diff options
74 files changed, 2793 insertions, 2512 deletions
diff --git a/Documentation/00-INDEX b/Documentation/00-INDEX index 73060819ed99..438277800103 100644 --- a/Documentation/00-INDEX +++ b/Documentation/00-INDEX @@ -159,8 +159,6 @@ hayes-esp.txt - info on using the Hayes ESP serial driver. highuid.txt - notes on the change from 16 bit to 32 bit user/group IDs. -hpet.txt - - High Precision Event Timer Driver for Linux. timers/ - info on the timer related topics hw_random.txt diff --git a/Documentation/timers/00-INDEX b/Documentation/timers/00-INDEX new file mode 100644 index 000000000000..397dc35e1323 --- /dev/null +++ b/Documentation/timers/00-INDEX @@ -0,0 +1,10 @@ +00-INDEX + - this file +highres.txt + - High resolution timers and dynamic ticks design notes +hpet.txt + - High Precision Event Timer Driver for Linux +hrtimers.txt + - subsystem for high-resolution kernel timers +timer_stats.txt + - timer usage statistics diff --git a/Documentation/hpet.txt b/Documentation/timers/hpet.txt index 6ad52d9dad6c..e7c09abcfab4 100644 --- a/Documentation/hpet.txt +++ b/Documentation/timers/hpet.txt @@ -1,21 +1,32 @@ High Precision Event Timer Driver for Linux -The High Precision Event Timer (HPET) hardware is the future replacement -for the 8254 and Real Time Clock (RTC) periodic timer functionality. -Each HPET can have up to 32 timers. It is possible to configure the -first two timers as legacy replacements for 8254 and RTC periodic timers. -A specification done by Intel and Microsoft can be found at -<http://www.intel.com/technology/architecture/hpetspec.htm>. +The High Precision Event Timer (HPET) hardware follows a specification +by Intel and Microsoft which can be found at + + http://www.intel.com/technology/architecture/hpetspec.htm + +Each HPET has one fixed-rate counter (at 10+ MHz, hence "High Precision") +and up to 32 comparators. Normally three or more comparators are provided, +each of which can generate oneshot interupts and at least one of which has +additional hardware to support periodic interrupts. The comparators are +also called "timers", which can be misleading since usually timers are +independent of each other ... these share a counter, complicating resets. + +HPET devices can support two interrupt routing modes. In one mode, the +comparators are additional interrupt sources with no particular system +role. Many x86 BIOS writers don't route HPET interrupts at all, which +prevents use of that mode. They support the other "legacy replacement" +mode where the first two comparators block interrupts from 8254 timers +and from the RTC. The driver supports detection of HPET driver allocation and initialization of the HPET before the driver module_init routine is called. This enables platform code which uses timer 0 or 1 as the main timer to intercept HPET initialization. An example of this initialization can be found in -arch/i386/kernel/time_hpet.c. +arch/x86/kernel/hpet.c. -The driver provides two APIs which are very similar to the API found in -the rtc.c driver. There is a user space API and a kernel space API. -An example user space program is provided below. +The driver provides a userspace API which resembles the API found in the +RTC driver framework. An example user space program is provided below. #include <stdio.h> #include <stdlib.h> @@ -286,15 +297,3 @@ out: return; } - -The kernel API has three interfaces exported from the driver: - - hpet_register(struct hpet_task *tp, int periodic) - hpet_unregister(struct hpet_task *tp) - hpet_control(struct hpet_task *tp, unsigned int cmd, unsigned long arg) - -The kernel module using this interface fills in the ht_func and ht_data -members of the hpet_task structure before calling hpet_register. -hpet_control simply vectors to the hpet_ioctl routine and has the same -commands and respective arguments as the user API. hpet_unregister -is used to terminate usage of the HPET timer reserved by hpet_register. diff --git a/arch/Kconfig b/arch/Kconfig index 364c6dadde0a..0267babe5eb9 100644 --- a/arch/Kconfig +++ b/arch/Kconfig @@ -13,6 +13,20 @@ config OPROFILE If unsure, say N. +config OPROFILE_IBS + bool "OProfile AMD IBS support (EXPERIMENTAL)" + default n + depends on OPROFILE && SMP && X86 + help + Instruction-Based Sampling (IBS) is a new profiling + technique that provides rich, precise program performance + information. IBS is introduced by AMD Family10h processors + (AMD Opteron Quad-Core processor “Barcelona”) to overcome + the limitations of conventional performance counter + sampling. + + If unsure, say N. + config HAVE_OPROFILE def_bool n diff --git a/arch/x86/Kconfig.cpu b/arch/x86/Kconfig.cpu index c5f101360520..0b7c4a3f0651 100644 --- a/arch/x86/Kconfig.cpu +++ b/arch/x86/Kconfig.cpu @@ -38,8 +38,7 @@ config M386 - "Crusoe" for the Transmeta Crusoe series. - "Efficeon" for the Transmeta Efficeon series. - "Winchip-C6" for original IDT Winchip. - - "Winchip-2" for IDT Winchip 2. - - "Winchip-2A" for IDT Winchips with 3dNow! capabilities. + - "Winchip-2" for IDT Winchips with 3dNow! capabilities. - "GeodeGX1" for Geode GX1 (Cyrix MediaGX). - "Geode GX/LX" For AMD Geode GX and LX processors. - "CyrixIII/VIA C3" for VIA Cyrix III or VIA C3. @@ -194,19 +193,11 @@ config MWINCHIPC6 treat this chip as a 586TSC with some extended instructions and alignment requirements. -config MWINCHIP2 - bool "Winchip-2" - depends on X86_32 - help - Select this for an IDT Winchip-2. Linux and GCC - treat this chip as a 586TSC with some extended instructions - and alignment requirements. - config MWINCHIP3D - bool "Winchip-2A/Winchip-3" + bool "Winchip-2/Winchip-2A/Winchip-3" depends on X86_32 help - Select this for an IDT Winchip-2A or 3. Linux and GCC + Select this for an IDT Winchip-2, 2A or 3. Linux and GCC treat this chip as a 586TSC with some extended instructions and alignment requirements. Also enable out of order memory stores for this CPU, which can increase performance of some @@ -318,7 +309,7 @@ config X86_L1_CACHE_SHIFT int default "7" if MPENTIUM4 || X86_GENERIC || GENERIC_CPU || MPSC default "4" if X86_ELAN || M486 || M386 || MGEODEGX1 - default "5" if MWINCHIP3D || MWINCHIP2 || MWINCHIPC6 || MCRUSOE || MEFFICEON || MCYRIXIII || MK6 || MPENTIUMIII || MPENTIUMII || M686 || M586MMX || M586TSC || M586 || MVIAC3_2 || MGEODE_LX + default "5" if MWINCHIP3D || MWINCHIPC6 || MCRUSOE || MEFFICEON || MCYRIXIII || MK6 || MPENTIUMIII || MPENTIUMII || M686 || M586MMX || M586TSC || M586 || MVIAC3_2 || MGEODE_LX default "6" if MK7 || MK8 || MPENTIUMM || MCORE2 || MVIAC7 config X86_XADD @@ -360,7 +351,7 @@ config X86_POPAD_OK config X86_ALIGNMENT_16 def_bool y - depends on MWINCHIP3D || MWINCHIP2 || MWINCHIPC6 || MCYRIXIII || X86_ELAN || MK6 || M586MMX || M586TSC || M586 || M486 || MVIAC3_2 || MGEODEGX1 + depends on MWINCHIP3D || MWINCHIPC6 || MCYRIXIII || X86_ELAN || MK6 || M586MMX || M586TSC || M586 || M486 || MVIAC3_2 || MGEODEGX1 config X86_INTEL_USERCOPY def_bool y @@ -368,7 +359,7 @@ config X86_INTEL_USERCOPY config X86_USE_PPRO_CHECKSUM def_bool y - depends on MWINCHIP3D || MWINCHIP2 || MWINCHIPC6 || MCYRIXIII || MK7 || MK6 || MPENTIUM4 || MPENTIUMM || MPENTIUMIII || MPENTIUMII || M686 || MK8 || MVIAC3_2 || MEFFICEON || MGEODE_LX || MCORE2 + depends on MWINCHIP3D || MWINCHIPC6 || MCYRIXIII || MK7 || MK6 || MPENTIUM4 || MPENTIUMM || MPENTIUMIII || MPENTIUMII || M686 || MK8 || MVIAC3_2 || MEFFICEON || MGEODE_LX || MCORE2 config X86_USE_3DNOW def_bool y @@ -376,7 +367,7 @@ config X86_USE_3DNOW config X86_OOSTORE def_bool y - depends on (MWINCHIP3D || MWINCHIP2 || MWINCHIPC6) && MTRR + depends on (MWINCHIP3D || MWINCHIPC6) && MTRR # # P6_NOPs are a relatively minor optimization that require a family >= @@ -396,7 +387,7 @@ config X86_P6_NOP config X86_TSC def_bool y - depends on ((MWINCHIP3D || MWINCHIP2 || MCRUSOE || MEFFICEON || MCYRIXIII || MK7 || MK6 || MPENTIUM4 || MPENTIUMM || MPENTIUMIII || MPENTIUMII || M686 || M586MMX || M586TSC || MK8 || MVIAC3_2 || MVIAC7 || MGEODEGX1 || MGEODE_LX || MCORE2) && !X86_NUMAQ) || X86_64 + depends on ((MWINCHIP3D || MCRUSOE || MEFFICEON || MCYRIXIII || MK7 || MK6 || MPENTIUM4 || MPENTIUMM || MPENTIUMIII || MPENTIUMII || M686 || M586MMX || M586TSC || MK8 || MVIAC3_2 || MVIAC7 || MGEODEGX1 || MGEODE_LX || MCORE2) && !X86_NUMAQ) || X86_64 config X86_CMPXCHG64 def_bool y @@ -406,7 +397,7 @@ config X86_CMPXCHG64 # generates cmov. config X86_CMOV def_bool y - depends on (MK7 || MPENTIUM4 || MPENTIUMM || MPENTIUMIII || MPENTIUMII || M686 || MVIAC3_2 || MVIAC7 || X86_64) + depends on (MK8 || MK7 || MCORE2 || MPENTIUM4 || MPENTIUMM || MPENTIUMIII || MPENTIUMII || M686 || MVIAC3_2 || MVIAC7 || MCRUSOE || MEFFICEON || X86_64) config X86_MINIMUM_CPU_FAMILY int @@ -417,7 +408,7 @@ config X86_MINIMUM_CPU_FAMILY config X86_DEBUGCTLMSR def_bool y - depends on !(MK6 || MWINCHIPC6 || MWINCHIP2 || MWINCHIP3D || MCYRIXIII || M586MMX || M586TSC || M586 || M486 || M386) + depends on !(MK6 || MWINCHIPC6 || MWINCHIP3D || MCYRIXIII || M586MMX || M586TSC || M586 || M486 || M386) menuconfig PROCESSOR_SELECT bool "Supported processor vendors" if EMBEDDED diff --git a/arch/x86/Makefile_32.cpu b/arch/x86/Makefile_32.cpu index b72b4f753113..80177ec052f0 100644 --- a/arch/x86/Makefile_32.cpu +++ b/arch/x86/Makefile_32.cpu @@ -28,7 +28,6 @@ cflags-$(CONFIG_MK8) += $(call cc-option,-march=k8,-march=athlon) cflags-$(CONFIG_MCRUSOE) += -march=i686 $(align)-functions=0 $(align)-jumps=0 $(align)-loops=0 cflags-$(CONFIG_MEFFICEON) += -march=i686 $(call tune,pentium3) $(align)-functions=0 $(align)-jumps=0 $(align)-loops=0 cflags-$(CONFIG_MWINCHIPC6) += $(call cc-option,-march=winchip-c6,-march=i586) -cflags-$(CONFIG_MWINCHIP2) += $(call cc-option,-march=winchip2,-march=i586) cflags-$(CONFIG_MWINCHIP3D) += $(call cc-option,-march=winchip2,-march=i586) cflags-$(CONFIG_MCYRIXIII) += $(call cc-option,-march=c3,-march=i486) $(align)-functions=0 $(align)-jumps=0 $(align)-loops=0 cflags-$(CONFIG_MVIAC3_2) += $(call cc-option,-march=c3-2,-march=i686) diff --git a/arch/x86/configs/i386_defconfig b/arch/x86/configs/i386_defconfig index ca226ca31288..52d0359719d7 100644 --- a/arch/x86/configs/i386_defconfig +++ b/arch/x86/configs/i386_defconfig @@ -213,7 +213,6 @@ CONFIG_M686=y # CONFIG_MCRUSOE is not set # CONFIG_MEFFICEON is not set # CONFIG_MWINCHIPC6 is not set -# CONFIG_MWINCHIP2 is not set # CONFIG_MWINCHIP3D is not set # CONFIG_MGEODEGX1 is not set # CONFIG_MGEODE_LX is not set diff --git a/arch/x86/configs/x86_64_defconfig b/arch/x86/configs/x86_64_defconfig index 2c4b1c771e28..f0a03d7a7d63 100644 --- a/arch/x86/configs/x86_64_defconfig +++ b/arch/x86/configs/x86_64_defconfig @@ -210,7 +210,6 @@ CONFIG_X86_PC=y # CONFIG_MCRUSOE is not set # CONFIG_MEFFICEON is not set # CONFIG_MWINCHIPC6 is not set -# CONFIG_MWINCHIP2 is not set # CONFIG_MWINCHIP3D is not set # CONFIG_MGEODEGX1 is not set # CONFIG_MGEODE_LX is not set diff --git a/arch/x86/ia32/ia32entry.S b/arch/x86/ia32/ia32entry.S index ffc1bb4fed7d..eb4314768bf7 100644 --- a/arch/x86/ia32/ia32entry.S +++ b/arch/x86/ia32/ia32entry.S @@ -39,11 +39,11 @@ .endm /* clobbers %eax */ - .macro CLEAR_RREGS + .macro CLEAR_RREGS _r9=rax xorl %eax,%eax movq %rax,R11(%rsp) movq %rax,R10(%rsp) - movq %rax,R9(%rsp) + movq %\_r9,R9(%rsp) movq %rax,R8(%rsp) .endm @@ -52,11 +52,10 @@ * We don't reload %eax because syscall_trace_enter() returned * the value it wants us to use in the table lookup. */ - .macro LOAD_ARGS32 offset - movl \offset(%rsp),%r11d - movl \offset+8(%rsp),%r10d + .macro LOAD_ARGS32 offset, _r9=0 + .if \_r9 movl \offset+16(%rsp),%r9d - movl \offset+24(%rsp),%r8d + .endif movl \offset+40(%rsp),%ecx movl \offset+48(%rsp),%edx movl \offset+56(%rsp),%esi @@ -145,7 +144,7 @@ ENTRY(ia32_sysenter_target) SAVE_ARGS 0,0,1 /* no need to do an access_ok check here because rbp has been 32bit zero extended */ -1: movl (%rbp),%r9d +1: movl (%rbp),%ebp .section __ex_table,"a" .quad 1b,ia32_badarg .previous @@ -157,7 +156,7 @@ ENTRY(ia32_sysenter_target) cmpl $(IA32_NR_syscalls-1),%eax ja ia32_badsys sysenter_do_call: - IA32_ARG_FIXUP 1 + IA32_ARG_FIXUP sysenter_dispatch: call *ia32_sys_call_table(,%rax,8) movq %rax,RAX-ARGOFFSET(%rsp) @@ -234,20 +233,17 @@ sysexit_audit: #endif sysenter_tracesys: - xchgl %r9d,%ebp #ifdef CONFIG_AUDITSYSCALL testl $(_TIF_WORK_SYSCALL_ENTRY & ~_TIF_SYSCALL_AUDIT),TI_flags(%r10) jz sysenter_auditsys #endif SAVE_REST CLEAR_RREGS - movq %r9,R9(%rsp) movq $-ENOSYS,RAX(%rsp)/* ptrace can change this for a bad syscall */ movq %rsp,%rdi /* &pt_regs -> arg1 */ call syscall_trace_enter LOAD_ARGS32 ARGOFFSET /* reload args from stack in case ptrace changed it */ RESTORE_REST - xchgl %ebp,%r9d cmpl $(IA32_NR_syscalls-1),%eax ja int_ret_from_sys_call /* sysenter_tracesys has set RAX(%rsp) */ jmp sysenter_do_call @@ -314,9 +310,9 @@ ENTRY(ia32_cstar_target) testl $_TIF_WORK_SYSCALL_ENTRY,TI_flags(%r10) CFI_REMEMBER_STATE jnz cstar_tracesys -cstar_do_call: cmpl $IA32_NR_syscalls-1,%eax ja ia32_badsys +cstar_do_call: IA32_ARG_FIXUP 1 cstar_dispatch: call *ia32_sys_call_table(,%rax,8) @@ -357,15 +353,13 @@ cstar_tracesys: #endif xchgl %r9d,%ebp SAVE_REST - CLEAR_RREGS - movq %r9,R9(%rsp) + CLEAR_RREGS r9 movq $-ENOSYS,RAX(%rsp) /* ptrace can change this for a bad syscall */ movq %rsp,%rdi /* &pt_regs -> arg1 */ call syscall_trace_enter - LOAD_ARGS32 ARGOFFSET /* reload args from stack in case ptrace changed it */ + LOAD_ARGS32 ARGOFFSET, 1 /* reload args from stack in case ptrace changed it */ RESTORE_REST xchgl %ebp,%r9d - movl RSP-ARGOFFSET(%rsp), %r8d cmpl $(IA32_NR_syscalls-1),%eax ja int_ret_from_sys_call /* cstar_tracesys has set RAX(%rsp) */ jmp cstar_do_call diff --git a/arch/x86/kernel/Makefile b/arch/x86/kernel/Makefile index 5098585f87ce..0d41f0343dc0 100644 --- a/arch/x86/kernel/Makefile +++ b/arch/x86/kernel/Makefile @@ -23,7 +23,7 @@ CFLAGS_hpet.o := $(nostackp) CFLAGS_tsc.o := $(nostackp) obj-y := process_$(BITS).o signal_$(BITS).o entry_$(BITS).o -obj-y += traps_$(BITS).o irq_$(BITS).o +obj-y += traps.o irq_$(BITS).o dumpstack_$(BITS).o obj-y += time_$(BITS).o ioport.o ldt.o obj-y += setup.o i8259.o irqinit_$(BITS).o setup_percpu.o obj-$(CONFIG_X86_VISWS) += visws_quirks.o diff --git a/arch/x86/kernel/alternative.c b/arch/x86/kernel/alternative.c index fb04e49776ba..a84ac7b570e6 100644 --- a/arch/x86/kernel/alternative.c +++ b/arch/x86/kernel/alternative.c @@ -444,7 +444,7 @@ void __init alternative_instructions(void) _text, _etext); /* Only switch to UP mode if we don't immediately boot others */ - if (num_possible_cpus() == 1 || setup_max_cpus <= 1) + if (num_present_cpus() == 1 || setup_max_cpus <= 1) alternatives_smp_switch(0); } #endif diff --git a/arch/x86/kernel/apic_32.c b/arch/x86/kernel/apic_32.c index a91c57cb666a..21c831d96af3 100644 --- a/arch/x86/kernel/apic_32.c +++ b/arch/x86/kernel/apic_32.c @@ -295,6 +295,9 @@ static void __setup_APIC_LVTT(unsigned int clocks, int oneshot, int irqen) * * Vector mappings are hard coded. On K8 only offset 0 (APIC500) and * MCE interrupts are supported. Thus MCE offset must be set to 0. + * + * If mask=1, the LVT entry does not generate interrupts while mask=0 + * enables the vector. See also the BKDGs. */ #define APIC_EILVT_LVTOFF_MCE 0 @@ -319,6 +322,7 @@ u8 setup_APIC_eilvt_ibs(u8 vector, u8 msg_type, u8 mask) setup_APIC_eilvt(APIC_EILVT_LVTOFF_IBS, vector, msg_type, mask); return APIC_EILVT_LVTOFF_IBS; } +EXPORT_SYMBOL_GPL(setup_APIC_eilvt_ibs); /* * Program the next event, relative to now diff --git a/arch/x86/kernel/apic_64.c b/arch/x86/kernel/apic_64.c index 53898b65a6ae..94ddb69ae15e 100644 --- a/arch/x86/kernel/apic_64.c +++ b/arch/x86/kernel/apic_64.c @@ -307,6 +307,9 @@ static void __setup_APIC_LVTT(unsigned int clocks, int oneshot, int irqen) * * Vector mappings are hard coded. On K8 only offset 0 (APIC500) and * MCE interrupts are supported. Thus MCE offset must be set to 0. + * + * If mask=1, the LVT entry does not generate interrupts while mask=0 + * enables the vector. See also the BKDGs. */ #define APIC_EILVT_LVTOFF_MCE 0 @@ -331,6 +334,7 @@ u8 setup_APIC_eilvt_ibs(u8 vector, u8 msg_type, u8 mask) setup_APIC_eilvt(APIC_EILVT_LVTOFF_IBS, vector, msg_type, mask); return APIC_EILVT_LVTOFF_IBS; } +EXPORT_SYMBOL_GPL(setup_APIC_eilvt_ibs); /* * Program the next event, relative to now diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c index fb789dd9e691..25581dcb280e 100644 --- a/arch/x86/kernel/cpu/common.c +++ b/arch/x86/kernel/cpu/common.c @@ -124,18 +124,25 @@ static inline int flag_is_changeable_p(u32 flag) { u32 f1, f2; - asm("pushfl\n\t" - "pushfl\n\t" - "popl %0\n\t" - "movl %0,%1\n\t" - "xorl %2,%0\n\t" - "pushl %0\n\t" - "popfl\n\t" - "pushfl\n\t" - "popl %0\n\t" - "popfl\n\t" - : "=&r" (f1), "=&r" (f2) - : "ir" (flag)); + /* + * Cyrix and IDT cpus allow disabling of CPUID + * so the code below may return different results + * when it is executed before and after enabling + * the CPUID. Add "volatile" to not allow gcc to + * optimize the subsequent calls to this function. + */ + asm volatile ("pushfl\n\t" + "pushfl\n\t" + "popl %0\n\t" + "movl %0,%1\n\t" + "xorl %2,%0\n\t" + "pushl %0\n\t" + "popfl\n\t" + "pushfl\n\t" + "popl %0\n\t" + "popfl\n\t" + : "=&r" (f1), "=&r" (f2) + : "ir" (flag)); return ((f1^f2) & flag) != 0; } @@ -719,12 +726,24 @@ static void __cpuinit identify_cpu(struct cpuinfo_x86 *c) #endif } +#ifdef CONFIG_X86_64 +static void vgetcpu_set_mode(void) +{ + if (cpu_has(&boot_cpu_data, X86_FEATURE_RDTSCP)) + vgetcpu_mode = VGETCPU_RDTSCP; + else + vgetcpu_mode = VGETCPU_LSL; +} +#endif + void __init identify_boot_cpu(void) { identify_cpu(&boot_cpu_data); #ifdef CONFIG_X86_32 sysenter_setup(); enable_sep_cpu(); +#else + vgetcpu_set_mode(); #endif } @@ -797,7 +816,7 @@ void __cpuinit print_cpu_info(struct cpuinfo_x86 *c) else if (c->cpuid_level >= 0) vendor = c->x86_vendor_id; - if (vendor && strncmp(c->x86_model_id, vendor, strlen(vendor))) + if (vendor && !strstr(c->x86_model_id, vendor)) printk(KERN_CONT "%s ", vendor); if (c->x86_model_id[0]) diff --git a/arch/x86/kernel/doublefault_32.c b/arch/x86/kernel/doublefault_32.c index 395acb12b0d1..b4f14c6c09d9 100644 --- a/arch/x86/kernel/doublefault_32.c +++ b/arch/x86/kernel/doublefault_32.c @@ -66,6 +66,6 @@ struct tss_struct doublefault_tss __cacheline_aligned = { .ds = __USER_DS, .fs = __KERNEL_PERCPU, - .__cr3 = __phys_addr_const((unsigned long)swapper_pg_dir) + .__cr3 = __pa_nodebug(swapper_pg_dir), } }; diff --git a/arch/x86/kernel/dumpstack_32.c b/arch/x86/kernel/dumpstack_32.c new file mode 100644 index 000000000000..201ee359a1a9 --- /dev/null +++ b/arch/x86/kernel/dumpstack_32.c @@ -0,0 +1,447 @@ +/* + * Copyright (C) 1991, 1992 Linus Torvalds + * Copyright (C) 2000, 2001, 2002 Andi Kleen, SuSE Labs + */ +#include <linux/kallsyms.h> +#include <linux/kprobes.h> +#include <linux/uaccess.h> +#include <linux/utsname.h> +#include <linux/hardirq.h> +#include <linux/kdebug.h> +#include <linux/module.h> +#include <linux/ptrace.h> +#include <linux/kexec.h> +#include <linux/bug.h> +#include <linux/nmi.h> + +#include <asm/stacktrace.h> + +#define STACKSLOTS_PER_LINE 8 +#define get_bp(bp) asm("movl %%ebp, %0" : "=r" (bp) :) + +int panic_on_unrecovered_nmi; +int kstack_depth_to_print = 3 * STACKSLOTS_PER_LINE; +static unsigned int code_bytes = 64; +static int die_counter; + +void printk_address(unsigned long address, int reliable) +{ + printk(" [<%p>] %s%pS\n", (void *) address, + reliable ? "" : "? ", (void *) address); +} + +static inline int valid_stack_ptr(struct thread_info *tinfo, + void *p, unsigned int size, void *end) +{ + void *t = tinfo; + if (end) { + if (p < end && p >= (end-THREAD_SIZE)) + return 1; + else + return 0; + } + return p > t && p < t + THREAD_SIZE - size; +} + +/* The form of the top of the frame on the stack */ +struct stack_frame { + struct stack_frame *next_frame; + unsigned long return_address; +}; + +static inline unsigned long +print_context_stack(struct thread_info *tinfo, + unsigned long *stack, unsigned long bp, + const struct stacktrace_ops *ops, void *data, + unsigned long *end) +{ + struct stack_frame *frame = (struct stack_frame *)bp; + + while (valid_stack_ptr(tinfo, stack, sizeof(*stack), end)) { + unsigned long addr; + + addr = *stack; + if (__kernel_text_address(addr)) { + if ((unsigned long) stack == bp + sizeof(long)) { + ops->address(data, addr, 1); + frame = frame->next_frame; + bp = (unsigned long) frame; + } else { + ops->address(data, addr, bp == 0); + } + } + stack++; + } + return bp; +} + +void dump_trace(struct task_struct *task, struct pt_regs *regs, + unsigned long *stack, unsigned long bp, + const struct stacktrace_ops *ops, void *data) +{ + if (!task) + task = current; + + if (!stack) { + unsigned long dummy; + stack = &dummy; + if (task && task != current) + stack = (unsigned long *)task->thread.sp; + } + +#ifdef CONFIG_FRAME_POINTER + if (!bp) { + if (task == current) { + /* Grab bp right from our regs */ + get_bp(bp); + } else { + /* bp is the last reg pushed by switch_to */ + bp = *(unsigned long *) task->thread.sp; + } + } +#endif + + for (;;) { + struct thread_info *context; + + context = (struct thread_info *) + ((unsigned long)stack & (~(THREAD_SIZE - 1))); + bp = print_context_stack(context, stack, bp, ops, data, NULL); + + stack = (unsigned long *)context->previous_esp; + if (!stack) + break; + if (ops->stack(data, "IRQ") < 0) + break; + touch_nmi_watchdog(); + } +} +EXPORT_SYMBOL(dump_trace); + +static void +print_trace_warning_symbol(void *data, char *msg, unsigned long symbol) +{ + printk(data); + print_symbol(msg, symbol); + printk("\n"); +} + +static void print_trace_warning(void *data, char *msg) +{ + printk("%s%s\n", (char *)data, msg); +} + +static int print_trace_stack(void *data, char *name) +{ + printk("%s <%s> ", (char *)data, name); + return 0; +} + +/* + * Print one address/symbol entries per line. + */ +static void print_trace_address(void *data, unsigned long addr, int reliable) +{ + touch_nmi_watchdog(); + printk(data); + printk_address(addr, reliable); +} + +static const struct stacktrace_ops print_trace_ops = { + .warning = print_trace_warning, + .warning_symbol = print_trace_warning_symbol, + .stack = print_trace_stack, + .address = print_trace_address, +}; + +static void +show_trace_log_lvl(struct task_struct *task, struct pt_regs *regs, + unsigned long *stack, unsigned long bp, char *log_lvl) +{ + printk("%sCall Trace:\n", log_lvl); + dump_trace(task, regs, stack, bp, &print_trace_ops, log_lvl); +} + +void show_trace(struct task_struct *task, struct pt_regs *regs, + unsigned long *stack, unsigned long bp) +{ + show_trace_log_lvl(task, regs, stack, bp, ""); +} + +static void +show_stack_log_lvl(struct task_struct *task, struct pt_regs *regs, + unsigned long *sp, unsigned long bp, char *log_lvl) +{ + unsigned long *stack; + int i; + + if (sp == NULL) { + if (task) + sp = (unsigned long *)task->thread.sp; + else + sp = (unsigned long *)&sp; + } + + stack = sp; + for (i = 0; i < kstack_depth_to_print; i++) { + if (kstack_end(stack)) + break; + if (i && ((i % STACKSLOTS_PER_LINE) == 0)) + printk("\n%s", log_lvl); + printk(" %08lx", *stack++); + touch_nmi_watchdog(); + } + printk("\n"); + show_trace_log_lvl(task, regs, sp, bp, log_lvl); +} + +void show_stack(struct task_struct *task, unsigned long *sp) +{ + show_stack_log_lvl(task, NULL, sp, 0, ""); +} + +/* + * The architecture-independent dump_stack generator + */ +void dump_stack(void) +{ + unsigned long bp = 0; + unsigned long stack; + +#ifdef CONFIG_FRAME_POINTER + if (!bp) + get_bp(bp); +#endif + + printk("Pid: %d, comm: %.20s %s %s %.*s\n", + current->pid, current->comm, print_tainted(), + init_utsname()->release, + (int)strcspn(init_utsname()->version, " "), + init_utsname()->version); + show_trace(NULL, NULL, &stack, bp); +} + +EXPORT_SYMBOL(dump_stack); + +void show_registers(struct pt_regs *regs) +{ + int i; + + print_modules(); + __show_regs(regs, 0); + + printk(KERN_EMERG "Process %.*s (pid: %d, ti=%p task=%p task.ti=%p)\n", + TASK_COMM_LEN, current->comm, task_pid_nr(current), + current_thread_info(), current, task_thread_info(current)); + /* + * When in-kernel, we also print out the stack and code at the + * time of the fault.. + */ + if (!user_mode_vm(regs)) { + unsigned int code_prologue = code_bytes * 43 / 64; + unsigned int code_len = code_bytes; + unsigned char c; + u8 *ip; + + printk(KERN_EMERG "Stack:\n"); + show_stack_log_lvl(NULL, regs, ®s->sp, + 0, KERN_EMERG); + + printk(KERN_EMERG "Code: "); + + ip = (u8 *)regs->ip - code_prologue; + if (ip < (u8 *)PAGE_OFFSET || probe_kernel_address(ip, c)) { + /* try starting at IP */ + ip = (u8 *)regs->ip; + code_len = code_len - code_prologue + 1; + } + for (i = 0; i < code_len; i++, ip++) { + if (ip < (u8 *)PAGE_OFFSET || + probe_kernel_address(ip, c)) { + printk(" Bad EIP value."); + break; + } + if (ip == (u8 *)regs->ip) + printk("<%02x> ", c); + else + printk("%02x ", c); + } + } + printk("\n"); +} + +int is_valid_bugaddr(unsigned long ip) +{ + unsigned short ud2; + + if (ip < PAGE_OFFSET) + return 0; + if (probe_kernel_address((unsigned short *)ip, ud2)) + return 0; + + return ud2 == 0x0b0f; +} + +static raw_spinlock_t die_lock = __RAW_SPIN_LOCK_UNLOCKED; +static int die_owner = -1; +static unsigned int die_nest_count; + +unsigned __kprobes long oops_begin(void) +{ + unsigned long flags; + + oops_enter(); + + if (die_owner != raw_smp_processor_id()) { + console_verbose(); + raw_local_irq_save(flags); + __raw_spin_lock(&die_lock); + die_owner = smp_processor_id(); + die_nest_count = 0; + bust_spinlocks(1); + } else { + raw_local_irq_save(flags); + } + die_nest_count++; + return flags; +} + +void __kprobes oops_end(unsigned long flags, struct pt_regs *regs, int signr) +{ + bust_spinlocks(0); + die_owner = -1; + add_taint(TAINT_DIE); + __raw_spin_unlock(&die_lock); + raw_local_irq_restore(flags); + + if (!regs) + return; + + if (kexec_should_crash(current)) + crash_kexec(regs); + if (in_interrupt()) + panic("Fatal exception in interrupt"); + if (panic_on_oops) + panic("Fatal exception"); + oops_exit(); + do_exit(signr); +} + +int __kprobes __die(const char *str, struct pt_regs *regs, long err) +{ + unsigned short ss; + unsigned long sp; + + printk(KERN_EMERG "%s: %04lx [#%d] ", str, err & 0xffff, ++die_counter); +#ifdef CONFIG_PREEMPT + printk("PREEMPT "); +#endif +#ifdef CONFIG_SMP + printk("SMP "); +#endif +#ifdef CONFIG_DEBUG_PAGEALLOC + printk("DEBUG_PAGEALLOC"); +#endif + printk("\n"); + if (notify_die(DIE_OOPS, str, regs, err, + current->thread.trap_no, SIGSEGV) == NOTIFY_STOP) + return 1; + + show_registers(regs); + /* Executive summary in case the oops scrolled away */ + sp = (unsigned long) (®s->sp); + savesegment(ss, ss); + if (user_mode(regs)) { + sp = regs->sp; + ss = regs->ss & 0xffff; + } + printk(KERN_EMERG "EIP: [<%08lx>] ", regs->ip); + print_symbol("%s", regs->ip); + printk(" SS:ESP %04x:%08lx\n", ss, sp); + return 0; +} + +/* + * This is gone through when something in the kernel has done something bad + * and is about to be terminated: + */ +void die(const char *str, struct pt_regs *regs, long err) +{ + unsigned long flags = oops_begin(); + + if (die_nest_count < 3) { + report_bug(regs->ip, regs); + + if (__die(str, regs, err)) + regs = NULL; + } else { + printk(KERN_EMERG "Recursive die() failure, output suppressed\n"); + } + + oops_end(flags, regs, SIGSEGV); +} + +static DEFINE_SPINLOCK(nmi_print_lock); + +void notrace __kprobes +die_nmi(char *str, struct pt_regs *regs, int do_panic) +{ + if (notify_die(DIE_NMIWATCHDOG, str, regs, 0, 2, SIGINT) == NOTIFY_STOP) + return; + + spin_lock(&nmi_print_lock); + /* + * We are in trouble anyway, lets at least try + * to get a message out: + */ + bust_spinlocks(1); + printk(KERN_EMERG "%s", str); + printk(" on CPU%d, ip %08lx, registers:\n", + smp_processor_id(), regs->ip); + show_registers(regs); + if (do_panic) + panic("Non maskable interrupt"); + console_silent(); + spin_unlock(&nmi_print_lock); + bust_spinlocks(0); + + /* + * If we are in kernel we are probably nested up pretty bad + * and might aswell get out now while we still can: + */ + if (!user_mode_vm(regs)) { + current->thread.trap_no = 2; + crash_kexec(regs); + } + + do_exit(SIGSEGV); +} + +static int __init oops_setup(char *s) +{ + if (!s) + return -EINVAL; + if (!strcmp(s, "panic")) + panic_on_oops = 1; + return 0; +} +early_param("oops", oops_setup); + +static int __init kstack_setup(char *s) +{ + if (!s) + return -EINVAL; + kstack_depth_to_print = simple_strtoul(s, NULL, 0); + return 0; +} +early_param("kstack", kstack_setup); + +static int __init code_bytes_setup(char *s) +{ + code_bytes = simple_strtoul(s, NULL, 0); + if (code_bytes > 8192) + code_bytes = 8192; + + return 1; +} +__setup("code_bytes=", code_bytes_setup); diff --git a/arch/x86/kernel/dumpstack_64.c b/arch/x86/kernel/dumpstack_64.c new file mode 100644 index 000000000000..086cc8118e39 --- /dev/null +++ b/arch/x86/kernel/dumpstack_64.c @@ -0,0 +1,573 @@ +/* + * Copyright (C) 1991, 1992 Linus Torvalds + * Copyright (C) 2000, 2001, 2002 Andi Kleen, SuSE Labs + */ +#include <linux/kallsyms.h> +#include <linux/kprobes.h> +#include <linux/uaccess.h> +#include <linux/utsname.h> +#include <linux/hardirq.h> +#include <linux/kdebug.h> +#include <linux/module.h> +#include <linux/ptrace.h> +#include <linux/kexec.h> +#include <linux/bug.h> +#include <linux/nmi.h> + +#include <asm/stacktrace.h> + +#define STACKSLOTS_PER_LINE 4 +#define get_bp(bp) asm("movq %%rbp, %0" : "=r" (bp) :) + +int panic_on_unrecovered_nmi; +int kstack_depth_to_print = 3 * STACKSLOTS_PER_LINE; +static unsigned int code_bytes = 64; +static int die_counter; + +void printk_address(unsigned long address, int reliable) +{ + printk(" [<%p>] %s%pS\n", (void *) address, + reliable ? "" : "? ", (void *) address); +} + +static unsigned long *in_exception_stack(unsigned cpu, unsigned long stack, + unsigned *usedp, char **idp) +{ + static char ids[][8] = { + [DEBUG_STACK - 1] = "#DB", + [NMI_STACK - 1] = "NMI", + [DOUBLEFAULT_STACK - 1] = "#DF", + [STACKFAULT_STACK - 1] = "#SS", + [MCE_STACK - 1] = "#MC", +#if DEBUG_STKSZ > EXCEPTION_STKSZ + [N_EXCEPTION_STACKS ... + N_EXCEPTION_STACKS + DEBUG_STKSZ / EXCEPTION_STKSZ - 2] = "#DB[?]" +#endif + }; + unsigned k; + + /* + * Iterate over all exception stacks, and figure out whether + * 'stack' is in one of them: + */ + for (k = 0; k < N_EXCEPTION_STACKS; k++) { + unsigned long end = per_cpu(orig_ist, cpu).ist[k]; + /* + * Is 'stack' above this exception frame's end? + * If yes then skip to the next frame. + */ + if (stack >= end) + continue; + /* + * Is 'stack' above this exception frame's start address? + * If yes then we found the right frame. + */ + if (stack >= end - EXCEPTION_STKSZ) { + /* + * Make sure we only iterate through an exception + * stack once. If it comes up for the second time + * then there's something wrong going on - just + * break out and return NULL: + */ + if (*usedp & (1U << k)) + break; + *usedp |= 1U << k; + *idp = ids[k]; + return (unsigned long *)end; + } + /* + * If this is a debug stack, and if it has a larger size than + * the usual exception stacks, then 'stack' might still + * be within the lower portion of the debug stack: + */ +#if DEBUG_STKSZ > EXCEPTION_STKSZ + if (k == DEBUG_STACK - 1 && stack >= end - DEBUG_STKSZ) { + unsigned j = N_EXCEPTION_STACKS - 1; + + /* + * Black magic. A large debug stack is composed of + * multiple exception stack entries, which we + * iterate through now. Dont look: + */ + do { + ++j; + end -= EXCEPTION_STKSZ; + ids[j][4] = '1' + (j - N_EXCEPTION_STACKS); + } while (stack < end - EXCEPTION_STKSZ); + if (*usedp & (1U << j)) + break; + *usedp |= 1U << j; + *idp = ids[j]; + return (unsigned long *)end; + } +#endif + } + return NULL; +} + +/* + * x86-64 can have up to three kernel stacks: + * process stack + * interrupt stack + * severe exception (double fault, nmi, stack fault, debug, mce) hardware stack + */ + +static inline int valid_stack_ptr(struct thread_info *tinfo, + void *p, unsigned int size, void *end) +{ + void *t = tinfo; + if (end) { + if (p < end && p >= (end-THREAD_SIZE)) + return 1; + else + return 0; + } + return p > t && p < t + THREAD_SIZE - size; +} + +/* The form of the top of the frame on the stack */ +struct stack_frame { + struct stack_frame *next_frame; + unsigned long return_address; +}; + +static inline unsigned long +print_context_stack(struct thread_info *tinfo, + unsigned long *stack, unsigned long bp, + const struct stacktrace_ops *ops, void *data, + unsigned long *end) +{ + struct stack_frame *frame = (struct stack_frame *)bp; + + while (valid_stack_ptr(tinfo, stack, sizeof(*stack), end)) { + unsigned long addr; + + addr = *stack; + if (__kernel_text_address(addr)) { + if ((unsigned long) stack == bp + sizeof(long)) { + ops->address(data, addr, 1); + frame = frame->next_frame; + bp = (unsigned long) frame; + } else { + ops->address(data, addr, bp == 0); + } + } + stack++; + } + return bp; +} + +void dump_trace(struct task_struct *task, struct pt_regs *regs, + unsigned long *stack, unsigned long bp, + const struct stacktrace_ops *ops, void *data) +{ + const unsigned cpu = get_cpu(); + unsigned long *irqstack_end = (unsigned long *)cpu_pda(cpu)->irqstackptr; + unsigned used = 0; + struct thread_info *tinfo; + + if (!task) + task = current; + + if (!stack) { + unsigned long dummy; + stack = &dummy; + if (task && task != current) + stack = (unsigned long *)task->thread.sp; + } + +#ifdef CONFIG_FRAME_POINTER + if (!bp) { + if (task == current) { + /* Grab bp right from our regs */ + get_bp(bp); + } else { + /* bp is the last reg pushed by switch_to */ + bp = *(unsigned long *) task->thread.sp; + } + } +#endif + + /* + * Print function call entries in all stacks, starting at the + * current stack address. If the stacks consist of nested + * exceptions + */ + tinfo = task_thread_info(task); + for (;;) { + char *id; + unsigned long *estack_end; + estack_end = in_exception_stack(cpu, (unsigned long)stack, + &used, &id); + + if (estack_end) { + if (ops->stack(data, id) < 0) + break; + + bp = print_context_stack(tinfo, stack, bp, ops, + data, estack_end); + ops->stack(data, "<EOE>"); + /* + * We link to the next stack via the + * second-to-last pointer (index -2 to end) in the + * exception stack: + */ + stack = (unsigned long *) estack_end[-2]; + continue; + } + if (irqstack_end) { + unsigned long *irqstack; + irqstack = irqstack_end - + (IRQSTACKSIZE - 64) / sizeof(*irqstack); + + if (stack >= irqstack && stack < irqstack_end) { + if (ops->stack(data, "IRQ") < 0) + break; + bp = print_context_stack(tinfo, stack, bp, + ops, data, irqstack_end); + /* + * We link to the next stack (which would be + * the process stack normally) the last + * pointer (index -1 to end) in the IRQ stack: + */ + stack = (unsigned long *) (irqstack_end[-1]); + irqstack_end = NULL; + ops->stack(data, "EOI"); + continue; + } + } + break; + } + + /* + * This handles the process stack: + */ + bp = print_context_stack(tinfo, stack, bp, ops, data, NULL); + put_cpu(); +} +EXPORT_SYMBOL(dump_trace); + +static void +print_trace_warning_symbol(void *data, char *msg, unsigned long symbol) +{ + printk(data); + print_symbol(msg, symbol); + printk("\n"); +} + +static void print_trace_warning(void *data, char *msg) +{ + printk("%s%s\n", (char *)data, msg); +} + +static int print_trace_stack(void *data, char *name) +{ + printk("%s <%s> ", (char *)data, name); + return 0; +} + +/* + * Print one address/symbol entries per line. + */ +static void print_trace_address(void *data, unsigned long addr, int reliable) +{ + touch_nmi_watchdog(); + printk(data); + printk_address(addr, reliable); +} + +static const struct stacktrace_ops print_trace_ops = { + .warning = print_trace_warning, + .warning_symbol = print_trace_warning_symbol, + .stack = print_trace_stack, + .address = print_trace_address, +}; + +static void +show_trace_log_lvl(struct task_struct *task, struct pt_regs *regs, + unsigned long *stack, unsigned long bp, char *log_lvl) +{ + printk("%sCall Trace:\n", log_lvl); + dump_trace(task, regs, stack, bp, &print_trace_ops, log_lvl); +} + +void show_trace(struct task_struct *task, struct pt_regs *regs, + unsigned long *stack, unsigned long bp) +{ + show_trace_log_lvl(task, regs, stack, bp, ""); +} + +static void +show_stack_log_lvl(struct task_struct *task, struct pt_regs *regs, + unsigned long *sp, unsigned long bp, char *log_lvl) +{ + unsigned long *stack; + int i; + const int cpu = smp_processor_id(); + unsigned long *irqstack_end = + (unsigned long *) (cpu_pda(cpu)->irqstackptr); + unsigned long *irqstack = + (unsigned long *) (cpu_pda(cpu)->irqstackptr - IRQSTACKSIZE); + + /* + * debugging aid: "show_stack(NULL, NULL);" prints the + * back trace for this cpu. + */ + + if (sp == NULL) { + if (task) + sp = (unsigned long *)task->thread.sp; + else + sp = (unsigned long *)&sp; + } + + stack = sp; + for (i = 0; i < kstack_depth_to_print; i++) { + if (stack >= irqstack && stack <= irqstack_end) { + if (stack == irqstack_end) { + stack = (unsigned long *) (irqstack_end[-1]); + printk(" <EOI> "); + } + } else { + if (((long) stack & (THREAD_SIZE-1)) == 0) + break; + } + if (i && ((i % STACKSLOTS_PER_LINE) == 0)) + printk("\n%s", log_lvl); + printk(" %016lx", *stack++); + touch_nmi_watchdog(); + } + printk("\n"); + show_trace_log_lvl(task, regs, sp, bp, log_lvl); +} + +void show_stack(struct task_struct *task, unsigned long *sp) +{ + show_stack_log_lvl(task, NULL, sp, 0, ""); +} + +/* + * The architecture-independent dump_stack generator + */ +void dump_stack(void) +{ + unsigned long bp = 0; + unsigned long stack; + +#ifdef CONFIG_FRAME_POINTER + if (!bp) + get_bp(bp); +#endif + + printk("Pid: %d, comm: %.20s %s %s %.*s\n", + current->pid, current->comm, print_tainted(), + init_utsname()->release, + (int)strcspn(init_utsname()->version, " "), + init_utsname()->version); + show_trace(NULL, NULL, &stack, bp); +} +EXPORT_SYMBOL(dump_stack); + +void show_registers(struct pt_regs *regs) +{ + int i; + unsigned long sp; + const int cpu = smp_processor_id(); + struct task_struct *cur = cpu_pda(cpu)->pcurrent; + + sp = regs->sp; + printk("CPU %d ", cpu); + __show_regs(regs, 1); + printk("Process %s (pid: %d, threadinfo %p, task %p)\n", + cur->comm, cur->pid, task_thread_info(cur), cur); + + /* + * When in-kernel, we also print out the stack and code at the + * time of the fault.. + */ + if (!user_mode(regs)) { + unsigned int code_prologue = code_bytes * 43 / 64; + unsigned int code_len = code_bytes; + unsigned char c; + u8 *ip; + + printk(KERN_EMERG "Stack:\n"); + show_stack_log_lvl(NULL, regs, (unsigned long *)sp, + regs->bp, KERN_EMERG); + + printk(KERN_EMERG "Code: "); + + ip = (u8 *)regs->ip - code_prologue; + if (ip < (u8 *)PAGE_OFFSET || probe_kernel_address(ip, c)) { + /* try starting at IP */ + ip = (u8 *)regs->ip; + code_len = code_len - code_prologue + 1; + } + for (i = 0; i < code_len; i++, ip++) { + if (ip < (u8 *)PAGE_OFFSET || + probe_kernel_address(ip, c)) { + printk(" Bad RIP value."); + break; + } + if (ip == (u8 *)regs->ip) + printk("<%02x> ", c); + else + printk("%02x ", c); + } + } + printk("\n"); +} + +int is_valid_bugaddr(unsigned long ip) +{ + unsigned short ud2; + + if (__copy_from_user(&ud2, (const void __user *) ip, sizeof(ud2))) + return 0; + + return ud2 == 0x0b0f; +} + +static raw_spinlock_t die_lock = __RAW_SPIN_LOCK_UNLOCKED; +static int die_owner = -1; +static unsigned int die_nest_count; + +unsigned __kprobes long oops_begin(void) +{ + int cpu; + unsigned long flags; + + oops_enter(); + + /* racy, but better than risking deadlock. */ + raw_local_irq_save(flags); + cpu = smp_processor_id(); + if (!__raw_spin_trylock(&die_lock)) { + if (cpu == die_owner) + /* nested oops. should stop eventually */; + else + __raw_spin_lock(&die_lock); + } + die_nest_count++; + die_owner = cpu; + console_verbose(); + bust_spinlocks(1); + return flags; +} + +void __kprobes oops_end(unsigned long flags, struct pt_regs *regs, int signr) +{ + die_owner = -1; + bust_spinlocks(0); + die_nest_count--; + if (!die_nest_count) + /* Nest count reaches zero, release the lock. */ + __raw_spin_unlock(&die_lock); + raw_local_irq_restore(flags); + if (!regs) { + oops_exit(); + return; + } + if (in_interrupt()) + panic("Fatal exception in interrupt"); + if (panic_on_oops) + panic("Fatal exception"); + oops_exit(); + do_exit(signr); +} + +int __kprobes __die(const char *str, struct pt_regs *regs, long err) +{ + printk(KERN_EMERG "%s: %04lx [#%d] ", str, err & 0xffff, ++die_counter); +#ifdef CONFIG_PREEMPT + printk("PREEMPT "); +#endif +#ifdef CONFIG_SMP + printk("SMP "); +#endif +#ifdef CONFIG_DEBUG_PAGEALLOC + printk("DEBUG_PAGEALLOC"); +#endif + printk("\n"); + if (notify_die(DIE_OOPS, str, regs, err, + current->thread.trap_no, SIGSEGV) == NOTIFY_STOP) + return 1; + + show_registers(regs); + add_taint(TAINT_DIE); + /* Executive summary in case the oops scrolled away */ + printk(KERN_ALERT "RIP "); + printk_address(regs->ip, 1); + printk(" RSP <%016lx>\n", regs->sp); + if (kexec_should_crash(current)) + crash_kexec(regs); + return 0; +} + +void die(const char *str, struct pt_regs *regs, long err) +{ + unsigned long flags = oops_begin(); + + if (!user_mode(regs)) + report_bug(regs->ip, regs); + + if (__die(str, regs, err)) + regs = NULL; + oops_end(flags, regs, SIGSEGV); +} + +notrace __kprobes void +die_nmi(char *str, struct pt_regs *regs, int do_panic) +{ + unsigned long flags; + + if (notify_die(DIE_NMIWATCHDOG, str, regs, 0, 2, SIGINT) == NOTIFY_STOP) + return; + + flags = oops_begin(); + /* + * We are in trouble anyway, lets at least try + * to get a message out. + */ + printk(KERN_EMERG "%s", str); + printk(" on CPU%d, ip %08lx, registers:\n", + smp_processor_id(), regs->ip); + show_registers(regs); + if (kexec_should_crash(current)) + crash_kexec(regs); + if (do_panic || panic_on_oops) + panic("Non maskable interrupt"); + oops_end(flags, NULL, SIGBUS); + nmi_exit(); + local_irq_enable(); + do_exit(SIGBUS); +} + +static int __init oops_setup(char *s) +{ + if (!s) + return -EINVAL; + if (!strcmp(s, "panic")) + panic_on_oops = 1; + return 0; +} +early_param("oops", oops_setup); + +static int __init kstack_setup(char *s) +{ + if (!s) + return -EINVAL; + kstack_depth_to_print = simple_strtoul(s, NULL, 0); + return 0; +} +early_param("kstack", kstack_setup); + +static int __init code_bytes_setup(char *s) +{ + code_bytes = simple_strtoul(s, NULL, 0); + if (code_bytes > 8192) + code_bytes = 8192; + + return 1; +} +__setup("code_bytes=", code_bytes_setup); diff --git a/arch/x86/kernel/entry_32.S b/arch/x86/kernel/entry_32.S index 109792bc7cfa..b21fbfaffe39 100644 --- a/arch/x86/kernel/entry_32.S +++ b/arch/x86/kernel/entry_32.S @@ -730,6 +730,7 @@ error_code: movl $(__USER_DS), %ecx movl %ecx, %ds movl %ecx, %es + TRACE_IRQS_OFF movl %esp,%eax # pt_regs pointer call *%edi jmp ret_from_exception @@ -760,20 +761,9 @@ ENTRY(device_not_available) RING0_INT_FRAME pushl $-1 # mark this as an int CFI_ADJUST_CFA_OFFSET 4 - SAVE_ALL - GET_CR0_INTO_EAX - testl $0x4, %eax # EM (math emulation bit) - jne device_not_available_emulate - preempt_stop(CLBR_ANY) - call math_state_restore - jmp ret_from_exception -device_not_available_emulate: - pushl $0 # temporary storage for ORIG_EIP + pushl $do_device_not_available CFI_ADJUST_CFA_OFFSET 4 - call math_emulate - addl $4, %esp - CFI_ADJUST_CFA_OFFSET -4 - jmp ret_from_exception + jmp error_code CFI_ENDPROC END(device_not_available) @@ -814,6 +804,7 @@ debug_stack_correct: pushl $-1 # mark this as an int CFI_ADJUST_CFA_OFFSET 4 SAVE_ALL + TRACE_IRQS_OFF xorl %edx,%edx # error code 0 movl %esp,%eax # pt_regs pointer call do_debug @@ -858,6 +849,7 @@ nmi_stack_correct: pushl %eax CFI_ADJUST_CFA_OFFSET 4 SAVE_ALL + TRACE_IRQS_OFF xorl %edx,%edx # zero error code movl %esp,%eax # pt_regs pointer call do_nmi @@ -898,6 +890,7 @@ nmi_espfix_stack: pushl %eax CFI_ADJUST_CFA_OFFSET 4 SAVE_ALL + TRACE_IRQS_OFF FIXUP_ESPFIX_STACK # %eax == %esp xorl %edx,%edx # zero error code call do_nmi @@ -928,6 +921,7 @@ KPROBE_ENTRY(int3) pushl $-1 # mark this as an int CFI_ADJUST_CFA_OFFSET 4 SAVE_ALL + TRACE_IRQS_OFF xorl %edx,%edx # zero error code movl %esp,%eax # pt_regs pointer call do_int3 @@ -1030,7 +1024,7 @@ ENTRY(machine_check) RING0_INT_FRAME pushl $0 CFI_ADJUST_CFA_OFFSET 4 - pushl machine_check_vector + pushl $do_machine_check CFI_ADJUST_CFA_OFFSET 4 jmp error_code CFI_ENDPROC diff --git a/arch/x86/kernel/entry_64.S b/arch/x86/kernel/entry_64.S index cf3a0b2d0059..1db6ce4314e1 100644 --- a/arch/x86/kernel/entry_64.S +++ b/arch/x86/kernel/entry_64.S @@ -667,6 +667,13 @@ END(stub_rt_sigreturn) SAVE_ARGS leaq -ARGOFFSET(%rsp),%rdi # arg1 for handler pushq %rbp + /* + * Save rbp twice: One is for marking the stack frame, as usual, and the + * other, to fill pt_regs properly. This is because bx comes right + * before the last saved register in that structure, and not bp. If the + * base pointer were in the place bx is today, this would not be needed. + */ + movq %rbp, -8(%rsp) CFI_ADJUST_CFA_OFFSET 8 CFI_REL_OFFSET rbp, 0 movq %rsp,%rbp @@ -932,6 +939,9 @@ END(spurious_interrupt) .if \ist movq %gs:pda_data_offset, %rbp .endif + .if \irqtrace + TRACE_IRQS_OFF + .endif movq %rsp,%rdi movq ORIG_RAX(%rsp),%rsi movq $-1,ORIG_RAX(%rsp) @@ -1058,7 +1068,8 @@ KPROBE_ENTRY(error_entry) je error_kernelspace error_swapgs: SWAPGS -error_sti: +error_sti: + TRACE_IRQS_OFF movq %rdi,RDI(%rsp) CFI_REL_OFFSET rdi,RDI movq %rsp,%rdi @@ -1232,7 +1243,7 @@ ENTRY(simd_coprocessor_error) END(simd_coprocessor_error) ENTRY(device_not_available) - zeroentry math_state_restore + zeroentry do_device_not_available END(device_not_available) /* runs on exception stack */ diff --git a/arch/x86/kernel/es7000_32.c b/arch/x86/kernel/es7000_32.c index 849e5cd485b8..f454c78fcef6 100644 --- a/arch/x86/kernel/es7000_32.c +++ b/arch/x86/kernel/es7000_32.c @@ -109,6 +109,7 @@ struct oem_table { }; extern int find_unisys_acpi_oem_table(unsigned long *oem_addr); +extern void unmap_unisys_acpi_oem_table(unsigned long oem_addr); #endif struct mip_reg { @@ -243,21 +244,38 @@ parse_unisys_oem (char *oemptr) } #ifdef CONFIG_ACPI -int __init -find_unisys_acpi_oem_table(unsigned long *oem_addr) +static unsigned long oem_addrX; +static unsigned long oem_size; +int __init find_unisys_acpi_oem_table(unsigned long *oem_addr) { struct acpi_table_header *header = NULL; int i = 0; - while (ACPI_SUCCESS(acpi_get_table("OEM1", i++, &header))) { + acpi_size tbl_size; + + while (ACPI_SUCCESS(acpi_get_table_with_size("OEM1", i++, &header, &tbl_size))) { if (!memcmp((char *) &header->oem_id, "UNISYS", 6)) { struct oem_table *t = (struct oem_table *)header; - *oem_addr = (unsigned long)__acpi_map_table(t->OEMTableAddr, - t->OEMTableSize); + + oem_addrX = t->OEMTableAddr; + oem_size = t->OEMTableSize; + early_acpi_os_unmap_memory(header, tbl_size); + + *oem_addr = (unsigned long)__acpi_map_table(oem_addrX, + oem_size); return 0; } + early_acpi_os_unmap_memory(header, tbl_size); } return -1; } + +void __init unmap_unisys_acpi_oem_table(unsigned long oem_addr) +{ + if (!oem_addr) + return; + + __acpi_unmap_table((char *)oem_addr, oem_size); +} #endif static void diff --git a/arch/x86/kernel/genx2apic_uv_x.c b/arch/x86/kernel/genx2apic_uv_x.c index ae2ffc8a400c..33581d94a90e 100644 --- a/arch/x86/kernel/genx2apic_uv_x.c +++ b/arch/x86/kernel/genx2apic_uv_x.c @@ -114,7 +114,7 @@ static void uv_send_IPI_one(int cpu, int vector) unsigned long val, apicid, lapicid; int pnode; - apicid = per_cpu(x86_cpu_to_apicid, cpu); /* ZZZ - cache node-local ? */ + apicid = per_cpu(x86_cpu_to_apicid, cpu); lapicid = apicid & 0x3f; /* ZZZ macro needed */ pnode = uv_apicid_to_pnode(apicid); val = @@ -202,12 +202,10 @@ static unsigned int phys_pkg_id(int index_msb) return uv_read_apic_id() >> index_msb; } -#ifdef ZZZ /* Needs x2apic patch */ static void uv_send_IPI_self(int vector) { apic_write(APIC_SELF_IPI, vector); } -#endif struct genapic apic_x2apic_uv_x = { .name = "UV large system", @@ -215,15 +213,15 @@ struct genapic apic_x2apic_uv_x = { .int_delivery_mode = dest_Fixed, .int_dest_mode = (APIC_DEST_PHYSICAL != 0), .target_cpus = uv_target_cpus, - .vector_allocation_domain = uv_vector_allocation_domain,/* Fixme ZZZ */ + .vector_allocation_domain = uv_vector_allocation_domain, .apic_id_registered = uv_apic_id_registered, .init_apic_ldr = uv_init_apic_ldr, .send_IPI_all = uv_send_IPI_all, .send_IPI_allbutself = uv_send_IPI_allbutself, .send_IPI_mask = uv_send_IPI_mask, - /* ZZZ.send_IPI_self = uv_send_IPI_self, */ + .send_IPI_self = uv_send_IPI_self, .cpu_mask_to_apicid = uv_cpu_mask_to_apicid, - .phys_pkg_id = phys_pkg_id, /* Fixme ZZZ */ + .phys_pkg_id = phys_pkg_id, .get_apic_id = get_apic_id, .set_apic_id = set_apic_id, .apic_id_mask = (0xFFFFFFFFu), @@ -286,12 +284,13 @@ static __init void map_low_mmrs(void) enum map_type {map_wb, map_uc}; -static __init void map_high(char *id, unsigned long base, int shift, enum map_type map_type) +static __init void map_high(char *id, unsigned long base, int shift, + int max_pnode, enum map_type map_type) { unsigned long bytes, paddr; paddr = base << shift; - bytes = (1UL << shift); + bytes = (1UL << shift) * (max_pnode + 1); printk(KERN_INFO "UV: Map %s_HI 0x%lx - 0x%lx\n", id, paddr, paddr + bytes); if (map_type == map_uc) @@ -307,7 +306,7 @@ static __init void map_gru_high(int max_pnode) gru.v = uv_read_local_mmr(UVH_RH_GAM_GRU_OVERLAY_CONFIG_MMR); if (gru.s.enable) - map_high("GRU", gru.s.base, shift, map_wb); + map_high("GRU", gru.s.base, shift, max_pnode, map_wb); } static __init void map_config_high(int max_pnode) @@ -317,7 +316,7 @@ static __init void map_config_high(int max_pnode) cfg.v = uv_read_local_mmr(UVH_RH_GAM_CFG_OVERLAY_CONFIG_MMR); if (cfg.s.enable) - map_high("CONFIG", cfg.s.base, shift, map_uc); + map_high("CONFIG", cfg.s.base, shift, max_pnode, map_uc); } static __init void map_mmr_high(int max_pnode) @@ -327,7 +326,7 @@ static __init void map_mmr_high(int max_pnode) mmr.v = uv_read_local_mmr(UVH_RH_GAM_MMR_OVERLAY_CONFIG_MMR); if (mmr.s.enable) - map_high("MMR", mmr.s.base, shift, map_uc); + map_high("MMR", mmr.s.base, shift, max_pnode, map_uc); } static __init void map_mmioh_high(int max_pnode) @@ -337,7 +336,7 @@ static __init void map_mmioh_high(int max_pnode) mmioh.v = uv_read_local_mmr(UVH_RH_GAM_MMIOH_OVERLAY_CONFIG_MMR); if (mmioh.s.enable) - map_high("MMIOH", mmioh.s.base, shift, map_uc); + map_high("MMIOH", mmioh.s.base, shift, max_pnode, map_uc); } static __init void uv_rtc_init(void) diff --git a/arch/x86/kernel/head.c b/arch/x86/kernel/head.c index 3e66bd364a9d..1dcb0f13897e 100644 --- a/arch/x86/kernel/head.c +++ b/arch/x86/kernel/head.c @@ -35,6 +35,7 @@ void __init reserve_ebda_region(void) /* start of EBDA area */ ebda_addr = get_bios_ebda(); + printk(KERN_INFO "BIOS EBDA/lowmem at: %08x/%08x\n", ebda_addr, lowmem); /* Fixup: bios puts an EBDA in the top 64K segment */ /* of conventional memory, but does not adjust lowmem. */ diff --git a/arch/x86/kernel/hpet.c b/arch/x86/kernel/hpet.c index 73deaffadd03..acf62fc233da 100644 --- a/arch/x86/kernel/hpet.c +++ b/arch/x86/kernel/hpet.c @@ -115,13 +115,17 @@ static void hpet_reserve_platform_timers(unsigned long id) hd.hd_phys_address = hpet_address; hd.hd_address = hpet; hd.hd_nirqs = nrtimers; - hd.hd_flags = HPET_DATA_PLATFORM; hpet_reserve_timer(&hd, 0); #ifdef CONFIG_HPET_EMULATE_RTC hpet_reserve_timer(&hd, 1); #endif + /* + * NOTE that hd_irq[] reflects IOAPIC input pins (LEGACY_8254 + * is wrong for i8259!) not the output IRQ. Many BIOS writers + * don't bother configuring *any* comparator interrupts. + */ hd.hd_irq[0] = HPET_LEGACY_8254; hd.hd_irq[1] = HPET_LEGACY_RTC; diff --git a/arch/x86/kernel/irqinit_64.c b/arch/x86/kernel/irqinit_64.c index 1f26fd9ec4f4..5b5be9d43c2a 100644 --- a/arch/x86/kernel/irqinit_64.c +++ b/arch/x86/kernel/irqinit_64.c @@ -135,7 +135,7 @@ DEFINE_PER_CPU(vector_irq_t, vector_irq) = { [IRQ15_VECTOR + 1 ... NR_VECTORS - 1] = -1 }; -static void __init init_ISA_irqs (void) +void __init init_ISA_irqs(void) { int i; @@ -164,22 +164,8 @@ static void __init init_ISA_irqs (void) void init_IRQ(void) __attribute__((weak, alias("native_init_IRQ"))); -void __init native_init_IRQ(void) +static void __init smp_intr_init(void) { - int i; - - init_ISA_irqs(); - /* - * Cover the whole vector space, no vector can escape - * us. (some of these will be overridden and become - * 'special' SMP interrupts) - */ - for (i = 0; i < (NR_VECTORS - FIRST_EXTERNAL_VECTOR); i++) { - int vector = FIRST_EXTERNAL_VECTOR + i; - if (vector != IA32_SYSCALL_VECTOR) - set_intr_gate(vector, interrupt[i]); - } - #ifdef CONFIG_SMP /* * The reschedule interrupt is a CPU-to-CPU reschedule-helper @@ -207,6 +193,12 @@ void __init native_init_IRQ(void) /* Low priority IPI to cleanup after moving an irq */ set_intr_gate(IRQ_MOVE_CLEANUP_VECTOR, irq_move_cleanup_interrupt); #endif +} + +static void __init apic_intr_init(void) +{ + smp_intr_init(); + alloc_intr_gate(THERMAL_APIC_VECTOR, thermal_interrupt); alloc_intr_gate(THRESHOLD_APIC_VECTOR, threshold_interrupt); @@ -216,6 +208,25 @@ void __init native_init_IRQ(void) /* IPI vectors for APIC spurious and error interrupts */ alloc_intr_gate(SPURIOUS_APIC_VECTOR, spurious_interrupt); alloc_intr_gate(ERROR_APIC_VECTOR, error_interrupt); +} + +void __init native_init_IRQ(void) +{ + int i; + + init_ISA_irqs(); + /* + * Cover the whole vector space, no vector can escape + * us. (some of these will be overridden and become + * 'special' SMP interrupts) + */ + for (i = 0; i < (NR_VECTORS - FIRST_EXTERNAL_VECTOR); i++) { + int vector = FIRST_EXTERNAL_VECTOR + i; + if (vector != IA32_SYSCALL_VECTOR) + set_intr_gate(vector, interrupt[i]); + } + + apic_intr_init(); if (!acpi_ioapic) setup_irq(2, &irq2); diff --git a/arch/x86/kernel/process_32.c b/arch/x86/kernel/process_32.c index 922c14058f97..0a1302fe6d45 100644 --- a/arch/x86/kernel/process_32.c +++ b/arch/x86/kernel/process_32.c @@ -123,7 +123,7 @@ void cpu_idle(void) } } -void __show_registers(struct pt_regs *regs, int all) +void __show_regs(struct pt_regs *regs, int all) { unsigned long cr0 = 0L, cr2 = 0L, cr3 = 0L, cr4 = 0L; unsigned long d0, d1, d2, d3, d6, d7; @@ -189,7 +189,7 @@ void __show_registers(struct pt_regs *regs, int all) void show_regs(struct pt_regs *regs) { - __show_registers(regs, 1); + __show_regs(regs, 1); show_trace(NULL, regs, ®s->sp, regs->bp); } diff --git a/arch/x86/kernel/process_64.c b/arch/x86/kernel/process_64.c index ca80394ef5b8..cd8c0ed02b7e 100644 --- a/arch/x86/kernel/process_64.c +++ b/arch/x86/kernel/process_64.c @@ -136,7 +136,7 @@ void cpu_idle(void) } /* Prints also some state that isn't saved in the pt_regs */ -void __show_regs(struct pt_regs *regs) +void __show_regs(struct pt_regs *regs, int all) { unsigned long cr0 = 0L, cr2 = 0L, cr3 = 0L, cr4 = 0L, fs, gs, shadowgs; unsigned long d0, d1, d2, d3, d6, d7; @@ -175,6 +175,9 @@ void __show_regs(struct pt_regs *regs) rdmsrl(MSR_GS_BASE, gs); rdmsrl(MSR_KERNEL_GS_BASE, shadowgs); + if (!all) + return; + cr0 = read_cr0(); cr2 = read_cr2(); cr3 = read_cr3(); @@ -200,7 +203,7 @@ void __show_regs(struct pt_regs *regs) void show_regs(struct pt_regs *regs) { printk(KERN_INFO "CPU %d:", smp_processor_id()); - __show_regs(regs); + __show_regs(regs, 1); show_trace(NULL, regs, (void *)(regs + 1), regs->bp); } diff --git a/arch/x86/kernel/quirks.c b/arch/x86/kernel/quirks.c index d13858818100..f6a11b9b1f98 100644 --- a/arch/x86/kernel/quirks.c +++ b/arch/x86/kernel/quirks.c @@ -354,9 +354,27 @@ static void ati_force_hpet_resume(void) printk(KERN_DEBUG "Force enabled HPET at resume\n"); } +static u32 ati_ixp4x0_rev(struct pci_dev *dev) +{ + u32 d; + u8 b; + + pci_read_config_byte(dev, 0xac, &b); + b &= ~(1<<5); + pci_write_config_byte(dev, 0xac, b); + pci_read_config_dword(dev, 0x70, &d); + d |= 1<<8; + pci_write_config_dword(dev, 0x70, d); + pci_read_config_dword(dev, 0x8, &d); + d &= 0xff; + dev_printk(KERN_DEBUG, &dev->dev, "SB4X0 revision 0x%x\n", d); + return d; +} + static void ati_force_enable_hpet(struct pci_dev *dev) { - u32 uninitialized_var(val); + u32 d, val; + u8 b; if (hpet_address || force_hpet_address) return; @@ -366,14 +384,33 @@ static void ati_force_enable_hpet(struct pci_dev *dev) return; } + d = ati_ixp4x0_rev(dev); + if (d < 0x82) + return; + + /* base address */ pci_write_config_dword(dev, 0x14, 0xfed00000); pci_read_config_dword(dev, 0x14, &val); + + /* enable interrupt */ + outb(0x72, 0xcd6); b = inb(0xcd7); + b |= 0x1; + outb(0x72, 0xcd6); outb(b, 0xcd7); + outb(0x72, 0xcd6); b = inb(0xcd7); + if (!(b & 0x1)) + return; + pci_read_config_dword(dev, 0x64, &d); + d |= (1<<10); + pci_write_config_dword(dev, 0x64, d); + pci_read_config_dword(dev, 0x64, &d); + if (!(d & (1<<10))) + return; + force_hpet_address = val; force_hpet_resume_type = ATI_FORCE_HPET_RESUME; dev_printk(KERN_DEBUG, &dev->dev, "Force enabled HPET at 0x%lx\n", force_hpet_address); cached_dev = dev; - return; } DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_ATI, PCI_DEVICE_ID_ATI_IXP400_SMBUS, ati_force_enable_hpet); diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c index 21b8e0a59780..2255782e8d4b 100644 --- a/arch/x86/kernel/setup.c +++ b/arch/x86/kernel/setup.c @@ -302,7 +302,7 @@ static void __init relocate_initrd(void) if (clen > MAX_MAP_CHUNK-slop) clen = MAX_MAP_CHUNK-slop; mapaddr = ramdisk_image & PAGE_MASK; - p = early_ioremap(mapaddr, clen+slop); + p = early_memremap(mapaddr, clen+slop); memcpy(q, p+slop, clen); early_iounmap(p, clen+slop); q += clen; @@ -379,7 +379,7 @@ static void __init parse_setup_data(void) return; pa_data = boot_params.hdr.setup_data; while (pa_data) { - data = early_ioremap(pa_data, PAGE_SIZE); + data = early_memremap(pa_data, PAGE_SIZE); switch (data->type) { case SETUP_E820_EXT: parse_e820_ext(data, pa_data); @@ -402,7 +402,7 @@ static void __init e820_reserve_setup_data(void) return; pa_data = boot_params.hdr.setup_data; while (pa_data) { - data = early_ioremap(pa_data, sizeof(*data)); + data = early_memremap(pa_data, sizeof(*data)); e820_update_range(pa_data, sizeof(*data)+data->len, E820_RAM, E820_RESERVED_KERN); found = 1; @@ -428,7 +428,7 @@ static void __init reserve_early_setup_data(void) return; pa_data = boot_params.hdr.setup_data; while (pa_data) { - data = early_ioremap(pa_data, sizeof(*data)); + data = early_memremap(pa_data, sizeof(*data)); sprintf(buf, "setup data %x", data->type); reserve_early(pa_data, pa_data+sizeof(*data)+data->len, buf); pa_data = data->next; @@ -998,6 +998,8 @@ void __init setup_arch(char **cmdline_p) */ acpi_boot_table_init(); + early_acpi_boot_init(); + #ifdef CONFIG_ACPI_NUMA /* * Parse SRAT to discover nodes. diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c index 76b6f50978f7..8c3aca7cb343 100644 --- a/arch/x86/kernel/smpboot.c +++ b/arch/x86/kernel/smpboot.c @@ -334,14 +334,17 @@ static void __cpuinit start_secondary(void *unused) * does not change while we are assigning vectors to cpus. Holding * this lock ensures we don't half assign or remove an irq from a cpu. */ - ipi_call_lock_irq(); + ipi_call_lock(); lock_vector_lock(); __setup_vector_irq(smp_processor_id()); cpu_set(smp_processor_id(), cpu_online_map); unlock_vector_lock(); - ipi_call_unlock_irq(); + ipi_call_unlock(); per_cpu(cpu_state, smp_processor_id()) = CPU_ONLINE; + /* enable local interrupts */ + local_irq_enable(); + setup_secondary_clock(); wmb(); @@ -596,10 +599,12 @@ wakeup_secondary_cpu(int logical_apicid, unsigned long start_eip) * Give the other CPU some time to accept the IPI. */ udelay(200); - maxlvt = lapic_get_maxlvt(); - if (maxlvt > 3) /* Due to the Pentium erratum 3AP. */ - apic_write(APIC_ESR, 0); - accept_status = (apic_read(APIC_ESR) & 0xEF); + if (APIC_INTEGRATED(apic_version[phys_apicid])) { + maxlvt = lapic_get_maxlvt(); + if (maxlvt > 3) /* Due to the Pentium erratum 3AP. */ + apic_write(APIC_ESR, 0); + accept_status = (apic_read(APIC_ESR) & 0xEF); + } pr_debug("NMI sent.\n"); if (send_status) @@ -1256,39 +1261,6 @@ void __init native_smp_cpus_done(unsigned int max_cpus) check_nmi_watchdog(); } -#ifdef CONFIG_HOTPLUG_CPU - -static void remove_siblinginfo(int cpu) -{ - int sibling; - struct cpuinfo_x86 *c = &cpu_data(cpu); - - for_each_cpu_mask_nr(sibling, per_cpu(cpu_core_map, cpu)) { - cpu_clear(cpu, per_cpu(cpu_core_map, sibling)); - /*/ - * last thread sibling in this cpu core going down - */ - if (cpus_weight(per_cpu(cpu_sibling_map, cpu)) == 1) - cpu_data(sibling).booted_cores--; - } - - for_each_cpu_mask_nr(sibling, per_cpu(cpu_sibling_map, cpu)) - cpu_clear(cpu, per_cpu(cpu_sibling_map, sibling)); - cpus_clear(per_cpu(cpu_sibling_map, cpu)); - cpus_clear(per_cpu(cpu_core_map, cpu)); - c->phys_proc_id = 0; - c->cpu_core_id = 0; - cpu_clear(cpu, cpu_sibling_setup_map); -} - -static int additional_cpus __initdata = -1; - -static __init int setup_additional_cpus(char *s) -{ - return s && get_option(&s, &additional_cpus) ? 0 : -EINVAL; -} -early_param("additional_cpus", setup_additional_cpus); - /* * cpu_possible_map should be static, it cannot change as cpu's * are onlined, or offlined. The reason is per-cpu data-structures @@ -1308,21 +1280,13 @@ early_param("additional_cpus", setup_additional_cpus); */ __init void prefill_possible_map(void) { - int i; - int possible; + int i, possible; /* no processor from mptable or madt */ if (!num_processors) num_processors = 1; - if (additional_cpus == -1) { - if (disabled_cpus > 0) - additional_cpus = disabled_cpus; - else - additional_cpus = 0; - } - - possible = num_processors + additional_cpus; + possible = num_processors + disabled_cpus; if (possible > NR_CPUS) possible = NR_CPUS; @@ -1335,6 +1299,31 @@ __init void prefill_possible_map(void) nr_cpu_ids = possible; } +#ifdef CONFIG_HOTPLUG_CPU + +static void remove_siblinginfo(int cpu) +{ + int sibling; + struct cpuinfo_x86 *c = &cpu_data(cpu); + + for_each_cpu_mask_nr(sibling, per_cpu(cpu_core_map, cpu)) { + cpu_clear(cpu, per_cpu(cpu_core_map, sibling)); + /*/ + * last thread sibling in this cpu core going down + */ + if (cpus_weight(per_cpu(cpu_sibling_map, cpu)) == 1) + cpu_data(sibling).booted_cores--; + } + + for_each_cpu_mask_nr(sibling, per_cpu(cpu_sibling_map, cpu)) + cpu_clear(cpu, per_cpu(cpu_sibling_map, sibling)); + cpus_clear(per_cpu(cpu_sibling_map, cpu)); + cpus_clear(per_cpu(cpu_core_map, cpu)); + c->phys_proc_id = 0; + c->cpu_core_id = 0; + cpu_clear(cpu, cpu_sibling_setup_map); +} + static void __ref remove_cpu_from_maps(int cpu) { cpu_clear(cpu, cpu_online_map); diff --git a/arch/x86/kernel/time_32.c b/arch/x86/kernel/time_32.c index bbecf8b6bf96..77b400f06ea2 100644 --- a/arch/x86/kernel/time_32.c +++ b/arch/x86/kernel/time_32.c @@ -47,10 +47,9 @@ unsigned long profile_pc(struct pt_regs *regs) unsigned long pc = instruction_pointer(regs); #ifdef CONFIG_SMP - if (!v8086_mode(regs) && SEGMENT_IS_KERNEL_CODE(regs->cs) && - in_lock_functions(pc)) { + if (!user_mode_vm(regs) && in_lock_functions(pc)) { #ifdef CONFIG_FRAME_POINTER - return *(unsigned long *)(regs->bp + 4); + return *(unsigned long *)(regs->bp + sizeof(long)); #else unsigned long *sp = (unsigned long *)®s->sp; @@ -95,6 +94,7 @@ irqreturn_t timer_interrupt(int irq, void *dev_id) do_timer_interrupt_hook(); +#ifdef CONFIG_MCA if (MCA_bus) { /* The PS/2 uses level-triggered interrupts. You can't turn them off, nor would you want to (any attempt to @@ -108,6 +108,7 @@ irqreturn_t timer_interrupt(int irq, void *dev_id) u8 irq_v = inb_p( 0x61 ); /* read the current state */ outb_p( irq_v|0x80, 0x61 ); /* reset the IRQ */ } +#endif return IRQ_HANDLED; } diff --git a/arch/x86/kernel/time_64.c b/arch/x86/kernel/time_64.c index e3d49c553af2..cb19d650c216 100644 --- a/arch/x86/kernel/time_64.c +++ b/arch/x86/kernel/time_64.c @@ -16,6 +16,7 @@ #include <linux/interrupt.h> #include <linux/module.h> #include <linux/time.h> +#include <linux/mca.h> #include <asm/i8253.h> #include <asm/hpet.h> @@ -33,23 +34,34 @@ unsigned long profile_pc(struct pt_regs *regs) /* Assume the lock function has either no stack frame or a copy of flags from PUSHF Eflags always has bits 22 and up cleared unlike kernel addresses. */ - if (!user_mode(regs) && in_lock_functions(pc)) { + if (!user_mode_vm(regs) && in_lock_functions(pc)) { +#ifdef CONFIG_FRAME_POINTER + return *(unsigned long *)(regs->bp + sizeof(long)); +#else unsigned long *sp = (unsigned long *)regs->sp; if (sp[0] >> 22) return sp[0]; if (sp[1] >> 22) return sp[1]; +#endif } return pc; } EXPORT_SYMBOL(profile_pc); -static irqreturn_t timer_event_interrupt(int irq, void *dev_id) +irqreturn_t timer_interrupt(int irq, void *dev_id) { add_pda(irq0_irqs, 1); global_clock_event->event_handler(global_clock_event); +#ifdef CONFIG_MCA + if (MCA_bus) { + u8 irq_v = inb_p(0x61); /* read the current state */ + outb_p(irq_v|0x80, 0x61); /* reset the IRQ */ + } +#endif + return IRQ_HANDLED; } @@ -100,7 +112,7 @@ unsigned long __init calibrate_cpu(void) } static struct irqaction irq0 = { - .handler = timer_event_interrupt, + .handler = timer_interrupt, .flags = IRQF_DISABLED | IRQF_IRQPOLL | IRQF_NOBALANCING, .mask = CPU_MASK_NONE, .name = "timer" @@ -111,16 +123,13 @@ void __init hpet_time_init(void) if (!hpet_enable()) setup_pit_timer(); + irq0.mask = cpumask_of_cpu(0); setup_irq(0, &irq0); } void __init time_init(void) { tsc_init(); - if (cpu_has(&boot_cpu_data, X86_FEATURE_RDTSCP)) - vgetcpu_mode = VGETCPU_RDTSCP; - else - vgetcpu_mode = VGETCPU_LSL; late_time_init = choose_time_init(); } diff --git a/arch/x86/kernel/traps_32.c b/arch/x86/kernel/traps.c index 0429c5de5ea9..e062974cce34 100644 --- a/arch/x86/kernel/traps_32.c +++ b/arch/x86/kernel/traps.c @@ -7,13 +7,11 @@ */ /* - * 'Traps.c' handles hardware traps and faults after we have saved some - * state in 'asm.s'. + * Handle hardware traps and faults. */ #include <linux/interrupt.h> #include <linux/kallsyms.h> #include <linux/spinlock.h> -#include <linux/highmem.h> #include <linux/kprobes.h> #include <linux/uaccess.h> #include <linux/utsname.h> @@ -32,6 +30,8 @@ #include <linux/bug.h> #include <linux/nmi.h> #include <linux/mm.h> +#include <linux/smp.h> +#include <linux/io.h> #ifdef CONFIG_EISA #include <linux/ioport.h> @@ -46,21 +46,31 @@ #include <linux/edac.h> #endif -#include <asm/arch_hooks.h> #include <asm/stacktrace.h> #include <asm/processor.h> #include <asm/debugreg.h> #include <asm/atomic.h> #include <asm/system.h> #include <asm/unwind.h> +#include <asm/traps.h> #include <asm/desc.h> #include <asm/i387.h> + +#include <mach_traps.h> + +#ifdef CONFIG_X86_64 +#include <asm/pgalloc.h> +#include <asm/proto.h> +#include <asm/pda.h> +#else +#include <asm/processor-flags.h> +#include <asm/arch_hooks.h> #include <asm/nmi.h> #include <asm/smp.h> #include <asm/io.h> #include <asm/traps.h> -#include "mach_traps.h" +#include "cpu/mcheck/mce.h" DECLARE_BITMAP(used_vectors, NR_VECTORS); EXPORT_SYMBOL_GPL(used_vectors); @@ -77,418 +87,104 @@ char ignore_fpu_irq; */ gate_desc idt_table[256] __attribute__((__section__(".data.idt"))) = { { { { 0, 0 } } }, }; - -int panic_on_unrecovered_nmi; -int kstack_depth_to_print = 24; -static unsigned int code_bytes = 64; -static int ignore_nmis; -static int die_counter; - -void printk_address(unsigned long address, int reliable) -{ -#ifdef CONFIG_KALLSYMS - unsigned long offset = 0; - unsigned long symsize; - const char *symname; - char *modname; - char *delim = ":"; - char namebuf[KSYM_NAME_LEN]; - char reliab[4] = ""; - - symname = kallsyms_lookup(address, &symsize, &offset, - &modname, namebuf); - if (!symname) { - printk(" [<%08lx>]\n", address); - return; - } - if (!reliable) - strcpy(reliab, "? "); - - if (!modname) - modname = delim = ""; - printk(" [<%08lx>] %s%s%s%s%s+0x%lx/0x%lx\n", - address, reliab, delim, modname, delim, symname, offset, symsize); -#else - printk(" [<%08lx>]\n", address); #endif -} - -static inline int valid_stack_ptr(struct thread_info *tinfo, - void *p, unsigned int size) -{ - void *t = tinfo; - return p > t && p <= t + THREAD_SIZE - size; -} - -/* The form of the top of the frame on the stack */ -struct stack_frame { - struct stack_frame *next_frame; - unsigned long return_address; -}; - -static inline unsigned long -print_context_stack(struct thread_info *tinfo, - unsigned long *stack, unsigned long bp, - const struct stacktrace_ops *ops, void *data) -{ - struct stack_frame *frame = (struct stack_frame *)bp; - - while (valid_stack_ptr(tinfo, stack, sizeof(*stack))) { - unsigned long addr; - - addr = *stack; - if (__kernel_text_address(addr)) { - if ((unsigned long) stack == bp + 4) { - ops->address(data, addr, 1); - frame = frame->next_frame; - bp = (unsigned long) frame; - } else { - ops->address(data, addr, bp == 0); - } - } - stack++; - } - return bp; -} - -void dump_trace(struct task_struct *task, struct pt_regs *regs, - unsigned long *stack, unsigned long bp, - const struct stacktrace_ops *ops, void *data) -{ - if (!task) - task = current; - - if (!stack) { - unsigned long dummy; - stack = &dummy; - if (task != current) - stack = (unsigned long *)task->thread.sp; - } - -#ifdef CONFIG_FRAME_POINTER - if (!bp) { - if (task == current) { - /* Grab bp right from our regs */ - asm("movl %%ebp, %0" : "=r" (bp) :); - } else { - /* bp is the last reg pushed by switch_to */ - bp = *(unsigned long *) task->thread.sp; - } - } -#endif - - for (;;) { - struct thread_info *context; - - context = (struct thread_info *) - ((unsigned long)stack & (~(THREAD_SIZE - 1))); - bp = print_context_stack(context, stack, bp, ops, data); - /* - * Should be after the line below, but somewhere - * in early boot context comes out corrupted and we - * can't reference it: - */ - if (ops->stack(data, "IRQ") < 0) - break; - stack = (unsigned long *)context->previous_esp; - if (!stack) - break; - touch_nmi_watchdog(); - } -} -EXPORT_SYMBOL(dump_trace); - -static void -print_trace_warning_symbol(void *data, char *msg, unsigned long symbol) -{ - printk(data); - print_symbol(msg, symbol); - printk("\n"); -} - -static void print_trace_warning(void *data, char *msg) -{ - printk("%s%s\n", (char *)data, msg); -} -static int print_trace_stack(void *data, char *name) -{ - return 0; -} - -/* - * Print one address/symbol entries per line. - */ -static void print_trace_address(void *data, unsigned long addr, int reliable) -{ - printk("%s [<%08lx>] ", (char *)data, addr); - if (!reliable) - printk("? "); - print_symbol("%s\n", addr); - touch_nmi_watchdog(); -} - -static const struct stacktrace_ops print_trace_ops = { - .warning = print_trace_warning, - .warning_symbol = print_trace_warning_symbol, - .stack = print_trace_stack, - .address = print_trace_address, -}; +static int ignore_nmis; -static void -show_trace_log_lvl(struct task_struct *task, struct pt_regs *regs, - unsigned long *stack, unsigned long bp, char *log_lvl) +static inline void conditional_sti(struct pt_regs *regs) { - dump_trace(task, regs, stack, bp, &print_trace_ops, log_lvl); - printk("%s =======================\n", log_lvl); + if (regs->flags & X86_EFLAGS_IF) + local_irq_enable(); } -void show_trace(struct task_struct *task, struct pt_regs *regs, - unsigned long *stack, unsigned long bp) +static inline void preempt_conditional_sti(struct pt_regs *regs) { - show_trace_log_lvl(task, regs, stack, bp, ""); + inc_preempt_count(); + if (regs->flags & X86_EFLAGS_IF) + local_irq_enable(); } -static void -show_stack_log_lvl(struct task_struct *task, struct pt_regs *regs, - unsigned long *sp, unsigned long bp, char *log_lvl) +static inline void preempt_conditional_cli(struct pt_regs *regs) { - unsigned long *stack; - int i; - - if (sp == NULL) { - if (task) - sp = (unsigned long *)task->thread.sp; - else - sp = (unsigned long *)&sp; - } - - stack = sp; - for (i = 0; i < kstack_depth_to_print; i++) { - if (kstack_end(stack)) - break; - if (i && ((i % 8) == 0)) - printk("\n%s ", log_lvl); - printk("%08lx ", *stack++); - } - printk("\n%sCall Trace:\n", log_lvl); - - show_trace_log_lvl(task, regs, sp, bp, log_lvl); + if (regs->flags & X86_EFLAGS_IF) + local_irq_disable(); + dec_preempt_count(); } -void show_stack(struct task_struct *task, unsigned long *sp) +#ifdef CONFIG_X86_32 +static inline void +die_if_kernel(const char *str, struct pt_regs *regs, long err) { - printk(" "); - show_stack_log_lvl(task, NULL, sp, 0, ""); + if (!user_mode_vm(regs)) + die(str, regs, err); } /* - * The architecture-independent dump_stack generator + * Perform the lazy TSS's I/O bitmap copy. If the TSS has an + * invalid offset set (the LAZY one) and the faulting thread has + * a valid I/O bitmap pointer, we copy the I/O bitmap in the TSS, + * we set the offset field correctly and return 1. */ -void dump_stack(void) +static int lazy_iobitmap_copy(void) { - unsigned long bp = 0; - unsigned long stack; - -#ifdef CONFIG_FRAME_POINTER - if (!bp) - asm("movl %%ebp, %0" : "=r" (bp):); -#endif - - printk("Pid: %d, comm: %.20s %s %s %.*s\n", - current->pid, current->comm, print_tainted(), - init_utsname()->release, - (int)strcspn(init_utsname()->version, " "), - init_utsname()->version); - - show_trace(current, NULL, &stack, bp); -} - -EXPORT_SYMBOL(dump_stack); - -void show_registers(struct pt_regs *regs) -{ - int i; + struct thread_struct *thread; + struct tss_struct *tss; + int cpu; - print_modules(); - __show_registers(regs, 0); + cpu = get_cpu(); + tss = &per_cpu(init_tss, cpu); + thread = ¤t->thread; - printk(KERN_EMERG "Process %.*s (pid: %d, ti=%p task=%p task.ti=%p)", - TASK_COMM_LEN, current->comm, task_pid_nr(current), - current_thread_info(), current, task_thread_info(current)); - /* - * When in-kernel, we also print out the stack and code at the - * time of the fault.. - */ - if (!user_mode_vm(regs)) { - unsigned int code_prologue = code_bytes * 43 / 64; - unsigned int code_len = code_bytes; - unsigned char c; - u8 *ip; - - printk("\n" KERN_EMERG "Stack: "); - show_stack_log_lvl(NULL, regs, ®s->sp, 0, KERN_EMERG); - - printk(KERN_EMERG "Code: "); - - ip = (u8 *)regs->ip - code_prologue; - if (ip < (u8 *)PAGE_OFFSET || probe_kernel_address(ip, c)) { - /* try starting at EIP */ - ip = (u8 *)regs->ip; - code_len = code_len - code_prologue + 1; - } - for (i = 0; i < code_len; i++, ip++) { - if (ip < (u8 *)PAGE_OFFSET || - probe_kernel_address(ip, c)) { - printk(" Bad EIP value."); - break; - } - if (ip == (u8 *)regs->ip) - printk("<%02x> ", c); - else - printk("%02x ", c); + if (tss->x86_tss.io_bitmap_base == INVALID_IO_BITMAP_OFFSET_LAZY && + thread->io_bitmap_ptr) { + memcpy(tss->io_bitmap, thread->io_bitmap_ptr, + thread->io_bitmap_max); + /* + * If the previously set map was extending to higher ports + * than the current one, pad extra space with 0xff (no access). + */ + if (thread->io_bitmap_max < tss->io_bitmap_max) { + memset((char *) tss->io_bitmap + + thread->io_bitmap_max, 0xff, + tss->io_bitmap_max - thread->io_bitmap_max); } - } - printk("\n"); -} - -int is_valid_bugaddr(unsigned long ip) -{ - unsigned short ud2; - - if (ip < PAGE_OFFSET) - return 0; - if (probe_kernel_address((unsigned short *)ip, ud2)) - return 0; - - return ud2 == 0x0b0f; -} - -static raw_spinlock_t die_lock = __RAW_SPIN_LOCK_UNLOCKED; -static int die_owner = -1; -static unsigned int die_nest_count; - -unsigned __kprobes long oops_begin(void) -{ - unsigned long flags; - - oops_enter(); - - if (die_owner != raw_smp_processor_id()) { - console_verbose(); - raw_local_irq_save(flags); - __raw_spin_lock(&die_lock); - die_owner = smp_processor_id(); - die_nest_count = 0; - bust_spinlocks(1); - } else { - raw_local_irq_save(flags); - } - die_nest_count++; - return flags; -} - -void __kprobes oops_end(unsigned long flags, struct pt_regs *regs, int signr) -{ - bust_spinlocks(0); - die_owner = -1; - add_taint(TAINT_DIE); - __raw_spin_unlock(&die_lock); - raw_local_irq_restore(flags); - - if (!regs) - return; - - if (kexec_should_crash(current)) - crash_kexec(regs); - - if (in_interrupt()) - panic("Fatal exception in interrupt"); - - if (panic_on_oops) - panic("Fatal exception"); - - oops_exit(); - do_exit(signr); -} - -int __kprobes __die(const char *str, struct pt_regs *regs, long err) -{ - unsigned short ss; - unsigned long sp; + tss->io_bitmap_max = thread->io_bitmap_max; + tss->x86_tss.io_bitmap_base = IO_BITMAP_OFFSET; + tss->io_bitmap_owner = thread; + put_cpu(); - printk(KERN_EMERG "%s: %04lx [#%d] ", str, err & 0xffff, ++die_counter); -#ifdef CONFIG_PREEMPT - printk("PREEMPT "); -#endif -#ifdef CONFIG_SMP - printk("SMP "); -#endif -#ifdef CONFIG_DEBUG_PAGEALLOC - printk("DEBUG_PAGEALLOC"); -#endif - printk("\n"); - if (notify_die(DIE_OOPS, str, regs, err, - current->thread.trap_no, SIGSEGV) == NOTIFY_STOP) return 1; - - show_registers(regs); - /* Executive summary in case the oops scrolled away */ - sp = (unsigned long) (®s->sp); - savesegment(ss, ss); - if (user_mode(regs)) { - sp = regs->sp; - ss = regs->ss & 0xffff; } - printk(KERN_EMERG "EIP: [<%08lx>] ", regs->ip); - print_symbol("%s", regs->ip); - printk(" SS:ESP %04x:%08lx\n", ss, sp); - return 0; -} - -/* - * This is gone through when something in the kernel has done something bad - * and is about to be terminated: - */ -void die(const char *str, struct pt_regs *regs, long err) -{ - unsigned long flags = oops_begin(); - - if (die_nest_count < 3) { - report_bug(regs->ip, regs); - - if (__die(str, regs, err)) - regs = NULL; - } else { - printk(KERN_EMERG "Recursive die() failure, output suppressed\n"); - } - - oops_end(flags, regs, SIGSEGV); -} + put_cpu(); -static inline void -die_if_kernel(const char *str, struct pt_regs *regs, long err) -{ - if (!user_mode_vm(regs)) - die(str, regs, err); + return 0; } +#endif static void __kprobes -do_trap(int trapnr, int signr, char *str, int vm86, struct pt_regs *regs, +do_trap(int trapnr, int signr, char *str, struct pt_regs *regs, long error_code, siginfo_t *info) { struct task_struct *tsk = current; +#ifdef CONFIG_X86_32 if (regs->flags & X86_VM_MASK) { - if (vm86) + /* + * traps 0, 1, 3, 4, and 5 should be forwarded to vm86. + * On nmi (interrupt 2), do_trap should not be called. + */ + if (trapnr < 6) goto vm86_trap; goto trap_signal; } +#endif if (!user_mode(regs)) goto kernel_trap; +#ifdef CONFIG_X86_32 trap_signal: +#endif /* * We want error_code and trap_no set for userspace faults and * kernelspace faults which result in die(), but not @@ -501,6 +197,18 @@ trap_signal: tsk->thread.error_code = error_code; tsk->thread.trap_no = trapnr; +#ifdef CONFIG_X86_64 + if (show_unhandled_signals && unhandled_signal(tsk, signr) && + printk_ratelimit()) { + printk(KERN_INFO + "%s[%d] trap %s ip:%lx sp:%lx error:%lx", + tsk->comm, tsk->pid, str, + regs->ip, regs->sp, error_code); + print_vma_addr(" in ", regs->ip); + printk("\n"); + } +#endif + if (info) force_sig_info(signr, info, tsk); else @@ -515,29 +223,29 @@ kernel_trap: } return; +#ifdef CONFIG_X86_32 vm86_trap: if (handle_vm86_trap((struct kernel_vm86_regs *) regs, error_code, trapnr)) goto trap_signal; return; +#endif } #define DO_ERROR(trapnr, signr, str, name) \ -void do_##name(struct pt_regs *regs, long error_code) \ +dotraplinkage void do_##name(struct pt_regs *regs, long error_code) \ { \ - trace_hardirqs_fixup(); \ if (notify_die(DIE_TRAP, str, regs, error_code, trapnr, signr) \ == NOTIFY_STOP) \ return; \ - do_trap(trapnr, signr, str, 0, regs, error_code, NULL); \ + conditional_sti(regs); \ + do_trap(trapnr, signr, str, regs, error_code, NULL); \ } -#define DO_ERROR_INFO(trapnr, signr, str, name, sicode, siaddr, irq) \ -void do_##name(struct pt_regs *regs, long error_code) \ +#define DO_ERROR_INFO(trapnr, signr, str, name, sicode, siaddr) \ +dotraplinkage void do_##name(struct pt_regs *regs, long error_code) \ { \ siginfo_t info; \ - if (irq) \ - local_irq_enable(); \ info.si_signo = signr; \ info.si_errno = 0; \ info.si_code = sicode; \ @@ -545,90 +253,68 @@ void do_##name(struct pt_regs *regs, long error_code) \ if (notify_die(DIE_TRAP, str, regs, error_code, trapnr, signr) \ == NOTIFY_STOP) \ return; \ - do_trap(trapnr, signr, str, 0, regs, error_code, &info); \ + conditional_sti(regs); \ + do_trap(trapnr, signr, str, regs, error_code, &info); \ } -#define DO_VM86_ERROR(trapnr, signr, str, name) \ -void do_##name(struct pt_regs *regs, long error_code) \ -{ \ - if (notify_die(DIE_TRAP, str, regs, error_code, trapnr, signr) \ - == NOTIFY_STOP) \ - return; \ - do_trap(trapnr, signr, str, 1, regs, error_code, NULL); \ -} - -#define DO_VM86_ERROR_INFO(trapnr, signr, str, name, sicode, siaddr) \ -void do_##name(struct pt_regs *regs, long error_code) \ -{ \ - siginfo_t info; \ - info.si_signo = signr; \ - info.si_errno = 0; \ - info.si_code = sicode; \ - info.si_addr = (void __user *)siaddr; \ - trace_hardirqs_fixup(); \ - if (notify_die(DIE_TRAP, str, regs, error_code, trapnr, signr) \ - == NOTIFY_STOP) \ - return; \ - do_trap(trapnr, signr, str, 1, regs, error_code, &info); \ -} - -DO_VM86_ERROR_INFO(0, SIGFPE, "divide error", divide_error, FPE_INTDIV, regs->ip) -#ifndef CONFIG_KPROBES -DO_VM86_ERROR(3, SIGTRAP, "int3", int3) -#endif -DO_VM86_ERROR(4, SIGSEGV, "overflow", overflow) -DO_VM86_ERROR(5, SIGSEGV, "bounds", bounds) -DO_ERROR_INFO(6, SIGILL, "invalid opcode", invalid_op, ILL_ILLOPN, regs->ip, 0) +DO_ERROR_INFO(0, SIGFPE, "divide error", divide_error, FPE_INTDIV, regs->ip) +DO_ERROR(4, SIGSEGV, "overflow", overflow) +DO_ERROR(5, SIGSEGV, "bounds", bounds) +DO_ERROR_INFO(6, SIGILL, "invalid opcode", invalid_op, ILL_ILLOPN, regs->ip) DO_ERROR(9, SIGFPE, "coprocessor segment overrun", coprocessor_segment_overrun) DO_ERROR(10, SIGSEGV, "invalid TSS", invalid_TSS) DO_ERROR(11, SIGBUS, "segment not present", segment_not_present) +#ifdef CONFIG_X86_32 DO_ERROR(12, SIGBUS, "stack segment", stack_segment) -DO_ERROR_INFO(17, SIGBUS, "alignment check", alignment_check, BUS_ADRALN, 0, 0) -DO_ERROR_INFO(32, SIGILL, "iret exception", iret_error, ILL_BADSTK, 0, 1) +#endif +DO_ERROR_INFO(17, SIGBUS, "alignment check", alignment_check, BUS_ADRALN, 0) + +#ifdef CONFIG_X86_64 +/* Runs on IST stack */ +dotraplinkage void do_stack_segment(struct pt_regs *regs, long error_code) +{ + if (notify_die(DIE_TRAP, "stack segment", regs, error_code, + 12, SIGBUS) == NOTIFY_STOP) + return; + preempt_conditional_sti(regs); + do_trap(12, SIGBUS, "stack segment", regs, error_code, NULL); + preempt_conditional_cli(regs); +} + +dotraplinkage void do_double_fault(struct pt_regs *regs, long error_code) +{ + static const char str[] = "double fault"; + struct task_struct *tsk = current; + + /* Return not checked because double check cannot be ignored */ + notify_die(DIE_TRAP, str, regs, error_code, 8, SIGSEGV); -void __kprobes + tsk->thread.error_code = error_code; + tsk->thread.trap_no = 8; + + /* This is always a kernel trap and never fixable (and thus must + never return). */ + for (;;) + die(str, regs, error_code); +} +#endif + +dotraplinkage void __kprobes do_general_protection(struct pt_regs *regs, long error_code) { struct task_struct *tsk; - struct thread_struct *thread; - struct tss_struct *tss; - int cpu; - cpu = get_cpu(); - tss = &per_cpu(init_tss, cpu); - thread = ¤t->thread; - - /* - * Perform the lazy TSS's I/O bitmap copy. If the TSS has an - * invalid offset set (the LAZY one) and the faulting thread has - * a valid I/O bitmap pointer, we copy the I/O bitmap in the TSS - * and we set the offset field correctly. Then we let the CPU to - * restart the faulting instruction. - */ - if (tss->x86_tss.io_bitmap_base == INVALID_IO_BITMAP_OFFSET_LAZY && - thread->io_bitmap_ptr) { - memcpy(tss->io_bitmap, thread->io_bitmap_ptr, - thread->io_bitmap_max); - /* - * If the previously set map was extending to higher ports - * than the current one, pad extra space with 0xff (no access). - */ - if (thread->io_bitmap_max < tss->io_bitmap_max) { - memset((char *) tss->io_bitmap + - thread->io_bitmap_max, 0xff, - tss->io_bitmap_max - thread->io_bitmap_max); - } - tss->io_bitmap_max = thread->io_bitmap_max; - tss->x86_tss.io_bitmap_base = IO_BITMAP_OFFSET; - tss->io_bitmap_owner = thread; - put_cpu(); + conditional_sti(regs); +#ifdef CONFIG_X86_32 + if (lazy_iobitmap_copy()) { + /* restart the faulting instruction */ return; } - put_cpu(); if (regs->flags & X86_VM_MASK) goto gp_in_vm86; +#endif tsk = current; if (!user_mode(regs)) @@ -650,10 +336,12 @@ do_general_protection(struct pt_regs *regs, long error_code) force_sig(SIGSEGV, tsk); return; +#ifdef CONFIG_X86_32 gp_in_vm86: local_irq_enable(); handle_vm86_fault((struct kernel_vm86_regs *) regs, error_code); return; +#endif gp_in_kernel: if (fixup_exception(regs)) @@ -690,7 +378,8 @@ mem_parity_error(unsigned char reason, struct pt_regs *regs) printk(KERN_EMERG "Dazed and confused, but trying to continue\n"); /* Clear and disable the memory parity error line. */ - clear_mem_error(reason); + reason = (reason & 0xf) | 4; + outb(reason, 0x61); } static notrace __kprobes void @@ -716,7 +405,8 @@ io_check_error(unsigned char reason, struct pt_regs *regs) static notrace __kprobes void unknown_nmi_error(unsigned char reason, struct pt_regs *regs) { - if (notify_die(DIE_NMIUNKNOWN, "nmi", regs, reason, 2, SIGINT) == NOTIFY_STOP) + if (notify_die(DIE_NMIUNKNOWN, "nmi", regs, reason, 2, SIGINT) == + NOTIFY_STOP) return; #ifdef CONFIG_MCA /* @@ -739,41 +429,6 @@ unknown_nmi_error(unsigned char reason, struct pt_regs *regs) printk(KERN_EMERG "Dazed and confused, but trying to continue\n"); } -static DEFINE_SPINLOCK(nmi_print_lock); - -void notrace __kprobes die_nmi(char *str, struct pt_regs *regs, int do_panic) -{ - if (notify_die(DIE_NMIWATCHDOG, str, regs, 0, 2, SIGINT) == NOTIFY_STOP) - return; - - spin_lock(&nmi_print_lock); - /* - * We are in trouble anyway, lets at least try - * to get a message out: - */ - bust_spinlocks(1); - printk(KERN_EMERG "%s", str); - printk(" on CPU%d, ip %08lx, registers:\n", - smp_processor_id(), regs->ip); - show_registers(regs); - if (do_panic) - panic("Non maskable interrupt"); - console_silent(); - spin_unlock(&nmi_print_lock); - bust_spinlocks(0); - - /* - * If we are in kernel we are probably nested up pretty bad - * and might aswell get out now while we still can: - */ - if (!user_mode_vm(regs)) { - current->thread.trap_no = 2; - crash_kexec(regs); - } - - do_exit(SIGSEGV); -} - static notrace __kprobes void default_do_nmi(struct pt_regs *regs) { unsigned char reason = 0; @@ -812,22 +467,25 @@ static notrace __kprobes void default_do_nmi(struct pt_regs *regs) mem_parity_error(reason, regs); if (reason & 0x40) io_check_error(reason, regs); +#ifdef CONFIG_X86_32 /* * Reassert NMI in case it became active meanwhile * as it's edge-triggered: */ reassert_nmi(); +#endif } -notrace __kprobes void do_nmi(struct pt_regs *regs, long error_code) +dotraplinkage notrace __kprobes void +do_nmi(struct pt_regs *regs, long error_code) { - int cpu; - nmi_enter(); - cpu = smp_processor_id(); - - ++nmi_count(cpu); +#ifdef CONFIG_X86_32 + { int cpu; cpu = smp_processor_id(); ++nmi_count(cpu); } +#else + add_pda(__nmi_count, 1); +#endif if (!ignore_nmis) default_do_nmi(regs); @@ -847,21 +505,44 @@ void restart_nmi(void) acpi_nmi_enable(); } -#ifdef CONFIG_KPROBES -void __kprobes do_int3(struct pt_regs *regs, long error_code) +/* May run on IST stack. */ +dotraplinkage void __kprobes do_int3(struct pt_regs *regs, long error_code) { - trace_hardirqs_fixup(); - +#ifdef CONFIG_KPROBES if (notify_die(DIE_INT3, "int3", regs, error_code, 3, SIGTRAP) == NOTIFY_STOP) return; - /* - * This is an interrupt gate, because kprobes wants interrupts - * disabled. Normal trap handlers don't. - */ - restore_interrupts(regs); +#else + if (notify_die(DIE_TRAP, "int3", regs, error_code, 3, SIGTRAP) + == NOTIFY_STOP) + return; +#endif + + preempt_conditional_sti(regs); + do_trap(3, SIGTRAP, "int3", regs, error_code, NULL); + preempt_conditional_cli(regs); +} - do_trap(3, SIGTRAP, "int3", 1, regs, error_code, NULL); +#ifdef CONFIG_X86_64 +/* Help handler running on IST stack to switch back to user stack + for scheduling or signal handling. The actual stack switch is done in + entry.S */ +asmlinkage __kprobes struct pt_regs *sync_regs(struct pt_regs *eregs) +{ + struct pt_regs *regs = eregs; + /* Did already sync */ + if (eregs == (struct pt_regs *)eregs->sp) + ; + /* Exception from user space */ + else if (user_mode(eregs)) + regs = task_pt_regs(current); + /* Exception from kernel and interrupts are enabled. Move to + kernel process stack. */ + else if (eregs->flags & X86_EFLAGS_IF) + regs = (struct pt_regs *)(eregs->sp -= sizeof(struct pt_regs)); + if (eregs != regs) + *regs = *eregs; + return regs; } #endif @@ -886,15 +567,15 @@ void __kprobes do_int3(struct pt_regs *regs, long error_code) * about restoring all the debug state, and ptrace doesn't have to * find every occurrence of the TF bit that could be saved away even * by user code) + * + * May run on IST stack. */ -void __kprobes do_debug(struct pt_regs *regs, long error_code) +dotraplinkage void __kprobes do_debug(struct pt_regs *regs, long error_code) { struct task_struct *tsk = current; - unsigned int condition; + unsigned long condition; int si_code; - trace_hardirqs_fixup(); - get_debugreg(condition, 6); /* @@ -906,9 +587,9 @@ void __kprobes do_debug(struct pt_regs *regs, long error_code) if (notify_die(DIE_DEBUG, "debug", regs, condition, error_code, SIGTRAP) == NOTIFY_STOP) return; + /* It's safe to allow irq's after DR6 has been saved */ - if (regs->flags & X86_EFLAGS_IF) - local_irq_enable(); + preempt_conditional_sti(regs); /* Mask out spurious debug traps due to lazy DR7 setting */ if (condition & (DR_TRAP0|DR_TRAP1|DR_TRAP2|DR_TRAP3)) { @@ -916,8 +597,10 @@ void __kprobes do_debug(struct pt_regs *regs, long error_code) goto clear_dr7; } +#ifdef CONFIG_X86_32 if (regs->flags & X86_VM_MASK) goto debug_vm86; +#endif /* Save debug status register where ptrace can see it */ tsk->thread.debugreg6 = condition; @@ -927,16 +610,11 @@ void __kprobes do_debug(struct pt_regs *regs, long error_code) * kernel space (but re-enable TF when returning to user mode). */ if (condition & DR_STEP) { - /* - * We already checked v86 mode above, so we can - * check for kernel mode by just checking the CPL - * of CS. - */ if (!user_mode(regs)) goto clear_TF_reenable; } - si_code = get_si_code((unsigned long)condition); + si_code = get_si_code(condition); /* Ok, finally something we can handle */ send_sigtrap(tsk, regs, error_code, si_code); @@ -946,18 +624,37 @@ void __kprobes do_debug(struct pt_regs *regs, long error_code) */ clear_dr7: set_debugreg(0, 7); + preempt_conditional_cli(regs); return; +#ifdef CONFIG_X86_32 debug_vm86: handle_vm86_trap((struct kernel_vm86_regs *) regs, error_code, 1); + preempt_conditional_cli(regs); return; +#endif clear_TF_reenable: set_tsk_thread_flag(tsk, TIF_SINGLESTEP); regs->flags &= ~X86_EFLAGS_TF; + preempt_conditional_cli(regs); return; } +#ifdef CONFIG_X86_64 +static int kernel_math_error(struct pt_regs *regs, const char *str, int trapnr) +{ + if (fixup_exception(regs)) + return 1; + + notify_die(DIE_GPF, str, regs, 0, trapnr, SIGFPE); + /* Illegal floating point operation in the kernel */ + current->thread.trap_no = trapnr; + die(str, regs, 0); + return 0; +} +#endif + /* * Note that we play around with the 'TS' bit in an attempt to get * the correct behaviour even in the presence of the asynchronous @@ -994,7 +691,9 @@ void math_error(void __user *ip) swd = get_fpu_swd(task); switch (swd & ~cwd & 0x3f) { case 0x000: /* No unmasked exception */ +#ifdef CONFIG_X86_32 return; +#endif default: /* Multiple exceptions */ break; case 0x001: /* Invalid Op */ @@ -1022,9 +721,18 @@ void math_error(void __user *ip) force_sig_info(SIGFPE, &info, task); } -void do_coprocessor_error(struct pt_regs *regs, long error_code) +dotraplinkage void do_coprocessor_error(struct pt_regs *regs, long error_code) { + conditional_sti(regs); + +#ifdef CONFIG_X86_32 ignore_fpu_irq = 1; +#else + if (!user_mode(regs) && + kernel_math_error(regs, "kernel x87 math error", 16)) + return; +#endif + math_error((void __user *)regs->ip); } @@ -1076,8 +784,12 @@ static void simd_math_error(void __user *ip) force_sig_info(SIGFPE, &info, task); } -void do_simd_coprocessor_error(struct pt_regs *regs, long error_code) +dotraplinkage void +do_simd_coprocessor_error(struct pt_regs *regs, long error_code) { + conditional_sti(regs); + +#ifdef CONFIG_X86_32 if (cpu_has_xmm) { /* Handle SIMD FPU exceptions on PIII+ processors. */ ignore_fpu_irq = 1; @@ -1096,16 +808,25 @@ void do_simd_coprocessor_error(struct pt_regs *regs, long error_code) current->thread.error_code = error_code; die_if_kernel("cache flush denied", regs, error_code); force_sig(SIGSEGV, current); +#else + if (!user_mode(regs) && + kernel_math_error(regs, "kernel simd math error", 19)) + return; + simd_math_error((void __user *)regs->ip); +#endif } -void do_spurious_interrupt_bug(struct pt_regs *regs, long error_code) +dotraplinkage void +do_spurious_interrupt_bug(struct pt_regs *regs, long error_code) { + conditional_sti(regs); #if 0 /* No need to warn about this any longer. */ printk(KERN_INFO "Ignoring P6 Local APIC Spurious Interrupt Bug...\n"); #endif } +#ifdef CONFIG_X86_32 unsigned long patch_espfix_desc(unsigned long uesp, unsigned long kesp) { struct desc_struct *gdt = get_cpu_gdt_table(smp_processor_id()); @@ -1124,6 +845,15 @@ unsigned long patch_espfix_desc(unsigned long uesp, unsigned long kesp) return new_kesp; } +#else +asmlinkage void __attribute__((weak)) smp_thermal_interrupt(void) +{ +} + +asmlinkage void __attribute__((weak)) mce_threshold_interrupt(void) +{ +} +#endif /* * 'math_state_restore()' saves the current math information in the @@ -1156,14 +886,24 @@ asmlinkage void math_state_restore(void) } clts(); /* Allow maths ops (or we recurse) */ +#ifdef CONFIG_X86_32 restore_fpu(tsk); +#else + /* + * Paranoid restore. send a SIGSEGV if we fail to restore the state. + */ + if (unlikely(restore_fpu_checking(tsk))) { + stts(); + force_sig(SIGSEGV, tsk); + return; + } +#endif thread->status |= TS_USEDFPU; /* So we fnsave on switch_to() */ tsk->fpu_counter++; } EXPORT_SYMBOL_GPL(math_state_restore); #ifndef CONFIG_MATH_EMULATION - asmlinkage void math_emulate(long arg) { printk(KERN_EMERG @@ -1172,12 +912,54 @@ asmlinkage void math_emulate(long arg) force_sig(SIGFPE, current); schedule(); } - #endif /* CONFIG_MATH_EMULATION */ +dotraplinkage void __kprobes +do_device_not_available(struct pt_regs *regs, long error) +{ +#ifdef CONFIG_X86_32 + if (read_cr0() & X86_CR0_EM) { + conditional_sti(regs); + math_emulate(0); + } else { + math_state_restore(); /* interrupts still off */ + conditional_sti(regs); + } +#else + math_state_restore(); +#endif +} + +#ifdef CONFIG_X86_32 +#ifdef CONFIG_X86_MCE +dotraplinkage void __kprobes do_machine_check(struct pt_regs *regs, long error) +{ + conditional_sti(regs); + machine_check_vector(regs, error); +} +#endif + +dotraplinkage void do_iret_error(struct pt_regs *regs, long error_code) +{ + siginfo_t info; + local_irq_enable(); + + info.si_signo = SIGILL; + info.si_errno = 0; + info.si_code = ILL_BADSTK; + info.si_addr = 0; + if (notify_die(DIE_TRAP, "iret exception", + regs, error_code, 32, SIGILL) == NOTIFY_STOP) + return; + do_trap(32, SIGILL, "iret exception", regs, error_code, &info); +} +#endif + void __init trap_init(void) { +#ifdef CONFIG_X86_32 int i; +#endif #ifdef CONFIG_EISA void __iomem *p = early_ioremap(0x0FFFD9, 4); @@ -1187,29 +969,40 @@ void __init trap_init(void) early_iounmap(p, 4); #endif - set_trap_gate(0, ÷_error); - set_intr_gate(1, &debug); - set_intr_gate(2, &nmi); - set_system_intr_gate(3, &int3); /* int3 can be called from all */ - set_system_gate(4, &overflow); /* int4 can be called from all */ - set_trap_gate(5, &bounds); - set_trap_gate(6, &invalid_op); - set_trap_gate(7, &device_not_available); + set_intr_gate(0, ÷_error); + set_intr_gate_ist(1, &debug, DEBUG_STACK); + set_intr_gate_ist(2, &nmi, NMI_STACK); + /* int3 can be called from all */ + set_system_intr_gate_ist(3, &int3, DEBUG_STACK); + /* int4 can be called from all */ + set_system_intr_gate(4, &overflow); + set_intr_gate(5, &bounds); + set_intr_gate(6, &invalid_op); + set_intr_gate(7, &device_not_available); +#ifdef CONFIG_X86_32 set_task_gate(8, GDT_ENTRY_DOUBLEFAULT_TSS); - set_trap_gate(9, &coprocessor_segment_overrun); - set_trap_gate(10, &invalid_TSS); - set_trap_gate(11, &segment_not_present); - set_trap_gate(12, &stack_segment); - set_trap_gate(13, &general_protection); +#else + set_intr_gate_ist(8, &double_fault, DOUBLEFAULT_STACK); +#endif + set_intr_gate(9, &coprocessor_segment_overrun); + set_intr_gate(10, &invalid_TSS); + set_intr_gate(11, &segment_not_present); + set_intr_gate_ist(12, &stack_segment, STACKFAULT_STACK); + set_intr_gate(13, &general_protection); set_intr_gate(14, &page_fault); - set_trap_gate(15, &spurious_interrupt_bug); - set_trap_gate(16, &coprocessor_error); - set_trap_gate(17, &alignment_check); + set_intr_gate(15, &spurious_interrupt_bug); + set_intr_gate(16, &coprocessor_error); + set_intr_gate(17, &alignment_check); #ifdef CONFIG_X86_MCE - set_trap_gate(18, &machine_check); + set_intr_gate_ist(18, &machine_check, MCE_STACK); #endif - set_trap_gate(19, &simd_coprocessor_error); + set_intr_gate(19, &simd_coprocessor_error); +#ifdef CONFIG_IA32_EMULATION + set_system_intr_gate(IA32_SYSCALL_VECTOR, ia32_syscall); +#endif + +#ifdef CONFIG_X86_32 if (cpu_has_fxsr) { printk(KERN_INFO "Enabling fast FPU save and restore... "); set_in_cr4(X86_CR4_OSFXSR); @@ -1222,36 +1015,20 @@ void __init trap_init(void) printk("done.\n"); } - set_system_gate(SYSCALL_VECTOR, &system_call); + set_system_trap_gate(SYSCALL_VECTOR, &system_call); /* Reserve all the builtin and the syscall vector: */ for (i = 0; i < FIRST_EXTERNAL_VECTOR; i++) set_bit(i, used_vectors); set_bit(SYSCALL_VECTOR, used_vectors); - +#endif /* * Should be a barrier for any external CPU state: */ cpu_init(); +#ifdef CONFIG_X86_32 trap_init_hook(); +#endif } - -static int __init kstack_setup(char *s) -{ - kstack_depth_to_print = simple_strtoul(s, NULL, 0); - - return 1; -} -__setup("kstack=", kstack_setup); - -static int __init code_bytes_setup(char *s) -{ - code_bytes = simple_strtoul(s, NULL, 0); - if (code_bytes > 8192) - code_bytes = 8192; - - return 1; -} -__setup("code_bytes=", code_bytes_setup); diff --git a/arch/x86/kernel/traps_64.c b/arch/x86/kernel/traps_64.c deleted file mode 100644 index 9c0ac0cab013..000000000000 --- a/arch/x86/kernel/traps_64.c +++ /dev/null @@ -1,1214 +0,0 @@ -/* - * Copyright (C) 1991, 1992 Linus Torvalds - * Copyright (C) 2000, 2001, 2002 Andi Kleen, SuSE Labs - * - * Pentium III FXSR, SSE support - * Gareth Hughes <gareth@valinux.com>, May 2000 - */ - -/* - * 'Traps.c' handles hardware traps and faults after we have saved some - * state in 'entry.S'. - */ -#include <linux/moduleparam.h> -#include <linux/interrupt.h> -#include <linux/kallsyms.h> -#include <linux/spinlock.h> -#include <linux/kprobes.h> -#include <linux/uaccess.h> -#include <linux/utsname.h> -#include <linux/kdebug.h> -#include <linux/kernel.h> -#include <linux/module.h> -#include <linux/ptrace.h> -#include <linux/string.h> -#include <linux/unwind.h> -#include <linux/delay.h> -#include <linux/errno.h> -#include <linux/kexec.h> -#include <linux/sched.h> -#include <linux/timer.h> -#include <linux/init.h> -#include <linux/bug.h> -#include <linux/nmi.h> -#include <linux/mm.h> -#include <linux/smp.h> -#include <linux/io.h> - -#if defined(CONFIG_EDAC) -#include <linux/edac.h> -#endif - -#include <asm/stacktrace.h> -#include <asm/processor.h> -#include <asm/debugreg.h> -#include <asm/atomic.h> -#include <asm/system.h> -#include <asm/unwind.h> -#include <asm/desc.h> -#include <asm/i387.h> -#include <asm/pgalloc.h> -#include <asm/proto.h> -#include <asm/pda.h> -#include <asm/traps.h> - -#include <mach_traps.h> - -int panic_on_unrecovered_nmi; -int kstack_depth_to_print = 12; -static unsigned int code_bytes = 64; -static int ignore_nmis; -static int die_counter; - -static inline void conditional_sti(struct pt_regs *regs) -{ - if (regs->flags & X86_EFLAGS_IF) - local_irq_enable(); -} - -static inline void preempt_conditional_sti(struct pt_regs *regs) -{ - inc_preempt_count(); - if (regs->flags & X86_EFLAGS_IF) - local_irq_enable(); -} - -static inline void preempt_conditional_cli(struct pt_regs *regs) -{ - if (regs->flags & X86_EFLAGS_IF) - local_irq_disable(); - /* Make sure to not schedule here because we could be running - on an exception stack. */ - dec_preempt_count(); -} - -void printk_address(unsigned long address, int reliable) -{ - printk(" [<%016lx>] %s%pS\n", - address, reliable ? "" : "? ", (void *) address); -} - -static unsigned long *in_exception_stack(unsigned cpu, unsigned long stack, - unsigned *usedp, char **idp) -{ - static char ids[][8] = { - [DEBUG_STACK - 1] = "#DB", - [NMI_STACK - 1] = "NMI", - [DOUBLEFAULT_STACK - 1] = "#DF", - [STACKFAULT_STACK - 1] = "#SS", - [MCE_STACK - 1] = "#MC", -#if DEBUG_STKSZ > EXCEPTION_STKSZ - [N_EXCEPTION_STACKS ... - N_EXCEPTION_STACKS + DEBUG_STKSZ / EXCEPTION_STKSZ - 2] = "#DB[?]" -#endif - }; - unsigned k; - - /* - * Iterate over all exception stacks, and figure out whether - * 'stack' is in one of them: - */ - for (k = 0; k < N_EXCEPTION_STACKS; k++) { - unsigned long end = per_cpu(orig_ist, cpu).ist[k]; - /* - * Is 'stack' above this exception frame's end? - * If yes then skip to the next frame. - */ - if (stack >= end) - continue; - /* - * Is 'stack' above this exception frame's start address? - * If yes then we found the right frame. - */ - if (stack >= end - EXCEPTION_STKSZ) { - /* - * Make sure we only iterate through an exception - * stack once. If it comes up for the second time - * then there's something wrong going on - just - * break out and return NULL: - */ - if (*usedp & (1U << k)) - break; - *usedp |= 1U << k; - *idp = ids[k]; - return (unsigned long *)end; - } - /* - * If this is a debug stack, and if it has a larger size than - * the usual exception stacks, then 'stack' might still - * be within the lower portion of the debug stack: - */ -#if DEBUG_STKSZ > EXCEPTION_STKSZ - if (k == DEBUG_STACK - 1 && stack >= end - DEBUG_STKSZ) { - unsigned j = N_EXCEPTION_STACKS - 1; - - /* - * Black magic. A large debug stack is composed of - * multiple exception stack entries, which we - * iterate through now. Dont look: - */ - do { - ++j; - end -= EXCEPTION_STKSZ; - ids[j][4] = '1' + (j - N_EXCEPTION_STACKS); - } while (stack < end - EXCEPTION_STKSZ); - if (*usedp & (1U << j)) - break; - *usedp |= 1U << j; - *idp = ids[j]; - return (unsigned long *)end; - } -#endif - } - return NULL; -} - -/* - * x86-64 can have up to three kernel stacks: - * process stack - * interrupt stack - * severe exception (double fault, nmi, stack fault, debug, mce) hardware stack - */ - -static inline int valid_stack_ptr(struct thread_info *tinfo, - void *p, unsigned int size, void *end) -{ - void *t = tinfo; - if (end) { - if (p < end && p >= (end-THREAD_SIZE)) - return 1; - else - return 0; - } - return p > t && p < t + THREAD_SIZE - size; -} - -/* The form of the top of the frame on the stack */ -struct stack_frame { - struct stack_frame *next_frame; - unsigned long return_address; -}; - -static inline unsigned long -print_context_stack(struct thread_info *tinfo, - unsigned long *stack, unsigned long bp, - const struct stacktrace_ops *ops, void *data, - unsigned long *end) -{ - struct stack_frame *frame = (struct stack_frame *)bp; - - while (valid_stack_ptr(tinfo, stack, sizeof(*stack), end)) { - unsigned long addr; - - addr = *stack; - if (__kernel_text_address(addr)) { - if ((unsigned long) stack == bp + 8) { - ops->address(data, addr, 1); - frame = frame->next_frame; - bp = (unsigned long) frame; - } else { - ops->address(data, addr, bp == 0); - } - } - stack++; - } - return bp; -} - -void dump_trace(struct task_struct *task, struct pt_regs *regs, - unsigned long *stack, unsigned long bp, - const struct stacktrace_ops *ops, void *data) -{ - const unsigned cpu = get_cpu(); - unsigned long *irqstack_end = (unsigned long *)cpu_pda(cpu)->irqstackptr; - unsigned used = 0; - struct thread_info *tinfo; - - if (!task) - task = current; - - if (!stack) { - unsigned long dummy; - stack = &dummy; - if (task && task != current) - stack = (unsigned long *)task->thread.sp; - } - -#ifdef CONFIG_FRAME_POINTER - if (!bp) { - if (task == current) { - /* Grab bp right from our regs */ - asm("movq %%rbp, %0" : "=r" (bp) : ); - } else { - /* bp is the last reg pushed by switch_to */ - bp = *(unsigned long *) task->thread.sp; - } - } -#endif - - /* - * Print function call entries in all stacks, starting at the - * current stack address. If the stacks consist of nested - * exceptions - */ - tinfo = task_thread_info(task); - for (;;) { - char *id; - unsigned long *estack_end; - estack_end = in_exception_stack(cpu, (unsigned long)stack, - &used, &id); - - if (estack_end) { - if (ops->stack(data, id) < 0) - break; - - bp = print_context_stack(tinfo, stack, bp, ops, - data, estack_end); - ops->stack(data, "<EOE>"); - /* - * We link to the next stack via the - * second-to-last pointer (index -2 to end) in the - * exception stack: - */ - stack = (unsigned long *) estack_end[-2]; - continue; - } - if (irqstack_end) { - unsigned long *irqstack; - irqstack = irqstack_end - - (IRQSTACKSIZE - 64) / sizeof(*irqstack); - - if (stack >= irqstack && stack < irqstack_end) { - if (ops->stack(data, "IRQ") < 0) - break; - bp = print_context_stack(tinfo, stack, bp, - ops, data, irqstack_end); - /* - * We link to the next stack (which would be - * the process stack normally) the last - * pointer (index -1 to end) in the IRQ stack: - */ - stack = (unsigned long *) (irqstack_end[-1]); - irqstack_end = NULL; - ops->stack(data, "EOI"); - continue; - } - } - break; - } - - /* - * This handles the process stack: - */ - bp = print_context_stack(tinfo, stack, bp, ops, data, NULL); - put_cpu(); -} -EXPORT_SYMBOL(dump_trace); - -static void -print_trace_warning_symbol(void *data, char *msg, unsigned long symbol) -{ - print_symbol(msg, symbol); - printk("\n"); -} - -static void print_trace_warning(void *data, char *msg) -{ - printk("%s\n", msg); -} - -static int print_trace_stack(void *data, char *name) -{ - printk(" <%s> ", name); - return 0; -} - -static void print_trace_address(void *data, unsigned long addr, int reliable) -{ - touch_nmi_watchdog(); - printk_address(addr, reliable); -} - -static const struct stacktrace_ops print_trace_ops = { - .warning = print_trace_warning, - .warning_symbol = print_trace_warning_symbol, - .stack = print_trace_stack, - .address = print_trace_address, -}; - -static void -show_trace_log_lvl(struct task_struct *task, struct pt_regs *regs, - unsigned long *stack, unsigned long bp, char *log_lvl) -{ - printk("Call Trace:\n"); - dump_trace(task, regs, stack, bp, &print_trace_ops, log_lvl); -} - -void show_trace(struct task_struct *task, struct pt_regs *regs, - unsigned long *stack, unsigned long bp) -{ - show_trace_log_lvl(task, regs, stack, bp, ""); -} - -static void -show_stack_log_lvl(struct task_struct *task, struct pt_regs *regs, - unsigned long *sp, unsigned long bp, char *log_lvl) -{ - unsigned long *stack; - int i; - const int cpu = smp_processor_id(); - unsigned long *irqstack_end = - (unsigned long *) (cpu_pda(cpu)->irqstackptr); - unsigned long *irqstack = - (unsigned long *) (cpu_pda(cpu)->irqstackptr - IRQSTACKSIZE); - - /* - * debugging aid: "show_stack(NULL, NULL);" prints the - * back trace for this cpu. - */ - - if (sp == NULL) { - if (task) - sp = (unsigned long *)task->thread.sp; - else - sp = (unsigned long *)&sp; - } - - stack = sp; - for (i = 0; i < kstack_depth_to_print; i++) { - if (stack >= irqstack && stack <= irqstack_end) { - if (stack == irqstack_end) { - stack = (unsigned long *) (irqstack_end[-1]); - printk(" <EOI> "); - } - } else { - if (((long) stack & (THREAD_SIZE-1)) == 0) - break; - } - if (i && ((i % 4) == 0)) - printk("\n"); - printk(" %016lx", *stack++); - touch_nmi_watchdog(); - } - printk("\n"); - show_trace_log_lvl(task, regs, sp, bp, log_lvl); -} - -void show_stack(struct task_struct *task, unsigned long *sp) -{ - show_stack_log_lvl(task, NULL, sp, 0, ""); -} - -/* - * The architecture-independent dump_stack generator - */ -void dump_stack(void) -{ - unsigned long bp = 0; - unsigned long stack; - -#ifdef CONFIG_FRAME_POINTER - if (!bp) - asm("movq %%rbp, %0" : "=r" (bp) : ); -#endif - - printk("Pid: %d, comm: %.20s %s %s %.*s\n", - current->pid, current->comm, print_tainted(), - init_utsname()->release, - (int)strcspn(init_utsname()->version, " "), - init_utsname()->version); - show_trace(NULL, NULL, &stack, bp); -} -EXPORT_SYMBOL(dump_stack); - -void show_registers(struct pt_regs *regs) -{ - int i; - unsigned long sp; - const int cpu = smp_processor_id(); - struct task_struct *cur = cpu_pda(cpu)->pcurrent; - - sp = regs->sp; - printk("CPU %d ", cpu); - __show_regs(regs); - printk("Process %s (pid: %d, threadinfo %p, task %p)\n", - cur->comm, cur->pid, task_thread_info(cur), cur); - - /* - * When in-kernel, we also print out the stack and code at the - * time of the fault.. - */ - if (!user_mode(regs)) { - unsigned int code_prologue = code_bytes * 43 / 64; - unsigned int code_len = code_bytes; - unsigned char c; - u8 *ip; - - printk("Stack: "); - show_stack_log_lvl(NULL, regs, (unsigned long *)sp, - regs->bp, ""); - - printk(KERN_EMERG "Code: "); - - ip = (u8 *)regs->ip - code_prologue; - if (ip < (u8 *)PAGE_OFFSET || probe_kernel_address(ip, c)) { - /* try starting at RIP */ - ip = (u8 *)regs->ip; - code_len = code_len - code_prologue + 1; - } - for (i = 0; i < code_len; i++, ip++) { - if (ip < (u8 *)PAGE_OFFSET || - probe_kernel_address(ip, c)) { - printk(" Bad RIP value."); - break; - } - if (ip == (u8 *)regs->ip) - printk("<%02x> ", c); - else - printk("%02x ", c); - } - } - printk("\n"); -} - -int is_valid_bugaddr(unsigned long ip) -{ - unsigned short ud2; - - if (__copy_from_user(&ud2, (const void __user *) ip, sizeof(ud2))) - return 0; - - return ud2 == 0x0b0f; -} - -static raw_spinlock_t die_lock = __RAW_SPIN_LOCK_UNLOCKED; -static int die_owner = -1; -static unsigned int die_nest_count; - -unsigned __kprobes long oops_begin(void) -{ - int cpu; - unsigned long flags; - - oops_enter(); - - /* racy, but better than risking deadlock. */ - raw_local_irq_save(flags); - cpu = smp_processor_id(); - if (!__raw_spin_trylock(&die_lock)) { - if (cpu == die_owner) - /* nested oops. should stop eventually */; - else - __raw_spin_lock(&die_lock); - } - die_nest_count++; - die_owner = cpu; - console_verbose(); - bust_spinlocks(1); - return flags; -} - -void __kprobes oops_end(unsigned long flags, struct pt_regs *regs, int signr) -{ - die_owner = -1; - bust_spinlocks(0); - die_nest_count--; - if (!die_nest_count) - /* Nest count reaches zero, release the lock. */ - __raw_spin_unlock(&die_lock); - raw_local_irq_restore(flags); - if (!regs) { - oops_exit(); - return; - } - if (panic_on_oops) - panic("Fatal exception"); - oops_exit(); - do_exit(signr); -} - -int __kprobes __die(const char *str, struct pt_regs *regs, long err) -{ - printk(KERN_EMERG "%s: %04lx [%u] ", str, err & 0xffff, ++die_counter); -#ifdef CONFIG_PREEMPT - printk("PREEMPT "); -#endif -#ifdef CONFIG_SMP - printk("SMP "); -#endif -#ifdef CONFIG_DEBUG_PAGEALLOC - printk("DEBUG_PAGEALLOC"); -#endif - printk("\n"); - if (notify_die(DIE_OOPS, str, regs, err, - current->thread.trap_no, SIGSEGV) == NOTIFY_STOP) - return 1; - - show_registers(regs); - add_taint(TAINT_DIE); - /* Executive summary in case the oops scrolled away */ - printk(KERN_ALERT "RIP "); - printk_address(regs->ip, 1); - printk(" RSP <%016lx>\n", regs->sp); - if (kexec_should_crash(current)) - crash_kexec(regs); - return 0; -} - -void die(const char *str, struct pt_regs *regs, long err) -{ - unsigned long flags = oops_begin(); - - if (!user_mode(regs)) - report_bug(regs->ip, regs); - - if (__die(str, regs, err)) - regs = NULL; - oops_end(flags, regs, SIGSEGV); -} - -notrace __kprobes void -die_nmi(char *str, struct pt_regs *regs, int do_panic) -{ - unsigned long flags; - - if (notify_die(DIE_NMIWATCHDOG, str, regs, 0, 2, SIGINT) == NOTIFY_STOP) - return; - - flags = oops_begin(); - /* - * We are in trouble anyway, lets at least try - * to get a message out. - */ - printk(KERN_EMERG "%s", str); - printk(" on CPU%d, ip %08lx, registers:\n", - smp_processor_id(), regs->ip); - show_registers(regs); - if (kexec_should_crash(current)) - crash_kexec(regs); - if (do_panic || panic_on_oops) - panic("Non maskable interrupt"); - oops_end(flags, NULL, SIGBUS); - nmi_exit(); - local_irq_enable(); - do_exit(SIGBUS); -} - -static void __kprobes -do_trap(int trapnr, int signr, char *str, struct pt_regs *regs, - long error_code, siginfo_t *info) -{ - struct task_struct *tsk = current; - - if (!user_mode(regs)) - goto kernel_trap; - - /* - * We want error_code and trap_no set for userspace faults and - * kernelspace faults which result in die(), but not - * kernelspace faults which are fixed up. die() gives the - * process no chance to handle the signal and notice the - * kernel fault information, so that won't result in polluting - * the information about previously queued, but not yet - * delivered, faults. See also do_general_protection below. - */ - tsk->thread.error_code = error_code; - tsk->thread.trap_no = trapnr; - - if (show_unhandled_signals && unhandled_signal(tsk, signr) && - printk_ratelimit()) { - printk(KERN_INFO - "%s[%d] trap %s ip:%lx sp:%lx error:%lx", - tsk->comm, tsk->pid, str, - regs->ip, regs->sp, error_code); - print_vma_addr(" in ", regs->ip); - printk("\n"); - } - - if (info) - force_sig_info(signr, info, tsk); - else - force_sig(signr, tsk); - return; - -kernel_trap: - if (!fixup_exception(regs)) { - tsk->thread.error_code = error_code; - tsk->thread.trap_no = trapnr; - die(str, regs, error_code); - } - return; -} - -#define DO_ERROR(trapnr, signr, str, name) \ -asmlinkage void do_##name(struct pt_regs *regs, long error_code) \ -{ \ - if (notify_die(DIE_TRAP, str, regs, error_code, trapnr, signr) \ - == NOTIFY_STOP) \ - return; \ - conditional_sti(regs); \ - do_trap(trapnr, signr, str, regs, error_code, NULL); \ -} - -#define DO_ERROR_INFO(trapnr, signr, str, name, sicode, siaddr) \ -asmlinkage void do_##name(struct pt_regs *regs, long error_code) \ -{ \ - siginfo_t info; \ - info.si_signo = signr; \ - info.si_errno = 0; \ - info.si_code = sicode; \ - info.si_addr = (void __user *)siaddr; \ - trace_hardirqs_fixup(); \ - if (notify_die(DIE_TRAP, str, regs, error_code, trapnr, signr) \ - == NOTIFY_STOP) \ - return; \ - conditional_sti(regs); \ - do_trap(trapnr, signr, str, regs, error_code, &info); \ -} - -DO_ERROR_INFO(0, SIGFPE, "divide error", divide_error, FPE_INTDIV, regs->ip) -DO_ERROR(4, SIGSEGV, "overflow", overflow) -DO_ERROR(5, SIGSEGV, "bounds", bounds) -DO_ERROR_INFO(6, SIGILL, "invalid opcode", invalid_op, ILL_ILLOPN, regs->ip) -DO_ERROR(9, SIGFPE, "coprocessor segment overrun", coprocessor_segment_overrun) -DO_ERROR(10, SIGSEGV, "invalid TSS", invalid_TSS) -DO_ERROR(11, SIGBUS, "segment not present", segment_not_present) -DO_ERROR_INFO(17, SIGBUS, "alignment check", alignment_check, BUS_ADRALN, 0) - -/* Runs on IST stack */ -asmlinkage void do_stack_segment(struct pt_regs *regs, long error_code) -{ - if (notify_die(DIE_TRAP, "stack segment", regs, error_code, - 12, SIGBUS) == NOTIFY_STOP) - return; - preempt_conditional_sti(regs); - do_trap(12, SIGBUS, "stack segment", regs, error_code, NULL); - preempt_conditional_cli(regs); -} - -asmlinkage void do_double_fault(struct pt_regs *regs, long error_code) -{ - static const char str[] = "double fault"; - struct task_struct *tsk = current; - - /* Return not checked because double check cannot be ignored */ - notify_die(DIE_TRAP, str, regs, error_code, 8, SIGSEGV); - - tsk->thread.error_code = error_code; - tsk->thread.trap_no = 8; - - /* This is always a kernel trap and never fixable (and thus must - never return). */ - for (;;) - die(str, regs, error_code); -} - -asmlinkage void __kprobes -do_general_protection(struct pt_regs *regs, long error_code) -{ - struct task_struct *tsk; - - conditional_sti(regs); - - tsk = current; - if (!user_mode(regs)) - goto gp_in_kernel; - - tsk->thread.error_code = error_code; - tsk->thread.trap_no = 13; - - if (show_unhandled_signals && unhandled_signal(tsk, SIGSEGV) && - printk_ratelimit()) { - printk(KERN_INFO - "%s[%d] general protection ip:%lx sp:%lx error:%lx", - tsk->comm, tsk->pid, - regs->ip, regs->sp, error_code); - print_vma_addr(" in ", regs->ip); - printk("\n"); - } - - force_sig(SIGSEGV, tsk); - return; - -gp_in_kernel: - if (fixup_exception(regs)) - return; - - tsk->thread.error_code = error_code; - tsk->thread.trap_no = 13; - if (notify_die(DIE_GPF, "general protection fault", regs, - error_code, 13, SIGSEGV) == NOTIFY_STOP) - return; - die("general protection fault", regs, error_code); -} - -static notrace __kprobes void -mem_parity_error(unsigned char reason, struct pt_regs *regs) -{ - printk(KERN_EMERG "Uhhuh. NMI received for unknown reason %02x.\n", - reason); - printk(KERN_EMERG "You have some hardware problem, likely on the PCI bus.\n"); - -#if defined(CONFIG_EDAC) - if (edac_handler_set()) { - edac_atomic_assert_error(); - return; - } -#endif - - if (panic_on_unrecovered_nmi) - panic("NMI: Not continuing"); - - printk(KERN_EMERG "Dazed and confused, but trying to continue\n"); - - /* Clear and disable the memory parity error line. */ - reason = (reason & 0xf) | 4; - outb(reason, 0x61); -} - -static notrace __kprobes void -io_check_error(unsigned char reason, struct pt_regs *regs) -{ - printk("NMI: IOCK error (debug interrupt?)\n"); - show_registers(regs); - - /* Re-enable the IOCK line, wait for a few seconds */ - reason = (reason & 0xf) | 8; - outb(reason, 0x61); - mdelay(2000); - reason &= ~8; - outb(reason, 0x61); -} - -static notrace __kprobes void -unknown_nmi_error(unsigned char reason, struct pt_regs *regs) -{ - if (notify_die(DIE_NMIUNKNOWN, "nmi", regs, reason, 2, SIGINT) == - NOTIFY_STOP) - return; - printk(KERN_EMERG "Uhhuh. NMI received for unknown reason %02x.\n", - reason); - printk(KERN_EMERG "Do you have a strange power saving mode enabled?\n"); - - if (panic_on_unrecovered_nmi) - panic("NMI: Not continuing"); - - printk(KERN_EMERG "Dazed and confused, but trying to continue\n"); -} - -/* Runs on IST stack. This code must keep interrupts off all the time. - Nested NMIs are prevented by the CPU. */ -asmlinkage notrace __kprobes void default_do_nmi(struct pt_regs *regs) -{ - unsigned char reason = 0; - int cpu; - - cpu = smp_processor_id(); - - /* Only the BSP gets external NMIs from the system. */ - if (!cpu) - reason = get_nmi_reason(); - - if (!(reason & 0xc0)) { - if (notify_die(DIE_NMI_IPI, "nmi_ipi", regs, reason, 2, SIGINT) - == NOTIFY_STOP) - return; - /* - * Ok, so this is none of the documented NMI sources, - * so it must be the NMI watchdog. - */ - if (nmi_watchdog_tick(regs, reason)) - return; - if (!do_nmi_callback(regs, cpu)) - unknown_nmi_error(reason, regs); - - return; - } - if (notify_die(DIE_NMI, "nmi", regs, reason, 2, SIGINT) == NOTIFY_STOP) - return; - - /* AK: following checks seem to be broken on modern chipsets. FIXME */ - if (reason & 0x80) - mem_parity_error(reason, regs); - if (reason & 0x40) - io_check_error(reason, regs); -} - -asmlinkage notrace __kprobes void -do_nmi(struct pt_regs *regs, long error_code) -{ - nmi_enter(); - - add_pda(__nmi_count, 1); - - if (!ignore_nmis) - default_do_nmi(regs); - - nmi_exit(); -} - -void stop_nmi(void) -{ - acpi_nmi_disable(); - ignore_nmis++; -} - -void restart_nmi(void) -{ - ignore_nmis--; - acpi_nmi_enable(); -} - -/* runs on IST stack. */ -asmlinkage void __kprobes do_int3(struct pt_regs *regs, long error_code) -{ - trace_hardirqs_fixup(); - - if (notify_die(DIE_INT3, "int3", regs, error_code, 3, SIGTRAP) - == NOTIFY_STOP) - return; - - preempt_conditional_sti(regs); - do_trap(3, SIGTRAP, "int3", regs, error_code, NULL); - preempt_conditional_cli(regs); -} - -/* Help handler running on IST stack to switch back to user stack - for scheduling or signal handling. The actual stack switch is done in - entry.S */ -asmlinkage __kprobes struct pt_regs *sync_regs(struct pt_regs *eregs) -{ - struct pt_regs *regs = eregs; - /* Did already sync */ - if (eregs == (struct pt_regs *)eregs->sp) - ; - /* Exception from user space */ - else if (user_mode(eregs)) - regs = task_pt_regs(current); - /* Exception from kernel and interrupts are enabled. Move to - kernel process stack. */ - else if (eregs->flags & X86_EFLAGS_IF) - regs = (struct pt_regs *)(eregs->sp -= sizeof(struct pt_regs)); - if (eregs != regs) - *regs = *eregs; - return regs; -} - -/* runs on IST stack. */ -asmlinkage void __kprobes do_debug(struct pt_regs *regs, - unsigned long error_code) -{ - struct task_struct *tsk = current; - unsigned long condition; - siginfo_t info; - - trace_hardirqs_fixup(); - - get_debugreg(condition, 6); - - /* - * The processor cleared BTF, so don't mark that we need it set. - */ - clear_tsk_thread_flag(tsk, TIF_DEBUGCTLMSR); - tsk->thread.debugctlmsr = 0; - - if (notify_die(DIE_DEBUG, "debug", regs, condition, error_code, - SIGTRAP) == NOTIFY_STOP) - return; - - preempt_conditional_sti(regs); - - /* Mask out spurious debug traps due to lazy DR7 setting */ - if (condition & (DR_TRAP0|DR_TRAP1|DR_TRAP2|DR_TRAP3)) { - if (!tsk->thread.debugreg7) - goto clear_dr7; - } - - tsk->thread.debugreg6 = condition; - - /* - * Single-stepping through TF: make sure we ignore any events in - * kernel space (but re-enable TF when returning to user mode). - */ - if (condition & DR_STEP) { - if (!user_mode(regs)) - goto clear_TF_reenable; - } - - /* Ok, finally something we can handle */ - tsk->thread.trap_no = 1; - tsk->thread.error_code = error_code; - info.si_signo = SIGTRAP; - info.si_errno = 0; - info.si_code = get_si_code(condition); - info.si_addr = user_mode(regs) ? (void __user *)regs->ip : NULL; - force_sig_info(SIGTRAP, &info, tsk); - -clear_dr7: - set_debugreg(0, 7); - preempt_conditional_cli(regs); - return; - -clear_TF_reenable: - set_tsk_thread_flag(tsk, TIF_SINGLESTEP); - regs->flags &= ~X86_EFLAGS_TF; - preempt_conditional_cli(regs); - return; -} - -static int kernel_math_error(struct pt_regs *regs, const char *str, int trapnr) -{ - if (fixup_exception(regs)) - return 1; - - notify_die(DIE_GPF, str, regs, 0, trapnr, SIGFPE); - /* Illegal floating point operation in the kernel */ - current->thread.trap_no = trapnr; - die(str, regs, 0); - return 0; -} - -/* - * Note that we play around with the 'TS' bit in an attempt to get - * the correct behaviour even in the presence of the asynchronous - * IRQ13 behaviour - */ -asmlinkage void do_coprocessor_error(struct pt_regs *regs) -{ - void __user *ip = (void __user *)(regs->ip); - struct task_struct *task; - siginfo_t info; - unsigned short cwd, swd; - - conditional_sti(regs); - if (!user_mode(regs) && - kernel_math_error(regs, "kernel x87 math error", 16)) - return; - - /* - * Save the info for the exception handler and clear the error. - */ - task = current; - save_init_fpu(task); - task->thread.trap_no = 16; - task->thread.error_code = 0; - info.si_signo = SIGFPE; - info.si_errno = 0; - info.si_code = __SI_FAULT; - info.si_addr = ip; - /* - * (~cwd & swd) will mask out exceptions that are not set to unmasked - * status. 0x3f is the exception bits in these regs, 0x200 is the - * C1 reg you need in case of a stack fault, 0x040 is the stack - * fault bit. We should only be taking one exception at a time, - * so if this combination doesn't produce any single exception, - * then we have a bad program that isn't synchronizing its FPU usage - * and it will suffer the consequences since we won't be able to - * fully reproduce the context of the exception - */ - cwd = get_fpu_cwd(task); - swd = get_fpu_swd(task); - switch (swd & ~cwd & 0x3f) { - case 0x000: /* No unmasked exception */ - default: /* Multiple exceptions */ - break; - case 0x001: /* Invalid Op */ - /* - * swd & 0x240 == 0x040: Stack Underflow - * swd & 0x240 == 0x240: Stack Overflow - * User must clear the SF bit (0x40) if set - */ - info.si_code = FPE_FLTINV; - break; - case 0x002: /* Denormalize */ - case 0x010: /* Underflow */ - info.si_code = FPE_FLTUND; - break; - case 0x004: /* Zero Divide */ - info.si_code = FPE_FLTDIV; - break; - case 0x008: /* Overflow */ - info.si_code = FPE_FLTOVF; - break; - case 0x020: /* Precision */ - info.si_code = FPE_FLTRES; - break; - } - force_sig_info(SIGFPE, &info, task); -} - -asmlinkage void bad_intr(void) -{ - printk("bad interrupt"); -} - -asmlinkage void do_simd_coprocessor_error(struct pt_regs *regs) -{ - void __user *ip = (void __user *)(regs->ip); - struct task_struct *task; - siginfo_t info; - unsigned short mxcsr; - - conditional_sti(regs); - if (!user_mode(regs) && - kernel_math_error(regs, "kernel simd math error", 19)) - return; - - /* - * Save the info for the exception handler and clear the error. - */ - task = current; - save_init_fpu(task); - task->thread.trap_no = 19; - task->thread.error_code = 0; - info.si_signo = SIGFPE; - info.si_errno = 0; - info.si_code = __SI_FAULT; - info.si_addr = ip; - /* - * The SIMD FPU exceptions are handled a little differently, as there - * is only a single status/control register. Thus, to determine which - * unmasked exception was caught we must mask the exception mask bits - * at 0x1f80, and then use these to mask the exception bits at 0x3f. - */ - mxcsr = get_fpu_mxcsr(task); - switch (~((mxcsr & 0x1f80) >> 7) & (mxcsr & 0x3f)) { - case 0x000: - default: - break; - case 0x001: /* Invalid Op */ - info.si_code = FPE_FLTINV; - break; - case 0x002: /* Denormalize */ - case 0x010: /* Underflow */ - info.si_code = FPE_FLTUND; - break; - case 0x004: /* Zero Divide */ - info.si_code = FPE_FLTDIV; - break; - case 0x008: /* Overflow */ - info.si_code = FPE_FLTOVF; - break; - case 0x020: /* Precision */ - info.si_code = FPE_FLTRES; - break; - } - force_sig_info(SIGFPE, &info, task); -} - -asmlinkage void do_spurious_interrupt_bug(struct pt_regs *regs) -{ -} - -asmlinkage void __attribute__((weak)) smp_thermal_interrupt(void) -{ -} - -asmlinkage void __attribute__((weak)) mce_threshold_interrupt(void) -{ -} - -/* - * 'math_state_restore()' saves the current math information in the - * old math state array, and gets the new ones from the current task - * - * Careful.. There are problems with IBM-designed IRQ13 behaviour. - * Don't touch unless you *really* know how it works. - */ -asmlinkage void math_state_restore(void) -{ - struct task_struct *me = current; - - if (!used_math()) { - local_irq_enable(); - /* - * does a slab alloc which can sleep - */ - if (init_fpu(me)) { - /* - * ran out of memory! - */ - do_group_exit(SIGKILL); - return; - } - local_irq_disable(); - } - - clts(); /* Allow maths ops (or we recurse) */ - /* - * Paranoid restore. send a SIGSEGV if we fail to restore the state. - */ - if (unlikely(restore_fpu_checking(me))) { - stts(); - force_sig(SIGSEGV, me); - return; - } - task_thread_info(me)->status |= TS_USEDFPU; - me->fpu_counter++; -} -EXPORT_SYMBOL_GPL(math_state_restore); - -void __init trap_init(void) -{ - set_intr_gate(0, ÷_error); - set_intr_gate_ist(1, &debug, DEBUG_STACK); - set_intr_gate_ist(2, &nmi, NMI_STACK); - /* int3 can be called from all */ - set_system_gate_ist(3, &int3, DEBUG_STACK); - /* int4 can be called from all */ - set_system_gate(4, &overflow); - set_intr_gate(5, &bounds); - set_intr_gate(6, &invalid_op); - set_intr_gate(7, &device_not_available); - set_intr_gate_ist(8, &double_fault, DOUBLEFAULT_STACK); - set_intr_gate(9, &coprocessor_segment_overrun); - set_intr_gate(10, &invalid_TSS); - set_intr_gate(11, &segment_not_present); - set_intr_gate_ist(12, &stack_segment, STACKFAULT_STACK); - set_intr_gate(13, &general_protection); - set_intr_gate(14, &page_fault); - set_intr_gate(15, &spurious_interrupt_bug); - set_intr_gate(16, &coprocessor_error); - set_intr_gate(17, &alignment_check); -#ifdef CONFIG_X86_MCE - set_intr_gate_ist(18, &machine_check, MCE_STACK); -#endif - set_intr_gate(19, &simd_coprocessor_error); - -#ifdef CONFIG_IA32_EMULATION - set_system_gate(IA32_SYSCALL_VECTOR, ia32_syscall); -#endif - /* - * Should be a barrier for any external CPU state: - */ - cpu_init(); -} - -static int __init oops_setup(char *s) -{ - if (!s) - return -EINVAL; - if (!strcmp(s, "panic")) - panic_on_oops = 1; - return 0; -} -early_param("oops", oops_setup); - -static int __init kstack_setup(char *s) -{ - if (!s) - return -EINVAL; - kstack_depth_to_print = simple_strtoul(s, NULL, 0); - return 0; -} -early_param("kstack", kstack_setup); - -static int __init code_bytes_setup(char *s) -{ - code_bytes = simple_strtoul(s, NULL, 0); - if (code_bytes > 8192) - code_bytes = 8192; - - return 1; -} -__setup("code_bytes=", code_bytes_setup); diff --git a/arch/x86/mach-generic/es7000.c b/arch/x86/mach-generic/es7000.c index 520cca0ee04e..6513d41ea21e 100644 --- a/arch/x86/mach-generic/es7000.c +++ b/arch/x86/mach-generic/es7000.c @@ -47,16 +47,26 @@ static __init int mps_oem_check(struct mp_config_table *mpc, char *oem, /* Hook from generic ACPI tables.c */ static int __init acpi_madt_oem_check(char *oem_id, char *oem_table_id) { - unsigned long oem_addr; + unsigned long oem_addr = 0; + int check_dsdt; + int ret = 0; + + /* check dsdt at first to avoid clear fix_map for oem_addr */ + check_dsdt = es7000_check_dsdt(); + if (!find_unisys_acpi_oem_table(&oem_addr)) { - if (es7000_check_dsdt()) - return parse_unisys_oem((char *)oem_addr); + if (check_dsdt) + ret = parse_unisys_oem((char *)oem_addr); else { setup_unisys(); - return 1; + ret = 1; } + /* + * we need to unmap it + */ + unmap_unisys_acpi_oem_table(oem_addr); } - return 0; + return ret; } #else static int __init acpi_madt_oem_check(char *oem_id, char *oem_table_id) diff --git a/arch/x86/mm/Makefile b/arch/x86/mm/Makefile index dfb932dcf136..59f89b434b45 100644 --- a/arch/x86/mm/Makefile +++ b/arch/x86/mm/Makefile @@ -13,12 +13,8 @@ obj-$(CONFIG_MMIOTRACE) += mmiotrace.o mmiotrace-y := pf_in.o mmio-mod.o obj-$(CONFIG_MMIOTRACE_TEST) += testmmiotrace.o -ifeq ($(CONFIG_X86_32),y) -obj-$(CONFIG_NUMA) += discontig_32.o -else -obj-$(CONFIG_NUMA) += numa_64.o +obj-$(CONFIG_NUMA) += numa_$(BITS).o obj-$(CONFIG_K8_NUMA) += k8topology_64.o -endif obj-$(CONFIG_ACPI_NUMA) += srat_$(BITS).o obj-$(CONFIG_MEMTEST) += memtest.o diff --git a/arch/x86/mm/fault.c b/arch/x86/mm/fault.c index a742d753d5b0..3f2b8962cbd0 100644 --- a/arch/x86/mm/fault.c +++ b/arch/x86/mm/fault.c @@ -592,11 +592,6 @@ void __kprobes do_page_fault(struct pt_regs *regs, unsigned long error_code) unsigned long flags; #endif - /* - * We can fault from pretty much anywhere, with unknown IRQ state. - */ - trace_hardirqs_fixup(); - tsk = current; mm = tsk->mm; prefetchw(&mm->mmap_sem); diff --git a/arch/x86/mm/gup.c b/arch/x86/mm/gup.c index 007bb06c7504..4ba373c5b8c8 100644 --- a/arch/x86/mm/gup.c +++ b/arch/x86/mm/gup.c @@ -82,7 +82,7 @@ static noinline int gup_pte_range(pmd_t pmd, unsigned long addr, pte_t pte = gup_get_pte(ptep); struct page *page; - if ((pte_val(pte) & (mask | _PAGE_SPECIAL)) != mask) { + if ((pte_flags(pte) & (mask | _PAGE_SPECIAL)) != mask) { pte_unmap(ptep); return 0; } @@ -116,10 +116,10 @@ static noinline int gup_huge_pmd(pmd_t pmd, unsigned long addr, mask = _PAGE_PRESENT|_PAGE_USER; if (write) mask |= _PAGE_RW; - if ((pte_val(pte) & mask) != mask) + if ((pte_flags(pte) & mask) != mask) return 0; /* hugepages are never "special" */ - VM_BUG_ON(pte_val(pte) & _PAGE_SPECIAL); + VM_BUG_ON(pte_flags(pte) & _PAGE_SPECIAL); VM_BUG_ON(!pfn_valid(pte_pfn(pte))); refs = 0; @@ -173,10 +173,10 @@ static noinline int gup_huge_pud(pud_t pud, unsigned long addr, mask = _PAGE_PRESENT|_PAGE_USER; if (write) mask |= _PAGE_RW; - if ((pte_val(pte) & mask) != mask) + if ((pte_flags(pte) & mask) != mask) return 0; /* hugepages are never "special" */ - VM_BUG_ON(pte_val(pte) & _PAGE_SPECIAL); + VM_BUG_ON(pte_flags(pte) & _PAGE_SPECIAL); VM_BUG_ON(!pfn_valid(pte_pfn(pte))); refs = 0; diff --git a/arch/x86/mm/init_32.c b/arch/x86/mm/init_32.c index bbe044dbe014..8396868e82c5 100644 --- a/arch/x86/mm/init_32.c +++ b/arch/x86/mm/init_32.c @@ -558,7 +558,7 @@ void zap_low_mappings(void) int nx_enabled; -pteval_t __supported_pte_mask __read_mostly = ~(_PAGE_NX | _PAGE_GLOBAL); +pteval_t __supported_pte_mask __read_mostly = ~(_PAGE_NX | _PAGE_GLOBAL | _PAGE_IOMAP); EXPORT_SYMBOL_GPL(__supported_pte_mask); #ifdef CONFIG_X86_PAE diff --git a/arch/x86/mm/init_64.c b/arch/x86/mm/init_64.c index 3e10054c5731..b8e461d49412 100644 --- a/arch/x86/mm/init_64.c +++ b/arch/x86/mm/init_64.c @@ -89,7 +89,7 @@ early_param("gbpages", parse_direct_gbpages_on); int after_bootmem; -unsigned long __supported_pte_mask __read_mostly = ~0UL; +pteval_t __supported_pte_mask __read_mostly = ~_PAGE_IOMAP; EXPORT_SYMBOL_GPL(__supported_pte_mask); static int do_not_nx __cpuinitdata; @@ -196,9 +196,6 @@ set_pte_vaddr_pud(pud_t *pud_page, unsigned long vaddr, pte_t new_pte) } pte = pte_offset_kernel(pmd, vaddr); - if (!pte_none(*pte) && pte_val(new_pte) && - pte_val(*pte) != (pte_val(new_pte) & __supported_pte_mask)) - pte_ERROR(*pte); set_pte(pte, new_pte); /* @@ -313,7 +310,7 @@ static __ref void *alloc_low_page(unsigned long *phys) if (pfn >= table_top) panic("alloc_low_page: ran out of memory"); - adr = early_ioremap(pfn * PAGE_SIZE, PAGE_SIZE); + adr = early_memremap(pfn * PAGE_SIZE, PAGE_SIZE); memset(adr, 0, PAGE_SIZE); *phys = pfn * PAGE_SIZE; return adr; @@ -749,7 +746,7 @@ unsigned long __init_refok init_memory_mapping(unsigned long start, old_start = mr[i].start; memmove(&mr[i], &mr[i+1], (nr_range - 1 - i) * sizeof (struct map_range)); - mr[i].start = old_start; + mr[i--].start = old_start; nr_range--; } diff --git a/arch/x86/mm/ioremap.c b/arch/x86/mm/ioremap.c index 8cbeda15cd29..e4c43ec71b29 100644 --- a/arch/x86/mm/ioremap.c +++ b/arch/x86/mm/ioremap.c @@ -45,6 +45,27 @@ unsigned long __phys_addr(unsigned long x) } EXPORT_SYMBOL(__phys_addr); +bool __virt_addr_valid(unsigned long x) +{ + if (x >= __START_KERNEL_map) { + x -= __START_KERNEL_map; + if (x >= KERNEL_IMAGE_SIZE) + return false; + x += phys_base; + } else { + if (x < PAGE_OFFSET) + return false; + x -= PAGE_OFFSET; + if (system_state == SYSTEM_BOOTING ? + x > MAXMEM : !phys_addr_valid(x)) { + return false; + } + } + + return pfn_valid(x >> PAGE_SHIFT); +} +EXPORT_SYMBOL(__virt_addr_valid); + #else static inline int phys_addr_valid(unsigned long addr) @@ -56,13 +77,24 @@ static inline int phys_addr_valid(unsigned long addr) unsigned long __phys_addr(unsigned long x) { /* VMALLOC_* aren't constants; not available at the boot time */ - VIRTUAL_BUG_ON(x < PAGE_OFFSET || (system_state != SYSTEM_BOOTING && - is_vmalloc_addr((void *)x))); + VIRTUAL_BUG_ON(x < PAGE_OFFSET); + VIRTUAL_BUG_ON(system_state != SYSTEM_BOOTING && + is_vmalloc_addr((void *) x)); return x - PAGE_OFFSET; } EXPORT_SYMBOL(__phys_addr); #endif +bool __virt_addr_valid(unsigned long x) +{ + if (x < PAGE_OFFSET) + return false; + if (system_state != SYSTEM_BOOTING && is_vmalloc_addr((void *) x)) + return false; + return pfn_valid((x - PAGE_OFFSET) >> PAGE_SHIFT); +} +EXPORT_SYMBOL(__virt_addr_valid); + #endif int page_is_ram(unsigned long pagenr) @@ -242,16 +274,16 @@ static void __iomem *__ioremap_caller(resource_size_t phys_addr, switch (prot_val) { case _PAGE_CACHE_UC: default: - prot = PAGE_KERNEL_NOCACHE; + prot = PAGE_KERNEL_IO_NOCACHE; break; case _PAGE_CACHE_UC_MINUS: - prot = PAGE_KERNEL_UC_MINUS; + prot = PAGE_KERNEL_IO_UC_MINUS; break; case _PAGE_CACHE_WC: - prot = PAGE_KERNEL_WC; + prot = PAGE_KERNEL_IO_WC; break; case _PAGE_CACHE_WB: - prot = PAGE_KERNEL; + prot = PAGE_KERNEL_IO; break; } @@ -568,12 +600,12 @@ static void __init __early_set_fixmap(enum fixed_addresses idx, } static inline void __init early_set_fixmap(enum fixed_addresses idx, - unsigned long phys) + unsigned long phys, pgprot_t prot) { if (after_paging_init) - set_fixmap(idx, phys); + __set_fixmap(idx, phys, prot); else - __early_set_fixmap(idx, phys, PAGE_KERNEL); + __early_set_fixmap(idx, phys, prot); } static inline void __init early_clear_fixmap(enum fixed_addresses idx) @@ -584,16 +616,22 @@ static inline void __init early_clear_fixmap(enum fixed_addresses idx) __early_set_fixmap(idx, 0, __pgprot(0)); } - -static int __initdata early_ioremap_nested; - +static void *prev_map[FIX_BTMAPS_SLOTS] __initdata; +static unsigned long prev_size[FIX_BTMAPS_SLOTS] __initdata; static int __init check_early_ioremap_leak(void) { - if (!early_ioremap_nested) + int count = 0; + int i; + + for (i = 0; i < FIX_BTMAPS_SLOTS; i++) + if (prev_map[i]) + count++; + + if (!count) return 0; WARN(1, KERN_WARNING "Debug warning: early ioremap leak of %d areas detected.\n", - early_ioremap_nested); + count); printk(KERN_WARNING "please boot with early_ioremap_debug and report the dmesg.\n"); @@ -601,18 +639,33 @@ static int __init check_early_ioremap_leak(void) } late_initcall(check_early_ioremap_leak); -void __init *early_ioremap(unsigned long phys_addr, unsigned long size) +static void __init *__early_ioremap(unsigned long phys_addr, unsigned long size, pgprot_t prot) { unsigned long offset, last_addr; - unsigned int nrpages, nesting; + unsigned int nrpages; enum fixed_addresses idx0, idx; + int i, slot; WARN_ON(system_state != SYSTEM_BOOTING); - nesting = early_ioremap_nested; + slot = -1; + for (i = 0; i < FIX_BTMAPS_SLOTS; i++) { + if (!prev_map[i]) { + slot = i; + break; + } + } + + if (slot < 0) { + printk(KERN_INFO "early_iomap(%08lx, %08lx) not found slot\n", + phys_addr, size); + WARN_ON(1); + return NULL; + } + if (early_ioremap_debug) { printk(KERN_INFO "early_ioremap(%08lx, %08lx) [%d] => ", - phys_addr, size, nesting); + phys_addr, size, slot); dump_stack(); } @@ -623,11 +676,7 @@ void __init *early_ioremap(unsigned long phys_addr, unsigned long size) return NULL; } - if (nesting >= FIX_BTMAPS_NESTING) { - WARN_ON(1); - return NULL; - } - early_ioremap_nested++; + prev_size[slot] = size; /* * Mappings have to be page-aligned */ @@ -647,10 +696,10 @@ void __init *early_ioremap(unsigned long phys_addr, unsigned long size) /* * Ok, go for it.. */ - idx0 = FIX_BTMAP_BEGIN - NR_FIX_BTMAPS*nesting; + idx0 = FIX_BTMAP_BEGIN - NR_FIX_BTMAPS*slot; idx = idx0; while (nrpages > 0) { - early_set_fixmap(idx, phys_addr); + early_set_fixmap(idx, phys_addr, prot); phys_addr += PAGE_SIZE; --idx; --nrpages; @@ -658,7 +707,20 @@ void __init *early_ioremap(unsigned long phys_addr, unsigned long size) if (early_ioremap_debug) printk(KERN_CONT "%08lx + %08lx\n", offset, fix_to_virt(idx0)); - return (void *) (offset + fix_to_virt(idx0)); + prev_map[slot] = (void *) (offset + fix_to_virt(idx0)); + return prev_map[slot]; +} + +/* Remap an IO device */ +void __init *early_ioremap(unsigned long phys_addr, unsigned long size) +{ + return __early_ioremap(phys_addr, size, PAGE_KERNEL_IO); +} + +/* Remap memory */ +void __init *early_memremap(unsigned long phys_addr, unsigned long size) +{ + return __early_ioremap(phys_addr, size, PAGE_KERNEL); } void __init early_iounmap(void *addr, unsigned long size) @@ -667,15 +729,33 @@ void __init early_iounmap(void *addr, unsigned long size) unsigned long offset; unsigned int nrpages; enum fixed_addresses idx; - int nesting; + int i, slot; + + slot = -1; + for (i = 0; i < FIX_BTMAPS_SLOTS; i++) { + if (prev_map[i] == addr) { + slot = i; + break; + } + } - nesting = --early_ioremap_nested; - if (WARN_ON(nesting < 0)) + if (slot < 0) { + printk(KERN_INFO "early_iounmap(%p, %08lx) not found slot\n", + addr, size); + WARN_ON(1); + return; + } + + if (prev_size[slot] != size) { + printk(KERN_INFO "early_iounmap(%p, %08lx) [%d] size not consistent %08lx\n", + addr, size, slot, prev_size[slot]); + WARN_ON(1); return; + } if (early_ioremap_debug) { printk(KERN_INFO "early_iounmap(%p, %08lx) [%d]\n", addr, - size, nesting); + size, slot); dump_stack(); } @@ -687,12 +767,13 @@ void __init early_iounmap(void *addr, unsigned long size) offset = virt_addr & ~PAGE_MASK; nrpages = PAGE_ALIGN(offset + size - 1) >> PAGE_SHIFT; - idx = FIX_BTMAP_BEGIN - NR_FIX_BTMAPS*nesting; + idx = FIX_BTMAP_BEGIN - NR_FIX_BTMAPS*slot; while (nrpages > 0) { early_clear_fixmap(idx); --idx; --nrpages; } + prev_map[slot] = 0; } void __this_fixmap_does_not_exist(void) diff --git a/arch/x86/mm/discontig_32.c b/arch/x86/mm/numa_32.c index 847c164725f4..847c164725f4 100644 --- a/arch/x86/mm/discontig_32.c +++ b/arch/x86/mm/numa_32.c diff --git a/arch/x86/mm/srat_64.c b/arch/x86/mm/srat_64.c index 1b4763e26ea9..51c0a2fc14fe 100644 --- a/arch/x86/mm/srat_64.c +++ b/arch/x86/mm/srat_64.c @@ -138,7 +138,7 @@ acpi_numa_processor_affinity_init(struct acpi_srat_cpu_affinity *pa) return; } - if (is_uv_system()) + if (get_uv_system_type() >= UV_X2APIC) apic_id = (pa->apic_id << 8) | pa->local_sapic_eid; else apic_id = pa->apic_id; diff --git a/arch/x86/oprofile/Makefile b/arch/x86/oprofile/Makefile index 30f3eb366667..446902b2a6b6 100644 --- a/arch/x86/oprofile/Makefile +++ b/arch/x86/oprofile/Makefile @@ -7,6 +7,6 @@ DRIVER_OBJS = $(addprefix ../../../drivers/oprofile/, \ timer_int.o ) oprofile-y := $(DRIVER_OBJS) init.o backtrace.o -oprofile-$(CONFIG_X86_LOCAL_APIC) += nmi_int.o op_model_athlon.o \ +oprofile-$(CONFIG_X86_LOCAL_APIC) += nmi_int.o op_model_amd.o \ op_model_ppro.o op_model_p4.o oprofile-$(CONFIG_X86_IO_APIC) += nmi_timer_int.o diff --git a/arch/x86/oprofile/nmi_int.c b/arch/x86/oprofile/nmi_int.c index 8a5f1614a3d5..57f6c9088081 100644 --- a/arch/x86/oprofile/nmi_int.c +++ b/arch/x86/oprofile/nmi_int.c @@ -1,10 +1,11 @@ /** * @file nmi_int.c * - * @remark Copyright 2002 OProfile authors + * @remark Copyright 2002-2008 OProfile authors * @remark Read the file COPYING * * @author John Levon <levon@movementarian.org> + * @author Robert Richter <robert.richter@amd.com> */ #include <linux/init.h> @@ -439,6 +440,7 @@ int __init op_nmi_init(struct oprofile_operations *ops) __u8 vendor = boot_cpu_data.x86_vendor; __u8 family = boot_cpu_data.x86; char *cpu_type; + int ret = 0; if (!cpu_has_apic) return -ENODEV; @@ -451,19 +453,23 @@ int __init op_nmi_init(struct oprofile_operations *ops) default: return -ENODEV; case 6: - model = &op_athlon_spec; + model = &op_amd_spec; cpu_type = "i386/athlon"; break; case 0xf: - model = &op_athlon_spec; + model = &op_amd_spec; /* Actually it could be i386/hammer too, but give user space an consistent name. */ cpu_type = "x86-64/hammer"; break; case 0x10: - model = &op_athlon_spec; + model = &op_amd_spec; cpu_type = "x86-64/family10"; break; + case 0x11: + model = &op_amd_spec; + cpu_type = "x86-64/family11h"; + break; } break; @@ -490,17 +496,24 @@ int __init op_nmi_init(struct oprofile_operations *ops) return -ENODEV; } - init_sysfs(); #ifdef CONFIG_SMP register_cpu_notifier(&oprofile_cpu_nb); #endif - using_nmi = 1; + /* default values, can be overwritten by model */ ops->create_files = nmi_create_files; ops->setup = nmi_setup; ops->shutdown = nmi_shutdown; ops->start = nmi_start; ops->stop = nmi_stop; ops->cpu_type = cpu_type; + + if (model->init) + ret = model->init(ops); + if (ret) + return ret; + + init_sysfs(); + using_nmi = 1; printk(KERN_INFO "oprofile: using NMI interrupt.\n"); return 0; } @@ -513,4 +526,6 @@ void op_nmi_exit(void) unregister_cpu_notifier(&oprofile_cpu_nb); #endif } + if (model->exit) + model->exit(); } diff --git a/arch/x86/oprofile/op_model_amd.c b/arch/x86/oprofile/op_model_amd.c new file mode 100644 index 000000000000..d9faf607b3a6 --- /dev/null +++ b/arch/x86/oprofile/op_model_amd.c @@ -0,0 +1,543 @@ +/* + * @file op_model_amd.c + * athlon / K7 / K8 / Family 10h model-specific MSR operations + * + * @remark Copyright 2002-2008 OProfile authors + * @remark Read the file COPYING + * + * @author John Levon + * @author Philippe Elie + * @author Graydon Hoare + * @author Robert Richter <robert.richter@amd.com> + * @author Barry Kasindorf +*/ + +#include <linux/oprofile.h> +#include <linux/device.h> +#include <linux/pci.h> + +#include <asm/ptrace.h> +#include <asm/msr.h> +#include <asm/nmi.h> + +#include "op_x86_model.h" +#include "op_counter.h" + +#define NUM_COUNTERS 4 +#define NUM_CONTROLS 4 + +#define CTR_IS_RESERVED(msrs, c) (msrs->counters[(c)].addr ? 1 : 0) +#define CTR_READ(l, h, msrs, c) do {rdmsr(msrs->counters[(c)].addr, (l), (h)); } while (0) +#define CTR_WRITE(l, msrs, c) do {wrmsr(msrs->counters[(c)].addr, -(unsigned int)(l), -1); } while (0) +#define CTR_OVERFLOWED(n) (!((n) & (1U<<31))) + +#define CTRL_IS_RESERVED(msrs, c) (msrs->controls[(c)].addr ? 1 : 0) +#define CTRL_READ(l, h, msrs, c) do {rdmsr(msrs->controls[(c)].addr, (l), (h)); } while (0) +#define CTRL_WRITE(l, h, msrs, c) do {wrmsr(msrs->controls[(c)].addr, (l), (h)); } while (0) +#define CTRL_SET_ACTIVE(n) (n |= (1<<22)) +#define CTRL_SET_INACTIVE(n) (n &= ~(1<<22)) +#define CTRL_CLEAR_LO(x) (x &= (1<<21)) +#define CTRL_CLEAR_HI(x) (x &= 0xfffffcf0) +#define CTRL_SET_ENABLE(val) (val |= 1<<20) +#define CTRL_SET_USR(val, u) (val |= ((u & 1) << 16)) +#define CTRL_SET_KERN(val, k) (val |= ((k & 1) << 17)) +#define CTRL_SET_UM(val, m) (val |= (m << 8)) +#define CTRL_SET_EVENT_LOW(val, e) (val |= (e & 0xff)) +#define CTRL_SET_EVENT_HIGH(val, e) (val |= ((e >> 8) & 0xf)) +#define CTRL_SET_HOST_ONLY(val, h) (val |= ((h & 1) << 9)) +#define CTRL_SET_GUEST_ONLY(val, h) (val |= ((h & 1) << 8)) + +static unsigned long reset_value[NUM_COUNTERS]; + +#ifdef CONFIG_OPROFILE_IBS + +/* IbsFetchCtl bits/masks */ +#define IBS_FETCH_HIGH_VALID_BIT (1UL << 17) /* bit 49 */ +#define IBS_FETCH_HIGH_ENABLE (1UL << 16) /* bit 48 */ +#define IBS_FETCH_LOW_MAX_CNT_MASK 0x0000FFFFUL /* MaxCnt mask */ + +/*IbsOpCtl bits */ +#define IBS_OP_LOW_VALID_BIT (1ULL<<18) /* bit 18 */ +#define IBS_OP_LOW_ENABLE (1ULL<<17) /* bit 17 */ + +/* Codes used in cpu_buffer.c */ +/* This produces duplicate code, need to be fixed */ +#define IBS_FETCH_BEGIN 3 +#define IBS_OP_BEGIN 4 + +/* The function interface needs to be fixed, something like add + data. Should then be added to linux/oprofile.h. */ +extern void oprofile_add_ibs_sample(struct pt_regs *const regs, + unsigned int * const ibs_sample, u8 code); + +struct ibs_fetch_sample { + /* MSRC001_1031 IBS Fetch Linear Address Register */ + unsigned int ibs_fetch_lin_addr_low; + unsigned int ibs_fetch_lin_addr_high; + /* MSRC001_1030 IBS Fetch Control Register */ + unsigned int ibs_fetch_ctl_low; + unsigned int ibs_fetch_ctl_high; + /* MSRC001_1032 IBS Fetch Physical Address Register */ + unsigned int ibs_fetch_phys_addr_low; + unsigned int ibs_fetch_phys_addr_high; +}; + +struct ibs_op_sample { + /* MSRC001_1034 IBS Op Logical Address Register (IbsRIP) */ + unsigned int ibs_op_rip_low; + unsigned int ibs_op_rip_high; + /* MSRC001_1035 IBS Op Data Register */ + unsigned int ibs_op_data1_low; + unsigned int ibs_op_data1_high; + /* MSRC001_1036 IBS Op Data 2 Register */ + unsigned int ibs_op_data2_low; + unsigned int ibs_op_data2_high; + /* MSRC001_1037 IBS Op Data 3 Register */ + unsigned int ibs_op_data3_low; + unsigned int ibs_op_data3_high; + /* MSRC001_1038 IBS DC Linear Address Register (IbsDcLinAd) */ + unsigned int ibs_dc_linear_low; + unsigned int ibs_dc_linear_high; + /* MSRC001_1039 IBS DC Physical Address Register (IbsDcPhysAd) */ + unsigned int ibs_dc_phys_low; + unsigned int ibs_dc_phys_high; +}; + +/* + * unitialize the APIC for the IBS interrupts if needed on AMD Family10h+ +*/ +static void clear_ibs_nmi(void); + +static int ibs_allowed; /* AMD Family10h and later */ + +struct op_ibs_config { + unsigned long op_enabled; + unsigned long fetch_enabled; + unsigned long max_cnt_fetch; + unsigned long max_cnt_op; + unsigned long rand_en; + unsigned long dispatched_ops; +}; + +static struct op_ibs_config ibs_config; + +#endif + +/* functions for op_amd_spec */ + +static void op_amd_fill_in_addresses(struct op_msrs * const msrs) +{ + int i; + + for (i = 0; i < NUM_COUNTERS; i++) { + if (reserve_perfctr_nmi(MSR_K7_PERFCTR0 + i)) + msrs->counters[i].addr = MSR_K7_PERFCTR0 + i; + else + msrs->counters[i].addr = 0; + } + + for (i = 0; i < NUM_CONTROLS; i++) { + if (reserve_evntsel_nmi(MSR_K7_EVNTSEL0 + i)) + msrs->controls[i].addr = MSR_K7_EVNTSEL0 + i; + else + msrs->controls[i].addr = 0; + } +} + + +static void op_amd_setup_ctrs(struct op_msrs const * const msrs) +{ + unsigned int low, high; + int i; + + /* clear all counters */ + for (i = 0 ; i < NUM_CONTROLS; ++i) { + if (unlikely(!CTRL_IS_RESERVED(msrs, i))) + continue; + CTRL_READ(low, high, msrs, i); + CTRL_CLEAR_LO(low); + CTRL_CLEAR_HI(high); + CTRL_WRITE(low, high, msrs, i); + } + + /* avoid a false detection of ctr overflows in NMI handler */ + for (i = 0; i < NUM_COUNTERS; ++i) { + if (unlikely(!CTR_IS_RESERVED(msrs, i))) + continue; + CTR_WRITE(1, msrs, i); + } + + /* enable active counters */ + for (i = 0; i < NUM_COUNTERS; ++i) { + if ((counter_config[i].enabled) && (CTR_IS_RESERVED(msrs, i))) { + reset_value[i] = counter_config[i].count; + + CTR_WRITE(counter_config[i].count, msrs, i); + + CTRL_READ(low, high, msrs, i); + CTRL_CLEAR_LO(low); + CTRL_CLEAR_HI(high); + CTRL_SET_ENABLE(low); + CTRL_SET_USR(low, counter_config[i].user); + CTRL_SET_KERN(low, counter_config[i].kernel); + CTRL_SET_UM(low, counter_config[i].unit_mask); + CTRL_SET_EVENT_LOW(low, counter_config[i].event); + CTRL_SET_EVENT_HIGH(high, counter_config[i].event); + CTRL_SET_HOST_ONLY(high, 0); + CTRL_SET_GUEST_ONLY(high, 0); + + CTRL_WRITE(low, high, msrs, i); + } else { + reset_value[i] = 0; + } + } +} + +#ifdef CONFIG_OPROFILE_IBS + +static inline int +op_amd_handle_ibs(struct pt_regs * const regs, + struct op_msrs const * const msrs) +{ + unsigned int low, high; + struct ibs_fetch_sample ibs_fetch; + struct ibs_op_sample ibs_op; + + if (!ibs_allowed) + return 1; + + if (ibs_config.fetch_enabled) { + rdmsr(MSR_AMD64_IBSFETCHCTL, low, high); + if (high & IBS_FETCH_HIGH_VALID_BIT) { + ibs_fetch.ibs_fetch_ctl_high = high; + ibs_fetch.ibs_fetch_ctl_low = low; + rdmsr(MSR_AMD64_IBSFETCHLINAD, low, high); + ibs_fetch.ibs_fetch_lin_addr_high = high; + ibs_fetch.ibs_fetch_lin_addr_low = low; + rdmsr(MSR_AMD64_IBSFETCHPHYSAD, low, high); + ibs_fetch.ibs_fetch_phys_addr_high = high; + ibs_fetch.ibs_fetch_phys_addr_low = low; + + oprofile_add_ibs_sample(regs, + (unsigned int *)&ibs_fetch, + IBS_FETCH_BEGIN); + + /*reenable the IRQ */ + rdmsr(MSR_AMD64_IBSFETCHCTL, low, high); + high &= ~IBS_FETCH_HIGH_VALID_BIT; + high |= IBS_FETCH_HIGH_ENABLE; + low &= IBS_FETCH_LOW_MAX_CNT_MASK; + wrmsr(MSR_AMD64_IBSFETCHCTL, low, high); + } + } + + if (ibs_config.op_enabled) { + rdmsr(MSR_AMD64_IBSOPCTL, low, high); + if (low & IBS_OP_LOW_VALID_BIT) { + rdmsr(MSR_AMD64_IBSOPRIP, low, high); + ibs_op.ibs_op_rip_low = low; + ibs_op.ibs_op_rip_high = high; + rdmsr(MSR_AMD64_IBSOPDATA, low, high); + ibs_op.ibs_op_data1_low = low; + ibs_op.ibs_op_data1_high = high; + rdmsr(MSR_AMD64_IBSOPDATA2, low, high); + ibs_op.ibs_op_data2_low = low; + ibs_op.ibs_op_data2_high = high; + rdmsr(MSR_AMD64_IBSOPDATA3, low, high); + ibs_op.ibs_op_data3_low = low; + ibs_op.ibs_op_data3_high = high; + rdmsr(MSR_AMD64_IBSDCLINAD, low, high); + ibs_op.ibs_dc_linear_low = low; + ibs_op.ibs_dc_linear_high = high; + rdmsr(MSR_AMD64_IBSDCPHYSAD, low, high); + ibs_op.ibs_dc_phys_low = low; + ibs_op.ibs_dc_phys_high = high; + + /* reenable the IRQ */ + oprofile_add_ibs_sample(regs, + (unsigned int *)&ibs_op, + IBS_OP_BEGIN); + rdmsr(MSR_AMD64_IBSOPCTL, low, high); + high = 0; + low &= ~IBS_OP_LOW_VALID_BIT; + low |= IBS_OP_LOW_ENABLE; + wrmsr(MSR_AMD64_IBSOPCTL, low, high); + } + } + + return 1; +} + +#endif + +static int op_amd_check_ctrs(struct pt_regs * const regs, + struct op_msrs const * const msrs) +{ + unsigned int low, high; + int i; + + for (i = 0 ; i < NUM_COUNTERS; ++i) { + if (!reset_value[i]) + continue; + CTR_READ(low, high, msrs, i); + if (CTR_OVERFLOWED(low)) { + oprofile_add_sample(regs, i); + CTR_WRITE(reset_value[i], msrs, i); + } + } + +#ifdef CONFIG_OPROFILE_IBS + op_amd_handle_ibs(regs, msrs); +#endif + + /* See op_model_ppro.c */ + return 1; +} + +static void op_amd_start(struct op_msrs const * const msrs) +{ + unsigned int low, high; + int i; + for (i = 0 ; i < NUM_COUNTERS ; ++i) { + if (reset_value[i]) { + CTRL_READ(low, high, msrs, i); + CTRL_SET_ACTIVE(low); + CTRL_WRITE(low, high, msrs, i); + } + } + +#ifdef CONFIG_OPROFILE_IBS + if (ibs_allowed && ibs_config.fetch_enabled) { + low = (ibs_config.max_cnt_fetch >> 4) & 0xFFFF; + high = IBS_FETCH_HIGH_ENABLE; + wrmsr(MSR_AMD64_IBSFETCHCTL, low, high); + } + + if (ibs_allowed && ibs_config.op_enabled) { + low = ((ibs_config.max_cnt_op >> 4) & 0xFFFF) + IBS_OP_LOW_ENABLE; + high = 0; + wrmsr(MSR_AMD64_IBSOPCTL, low, high); + } +#endif +} + + +static void op_amd_stop(struct op_msrs const * const msrs) +{ + unsigned int low, high; + int i; + + /* Subtle: stop on all counters to avoid race with + * setting our pm callback */ + for (i = 0 ; i < NUM_COUNTERS ; ++i) { + if (!reset_value[i]) + continue; + CTRL_READ(low, high, msrs, i); + CTRL_SET_INACTIVE(low); + CTRL_WRITE(low, high, msrs, i); + } + +#ifdef CONFIG_OPROFILE_IBS + if (ibs_allowed && ibs_config.fetch_enabled) { + low = 0; /* clear max count and enable */ + high = 0; + wrmsr(MSR_AMD64_IBSFETCHCTL, low, high); + } + + if (ibs_allowed && ibs_config.op_enabled) { + low = 0; /* clear max count and enable */ + high = 0; + wrmsr(MSR_AMD64_IBSOPCTL, low, high); + } +#endif +} + +static void op_amd_shutdown(struct op_msrs const * const msrs) +{ + int i; + + for (i = 0 ; i < NUM_COUNTERS ; ++i) { + if (CTR_IS_RESERVED(msrs, i)) + release_perfctr_nmi(MSR_K7_PERFCTR0 + i); + } + for (i = 0 ; i < NUM_CONTROLS ; ++i) { + if (CTRL_IS_RESERVED(msrs, i)) + release_evntsel_nmi(MSR_K7_EVNTSEL0 + i); + } +} + +#ifndef CONFIG_OPROFILE_IBS + +/* no IBS support */ + +static int op_amd_init(struct oprofile_operations *ops) +{ + return 0; +} + +static void op_amd_exit(void) {} + +#else + +static u8 ibs_eilvt_off; + +static inline void apic_init_ibs_nmi_per_cpu(void *arg) +{ + ibs_eilvt_off = setup_APIC_eilvt_ibs(0, APIC_EILVT_MSG_NMI, 0); +} + +static inline void apic_clear_ibs_nmi_per_cpu(void *arg) +{ + setup_APIC_eilvt_ibs(0, APIC_EILVT_MSG_FIX, 1); +} + +static int pfm_amd64_setup_eilvt(void) +{ +#define IBSCTL_LVTOFFSETVAL (1 << 8) +#define IBSCTL 0x1cc + struct pci_dev *cpu_cfg; + int nodes; + u32 value = 0; + + /* per CPU setup */ + on_each_cpu(apic_init_ibs_nmi_per_cpu, NULL, 1); + + nodes = 0; + cpu_cfg = NULL; + do { + cpu_cfg = pci_get_device(PCI_VENDOR_ID_AMD, + PCI_DEVICE_ID_AMD_10H_NB_MISC, + cpu_cfg); + if (!cpu_cfg) + break; + ++nodes; + pci_write_config_dword(cpu_cfg, IBSCTL, ibs_eilvt_off + | IBSCTL_LVTOFFSETVAL); + pci_read_config_dword(cpu_cfg, IBSCTL, &value); + if (value != (ibs_eilvt_off | IBSCTL_LVTOFFSETVAL)) { + printk(KERN_DEBUG "Failed to setup IBS LVT offset, " + "IBSCTL = 0x%08x", value); + return 1; + } + } while (1); + + if (!nodes) { + printk(KERN_DEBUG "No CPU node configured for IBS"); + return 1; + } + +#ifdef CONFIG_NUMA + /* Sanity check */ + /* Works only for 64bit with proper numa implementation. */ + if (nodes != num_possible_nodes()) { + printk(KERN_DEBUG "Failed to setup CPU node(s) for IBS, " + "found: %d, expected %d", + nodes, num_possible_nodes()); + return 1; + } +#endif + return 0; +} + +/* + * initialize the APIC for the IBS interrupts + * if available (AMD Family10h rev B0 and later) + */ +static void setup_ibs(void) +{ + ibs_allowed = boot_cpu_has(X86_FEATURE_IBS); + + if (!ibs_allowed) + return; + + if (pfm_amd64_setup_eilvt()) { + ibs_allowed = 0; + return; + } + + printk(KERN_INFO "oprofile: AMD IBS detected\n"); +} + + +/* + * unitialize the APIC for the IBS interrupts if needed on AMD Family10h + * rev B0 and later */ +static void clear_ibs_nmi(void) +{ + if (ibs_allowed) + on_each_cpu(apic_clear_ibs_nmi_per_cpu, NULL, 1); +} + +static int (*create_arch_files)(struct super_block * sb, struct dentry * root); + +static int setup_ibs_files(struct super_block * sb, struct dentry * root) +{ + char buf[12]; + struct dentry *dir; + int ret = 0; + + /* architecture specific files */ + if (create_arch_files) + ret = create_arch_files(sb, root); + + if (ret) + return ret; + + if (!ibs_allowed) + return ret; + + /* model specific files */ + + /* setup some reasonable defaults */ + ibs_config.max_cnt_fetch = 250000; + ibs_config.fetch_enabled = 0; + ibs_config.max_cnt_op = 250000; + ibs_config.op_enabled = 0; + ibs_config.dispatched_ops = 1; + snprintf(buf, sizeof(buf), "ibs_fetch"); + dir = oprofilefs_mkdir(sb, root, buf); + oprofilefs_create_ulong(sb, dir, "rand_enable", + &ibs_config.rand_en); + oprofilefs_create_ulong(sb, dir, "enable", + &ibs_config.fetch_enabled); + oprofilefs_create_ulong(sb, dir, "max_count", + &ibs_config.max_cnt_fetch); + snprintf(buf, sizeof(buf), "ibs_uops"); + dir = oprofilefs_mkdir(sb, root, buf); + oprofilefs_create_ulong(sb, dir, "enable", + &ibs_config.op_enabled); + oprofilefs_create_ulong(sb, dir, "max_count", + &ibs_config.max_cnt_op); + oprofilefs_create_ulong(sb, dir, "dispatched_ops", + &ibs_config.dispatched_ops); + + return 0; +} + +static int op_amd_init(struct oprofile_operations *ops) +{ + setup_ibs(); + create_arch_files = ops->create_files; + ops->create_files = setup_ibs_files; + return 0; +} + +static void op_amd_exit(void) +{ + clear_ibs_nmi(); +} + +#endif + +struct op_x86_model_spec const op_amd_spec = { + .init = op_amd_init, + .exit = op_amd_exit, + .num_counters = NUM_COUNTERS, + .num_controls = NUM_CONTROLS, + .fill_in_addresses = &op_amd_fill_in_addresses, + .setup_ctrs = &op_amd_setup_ctrs, + .check_ctrs = &op_amd_check_ctrs, + .start = &op_amd_start, + .stop = &op_amd_stop, + .shutdown = &op_amd_shutdown +}; diff --git a/arch/x86/oprofile/op_model_athlon.c b/arch/x86/oprofile/op_model_athlon.c deleted file mode 100644 index 3d534879a9dc..000000000000 --- a/arch/x86/oprofile/op_model_athlon.c +++ /dev/null @@ -1,190 +0,0 @@ -/* - * @file op_model_athlon.h - * athlon / K7 / K8 / Family 10h model-specific MSR operations - * - * @remark Copyright 2002 OProfile authors - * @remark Read the file COPYING - * - * @author John Levon - * @author Philippe Elie - * @author Graydon Hoare - */ - -#include <linux/oprofile.h> -#include <asm/ptrace.h> -#include <asm/msr.h> -#include <asm/nmi.h> - -#include "op_x86_model.h" -#include "op_counter.h" - -#define NUM_COUNTERS 4 -#define NUM_CONTROLS 4 - -#define CTR_IS_RESERVED(msrs, c) (msrs->counters[(c)].addr ? 1 : 0) -#define CTR_READ(l, h, msrs, c) do {rdmsr(msrs->counters[(c)].addr, (l), (h)); } while (0) -#define CTR_WRITE(l, msrs, c) do {wrmsr(msrs->counters[(c)].addr, -(unsigned int)(l), -1); } while (0) -#define CTR_OVERFLOWED(n) (!((n) & (1U<<31))) - -#define CTRL_IS_RESERVED(msrs, c) (msrs->controls[(c)].addr ? 1 : 0) -#define CTRL_READ(l, h, msrs, c) do {rdmsr(msrs->controls[(c)].addr, (l), (h)); } while (0) -#define CTRL_WRITE(l, h, msrs, c) do {wrmsr(msrs->controls[(c)].addr, (l), (h)); } while (0) -#define CTRL_SET_ACTIVE(n) (n |= (1<<22)) -#define CTRL_SET_INACTIVE(n) (n &= ~(1<<22)) -#define CTRL_CLEAR_LO(x) (x &= (1<<21)) -#define CTRL_CLEAR_HI(x) (x &= 0xfffffcf0) -#define CTRL_SET_ENABLE(val) (val |= 1<<20) -#define CTRL_SET_USR(val, u) (val |= ((u & 1) << 16)) -#define CTRL_SET_KERN(val, k) (val |= ((k & 1) << 17)) -#define CTRL_SET_UM(val, m) (val |= (m << 8)) -#define CTRL_SET_EVENT_LOW(val, e) (val |= (e & 0xff)) -#define CTRL_SET_EVENT_HIGH(val, e) (val |= ((e >> 8) & 0xf)) -#define CTRL_SET_HOST_ONLY(val, h) (val |= ((h & 1) << 9)) -#define CTRL_SET_GUEST_ONLY(val, h) (val |= ((h & 1) << 8)) - -static unsigned long reset_value[NUM_COUNTERS]; - -static void athlon_fill_in_addresses(struct op_msrs * const msrs) -{ - int i; - - for (i = 0; i < NUM_COUNTERS; i++) { - if (reserve_perfctr_nmi(MSR_K7_PERFCTR0 + i)) - msrs->counters[i].addr = MSR_K7_PERFCTR0 + i; - else - msrs->counters[i].addr = 0; - } - - for (i = 0; i < NUM_CONTROLS; i++) { - if (reserve_evntsel_nmi(MSR_K7_EVNTSEL0 + i)) - msrs->controls[i].addr = MSR_K7_EVNTSEL0 + i; - else - msrs->controls[i].addr = 0; - } -} - - -static void athlon_setup_ctrs(struct op_msrs const * const msrs) -{ - unsigned int low, high; - int i; - - /* clear all counters */ - for (i = 0 ; i < NUM_CONTROLS; ++i) { - if (unlikely(!CTRL_IS_RESERVED(msrs, i))) - continue; - CTRL_READ(low, high, msrs, i); - CTRL_CLEAR_LO(low); - CTRL_CLEAR_HI(high); - CTRL_WRITE(low, high, msrs, i); - } - - /* avoid a false detection of ctr overflows in NMI handler */ - for (i = 0; i < NUM_COUNTERS; ++i) { - if (unlikely(!CTR_IS_RESERVED(msrs, i))) - continue; - CTR_WRITE(1, msrs, i); - } - - /* enable active counters */ - for (i = 0; i < NUM_COUNTERS; ++i) { - if ((counter_config[i].enabled) && (CTR_IS_RESERVED(msrs, i))) { - reset_value[i] = counter_config[i].count; - - CTR_WRITE(counter_config[i].count, msrs, i); - - CTRL_READ(low, high, msrs, i); - CTRL_CLEAR_LO(low); - CTRL_CLEAR_HI(high); - CTRL_SET_ENABLE(low); - CTRL_SET_USR(low, counter_config[i].user); - CTRL_SET_KERN(low, counter_config[i].kernel); - CTRL_SET_UM(low, counter_config[i].unit_mask); - CTRL_SET_EVENT_LOW(low, counter_config[i].event); - CTRL_SET_EVENT_HIGH(high, counter_config[i].event); - CTRL_SET_HOST_ONLY(high, 0); - CTRL_SET_GUEST_ONLY(high, 0); - - CTRL_WRITE(low, high, msrs, i); - } else { - reset_value[i] = 0; - } - } -} - - -static int athlon_check_ctrs(struct pt_regs * const regs, - struct op_msrs const * const msrs) -{ - unsigned int low, high; - int i; - - for (i = 0 ; i < NUM_COUNTERS; ++i) { - if (!reset_value[i]) - continue; - CTR_READ(low, high, msrs, i); - if (CTR_OVERFLOWED(low)) { - oprofile_add_sample(regs, i); - CTR_WRITE(reset_value[i], msrs, i); - } - } - - /* See op_model_ppro.c */ - return 1; -} - - -static void athlon_start(struct op_msrs const * const msrs) -{ - unsigned int low, high; - int i; - for (i = 0 ; i < NUM_COUNTERS ; ++i) { - if (reset_value[i]) { - CTRL_READ(low, high, msrs, i); - CTRL_SET_ACTIVE(low); - CTRL_WRITE(low, high, msrs, i); - } - } -} - - -static void athlon_stop(struct op_msrs const * const msrs) -{ - unsigned int low, high; - int i; - - /* Subtle: stop on all counters to avoid race with - * setting our pm callback */ - for (i = 0 ; i < NUM_COUNTERS ; ++i) { - if (!reset_value[i]) - continue; - CTRL_READ(low, high, msrs, i); - CTRL_SET_INACTIVE(low); - CTRL_WRITE(low, high, msrs, i); - } -} - -static void athlon_shutdown(struct op_msrs const * const msrs) -{ - int i; - - for (i = 0 ; i < NUM_COUNTERS ; ++i) { - if (CTR_IS_RESERVED(msrs, i)) - release_perfctr_nmi(MSR_K7_PERFCTR0 + i); - } - for (i = 0 ; i < NUM_CONTROLS ; ++i) { - if (CTRL_IS_RESERVED(msrs, i)) - release_evntsel_nmi(MSR_K7_EVNTSEL0 + i); - } -} - -struct op_x86_model_spec const op_athlon_spec = { - .num_counters = NUM_COUNTERS, - .num_controls = NUM_CONTROLS, - .fill_in_addresses = &athlon_fill_in_addresses, - .setup_ctrs = &athlon_setup_ctrs, - .check_ctrs = &athlon_check_ctrs, - .start = &athlon_start, - .stop = &athlon_stop, - .shutdown = &athlon_shutdown -}; diff --git a/arch/x86/oprofile/op_x86_model.h b/arch/x86/oprofile/op_x86_model.h index 45b605fa71d0..05a0261ba0c3 100644 --- a/arch/x86/oprofile/op_x86_model.h +++ b/arch/x86/oprofile/op_x86_model.h @@ -32,6 +32,8 @@ struct pt_regs; * various x86 CPU models' perfctr support. */ struct op_x86_model_spec { + int (*init)(struct oprofile_operations *ops); + void (*exit)(void); unsigned int const num_counters; unsigned int const num_controls; void (*fill_in_addresses)(struct op_msrs * const msrs); @@ -46,6 +48,6 @@ struct op_x86_model_spec { extern struct op_x86_model_spec const op_ppro_spec; extern struct op_x86_model_spec const op_p4_spec; extern struct op_x86_model_spec const op_p4_ht2_spec; -extern struct op_x86_model_spec const op_athlon_spec; +extern struct op_x86_model_spec const op_amd_spec; #endif /* OP_X86_MODEL_H */ diff --git a/arch/x86/pci/fixup.c b/arch/x86/pci/fixup.c index 4bdaa590375d..3c27a809393b 100644 --- a/arch/x86/pci/fixup.c +++ b/arch/x86/pci/fixup.c @@ -511,3 +511,31 @@ DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_AMD, 0x1201, fam10h_pci_cfg_space_size); DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_AMD, 0x1202, fam10h_pci_cfg_space_size); DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_AMD, 0x1203, fam10h_pci_cfg_space_size); DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_AMD, 0x1204, fam10h_pci_cfg_space_size); + +/* + * SB600: Disable BAR1 on device 14.0 to avoid HPET resources from + * confusing the PCI engine: + */ +static void sb600_disable_hpet_bar(struct pci_dev *dev) +{ + u8 val; + + /* + * The SB600 and SB700 both share the same device + * ID, but the PM register 0x55 does something different + * for the SB700, so make sure we are dealing with the + * SB600 before touching the bit: + */ + + pci_read_config_byte(dev, 0x08, &val); + + if (val < 0x2F) { + outb(0x55, 0xCD6); + val = inb(0xCD7); + + /* Set bit 7 in PM register 0x55 */ + outb(0x55, 0xCD6); + outb(val | 0x80, 0xCD7); + } +} +DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_ATI, 0x4385, sb600_disable_hpet_bar); diff --git a/drivers/char/hpet.c b/drivers/char/hpet.c index b3f5dbc6d880..f3cfb4c76125 100644 --- a/drivers/char/hpet.c +++ b/drivers/char/hpet.c @@ -53,6 +53,11 @@ #define HPET_RANGE_SIZE 1024 /* from HPET spec */ + +/* WARNING -- don't get confused. These macros are never used + * to write the (single) counter, and rarely to read it. + * They're badly named; to fix, someday. + */ #if BITS_PER_LONG == 64 #define write_counter(V, MC) writeq(V, MC) #define read_counter(MC) readq(MC) @@ -77,7 +82,7 @@ static struct clocksource clocksource_hpet = { .rating = 250, .read = read_hpet, .mask = CLOCKSOURCE_MASK(64), - .mult = 0, /*to be caluclated*/ + .mult = 0, /* to be calculated */ .shift = 10, .flags = CLOCK_SOURCE_IS_CONTINUOUS, }; @@ -86,8 +91,6 @@ static struct clocksource *hpet_clocksource; /* A lock for concurrent access by app and isr hpet activity. */ static DEFINE_SPINLOCK(hpet_lock); -/* A lock for concurrent intermodule access to hpet and isr hpet activity. */ -static DEFINE_SPINLOCK(hpet_task_lock); #define HPET_DEV_NAME (7) @@ -99,7 +102,6 @@ struct hpet_dev { unsigned long hd_irqdata; wait_queue_head_t hd_waitqueue; struct fasync_struct *hd_async_queue; - struct hpet_task *hd_task; unsigned int hd_flags; unsigned int hd_irq; unsigned int hd_hdwirq; @@ -173,11 +175,6 @@ static irqreturn_t hpet_interrupt(int irq, void *data) writel(isr, &devp->hd_hpet->hpet_isr); spin_unlock(&hpet_lock); - spin_lock(&hpet_task_lock); - if (devp->hd_task) - devp->hd_task->ht_func(devp->hd_task->ht_data); - spin_unlock(&hpet_task_lock); - wake_up_interruptible(&devp->hd_waitqueue); kill_fasync(&devp->hd_async_queue, SIGIO, POLL_IN); @@ -185,6 +182,67 @@ static irqreturn_t hpet_interrupt(int irq, void *data) return IRQ_HANDLED; } +static void hpet_timer_set_irq(struct hpet_dev *devp) +{ + unsigned long v; + int irq, gsi; + struct hpet_timer __iomem *timer; + + spin_lock_irq(&hpet_lock); + if (devp->hd_hdwirq) { + spin_unlock_irq(&hpet_lock); + return; + } + + timer = devp->hd_timer; + + /* we prefer level triggered mode */ + v = readl(&timer->hpet_config); + if (!(v & Tn_INT_TYPE_CNF_MASK)) { + v |= Tn_INT_TYPE_CNF_MASK; + writel(v, &timer->hpet_config); + } + spin_unlock_irq(&hpet_lock); + + v = (readq(&timer->hpet_config) & Tn_INT_ROUTE_CAP_MASK) >> + Tn_INT_ROUTE_CAP_SHIFT; + + /* + * In PIC mode, skip IRQ0-4, IRQ6-9, IRQ12-15 which is always used by + * legacy device. In IO APIC mode, we skip all the legacy IRQS. + */ + if (acpi_irq_model == ACPI_IRQ_MODEL_PIC) + v &= ~0xf3df; + else + v &= ~0xffff; + + for (irq = find_first_bit(&v, HPET_MAX_IRQ); irq < HPET_MAX_IRQ; + irq = find_next_bit(&v, HPET_MAX_IRQ, 1 + irq)) { + + if (irq >= NR_IRQS) { + irq = HPET_MAX_IRQ; + break; + } + + gsi = acpi_register_gsi(irq, ACPI_LEVEL_SENSITIVE, + ACPI_ACTIVE_LOW); + if (gsi > 0) + break; + + /* FIXME: Setup interrupt source table */ + } + + if (irq < HPET_MAX_IRQ) { + spin_lock_irq(&hpet_lock); + v = readl(&timer->hpet_config); + v |= irq << Tn_INT_ROUTE_CNF_SHIFT; + writel(v, &timer->hpet_config); + devp->hd_hdwirq = gsi; + spin_unlock_irq(&hpet_lock); + } + return; +} + static int hpet_open(struct inode *inode, struct file *file) { struct hpet_dev *devp; @@ -199,8 +257,7 @@ static int hpet_open(struct inode *inode, struct file *file) for (devp = NULL, hpetp = hpets; hpetp && !devp; hpetp = hpetp->hp_next) for (i = 0; i < hpetp->hp_ntimer; i++) - if (hpetp->hp_dev[i].hd_flags & HPET_OPEN - || hpetp->hp_dev[i].hd_task) + if (hpetp->hp_dev[i].hd_flags & HPET_OPEN) continue; else { devp = &hpetp->hp_dev[i]; @@ -219,6 +276,8 @@ static int hpet_open(struct inode *inode, struct file *file) spin_unlock_irq(&hpet_lock); unlock_kernel(); + hpet_timer_set_irq(devp); + return 0; } @@ -441,7 +500,11 @@ static int hpet_ioctl_ieon(struct hpet_dev *devp) devp->hd_irq = irq; t = devp->hd_ireqfreq; v = readq(&timer->hpet_config); - g = v | Tn_INT_ENB_CNF_MASK; + + /* 64-bit comparators are not yet supported through the ioctls, + * so force this into 32-bit mode if it supports both modes + */ + g = v | Tn_32MODE_CNF_MASK | Tn_INT_ENB_CNF_MASK; if (devp->hd_flags & HPET_PERIODIC) { write_counter(t, &timer->hpet_compare); @@ -451,6 +514,12 @@ static int hpet_ioctl_ieon(struct hpet_dev *devp) v |= Tn_VAL_SET_CNF_MASK; writeq(v, &timer->hpet_config); local_irq_save(flags); + + /* NOTE: what we modify here is a hidden accumulator + * register supported by periodic-capable comparators. + * We never want to modify the (single) counter; that + * would affect all the comparators. + */ m = read_counter(&hpet->hpet_mc); write_counter(t + m + hpetp->hp_delta, &timer->hpet_compare); } else { @@ -604,57 +673,6 @@ static int hpet_is_known(struct hpet_data *hdp) return 0; } -static inline int hpet_tpcheck(struct hpet_task *tp) -{ - struct hpet_dev *devp; - struct hpets *hpetp; - - devp = tp->ht_opaque; - - if (!devp) - return -ENXIO; - - for (hpetp = hpets; hpetp; hpetp = hpetp->hp_next) - if (devp >= hpetp->hp_dev - && devp < (hpetp->hp_dev + hpetp->hp_ntimer) - && devp->hd_hpet == hpetp->hp_hpet) - return 0; - - return -ENXIO; -} - -#if 0 -int hpet_unregister(struct hpet_task *tp) -{ - struct hpet_dev *devp; - struct hpet_timer __iomem *timer; - int err; - - if ((err = hpet_tpcheck(tp))) - return err; - - spin_lock_irq(&hpet_task_lock); - spin_lock(&hpet_lock); - - devp = tp->ht_opaque; - if (devp->hd_task != tp) { - spin_unlock(&hpet_lock); - spin_unlock_irq(&hpet_task_lock); - return -ENXIO; - } - - timer = devp->hd_timer; - writeq((readq(&timer->hpet_config) & ~Tn_INT_ENB_CNF_MASK), - &timer->hpet_config); - devp->hd_flags &= ~(HPET_IE | HPET_PERIODIC); - devp->hd_task = NULL; - spin_unlock(&hpet_lock); - spin_unlock_irq(&hpet_task_lock); - - return 0; -} -#endif /* 0 */ - static ctl_table hpet_table[] = { { .ctl_name = CTL_UNNUMBERED, @@ -746,6 +764,7 @@ int hpet_alloc(struct hpet_data *hdp) static struct hpets *last = NULL; unsigned long period; unsigned long long temp; + u32 remainder; /* * hpet_alloc can be called by platform dependent code. @@ -809,9 +828,13 @@ int hpet_alloc(struct hpet_data *hdp) printk("%s %d", i > 0 ? "," : "", hdp->hd_irq[i]); printk("\n"); - printk(KERN_INFO "hpet%u: %u %d-bit timers, %Lu Hz\n", - hpetp->hp_which, hpetp->hp_ntimer, - cap & HPET_COUNTER_SIZE_MASK ? 64 : 32, hpetp->hp_tick_freq); + temp = hpetp->hp_tick_freq; + remainder = do_div(temp, 1000000); + printk(KERN_INFO + "hpet%u: %u comparators, %d-bit %u.%06u MHz counter\n", + hpetp->hp_which, hpetp->hp_ntimer, + cap & HPET_COUNTER_SIZE_MASK ? 64 : 32, + (unsigned) temp, remainder); mcfg = readq(&hpet->hpet_config); if ((mcfg & HPET_ENABLE_CNF_MASK) == 0) { @@ -874,8 +897,6 @@ static acpi_status hpet_resources(struct acpi_resource *res, void *data) hdp->hd_address = ioremap(addr.minimum, addr.address_length); if (hpet_is_known(hdp)) { - printk(KERN_DEBUG "%s: 0x%lx is busy\n", - __func__, hdp->hd_phys_address); iounmap(hdp->hd_address); return AE_ALREADY_EXISTS; } @@ -891,8 +912,6 @@ static acpi_status hpet_resources(struct acpi_resource *res, void *data) HPET_RANGE_SIZE); if (hpet_is_known(hdp)) { - printk(KERN_DEBUG "%s: 0x%lx is busy\n", - __func__, hdp->hd_phys_address); iounmap(hdp->hd_address); return AE_ALREADY_EXISTS; } diff --git a/drivers/oprofile/buffer_sync.c b/drivers/oprofile/buffer_sync.c index 9304c4555079..ed982273fb8b 100644 --- a/drivers/oprofile/buffer_sync.c +++ b/drivers/oprofile/buffer_sync.c @@ -5,6 +5,7 @@ * @remark Read the file COPYING * * @author John Levon <levon@movementarian.org> + * @author Barry Kasindorf * * This is the core of the buffer management. Each * CPU buffer is processed and entered into the @@ -33,7 +34,7 @@ #include "event_buffer.h" #include "cpu_buffer.h" #include "buffer_sync.h" - + static LIST_HEAD(dying_tasks); static LIST_HEAD(dead_tasks); static cpumask_t marked_cpus = CPU_MASK_NONE; @@ -48,10 +49,11 @@ static void process_task_mortuary(void); * Can be invoked from softirq via RCU callback due to * call_rcu() of the task struct, hence the _irqsave. */ -static int task_free_notify(struct notifier_block * self, unsigned long val, void * data) +static int +task_free_notify(struct notifier_block *self, unsigned long val, void *data) { unsigned long flags; - struct task_struct * task = data; + struct task_struct *task = data; spin_lock_irqsave(&task_mortuary, flags); list_add(&task->tasks, &dying_tasks); spin_unlock_irqrestore(&task_mortuary, flags); @@ -62,13 +64,14 @@ static int task_free_notify(struct notifier_block * self, unsigned long val, voi /* The task is on its way out. A sync of the buffer means we can catch * any remaining samples for this task. */ -static int task_exit_notify(struct notifier_block * self, unsigned long val, void * data) +static int +task_exit_notify(struct notifier_block *self, unsigned long val, void *data) { /* To avoid latency problems, we only process the current CPU, * hoping that most samples for the task are on this CPU */ sync_buffer(raw_smp_processor_id()); - return 0; + return 0; } @@ -77,11 +80,12 @@ static int task_exit_notify(struct notifier_block * self, unsigned long val, voi * we don't lose any. This does not have to be exact, it's a QoI issue * only. */ -static int munmap_notify(struct notifier_block * self, unsigned long val, void * data) +static int +munmap_notify(struct notifier_block *self, unsigned long val, void *data) { unsigned long addr = (unsigned long)data; - struct mm_struct * mm = current->mm; - struct vm_area_struct * mpnt; + struct mm_struct *mm = current->mm; + struct vm_area_struct *mpnt; down_read(&mm->mmap_sem); @@ -99,11 +103,12 @@ static int munmap_notify(struct notifier_block * self, unsigned long val, void * return 0; } - + /* We need to be told about new modules so we don't attribute to a previously * loaded module, or drop the samples on the floor. */ -static int module_load_notify(struct notifier_block * self, unsigned long val, void * data) +static int +module_load_notify(struct notifier_block *self, unsigned long val, void *data) { #ifdef CONFIG_MODULES if (val != MODULE_STATE_COMING) @@ -118,7 +123,7 @@ static int module_load_notify(struct notifier_block * self, unsigned long val, v return 0; } - + static struct notifier_block task_free_nb = { .notifier_call = task_free_notify, }; @@ -135,7 +140,7 @@ static struct notifier_block module_load_nb = { .notifier_call = module_load_notify, }; - + static void end_sync(void) { end_cpu_work(); @@ -208,14 +213,14 @@ static inline unsigned long fast_get_dcookie(struct path *path) * not strictly necessary but allows oprofile to associate * shared-library samples with particular applications */ -static unsigned long get_exec_dcookie(struct mm_struct * mm) +static unsigned long get_exec_dcookie(struct mm_struct *mm) { unsigned long cookie = NO_COOKIE; - struct vm_area_struct * vma; - + struct vm_area_struct *vma; + if (!mm) goto out; - + for (vma = mm->mmap; vma; vma = vma->vm_next) { if (!vma->vm_file) continue; @@ -235,13 +240,14 @@ out: * sure to do this lookup before a mm->mmap modification happens so * we don't lose track. */ -static unsigned long lookup_dcookie(struct mm_struct * mm, unsigned long addr, off_t * offset) +static unsigned long +lookup_dcookie(struct mm_struct *mm, unsigned long addr, off_t *offset) { unsigned long cookie = NO_COOKIE; - struct vm_area_struct * vma; + struct vm_area_struct *vma; for (vma = find_vma(mm, addr); vma; vma = vma->vm_next) { - + if (addr < vma->vm_start || addr >= vma->vm_end) continue; @@ -263,9 +269,20 @@ static unsigned long lookup_dcookie(struct mm_struct * mm, unsigned long addr, o return cookie; } +static void increment_tail(struct oprofile_cpu_buffer *b) +{ + unsigned long new_tail = b->tail_pos + 1; + + rmb(); /* be sure fifo pointers are synchromized */ + + if (new_tail < b->buffer_size) + b->tail_pos = new_tail; + else + b->tail_pos = 0; +} static unsigned long last_cookie = INVALID_COOKIE; - + static void add_cpu_switch(int i) { add_event_entry(ESCAPE_CODE); @@ -278,16 +295,16 @@ static void add_kernel_ctx_switch(unsigned int in_kernel) { add_event_entry(ESCAPE_CODE); if (in_kernel) - add_event_entry(KERNEL_ENTER_SWITCH_CODE); + add_event_entry(KERNEL_ENTER_SWITCH_CODE); else - add_event_entry(KERNEL_EXIT_SWITCH_CODE); + add_event_entry(KERNEL_EXIT_SWITCH_CODE); } - + static void -add_user_ctx_switch(struct task_struct const * task, unsigned long cookie) +add_user_ctx_switch(struct task_struct const *task, unsigned long cookie) { add_event_entry(ESCAPE_CODE); - add_event_entry(CTX_SWITCH_CODE); + add_event_entry(CTX_SWITCH_CODE); add_event_entry(task->pid); add_event_entry(cookie); /* Another code for daemon back-compat */ @@ -296,7 +313,7 @@ add_user_ctx_switch(struct task_struct const * task, unsigned long cookie) add_event_entry(task->tgid); } - + static void add_cookie_switch(unsigned long cookie) { add_event_entry(ESCAPE_CODE); @@ -304,13 +321,78 @@ static void add_cookie_switch(unsigned long cookie) add_event_entry(cookie); } - + static void add_trace_begin(void) { add_event_entry(ESCAPE_CODE); add_event_entry(TRACE_BEGIN_CODE); } +#ifdef CONFIG_OPROFILE_IBS + +#define IBS_FETCH_CODE_SIZE 2 +#define IBS_OP_CODE_SIZE 5 +#define IBS_EIP(offset) \ + (((struct op_sample *)&cpu_buf->buffer[(offset)])->eip) +#define IBS_EVENT(offset) \ + (((struct op_sample *)&cpu_buf->buffer[(offset)])->event) + +/* + * Add IBS fetch and op entries to event buffer + */ +static void add_ibs_begin(struct oprofile_cpu_buffer *cpu_buf, int code, + int in_kernel, struct mm_struct *mm) +{ + unsigned long rip; + int i, count; + unsigned long ibs_cookie = 0; + off_t offset; + + increment_tail(cpu_buf); /* move to RIP entry */ + + rip = IBS_EIP(cpu_buf->tail_pos); + +#ifdef __LP64__ + rip += IBS_EVENT(cpu_buf->tail_pos) << 32; +#endif + + if (mm) { + ibs_cookie = lookup_dcookie(mm, rip, &offset); + + if (ibs_cookie == NO_COOKIE) + offset = rip; + if (ibs_cookie == INVALID_COOKIE) { + atomic_inc(&oprofile_stats.sample_lost_no_mapping); + offset = rip; + } + if (ibs_cookie != last_cookie) { + add_cookie_switch(ibs_cookie); + last_cookie = ibs_cookie; + } + } else + offset = rip; + + add_event_entry(ESCAPE_CODE); + add_event_entry(code); + add_event_entry(offset); /* Offset from Dcookie */ + + /* we send the Dcookie offset, but send the raw Linear Add also*/ + add_event_entry(IBS_EIP(cpu_buf->tail_pos)); + add_event_entry(IBS_EVENT(cpu_buf->tail_pos)); + + if (code == IBS_FETCH_CODE) + count = IBS_FETCH_CODE_SIZE; /*IBS FETCH is 2 int64s*/ + else + count = IBS_OP_CODE_SIZE; /*IBS OP is 5 int64s*/ + + for (i = 0; i < count; i++) { + increment_tail(cpu_buf); + add_event_entry(IBS_EIP(cpu_buf->tail_pos)); + add_event_entry(IBS_EVENT(cpu_buf->tail_pos)); + } +} + +#endif static void add_sample_entry(unsigned long offset, unsigned long event) { @@ -319,13 +401,13 @@ static void add_sample_entry(unsigned long offset, unsigned long event) } -static int add_us_sample(struct mm_struct * mm, struct op_sample * s) +static int add_us_sample(struct mm_struct *mm, struct op_sample *s) { unsigned long cookie; off_t offset; - - cookie = lookup_dcookie(mm, s->eip, &offset); - + + cookie = lookup_dcookie(mm, s->eip, &offset); + if (cookie == INVALID_COOKIE) { atomic_inc(&oprofile_stats.sample_lost_no_mapping); return 0; @@ -341,13 +423,13 @@ static int add_us_sample(struct mm_struct * mm, struct op_sample * s) return 1; } - + /* Add a sample to the global event buffer. If possible the * sample is converted into a persistent dentry/offset pair * for later lookup from userspace. */ static int -add_sample(struct mm_struct * mm, struct op_sample * s, int in_kernel) +add_sample(struct mm_struct *mm, struct op_sample *s, int in_kernel) { if (in_kernel) { add_sample_entry(s->eip, s->event); @@ -359,9 +441,9 @@ add_sample(struct mm_struct * mm, struct op_sample * s, int in_kernel) } return 0; } - -static void release_mm(struct mm_struct * mm) + +static void release_mm(struct mm_struct *mm) { if (!mm) return; @@ -370,9 +452,9 @@ static void release_mm(struct mm_struct * mm) } -static struct mm_struct * take_tasks_mm(struct task_struct * task) +static struct mm_struct *take_tasks_mm(struct task_struct *task) { - struct mm_struct * mm = get_task_mm(task); + struct mm_struct *mm = get_task_mm(task); if (mm) down_read(&mm->mmap_sem); return mm; @@ -383,10 +465,10 @@ static inline int is_code(unsigned long val) { return val == ESCAPE_CODE; } - + /* "acquire" as many cpu buffer slots as we can */ -static unsigned long get_slots(struct oprofile_cpu_buffer * b) +static unsigned long get_slots(struct oprofile_cpu_buffer *b) { unsigned long head = b->head_pos; unsigned long tail = b->tail_pos; @@ -412,19 +494,6 @@ static unsigned long get_slots(struct oprofile_cpu_buffer * b) } -static void increment_tail(struct oprofile_cpu_buffer * b) -{ - unsigned long new_tail = b->tail_pos + 1; - - rmb(); - - if (new_tail < b->buffer_size) - b->tail_pos = new_tail; - else - b->tail_pos = 0; -} - - /* Move tasks along towards death. Any tasks on dead_tasks * will definitely have no remaining references in any * CPU buffers at this point, because we use two lists, @@ -435,8 +504,8 @@ static void process_task_mortuary(void) { unsigned long flags; LIST_HEAD(local_dead_tasks); - struct task_struct * task; - struct task_struct * ttask; + struct task_struct *task; + struct task_struct *ttask; spin_lock_irqsave(&task_mortuary, flags); @@ -493,7 +562,7 @@ void sync_buffer(int cpu) { struct oprofile_cpu_buffer *cpu_buf = &per_cpu(cpu_buffer, cpu); struct mm_struct *mm = NULL; - struct task_struct * new; + struct task_struct *new; unsigned long cookie = 0; int in_kernel = 1; unsigned int i; @@ -501,7 +570,7 @@ void sync_buffer(int cpu) unsigned long available; mutex_lock(&buffer_mutex); - + add_cpu_switch(cpu); /* Remember, only we can modify tail_pos */ @@ -509,8 +578,8 @@ void sync_buffer(int cpu) available = get_slots(cpu_buf); for (i = 0; i < available; ++i) { - struct op_sample * s = &cpu_buf->buffer[cpu_buf->tail_pos]; - + struct op_sample *s = &cpu_buf->buffer[cpu_buf->tail_pos]; + if (is_code(s->eip)) { if (s->event <= CPU_IS_KERNEL) { /* kernel/userspace switch */ @@ -521,8 +590,18 @@ void sync_buffer(int cpu) } else if (s->event == CPU_TRACE_BEGIN) { state = sb_bt_start; add_trace_begin(); +#ifdef CONFIG_OPROFILE_IBS + } else if (s->event == IBS_FETCH_BEGIN) { + state = sb_bt_start; + add_ibs_begin(cpu_buf, + IBS_FETCH_CODE, in_kernel, mm); + } else if (s->event == IBS_OP_BEGIN) { + state = sb_bt_start; + add_ibs_begin(cpu_buf, + IBS_OP_CODE, in_kernel, mm); +#endif } else { - struct mm_struct * oldmm = mm; + struct mm_struct *oldmm = mm; /* userspace context switch */ new = (struct task_struct *)s->event; @@ -533,13 +612,11 @@ void sync_buffer(int cpu) cookie = get_exec_dcookie(mm); add_user_ctx_switch(new, cookie); } - } else { - if (state >= sb_bt_start && - !add_sample(mm, s, in_kernel)) { - if (state == sb_bt_start) { - state = sb_bt_ignore; - atomic_inc(&oprofile_stats.bt_lost_no_mapping); - } + } else if (state >= sb_bt_start && + !add_sample(mm, s, in_kernel)) { + if (state == sb_bt_start) { + state = sb_bt_ignore; + atomic_inc(&oprofile_stats.bt_lost_no_mapping); } } diff --git a/drivers/oprofile/cpu_buffer.c b/drivers/oprofile/cpu_buffer.c index 7ba78e6d210e..e1bd5a937f6c 100644 --- a/drivers/oprofile/cpu_buffer.c +++ b/drivers/oprofile/cpu_buffer.c @@ -5,6 +5,7 @@ * @remark Read the file COPYING * * @author John Levon <levon@movementarian.org> + * @author Barry Kasindorf <barry.kasindorf@amd.com> * * Each CPU has a local buffer that stores PC value/event * pairs. We also log context switches when we notice them. @@ -209,7 +210,7 @@ static int log_sample(struct oprofile_cpu_buffer * cpu_buf, unsigned long pc, return 1; } -static int oprofile_begin_trace(struct oprofile_cpu_buffer * cpu_buf) +static int oprofile_begin_trace(struct oprofile_cpu_buffer *cpu_buf) { if (nr_available_slots(cpu_buf) < 4) { cpu_buf->sample_lost_overflow++; @@ -254,6 +255,75 @@ void oprofile_add_sample(struct pt_regs * const regs, unsigned long event) oprofile_add_ext_sample(pc, regs, event, is_kernel); } +#ifdef CONFIG_OPROFILE_IBS + +#define MAX_IBS_SAMPLE_SIZE 14 +static int log_ibs_sample(struct oprofile_cpu_buffer *cpu_buf, + unsigned long pc, int is_kernel, unsigned int *ibs, int ibs_code) +{ + struct task_struct *task; + + cpu_buf->sample_received++; + + if (nr_available_slots(cpu_buf) < MAX_IBS_SAMPLE_SIZE) { + cpu_buf->sample_lost_overflow++; + return 0; + } + + is_kernel = !!is_kernel; + + /* notice a switch from user->kernel or vice versa */ + if (cpu_buf->last_is_kernel != is_kernel) { + cpu_buf->last_is_kernel = is_kernel; + add_code(cpu_buf, is_kernel); + } + + /* notice a task switch */ + if (!is_kernel) { + task = current; + + if (cpu_buf->last_task != task) { + cpu_buf->last_task = task; + add_code(cpu_buf, (unsigned long)task); + } + } + + add_code(cpu_buf, ibs_code); + add_sample(cpu_buf, ibs[0], ibs[1]); + add_sample(cpu_buf, ibs[2], ibs[3]); + add_sample(cpu_buf, ibs[4], ibs[5]); + + if (ibs_code == IBS_OP_BEGIN) { + add_sample(cpu_buf, ibs[6], ibs[7]); + add_sample(cpu_buf, ibs[8], ibs[9]); + add_sample(cpu_buf, ibs[10], ibs[11]); + } + + return 1; +} + +void oprofile_add_ibs_sample(struct pt_regs *const regs, + unsigned int * const ibs_sample, u8 code) +{ + int is_kernel = !user_mode(regs); + unsigned long pc = profile_pc(regs); + + struct oprofile_cpu_buffer *cpu_buf = + &per_cpu(cpu_buffer, smp_processor_id()); + + if (!backtrace_depth) { + log_ibs_sample(cpu_buf, pc, is_kernel, ibs_sample, code); + return; + } + + /* if log_sample() fails we can't backtrace since we lost the source + * of this event */ + if (log_ibs_sample(cpu_buf, pc, is_kernel, ibs_sample, code)) + oprofile_ops.backtrace(regs, backtrace_depth); +} + +#endif + void oprofile_add_pc(unsigned long pc, int is_kernel, unsigned long event) { struct oprofile_cpu_buffer *cpu_buf = &__get_cpu_var(cpu_buffer); @@ -296,7 +366,7 @@ static void wq_sync_buffer(struct work_struct *work) struct oprofile_cpu_buffer * b = container_of(work, struct oprofile_cpu_buffer, work.work); if (b->cpu != smp_processor_id()) { - printk("WQ on CPU%d, prefer CPU%d\n", + printk(KERN_DEBUG "WQ on CPU%d, prefer CPU%d\n", smp_processor_id(), b->cpu); } sync_buffer(b->cpu); diff --git a/drivers/oprofile/cpu_buffer.h b/drivers/oprofile/cpu_buffer.h index c3e366b52261..9c44d004da69 100644 --- a/drivers/oprofile/cpu_buffer.h +++ b/drivers/oprofile/cpu_buffer.h @@ -55,5 +55,7 @@ void cpu_buffer_reset(struct oprofile_cpu_buffer * cpu_buf); /* transient events for the CPU buffer -> event buffer */ #define CPU_IS_KERNEL 1 #define CPU_TRACE_BEGIN 2 +#define IBS_FETCH_BEGIN 3 +#define IBS_OP_BEGIN 4 #endif /* OPROFILE_CPU_BUFFER_H */ diff --git a/include/asm-x86/desc.h b/include/asm-x86/desc.h index ebc307817e98..f06adac7938c 100644 --- a/include/asm-x86/desc.h +++ b/include/asm-x86/desc.h @@ -351,20 +351,16 @@ static inline void set_system_intr_gate(unsigned int n, void *addr) _set_gate(n, GATE_INTERRUPT, addr, 0x3, 0, __KERNEL_CS); } -static inline void set_trap_gate(unsigned int n, void *addr) +static inline void set_system_trap_gate(unsigned int n, void *addr) { BUG_ON((unsigned)n > 0xFF); - _set_gate(n, GATE_TRAP, addr, 0, 0, __KERNEL_CS); + _set_gate(n, GATE_TRAP, addr, 0x3, 0, __KERNEL_CS); } -static inline void set_system_gate(unsigned int n, void *addr) +static inline void set_trap_gate(unsigned int n, void *addr) { BUG_ON((unsigned)n > 0xFF); -#ifdef CONFIG_X86_32 - _set_gate(n, GATE_TRAP, addr, 0x3, 0, __KERNEL_CS); -#else - _set_gate(n, GATE_INTERRUPT, addr, 0x3, 0, __KERNEL_CS); -#endif + _set_gate(n, GATE_TRAP, addr, 0, 0, __KERNEL_CS); } static inline void set_task_gate(unsigned int n, unsigned int gdt_entry) @@ -379,7 +375,7 @@ static inline void set_intr_gate_ist(int n, void *addr, unsigned ist) _set_gate(n, GATE_INTERRUPT, addr, 0, ist, __KERNEL_CS); } -static inline void set_system_gate_ist(int n, void *addr, unsigned ist) +static inline void set_system_intr_gate_ist(int n, void *addr, unsigned ist) { BUG_ON((unsigned)n > 0xFF); _set_gate(n, GATE_INTERRUPT, addr, 0x3, ist, __KERNEL_CS); diff --git a/include/asm-x86/es7000/mpparse.h b/include/asm-x86/es7000/mpparse.h index 7b5c889d8e7d..ed5a3caae141 100644 --- a/include/asm-x86/es7000/mpparse.h +++ b/include/asm-x86/es7000/mpparse.h @@ -5,6 +5,7 @@ extern int parse_unisys_oem (char *oemptr); extern int find_unisys_acpi_oem_table(unsigned long *oem_addr); +extern void unmap_unisys_acpi_oem_table(unsigned long oem_addr); extern void setup_unisys(void); #ifndef CONFIG_X86_GENERICARCH diff --git a/include/asm-x86/fixmap_32.h b/include/asm-x86/fixmap_32.h index 784e3e759866..8844002da0e0 100644 --- a/include/asm-x86/fixmap_32.h +++ b/include/asm-x86/fixmap_32.h @@ -94,10 +94,10 @@ enum fixed_addresses { * can have a single pgd entry and a single pte table: */ #define NR_FIX_BTMAPS 64 -#define FIX_BTMAPS_NESTING 4 +#define FIX_BTMAPS_SLOTS 4 FIX_BTMAP_END = __end_of_permanent_fixed_addresses + 256 - (__end_of_permanent_fixed_addresses & 255), - FIX_BTMAP_BEGIN = FIX_BTMAP_END + NR_FIX_BTMAPS*FIX_BTMAPS_NESTING - 1, + FIX_BTMAP_BEGIN = FIX_BTMAP_END + NR_FIX_BTMAPS*FIX_BTMAPS_SLOTS - 1, FIX_WP_TEST, #ifdef CONFIG_ACPI FIX_ACPI_BEGIN, diff --git a/include/asm-x86/fixmap_64.h b/include/asm-x86/fixmap_64.h index dafb24bc0424..dab4751d1307 100644 --- a/include/asm-x86/fixmap_64.h +++ b/include/asm-x86/fixmap_64.h @@ -49,6 +49,7 @@ enum fixed_addresses { #ifdef CONFIG_PARAVIRT FIX_PARAVIRT_BOOTMAP, #endif + __end_of_permanent_fixed_addresses, #ifdef CONFIG_ACPI FIX_ACPI_BEGIN, FIX_ACPI_END = FIX_ACPI_BEGIN + FIX_ACPI_PAGES - 1, @@ -56,19 +57,18 @@ enum fixed_addresses { #ifdef CONFIG_PROVIDE_OHCI1394_DMA_INIT FIX_OHCI1394_BASE, #endif - __end_of_permanent_fixed_addresses, /* * 256 temporary boot-time mappings, used by early_ioremap(), * before ioremap() is functional. * - * We round it up to the next 512 pages boundary so that we + * We round it up to the next 256 pages boundary so that we * can have a single pgd entry and a single pte table: */ #define NR_FIX_BTMAPS 64 -#define FIX_BTMAPS_NESTING 4 - FIX_BTMAP_END = __end_of_permanent_fixed_addresses + 512 - - (__end_of_permanent_fixed_addresses & 511), - FIX_BTMAP_BEGIN = FIX_BTMAP_END + NR_FIX_BTMAPS*FIX_BTMAPS_NESTING - 1, +#define FIX_BTMAPS_SLOTS 4 + FIX_BTMAP_END = __end_of_permanent_fixed_addresses + 256 - + (__end_of_permanent_fixed_addresses & 255), + FIX_BTMAP_BEGIN = FIX_BTMAP_END + NR_FIX_BTMAPS*FIX_BTMAPS_SLOTS - 1, __end_of_fixed_addresses }; diff --git a/include/asm-x86/io.h b/include/asm-x86/io.h index 72b7719523bf..a233f835e0b5 100644 --- a/include/asm-x86/io.h +++ b/include/asm-x86/io.h @@ -5,20 +5,6 @@ #include <linux/compiler.h> -/* - * early_ioremap() and early_iounmap() are for temporary early boot-time - * mappings, before the real ioremap() is functional. - * A boot-time mapping is currently limited to at most 16 pages. - */ -#ifndef __ASSEMBLY__ -extern void early_ioremap_init(void); -extern void early_ioremap_clear(void); -extern void early_ioremap_reset(void); -extern void *early_ioremap(unsigned long offset, unsigned long size); -extern void early_iounmap(void *addr, unsigned long size); -extern void __iomem *fix_ioremap(unsigned idx, unsigned long phys); -#endif - #define build_mmio_read(name, size, type, reg, barrier) \ static inline type name(const volatile void __iomem *addr) \ { type ret; asm volatile("mov" size " %1,%0":reg (ret) \ @@ -97,6 +83,7 @@ extern void early_ioremap_init(void); extern void early_ioremap_clear(void); extern void early_ioremap_reset(void); extern void *early_ioremap(unsigned long offset, unsigned long size); +extern void *early_memremap(unsigned long offset, unsigned long size); extern void early_iounmap(void *addr, unsigned long size); extern void __iomem *fix_ioremap(unsigned idx, unsigned long phys); diff --git a/include/asm-x86/io_64.h b/include/asm-x86/io_64.h index 64429e9431a8..ee6e086b7dfe 100644 --- a/include/asm-x86/io_64.h +++ b/include/asm-x86/io_64.h @@ -165,9 +165,6 @@ static inline void *phys_to_virt(unsigned long address) #include <asm-generic/iomap.h> -extern void *early_ioremap(unsigned long addr, unsigned long size); -extern void early_iounmap(void *addr, unsigned long size); - /* * This one maps high address device memory and turns off caching for that area. * it's useful if some control registers are in such an area and write combining diff --git a/include/asm-x86/irqflags.h b/include/asm-x86/irqflags.h index 424acb48cd61..2bdab21f0898 100644 --- a/include/asm-x86/irqflags.h +++ b/include/asm-x86/irqflags.h @@ -166,27 +166,6 @@ static inline int raw_irqs_disabled(void) return raw_irqs_disabled_flags(flags); } -/* - * makes the traced hardirq state match with the machine state - * - * should be a rarely used function, only in places where its - * otherwise impossible to know the irq state, like in traps. - */ -static inline void trace_hardirqs_fixup_flags(unsigned long flags) -{ - if (raw_irqs_disabled_flags(flags)) - trace_hardirqs_off(); - else - trace_hardirqs_on(); -} - -static inline void trace_hardirqs_fixup(void) -{ - unsigned long flags = __raw_local_save_flags(); - - trace_hardirqs_fixup_flags(flags); -} - #else #ifdef CONFIG_X86_64 diff --git a/include/asm-x86/kdebug.h b/include/asm-x86/kdebug.h index 5ec3ad3e825c..fbbab66ee9df 100644 --- a/include/asm-x86/kdebug.h +++ b/include/asm-x86/kdebug.h @@ -27,10 +27,9 @@ extern void printk_address(unsigned long address, int reliable); extern void die(const char *, struct pt_regs *,long); extern int __must_check __die(const char *, struct pt_regs *, long); extern void show_registers(struct pt_regs *regs); -extern void __show_registers(struct pt_regs *, int all); extern void show_trace(struct task_struct *t, struct pt_regs *regs, unsigned long *sp, unsigned long bp); -extern void __show_regs(struct pt_regs *regs); +extern void __show_regs(struct pt_regs *regs, int all); extern void show_regs(struct pt_regs *regs); extern unsigned long oops_begin(void); extern void oops_end(unsigned long, struct pt_regs *, int signr); diff --git a/include/asm-x86/kprobes.h b/include/asm-x86/kprobes.h index bd8407863c13..8a0748d01036 100644 --- a/include/asm-x86/kprobes.h +++ b/include/asm-x86/kprobes.h @@ -82,15 +82,6 @@ struct kprobe_ctlblk { struct prev_kprobe prev_kprobe; }; -/* trap3/1 are intr gates for kprobes. So, restore the status of IF, - * if necessary, before executing the original int3/1 (trap) handler. - */ -static inline void restore_interrupts(struct pt_regs *regs) -{ - if (regs->flags & X86_EFLAGS_IF) - local_irq_enable(); -} - 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/include/asm-x86/mach-default/mach_traps.h b/include/asm-x86/mach-default/mach_traps.h index de9ac3f5c4ce..ff8778f26b84 100644 --- a/include/asm-x86/mach-default/mach_traps.h +++ b/include/asm-x86/mach-default/mach_traps.h @@ -7,12 +7,6 @@ #include <asm/mc146818rtc.h> -static inline void clear_mem_error(unsigned char reason) -{ - reason = (reason & 0xf) | 4; - outb(reason, 0x61); -} - static inline unsigned char get_nmi_reason(void) { return inb(0x61); diff --git a/include/asm-x86/module.h b/include/asm-x86/module.h index 48dc3e0c07d9..864f2005fc1d 100644 --- a/include/asm-x86/module.h +++ b/include/asm-x86/module.h @@ -52,8 +52,6 @@ struct mod_arch_specific {}; #define MODULE_PROC_FAMILY "EFFICEON " #elif defined CONFIG_MWINCHIPC6 #define MODULE_PROC_FAMILY "WINCHIPC6 " -#elif defined CONFIG_MWINCHIP2 -#define MODULE_PROC_FAMILY "WINCHIP2 " #elif defined CONFIG_MWINCHIP3D #define MODULE_PROC_FAMILY "WINCHIP3D " #elif defined CONFIG_MCYRIXIII diff --git a/include/asm-x86/nmi.h b/include/asm-x86/nmi.h index d5e715f024dc..a53f829a97c5 100644 --- a/include/asm-x86/nmi.h +++ b/include/asm-x86/nmi.h @@ -15,10 +15,6 @@ */ int do_nmi_callback(struct pt_regs *regs, int cpu); -#ifdef CONFIG_X86_64 -extern void default_do_nmi(struct pt_regs *); -#endif - extern void die_nmi(char *str, struct pt_regs *regs, int do_panic); extern int check_nmi_watchdog(void); extern int nmi_watchdog_enabled; diff --git a/include/asm-x86/page.h b/include/asm-x86/page.h index c91574776751..d4f1d5791fc1 100644 --- a/include/asm-x86/page.h +++ b/include/asm-x86/page.h @@ -179,6 +179,7 @@ static inline pteval_t native_pte_flags(pte_t pte) #endif /* CONFIG_PARAVIRT */ #define __pa(x) __phys_addr((unsigned long)(x)) +#define __pa_nodebug(x) __phys_addr_nodebug((unsigned long)(x)) /* __pa_symbol should be used for C visible symbols. This seems to be the official gcc blessed way to do such arithmetic. */ #define __pa_symbol(x) __pa(__phys_reloc_hide((unsigned long)(x))) @@ -188,9 +189,14 @@ static inline pteval_t native_pte_flags(pte_t pte) #define __boot_va(x) __va(x) #define __boot_pa(x) __pa(x) +/* + * virt_to_page(kaddr) returns a valid pointer if and only if + * virt_addr_valid(kaddr) returns true. + */ #define virt_to_page(kaddr) pfn_to_page(__pa(kaddr) >> PAGE_SHIFT) #define pfn_to_kaddr(pfn) __va((pfn) << PAGE_SHIFT) -#define virt_addr_valid(kaddr) pfn_valid(__pa(kaddr) >> PAGE_SHIFT) +extern bool __virt_addr_valid(unsigned long kaddr); +#define virt_addr_valid(kaddr) __virt_addr_valid((unsigned long) (kaddr)) #endif /* __ASSEMBLY__ */ diff --git a/include/asm-x86/page_32.h b/include/asm-x86/page_32.h index 9c5a737a9af9..e8d80d1de237 100644 --- a/include/asm-x86/page_32.h +++ b/include/asm-x86/page_32.h @@ -20,6 +20,12 @@ #endif #define THREAD_SIZE (PAGE_SIZE << THREAD_ORDER) +#define STACKFAULT_STACK 0 +#define DOUBLEFAULT_STACK 1 +#define NMI_STACK 0 +#define DEBUG_STACK 0 +#define MCE_STACK 0 +#define N_EXCEPTION_STACKS 1 #ifdef CONFIG_X86_PAE /* 44=32+12, the limit we can fit into an unsigned long pfn */ @@ -73,11 +79,11 @@ typedef struct page *pgtable_t; #endif #ifndef __ASSEMBLY__ -#define __phys_addr_const(x) ((x) - PAGE_OFFSET) +#define __phys_addr_nodebug(x) ((x) - PAGE_OFFSET) #ifdef CONFIG_DEBUG_VIRTUAL extern unsigned long __phys_addr(unsigned long); #else -#define __phys_addr(x) ((x) - PAGE_OFFSET) +#define __phys_addr(x) __phys_addr_nodebug(x) #endif #define __phys_reloc_hide(x) RELOC_HIDE((x), 0) diff --git a/include/asm-x86/pgtable.h b/include/asm-x86/pgtable.h index ed932453ef26..182f9d4c570f 100644 --- a/include/asm-x86/pgtable.h +++ b/include/asm-x86/pgtable.h @@ -15,7 +15,7 @@ #define _PAGE_BIT_PAT 7 /* on 4KB pages */ #define _PAGE_BIT_GLOBAL 8 /* Global TLB entry PPro+ */ #define _PAGE_BIT_UNUSED1 9 /* available for programmer */ -#define _PAGE_BIT_UNUSED2 10 +#define _PAGE_BIT_IOMAP 10 /* flag used to indicate IO mapping */ #define _PAGE_BIT_UNUSED3 11 #define _PAGE_BIT_PAT_LARGE 12 /* On 2MB or 1GB pages */ #define _PAGE_BIT_SPECIAL _PAGE_BIT_UNUSED1 @@ -32,7 +32,7 @@ #define _PAGE_PSE (_AT(pteval_t, 1) << _PAGE_BIT_PSE) #define _PAGE_GLOBAL (_AT(pteval_t, 1) << _PAGE_BIT_GLOBAL) #define _PAGE_UNUSED1 (_AT(pteval_t, 1) << _PAGE_BIT_UNUSED1) -#define _PAGE_UNUSED2 (_AT(pteval_t, 1) << _PAGE_BIT_UNUSED2) +#define _PAGE_IOMAP (_AT(pteval_t, 1) << _PAGE_BIT_IOMAP) #define _PAGE_UNUSED3 (_AT(pteval_t, 1) << _PAGE_BIT_UNUSED3) #define _PAGE_PAT (_AT(pteval_t, 1) << _PAGE_BIT_PAT) #define _PAGE_PAT_LARGE (_AT(pteval_t, 1) << _PAGE_BIT_PAT_LARGE) @@ -99,6 +99,11 @@ #define __PAGE_KERNEL_LARGE_NOCACHE (__PAGE_KERNEL | _PAGE_CACHE_UC | _PAGE_PSE) #define __PAGE_KERNEL_LARGE_EXEC (__PAGE_KERNEL_EXEC | _PAGE_PSE) +#define __PAGE_KERNEL_IO (__PAGE_KERNEL | _PAGE_IOMAP) +#define __PAGE_KERNEL_IO_NOCACHE (__PAGE_KERNEL_NOCACHE | _PAGE_IOMAP) +#define __PAGE_KERNEL_IO_UC_MINUS (__PAGE_KERNEL_UC_MINUS | _PAGE_IOMAP) +#define __PAGE_KERNEL_IO_WC (__PAGE_KERNEL_WC | _PAGE_IOMAP) + #define PAGE_KERNEL __pgprot(__PAGE_KERNEL) #define PAGE_KERNEL_RO __pgprot(__PAGE_KERNEL_RO) #define PAGE_KERNEL_EXEC __pgprot(__PAGE_KERNEL_EXEC) @@ -113,6 +118,11 @@ #define PAGE_KERNEL_VSYSCALL __pgprot(__PAGE_KERNEL_VSYSCALL) #define PAGE_KERNEL_VSYSCALL_NOCACHE __pgprot(__PAGE_KERNEL_VSYSCALL_NOCACHE) +#define PAGE_KERNEL_IO __pgprot(__PAGE_KERNEL_IO) +#define PAGE_KERNEL_IO_NOCACHE __pgprot(__PAGE_KERNEL_IO_NOCACHE) +#define PAGE_KERNEL_IO_UC_MINUS __pgprot(__PAGE_KERNEL_IO_UC_MINUS) +#define PAGE_KERNEL_IO_WC __pgprot(__PAGE_KERNEL_IO_WC) + /* xwr */ #define __P000 PAGE_NONE #define __P001 PAGE_READONLY @@ -196,7 +206,7 @@ static inline int pte_exec(pte_t pte) static inline int pte_special(pte_t pte) { - return pte_val(pte) & _PAGE_SPECIAL; + return pte_flags(pte) & _PAGE_SPECIAL; } static inline unsigned long pte_pfn(pte_t pte) diff --git a/include/asm-x86/ptrace.h b/include/asm-x86/ptrace.h index ac578f11c1c5..a2025525a15a 100644 --- a/include/asm-x86/ptrace.h +++ b/include/asm-x86/ptrace.h @@ -174,12 +174,8 @@ extern unsigned long profile_pc(struct pt_regs *regs); extern unsigned long convert_ip_to_linear(struct task_struct *child, struct pt_regs *regs); - -#ifdef CONFIG_X86_32 extern void send_sigtrap(struct task_struct *tsk, struct pt_regs *regs, int error_code, int si_code); -#endif - void signal_fault(struct pt_regs *regs, void __user *frame, char *where); extern long syscall_trace_enter(struct pt_regs *); diff --git a/include/asm-x86/segment.h b/include/asm-x86/segment.h index ea5f0a8686f7..5d6e69454891 100644 --- a/include/asm-x86/segment.h +++ b/include/asm-x86/segment.h @@ -131,12 +131,6 @@ * Matching rules for certain types of segments. */ -/* Matches only __KERNEL_CS, ignoring PnP / USER / APM segments */ -#define SEGMENT_IS_KERNEL_CODE(x) (((x) & 0xfc) == GDT_ENTRY_KERNEL_CS * 8) - -/* Matches __KERNEL_CS and __USER_CS (they must be 2 entries apart) */ -#define SEGMENT_IS_FLAT_CODE(x) (((x) & 0xec) == GDT_ENTRY_KERNEL_CS * 8) - /* Matches PNP_CS32 and PNP_CS16 (they must be consecutive) */ #define SEGMENT_IS_PNP_CODE(x) (((x) & 0xf4) == GDT_ENTRY_PNPBIOS_BASE * 8) diff --git a/include/asm-x86/smp.h b/include/asm-x86/smp.h index 6df2615f9138..a6afc29f2dd9 100644 --- a/include/asm-x86/smp.h +++ b/include/asm-x86/smp.h @@ -141,6 +141,8 @@ void play_dead_common(void); void native_send_call_func_ipi(cpumask_t mask); void native_send_call_func_single_ipi(int cpu); +extern void prefill_possible_map(void); + void smp_store_cpu_info(int id); #define cpu_physical_id(cpu) per_cpu(x86_cpu_to_apicid, cpu) @@ -149,15 +151,11 @@ static inline int num_booting_cpus(void) { return cpus_weight(cpu_callout_map); } -#endif /* CONFIG_SMP */ - -#if defined(CONFIG_SMP) && defined(CONFIG_HOTPLUG_CPU) -extern void prefill_possible_map(void); #else static inline void prefill_possible_map(void) { } -#endif +#endif /* CONFIG_SMP */ extern unsigned disabled_cpus __cpuinitdata; diff --git a/include/asm-x86/system.h b/include/asm-x86/system.h index 34505dd7b24d..b20c894660f9 100644 --- a/include/asm-x86/system.h +++ b/include/asm-x86/system.h @@ -64,7 +64,10 @@ do { \ \ /* regparm parameters for __switch_to(): */ \ [prev] "a" (prev), \ - [next] "d" (next)); \ + [next] "d" (next) \ + \ + : /* reloaded segment registers */ \ + "memory"); \ } while (0) /* diff --git a/include/asm-x86/traps.h b/include/asm-x86/traps.h index 7a692baa51ae..6c3dc2c65751 100644 --- a/include/asm-x86/traps.h +++ b/include/asm-x86/traps.h @@ -3,7 +3,12 @@ #include <asm/debugreg.h> -/* Common in X86_32 and X86_64 */ +#ifdef CONFIG_X86_32 +#define dotraplinkage +#else +#define dotraplinkage asmlinkage +#endif + asmlinkage void divide_error(void); asmlinkage void debug(void); asmlinkage void nmi(void); @@ -12,31 +17,47 @@ asmlinkage void overflow(void); asmlinkage void bounds(void); asmlinkage void invalid_op(void); asmlinkage void device_not_available(void); +#ifdef CONFIG_X86_64 +asmlinkage void double_fault(void); +#endif asmlinkage void coprocessor_segment_overrun(void); asmlinkage void invalid_TSS(void); asmlinkage void segment_not_present(void); asmlinkage void stack_segment(void); asmlinkage void general_protection(void); asmlinkage void page_fault(void); +asmlinkage void spurious_interrupt_bug(void); asmlinkage void coprocessor_error(void); -asmlinkage void simd_coprocessor_error(void); asmlinkage void alignment_check(void); -asmlinkage void spurious_interrupt_bug(void); #ifdef CONFIG_X86_MCE asmlinkage void machine_check(void); #endif /* CONFIG_X86_MCE */ +asmlinkage void simd_coprocessor_error(void); -void do_divide_error(struct pt_regs *, long); -void do_overflow(struct pt_regs *, long); -void do_bounds(struct pt_regs *, long); -void do_coprocessor_segment_overrun(struct pt_regs *, long); -void do_invalid_TSS(struct pt_regs *, long); -void do_segment_not_present(struct pt_regs *, long); -void do_stack_segment(struct pt_regs *, long); -void do_alignment_check(struct pt_regs *, long); -void do_invalid_op(struct pt_regs *, long); -void do_general_protection(struct pt_regs *, long); -void do_nmi(struct pt_regs *, long); +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); +dotraplinkage void do_int3(struct pt_regs *, long); +dotraplinkage void do_overflow(struct pt_regs *, long); +dotraplinkage void do_bounds(struct pt_regs *, long); +dotraplinkage void do_invalid_op(struct pt_regs *, long); +dotraplinkage void do_device_not_available(struct pt_regs *, long); +dotraplinkage void do_coprocessor_segment_overrun(struct pt_regs *, long); +dotraplinkage void do_invalid_TSS(struct pt_regs *, long); +dotraplinkage void do_segment_not_present(struct pt_regs *, long); +dotraplinkage void do_stack_segment(struct pt_regs *, long); +dotraplinkage void do_general_protection(struct pt_regs *, long); +dotraplinkage void do_page_fault(struct pt_regs *, unsigned long); +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); +#ifdef CONFIG_X86_MCE +dotraplinkage void do_machine_check(struct pt_regs *, long); +#endif +dotraplinkage void do_simd_coprocessor_error(struct pt_regs *, long); +#ifdef CONFIG_X86_32 +dotraplinkage void do_iret_error(struct pt_regs *, long); +#endif static inline int get_si_code(unsigned long condition) { @@ -52,31 +73,9 @@ extern int panic_on_unrecovered_nmi; extern int kstack_depth_to_print; #ifdef CONFIG_X86_32 - -void do_iret_error(struct pt_regs *, long); -void do_int3(struct pt_regs *, long); -void do_debug(struct pt_regs *, long); void math_error(void __user *); -void do_coprocessor_error(struct pt_regs *, long); -void do_simd_coprocessor_error(struct pt_regs *, long); -void do_spurious_interrupt_bug(struct pt_regs *, long); unsigned long patch_espfix_desc(unsigned long, unsigned long); asmlinkage void math_emulate(long); +#endif -void do_page_fault(struct pt_regs *regs, unsigned long error_code); - -#else /* CONFIG_X86_32 */ - -asmlinkage void double_fault(void); - -asmlinkage void do_int3(struct pt_regs *, long); -asmlinkage void do_stack_segment(struct pt_regs *, long); -asmlinkage void do_debug(struct pt_regs *, unsigned long); -asmlinkage void do_coprocessor_error(struct pt_regs *); -asmlinkage void do_simd_coprocessor_error(struct pt_regs *); -asmlinkage void do_spurious_interrupt_bug(struct pt_regs *); - -asmlinkage void do_page_fault(struct pt_regs *regs, unsigned long error_code); - -#endif /* CONFIG_X86_32 */ #endif /* ASM_X86__TRAPS_H */ diff --git a/include/linux/hpet.h b/include/linux/hpet.h index 2dc29ce6c8e4..79f63a27bcef 100644 --- a/include/linux/hpet.h +++ b/include/linux/hpet.h @@ -37,6 +37,7 @@ struct hpet { #define hpet_compare _u1._hpet_compare #define HPET_MAX_TIMERS (32) +#define HPET_MAX_IRQ (32) /* * HPET general capabilities register @@ -64,7 +65,7 @@ struct hpet { */ #define Tn_INT_ROUTE_CAP_MASK (0xffffffff00000000ULL) -#define Tn_INI_ROUTE_CAP_SHIFT (32UL) +#define Tn_INT_ROUTE_CAP_SHIFT (32UL) #define Tn_FSB_INT_DELCAP_MASK (0x8000UL) #define Tn_FSB_INT_DELCAP_SHIFT (15) #define Tn_FSB_EN_CNF_MASK (0x4000UL) @@ -91,23 +92,14 @@ struct hpet { * exported interfaces */ -struct hpet_task { - void (*ht_func) (void *); - void *ht_data; - void *ht_opaque; -}; - struct hpet_data { unsigned long hd_phys_address; void __iomem *hd_address; unsigned short hd_nirqs; - unsigned short hd_flags; unsigned int hd_state; /* timer allocated */ unsigned int hd_irq[HPET_MAX_TIMERS]; }; -#define HPET_DATA_PLATFORM 0x0001 /* platform call to hpet_alloc */ - static inline void hpet_reserve_timer(struct hpet_data *hd, int timer) { hd->hd_state |= (1 << timer); @@ -125,7 +117,7 @@ struct hpet_info { unsigned short hi_timer; }; -#define HPET_INFO_PERIODIC 0x0001 /* timer is periodic */ +#define HPET_INFO_PERIODIC 0x0010 /* periodic-capable comparator */ #define HPET_IE_ON _IO('h', 0x01) /* interrupt on */ #define HPET_IE_OFF _IO('h', 0x02) /* interrupt off */ diff --git a/include/linux/oprofile.h b/include/linux/oprofile.h index 041bb31100f4..bcb8f725427c 100644 --- a/include/linux/oprofile.h +++ b/include/linux/oprofile.h @@ -36,6 +36,8 @@ #define XEN_ENTER_SWITCH_CODE 10 #define SPU_PROFILING_CODE 11 #define SPU_CTX_SWITCH_CODE 12 +#define IBS_FETCH_CODE 13 +#define IBS_OP_CODE 14 struct super_block; struct dentry; |