diff options
| author | Ingo Molnar <mingo@elte.hu> | 2011-01-07 14:14:15 +0100 |
|---|---|---|
| committer | Ingo Molnar <mingo@elte.hu> | 2011-01-07 14:14:15 +0100 |
| commit | 1c2a48cf65580a276552151eb8f78d78c55b828e (patch) | |
| tree | 68ed0628a276b33cb5aa0ad4899c1afe0a33a69d /arch/x86 | |
| parent | 0aa002fe602939370e9476e5ec32b562000a0425 (diff) | |
| parent | cb600d2f83c854ec3d6660063e4466431999489b (diff) | |
Merge branch 'linus' into x86/apic-cleanups
Conflicts:
arch/x86/include/asm/io_apic.h
Merge reason: Resolve the conflict, update to a more recent -rc base
Signed-off-by: Ingo Molnar <mingo@elte.hu>
Diffstat (limited to 'arch/x86')
118 files changed, 1437 insertions, 2006 deletions
diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig index 58ecad57aad1..b6fccb07123e 100644 --- a/arch/x86/Kconfig +++ b/arch/x86/Kconfig @@ -21,7 +21,7 @@ config X86 select HAVE_UNSTABLE_SCHED_CLOCK select HAVE_IDE select HAVE_OPROFILE - select HAVE_PERF_EVENTS if (!M386 && !M486) + select HAVE_PERF_EVENTS select HAVE_IRQ_WORK select HAVE_IOREMAP_PROT select HAVE_KPROBES diff --git a/arch/x86/Kconfig.debug b/arch/x86/Kconfig.debug index b59ee765414e..45143bbcfe5e 100644 --- a/arch/x86/Kconfig.debug +++ b/arch/x86/Kconfig.debug @@ -117,6 +117,17 @@ config DEBUG_RODATA_TEST feature as well as for the change_page_attr() infrastructure. If in doubt, say "N" +config DEBUG_SET_MODULE_RONX + bool "Set loadable kernel module data as NX and text as RO" + depends on MODULES + ---help--- + This option helps catch unintended modifications to loadable + kernel module's text and read-only data. It also prevents execution + of module data. Such protection may interfere with run-time code + patching and dynamic kernel tracing - and they might also protect + against certain classes of kernel exploits. + If in doubt, say "N". + config DEBUG_NX_TEST tristate "Testcase for the NX non-executable stack feature" depends on DEBUG_KERNEL && m diff --git a/arch/x86/boot/compressed/head_64.S b/arch/x86/boot/compressed/head_64.S index 52f85a196fa0..35af09d13dc1 100644 --- a/arch/x86/boot/compressed/head_64.S +++ b/arch/x86/boot/compressed/head_64.S @@ -182,7 +182,7 @@ no_longmode: hlt jmp 1b -#include "../../kernel/verify_cpu_64.S" +#include "../../kernel/verify_cpu.S" /* * Be careful here startup_64 needs to be at a predictable diff --git a/arch/x86/boot/compressed/misc.c b/arch/x86/boot/compressed/misc.c index 23f315c9f215..325c05294fc4 100644 --- a/arch/x86/boot/compressed/misc.c +++ b/arch/x86/boot/compressed/misc.c @@ -355,7 +355,7 @@ asmlinkage void decompress_kernel(void *rmode, memptr heap, if (heap > 0x3fffffffffffUL) error("Destination address too large"); #else - if (heap > ((-__PAGE_OFFSET-(512<<20)-1) & 0x7fffffff)) + if (heap > ((-__PAGE_OFFSET-(128<<20)-1) & 0x7fffffff)) error("Destination address too large"); #endif #ifndef CONFIG_RELOCATABLE diff --git a/arch/x86/crypto/ghash-clmulni-intel_glue.c b/arch/x86/crypto/ghash-clmulni-intel_glue.c index cbcc8d8ea93a..7a6e68e4f748 100644 --- a/arch/x86/crypto/ghash-clmulni-intel_glue.c +++ b/arch/x86/crypto/ghash-clmulni-intel_glue.c @@ -10,6 +10,7 @@ * by the Free Software Foundation. */ +#include <linux/err.h> #include <linux/module.h> #include <linux/init.h> #include <linux/kernel.h> diff --git a/arch/x86/ia32/sys_ia32.c b/arch/x86/ia32/sys_ia32.c index 849813f398e7..5852519b2d0f 100644 --- a/arch/x86/ia32/sys_ia32.c +++ b/arch/x86/ia32/sys_ia32.c @@ -28,7 +28,6 @@ #include <linux/syscalls.h> #include <linux/times.h> #include <linux/utsname.h> -#include <linux/smp_lock.h> #include <linux/mm.h> #include <linux/uio.h> #include <linux/poll.h> diff --git a/arch/x86/include/asm/alternative.h b/arch/x86/include/asm/alternative.h index 76561d20ea2f..13009d1af99a 100644 --- a/arch/x86/include/asm/alternative.h +++ b/arch/x86/include/asm/alternative.h @@ -66,6 +66,7 @@ extern void alternatives_smp_module_add(struct module *mod, char *name, extern void alternatives_smp_module_del(struct module *mod); extern void alternatives_smp_switch(int smp); extern int alternatives_text_reserved(void *start, void *end); +extern bool skip_smp_alternatives; #else static inline void alternatives_smp_module_add(struct module *mod, char *name, void *locks, void *locks_end, @@ -180,8 +181,15 @@ extern void *text_poke_early(void *addr, const void *opcode, size_t len); * On the local CPU you need to be protected again NMI or MCE handlers seeing an * inconsistent instruction while you patch. */ +struct text_poke_param { + void *addr; + const void *opcode; + size_t len; +}; + extern void *text_poke(void *addr, const void *opcode, size_t len); extern void *text_poke_smp(void *addr, const void *opcode, size_t len); +extern void text_poke_smp_batch(struct text_poke_param *params, int n); #if defined(CONFIG_DYNAMIC_FTRACE) || defined(HAVE_JUMP_LABEL) #define IDEAL_NOP_SIZE_5 5 diff --git a/arch/x86/include/asm/apicdef.h b/arch/x86/include/asm/apicdef.h index a859ca461fb0..47a30ff8e517 100644 --- a/arch/x86/include/asm/apicdef.h +++ b/arch/x86/include/asm/apicdef.h @@ -145,6 +145,7 @@ #ifdef CONFIG_X86_32 # define MAX_IO_APICS 64 +# define MAX_LOCAL_APIC 256 #else # define MAX_IO_APICS 128 # define MAX_LOCAL_APIC 32768 diff --git a/arch/x86/include/asm/e820.h b/arch/x86/include/asm/e820.h index 5be1542fbfaf..e99d55d74df5 100644 --- a/arch/x86/include/asm/e820.h +++ b/arch/x86/include/asm/e820.h @@ -72,6 +72,9 @@ struct e820map { #define BIOS_BEGIN 0x000a0000 #define BIOS_END 0x00100000 +#define BIOS_ROM_BASE 0xffe00000 +#define BIOS_ROM_END 0xffffffff + #ifdef __KERNEL__ /* see comment in arch/x86/kernel/e820.c */ extern struct e820map e820; diff --git a/arch/x86/include/asm/fixmap.h b/arch/x86/include/asm/fixmap.h index 139591a933f6..0141b234406f 100644 --- a/arch/x86/include/asm/fixmap.h +++ b/arch/x86/include/asm/fixmap.h @@ -220,8 +220,8 @@ static inline unsigned long virt_to_fix(const unsigned long vaddr) } /* Return an pointer with offset calculated */ -static inline unsigned long __set_fixmap_offset(enum fixed_addresses idx, - phys_addr_t phys, pgprot_t flags) +static __always_inline unsigned long +__set_fixmap_offset(enum fixed_addresses idx, phys_addr_t phys, pgprot_t flags) { __set_fixmap(idx, phys, flags); return fix_to_virt(idx) + (phys & (PAGE_SIZE - 1)); diff --git a/arch/x86/include/asm/i387.h b/arch/x86/include/asm/i387.h index 4aa2bb3b242a..ef328901c802 100644 --- a/arch/x86/include/asm/i387.h +++ b/arch/x86/include/asm/i387.h @@ -93,6 +93,17 @@ static inline int fxrstor_checking(struct i387_fxsave_struct *fx) int err; /* See comment in fxsave() below. */ +#ifdef CONFIG_AS_FXSAVEQ + asm volatile("1: fxrstorq %[fx]\n\t" + "2:\n" + ".section .fixup,\"ax\"\n" + "3: movl $-1,%[err]\n" + " jmp 2b\n" + ".previous\n" + _ASM_EXTABLE(1b, 3b) + : [err] "=r" (err) + : [fx] "m" (*fx), "0" (0)); +#else asm volatile("1: rex64/fxrstor (%[fx])\n\t" "2:\n" ".section .fixup,\"ax\"\n" @@ -102,6 +113,7 @@ static inline int fxrstor_checking(struct i387_fxsave_struct *fx) _ASM_EXTABLE(1b, 3b) : [err] "=r" (err) : [fx] "R" (fx), "m" (*fx), "0" (0)); +#endif return err; } @@ -119,6 +131,17 @@ static inline int fxsave_user(struct i387_fxsave_struct __user *fx) return -EFAULT; /* See comment in fxsave() below. */ +#ifdef CONFIG_AS_FXSAVEQ + asm volatile("1: fxsaveq %[fx]\n\t" + "2:\n" + ".section .fixup,\"ax\"\n" + "3: movl $-1,%[err]\n" + " jmp 2b\n" + ".previous\n" + _ASM_EXTABLE(1b, 3b) + : [err] "=r" (err), [fx] "=m" (*fx) + : "0" (0)); +#else asm volatile("1: rex64/fxsave (%[fx])\n\t" "2:\n" ".section .fixup,\"ax\"\n" @@ -128,6 +151,7 @@ static inline int fxsave_user(struct i387_fxsave_struct __user *fx) _ASM_EXTABLE(1b, 3b) : [err] "=r" (err), "=m" (*fx) : [fx] "R" (fx), "0" (0)); +#endif if (unlikely(err) && __clear_user(fx, sizeof(struct i387_fxsave_struct))) err = -EFAULT; diff --git a/arch/x86/include/asm/irq.h b/arch/x86/include/asm/irq.h index 13b0ebaa512f..ba870bb6dd8e 100644 --- a/arch/x86/include/asm/irq.h +++ b/arch/x86/include/asm/irq.h @@ -15,10 +15,6 @@ static inline int irq_canonicalize(int irq) return ((irq == 2) ? 9 : irq); } -#ifdef CONFIG_X86_LOCAL_APIC -# define ARCH_HAS_NMI_WATCHDOG -#endif - #ifdef CONFIG_X86_32 extern void irq_ctx_init(int cpu); #else diff --git a/arch/x86/include/asm/kdebug.h b/arch/x86/include/asm/kdebug.h index 5bdfca86581b..f23eb2528464 100644 --- a/arch/x86/include/asm/kdebug.h +++ b/arch/x86/include/asm/kdebug.h @@ -28,7 +28,7 @@ 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_trace(struct task_struct *t, struct pt_regs *regs, - unsigned long *sp, unsigned long bp); + unsigned long *sp); extern void __show_regs(struct pt_regs *regs, int all); extern void show_regs(struct pt_regs *regs); extern unsigned long oops_begin(void); diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h index 9e6fe391094e..f702f82aa1eb 100644 --- a/arch/x86/include/asm/kvm_host.h +++ b/arch/x86/include/asm/kvm_host.h @@ -79,7 +79,7 @@ #define KVM_NUM_MMU_PAGES (1 << KVM_MMU_HASH_SHIFT) #define KVM_MIN_FREE_MMU_PAGES 5 #define KVM_REFILL_PAGES 25 -#define KVM_MAX_CPUID_ENTRIES 40 +#define KVM_MAX_CPUID_ENTRIES 80 #define KVM_NR_FIXED_MTRR_REGION 88 #define KVM_NR_VAR_MTRR 8 diff --git a/arch/x86/include/asm/mce.h b/arch/x86/include/asm/mce.h index c62c13cb9788..eb16e94ae04f 100644 --- a/arch/x86/include/asm/mce.h +++ b/arch/x86/include/asm/mce.h @@ -223,6 +223,9 @@ void intel_init_thermal(struct cpuinfo_x86 *c); void mce_log_therm_throt_event(__u64 status); +/* Interrupt Handler for core thermal thresholds */ +extern int (*platform_thermal_notify)(__u64 msr_val); + #ifdef CONFIG_X86_THERMAL_VECTOR extern void mcheck_intel_therm_init(void); #else diff --git a/arch/x86/include/asm/microcode.h b/arch/x86/include/asm/microcode.h index ef51b501e22a..24215072d0e1 100644 --- a/arch/x86/include/asm/microcode.h +++ b/arch/x86/include/asm/microcode.h @@ -48,6 +48,12 @@ static inline struct microcode_ops * __init init_intel_microcode(void) #ifdef CONFIG_MICROCODE_AMD extern struct microcode_ops * __init init_amd_microcode(void); + +static inline void get_ucode_data(void *to, const u8 *from, size_t n) +{ + memcpy(to, from, n); +} + #else static inline struct microcode_ops * __init init_amd_microcode(void) { diff --git a/arch/x86/include/asm/mpspec.h b/arch/x86/include/asm/mpspec.h index c82868e9f905..0c90dd9f0505 100644 --- a/arch/x86/include/asm/mpspec.h +++ b/arch/x86/include/asm/mpspec.h @@ -5,8 +5,9 @@ #include <asm/mpspec_def.h> #include <asm/x86_init.h> +#include <asm/apicdef.h> -extern int apic_version[MAX_APICS]; +extern int apic_version[]; extern int pic_mode; #ifdef CONFIG_X86_32 @@ -107,7 +108,7 @@ extern int mp_register_gsi(struct device *dev, u32 gsi, int edge_level, int active_high_low); #endif /* CONFIG_ACPI */ -#define PHYSID_ARRAY_SIZE BITS_TO_LONGS(MAX_APICS) +#define PHYSID_ARRAY_SIZE BITS_TO_LONGS(MAX_LOCAL_APIC) struct physid_mask { unsigned long mask[PHYSID_ARRAY_SIZE]; @@ -122,31 +123,31 @@ typedef struct physid_mask physid_mask_t; test_and_set_bit(physid, (map).mask) #define physids_and(dst, src1, src2) \ - bitmap_and((dst).mask, (src1).mask, (src2).mask, MAX_APICS) + bitmap_and((dst).mask, (src1).mask, (src2).mask, MAX_LOCAL_APIC) #define physids_or(dst, src1, src2) \ - bitmap_or((dst).mask, (src1).mask, (src2).mask, MAX_APICS) + bitmap_or((dst).mask, (src1).mask, (src2).mask, MAX_LOCAL_APIC) #define physids_clear(map) \ - bitmap_zero((map).mask, MAX_APICS) + bitmap_zero((map).mask, MAX_LOCAL_APIC) #define physids_complement(dst, src) \ - bitmap_complement((dst).mask, (src).mask, MAX_APICS) + bitmap_complement((dst).mask, (src).mask, MAX_LOCAL_APIC) #define physids_empty(map) \ - bitmap_empty((map).mask, MAX_APICS) + bitmap_empty((map).mask, MAX_LOCAL_APIC) #define physids_equal(map1, map2) \ - bitmap_equal((map1).mask, (map2).mask, MAX_APICS) + bitmap_equal((map1).mask, (map2).mask, MAX_LOCAL_APIC) #define physids_weight(map) \ - bitmap_weight((map).mask, MAX_APICS) + bitmap_weight((map).mask, MAX_LOCAL_APIC) #define physids_shift_right(d, s, n) \ - bitmap_shift_right((d).mask, (s).mask, n, MAX_APICS) + bitmap_shift_right((d).mask, (s).mask, n, MAX_LOCAL_APIC) #define physids_shift_left(d, s, n) \ - bitmap_shift_left((d).mask, (s).mask, n, MAX_APICS) + bitmap_shift_left((d).mask, (s).mask, n, MAX_LOCAL_APIC) static inline unsigned long physids_coerce(physid_mask_t *map) { @@ -159,14 +160,6 @@ static inline void physids_promote(unsigned long physids, physid_mask_t *map) map->mask[0] = physids; } -/* Note: will create very large stack frames if physid_mask_t is big */ -#define physid_mask_of_physid(physid) \ - ({ \ - physid_mask_t __physid_mask = PHYSID_MASK_NONE; \ - physid_set(physid, __physid_mask); \ - __physid_mask; \ - }) - static inline void physid_set_mask_of_physid(int physid, physid_mask_t *map) { physids_clear(*map); diff --git a/arch/x86/include/asm/mpspec_def.h b/arch/x86/include/asm/mpspec_def.h index 4a7f96d7c188..c0a955a9a087 100644 --- a/arch/x86/include/asm/mpspec_def.h +++ b/arch/x86/include/asm/mpspec_def.h @@ -15,13 +15,6 @@ #ifdef CONFIG_X86_32 # define MAX_MPC_ENTRY 1024 -# define MAX_APICS 256 -#else -# if NR_CPUS <= 255 -# define MAX_APICS 255 -# else -# define MAX_APICS 32768 -# endif #endif /* Intel MP Floating Pointer Structure */ diff --git a/arch/x86/include/asm/msr-index.h b/arch/x86/include/asm/msr-index.h index 3ea3dc487047..4d0dfa0d998e 100644 --- a/arch/x86/include/asm/msr-index.h +++ b/arch/x86/include/asm/msr-index.h @@ -123,12 +123,16 @@ #define MSR_AMD64_IBSCTL 0xc001103a #define MSR_AMD64_IBSBRTARGET 0xc001103b +/* Fam 15h MSRs */ +#define MSR_F15H_PERF_CTL 0xc0010200 +#define MSR_F15H_PERF_CTR 0xc0010201 + /* Fam 10h MSRs */ #define MSR_FAM10H_MMIO_CONF_BASE 0xc0010058 #define FAM10H_MMIO_CONF_ENABLE (1<<0) #define FAM10H_MMIO_CONF_BUSRANGE_MASK 0xf #define FAM10H_MMIO_CONF_BUSRANGE_SHIFT 2 -#define FAM10H_MMIO_CONF_BASE_MASK 0xfffffff +#define FAM10H_MMIO_CONF_BASE_MASK 0xfffffffULL #define FAM10H_MMIO_CONF_BASE_SHIFT 20 #define MSR_FAM10H_NODE_ID 0xc001100c @@ -253,6 +257,18 @@ #define PACKAGE_THERM_INT_LOW_ENABLE (1 << 1) #define PACKAGE_THERM_INT_PLN_ENABLE (1 << 24) +/* Thermal Thresholds Support */ +#define THERM_INT_THRESHOLD0_ENABLE (1 << 15) +#define THERM_SHIFT_THRESHOLD0 8 +#define THERM_MASK_THRESHOLD0 (0x7f << THERM_SHIFT_THRESHOLD0) +#define THERM_INT_THRESHOLD1_ENABLE (1 << 23) +#define THERM_SHIFT_THRESHOLD1 16 +#define THERM_MASK_THRESHOLD1 (0x7f << THERM_SHIFT_THRESHOLD1) +#define THERM_STATUS_THRESHOLD0 (1 << 6) +#define THERM_LOG_THRESHOLD0 (1 << 7) +#define THERM_STATUS_THRESHOLD1 (1 << 8) +#define THERM_LOG_THRESHOLD1 (1 << 9) + /* MISC_ENABLE bits: architectural */ #define MSR_IA32_MISC_ENABLE_FAST_STRING (1ULL << 0) #define MSR_IA32_MISC_ENABLE_TCC (1ULL << 1) diff --git a/arch/x86/include/asm/nmi.h b/arch/x86/include/asm/nmi.h index 932f0f86b4b7..c4021b953510 100644 --- a/arch/x86/include/asm/nmi.h +++ b/arch/x86/include/asm/nmi.h @@ -5,41 +5,15 @@ #include <asm/irq.h> #include <asm/io.h> -#ifdef ARCH_HAS_NMI_WATCHDOG - -/** - * do_nmi_callback - * - * Check to see if a callback exists and execute it. Return 1 - * if the handler exists and was handled successfully. - */ -int do_nmi_callback(struct pt_regs *regs, int cpu); +#ifdef CONFIG_X86_LOCAL_APIC extern void die_nmi(char *str, struct pt_regs *regs, int do_panic); -extern int check_nmi_watchdog(void); -#if !defined(CONFIG_LOCKUP_DETECTOR) -extern int nmi_watchdog_enabled; -#endif extern int avail_to_resrv_perfctr_nmi_bit(unsigned int); extern int reserve_perfctr_nmi(unsigned int); extern void release_perfctr_nmi(unsigned int); extern int reserve_evntsel_nmi(unsigned int); extern void release_evntsel_nmi(unsigned int); -extern void setup_apic_nmi_watchdog(void *); -extern void stop_apic_nmi_watchdog(void *); -extern void disable_timer_nmi_watchdog(void); -extern void enable_timer_nmi_watchdog(void); -extern int nmi_watchdog_tick(struct pt_regs *regs, unsigned reason); -extern void cpu_nmi_set_wd_enabled(void); - -extern atomic_t nmi_active; -extern unsigned int nmi_watchdog; -#define NMI_NONE 0 -#define NMI_IO_APIC 1 -#define NMI_LOCAL_APIC 2 -#define NMI_INVALID 3 - struct ctl_table; extern int proc_nmi_enabled(struct ctl_table *, int , void __user *, size_t *, loff_t *); @@ -47,33 +21,8 @@ extern int unknown_nmi_panic; void arch_trigger_all_cpu_backtrace(void); #define arch_trigger_all_cpu_backtrace arch_trigger_all_cpu_backtrace - -static inline void localise_nmi_watchdog(void) -{ - if (nmi_watchdog == NMI_IO_APIC) - nmi_watchdog = NMI_LOCAL_APIC; -} - -/* check if nmi_watchdog is active (ie was specified at boot) */ -static inline int nmi_watchdog_active(void) -{ - /* - * actually it should be: - * return (nmi_watchdog == NMI_LOCAL_APIC || - * nmi_watchdog == NMI_IO_APIC) - * but since they are power of two we could use a - * cheaper way --cvg - */ - return nmi_watchdog & (NMI_LOCAL_APIC | NMI_IO_APIC); -} #endif -void lapic_watchdog_stop(void); -int lapic_watchdog_init(unsigned nmi_hz); -int lapic_wd_event(unsigned nmi_hz); -unsigned lapic_adjust_nmi_hz(unsigned hz); -void disable_lapic_nmi_watchdog(void); -void enable_lapic_nmi_watchdog(void); void stop_nmi(void); void restart_nmi(void); diff --git a/arch/x86/include/asm/paravirt.h b/arch/x86/include/asm/paravirt.h index 18e3b8a8709f..7709c12431b8 100644 --- a/arch/x86/include/asm/paravirt.h +++ b/arch/x86/include/asm/paravirt.h @@ -112,7 +112,7 @@ static inline void arch_safe_halt(void) static inline void halt(void) { - PVOP_VCALL0(pv_irq_ops.safe_halt); + PVOP_VCALL0(pv_irq_ops.halt); } static inline void wbinvd(void) @@ -824,27 +824,27 @@ static __always_inline void arch_spin_unlock(struct arch_spinlock *lock) #define __PV_IS_CALLEE_SAVE(func) \ ((struct paravirt_callee_save) { func }) -static inline unsigned long arch_local_save_flags(void) +static inline notrace unsigned long arch_local_save_flags(void) { return PVOP_CALLEE0(unsigned long, pv_irq_ops.save_fl); } -static inline void arch_local_irq_restore(unsigned long f) +static inline notrace void arch_local_irq_restore(unsigned long f) { PVOP_VCALLEE1(pv_irq_ops.restore_fl, f); } -static inline void arch_local_irq_disable(void) +static inline notrace void arch_local_irq_disable(void) { PVOP_VCALLEE0(pv_irq_ops.irq_disable); } -static inline void arch_local_irq_enable(void) +static inline notrace void arch_local_irq_enable(void) { PVOP_VCALLEE0(pv_irq_ops.irq_enable); } -static inline unsigned long arch_local_irq_save(void) +static inline notrace unsigned long arch_local_irq_save(void) { unsigned long f; diff --git a/arch/x86/include/asm/pci.h b/arch/x86/include/asm/pci.h index ca0437c714b2..676129229630 100644 --- a/arch/x86/include/asm/pci.h +++ b/arch/x86/include/asm/pci.h @@ -65,6 +65,7 @@ extern unsigned long pci_mem_start; #define PCIBIOS_MIN_CARDBUS_IO 0x4000 +extern int pcibios_enabled; void pcibios_config_init(void); struct pci_bus *pcibios_scan_root(int bus); diff --git a/arch/x86/include/asm/perf_event.h b/arch/x86/include/asm/perf_event.h index 550e26b1dbb3..d9d4dae305f6 100644 --- a/arch/x86/include/asm/perf_event.h +++ b/arch/x86/include/asm/perf_event.h @@ -125,7 +125,6 @@ union cpuid10_edx { #define IBS_OP_MAX_CNT_EXT 0x007FFFFFULL /* not a register bit mask */ #ifdef CONFIG_PERF_EVENTS -extern void init_hw_perf_events(void); extern void perf_events_lapic_init(void); #define PERF_EVENT_INDEX_OFFSET 0 @@ -156,7 +155,6 @@ extern unsigned long perf_misc_flags(struct pt_regs *regs); } #else -static inline void init_hw_perf_events(void) { } static inline void perf_events_lapic_init(void) { } #endif diff --git a/arch/x86/include/asm/perf_event_p4.h b/arch/x86/include/asm/perf_event_p4.h index a70cd216be5d..295e2ff18a6a 100644 --- a/arch/x86/include/asm/perf_event_p4.h +++ b/arch/x86/include/asm/perf_event_p4.h @@ -744,14 +744,6 @@ enum P4_ESCR_EMASKS { }; /* - * P4 PEBS specifics (Replay Event only) - * - * Format (bits): - * 0-6: metric from P4_PEBS_METRIC enum - * 7 : reserved - * 8 : reserved - * 9-11 : reserved - * * Note we have UOP and PEBS bits reserved for now * just in case if we will need them once */ @@ -788,5 +780,60 @@ enum P4_PEBS_METRIC { P4_PEBS_METRIC__max }; +/* + * Notes on internal configuration of ESCR+CCCR tuples + * + * Since P4 has quite the different architecture of + * performance registers in compare with "architectural" + * once and we have on 64 bits to keep configuration + * of performance event, the following trick is used. + * + * 1) Since both ESCR and CCCR registers have only low + * 32 bits valuable, we pack them into a single 64 bit + * configuration. Low 32 bits of such config correspond + * to low 32 bits of CCCR register and high 32 bits + * correspond to low 32 bits of ESCR register. + * + * 2) The meaning of every bit of such config field can + * be found in Intel SDM but it should be noted that + * we "borrow" some reserved bits for own usage and + * clean them or set to a proper value when we do + * a real write to hardware registers. + * + * 3) The format of bits of config is the following + * and should be either 0 or set to some predefined + * values: + * + * Low 32 bits + * ----------- + * 0-6: P4_PEBS_METRIC enum + * 7-11: reserved + * 12: reserved (Enable) + * 13-15: reserved (ESCR select) + * 16-17: Active Thread + * 18: Compare + * 19: Complement + * 20-23: Threshold + * 24: Edge + * 25: reserved (FORCE_OVF) + * 26: reserved (OVF_PMI_T0) + * 27: reserved (OVF_PMI_T1) + * 28-29: reserved + * 30: reserved (Cascade) + * 31: reserved (OVF) + * + * High 32 bits + * ------------ + * 0: reserved (T1_USR) + * 1: reserved (T1_OS) + * 2: reserved (T0_USR) + * 3: reserved (T0_OS) + * 4: Tag Enable + * 5-8: Tag Value + * 9-24: Event Mask (may use P4_ESCR_EMASK_BIT helper) + * 25-30: enum P4_EVENTS + * 31: reserved (HT thread) + */ + #endif /* PERF_EVENT_P4_H */ diff --git a/arch/x86/include/asm/pvclock.h b/arch/x86/include/asm/pvclock.h index 7f7e577a0e39..31d84acc1512 100644 --- a/arch/x86/include/asm/pvclock.h +++ b/arch/x86/include/asm/pvclock.h @@ -11,6 +11,7 @@ unsigned long pvclock_tsc_khz(struct pvclock_vcpu_time_info *src); void pvclock_read_wallclock(struct pvclock_wall_clock *wall, struct pvclock_vcpu_time_info *vcpu, struct timespec *ts); +void pvclock_resume(void); /* * Scale a 64-bit delta by scaling and multiplying by a 32-bit fraction, diff --git a/arch/x86/include/asm/smpboot_hooks.h b/arch/x86/include/asm/smpboot_hooks.h index 1def60114906..6c22bf353f26 100644 --- a/arch/x86/include/asm/smpboot_hooks.h +++ b/arch/x86/include/asm/smpboot_hooks.h @@ -48,7 +48,6 @@ static inline void __init smpboot_setup_io_apic(void) setup_IO_APIC(); else { nr_ioapics = 0; - localise_nmi_watchdog(); } #endif } diff --git a/arch/x86/include/asm/stacktrace.h b/arch/x86/include/asm/stacktrace.h index 2b16a2ad23dc..52b5c7ed3608 100644 --- a/arch/x86/include/asm/stacktrace.h +++ b/arch/x86/include/asm/stacktrace.h @@ -7,6 +7,7 @@ #define _ASM_X86_STACKTRACE_H #include <linux/uaccess.h> +#include <linux/ptrace.h> extern int kstack_depth_to_print; @@ -46,7 +47,7 @@ struct stacktrace_ops { }; void dump_trace(struct task_struct *tsk, struct pt_regs *regs, - unsigned long *stack, unsigned long bp, + unsigned long *stack, const struct stacktrace_ops *ops, void *data); #ifdef CONFIG_X86_32 @@ -57,13 +58,39 @@ void dump_trace(struct task_struct *tsk, struct pt_regs *regs, #define get_bp(bp) asm("movq %%rbp, %0" : "=r" (bp) :) #endif +#ifdef CONFIG_FRAME_POINTER +static inline unsigned long +stack_frame(struct task_struct *task, struct pt_regs *regs) +{ + unsigned long bp; + + if (regs) + return regs->bp; + + if (task == current) { + /* Grab bp right from our regs */ + get_bp(bp); + return bp; + } + + /* bp is the last reg pushed by switch_to */ + return *(unsigned long *)task->thread.sp; +} +#else +static inline unsigned long +stack_frame(struct task_struct *task, struct pt_regs *regs) +{ + return 0; +} +#endif + extern void show_trace_log_lvl(struct task_struct *task, struct pt_regs *regs, - unsigned long *stack, unsigned long bp, char *log_lvl); + unsigned long *stack, char *log_lvl); extern void show_stack_log_lvl(struct task_struct *task, struct pt_regs *regs, - unsigned long *sp, unsigned long bp, char *log_lvl); + unsigned long *sp, char *log_lvl); extern unsigned int code_bytes; diff --git a/arch/x86/include/asm/timer.h b/arch/x86/include/asm/timer.h index 5469630b27f5..fa7b9176b76c 100644 --- a/arch/x86/include/asm/timer.h +++ b/arch/x86/include/asm/timer.h @@ -10,12 +10,6 @@ unsigned long long native_sched_clock(void); extern int recalibrate_cpu_khz(void); -#if defined(CONFIG_X86_32) && defined(CONFIG_X86_IO_APIC) -extern int timer_ack; -#else -# define timer_ack (0) -#endif - extern int no_timer_check; /* Accelerators for sched_clock() diff --git a/arch/x86/include/asm/uv/uv_bau.h b/arch/x86/include/asm/uv/uv_bau.h index 42d412fd8b02..ce1d54c8a433 100644 --- a/arch/x86/include/asm/uv/uv_bau.h +++ b/arch/x86/include/asm/uv/uv_bau.h @@ -26,20 +26,22 @@ * BAU_SB_DESCRIPTOR_BASE register, set 1 is located at BASE + 512, * set 2 is at BASE + 2*512, set 3 at BASE + 3*512, and so on. * - * We will use 31 sets, one for sending BAU messages from each of the 32 + * We will use one set for sending BAU messages from each of the * cpu's on the uvhub. * * TLB shootdown will use the first of the 8 descriptors of each set. * Each of the descriptors is 64 bytes in size (8*64 = 512 bytes in a set). */ +#define MAX_CPUS_PER_UVHUB 64 +#define MAX_CPUS_PER_SOCKET 32 +#define UV_ADP_SIZE 64 /* hardware-provided max. */ +#define UV_CPUS_PER_ACT_STATUS 32 /* hardware-provided max. */ #define UV_ITEMS_PER_DESCRIPTOR 8 /* the 'throttle' to prevent the hardware stay-busy bug */ #define MAX_BAU_CONCURRENT 3 -#define UV_CPUS_PER_ACT_STATUS 32 #define UV_ACT_STATUS_MASK 0x3 #define UV_ACT_STATUS_SIZE 2 -#define UV_ADP_SIZE 32 #define UV_DISTRIBUTION_SIZE 256 #define UV_SW_ACK_NPENDING 8 #define UV_NET_ENDPOINT_INTD 0x38 @@ -100,7 +102,6 @@ * number of destination side software ack resources */ #define DEST_NUM_RESOURCES 8 -#define MAX_CPUS_PER_NODE 32 /* * completion statuses for sending a TLB flush message */ diff --git a/arch/x86/include/asm/uv/uv_hub.h b/arch/x86/include/asm/uv/uv_hub.h index e969f691cbfd..a501741c2335 100644 --- a/arch/x86/include/asm/uv/uv_hub.h +++ b/arch/x86/include/asm/uv/uv_hub.h @@ -199,6 +199,8 @@ union uvh_apicid { #define UVH_APICID 0x002D0E00L #define UV_APIC_PNODE_SHIFT 6 +#define UV_APICID_HIBIT_MASK 0xffff0000 + /* Local Bus from cpu's perspective */ #define LOCAL_BUS_BASE 0x1c00000 #define LOCAL_BUS_SIZE (4 * 1024 * 1024) @@ -491,8 +493,10 @@ static inline void uv_set_cpu_scir_bits(int cpu, unsigned char value) } } +extern unsigned int uv_apicid_hibits; static unsigned long uv_hub_ipi_value(int apicid, int vector, int mode) { + apicid |= uv_apicid_hibits; return (1UL << UVH_IPI_INT_SEND_SHFT) | ((apicid) << UVH_IPI_INT_APIC_ID_SHFT) | (mode << UVH_IPI_INT_DELIVERY_MODE_SHFT) | diff --git a/arch/x86/include/asm/uv/uv_mmrs.h b/arch/x86/include/asm/uv/uv_mmrs.h index 6d90adf4428a..20cafeac7455 100644 --- a/arch/x86/include/asm/uv/uv_mmrs.h +++ b/arch/x86/include/asm/uv/uv_mmrs.h @@ -5,7 +5,7 @@ * * SGI UV MMR definitions * - * Copyright (C) 2007-2008 Silicon Graphics, Inc. All rights reserved. + * Copyright (C) 2007-2010 Silicon Graphics, Inc. All rights reserved. */ #ifndef _ASM_X86_UV_UV_MMRS_H @@ -754,6 +754,23 @@ union uvh_lb_bau_sb_descriptor_base_u { }; /* ========================================================================= */ +/* UVH_LB_TARGET_PHYSICAL_APIC_ID_MASK */ +/* ========================================================================= */ +#define UVH_LB_TARGET_PHYSICAL_APIC_ID_MASK 0x320130UL +#define UVH_LB_TARGET_PHYSICAL_APIC_ID_MASK_32 0x009f0 + +#define UVH_LB_TARGET_PHYSICAL_APIC_ID_MASK_BIT_ENABLES_SHFT 0 +#define UVH_LB_TARGET_PHYSICAL_APIC_ID_MASK_BIT_ENABLES_MASK 0x00000000ffffffffUL + +union uvh_lb_target_physical_apic_id_mask_u { + unsigned long v; + struct uvh_lb_target_physical_apic_id_mask_s { + unsigned long bit_enables : 32; /* RW */ + unsigned long rsvd_32_63 : 32; /* */ + } s; +}; + +/* ========================================================================= */ /* UVH_NODE_ID */ /* ========================================================================= */ #define UVH_NODE_ID 0x0UL diff --git a/arch/x86/include/asm/xen/interface.h b/arch/x86/include/asm/xen/interface.h index e8506c1f0c55..1c10c88ee4e1 100644 --- a/arch/x86/include/asm/xen/interface.h +++ b/arch/x86/include/asm/xen/interface.h @@ -61,9 +61,9 @@ DEFINE_GUEST_HANDLE(void); #define HYPERVISOR_VIRT_START mk_unsigned_long(__HYPERVISOR_VIRT_START) #endif -#ifndef machine_to_phys_mapping -#define machine_to_phys_mapping ((unsigned long *)HYPERVISOR_VIRT_START) -#endif +#define MACH2PHYS_VIRT_START mk_unsigned_long(__MACH2PHYS_VIRT_START) +#define MACH2PHYS_VIRT_END mk_unsigned_long(__MACH2PHYS_VIRT_END) +#define MACH2PHYS_NR_ENTRIES ((MACH2PHYS_VIRT_END-MACH2PHYS_VIRT_START)>>__MACH2PHYS_SHIFT) /* Maximum number of virtual CPUs in multi-processor guests. */ #define MAX_VIRT_CPUS 32 diff --git a/arch/x86/include/asm/xen/interface_32.h b/arch/x86/include/asm/xen/interface_32.h index 42a7e004ae5c..8413688b2571 100644 --- a/arch/x86/include/asm/xen/interface_32.h +++ b/arch/x86/include/asm/xen/interface_32.h @@ -32,6 +32,11 @@ /* And the trap vector is... */ #define TRAP_INSTR "int $0x82" +#define __MACH2PHYS_VIRT_START 0xF5800000 +#define __MACH2PHYS_VIRT_END 0xF6800000 + +#define __MACH2PHYS_SHIFT 2 + /* * Virtual addresses beyond this are not modifiable by guest OSes. The * machine->physical mapping table starts at this address, read-only. diff --git a/arch/x86/include/asm/xen/interface_64.h b/arch/x86/include/asm/xen/interface_64.h index 100d2662b97c..839a4811cf98 100644 --- a/arch/x86/include/asm/xen/interface_64.h +++ b/arch/x86/include/asm/xen/interface_64.h @@ -39,18 +39,7 @@ #define __HYPERVISOR_VIRT_END 0xFFFF880000000000 #define __MACH2PHYS_VIRT_START 0xFFFF800000000000 #define __MACH2PHYS_VIRT_END 0xFFFF804000000000 - -#ifndef HYPERVISOR_VIRT_START -#define HYPERVISOR_VIRT_START mk_unsigned_long(__HYPERVISOR_VIRT_START) -#define HYPERVISOR_VIRT_END mk_unsigned_long(__HYPERVISOR_VIRT_END) -#endif - -#define MACH2PHYS_VIRT_START mk_unsigned_long(__MACH2PHYS_VIRT_START) -#define MACH2PHYS_VIRT_END mk_unsigned_long(__MACH2PHYS_VIRT_END) -#define MACH2PHYS_NR_ENTRIES ((MACH2PHYS_VIRT_END-MACH2PHYS_VIRT_START)>>3) -#ifndef machine_to_phys_mapping -#define machine_to_phys_mapping ((unsigned long *)HYPERVISOR_VIRT_START) -#endif +#define __MACH2PHYS_SHIFT 3 /* * int HYPERVISOR_set_segment_base(unsigned int which, unsigned long base) diff --git a/arch/x86/include/asm/xen/page.h b/arch/x86/include/asm/xen/page.h index dd8c1414b3d5..8760cc60a21c 100644 --- a/arch/x86/include/asm/xen/page.h +++ b/arch/x86/include/asm/xen/page.h @@ -5,6 +5,7 @@ #include <linux/types.h> #include <linux/spinlock.h> #include <linux/pfn.h> +#include <linux/mm.h> #include <asm/uaccess.h> #include <asm/page.h> @@ -35,6 +36,8 @@ typedef struct xpaddr { #define MAX_DOMAIN_PAGES \ ((unsigned long)((u64)CONFIG_XEN_MAX_DOMAIN_MEMORY * 1024 * 1024 * 1024 / PAGE_SIZE)) +extern unsigned long *machine_to_phys_mapping; +extern unsigned int machine_to_phys_order; extern unsigned long get_phys_to_machine(unsigned long pfn); extern bool set_phys_to_machine(unsigned long pfn, unsigned long mfn); @@ -69,10 +72,8 @@ static inline unsigned long mfn_to_pfn(unsigned long mfn) if (xen_feature(XENFEAT_auto_translated_physmap)) return mfn; -#if 0 if (unlikely((mfn >> machine_to_phys_order) != 0)) - return max_mapnr; -#endif + return ~0; pfn = 0; /* diff --git a/arch/x86/kernel/Makefile b/arch/x86/kernel/Makefile index f60153d5de57..34244b2cd880 100644 --- a/arch/x86/kernel/Makefile +++ b/arch/x86/kernel/Makefile @@ -45,6 +45,7 @@ obj-y += pci-dma.o quirks.o i8237.o topology.o kdebugfs.o obj-y += alternative.o i8253.o pci-nommu.o hw_breakpoint.o obj-y += tsc.o io_delay.o rtc.o obj-y += pci-iommu_table.o +obj-y += resource.o obj-$(CONFIG_X86_TRAMPOLINE) += trampoline.o obj-y += process.o diff --git a/arch/x86/kernel/acpi/boot.c b/arch/x86/kernel/acpi/boot.c index 1a5b9a8e6c4f..ec881c6bfee0 100644 --- a/arch/x86/kernel/acpi/boot.c +++ b/arch/x86/kernel/acpi/boot.c @@ -198,6 +198,11 @@ static void __cpuinit acpi_register_lapic(int id, u8 enabled) { unsigned int ver = 0; + if (id >= (MAX_LOCAL_APIC-1)) { + printk(KERN_INFO PREFIX "skipped apicid that is too big\n"); + return; + } + if (!enabled) { ++disabled_cpus; return; @@ -898,13 +903,13 @@ static int __init acpi_parse_madt_lapic_entries(void) register_lapic_address(acpi_lapic_addr); count = acpi_table_parse_madt(ACPI_MADT_TYPE_LOCAL_SAPIC, - acpi_parse_sapic, MAX_APICS); + acpi_parse_sapic, MAX_LOCAL_APIC); if (!count) { x2count = acpi_table_parse_madt(ACPI_MADT_TYPE_LOCAL_X2APIC, - acpi_parse_x2apic, MAX_APICS); + acpi_parse_x2apic, MAX_LOCAL_APIC); count = acpi_table_parse_madt(ACPI_MADT_TYPE_LOCAL_APIC, - acpi_parse_lapic, MAX_APICS); + acpi_parse_lapic, MAX_LOCAL_APIC); } if (!count && !x2count) { printk(KERN_ERR PREFIX "No LAPIC entries present\n"); diff --git a/arch/x86/kernel/alternative.c b/arch/x86/kernel/alternative.c index 5079f24c955a..123608531c8f 100644 --- a/arch/x86/kernel/alternative.c +++ b/arch/x86/kernel/alternative.c @@ -353,6 +353,7 @@ void __init_or_module alternatives_smp_module_del(struct module *mod) mutex_unlock(&smp_alt); } +bool skip_smp_alternatives; void alternatives_smp_switch(int smp) { struct smp_alt_module *mod; @@ -368,7 +369,7 @@ void alternatives_smp_switch(int smp) printk("lockdep: fixing up alternatives.\n"); #endif - if (noreplace_smp || smp_alt_once) + if (noreplace_smp || smp_alt_once || skip_smp_alternatives) return; BUG_ON(!smp && (num_online_cpus() > 1)); @@ -591,17 +592,21 @@ static atomic_t stop_machine_first; static int wrote_text; struct text_poke_params { - void *addr; - const void *opcode; - size_t len; + struct text_poke_param *params; + int nparams; }; static int __kprobes stop_machine_text_poke(void *data) { struct text_poke_params *tpp = data; + struct text_poke_param *p; + int i; if (atomic_dec_and_test(&stop_machine_first)) { - text_poke(tpp->addr, tpp->opcode, tpp->len); + for (i = 0; i < tpp->nparams; i++) { + p = &tpp->params[i]; + text_poke(p->addr, p->opcode, p->len); + } smp_wmb(); /* Make sure other cpus see that this has run */ wrote_text = 1; } else { @@ -610,8 +615,12 @@ static int __kprobes stop_machine_text_poke(void *data) smp_mb(); /* Load wrote_text before following execution */ } - flush_icache_range((unsigned long)tpp->addr, - (unsigned long)tpp->addr + tpp->len); + for (i = 0; i < tpp->nparams; i++) { + p = &tpp->params[i]; + flush_icache_range((unsigned long)p->addr, + (unsigned long)p->addr + p->len); + } + return 0; } @@ -631,10 +640,13 @@ static int __kprobes stop_machine_text_poke(void *data) void *__kprobes text_poke_smp(void *addr, const void *opcode, size_t len) { struct text_poke_params tpp; + struct text_poke_param p; - tpp.addr = addr; - tpp.opcode = opcode; - tpp.len = len; + p.addr = addr; + p.opcode = opcode; + p.len = len; + tpp.params = &p; + tpp.nparams = 1; atomic_set(&stop_machine_first, 1); wrote_text = 0; /* Use __stop_machine() because the caller already got online_cpus. */ @@ -642,6 +654,26 @@ void *__kprobes text_poke_smp(void *addr, const void *opcode, size_t len) return addr; } +/** + * text_poke_smp_batch - Update instructions on a live kernel on SMP + * @params: an array of text_poke parameters + * @n: the number of elements in params. + * + * Modify multi-byte instruction by using stop_machine() on SMP. Since the + * stop_machine() is heavy task, it is better to aggregate text_poke requests + * and do it once if possible. + * + * Note: Must be called under get_online_cpus() and text_mutex. + */ +void __kprobes text_poke_smp_batch(struct text_poke_param *params, int n) +{ + struct text_poke_params tpp = {.params = params, .nparams = n}; + + atomic_set(&stop_machine_first, 1); + wrote_text = 0; + stop_machine(stop_machine_text_poke, (void *)&tpp, NULL); +} + #if defined(CONFIG_DYNAMIC_FTRACE) || defined(HAVE_JUMP_LABEL) #ifdef CONFIG_X86_64 diff --git a/arch/x86/kernel/apic/Makefile b/arch/x86/kernel/apic/Makefile index 910f20b457c4..3966b564ea47 100644 --- a/arch/x86/kernel/apic/Makefile +++ b/arch/x86/kernel/apic/Makefile @@ -3,10 +3,7 @@ # obj-$(CONFIG_X86_LOCAL_APIC) += apic.o apic_noop.o probe_$(BITS).o ipi.o -ifneq ($(CONFIG_HARDLOCKUP_DETECTOR),y) -obj-$(CONFIG_X86_LOCAL_APIC) += nmi.o -endif -obj-$(CONFIG_HARDLOCKUP_DETECTOR) += hw_nmi.o +obj-y += hw_nmi.o obj-$(CONFIG_X86_IO_APIC) += io_apic.o obj-$(CONFIG_SMP) += ipi.o diff --git a/arch/x86/kernel/apic/apic.c b/arch/x86/kernel/apic/apic.c index c0f6426cd337..ce65d449b750 100644 --- a/arch/x86/kernel/apic/apic.c +++ b/arch/x86/kernel/apic/apic.c @@ -31,7 +31,6 @@ #include <linux/init.h> #include <linux/cpu.h> #include <linux/dmi.h> -#include <linux/nmi.h> #include <linux/smp.h> #include <linux/mm.h> @@ -432,17 +431,18 @@ int setup_APIC_eilvt(u8 offset, u8 vector, u8 msg_type, u8 mask) reserved = reserve_eilvt_offset(offset, new); if (reserved != new) { - pr_err(FW_BUG "cpu %d, try to setup vector 0x%x, but " - "vector 0x%x was already reserved by another core, " - "APIC%lX=0x%x\n", - smp_processor_id(), new, reserved, reg, old); + pr_err(FW_BUG "cpu %d, try to use APIC%lX (LVT offset %d) for " + "vector 0x%x, but the register is already in use for " + "vector 0x%x on another cpu\n", + smp_processor_id(), reg, offset, new, reserved); return -EINVAL; } if (!eilvt_entry_is_changeable(old, new)) { - pr_err(FW_BUG "cpu %d, try to setup vector 0x%x but " - "register already in use, APIC%lX=0x%x\n", - smp_processor_id(), new, reg, old); + pr_err(FW_BUG "cpu %d, try to use APIC%lX (LVT offset %d) for " + "vector 0x%x, but the register is already in use for " + "vector 0x%x on this cpu\n", + smp_processor_id(), reg, offset, new, old); return -EBUSY; } @@ -799,11 +799,7 @@ void __init setup_boot_APIC_clock(void) * PIT/HPET going. Otherwise register lapic as a dummy * device. */ - if (nmi_watchdog != NMI_IO_APIC) - lapic_clockevent.features &= ~CLOCK_EVT_FEAT_DUMMY; - else - pr_warning("APIC timer registered as dummy," - " due to nmi_watchdog=%d!\n", nmi_watchdog); + lapic_clockevent.features &= ~CLOCK_EVT_FEAT_DUMMY; /* Setup the lapic or request the broadcast */ setup_APIC_timer(); @@ -1384,8 +1380,15 @@ void __cpuinit end_local_APIC_setup(void) } #endif - setup_apic_nmi_watchdog(NULL); apic_pm_activate(); + + /* + * Now that local APIC setup is completed for BP, configure the fault + * handling for interrupt remapping. + */ + if (!smp_processor_id() && intr_remapping_enabled) + enable_drhd_fault_handling(); + } #ifdef CONFIG_X86_X2APIC @@ -1694,7 +1697,7 @@ void __init register_lapic_address(unsigned long address) * This initializes the IO-APIC and APIC hardware if this is * a UP kernel. */ -int apic_version[MAX_APICS]; +int apic_version[MAX_LOCAL_APIC]; int __init APIC_init_uniprocessor(void) { @@ -1759,17 +1762,10 @@ int __init APIC_init_uniprocessor(void) setup_IO_APIC(); else { nr_ioapics = 0; - localise_nmi_watchdog(); } -#else - localise_nmi_watchdog(); #endif x86_init.timers.setup_percpu_clockev(); -#ifdef CONFIG_X86_64 - check_nmi_watchdog(); -#endif - return 0; } diff --git a/arch/x86/kernel/apic/hw_nmi.c b/arch/x86/kernel/apic/hw_nmi.c index cefd6942f0e9..72ec29e1ae06 100644 --- a/arch/x86/kernel/apic/hw_nmi.c +++ b/arch/x86/kernel/apic/hw_nmi.c @@ -17,19 +17,31 @@ #include <linux/nmi.h> #include <linux/module.h> -/* For reliability, we're prepared to waste bits here. */ -static DECLARE_BITMAP(backtrace_mask, NR_CPUS) __read_mostly; - +#ifdef CONFIG_HARDLOCKUP_DETECTOR u64 hw_nmi_get_sample_period(void) { return (u64)(cpu_khz) * 1000 * 60; } +#endif + +#ifdef arch_trigger_all_cpu_backtrace +/* For reliability, we're prepared to waste bits here. */ +static DECLARE_BITMAP(backtrace_mask, NR_CPUS) __read_mostly; + +/* "in progress" flag of arch_trigger_all_cpu_backtrace */ +static unsigned long backtrace_flag; -#ifdef ARCH_HAS_NMI_WATCHDOG void arch_trigger_all_cpu_backtrace(void) { int i; + if (test_and_set_bit(0, &backtrace_flag)) + /* + * If there is already a trigger_all_cpu_backtrace() in progress + * (backtrace_flag == 1), don't output double cpu dump infos. + */ + return; + cpumask_copy(to_cpumask(backtrace_mask), cpu_online_mask); printk(KERN_INFO "sending NMI to all CPUs:\n"); @@ -41,6 +53,9 @@ void arch_trigger_all_cpu_backtrace(void) break; mdelay(1); } + + clear_bit(0, &backtrace_flag); + smp_mb__after_clear_bit(); } static int __kprobes @@ -49,7 +64,7 @@ arch_trigger_all_cpu_backtrace_handler(struct notifier_block *self, { struct die_args *args = __args; struct pt_regs *regs; - int cpu = smp_processor_id(); + int cpu; switch (cmd) { case DIE_NMI: @@ -61,6 +76,7 @@ arch_trigger_all_cpu_backtrace_handler(struct notifier_block *self, } regs = args->regs; + cpu = smp_processor_id(); if (cpumask_test_cpu(cpu, to_cpumask(backtrace_mask))) { static arch_spinlock_t lock = __ARCH_SPIN_LOCK_UNLOCKED; @@ -90,18 +106,3 @@ static int __init register_trigger_all_cpu_backtrace(void) } early_initcall(register_trigger_all_cpu_backtrace); #endif - -/* STUB calls to mimic old nmi_watchdog behaviour */ -#if defined(CONFIG_X86_LOCAL_APIC) -unsigned int nmi_watchdog = NMI_NONE; -EXPORT_SYMBOL(nmi_watchdog); -void acpi_nmi_enable(void) { return; } -void acpi_nmi_disable(void) { return; } -#endif -atomic_t nmi_active = ATOMIC_INIT(0); /* oprofile uses this */ -EXPORT_SYMBOL(nmi_active); -int unknown_nmi_panic; -void cpu_nmi_set_wd_enabled(void) { return; } -void stop_apic_nmi_watchdog(void *unused) { return; } -void setup_apic_nmi_watchdog(void *unused) { return; } -int __init check_nmi_watchdog(void) { return 0; } diff --git a/arch/x86/kernel/apic/io_apic.c b/arch/x86/kernel/apic/io_apic.c index bb61a552d8c6..52735a710c30 100644 --- a/arch/x86/kernel/apic/io_apic.c +++ b/arch/x86/kernel/apic/io_apic.c @@ -54,7 +54,6 @@ #include <asm/dma.h> #include <asm/timer.h> #include <asm/i8259.h> -#include <asm/nmi.h> #include <asm/msidef.h> #include <asm/hypertransport.h> #include <asm/setup.h> @@ -2458,13 +2457,12 @@ static void ack_apic_level(struct irq_data *data) { struct irq_cfg *cfg = data->chip_data; int i, do_unmask_irq = 0, irq = data->irq; - struct irq_desc *desc = irq_to_desc(irq); unsigned long v; irq_complete_move(cfg); #ifdef CONFIG_GENERIC_PENDING_IRQ /* If we are moving the irq we need to mask it */ - if (unlikely(desc->status & IRQ_MOVE_PENDING)) { + if (unlikely(irq_to_desc(irq)->status & IRQ_MOVE_PENDING)) { do_unmask_irq = 1; mask_ioapic(cfg); } @@ -2671,24 +2669,6 @@ static void lapic_register_intr(int irq) "edge"); } -static void __init setup_nmi(void) -{ - /* - * Dirty trick to enable the NMI watchdog ... - * We put the 8259A master into AEOI mode and - * unmask on all local APICs LVT0 as NMI. - * - * The idea to use the 8259A in AEOI mode ('8259A Virtual Wire') - * is from Maciej W. Rozycki - so we do not have to EOI from - * the NMI handler or the timer interrupt. - */ - apic_printk(APIC_VERBOSE, KERN_INFO "activating NMI Watchdog ..."); - - enable_NMI_through_LVT0(); - - apic_printk(APIC_VERBOSE, " done.\n"); -} - /* * This looks a bit hackish but it's about the only one way of sending * a few INTA cycles to 8259As and any associated glue logic. ICR does @@ -2794,15 +2774,6 @@ static inline void __init check_timer(void) */ apic_write(APIC_LVT0, APIC_LVT_MASKED | APIC_DM_EXTINT); legacy_pic->init(1); -#ifdef CONFIG_X86_32 - { - unsigned int ver; - - ver = apic_read(APIC_LVR); - ver = GET_APIC_VERSION(ver); - timer_ack = (nmi_watchdog == NMI_IO_APIC && !APIC_INTEGRATED(ver)); - } -#endif pin1 = find_isa_irq_pin(0, mp_INT); apic1 = find_isa_irq_apic(0, mp_INT); @@ -2850,10 +2821,6 @@ static inline void __init check_timer(void) unmask_ioapic(cfg); } if (timer_irq_works()) { - if (nmi_watchdog == NMI_IO_APIC) { - setup_nmi(); - legacy_pic->unmask(0); - } if (disable_timer_pin_1 > 0) clear_IO_APIC_pin(0, pin1); goto out; @@ -2879,11 +2846,6 @@ static inline void __init check_timer(void) if (timer_irq_works()) { apic_printk(APIC_QUIET, KERN_INFO "....... works.\n"); timer_through_8259 = 1; - if (nmi_watchdog == NMI_IO_APIC) { - legacy_pic->mask(0); - setup_nmi(); - legacy_pic->unmask(0); - } goto out; } /* @@ -2895,15 +2857,6 @@ static inline void __init check_timer(void) apic_printk(APIC_QUIET, KERN_INFO "....... failed.\n"); } - if (nmi_watchdog == NMI_IO_APIC) { - apic_printk(APIC_QUIET, KERN_WARNING "timer doesn't work " - "through the IO-APIC - disabling NMI Watchdog!\n"); - nmi_watchdog = NMI_NONE; - } -#ifdef CONFIG_X86_32 - timer_ack = 0; -#endif - apic_printk(APIC_QUIET, KERN_INFO "...trying to set up timer as Virtual Wire IRQ...\n"); @@ -3441,6 +3394,7 @@ dmar_msi_set_affinity(struct irq_data *data, const struct cpumask *mask, msg.data |= MSI_DATA_VECTOR(cfg->vector); msg.address_lo &= ~MSI_ADDR_DEST_ID_MASK; msg.address_lo |= MSI_ADDR_DEST_ID(dest); + msg.address_hi = MSI_ADDR_BASE_HI | MSI_ADDR_EXT_DEST_ID(dest); dmar_msi_write(irq, &msg); @@ -4133,7 +4087,8 @@ void __init pre_init_apic_IRQ0(void) printk(KERN_INFO "Early APIC setup for system timer0\n"); #ifndef CONFIG_SMP - phys_cpu_present_map = physid_mask_of_physid(boot_cpu_physical_apicid); + physid_set_mask_of_physid(boot_cpu_physical_apicid, + &phys_cpu_present_map); #endif /* Make sure the irq descriptor is set up */ cfg = alloc_irq_and_cfg_at(0, 0); diff --git a/arch/x86/kernel/apic/nmi.c b/arch/x86/kernel/apic/nmi.c deleted file mode 100644 index c90041ccb742..000000000000 --- a/arch/x86/kernel/apic/nmi.c +++ /dev/null @@ -1,567 +0,0 @@ -/* - * NMI watchdog support on APIC systems - * - * Started by Ingo Molnar <mingo@redhat.com> - * - * Fixes: - * Mikael Pettersson : AMD K7 support for local APIC NMI watchdog. - * Mikael Pettersson : Power Management for local APIC NMI watchdog. - * Mikael Pettersson : Pentium 4 support for local APIC NMI watchdog. - * Pavel Machek and - * Mikael Pettersson : PM converted to driver model. Disable/enable API. - */ - -#include <asm/apic.h> - -#include <linux/nmi.h> -#include <linux/mm.h> -#include <linux/delay.h> -#include <linux/interrupt.h> -#include <linux/module.h> -#include <linux/slab.h> -#include <linux/sysdev.h> -#include <linux/sysctl.h> -#include <linux/percpu.h> -#include <linux/kprobes.h> -#include <linux/cpumask.h> -#include <linux/kernel_stat.h> -#include <linux/kdebug.h> -#include <linux/smp.h> - -#include <asm/i8259.h> -#include <asm/io_apic.h> -#include <asm/proto.h> -#include <asm/timer.h> - -#include <asm/mce.h> - -#include <asm/mach_traps.h> - -int unknown_nmi_panic; -int nmi_watchdog_enabled; - -/* For reliability, we're prepared to waste bits here. */ -static DECLARE_BITMAP(backtrace_mask, NR_CPUS) __read_mostly; - -/* nmi_active: - * >0: the lapic NMI watchdog is active, but can be disabled - * <0: the lapic NMI watchdog has not been set up, and cannot - * be enabled - * 0: the lapic NMI watchdog is disabled, but can be enabled - */ -atomic_t nmi_active = ATOMIC_INIT(0); /* oprofile uses this */ -EXPORT_SYMBOL(nmi_active); - -unsigned int nmi_watchdog = NMI_NONE; -EXPORT_SYMBOL(nmi_watchdog); - -static int panic_on_timeout; - -static unsigned int nmi_hz = HZ; -static DEFINE_PER_CPU(short, wd_enabled); -static int endflag __initdata; - -static inline unsigned int get_nmi_count(int cpu) -{ - return per_cpu(irq_stat, cpu).__nmi_count; -} - -static inline int mce_in_progress(void) -{ -#if defined(CONFIG_X86_MCE) - return atomic_read(&mce_entry) > 0; -#endif - return 0; -} - -/* - * Take the local apic timer and PIT/HPET into account. We don't - * know which one is active, when we have highres/dyntick on - */ -static inline unsigned int get_timer_irqs(int cpu) -{ - return per_cpu(irq_stat, cpu).apic_timer_irqs + - per_cpu(irq_stat, cpu).irq0_irqs; -} - -#ifdef CONFIG_SMP -/* - * The performance counters used by NMI_LOCAL_APIC don't trigger when - * the CPU is idle. To make sure the NMI watchdog really ticks on all - * CPUs during the test make them busy. - */ -static __init void nmi_cpu_busy(void *data) -{ - local_irq_enable_in_hardirq(); - /* - * Intentionally don't use cpu_relax here. This is - * to make sure that the performance counter really ticks, - * even if there is a simulator or similar that catches the - * pause instruction. On a real HT machine this is fine because - * all other CPUs are busy with "useless" delay loops and don't - * care if they get somewhat less cycles. - */ - while (endflag == 0) - mb(); -} -#endif - -static void report_broken_nmi(int cpu, unsigned int *prev_nmi_count) -{ - printk(KERN_CONT "\n"); - - printk(KERN_WARNING - "WARNING: CPU#%d: NMI appears to be stuck (%d->%d)!\n", - cpu, prev_nmi_count[cpu], get_nmi_count(cpu)); - - printk(KERN_WARNING - "Please report this to bugzilla.kernel.org,\n"); - printk(KERN_WARNING - "and attach the output of the 'dmesg' command.\n"); - - per_cpu(wd_enabled, cpu) = 0; - atomic_dec(&nmi_active); -} - -static void __acpi_nmi_disable(void *__unused) -{ - apic_write(APIC_LVT0, APIC_DM_NMI | APIC_LVT_MASKED); -} - -int __init check_nmi_watchdog(void) -{ - unsigned int *prev_nmi_count; - int cpu; - - if (!nmi_watchdog_active() || !atomic_read(&nmi_active)) - return 0; - - prev_nmi_count = kmalloc(nr_cpu_ids * sizeof(int), GFP_KERNEL); - if (!prev_nmi_count) - goto error; - - printk(KERN_INFO "Testing NMI watchdog ... "); - -#ifdef CONFIG_SMP - if (nmi_watchdog == NMI_LOCAL_APIC) - smp_call_function(nmi_cpu_busy, (void *)&endflag, 0); -#endif - - for_each_possible_cpu(cpu) - prev_nmi_count[cpu] = get_nmi_count(cpu); - local_irq_enable(); - mdelay((20 * 1000) / nmi_hz); /* wait 20 ticks */ - - for_each_online_cpu(cpu) { - if (!per_cpu(wd_enabled, cpu)) - continue; - if (get_nmi_count(cpu) - prev_nmi_count[cpu] <= 5) - report_broken_nmi(cpu, prev_nmi_count); - } - endflag = 1; - if (!atomic_read(&nmi_active)) { - kfree(prev_nmi_count); - atomic_set(&nmi_active, -1); - goto error; - } - printk("OK.\n"); - - /* - * now that we know it works we can reduce NMI frequency to - * something more reasonable; makes a difference in some configs - */ - if (nmi_watchdog == NMI_LOCAL_APIC) - nmi_hz = lapic_adjust_nmi_hz(1); - - kfree(prev_nmi_count); - return 0; -error: - if (nmi_watchdog == NMI_IO_APIC) { - if (!timer_through_8259) - legacy_pic->mask(0); - on_each_cpu(__acpi_nmi_disable, NULL, 1); - } - -#ifdef CONFIG_X86_32 - timer_ack = 0; -#endif - return -1; -} - -static int __init setup_nmi_watchdog(char *str) -{ - unsigned int nmi; - - if (!strncmp(str, "panic", 5)) { - panic_on_timeout = 1; - str = strchr(str, ','); - if (!str) - return 1; - ++str; - } - - if (!strncmp(str, "lapic", 5)) - nmi_watchdog = NMI_LOCAL_APIC; - else if (!strncmp(str, "ioapic", 6)) - nmi_watchdog = NMI_IO_APIC; - else { - get_option(&str, &nmi); - if (nmi >= NMI_INVALID) - return 0; - nmi_watchdog = nmi; - } - - return 1; -} -__setup("nmi_watchdog=", setup_nmi_watchdog); - -/* - * Suspend/resume support - */ -#ifdef CONFIG_PM - -static int nmi_pm_active; /* nmi_active before suspend */ - -static int lapic_nmi_suspend(struct sys_device *dev, pm_message_t state) -{ - /* only CPU0 goes here, other CPUs should be offline */ - nmi_pm_active = atomic_read(&nmi_active); - stop_apic_nmi_watchdog(NULL); - BUG_ON(atomic_read(&nmi_active) != 0); - return 0; -} - -static int lapic_nmi_resume(struct sys_device *dev) -{ - /* only CPU0 goes here, other CPUs should be offline */ - if (nmi_pm_active > 0) { - setup_apic_nmi_watchdog(NULL); - touch_nmi_watchdog(); - } - return 0; -} - -static struct sysdev_class nmi_sysclass = { - .name = "lapic_nmi", - .resume = lapic_nmi_resume, - .suspend = lapic_nmi_suspend, -}; - -static struct sys_device device_lapic_nmi = { - .id = 0, - .cls = &nmi_sysclass, -}; - -static int __init init_lapic_nmi_sysfs(void) -{ - int error; - - /* - * should really be a BUG_ON but b/c this is an - * init call, it just doesn't work. -dcz - */ - if (nmi_watchdog != NMI_LOCAL_APIC) - return 0; - - if (atomic_read(&nmi_active) < 0) - return 0; - - error = sysdev_class_register(&nmi_sysclass); - if (!error) - error = sysdev_register(&device_lapic_nmi); - return error; -} - -/* must come after the local APIC's device_initcall() */ -late_initcall(init_lapic_nmi_sysfs); - -#endif /* CONFIG_PM */ - -static void __acpi_nmi_enable(void *__unused) -{ - apic_write(APIC_LVT0, APIC_DM_NMI); -} - -/* - * Enable timer based NMIs on all CPUs: - */ -void acpi_nmi_enable(void) -{ - if (atomic_read(&nmi_active) && nmi_watchdog == NMI_IO_APIC) - on_each_cpu(__acpi_nmi_enable, NULL, 1); -} - -/* - * Disable timer based NMIs on all CPUs: - */ -void acpi_nmi_disable(void) -{ - if (atomic_read(&nmi_active) && nmi_watchdog == NMI_IO_APIC) - on_each_cpu(__acpi_nmi_disable, NULL, 1); -} - -/* - * This function is called as soon the LAPIC NMI watchdog driver has everything - * in place and it's ready to check if the NMIs belong to the NMI watchdog - */ -void cpu_nmi_set_wd_enabled(void) -{ - __get_cpu_var(wd_enabled) = 1; -} - -void setup_apic_nmi_watchdog(void *unused) -{ - if (__get_cpu_var(wd_enabled)) - return; - - /* cheap hack to support suspend/resume */ - /* if cpu0 is not active neither should the other cpus */ - if (smp_processor_id() != 0 && atomic_read(&nmi_active) <= 0) - return; - - switch (nmi_watchdog) { - case NMI_LOCAL_APIC: - if (lapic_watchdog_init(nmi_hz) < 0) { - __get_cpu_var(wd_enabled) = 0; - return; - } - /* FALL THROUGH */ - case NMI_IO_APIC: - __get_cpu_var(wd_enabled) = 1; - atomic_inc(&nmi_active); - } -} - -void stop_apic_nmi_watchdog(void *unused) -{ - /* only support LOCAL and IO APICs for now */ - if (!nmi_watchdog_active()) - return; - if (__get_cpu_var(wd_enabled) == 0) - return; - if (nmi_watchdog == NMI_LOCAL_APIC) - lapic_watchdog_stop(); - else - __acpi_nmi_disable(NULL); - __get_cpu_var(wd_enabled) = 0; - atomic_dec(&nmi_active); -} - -/* - * the best way to detect whether a CPU has a 'hard lockup' problem - * is to check it's local APIC timer IRQ counts. If they are not - * changing then that CPU has some problem. - * - * as these watchdog NMI IRQs are generated on every CPU, we only - * have to check the current processor. - * - * since NMIs don't listen to _any_ locks, we have to be extremely - * careful not to rely on unsafe variables. The printk might lock - * up though, so we have to break up any console locks first ... - * [when there will be more tty-related locks, break them up here too!] - */ - -static DEFINE_PER_CPU(unsigned, last_irq_sum); -static DEFINE_PER_CPU(long, alert_counter); -static DEFINE_PER_CPU(int, nmi_touch); - -void touch_nmi_watchdog(void) -{ - if (nmi_watchdog_active()) { - unsigned cpu; - - /* - * Tell other CPUs to reset their alert counters. We cannot - * do it ourselves because the alert count increase is not - * atomic. - */ - for_each_present_cpu(cpu) { - if (per_cpu(nmi_touch, cpu) != 1) - per_cpu(nmi_touch, cpu) = 1; - } - } - - /* - * Tickle the softlockup detector too: - */ - touch_softlockup_watchdog(); -} -EXPORT_SYMBOL(touch_nmi_watchdog); - -notrace __kprobes int -nmi_watchdog_tick(struct pt_regs *regs, unsigned reason) -{ - /* - * Since current_thread_info()-> is always on the stack, and we - * always switch the stack NMI-atomically, it's safe to use - * smp_processor_id(). - */ - unsigned int sum; - int touched = 0; - int cpu = smp_processor_id(); - int rc = 0; - - sum = get_timer_irqs(cpu); - - if (__get_cpu_var(nmi_touch)) { - __get_cpu_var(nmi_touch) = 0; - touched = 1; - } - - /* We can be called before check_nmi_watchdog, hence NULL check. */ - if (cpumask_test_cpu(cpu, to_cpumask(backtrace_mask))) { - static DEFINE_RAW_SPINLOCK(lock); /* Serialise the printks */ - - raw_spin_lock(&lock); - printk(KERN_WARNING "NMI backtrace for cpu %d\n", cpu); - show_regs(regs); - dump_stack(); - raw_spin_unlock(&lock); - cpumask_clear_cpu(cpu, to_cpumask(backtrace_mask)); - - rc = 1; - } - - /* Could check oops_in_progress here too, but it's safer not to */ - if (mce_in_progress()) - touched = 1; - - /* if the none of the timers isn't firing, this cpu isn't doing much */ - if (!touched && __get_cpu_var(last_irq_sum) == sum) { - /* - * Ayiee, looks like this CPU is stuck ... - * wait a few IRQs (5 seconds) before doing the oops ... - */ - __this_cpu_inc(alert_counter); - if (__this_cpu_read(alert_counter) == 5 * nmi_hz) - /* - * die_nmi will return ONLY if NOTIFY_STOP happens.. - */ - die_nmi("BUG: NMI Watchdog detected LOCKUP", - regs, panic_on_timeout); - } else { - __get_cpu_var(last_irq_sum) = sum; - __this_cpu_write(alert_counter, 0); - } - - /* see if the nmi watchdog went off */ - if (!__get_cpu_var(wd_enabled)) - return rc; - switch (nmi_watchdog) { - case NMI_LOCAL_APIC: - rc |= lapic_wd_event(nmi_hz); - break; - case NMI_IO_APIC: - /* - * don't know how to accurately check for this. - * just assume it was a watchdog timer interrupt - * This matches the old behaviour. - */ - rc = 1; - break; - } - return rc; -} - -#ifdef CONFIG_SYSCTL - -static void enable_ioapic_nmi_watchdog_single(void *unused) -{ - __get_cpu_var(wd_enabled) = 1; - atomic_inc(&nmi_active); - __acpi_nmi_enable(NULL); -} - -static void enable_ioapic_nmi_watchdog(void) -{ - on_each_cpu(enable_ioapic_nmi_watchdog_single, NULL, 1); - touch_nmi_watchdog(); -} - -static void disable_ioapic_nmi_watchdog(void) -{ - on_each_cpu(stop_apic_nmi_watchdog, NULL, 1); -} - -static int __init setup_unknown_nmi_panic(char *str) -{ - unknown_nmi_panic = 1; - return 1; -} -__setup("unknown_nmi_panic", setup_unknown_nmi_panic); - -static int unknown_nmi_panic_callback(struct pt_regs *regs, int cpu) -{ - unsigned char reason = get_nmi_reason(); - char buf[64]; - - sprintf(buf, "NMI received for unknown reason %02x\n", reason); - die_nmi(buf, regs, 1); /* Always panic here */ - return 0; -} - -/* - * proc handler for /proc/sys/kernel/nmi - */ -int proc_nmi_enabled(struct ctl_table *table, int write, - void __user *buffer, size_t *length, loff_t *ppos) -{ - int old_state; - - nmi_watchdog_enabled = (atomic_read(&nmi_active) > 0) ? 1 : 0; - old_state = nmi_watchdog_enabled; - proc_dointvec(table, write, buffer, length, ppos); - if (!!old_state == !!nmi_watchdog_enabled) - return 0; - - if (atomic_read(&nmi_active) < 0 || !nmi_watchdog_active()) { - printk(KERN_WARNING - "NMI watchdog is permanently disabled\n"); - return -EIO; - } - - if (nmi_watchdog == NMI_LOCAL_APIC) { - if (nmi_watchdog_enabled) - enable_lapic_nmi_watchdog(); - else - disable_lapic_nmi_watchdog(); - } else if (nmi_watchdog == NMI_IO_APIC) { - if (nmi_watchdog_enabled) - enable_ioapic_nmi_watchdog(); - else - disable_ioapic_nmi_watchdog(); - } else { - printk(KERN_WARNING - "NMI watchdog doesn't know what hardware to touch\n"); - return -EIO; - } - return 0; -} - -#endif /* CONFIG_SYSCTL */ - -int do_nmi_callback(struct pt_regs *regs, int cpu) -{ -#ifdef CONFIG_SYSCTL - if (unknown_nmi_panic) - return unknown_nmi_panic_callback(regs, cpu); -#endif - return 0; -} - -void arch_trigger_all_cpu_backtrace(void) -{ - int i; - - cpumask_copy(to_cpumask(backtrace_mask), cpu_online_mask); - - printk(KERN_INFO "sending NMI to all CPUs:\n"); - apic->send_IPI_all(NMI_VECTOR); - - /* Wait for up to 10 seconds for all CPUs to do the backtrace */ - for (i = 0; i < 10 * 1000; i++) { - if (cpumask_empty(to_cpumask(backtrace_mask))) - break; - mdelay(1); - } -} diff --git a/arch/x86/kernel/apic/probe_64.c b/arch/x86/kernel/apic/probe_64.c index f9e4e6a54073..d8c4a6feb286 100644 --- a/arch/x86/kernel/apic/probe_64.c +++ b/arch/x86/kernel/apic/probe_64.c @@ -79,13 +79,6 @@ void __init default_setup_apic_routing(void) /* need to update phys_pkg_id */ apic->phys_pkg_id = apicid_phys_pkg_id; } - - /* - * Now that apic routing model is selected, configure the - * fault handling for intr remapping. - */ - if (intr_remapping_enabled) - enable_drhd_fault_handling(); } /* Same for both flat and physical. */ diff --git a/arch/x86/kernel/apic/x2apic_uv_x.c b/arch/x86/kernel/apic/x2apic_uv_x.c index 194539aea175..2a3f2a7db243 100644 --- a/arch/x86/kernel/apic/x2apic_uv_x.c +++ b/arch/x86/kernel/apic/x2apic_uv_x.c @@ -44,8 +44,20 @@ static u64 gru_start_paddr, gru_end_paddr; static union uvh_apicid uvh_apicid; int uv_min_hub_revision_id; EXPORT_SYMBOL_GPL(uv_min_hub_revision_id); +unsigned int uv_apicid_hibits; +EXPORT_SYMBOL_GPL(uv_apicid_hibits); static DEFINE_SPINLOCK(uv_nmi_lock); +static unsigned long __init uv_early_read_mmr(unsigned long addr) +{ + unsigned long val, *mmr; + + mmr = early_ioremap(UV_LOCAL_MMR_BASE | addr, sizeof(*mmr)); + val = *mmr; + early_iounmap(mmr, sizeof(*mmr)); + return val; +} + static inline bool is_GRU_range(u64 start, u64 end) { return start >= gru_start_paddr && end <= gru_end_paddr; @@ -56,28 +68,24 @@ static bool uv_is_untracked_pat_range(u64 start, u64 end) return is_ISA_range(start, end) || is_GRU_range(start, end); } -static int early_get_nodeid(void) +static int __init early_get_pnodeid(void) { union uvh_node_id_u node_id; - unsigned long *mmr; - - mmr = early_ioremap(UV_LOCAL_MMR_BASE | UVH_NODE_ID, sizeof(*mmr)); - node_id.v = *mmr; - early_iounmap(mmr, sizeof(*mmr)); + union uvh_rh_gam_config_mmr_u m_n_config; + int pnode; /* Currently, all blades have same revision number */ + node_id.v = uv_early_read_mmr(UVH_NODE_ID); + m_n_config.v = uv_early_read_mmr(UVH_RH_GAM_CONFIG_MMR); uv_min_hub_revision_id = node_id.s.revision; - return node_id.s.node_id; + pnode = (node_id.s.node_id >> 1) & ((1 << m_n_config.s.n_skt) - 1); + return pnode; } static void __init early_get_apic_pnode_shift(void) { - unsigned long *mmr; - - mmr = early_ioremap(UV_LOCAL_MMR_BASE | UVH_APICID, sizeof(*mmr)); - uvh_apicid.v = *mmr; - early_iounmap(mmr, sizeof(*mmr)); + uvh_apicid.v = uv_early_read_mmr(UVH_APICID); if (!uvh_apicid.v) /* * Old bios, use default value @@ -85,12 +93,25 @@ static void __init early_get_apic_pnode_shift(void) uvh_apicid.s.pnode_shift = UV_APIC_PNODE_SHIFT; } +/* + * Add an extra bit as dictated by bios to the destination apicid of + * interrupts potentially passing through the UV HUB. This prevents + * a deadlock between interrupts and IO port operations. + */ +static void __init uv_set_apicid_hibit(void) +{ + union uvh_lb_target_physical_apic_id_mask_u apicid_mask; + + apicid_mask.v = uv_early_read_mmr(UVH_LB_TARGET_PHYSICAL_APIC_ID_MASK); + uv_apicid_hibits = apicid_mask.s.bit_enables & UV_APICID_HIBIT_MASK; +} + static int __init uv_acpi_madt_oem_check(char *oem_id, char *oem_table_id) { - int nodeid; + int pnodeid; if (!strcmp(oem_id, "SGI")) { - nodeid = early_get_nodeid(); + pnodeid = early_get_pnodeid(); early_get_apic_pnode_shift(); x86_platform.is_untracked_pat_range = uv_is_untracked_pat_range; x86_platform.nmi_init = uv_nmi_init; @@ -100,8 +121,9 @@ static int __init uv_acpi_madt_oem_check(char *oem_id, char *oem_table_id) uv_system_type = UV_X2APIC; else if (!strcmp(oem_table_id, "UVH")) { __get_cpu_var(x2apic_extra_bits) = - nodeid << (uvh_apicid.s.pnode_shift - 1); + pnodeid << uvh_apicid.s.pnode_shift; uv_system_type = UV_NON_UNIQUE_APIC; + uv_set_apicid_hibit(); return 1; } } @@ -155,6 +177,7 @@ static int __cpuinit uv_wakeup_secondary(int phys_apicid, unsigned long start_ri int pnode; pnode = uv_apicid_to_pnode(phys_apicid); + phys_apicid |= uv_apicid_hibits; val = (1UL << UVH_IPI_INT_SEND_SHFT) | (phys_apicid << UVH_IPI_INT_APIC_ID_SHFT) | ((start_rip << UVH_IPI_INT_VECTOR_SHFT) >> 12) | @@ -236,7 +259,7 @@ static unsigned int uv_cpu_mask_to_apicid(const struct cpumask *cpumask) int cpu = cpumask_first(cpumask); if ((unsigned)cpu < nr_cpu_ids) - return per_cpu(x86_cpu_to_apicid, cpu); + return per_cpu(x86_cpu_to_apicid, cpu) | uv_apicid_hibits; else return BAD_APICID; } @@ -255,7 +278,7 @@ uv_cpu_mask_to_apicid_and(const struct cpumask *cpumask, if (cpumask_test_cpu(cpu, cpu_online_mask)) break; } - return per_cpu(x86_cpu_to_apicid, cpu); + return per_cpu(x86_cpu_to_apicid, cpu) | uv_apicid_hibits; } static unsigned int x2apic_get_apic_id(unsigned long x) @@ -661,27 +684,32 @@ void uv_nmi_init(void) void __init uv_system_init(void) { union uvh_rh_gam_config_mmr_u m_n_config; + union uvh_rh_gam_mmioh_overlay_config_mmr_u mmioh; union uvh_node_id_u node_id; unsigned long gnode_upper, lowmem_redir_base, lowmem_redir_size; - int bytes, nid, cpu, lcpu, pnode, blade, i, j, m_val, n_val; + int bytes, nid, cpu, lcpu, pnode, blade, i, j, m_val, n_val, n_io; int gnode_extra, max_pnode = 0; unsigned long mmr_base, present, paddr; - unsigned short pnode_mask; + unsigned short pnode_mask, pnode_io_mask; map_low_mmrs(); m_n_config.v = uv_read_local_mmr(UVH_RH_GAM_CONFIG_MMR ); m_val = m_n_config.s.m_skt; n_val = m_n_config.s.n_skt; + mmioh.v = uv_read_local_mmr(UVH_RH_GAM_MMIOH_OVERLAY_CONFIG_MMR); + n_io = mmioh.s.n_io; mmr_base = uv_read_local_mmr(UVH_RH_GAM_MMR_OVERLAY_CONFIG_MMR) & ~UV_MMR_ENABLE; pnode_mask = (1 << n_val) - 1; + pnode_io_mask = (1 << n_io) - 1; + node_id.v = uv_read_local_mmr(UVH_NODE_ID); gnode_extra = (node_id.s.node_id & ~((1 << n_val) - 1)) >> 1; gnode_upper = ((unsigned long)gnode_extra << m_val); - printk(KERN_DEBUG "UV: N %d, M %d, gnode_upper 0x%lx, gnode_extra 0x%x\n", - n_val, m_val, gnode_upper, gnode_extra); + printk(KERN_INFO "UV: N %d, M %d, N_IO: %d, gnode_upper 0x%lx, gnode_extra 0x%x, pnode_mask 0x%x, pnode_io_mask 0x%x\n", + n_val, m_val, n_io, gnode_upper, gnode_extra, pnode_mask, pnode_io_mask); printk(KERN_DEBUG "UV: global MMR base 0x%lx\n", mmr_base); @@ -714,7 +742,7 @@ void __init uv_system_init(void) for (j = 0; j < 64; j++) { if (!test_bit(j, &present)) continue; - pnode = (i * 64 + j); + pnode = (i * 64 + j) & pnode_mask; uv_blade_info[blade].pnode = pnode; uv_blade_info[blade].nr_possible_cpus = 0; uv_blade_info[blade].nr_online_cpus = 0; @@ -735,6 +763,7 @@ void __init uv_system_init(void) /* * apic_pnode_shift must be set before calling uv_apicid_to_pnode(); */ + uv_cpu_hub_info(cpu)->pnode_mask = pnode_mask; uv_cpu_hub_info(cpu)->apic_pnode_shift = uvh_apicid.s.pnode_shift; pnode = uv_apicid_to_pnode(apicid); blade = boot_pnode_to_blade(pnode); @@ -751,7 +780,6 @@ void __init uv_system_init(void) uv_cpu_hub_info(cpu)->numa_blade_id = blade; uv_cpu_hub_info(cpu)->blade_processor_id = lcpu; uv_cpu_hub_info(cpu)->pnode = pnode; - uv_cpu_hub_info(cpu)->pnode_mask = pnode_mask; uv_cpu_hub_info(cpu)->gpa_mask = (1UL << (m_val + n_val)) - 1; uv_cpu_hub_info(cpu)->gnode_upper = gnode_upper; uv_cpu_hub_info(cpu)->gnode_extra = gnode_extra; @@ -775,7 +803,7 @@ void __init uv_system_init(void) map_gru_high(max_pnode); map_mmr_high(max_pnode); - map_mmioh_high(max_pnode); + map_mmioh_high(max_pnode & pnode_io_mask); uv_cpu_init(); uv_scir_register_cpu_notifier(); diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c index 4b68bda30938..1d59834396bd 100644 --- a/arch/x86/kernel/cpu/common.c +++ b/arch/x86/kernel/cpu/common.c @@ -894,7 +894,6 @@ void __init identify_boot_cpu(void) #else vgetcpu_set_mode(); #endif - init_hw_perf_events(); } void __cpuinit identify_secondary_cpu(struct cpuinfo_x86 *c) diff --git a/arch/x86/kernel/cpu/mcheck/mce_amd.c b/arch/x86/kernel/cpu/mcheck/mce_amd.c index 80c482382d5c..5bf2fac52aca 100644 --- a/arch/x86/kernel/cpu/mcheck/mce_amd.c +++ b/arch/x86/kernel/cpu/mcheck/mce_amd.c @@ -31,8 +31,6 @@ #include <asm/mce.h> #include <asm/msr.h> -#define PFX "mce_threshold: " -#define VERSION "version 1.1.1" #define NR_BANKS 6 #define NR_BLOCKS 9 #define THRESHOLD_MAX 0xFFF @@ -59,12 +57,6 @@ struct threshold_block { struct list_head miscj; }; -/* defaults used early on boot */ -static struct threshold_block threshold_defaults = { - .interrupt_enable = 0, - .threshold_limit = THRESHOLD_MAX, -}; - struct threshold_bank { struct kobject *kobj; struct threshold_block *blocks; @@ -89,50 +81,101 @@ static void amd_threshold_interrupt(void); struct thresh_restart { struct threshold_block *b; int reset; + int set_lvt_off; + int lvt_off; u16 old_limit; }; +static int lvt_off_valid(struct threshold_block *b, int apic, u32 lo, u32 hi) +{ + int msr = (hi & MASK_LVTOFF_HI) >> 20; + + if (apic < 0) { + pr_err(FW_BUG "cpu %d, failed to setup threshold interrupt " + "for bank %d, block %d (MSR%08X=0x%x%08x)\n", b->cpu, + b->bank, b->block, b->address, hi, lo); + return 0; + } + + if (apic != msr) { + pr_err(FW_BUG "cpu %d, invalid threshold interrupt offset %d " + "for bank %d, block %d (MSR%08X=0x%x%08x)\n", + b->cpu, apic, b->bank, b->block, b->address, hi, lo); + return 0; + } + + return 1; +}; + /* must be called with correct cpu affinity */ /* Called via smp_call_function_single() */ static void threshold_restart_bank(void *_tr) { struct thresh_restart *tr = _tr; - u32 mci_misc_hi, mci_misc_lo; + u32 hi, lo; - rdmsr(tr->b->address, mci_misc_lo, mci_misc_hi); + rdmsr(tr->b->address, lo, hi); - if (tr->b->threshold_limit < (mci_misc_hi & THRESHOLD_MAX)) + if (tr->b->threshold_limit < (hi & THRESHOLD_MAX)) tr->reset = 1; /* limit cannot be lower than err count */ if (tr->reset) { /* reset err count and overflow bit */ - mci_misc_hi = - (mci_misc_hi & ~(MASK_ERR_COUNT_HI | MASK_OVERFLOW_HI)) | + hi = + (hi & ~(MASK_ERR_COUNT_HI | MASK_OVERFLOW_HI)) | (THRESHOLD_MAX - tr->b->threshold_limit); } else if (tr->old_limit) { /* change limit w/o reset */ - int new_count = (mci_misc_hi & THRESHOLD_MAX) + + int new_count = (hi & THRESHOLD_MAX) + (tr->old_limit - tr->b->threshold_limit); - mci_misc_hi = (mci_misc_hi & ~MASK_ERR_COUNT_HI) | + hi = (hi & ~MASK_ERR_COUNT_HI) | (new_count & THRESHOLD_MAX); } + if (tr->set_lvt_off) { + if (lvt_off_valid(tr->b, tr->lvt_off, lo, hi)) { + /* set new lvt offset */ + hi &= ~MASK_LVTOFF_HI; + hi |= tr->lvt_off << 20; + } + } + tr->b->interrupt_enable ? - (mci_misc_hi = (mci_misc_hi & ~MASK_INT_TYPE_HI) | INT_TYPE_APIC) : - (mci_misc_hi &= ~MASK_INT_TYPE_HI); + (hi = (hi & ~MASK_INT_TYPE_HI) | INT_TYPE_APIC) : + (hi &= ~MASK_INT_TYPE_HI); - mci_misc_hi |= MASK_COUNT_EN_HI; - wrmsr(tr->b->address, mci_misc_lo, mci_misc_hi); + hi |= MASK_COUNT_EN_HI; + wrmsr(tr->b->address, lo, hi); +} + +static void mce_threshold_block_init(struct threshold_block *b, int offset) +{ + struct thresh_restart tr = { + .b = b, + .set_lvt_off = 1, + .lvt_off = offset, + }; + + b->threshold_limit = THRESHOLD_MAX; + threshold_restart_bank(&tr); +}; + +static int setup_APIC_mce(int reserved, int new) +{ + if (reserved < 0 && !setup_APIC_eilvt(new, THRESHOLD_APIC_VECTOR, + APIC_EILVT_MSG_FIX, 0)) + return new; + + return reserved; } /* cpu init entry point, called from mce.c with preempt off */ void mce_amd_feature_init(struct cpuinfo_x86 *c) { + struct threshold_block b; unsigned int cpu = smp_processor_id(); u32 low = 0, high = 0, address = 0; unsigned int bank, block; - struct thresh_restart tr; - int lvt_off = -1; - u8 offset; + int offset = -1; for (bank = 0; bank < NR_BANKS; ++bank) { for (block = 0; block < NR_BLOCKS; ++block) { @@ -163,39 +206,16 @@ void mce_amd_feature_init(struct cpuinfo_x86 *c) if (shared_bank[bank] && c->cpu_core_id) break; #endif - offset = (high & MASK_LVTOFF_HI) >> 20; - if (lvt_off < 0) { - if (setup_APIC_eilvt(offset, - THRESHOLD_APIC_VECTOR, - APIC_EILVT_MSG_FIX, 0)) { - pr_err(FW_BUG "cpu %d, failed to " - "setup threshold interrupt " - "for bank %d, block %d " - "(MSR%08X=0x%x%08x)", - smp_processor_id(), bank, block, - address, high, low); - continue; - } - lvt_off = offset; - } else if (lvt_off != offset) { - pr_err(FW_BUG "cpu %d, invalid threshold " - "interrupt offset %d for bank %d," - "block %d (MSR%08X=0x%x%08x)", - smp_processor_id(), lvt_off, bank, - block, address, high, low); - continue; - } - - high &= ~MASK_LVTOFF_HI; - high |= lvt_off << 20; - wrmsr(address, low, high); + offset = setup_APIC_mce(offset, + (high & MASK_LVTOFF_HI) >> 20); - threshold_defaults.address = address; - tr.b = &threshold_defaults; - tr.reset = 0; - tr.old_limit = 0; - threshold_restart_bank(&tr); + memset(&b, 0, sizeof(b)); + b.cpu = cpu; + b.bank = bank; + b.block = block; + b.address = address; + mce_threshold_block_init(&b, offset); mce_threshold_vector = amd_threshold_interrupt; } } @@ -298,9 +318,8 @@ store_interrupt_enable(struct threshold_block *b, const char *buf, size_t size) b->interrupt_enable = !!new; + memset(&tr, 0, sizeof(tr)); tr.b = b; - tr.reset = 0; - tr.old_limit = 0; smp_call_function_single(b->cpu, threshold_restart_bank, &tr, 1); @@ -321,10 +340,10 @@ store_threshold_limit(struct threshold_block *b, const char *buf, size_t size) if (new < 1) new = 1; + memset(&tr, 0, sizeof(tr)); tr.old_limit = b->threshold_limit; b->threshold_limit = new; tr.b = b; - tr.reset = 0; smp_call_function_single(b->cpu, threshold_restart_bank, &tr, 1); @@ -603,9 +622,9 @@ static __cpuinit int threshold_create_device(unsigned int cpu) continue; err = threshold_create_bank(cpu, bank); if (err) - goto out; + return err; } -out: + return err; } diff --git a/arch/x86/kernel/cpu/mcheck/therm_throt.c b/arch/x86/kernel/cpu/mcheck/therm_throt.c index 4b683267eca5..e12246ff5aa6 100644 --- a/arch/x86/kernel/cpu/mcheck/therm_throt.c +++ b/arch/x86/kernel/cpu/mcheck/therm_throt.c @@ -53,8 +53,13 @@ struct thermal_state { struct _thermal_state core_power_limit; struct _thermal_state package_throttle; struct _thermal_state package_power_limit; + struct _thermal_state core_thresh0; + struct _thermal_state core_thresh1; }; +/* Callback to handle core threshold interrupts */ +int (*platform_thermal_notify)(__u64 msr_val); + static DEFINE_PER_CPU(struct thermal_state, thermal_state); static atomic_t therm_throt_en = ATOMIC_INIT(0); @@ -200,6 +205,22 @@ static int therm_throt_process(bool new_event, int event, int level) return 0; } +static int thresh_event_valid(int event) +{ + struct _thermal_state *state; + unsigned int this_cpu = smp_processor_id(); + struct thermal_state *pstate = &per_cpu(thermal_state, this_cpu); + u64 now = get_jiffies_64(); + + state = (event == 0) ? &pstate->core_thresh0 : &pstate->core_thresh1; + + if (time_before64(now, state->next_check)) + return 0; + + state->next_check = now + CHECK_INTERVAL; + return 1; +} + #ifdef CONFIG_SYSFS /* Add/Remove thermal_throttle interface for CPU device: */ static __cpuinit int thermal_throttle_add_dev(struct sys_device *sys_dev, @@ -313,6 +334,22 @@ device_initcall(thermal_throttle_init_device); #define PACKAGE_THROTTLED ((__u64)2 << 62) #define PACKAGE_POWER_LIMIT ((__u64)3 << 62) +static void notify_thresholds(__u64 msr_val) +{ + /* check whether the interrupt handler is defined; + * otherwise simply return + */ + if (!platform_thermal_notify) + return; + + /* lower threshold reached */ + if ((msr_val & THERM_LOG_THRESHOLD0) && thresh_event_valid(0)) + platform_thermal_notify(msr_val); + /* higher threshold reached */ + if ((msr_val & THERM_LOG_THRESHOLD1) && thresh_event_valid(1)) + platform_thermal_notify(msr_val); +} + /* Thermal transition interrupt handler */ static void intel_thermal_interrupt(void) { @@ -321,6 +358,9 @@ static void intel_thermal_interrupt(void) rdmsrl(MSR_IA32_THERM_STATUS, msr_val); + /* Check for violation of core thermal thresholds*/ + notify_thresholds(msr_val); + if (therm_throt_process(msr_val & THERM_STATUS_PROCHOT, THERMAL_THROTTLING_EVENT, CORE_LEVEL) != 0) diff --git a/arch/x86/kernel/cpu/perf_event.c b/arch/x86/kernel/cpu/perf_event.c index ed6310183efb..0a360d146596 100644 --- a/arch/x86/kernel/cpu/perf_event.c +++ b/arch/x86/kernel/cpu/perf_event.c @@ -330,9 +330,6 @@ static bool reserve_pmc_hardware(void) { int i; - if (nmi_watchdog == NMI_LOCAL_APIC) - disable_lapic_nmi_watchdog(); - for (i = 0; i < x86_pmu.num_counters; i++) { if (!reserve_perfctr_nmi(x86_pmu.perfctr + i)) goto perfctr_fail; @@ -355,9 +352,6 @@ perfctr_fail: for (i--; i >= 0; i--) release_perfctr_nmi(x86_pmu.perfctr + i); - if (nmi_watchdog == NMI_LOCAL_APIC) - enable_lapic_nmi_watchdog(); - return false; } @@ -369,9 +363,6 @@ static void release_pmc_hardware(void) release_perfctr_nmi(x86_pmu.perfctr + i); release_evntsel_nmi(x86_pmu.eventsel + i); } - - if (nmi_watchdog == NMI_LOCAL_APIC) - enable_lapic_nmi_watchdog(); } #else @@ -381,6 +372,58 @@ static void release_pmc_hardware(void) {} #endif +static bool check_hw_exists(void) +{ + u64 val, val_new = 0; + int i, reg, ret = 0; + + /* + * Check to see if the BIOS enabled any of the counters, if so + * complain and bail. + */ + for (i = 0; i < x86_pmu.num_counters; i++) { + reg = x86_pmu.eventsel + i; + ret = rdmsrl_safe(reg, &val); + if (ret) + goto msr_fail; + if (val & ARCH_PERFMON_EVENTSEL_ENABLE) + goto bios_fail; + } + + if (x86_pmu.num_counters_fixed) { + reg = MSR_ARCH_PERFMON_FIXED_CTR_CTRL; + ret = rdmsrl_safe(reg, &val); + if (ret) + goto msr_fail; + for (i = 0; i < x86_pmu.num_counters_fixed; i++) { + if (val & (0x03 << i*4)) + goto bios_fail; + } + } + + /* + * Now write a value and read it back to see if it matches, + * this is needed to detect certain hardware emulators (qemu/kvm) + * that don't trap on the MSR access and always return 0s. + */ + val = 0xabcdUL; + ret = checking_wrmsrl(x86_pmu.perfctr, val); + ret |= rdmsrl_safe(x86_pmu.perfctr, &val_new); + if (ret || val != val_new) + goto msr_fail; + + return true; + +bios_fail: + printk(KERN_CONT "Broken BIOS detected, using software events only.\n"); + printk(KERN_ERR FW_BUG "the BIOS has corrupted hw-PMU resources (MSR %x is %Lx)\n", reg, val); + return false; + +msr_fail: + printk(KERN_CONT "Broken PMU hardware detected, using software events only.\n"); + return false; +} + static void reserve_ds_buffers(void); static void release_ds_buffers(void); @@ -437,7 +480,7 @@ static int x86_setup_perfctr(struct perf_event *event) struct hw_perf_event *hwc = &event->hw; u64 config; - if (!hwc->sample_period) { + if (!is_sampling_event(event)) { hwc->sample_period = x86_pmu.max_period; hwc->last_period = hwc->sample_period; local64_set(&hwc->period_left, hwc->sample_period); @@ -1348,7 +1391,7 @@ static void __init pmu_check_apic(void) pr_info("no hardware sampling interrupt available.\n"); } -void __init init_hw_perf_events(void) +int __init init_hw_perf_events(void) { struct event_constraint *c; int err; @@ -1363,15 +1406,19 @@ void __init init_hw_perf_events(void) err = amd_pmu_init(); break; default: - return; + return 0; } if (err != 0) { pr_cont("no PMU driver, software events only.\n"); - return; + return 0; } pmu_check_apic(); + /* sanity check that the hardware exists or is emulated */ + if (!check_hw_exists()) + return 0; + pr_cont("%s PMU driver.\n", x86_pmu.name); if (x86_pmu.quirks) @@ -1418,9 +1465,12 @@ void __init init_hw_perf_events(void) pr_info("... fixed-purpose events: %d\n", x86_pmu.num_counters_fixed); pr_info("... event mask: %016Lx\n", x86_pmu.intel_ctrl); - perf_pmu_register(&pmu); + perf_pmu_register(&pmu, "cpu", PERF_TYPE_RAW); perf_cpu_notifier(x86_pmu_notifier); + + return 0; } +early_initcall(init_hw_perf_events); static inline void x86_pmu_read(struct perf_event *event) { @@ -1666,7 +1716,7 @@ perf_callchain_kernel(struct perf_callchain_entry *entry, struct pt_regs *regs) perf_callchain_store(entry, regs->ip); - dump_trace(NULL, regs, NULL, regs->bp, &backtrace_ops, entry); + dump_trace(NULL, regs, NULL, &backtrace_ops, entry); } #ifdef CONFIG_COMPAT diff --git a/arch/x86/kernel/cpu/perf_event_amd.c b/arch/x86/kernel/cpu/perf_event_amd.c index e421b8cd6944..67e2202a6039 100644 --- a/arch/x86/kernel/cpu/perf_event_amd.c +++ b/arch/x86/kernel/cpu/perf_event_amd.c @@ -1,7 +1,5 @@ #ifdef CONFIG_CPU_SUP_AMD -static DEFINE_RAW_SPINLOCK(amd_nb_lock); - static __initconst const u64 amd_hw_cache_event_ids [PERF_COUNT_HW_CACHE_MAX] [PERF_COUNT_HW_CACHE_OP_MAX] @@ -275,7 +273,7 @@ done: return &emptyconstraint; } -static struct amd_nb *amd_alloc_nb(int cpu, int nb_id) +static struct amd_nb *amd_alloc_nb(int cpu) { struct amd_nb *nb; int i; @@ -285,7 +283,7 @@ static struct amd_nb *amd_alloc_nb(int cpu, int nb_id) if (!nb) return NULL; - nb->nb_id = nb_id; + nb->nb_id = -1; /* * initialize all possible NB constraints @@ -306,7 +304,7 @@ static int amd_pmu_cpu_prepare(int cpu) if (boot_cpu_data.x86_max_cores < 2) return NOTIFY_OK; - cpuc->amd_nb = amd_alloc_nb(cpu, -1); + cpuc->amd_nb = amd_alloc_nb(cpu); if (!cpuc->amd_nb) return NOTIFY_BAD; @@ -325,8 +323,6 @@ static void amd_pmu_cpu_starting(int cpu) nb_id = amd_get_nb_id(cpu); WARN_ON_ONCE(nb_id == BAD_APICID); - raw_spin_lock(&amd_nb_lock); - for_each_online_cpu(i) { nb = per_cpu(cpu_hw_events, i).amd_nb; if (WARN_ON_ONCE(!nb)) @@ -341,8 +337,6 @@ static void amd_pmu_cpu_starting(int cpu) cpuc->amd_nb->nb_id = nb_id; cpuc->amd_nb->refcnt++; - - raw_spin_unlock(&amd_nb_lock); } static void amd_pmu_cpu_dead(int cpu) @@ -354,8 +348,6 @@ static void amd_pmu_cpu_dead(int cpu) cpuhw = &per_cpu(cpu_hw_events, cpu); - raw_spin_lock(&amd_nb_lock); - if (cpuhw->amd_nb) { struct amd_nb *nb = cpuhw->amd_nb; @@ -364,8 +356,6 @@ static void amd_pmu_cpu_dead(int cpu) cpuhw->amd_nb = NULL; } - - raw_spin_unlock(&amd_nb_lock); } static __initconst const struct x86_pmu amd_pmu = { diff --git a/arch/x86/kernel/cpu/perf_event_intel.c b/arch/x86/kernel/cpu/perf_event_intel.c index c8f5c088cad1..24e390e40f2e 100644 --- a/arch/x86/kernel/cpu/perf_event_intel.c +++ b/arch/x86/kernel/cpu/perf_event_intel.c @@ -816,6 +816,32 @@ static int intel_pmu_hw_config(struct perf_event *event) if (ret) return ret; + if (event->attr.precise_ip && + (event->hw.config & X86_RAW_EVENT_MASK) == 0x003c) { + /* + * Use an alternative encoding for CPU_CLK_UNHALTED.THREAD_P + * (0x003c) so that we can use it with PEBS. + * + * The regular CPU_CLK_UNHALTED.THREAD_P event (0x003c) isn't + * PEBS capable. However we can use INST_RETIRED.ANY_P + * (0x00c0), which is a PEBS capable event, to get the same + * count. + * + * INST_RETIRED.ANY_P counts the number of cycles that retires + * CNTMASK instructions. By setting CNTMASK to a value (16) + * larger than the maximum number of instructions that can be + * retired per cycle (4) and then inverting the condition, we + * count all cycles that retire 16 or less instructions, which + * is every cycle. + * + * Thereby we gain a PEBS capable cycle counter. + */ + u64 alt_config = 0x108000c0; /* INST_RETIRED.TOTAL_CYCLES */ + + alt_config |= (event->hw.config & ~X86_RAW_EVENT_MASK); + event->hw.config = alt_config; + } + if (event->attr.type != PERF_TYPE_RAW) return 0; diff --git a/arch/x86/kernel/cpu/perfctr-watchdog.c b/arch/x86/kernel/cpu/perfctr-watchdog.c index d9f4ff8fcd69..d5a236615501 100644 --- a/arch/x86/kernel/cpu/perfctr-watchdog.c +++ b/arch/x86/kernel/cpu/perfctr-watchdog.c @@ -16,32 +16,12 @@ #include <linux/kernel.h> #include <linux/bitops.h> #include <linux/smp.h> -#include <linux/nmi.h> +#include <asm/nmi.h> #include <linux/kprobes.h> #include <asm/apic.h> #include <asm/perf_event.h> -struct nmi_watchdog_ctlblk { - unsigned int cccr_msr; - unsigned int perfctr_msr; /* the MSR to reset in NMI handler */ - unsigned int evntsel_msr; /* the MSR to select the events to handle */ -}; - -/* Interface defining a CPU specific perfctr watchdog */ -struct wd_ops { - int (*reserve)(void); - void (*unreserve)(void); - int (*setup)(unsigned nmi_hz); - void (*rearm)(struct nmi_watchdog_ctlblk *wd, unsigned nmi_hz); - void (*stop)(void); - unsigned perfctr; - unsigned evntsel; - u64 checkbit; -}; - -static const struct wd_ops *wd_ops; - /* * this number is calculated from Intel's MSR_P4_CRU_ESCR5 register and it's * offset from MSR_P4_BSU_ESCR0. @@ -60,8 +40,6 @@ static const struct wd_ops *wd_ops; static DECLARE_BITMAP(perfctr_nmi_owner, NMI_MAX_COUNTER_BITS); static DECLARE_BITMAP(evntsel_nmi_owner, NMI_MAX_COUNTER_BITS); -static DEFINE_PER_CPU(struct nmi_watchdog_ctlblk, nmi_watchdog_ctlblk); - /* converts an msr to an appropriate reservation bit */ static inline unsigned int nmi_perfctr_msr_to_bit(unsigned int msr) { @@ -172,623 +150,3 @@ void release_evntsel_nmi(unsigned int msr) clear_bit(counter, evntsel_nmi_owner); } EXPORT_SYMBOL(release_evntsel_nmi); - -void disable_lapic_nmi_watchdog(void) -{ - BUG_ON(nmi_watchdog != NMI_LOCAL_APIC); - - if (atomic_read(&nmi_active) <= 0) - return; - - on_each_cpu(stop_apic_nmi_watchdog, NULL, 1); - - if (wd_ops) - wd_ops->unreserve(); - - BUG_ON(atomic_read(&nmi_active) != 0); -} - -void enable_lapic_nmi_watchdog(void) -{ - BUG_ON(nmi_watchdog != NMI_LOCAL_APIC); - - /* are we already enabled */ - if (atomic_read(&nmi_active) != 0) - return; - - /* are we lapic aware */ - if (!wd_ops) - return; - if (!wd_ops->reserve()) { - printk(KERN_ERR "NMI watchdog: cannot reserve perfctrs\n"); - return; - } - - on_each_cpu(setup_apic_nmi_watchdog, NULL, 1); - touch_nmi_watchdog(); -} - -/* - * Activate the NMI watchdog via the local APIC. - */ - -static unsigned int adjust_for_32bit_ctr(unsigned int hz) -{ - u64 counter_val; - unsigned int retval = hz; - - /* - * On Intel CPUs with P6/ARCH_PERFMON only 32 bits in the counter - * are writable, with higher bits sign extending from bit 31. - * So, we can only program the counter with 31 bit values and - * 32nd bit should be 1, for 33.. to be 1. - * Find the appropriate nmi_hz - */ - counter_val = (u64)cpu_khz * 1000; - do_div(counter_val, retval); - if (counter_val > 0x7fffffffULL) { - u64 count = (u64)cpu_khz * 1000; - do_div(count, 0x7fffffffUL); - retval = count + 1; - } - return retval; -} - -static void write_watchdog_counter(unsigned int perfctr_msr, - const char *descr, unsigned nmi_hz) -{ - u64 count = (u64)cpu_khz * 1000; - - do_div(count, nmi_hz); - if (descr) - pr_debug("setting %s to -0x%08Lx\n", descr, count); - wrmsrl(perfctr_msr, 0 - count); -} - -static void write_watchdog_counter32(unsigned int perfctr_msr, - const char *descr, unsigned nmi_hz) -{ - u64 count = (u64)cpu_khz * 1000; - - do_div(count, nmi_hz); - if (descr) - pr_debug("setting %s to -0x%08Lx\n", descr, count); - wrmsr(perfctr_msr, (u32)(-count), 0); -} - -/* - * AMD K7/K8/Family10h/Family11h support. - * AMD keeps this interface nicely stable so there is not much variety - */ -#define K7_EVNTSEL_ENABLE (1 << 22) -#define K7_EVNTSEL_INT (1 << 20) -#define K7_EVNTSEL_OS (1 << 17) -#define K7_EVNTSEL_USR (1 << 16) -#define K7_EVENT_CYCLES_PROCESSOR_IS_RUNNING 0x76 -#define K7_NMI_EVENT K7_EVENT_CYCLES_PROCESSOR_IS_RUNNING - -static int setup_k7_watchdog(unsigned nmi_hz) -{ - unsigned int perfctr_msr, evntsel_msr; - unsigned int evntsel; - struct nmi_watchdog_ctlblk *wd = &__get_cpu_var(nmi_watchdog_ctlblk); - - perfctr_msr = wd_ops->perfctr; - evntsel_msr = wd_ops->evntsel; - - wrmsrl(perfctr_msr, 0UL); - - evntsel = K7_EVNTSEL_INT - | K7_EVNTSEL_OS - | K7_EVNTSEL_USR - | K7_NMI_EVENT; - - /* setup the timer */ - wrmsr(evntsel_msr, evntsel, 0); - write_watchdog_counter(perfctr_msr, "K7_PERFCTR0", nmi_hz); - - /* initialize the wd struct before enabling */ - wd->perfctr_msr = perfctr_msr; - wd->evntsel_msr = evntsel_msr; - wd->cccr_msr = 0; /* unused */ - - /* ok, everything is initialized, announce that we're set */ - cpu_nmi_set_wd_enabled(); - - apic_write(APIC_LVTPC, APIC_DM_NMI); - evntsel |= K7_EVNTSEL_ENABLE; - wrmsr(evntsel_msr, evntsel, 0); - - return 1; -} - -static void single_msr_stop_watchdog(void) -{ - struct nmi_watchdog_ctlblk *wd = &__get_cpu_var(nmi_watchdog_ctlblk); - - wrmsr(wd->evntsel_msr, 0, 0); -} - -static int single_msr_reserve(void) -{ - if (!reserve_perfctr_nmi(wd_ops->perfctr)) - return 0; - - if (!reserve_evntsel_nmi(wd_ops->evntsel)) { - release_perfctr_nmi(wd_ops->perfctr); - return 0; - } - return 1; -} - -static void single_msr_unreserve(void) -{ - release_evntsel_nmi(wd_ops->evntsel); - release_perfctr_nmi(wd_ops->perfctr); -} - -static void __kprobes -single_msr_rearm(struct nmi_watchdog_ctlblk *wd, unsigned nmi_hz) -{ - /* start the cycle over again */ - write_watchdog_counter(wd->perfctr_msr, NULL, nmi_hz); -} - -static const struct wd_ops k7_wd_ops = { - .reserve = single_msr_reserve, - .unreserve = single_msr_unreserve, - .setup = setup_k7_watchdog, - .rearm = single_msr_rearm, - .stop = single_msr_stop_watchdog, - .perfctr = MSR_K7_PERFCTR0, - .evntsel = MSR_K7_EVNTSEL0, - .checkbit = 1ULL << 47, -}; - -/* - * Intel Model 6 (PPro+,P2,P3,P-M,Core1) - */ -#define P6_EVNTSEL0_ENABLE (1 << 22) -#define P6_EVNTSEL_INT (1 << 20) -#define P6_EVNTSEL_OS (1 << 17) -#define P6_EVNTSEL_USR (1 << 16) -#define P6_EVENT_CPU_CLOCKS_NOT_HALTED 0x79 -#define P6_NMI_EVENT P6_EVENT_CPU_CLOCKS_NOT_HALTED - -static int setup_p6_watchdog(unsigned nmi_hz) -{ - unsigned int perfctr_msr, evntsel_msr; - unsigned int evntsel; - struct nmi_watchdog_ctlblk *wd = &__get_cpu_var(nmi_watchdog_ctlblk); - - perfctr_msr = wd_ops->perfctr; - evntsel_msr = wd_ops->evntsel; - - /* KVM doesn't implement this MSR */ - if (wrmsr_safe(perfctr_msr, 0, 0) < 0) - return 0; - - evntsel = P6_EVNTSEL_INT - | P6_EVNTSEL_OS - | P6_EVNTSEL_USR - | P6_NMI_EVENT; - - /* setup the timer */ - wrmsr(evntsel_msr, evntsel, 0); - nmi_hz = adjust_for_32bit_ctr(nmi_hz); - write_watchdog_counter32(perfctr_msr, "P6_PERFCTR0", nmi_hz); - - /* initialize the wd struct before enabling */ - wd->perfctr_msr = perfctr_msr; - wd->evntsel_msr = evntsel_msr; - wd->cccr_msr = 0; /* unused */ - - /* ok, everything is initialized, announce that we're set */ - cpu_nmi_set_wd_enabled(); - - apic_write(APIC_LVTPC, APIC_DM_NMI); - evntsel |= P6_EVNTSEL0_ENABLE; - wrmsr(evntsel_msr, evntsel, 0); - - return 1; -} - -static void __kprobes p6_rearm(struct nmi_watchdog_ctlblk *wd, unsigned nmi_hz) -{ - /* - * P6 based Pentium M need to re-unmask - * the apic vector but it doesn't hurt - * other P6 variant. - * ArchPerfom/Core Duo also needs this - */ - apic_write(APIC_LVTPC, APIC_DM_NMI); - - /* P6/ARCH_PERFMON has 32 bit counter write */ - write_watchdog_counter32(wd->perfctr_msr, NULL, nmi_hz); -} - -static const struct wd_ops p6_wd_ops = { - .reserve = single_msr_reserve, - .unreserve = single_msr_unreserve, - .setup = setup_p6_watchdog, - .rearm = p6_rearm, - .stop = single_msr_stop_watchdog, - .perfctr = MSR_P6_PERFCTR0, - .evntsel = MSR_P6_EVNTSEL0, - .checkbit = 1ULL << 39, -}; - -/* - * Intel P4 performance counters. - * By far the most complicated of all. - */ -#define MSR_P4_MISC_ENABLE_PERF_AVAIL (1 << 7) -#define P4_ESCR_EVENT_SELECT(N) ((N) << 25) -#define P4_ESCR_OS (1 << 3) -#define P4_ESCR_USR (1 << 2) -#define P4_CCCR_OVF_PMI0 (1 << 26) -#define P4_CCCR_OVF_PMI1 (1 << 27) -#define P4_CCCR_THRESHOLD(N) ((N) << 20) -#define P4_CCCR_COMPLEMENT (1 << 19) -#define P4_CCCR_COMPARE (1 << 18) -#define P4_CCCR_REQUIRED (3 << 16) -#define P4_CCCR_ESCR_SELECT(N) ((N) << 13) -#define P4_CCCR_ENABLE (1 << 12) -#define P4_CCCR_OVF (1 << 31) - -#define P4_CONTROLS 18 -static unsigned int p4_controls[18] = { - MSR_P4_BPU_CCCR0, - MSR_P4_BPU_CCCR1, - MSR_P4_BPU_CCCR2, - MSR_P4_BPU_CCCR3, - MSR_P4_MS_CCCR0, - MSR_P4_MS_CCCR1, - MSR_P4_MS_CCCR2, - MSR_P4_MS_CCCR3, - MSR_P4_FLAME_CCCR0, - MSR_P4_FLAME_CCCR1, - MSR_P4_FLAME_CCCR2, - MSR_P4_FLAME_CCCR3, - MSR_P4_IQ_CCCR0, - MSR_P4_IQ_CCCR1, - MSR_P4_IQ_CCCR2, - MSR_P4_IQ_CCCR3, - MSR_P4_IQ_CCCR4, - MSR_P4_IQ_CCCR5, -}; -/* - * Set up IQ_COUNTER0 to behave like a clock, by having IQ_CCCR0 filter - * CRU_ESCR0 (with any non-null event selector) through a complemented - * max threshold. [IA32-Vol3, Section 14.9.9] - */ -static int setup_p4_watchdog(unsigned nmi_hz) -{ - unsigned int perfctr_msr, evntsel_msr, cccr_msr; - unsigned int evntsel, cccr_val; - unsigned int misc_enable, dummy; - unsigned int ht_num; - struct nmi_watchdog_ctlblk *wd = &__get_cpu_var(nmi_watchdog_ctlblk); - - rdmsr(MSR_IA32_MISC_ENABLE, misc_enable, dummy); - if (!(misc_enable & MSR_P4_MISC_ENABLE_PERF_AVAIL)) - return 0; - -#ifdef CONFIG_SMP - /* detect which hyperthread we are on */ - if (smp_num_siblings == 2) { - unsigned int ebx, apicid; - - ebx = cpuid_ebx(1); - apicid = (ebx >> 24) & 0xff; - ht_num = apicid & 1; - } else -#endif - ht_num = 0; - - /* - * performance counters are shared resources - * assign each hyperthread its own set - * (re-use the ESCR0 register, seems safe - * and keeps the cccr_val the same) - */ - if (!ht_num) { - /* logical cpu 0 */ - perfctr_msr = MSR_P4_IQ_PERFCTR0; - evntsel_msr = MSR_P4_CRU_ESCR0; - cccr_msr = MSR_P4_IQ_CCCR0; - cccr_val = P4_CCCR_OVF_PMI0 | P4_CCCR_ESCR_SELECT(4); - - /* - * If we're on the kdump kernel or other situation, we may - * still have other performance counter registers set to - * interrupt and they'll keep interrupting forever because - * of the P4_CCCR_OVF quirk. So we need to ACK all the - * pending interrupts and disable all the registers here, - * before reenabling the NMI delivery. Refer to p4_rearm() - * about the P4_CCCR_OVF quirk. - */ - if (reset_devices) { - unsigned int low, high; - int i; - - for (i = 0; i < P4_CONTROLS; i++) { - rdmsr(p4_controls[i], low, high); - low &= ~(P4_CCCR_ENABLE | P4_CCCR_OVF); - wrmsr(p4_controls[i], low, high); - } - } - } else { - /* logical cpu 1 */ - perfctr_msr = MSR_P4_IQ_PERFCTR1; - evntsel_msr = MSR_P4_CRU_ESCR0; - cccr_msr = MSR_P4_IQ_CCCR1; - - /* Pentium 4 D processors don't support P4_CCCR_OVF_PMI1 */ - if (boot_cpu_data.x86_model == 4 && boot_cpu_data.x86_mask == 4) - cccr_val = P4_CCCR_OVF_PMI0; - else - cccr_val = P4_CCCR_OVF_PMI1; - cccr_val |= P4_CCCR_ESCR_SELECT(4); - } - - evntsel = P4_ESCR_EVENT_SELECT(0x3F) - | P4_ESCR_OS - | P4_ESCR_USR; - - cccr_val |= P4_CCCR_THRESHOLD(15) - | P4_CCCR_COMPLEMENT - | P4_CCCR_COMPARE - | P4_CCCR_REQUIRED; - - wrmsr(evntsel_msr, evntsel, 0); - wrmsr(cccr_msr, cccr_val, 0); - write_watchdog_counter(perfctr_msr, "P4_IQ_COUNTER0", nmi_hz); - - wd->perfctr_msr = perfctr_msr; - wd->evntsel_msr = evntsel_msr; - wd->cccr_msr = cccr_msr; - - /* ok, everything is initialized, announce that we're set */ - cpu_nmi_set_wd_enabled(); - - apic_write(APIC_LVTPC, APIC_DM_NMI); - cccr_val |= P4_CCCR_ENABLE; - wrmsr(cccr_msr, cccr_val, 0); - return 1; -} - -static void stop_p4_watchdog(void) -{ - struct nmi_watchdog_ctlblk *wd = &__get_cpu_var(nmi_watchdog_ctlblk); - wrmsr(wd->cccr_msr, 0, 0); - wrmsr(wd->evntsel_msr, 0, 0); -} - -static int p4_reserve(void) -{ - if (!reserve_perfctr_nmi(MSR_P4_IQ_PERFCTR0)) - return 0; -#ifdef CONFIG_SMP - if (smp_num_siblings > 1 && !reserve_perfctr_nmi(MSR_P4_IQ_PERFCTR1)) - goto fail1; -#endif - if (!reserve_evntsel_nmi(MSR_P4_CRU_ESCR0)) - goto fail2; - /* RED-PEN why is ESCR1 not reserved here? */ - return 1; - fail2: -#ifdef CONFIG_SMP - if (smp_num_siblings > 1) - release_perfctr_nmi(MSR_P4_IQ_PERFCTR1); - fail1: -#endif - release_perfctr_nmi(MSR_P4_IQ_PERFCTR0); - return 0; -} - -static void p4_unreserve(void) -{ -#ifdef CONFIG_SMP - if (smp_num_siblings > 1) - release_perfctr_nmi(MSR_P4_IQ_PERFCTR1); -#endif - release_evntsel_nmi(MSR_P4_CRU_ESCR0); - release_perfctr_nmi(MSR_P4_IQ_PERFCTR0); -} - -static void __kprobes p4_rearm(struct nmi_watchdog_ctlblk *wd, unsigned nmi_hz) -{ - unsigned dummy; - /* - * P4 quirks: - * - An overflown perfctr will assert its interrupt - * until the OVF flag in its CCCR is cleared. - * - LVTPC is masked on interrupt and must be - * unmasked by the LVTPC handler. - */ - rdmsrl(wd->cccr_msr, dummy); - dummy &= ~P4_CCCR_OVF; - wrmsrl(wd->cccr_msr, dummy); - apic_write(APIC_LVTPC, APIC_DM_NMI); - /* start the cycle over again */ - write_watchdog_counter(wd->perfctr_msr, NULL, nmi_hz); -} - -static const struct wd_ops p4_wd_ops = { - .reserve = p4_reserve, - .unreserve = p4_unreserve, - .setup = setup_p4_watchdog, - .rearm = p4_rearm, - .stop = stop_p4_watchdog, - /* RED-PEN this is wrong for the other sibling */ - .perfctr = MSR_P4_BPU_PERFCTR0, - .evntsel = MSR_P4_BSU_ESCR0, - .checkbit = 1ULL << 39, -}; - -/* - * Watchdog using the Intel architected PerfMon. - * Used for Core2 and hopefully all future Intel CPUs. - */ -#define ARCH_PERFMON_NMI_EVENT_SEL ARCH_PERFMON_UNHALTED_CORE_CYCLES_SEL -#define ARCH_PERFMON_NMI_EVENT_UMASK ARCH_PERFMON_UNHALTED_CORE_CYCLES_UMASK - -static struct wd_ops intel_arch_wd_ops; - -static int setup_intel_arch_watchdog(unsigned nmi_hz) -{ - unsigned int ebx; - union cpuid10_eax eax; - unsigned int unused; - unsigned int perfctr_msr, evntsel_msr; - unsigned int evntsel; - struct nmi_watchdog_ctlblk *wd = &__get_cpu_var(nmi_watchdog_ctlblk); - - /* - * Check whether the Architectural PerfMon supports - * Unhalted Core Cycles Event or not. - * NOTE: Corresponding bit = 0 in ebx indicates event present. - */ - cpuid(10, &(eax.full), &ebx, &unused, &unused); - if ((eax.split.mask_length < - (ARCH_PERFMON_UNHALTED_CORE_CYCLES_INDEX+1)) || - (ebx & ARCH_PERFMON_UNHALTED_CORE_CYCLES_PRESENT)) - return 0; - - perfctr_msr = wd_ops->perfctr; - evntsel_msr = wd_ops->evntsel; - - wrmsrl(perfctr_msr, 0UL); - - evntsel = ARCH_PERFMON_EVENTSEL_INT - | ARCH_PERFMON_EVENTSEL_OS - | ARCH_PERFMON_EVENTSEL_USR - | ARCH_PERFMON_NMI_EVENT_SEL - | ARCH_PERFMON_NMI_EVENT_UMASK; - - /* setup the timer */ - wrmsr(evntsel_msr, evntsel, 0); - nmi_hz = adjust_for_32bit_ctr(nmi_hz); - write_watchdog_counter32(perfctr_msr, "INTEL_ARCH_PERFCTR0", nmi_hz); - - wd->perfctr_msr = perfctr_msr; - wd->evntsel_msr = evntsel_msr; - wd->cccr_msr = 0; /* unused */ - - /* ok, everything is initialized, announce that we're set */ - cpu_nmi_set_wd_enabled(); - - apic_write(APIC_LVTPC, APIC_DM_NMI); - evntsel |= ARCH_PERFMON_EVENTSEL_ENABLE; - wrmsr(evntsel_msr, evntsel, 0); - intel_arch_wd_ops.checkbit = 1ULL << (eax.split.bit_width - 1); - return 1; -} - -static struct wd_ops intel_arch_wd_ops __read_mostly = { - .reserve = single_msr_reserve, - .unreserve = single_msr_unreserve, - .setup = setup_intel_arch_watchdog, - .rearm = p6_rearm, - .stop = single_msr_stop_watchdog, - .perfctr = MSR_ARCH_PERFMON_PERFCTR1, - .evntsel = MSR_ARCH_PERFMON_EVENTSEL1, -}; - -static void probe_nmi_watchdog(void) -{ - switch (boot_cpu_data.x86_vendor) { - case X86_VENDOR_AMD: - if (boot_cpu_data.x86 == 6 || - (boot_cpu_data.x86 >= 0xf && boot_cpu_data.x86 <= 0x15)) - wd_ops = &k7_wd_ops; - return; - case X86_VENDOR_INTEL: - /* Work around where perfctr1 doesn't have a working enable - * bit as described in the following errata: - * AE49 Core Duo and Intel Core Solo 65 nm - * AN49 Intel Pentium Dual-Core - * AF49 Dual-Core Intel Xeon Processor LV - */ - if ((boot_cpu_data.x86 == 6 && boot_cpu_data.x86_model == 14) || - ((boot_cpu_data.x86 == 6 && boot_cpu_data.x86_model == 15 && - boot_cpu_data.x86_mask == 4))) { - intel_arch_wd_ops.perfctr = MSR_ARCH_PERFMON_PERFCTR0; - intel_arch_wd_ops.evntsel = MSR_ARCH_PERFMON_EVENTSEL0; - } - if (cpu_has(&boot_cpu_data, X86_FEATURE_ARCH_PERFMON)) { - wd_ops = &intel_arch_wd_ops; - break; - } - switch (boot_cpu_data.x86) { - case 6: - if (boot_cpu_data.x86_model > 13) - return; - - wd_ops = &p6_wd_ops; - break; - case 15: - wd_ops = &p4_wd_ops; - break; - default: - return; - } - break; - } -} - -/* Interface to nmi.c */ - -int lapic_watchdog_init(unsigned nmi_hz) -{ - if (!wd_ops) { - probe_nmi_watchdog(); - if (!wd_ops) { - printk(KERN_INFO "NMI watchdog: CPU not supported\n"); - return -1; - } - - if (!wd_ops->reserve()) { - printk(KERN_ERR - "NMI watchdog: cannot reserve perfctrs\n"); - return -1; - } - } - - if (!(wd_ops->setup(nmi_hz))) { - printk(KERN_ERR "Cannot setup NMI watchdog on CPU %d\n", - raw_smp_processor_id()); - return -1; - } - - return 0; -} - -void lapic_watchdog_stop(void) -{ - if (wd_ops) - wd_ops->stop(); -} - -unsigned lapic_adjust_nmi_hz(unsigned hz) -{ - struct nmi_watchdog_ctlblk *wd = &__get_cpu_var(nmi_watchdog_ctlblk); - if (wd->perfctr_msr == MSR_P6_PERFCTR0 || - wd->perfctr_msr == MSR_ARCH_PERFMON_PERFCTR1) - hz = adjust_for_32bit_ctr(hz); - return hz; -} - -int __kprobes lapic_wd_event(unsigned nmi_hz) -{ - struct nmi_watchdog_ctlblk *wd = &__get_cpu_var(nmi_watchdog_ctlblk); - u64 ctr; - - rdmsrl(wd->perfctr_msr, ctr); - if (ctr & wd_ops->checkbit) /* perfctr still running? */ - return 0; - - wd_ops->rearm(wd, nmi_hz); - return 1; -} diff --git a/arch/x86/kernel/cpuid.c b/arch/x86/kernel/cpuid.c index 1b7b31ab7d86..212a6a42527c 100644 --- a/arch/x86/kernel/cpuid.c +++ b/arch/x86/kernel/cpuid.c @@ -33,7 +33,6 @@ #include <linux/init.h> #include <linux/poll.h> #include <linux/smp.h> -#include <linux/smp_lock.h> #include <linux/major.h> #include <linux/fs.h> #include <linux/device.h> diff --git a/arch/x86/kernel/dumpstack.c b/arch/x86/kernel/dumpstack.c index 6e8752c1bd52..8474c998cbd4 100644 --- a/arch/x86/kernel/dumpstack.c +++ b/arch/x86/kernel/dumpstack.c @@ -175,21 +175,21 @@ static const struct stacktrace_ops print_trace_ops = { void show_trace_log_lvl(struct task_struct *task, struct pt_regs *regs, - unsigned long *stack, unsigned long bp, char *log_lvl) + unsigned long *stack, char *log_lvl) { printk("%sCall Trace:\n", log_lvl); - dump_trace(task, regs, stack, bp, &print_trace_ops, log_lvl); + dump_trace(task, regs, stack, &print_trace_ops, log_lvl); } void show_trace(struct task_struct *task, struct pt_regs *regs, - unsigned long *stack, unsigned long bp) + unsigned long *stack) { - show_trace_log_lvl(task, regs, stack, bp, ""); + show_trace_log_lvl(task, regs, stack, ""); } void show_stack(struct task_struct *task, unsigned long *sp) { - show_stack_log_lvl(task, NULL, sp, 0, ""); + show_stack_log_lvl(task, NULL, sp, ""); } /* @@ -210,7 +210,7 @@ void dump_stack(void) init_utsname()->release, (int)strcspn(init_utsname()->version, " "), init_utsname()->version); - show_trace(NULL, NULL, &stack, bp); + show_trace(NULL, NULL, &stack); } EXPORT_SYMBOL(dump_stack); diff --git a/arch/x86/kernel/dumpstack_32.c b/arch/x86/kernel/dumpstack_32.c index 1bc7f75a5bda..74cc1eda384b 100644 --- a/arch/x86/kernel/dumpstack_32.c +++ b/arch/x86/kernel/dumpstack_32.c @@ -17,11 +17,12 @@ #include <asm/stacktrace.h> -void dump_trace(struct task_struct *task, struct pt_regs *regs, - unsigned long *stack, unsigned long bp, +void dump_trace(struct task_struct *task, + struct pt_regs *regs, unsigned long *stack, const struct stacktrace_ops *ops, void *data) { int graph = 0; + unsigned long bp; if (!task) task = current; @@ -34,18 +35,7 @@ void dump_trace(struct task_struct *task, struct pt_regs *regs, 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 - + bp = stack_frame(task, regs); for (;;) { struct thread_info *context; @@ -65,7 +55,7 @@ EXPORT_SYMBOL(dump_trace); void show_stack_log_lvl(struct task_struct *task, struct pt_regs *regs, - unsigned long *sp, unsigned long bp, char *log_lvl) + unsigned long *sp, char *log_lvl) { unsigned long *stack; int i; @@ -87,7 +77,7 @@ show_stack_log_lvl(struct task_struct *task, struct pt_regs *regs, touch_nmi_watchdog(); } printk(KERN_CONT "\n"); - show_trace_log_lvl(task, regs, sp, bp, log_lvl); + show_trace_log_lvl(task, regs, sp, log_lvl); } @@ -112,8 +102,7 @@ void show_registers(struct pt_regs *regs) u8 *ip; printk(KERN_EMERG "Stack:\n"); - show_stack_log_lvl(NULL, regs, ®s->sp, - 0, KERN_EMERG); + show_stack_log_lvl(NULL, regs, ®s->sp, KERN_EMERG); printk(KERN_EMERG "Code: "); diff --git a/arch/x86/kernel/dumpstack_64.c b/arch/x86/kernel/dumpstack_64.c index 6a340485249a..64101335de19 100644 --- a/arch/x86/kernel/dumpstack_64.c +++ b/arch/x86/kernel/dumpstack_64.c @@ -139,8 +139,8 @@ fixup_bp_irq_link(unsigned long bp, unsigned long *stack, * severe exception (double fault, nmi, stack fault, debug, mce) hardware stack */ -void dump_trace(struct task_struct *task, struct pt_regs *regs, - unsigned long *stack, unsigned long bp, +void dump_trace(struct task_struct *task, + struct pt_regs *regs, unsigned long *stack, const struct stacktrace_ops *ops, void *data) { const unsigned cpu = get_cpu(); @@ -149,6 +149,7 @@ void dump_trace(struct task_struct *task, struct pt_regs *regs, unsigned used = 0; struct thread_info *tinfo; int graph = 0; + unsigned long bp; if (!task) task = current; @@ -160,18 +161,7 @@ void dump_trace(struct task_struct *task, struct pt_regs *regs, 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 - + bp = stack_frame(task, regs); /* * Print function call entries in all stacks, starting at the * current stack address. If the stacks consist of nested @@ -235,7 +225,7 @@ EXPORT_SYMBOL(dump_trace); void show_stack_log_lvl(struct task_struct *task, struct pt_regs *regs, - unsigned long *sp, unsigned long bp, char *log_lvl) + unsigned long *sp, char *log_lvl) { unsigned long *irq_stack_end; unsigned long *irq_stack; @@ -279,7 +269,7 @@ show_stack_log_lvl(struct task_struct *task, struct pt_regs *regs, preempt_enable(); printk(KERN_CONT "\n"); - show_trace_log_lvl(task, regs, sp, bp, log_lvl); + show_trace_log_lvl(task, regs, sp, log_lvl); } void show_registers(struct pt_regs *regs) @@ -308,7 +298,7 @@ void show_registers(struct pt_regs *regs) printk(KERN_EMERG "Stack:\n"); show_stack_log_lvl(NULL, regs, (unsigned long *)sp, - regs->bp, KERN_EMERG); + KERN_EMERG); printk(KERN_EMERG "Code: "); diff --git a/arch/x86/kernel/entry_32.S b/arch/x86/kernel/entry_32.S index 59e175e89599..591e60104278 100644 --- a/arch/x86/kernel/entry_32.S +++ b/arch/x86/kernel/entry_32.S @@ -395,7 +395,7 @@ sysenter_past_esp: * A tiny bit of offset fixup is necessary - 4*4 means the 4 words * pushed above; +8 corresponds to copy_thread's esp0 setting. */ - pushl_cfi (TI_sysenter_return-THREAD_SIZE_asm+8+4*4)(%esp) + pushl_cfi ((TI_sysenter_return)-THREAD_SIZE_asm+8+4*4)(%esp) CFI_REL_OFFSET eip, 0 pushl_cfi %eax diff --git a/arch/x86/kernel/entry_64.S b/arch/x86/kernel/entry_64.S index fe2690d71c0c..e3ba417e8697 100644 --- a/arch/x86/kernel/entry_64.S +++ b/arch/x86/kernel/entry_64.S @@ -295,6 +295,7 @@ ENDPROC(native_usergs_sysret64) .endm /* save partial stack frame */ + .pushsection .kprobes.text, "ax" ENTRY(save_args) XCPT_FRAME cld @@ -334,6 +335,7 @@ ENTRY(save_args) ret CFI_ENDPROC END(save_args) + .popsection ENTRY(save_rest) PARTIAL_FRAME 1 REST_SKIP+8 diff --git a/arch/x86/kernel/ftrace.c b/arch/x86/kernel/ftrace.c index 3afb33f14d2d..298448656b60 100644 --- a/arch/x86/kernel/ftrace.c +++ b/arch/x86/kernel/ftrace.c @@ -19,6 +19,7 @@ #include <linux/sched.h> #include <linux/init.h> #include <linux/list.h> +#include <linux/module.h> #include <trace/syscall.h> @@ -49,6 +50,7 @@ static DEFINE_PER_CPU(int, save_modifying_code); int ftrace_arch_code_modify_prepare(void) { set_kernel_text_rw(); + set_all_modules_text_rw(); modifying_code = 1; return 0; } @@ -56,6 +58,7 @@ int ftrace_arch_code_modify_prepare(void) int ftrace_arch_code_modify_post_process(void) { modifying_code = 0; + set_all_modules_text_ro(); set_kernel_text_ro(); return 0; } diff --git a/arch/x86/kernel/head_32.S b/arch/x86/kernel/head_32.S index bcece91dd311..9f54b209c378 100644 --- a/arch/x86/kernel/head_32.S +++ b/arch/x86/kernel/head_32.S @@ -60,16 +60,18 @@ #define PAGE_TABLE_SIZE(pages) ((pages) / PTRS_PER_PGD) #endif +/* Number of possible pages in the lowmem region */ +LOWMEM_PAGES = (((1<<32) - __PAGE_OFFSET) >> PAGE_SHIFT) + /* Enough space to fit pagetables for the low memory linear map */ -MAPPING_BEYOND_END = \ - PAGE_TABLE_SIZE(((1<<32) - __PAGE_OFFSET) >> PAGE_SHIFT) << PAGE_SHIFT +MAPPING_BEYOND_END = PAGE_TABLE_SIZE(LOWMEM_PAGES) << PAGE_SHIFT /* * Worst-case size of the kernel mapping we need to make: - * the worst-case size of the kernel itself, plus the extra we need - * to map for the linear map. + * a relocatable kernel can live anywhere in lowmem, so we need to be able + * to map all of lowmem. */ -KERNEL_PAGES = (KERNEL_IMAGE_SIZE + MAPPING_BEYOND_END)>>PAGE_SHIFT +KERNEL_PAGES = LOWMEM_PAGES INIT_MAP_SIZE = PAGE_TABLE_SIZE(KERNEL_PAGES) * PAGE_SIZE_asm RESERVE_BRK(pagetables, INIT_MAP_SIZE) @@ -137,39 +139,6 @@ ENTRY(startup_32) movl %eax, pa(olpc_ofw_pgd) #endif -#ifdef CONFIG_PARAVIRT - /* This is can only trip for a broken bootloader... */ - cmpw $0x207, pa(boot_params + BP_version) - jb default_entry - - /* Paravirt-compatible boot parameters. Look to see what architecture - we're booting under. */ - movl pa(boot_params + BP_hardware_subarch), %eax - cmpl $num_subarch_entries, %eax - jae bad_subarch - - movl pa(subarch_entries)(,%eax,4), %eax - subl $__PAGE_OFFSET, %eax - jmp *%eax - -bad_subarch: -WEAK(lguest_entry) -WEAK(xen_entry) - /* Unknown implementation; there's really - nothing we can do at this point. */ - ud2a - - __INITDATA - -subarch_entries: - .long default_entry /* normal x86/PC */ - .long lguest_entry /* lguest hypervisor */ - .long xen_entry /* Xen hypervisor */ - .long default_entry /* Moorestown MID */ -num_subarch_entries = (. - subarch_entries) / 4 -.previous -#endif /* CONFIG_PARAVIRT */ - /* * Initialize page tables. This creates a PDE and a set of page * tables, which are located immediately beyond __brk_base. The variable @@ -179,7 +148,6 @@ num_subarch_entries = (. - subarch_entries) / 4 * * Note that the stack is not yet set up! */ -default_entry: #ifdef CONFIG_X86_PAE /* @@ -259,7 +227,42 @@ page_pde_offset = (__PAGE_OFFSET >> 20); movl $pa(initial_pg_fixmap)+PDE_IDENT_ATTR,%eax movl %eax,pa(initial_page_table+0xffc) #endif - jmp 3f + +#ifdef CONFIG_PARAVIRT + /* This is can only trip for a broken bootloader... */ + cmpw $0x207, pa(boot_params + BP_version) + jb default_entry + + /* Paravirt-compatible boot parameters. Look to see what architecture + we're booting under. */ + movl pa(boot_params + BP_hardware_subarch), %eax + cmpl $num_subarch_entries, %eax + jae bad_subarch + + movl pa(subarch_entries)(,%eax,4), %eax + subl $__PAGE_OFFSET, %eax + jmp *%eax + +bad_subarch: +WEAK(lguest_entry) +WEAK(xen_entry) + /* Unknown implementation; there's really + nothing we can do at this point. */ + ud2a + + __INITDATA + +subarch_entries: + .long default_entry /* normal x86/PC */ + .long lguest_entry /* lguest hypervisor */ + .long xen_entry /* Xen hypervisor */ + .long default_entry /* Moorestown MID */ +num_subarch_entries = (. - subarch_entries) / 4 +.previous +#else + jmp default_entry +#endif /* CONFIG_PARAVIRT */ + /* * Non-boot CPU entry point; entered from trampoline.S * We can't lgdt here, because lgdt itself uses a data segment, but @@ -280,7 +283,7 @@ ENTRY(startup_32_smp) movl %eax,%fs movl %eax,%gs #endif /* CONFIG_SMP */ -3: +default_entry: /* * New page tables may be in 4Mbyte page mode and may @@ -314,6 +317,10 @@ ENTRY(startup_32_smp) subl $0x80000001, %eax cmpl $(0x8000ffff-0x80000001), %eax ja 6f + + /* Clear bogus XD_DISABLE bits */ + call verify_cpu + mov $0x80000001, %eax cpuid /* Execute Disable bit supported? */ @@ -609,6 +616,8 @@ ignore_int: #endif iret +#include "verify_cpu.S" + __REFDATA .align 4 ENTRY(initial_code) diff --git a/arch/x86/kernel/hpet.c b/arch/x86/kernel/hpet.c index ae03cab4352e..4ff5968f12d2 100644 --- a/arch/x86/kernel/hpet.c +++ b/arch/x86/kernel/hpet.c @@ -27,6 +27,9 @@ #define HPET_DEV_FSB_CAP 0x1000 #define HPET_DEV_PERI_CAP 0x2000 +#define HPET_MIN_CYCLES 128 +#define HPET_MIN_PROG_DELTA (HPET_MIN_CYCLES + (HPET_MIN_CYCLES >> 1)) + #define EVT_TO_HPET_DEV(evt) container_of(evt, struct hpet_dev, evt) /* @@ -299,8 +302,9 @@ static void hpet_legacy_clockevent_register(void) /* Calculate the min / max delta */ hpet_clockevent.max_delta_ns = clockevent_delta2ns(0x7FFFFFFF, &hpet_clockevent); - /* 5 usec minimum reprogramming delta. */ - hpet_clockevent.min_delta_ns = 5000; + /* Setup minimum reprogramming delta. */ + hpet_clockevent.min_delta_ns = clockevent_delta2ns(HPET_MIN_PROG_DELTA, + &hpet_clockevent); /* * Start hpet with the boot cpu mask and make it @@ -393,22 +397,24 @@ static int hpet_next_event(unsigned long delta, * the wraparound into account) nor a simple count down event * mode. Further the write to the comparator register is * delayed internally up to two HPET clock cycles in certain - * chipsets (ATI, ICH9,10). We worked around that by reading - * back the compare register, but that required another - * workaround for ICH9,10 chips where the first readout after - * write can return the old stale value. We already have a - * minimum delta of 5us enforced, but a NMI or SMI hitting + * chipsets (ATI, ICH9,10). Some newer AMD chipsets have even + * longer delays. We worked around that by reading back the + * compare register, but that required another workaround for + * ICH9,10 chips where the first readout after write can + * return the old stale value. We already had a minimum + * programming delta of 5us enforced, but a NMI or SMI hitting * between the counter readout and the comparator write can * move us behind that point easily. Now instead of reading * the compare register back several times, we make the ETIME * decision based on the following: Return ETIME if the - * counter value after the write is less than 8 HPET cycles + * counter value after the write is less than HPET_MIN_CYCLES * away from the event or if the counter is already ahead of - * the event. + * the event. The minimum programming delta for the generic + * clockevents code is set to 1.5 * HPET_MIN_CYCLES. */ res = (s32)(cnt - hpet_readl(HPET_COUNTER)); - return res < 8 ? -ETIME : 0; + return res < HPET_MIN_CYCLES ? -ETIME : 0; } static void hpet_legacy_set_mode(enum clock_event_mode mode, diff --git a/arch/x86/kernel/hw_breakpoint.c b/arch/x86/kernel/hw_breakpoint.c index ff15c9dcc25d..42c594254507 100644 --- a/arch/x86/kernel/hw_breakpoint.c +++ b/arch/x86/kernel/hw_breakpoint.c @@ -433,6 +433,10 @@ static int __kprobes hw_breakpoint_handler(struct die_args *args) dr6_p = (unsigned long *)ERR_PTR(args->err); dr6 = *dr6_p; + /* If it's a single step, TRAP bits are random */ + if (dr6 & DR_STEP) + return NOTIFY_DONE; + /* Do an early return if no trap bits are set in DR6 */ if ((dr6 & DR_TRAP_BITS) == 0) return NOTIFY_DONE; diff --git a/arch/x86/kernel/kgdb.c b/arch/x86/kernel/kgdb.c index ec592caac4b4..cd21b654dec6 100644 --- a/arch/x86/kernel/kgdb.c +++ b/arch/x86/kernel/kgdb.c @@ -315,14 +315,18 @@ static void kgdb_remove_all_hw_break(void) if (!breakinfo[i].enabled) continue; bp = *per_cpu_ptr(breakinfo[i].pev, cpu); - if (bp->attr.disabled == 1) + if (!bp->attr.disabled) { + arch_uninstall_hw_breakpoint(bp); + bp->attr.disabled = 1; continue; + } if (dbg_is_early) early_dr7 &= ~encode_dr7(i, breakinfo[i].len, breakinfo[i].type); - else - arch_uninstall_hw_breakpoint(bp); - bp->attr.disabled = 1; + else if (hw_break_release_slot(i)) + printk(KERN_ERR "KGDB: hw bpt remove failed %lx\n", + breakinfo[i].addr); + breakinfo[i].enabled = 0; } } diff --git a/arch/x86/kernel/kprobes.c b/arch/x86/kernel/kprobes.c index 1cbd54c0df99..5940282bd2f9 100644 --- a/arch/x86/kernel/kprobes.c +++ b/arch/x86/kernel/kprobes.c @@ -1184,6 +1184,10 @@ static void __kprobes optimized_callback(struct optimized_kprobe *op, { struct kprobe_ctlblk *kcb = get_kprobe_ctlblk(); + /* This is possible if op is under delayed unoptimizing */ + if (kprobe_disabled(&op->kp)) + return; + preempt_disable(); if (kprobe_running()) { kprobes_inc_nmissed_count(&op->kp); @@ -1401,10 +1405,16 @@ int __kprobes arch_prepare_optimized_kprobe(struct optimized_kprobe *op) return 0; } -/* Replace a breakpoint (int3) with a relative jump. */ -int __kprobes arch_optimize_kprobe(struct optimized_kprobe *op) +#define MAX_OPTIMIZE_PROBES 256 +static struct text_poke_param *jump_poke_params; +static struct jump_poke_buffer { + u8 buf[RELATIVEJUMP_SIZE]; +} *jump_poke_bufs; + +static void __kprobes setup_optimize_kprobe(struct text_poke_param *tprm, + u8 *insn_buf, + struct optimized_kprobe *op) { - unsigned char jmp_code[RELATIVEJUMP_SIZE]; s32 rel = (s32)((long)op->optinsn.insn - ((long)op->kp.addr + RELATIVEJUMP_SIZE)); @@ -1412,16 +1422,79 @@ int __kprobes arch_optimize_kprobe(struct optimized_kprobe *op) memcpy(op->optinsn.copied_insn, op->kp.addr + INT3_SIZE, RELATIVE_ADDR_SIZE); - jmp_code[0] = RELATIVEJUMP_OPCODE; - *(s32 *)(&jmp_code[1]) = rel; + insn_buf[0] = RELATIVEJUMP_OPCODE; + *(s32 *)(&insn_buf[1]) = rel; + + tprm->addr = op->kp.addr; + tprm->opcode = insn_buf; + tprm->len = RELATIVEJUMP_SIZE; +} + +/* + * Replace breakpoints (int3) with relative jumps. + * Caller must call with locking kprobe_mutex and text_mutex. + */ +void __kprobes arch_optimize_kprobes(struct list_head *oplist) +{ + struct optimized_kprobe *op, *tmp; + int c = 0; + + list_for_each_entry_safe(op, tmp, oplist, list) { + WARN_ON(kprobe_disabled(&op->kp)); + /* Setup param */ + setup_optimize_kprobe(&jump_poke_params[c], + jump_poke_bufs[c].buf, op); + list_del_init(&op->list); + if (++c >= MAX_OPTIMIZE_PROBES) + break; + } /* * text_poke_smp doesn't support NMI/MCE code modifying. * However, since kprobes itself also doesn't support NMI/MCE * code probing, it's not a problem. */ - text_poke_smp(op->kp.addr, jmp_code, RELATIVEJUMP_SIZE); - return 0; + text_poke_smp_batch(jump_poke_params, c); +} + +static void __kprobes setup_unoptimize_kprobe(struct text_poke_param *tprm, + u8 *insn_buf, + struct optimized_kprobe *op) +{ + /* Set int3 to first byte for kprobes */ + insn_buf[0] = BREAKPOINT_INSTRUCTION; + memcpy(insn_buf + 1, op->optinsn.copied_insn, RELATIVE_ADDR_SIZE); + + tprm->addr = op->kp.addr; + tprm->opcode = insn_buf; + tprm->len = RELATIVEJUMP_SIZE; +} + +/* + * Recover original instructions and breakpoints from relative jumps. + * Caller must call with locking kprobe_mutex. + */ +extern void arch_unoptimize_kprobes(struct list_head *oplist, + struct list_head *done_list) +{ + struct optimized_kprobe *op, *tmp; + int c = 0; + + list_for_each_entry_safe(op, tmp, oplist, list) { + /* Setup param */ + setup_unoptimize_kprobe(&jump_poke_params[c], + jump_poke_bufs[c].buf, op); + list_move(&op->list, done_list); + if (++c >= MAX_OPTIMIZE_PROBES) + break; + } + + /* + * text_poke_smp doesn't support NMI/MCE code modifying. + * However, since kprobes itself also doesn't support NMI/MCE + * code probing, it's not a problem. + */ + text_poke_smp_batch(jump_poke_params, c); } /* Replace a relative jump with a breakpoint (int3). */ @@ -1453,11 +1526,35 @@ static int __kprobes setup_detour_execution(struct kprobe *p, } return 0; } + +static int __kprobes init_poke_params(void) +{ + /* Allocate code buffer and parameter array */ + jump_poke_bufs = kmalloc(sizeof(struct jump_poke_buffer) * + MAX_OPTIMIZE_PROBES, GFP_KERNEL); + if (!jump_poke_bufs) + return -ENOMEM; + + jump_poke_params = kmalloc(sizeof(struct text_poke_param) * + MAX_OPTIMIZE_PROBES, GFP_KERNEL); + if (!jump_poke_params) { + kfree(jump_poke_bufs); + jump_poke_bufs = NULL; + return -ENOMEM; + } + + return 0; +} +#else /* !CONFIG_OPTPROBES */ +static int __kprobes init_poke_params(void) +{ + return 0; +} #endif int __init arch_init_kprobes(void) { - return 0; + return init_poke_params(); } int __kprobes arch_trampoline_kprobe(struct kprobe *p) diff --git a/arch/x86/kernel/microcode_amd.c b/arch/x86/kernel/microcode_amd.c index ce0cb4721c9a..0fe6d1a66c38 100644 --- a/arch/x86/kernel/microcode_amd.c +++ b/arch/x86/kernel/microcode_amd.c @@ -155,12 +155,6 @@ static int apply_microcode_amd(int cpu) return 0; } -static int get_ucode_data(void *to, const u8 *from, size_t n) -{ - memcpy(to, from, n); - return 0; -} - static void * get_next_ucode(const u8 *buf, unsigned int size, unsigned int *mc_size) { @@ -168,8 +162,7 @@ get_next_ucode(const u8 *buf, unsigned int size, unsigned int *mc_size) u8 section_hdr[UCODE_CONTAINER_SECTION_HDR]; void *mc; - if (get_ucode_data(section_hdr, buf, UCODE_CONTAINER_SECTION_HDR)) - return NULL; + get_ucode_data(section_hdr, buf, UCODE_CONTAINER_SECTION_HDR); if (section_hdr[0] != UCODE_UCODE_TYPE) { pr_err("error: invalid type field in container file section header\n"); @@ -183,16 +176,13 @@ get_next_ucode(const u8 *buf, unsigned int size, unsigned int *mc_size) return NULL; } - mc = vmalloc(UCODE_MAX_SIZE); - if (mc) { - memset(mc, 0, UCODE_MAX_SIZE); - if (get_ucode_data(mc, buf + UCODE_CONTAINER_SECTION_HDR, - total_size)) { - vfree(mc); - mc = NULL; - } else - *mc_size = total_size + UCODE_CONTAINER_SECTION_HDR; - } + mc = vzalloc(UCODE_MAX_SIZE); + if (!mc) + return NULL; + + get_ucode_data(mc, buf + UCODE_CONTAINER_SECTION_HDR, total_size); + *mc_size = total_size + UCODE_CONTAINER_SECTION_HDR; + return mc; } @@ -202,8 +192,7 @@ static int install_equiv_cpu_table(const u8 *buf) unsigned int *buf_pos = (unsigned int *)container_hdr; unsigned long size; - if (get_ucode_data(&container_hdr, buf, UCODE_CONTAINER_HEADER_SIZE)) - return 0; + get_ucode_data(&container_hdr, buf, UCODE_CONTAINER_HEADER_SIZE); size = buf_pos[2]; @@ -219,10 +208,7 @@ static int install_equiv_cpu_table(const u8 *buf) } buf += UCODE_CONTAINER_HEADER_SIZE; - if (get_ucode_data(equiv_cpu_table, buf, size)) { - vfree(equiv_cpu_table); - return 0; - } + get_ucode_data(equiv_cpu_table, buf, size); return size + UCODE_CONTAINER_HEADER_SIZE; /* add header length */ } diff --git a/arch/x86/kernel/microcode_intel.c b/arch/x86/kernel/microcode_intel.c index dcb65cc0a053..1a1b606d3e92 100644 --- a/arch/x86/kernel/microcode_intel.c +++ b/arch/x86/kernel/microcode_intel.c @@ -364,8 +364,7 @@ static enum ucode_state generic_load_microcode(int cpu, void *data, size_t size, /* For performance reasons, reuse mc area when possible */ if (!mc || mc_size > curr_mc_size) { - if (mc) - vfree(mc); + vfree(mc); mc = vmalloc(mc_size); if (!mc) break; @@ -374,13 +373,11 @@ static enum ucode_state generic_load_microcode(int cpu, void *data, size_t size, if (get_ucode_data(mc, ucode_ptr, mc_size) || microcode_sanity_check(mc) < 0) { - vfree(mc); break; } if (get_matching_microcode(&uci->cpu_sig, mc, new_rev)) { - if (new_mc) - vfree(new_mc); + vfree(new_mc); new_rev = mc_header.rev; new_mc = mc; mc = NULL; /* trigger new vmalloc */ @@ -390,12 +387,10 @@ static enum ucode_state generic_load_microcode(int cpu, void *data, size_t size, leftover -= mc_size; } - if (mc) - vfree(mc); + vfree(mc); if (leftover) { - if (new_mc) - vfree(new_mc); + vfree(new_mc); state = UCODE_ERROR; goto out; } @@ -405,8 +400,7 @@ static enum ucode_state generic_load_microcode(int cpu, void *data, size_t size, goto out; } - if (uci->mc) - vfree(uci->mc); + vfree(uci->mc); uci->mc = (struct microcode_intel *)new_mc; pr_debug("CPU%d found a matching microcode update with version 0x%x (current=0x%x)\n", diff --git a/arch/x86/kernel/mmconf-fam10h_64.c b/arch/x86/kernel/mmconf-fam10h_64.c index 6da143c2a6b8..ac861b8348e2 100644 --- a/arch/x86/kernel/mmconf-fam10h_64.c +++ b/arch/x86/kernel/mmconf-fam10h_64.c @@ -25,7 +25,6 @@ struct pci_hostbridge_probe { }; static u64 __cpuinitdata fam10h_pci_mmconf_base; -static int __cpuinitdata fam10h_pci_mmconf_base_status; static struct pci_hostbridge_probe pci_probes[] __cpuinitdata = { { 0, 0x18, PCI_VENDOR_ID_AMD, 0x1200 }, @@ -44,10 +43,12 @@ static int __cpuinit cmp_range(const void *x1, const void *x2) return start1 - start2; } -/*[47:0] */ -/* need to avoid (0xfd<<32) and (0xfe<<32), ht used space */ +#define MMCONF_UNIT (1ULL << FAM10H_MMIO_CONF_BASE_SHIFT) +#define MMCONF_MASK (~(MMCONF_UNIT - 1)) +#define MMCONF_SIZE (MMCONF_UNIT << 8) +/* need to avoid (0xfd<<32), (0xfe<<32), and (0xff<<32), ht used space */ #define FAM10H_PCI_MMCONF_BASE (0xfcULL<<32) -#define BASE_VALID(b) ((b != (0xfdULL << 32)) && (b != (0xfeULL << 32))) +#define BASE_VALID(b) ((b) + MMCONF_SIZE <= (0xfdULL<<32) || (b) >= (1ULL<<40)) static void __cpuinit get_fam10h_pci_mmconf_base(void) { int i; @@ -64,12 +65,11 @@ static void __cpuinit get_fam10h_pci_mmconf_base(void) struct range range[8]; /* only try to get setting from BSP */ - /* -1 or 1 */ - if (fam10h_pci_mmconf_base_status) + if (fam10h_pci_mmconf_base) return; if (!early_pci_allowed()) - goto fail; + return; found = 0; for (i = 0; i < ARRAY_SIZE(pci_probes); i++) { @@ -91,7 +91,7 @@ static void __cpuinit get_fam10h_pci_mmconf_base(void) } if (!found) - goto fail; + return; /* SYS_CFG */ address = MSR_K8_SYSCFG; @@ -99,16 +99,16 @@ static void __cpuinit get_fam10h_pci_mmconf_base(void) /* TOP_MEM2 is not enabled? */ if (!(val & (1<<21))) { - tom2 = 0; + tom2 = 1ULL << 32; } else { /* TOP_MEM2 */ address = MSR_K8_TOP_MEM2; rdmsrl(address, val); - tom2 = val & (0xffffULL<<32); + tom2 = max(val & 0xffffff800000ULL, 1ULL << 32); } if (base <= tom2) - base = tom2 + (1ULL<<32); + base = (tom2 + 2 * MMCONF_UNIT - 1) & MMCONF_MASK; /* * need to check if the range is in the high mmio range that is @@ -123,11 +123,11 @@ static void __cpuinit get_fam10h_pci_mmconf_base(void) if (!(reg & 3)) continue; - start = (((u64)reg) << 8) & (0xffULL << 32); /* 39:16 on 31:8*/ + start = (u64)(reg & 0xffffff00) << 8; /* 39:16 on 31:8*/ reg = read_pci_config(bus, slot, 1, 0x84 + (i << 3)); - end = (((u64)reg) << 8) & (0xffULL << 32); /* 39:16 on 31:8*/ + end = ((u64)(reg & 0xffffff00) << 8) | 0xffff; /* 39:16 on 31:8*/ - if (!end) + if (end < tom2) continue; range[hi_mmio_num].start = start; @@ -143,32 +143,27 @@ static void __cpuinit get_fam10h_pci_mmconf_base(void) if (range[hi_mmio_num - 1].end < base) goto out; - if (range[0].start > base) + if (range[0].start > base + MMCONF_SIZE) goto out; /* need to find one window */ - base = range[0].start - (1ULL << 32); + base = (range[0].start & MMCONF_MASK) - MMCONF_UNIT; if ((base > tom2) && BASE_VALID(base)) goto out; - base = range[hi_mmio_num - 1].end + (1ULL << 32); - if ((base > tom2) && BASE_VALID(base)) + base = (range[hi_mmio_num - 1].end + MMCONF_UNIT) & MMCONF_MASK; + if (BASE_VALID(base)) goto out; /* need to find window between ranges */ - if (hi_mmio_num > 1) - for (i = 0; i < hi_mmio_num - 1; i++) { - if (range[i + 1].start > (range[i].end + (1ULL << 32))) { - base = range[i].end + (1ULL << 32); - if ((base > tom2) && BASE_VALID(base)) - goto out; - } + for (i = 1; i < hi_mmio_num; i++) { + base = (range[i - 1].end + MMCONF_UNIT) & MMCONF_MASK; + val = range[i].start & MMCONF_MASK; + if (val >= base + MMCONF_SIZE && BASE_VALID(base)) + goto out; } - -fail: - fam10h_pci_mmconf_base_status = -1; return; + out: fam10h_pci_mmconf_base = base; - fam10h_pci_mmconf_base_status = 1; } void __cpuinit fam10h_check_enable_mmcfg(void) @@ -190,11 +185,10 @@ void __cpuinit fam10h_check_enable_mmcfg(void) /* only trust the one handle 256 buses, if acpi=off */ if (!acpi_pci_disabled || busnbits >= 8) { - u64 base; - base = val & (0xffffULL << 32); - if (fam10h_pci_mmconf_base_status <= 0) { + u64 base = val & MMCONF_MASK; + + if (!fam10h_pci_mmconf_base) { fam10h_pci_mmconf_base = base; - fam10h_pci_mmconf_base_status = 1; return; } else if (fam10h_pci_mmconf_base == base) return; @@ -206,8 +200,10 @@ void __cpuinit fam10h_check_enable_mmcfg(void) * with 256 buses */ get_fam10h_pci_mmconf_base(); - if (fam10h_pci_mmconf_base_status <= 0) + if (!fam10h_pci_mmconf_base) { + pci_probe &= ~PCI_CHECK_ENABLE_AMD_MMCONF; return; + } printk(KERN_INFO "Enable MMCONFIG on AMD Family 10h\n"); val &= ~((FAM10H_MMIO_CONF_BASE_MASK<<FAM10H_MMIO_CONF_BASE_SHIFT) | diff --git a/arch/x86/kernel/msr.c b/arch/x86/kernel/msr.c index 7bf2dc4c8f70..12fcbe2c143e 100644 --- a/arch/x86/kernel/msr.c +++ b/arch/x86/kernel/msr.c @@ -30,7 +30,6 @@ #include <linux/init.h> #include <linux/poll.h> #include <linux/smp.h> -#include <linux/smp_lock.h> #include <linux/major.h> #include <linux/fs.h> #include <linux/device.h> diff --git a/arch/x86/kernel/process.c b/arch/x86/kernel/process.c index 57d1868a86aa..c852041bfc3d 100644 --- a/arch/x86/kernel/process.c +++ b/arch/x86/kernel/process.c @@ -91,8 +91,7 @@ void exit_thread(void) void show_regs(struct pt_regs *regs) { show_registers(regs); - show_trace(NULL, regs, (unsigned long *)kernel_stack_pointer(regs), - regs->bp); + show_trace(NULL, regs, (unsigned long *)kernel_stack_pointer(regs)); } void show_regs_common(void) @@ -374,6 +373,7 @@ void default_idle(void) { if (hlt_use_halt()) { trace_power_start(POWER_CSTATE, 1, smp_processor_id()); + trace_cpu_idle(1, smp_processor_id()); current_thread_info()->status &= ~TS_POLLING; /* * TS_POLLING-cleared state must be visible before we @@ -444,6 +444,7 @@ EXPORT_SYMBOL_GPL(cpu_idle_wait); void mwait_idle_with_hints(unsigned long ax, unsigned long cx) { trace_power_start(POWER_CSTATE, (ax>>4)+1, smp_processor_id()); + trace_cpu_idle((ax>>4)+1, smp_processor_id()); if (!need_resched()) { if (cpu_has(¤t_cpu_data, X86_FEATURE_CLFLUSH_MONITOR)) clflush((void *)¤t_thread_info()->flags); @@ -460,6 +461,7 @@ static void mwait_idle(void) { if (!need_resched()) { trace_power_start(POWER_CSTATE, 1, smp_processor_id()); + trace_cpu_idle(1, smp_processor_id()); if (cpu_has(¤t_cpu_data, X86_FEATURE_CLFLUSH_MONITOR)) clflush((void *)¤t_thread_info()->flags); @@ -481,10 +483,12 @@ static void mwait_idle(void) static void poll_idle(void) { trace_power_start(POWER_CSTATE, 0, smp_processor_id()); + trace_cpu_idle(0, smp_processor_id()); local_irq_enable(); while (!need_resched()) cpu_relax(); - trace_power_end(0); + trace_power_end(smp_processor_id()); + trace_cpu_idle(PWR_EVENT_EXIT, smp_processor_id()); } /* diff --git a/arch/x86/kernel/process_32.c b/arch/x86/kernel/process_32.c index 96586c3cbbbf..4b9befa0e347 100644 --- a/arch/x86/kernel/process_32.c +++ b/arch/x86/kernel/process_32.c @@ -113,8 +113,8 @@ void cpu_idle(void) stop_critical_timings(); pm_idle(); start_critical_timings(); - trace_power_end(smp_processor_id()); + trace_cpu_idle(PWR_EVENT_EXIT, smp_processor_id()); } tick_nohz_restart_sched_tick(); preempt_enable_no_resched(); diff --git a/arch/x86/kernel/process_64.c b/arch/x86/kernel/process_64.c index b3d7a3a04f38..4c818a738396 100644 --- a/arch/x86/kernel/process_64.c +++ b/arch/x86/kernel/process_64.c @@ -142,6 +142,8 @@ void cpu_idle(void) start_critical_timings(); trace_power_end(smp_processor_id()); + trace_cpu_idle(PWR_EVENT_EXIT, + smp_processor_id()); /* In many cases the interrupt that ended idle has already called exit_idle. But some idle diff --git a/arch/x86/kernel/pvclock.c b/arch/x86/kernel/pvclock.c index 008b91eefa18..42eb3300dfc6 100644 --- a/arch/x86/kernel/pvclock.c +++ b/arch/x86/kernel/pvclock.c @@ -83,6 +83,11 @@ unsigned long pvclock_tsc_khz(struct pvclock_vcpu_time_info *src) static atomic64_t last_value = ATOMIC64_INIT(0); +void pvclock_resume(void) +{ + atomic64_set(&last_value, 0); +} + cycle_t pvclock_clocksource_read(struct pvclock_vcpu_time_info *src) { struct pvclock_shadow_time shadow; diff --git a/arch/x86/kernel/resource.c b/arch/x86/kernel/resource.c new file mode 100644 index 000000000000..2a26819bb6a8 --- /dev/null +++ b/arch/x86/kernel/resource.c @@ -0,0 +1,48 @@ +#include <linux/ioport.h> +#include <asm/e820.h> + +static void resource_clip(struct resource *res, resource_size_t start, + resource_size_t end) +{ + resource_size_t low = 0, high = 0; + + if (res->end < start || res->start > end) + return; /* no conflict */ + + if (res->start < start) + low = start - res->start; + + if (res->end > end) + high = res->end - end; + + /* Keep the area above or below the conflict, whichever is larger */ + if (low > high) + res->end = start - 1; + else + res->start = end + 1; +} + +static void remove_e820_regions(struct resource *avail) +{ + int i; + struct e820entry *entry; + + for (i = 0; i < e820.nr_map; i++) { + entry = &e820.map[i]; + + resource_clip(avail, entry->addr, + entry->addr + entry->size - 1); + } +} + +void arch_remove_reservations(struct resource *avail) +{ + /* Trim out BIOS areas (low 1MB and high 2MB) and E820 regions */ + if (avail->flags & IORESOURCE_MEM) { + if (avail->start < BIOS_END) + avail->start = BIOS_END; + resource_clip(avail, BIOS_ROM_BASE, BIOS_ROM_END); + + remove_e820_regions(avail); + } +} diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c index 0afb8c7e3803..d3cfe26c0252 100644 --- a/arch/x86/kernel/setup.c +++ b/arch/x86/kernel/setup.c @@ -501,7 +501,18 @@ static inline unsigned long long get_total_mem(void) return total << PAGE_SHIFT; } -#define DEFAULT_BZIMAGE_ADDR_MAX 0x37FFFFFF +/* + * Keep the crash kernel below this limit. On 32 bits earlier kernels + * would limit the kernel to the low 512 MiB due to mapping restrictions. + * On 64 bits, kexec-tools currently limits us to 896 MiB; increase this + * limit once kexec-tools are fixed. + */ +#ifdef CONFIG_X86_32 +# define CRASH_KERNEL_ADDR_MAX (512 << 20) +#else +# define CRASH_KERNEL_ADDR_MAX (896 << 20) +#endif + static void __init reserve_crashkernel(void) { unsigned long long total_mem; @@ -520,10 +531,10 @@ static void __init reserve_crashkernel(void) const unsigned long long alignment = 16<<20; /* 16M */ /* - * kexec want bzImage is below DEFAULT_BZIMAGE_ADDR_MAX + * kexec want bzImage is below CRASH_KERNEL_ADDR_MAX */ crash_base = memblock_find_in_range(alignment, - DEFAULT_BZIMAGE_ADDR_MAX, crash_size, alignment); + CRASH_KERNEL_ADDR_MAX, crash_size, alignment); if (crash_base == MEMBLOCK_ERROR) { pr_info("crashkernel reservation failed - No suitable area found.\n"); @@ -769,7 +780,6 @@ void __init setup_arch(char **cmdline_p) x86_init.oem.arch_setup(); - resource_alloc_from_bottom = 0; iomem_resource.end = (1ULL << boot_cpu_data.x86_phys_bits) - 1; setup_memory_map(); parse_setup_data(); diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c index 083e99d1b7df..ee886fe10ef4 100644 --- a/arch/x86/kernel/smpboot.c +++ b/arch/x86/kernel/smpboot.c @@ -281,6 +281,13 @@ static void __cpuinit smp_callin(void) */ smp_store_cpu_info(cpuid); + /* + * This must be done before setting cpu_online_mask + * or calling notify_cpu_starting. + */ + set_cpu_sibling_map(raw_smp_processor_id()); + wmb(); + notify_cpu_starting(cpuid); /* @@ -316,16 +323,6 @@ notrace static void __cpuinit start_secondary(void *unused) */ check_tsc_sync_target(); - if (nmi_watchdog == NMI_IO_APIC) { - legacy_pic->mask(0); - enable_NMI_through_LVT0(); - legacy_pic->unmask(0); - } - - /* This must be done before setting cpu_online_mask */ - set_cpu_sibling_map(raw_smp_processor_id()); - wmb(); - /* * We need to hold call_lock, so there is no inconsistency * between the time smp_call_function() determines number of @@ -1061,8 +1058,6 @@ static int __init smp_sanity_check(unsigned max_cpus) printk(KERN_INFO "SMP mode deactivated.\n"); smpboot_clear_io_apic(); - localise_nmi_watchdog(); - connect_bsp_APIC(); setup_local_APIC(); end_local_APIC_setup(); @@ -1166,6 +1161,20 @@ out: preempt_enable(); } +void arch_disable_nonboot_cpus_begin(void) +{ + /* + * Avoid the smp alternatives switch during the disable_nonboot_cpus(). + * In the suspend path, we will be back in the SMP mode shortly anyways. + */ + skip_smp_alternatives = true; +} + +void arch_disable_nonboot_cpus_end(void) +{ + skip_smp_alternatives = false; +} + void arch_enable_nonboot_cpus_begin(void) { set_mtrr_aps_delayed_init(); @@ -1196,7 +1205,6 @@ void __init native_smp_cpus_done(unsigned int max_cpus) #ifdef CONFIG_X86_IO_APIC setup_ioapic_dest(); #endif - check_nmi_watchdog(); mtrr_aps_init(); } @@ -1341,8 +1349,6 @@ int native_cpu_disable(void) if (cpu == 0) return -EBUSY; - if (nmi_watchdog == NMI_LOCAL_APIC) - stop_apic_nmi_watchdog(NULL); clear_local_APIC(); cpu_disable_common(); diff --git a/arch/x86/kernel/stacktrace.c b/arch/x86/kernel/stacktrace.c index b53c525368a7..938c8e10a19a 100644 --- a/arch/x86/kernel/stacktrace.c +++ b/arch/x86/kernel/stacktrace.c @@ -73,22 +73,22 @@ static const struct stacktrace_ops save_stack_ops_nosched = { */ void save_stack_trace(struct stack_trace *trace) { - dump_trace(current, NULL, NULL, 0, &save_stack_ops, trace); + dump_trace(current, NULL, NULL, &save_stack_ops, trace); if (trace->nr_entries < trace->max_entries) trace->entries[trace->nr_entries++] = ULONG_MAX; } EXPORT_SYMBOL_GPL(save_stack_trace); -void save_stack_trace_bp(struct stack_trace *trace, unsigned long bp) +void save_stack_trace_regs(struct stack_trace *trace, struct pt_regs *regs) { - dump_trace(current, NULL, NULL, bp, &save_stack_ops, trace); + dump_trace(current, regs, NULL, &save_stack_ops, trace); if (trace->nr_entries < trace->max_entries) trace->entries[trace->nr_entries++] = ULONG_MAX; } void save_stack_trace_tsk(struct task_struct *tsk, struct stack_trace *trace) { - dump_trace(tsk, NULL, NULL, 0, &save_stack_ops_nosched, trace); + dump_trace(tsk, NULL, NULL, &save_stack_ops_nosched, trace); if (trace->nr_entries < trace->max_entries) trace->entries[trace->nr_entries++] = ULONG_MAX; } diff --git a/arch/x86/kernel/time.c b/arch/x86/kernel/time.c index fb5cc5e14cfa..25a28a245937 100644 --- a/arch/x86/kernel/time.c +++ b/arch/x86/kernel/time.c @@ -22,10 +22,6 @@ #include <asm/hpet.h> #include <asm/time.h> -#if defined(CONFIG_X86_32) && defined(CONFIG_X86_IO_APIC) -int timer_ack; -#endif - #ifdef CONFIG_X86_64 volatile unsigned long __jiffies __section_jiffies = INITIAL_JIFFIES; #endif @@ -63,20 +59,6 @@ static irqreturn_t timer_interrupt(int irq, void *dev_id) /* Keep nmi watchdog up to date */ inc_irq_stat(irq0_irqs); - /* Optimized out for !IO_APIC and x86_64 */ - if (timer_ack) { - /* - * Subtle, when I/O APICs are used we have to ack timer IRQ - * manually to deassert NMI lines for the watchdog if run - * on an 82489DX-based system. - */ - raw_spin_lock(&i8259A_lock); - outb(0x0c, PIC_MASTER_OCW3); - /* Ack the IRQ; AEOI will end it automatically. */ - inb(PIC_MASTER_POLL); - raw_spin_unlock(&i8259A_lock); - } - global_clock_event->event_handler(global_clock_event); /* MCA bus quirk: Acknowledge irq0 by setting bit 7 in port 0x61 */ diff --git a/arch/x86/kernel/trampoline_64.S b/arch/x86/kernel/trampoline_64.S index 3af2dff58b21..075d130efcf9 100644 --- a/arch/x86/kernel/trampoline_64.S +++ b/arch/x86/kernel/trampoline_64.S @@ -127,7 +127,7 @@ startup_64: no_longmode: hlt jmp no_longmode -#include "verify_cpu_64.S" +#include "verify_cpu.S" # Careful these need to be in the same 64K segment as the above; tidt: diff --git a/arch/x86/kernel/traps.c b/arch/x86/kernel/traps.c index cb838ca42c96..c76aaca5694d 100644 --- a/arch/x86/kernel/traps.c +++ b/arch/x86/kernel/traps.c @@ -83,6 +83,8 @@ EXPORT_SYMBOL_GPL(used_vectors); static int ignore_nmis; +int unknown_nmi_panic; + static inline void conditional_sti(struct pt_regs *regs) { if (regs->flags & X86_EFLAGS_IF) @@ -300,6 +302,13 @@ gp_in_kernel: die("general protection fault", regs, error_code); } +static int __init setup_unknown_nmi_panic(char *str) +{ + unknown_nmi_panic = 1; + return 1; +} +__setup("unknown_nmi_panic", setup_unknown_nmi_panic); + static notrace __kprobes void mem_parity_error(unsigned char reason, struct pt_regs *regs) { @@ -342,9 +351,11 @@ io_check_error(unsigned char reason, struct pt_regs *regs) reason = (reason & 0xf) | 8; outb(reason, 0x61); - i = 2000; - while (--i) - udelay(1000); + i = 20000; + while (--i) { + touch_nmi_watchdog(); + udelay(100); + } reason &= ~8; outb(reason, 0x61); @@ -371,7 +382,7 @@ unknown_nmi_error(unsigned char reason, struct pt_regs *regs) reason, smp_processor_id()); printk(KERN_EMERG "Do you have a strange power saving mode enabled?\n"); - if (panic_on_unrecovered_nmi) + if (unknown_nmi_panic || panic_on_unrecovered_nmi) panic("NMI: Not continuing"); printk(KERN_EMERG "Dazed and confused, but trying to continue\n"); @@ -397,20 +408,8 @@ static notrace __kprobes void default_do_nmi(struct pt_regs *regs) if (notify_die(DIE_NMI, "nmi", regs, reason, 2, SIGINT) == NOTIFY_STOP) return; - -#ifndef CONFIG_LOCKUP_DETECTOR - /* - * 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)) -#endif /* !CONFIG_LOCKUP_DETECTOR */ - unknown_nmi_error(reason, regs); -#else - unknown_nmi_error(reason, regs); #endif + unknown_nmi_error(reason, regs); return; } @@ -446,14 +445,12 @@ do_nmi(struct pt_regs *regs, long error_code) void stop_nmi(void) { - acpi_nmi_disable(); ignore_nmis++; } void restart_nmi(void) { ignore_nmis--; - acpi_nmi_enable(); } /* May run on IST stack. */ diff --git a/arch/x86/kernel/tsc.c b/arch/x86/kernel/tsc.c index 0c40d8b72416..356a0d455cf9 100644 --- a/arch/x86/kernel/tsc.c +++ b/arch/x86/kernel/tsc.c @@ -872,6 +872,9 @@ __cpuinit int unsynchronized_tsc(void) if (boot_cpu_has(X86_FEATURE_CONSTANT_TSC)) return 0; + + if (tsc_clocksource_reliable) + return 0; /* * Intel systems are normally all synchronized. * Exceptions must mark TSC as unstable: @@ -879,14 +882,92 @@ __cpuinit int unsynchronized_tsc(void) if (boot_cpu_data.x86_vendor != X86_VENDOR_INTEL) { /* assume multi socket systems are not synchronized: */ if (num_possible_cpus() > 1) - tsc_unstable = 1; + return 1; } - return tsc_unstable; + return 0; +} + + +static void tsc_refine_calibration_work(struct work_struct *work); +static DECLARE_DELAYED_WORK(tsc_irqwork, tsc_refine_calibration_work); +/** + * tsc_refine_calibration_work - Further refine tsc freq calibration + * @work - ignored. + * + * This functions uses delayed work over a period of a + * second to further refine the TSC freq value. Since this is + * timer based, instead of loop based, we don't block the boot + * process while this longer calibration is done. + * + * If there are any calibration anomolies (too many SMIs, etc), + * or the refined calibration is off by 1% of the fast early + * calibration, we throw out the new calibration and use the + * early calibration. + */ +static void tsc_refine_calibration_work(struct work_struct *work) +{ + static u64 tsc_start = -1, ref_start; + static int hpet; + u64 tsc_stop, ref_stop, delta; + unsigned long freq; + + /* Don't bother refining TSC on unstable systems */ + if (check_tsc_unstable()) + goto out; + + /* + * Since the work is started early in boot, we may be + * delayed the first time we expire. So set the workqueue + * again once we know timers are working. + */ + if (tsc_start == -1) { + /* + * Only set hpet once, to avoid mixing hardware + * if the hpet becomes enabled later. + */ + hpet = is_hpet_enabled(); + schedule_delayed_work(&tsc_irqwork, HZ); + tsc_start = tsc_read_refs(&ref_start, hpet); + return; + } + + tsc_stop = tsc_read_refs(&ref_stop, hpet); + + /* hpet or pmtimer available ? */ + if (!hpet && !ref_start && !ref_stop) + goto out; + + /* Check, whether the sampling was disturbed by an SMI */ + if (tsc_start == ULLONG_MAX || tsc_stop == ULLONG_MAX) + goto out; + + delta = tsc_stop - tsc_start; + delta *= 1000000LL; + if (hpet) + freq = calc_hpet_ref(delta, ref_start, ref_stop); + else + freq = calc_pmtimer_ref(delta, ref_start, ref_stop); + + /* Make sure we're within 1% */ + if (abs(tsc_khz - freq) > tsc_khz/100) + goto out; + + tsc_khz = freq; + printk(KERN_INFO "Refined TSC clocksource calibration: " + "%lu.%03lu MHz.\n", (unsigned long)tsc_khz / 1000, + (unsigned long)tsc_khz % 1000); + +out: + clocksource_register_khz(&clocksource_tsc, tsc_khz); } -static void __init init_tsc_clocksource(void) + +static int __init init_tsc_clocksource(void) { + if (!cpu_has_tsc || tsc_disabled > 0) + return 0; + if (tsc_clocksource_reliable) clocksource_tsc.flags &= ~CLOCK_SOURCE_MUST_VERIFY; /* lower the rating if we already know its unstable: */ @@ -894,8 +975,14 @@ static void __init init_tsc_clocksource(void) clocksource_tsc.rating = 0; clocksource_tsc.flags &= ~CLOCK_SOURCE_IS_CONTINUOUS; } - clocksource_register_khz(&clocksource_tsc, tsc_khz); + schedule_delayed_work(&tsc_irqwork, 0); + return 0; } +/* + * We use device_initcall here, to ensure we run after the hpet + * is fully initialized, which may occur at fs_initcall time. + */ +device_initcall(init_tsc_clocksource); void __init tsc_init(void) { @@ -949,6 +1036,5 @@ void __init tsc_init(void) mark_tsc_unstable("TSCs unsynchronized"); check_system_tsc_reliable(); - init_tsc_clocksource(); } diff --git a/arch/x86/kernel/verify_cpu_64.S b/arch/x86/kernel/verify_cpu.S index 56a8c2a867d9..0edefc19a113 100644 --- a/arch/x86/kernel/verify_cpu_64.S +++ b/arch/x86/kernel/verify_cpu.S @@ -7,6 +7,7 @@ * Copyright (c) 2007 Andi Kleen (ak@suse.de) * Copyright (c) 2007 Eric Biederman (ebiederm@xmission.com) * Copyright (c) 2007 Vivek Goyal (vgoyal@in.ibm.com) + * Copyright (c) 2010 Kees Cook (kees.cook@canonical.com) * * This source code is licensed under the GNU General Public License, * Version 2. See the file COPYING for more details. @@ -14,18 +15,17 @@ * This is a common code for verification whether CPU supports * long mode and SSE or not. It is not called directly instead this * file is included at various places and compiled in that context. - * Following are the current usage. + * This file is expected to run in 32bit code. Currently: * - * This file is included by both 16bit and 32bit code. + * arch/x86/boot/compressed/head_64.S: Boot cpu verification + * arch/x86/kernel/trampoline_64.S: secondary processor verfication + * arch/x86/kernel/head_32.S: processor startup * - * arch/x86_64/boot/setup.S : Boot cpu verification (16bit) - * arch/x86_64/boot/compressed/head.S: Boot cpu verification (32bit) - * arch/x86_64/kernel/trampoline.S: secondary processor verfication (16bit) - * arch/x86_64/kernel/acpi/wakeup.S:Verfication at resume (16bit) - * - * verify_cpu, returns the status of cpu check in register %eax. + * verify_cpu, returns the status of longmode and SSE in register %eax. * 0: Success 1: Failure * + * On Intel, the XD_DISABLE flag will be cleared as a side-effect. + * * The caller needs to check for the error code and take the action * appropriately. Either display a message or halt. */ @@ -62,8 +62,41 @@ verify_cpu: cmpl $0x444d4163,%ecx jnz verify_cpu_noamd mov $1,%di # cpu is from AMD + jmp verify_cpu_check verify_cpu_noamd: + cmpl $0x756e6547,%ebx # GenuineIntel? + jnz verify_cpu_check + cmpl $0x49656e69,%edx + jnz verify_cpu_check + cmpl $0x6c65746e,%ecx + jnz verify_cpu_check + + # only call IA32_MISC_ENABLE when: + # family > 6 || (family == 6 && model >= 0xd) + movl $0x1, %eax # check CPU family and model + cpuid + movl %eax, %ecx + + andl $0x0ff00f00, %eax # mask family and extended family + shrl $8, %eax + cmpl $6, %eax + ja verify_cpu_clear_xd # family > 6, ok + jb verify_cpu_check # family < 6, skip + + andl $0x000f00f0, %ecx # mask model and extended model + shrl $4, %ecx + cmpl $0xd, %ecx + jb verify_cpu_check # family == 6, model < 0xd, skip + +verify_cpu_clear_xd: + movl $MSR_IA32_MISC_ENABLE, %ecx + rdmsr + btrl $2, %edx # clear MSR_IA32_MISC_ENABLE_XD_DISABLE + jnc verify_cpu_check # only write MSR if bit was changed + wrmsr + +verify_cpu_check: movl $0x1,%eax # Does the cpu have what it takes cpuid andl $REQUIRED_MASK0,%edx diff --git a/arch/x86/kernel/vmlinux.lds.S b/arch/x86/kernel/vmlinux.lds.S index e03530aebfd0..bf4700755184 100644 --- a/arch/x86/kernel/vmlinux.lds.S +++ b/arch/x86/kernel/vmlinux.lds.S @@ -69,7 +69,7 @@ jiffies_64 = jiffies; PHDRS { text PT_LOAD FLAGS(5); /* R_E */ - data PT_LOAD FLAGS(7); /* RWE */ + data PT_LOAD FLAGS(6); /* RW_ */ #ifdef CONFIG_X86_64 user PT_LOAD FLAGS(5); /* R_E */ #ifdef CONFIG_SMP @@ -116,6 +116,10 @@ SECTIONS EXCEPTION_TABLE(16) :text = 0x9090 +#if defined(CONFIG_DEBUG_RODATA) + /* .text should occupy whole number of pages */ + . = ALIGN(PAGE_SIZE); +#endif X64_ALIGN_DEBUG_RODATA_BEGIN RO_DATA(PAGE_SIZE) X64_ALIGN_DEBUG_RODATA_END @@ -335,7 +339,7 @@ SECTIONS __bss_start = .; *(.bss..page_aligned) *(.bss) - . = ALIGN(4); + . = ALIGN(PAGE_SIZE); __bss_stop = .; } diff --git a/arch/x86/kernel/xsave.c b/arch/x86/kernel/xsave.c index 9c253bd65e24..547128546cc3 100644 --- a/arch/x86/kernel/xsave.c +++ b/arch/x86/kernel/xsave.c @@ -394,7 +394,8 @@ static void __init setup_xstate_init(void) * Setup init_xstate_buf to represent the init state of * all the features managed by the xsave */ - init_xstate_buf = alloc_bootmem(xstate_size); + init_xstate_buf = alloc_bootmem_align(xstate_size, + __alignof__(struct xsave_struct)); init_xstate_buf->i387.mxcsr = MXCSR_DEFAULT; clts(); diff --git a/arch/x86/kvm/i8259.c b/arch/x86/kvm/i8259.c index f628234fbeca..3cece05e4ac4 100644 --- a/arch/x86/kvm/i8259.c +++ b/arch/x86/kvm/i8259.c @@ -575,6 +575,8 @@ struct kvm_pic *kvm_create_pic(struct kvm *kvm) s->pics[1].elcr_mask = 0xde; s->pics[0].pics_state = s; s->pics[1].pics_state = s; + s->pics[0].isr_ack = 0xff; + s->pics[1].isr_ack = 0xff; /* * Initialize PIO device diff --git a/arch/x86/kvm/mmu.c b/arch/x86/kvm/mmu.c index fb8b376bf28c..fbb04aee8301 100644 --- a/arch/x86/kvm/mmu.c +++ b/arch/x86/kvm/mmu.c @@ -2394,7 +2394,8 @@ static int mmu_alloc_direct_roots(struct kvm_vcpu *vcpu) ASSERT(!VALID_PAGE(root)); spin_lock(&vcpu->kvm->mmu_lock); kvm_mmu_free_some_pages(vcpu); - sp = kvm_mmu_get_page(vcpu, i << 30, i << 30, + sp = kvm_mmu_get_page(vcpu, i << (30 - PAGE_SHIFT), + i << 30, PT32_ROOT_LEVEL, 1, ACC_ALL, NULL); root = __pa(sp->spt); diff --git a/arch/x86/kvm/svm.c b/arch/x86/kvm/svm.c index 82e144a4e514..b81a9b7c2ca4 100644 --- a/arch/x86/kvm/svm.c +++ b/arch/x86/kvm/svm.c @@ -3395,6 +3395,7 @@ static void svm_vcpu_run(struct kvm_vcpu *vcpu) vcpu->arch.regs[VCPU_REGS_RIP] = svm->vmcb->save.rip; load_host_msrs(vcpu); + kvm_load_ldt(ldt_selector); loadsegment(fs, fs_selector); #ifdef CONFIG_X86_64 load_gs_index(gs_selector); @@ -3402,7 +3403,6 @@ static void svm_vcpu_run(struct kvm_vcpu *vcpu) #else loadsegment(gs, gs_selector); #endif - kvm_load_ldt(ldt_selector); reload_tss(vcpu); @@ -3494,6 +3494,10 @@ static void svm_cpuid_update(struct kvm_vcpu *vcpu) static void svm_set_supported_cpuid(u32 func, struct kvm_cpuid_entry2 *entry) { switch (func) { + case 0x00000001: + /* Mask out xsave bit as long as it is not supported by SVM */ + entry->ecx &= ~(bit(X86_FEATURE_XSAVE)); + break; case 0x80000001: if (nested) entry->ecx |= (1 << 2); /* Set SVM bit */ diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c index 8da0e45ff7c9..81fcbe9515c5 100644 --- a/arch/x86/kvm/vmx.c +++ b/arch/x86/kvm/vmx.c @@ -821,10 +821,9 @@ static void vmx_save_host_state(struct kvm_vcpu *vcpu) #endif #ifdef CONFIG_X86_64 - if (is_long_mode(&vmx->vcpu)) { - rdmsrl(MSR_KERNEL_GS_BASE, vmx->msr_host_kernel_gs_base); + rdmsrl(MSR_KERNEL_GS_BASE, vmx->msr_host_kernel_gs_base); + if (is_long_mode(&vmx->vcpu)) wrmsrl(MSR_KERNEL_GS_BASE, vmx->msr_guest_kernel_gs_base); - } #endif for (i = 0; i < vmx->save_nmsrs; ++i) kvm_set_shared_msr(vmx->guest_msrs[i].index, @@ -839,23 +838,23 @@ static void __vmx_load_host_state(struct vcpu_vmx *vmx) ++vmx->vcpu.stat.host_state_reload; vmx->host_state.loaded = 0; - if (vmx->host_state.fs_reload_needed) - loadsegment(fs, vmx->host_state.fs_sel); +#ifdef CONFIG_X86_64 + if (is_long_mode(&vmx->vcpu)) + rdmsrl(MSR_KERNEL_GS_BASE, vmx->msr_guest_kernel_gs_base); +#endif if (vmx->host_state.gs_ldt_reload_needed) { kvm_load_ldt(vmx->host_state.ldt_sel); #ifdef CONFIG_X86_64 load_gs_index(vmx->host_state.gs_sel); - wrmsrl(MSR_KERNEL_GS_BASE, current->thread.gs); #else loadsegment(gs, vmx->host_state.gs_sel); #endif } + if (vmx->host_state.fs_reload_needed) + loadsegment(fs, vmx->host_state.fs_sel); reload_tss(); #ifdef CONFIG_X86_64 - if (is_long_mode(&vmx->vcpu)) { - rdmsrl(MSR_KERNEL_GS_BASE, vmx->msr_guest_kernel_gs_base); - wrmsrl(MSR_KERNEL_GS_BASE, vmx->msr_host_kernel_gs_base); - } + wrmsrl(MSR_KERNEL_GS_BASE, vmx->msr_host_kernel_gs_base); #endif if (current_thread_info()->status & TS_USEDFPU) clts(); @@ -4228,11 +4227,6 @@ static int vmx_get_lpage_level(void) return PT_PDPE_LEVEL; } -static inline u32 bit(int bitno) -{ - return 1 << (bitno & 31); -} - static void vmx_cpuid_update(struct kvm_vcpu *vcpu) { struct kvm_cpuid_entry2 *best; diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index cdac9e592aa5..b989e1f1e5d3 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -155,11 +155,6 @@ struct kvm_stats_debugfs_item debugfs_entries[] = { u64 __read_mostly host_xcr0; -static inline u32 bit(int bitno) -{ - return 1 << (bitno & 31); -} - static void kvm_on_user_return(struct user_return_notifier *urn) { unsigned slot; @@ -4569,9 +4564,11 @@ static void kvm_timer_init(void) #ifdef CONFIG_CPU_FREQ struct cpufreq_policy policy; memset(&policy, 0, sizeof(policy)); - cpufreq_get_policy(&policy, get_cpu()); + cpu = get_cpu(); + cpufreq_get_policy(&policy, cpu); if (policy.cpuinfo.max_freq) max_tsc_khz = policy.cpuinfo.max_freq; + put_cpu(); #endif cpufreq_register_notifier(&kvmclock_cpufreq_notifier_block, CPUFREQ_TRANSITION_NOTIFIER); @@ -5522,6 +5519,8 @@ int kvm_arch_vcpu_ioctl_set_sregs(struct kvm_vcpu *vcpu, mmu_reset_needed |= kvm_read_cr4(vcpu) != sregs->cr4; kvm_x86_ops->set_cr4(vcpu, sregs->cr4); + if (sregs->cr4 & X86_CR4_OSXSAVE) + update_cpuid(vcpu); if (!is_long_mode(vcpu) && is_pae(vcpu)) { load_pdptrs(vcpu, vcpu->arch.walk_mmu, vcpu->arch.cr3); mmu_reset_needed = 1; diff --git a/arch/x86/kvm/x86.h b/arch/x86/kvm/x86.h index 2cea414489f3..c600da830ce0 100644 --- a/arch/x86/kvm/x86.h +++ b/arch/x86/kvm/x86.h @@ -70,6 +70,11 @@ static inline int is_paging(struct kvm_vcpu *vcpu) return kvm_read_cr0_bits(vcpu, X86_CR0_PG); } +static inline u32 bit(int bitno) +{ + return 1 << (bitno & 31); +} + void kvm_before_handle_nmi(struct kvm_vcpu *vcpu); void kvm_after_handle_nmi(struct kvm_vcpu *vcpu); int kvm_inject_realmode_interrupt(struct kvm_vcpu *vcpu, int irq); diff --git a/arch/x86/lguest/boot.c b/arch/x86/lguest/boot.c index 73b1e1a1f489..4996cf5f73a0 100644 --- a/arch/x86/lguest/boot.c +++ b/arch/x86/lguest/boot.c @@ -531,7 +531,10 @@ static void lguest_write_cr3(unsigned long cr3) { lguest_data.pgdir = cr3; lazy_hcall1(LHCALL_NEW_PGTABLE, cr3); - cr3_changed = true; + + /* These two page tables are simple, linear, and used during boot */ + if (cr3 != __pa(swapper_pg_dir) && cr3 != __pa(initial_page_table)) + cr3_changed = true; } static unsigned long lguest_read_cr3(void) @@ -703,9 +706,9 @@ static void lguest_set_pmd(pmd_t *pmdp, pmd_t pmdval) * to forget all of them. Fortunately, this is very rare. * * ... except in early boot when the kernel sets up the initial pagetables, - * which makes booting astonishingly slow: 1.83 seconds! So we don't even tell - * the Host anything changed until we've done the first page table switch, - * which brings boot back to 0.25 seconds. + * which makes booting astonishingly slow: 48 seconds! So we don't even tell + * the Host anything changed until we've done the first real page table switch, + * which brings boot back to 4.3 seconds. */ static void lguest_set_pte(pte_t *ptep, pte_t pteval) { @@ -1002,7 +1005,7 @@ static void lguest_time_init(void) clockevents_register_device(&lguest_clockevent); /* Finally, we unblock the timer interrupt. */ - enable_lguest_irq(0); + clear_bit(0, lguest_data.blocked_interrupts); } /* @@ -1349,9 +1352,6 @@ __init void lguest_init(void) */ switch_to_new_gdt(0); - /* We actually boot with all memory mapped, but let's say 128MB. */ - max_pfn_mapped = (128*1024*1024) >> PAGE_SHIFT; - /* * The Host<->Guest Switcher lives at the top of our address space, and * the Host told us how big it is when we made LGUEST_INIT hypercall: diff --git a/arch/x86/mm/init.c b/arch/x86/mm/init.c index c0e28a13de7d..947f42abe820 100644 --- a/arch/x86/mm/init.c +++ b/arch/x86/mm/init.c @@ -364,8 +364,9 @@ void free_init_pages(char *what, unsigned long begin, unsigned long end) /* * We just marked the kernel text read only above, now that * we are going to free part of that, we need to make that - * writeable first. + * writeable and non-executable first. */ + set_memory_nx(begin, (end - begin) >> PAGE_SHIFT); set_memory_rw(begin, (end - begin) >> PAGE_SHIFT); printk(KERN_INFO "Freeing %s: %luk freed\n", what, (end - begin) >> 10); diff --git a/arch/x86/mm/init_32.c b/arch/x86/mm/init_32.c index 0e969f9f401b..f89b5bb4e93f 100644 --- a/arch/x86/mm/init_32.c +++ b/arch/x86/mm/init_32.c @@ -226,7 +226,7 @@ page_table_range_init(unsigned long start, unsigned long end, pgd_t *pgd_base) static inline int is_kernel_text(unsigned long addr) { - if (addr >= PAGE_OFFSET && addr <= (unsigned long)__init_end) + if (addr >= (unsigned long)_text && addr <= (unsigned long)__init_end) return 1; return 0; } @@ -912,6 +912,23 @@ void set_kernel_text_ro(void) set_pages_ro(virt_to_page(start), size >> PAGE_SHIFT); } +static void mark_nxdata_nx(void) +{ + /* + * When this called, init has already been executed and released, + * so everything past _etext sould be NX. + */ + unsigned long start = PFN_ALIGN(_etext); + /* + * This comes from is_kernel_text upper limit. Also HPAGE where used: + */ + unsigned long size = (((unsigned long)__init_end + HPAGE_SIZE) & HPAGE_MASK) - start; + + if (__supported_pte_mask & _PAGE_NX) + printk(KERN_INFO "NX-protecting the kernel data: %luk\n", size >> 10); + set_pages_nx(virt_to_page(start), size >> PAGE_SHIFT); +} + void mark_rodata_ro(void) { unsigned long start = PFN_ALIGN(_text); @@ -946,6 +963,7 @@ void mark_rodata_ro(void) printk(KERN_INFO "Testing CPA: write protecting again\n"); set_pages_ro(virt_to_page(start), size >> PAGE_SHIFT); #endif + mark_nxdata_nx(); } #endif diff --git a/arch/x86/mm/kmemcheck/error.c b/arch/x86/mm/kmemcheck/error.c index af3b6c8a436f..704a37cedddb 100644 --- a/arch/x86/mm/kmemcheck/error.c +++ b/arch/x86/mm/kmemcheck/error.c @@ -185,7 +185,7 @@ void kmemcheck_error_save(enum kmemcheck_shadow state, e->trace.entries = e->trace_entries; e->trace.max_entries = ARRAY_SIZE(e->trace_entries); e->trace.skip = 0; - save_stack_trace_bp(&e->trace, regs->bp); + save_stack_trace_regs(&e->trace, regs); /* Round address down to nearest 16 bytes */ shadow_copy = kmemcheck_shadow_lookup(address diff --git a/arch/x86/mm/pageattr.c b/arch/x86/mm/pageattr.c index 532e7933d606..8b830ca14ac4 100644 --- a/arch/x86/mm/pageattr.c +++ b/arch/x86/mm/pageattr.c @@ -13,6 +13,7 @@ #include <linux/pfn.h> #include <linux/percpu.h> #include <linux/gfp.h> +#include <linux/pci.h> #include <asm/e820.h> #include <asm/processor.h> @@ -255,13 +256,16 @@ static inline pgprot_t static_protections(pgprot_t prot, unsigned long address, unsigned long pfn) { pgprot_t forbidden = __pgprot(0); + pgprot_t required = __pgprot(0); /* * The BIOS area between 640k and 1Mb needs to be executable for * PCI BIOS based config access (CONFIG_PCI_GOBIOS) support. */ - if (within(pfn, BIOS_BEGIN >> PAGE_SHIFT, BIOS_END >> PAGE_SHIFT)) +#ifdef CONFIG_PCI_BIOS + if (pcibios_enabled && within(pfn, BIOS_BEGIN >> PAGE_SHIFT, BIOS_END >> PAGE_SHIFT)) pgprot_val(forbidden) |= _PAGE_NX; +#endif /* * The kernel text needs to be executable for obvious reasons @@ -278,6 +282,12 @@ static inline pgprot_t static_protections(pgprot_t prot, unsigned long address, if (within(pfn, __pa((unsigned long)__start_rodata) >> PAGE_SHIFT, __pa((unsigned long)__end_rodata) >> PAGE_SHIFT)) pgprot_val(forbidden) |= _PAGE_RW; + /* + * .data and .bss should always be writable. + */ + if (within(address, (unsigned long)_sdata, (unsigned long)_edata) || + within(address, (unsigned long)__bss_start, (unsigned long)__bss_stop)) + pgprot_val(required) |= _PAGE_RW; #if defined(CONFIG_X86_64) && defined(CONFIG_DEBUG_RODATA) /* @@ -317,6 +327,7 @@ static inline pgprot_t static_protections(pgprot_t prot, unsigned long address, #endif prot = __pgprot(pgprot_val(prot) & ~pgprot_val(forbidden)); + prot = __pgprot(pgprot_val(prot) | pgprot_val(required)); return prot; } @@ -393,7 +404,7 @@ try_preserve_large_page(pte_t *kpte, unsigned long address, { unsigned long nextpage_addr, numpages, pmask, psize, flags, addr, pfn; pte_t new_pte, old_pte, *tmp; - pgprot_t old_prot, new_prot; + pgprot_t old_prot, new_prot, req_prot; int i, do_split = 1; unsigned int level; @@ -438,10 +449,10 @@ try_preserve_large_page(pte_t *kpte, unsigned long address, * We are safe now. Check whether the new pgprot is the same: */ old_pte = *kpte; - old_prot = new_prot = pte_pgprot(old_pte); + old_prot = new_prot = req_prot = pte_pgprot(old_pte); - pgprot_val(new_prot) &= ~pgprot_val(cpa->mask_clr); - pgprot_val(new_prot) |= pgprot_val(cpa->mask_set); + pgprot_val(req_prot) &= ~pgprot_val(cpa->mask_clr); + pgprot_val(req_prot) |= pgprot_val(cpa->mask_set); /* * old_pte points to the large page base address. So we need @@ -450,17 +461,17 @@ try_preserve_large_page(pte_t *kpte, unsigned long address, pfn = pte_pfn(old_pte) + ((address & (psize - 1)) >> PAGE_SHIFT); cpa->pfn = pfn; - new_prot = static_protections(new_prot, address, pfn); + new_prot = static_protections(req_prot, address, pfn); /* * We need to check the full range, whether * static_protection() requires a different pgprot for one of * the pages in the range we try to preserve: */ - addr = address + PAGE_SIZE; - pfn++; - for (i = 1; i < cpa->numpages; i++, addr += PAGE_SIZE, pfn++) { - pgprot_t chk_prot = static_protections(new_prot, addr, pfn); + addr = address & pmask; + pfn = pte_pfn(old_pte); + for (i = 0; i < (psize >> PAGE_SHIFT); i++, addr += PAGE_SIZE, pfn++) { + pgprot_t chk_prot = static_protections(req_prot, addr, pfn); if (pgprot_val(chk_prot) != pgprot_val(new_prot)) goto out_unlock; @@ -483,7 +494,7 @@ try_preserve_large_page(pte_t *kpte, unsigned long address, * that we limited the number of possible pages already to * the number of pages in the large page. */ - if (address == (nextpage_addr - psize) && cpa->numpages == numpages) { + if (address == (address & pmask) && cpa->numpages == (psize >> PAGE_SHIFT)) { /* * The address is aligned and the number of pages * covers the full page. diff --git a/arch/x86/mm/setup_nx.c b/arch/x86/mm/setup_nx.c index a3250aa34086..410531d3c292 100644 --- a/arch/x86/mm/setup_nx.c +++ b/arch/x86/mm/setup_nx.c @@ -41,7 +41,7 @@ void __init x86_report_nx(void) { if (!cpu_has_nx) { printk(KERN_NOTICE "Notice: NX (Execute Disable) protection " - "missing in CPU or disabled in BIOS!\n"); + "missing in CPU!\n"); } else { #if defined(CONFIG_X86_64) || defined(CONFIG_X86_PAE) if (disable_nx) { diff --git a/arch/x86/mm/srat_32.c b/arch/x86/mm/srat_32.c index a17dffd136c1..f16434568a51 100644 --- a/arch/x86/mm/srat_32.c +++ b/arch/x86/mm/srat_32.c @@ -92,6 +92,7 @@ acpi_numa_processor_affinity_init(struct acpi_srat_cpu_affinity *cpu_affinity) /* mark this node as "seen" in node bitmap */ BMAP_SET(pxm_bitmap, cpu_affinity->proximity_domain_lo); + /* don't need to check apic_id here, because it is always 8 bits */ apicid_to_pxm[cpu_affinity->apic_id] = cpu_affinity->proximity_domain_lo; printk(KERN_DEBUG "CPU %02x in proximity domain %02x\n", diff --git a/arch/x86/mm/srat_64.c b/arch/x86/mm/srat_64.c index a35cb9d8b060..171a0aacb99a 100644 --- a/arch/x86/mm/srat_64.c +++ b/arch/x86/mm/srat_64.c @@ -134,6 +134,10 @@ acpi_numa_x2apic_affinity_init(struct acpi_srat_x2apic_cpu_affinity *pa) } apic_id = pa->apic_id; + if (apic_id >= MAX_LOCAL_APIC) { + printk(KERN_INFO "SRAT: PXM %u -> APIC 0x%04x -> Node %u skipped apicid that is too big\n", pxm, apic_id, node); + return; + } apicid_to_node[apic_id] = node; node_set(node, cpu_nodes_parsed); acpi_numa = 1; @@ -168,6 +172,12 @@ acpi_numa_processor_affinity_init(struct acpi_srat_cpu_affinity *pa) apic_id = (pa->apic_id << 8) | pa->local_sapic_eid; else apic_id = pa->apic_id; + + if (apic_id >= MAX_LOCAL_APIC) { + printk(KERN_INFO "SRAT: PXM %u -> APIC 0x%02x -> Node %u skipped apicid that is too big\n", pxm, apic_id, node); + return; + } + apicid_to_node[apic_id] = node; node_set(node, cpu_nodes_parsed); acpi_numa = 1; diff --git a/arch/x86/mm/tlb.c b/arch/x86/mm/tlb.c index 12cdbb17ad18..6acc724d5d8f 100644 --- a/arch/x86/mm/tlb.c +++ b/arch/x86/mm/tlb.c @@ -223,7 +223,7 @@ void native_flush_tlb_others(const struct cpumask *cpumask, static void __cpuinit calculate_tlb_offset(void) { - int cpu, node, nr_node_vecs; + int cpu, node, nr_node_vecs, idx = 0; /* * we are changing tlb_vector_offset for each CPU in runtime, but this * will not cause inconsistency, as the write is atomic under X86. we @@ -239,7 +239,7 @@ static void __cpuinit calculate_tlb_offset(void) nr_node_vecs = NUM_INVALIDATE_TLB_VECTORS/nr_online_nodes; for_each_online_node(node) { - int node_offset = (node % NUM_INVALIDATE_TLB_VECTORS) * + int node_offset = (idx % NUM_INVALIDATE_TLB_VECTORS) * nr_node_vecs; int cpu_offset = 0; for_each_cpu(cpu, cpumask_of_node(node)) { @@ -248,6 +248,7 @@ static void __cpuinit calculate_tlb_offset(void) cpu_offset++; cpu_offset = cpu_offset % nr_node_vecs; } + idx++; } } diff --git a/arch/x86/oprofile/backtrace.c b/arch/x86/oprofile/backtrace.c index 2d49d4e19a36..72cbec14d783 100644 --- a/arch/x86/oprofile/backtrace.c +++ b/arch/x86/oprofile/backtrace.c @@ -126,7 +126,7 @@ x86_backtrace(struct pt_regs * const regs, unsigned int depth) if (!user_mode_vm(regs)) { unsigned long stack = kernel_stack_pointer(regs); if (depth) - dump_trace(NULL, regs, (unsigned long *)stack, 0, + dump_trace(NULL, regs, (unsigned long *)stack, &backtrace_ops, &depth); return; } diff --git a/arch/x86/oprofile/nmi_int.c b/arch/x86/oprofile/nmi_int.c index 4e8baad36d37..358c8b9c96a7 100644 --- a/arch/x86/oprofile/nmi_int.c +++ b/arch/x86/oprofile/nmi_int.c @@ -732,6 +732,9 @@ int __init op_nmi_init(struct oprofile_operations *ops) case 0x14: cpu_type = "x86-64/family14h"; break; + case 0x15: + cpu_type = "x86-64/family15h"; + break; default: return -ENODEV; } diff --git a/arch/x86/oprofile/nmi_timer_int.c b/arch/x86/oprofile/nmi_timer_int.c index e3ecb71b5790..0636dd93cef8 100644 --- a/arch/x86/oprofile/nmi_timer_int.c +++ b/arch/x86/oprofile/nmi_timer_int.c @@ -58,9 +58,6 @@ static void timer_stop(void) int __init op_nmi_timer_init(struct oprofile_operations *ops) { - if ((nmi_watchdog != NMI_IO_APIC) || (atomic_read(&nmi_active) <= 0)) - return -ENODEV; - ops->start = timer_start; ops->stop = timer_stop; ops->cpu_type = "timer"; diff --git a/arch/x86/oprofile/op_model_amd.c b/arch/x86/oprofile/op_model_amd.c index a011bcc0f943..c3b8e24f2b16 100644 --- a/arch/x86/oprofile/op_model_amd.c +++ b/arch/x86/oprofile/op_model_amd.c @@ -29,11 +29,12 @@ #include "op_x86_model.h" #include "op_counter.h" -#define NUM_COUNTERS 4 +#define NUM_COUNTERS 4 +#define NUM_COUNTERS_F15H 6 #ifdef CONFIG_OPROFILE_EVENT_MULTIPLEX -#define NUM_VIRT_COUNTERS 32 +#define NUM_VIRT_COUNTERS 32 #else -#define NUM_VIRT_COUNTERS NUM_COUNTERS +#define NUM_VIRT_COUNTERS 0 #endif #define OP_EVENT_MASK 0x0FFF @@ -41,7 +42,8 @@ #define MSR_AMD_EVENTSEL_RESERVED ((0xFFFFFCF0ULL<<32)|(1ULL<<21)) -static unsigned long reset_value[NUM_VIRT_COUNTERS]; +static int num_counters; +static unsigned long reset_value[OP_MAX_COUNTER]; #define IBS_FETCH_SIZE 6 #define IBS_OP_SIZE 12 @@ -387,7 +389,7 @@ static void op_mux_switch_ctrl(struct op_x86_model_spec const *model, int i; /* enable active counters */ - for (i = 0; i < NUM_COUNTERS; ++i) { + for (i = 0; i < num_counters; ++i) { int virt = op_x86_phys_to_virt(i); if (!reset_value[virt]) continue; @@ -406,7 +408,7 @@ static void op_amd_shutdown(struct op_msrs const * const msrs) { int i; - for (i = 0; i < NUM_COUNTERS; ++i) { + for (i = 0; i < num_counters; ++i) { if (!msrs->counters[i].addr) continue; release_perfctr_nmi(MSR_K7_PERFCTR0 + i); @@ -418,7 +420,7 @@ static int op_amd_fill_in_addresses(struct op_msrs * const msrs) { int i; - for (i = 0; i < NUM_COUNTERS; i++) { + for (i = 0; i < num_counters; i++) { if (!reserve_perfctr_nmi(MSR_K7_PERFCTR0 + i)) goto fail; if (!reserve_evntsel_nmi(MSR_K7_EVNTSEL0 + i)) { @@ -426,8 +428,13 @@ static int op_amd_fill_in_addresses(struct op_msrs * const msrs) goto fail; } /* both registers must be reserved */ - msrs->counters[i].addr = MSR_K7_PERFCTR0 + i; - msrs->controls[i].addr = MSR_K7_EVNTSEL0 + i; + if (num_counters == NUM_COUNTERS_F15H) { + msrs->counters[i].addr = MSR_F15H_PERF_CTR + (i << 1); + msrs->controls[i].addr = MSR_F15H_PERF_CTL + (i << 1); + } else { + msrs->controls[i].addr = MSR_K7_EVNTSEL0 + i; + msrs->counters[i].addr = MSR_K7_PERFCTR0 + i; + } continue; fail: if (!counter_config[i].enabled) @@ -447,7 +454,7 @@ static void op_amd_setup_ctrs(struct op_x86_model_spec const *model, int i; /* setup reset_value */ - for (i = 0; i < NUM_VIRT_COUNTERS; ++i) { + for (i = 0; i < OP_MAX_COUNTER; ++i) { if (counter_config[i].enabled && msrs->counters[op_x86_virt_to_phys(i)].addr) reset_value[i] = counter_config[i].count; @@ -456,7 +463,7 @@ static void op_amd_setup_ctrs(struct op_x86_model_spec const *model, } /* clear all counters */ - for (i = 0; i < NUM_COUNTERS; ++i) { + for (i = 0; i < num_counters; ++i) { if (!msrs->controls[i].addr) continue; rdmsrl(msrs->controls[i].addr, val); @@ -472,7 +479,7 @@ static void op_amd_setup_ctrs(struct op_x86_model_spec const *model, } /* enable active counters */ - for (i = 0; i < NUM_COUNTERS; ++i) { + for (i = 0; i < num_counters; ++i) { int virt = op_x86_phys_to_virt(i); if (!reset_value[virt]) continue; @@ -503,7 +510,7 @@ static int op_amd_check_ctrs(struct pt_regs * const regs, u64 val; int i; - for (i = 0; i < NUM_COUNTERS; ++i) { + for (i = 0; i < num_counters; ++i) { int virt = op_x86_phys_to_virt(i); if (!reset_value[virt]) continue; @@ -526,7 +533,7 @@ static void op_amd_start(struct op_msrs const * const msrs) u64 val; int i; - for (i = 0; i < NUM_COUNTERS; ++i) { + for (i = 0; i < num_counters; ++i) { if (!reset_value[op_x86_phys_to_virt(i)]) continue; rdmsrl(msrs->controls[i].addr, val); @@ -546,7 +553,7 @@ static void op_amd_stop(struct op_msrs const * const msrs) * Subtle: stop on all counters to avoid race with setting our * pm callback */ - for (i = 0; i < NUM_COUNTERS; ++i) { + for (i = 0; i < num_counters; ++i) { if (!reset_value[op_x86_phys_to_virt(i)]) continue; rdmsrl(msrs->controls[i].addr, val); @@ -603,6 +610,7 @@ static int force_ibs_eilvt_setup(void) ret = setup_ibs_ctl(i); if (ret) return ret; + pr_err(FW_BUG "using offset %d for IBS interrupts\n", i); return 0; } @@ -630,21 +638,29 @@ static int __init_ibs_nmi(void) return 0; } -/* initialize the APIC for the IBS interrupts if available */ +/* + * check and reserve APIC extended interrupt LVT offset for IBS if + * available + * + * init_ibs() preforms implicitly cpu-local operations, so pin this + * thread to its current CPU + */ + static void init_ibs(void) { - ibs_caps = get_ibs_caps(); + preempt_disable(); + ibs_caps = get_ibs_caps(); if (!ibs_caps) - return; + goto out; - if (__init_ibs_nmi()) { + if (__init_ibs_nmi() < 0) ibs_caps = 0; - return; - } + else + printk(KERN_INFO "oprofile: AMD IBS detected (0x%08x)\n", ibs_caps); - printk(KERN_INFO "oprofile: AMD IBS detected (0x%08x)\n", - (unsigned)ibs_caps); +out: + preempt_enable(); } static int (*create_arch_files)(struct super_block *sb, struct dentry *root); @@ -698,18 +714,29 @@ static int setup_ibs_files(struct super_block *sb, struct dentry *root) return 0; } +struct op_x86_model_spec op_amd_spec; + static int op_amd_init(struct oprofile_operations *ops) { init_ibs(); create_arch_files = ops->create_files; ops->create_files = setup_ibs_files; + + if (boot_cpu_data.x86 == 0x15) { + num_counters = NUM_COUNTERS_F15H; + } else { + num_counters = NUM_COUNTERS; + } + + op_amd_spec.num_counters = num_counters; + op_amd_spec.num_controls = num_counters; + op_amd_spec.num_virt_counters = max(num_counters, NUM_VIRT_COUNTERS); + return 0; } struct op_x86_model_spec op_amd_spec = { - .num_counters = NUM_COUNTERS, - .num_controls = NUM_COUNTERS, - .num_virt_counters = NUM_VIRT_COUNTERS, + /* num_counters/num_controls filled in at runtime */ .reserved = MSR_AMD_EVENTSEL_RESERVED, .event_mask = OP_EVENT_MASK, .init = op_amd_init, diff --git a/arch/x86/oprofile/op_model_p4.c b/arch/x86/oprofile/op_model_p4.c index 182558dd5515..9fadec074142 100644 --- a/arch/x86/oprofile/op_model_p4.c +++ b/arch/x86/oprofile/op_model_p4.c @@ -11,7 +11,7 @@ #include <linux/oprofile.h> #include <linux/smp.h> #include <linux/ptrace.h> -#include <linux/nmi.h> +#include <asm/nmi.h> #include <asm/msr.h> #include <asm/fixmap.h> #include <asm/apic.h> diff --git a/arch/x86/pci/i386.c b/arch/x86/pci/i386.c index c4bb261c106e..b1805b78842f 100644 --- a/arch/x86/pci/i386.c +++ b/arch/x86/pci/i386.c @@ -65,21 +65,13 @@ pcibios_align_resource(void *data, const struct resource *res, resource_size_t size, resource_size_t align) { struct pci_dev *dev = data; - resource_size_t start = round_down(res->end - size + 1, align); + resource_size_t start = res->start; if (res->flags & IORESOURCE_IO) { - - /* - * If we're avoiding ISA aliases, the largest contiguous I/O - * port space is 256 bytes. Clearing bits 9 and 10 preserves - * all 256-byte and smaller alignments, so the result will - * still be correctly aligned. - */ - if (!skip_isa_ioresource_align(dev)) - start &= ~0x300; - } else if (res->flags & IORESOURCE_MEM) { - if (start < BIOS_END) - start = res->end; /* fail; no space */ + if (skip_isa_ioresource_align(dev)) + return start; + if (start & 0x300) + start = (start + 0x3ff) & ~0x3ff; } return start; } diff --git a/arch/x86/pci/pcbios.c b/arch/x86/pci/pcbios.c index 2492d165096a..a5f7d0d63de0 100644 --- a/arch/x86/pci/pcbios.c +++ b/arch/x86/pci/pcbios.c @@ -9,6 +9,7 @@ #include <linux/uaccess.h> #include <asm/pci_x86.h> #include <asm/pci-functions.h> +#include <asm/cacheflush.h> /* BIOS32 signature: "_32_" */ #define BIOS32_SIGNATURE (('_' << 0) + ('3' << 8) + ('2' << 16) + ('_' << 24)) @@ -25,6 +26,27 @@ #define PCIBIOS_HW_TYPE1_SPEC 0x10 #define PCIBIOS_HW_TYPE2_SPEC 0x20 +int pcibios_enabled; + +/* According to the BIOS specification at: + * http://members.datafast.net.au/dft0802/specs/bios21.pdf, we could + * restrict the x zone to some pages and make it ro. But this may be + * broken on some bios, complex to handle with static_protections. + * We could make the 0xe0000-0x100000 range rox, but this can break + * some ISA mapping. + * + * So we let's an rw and x hole when pcibios is used. This shouldn't + * happen for modern system with mmconfig, and if you don't want it + * you could disable pcibios... + */ +static inline void set_bios_x(void) +{ + pcibios_enabled = 1; + set_memory_x(PAGE_OFFSET + BIOS_BEGIN, (BIOS_END - BIOS_BEGIN) >> PAGE_SHIFT); + if (__supported_pte_mask & _PAGE_NX) + printk(KERN_INFO "PCI : PCI BIOS aera is rw and x. Use pci=nobios if you want it NX.\n"); +} + /* * This is the standard structure used to identify the entry point * to the BIOS32 Service Directory, as documented in @@ -332,6 +354,7 @@ static struct pci_raw_ops * __devinit pci_find_bios(void) DBG("PCI: BIOS32 Service Directory entry at 0x%lx\n", bios32_entry); bios32_indirect.address = bios32_entry + PAGE_OFFSET; + set_bios_x(); if (check_pcibios()) return &pci_bios_access; } diff --git a/arch/x86/pci/xen.c b/arch/x86/pci/xen.c index d7b5109f7a9c..25cd4a07d09f 100644 --- a/arch/x86/pci/xen.c +++ b/arch/x86/pci/xen.c @@ -70,6 +70,9 @@ static int acpi_register_gsi_xen_hvm(struct device *dev, u32 gsi, struct xen_pci_frontend_ops *xen_pci_frontend; EXPORT_SYMBOL_GPL(xen_pci_frontend); +#define XEN_PIRQ_MSI_DATA (MSI_DATA_TRIGGER_EDGE | \ + MSI_DATA_LEVEL_ASSERT | (3 << 8) | MSI_DATA_VECTOR(0)) + static void xen_msi_compose_msg(struct pci_dev *pdev, unsigned int pirq, struct msi_msg *msg) { @@ -83,12 +86,7 @@ static void xen_msi_compose_msg(struct pci_dev *pdev, unsigned int pirq, MSI_ADDR_REDIRECTION_CPU | MSI_ADDR_DEST_ID(pirq); - msg->data = - MSI_DATA_TRIGGER_EDGE | - MSI_DATA_LEVEL_ASSERT | - /* delivery mode reserved */ - (3 << 8) | - MSI_DATA_VECTOR(0); + msg->data = XEN_PIRQ_MSI_DATA; } static int xen_hvm_setup_msi_irqs(struct pci_dev *dev, int nvec, int type) @@ -98,8 +96,23 @@ static int xen_hvm_setup_msi_irqs(struct pci_dev *dev, int nvec, int type) struct msi_msg msg; list_for_each_entry(msidesc, &dev->msi_list, list) { + __read_msi_msg(msidesc, &msg); + pirq = MSI_ADDR_EXT_DEST_ID(msg.address_hi) | + ((msg.address_lo >> MSI_ADDR_DEST_ID_SHIFT) & 0xff); + if (xen_irq_from_pirq(pirq) >= 0 && msg.data == XEN_PIRQ_MSI_DATA) { + xen_allocate_pirq_msi((type == PCI_CAP_ID_MSIX) ? + "msi-x" : "msi", &irq, &pirq, XEN_ALLOC_IRQ); + if (irq < 0) + goto error; + ret = set_irq_msi(irq, msidesc); + if (ret < 0) + goto error_while; + printk(KERN_DEBUG "xen: msi already setup: msi --> irq=%d" + " pirq=%d\n", irq, pirq); + return 0; + } xen_allocate_pirq_msi((type == PCI_CAP_ID_MSIX) ? - "msi-x" : "msi", &irq, &pirq); + "msi-x" : "msi", &irq, &pirq, (XEN_ALLOC_IRQ | XEN_ALLOC_PIRQ)); if (irq < 0 || pirq < 0) goto error; printk(KERN_DEBUG "xen: msi --> irq=%d, pirq=%d\n", irq, pirq); diff --git a/arch/x86/platform/sfi/sfi.c b/arch/x86/platform/sfi/sfi.c index cc822a29b227..7785b72ecc3a 100644 --- a/arch/x86/platform/sfi/sfi.c +++ b/arch/x86/platform/sfi/sfi.c @@ -37,9 +37,9 @@ static unsigned long sfi_lapic_addr __initdata = APIC_DEFAULT_PHYS_BASE; /* All CPUs enumerated by SFI must be present and enabled */ static void __cpuinit mp_sfi_register_lapic(u8 id) { - if (MAX_APICS - id <= 0) { + if (MAX_LOCAL_APIC - id <= 0) { pr_warning("Processor #%d invalid (max %d)\n", - id, MAX_APICS); + id, MAX_LOCAL_APIC); return; } diff --git a/arch/x86/platform/uv/tlb_uv.c b/arch/x86/platform/uv/tlb_uv.c index a318194002b5..df58e9cad96a 100644 --- a/arch/x86/platform/uv/tlb_uv.c +++ b/arch/x86/platform/uv/tlb_uv.c @@ -1341,7 +1341,7 @@ uv_activation_descriptor_init(int node, int pnode) /* * each bau_desc is 64 bytes; there are 8 (UV_ITEMS_PER_DESCRIPTOR) - * per cpu; and up to 32 (UV_ADP_SIZE) cpu's per uvhub + * per cpu; and one per cpu on the uvhub (UV_ADP_SIZE) */ bau_desc = kmalloc_node(sizeof(struct bau_desc) * UV_ADP_SIZE * UV_ITEMS_PER_DESCRIPTOR, GFP_KERNEL, node); @@ -1455,7 +1455,7 @@ static void __init uv_init_uvhub(int uvhub, int vector) * the below initialization can't be in firmware because the * messaging IRQ will be determined by the OS */ - apicid = uvhub_to_first_apicid(uvhub); + apicid = uvhub_to_first_apicid(uvhub) | uv_apicid_hibits; uv_write_global_mmr64(pnode, UVH_BAU_DATA_CONFIG, ((apicid << 32) | vector)); } @@ -1490,7 +1490,7 @@ calculate_destination_timeout(void) /* * initialize the bau_control structure for each cpu */ -static void __init uv_init_per_cpu(int nuvhubs) +static int __init uv_init_per_cpu(int nuvhubs) { int i; int cpu; @@ -1507,7 +1507,7 @@ static void __init uv_init_per_cpu(int nuvhubs) struct bau_control *smaster = NULL; struct socket_desc { short num_cpus; - short cpu_number[16]; + short cpu_number[MAX_CPUS_PER_SOCKET]; }; struct uvhub_desc { unsigned short socket_mask; @@ -1540,6 +1540,10 @@ static void __init uv_init_per_cpu(int nuvhubs) sdp = &bdp->socket[socket]; sdp->cpu_number[sdp->num_cpus] = cpu; sdp->num_cpus++; + if (sdp->num_cpus > MAX_CPUS_PER_SOCKET) { + printk(KERN_EMERG "%d cpus per socket invalid\n", sdp->num_cpus); + return 1; + } } for (uvhub = 0; uvhub < nuvhubs; uvhub++) { if (!(*(uvhub_mask + (uvhub/8)) & (1 << (uvhub%8)))) @@ -1570,6 +1574,12 @@ static void __init uv_init_per_cpu(int nuvhubs) bcp->uvhub_master = hmaster; bcp->uvhub_cpu = uv_cpu_hub_info(cpu)-> blade_processor_id; + if (bcp->uvhub_cpu >= MAX_CPUS_PER_UVHUB) { + printk(KERN_EMERG + "%d cpus per uvhub invalid\n", + bcp->uvhub_cpu); + return 1; + } } nextsocket: socket++; @@ -1595,6 +1605,7 @@ nextsocket: bcp->congested_reps = congested_reps; bcp->congested_period = congested_period; } + return 0; } /* @@ -1625,7 +1636,10 @@ static int __init uv_bau_init(void) spin_lock_init(&disable_lock); congested_cycles = microsec_2_cycles(congested_response_us); - uv_init_per_cpu(nuvhubs); + if (uv_init_per_cpu(nuvhubs)) { + nobau = 1; + return 0; + } uv_partition_base_pnode = 0x7fffffff; for (uvhub = 0; uvhub < nuvhubs; uvhub++) diff --git a/arch/x86/platform/uv/uv_time.c b/arch/x86/platform/uv/uv_time.c index 56e421bc379b..9daf5d1af9f1 100644 --- a/arch/x86/platform/uv/uv_time.c +++ b/arch/x86/platform/uv/uv_time.c @@ -89,6 +89,7 @@ static void uv_rtc_send_IPI(int cpu) apicid = cpu_physical_id(cpu); pnode = uv_apicid_to_pnode(apicid); + apicid |= uv_apicid_hibits; val = (1UL << UVH_IPI_INT_SEND_SHFT) | (apicid << UVH_IPI_INT_APIC_ID_SHFT) | (X86_PLATFORM_IPI_VECTOR << UVH_IPI_INT_VECTOR_SHFT); @@ -107,6 +108,7 @@ static int uv_intr_pending(int pnode) static int uv_setup_intr(int cpu, u64 expires) { u64 val; + unsigned long apicid = cpu_physical_id(cpu) | uv_apicid_hibits; int pnode = uv_cpu_to_pnode(cpu); uv_write_global_mmr64(pnode, UVH_RTC1_INT_CONFIG, @@ -117,7 +119,7 @@ static int uv_setup_intr(int cpu, u64 expires) UVH_EVENT_OCCURRED0_RTC1_MASK); val = (X86_PLATFORM_IPI_VECTOR << UVH_RTC1_INT_CONFIG_VECTOR_SHFT) | - ((u64)cpu_physical_id(cpu) << UVH_RTC1_INT_CONFIG_APIC_ID_SHFT); + ((u64)apicid << UVH_RTC1_INT_CONFIG_APIC_ID_SHFT); /* Set configuration */ uv_write_global_mmr64(pnode, UVH_RTC1_INT_CONFIG, val); diff --git a/arch/x86/platform/visws/visws_quirks.c b/arch/x86/platform/visws/visws_quirks.c index 3371bd053b89..632037671746 100644 --- a/arch/x86/platform/visws/visws_quirks.c +++ b/arch/x86/platform/visws/visws_quirks.c @@ -171,7 +171,7 @@ static void __init MP_processor_info(struct mpc_cpu *m) ver = m->apicver; if ((ver >= 0x14 && m->apicid >= 0xff) || m->apicid >= 0xf) { printk(KERN_ERR "Processor #%d INVALID. (Max ID: %d).\n", - m->apicid, MAX_APICS); + m->apicid, MAX_LOCAL_APIC); return; } diff --git a/arch/x86/vdso/Makefile b/arch/x86/vdso/Makefile index 4a2afa1bac51..b6552b189bcd 100644 --- a/arch/x86/vdso/Makefile +++ b/arch/x86/vdso/Makefile @@ -25,7 +25,7 @@ targets += vdso.so vdso.so.dbg vdso.lds $(vobjs-y) export CPPFLAGS_vdso.lds += -P -C -VDSO_LDFLAGS_vdso.lds = -m elf_x86_64 -Wl,-soname=linux-vdso.so.1 \ +VDSO_LDFLAGS_vdso.lds = -m64 -Wl,-soname=linux-vdso.so.1 \ -Wl,-z,max-page-size=4096 -Wl,-z,common-page-size=4096 $(obj)/vdso.o: $(src)/vdso.S $(obj)/vdso.so @@ -69,7 +69,7 @@ vdso32.so-$(VDSO32-y) += sysenter vdso32-images = $(vdso32.so-y:%=vdso32-%.so) CPPFLAGS_vdso32.lds = $(CPPFLAGS_vdso.lds) -VDSO_LDFLAGS_vdso32.lds = -m elf_i386 -Wl,-soname=linux-gate.so.1 +VDSO_LDFLAGS_vdso32.lds = -m32 -Wl,-soname=linux-gate.so.1 # This makes sure the $(obj) subdirectory exists even though vdso32/ # is not a kbuild sub-make subdirectory. diff --git a/arch/x86/xen/enlighten.c b/arch/x86/xen/enlighten.c index 235c0f4d3861..44dcad43989d 100644 --- a/arch/x86/xen/enlighten.c +++ b/arch/x86/xen/enlighten.c @@ -75,6 +75,11 @@ DEFINE_PER_CPU(struct vcpu_info, xen_vcpu_info); enum xen_domain_type xen_domain_type = XEN_NATIVE; EXPORT_SYMBOL_GPL(xen_domain_type); +unsigned long *machine_to_phys_mapping = (void *)MACH2PHYS_VIRT_START; +EXPORT_SYMBOL(machine_to_phys_mapping); +unsigned int machine_to_phys_order; +EXPORT_SYMBOL(machine_to_phys_order); + struct start_info *xen_start_info; EXPORT_SYMBOL_GPL(xen_start_info); @@ -1016,10 +1021,6 @@ static void xen_reboot(int reason) { struct sched_shutdown r = { .reason = reason }; -#ifdef CONFIG_SMP - stop_other_cpus(); -#endif - if (HYPERVISOR_sched_op(SCHEDOP_shutdown, &r)) BUG(); } @@ -1090,6 +1091,8 @@ static void __init xen_setup_stackprotector(void) /* First C function to be called on Xen boot */ asmlinkage void __init xen_start_kernel(void) { + struct physdev_set_iopl set_iopl; + int rc; pgd_t *pgd; if (!xen_start_info) @@ -1097,6 +1100,8 @@ asmlinkage void __init xen_start_kernel(void) xen_domain_type = XEN_PV_DOMAIN; + xen_setup_machphys_mapping(); + /* Install Xen paravirt ops */ pv_info = xen_info; pv_init_ops = xen_init_ops; @@ -1191,8 +1196,6 @@ asmlinkage void __init xen_start_kernel(void) /* Allocate and initialize top and mid mfn levels for p2m structure */ xen_build_mfn_list_list(); - init_mm.pgd = pgd; - /* keep using Xen gdt for now; no urgent need to change it */ #ifdef CONFIG_X86_32 @@ -1202,10 +1205,18 @@ asmlinkage void __init xen_start_kernel(void) #else pv_info.kernel_rpl = 0; #endif - /* set the limit of our address space */ xen_reserve_top(); + /* We used to do this in xen_arch_setup, but that is too late on AMD + * were early_cpu_init (run before ->arch_setup()) calls early_amd_init + * which pokes 0xcf8 port. + */ + set_iopl.iopl = 1; + rc = HYPERVISOR_physdev_op(PHYSDEVOP_set_iopl, &set_iopl); + if (rc != 0) + xen_raw_printk("physdev_op failed %d\n", rc); + #ifdef CONFIG_X86_32 /* set up basic CPUID stuff */ cpu_detect(&new_cpu_data); diff --git a/arch/x86/xen/mmu.c b/arch/x86/xen/mmu.c index 21ed8d7f75a5..44924e551fde 100644 --- a/arch/x86/xen/mmu.c +++ b/arch/x86/xen/mmu.c @@ -2034,6 +2034,20 @@ static __init void xen_map_identity_early(pmd_t *pmd, unsigned long max_pfn) set_page_prot(pmd, PAGE_KERNEL_RO); } +void __init xen_setup_machphys_mapping(void) +{ + struct xen_machphys_mapping mapping; + unsigned long machine_to_phys_nr_ents; + + if (HYPERVISOR_memory_op(XENMEM_machphys_mapping, &mapping) == 0) { + machine_to_phys_mapping = (unsigned long *)mapping.v_start; + machine_to_phys_nr_ents = mapping.max_mfn + 1; + } else { + machine_to_phys_nr_ents = MACH2PHYS_NR_ENTRIES; + } + machine_to_phys_order = fls(machine_to_phys_nr_ents - 1); +} + #ifdef CONFIG_X86_64 static void convert_pfn_mfn(void *v) { @@ -2119,44 +2133,83 @@ __init pgd_t *xen_setup_kernel_pagetable(pgd_t *pgd, return pgd; } #else /* !CONFIG_X86_64 */ -static RESERVE_BRK_ARRAY(pmd_t, level2_kernel_pgt, PTRS_PER_PMD); +static RESERVE_BRK_ARRAY(pmd_t, initial_kernel_pmd, PTRS_PER_PMD); +static RESERVE_BRK_ARRAY(pmd_t, swapper_kernel_pmd, PTRS_PER_PMD); + +static __init void xen_write_cr3_init(unsigned long cr3) +{ + unsigned long pfn = PFN_DOWN(__pa(swapper_pg_dir)); + + BUG_ON(read_cr3() != __pa(initial_page_table)); + BUG_ON(cr3 != __pa(swapper_pg_dir)); + + /* + * We are switching to swapper_pg_dir for the first time (from + * initial_page_table) and therefore need to mark that page + * read-only and then pin it. + * + * Xen disallows sharing of kernel PMDs for PAE + * guests. Therefore we must copy the kernel PMD from + * initial_page_table into a new kernel PMD to be used in + * swapper_pg_dir. + */ + swapper_kernel_pmd = + extend_brk(sizeof(pmd_t) * PTRS_PER_PMD, PAGE_SIZE); + memcpy(swapper_kernel_pmd, initial_kernel_pmd, + sizeof(pmd_t) * PTRS_PER_PMD); + swapper_pg_dir[KERNEL_PGD_BOUNDARY] = + __pgd(__pa(swapper_kernel_pmd) | _PAGE_PRESENT); + set_page_prot(swapper_kernel_pmd, PAGE_KERNEL_RO); + + set_page_prot(swapper_pg_dir, PAGE_KERNEL_RO); + xen_write_cr3(cr3); + pin_pagetable_pfn(MMUEXT_PIN_L3_TABLE, pfn); + + pin_pagetable_pfn(MMUEXT_UNPIN_TABLE, + PFN_DOWN(__pa(initial_page_table))); + set_page_prot(initial_page_table, PAGE_KERNEL); + set_page_prot(initial_kernel_pmd, PAGE_KERNEL); + + pv_mmu_ops.write_cr3 = &xen_write_cr3; +} __init pgd_t *xen_setup_kernel_pagetable(pgd_t *pgd, unsigned long max_pfn) { pmd_t *kernel_pmd; - level2_kernel_pgt = extend_brk(sizeof(pmd_t) * PTRS_PER_PMD, PAGE_SIZE); + initial_kernel_pmd = + extend_brk(sizeof(pmd_t) * PTRS_PER_PMD, PAGE_SIZE); max_pfn_mapped = PFN_DOWN(__pa(xen_start_info->pt_base) + xen_start_info->nr_pt_frames * PAGE_SIZE + 512*1024); kernel_pmd = m2v(pgd[KERNEL_PGD_BOUNDARY].pgd); - memcpy(level2_kernel_pgt, kernel_pmd, sizeof(pmd_t) * PTRS_PER_PMD); + memcpy(initial_kernel_pmd, kernel_pmd, sizeof(pmd_t) * PTRS_PER_PMD); - xen_map_identity_early(level2_kernel_pgt, max_pfn); + xen_map_identity_early(initial_kernel_pmd, max_pfn); - memcpy(swapper_pg_dir, pgd, sizeof(pgd_t) * PTRS_PER_PGD); - set_pgd(&swapper_pg_dir[KERNEL_PGD_BOUNDARY], - __pgd(__pa(level2_kernel_pgt) | _PAGE_PRESENT)); + memcpy(initial_page_table, pgd, sizeof(pgd_t) * PTRS_PER_PGD); + initial_page_table[KERNEL_PGD_BOUNDARY] = + __pgd(__pa(initial_kernel_pmd) | _PAGE_PRESENT); - set_page_prot(level2_kernel_pgt, PAGE_KERNEL_RO); - set_page_prot(swapper_pg_dir, PAGE_KERNEL_RO); + set_page_prot(initial_kernel_pmd, PAGE_KERNEL_RO); + set_page_prot(initial_page_table, PAGE_KERNEL_RO); set_page_prot(empty_zero_page, PAGE_KERNEL_RO); pin_pagetable_pfn(MMUEXT_UNPIN_TABLE, PFN_DOWN(__pa(pgd))); - xen_write_cr3(__pa(swapper_pg_dir)); - - pin_pagetable_pfn(MMUEXT_PIN_L3_TABLE, PFN_DOWN(__pa(swapper_pg_dir))); + pin_pagetable_pfn(MMUEXT_PIN_L3_TABLE, + PFN_DOWN(__pa(initial_page_table))); + xen_write_cr3(__pa(initial_page_table)); memblock_x86_reserve_range(__pa(xen_start_info->pt_base), __pa(xen_start_info->pt_base + xen_start_info->nr_pt_frames * PAGE_SIZE), "XEN PAGETABLES"); - return swapper_pg_dir; + return initial_page_table; } #endif /* CONFIG_X86_64 */ @@ -2290,7 +2343,11 @@ static const struct pv_mmu_ops xen_mmu_ops __initdata = { .write_cr2 = xen_write_cr2, .read_cr3 = xen_read_cr3, +#ifdef CONFIG_X86_32 + .write_cr3 = xen_write_cr3_init, +#else .write_cr3 = xen_write_cr3, +#endif .flush_tlb_user = xen_flush_tlb, .flush_tlb_kernel = xen_flush_tlb, @@ -2358,8 +2415,6 @@ void __init xen_init_mmu_ops(void) x86_init.paging.pagetable_setup_done = xen_pagetable_setup_done; pv_mmu_ops = xen_mmu_ops; - vmap_lazy_unmap = false; - memset(dummy_mapping, 0xff, PAGE_SIZE); } @@ -2627,7 +2682,8 @@ int xen_remap_domain_mfn_range(struct vm_area_struct *vma, prot = __pgprot(pgprot_val(prot) | _PAGE_IOMAP); - vma->vm_flags |= VM_IO | VM_RESERVED | VM_PFNMAP; + BUG_ON(!((vma->vm_flags & (VM_PFNMAP | VM_RESERVED | VM_IO)) == + (VM_PFNMAP | VM_RESERVED | VM_IO))); rmd.mfn = mfn; rmd.prot = prot; diff --git a/arch/x86/xen/platform-pci-unplug.c b/arch/x86/xen/platform-pci-unplug.c index 0f456386cce5..25c52f94a27c 100644 --- a/arch/x86/xen/platform-pci-unplug.c +++ b/arch/x86/xen/platform-pci-unplug.c @@ -68,7 +68,7 @@ static int __init check_platform_magic(void) return 0; } -void __init xen_unplug_emulated_devices(void) +void xen_unplug_emulated_devices(void) { int r; diff --git a/arch/x86/xen/setup.c b/arch/x86/xen/setup.c index 769c4b01fa32..b5a7f928234b 100644 --- a/arch/x86/xen/setup.c +++ b/arch/x86/xen/setup.c @@ -23,7 +23,6 @@ #include <xen/interface/callback.h> #include <xen/interface/memory.h> #include <xen/interface/physdev.h> -#include <xen/interface/memory.h> #include <xen/features.h> #include "xen-ops.h" @@ -182,24 +181,21 @@ char * __init xen_memory_setup(void) for (i = 0; i < memmap.nr_entries; i++) { unsigned long long end = map[i].addr + map[i].size; - if (map[i].type == E820_RAM) { - if (map[i].addr < mem_end && end > mem_end) { - /* Truncate region to max_mem. */ - u64 delta = end - mem_end; + if (map[i].type == E820_RAM && end > mem_end) { + /* RAM off the end - may be partially included */ + u64 delta = min(map[i].size, end - mem_end); - map[i].size -= delta; - extra_pages += PFN_DOWN(delta); + map[i].size -= delta; + end -= delta; - end = mem_end; - } + extra_pages += PFN_DOWN(delta); } - if (end > xen_extra_mem_start) + if (map[i].size > 0 && end > xen_extra_mem_start) xen_extra_mem_start = end; - /* If region is non-RAM or below mem_end, add what remains */ - if ((map[i].type != E820_RAM || map[i].addr < mem_end) && - map[i].size > 0) + /* Add region if any remains */ + if (map[i].size > 0) e820_add_region(map[i].addr, map[i].size, map[i].type); } @@ -248,26 +244,11 @@ char * __init xen_memory_setup(void) else extra_pages = 0; - if (!xen_initial_domain()) - xen_add_extra_mem(extra_pages); + xen_add_extra_mem(extra_pages); return "Xen"; } -static void xen_idle(void) -{ - local_irq_disable(); - - if (need_resched()) - local_irq_enable(); - else { - current_thread_info()->status &= ~TS_POLLING; - smp_mb__after_clear_bit(); - safe_halt(); - current_thread_info()->status |= TS_POLLING; - } -} - /* * Set the bit indicating "nosegneg" library variants should be used. * We only need to bother in pure 32-bit mode; compat 32-bit processes @@ -337,9 +318,6 @@ void __cpuinit xen_enable_syscall(void) void __init xen_arch_setup(void) { - struct physdev_set_iopl set_iopl; - int rc; - xen_panic_handler_init(); HYPERVISOR_vm_assist(VMASST_CMD_enable, VMASST_TYPE_4gb_segments); @@ -356,11 +334,6 @@ void __init xen_arch_setup(void) xen_enable_sysenter(); xen_enable_syscall(); - set_iopl.iopl = 1; - rc = HYPERVISOR_physdev_op(PHYSDEVOP_set_iopl, &set_iopl); - if (rc != 0) - printk(KERN_INFO "physdev_op failed %d\n", rc); - #ifdef CONFIG_ACPI if (!(xen_start_info->flags & SIF_INITDOMAIN)) { printk(KERN_INFO "ACPI in unprivileged domain disabled\n"); @@ -372,7 +345,11 @@ void __init xen_arch_setup(void) MAX_GUEST_CMDLINE > COMMAND_LINE_SIZE ? COMMAND_LINE_SIZE : MAX_GUEST_CMDLINE); - pm_idle = xen_idle; + /* Set up idle, making sure it calls safe_halt() pvop */ +#ifdef CONFIG_X86_32 + boot_cpu_data.hlt_works_ok = 1; +#endif + pm_idle = default_idle; fiddle_vdso(); } diff --git a/arch/x86/xen/suspend.c b/arch/x86/xen/suspend.c index 1d789d56877c..9bbd63a129b5 100644 --- a/arch/x86/xen/suspend.c +++ b/arch/x86/xen/suspend.c @@ -31,6 +31,7 @@ void xen_hvm_post_suspend(int suspend_cancelled) int cpu; xen_hvm_init_shared_info(); xen_callback_vector(); + xen_unplug_emulated_devices(); if (xen_feature(XENFEAT_hvm_safe_pvclock)) { for_each_online_cpu(cpu) { xen_setup_runstate_info(cpu); diff --git a/arch/x86/xen/time.c b/arch/x86/xen/time.c index b2bb5aa3b054..5da5e53fb94c 100644 --- a/arch/x86/xen/time.c +++ b/arch/x86/xen/time.c @@ -426,6 +426,8 @@ void xen_timer_resume(void) { int cpu; + pvclock_resume(); + if (xen_clockevent != &xen_vcpuop_clockevent) return; diff --git a/arch/x86/xen/xen-ops.h b/arch/x86/xen/xen-ops.h index 64044747348e..9d41bf985757 100644 --- a/arch/x86/xen/xen-ops.h +++ b/arch/x86/xen/xen-ops.h @@ -43,7 +43,7 @@ void xen_vcpu_restore(void); void xen_callback_vector(void); void xen_hvm_init_shared_info(void); -void __init xen_unplug_emulated_devices(void); +void xen_unplug_emulated_devices(void); void __init xen_build_dynamic_phys_to_machine(void); |