlining cores wildly. - */ -static DEFINE_MUTEX(x86_cpu_hotplug_driver_mutex); - -void cpu_hotplug_driver_lock(void) -{ - mutex_lock(&x86_cpu_hotplug_driver_mutex); -} - -void cpu_hotplug_driver_unlock(void) -{ - mutex_unlock(&x86_cpu_hotplug_driver_mutex); -} - -ssize_t arch_cpu_probe(const char *buf, size_t count) { return -1; } -ssize_t arch_cpu_release(const char *buf, size_t count) { return -1; } -#endif - /* Number of siblings per CPU package */ int smp_num_siblings = 1; EXPORT_SYMBOL(smp_num_siblings); diff --git a/arch/x86/kernel/topology.c b/arch/x86/kernel/topology.c index 6e60b5fe2244..649b010da00b 100644 --- a/arch/x86/kernel/topology.c +++ b/arch/x86/kernel/topology.c @@ -65,29 +65,32 @@ int __ref _debug_hotplug_cpu(int cpu, int action) if (!cpu_is_hotpluggable(cpu)) return -EINVAL; - cpu_hotplug_driver_lock(); + lock_device_hotplug(); switch (action) { case 0: ret = cpu_down(cpu); if (!ret) { pr_info("CPU %u is now offline\n", cpu); + dev->offline = true; kobject_uevent(&dev->kobj, KOBJ_OFFLINE); } else pr_debug("Can't offline CPU%d.\n", cpu); break; case 1: ret = cpu_up(cpu); - if (!ret) + if (!ret) { + dev->offline = false; kobject_uevent(&dev->kobj, KOBJ_ONLINE); - else + } else { pr_debug("Can't online CPU%d.\n", cpu); + } break; default: ret = -EINVAL; } - cpu_hotplug_driver_unlock(); + unlock_device_hotplug(); return ret; } diff --git a/arch/x86/kernel/traps.c b/arch/x86/kernel/traps.c index 996ce2313ce6..b857ed890b4c 100644 --- a/arch/x86/kernel/traps.c +++ b/arch/x86/kernel/traps.c @@ -713,7 +713,7 @@ void __init early_trap_init(void) /* int3 can be called from all */ set_system_intr_gate_ist(X86_TRAP_BP, &int3, DEBUG_STACK); #ifdef CONFIG_X86_32 - set_intr_gate(X86_TRAP_PF, &page_fault); + set_intr_gate(X86_TRAP_PF, page_fault); #endif load_idt(&idt_descr); } @@ -721,7 +721,7 @@ void __init early_trap_init(void) void __init early_trap_pf_init(void) { #ifdef CONFIG_X86_64 - set_intr_gate(X86_TRAP_PF, &page_fault); + set_intr_gate(X86_TRAP_PF, page_fault); #endif } @@ -737,30 +737,30 @@ void __init trap_init(void) early_iounmap(p, 4); #endif - set_intr_gate(X86_TRAP_DE, ÷_error); + set_intr_gate(X86_TRAP_DE, divide_error); set_intr_gate_ist(X86_TRAP_NMI, &nmi, NMI_STACK); /* int4 can be called from all */ set_system_intr_gate(X86_TRAP_OF, &overflow); - set_intr_gate(X86_TRAP_BR, &bounds); - set_intr_gate(X86_TRAP_UD, &invalid_op); - set_intr_gate(X86_TRAP_NM, &device_not_available); + set_intr_gate(X86_TRAP_BR, bounds); + set_intr_gate(X86_TRAP_UD, invalid_op); + set_intr_gate(X86_TRAP_NM, device_not_available); #ifdef CONFIG_X86_32 set_task_gate(X86_TRAP_DF, GDT_ENTRY_DOUBLEFAULT_TSS); #else set_intr_gate_ist(X86_TRAP_DF, &double_fault, DOUBLEFAULT_STACK); #endif - set_intr_gate(X86_TRAP_OLD_MF, &coprocessor_segment_overrun); - set_intr_gate(X86_TRAP_TS, &invalid_TSS); - set_intr_gate(X86_TRAP_NP, &segment_not_present); + set_intr_gate(X86_TRAP_OLD_MF, coprocessor_segment_overrun); + set_intr_gate(X86_TRAP_TS, invalid_TSS); + set_intr_gate(X86_TRAP_NP, segment_not_present); set_intr_gate_ist(X86_TRAP_SS, &stack_segment, STACKFAULT_STACK); - set_intr_gate(X86_TRAP_GP, &general_protection); - set_intr_gate(X86_TRAP_SPURIOUS, &spurious_interrupt_bug); - set_intr_gate(X86_TRAP_MF, &coprocessor_error); - set_intr_gate(X86_TRAP_AC, &alignment_check); + set_intr_gate(X86_TRAP_GP, general_protection); + set_intr_gate(X86_TRAP_SPURIOUS, spurious_interrupt_bug); + set_intr_gate(X86_TRAP_MF, coprocessor_error); + set_intr_gate(X86_TRAP_AC, alignment_check); #ifdef CONFIG_X86_MCE set_intr_gate_ist(X86_TRAP_MC, &machine_check, MCE_STACK); #endif - set_intr_gate(X86_TRAP_XF, &simd_coprocessor_error); + set_intr_gate(X86_TRAP_XF, simd_coprocessor_error); /* Reserve all the builtin and the syscall vector: */ for (i = 0; i < FIRST_EXTERNAL_VECTOR; i++) diff --git a/arch/x86/kernel/x86_init.c b/arch/x86/kernel/x86_init.c index 8ce0072cd700..021783b1f46a 100644 --- a/arch/x86/kernel/x86_init.c +++ b/arch/x86/kernel/x86_init.c @@ -116,6 +116,8 @@ struct x86_msi_ops x86_msi = { .teardown_msi_irqs = default_teardown_msi_irqs, .restore_msi_irqs = default_restore_msi_irqs, .setup_hpet_msi = default_setup_hpet_msi, + .msi_mask_irq = default_msi_mask_irq, + .msix_mask_irq = default_msix_mask_irq, }; /* MSI arch specific hooks */ @@ -138,6 +140,14 @@ void arch_restore_msi_irqs(struct pci_dev *dev, int irq) { x86_msi.restore_msi_irqs(dev, irq); } +u32 arch_msi_mask_irq(struct msi_desc *desc, u32 mask, u32 flag) +{ + return x86_msi.msi_mask_irq(desc, mask, flag); +} +u32 arch_msix_mask_irq(struct msi_desc *desc, u32 flag) +{ + return x86_msi.msix_mask_irq(desc, flag); +} #endif struct x86_io_apic_ops x86_io_apic_ops = { diff --git a/arch/x86/kvm/Kconfig b/arch/x86/kvm/Kconfig index a47a3e54b964..b89c5db2b832 100644 --- a/arch/x86/kvm/Kconfig +++ b/arch/x86/kvm/Kconfig @@ -38,6 +38,7 @@ config KVM select PERF_EVENTS select HAVE_KVM_MSI select HAVE_KVM_CPU_RELAX_INTERCEPT + select KVM_VFIO ---help--- Support hosting fully virtualized guest machines using hardware virtualization extensions. You will need a fairly recent diff --git a/arch/x86/kvm/Makefile b/arch/x86/kvm/Makefile index bf4fb04d0112..25d22b2d6509 100644 --- a/arch/x86/kvm/Makefile +++ b/arch/x86/kvm/Makefile @@ -9,7 +9,7 @@ KVM := ../../../virt/kvm kvm-y += $(KVM)/kvm_main.o $(KVM)/ioapic.o \ $(KVM)/coalesced_mmio.o $(KVM)/irq_comm.o \ - $(KVM)/eventfd.o $(KVM)/irqchip.o + $(KVM)/eventfd.o $(KVM)/irqchip.o $(KVM)/vfio.o kvm-$(CONFIG_KVM_DEVICE_ASSIGNMENT) += $(KVM)/assigned-dev.o $(KVM)/iommu.o kvm-$(CONFIG_KVM_ASYNC_PF) += $(KVM)/async_pf.o diff --git a/arch/x86/kvm/cpuid.c b/arch/x86/kvm/cpuid.c index b110fe6c03d4..c6976257eff5 100644 --- a/arch/x86/kvm/cpuid.c +++ b/arch/x86/kvm/cpuid.c @@ -23,6 +23,26 @@ #include "mmu.h" #include "trace.h" +static u32 xstate_required_size(u64 xstate_bv) +{ + int feature_bit = 0; + u32 ret = XSAVE_HDR_SIZE + XSAVE_HDR_OFFSET; + + xstate_bv &= ~XSTATE_FPSSE; + while (xstate_bv) { + if (xstate_bv & 0x1) { + u32 eax, ebx, ecx, edx; + cpuid_count(0xD, feature_bit, &eax, &ebx, &ecx, &edx); + ret = max(ret, eax + ebx); + } + + xstate_bv >>= 1; + feature_bit++; + } + + return ret; +} + void kvm_update_cpuid(struct kvm_vcpu *vcpu) { struct kvm_cpuid_entry2 *best; @@ -46,6 +66,18 @@ void kvm_update_cpuid(struct kvm_vcpu *vcpu) apic->lapic_timer.timer_mode_mask = 1 << 17; } + best = kvm_find_cpuid_entry(vcpu, 0xD, 0); + if (!best) { + vcpu->arch.guest_supported_xcr0 = 0; + vcpu->arch.guest_xstate_size = XSAVE_HDR_SIZE + XSAVE_HDR_OFFSET; + } else { + vcpu->arch.guest_supported_xcr0 = + (best->eax | ((u64)best->edx << 32)) & + host_xcr0 & KVM_SUPPORTED_XCR0; + vcpu->arch.guest_xstate_size = + xstate_required_size(vcpu->arch.guest_supported_xcr0); + } + kvm_pmu_cpuid_update(vcpu); } @@ -182,13 +214,35 @@ static bool supported_xcr0_bit(unsigned bit) { u64 mask = ((u64)1 << bit); - return mask & (XSTATE_FP | XSTATE_SSE | XSTATE_YMM) & host_xcr0; + return mask & KVM_SUPPORTED_XCR0 & host_xcr0; } #define F(x) bit(X86_FEATURE_##x) -static int do_cpuid_ent(struct kvm_cpuid_entry2 *entry, u32 function, - u32 index, int *nent, int maxnent) +static int __do_cpuid_ent_emulated(struct kvm_cpuid_entry2 *entry, + u32 func, u32 index, int *nent, int maxnent) +{ + switch (func) { + case 0: + entry->eax = 1; /* only one leaf currently */ + ++*nent; + break; + case 1: + entry->ecx = F(MOVBE); + ++*nent; + break; + default: + break; + } + + entry->function = func; + entry->index = index; + + return 0; +} + +static inline int __do_cpuid_ent(struct kvm_cpuid_entry2 *entry, u32 function, + u32 index, int *nent, int maxnent) { int r; unsigned f_nx = is_efer_nx() ? F(NX) : 0; @@ -383,6 +437,8 @@ static int do_cpuid_ent(struct kvm_cpuid_entry2 *entry, u32 function, case 0xd: { int idx, i; + entry->eax &= host_xcr0 & KVM_SUPPORTED_XCR0; + entry->edx &= (host_xcr0 & KVM_SUPPORTED_XCR0) >> 32; entry->flags |= KVM_CPUID_FLAG_SIGNIFCANT_INDEX; for (idx = 1, i = 1; idx < 64; ++idx) { if (*nent >= maxnent) @@ -481,6 +537,15 @@ out: return r; } +static int do_cpuid_ent(struct kvm_cpuid_entry2 *entry, u32 func, + u32 idx, int *nent, int maxnent, unsigned int type) +{ + if (type == KVM_GET_EMULATED_CPUID) + return __do_cpuid_ent_emulated(entry, func, idx, nent, maxnent); + + return __do_cpuid_ent(entry, func, idx, nent, maxnent); +} + #undef F struct kvm_cpuid_param { @@ -495,8 +560,36 @@ static bool is_centaur_cpu(const struct kvm_cpuid_param *param) return boot_cpu_data.x86_vendor == X86_VENDOR_CENTAUR; } -int kvm_dev_ioctl_get_supported_cpuid(struct kvm_cpuid2 *cpuid, - struct kvm_cpuid_entry2 __user *entries) +static bool sanity_check_entries(struct kvm_cpuid_entry2 __user *entries, + __u32 num_entries, unsigned int ioctl_type) +{ + int i; + __u32 pad[3]; + + if (ioctl_type != KVM_GET_EMULATED_CPUID) + return false; + + /* + * We want to make sure that ->padding is being passed clean from + * userspace in case we want to use it for something in the future. + * + * Sadly, this wasn't enforced for KVM_GET_SUPPORTED_CPUID and so we + * have to give ourselves satisfied only with the emulated side. /me + * sheds a tear. + */ + for (i = 0; i < num_entries; i++) { + if (copy_from_user(pad, entries[i].padding, sizeof(pad))) + return true; + + if (pad[0] || pad[1] || pad[2]) + return true; + } + return false; +} + +int kvm_dev_ioctl_get_cpuid(struct kvm_cpuid2 *cpuid, + struct kvm_cpuid_entry2 __user *entries, + unsigned int type) { struct kvm_cpuid_entry2 *cpuid_entries; int limit, nent = 0, r = -E2BIG, i; @@ -513,8 +606,12 @@ int kvm_dev_ioctl_get_supported_cpuid(struct kvm_cpuid2 *cpuid, goto out; if (cpuid->nent > KVM_MAX_CPUID_ENTRIES) cpuid->nent = KVM_MAX_CPUID_ENTRIES; + + if (sanity_check_entries(entries, cpuid->nent, type)) + return -EINVAL; + r = -ENOMEM; - cpuid_entries = vmalloc(sizeof(struct kvm_cpuid_entry2) * cpuid->nent); + cpuid_entries = vzalloc(sizeof(struct kvm_cpuid_entry2) * cpuid->nent); if (!cpuid_entries) goto out; @@ -526,7 +623,7 @@ int kvm_dev_ioctl_get_supported_cpuid(struct kvm_cpuid2 *cpuid, continue; r = do_cpuid_ent(&cpuid_entries[nent], ent->func, ent->idx, - &nent, cpuid->nent); + &nent, cpuid->nent, type); if (r) goto out_free; @@ -537,7 +634,7 @@ int kvm_dev_ioctl_get_supported_cpuid(struct kvm_cpuid2 *cpuid, limit = cpuid_entries[nent - 1].eax; for (func = ent->func + 1; func <= limit && nent < cpuid->nent && r == 0; ++func) r = do_cpuid_ent(&cpuid_entries[nent], func, ent->idx, - &nent, cpuid->nent); + &nent, cpuid->nent, type); if (r) goto out_free; @@ -661,6 +758,7 @@ void kvm_cpuid(struct kvm_vcpu *vcpu, u32 *eax, u32 *ebx, u32 *ecx, u32 *edx) *edx = best->edx; } else *eax = *ebx = *ecx = *edx = 0; + trace_kvm_cpuid(function, *eax, *ebx, *ecx, *edx); } EXPORT_SYMBOL_GPL(kvm_cpuid); @@ -676,6 +774,5 @@ void kvm_emulate_cpuid(struct kvm_vcpu *vcpu) kvm_register_write(vcpu, VCPU_REGS_RCX, ecx); kvm_register_write(vcpu, VCPU_REGS_RDX, edx); kvm_x86_ops->skip_emulated_instruction(vcpu); - trace_kvm_cpuid(function, eax, ebx, ecx, edx); } EXPORT_SYMBOL_GPL(kvm_emulate_cpuid); diff --git a/arch/x86/kvm/cpuid.h b/arch/x86/kvm/cpuid.h index b7fd07984888..f1e4895174b2 100644 --- a/arch/x86/kvm/cpuid.h +++ b/arch/x86/kvm/cpuid.h @@ -6,8 +6,9 @@ void kvm_update_cpuid(struct kvm_vcpu *vcpu); struct kvm_cpuid_entry2 *kvm_find_cpuid_entry(struct kvm_vcpu *vcpu, u32 function, u32 index); -int kvm_dev_ioctl_get_supported_cpuid(struct kvm_cpuid2 *cpuid, - struct kvm_cpuid_entry2 __user *entries); +int kvm_dev_ioctl_get_cpuid(struct kvm_cpuid2 *cpuid, + struct kvm_cpuid_entry2 __user *entries, + unsigned int type); int kvm_vcpu_ioctl_set_cpuid(struct kvm_vcpu *vcpu, struct kvm_cpuid *cpuid, struct kvm_cpuid_entry __user *entries); diff --git a/arch/x86/kvm/emulate.c b/arch/x86/kvm/emulate.c index ddc3f3d2afdb..07ffca0a89e9 100644 --- a/arch/x86/kvm/emulate.c +++ b/arch/x86/kvm/emulate.c @@ -130,7 +130,7 @@ #define Mov (1<<20) /* Misc flags */ #define Prot (1<<21) /* instruction generates #UD if not in prot-mode */ -#define VendorSpecific (1<<22) /* Vendor specific instruction */ +#define EmulateOnUD (1<<22) /* Emulate if unsupported by the host */ #define NoAccess (1<<23) /* Don't access memory (lea/invlpg/verr etc) */ #define Op3264 (1<<24) /* Operand is 64b in long mode, 32b otherwise */ #define Undefined (1<<25) /* No Such Instruction */ @@ -785,9 +785,10 @@ static int do_insn_fetch(struct x86_emulate_ctxt *ctxt, * @highbyte_regs specifies whether to decode AH,CH,DH,BH. */ static void *decode_register(struct x86_emulate_ctxt *ctxt, u8 modrm_reg, - int highbyte_regs) + int byteop) { void *p; + int highbyte_regs = (ctxt->rex_prefix == 0) && byteop; if (highbyte_regs && modrm_reg >= 4 && modrm_reg < 8) p = (unsigned char *)reg_rmw(ctxt, modrm_reg & 3) + 1; @@ -1024,7 +1025,6 @@ static void decode_register_operand(struct x86_emulate_ctxt *ctxt, struct operand *op) { unsigned reg = ctxt->modrm_reg; - int highbyte_regs = ctxt->rex_prefix == 0; if (!(ctxt->d & ModRM)) reg = (ctxt->b & 7) | ((ctxt->rex_prefix & 1) << 3); @@ -1045,13 +1045,9 @@ static void decode_register_operand(struct x86_emulate_ctxt *ctxt, } op->type = OP_REG; - if (ctxt->d & ByteOp) { - op->addr.reg = decode_register(ctxt, reg, highbyte_regs); - op->bytes = 1; - } else { - op->addr.reg = decode_register(ctxt, reg, 0); - op->bytes = ctxt->op_bytes; - } + op->bytes = (ctxt->d & ByteOp) ? 1 : ctxt->op_bytes; + op->addr.reg = decode_register(ctxt, reg, ctxt->d & ByteOp); + fetch_register_operand(op); op->orig_val = op->val; } @@ -1082,12 +1078,10 @@ static int decode_modrm(struct x86_emulate_ctxt *ctxt, ctxt->modrm_seg = VCPU_SREG_DS; if (ctxt->modrm_mod == 3) { - int highbyte_regs = ctxt->rex_prefix == 0; - op->type = OP_REG; op->bytes = (ctxt->d & ByteOp) ? 1 : ctxt->op_bytes; op->addr.reg = decode_register(ctxt, ctxt->modrm_rm, - highbyte_regs && (ctxt->d & ByteOp)); + ctxt->d & ByteOp); if (ctxt->d & Sse) { op->type = OP_XMM; op->bytes = 16; @@ -2961,6 +2955,46 @@ static int em_mov(struct x86_emulate_ctxt *ctxt) return X86EMUL_CONTINUE; } +#define FFL(x) bit(X86_FEATURE_##x) + +static int em_movbe(struct x86_emulate_ctxt *ctxt) +{ + u32 ebx, ecx, edx, eax = 1; + u16 tmp; + + /* + * Check MOVBE is set in the guest-visible CPUID leaf. + */ + ctxt->ops->get_cpuid(ctxt, &eax, &ebx, &ecx, &edx); + if (!(ecx & FFL(MOVBE))) + return emulate_ud(ctxt); + + switch (ctxt->op_bytes) { + case 2: + /* + * From MOVBE definition: "...When the operand size is 16 bits, + * the upper word of the destination register remains unchanged + * ..." + * + * Both casting ->valptr and ->val to u16 breaks strict aliasing + * rules so we have to do the operation almost per hand. + */ + tmp = (u16)ctxt->src.val; + ctxt->dst.val &= ~0xffffUL; + ctxt->dst.val |= (unsigned long)swab16(tmp); + break; + case 4: + ctxt->dst.val = swab32((u32)ctxt->src.val); + break; + case 8: + ctxt->dst.val = swab64(ctxt->src.val); + break; + default: + return X86EMUL_PROPAGATE_FAULT; + } + return X86EMUL_CONTINUE; +} + static int em_cr_write(struct x86_emulate_ctxt *ctxt) { if (ctxt->ops->set_cr(ctxt, ctxt->modrm_reg, ctxt->src.val)) @@ -3256,6 +3290,18 @@ static int em_cpuid(struct x86_emulate_ctxt *ctxt) return X86EMUL_CONTINUE; } +static int em_sahf(struct x86_emulate_ctxt *ctxt) +{ + u32 flags; + + flags = EFLG_CF | EFLG_PF | EFLG_AF | EFLG_ZF | EFLG_SF; + flags &= *reg_rmw(ctxt, VCPU_REGS_RAX) >> 8; + + ctxt->eflags &= ~0xffUL; + ctxt->eflags |= flags | X86_EFLAGS_FIXED; + return X86EMUL_CONTINUE; +} + static int em_lahf(struct x86_emulate_ctxt *ctxt) { *reg_rmw(ctxt, VCPU_REGS_RAX) &= ~0xff00UL; @@ -3502,7 +3548,7 @@ static const struct opcode group7_rm1[] = { static const struct opcode group7_rm3[] = { DIP(SrcNone | Prot | Priv, vmrun, check_svme_pa), - II(SrcNone | Prot | VendorSpecific, em_vmmcall, vmmcall), + II(SrcNone | Prot | EmulateOnUD, em_vmmcall, vmmcall), DIP(SrcNone | Prot | Priv, vmload, check_svme_pa), DIP(SrcNone | Prot | Priv, vmsave, check_svme_pa), DIP(SrcNone | Prot | Priv, stgi, check_svme), @@ -3587,7 +3633,7 @@ static const struct group_dual group7 = { { II(SrcMem16 | Mov | Priv, em_lmsw, lmsw), II(SrcMem | ByteOp | Priv | NoAccess, em_invlpg, invlpg), }, { - I(SrcNone | Priv | VendorSpecific, em_vmcall), + I(SrcNone | Priv | EmulateOnUD, em_vmcall), EXT(0, group7_rm1), N, EXT(0, group7_rm3), II(SrcNone | DstMem | Mov, em_smsw, smsw), N, @@ -3750,7 +3796,8 @@ static const struct opcode opcode_table[256] = { D(DstAcc | SrcNone), I(ImplicitOps | SrcAcc, em_cwd), I(SrcImmFAddr | No64, em_call_far), N, II(ImplicitOps | Stack, em_pushf, pushf), - II(ImplicitOps | Stack, em_popf, popf), N, I(ImplicitOps, em_lahf), + II(ImplicitOps | Stack, em_popf, popf), + I(ImplicitOps, em_sahf), I(ImplicitOps, em_lahf), /* 0xA0 - 0xA7 */ I2bv(DstAcc | SrcMem | Mov | MemAbs, em_mov), I2bv(DstMem | SrcAcc | Mov | MemAbs | PageTable, em_mov), @@ -3810,7 +3857,7 @@ static const struct opcode opcode_table[256] = { static const struct opcode twobyte_table[256] = { /* 0x00 - 0x0F */ G(0, group6), GD(0, &group7), N, N, - N, I(ImplicitOps | VendorSpecific, em_syscall), + N, I(ImplicitOps | EmulateOnUD, em_syscall), II(ImplicitOps | Priv, em_clts, clts), N, DI(ImplicitOps | Priv, invd), DI(ImplicitOps | Priv, wbinvd), N, N, N, D(ImplicitOps | ModRM), N, N, @@ -3830,8 +3877,8 @@ static const struct opcode twobyte_table[256] = { IIP(ImplicitOps, em_rdtsc, rdtsc, check_rdtsc), II(ImplicitOps | Priv, em_rdmsr, rdmsr), IIP(ImplicitOps, em_rdpmc, rdpmc, check_rdpmc), - I(ImplicitOps | VendorSpecific, em_sysenter), - I(ImplicitOps | Priv | VendorSpecific, em_sysexit), + I(ImplicitOps | EmulateOnUD, em_sysenter), + I(ImplicitOps | Priv | EmulateOnUD, em_sysexit), N, N, N, N, N, N, N, N, N, N, /* 0x40 - 0x4F */ @@ -3892,6 +3939,30 @@ static const struct opcode twobyte_table[256] = { N, N, N, N, N, N, N, N, N, N, N, N, N, N, N, N }; +static const struct gprefix three_byte_0f_38_f0 = { + I(DstReg | SrcMem | Mov, em_movbe), N, N, N +}; + +static const struct gprefix three_byte_0f_38_f1 = { + I(DstMem | SrcReg | Mov, em_movbe), N, N, N +}; + +/* + * Insns below are selected by the prefix which indexed by the third opcode + * byte. + */ +static const struct opcode opcode_map_0f_38[256] = { + /* 0x00 - 0x7f */ + X16(N), X16(N), X16(N), X16(N), X16(N), X16(N), X16(N), X16(N), + /* 0x80 - 0xef */ + X16(N), X16(N), X16(N), X16(N), X16(N), X16(N), X16(N), + /* 0xf0 - 0xf1 */ + GP(EmulateOnUD | ModRM | Prefix, &three_byte_0f_38_f0), + GP(EmulateOnUD | ModRM | Prefix, &three_byte_0f_38_f1), + /* 0xf2 - 0xff */ + N, N, X4(N), X8(N) +}; + #undef D #undef N #undef G @@ -4040,7 +4111,8 @@ static int decode_operand(struct x86_emulate_ctxt *ctxt, struct operand *op, case OpMem8: ctxt->memop.bytes = 1; if (ctxt->memop.type == OP_REG) { - ctxt->memop.addr.reg = decode_register(ctxt, ctxt->modrm_rm, 1); + ctxt->memop.addr.reg = decode_register(ctxt, + ctxt->modrm_rm, true); fetch_register_operand(&ctxt->memop); } goto mem_common; @@ -4126,6 +4198,7 @@ int x86_decode_insn(struct x86_emulate_ctxt *ctxt, void *insn, int insn_len) ctxt->_eip = ctxt->eip; ctxt->fetch.start = ctxt->_eip; ctxt->fetch.end = ctxt->fetch.start + insn_len; + ctxt->opcode_len = 1; if (insn_len > 0) memcpy(ctxt->fetch.data, insn, insn_len); @@ -4208,9 +4281,16 @@ done_prefixes: opcode = opcode_table[ctxt->b]; /* Two-byte opcode? */ if (ctxt->b == 0x0f) { - ctxt->twobyte = 1; + ctxt->opcode_len = 2; ctxt->b = insn_fetch(u8, ctxt); opcode = twobyte_table[ctxt->b]; + + /* 0F_38 opcode map */ + if (ctxt->b == 0x38) { + ctxt->opcode_len = 3; + ctxt->b = insn_fetch(u8, ctxt); + opcode = opcode_map_0f_38[ctxt->b]; + } } ctxt->d = opcode.flags; @@ -4267,7 +4347,7 @@ done_prefixes: if (ctxt->d == 0 || (ctxt->d & NotImpl)) return EMULATION_FAILED; - if (!(ctxt->d & VendorSpecific) && ctxt->only_vendor_specific_insn) + if (!(ctxt->d & EmulateOnUD) && ctxt->ud) return EMULATION_FAILED; if (mode == X86EMUL_MODE_PROT64 && (ctxt->d & Stack)) @@ -4540,8 +4620,10 @@ special_insn: goto writeback; } - if (ctxt->twobyte) + if (ctxt->opcode_len == 2) goto twobyte_insn; + else if (ctxt->opcode_len == 3) + goto threebyte_insn; switch (ctxt->b) { case 0x63: /* movsxd */ @@ -4726,6 +4808,8 @@ twobyte_insn: goto cannot_emulate; } +threebyte_insn: + if (rc != X86EMUL_CONTINUE) goto done; diff --git a/arch/x86/kvm/mmu.c b/arch/x86/kvm/mmu.c index dce0df8150df..40772ef0f2b1 100644 --- a/arch/x86/kvm/mmu.c +++ b/arch/x86/kvm/mmu.c @@ -2570,11 +2570,6 @@ static void mmu_set_spte(struct kvm_vcpu *vcpu, u64 *sptep, kvm_release_pfn_clean(pfn); } -static void nonpaging_new_cr3(struct kvm_vcpu *vcpu) -{ - mmu_free_roots(vcpu); -} - static pfn_t pte_prefetch_gfn_to_pfn(struct kvm_vcpu *vcpu, gfn_t gfn, bool no_dirty_log) { @@ -3424,18 +3419,11 @@ out_unlock: return 0; } -static void nonpaging_free(struct kvm_vcpu *vcpu) -{ - mmu_free_roots(vcpu); -} - -static int nonpaging_init_context(struct kvm_vcpu *vcpu, - struct kvm_mmu *context) +static void nonpaging_init_context(struct kvm_vcpu *vcpu, + struct kvm_mmu *context) { - context->new_cr3 = nonpaging_new_cr3; context->page_fault = nonpaging_page_fault; context->gva_to_gpa = nonpaging_gva_to_gpa; - context->free = nonpaging_free; context->sync_page = nonpaging_sync_page; context->invlpg = nonpaging_invlpg; context->update_pte = nonpaging_update_pte; @@ -3444,7 +3432,6 @@ static int nonpaging_init_context(struct kvm_vcpu *vcpu, context->root_hpa = INVALID_PAGE; context->direct_map = true; context->nx = false; - return 0; } void kvm_mmu_flush_tlb(struct kvm_vcpu *vcpu) @@ -3454,9 +3441,8 @@ void kvm_mmu_flush_tlb(struct kvm_vcpu *vcpu) } EXPORT_SYMBOL_GPL(kvm_mmu_flush_tlb); -static void paging_new_cr3(struct kvm_vcpu *vcpu) +void kvm_mmu_new_cr3(struct kvm_vcpu *vcpu) { - pgprintk("%s: cr3 %lx\n", __func__, kvm_read_cr3(vcpu)); mmu_free_roots(vcpu); } @@ -3471,11 +3457,6 @@ static void inject_page_fault(struct kvm_vcpu *vcpu, vcpu->arch.mmu.inject_page_fault(vcpu, fault); } -static void paging_free(struct kvm_vcpu *vcpu) -{ - nonpaging_free(vcpu); -} - static bool sync_mmio_spte(struct kvm *kvm, u64 *sptep, gfn_t gfn, unsigned access, int *nr_present) { @@ -3665,9 +3646,9 @@ static void update_last_pte_bitmap(struct kvm_vcpu *vcpu, struct kvm_mmu *mmu) mmu->last_pte_bitmap = map; } -static int paging64_init_context_common(struct kvm_vcpu *vcpu, - struct kvm_mmu *context, - int level) +static void paging64_init_context_common(struct kvm_vcpu *vcpu, + struct kvm_mmu *context, + int level) { context->nx = is_nx(vcpu); context->root_level = level; @@ -3677,27 +3658,24 @@ static int paging64_init_context_common(struct kvm_vcpu *vcpu, update_last_pte_bitmap(vcpu, context); ASSERT(is_pae(vcpu)); - context->new_cr3 = paging_new_cr3; context->page_fault = paging64_page_fault; context->gva_to_gpa = paging64_gva_to_gpa; context->sync_page = paging64_sync_page; context->invlpg = paging64_invlpg; context->update_pte = paging64_update_pte; - context->free = paging_free; context->shadow_root_level = level; context->root_hpa = INVALID_PAGE; context->direct_map = false; - return 0; } -static int paging64_init_context(struct kvm_vcpu *vcpu, - struct kvm_mmu *context) +static void paging64_init_context(struct kvm_vcpu *vcpu, + struct kvm_mmu *context) { - return paging64_init_context_common(vcpu, context, PT64_ROOT_LEVEL); + paging64_init_context_common(vcpu, context, PT64_ROOT_LEVEL); } -static int paging32_init_context(struct kvm_vcpu *vcpu, - struct kvm_mmu *context) +static void paging32_init_context(struct kvm_vcpu *vcpu, + struct kvm_mmu *context) { context->nx = false; context->root_level = PT32_ROOT_LEVEL; @@ -3706,33 +3684,28 @@ static int paging32_init_context(struct kvm_vcpu *vcpu, update_permission_bitmask(vcpu, context, false); update_last_pte_bitmap(vcpu, context); - context->new_cr3 = paging_new_cr3; context->page_fault = paging32_page_fault; context->gva_to_gpa = paging32_gva_to_gpa; - context->free = paging_free; context->sync_page = paging32_sync_page; context->invlpg = paging32_invlpg; context->update_pte = paging32_update_pte; context->shadow_root_level = PT32E_ROOT_LEVEL; context->root_hpa = INVALID_PAGE; context->direct_map = false; - return 0; } -static int paging32E_init_context(struct kvm_vcpu *vcpu, - struct kvm_mmu *context) +static void paging32E_init_context(struct kvm_vcpu *vcpu, + struct kvm_mmu *context) { - return paging64_init_context_common(vcpu, context, PT32E_ROOT_LEVEL); + paging64_init_context_common(vcpu, context, PT32E_ROOT_LEVEL); } -static int init_kvm_tdp_mmu(struct kvm_vcpu *vcpu) +static void init_kvm_tdp_mmu(struct kvm_vcpu *vcpu) { struct kvm_mmu *context = vcpu->arch.walk_mmu; context->base_role.word = 0; - context->new_cr3 = nonpaging_new_cr3; context->page_fault = tdp_page_fault; - context->free = nonpaging_free; context->sync_page = nonpaging_sync_page; context->invlpg = nonpaging_invlpg; context->update_pte = nonpaging_update_pte; @@ -3767,37 +3740,32 @@ static int init_kvm_tdp_mmu(struct kvm_vcpu *vcpu) update_permission_bitmask(vcpu, context, false); update_last_pte_bitmap(vcpu, context); - - return 0; } -int kvm_init_shadow_mmu(struct kvm_vcpu *vcpu, struct kvm_mmu *context) +void kvm_init_shadow_mmu(struct kvm_vcpu *vcpu, struct kvm_mmu *context) { - int r; bool smep = kvm_read_cr4_bits(vcpu, X86_CR4_SMEP); ASSERT(vcpu); ASSERT(!VALID_PAGE(vcpu->arch.mmu.root_hpa)); if (!is_paging(vcpu)) - r = nonpaging_init_context(vcpu, context); + nonpaging_init_context(vcpu, context); else if (is_long_mode(vcpu)) - r = paging64_init_context(vcpu, context); + paging64_init_context(vcpu, context); else if (is_pae(vcpu)) - r = paging32E_init_context(vcpu, context); + paging32E_init_context(vcpu, context); else - r = paging32_init_context(vcpu, context); + paging32_init_context(vcpu, context); vcpu->arch.mmu.base_role.nxe = is_nx(vcpu); vcpu->arch.mmu.base_role.cr4_pae = !!is_pae(vcpu); vcpu->arch.mmu.base_role.cr0_wp = is_write_protection(vcpu); vcpu->arch.mmu.base_role.smep_andnot_wp = smep && !is_write_protection(vcpu); - - return r; } EXPORT_SYMBOL_GPL(kvm_init_shadow_mmu); -int kvm_init_shadow_ept_mmu(struct kvm_vcpu *vcpu, struct kvm_mmu *context, +void kvm_init_shadow_ept_mmu(struct kvm_vcpu *vcpu, struct kvm_mmu *context, bool execonly) { ASSERT(vcpu); @@ -3806,37 +3774,30 @@ int kvm_init_shadow_ept_mmu(struct kvm_vcpu *vcpu, struct kvm_mmu *context, context->shadow_root_level = kvm_x86_ops->get_tdp_level(); context->nx = true; - context->new_cr3 = paging_new_cr3; context->page_fault = ept_page_fault; context->gva_to_gpa = ept_gva_to_gpa; context->sync_page = ept_sync_page; context->invlpg = ept_invlpg; context->update_pte = ept_update_pte; - context->free = paging_free; context->root_level = context->shadow_root_level; context->root_hpa = INVALID_PAGE; context->direct_map = false; update_permission_bitmask(vcpu, context, true); reset_rsvds_bits_mask_ept(vcpu, context, execonly); - - return 0; } EXPORT_SYMBOL_GPL(kvm_init_shadow_ept_mmu); -static int init_kvm_softmmu(struct kvm_vcpu *vcpu) +static void init_kvm_softmmu(struct kvm_vcpu *vcpu) { - int r = kvm_init_shadow_mmu(vcpu, vcpu->arch.walk_mmu); - + kvm_init_shadow_mmu(vcpu, vcpu->arch.walk_mmu); vcpu->arch.walk_mmu->set_cr3 = kvm_x86_ops->set_cr3; vcpu->arch.walk_mmu->get_cr3 = get_cr3; vcpu->arch.walk_mmu->get_pdptr = kvm_pdptr_read; vcpu->arch.walk_mmu->inject_page_fault = kvm_inject_page_fault; - - return r; } -static int init_kvm_nested_mmu(struct kvm_vcpu *vcpu) +static void init_kvm_nested_mmu(struct kvm_vcpu *vcpu) { struct kvm_mmu *g_context = &vcpu->arch.nested_mmu; @@ -3873,11 +3834,9 @@ static int init_kvm_nested_mmu(struct kvm_vcpu *vcpu) update_permission_bitmask(vcpu, g_context, false); update_last_pte_bitmap(vcpu, g_context); - - return 0; } -static int init_kvm_mmu(struct kvm_vcpu *vcpu) +static void init_kvm_mmu(struct kvm_vcpu *vcpu) { if (mmu_is_nested(vcpu)) return init_kvm_nested_mmu(vcpu); @@ -3887,18 +3846,12 @@ static int init_kvm_mmu(struct kvm_vcpu *vcpu) return init_kvm_softmmu(vcpu); } -static void destroy_kvm_mmu(struct kvm_vcpu *vcpu) +void kvm_mmu_reset_context(struct kvm_vcpu *vcpu) { ASSERT(vcpu); - if (VALID_PAGE(vcpu->arch.mmu.root_hpa)) - /* mmu.free() should set root_hpa = INVALID_PAGE */ - vcpu->arch.mmu.free(vcpu); -} -int kvm_mmu_reset_context(struct kvm_vcpu *vcpu) -{ - destroy_kvm_mmu(vcpu); - return init_kvm_mmu(vcpu); + kvm_mmu_unload(vcpu); + init_kvm_mmu(vcpu); } EXPORT_SYMBOL_GPL(kvm_mmu_reset_context); @@ -3923,6 +3876,7 @@ EXPORT_SYMBOL_GPL(kvm_mmu_load); void kvm_mmu_unload(struct kvm_vcpu *vcpu) { mmu_free_roots(vcpu); + WARN_ON(VALID_PAGE(vcpu->arch.mmu.root_hpa)); } EXPORT_SYMBOL_GPL(kvm_mmu_unload); @@ -4281,12 +4235,12 @@ int kvm_mmu_create(struct kvm_vcpu *vcpu) return alloc_mmu_pages(vcpu); } -int kvm_mmu_setup(struct kvm_vcpu *vcpu) +void kvm_mmu_setup(struct kvm_vcpu *vcpu) { ASSERT(vcpu); ASSERT(!VALID_PAGE(vcpu->arch.mmu.root_hpa)); - return init_kvm_mmu(vcpu); + init_kvm_mmu(vcpu); } void kvm_mmu_slot_remove_write_access(struct kvm *kvm, int slot) @@ -4428,7 +4382,7 @@ mmu_shrink_scan(struct shrinker *shrink, struct shrink_control *sc) int nr_to_scan = sc->nr_to_scan; unsigned long freed = 0; - raw_spin_lock(&kvm_lock); + spin_lock(&kvm_lock); list_for_each_entry(kvm, &vm_list, vm_list) { int idx; @@ -4478,9 +4432,8 @@ unlock: break; } - raw_spin_unlock(&kvm_lock); + spin_unlock(&kvm_lock); return freed; - } static unsigned long @@ -4574,7 +4527,7 @@ void kvm_mmu_destroy(struct kvm_vcpu *vcpu) { ASSERT(vcpu); - destroy_kvm_mmu(vcpu); + kvm_mmu_unload(vcpu); free_mmu_pages(vcpu); mmu_free_memory_caches(vcpu); } diff --git a/arch/x86/kvm/mmu.h b/arch/x86/kvm/mmu.h index 77e044a0f5f7..292615274358 100644 --- a/arch/x86/kvm/mmu.h +++ b/arch/x86/kvm/mmu.h @@ -70,8 +70,8 @@ enum { }; int handle_mmio_page_fault_common(struct kvm_vcpu *vcpu, u64 addr, bool direct); -int kvm_init_shadow_mmu(struct kvm_vcpu *vcpu, struct kvm_mmu *context); -int kvm_init_shadow_ept_mmu(struct kvm_vcpu *vcpu, struct kvm_mmu *context, +void kvm_init_shadow_mmu(struct kvm_vcpu *vcpu, struct kvm_mmu *context); +void kvm_init_shadow_ept_mmu(struct kvm_vcpu *vcpu, struct kvm_mmu *context, bool execonly); static inline unsigned int kvm_mmu_available_pages(struct kvm *kvm) diff --git a/arch/x86/kvm/mmu_audit.c b/arch/x86/kvm/mmu_audit.c index daff69e21150..1185fe7a7f47 100644 --- a/arch/x86/kvm/mmu_audit.c +++ b/arch/x86/kvm/mmu_audit.c @@ -296,4 +296,4 @@ static struct kernel_param_ops audit_param_ops = { .get = param_get_bool, }; -module_param_cb(mmu_audit, &audit_param_ops, &mmu_audit, 0644); +arch_param_cb(mmu_audit, &audit_param_ops, &mmu_audit, 0644); diff --git a/arch/x86/kvm/svm.c b/arch/x86/kvm/svm.c index c0bc80391e40..c7168a5cff1b 100644 --- a/arch/x86/kvm/svm.c +++ b/arch/x86/kvm/svm.c @@ -1959,11 +1959,9 @@ static void nested_svm_inject_npf_exit(struct kvm_vcpu *vcpu, nested_svm_vmexit(svm); } -static int nested_svm_init_mmu_context(struct kvm_vcpu *vcpu) +static void nested_svm_init_mmu_context(struct kvm_vcpu *vcpu) { - int r; - - r = kvm_init_shadow_mmu(vcpu, &vcpu->arch.mmu); + kvm_init_shadow_mmu(vcpu, &vcpu->arch.mmu); vcpu->arch.mmu.set_cr3 = nested_svm_set_tdp_cr3; vcpu->arch.mmu.get_cr3 = nested_svm_get_tdp_cr3; @@ -1971,8 +1969,6 @@ static int nested_svm_init_mmu_context(struct kvm_vcpu *vcpu) vcpu->arch.mmu.inject_page_fault = nested_svm_inject_npf_exit; vcpu->arch.mmu.shadow_root_level = get_npt_level(); vcpu->arch.walk_mmu = &vcpu->arch.nested_mmu; - - return r; } static void nested_svm_uninit_mmu_context(struct kvm_vcpu *vcpu) diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c index 2b2fce1b2009..b2fe1c252f35 100644 --- a/arch/x86/kvm/vmx.c +++ b/arch/x86/kvm/vmx.c @@ -1498,7 +1498,7 @@ static void add_atomic_switch_msr(struct vcpu_vmx *vmx, unsigned msr, break; if (i == NR_AUTOLOAD_MSRS) { - printk_once(KERN_WARNING"Not enough mst switch entries. " + printk_once(KERN_WARNING "Not enough msr switch entries. " "Can't add msr %x\n", msr); return; } else if (i == m->nr) { @@ -1898,16 +1898,12 @@ static void skip_emulated_instruction(struct kvm_vcpu *vcpu) /* * KVM wants to inject page-faults which it got to the guest. This function * checks whether in a nested guest, we need to inject them to L1 or L2. - * This function assumes it is called with the exit reason in vmcs02 being - * a #PF exception (this is the only case in which KVM injects a #PF when L2 - * is running). */ -static int nested_pf_handled(struct kvm_vcpu *vcpu) +static int nested_vmx_check_exception(struct kvm_vcpu *vcpu, unsigned nr) { struct vmcs12 *vmcs12 = get_vmcs12(vcpu); - /* TODO: also check PFEC_MATCH/MASK, not just EB.PF. */ - if (!(vmcs12->exception_bitmap & (1u << PF_VECTOR))) + if (!(vmcs12->exception_bitmap & (1u << nr))) return 0; nested_vmx_vmexit(vcpu); @@ -1921,8 +1917,8 @@ static void vmx_queue_exception(struct kvm_vcpu *vcpu, unsigned nr, struct vcpu_vmx *vmx = to_vmx(vcpu); u32 intr_info = nr | INTR_INFO_VALID_MASK; - if (nr == PF_VECTOR && is_guest_mode(vcpu) && - !vmx->nested.nested_run_pending && nested_pf_handled(vcpu)) + if (!reinject && is_guest_mode(vcpu) && + nested_vmx_check_exception(vcpu, nr)) return; if (has_error_code) { @@ -2204,9 +2200,15 @@ static __init void nested_vmx_setup_ctls_msrs(void) #ifdef CONFIG_X86_64 VM_EXIT_HOST_ADDR_SPACE_SIZE | #endif - VM_EXIT_LOAD_IA32_PAT | VM_EXIT_SAVE_IA32_PAT; + VM_EXIT_LOAD_IA32_PAT | VM_EXIT_SAVE_IA32_PAT | + VM_EXIT_SAVE_VMX_PREEMPTION_TIMER; + if (!(nested_vmx_pinbased_ctls_high & PIN_BASED_VMX_PREEMPTION_TIMER) || + !(nested_vmx_exit_ctls_high & VM_EXIT_SAVE_VMX_PREEMPTION_TIMER)) { + nested_vmx_exit_ctls_high &= ~VM_EXIT_SAVE_VMX_PREEMPTION_TIMER; + nested_vmx_pinbased_ctls_high &= ~PIN_BASED_VMX_PREEMPTION_TIMER; + } nested_vmx_exit_ctls_high |= (VM_EXIT_ALWAYSON_WITHOUT_TRUE_MSR | - VM_EXIT_LOAD_IA32_EFER); + VM_EXIT_LOAD_IA32_EFER | VM_EXIT_SAVE_IA32_EFER); /* entry controls */ rdmsr(MSR_IA32_VMX_ENTRY_CTLS, @@ -2226,7 +2228,8 @@ static __init void nested_vmx_setup_ctls_msrs(void) nested_vmx_procbased_ctls_low, nested_vmx_procbased_ctls_high); nested_vmx_procbased_ctls_low = 0; nested_vmx_procbased_ctls_high &= - CPU_BASED_VIRTUAL_INTR_PENDING | CPU_BASED_USE_TSC_OFFSETING | + CPU_BASED_VIRTUAL_INTR_PENDING | + CPU_BASED_VIRTUAL_NMI_PENDING | CPU_BASED_USE_TSC_OFFSETING | CPU_BASED_HLT_EXITING | CPU_BASED_INVLPG_EXITING | CPU_BASED_MWAIT_EXITING | CPU_BASED_CR3_LOAD_EXITING | CPU_BASED_CR3_STORE_EXITING | @@ -2252,13 +2255,15 @@ static __init void nested_vmx_setup_ctls_msrs(void) nested_vmx_secondary_ctls_low = 0; nested_vmx_secondary_ctls_high &= SECONDARY_EXEC_VIRTUALIZE_APIC_ACCESSES | + SECONDARY_EXEC_UNRESTRICTED_GUEST | SECONDARY_EXEC_WBINVD_EXITING; if (enable_ept) { /* nested EPT: emulate EPT also to L1 */ nested_vmx_secondary_ctls_high |= SECONDARY_EXEC_ENABLE_EPT; nested_vmx_ept_caps = VMX_EPT_PAGE_WALK_4_BIT | - VMX_EPTP_WB_BIT | VMX_EPT_INVEPT_BIT; + VMX_EPTP_WB_BIT | VMX_EPT_2MB_PAGE_BIT | + VMX_EPT_INVEPT_BIT; nested_vmx_ept_caps &= vmx_capability.ept; /* * Since invept is completely emulated we support both global @@ -3380,8 +3385,10 @@ static void vmx_set_cr3(struct kvm_vcpu *vcpu, unsigned long cr3) if (enable_ept) { eptp = construct_eptp(cr3); vmcs_write64(EPT_POINTER, eptp); - guest_cr3 = is_paging(vcpu) ? kvm_read_cr3(vcpu) : - vcpu->kvm->arch.ept_identity_map_addr; + if (is_paging(vcpu) || is_guest_mode(vcpu)) + guest_cr3 = kvm_read_cr3(vcpu); + else + guest_cr3 = vcpu->kvm->arch.ept_identity_map_addr; ept_load_pdptrs(vcpu); } @@ -4879,6 +4886,17 @@ vmx_patch_hypercall(struct kvm_vcpu *vcpu, unsigned char *hypercall) hypercall[2] = 0xc1; } +static bool nested_cr0_valid(struct vmcs12 *vmcs12, unsigned long val) +{ + unsigned long always_on = VMXON_CR0_ALWAYSON; + + if (nested_vmx_secondary_ctls_high & + SECONDARY_EXEC_UNRESTRICTED_GUEST && + nested_cpu_has2(vmcs12, SECONDARY_EXEC_UNRESTRICTED_GUEST)) + always_on &= ~(X86_CR0_PE | X86_CR0_PG); + return (val & always_on) == always_on; +} + /* called to set cr0 as appropriate for a mov-to-cr0 exit. */ static int handle_set_cr0(struct kvm_vcpu *vcpu, unsigned long val) { @@ -4897,9 +4915,7 @@ static int handle_set_cr0(struct kvm_vcpu *vcpu, unsigned long val) val = (val & ~vmcs12->cr0_guest_host_mask) | (vmcs12->guest_cr0 & vmcs12->cr0_guest_host_mask); - /* TODO: will have to take unrestricted guest mode into - * account */ - if ((val & VMXON_CR0_ALWAYSON) != VMXON_CR0_ALWAYSON) + if (!nested_cr0_valid(vmcs12, val)) return 1; if (kvm_set_cr0(vcpu, val)) @@ -6627,6 +6643,9 @@ static bool nested_vmx_exit_handled(struct kvm_vcpu *vcpu) return 0; else if (is_page_fault(intr_info)) return enable_ept; + else if (is_no_device(intr_info) && + !(nested_read_cr0(vmcs12) & X86_CR0_TS)) + return 0; return vmcs12->exception_bitmap & (1u << (intr_info & INTR_INFO_VECTOR_MASK)); case EXIT_REASON_EXTERNAL_INTERRUPT: @@ -6722,6 +6741,27 @@ static void vmx_get_exit_info(struct kvm_vcpu *vcpu, u64 *info1, u64 *info2) *info2 = vmcs_read32(VM_EXIT_INTR_INFO); } +static void nested_adjust_preemption_timer(struct kvm_vcpu *vcpu) +{ + u64 delta_tsc_l1; + u32 preempt_val_l1, preempt_val_l2, preempt_scale; + + if (!(get_vmcs12(vcpu)->pin_based_vm_exec_control & + PIN_BASED_VMX_PREEMPTION_TIMER)) + return; + preempt_scale = native_read_msr(MSR_IA32_VMX_MISC) & + MSR_IA32_VMX_MISC_PREEMPTION_TIMER_SCALE; + preempt_val_l2 = vmcs_read32(VMX_PREEMPTION_TIMER_VALUE); + delta_tsc_l1 = vmx_read_l1_tsc(vcpu, native_read_tsc()) + - vcpu->arch.last_guest_tsc; + preempt_val_l1 = delta_tsc_l1 >> preempt_scale; + if (preempt_val_l2 <= preempt_val_l1) + preempt_val_l2 = 0; + else + preempt_val_l2 -= preempt_val_l1; + vmcs_write32(VMX_PREEMPTION_TIMER_VALUE, preempt_val_l2); +} + /* * The guest has exited. See if we can fix it or if we need userspace * assistance. @@ -6736,20 +6776,6 @@ static int vmx_handle_exit(struct kvm_vcpu *vcpu) if (vmx->emulation_required) return handle_invalid_guest_state(vcpu); - /* - * the KVM_REQ_EVENT optimization bit is only on for one entry, and if - * we did not inject a still-pending event to L1 now because of - * nested_run_pending, we need to re-enable this bit. - */ - if (vmx->nested.nested_run_pending) - kvm_make_request(KVM_REQ_EVENT, vcpu); - - if (!is_guest_mode(vcpu) && (exit_reason == EXIT_REASON_VMLAUNCH || - exit_reason == EXIT_REASON_VMRESUME)) - vmx->nested.nested_run_pending = 1; - else - vmx->nested.nested_run_pending = 0; - if (is_guest_mode(vcpu) && nested_vmx_exit_handled(vcpu)) { nested_vmx_vmexit(vcpu); return 1; @@ -7061,9 +7087,9 @@ static void __vmx_complete_interrupts(struct kvm_vcpu *vcpu, case INTR_TYPE_HARD_EXCEPTION: if (idt_vectoring_info & VECTORING_INFO_DELIVER_CODE_MASK) { u32 err = vmcs_read32(error_code_field); - kvm_queue_exception_e(vcpu, vector, err); + kvm_requeue_exception_e(vcpu, vector, err); } else - kvm_queue_exception(vcpu, vector); + kvm_requeue_exception(vcpu, vector); break; case INTR_TYPE_SOFT_INTR: vcpu->arch.event_exit_inst_len = vmcs_read32(instr_len_field); @@ -7146,6 +7172,8 @@ static void __noclone vmx_vcpu_run(struct kvm_vcpu *vcpu) atomic_switch_perf_msrs(vmx); debugctlmsr = get_debugctlmsr(); + if (is_guest_mode(vcpu) && !vmx->nested.nested_run_pending) + nested_adjust_preemption_timer(vcpu); vmx->__launched = vmx->loaded_vmcs->launched; asm( /* Store host registers */ @@ -7284,6 +7312,16 @@ static void __noclone vmx_vcpu_run(struct kvm_vcpu *vcpu) 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 + * we did not inject a still-pending event to L1 now because of + * nested_run_pending, we need to re-enable this bit. + */ + if (vmx->nested.nested_run_pending) + kvm_make_request(KVM_REQ_EVENT, vcpu); + + vmx->nested.nested_run_pending = 0; + vmx_complete_atomic_exit(vmx); vmx_recover_nmi_blocking(vmx); vmx_complete_interrupts(vmx); @@ -7410,8 +7448,7 @@ static u64 vmx_get_mt_mask(struct kvm_vcpu *vcpu, gfn_t gfn, bool is_mmio) */ if (is_mmio) ret = MTRR_TYPE_UNCACHABLE << VMX_EPT_MT_EPTE_SHIFT; - else if (vcpu->kvm->arch.iommu_domain && - !(vcpu->kvm->arch.iommu_flags & KVM_IOMMU_CACHE_COHERENCY)) + else if (kvm_arch_has_noncoherent_dma(vcpu->kvm)) ret = kvm_get_guest_memory_type(vcpu, gfn) << VMX_EPT_MT_EPTE_SHIFT; else @@ -7501,9 +7538,9 @@ static unsigned long nested_ept_get_cr3(struct kvm_vcpu *vcpu) return get_vmcs12(vcpu)->ept_pointer; } -static int nested_ept_init_mmu_context(struct kvm_vcpu *vcpu) +static void nested_ept_init_mmu_context(struct kvm_vcpu *vcpu) { - int r = kvm_init_shadow_ept_mmu(vcpu, &vcpu->arch.mmu, + kvm_init_shadow_ept_mmu(vcpu, &vcpu->arch.mmu, nested_vmx_ept_caps & VMX_EPT_EXECUTE_ONLY_BIT); vcpu->arch.mmu.set_cr3 = vmx_set_cr3; @@ -7511,8 +7548,6 @@ static int nested_ept_init_mmu_context(struct kvm_vcpu *vcpu) vcpu->arch.mmu.inject_page_fault = nested_ept_inject_page_fault; vcpu->arch.walk_mmu = &vcpu->arch.nested_mmu; - - return r; } static void nested_ept_uninit_mmu_context(struct kvm_vcpu *vcpu) @@ -7520,6 +7555,20 @@ static void nested_ept_uninit_mmu_context(struct kvm_vcpu *vcpu) vcpu->arch.walk_mmu = &vcpu->arch.mmu; } +static void vmx_inject_page_fault_nested(struct kvm_vcpu *vcpu, + struct x86_exception *fault) +{ + struct vmcs12 *vmcs12 = get_vmcs12(vcpu); + + WARN_ON(!is_guest_mode(vcpu)); + + /* TODO: also check PFEC_MATCH/MASK, not just EB.PF. */ + if (vmcs12->exception_bitmap & (1u << PF_VECTOR)) + nested_vmx_vmexit(vcpu); + else + kvm_inject_page_fault(vcpu, fault); +} + /* * prepare_vmcs02 is called when the L1 guest hypervisor runs its nested * L2 guest. L1 has a vmcs for L2 (vmcs12), and this function "merges" it @@ -7533,6 +7582,7 @@ static void prepare_vmcs02(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12) { struct vcpu_vmx *vmx = to_vmx(vcpu); u32 exec_control; + u32 exit_control; vmcs_write16(GUEST_ES_SELECTOR, vmcs12->guest_es_selector); vmcs_write16(GUEST_CS_SELECTOR, vmcs12->guest_cs_selector); @@ -7706,7 +7756,10 @@ static void prepare_vmcs02(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12) * we should use its exit controls. Note that VM_EXIT_LOAD_IA32_EFER * bits are further modified by vmx_set_efer() below. */ - vmcs_write32(VM_EXIT_CONTROLS, vmcs_config.vmexit_ctrl); + exit_control = vmcs_config.vmexit_ctrl; + if (vmcs12->pin_based_vm_exec_control & PIN_BASED_VMX_PREEMPTION_TIMER) + exit_control |= VM_EXIT_SAVE_VMX_PREEMPTION_TIMER; + vmcs_write32(VM_EXIT_CONTROLS, exit_control); /* vmcs12's VM_ENTRY_LOAD_IA32_EFER and VM_ENTRY_IA32E_MODE are * emulated by vmx_set_efer(), below. @@ -7773,6 +7826,9 @@ static void prepare_vmcs02(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12) kvm_set_cr3(vcpu, vmcs12->guest_cr3); kvm_mmu_reset_context(vcpu); + if (!enable_ept) + vcpu->arch.walk_mmu->inject_page_fault = vmx_inject_page_fault_nested; + /* * L1 may access the L2's PDPTR, so save them to construct vmcs12 */ @@ -7876,7 +7932,7 @@ static int nested_vmx_run(struct kvm_vcpu *vcpu, bool launch) return 1; } - if (((vmcs12->guest_cr0 & VMXON_CR0_ALWAYSON) != VMXON_CR0_ALWAYSON) || + if (!nested_cr0_valid(vmcs12, vmcs12->guest_cr0) || ((vmcs12->guest_cr4 & VMXON_CR4_ALWAYSON) != VMXON_CR4_ALWAYSON)) { nested_vmx_entry_failure(vcpu, vmcs12, EXIT_REASON_INVALID_STATE, ENTRY_FAIL_DEFAULT); @@ -7938,6 +7994,8 @@ static int nested_vmx_run(struct kvm_vcpu *vcpu, bool launch) enter_guest_mode(vcpu); + vmx->nested.nested_run_pending = 1; + vmx->nested.vmcs01_tsc_offset = vmcs_read64(TSC_OFFSET); cpu = get_cpu(); @@ -8005,7 +8063,7 @@ static void vmcs12_save_pending_event(struct kvm_vcpu *vcpu, u32 idt_vectoring; unsigned int nr; - if (vcpu->arch.exception.pending) { + if (vcpu->arch.exception.pending && vcpu->arch.exception.reinject) { nr = vcpu->arch.exception.nr; idt_vectoring = nr | VECTORING_INFO_VALID_MASK; @@ -8023,7 +8081,7 @@ static void vmcs12_save_pending_event(struct kvm_vcpu *vcpu, } vmcs12->idt_vectoring_info_field = idt_vectoring; - } else if (vcpu->arch.nmi_pending) { + } else if (vcpu->arch.nmi_injected) { vmcs12->idt_vectoring_info_field = INTR_TYPE_NMI_INTR | INTR_INFO_VALID_MASK | NMI_VECTOR; } else if (vcpu->arch.interrupt.pending) { @@ -8105,6 +8163,11 @@ static void prepare_vmcs12(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12) vmcs12->guest_pending_dbg_exceptions = vmcs_readl(GUEST_PENDING_DBG_EXCEPTIONS); + if ((vmcs12->pin_based_vm_exec_control & PIN_BASED_VMX_PREEMPTION_TIMER) && + (vmcs12->vm_exit_controls & VM_EXIT_SAVE_VMX_PREEMPTION_TIMER)) + vmcs12->vmx_preemption_timer_value = + vmcs_read32(VMX_PREEMPTION_TIMER_VALUE); + /* * In some cases (usually, nested EPT), L2 is allowed to change its * own CR3 without exiting. If it has changed it, we must keep it. @@ -8130,6 +8193,8 @@ static void prepare_vmcs12(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12) vmcs12->guest_ia32_debugctl = vmcs_read64(GUEST_IA32_DEBUGCTL); if (vmcs12->vm_exit_controls & VM_EXIT_SAVE_IA32_PAT) vmcs12->guest_ia32_pat = vmcs_read64(GUEST_IA32_PAT); + if (vmcs12->vm_exit_controls & VM_EXIT_SAVE_IA32_EFER) + vmcs12->guest_ia32_efer = vcpu->arch.efer; vmcs12->guest_sysenter_cs = vmcs_read32(GUEST_SYSENTER_CS); vmcs12->guest_sysenter_esp = vmcs_readl(GUEST_SYSENTER_ESP); vmcs12->guest_sysenter_eip = vmcs_readl(GUEST_SYSENTER_EIP); @@ -8201,7 +8266,7 @@ static void load_vmcs12_host_state(struct kvm_vcpu *vcpu, * fpu_active (which may have changed). * Note that vmx_set_cr0 refers to efer set above. */ - kvm_set_cr0(vcpu, vmcs12->host_cr0); + vmx_set_cr0(vcpu, vmcs12->host_cr0); /* * If we did fpu_activate()/fpu_deactivate() during L2's run, we need * to apply the same changes to L1's vmcs. We just set cr0 correctly, @@ -8224,6 +8289,9 @@ static void load_vmcs12_host_state(struct kvm_vcpu *vcpu, kvm_set_cr3(vcpu, vmcs12->host_cr3); kvm_mmu_reset_context(vcpu); + if (!enable_ept) + vcpu->arch.walk_mmu->inject_page_fault = kvm_inject_page_fault; + if (enable_vpid) { /* * Trivially support vpid by letting L2s share their parent diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index e5ca72a5cdb6..21ef1ba184ae 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -577,6 +577,7 @@ static void kvm_put_guest_xcr0(struct kvm_vcpu *vcpu) int __kvm_set_xcr(struct kvm_vcpu *vcpu, u32 index, u64 xcr) { u64 xcr0; + u64 valid_bits; /* Only support XCR_XFEATURE_ENABLED_MASK(xcr0) now */ if (index != XCR_XFEATURE_ENABLED_MASK) @@ -586,8 +587,16 @@ int __kvm_set_xcr(struct kvm_vcpu *vcpu, u32 index, u64 xcr) return 1; if ((xcr0 & XSTATE_YMM) && !(xcr0 & XSTATE_SSE)) return 1; - if (xcr0 & ~host_xcr0) + + /* + * Do not allow the guest to set bits that we do not support + * saving. However, xcr0 bit 0 is always set, even if the + * emulated CPU does not support XSAVE (see fx_init). + */ + valid_bits = vcpu->arch.guest_supported_xcr0 | XSTATE_FP; + if (xcr0 & ~valid_bits) return 1; + kvm_put_guest_xcr0(vcpu); vcpu->arch.xcr0 = xcr0; return 0; @@ -684,7 +693,7 @@ int kvm_set_cr3(struct kvm_vcpu *vcpu, unsigned long cr3) vcpu->arch.cr3 = cr3; __set_bit(VCPU_EXREG_CR3, (ulong *)&vcpu->arch.regs_avail); - vcpu->arch.mmu.new_cr3(vcpu); + kvm_mmu_new_cr3(vcpu); return 0; } EXPORT_SYMBOL_GPL(kvm_set_cr3); @@ -2564,6 +2573,7 @@ int kvm_dev_ioctl_check_extension(long ext) case KVM_CAP_MMU_SHADOW_CACHE_CONTROL: case KVM_CAP_SET_TSS_ADDR: case KVM_CAP_EXT_CPUID: + case KVM_CAP_EXT_EMUL_CPUID: case KVM_CAP_CLOCKSOURCE: case KVM_CAP_PIT: case KVM_CAP_NOP_IO_DELAY: @@ -2673,15 +2683,17 @@ long kvm_arch_dev_ioctl(struct file *filp, r = 0; break; } - case KVM_GET_SUPPORTED_CPUID: { + case KVM_GET_SUPPORTED_CPUID: + case KVM_GET_EMULATED_CPUID: { struct kvm_cpuid2 __user *cpuid_arg = argp; struct kvm_cpuid2 cpuid; r = -EFAULT; if (copy_from_user(&cpuid, cpuid_arg, sizeof cpuid)) goto out; - r = kvm_dev_ioctl_get_supported_cpuid(&cpuid, - cpuid_arg->entries); + + r = kvm_dev_ioctl_get_cpuid(&cpuid, cpuid_arg->entries, + ioctl); if (r) goto out; @@ -2715,8 +2727,7 @@ static void wbinvd_ipi(void *garbage) static bool need_emulate_wbinvd(struct kvm_vcpu *vcpu) { - return vcpu->kvm->arch.iommu_domain && - !(vcpu->kvm->arch.iommu_flags & KVM_IOMMU_CACHE_COHERENCY); + return kvm_arch_has_noncoherent_dma(vcpu->kvm); } void kvm_arch_vcpu_load(struct kvm_vcpu *vcpu, int cpu) @@ -2984,11 +2995,13 @@ static int kvm_vcpu_ioctl_x86_set_debugregs(struct kvm_vcpu *vcpu, static void kvm_vcpu_ioctl_x86_get_xsave(struct kvm_vcpu *vcpu, struct kvm_xsave *guest_xsave) { - if (cpu_has_xsave) + if (cpu_has_xsave) { memcpy(guest_xsave->region, &vcpu->arch.guest_fpu.state->xsave, - xstate_size); - else { + vcpu->arch.guest_xstate_size); + *(u64 *)&guest_xsave->region[XSAVE_HDR_OFFSET / sizeof(u32)] &= + vcpu->arch.guest_supported_xcr0 | XSTATE_FPSSE; + } else { memcpy(guest_xsave->region, &vcpu->arch.guest_fpu.state->fxsave, sizeof(struct i387_fxsave_struct)); @@ -3003,10 +3016,19 @@ static int kvm_vcpu_ioctl_x86_set_xsave(struct kvm_vcpu *vcpu, u64 xstate_bv = *(u64 *)&guest_xsave->region[XSAVE_HDR_OFFSET / sizeof(u32)]; - if (cpu_has_xsave) + if (cpu_has_xsave) { + /* + * Here we allow setting states that are not present in + * CPUID leaf 0xD, index 0, EDX:EAX. This is for compatibility + * with old userspace. + */ + if (xstate_bv & ~KVM_SUPPORTED_XCR0) + return -EINVAL; + if (xstate_bv & ~host_xcr0) + return -EINVAL; memcpy(&vcpu->arch.guest_fpu.state->xsave, - guest_xsave->region, xstate_size); - else { + guest_xsave->region, vcpu->arch.guest_xstate_size); + } else { if (xstate_bv & ~XSTATE_FPSSE) return -EINVAL; memcpy(&vcpu->arch.guest_fpu.state->fxsave, @@ -3042,9 +3064,9 @@ static int kvm_vcpu_ioctl_x86_set_xcrs(struct kvm_vcpu *vcpu, for (i = 0; i < guest_xcrs->nr_xcrs; i++) /* Only support XCR0 currently */ - if (guest_xcrs->xcrs[0].xcr == XCR_XFEATURE_ENABLED_MASK) { + if (guest_xcrs->xcrs[i].xcr == XCR_XFEATURE_ENABLED_MASK) { r = __kvm_set_xcr(vcpu, XCR_XFEATURE_ENABLED_MASK, - guest_xcrs->xcrs[0].value); + guest_xcrs->xcrs[i].value); break; } if (r) @@ -4775,8 +4797,8 @@ static void inject_emulated_exception(struct kvm_vcpu *vcpu) static void init_decode_cache(struct x86_emulate_ctxt *ctxt) { - memset(&ctxt->twobyte, 0, - (void *)&ctxt->_regs - (void *)&ctxt->twobyte); + memset(&ctxt->opcode_len, 0, + (void *)&ctxt->_regs - (void *)&ctxt->opcode_len); ctxt->fetch.start = 0; ctxt->fetch.end = 0; @@ -5094,8 +5116,7 @@ int x86_emulate_instruction(struct kvm_vcpu *vcpu, ctxt->have_exception = false; ctxt->perm_ok = false; - ctxt->only_vendor_specific_insn - = emulation_type & EMULTYPE_TRAP_UD; + ctxt->ud = emulation_type & EMULTYPE_TRAP_UD; r = x86_decode_insn(ctxt, insn, insn_len); @@ -5263,7 +5284,7 @@ static int kvmclock_cpufreq_notifier(struct notifier_block *nb, unsigned long va smp_call_function_single(freq->cpu, tsc_khz_changed, freq, 1); - raw_spin_lock(&kvm_lock); + spin_lock(&kvm_lock); list_for_each_entry(kvm, &vm_list, vm_list) { kvm_for_each_vcpu(i, vcpu, kvm) { if (vcpu->cpu != freq->cpu) @@ -5273,7 +5294,7 @@ static int kvmclock_cpufreq_notifier(struct notifier_block *nb, unsigned long va send_ipi = 1; } } - raw_spin_unlock(&kvm_lock); + spin_unlock(&kvm_lock); if (freq->old < freq->new && send_ipi) { /* @@ -5426,12 +5447,12 @@ static void pvclock_gtod_update_fn(struct work_struct *work) struct kvm_vcpu *vcpu; int i; - raw_spin_lock(&kvm_lock); + spin_lock(&kvm_lock); list_for_each_entry(kvm, &vm_list, vm_list) kvm_for_each_vcpu(i, vcpu, kvm) set_bit(KVM_REQ_MASTERCLOCK_UPDATE, &vcpu->requests); atomic_set(&kvm_guest_has_master_clock, 0); - raw_spin_unlock(&kvm_lock); + spin_unlock(&kvm_lock); } static DECLARE_WORK(pvclock_gtod_work, pvclock_gtod_update_fn); @@ -5945,10 +5966,12 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu) vcpu->mode = IN_GUEST_MODE; + srcu_read_unlock(&vcpu->kvm->srcu, vcpu->srcu_idx); + /* We should set ->mode before check ->requests, * see the comment in make_all_cpus_request. */ - smp_mb(); + smp_mb__after_srcu_read_unlock(); local_irq_disable(); @@ -5958,12 +5981,11 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu) smp_wmb(); local_irq_enable(); preempt_enable(); + vcpu->srcu_idx = srcu_read_lock(&vcpu->kvm->srcu); r = 1; goto cancel_injection; } - srcu_read_unlock(&vcpu->kvm->srcu, vcpu->srcu_idx); - if (req_immediate_exit) smp_send_reschedule(vcpu->cpu); @@ -6688,7 +6710,7 @@ int kvm_arch_vcpu_setup(struct kvm_vcpu *vcpu) if (r) return r; kvm_vcpu_reset(vcpu); - r = kvm_mmu_setup(vcpu); + kvm_mmu_setup(vcpu); vcpu_put(vcpu); return r; @@ -6940,6 +6962,10 @@ int kvm_arch_vcpu_init(struct kvm_vcpu *vcpu) vcpu->arch.ia32_tsc_adjust_msr = 0x0; vcpu->arch.pv_time_enabled = false; + + vcpu->arch.guest_supported_xcr0 = 0; + vcpu->arch.guest_xstate_size = XSAVE_HDR_SIZE + XSAVE_HDR_OFFSET; + kvm_async_pf_hash_reset(vcpu); kvm_pmu_init(vcpu); @@ -6981,6 +7007,7 @@ int kvm_arch_init_vm(struct kvm *kvm, unsigned long type) INIT_LIST_HEAD(&kvm->arch.active_mmu_pages); INIT_LIST_HEAD(&kvm->arch.zapped_obsolete_pages); INIT_LIST_HEAD(&kvm->arch.assigned_dev_head); + atomic_set(&kvm->arch.noncoherent_dma_count, 0); /* Reserve bit 0 of irq_sources_bitmap for userspace irq source */ set_bit(KVM_USERSPACE_IRQ_SOURCE_ID, &kvm->arch.irq_sources_bitmap); @@ -7065,7 +7092,7 @@ void kvm_arch_destroy_vm(struct kvm *kvm) kfree(rcu_dereference_check(kvm->arch.apic_map, 1)); } -void kvm_arch_free_memslot(struct kvm_memory_slot *free, +void kvm_arch_free_memslot(struct kvm *kvm, struct kvm_memory_slot *free, struct kvm_memory_slot *dont) { int i; @@ -7086,7 +7113,8 @@ void kvm_arch_free_memslot(struct kvm_memory_slot *free, } } -int kvm_arch_create_memslot(struct kvm_memory_slot *slot, unsigned long npages) +int kvm_arch_create_memslot(struct kvm *kvm, struct kvm_memory_slot *slot, + unsigned long npages) { int i; @@ -7283,7 +7311,7 @@ void kvm_arch_async_page_ready(struct kvm_vcpu *vcpu, struct kvm_async_pf *work) int r; if ((vcpu->arch.mmu.direct_map != work->arch.direct_map) || - is_error_page(work->page)) + work->wakeup_all) return; r = kvm_mmu_reload(vcpu); @@ -7393,7 +7421,7 @@ void kvm_arch_async_page_present(struct kvm_vcpu *vcpu, struct x86_exception fault; trace_kvm_async_pf_ready(work->arch.token, work->gva); - if (is_error_page(work->page)) + if (work->wakeup_all) work->arch.token = ~0; /* broadcast wakeup */ else kvm_del_async_pf_gfn(vcpu, work->arch.gfn); @@ -7420,6 +7448,24 @@ bool kvm_arch_can_inject_async_page_present(struct kvm_vcpu *vcpu) kvm_x86_ops->interrupt_allowed(vcpu); } +void kvm_arch_register_noncoherent_dma(struct kvm *kvm) +{ + atomic_inc(&kvm->arch.noncoherent_dma_count); +} +EXPORT_SYMBOL_GPL(kvm_arch_register_noncoherent_dma); + +void kvm_arch_unregister_noncoherent_dma(struct kvm *kvm) +{ + atomic_dec(&kvm->arch.noncoherent_dma_count); +} +EXPORT_SYMBOL_GPL(kvm_arch_unregister_noncoherent_dma); + +bool kvm_arch_has_noncoherent_dma(struct kvm *kvm) +{ + return atomic_read(&kvm->arch.noncoherent_dma_count); +} +EXPORT_SYMBOL_GPL(kvm_arch_has_noncoherent_dma); + EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_exit); EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_inj_virq); EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_page_fault); diff --git a/arch/x86/kvm/x86.h b/arch/x86/kvm/x86.h index e224f7a671b6..587fb9ede436 100644 --- a/arch/x86/kvm/x86.h +++ b/arch/x86/kvm/x86.h @@ -122,6 +122,7 @@ int kvm_write_guest_virt_system(struct x86_emulate_ctxt *ctxt, gva_t addr, void *val, unsigned int bytes, struct x86_exception *exception); +#define KVM_SUPPORTED_XCR0 (XSTATE_FP | XSTATE_SSE | XSTATE_YMM) extern u64 host_xcr0; extern struct static_key kvm_no_apic_vcpu; diff --git a/arch/x86/lib/msr-smp.c b/arch/x86/lib/msr-smp.c index a6b1b86d2253..518532e6a3fa 100644 --- a/arch/x86/lib/msr-smp.c +++ b/arch/x86/lib/msr-smp.c @@ -47,6 +47,21 @@ int rdmsr_on_cpu(unsigned int cpu, u32 msr_no, u32 *l, u32 *h) } EXPORT_SYMBOL(rdmsr_on_cpu); +int rdmsrl_on_cpu(unsigned int cpu, u32 msr_no, u64 *q) +{ + int err; + struct msr_info rv; + + memset(&rv, 0, sizeof(rv)); + + rv.msr_no = msr_no; + err = smp_call_function_single(cpu, __rdmsr_on_cpu, &rv, 1); + *q = rv.reg.q; + + return err; +} +EXPORT_SYMBOL(rdmsrl_on_cpu); + int wrmsr_on_cpu(unsigned int cpu, u32 msr_no, u32 l, u32 h) { int err; @@ -63,6 +78,22 @@ int wrmsr_on_cpu(unsigned int cpu, u32 msr_no, u32 l, u32 h) } EXPORT_SYMBOL(wrmsr_on_cpu); +int wrmsrl_on_cpu(unsigned int cpu, u32 msr_no, u64 q) +{ + int err; + struct msr_info rv; + + memset(&rv, 0, sizeof(rv)); + + rv.msr_no = msr_no; + rv.reg.q = q; + + err = smp_call_function_single(cpu, __wrmsr_on_cpu, &rv, 1); + + return err; +} +EXPORT_SYMBOL(wrmsrl_on_cpu); + static void __rwmsr_on_cpus(const struct cpumask *mask, u32 msr_no, struct msr *msrs, void (*msr_func) (void *info)) @@ -159,6 +190,37 @@ int wrmsr_safe_on_cpu(unsigned int cpu, u32 msr_no, u32 l, u32 h) } EXPORT_SYMBOL(wrmsr_safe_on_cpu); +int wrmsrl_safe_on_cpu(unsigned int cpu, u32 msr_no, u64 q) +{ + int err; + struct msr_info rv; + + memset(&rv, 0, sizeof(rv)); + + rv.msr_no = msr_no; + rv.reg.q = q; + + err = smp_call_function_single(cpu, __wrmsr_safe_on_cpu, &rv, 1); + + return err ? err : rv.err; +} +EXPORT_SYMBOL(wrmsrl_safe_on_cpu); + +int rdmsrl_safe_on_cpu(unsigned int cpu, u32 msr_no, u64 *q) +{ + int err; + struct msr_info rv; + + memset(&rv, 0, sizeof(rv)); + + rv.msr_no = msr_no; + err = smp_call_function_single(cpu, __rdmsr_safe_on_cpu, &rv, 1); + *q = rv.reg.q; + + return err ? err : rv.err; +} +EXPORT_SYMBOL(rdmsrl_safe_on_cpu); + /* * These variants are significantly slower, but allows control over * the entire 32-bit GPR set. diff --git a/arch/x86/mm/Makefile b/arch/x86/mm/Makefile index 23d8e5fecf76..6a19ad9f370d 100644 --- a/arch/x86/mm/Makefile +++ b/arch/x86/mm/Makefile @@ -6,6 +6,8 @@ nostackp := $(call cc-option, -fno-stack-protector) CFLAGS_physaddr.o := $(nostackp) CFLAGS_setup_nx.o := $(nostackp) +CFLAGS_fault.o := -I$(src)/../include/asm/trace + obj-$(CONFIG_X86_PAT) += pat_rbtree.o obj-$(CONFIG_SMP) += tlb.o diff --git a/arch/x86/mm/fault.c b/arch/x86/mm/fault.c index 7a517bb41060..9ff85bb8dd69 100644 --- a/arch/x86/mm/fault.c +++ b/arch/x86/mm/fault.c @@ -20,6 +20,9 @@ #include <asm/kmemcheck.h> /* kmemcheck_*(), ... */ #include <asm/fixmap.h> /* VSYSCALL_START */ +#define CREATE_TRACE_POINTS +#include <asm/trace/exceptions.h> + /* * Page fault error code bits: * @@ -596,7 +599,7 @@ show_fault_oops(struct pt_regs *regs, unsigned long error_code, printk(KERN_CONT " at %p\n", (void *) address); printk(KERN_ALERT "IP:"); - printk_address(regs->ip, 1); + printk_address(regs->ip); dump_pagetable(address); } @@ -1232,3 +1235,23 @@ do_page_fault(struct pt_regs *regs, unsigned long error_code) __do_page_fault(regs, error_code); exception_exit(prev_state); } + +static void trace_page_fault_entries(struct pt_regs *regs, + unsigned long error_code) +{ + if (user_mode(regs)) + trace_page_fault_user(read_cr2(), regs, error_code); + else + trace_page_fault_kernel(read_cr2(), regs, error_code); +} + +dotraplinkage void __kprobes +trace_do_page_fault(struct pt_regs *regs, unsigned long error_code) +{ + enum ctx_state prev_state; + + prev_state = exception_enter(); + trace_page_fault_entries(regs, error_code); + __do_page_fault(regs, error_code); + exception_exit(prev_state); +} diff --git a/arch/x86/mm/pgtable.c b/arch/x86/mm/pgtable.c index dfa537a03be1..c96314abd144 100644 --- a/arch/x86/mm/pgtable.c +++ b/arch/x86/mm/pgtable.c @@ -25,8 +25,12 @@ pgtable_t pte_alloc_one(struct mm_struct *mm, unsigned long address) struct page *pte; pte = alloc_pages(__userpte_alloc_gfp, 0); - if (pte) - pgtable_page_ctor(pte); + if (!pte) + return NULL; + if (!pgtable_page_ctor(pte)) { + __free_page(pte); + return NULL; + } return pte; } @@ -57,6 +61,7 @@ void ___pte_free_tlb(struct mmu_gather *tlb, struct page *pte) #if PAGETABLE_LEVELS > 2 void ___pmd_free_tlb(struct mmu_gather *tlb, pmd_t *pmd) { + struct page *page = virt_to_page(pmd); paravirt_release_pmd(__pa(pmd) >> PAGE_SHIFT); /* * NOTE! For PAE, any changes to the top page-directory-pointer-table @@ -65,7 +70,8 @@ void ___pmd_free_tlb(struct mmu_gather *tlb, pmd_t *pmd) #ifdef CONFIG_X86_PAE tlb->need_flush_all = 1; #endif - tlb_remove_page(tlb, virt_to_page(pmd)); + pgtable_pmd_page_dtor(page); + tlb_remove_page(tlb, page); } #if PAGETABLE_LEVELS > 3 @@ -189,8 +195,10 @@ static void free_pmds(pmd_t *pmds[]) int i; for(i = 0; i < PREALLOCATED_PMDS; i++) - if (pmds[i]) + if (pmds[i]) { + pgtable_pmd_page_dtor(virt_to_page(pmds[i])); free_page((unsigned long)pmds[i]); + } } static int preallocate_pmds(pmd_t *pmds[]) @@ -200,8 +208,13 @@ static int preallocate_pmds(pmd_t *pmds[]) for(i = 0; i < PREALLOCATED_PMDS; i++) { pmd_t *pmd = (pmd_t *)__get_free_page(PGALLOC_GFP); - if (pmd == NULL) + if (!pmd) failed = true; + if (pmd && !pgtable_pmd_page_ctor(virt_to_page(pmd))) { + free_page((unsigned long)pmd); + pmd = NULL; + failed = true; + } pmds[i] = pmd; } diff --git a/arch/x86/pci/acpi.c b/arch/x86/pci/acpi.c index b30e937689d6..4f25ec077552 100644 --- a/arch/x86/pci/acpi.c +++ b/arch/x86/pci/acpi.c @@ -354,12 +354,12 @@ static void coalesce_windows(struct pci_root_info *info, unsigned long type) * the kernel resource tree doesn't allow overlaps. */ if (resource_overlaps(res1, res2)) { - res1->start = min(res1->start, res2->start); - res1->end = max(res1->end, res2->end); + res2->start = min(res1->start, res2->start); + res2->end = max(res1->end, res2->end); dev_info(&info->bridge->dev, "host bridge window expanded to %pR; %pR ignored\n", - res1, res2); - res2->flags = 0; + res2, res1); + res1->flags = 0; } } } @@ -518,7 +518,7 @@ struct pci_bus *pci_acpi_scan_root(struct acpi_pci_root *root) sd = &info->sd; sd->domain = domain; sd->node = node; - sd->acpi = device->handle; + sd->companion = device; /* * Maybe the desired pci bus has been already scanned. In such case * it is unnecessary to scan the pci bus with the given domain,busnum. @@ -589,7 +589,7 @@ int pcibios_root_bridge_prepare(struct pci_host_bridge *bridge) { struct pci_sysdata *sd = bridge->bus->sysdata; - ACPI_HANDLE_SET(&bridge->dev, sd->acpi); + ACPI_COMPANION_SET(&bridge->dev, sd->companion); return 0; } diff --git a/arch/x86/pci/fixup.c b/arch/x86/pci/fixup.c index f5809fa2753e..b046e070e088 100644 --- a/arch/x86/pci/fixup.c +++ b/arch/x86/pci/fixup.c @@ -231,7 +231,7 @@ static int quirk_pcie_aspm_write(struct pci_bus *bus, unsigned int devfn, int wh offset = quirk_aspm_offset[GET_INDEX(bus->self->device, devfn)]; if ((offset) && (where == offset)) - value = value & 0xfffffffc; + value = value & ~PCI_EXP_LNKCTL_ASPMC; return raw_pci_write(pci_domain_nr(bus), bus->number, devfn, where, size, value); @@ -252,7 +252,7 @@ static struct pci_ops quirk_pcie_aspm_ops = { */ static void pcie_rootport_aspm_quirk(struct pci_dev *pdev) { - int cap_base, i; + int i; struct pci_bus *pbus; struct pci_dev *dev; @@ -278,7 +278,7 @@ static void pcie_rootport_aspm_quirk(struct pci_dev *pdev) for (i = GET_INDEX(pdev->device, 0); i <= GET_INDEX(pdev->device, 7); ++i) quirk_aspm_offset[i] = 0; - pbus->ops = pbus->parent->ops; + pci_bus_set_ops(pbus, pbus->parent->ops); } else { /* * If devices are attached to the root port at power-up or @@ -286,13 +286,15 @@ static void pcie_rootport_aspm_quirk(struct pci_dev *pdev) * each root port to save the register offsets and replace the * bus ops. */ - list_for_each_entry(dev, &pbus->devices, bus_list) { + list_for_each_entry(dev, &pbus->devices, bus_list) /* There are 0 to 8 devices attached to this bus */ - cap_base = pci_find_capability(dev, PCI_CAP_ID_EXP); - quirk_aspm_offset[GET_INDEX(pdev->device, dev->devfn)] = cap_base + 0x10; - } - pbus->ops = &quirk_pcie_aspm_ops; + quirk_aspm_offset[GET_INDEX(pdev->device, dev->devfn)] = + dev->pcie_cap + PCI_EXP_LNKCTL; + + pci_bus_set_ops(pbus, &quirk_pcie_aspm_ops); + dev_info(&pbus->dev, "writes to ASPM control bits will be ignored\n"); } + } DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_MCH_PA, pcie_rootport_aspm_quirk); DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_MCH_PA1, pcie_rootport_aspm_quirk); diff --git a/arch/x86/pci/xen.c b/arch/x86/pci/xen.c index 48e8461057ba..5eee4959785d 100644 --- a/arch/x86/pci/xen.c +++ b/arch/x86/pci/xen.c @@ -382,7 +382,14 @@ static void xen_teardown_msi_irq(unsigned int irq) { xen_destroy_irq(irq); } - +static u32 xen_nop_msi_mask_irq(struct msi_desc *desc, u32 mask, u32 flag) +{ + return 0; +} +static u32 xen_nop_msix_mask_irq(struct msi_desc *desc, u32 flag) +{ + return 0; +} #endif int __init pci_xen_init(void) @@ -406,6 +413,8 @@ int __init pci_xen_init(void) x86_msi.setup_msi_irqs = xen_setup_msi_irqs; x86_msi.teardown_msi_irq = xen_teardown_msi_irq; x86_msi.teardown_msi_irqs = xen_teardown_msi_irqs; + x86_msi.msi_mask_irq = xen_nop_msi_mask_irq; + x86_msi.msix_mask_irq = xen_nop_msix_mask_irq; #endif return 0; } @@ -485,6 +494,8 @@ int __init pci_xen_initial_domain(void) x86_msi.setup_msi_irqs = xen_initdom_setup_msi_irqs; x86_msi.teardown_msi_irq = xen_teardown_msi_irq; x86_msi.restore_msi_irqs = xen_initdom_restore_msi_irqs; + x86_msi.msi_mask_irq = xen_nop_msi_mask_irq; + x86_msi.msix_mask_irq = xen_nop_msix_mask_irq; #endif xen_setup_acpi_sci(); __acpi_register_gsi = acpi_register_gsi_xen; diff --git a/arch/x86/platform/olpc/olpc-xo15-sci.c b/arch/x86/platform/olpc/olpc-xo15-sci.c index fef7d0ba7e3a..649a12befba9 100644 --- a/arch/x86/platform/olpc/olpc-xo15-sci.c +++ b/arch/x86/platform/olpc/olpc-xo15-sci.c @@ -40,16 +40,9 @@ static bool lid_wake_on_close; */ static int set_lid_wake_behavior(bool wake_on_close) { - struct acpi_object_list arg_list; - union acpi_object arg; acpi_status status; - arg_list.count = 1; - arg_list.pointer = &arg; - arg.type = ACPI_TYPE_INTEGER; - arg.integer.value = wake_on_close; - - status = acpi_evaluate_object(NULL, "\\_SB.PCI0.LID.LIDW", &arg_list, NULL); + status = acpi_execute_simple_method(NULL, "\\_SB.PCI0.LID.LIDW", wake_on_close); if (ACPI_FAILURE(status)) { pr_warning(PFX "failed to set lid behavior\n"); return 1; diff --git a/arch/x86/platform/uv/uv_nmi.c b/arch/x86/platform/uv/uv_nmi.c index 2e863ad4a772..8eeccba73130 100644 --- a/arch/x86/platform/uv/uv_nmi.c +++ b/arch/x86/platform/uv/uv_nmi.c @@ -399,7 +399,7 @@ static void uv_nmi_dump_cpu_ip(int cpu, struct pt_regs *regs) printk(KERN_DEFAULT "UV: %4d %6d %-32.32s ", cpu, current->pid, current->comm); - printk_address(regs->ip, 1); + printk_address(regs->ip); } /* Dump this cpu's state */ diff --git a/arch/x86/um/Kconfig b/arch/x86/um/Kconfig index 14ef8d1dbc33..ed56a1c4ae73 100644 --- a/arch/x86/um/Kconfig +++ b/arch/x86/um/Kconfig @@ -31,6 +31,11 @@ config X86_64 def_bool 64BIT select MODULES_USE_ELF_RELA +config ARCH_DEFCONFIG + string + default "arch/um/configs/i386_defconfig" if X86_32 + default "arch/um/configs/x86_64_defconfig" if X86_64 + config RWSEM_XCHGADD_ALGORITHM def_bool 64BIT diff --git a/arch/x86/um/asm/processor_32.h b/arch/x86/um/asm/processor_32.h index 6c6689e574ce..c112de81c9e1 100644 --- a/arch/x86/um/asm/processor_32.h +++ b/arch/x86/um/asm/processor_32.h @@ -33,6 +33,8 @@ struct arch_thread { .faultinfo = { 0, 0, 0 } \ } +#define STACKSLOTS_PER_LINE 8 + static inline void arch_flush_thread(struct arch_thread *thread) { /* Clear any TLS still hanging */ @@ -53,4 +55,7 @@ static inline void arch_copy_thread(struct arch_thread *from, #define current_text_addr() \ ({ void *pc; __asm__("movl $1f,%0\n1:":"=g" (pc)); pc; }) +#define current_sp() ({ void *sp; __asm__("movl %%esp, %0" : "=r" (sp) : ); sp; }) +#define current_bp() ({ unsigned long bp; __asm__("movl %%ebp, %0" : "=r" (bp) : ); bp; }) + #endif diff --git a/arch/x86/um/asm/processor_64.h b/arch/x86/um/asm/processor_64.h index 4b02a8455bd1..c3be85205a65 100644 --- a/arch/x86/um/asm/processor_64.h +++ b/arch/x86/um/asm/processor_64.h @@ -19,6 +19,8 @@ struct arch_thread { .fs = 0, \ .faultinfo = { 0, 0, 0 } } +#define STACKSLOTS_PER_LINE 4 + static inline void arch_flush_thread(struct arch_thread *thread) { } @@ -32,4 +34,7 @@ static inline void arch_copy_thread(struct arch_thread *from, #define current_text_addr() \ ({ void *pc; __asm__("movq $1f,%0\n1:":"=g" (pc)); pc; }) +#define current_sp() ({ void *sp; __asm__("movq %%rsp, %0" : "=r" (sp) : ); sp; }) +#define current_bp() ({ unsigned long bp; __asm__("movq %%rbp, %0" : "=r" (bp) : ); bp; }) + #endif diff --git a/arch/x86/um/sysrq_32.c b/arch/x86/um/sysrq_32.c index c9bee5b8c0d3..16ee0e450e3e 100644 --- a/arch/x86/um/sysrq_32.c +++ b/arch/x86/um/sysrq_32.c @@ -30,70 +30,4 @@ void show_regs(struct pt_regs *regs) printk(" DS: %04lx ES: %04lx\n", 0xffff & PT_REGS_DS(regs), 0xffff & PT_REGS_ES(regs)); - - show_trace(NULL, (unsigned long *) ®s); } - -/* Copied from i386. */ -static inline int valid_stack_ptr(struct thread_info *tinfo, void *p) -{ - return p > (void *)tinfo && - p < (void *)tinfo + THREAD_SIZE - 3; -} - -/* Adapted from i386 (we also print the address we read from). */ -static inline unsigned long print_context_stack(struct thread_info *tinfo, - unsigned long *stack, unsigned long ebp) -{ - unsigned long addr; - -#ifdef CONFIG_FRAME_POINTER - while (valid_stack_ptr(tinfo, (void *)ebp)) { - addr = *(unsigned long *)(ebp + 4); - printk("%08lx: [<%08lx>]", ebp + 4, addr); - print_symbol(" %s", addr); - printk("\n"); - ebp = *(unsigned long *)ebp; - } -#else - while (valid_stack_ptr(tinfo, stack)) { - addr = *stack; - if (__kernel_text_address(addr)) { - printk("%08lx: [<%08lx>]", (unsigned long) stack, addr); - print_symbol(" %s", addr); - printk("\n"); - } - stack++; - } -#endif - return ebp; -} - -void show_trace(struct task_struct* task, unsigned long * stack) -{ - unsigned long ebp; - struct thread_info *context; - - /* Turn this into BUG_ON if possible. */ - if (!stack) { - stack = (unsigned long*) &stack; - printk("show_trace: got NULL stack, implicit assumption task == current"); - WARN_ON(1); - } - - if (!task) - task = current; - - if (task != current) { - ebp = (unsigned long) KSTK_EBP(task); - } else { - asm ("movl %%ebp, %0" : "=r" (ebp) : ); - } - - context = (struct thread_info *) - ((unsigned long)stack & (~(THREAD_SIZE - 1))); - print_context_stack(context, stack, ebp); - - printk("\n"); -} - diff --git a/arch/x86/um/sysrq_64.c b/arch/x86/um/sysrq_64.c index a0e7fb1134a0..38b4e4abd0f8 100644 --- a/arch/x86/um/sysrq_64.c +++ b/arch/x86/um/sysrq_64.c @@ -12,7 +12,7 @@ #include <asm/ptrace.h> #include <asm/sysrq.h> -void __show_regs(struct pt_regs *regs) +void show_regs(struct pt_regs *regs) { printk("\n"); print_modules(); @@ -33,9 +33,3 @@ void __show_regs(struct pt_regs *regs) printk(KERN_INFO "R13: %016lx R14: %016lx R15: %016lx\n", PT_REGS_R13(regs), PT_REGS_R14(regs), PT_REGS_R15(regs)); } - -void show_regs(struct pt_regs *regs) -{ - __show_regs(regs); - show_trace(current, (unsigned long *) ®s); -} diff --git a/arch/x86/um/vdso/.gitignore b/arch/x86/um/vdso/.gitignore new file mode 100644 index 000000000000..9cac6d072199 --- /dev/null +++ b/arch/x86/um/vdso/.gitignore @@ -0,0 +1,2 @@ +vdso-syms.lds +vdso.lds diff --git a/arch/x86/vdso/vclock_gettime.c b/arch/x86/vdso/vclock_gettime.c index 72074d528400..2ada505067cc 100644 --- a/arch/x86/vdso/vclock_gettime.c +++ b/arch/x86/vdso/vclock_gettime.c @@ -178,7 +178,7 @@ notrace static int __always_inline do_realtime(struct timespec *ts) ts->tv_nsec = 0; do { - seq = read_seqcount_begin(>od->seq); + seq = read_seqcount_begin_no_lockdep(>od->seq); mode = gtod->clock.vclock_mode; ts->tv_sec = gtod->wall_time_sec; ns = gtod->wall_time_snsec; @@ -198,7 +198,7 @@ notrace static int do_monotonic(struct timespec *ts) ts->tv_nsec = 0; do { - seq = read_seqcount_begin(>od->seq); + seq = read_seqcount_begin_no_lockdep(>od->seq); mode = gtod->clock.vclock_mode; ts->tv_sec = gtod->monotonic_time_sec; ns = gtod->monotonic_time_snsec; @@ -214,7 +214,7 @@ notrace static int do_realtime_coarse(struct timespec *ts) { unsigned long seq; do { - seq = read_seqcount_begin(>od->seq); + seq = read_seqcount_begin_no_lockdep(>od->seq); ts->tv_sec = gtod->wall_time_coarse.tv_sec; ts->tv_nsec = gtod->wall_time_coarse.tv_nsec; } while (unlikely(read_seqcount_retry(>od->seq, seq))); @@ -225,7 +225,7 @@ notrace static int do_monotonic_coarse(struct timespec *ts) { unsigned long seq; do { - seq = read_seqcount_begin(>od->seq); + seq = read_seqcount_begin_no_lockdep(>od->seq); ts->tv_sec = gtod->monotonic_time_coarse.tv_sec; ts->tv_nsec = gtod->monotonic_time_coarse.tv_nsec; } while (unlikely(read_seqcount_retry(>od->seq, seq))); diff --git a/arch/x86/xen/mmu.c b/arch/x86/xen/mmu.c index fdc3ba28ca38..ce563be09cc1 100644 --- a/arch/x86/xen/mmu.c +++ b/arch/x86/xen/mmu.c @@ -468,8 +468,8 @@ PV_CALLEE_SAVE_REGS_THUNK(xen_pgd_val); * 3 PCD PWT UC UC UC * 4 PAT WB WC WB * 5 PAT PWT WC WP WT - * 6 PAT PCD UC- UC UC- - * 7 PAT PCD PWT UC UC UC + * 6 PAT PCD UC- rsv UC- + * 7 PAT PCD PWT UC rsv UC */ void xen_set_pat(u64 pat) @@ -796,8 +796,8 @@ static spinlock_t *xen_pte_lock(struct page *page, struct mm_struct *mm) { spinlock_t *ptl = NULL; -#if USE_SPLIT_PTLOCKS - ptl = __pte_lockptr(page); +#if USE_SPLIT_PTE_PTLOCKS + ptl = ptlock_ptr(page); spin_lock_nest_lock(ptl, &mm->page_table_lock); #endif @@ -1637,7 +1637,7 @@ static inline void xen_alloc_ptpage(struct mm_struct *mm, unsigned long pfn, __set_pfn_prot(pfn, PAGE_KERNEL_RO); - if (level == PT_PTE && USE_SPLIT_PTLOCKS) + if (level == PT_PTE && USE_SPLIT_PTE_PTLOCKS) __pin_pagetable_pfn(MMUEXT_PIN_L1_TABLE, pfn); xen_mc_issue(PARAVIRT_LAZY_MMU); @@ -1671,7 +1671,7 @@ static inline void xen_release_ptpage(unsigned long pfn, unsigned level) if (!PageHighMem(page)) { xen_mc_batch(); - if (level == PT_PTE && USE_SPLIT_PTLOCKS) + if (level == PT_PTE && USE_SPLIT_PTE_PTLOCKS) __pin_pagetable_pfn(MMUEXT_UNPIN_TABLE, pfn); __set_pfn_prot(pfn, PAGE_KERNEL); @@ -2328,12 +2328,14 @@ static int xen_exchange_memory(unsigned long extents_in, unsigned int order_in, return success; } -int xen_create_contiguous_region(unsigned long vstart, unsigned int order, - unsigned int address_bits) +int xen_create_contiguous_region(phys_addr_t pstart, unsigned int order, + unsigned int address_bits, + dma_addr_t *dma_handle) { unsigned long *in_frames = discontig_frames, out_frame; unsigned long flags; int success; + unsigned long vstart = (unsigned long)phys_to_virt(pstart); /* * Currently an auto-translated guest will not perform I/O, nor will @@ -2368,15 +2370,17 @@ int xen_create_contiguous_region(unsigned long vstart, unsigned int order, spin_unlock_irqrestore(&xen_reservation_lock, flags); + *dma_handle = virt_to_machine(vstart).maddr; return success ? 0 : -ENOMEM; } EXPORT_SYMBOL_GPL(xen_create_contiguous_region); -void xen_destroy_contiguous_region(unsigned long vstart, unsigned int order) +void xen_destroy_contiguous_region(phys_addr_t pstart, unsigned int order) { unsigned long *out_frames = discontig_frames, in_frame; unsigned long flags; int success; + unsigned long vstart; if (xen_feature(XENFEAT_auto_translated_physmap)) return; @@ -2384,6 +2388,7 @@ void xen_destroy_contiguous_region(unsigned long vstart, unsigned int order) if (unlikely(order > MAX_CONTIG_ORDER)) return; + vstart = (unsigned long)phys_to_virt(pstart); memset((void *) vstart, 0, PAGE_SIZE << order); spin_lock_irqsave(&xen_reservation_lock, flags); diff --git a/arch/x86/xen/p2m.c b/arch/x86/xen/p2m.c index a61c7d5811be..2ae8699e8767 100644 --- a/arch/x86/xen/p2m.c +++ b/arch/x86/xen/p2m.c @@ -799,10 +799,10 @@ bool __set_phys_to_machine(unsigned long pfn, unsigned long mfn) { unsigned topidx, mididx, idx; - if (unlikely(xen_feature(XENFEAT_auto_translated_physmap))) { - BUG_ON(pfn != mfn && mfn != INVALID_P2M_ENTRY); + /* don't track P2M changes in autotranslate guests */ + if (unlikely(xen_feature(XENFEAT_auto_translated_physmap))) return true; - } + if (unlikely(pfn >= MAX_P2M_PFN)) { BUG_ON(mfn != INVALID_P2M_ENTRY); return true; diff --git a/arch/x86/xen/pci-swiotlb-xen.c b/arch/x86/xen/pci-swiotlb-xen.c index 969570491c39..0e98e5d241d0 100644 --- a/arch/x86/xen/pci-swiotlb-xen.c +++ b/arch/x86/xen/pci-swiotlb-xen.c @@ -75,8 +75,10 @@ void __init pci_xen_swiotlb_init(void) xen_swiotlb_init(1, true /* early */); dma_ops = &xen_swiotlb_dma_ops; +#ifdef CONFIG_PCI /* Make sure ACS will be enabled */ pci_request_acs(); +#endif } } @@ -92,8 +94,10 @@ int pci_xen_swiotlb_init_late(void) return rc; dma_ops = &xen_swiotlb_dma_ops; +#ifdef CONFIG_PCI /* Make sure ACS will be enabled */ pci_request_acs(); +#endif return 0; } diff --git a/arch/x86/xen/setup.c b/arch/x86/xen/setup.c index 09f3059cb00b..68c054f59de6 100644 --- a/arch/x86/xen/setup.c +++ b/arch/x86/xen/setup.c @@ -556,7 +556,7 @@ void xen_enable_syscall(void) } #endif /* CONFIG_X86_64 */ } -void __cpuinit xen_enable_nmi(void) +void xen_enable_nmi(void) { #ifdef CONFIG_X86_64 if (register_callback(CALLBACKTYPE_nmi, nmi)) diff --git a/arch/x86/xen/smp.c b/arch/x86/xen/smp.c index 31d04758b76f..c36b325abd83 100644 --- a/arch/x86/xen/smp.c +++ b/arch/x86/xen/smp.c @@ -149,7 +149,7 @@ static int xen_smp_intr_init(unsigned int cpu) rc = bind_ipi_to_irqhandler(XEN_RESCHEDULE_VECTOR, cpu, xen_reschedule_interrupt, - IRQF_DISABLED|IRQF_PERCPU|IRQF_NOBALANCING, + IRQF_PERCPU|IRQF_NOBALANCING, resched_name, NULL); if (rc < 0) @@ -161,7 +161,7 @@ static int xen_smp_intr_init(unsigned int cpu) rc = bind_ipi_to_irqhandler(XEN_CALL_FUNCTION_VECTOR, cpu, xen_call_function_interrupt, - IRQF_DISABLED|IRQF_PERCPU|IRQF_NOBALANCING, + IRQF_PERCPU|IRQF_NOBALANCING, callfunc_name, NULL); if (rc < 0) @@ -171,7 +171,7 @@ static int xen_smp_intr_init(unsigned int cpu) debug_name = kasprintf(GFP_KERNEL, "debug%d", cpu); rc = bind_virq_to_irqhandler(VIRQ_DEBUG, cpu, xen_debug_interrupt, - IRQF_DISABLED | IRQF_PERCPU | IRQF_NOBALANCING, + IRQF_PERCPU | IRQF_NOBALANCING, debug_name, NULL); if (rc < 0) goto fail; @@ -182,7 +182,7 @@ static int xen_smp_intr_init(unsigned int cpu) rc = bind_ipi_to_irqhandler(XEN_CALL_FUNCTION_SINGLE_VECTOR, cpu, xen_call_function_single_interrupt, - IRQF_DISABLED|IRQF_PERCPU|IRQF_NOBALANCING, + IRQF_PERCPU|IRQF_NOBALANCING, callfunc_name, NULL); if (rc < 0) @@ -201,7 +201,7 @@ static int xen_smp_intr_init(unsigned int cpu) rc = bind_ipi_to_irqhandler(XEN_IRQ_WORK_VECTOR, cpu, xen_irq_work_interrupt, - IRQF_DISABLED|IRQF_PERCPU|IRQF_NOBALANCING, + IRQF_PERCPU|IRQF_NOBALANCING, callfunc_name, NULL); if (rc < 0) diff --git a/arch/x86/xen/spinlock.c b/arch/x86/xen/spinlock.c index be6b86078957..0e36cde12f7e 100644 --- a/arch/x86/xen/spinlock.c +++ b/arch/x86/xen/spinlock.c @@ -234,7 +234,7 @@ void xen_init_lock_cpu(int cpu) irq = bind_ipi_to_irqhandler(XEN_SPIN_UNLOCK_VECTOR, cpu, dummy_handler, - IRQF_DISABLED|IRQF_PERCPU|IRQF_NOBALANCING, + IRQF_PERCPU|IRQF_NOBALANCING, name, NULL); diff --git a/arch/x86/xen/time.c b/arch/x86/xen/time.c index ee365895b06b..12a1ca707b94 100644 --- a/arch/x86/xen/time.c +++ b/arch/x86/xen/time.c @@ -443,8 +443,7 @@ void xen_setup_timer(int cpu) name = "<timer kasprintf failed>"; irq = bind_virq_to_irqhandler(VIRQ_TIMER, cpu, xen_timer_interrupt, - IRQF_DISABLED|IRQF_PERCPU| - IRQF_NOBALANCING|IRQF_TIMER| + IRQF_PERCPU|IRQF_NOBALANCING|IRQF_TIMER| IRQF_FORCE_RESUME, name, NULL); diff --git a/arch/xtensa/include/asm/pgalloc.h b/arch/xtensa/include/asm/pgalloc.h index cf914c8c249a..d38eb9237e64 100644 --- a/arch/xtensa/include/asm/pgalloc.h +++ b/arch/xtensa/include/asm/pgalloc.h @@ -38,35 +38,46 @@ static inline void pgd_free(struct mm_struct *mm, pgd_t *pgd) free_page((unsigned long)pgd); } -/* Use a slab cache for the pte pages (see also sparc64 implementation) */ - -extern struct kmem_cache *pgtable_cache; - static inline pte_t *pte_alloc_one_kernel(struct mm_struct *mm, unsigned long address) { - return kmem_cache_alloc(pgtable_cache, GFP_KERNEL|__GFP_REPEAT); + pte_t *ptep; + int i; + + ptep = (pte_t *)__get_free_page(GFP_KERNEL|__GFP_REPEAT); + if (!ptep) + return NULL; + for (i = 0; i < 1024; i++) + pte_clear(NULL, 0, ptep + i); + return ptep; } static inline pgtable_t pte_alloc_one(struct mm_struct *mm, unsigned long addr) { + pte_t *pte; struct page *page; - page = virt_to_page(pte_alloc_one_kernel(mm, addr)); - pgtable_page_ctor(page); + pte = pte_alloc_one_kernel(mm, addr); + if (!pte) + return NULL; + page = virt_to_page(pte); + if (!pgtable_page_ctor(page)) { + __free_page(page); + return NULL; + } return page; } static inline void pte_free_kernel(struct mm_struct *mm, pte_t *pte) { - kmem_cache_free(pgtable_cache, pte); + free_page((unsigned long)pte); } static inline void pte_free(struct mm_struct *mm, pgtable_t pte) { pgtable_page_dtor(pte); - kmem_cache_free(pgtable_cache, page_address(pte)); + __free_page(pte); } #define pmd_pgtable(pmd) pmd_page(pmd) diff --git a/arch/xtensa/include/asm/pgtable.h b/arch/xtensa/include/asm/pgtable.h index 0fdf5d043f82..216446295ada 100644 --- a/arch/xtensa/include/asm/pgtable.h +++ b/arch/xtensa/include/asm/pgtable.h @@ -220,12 +220,11 @@ extern unsigned long empty_zero_page[1024]; #ifdef CONFIG_MMU extern pgd_t swapper_pg_dir[PAGE_SIZE/sizeof(pgd_t)]; extern void paging_init(void); -extern void pgtable_cache_init(void); #else # define swapper_pg_dir NULL static inline void paging_init(void) { } -static inline void pgtable_cache_init(void) { } #endif +static inline void pgtable_cache_init(void) { } /* * The pmd contains the kernel virtual address of the pte page. diff --git a/arch/xtensa/include/asm/thread_info.h b/arch/xtensa/include/asm/thread_info.h index 9481004ac119..470153e8547c 100644 --- a/arch/xtensa/include/asm/thread_info.h +++ b/arch/xtensa/include/asm/thread_info.h @@ -76,8 +76,6 @@ struct thread_info { #endif -#define PREEMPT_ACTIVE 0x10000000 - /* * macros/functions for gaining access to the thread information structure */ diff --git a/arch/xtensa/mm/mmu.c b/arch/xtensa/mm/mmu.c index a1077570e383..c43771c974be 100644 --- a/arch/xtensa/mm/mmu.c +++ b/arch/xtensa/mm/mmu.c @@ -50,23 +50,3 @@ void __init init_mmu(void) */ set_ptevaddr_register(PGTABLE_START); } - -struct kmem_cache *pgtable_cache __read_mostly; - -static void pgd_ctor(void *addr) -{ - pte_t *ptep = (pte_t *)addr; - int i; - - for (i = 0; i < 1024; i++, ptep++) - pte_clear(NULL, 0, ptep); - -} - -void __init pgtable_cache_init(void) -{ - pgtable_cache = kmem_cache_create("pgd", - PAGE_SIZE, PAGE_SIZE, - SLAB_HWCACHE_ALIGN, - pgd_ctor); -} |