diff options
Diffstat (limited to 'arch')
64 files changed, 596 insertions, 522 deletions
diff --git a/arch/arm/Kconfig b/arch/arm/Kconfig index ac2ffdcfbbb4..e7baca29f3fb 100644 --- a/arch/arm/Kconfig +++ b/arch/arm/Kconfig @@ -21,6 +21,10 @@ config ARM config SYS_SUPPORTS_APM_EMULATION bool +config GENERIC_GPIO + bool + default n + config GENERIC_TIME bool default n @@ -163,6 +167,7 @@ config ARCH_VERSATILE config ARCH_AT91 bool "Atmel AT91" + select GENERIC_GPIO help This enables support for systems based on the Atmel AT91RM9200 and AT91SAM9xxx processors. @@ -304,6 +309,7 @@ config ARCH_PXA bool "PXA2xx-based" depends on MMU select ARCH_MTD_XIP + select GENERIC_GPIO select GENERIC_TIME help Support for Intel's PXA2XX processor line. @@ -325,11 +331,13 @@ config ARCH_SA1100 select ISA select ARCH_DISCONTIGMEM_ENABLE select ARCH_MTD_XIP + select GENERIC_GPIO help Support for StrongARM 11x0 based boards. config ARCH_S3C2410 bool "Samsung S3C2410, S3C2412, S3C2413, S3C2440, S3C2442, S3C2443" + select GENERIC_GPIO help Samsung S3C2410X CPU based systems, such as the Simtec Electronics BAST (<http://www.simtec.co.uk/products/EB110ITX/>), the IPAQ 1940 or @@ -354,6 +362,7 @@ config ARCH_LH7A40X config ARCH_OMAP bool "TI OMAP" + select GENERIC_GPIO help Support for TI's OMAP platform (OMAP1 and OMAP2). diff --git a/arch/avr32/Kconfig b/arch/avr32/Kconfig index bb059a4e1df9..ce4013aee59b 100644 --- a/arch/avr32/Kconfig +++ b/arch/avr32/Kconfig @@ -22,6 +22,10 @@ config AVR32 config UID16 bool +config GENERIC_GPIO + bool + default y + config GENERIC_HARDIRQS bool default y diff --git a/arch/i386/Kconfig b/arch/i386/Kconfig index 2f7672545fe9..27e8453274e6 100644 --- a/arch/i386/Kconfig +++ b/arch/i386/Kconfig @@ -220,11 +220,11 @@ config PARAVIRT config VMI bool "VMI Paravirt-ops support" - depends on PARAVIRT && !NO_HZ - default y + depends on PARAVIRT help - VMI provides a paravirtualized interface to multiple hypervisors - include VMware ESX server and Xen by connecting to a ROM module + VMI provides a paravirtualized interface to the VMware ESX server + (it could be used by other hypervisors in theory too, but is not + at the moment), by linking the kernel to a GPL-ed ROM module provided by the hypervisor. config ACPI_SRAT @@ -893,7 +893,6 @@ config HOTPLUG_CPU config COMPAT_VDSO bool "Compat VDSO support" default y - depends on !PARAVIRT help Map the VDSO to the predictable old-style address too. ---help--- @@ -1287,12 +1286,3 @@ config X86_TRAMPOLINE config KTIME_SCALAR bool default y - -config NO_IDLE_HZ - bool - depends on PARAVIRT - default y - help - Switches the regular HZ timer off when the system is going idle. - This helps a hypervisor detect that the Linux system is idle, - reducing the overhead of idle systems. diff --git a/arch/i386/kernel/apic.c b/arch/i386/kernel/apic.c index 7a2c9cbdb511..2383bcf18c5d 100644 --- a/arch/i386/kernel/apic.c +++ b/arch/i386/kernel/apic.c @@ -493,8 +493,15 @@ void __init setup_boot_APIC_clock(void) /* No broadcast on UP ! */ if (num_possible_cpus() == 1) return; - } else - lapic_clockevent.features &= ~CLOCK_EVT_FEAT_DUMMY; + } else { + /* + * If nmi_watchdog is set to IO_APIC, we need the + * PIT/HPET going. Otherwise register lapic as a dummy + * device. + */ + if (nmi_watchdog != NMI_IO_APIC) + lapic_clockevent.features &= ~CLOCK_EVT_FEAT_DUMMY; + } /* Setup the lapic or request the broadcast */ setup_APIC_timer(); diff --git a/arch/i386/kernel/hpet.c b/arch/i386/kernel/hpet.c index e1006b7acc9e..f3ab61ee7498 100644 --- a/arch/i386/kernel/hpet.c +++ b/arch/i386/kernel/hpet.c @@ -201,12 +201,30 @@ static int hpet_next_event(unsigned long delta, } /* + * Clock source related code + */ +static cycle_t read_hpet(void) +{ + return (cycle_t)hpet_readl(HPET_COUNTER); +} + +static struct clocksource clocksource_hpet = { + .name = "hpet", + .rating = 250, + .read = read_hpet, + .mask = HPET_MASK, + .shift = HPET_SHIFT, + .flags = CLOCK_SOURCE_IS_CONTINUOUS, +}; + +/* * Try to setup the HPET timer */ int __init hpet_enable(void) { unsigned long id; uint64_t hpet_freq; + u64 tmp; if (!is_hpet_capable()) return 0; @@ -253,6 +271,25 @@ int __init hpet_enable(void) /* Start the counter */ hpet_start_counter(); + /* Initialize and register HPET clocksource + * + * hpet period is in femto seconds per cycle + * so we need to convert this to ns/cyc units + * aproximated by mult/2^shift + * + * fsec/cyc * 1nsec/1000000fsec = nsec/cyc = mult/2^shift + * fsec/cyc * 1ns/1000000fsec * 2^shift = mult + * fsec/cyc * 2^shift * 1nsec/1000000fsec = mult + * (fsec/cyc << shift)/1000000 = mult + * (hpet_period << shift)/FSEC_PER_NSEC = mult + */ + tmp = (u64)hpet_period << HPET_SHIFT; + do_div(tmp, FSEC_PER_NSEC); + clocksource_hpet.mult = (u32)tmp; + + clocksource_register(&clocksource_hpet); + + if (id & HPET_ID_LEGSUP) { hpet_enable_int(); hpet_reserve_platform_timers(id); @@ -273,49 +310,6 @@ out_nohpet: return 0; } -/* - * Clock source related code - */ -static cycle_t read_hpet(void) -{ - return (cycle_t)hpet_readl(HPET_COUNTER); -} - -static struct clocksource clocksource_hpet = { - .name = "hpet", - .rating = 250, - .read = read_hpet, - .mask = HPET_MASK, - .shift = HPET_SHIFT, - .flags = CLOCK_SOURCE_IS_CONTINUOUS, -}; - -static int __init init_hpet_clocksource(void) -{ - u64 tmp; - - if (!hpet_virt_address) - return -ENODEV; - - /* - * hpet period is in femto seconds per cycle - * so we need to convert this to ns/cyc units - * aproximated by mult/2^shift - * - * fsec/cyc * 1nsec/1000000fsec = nsec/cyc = mult/2^shift - * fsec/cyc * 1ns/1000000fsec * 2^shift = mult - * fsec/cyc * 2^shift * 1nsec/1000000fsec = mult - * (fsec/cyc << shift)/1000000 = mult - * (hpet_period << shift)/FSEC_PER_NSEC = mult - */ - tmp = (u64)hpet_period << HPET_SHIFT; - do_div(tmp, FSEC_PER_NSEC); - clocksource_hpet.mult = (u32)tmp; - - return clocksource_register(&clocksource_hpet); -} - -module_init(init_hpet_clocksource); #ifdef CONFIG_HPET_EMULATE_RTC diff --git a/arch/i386/kernel/i8253.c b/arch/i386/kernel/i8253.c index a6bc7bb38834..5cbb776b3089 100644 --- a/arch/i386/kernel/i8253.c +++ b/arch/i386/kernel/i8253.c @@ -195,4 +195,4 @@ static int __init init_pit_clocksource(void) clocksource_pit.mult = clocksource_hz2mult(CLOCK_TICK_RATE, 20); return clocksource_register(&clocksource_pit); } -module_init(init_pit_clocksource); +arch_initcall(init_pit_clocksource); diff --git a/arch/i386/kernel/paravirt.c b/arch/i386/kernel/paravirt.c index c156ecfa3872..2ec331e03fa9 100644 --- a/arch/i386/kernel/paravirt.c +++ b/arch/i386/kernel/paravirt.c @@ -32,6 +32,7 @@ #include <asm/fixmap.h> #include <asm/apic.h> #include <asm/tlbflush.h> +#include <asm/timer.h> /* nop stub */ static void native_nop(void) @@ -493,7 +494,7 @@ struct paravirt_ops paravirt_ops = { .memory_setup = machine_specific_memory_setup, .get_wallclock = native_get_wallclock, .set_wallclock = native_set_wallclock, - .time_init = time_init_hook, + .time_init = hpet_time_init, .init_IRQ = native_init_IRQ, .cpuid = native_cpuid, @@ -520,6 +521,8 @@ struct paravirt_ops paravirt_ops = { .write_msr = native_write_msr, .read_tsc = native_read_tsc, .read_pmc = native_read_pmc, + .get_scheduled_cycles = native_read_tsc, + .get_cpu_khz = native_calculate_cpu_khz, .load_tr_desc = native_load_tr_desc, .set_ldt = native_set_ldt, .load_gdt = native_load_gdt, @@ -535,7 +538,6 @@ struct paravirt_ops paravirt_ops = { .set_iopl_mask = native_set_iopl_mask, .io_delay = native_io_delay, - .const_udelay = __const_udelay, #ifdef CONFIG_X86_LOCAL_APIC .apic_write = native_apic_write, @@ -550,6 +552,8 @@ struct paravirt_ops paravirt_ops = { .flush_tlb_kernel = native_flush_tlb_global, .flush_tlb_single = native_flush_tlb_single, + .map_pt_hook = (void *)native_nop, + .alloc_pt = (void *)native_nop, .alloc_pd = (void *)native_nop, .alloc_pd_clone = (void *)native_nop, diff --git a/arch/i386/kernel/setup.c b/arch/i386/kernel/setup.c index 122623dcc6e1..698c24fe482e 100644 --- a/arch/i386/kernel/setup.c +++ b/arch/i386/kernel/setup.c @@ -657,5 +657,4 @@ void __init setup_arch(char **cmdline_p) conswitchp = &dummy_con; #endif #endif - tsc_init(); } diff --git a/arch/i386/kernel/smpboot.c b/arch/i386/kernel/smpboot.c index 48bfcaa13ecc..4ff55e675576 100644 --- a/arch/i386/kernel/smpboot.c +++ b/arch/i386/kernel/smpboot.c @@ -33,11 +33,6 @@ * Dave Jones : Report invalid combinations of Athlon CPUs. * Rusty Russell : Hacked into shape for new "hotplug" boot process. */ - -/* SMP boot always wants to use real time delay to allow sufficient time for - * the APs to come online */ -#define USE_REAL_TIME_DELAY - #include <linux/module.h> #include <linux/init.h> #include <linux/kernel.h> @@ -50,6 +45,7 @@ #include <linux/notifier.h> #include <linux/cpu.h> #include <linux/percpu.h> +#include <linux/nmi.h> #include <linux/delay.h> #include <linux/mc146818rtc.h> @@ -1283,8 +1279,9 @@ void __cpu_die(unsigned int cpu) int __cpuinit __cpu_up(unsigned int cpu) { + unsigned long flags; #ifdef CONFIG_HOTPLUG_CPU - int ret=0; + int ret = 0; /* * We do warm boot only on cpus that had booted earlier @@ -1302,23 +1299,25 @@ int __cpuinit __cpu_up(unsigned int cpu) /* In case one didn't come up */ if (!cpu_isset(cpu, cpu_callin_map)) { printk(KERN_DEBUG "skipping cpu%d, didn't come online\n", cpu); - local_irq_enable(); return -EIO; } - local_irq_enable(); - per_cpu(cpu_state, cpu) = CPU_UP_PREPARE; /* Unleash the CPU! */ cpu_set(cpu, smp_commenced_mask); /* - * Check TSC synchronization with the AP: + * Check TSC synchronization with the AP (keep irqs disabled + * while doing so): */ + local_irq_save(flags); check_tsc_sync_source(cpu); + local_irq_restore(flags); - while (!cpu_isset(cpu, cpu_online_map)) + while (!cpu_isset(cpu, cpu_online_map)) { cpu_relax(); + touch_nmi_watchdog(); + } #ifdef CONFIG_X86_GENERICARCH if (num_online_cpus() > 8 && genapic == &apic_default) diff --git a/arch/i386/kernel/time.c b/arch/i386/kernel/time.c index a5350059557a..94e5cb091104 100644 --- a/arch/i386/kernel/time.c +++ b/arch/i386/kernel/time.c @@ -262,14 +262,23 @@ void notify_arch_cmos_timer(void) extern void (*late_time_init)(void); /* Duplicate of time_init() below, with hpet_enable part added */ -static void __init hpet_time_init(void) +void __init hpet_time_init(void) { if (!hpet_enable()) setup_pit_timer(); - do_time_init(); + time_init_hook(); } +/* + * This is called directly from init code; we must delay timer setup in the + * HPET case as we can't make the decision to turn on HPET this early in the + * boot process. + * + * The chosen time_init function will usually be hpet_time_init, above, but + * in the case of virtual hardware, an alternative function may be substituted. + */ void __init time_init(void) { - late_time_init = hpet_time_init; + tsc_init(); + late_time_init = choose_time_init(); } diff --git a/arch/i386/kernel/tsc.c b/arch/i386/kernel/tsc.c index 3082a418635c..602660df455c 100644 --- a/arch/i386/kernel/tsc.c +++ b/arch/i386/kernel/tsc.c @@ -14,6 +14,7 @@ #include <asm/delay.h> #include <asm/tsc.h> #include <asm/io.h> +#include <asm/timer.h> #include "mach_timer.h" @@ -23,7 +24,6 @@ * an extra value to store the TSC freq */ unsigned int tsc_khz; -unsigned long long (*custom_sched_clock)(void); int tsc_disable; @@ -102,9 +102,6 @@ unsigned long long sched_clock(void) { unsigned long long this_offset; - if (unlikely(custom_sched_clock)) - return (*custom_sched_clock)(); - /* * Fall back to jiffies if there's no TSC available: */ @@ -113,13 +110,13 @@ unsigned long long sched_clock(void) return (jiffies_64 - INITIAL_JIFFIES) * (1000000000 / HZ); /* read the Time Stamp Counter: */ - rdtscll(this_offset); + get_scheduled_cycles(this_offset); /* return the value in ns */ return cycles_2_ns(this_offset); } -static unsigned long calculate_cpu_khz(void) +unsigned long native_calculate_cpu_khz(void) { unsigned long long start, end; unsigned long count; @@ -186,34 +183,6 @@ int recalibrate_cpu_khz(void) EXPORT_SYMBOL(recalibrate_cpu_khz); -void __init tsc_init(void) -{ - if (!cpu_has_tsc || tsc_disable) - goto out_no_tsc; - - cpu_khz = calculate_cpu_khz(); - tsc_khz = cpu_khz; - - if (!cpu_khz) - goto out_no_tsc; - - printk("Detected %lu.%03lu MHz processor.\n", - (unsigned long)cpu_khz / 1000, - (unsigned long)cpu_khz % 1000); - - set_cyc2ns_scale(cpu_khz); - use_tsc_delay(); - return; - -out_no_tsc: - /* - * Set the tsc_disable flag if there's no TSC support, this - * makes it a fast flag for the kernel to see whether it - * should be using the TSC. - */ - tsc_disable = 1; -} - #ifdef CONFIG_CPU_FREQ /* @@ -383,28 +352,47 @@ static void __init check_geode_tsc_reliable(void) static inline void check_geode_tsc_reliable(void) { } #endif -static int __init init_tsc_clocksource(void) + +void __init tsc_init(void) { + if (!cpu_has_tsc || tsc_disable) + goto out_no_tsc; - if (cpu_has_tsc && tsc_khz && !tsc_disable) { - /* check blacklist */ - dmi_check_system(bad_tsc_dmi_table); + cpu_khz = calculate_cpu_khz(); + tsc_khz = cpu_khz; - unsynchronized_tsc(); - check_geode_tsc_reliable(); - current_tsc_khz = tsc_khz; - clocksource_tsc.mult = clocksource_khz2mult(current_tsc_khz, - clocksource_tsc.shift); - /* lower the rating if we already know its unstable: */ - if (check_tsc_unstable()) { - clocksource_tsc.rating = 0; - clocksource_tsc.flags &= ~CLOCK_SOURCE_IS_CONTINUOUS; - } + if (!cpu_khz) + goto out_no_tsc; + + printk("Detected %lu.%03lu MHz processor.\n", + (unsigned long)cpu_khz / 1000, + (unsigned long)cpu_khz % 1000); + + set_cyc2ns_scale(cpu_khz); + use_tsc_delay(); - return clocksource_register(&clocksource_tsc); + /* Check and install the TSC clocksource */ + dmi_check_system(bad_tsc_dmi_table); + + unsynchronized_tsc(); + check_geode_tsc_reliable(); + current_tsc_khz = tsc_khz; + clocksource_tsc.mult = clocksource_khz2mult(current_tsc_khz, + clocksource_tsc.shift); + /* lower the rating if we already know its unstable: */ + if (check_tsc_unstable()) { + clocksource_tsc.rating = 0; + clocksource_tsc.flags &= ~CLOCK_SOURCE_IS_CONTINUOUS; } + clocksource_register(&clocksource_tsc); - return 0; -} + return; -module_init(init_tsc_clocksource); +out_no_tsc: + /* + * Set the tsc_disable flag if there's no TSC support, this + * makes it a fast flag for the kernel to see whether it + * should be using the TSC. + */ + tsc_disable = 1; +} diff --git a/arch/i386/kernel/vmi.c b/arch/i386/kernel/vmi.c index bb5a7abf949c..fbf45fa08320 100644 --- a/arch/i386/kernel/vmi.c +++ b/arch/i386/kernel/vmi.c @@ -35,6 +35,7 @@ #include <asm/processor.h> #include <asm/timer.h> #include <asm/vmi_time.h> +#include <asm/kmap_types.h> /* Convenient for calling VMI functions indirectly in the ROM */ typedef u32 __attribute__((regparm(1))) (VROMFUNC)(void); @@ -48,12 +49,13 @@ typedef u64 __attribute__((regparm(2))) (VROMLONGFUNC)(int); static struct vrom_header *vmi_rom; static int license_gplok; -static int disable_nodelay; static int disable_pge; static int disable_pse; static int disable_sep; static int disable_tsc; static int disable_mtrr; +static int disable_noidle; +static int disable_vmi_timer; /* Cached VMI operations */ struct { @@ -255,7 +257,6 @@ static void vmi_nop(void) } /* For NO_IDLE_HZ, we stop the clock when halting the kernel */ -#ifdef CONFIG_NO_IDLE_HZ static fastcall void vmi_safe_halt(void) { int idle = vmi_stop_hz_timer(); @@ -266,7 +267,6 @@ static fastcall void vmi_safe_halt(void) local_irq_enable(); } } -#endif #ifdef CONFIG_DEBUG_PAGE_TYPE @@ -371,6 +371,24 @@ static void vmi_check_page_type(u32 pfn, int type) #define vmi_check_page_type(p,t) do { } while (0) #endif +static void vmi_map_pt_hook(int type, pte_t *va, u32 pfn) +{ + /* + * Internally, the VMI ROM must map virtual addresses to physical + * addresses for processing MMU updates. By the time MMU updates + * are issued, this information is typically already lost. + * Fortunately, the VMI provides a cache of mapping slots for active + * page tables. + * + * We use slot zero for the linear mapping of physical memory, and + * in HIGHPTE kernels, slot 1 and 2 for KM_PTE0 and KM_PTE1. + * + * args: SLOT VA COUNT PFN + */ + BUG_ON(type != KM_PTE0 && type != KM_PTE1); + vmi_ops.set_linear_mapping((type - KM_PTE0)+1, (u32)va, 1, pfn); +} + static void vmi_allocate_pt(u32 pfn) { vmi_set_page_type(pfn, VMI_PAGE_L1); @@ -508,13 +526,14 @@ void vmi_pmd_clear(pmd_t *pmd) #endif #ifdef CONFIG_SMP -struct vmi_ap_state ap; extern void setup_pda(void); -static void __init /* XXX cpu hotplug */ +static void __devinit vmi_startup_ipi_hook(int phys_apicid, unsigned long start_eip, unsigned long start_esp) { + struct vmi_ap_state ap; + /* Default everything to zero. This is fine for most GPRs. */ memset(&ap, 0, sizeof(struct vmi_ap_state)); @@ -553,7 +572,7 @@ vmi_startup_ipi_hook(int phys_apicid, unsigned long start_eip, /* Protected mode, paging, AM, WP, NE, MP. */ ap.cr0 = 0x80050023; ap.cr4 = mmu_cr4_features; - vmi_ops.set_initial_ap_state(__pa(&ap), phys_apicid); + vmi_ops.set_initial_ap_state((u32)&ap, phys_apicid); } #endif @@ -645,12 +664,12 @@ static inline int __init probe_vmi_rom(void) void vmi_bringup(void) { /* We must establish the lowmem mapping for MMU ops to work */ - if (vmi_rom) + if (vmi_ops.set_linear_mapping) vmi_ops.set_linear_mapping(0, __PAGE_OFFSET, max_low_pfn, 0); } /* - * Return a pointer to the VMI function or a NOP stub + * Return a pointer to a VMI function or NULL if unimplemented */ static void *vmi_get_function(int vmicall) { @@ -661,12 +680,13 @@ static void *vmi_get_function(int vmicall) if (rel->type == VMI_RELOCATION_CALL_REL) return (void *)rel->eip; else - return (void *)vmi_nop; + return NULL; } /* * Helper macro for making the VMI paravirt-ops fill code readable. - * For unimplemented operations, fall back to default. + * For unimplemented operations, fall back to default, unless nop + * is returned by the ROM. */ #define para_fill(opname, vmicall) \ do { \ @@ -675,9 +695,29 @@ do { \ if (rel->type != VMI_RELOCATION_NONE) { \ BUG_ON(rel->type != VMI_RELOCATION_CALL_REL); \ paravirt_ops.opname = (void *)rel->eip; \ + } else if (rel->type == VMI_RELOCATION_NOP) \ + paravirt_ops.opname = (void *)vmi_nop; \ +} while (0) + +/* + * Helper macro for making the VMI paravirt-ops fill code readable. + * For cached operations which do not match the VMI ROM ABI and must + * go through a tranlation stub. Ignore NOPs, since it is not clear + * a NOP * VMI function corresponds to a NOP paravirt-op when the + * functions are not in 1-1 correspondence. + */ +#define para_wrap(opname, wrapper, cache, vmicall) \ +do { \ + reloc = call_vrom_long_func(vmi_rom, get_reloc, \ + VMI_CALL_##vmicall); \ + BUG_ON(rel->type == VMI_RELOCATION_JUMP_REL); \ + if (rel->type == VMI_RELOCATION_CALL_REL) { \ + paravirt_ops.opname = wrapper; \ + vmi_ops.cache = (void *)rel->eip; \ } \ } while (0) + /* * Activate the VMI interface and switch into paravirtualized mode */ @@ -714,13 +754,8 @@ static inline int __init activate_vmi(void) * rdpmc is not yet used in Linux */ - /* CPUID is special, so very special */ - reloc = call_vrom_long_func(vmi_rom, get_reloc, VMI_CALL_CPUID); - if (rel->type != VMI_RELOCATION_NONE) { - BUG_ON(rel->type != VMI_RELOCATION_CALL_REL); - vmi_ops.cpuid = (void *)rel->eip; - paravirt_ops.cpuid = vmi_cpuid; - } + /* CPUID is special, so very special it gets wrapped like a present */ + para_wrap(cpuid, vmi_cpuid, cpuid, CPUID); para_fill(clts, CLTS); para_fill(get_debugreg, GetDR); @@ -737,38 +772,26 @@ static inline int __init activate_vmi(void) para_fill(restore_fl, SetInterruptMask); para_fill(irq_disable, DisableInterrupts); para_fill(irq_enable, EnableInterrupts); + /* irq_save_disable !!! sheer pain */ patch_offset(&irq_save_disable_callout[IRQ_PATCH_INT_MASK], (char *)paravirt_ops.save_fl); patch_offset(&irq_save_disable_callout[IRQ_PATCH_DISABLE], (char *)paravirt_ops.irq_disable); -#ifndef CONFIG_NO_IDLE_HZ - para_fill(safe_halt, Halt); -#else - vmi_ops.halt = vmi_get_function(VMI_CALL_Halt); - paravirt_ops.safe_halt = vmi_safe_halt; -#endif + para_fill(wbinvd, WBINVD); + para_fill(read_tsc, RDTSC); + + /* The following we emulate with trap and emulate for now */ /* paravirt_ops.read_msr = vmi_rdmsr */ /* paravirt_ops.write_msr = vmi_wrmsr */ - para_fill(read_tsc, RDTSC); /* paravirt_ops.rdpmc = vmi_rdpmc */ - /* TR interface doesn't pass TR value */ - reloc = call_vrom_long_func(vmi_rom, get_reloc, VMI_CALL_SetTR); - if (rel->type != VMI_RELOCATION_NONE) { - BUG_ON(rel->type != VMI_RELOCATION_CALL_REL); - vmi_ops.set_tr = (void *)rel->eip; - paravirt_ops.load_tr_desc = vmi_set_tr; - } + /* TR interface doesn't pass TR value, wrap */ + para_wrap(load_tr_desc, vmi_set_tr, set_tr, SetTR); /* LDT is special, too */ - reloc = call_vrom_long_func(vmi_rom, get_reloc, VMI_CALL_SetLDT); - if (rel->type != VMI_RELOCATION_NONE) { - BUG_ON(rel->type != VMI_RELOCATION_CALL_REL); - vmi_ops._set_ldt = (void *)rel->eip; - paravirt_ops.set_ldt = vmi_set_ldt; - } + para_wrap(set_ldt, vmi_set_ldt, _set_ldt, SetLDT); para_fill(load_gdt, SetGDT); para_fill(load_idt, SetIDT); @@ -779,28 +802,14 @@ static inline int __init activate_vmi(void) para_fill(write_ldt_entry, WriteLDTEntry); para_fill(write_gdt_entry, WriteGDTEntry); para_fill(write_idt_entry, WriteIDTEntry); - reloc = call_vrom_long_func(vmi_rom, get_reloc, - VMI_CALL_UpdateKernelStack); - if (rel->type != VMI_RELOCATION_NONE) { - BUG_ON(rel->type != VMI_RELOCATION_CALL_REL); - vmi_ops.set_kernel_stack = (void *)rel->eip; - paravirt_ops.load_esp0 = vmi_load_esp0; - } - + para_wrap(load_esp0, vmi_load_esp0, set_kernel_stack, UpdateKernelStack); para_fill(set_iopl_mask, SetIOPLMask); - paravirt_ops.io_delay = (void *)vmi_nop; - if (!disable_nodelay) { - paravirt_ops.const_udelay = (void *)vmi_nop; - } - + para_fill(io_delay, IODelay); para_fill(set_lazy_mode, SetLazyMode); - reloc = call_vrom_long_func(vmi_rom, get_reloc, VMI_CALL_FlushTLB); - if (rel->type != VMI_RELOCATION_NONE) { - vmi_ops.flush_tlb = (void *)rel->eip; - paravirt_ops.flush_tlb_user = vmi_flush_tlb_user; - paravirt_ops.flush_tlb_kernel = vmi_flush_tlb_kernel; - } + /* user and kernel flush are just handled with different flags to FlushTLB */ + para_wrap(flush_tlb_user, vmi_flush_tlb_user, flush_tlb, FlushTLB); + para_wrap(flush_tlb_kernel, vmi_flush_tlb_kernel, flush_tlb, FlushTLB); para_fill(flush_tlb_single, InvalPage); /* @@ -815,27 +824,40 @@ static inline int __init activate_vmi(void) vmi_ops.set_pte = vmi_get_function(VMI_CALL_SetPxE); vmi_ops.update_pte = vmi_get_function(VMI_CALL_UpdatePxE); #endif - vmi_ops.set_linear_mapping = vmi_get_function(VMI_CALL_SetLinearMapping); - vmi_ops.allocate_page = vmi_get_function(VMI_CALL_AllocatePage); - vmi_ops.release_page = vmi_get_function(VMI_CALL_ReleasePage); - paravirt_ops.alloc_pt = vmi_allocate_pt; - paravirt_ops.alloc_pd = vmi_allocate_pd; - paravirt_ops.alloc_pd_clone = vmi_allocate_pd_clone; - paravirt_ops.release_pt = vmi_release_pt; - paravirt_ops.release_pd = vmi_release_pd; - paravirt_ops.set_pte = vmi_set_pte; - paravirt_ops.set_pte_at = vmi_set_pte_at; - paravirt_ops.set_pmd = vmi_set_pmd; - paravirt_ops.pte_update = vmi_update_pte; - paravirt_ops.pte_update_defer = vmi_update_pte_defer; + if (vmi_ops.set_pte) { + paravirt_ops.set_pte = vmi_set_pte; + paravirt_ops.set_pte_at = vmi_set_pte_at; + paravirt_ops.set_pmd = vmi_set_pmd; #ifdef CONFIG_X86_PAE - paravirt_ops.set_pte_atomic = vmi_set_pte_atomic; - paravirt_ops.set_pte_present = vmi_set_pte_present; - paravirt_ops.set_pud = vmi_set_pud; - paravirt_ops.pte_clear = vmi_pte_clear; - paravirt_ops.pmd_clear = vmi_pmd_clear; + paravirt_ops.set_pte_atomic = vmi_set_pte_atomic; + paravirt_ops.set_pte_present = vmi_set_pte_present; + paravirt_ops.set_pud = vmi_set_pud; + paravirt_ops.pte_clear = vmi_pte_clear; + paravirt_ops.pmd_clear = vmi_pmd_clear; #endif + } + + if (vmi_ops.update_pte) { + paravirt_ops.pte_update = vmi_update_pte; + paravirt_ops.pte_update_defer = vmi_update_pte_defer; + } + + vmi_ops.allocate_page = vmi_get_function(VMI_CALL_AllocatePage); + if (vmi_ops.allocate_page) { + paravirt_ops.alloc_pt = vmi_allocate_pt; + paravirt_ops.alloc_pd = vmi_allocate_pd; + paravirt_ops.alloc_pd_clone = vmi_allocate_pd_clone; + } + + vmi_ops.release_page = vmi_get_function(VMI_CALL_ReleasePage); + if (vmi_ops.release_page) { + paravirt_ops.release_pt = vmi_release_pt; + paravirt_ops.release_pd = vmi_release_pd; + } + para_wrap(map_pt_hook, vmi_map_pt_hook, set_linear_mapping, + SetLinearMapping); + /* * These MUST always be patched. Don't support indirect jumps * through these operations, as the VMI interface may use either @@ -847,21 +869,20 @@ static inline int __init activate_vmi(void) paravirt_ops.iret = (void *)0xbadbab0; #ifdef CONFIG_SMP - paravirt_ops.startup_ipi_hook = vmi_startup_ipi_hook; - vmi_ops.set_initial_ap_state = vmi_get_function(VMI_CALL_SetInitialAPState); + para_wrap(startup_ipi_hook, vmi_startup_ipi_hook, set_initial_ap_state, SetInitialAPState); #endif #ifdef CONFIG_X86_LOCAL_APIC - paravirt_ops.apic_read = vmi_get_function(VMI_CALL_APICRead); - paravirt_ops.apic_write = vmi_get_function(VMI_CALL_APICWrite); - paravirt_ops.apic_write_atomic = vmi_get_function(VMI_CALL_APICWrite); + para_fill(apic_read, APICRead); + para_fill(apic_write, APICWrite); + para_fill(apic_write_atomic, APICWrite); #endif /* * Check for VMI timer functionality by probing for a cycle frequency method */ reloc = call_vrom_long_func(vmi_rom, get_reloc, VMI_CALL_GetCycleFrequency); - if (rel->type != VMI_RELOCATION_NONE) { + if (!disable_vmi_timer && rel->type != VMI_RELOCATION_NONE) { vmi_timer_ops.get_cycle_frequency = (void *)rel->eip; vmi_timer_ops.get_cycle_counter = vmi_get_function(VMI_CALL_GetCycleCounter); @@ -879,9 +900,22 @@ static inline int __init activate_vmi(void) paravirt_ops.setup_boot_clock = vmi_timer_setup_boot_alarm; paravirt_ops.setup_secondary_clock = vmi_timer_setup_secondary_alarm; #endif - custom_sched_clock = vmi_sched_clock; + paravirt_ops.get_scheduled_cycles = vmi_get_sched_cycles; + paravirt_ops.get_cpu_khz = vmi_cpu_khz; + + /* We have true wallclock functions; disable CMOS clock sync */ + no_sync_cmos_clock = 1; + } else { + disable_noidle = 1; + disable_vmi_timer = 1; } + /* No idle HZ mode only works if VMI timer and no idle is enabled */ + if (disable_noidle || disable_vmi_timer) + para_fill(safe_halt, Halt); + else + para_wrap(safe_halt, vmi_safe_halt, halt, Halt); + /* * Alternative instruction rewriting doesn't happen soon enough * to convert VMI_IRET to a call instead of a jump; so we have @@ -914,7 +948,9 @@ void __init vmi_init(void) local_irq_save(flags); activate_vmi(); -#ifdef CONFIG_SMP + +#ifdef CONFIG_X86_IO_APIC + /* This is virtual hardware; timer routing is wired correctly */ no_timer_check = 1; #endif local_irq_restore(flags & X86_EFLAGS_IF); @@ -925,9 +961,7 @@ static int __init parse_vmi(char *arg) if (!arg) return -EINVAL; - if (!strcmp(arg, "disable_nodelay")) - disable_nodelay = 1; - else if (!strcmp(arg, "disable_pge")) { + if (!strcmp(arg, "disable_pge")) { clear_bit(X86_FEATURE_PGE, boot_cpu_data.x86_capability); disable_pge = 1; } else if (!strcmp(arg, "disable_pse")) { @@ -942,7 +976,11 @@ static int __init parse_vmi(char *arg) } else if (!strcmp(arg, "disable_mtrr")) { clear_bit(X86_FEATURE_MTRR, boot_cpu_data.x86_capability); disable_mtrr = 1; - } + } else if (!strcmp(arg, "disable_timer")) { + disable_vmi_timer = 1; + disable_noidle = 1; + } else if (!strcmp(arg, "disable_noidle")) + disable_noidle = 1; return 0; } diff --git a/arch/i386/kernel/vmitime.c b/arch/i386/kernel/vmitime.c index 76d2adcae5a3..9dfb17739b67 100644 --- a/arch/i386/kernel/vmitime.c +++ b/arch/i386/kernel/vmitime.c @@ -123,12 +123,10 @@ static struct clocksource clocksource_vmi = { static irqreturn_t vmi_timer_interrupt(int irq, void *dev_id); static struct irqaction vmi_timer_irq = { - vmi_timer_interrupt, - SA_INTERRUPT, - CPU_MASK_NONE, - "VMI-alarm", - NULL, - NULL + .handler = vmi_timer_interrupt, + .flags = IRQF_DISABLED, + .mask = CPU_MASK_NONE, + .name = "VMI-alarm", }; /* Alarm rate */ @@ -153,13 +151,6 @@ static void vmi_get_wallclock_ts(struct timespec *ts) ts->tv_sec = wallclock; } -static void update_xtime_from_wallclock(void) -{ - struct timespec ts; - vmi_get_wallclock_ts(&ts); - do_settimeofday(&ts); -} - unsigned long vmi_get_wallclock(void) { struct timespec ts; @@ -172,11 +163,20 @@ int vmi_set_wallclock(unsigned long now) return -1; } -unsigned long long vmi_sched_clock(void) +unsigned long long vmi_get_sched_cycles(void) { return read_available_cycles(); } +unsigned long vmi_cpu_khz(void) +{ + unsigned long long khz; + + khz = vmi_timer_ops.get_cycle_frequency(); + (void)do_div(khz, 1000); + return khz; +} + void __init vmi_time_init(void) { unsigned long long cycles_per_sec, cycles_per_msec; @@ -188,25 +188,16 @@ void __init vmi_time_init(void) set_intr_gate(LOCAL_TIMER_VECTOR, apic_vmi_timer_interrupt); #endif - no_sync_cmos_clock = 1; - - vmi_get_wallclock_ts(&xtime); - set_normalized_timespec(&wall_to_monotonic, - -xtime.tv_sec, -xtime.tv_nsec); - real_cycles_accounted_system = read_real_cycles(); - update_xtime_from_wallclock(); per_cpu(process_times_cycles_accounted_cpu, 0) = read_available_cycles(); cycles_per_sec = vmi_timer_ops.get_cycle_frequency(); - cycles_per_jiffy = cycles_per_sec; (void)do_div(cycles_per_jiffy, HZ); cycles_per_alarm = cycles_per_sec; (void)do_div(cycles_per_alarm, alarm_hz); cycles_per_msec = cycles_per_sec; (void)do_div(cycles_per_msec, 1000); - cpu_khz = cycles_per_msec; printk(KERN_WARNING "VMI timer cycles/sec = %llu ; cycles/jiffy = %llu ;" "cycles/alarm = %llu\n", cycles_per_sec, cycles_per_jiffy, @@ -250,7 +241,7 @@ void __init vmi_timer_setup_boot_alarm(void) /* Initialize the time accounting variables for an AP on an SMP system. * Also, set the local alarm for the AP. */ -void __init vmi_timer_setup_secondary_alarm(void) +void __devinit vmi_timer_setup_secondary_alarm(void) { int cpu = smp_processor_id(); @@ -276,16 +267,13 @@ static void vmi_account_real_cycles(unsigned long long cur_real_cycles) cycles_not_accounted = cur_real_cycles - real_cycles_accounted_system; while (cycles_not_accounted >= cycles_per_jiffy) { - /* systems wide jiffies and wallclock. */ + /* systems wide jiffies. */ do_timer(1); cycles_not_accounted -= cycles_per_jiffy; real_cycles_accounted_system += cycles_per_jiffy; } - if (vmi_timer_ops.wallclock_updated()) - update_xtime_from_wallclock(); - write_sequnlock(&xtime_lock); } @@ -380,7 +368,6 @@ int vmi_stop_hz_timer(void) unsigned long seq, next; unsigned long long real_cycles_expiry; int cpu = smp_processor_id(); - int idle; BUG_ON(!irqs_disabled()); if (sysctl_hz_timer != 0) @@ -388,13 +375,13 @@ int vmi_stop_hz_timer(void) cpu_set(cpu, nohz_cpu_mask); smp_mb(); + if (rcu_needs_cpu(cpu) || local_softirq_pending() || - (next = next_timer_interrupt(), time_before_eq(next, jiffies))) { + (next = next_timer_interrupt(), + time_before_eq(next, jiffies + HZ/CONFIG_VMI_ALARM_HZ))) { cpu_clear(cpu, nohz_cpu_mask); - next = jiffies; - idle = 0; - } else - idle = 1; + return 0; + } /* Convert jiffies to the real cycle counter. */ do { @@ -404,17 +391,13 @@ int vmi_stop_hz_timer(void) } while (read_seqretry(&xtime_lock, seq)); /* This cpu is going idle. Disable the periodic alarm. */ - if (idle) { - vmi_timer_ops.cancel_alarm(VMI_CYCLES_AVAILABLE); - per_cpu(idle_start_jiffies, cpu) = jiffies; - } - + vmi_timer_ops.cancel_alarm(VMI_CYCLES_AVAILABLE); + per_cpu(idle_start_jiffies, cpu) = jiffies; /* Set the real time alarm to expire at the next event. */ vmi_timer_ops.set_alarm( - VMI_ALARM_WIRING | VMI_ALARM_IS_ONESHOT | VMI_CYCLES_REAL, - real_cycles_expiry, 0); - - return idle; + VMI_ALARM_WIRING | VMI_ALARM_IS_ONESHOT | VMI_CYCLES_REAL, + real_cycles_expiry, 0); + return 1; } static void vmi_reenable_hz_timer(int cpu) diff --git a/arch/ia64/ia32/sys_ia32.c b/arch/ia64/ia32/sys_ia32.c index d430d36ae49d..0afb4fe7c35b 100644 --- a/arch/ia64/ia32/sys_ia32.c +++ b/arch/ia64/ia32/sys_ia32.c @@ -1267,6 +1267,10 @@ sys32_getdents (unsigned int fd, struct compat_dirent __user *dirent, unsigned i struct getdents32_callback buf; int error; + error = -EFAULT; + if (!access_ok(VERIFY_WRITE, dirent, count)) + goto out; + error = -EBADF; file = fget(fd); if (!file) @@ -1283,10 +1287,10 @@ sys32_getdents (unsigned int fd, struct compat_dirent __user *dirent, unsigned i error = buf.error; lastdirent = buf.previous; if (lastdirent) { - error = -EINVAL; if (put_user(file->f_pos, &lastdirent->d_off)) - goto out_putf; - error = count - buf.count; + error = -EFAULT; + else + error = count - buf.count; } out_putf: diff --git a/arch/ia64/kernel/efi.c b/arch/ia64/kernel/efi.c index 772ba6fe110f..4061593e5b17 100644 --- a/arch/ia64/kernel/efi.c +++ b/arch/ia64/kernel/efi.c @@ -21,6 +21,7 @@ * Skip non-WB memory and ignore empty memory ranges. */ #include <linux/module.h> +#include <linux/bootmem.h> #include <linux/kernel.h> #include <linux/init.h> #include <linux/types.h> @@ -1009,6 +1010,11 @@ efi_memmap_init(unsigned long *s, unsigned long *e) } else ae = efi_md_end(md); +#ifdef CONFIG_CRASH_DUMP + /* saved_max_pfn should ignore max_addr= command line arg */ + if (saved_max_pfn < (ae >> PAGE_SHIFT)) + saved_max_pfn = (ae >> PAGE_SHIFT); +#endif /* keep within max_addr= and min_addr= command line arg */ as = max(as, min_addr); ae = min(ae, max_addr); @@ -1177,3 +1183,33 @@ kdump_find_rsvd_region (unsigned long size, return ~0UL; } #endif + +#ifdef CONFIG_PROC_VMCORE +/* locate the size find a the descriptor at a certain address */ +unsigned long +vmcore_find_descriptor_size (unsigned long address) +{ + void *efi_map_start, *efi_map_end, *p; + efi_memory_desc_t *md; + u64 efi_desc_size; + unsigned long ret = 0; + + efi_map_start = __va(ia64_boot_param->efi_memmap); + efi_map_end = efi_map_start + ia64_boot_param->efi_memmap_size; + efi_desc_size = ia64_boot_param->efi_memdesc_size; + + for (p = efi_map_start; p < efi_map_end; p += efi_desc_size) { + md = p; + if (efi_wb(md) && md->type == EFI_LOADER_DATA + && md->phys_addr == address) { + ret = efi_md_size(md); + break; + } + } + + if (ret == 0) + printk(KERN_WARNING "Cannot locate EFI vmcore descriptor\n"); + + return ret; +} +#endif diff --git a/arch/ia64/kernel/perfmon.c b/arch/ia64/kernel/perfmon.c index 9ddf896a137a..abc7ad035886 100644 --- a/arch/ia64/kernel/perfmon.c +++ b/arch/ia64/kernel/perfmon.c @@ -2299,7 +2299,7 @@ pfm_remap_buffer(struct vm_area_struct *vma, unsigned long buf, unsigned long ad * allocate a sampling buffer and remaps it into the user address space of the task */ static int -pfm_smpl_buffer_alloc(struct task_struct *task, pfm_context_t *ctx, unsigned long rsize, void **user_vaddr) +pfm_smpl_buffer_alloc(struct task_struct *task, struct file *filp, pfm_context_t *ctx, unsigned long rsize, void **user_vaddr) { struct mm_struct *mm = task->mm; struct vm_area_struct *vma = NULL; @@ -2349,6 +2349,7 @@ pfm_smpl_buffer_alloc(struct task_struct *task, pfm_context_t *ctx, unsigned lon * partially initialize the vma for the sampling buffer */ vma->vm_mm = mm; + vma->vm_file = filp; vma->vm_flags = VM_READ| VM_MAYREAD |VM_RESERVED; vma->vm_page_prot = PAGE_READONLY; /* XXX may need to change */ @@ -2387,6 +2388,8 @@ pfm_smpl_buffer_alloc(struct task_struct *task, pfm_context_t *ctx, unsigned lon goto error; } + get_file(filp); + /* * now insert the vma in the vm list for the process, must be * done with mmap lock held @@ -2464,7 +2467,7 @@ pfarg_is_sane(struct task_struct *task, pfarg_context_t *pfx) } static int -pfm_setup_buffer_fmt(struct task_struct *task, pfm_context_t *ctx, unsigned int ctx_flags, +pfm_setup_buffer_fmt(struct task_struct *task, struct file *filp, pfm_context_t *ctx, unsigned int ctx_flags, unsigned int cpu, pfarg_context_t *arg) { pfm_buffer_fmt_t *fmt = NULL; @@ -2505,7 +2508,7 @@ pfm_setup_buffer_fmt(struct task_struct *task, pfm_context_t *ctx, unsigned int /* * buffer is always remapped into the caller's address space */ - ret = pfm_smpl_buffer_alloc(current, ctx, size, &uaddr); + ret = pfm_smpl_buffer_alloc(current, filp, ctx, size, &uaddr); if (ret) goto error; /* keep track of user address of buffer */ @@ -2716,7 +2719,7 @@ pfm_context_create(pfm_context_t *ctx, void *arg, int count, struct pt_regs *reg * does the user want to sample? */ if (pfm_uuid_cmp(req->ctx_smpl_buf_id, pfm_null_uuid)) { - ret = pfm_setup_buffer_fmt(current, ctx, ctx_flags, 0, req); + ret = pfm_setup_buffer_fmt(current, filp, ctx, ctx_flags, 0, req); if (ret) goto buffer_error; } diff --git a/arch/ia64/kernel/setup.c b/arch/ia64/kernel/setup.c index 5fa09d141ab7..7d6fe65c93f4 100644 --- a/arch/ia64/kernel/setup.c +++ b/arch/ia64/kernel/setup.c @@ -251,6 +251,12 @@ reserve_memory (void) } #endif +#ifdef CONFIG_PROC_VMCORE + if (reserve_elfcorehdr(&rsvd_region[n].start, + &rsvd_region[n].end) == 0) + n++; +#endif + efi_memmap_init(&rsvd_region[n].start, &rsvd_region[n].end); n++; @@ -453,6 +459,30 @@ static int __init parse_elfcorehdr(char *arg) return 0; } early_param("elfcorehdr", parse_elfcorehdr); + +int __init reserve_elfcorehdr(unsigned long *start, unsigned long *end) +{ + unsigned long length; + + /* We get the address using the kernel command line, + * but the size is extracted from the EFI tables. + * Both address and size are required for reservation + * to work properly. + */ + + if (elfcorehdr_addr >= ELFCORE_ADDR_MAX) + return -EINVAL; + + if ((length = vmcore_find_descriptor_size(elfcorehdr_addr)) == 0) { + elfcorehdr_addr = ELFCORE_ADDR_MAX; + return -EINVAL; + } + + *start = (unsigned long)__va(elfcorehdr_addr); + *end = *start + length; + return 0; +} + #endif /* CONFIG_PROC_VMCORE */ void __init diff --git a/arch/ia64/lib/Makefile b/arch/ia64/lib/Makefile index 38fa6e49e791..46edf8444c7e 100644 --- a/arch/ia64/lib/Makefile +++ b/arch/ia64/lib/Makefile @@ -9,12 +9,11 @@ lib-y := __divsi3.o __udivsi3.o __modsi3.o __umodsi3.o \ checksum.o clear_page.o csum_partial_copy.o \ clear_user.o strncpy_from_user.o strlen_user.o strnlen_user.o \ flush.o ip_fast_csum.o do_csum.o \ - memset.o strlen.o + memset.o strlen.o xor.o lib-$(CONFIG_ITANIUM) += copy_page.o copy_user.o memcpy.o lib-$(CONFIG_MCKINLEY) += copy_page_mck.o memcpy_mck.o lib-$(CONFIG_PERFMON) += carta_random.o -lib-$(CONFIG_MD_RAID456) += xor.o AFLAGS___divdi3.o = AFLAGS___udivdi3.o = -DUNSIGNED diff --git a/arch/ia64/mm/contig.c b/arch/ia64/mm/contig.c index ca4d41e5f177..fb0f4698f5d0 100644 --- a/arch/ia64/mm/contig.c +++ b/arch/ia64/mm/contig.c @@ -197,11 +197,6 @@ find_memory (void) find_initrd(); -#ifdef CONFIG_CRASH_DUMP - /* If we are doing a crash dump, we still need to know the real mem - * size before original memory map is reset. */ - saved_max_pfn = max_pfn; -#endif } #ifdef CONFIG_SMP diff --git a/arch/ia64/mm/discontig.c b/arch/ia64/mm/discontig.c index 16835108bb5b..11a2d8825d89 100644 --- a/arch/ia64/mm/discontig.c +++ b/arch/ia64/mm/discontig.c @@ -480,12 +480,6 @@ void __init find_memory(void) max_pfn = max_low_pfn; find_initrd(); - -#ifdef CONFIG_CRASH_DUMP - /* If we are doing a crash dump, we still need to know the real mem - * size before original memory map is reset. */ - saved_max_pfn = max_pfn; -#endif } #ifdef CONFIG_SMP diff --git a/arch/m68knommu/kernel/setup.c b/arch/m68knommu/kernel/setup.c index d5c25d27b64d..8133b1047353 100644 --- a/arch/m68knommu/kernel/setup.c +++ b/arch/m68knommu/kernel/setup.c @@ -51,7 +51,7 @@ static void dummy_waitbut(void) { } -void (*mach_sched_init) (irqreturn_t (*handler)(int, void *, struct pt_regs *)); +void (*mach_sched_init) (irq_handler_t handler); void (*mach_tick)( void ); /* machine dependent keyboard functions */ int (*mach_keyb_init) (void); @@ -66,7 +66,7 @@ void (*mach_trap_init) (void); /* machine dependent timer functions */ unsigned long (*mach_gettimeoffset) (void); void (*mach_gettod) (int*, int*, int*, int*, int*, int*); -int (*mach_hwclk) (int, struct hwclk_time*); +int (*mach_hwclk) (int, struct rtc_time*); int (*mach_set_clock_mmss) (unsigned long); void (*mach_mksound)( unsigned int count, unsigned int ticks ); void (*mach_reset)( void ); diff --git a/arch/m68knommu/platform/5307/ints.c b/arch/m68knommu/platform/5307/ints.c index 20f12a19a522..751633038c4b 100644 --- a/arch/m68knommu/platform/5307/ints.c +++ b/arch/m68knommu/platform/5307/ints.c @@ -42,7 +42,6 @@ static irq_node_t nodes[NUM_IRQ_NODES]; /* The number of spurious interrupts */ volatile unsigned int num_spurious; -unsigned int local_bh_count[NR_CPUS]; unsigned int local_irq_count[NR_CPUS]; static irqreturn_t default_irq_handler(int irq, void *ptr) diff --git a/arch/m68knommu/platform/68328/ints.c b/arch/m68knommu/platform/68328/ints.c index 2dda7339aae5..3de6e337554e 100644 --- a/arch/m68knommu/platform/68328/ints.c +++ b/arch/m68knommu/platform/68328/ints.c @@ -15,6 +15,7 @@ #include <linux/sched.h> #include <linux/kernel_stat.h> #include <linux/errno.h> +#include <linux/interrupt.h> #include <asm/system.h> #include <asm/irq.h> @@ -64,7 +65,7 @@ asmlinkage void trap44(void); asmlinkage void trap45(void); asmlinkage void trap46(void); asmlinkage void trap47(void); -asmlinkage irqreturn_t bad_interrupt(int, void *, struct pt_regs *); +asmlinkage irqreturn_t bad_interrupt(int, void *); asmlinkage irqreturn_t inthandler(void); asmlinkage irqreturn_t inthandler1(void); asmlinkage irqreturn_t inthandler2(void); @@ -121,7 +122,7 @@ void init_IRQ(void) int request_irq( unsigned int irq, - irqreturn_t (*handler)(int, void *, struct pt_regs *), + irq_handler_t handler, unsigned long flags, const char *devname, void *dev_id) diff --git a/arch/m68knommu/platform/68328/timers.c b/arch/m68knommu/platform/68328/timers.c index 438ef6ee9720..ef067f4c3cd4 100644 --- a/arch/m68knommu/platform/68328/timers.c +++ b/arch/m68knommu/platform/68328/timers.c @@ -17,6 +17,7 @@ #include <linux/types.h> #include <linux/kernel.h> #include <linux/mm.h> +#include <linux/interrupt.h> #include <asm/setup.h> #include <asm/system.h> #include <asm/pgtable.h> @@ -52,7 +53,7 @@ /***************************************************************************/ -void m68328_timer_init(irqreturn_t (*timer_routine) (int, void *, struct pt_regs *)) +void m68328_timer_init(irq_handler_t timer_routine) { /* disable timer 1 */ TCTL = 0; diff --git a/arch/m68knommu/platform/68360/config.c b/arch/m68knommu/platform/68360/config.c index 1b36f6261764..4ff13bd51ffd 100644 --- a/arch/m68knommu/platform/68360/config.c +++ b/arch/m68knommu/platform/68360/config.c @@ -16,6 +16,7 @@ #include <linux/mm.h> #include <linux/tty.h> #include <linux/console.h> +#include <linux/interrupt.h> #include <asm/setup.h> #include <asm/system.h> @@ -50,7 +51,7 @@ extern unsigned long int system_clock; //In kernel setup.c extern void config_M68360_irq(void); -void BSP_sched_init(void (*timer_routine)(int, void *, struct pt_regs *)) +void BSP_sched_init(irq_handler_t timer_routine) { unsigned char prescaler; unsigned short tgcr_save; diff --git a/arch/m68knommu/platform/68EZ328/config.c b/arch/m68knommu/platform/68EZ328/config.c index 659b80aca118..ab36551fc969 100644 --- a/arch/m68knommu/platform/68EZ328/config.c +++ b/arch/m68knommu/platform/68EZ328/config.c @@ -19,6 +19,7 @@ #include <linux/mm.h> #include <linux/tty.h> #include <linux/console.h> +#include <linux/interrupt.h> #include <asm/setup.h> #include <asm/system.h> @@ -31,7 +32,7 @@ /***************************************************************************/ -void m68328_timer_init(irqreturn_t (*timer_routine) (int, void *, struct pt_regs *)); +void m68328_timer_init(irq_handler_t timer_routine); void m68328_timer_tick(void); unsigned long m68328_timer_gettimeoffset(void); void m68328_timer_gettod(int *year, int *mon, int *day, int *hour, int *min, int *sec); diff --git a/arch/m68knommu/platform/68VZ328/config.c b/arch/m68knommu/platform/68VZ328/config.c index fcd100b7594d..8abe0f6e7235 100644 --- a/arch/m68knommu/platform/68VZ328/config.c +++ b/arch/m68knommu/platform/68VZ328/config.c @@ -21,6 +21,7 @@ #include <linux/console.h> #include <linux/kd.h> #include <linux/netdevice.h> +#include <linux/interrupt.h> #include <asm/setup.h> #include <asm/system.h> @@ -36,7 +37,7 @@ /***************************************************************************/ -void m68328_timer_init(irqreturn_t (*timer_routine) (int, void *, struct pt_regs *)); +void m68328_timer_init(irq_handler_t timer_routine); void m68328_timer_tick(void); unsigned long m68328_timer_gettimeoffset(void); void m68328_timer_gettod(int *year, int *mon, int *day, int *hour, int *min, int *sec); diff --git a/arch/mips/Kconfig b/arch/mips/Kconfig index 4ec2dd5455f3..a1cd84f9b3bc 100644 --- a/arch/mips/Kconfig +++ b/arch/mips/Kconfig @@ -167,6 +167,7 @@ config MIPS_COBALT select IRQ_CPU select MIPS_GT64111 select SYS_HAS_CPU_NEVADA + select SYS_HAS_EARLY_PRINTK select SYS_SUPPORTS_32BIT_KERNEL select SYS_SUPPORTS_64BIT_KERNEL if EXPERIMENTAL select SYS_SUPPORTS_LITTLE_ENDIAN @@ -837,7 +838,6 @@ source "arch/mips/tx4927/Kconfig" source "arch/mips/tx4938/Kconfig" source "arch/mips/vr41xx/Kconfig" source "arch/mips/philips/pnx8550/common/Kconfig" -source "arch/mips/cobalt/Kconfig" endmenu diff --git a/arch/mips/cobalt/Kconfig b/arch/mips/cobalt/Kconfig deleted file mode 100644 index 7c42b088d16c..000000000000 --- a/arch/mips/cobalt/Kconfig +++ /dev/null @@ -1,7 +0,0 @@ -config EARLY_PRINTK - bool "Early console support" - depends on MIPS_COBALT - help - Provide early console support by direct access to the - on board UART. The UART must have been previously - initialised by the boot loader. diff --git a/arch/mips/cobalt/console.c b/arch/mips/cobalt/console.c index fff20d28114f..ca56b415b8ac 100644 --- a/arch/mips/cobalt/console.c +++ b/arch/mips/cobalt/console.c @@ -9,11 +9,8 @@ #include <asm/addrspace.h> #include <asm/mach-cobalt/cobalt.h> -static void putchar(int c) +void prom_putchar(char c) { - if(c == '\n') - putchar('\r'); - while(!(COBALT_UART[UART_LSR] & UART_LSR_THRE)) ; diff --git a/arch/mips/kernel/mips_ksyms.c b/arch/mips/kernel/mips_ksyms.c index 2ef857c3ee53..225755d0c1f6 100644 --- a/arch/mips/kernel/mips_ksyms.c +++ b/arch/mips/kernel/mips_ksyms.c @@ -37,6 +37,7 @@ EXPORT_SYMBOL(kernel_thread); * Userspace access stuff. */ EXPORT_SYMBOL(__copy_user); +EXPORT_SYMBOL(__copy_user_inatomic); EXPORT_SYMBOL(__bzero); EXPORT_SYMBOL(__strncpy_from_user_nocheck_asm); EXPORT_SYMBOL(__strncpy_from_user_asm); diff --git a/arch/mips/kernel/scall32-o32.S b/arch/mips/kernel/scall32-o32.S index 7c0b3936ba44..0c9a9ff8cd25 100644 --- a/arch/mips/kernel/scall32-o32.S +++ b/arch/mips/kernel/scall32-o32.S @@ -656,6 +656,8 @@ einval: li v0, -EINVAL sys sys_kexec_load 4 sys sys_getcpu 3 sys sys_epoll_pwait 6 + sys sys_ioprio_set 3 + sys sys_ioprio_get 2 .endm /* We pre-compute the number of _instruction_ bytes needed to diff --git a/arch/mips/kernel/scall64-64.S b/arch/mips/kernel/scall64-64.S index e569b846e9a3..23f3b118f718 100644 --- a/arch/mips/kernel/scall64-64.S +++ b/arch/mips/kernel/scall64-64.S @@ -471,3 +471,6 @@ sys_call_table: PTR sys_kexec_load /* 5270 */ PTR sys_getcpu PTR sys_epoll_pwait + PTR sys_ioprio_set + PTR sys_ioprio_get + .size sys_call_table,.-sys_call_table diff --git a/arch/mips/kernel/scall64-n32.S b/arch/mips/kernel/scall64-n32.S index f17e31e3bff2..6eac28337423 100644 --- a/arch/mips/kernel/scall64-n32.S +++ b/arch/mips/kernel/scall64-n32.S @@ -395,5 +395,8 @@ EXPORT(sysn32_call_table) PTR compat_sys_set_robust_list PTR compat_sys_get_robust_list PTR compat_sys_kexec_load - PTR sys_getcpu + PTR sys_getcpu /* 6275 */ PTR compat_sys_epoll_pwait + PTR sys_ioprio_set + PTR sys_ioprio_get + .size sysn32_call_table,.-sysn32_call_table diff --git a/arch/mips/kernel/scall64-o32.S b/arch/mips/kernel/scall64-o32.S index 142c9b70c026..7e74b412a782 100644 --- a/arch/mips/kernel/scall64-o32.S +++ b/arch/mips/kernel/scall64-o32.S @@ -519,4 +519,6 @@ sys_call_table: PTR compat_sys_kexec_load PTR sys_getcpu PTR compat_sys_epoll_pwait + PTR sys_ioprio_set + PTR sys_ioprio_get /* 4315 */ .size sys_call_table,.-sys_call_table diff --git a/arch/mips/mips-boards/generic/init.c b/arch/mips/mips-boards/generic/init.c index b11337600129..1acdf091c258 100644 --- a/arch/mips/mips-boards/generic/init.c +++ b/arch/mips/mips-boards/generic/init.c @@ -251,8 +251,6 @@ void __init mips_ejtag_setup (void) void __init prom_init(void) { - u32 start, map, mask, data; - prom_argc = fw_arg0; _prom_argv = (int *) fw_arg1; _prom_envp = (int *) fw_arg2; @@ -278,6 +276,8 @@ void __init prom_init(void) mips_revision_corid = MIPS_REVISION_CORID_CORE_EMUL_MSC; } switch(mips_revision_corid) { + u32 start, map, mask, data; + case MIPS_REVISION_CORID_QED_RM5261: case MIPS_REVISION_CORID_CORE_LV: case MIPS_REVISION_CORID_CORE_FPGA: diff --git a/arch/mips/mips-boards/malta/Makefile b/arch/mips/mips-boards/malta/Makefile index cb7f349b0514..377d9e8f250a 100644 --- a/arch/mips/mips-boards/malta/Makefile +++ b/arch/mips/mips-boards/malta/Makefile @@ -21,4 +21,4 @@ obj-y := malta_int.o malta_setup.o obj-$(CONFIG_MTD) += malta_mtd.o -obj-$(CONFIG_SMP) += malta_smp.o +obj-$(CONFIG_MIPS_MT_SMTC) += malta_smtc.o diff --git a/arch/mips/mips-boards/malta/malta_smp.c b/arch/mips/mips-boards/malta/malta_smtc.c index cf967170fe29..d1c80f631100 100644 --- a/arch/mips/mips-boards/malta/malta_smp.c +++ b/arch/mips/mips-boards/malta/malta_smtc.c @@ -1,25 +1,14 @@ /* * Malta Platform-specific hooks for SMP operation */ +#include <linux/init.h> -#include <linux/kernel.h> -#include <linux/sched.h> -#include <linux/cpumask.h> -#include <linux/interrupt.h> - -#include <asm/atomic.h> -#include <asm/cpu.h> -#include <asm/processor.h> -#include <asm/system.h> -#include <asm/hardirq.h> -#include <asm/mmu_context.h> -#include <asm/smp.h> -#ifdef CONFIG_MIPS_MT_SMTC +#include <asm/mipsregs.h> +#include <asm/mipsmtregs.h> +#include <asm/smtc.h> #include <asm/smtc_ipi.h> -#endif /* CONFIG_MIPS_MT_SMTC */ /* VPE/SMP Prototype implements platform interfaces directly */ -#if !defined(CONFIG_MIPS_MT_SMP) /* * Cause the specified action to be performed on a targeted "CPU" @@ -27,10 +16,8 @@ void core_send_ipi(int cpu, unsigned int action) { -/* "CPU" may be TC of same VPE, VPE of same CPU, or different CPU */ -#ifdef CONFIG_MIPS_MT_SMTC + /* "CPU" may be TC of same VPE, VPE of same CPU, or different CPU */ smtc_send_ipi(cpu, LINUX_SMP_IPI, action); -#endif /* CONFIG_MIPS_MT_SMTC */ } /* @@ -39,9 +26,7 @@ void core_send_ipi(int cpu, unsigned int action) void prom_boot_secondary(int cpu, struct task_struct *idle) { -#ifdef CONFIG_MIPS_MT_SMTC smtc_boot_secondary(cpu, idle); -#endif /* CONFIG_MIPS_MT_SMTC */ } /* @@ -50,7 +35,6 @@ void prom_boot_secondary(int cpu, struct task_struct *idle) void prom_init_secondary(void) { -#ifdef CONFIG_MIPS_MT_SMTC void smtc_init_secondary(void); int myvpe; @@ -65,7 +49,6 @@ void prom_init_secondary(void) } smtc_init_secondary(); -#endif /* CONFIG_MIPS_MT_SMTC */ } /* @@ -93,9 +76,7 @@ void __init plat_prepare_cpus(unsigned int max_cpus) void prom_smp_finish(void) { -#ifdef CONFIG_MIPS_MT_SMTC smtc_smp_finish(); -#endif /* CONFIG_MIPS_MT_SMTC */ } /* @@ -105,5 +86,3 @@ void prom_smp_finish(void) void prom_cpus_done(void) { } - -#endif /* CONFIG_MIPS32R2_MT_SMP */ diff --git a/arch/mips/mm/c-tx39.c b/arch/mips/mm/c-tx39.c index f32ebde30ccf..560a6de96556 100644 --- a/arch/mips/mm/c-tx39.c +++ b/arch/mips/mm/c-tx39.c @@ -128,7 +128,6 @@ static inline void tx39_flush_cache_all(void) return; tx39_blast_dcache(); - tx39_blast_icache(); } static inline void tx39___flush_cache_all(void) @@ -142,24 +141,19 @@ static void tx39_flush_cache_mm(struct mm_struct *mm) if (!cpu_has_dc_aliases) return; - if (cpu_context(smp_processor_id(), mm) != 0) { - tx39_flush_cache_all(); - } + if (cpu_context(smp_processor_id(), mm) != 0) + tx39_blast_dcache(); } static void tx39_flush_cache_range(struct vm_area_struct *vma, unsigned long start, unsigned long end) { - int exec; - + if (!cpu_has_dc_aliases) + return; if (!(cpu_context(smp_processor_id(), vma->vm_mm))) return; - exec = vma->vm_flags & VM_EXEC; - if (cpu_has_dc_aliases || exec) - tx39_blast_dcache(); - if (exec) - tx39_blast_icache(); + tx39_blast_dcache(); } static void tx39_flush_cache_page(struct vm_area_struct *vma, unsigned long page, unsigned long pfn) @@ -218,7 +212,7 @@ static void tx39_flush_cache_page(struct vm_area_struct *vma, unsigned long page static void local_tx39_flush_data_cache_page(void * addr) { - tx39_blast_dcache_page(addr); + tx39_blast_dcache_page((unsigned long)addr); } static void tx39_flush_data_cache_page(unsigned long addr) diff --git a/arch/mips/momentum/jaguar_atx/platform.c b/arch/mips/momentum/jaguar_atx/platform.c index 771e55f39875..561844878a90 100644 --- a/arch/mips/momentum/jaguar_atx/platform.c +++ b/arch/mips/momentum/jaguar_atx/platform.c @@ -48,6 +48,8 @@ static struct resource mv64x60_eth0_resources[] = { }; static struct mv643xx_eth_platform_data eth0_pd = { + .port_number = 0, + .tx_sram_addr = MV_SRAM_BASE_ETH0, .tx_sram_size = MV_SRAM_TXRING_SIZE, .tx_queue_size = MV_SRAM_TXRING_SIZE / 16, @@ -77,6 +79,8 @@ static struct resource mv64x60_eth1_resources[] = { }; static struct mv643xx_eth_platform_data eth1_pd = { + .port_number = 1, + .tx_sram_addr = MV_SRAM_BASE_ETH1, .tx_sram_size = MV_SRAM_TXRING_SIZE, .tx_queue_size = MV_SRAM_TXRING_SIZE / 16, @@ -105,7 +109,9 @@ static struct resource mv64x60_eth2_resources[] = { }, }; -static struct mv643xx_eth_platform_data eth2_pd; +static struct mv643xx_eth_platform_data eth2_pd = { + .port_number = 2, +}; static struct platform_device eth2_device = { .name = MV643XX_ETH_NAME, diff --git a/arch/mips/momentum/ocelot_3/platform.c b/arch/mips/momentum/ocelot_3/platform.c index b80733f0c66d..44e4c3fc7403 100644 --- a/arch/mips/momentum/ocelot_3/platform.c +++ b/arch/mips/momentum/ocelot_3/platform.c @@ -48,6 +48,8 @@ static struct resource mv64x60_eth0_resources[] = { }; static struct mv643xx_eth_platform_data eth0_pd = { + .port_number = 0, + .tx_sram_addr = MV_SRAM_BASE_ETH0, .tx_sram_size = MV_SRAM_TXRING_SIZE, .tx_queue_size = MV_SRAM_TXRING_SIZE / 16, @@ -77,6 +79,8 @@ static struct resource mv64x60_eth1_resources[] = { }; static struct mv643xx_eth_platform_data eth1_pd = { + .port_number = 1, + .tx_sram_addr = MV_SRAM_BASE_ETH1, .tx_sram_size = MV_SRAM_TXRING_SIZE, .tx_queue_size = MV_SRAM_TXRING_SIZE / 16, @@ -105,7 +109,9 @@ static struct resource mv64x60_eth2_resources[] = { }, }; -static struct mv643xx_eth_platform_data eth2_pd; +static struct mv643xx_eth_platform_data eth2_pd = { + .port_number = 2, +}; static struct platform_device eth2_device = { .name = MV643XX_ETH_NAME, diff --git a/arch/mips/momentum/ocelot_c/platform.c b/arch/mips/momentum/ocelot_c/platform.c index f7cd303f3eba..7780aa0c6555 100644 --- a/arch/mips/momentum/ocelot_c/platform.c +++ b/arch/mips/momentum/ocelot_c/platform.c @@ -47,6 +47,8 @@ static struct resource mv64x60_eth0_resources[] = { }; static struct mv643xx_eth_platform_data eth0_pd = { + .port_number = 0, + .tx_sram_addr = MV_SRAM_BASE_ETH0, .tx_sram_size = MV_SRAM_TXRING_SIZE, .tx_queue_size = MV_SRAM_TXRING_SIZE / 16, @@ -76,6 +78,8 @@ static struct resource mv64x60_eth1_resources[] = { }; static struct mv643xx_eth_platform_data eth1_pd = { + .port_number = 1, + .tx_sram_addr = MV_SRAM_BASE_ETH1, .tx_sram_size = MV_SRAM_TXRING_SIZE, .tx_queue_size = MV_SRAM_TXRING_SIZE / 16, diff --git a/arch/mips/sgi-ip27/ip27-init.c b/arch/mips/sgi-ip27/ip27-init.c index 9094baf31d0e..74158d349630 100644 --- a/arch/mips/sgi-ip27/ip27-init.c +++ b/arch/mips/sgi-ip27/ip27-init.c @@ -191,7 +191,6 @@ static inline void ioc3_eth_init(void) ioc3->eier = 0; } -extern void ip27_setup_console(void); extern void ip27_time_init(void); extern void ip27_reboot_setup(void); @@ -200,7 +199,6 @@ void __init plat_mem_setup(void) hubreg_t p, e, n_mode; nasid_t nid; - ip27_setup_console(); ip27_reboot_setup(); /* diff --git a/arch/powerpc/kernel/irq.c b/arch/powerpc/kernel/irq.c index 919fbf568495..100930826850 100644 --- a/arch/powerpc/kernel/irq.c +++ b/arch/powerpc/kernel/irq.c @@ -968,7 +968,6 @@ void pci_scan_msi_device(struct pci_dev *dev) {} int pci_enable_msix(struct pci_dev* dev, struct msix_entry *entries, int nvec) {return -1;} void pci_disable_msix(struct pci_dev *dev) {} void msi_remove_pci_irq_vectors(struct pci_dev *dev) {} -void disable_msi_mode(struct pci_dev *dev, int pos, int type) {} void pci_no_msi(void) {} EXPORT_SYMBOL(pci_enable_msix); EXPORT_SYMBOL(pci_disable_msix); diff --git a/arch/powerpc/platforms/chrp/pegasos_eth.c b/arch/powerpc/platforms/chrp/pegasos_eth.c index 6ad4b1a72c96..71045677559a 100644 --- a/arch/powerpc/platforms/chrp/pegasos_eth.c +++ b/arch/powerpc/platforms/chrp/pegasos_eth.c @@ -58,6 +58,7 @@ static struct resource mv643xx_eth0_resources[] = { static struct mv643xx_eth_platform_data eth0_pd = { + .port_number = 0, .tx_sram_addr = PEGASOS2_SRAM_BASE_ETH0, .tx_sram_size = PEGASOS2_SRAM_TXRING_SIZE, .tx_queue_size = PEGASOS2_SRAM_TXRING_SIZE/16, @@ -87,6 +88,7 @@ static struct resource mv643xx_eth1_resources[] = { }; static struct mv643xx_eth_platform_data eth1_pd = { + .port_number = 1, .tx_sram_addr = PEGASOS2_SRAM_BASE_ETH1, .tx_sram_size = PEGASOS2_SRAM_TXRING_SIZE, .tx_queue_size = PEGASOS2_SRAM_TXRING_SIZE/16, diff --git a/arch/ppc/syslib/mv64x60.c b/arch/ppc/syslib/mv64x60.c index 3b039c30a439..a6f8b686ea83 100644 --- a/arch/ppc/syslib/mv64x60.c +++ b/arch/ppc/syslib/mv64x60.c @@ -339,7 +339,9 @@ static struct resource mv64x60_eth0_resources[] = { }, }; -static struct mv643xx_eth_platform_data eth0_pd; +static struct mv643xx_eth_platform_data eth0_pd = { + .port_number = 0, +}; static struct platform_device eth0_device = { .name = MV643XX_ETH_NAME, @@ -362,7 +364,9 @@ static struct resource mv64x60_eth1_resources[] = { }, }; -static struct mv643xx_eth_platform_data eth1_pd; +static struct mv643xx_eth_platform_data eth1_pd = { + .port_number = 1, +}; static struct platform_device eth1_device = { .name = MV643XX_ETH_NAME, @@ -385,7 +389,9 @@ static struct resource mv64x60_eth2_resources[] = { }, }; -static struct mv643xx_eth_platform_data eth2_pd; +static struct mv643xx_eth_platform_data eth2_pd = { + .port_number = 2, +}; static struct platform_device eth2_device = { .name = MV643XX_ETH_NAME, diff --git a/arch/s390/Kconfig b/arch/s390/Kconfig index d9425f59be91..0f293aa7b0fa 100644 --- a/arch/s390/Kconfig +++ b/arch/s390/Kconfig @@ -376,6 +376,8 @@ config SHARED_KERNEL Select this option, if you want to share the text segment of the Linux kernel between different VM guests. This reduces memory usage with lots of guests but greatly increases kernel size. + Also if a kernel was IPL'ed from a shared segment the kexec system + call will not work. You should only select this option if you know what you are doing and want to exploit this feature. diff --git a/arch/s390/kernel/head31.S b/arch/s390/kernel/head31.S index da7c8bb80982..dc364c1419af 100644 --- a/arch/s390/kernel/head31.S +++ b/arch/s390/kernel/head31.S @@ -121,7 +121,7 @@ startup_continue: .long .Lduct # cr2: dispatchable unit control table .long 0 # cr3: instruction authorization .long 0 # cr4: instruction authorization - .long 0xffffffff # cr5: primary-aste origin + .long .Lduct # cr5: primary-aste origin .long 0 # cr6: I/O interrupts .long 0 # cr7: secondary space segment table .long 0 # cr8: access registers translation @@ -132,8 +132,6 @@ startup_continue: .long 0 # cr13: home space segment table .long 0xc0000000 # cr14: machine check handling off .long 0 # cr15: linkage stack operations -.Lduct: .long 0,0,0,0,0,0,0,0 - .long 0,0,0,0,0,0,0,0 .Lpcfpu:.long 0x00080000,0x80000000 + .Lchkfpu .Lpccsp:.long 0x00080000,0x80000000 + .Lchkcsp .Lpcmvpg:.long 0x00080000,0x80000000 + .Lchkmvpg @@ -147,6 +145,13 @@ startup_continue: .Linittu: .long init_thread_union .Lstartup_init: .long startup_init + .align 64 +.Lduct: .long 0,0,0,0,.Lduald,0,0,0 + .long 0,0,0,0,0,0,0,0 + .align 128 +.Lduald:.rept 8 + .long 0x80000000,0,0,0 # invalid access-list entries + .endr .org 0x12000 .globl _ehead diff --git a/arch/s390/kernel/head64.S b/arch/s390/kernel/head64.S index af09e18cc5d0..37010709fe68 100644 --- a/arch/s390/kernel/head64.S +++ b/arch/s390/kernel/head64.S @@ -134,7 +134,7 @@ startup_continue: .quad .Lduct # cr2: dispatchable unit control table .quad 0 # cr3: instruction authorization .quad 0 # cr4: instruction authorization - .quad 0xffffffffffffffff # cr5: primary-aste origin + .quad .Lduct # cr5: primary-aste origin .quad 0 # cr6: I/O interrupts .quad 0 # cr7: secondary space segment table .quad 0 # cr8: access registers translation @@ -145,14 +145,19 @@ startup_continue: .quad 0 # cr13: home space segment table .quad 0xc0000000 # cr14: machine check handling off .quad 0 # cr15: linkage stack operations -.Lduct: .long 0,0,0,0,0,0,0,0 - .long 0,0,0,0,0,0,0,0 .Lpcmsk:.quad 0x0000000180000000 .L4malign:.quad 0xffffffffffc00000 .Lscan2g:.quad 0x80000000 + 0x20000 - 8 # 2GB + 128K - 8 .Lnop: .long 0x07000700 .Lparmaddr: .quad PARMAREA + .align 64 +.Lduct: .long 0,0,0,0,.Lduald,0,0,0 + .long 0,0,0,0,0,0,0,0 + .align 128 +.Lduald:.rept 8 + .long 0x80000000,0,0,0 # invalid access-list entries + .endr .org 0x12000 .globl _ehead diff --git a/arch/s390/kernel/ipl.c b/arch/s390/kernel/ipl.c index 5a863a3bf10c..d125a4ead08d 100644 --- a/arch/s390/kernel/ipl.c +++ b/arch/s390/kernel/ipl.c @@ -1066,7 +1066,7 @@ static void do_reset_calls(void) reset->fn(); } -extern __u32 dump_prefix_page; +u32 dump_prefix_page; void s390_reset_system(void) { @@ -1078,7 +1078,7 @@ void s390_reset_system(void) lc->panic_stack = S390_lowcore.panic_stack; /* Save prefix page address for dump case */ - dump_prefix_page = (unsigned long) lc; + dump_prefix_page = (u32)(unsigned long) lc; /* Disable prefixing */ set_prefix(0); diff --git a/arch/s390/kernel/kprobes.c b/arch/s390/kernel/kprobes.c index a466bab6677e..8af549e95730 100644 --- a/arch/s390/kernel/kprobes.c +++ b/arch/s390/kernel/kprobes.c @@ -337,21 +337,14 @@ static int __kprobes kprobe_handler(struct pt_regs *regs) } p = get_kprobe(addr); - if (!p) { - if (*addr != BREAKPOINT_INSTRUCTION) { - /* - * The breakpoint instruction was removed right - * after we hit it. Another cpu has removed - * either a probepoint or a debugger breakpoint - * at this address. In either case, no further - * handling of this interrupt is appropriate. - * - */ - ret = 1; - } - /* Not one of ours: let kernel handle it */ + if (!p) + /* + * No kprobe at this address. The fault has not been + * caused by a kprobe breakpoint. The race of breakpoint + * vs. kprobe remove does not exist because on s390 we + * use stop_machine_run to arm/disarm the breakpoints. + */ goto no_kprobe; - } kcb->kprobe_status = KPROBE_HIT_ACTIVE; set_current_kprobe(p, regs, kcb); diff --git a/arch/s390/kernel/machine_kexec.c b/arch/s390/kernel/machine_kexec.c index 52f57af252b4..3c77dd36994c 100644 --- a/arch/s390/kernel/machine_kexec.c +++ b/arch/s390/kernel/machine_kexec.c @@ -19,6 +19,7 @@ #include <asm/system.h> #include <asm/smp.h> #include <asm/reset.h> +#include <asm/ipl.h> typedef void (*relocate_kernel_t)(kimage_entry_t *, unsigned long); @@ -29,6 +30,10 @@ int machine_kexec_prepare(struct kimage *image) { void *reboot_code_buffer; + /* Can't replace kernel image since it is read-only. */ + if (ipl_flags & IPL_NSS_VALID) + return -ENOSYS; + /* We don't support anything but the default image type for now. */ if (image->type != KEXEC_TYPE_DEFAULT) return -EINVAL; diff --git a/arch/s390/kernel/reipl.S b/arch/s390/kernel/reipl.S index c3f4d9b95083..2f481cc3d1c9 100644 --- a/arch/s390/kernel/reipl.S +++ b/arch/s390/kernel/reipl.S @@ -8,6 +8,10 @@ #include <asm/lowcore.h> +# +# do_reipl_asm +# Parameter: r2 = schid of reipl device +# .globl do_reipl_asm do_reipl_asm: basr %r13,0 .Lpg0: lpsw .Lnewpsw-.Lpg0(%r13) @@ -16,12 +20,12 @@ do_reipl_asm: basr %r13,0 stm %r0,%r15,__LC_GPREGS_SAVE_AREA stctl %c0,%c15,__LC_CREGS_SAVE_AREA stam %a0,%a15,__LC_AREGS_SAVE_AREA - mvc __LC_PREFIX_SAVE_AREA(4),dump_prefix_page-.Lpg0(%r13) + l %r10,.Ldump_pfx-.Lpg0(%r13) + mvc __LC_PREFIX_SAVE_AREA(4),0(%r10) stckc .Lclkcmp-.Lpg0(%r13) mvc __LC_CLOCK_COMP_SAVE_AREA(8),.Lclkcmp-.Lpg0(%r13) stpt __LC_CPU_TIMER_SAVE_AREA st %r13, __LC_PSW_SAVE_AREA+4 - lctl %c6,%c6,.Lall-.Lpg0(%r13) lr %r1,%r2 mvc __LC_PGM_NEW_PSW(8),.Lpcnew-.Lpg0(%r13) @@ -55,6 +59,7 @@ do_reipl_asm: basr %r13,0 .align 8 .Lclkcmp: .quad 0x0000000000000000 .Lall: .long 0xff000000 +.Ldump_pfx: .long dump_prefix_page .align 8 .Lnewpsw: .long 0x00080000,0x80000000+.Lpg1 .Lpcnew: .long 0x00080000,0x80000000+.Lecs @@ -79,7 +84,3 @@ do_reipl_asm: basr %r13,0 .long 0x00000000,0x00000000 .long 0x00000000,0x00000000 .long 0x00000000,0x00000000 - .globl dump_prefix_page -dump_prefix_page: - .long 0x00000000 - diff --git a/arch/s390/kernel/reipl64.S b/arch/s390/kernel/reipl64.S index dbb3eed38865..c41930499a5f 100644 --- a/arch/s390/kernel/reipl64.S +++ b/arch/s390/kernel/reipl64.S @@ -8,6 +8,12 @@ */ #include <asm/lowcore.h> + +# +# do_reipl_asm +# Parameter: r2 = schid of reipl device +# + .globl do_reipl_asm do_reipl_asm: basr %r13,0 .Lpg0: lpswe .Lnewpsw-.Lpg0(%r13) @@ -20,7 +26,8 @@ do_reipl_asm: basr %r13,0 stg %r0,__LC_GPREGS_SAVE_AREA-0x1000+8(%r1) stctg %c0,%c15,__LC_CREGS_SAVE_AREA-0x1000(%r1) stam %a0,%a15,__LC_AREGS_SAVE_AREA-0x1000(%r1) - mvc __LC_PREFIX_SAVE_AREA-0x1000(4,%r1),dump_prefix_page-.Lpg0(%r13) + lg %r10,.Ldump_pfx-.Lpg0(%r13) + mvc __LC_PREFIX_SAVE_AREA-0x1000(4,%r1),0(%r10) stfpc __LC_FP_CREG_SAVE_AREA-0x1000(%r1) stckc .Lclkcmp-.Lpg0(%r13) mvc __LC_CLOCK_COMP_SAVE_AREA-0x1000(8,%r1),.Lclkcmp-.Lpg0(%r13) @@ -64,6 +71,7 @@ do_reipl_asm: basr %r13,0 .align 8 .Lclkcmp: .quad 0x0000000000000000 .Lall: .quad 0x00000000ff000000 +.Ldump_pfx: .quad dump_prefix_page .Lregsave: .quad 0x0000000000000000 .align 16 /* @@ -103,6 +111,3 @@ do_reipl_asm: basr %r13,0 .long 0x00000000,0x00000000 .long 0x00000000,0x00000000 .long 0x00000000,0x00000000 - .globl dump_prefix_page -dump_prefix_page: - .long 0x00000000 diff --git a/arch/s390/kernel/smp.c b/arch/s390/kernel/smp.c index ecaa432a99f8..97764f710bb7 100644 --- a/arch/s390/kernel/smp.c +++ b/arch/s390/kernel/smp.c @@ -94,10 +94,9 @@ static void __smp_call_function_map(void (*func) (void *info), void *info, int cpu, local = 0; /* - * Can deadlock when interrupts are disabled or if in wrong context, - * caller must disable preemption + * Can deadlock when interrupts are disabled or if in wrong context. */ - WARN_ON(irqs_disabled() || in_irq() || preemptible()); + WARN_ON(irqs_disabled() || in_irq()); /* * Check for local function call. We have to have the same call order @@ -152,17 +151,18 @@ out: * Run a function on all other CPUs. * * You must not call this function with disabled interrupts or from a - * hardware interrupt handler. Must be called with preemption disabled. - * You may call it from a bottom half. + * hardware interrupt handler. You may call it from a bottom half. */ int smp_call_function(void (*func) (void *info), void *info, int nonatomic, int wait) { cpumask_t map; + preempt_disable(); map = cpu_online_map; cpu_clear(smp_processor_id(), map); __smp_call_function_map(func, info, nonatomic, wait, map); + preempt_enable(); return 0; } EXPORT_SYMBOL(smp_call_function); @@ -178,16 +178,17 @@ EXPORT_SYMBOL(smp_call_function); * Run a function on one processor. * * You must not call this function with disabled interrupts or from a - * hardware interrupt handler. Must be called with preemption disabled. - * You may call it from a bottom half. + * hardware interrupt handler. You may call it from a bottom half. */ int smp_call_function_on(void (*func) (void *info), void *info, int nonatomic, int wait, int cpu) { cpumask_t map = CPU_MASK_NONE; + preempt_disable(); cpu_set(cpu, map); __smp_call_function_map(func, info, nonatomic, wait, map); + preempt_enable(); return 0; } EXPORT_SYMBOL(smp_call_function_on); diff --git a/arch/s390/mm/fault.c b/arch/s390/mm/fault.c index 641aef36ccc4..7462aebd3eb6 100644 --- a/arch/s390/mm/fault.c +++ b/arch/s390/mm/fault.c @@ -108,53 +108,40 @@ void bust_spinlocks(int yes) } /* - * Check which address space is addressed by the access - * register in S390_lowcore.exc_access_id. - * Returns 1 for user space and 0 for kernel space. + * Returns the address space associated with the fault. + * Returns 0 for kernel space, 1 for user space and + * 2 for code execution in user space with noexec=on. */ -static int __check_access_register(struct pt_regs *regs, int error_code) -{ - int areg = S390_lowcore.exc_access_id; - - if (areg == 0) - /* Access via access register 0 -> kernel address */ - return 0; - save_access_regs(current->thread.acrs); - if (regs && areg < NUM_ACRS && current->thread.acrs[areg] <= 1) - /* - * access register contains 0 -> kernel address, - * access register contains 1 -> user space address - */ - return current->thread.acrs[areg]; - - /* Something unhealthy was done with the access registers... */ - die("page fault via unknown access register", regs, error_code); - do_exit(SIGKILL); - return 0; -} - -/* - * Check which address space the address belongs to. - * May return 1 or 2 for user space and 0 for kernel space. - * Returns 2 for user space in primary addressing mode with - * CONFIG_S390_EXEC_PROTECT on and kernel parameter noexec=on. - */ -static inline int check_user_space(struct pt_regs *regs, int error_code) +static inline int check_space(struct task_struct *tsk) { /* - * The lowest two bits of S390_lowcore.trans_exc_code indicate - * which paging table was used: - * 0: Primary Segment Table Descriptor - * 1: STD determined via access register - * 2: Secondary Segment Table Descriptor - * 3: Home Segment Table Descriptor + * The lowest two bits of S390_lowcore.trans_exc_code + * indicate which paging table was used. */ - int descriptor = S390_lowcore.trans_exc_code & 3; - if (unlikely(descriptor == 1)) - return __check_access_register(regs, error_code); - if (descriptor == 2) - return current->thread.mm_segment.ar4; - return ((descriptor != 0) ^ (switch_amode)) << s390_noexec; + int desc = S390_lowcore.trans_exc_code & 3; + + if (desc == 3) /* Home Segment Table Descriptor */ + return switch_amode == 0; + if (desc == 2) /* Secondary Segment Table Descriptor */ + return tsk->thread.mm_segment.ar4; +#ifdef CONFIG_S390_SWITCH_AMODE + if (unlikely(desc == 1)) { /* STD determined via access register */ + /* %a0 always indicates primary space. */ + if (S390_lowcore.exc_access_id != 0) { + save_access_regs(tsk->thread.acrs); + /* + * An alet of 0 indicates primary space. + * An alet of 1 indicates secondary space. + * Any other alet values generate an + * alen-translation exception. + */ + if (tsk->thread.acrs[S390_lowcore.exc_access_id]) + return tsk->thread.mm_segment.ar4; + } + } +#endif + /* Primary Segment Table Descriptor */ + return switch_amode << s390_noexec; } /* @@ -265,16 +252,16 @@ out_fault: * 11 Page translation -> Not present (nullification) * 3b Region third trans. -> Not present (nullification) */ -static inline void __kprobes +static inline void do_exception(struct pt_regs *regs, unsigned long error_code, int is_protection) { struct task_struct *tsk; struct mm_struct *mm; struct vm_area_struct * vma; unsigned long address; - int user_address; const struct exception_table_entry *fixup; - int si_code = SEGV_MAPERR; + int si_code; + int space; tsk = current; mm = tsk->mm; @@ -294,7 +281,7 @@ do_exception(struct pt_regs *regs, unsigned long error_code, int is_protection) NULL pointer write access in kernel mode. */ if (!(regs->psw.mask & PSW_MASK_PSTATE)) { address = 0; - user_address = 0; + space = 0; goto no_context; } @@ -309,15 +296,15 @@ do_exception(struct pt_regs *regs, unsigned long error_code, int is_protection) * the address */ address = S390_lowcore.trans_exc_code & __FAIL_ADDR_MASK; - user_address = check_user_space(regs, error_code); + space = check_space(tsk); /* * Verify that the fault happened in user space, that * we are not in an interrupt and that there is a * user context. */ - if (user_address == 0 || in_atomic() || !mm) - goto no_context; + if (unlikely(space == 0 || in_atomic() || !mm)) + goto no_context; /* * When we get here, the fault happened in the current @@ -328,12 +315,13 @@ do_exception(struct pt_regs *regs, unsigned long error_code, int is_protection) down_read(&mm->mmap_sem); - vma = find_vma(mm, address); - if (!vma) - goto bad_area; + si_code = SEGV_MAPERR; + vma = find_vma(mm, address); + if (!vma) + goto bad_area; #ifdef CONFIG_S390_EXEC_PROTECT - if (unlikely((user_address == 2) && !(vma->vm_flags & VM_EXEC))) + if (unlikely((space == 2) && !(vma->vm_flags & VM_EXEC))) if (!signal_return(mm, regs, address, error_code)) /* * signal_return() has done an up_read(&mm->mmap_sem) @@ -389,7 +377,7 @@ survive: * The instruction that caused the program check will * be repeated. Don't signal single step via SIGTRAP. */ - clear_tsk_thread_flag(current, TIF_SINGLE_STEP); + clear_tsk_thread_flag(tsk, TIF_SINGLE_STEP); return; /* @@ -419,7 +407,7 @@ no_context: * Oops. The kernel tried to access some bad page. We'll have to * terminate things with extreme prejudice. */ - if (user_address == 0) + if (space == 0) printk(KERN_ALERT "Unable to handle kernel pointer dereference" " at virtual kernel address %p\n", (void *)address); else @@ -462,13 +450,14 @@ do_sigbus: goto no_context; } -void do_protection_exception(struct pt_regs *regs, unsigned long error_code) +void __kprobes do_protection_exception(struct pt_regs *regs, + unsigned long error_code) { regs->psw.addr -= (error_code >> 16); do_exception(regs, 4, 1); } -void do_dat_exception(struct pt_regs *regs, unsigned long error_code) +void __kprobes do_dat_exception(struct pt_regs *regs, unsigned long error_code) { do_exception(regs, error_code & 0xff, 0); } diff --git a/arch/um/kernel/signal.c b/arch/um/kernel/signal.c index 2a32e5e8e9c9..3c798cdde550 100644 --- a/arch/um/kernel/signal.c +++ b/arch/um/kernel/signal.c @@ -158,12 +158,12 @@ static int kern_do_signal(struct pt_regs *regs) clear_thread_flag(TIF_RESTORE_SIGMASK); sigprocmask(SIG_SETMASK, ¤t->saved_sigmask, NULL); } - return(handled_sig); + return handled_sig; } int do_signal(void) { - return(kern_do_signal(¤t->thread.regs)); + return kern_do_signal(¤t->thread.regs); } /* @@ -186,5 +186,5 @@ long sys_sigsuspend(int history0, int history1, old_sigset_t mask) long sys_sigaltstack(const stack_t __user *uss, stack_t __user *uoss) { - return(do_sigaltstack(uss, uoss, PT_REGS_SP(¤t->thread.regs))); + return do_sigaltstack(uss, uoss, PT_REGS_SP(¤t->thread.regs)); } diff --git a/arch/um/os-Linux/skas/process.c b/arch/um/os-Linux/skas/process.c index 9b34fe65949a..dda06789bcb0 100644 --- a/arch/um/os-Linux/skas/process.c +++ b/arch/um/os-Linux/skas/process.c @@ -419,9 +419,12 @@ void map_stub_pages(int fd, unsigned long code, .offset = code_offset } } }); n = os_write_file(fd, &mmop, sizeof(mmop)); - if(n != sizeof(mmop)) + if(n != sizeof(mmop)){ + printk("mmap args - addr = 0x%lx, fd = %d, offset = %llx\n", + code, code_fd, (unsigned long long) code_offset); panic("map_stub_pages : /proc/mm map for code failed, " "err = %d\n", -n); + } if ( stack ) { __u64 map_offset; diff --git a/arch/um/os-Linux/trap.c b/arch/um/os-Linux/trap.c index 1df231a26244..d221214d2ed5 100644 --- a/arch/um/os-Linux/trap.c +++ b/arch/um/os-Linux/trap.c @@ -16,6 +16,7 @@ void usr2_handler(int sig, union uml_pt_regs *regs) CHOOSE_MODE(syscall_handler_tt(sig, regs), (void) 0); } +/* Initialized from linux_main() */ void (*sig_info[NSIG])(int, union uml_pt_regs *); void os_fill_handlinfo(struct kern_handlers h) diff --git a/arch/x86_64/kernel/hpet.c b/arch/x86_64/kernel/hpet.c index 65a0edd71a17..8cf0b8a13778 100644 --- a/arch/x86_64/kernel/hpet.c +++ b/arch/x86_64/kernel/hpet.c @@ -12,6 +12,12 @@ #include <asm/timex.h> #include <asm/hpet.h> +#define HPET_MASK 0xFFFFFFFF +#define HPET_SHIFT 22 + +/* FSEC = 10^-15 NSEC = 10^-9 */ +#define FSEC_PER_NSEC 1000000 + int nohpet __initdata; unsigned long hpet_address; @@ -106,9 +112,31 @@ int hpet_timer_stop_set_go(unsigned long tick) return 0; } +static cycle_t read_hpet(void) +{ + return (cycle_t)hpet_readl(HPET_COUNTER); +} + +static cycle_t __vsyscall_fn vread_hpet(void) +{ + return readl((void __iomem *)fix_to_virt(VSYSCALL_HPET) + 0xf0); +} + +struct clocksource clocksource_hpet = { + .name = "hpet", + .rating = 250, + .read = read_hpet, + .mask = (cycle_t)HPET_MASK, + .mult = 0, /* set below */ + .shift = HPET_SHIFT, + .flags = CLOCK_SOURCE_IS_CONTINUOUS, + .vread = vread_hpet, +}; + int hpet_arch_init(void) { unsigned int id; + u64 tmp; if (!hpet_address) return -1; @@ -132,6 +160,22 @@ int hpet_arch_init(void) hpet_use_timer = (id & HPET_ID_LEGSUP); + /* + * hpet period is in femto seconds per cycle + * so we need to convert this to ns/cyc units + * aproximated by mult/2^shift + * + * fsec/cyc * 1nsec/1000000fsec = nsec/cyc = mult/2^shift + * fsec/cyc * 1ns/1000000fsec * 2^shift = mult + * fsec/cyc * 2^shift * 1nsec/1000000fsec = mult + * (fsec/cyc << shift)/1000000 = mult + * (hpet_period << shift)/FSEC_PER_NSEC = mult + */ + tmp = (u64)hpet_period << HPET_SHIFT; + do_div(tmp, FSEC_PER_NSEC); + clocksource_hpet.mult = (u32)tmp; + clocksource_register(&clocksource_hpet); + return hpet_timer_stop_set_go(hpet_tick); } @@ -444,68 +488,3 @@ static int __init nohpet_setup(char *s) } __setup("nohpet", nohpet_setup); - -#define HPET_MASK 0xFFFFFFFF -#define HPET_SHIFT 22 - -/* FSEC = 10^-15 NSEC = 10^-9 */ -#define FSEC_PER_NSEC 1000000 - -static void *hpet_ptr; - -static cycle_t read_hpet(void) -{ - return (cycle_t)readl(hpet_ptr); -} - -static cycle_t __vsyscall_fn vread_hpet(void) -{ - return readl((void __iomem *)fix_to_virt(VSYSCALL_HPET) + 0xf0); -} - -struct clocksource clocksource_hpet = { - .name = "hpet", - .rating = 250, - .read = read_hpet, - .mask = (cycle_t)HPET_MASK, - .mult = 0, /* set below */ - .shift = HPET_SHIFT, - .flags = CLOCK_SOURCE_IS_CONTINUOUS, - .vread = vread_hpet, -}; - -static int __init init_hpet_clocksource(void) -{ - unsigned long hpet_period; - void __iomem *hpet_base; - u64 tmp; - - if (!hpet_address) - return -ENODEV; - - /* calculate the hpet address: */ - hpet_base = ioremap_nocache(hpet_address, HPET_MMAP_SIZE); - hpet_ptr = hpet_base + HPET_COUNTER; - - /* calculate the frequency: */ - hpet_period = readl(hpet_base + HPET_PERIOD); - - /* - * hpet period is in femto seconds per cycle - * so we need to convert this to ns/cyc units - * aproximated by mult/2^shift - * - * fsec/cyc * 1nsec/1000000fsec = nsec/cyc = mult/2^shift - * fsec/cyc * 1ns/1000000fsec * 2^shift = mult - * fsec/cyc * 2^shift * 1nsec/1000000fsec = mult - * (fsec/cyc << shift)/1000000 = mult - * (hpet_period << shift)/FSEC_PER_NSEC = mult - */ - tmp = (u64)hpet_period << HPET_SHIFT; - do_div(tmp, FSEC_PER_NSEC); - clocksource_hpet.mult = (u32)tmp; - - return clocksource_register(&clocksource_hpet); -} - -module_init(init_hpet_clocksource); diff --git a/arch/x86_64/kernel/io_apic.c b/arch/x86_64/kernel/io_apic.c index 0a91368f8b60..c6a5bc7e8118 100644 --- a/arch/x86_64/kernel/io_apic.c +++ b/arch/x86_64/kernel/io_apic.c @@ -789,7 +789,6 @@ static void setup_IO_APIC_irq(int apic, int pin, unsigned int irq, struct irq_cfg *cfg = irq_cfg + irq; struct IO_APIC_route_entry entry; cpumask_t mask; - unsigned long flags; if (!IO_APIC_IRQ(irq)) return; diff --git a/arch/x86_64/kernel/smpboot.c b/arch/x86_64/kernel/smpboot.c index 35443729aad8..cd4643a37022 100644 --- a/arch/x86_64/kernel/smpboot.c +++ b/arch/x86_64/kernel/smpboot.c @@ -923,8 +923,9 @@ void __init smp_prepare_boot_cpu(void) */ int __cpuinit __cpu_up(unsigned int cpu) { - int err; int apicid = cpu_present_to_apicid(cpu); + unsigned long flags; + int err; WARN_ON(irqs_disabled()); @@ -958,7 +959,9 @@ int __cpuinit __cpu_up(unsigned int cpu) /* * Make sure and check TSC sync: */ + local_irq_save(flags); check_tsc_sync_source(cpu); + local_irq_restore(flags); while (!cpu_isset(cpu, cpu_online_map)) cpu_relax(); diff --git a/arch/x86_64/kernel/time.c b/arch/x86_64/kernel/time.c index c9addcfb96dc..75d73a9aa9ff 100644 --- a/arch/x86_64/kernel/time.c +++ b/arch/x86_64/kernel/time.c @@ -358,6 +358,8 @@ void __init time_init(void) set_cyc2ns_scale(cpu_khz); printk(KERN_INFO "time.c: Detected %d.%03d MHz processor.\n", cpu_khz / 1000, cpu_khz % 1000); + init_tsc_clocksource(); + setup_irq(0, &irq0); } diff --git a/arch/x86_64/kernel/tsc.c b/arch/x86_64/kernel/tsc.c index 895831865019..1a0edbbffaa0 100644 --- a/arch/x86_64/kernel/tsc.c +++ b/arch/x86_64/kernel/tsc.c @@ -210,7 +210,7 @@ void mark_tsc_unstable(void) } EXPORT_SYMBOL_GPL(mark_tsc_unstable); -static int __init init_tsc_clocksource(void) +void __init init_tsc_clocksource(void) { if (!notsc) { clocksource_tsc.mult = clocksource_khz2mult(cpu_khz, @@ -218,9 +218,6 @@ static int __init init_tsc_clocksource(void) if (check_tsc_unstable()) clocksource_tsc.rating = 0; - return clocksource_register(&clocksource_tsc); + clocksource_register(&clocksource_tsc); } - return 0; } - -module_init(init_tsc_clocksource); |