diff options
Diffstat (limited to 'arch/x86')
50 files changed, 563 insertions, 346 deletions
diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig index 725e1573ea85..6e3e1cb3f6a0 100644 --- a/arch/x86/Kconfig +++ b/arch/x86/Kconfig @@ -255,10 +255,6 @@ config ARCH_HWEIGHT_CFLAGS default "-fcall-saved-ecx -fcall-saved-edx" if X86_32 default "-fcall-saved-rdi -fcall-saved-rsi -fcall-saved-rdx -fcall-saved-rcx -fcall-saved-r8 -fcall-saved-r9 -fcall-saved-r10 -fcall-saved-r11" if X86_64 -config ARCH_CPU_PROBE_RELEASE - def_bool y - depends on HOTPLUG_CPU - config ARCH_SUPPORTS_UPROBES def_bool y @@ -639,10 +635,10 @@ config PARAVIRT_SPINLOCKS spinlock implementation with something virtualization-friendly (for example, block the virtual CPU rather than spinning). - Unfortunately the downside is an up to 5% performance hit on - native kernels, with various workloads. + It has a minimal impact on native kernels and gives a nice performance + benefit on paravirtualized KVM / Xen kernels. - If you are unsure how to answer this question, answer N. + If you are unsure how to answer this question, answer Y. source "arch/x86/xen/Kconfig" diff --git a/arch/x86/ia32/ia32_aout.c b/arch/x86/ia32/ia32_aout.c index bae3aba95b15..d21ff89207cd 100644 --- a/arch/x86/ia32/ia32_aout.c +++ b/arch/x86/ia32/ia32_aout.c @@ -25,6 +25,7 @@ #include <linux/personality.h> #include <linux/init.h> #include <linux/jiffies.h> +#include <linux/perf_event.h> #include <asm/uaccess.h> #include <asm/pgalloc.h> @@ -33,14 +34,18 @@ #include <asm/ia32.h> #undef WARN_OLD -#undef CORE_DUMP /* definitely broken */ static int load_aout_binary(struct linux_binprm *); static int load_aout_library(struct file *); -#ifdef CORE_DUMP -static int aout_core_dump(long signr, struct pt_regs *regs, struct file *file, - unsigned long limit); +#ifdef CONFIG_COREDUMP +static int aout_core_dump(struct coredump_params *); + +static unsigned long get_dr(int n) +{ + struct perf_event *bp = current->thread.ptrace_bps[n]; + return bp ? bp->hw.info.address : 0; +} /* * fill in the user structure for a core dump.. @@ -48,6 +53,7 @@ static int aout_core_dump(long signr, struct pt_regs *regs, struct file *file, static void dump_thread32(struct pt_regs *regs, struct user32 *dump) { u32 fs, gs; + memset(dump, 0, sizeof(*dump)); /* changed the size calculations - should hopefully work better. lbt */ dump->magic = CMAGIC; @@ -57,15 +63,12 @@ static void dump_thread32(struct pt_regs *regs, struct user32 *dump) dump->u_dsize = ((unsigned long) (current->mm->brk + (PAGE_SIZE-1))) >> PAGE_SHIFT; dump->u_dsize -= dump->u_tsize; - dump->u_ssize = 0; - dump->u_debugreg[0] = current->thread.debugreg0; - dump->u_debugreg[1] = current->thread.debugreg1; - dump->u_debugreg[2] = current->thread.debugreg2; - dump->u_debugreg[3] = current->thread.debugreg3; - dump->u_debugreg[4] = 0; - dump->u_debugreg[5] = 0; + dump->u_debugreg[0] = get_dr(0); + dump->u_debugreg[1] = get_dr(1); + dump->u_debugreg[2] = get_dr(2); + dump->u_debugreg[3] = get_dr(3); dump->u_debugreg[6] = current->thread.debugreg6; - dump->u_debugreg[7] = current->thread.debugreg7; + dump->u_debugreg[7] = current->thread.ptrace_dr7; if (dump->start_stack < 0xc0000000) { unsigned long tmp; @@ -74,24 +77,24 @@ static void dump_thread32(struct pt_regs *regs, struct user32 *dump) dump->u_ssize = tmp >> PAGE_SHIFT; } - dump->regs.bx = regs->bx; - dump->regs.cx = regs->cx; - dump->regs.dx = regs->dx; - dump->regs.si = regs->si; - dump->regs.di = regs->di; - dump->regs.bp = regs->bp; - dump->regs.ax = regs->ax; + dump->regs.ebx = regs->bx; + dump->regs.ecx = regs->cx; + dump->regs.edx = regs->dx; + dump->regs.esi = regs->si; + dump->regs.edi = regs->di; + dump->regs.ebp = regs->bp; + dump->regs.eax = regs->ax; dump->regs.ds = current->thread.ds; dump->regs.es = current->thread.es; savesegment(fs, fs); dump->regs.fs = fs; savesegment(gs, gs); dump->regs.gs = gs; - dump->regs.orig_ax = regs->orig_ax; - dump->regs.ip = regs->ip; + dump->regs.orig_eax = regs->orig_ax; + dump->regs.eip = regs->ip; dump->regs.cs = regs->cs; - dump->regs.flags = regs->flags; - dump->regs.sp = regs->sp; + dump->regs.eflags = regs->flags; + dump->regs.esp = regs->sp; dump->regs.ss = regs->ss; #if 1 /* FIXME */ @@ -107,7 +110,7 @@ static struct linux_binfmt aout_format = { .module = THIS_MODULE, .load_binary = load_aout_binary, .load_shlib = load_aout_library, -#ifdef CORE_DUMP +#ifdef CONFIG_COREDUMP .core_dump = aout_core_dump, #endif .min_coredump = PAGE_SIZE @@ -122,7 +125,7 @@ static void set_brk(unsigned long start, unsigned long end) vm_brk(start, end - start); } -#ifdef CORE_DUMP +#ifdef CONFIG_COREDUMP /* * These are the only things you should do on a core-file: use only these * macros to write out all the necessary info. @@ -130,15 +133,7 @@ static void set_brk(unsigned long start, unsigned long end) #include <linux/coredump.h> -#define DUMP_WRITE(addr, nr) \ - if (!dump_write(file, (void *)(addr), (nr))) \ - goto end_coredump; - -#define DUMP_SEEK(offset) \ - if (!dump_seek(file, offset)) \ - goto end_coredump; - -#define START_DATA() (u.u_tsize << PAGE_SHIFT) +#define START_DATA(u) (u.u_tsize << PAGE_SHIFT) #define START_STACK(u) (u.start_stack) /* @@ -151,8 +146,7 @@ static void set_brk(unsigned long start, unsigned long end) * dumping of the process results in another error.. */ -static int aout_core_dump(long signr, struct pt_regs *regs, struct file *file, - unsigned long limit) +static int aout_core_dump(struct coredump_params *cprm) { mm_segment_t fs; int has_dumped = 0; @@ -164,19 +158,19 @@ static int aout_core_dump(long signr, struct pt_regs *regs, struct file *file, has_dumped = 1; strncpy(dump.u_comm, current->comm, sizeof(current->comm)); dump.u_ar0 = offsetof(struct user32, regs); - dump.signal = signr; - dump_thread32(regs, &dump); + dump.signal = cprm->siginfo->si_signo; + dump_thread32(cprm->regs, &dump); /* * If the size of the dump file exceeds the rlimit, then see * what would happen if we wrote the stack, but not the data * area. */ - if ((dump.u_dsize + dump.u_ssize + 1) * PAGE_SIZE > limit) + if ((dump.u_dsize + dump.u_ssize + 1) * PAGE_SIZE > cprm->limit) dump.u_dsize = 0; /* Make sure we have enough room to write the stack and data areas. */ - if ((dump.u_ssize + 1) * PAGE_SIZE > limit) + if ((dump.u_ssize + 1) * PAGE_SIZE > cprm->limit) dump.u_ssize = 0; /* make sure we actually have a data and stack area to dump */ @@ -190,22 +184,26 @@ static int aout_core_dump(long signr, struct pt_regs *regs, struct file *file, set_fs(KERNEL_DS); /* struct user */ - DUMP_WRITE(&dump, sizeof(dump)); + if (!dump_emit(cprm, &dump, sizeof(dump))) + goto end_coredump; /* Now dump all of the user data. Include malloced stuff as well */ - DUMP_SEEK(PAGE_SIZE - sizeof(dump)); + if (!dump_skip(cprm, PAGE_SIZE - sizeof(dump))) + goto end_coredump; /* now we start writing out the user space info */ set_fs(USER_DS); /* Dump the data area */ if (dump.u_dsize != 0) { dump_start = START_DATA(dump); dump_size = dump.u_dsize << PAGE_SHIFT; - DUMP_WRITE(dump_start, dump_size); + if (!dump_emit(cprm, (void *)dump_start, dump_size)) + goto end_coredump; } /* Now prepare to dump the stack area */ if (dump.u_ssize != 0) { dump_start = START_STACK(dump); dump_size = dump.u_ssize << PAGE_SHIFT; - DUMP_WRITE(dump_start, dump_size); + if (!dump_emit(cprm, (void *)dump_start, dump_size)) + goto end_coredump; } end_coredump: set_fs(fs); diff --git a/arch/x86/ia32/ia32_signal.c b/arch/x86/ia32/ia32_signal.c index 665a730307f2..220675795e08 100644 --- a/arch/x86/ia32/ia32_signal.c +++ b/arch/x86/ia32/ia32_signal.c @@ -34,7 +34,7 @@ #include <asm/sys_ia32.h> #include <asm/smap.h> -int copy_siginfo_to_user32(compat_siginfo_t __user *to, siginfo_t *from) +int copy_siginfo_to_user32(compat_siginfo_t __user *to, const siginfo_t *from) { int err = 0; bool ia32 = test_thread_flag(TIF_IA32); diff --git a/arch/x86/include/asm/acpi.h b/arch/x86/include/asm/acpi.h index b1977bad5435..c8c1e700c26e 100644 --- a/arch/x86/include/asm/acpi.h +++ b/arch/x86/include/asm/acpi.h @@ -26,6 +26,7 @@ #include <acpi/pdc_intel.h> #include <asm/numa.h> +#include <asm/fixmap.h> #include <asm/processor.h> #include <asm/mmu.h> #include <asm/mpspec.h> diff --git a/arch/x86/include/asm/desc.h b/arch/x86/include/asm/desc.h index b90e5dfeee46..50d033a8947d 100644 --- a/arch/x86/include/asm/desc.h +++ b/arch/x86/include/asm/desc.h @@ -327,10 +327,25 @@ static inline void write_trace_idt_entry(int entry, const gate_desc *gate) { write_idt_entry(trace_idt_table, entry, gate); } + +static inline void _trace_set_gate(int gate, unsigned type, void *addr, + unsigned dpl, unsigned ist, unsigned seg) +{ + gate_desc s; + + pack_gate(&s, type, (unsigned long)addr, dpl, ist, seg); + /* + * does not need to be atomic because it is only done once at + * setup time + */ + write_trace_idt_entry(gate, &s); +} #else static inline void write_trace_idt_entry(int entry, const gate_desc *gate) { } + +#define _trace_set_gate(gate, type, addr, dpl, ist, seg) #endif static inline void _set_gate(int gate, unsigned type, void *addr, @@ -353,11 +368,14 @@ static inline void _set_gate(int gate, unsigned type, void *addr, * Pentium F0 0F bugfix can have resulted in the mapped * IDT being write-protected. */ -static inline void set_intr_gate(unsigned int n, void *addr) -{ - BUG_ON((unsigned)n > 0xFF); - _set_gate(n, GATE_INTERRUPT, addr, 0, 0, __KERNEL_CS); -} +#define set_intr_gate(n, addr) \ + do { \ + BUG_ON((unsigned)n > 0xFF); \ + _set_gate(n, GATE_INTERRUPT, (void *)addr, 0, 0, \ + __KERNEL_CS); \ + _trace_set_gate(n, GATE_INTERRUPT, (void *)trace_##addr,\ + 0, 0, __KERNEL_CS); \ + } while (0) extern int first_system_vector; /* used_vectors is BITMAP for irq is not managed by percpu vector_irq */ @@ -374,37 +392,10 @@ static inline void alloc_system_vector(int vector) } } -#ifdef CONFIG_TRACING -static inline void trace_set_intr_gate(unsigned int gate, void *addr) -{ - gate_desc s; - - pack_gate(&s, GATE_INTERRUPT, (unsigned long)addr, 0, 0, __KERNEL_CS); - write_idt_entry(trace_idt_table, gate, &s); -} - -static inline void __trace_alloc_intr_gate(unsigned int n, void *addr) -{ - trace_set_intr_gate(n, addr); -} -#else -static inline void trace_set_intr_gate(unsigned int gate, void *addr) -{ -} - -#define __trace_alloc_intr_gate(n, addr) -#endif - -static inline void __alloc_intr_gate(unsigned int n, void *addr) -{ - set_intr_gate(n, addr); -} - #define alloc_intr_gate(n, addr) \ do { \ alloc_system_vector(n); \ - __alloc_intr_gate(n, addr); \ - __trace_alloc_intr_gate(n, trace_##addr); \ + set_intr_gate(n, addr); \ } while (0) /* diff --git a/arch/x86/include/asm/fpu-internal.h b/arch/x86/include/asm/fpu-internal.h index 4d0bda7b11e3..c49a613c6452 100644 --- a/arch/x86/include/asm/fpu-internal.h +++ b/arch/x86/include/asm/fpu-internal.h @@ -365,7 +365,7 @@ static inline void drop_fpu(struct task_struct *tsk) * Forget coprocessor state.. */ preempt_disable(); - tsk->fpu_counter = 0; + tsk->thread.fpu_counter = 0; __drop_fpu(tsk); clear_used_math(); preempt_enable(); @@ -424,7 +424,7 @@ static inline fpu_switch_t switch_fpu_prepare(struct task_struct *old, struct ta * or if the past 5 consecutive context-switches used math. */ fpu.preload = tsk_used_math(new) && (use_eager_fpu() || - new->fpu_counter > 5); + new->thread.fpu_counter > 5); if (__thread_has_fpu(old)) { if (!__save_init_fpu(old)) cpu = ~0; @@ -433,16 +433,16 @@ static inline fpu_switch_t switch_fpu_prepare(struct task_struct *old, struct ta /* Don't change CR0.TS if we just switch! */ if (fpu.preload) { - new->fpu_counter++; + new->thread.fpu_counter++; __thread_set_has_fpu(new); prefetch(new->thread.fpu.state); } else if (!use_eager_fpu()) stts(); } else { - old->fpu_counter = 0; + old->thread.fpu_counter = 0; old->thread.fpu.last_cpu = ~0; if (fpu.preload) { - new->fpu_counter++; + new->thread.fpu_counter++; if (!use_eager_fpu() && fpu_lazy_restore(new, cpu)) fpu.preload = 0; else diff --git a/arch/x86/include/asm/hw_irq.h b/arch/x86/include/asm/hw_irq.h index 92b3bae08b74..cba45d99ac1a 100644 --- a/arch/x86/include/asm/hw_irq.h +++ b/arch/x86/include/asm/hw_irq.h @@ -187,6 +187,9 @@ extern __visible void smp_invalidate_interrupt(struct pt_regs *); #endif extern void (*__initconst interrupt[NR_VECTORS-FIRST_EXTERNAL_VECTOR])(void); +#ifdef CONFIG_TRACING +#define trace_interrupt interrupt +#endif typedef int vector_irq_t[NR_VECTORS]; DECLARE_PER_CPU(vector_irq_t, vector_irq); diff --git a/arch/x86/include/asm/mpspec.h b/arch/x86/include/asm/mpspec.h index 626cf70082d7..3142a94c7b4b 100644 --- a/arch/x86/include/asm/mpspec.h +++ b/arch/x86/include/asm/mpspec.h @@ -94,7 +94,7 @@ static inline void early_reserve_e820_mpc_new(void) { } #define default_get_smp_config x86_init_uint_noop #endif -void generic_processor_info(int apicid, int version); +int generic_processor_info(int apicid, int version); #ifdef CONFIG_ACPI extern void mp_register_ioapic(int id, u32 address, u32 gsi_base); extern void mp_override_legacy_irq(u8 bus_irq, u8 polarity, u8 trigger, diff --git a/arch/x86/include/asm/msr.h b/arch/x86/include/asm/msr.h index cb7502852acb..e139b13f2a33 100644 --- a/arch/x86/include/asm/msr.h +++ b/arch/x86/include/asm/msr.h @@ -218,10 +218,14 @@ void msrs_free(struct msr *msrs); #ifdef CONFIG_SMP int rdmsr_on_cpu(unsigned int cpu, u32 msr_no, u32 *l, u32 *h); int wrmsr_on_cpu(unsigned int cpu, u32 msr_no, u32 l, u32 h); +int rdmsrl_on_cpu(unsigned int cpu, u32 msr_no, u64 *q); +int wrmsrl_on_cpu(unsigned int cpu, u32 msr_no, u64 q); void rdmsr_on_cpus(const struct cpumask *mask, u32 msr_no, struct msr *msrs); void wrmsr_on_cpus(const struct cpumask *mask, u32 msr_no, struct msr *msrs); int rdmsr_safe_on_cpu(unsigned int cpu, u32 msr_no, u32 *l, u32 *h); int wrmsr_safe_on_cpu(unsigned int cpu, u32 msr_no, u32 l, u32 h); +int rdmsrl_safe_on_cpu(unsigned int cpu, u32 msr_no, u64 *q); +int wrmsrl_safe_on_cpu(unsigned int cpu, u32 msr_no, u64 q); int rdmsr_safe_regs_on_cpu(unsigned int cpu, u32 regs[8]); int wrmsr_safe_regs_on_cpu(unsigned int cpu, u32 regs[8]); #else /* CONFIG_SMP */ @@ -235,6 +239,16 @@ static inline int wrmsr_on_cpu(unsigned int cpu, u32 msr_no, u32 l, u32 h) wrmsr(msr_no, l, h); return 0; } +static inline int rdmsrl_on_cpu(unsigned int cpu, u32 msr_no, u64 *q) +{ + rdmsrl(msr_no, *q); + return 0; +} +static inline int wrmsrl_on_cpu(unsigned int cpu, u32 msr_no, u64 q) +{ + wrmsrl(msr_no, q); + return 0; +} static inline void rdmsr_on_cpus(const struct cpumask *m, u32 msr_no, struct msr *msrs) { @@ -254,6 +268,14 @@ static inline int wrmsr_safe_on_cpu(unsigned int cpu, u32 msr_no, u32 l, u32 h) { return wrmsr_safe(msr_no, l, h); } +static inline int rdmsrl_safe_on_cpu(unsigned int cpu, u32 msr_no, u64 *q) +{ + return rdmsrl_safe(msr_no, q); +} +static inline int wrmsrl_safe_on_cpu(unsigned int cpu, u32 msr_no, u64 q) +{ + return wrmsrl_safe(msr_no, q); +} static inline int rdmsr_safe_regs_on_cpu(unsigned int cpu, u32 regs[8]) { return rdmsr_safe_regs(regs); diff --git a/arch/x86/include/asm/percpu.h b/arch/x86/include/asm/percpu.h index b3e18f800302..94220d14d5cc 100644 --- a/arch/x86/include/asm/percpu.h +++ b/arch/x86/include/asm/percpu.h @@ -378,9 +378,6 @@ do { \ #define __this_cpu_or_1(pcp, val) percpu_to_op("or", (pcp), val) #define __this_cpu_or_2(pcp, val) percpu_to_op("or", (pcp), val) #define __this_cpu_or_4(pcp, val) percpu_to_op("or", (pcp), val) -#define __this_cpu_xor_1(pcp, val) percpu_to_op("xor", (pcp), val) -#define __this_cpu_xor_2(pcp, val) percpu_to_op("xor", (pcp), val) -#define __this_cpu_xor_4(pcp, val) percpu_to_op("xor", (pcp), val) #define __this_cpu_xchg_1(pcp, val) percpu_xchg_op(pcp, val) #define __this_cpu_xchg_2(pcp, val) percpu_xchg_op(pcp, val) #define __this_cpu_xchg_4(pcp, val) percpu_xchg_op(pcp, val) @@ -400,9 +397,6 @@ do { \ #define this_cpu_or_1(pcp, val) percpu_to_op("or", (pcp), val) #define this_cpu_or_2(pcp, val) percpu_to_op("or", (pcp), val) #define this_cpu_or_4(pcp, val) percpu_to_op("or", (pcp), val) -#define this_cpu_xor_1(pcp, val) percpu_to_op("xor", (pcp), val) -#define this_cpu_xor_2(pcp, val) percpu_to_op("xor", (pcp), val) -#define this_cpu_xor_4(pcp, val) percpu_to_op("xor", (pcp), val) #define this_cpu_xchg_1(pcp, nval) percpu_xchg_op(pcp, nval) #define this_cpu_xchg_2(pcp, nval) percpu_xchg_op(pcp, nval) #define this_cpu_xchg_4(pcp, nval) percpu_xchg_op(pcp, nval) @@ -447,7 +441,6 @@ do { \ #define __this_cpu_add_8(pcp, val) percpu_add_op((pcp), val) #define __this_cpu_and_8(pcp, val) percpu_to_op("and", (pcp), val) #define __this_cpu_or_8(pcp, val) percpu_to_op("or", (pcp), val) -#define __this_cpu_xor_8(pcp, val) percpu_to_op("xor", (pcp), val) #define __this_cpu_add_return_8(pcp, val) percpu_add_return_op(pcp, val) #define __this_cpu_xchg_8(pcp, nval) percpu_xchg_op(pcp, nval) #define __this_cpu_cmpxchg_8(pcp, oval, nval) percpu_cmpxchg_op(pcp, oval, nval) @@ -457,7 +450,6 @@ do { \ #define this_cpu_add_8(pcp, val) percpu_add_op((pcp), val) #define this_cpu_and_8(pcp, val) percpu_to_op("and", (pcp), val) #define this_cpu_or_8(pcp, val) percpu_to_op("or", (pcp), val) -#define this_cpu_xor_8(pcp, val) percpu_to_op("xor", (pcp), val) #define this_cpu_add_return_8(pcp, val) percpu_add_return_op(pcp, val) #define this_cpu_xchg_8(pcp, nval) percpu_xchg_op(pcp, nval) #define this_cpu_cmpxchg_8(pcp, oval, nval) percpu_cmpxchg_op(pcp, oval, nval) diff --git a/arch/x86/include/asm/processor.h b/arch/x86/include/asm/processor.h index 987c75ecc334..7b034a4057f9 100644 --- a/arch/x86/include/asm/processor.h +++ b/arch/x86/include/asm/processor.h @@ -488,6 +488,15 @@ struct thread_struct { unsigned long iopl; /* Max allowed port in the bitmap, in bytes: */ unsigned io_bitmap_max; + /* + * fpu_counter contains the number of consecutive context switches + * that the FPU is used. If this is over a threshold, the lazy fpu + * saving becomes unlazy to save the trap. This is an unsigned char + * so that after 256 times the counter wraps and the behavior turns + * lazy again; this to deal with bursty apps that only use FPU for + * a short time + */ + unsigned char fpu_counter; }; /* diff --git a/arch/x86/include/asm/prom.h b/arch/x86/include/asm/prom.h index bade6ac3b14f..fbeb06ed0eaa 100644 --- a/arch/x86/include/asm/prom.h +++ b/arch/x86/include/asm/prom.h @@ -39,10 +39,5 @@ static inline void x86_dtb_init(void) { } extern char cmd_line[COMMAND_LINE_SIZE]; -#define pci_address_to_pio pci_address_to_pio -unsigned long pci_address_to_pio(phys_addr_t addr); - -#define HAVE_ARCH_DEVTREE_FIXUPS - #endif /* __ASSEMBLY__ */ #endif diff --git a/arch/x86/include/asm/segment.h b/arch/x86/include/asm/segment.h index c48a95035a77..6f1c3a8a33ab 100644 --- a/arch/x86/include/asm/segment.h +++ b/arch/x86/include/asm/segment.h @@ -214,6 +214,9 @@ #ifdef __KERNEL__ #ifndef __ASSEMBLY__ extern const char early_idt_handlers[NUM_EXCEPTION_VECTORS][2+2+5]; +#ifdef CONFIG_TRACING +#define trace_early_idt_handlers early_idt_handlers +#endif /* * Load a segment. Fall back on loading the zero diff --git a/arch/x86/include/asm/trace/exceptions.h b/arch/x86/include/asm/trace/exceptions.h new file mode 100644 index 000000000000..2fbc66c7885b --- /dev/null +++ b/arch/x86/include/asm/trace/exceptions.h @@ -0,0 +1,52 @@ +#undef TRACE_SYSTEM +#define TRACE_SYSTEM exceptions + +#if !defined(_TRACE_PAGE_FAULT_H) || defined(TRACE_HEADER_MULTI_READ) +#define _TRACE_PAGE_FAULT_H + +#include <linux/tracepoint.h> + +extern void trace_irq_vector_regfunc(void); +extern void trace_irq_vector_unregfunc(void); + +DECLARE_EVENT_CLASS(x86_exceptions, + + TP_PROTO(unsigned long address, struct pt_regs *regs, + unsigned long error_code), + + TP_ARGS(address, regs, error_code), + + TP_STRUCT__entry( + __field( unsigned long, address ) + __field( unsigned long, ip ) + __field( unsigned long, error_code ) + ), + + TP_fast_assign( + __entry->address = address; + __entry->ip = regs->ip; + __entry->error_code = error_code; + ), + + TP_printk("address=%pf ip=%pf error_code=0x%lx", + (void *)__entry->address, (void *)__entry->ip, + __entry->error_code) ); + +#define DEFINE_PAGE_FAULT_EVENT(name) \ +DEFINE_EVENT_FN(x86_exceptions, name, \ + TP_PROTO(unsigned long address, struct pt_regs *regs, \ + unsigned long error_code), \ + TP_ARGS(address, regs, error_code), \ + trace_irq_vector_regfunc, \ + trace_irq_vector_unregfunc); + +DEFINE_PAGE_FAULT_EVENT(page_fault_user); +DEFINE_PAGE_FAULT_EVENT(page_fault_kernel); + +#undef TRACE_INCLUDE_PATH +#define TRACE_INCLUDE_PATH . +#define TRACE_INCLUDE_FILE exceptions +#endif /* _TRACE_PAGE_FAULT_H */ + +/* This part must be outside protection */ +#include <trace/define_trace.h> diff --git a/arch/x86/include/asm/traps.h b/arch/x86/include/asm/traps.h index 7036cb60cd87..58d66fe06b61 100644 --- a/arch/x86/include/asm/traps.h +++ b/arch/x86/include/asm/traps.h @@ -37,6 +37,23 @@ asmlinkage void machine_check(void); #endif /* CONFIG_X86_MCE */ asmlinkage void simd_coprocessor_error(void); +#ifdef CONFIG_TRACING +asmlinkage void trace_page_fault(void); +#define trace_divide_error divide_error +#define trace_bounds bounds +#define trace_invalid_op invalid_op +#define trace_device_not_available device_not_available +#define trace_coprocessor_segment_overrun coprocessor_segment_overrun +#define trace_invalid_TSS invalid_TSS +#define trace_segment_not_present segment_not_present +#define trace_general_protection general_protection +#define trace_spurious_interrupt_bug spurious_interrupt_bug +#define trace_coprocessor_error coprocessor_error +#define trace_alignment_check alignment_check +#define trace_simd_coprocessor_error simd_coprocessor_error +#define trace_async_page_fault async_page_fault +#endif + dotraplinkage void do_divide_error(struct pt_regs *, long); dotraplinkage void do_debug(struct pt_regs *, long); dotraplinkage void do_nmi(struct pt_regs *, long); @@ -55,6 +72,9 @@ asmlinkage __kprobes struct pt_regs *sync_regs(struct pt_regs *); #endif dotraplinkage void do_general_protection(struct pt_regs *, long); dotraplinkage void do_page_fault(struct pt_regs *, unsigned long); +#ifdef CONFIG_TRACING +dotraplinkage void trace_do_page_fault(struct pt_regs *, unsigned long); +#endif dotraplinkage void do_spurious_interrupt_bug(struct pt_regs *, long); dotraplinkage void do_coprocessor_error(struct pt_regs *, long); dotraplinkage void do_alignment_check(struct pt_regs *, long); diff --git a/arch/x86/include/asm/x86_init.h b/arch/x86/include/asm/x86_init.h index 828a1565ba57..0f1be11e43d2 100644 --- a/arch/x86/include/asm/x86_init.h +++ b/arch/x86/include/asm/x86_init.h @@ -172,6 +172,7 @@ struct x86_platform_ops { struct pci_dev; struct msi_msg; +struct msi_desc; struct x86_msi_ops { int (*setup_msi_irqs)(struct pci_dev *dev, int nvec, int type); @@ -182,6 +183,8 @@ struct x86_msi_ops { void (*teardown_msi_irqs)(struct pci_dev *dev); void (*restore_msi_irqs)(struct pci_dev *dev, int irq); int (*setup_hpet_msi)(unsigned int irq, unsigned int id); + u32 (*msi_mask_irq)(struct msi_desc *desc, u32 mask, u32 flag); + u32 (*msix_mask_irq)(struct msi_desc *desc, u32 flag); }; struct IO_APIC_route_entry; diff --git a/arch/x86/kernel/acpi/boot.c b/arch/x86/kernel/acpi/boot.c index 40c76604199f..6c0b43bd024b 100644 --- a/arch/x86/kernel/acpi/boot.c +++ b/arch/x86/kernel/acpi/boot.c @@ -189,24 +189,31 @@ static int __init acpi_parse_madt(struct acpi_table_header *table) return 0; } -static void acpi_register_lapic(int id, u8 enabled) +/** + * acpi_register_lapic - register a local apic and generates a logic cpu number + * @id: local apic id to register + * @enabled: this cpu is enabled or not + * + * Returns the logic cpu number which maps to the local apic + */ +static int acpi_register_lapic(int id, u8 enabled) { unsigned int ver = 0; if (id >= MAX_LOCAL_APIC) { printk(KERN_INFO PREFIX "skipped apicid that is too big\n"); - return; + return -EINVAL; } if (!enabled) { ++disabled_cpus; - return; + return -EINVAL; } if (boot_cpu_physical_apicid != -1U) ver = apic_version[boot_cpu_physical_apicid]; - generic_processor_info(id, ver); + return generic_processor_info(id, ver); } static int __init @@ -614,84 +621,27 @@ static void acpi_map_cpu2node(acpi_handle handle, int cpu, int physid) #endif } -static int _acpi_map_lsapic(acpi_handle handle, int *pcpu) +static int _acpi_map_lsapic(acpi_handle handle, int physid, int *pcpu) { - struct acpi_buffer buffer = { ACPI_ALLOCATE_BUFFER, NULL }; - union acpi_object *obj; - struct acpi_madt_local_apic *lapic; - cpumask_var_t tmp_map, new_map; - u8 physid; int cpu; - int retval = -ENOMEM; - - if (ACPI_FAILURE(acpi_evaluate_object(handle, "_MAT", NULL, &buffer))) - return -EINVAL; - - if (!buffer.length || !buffer.pointer) - return -EINVAL; - - obj = buffer.pointer; - if (obj->type != ACPI_TYPE_BUFFER || - obj->buffer.length < sizeof(*lapic)) { - kfree(buffer.pointer); - return -EINVAL; - } - lapic = (struct acpi_madt_local_apic *)obj->buffer.pointer; - - if (lapic->header.type != ACPI_MADT_TYPE_LOCAL_APIC || - !(lapic->lapic_flags & ACPI_MADT_ENABLED)) { - kfree(buffer.pointer); - return -EINVAL; - } - - physid = lapic->id; - - kfree(buffer.pointer); - buffer.length = ACPI_ALLOCATE_BUFFER; - buffer.pointer = NULL; - lapic = NULL; - - if (!alloc_cpumask_var(&tmp_map, GFP_KERNEL)) - goto out; - - if (!alloc_cpumask_var(&new_map, GFP_KERNEL)) - goto free_tmp_map; - - cpumask_copy(tmp_map, cpu_present_mask); - acpi_register_lapic(physid, ACPI_MADT_ENABLED); - - /* - * If acpi_register_lapic successfully generates a new logical cpu - * number, then the following will get us exactly what was mapped - */ - cpumask_andnot(new_map, cpu_present_mask, tmp_map); - if (cpumask_empty(new_map)) { - printk ("Unable to map lapic to logical cpu number\n"); - retval = -EINVAL; - goto free_new_map; + cpu = acpi_register_lapic(physid, ACPI_MADT_ENABLED); + if (cpu < 0) { + pr_info(PREFIX "Unable to map lapic to logical cpu number\n"); + return cpu; } acpi_processor_set_pdc(handle); - - cpu = cpumask_first(new_map); acpi_map_cpu2node(handle, cpu, physid); *pcpu = cpu; - retval = 0; - -free_new_map: - free_cpumask_var(new_map); -free_tmp_map: - free_cpumask_var(tmp_map); -out: - return retval; + return 0; } /* wrapper to silence section mismatch warning */ -int __ref acpi_map_lsapic(acpi_handle handle, int *pcpu) +int __ref acpi_map_lsapic(acpi_handle handle, int physid, int *pcpu) { - return _acpi_map_lsapic(handle, pcpu); + return _acpi_map_lsapic(handle, physid, pcpu); } EXPORT_SYMBOL(acpi_map_lsapic); @@ -745,7 +695,7 @@ static int __init acpi_parse_sbf(struct acpi_table_header *table) #ifdef CONFIG_HPET_TIMER #include <asm/hpet.h> -static struct __initdata resource *hpet_res; +static struct resource *hpet_res __initdata; static int __init acpi_parse_hpet(struct acpi_table_header *table) { diff --git a/arch/x86/kernel/acpi/sleep.c b/arch/x86/kernel/acpi/sleep.c index 33120100ff5e..3a2ae4c88948 100644 --- a/arch/x86/kernel/acpi/sleep.c +++ b/arch/x86/kernel/acpi/sleep.c @@ -26,6 +26,17 @@ static char temp_stack[4096]; #endif /** + * x86_acpi_enter_sleep_state - enter sleep state + * @state: Sleep state to enter. + * + * Wrapper around acpi_enter_sleep_state() to be called by assmebly. + */ +acpi_status asmlinkage x86_acpi_enter_sleep_state(u8 state) +{ + return acpi_enter_sleep_state(state); +} + +/** * x86_acpi_suspend_lowlevel - save kernel state * * Create an identity mapped page table and copy the wakeup routine to diff --git a/arch/x86/kernel/acpi/sleep.h b/arch/x86/kernel/acpi/sleep.h index c9c2c982d5e4..65c7b606b606 100644 --- a/arch/x86/kernel/acpi/sleep.h +++ b/arch/x86/kernel/acpi/sleep.h @@ -17,3 +17,5 @@ extern void wakeup_long64(void); extern void do_suspend_lowlevel(void); extern int x86_acpi_suspend_lowlevel(void); + +acpi_status asmlinkage x86_acpi_enter_sleep_state(u8 state); diff --git a/arch/x86/kernel/acpi/wakeup_32.S b/arch/x86/kernel/acpi/wakeup_32.S index d1daa66ab162..665c6b7d2ea9 100644 --- a/arch/x86/kernel/acpi/wakeup_32.S +++ b/arch/x86/kernel/acpi/wakeup_32.S @@ -73,7 +73,7 @@ ENTRY(do_suspend_lowlevel) call save_processor_state call save_registers pushl $3 - call acpi_enter_sleep_state + call x86_acpi_enter_sleep_state addl $4, %esp # In case of S3 failure, we'll emerge here. Jump diff --git a/arch/x86/kernel/acpi/wakeup_64.S b/arch/x86/kernel/acpi/wakeup_64.S index 8ea5164cbd04..ae693b51ed8e 100644 --- a/arch/x86/kernel/acpi/wakeup_64.S +++ b/arch/x86/kernel/acpi/wakeup_64.S @@ -73,7 +73,7 @@ ENTRY(do_suspend_lowlevel) addq $8, %rsp movl $3, %edi xorl %eax, %eax - call acpi_enter_sleep_state + call x86_acpi_enter_sleep_state /* in case something went wrong, restore the machine status and go on */ jmp resume_point diff --git a/arch/x86/kernel/alternative.c b/arch/x86/kernel/alternative.c index 15e8563e5c24..df94598ad05a 100644 --- a/arch/x86/kernel/alternative.c +++ b/arch/x86/kernel/alternative.c @@ -402,17 +402,6 @@ void alternatives_enable_smp(void) { struct smp_alt_module *mod; -#ifdef CONFIG_LOCKDEP - /* - * Older binutils section handling bug prevented - * alternatives-replacement from working reliably. - * - * If this still occurs then you should see a hang - * or crash shortly after this line: - */ - pr_info("lockdep: fixing up alternatives\n"); -#endif - /* Why bother if there are no other CPUs? */ BUG_ON(num_possible_cpus() == 1); diff --git a/arch/x86/kernel/apic/apic.c b/arch/x86/kernel/apic/apic.c index a7eb82d9b012..ed165d657380 100644 --- a/arch/x86/kernel/apic/apic.c +++ b/arch/x86/kernel/apic/apic.c @@ -2107,7 +2107,7 @@ void disconnect_bsp_APIC(int virt_wire_setup) apic_write(APIC_LVT1, value); } -void generic_processor_info(int apicid, int version) +int generic_processor_info(int apicid, int version) { int cpu, max = nr_cpu_ids; bool boot_cpu_detected = physid_isset(boot_cpu_physical_apicid, @@ -2127,7 +2127,7 @@ void generic_processor_info(int apicid, int version) " Processor %d/0x%x ignored.\n", max, thiscpu, apicid); disabled_cpus++; - return; + return -ENODEV; } if (num_processors >= nr_cpu_ids) { @@ -2138,7 +2138,7 @@ void generic_processor_info(int apicid, int version) " Processor %d/0x%x ignored.\n", max, thiscpu, apicid); disabled_cpus++; - return; + return -EINVAL; } num_processors++; @@ -2183,6 +2183,8 @@ void generic_processor_info(int apicid, int version) #endif set_cpu_possible(cpu, true); set_cpu_present(cpu, true); + + return cpu; } int hard_smp_processor_id(void) diff --git a/arch/x86/kernel/devicetree.c b/arch/x86/kernel/devicetree.c index 376dc7873447..d35078ea1446 100644 --- a/arch/x86/kernel/devicetree.c +++ b/arch/x86/kernel/devicetree.c @@ -20,22 +20,13 @@ #include <asm/hpet.h> #include <asm/apic.h> #include <asm/pci_x86.h> +#include <asm/setup.h> __initdata u64 initial_dtb; char __initdata cmd_line[COMMAND_LINE_SIZE]; int __initdata of_ioapic; -unsigned long pci_address_to_pio(phys_addr_t address) -{ - /* - * The ioport address can be directly used by inX / outX - */ - BUG_ON(address >= (1 << 16)); - return (unsigned long)address; -} -EXPORT_SYMBOL_GPL(pci_address_to_pio); - void __init early_init_dt_scan_chosen_arch(unsigned long node) { BUG(); @@ -51,15 +42,6 @@ void * __init early_init_dt_alloc_memory_arch(u64 size, u64 align) return __alloc_bootmem(size, align, __pa(MAX_DMA_ADDRESS)); } -#ifdef CONFIG_BLK_DEV_INITRD -void __init early_init_dt_setup_initrd_arch(u64 start, u64 end) -{ - initrd_start = (unsigned long)__va(start); - initrd_end = (unsigned long)__va(end); - initrd_below_start_ok = 1; -} -#endif - void __init add_dtb(u64 data) { initial_dtb = data + offsetof(struct setup_data, data); @@ -105,7 +87,6 @@ struct device_node *pcibios_get_phb_of_node(struct pci_bus *bus) static int x86_of_pci_irq_enable(struct pci_dev *dev) { - struct of_irq oirq; u32 virq; int ret; u8 pin; @@ -116,12 +97,7 @@ static int x86_of_pci_irq_enable(struct pci_dev *dev) if (!pin) return 0; - ret = of_irq_map_pci(dev, &oirq); - if (ret) - return ret; - - virq = irq_create_of_mapping(oirq.controller, oirq.specifier, - oirq.size); + virq = of_irq_parse_and_map_pci(dev, 0, 0); if (virq == 0) return -EINVAL; dev->irq = virq; @@ -230,7 +206,7 @@ static void __init dtb_apic_setup(void) static void __init x86_flattree_get_config(void) { u32 size, map_len; - void *new_dtb; + struct boot_param_header *dt; if (!initial_dtb) return; @@ -238,24 +214,17 @@ static void __init x86_flattree_get_config(void) map_len = max(PAGE_SIZE - (initial_dtb & ~PAGE_MASK), (u64)sizeof(struct boot_param_header)); - initial_boot_params = early_memremap(initial_dtb, map_len); - size = be32_to_cpu(initial_boot_params->totalsize); + dt = early_memremap(initial_dtb, map_len); + size = be32_to_cpu(dt->totalsize); if (map_len < size) { - early_iounmap(initial_boot_params, map_len); - initial_boot_params = early_memremap(initial_dtb, size); + early_iounmap(dt, map_len); + dt = early_memremap(initial_dtb, size); map_len = size; } - new_dtb = alloc_bootmem(size); - memcpy(new_dtb, initial_boot_params, size); - early_iounmap(initial_boot_params, map_len); - - initial_boot_params = new_dtb; - - /* root level address cells */ - of_scan_flat_dt(early_init_dt_scan_root, NULL); - - unflatten_device_tree(); + initial_boot_params = dt; + unflatten_and_copy_device_tree(); + early_iounmap(dt, map_len); } #else static inline void x86_flattree_get_config(void) { } diff --git a/arch/x86/kernel/entry_32.S b/arch/x86/kernel/entry_32.S index fd1bc1b15e6d..51e2988c5728 100644 --- a/arch/x86/kernel/entry_32.S +++ b/arch/x86/kernel/entry_32.S @@ -1244,6 +1244,16 @@ return_to_handler: */ .pushsection .kprobes.text, "ax" +#ifdef CONFIG_TRACING +ENTRY(trace_page_fault) + RING0_EC_FRAME + ASM_CLAC + pushl_cfi $trace_do_page_fault + jmp error_code + CFI_ENDPROC +END(trace_page_fault) +#endif + ENTRY(page_fault) RING0_EC_FRAME ASM_CLAC diff --git a/arch/x86/kernel/entry_64.S b/arch/x86/kernel/entry_64.S index 603be7c70675..e21b0785a85b 100644 --- a/arch/x86/kernel/entry_64.S +++ b/arch/x86/kernel/entry_64.S @@ -1278,6 +1278,17 @@ ENTRY(\sym) END(\sym) .endm +#ifdef CONFIG_TRACING +.macro trace_errorentry sym do_sym +errorentry trace(\sym) trace(\do_sym) +errorentry \sym \do_sym +.endm +#else +.macro trace_errorentry sym do_sym +errorentry \sym \do_sym +.endm +#endif + /* error code is on the stack already */ .macro paranoiderrorentry sym do_sym ENTRY(\sym) @@ -1480,7 +1491,7 @@ zeroentry xen_int3 do_int3 errorentry xen_stack_segment do_stack_segment #endif errorentry general_protection do_general_protection -errorentry page_fault do_page_fault +trace_errorentry page_fault do_page_fault #ifdef CONFIG_KVM_GUEST errorentry async_page_fault do_async_page_fault #endif diff --git a/arch/x86/kernel/head64.c b/arch/x86/kernel/head64.c index 1be8e43b669e..85126ccbdf6b 100644 --- a/arch/x86/kernel/head64.c +++ b/arch/x86/kernel/head64.c @@ -162,7 +162,7 @@ asmlinkage void __init x86_64_start_kernel(char * real_mode_data) clear_bss(); for (i = 0; i < NUM_EXCEPTION_VECTORS; i++) - set_intr_gate(i, &early_idt_handlers[i]); + set_intr_gate(i, early_idt_handlers[i]); load_idt((const struct desc_ptr *)&idt_descr); copy_bootdata(__va(real_mode_data)); diff --git a/arch/x86/kernel/i387.c b/arch/x86/kernel/i387.c index 5d576ab34403..e8368c6dd2a2 100644 --- a/arch/x86/kernel/i387.c +++ b/arch/x86/kernel/i387.c @@ -100,7 +100,7 @@ void unlazy_fpu(struct task_struct *tsk) __save_init_fpu(tsk); __thread_fpu_end(tsk); } else - tsk->fpu_counter = 0; + tsk->thread.fpu_counter = 0; preempt_enable(); } EXPORT_SYMBOL(unlazy_fpu); diff --git a/arch/x86/kernel/jump_label.c b/arch/x86/kernel/jump_label.c index ee11b7dfbfbb..26d5a55a2736 100644 --- a/arch/x86/kernel/jump_label.c +++ b/arch/x86/kernel/jump_label.c @@ -42,15 +42,27 @@ static void __jump_label_transform(struct jump_entry *entry, int init) { union jump_code_union code; + const unsigned char default_nop[] = { STATIC_KEY_INIT_NOP }; const unsigned char *ideal_nop = ideal_nops[NOP_ATOMIC5]; if (type == JUMP_LABEL_ENABLE) { - /* - * We are enabling this jump label. If it is not a nop - * then something must have gone wrong. - */ - if (unlikely(memcmp((void *)entry->code, ideal_nop, 5) != 0)) - bug_at((void *)entry->code, __LINE__); + if (init) { + /* + * Jump label is enabled for the first time. + * So we expect a default_nop... + */ + if (unlikely(memcmp((void *)entry->code, default_nop, 5) + != 0)) + bug_at((void *)entry->code, __LINE__); + } else { + /* + * ...otherwise expect an ideal_nop. Otherwise + * something went horribly wrong. + */ + if (unlikely(memcmp((void *)entry->code, ideal_nop, 5) + != 0)) + bug_at((void *)entry->code, __LINE__); + } code.jump = 0xe9; code.offset = entry->target - @@ -63,7 +75,6 @@ static void __jump_label_transform(struct jump_entry *entry, * are converting the default nop to the ideal nop. */ if (init) { - const unsigned char default_nop[] = { STATIC_KEY_INIT_NOP }; if (unlikely(memcmp((void *)entry->code, default_nop, 5) != 0)) bug_at((void *)entry->code, __LINE__); } else { diff --git a/arch/x86/kernel/kvm.c b/arch/x86/kernel/kvm.c index b2046e4d0b59..6dd802c6d780 100644 --- a/arch/x86/kernel/kvm.c +++ b/arch/x86/kernel/kvm.c @@ -464,7 +464,7 @@ static struct notifier_block kvm_cpu_notifier = { static void __init kvm_apf_trap_init(void) { - set_intr_gate(14, &async_page_fault); + set_intr_gate(14, async_page_fault); } void __init kvm_guest_init(void) diff --git a/arch/x86/kernel/module.c b/arch/x86/kernel/module.c index 216a4d754b0c..18be189368bb 100644 --- a/arch/x86/kernel/module.c +++ b/arch/x86/kernel/module.c @@ -49,7 +49,7 @@ void *module_alloc(unsigned long size) return NULL; return __vmalloc_node_range(size, 1, MODULES_VADDR, MODULES_END, GFP_KERNEL | __GFP_HIGHMEM, PAGE_KERNEL_EXEC, - -1, __builtin_return_address(0)); + NUMA_NO_NODE, __builtin_return_address(0)); } #ifdef CONFIG_X86_32 diff --git a/arch/x86/kernel/process_32.c b/arch/x86/kernel/process_32.c index c2ec1aa6d454..6f1236c29c4b 100644 --- a/arch/x86/kernel/process_32.c +++ b/arch/x86/kernel/process_32.c @@ -153,7 +153,7 @@ int copy_thread(unsigned long clone_flags, unsigned long sp, childregs->orig_ax = -1; childregs->cs = __KERNEL_CS | get_kernel_rpl(); childregs->flags = X86_EFLAGS_IF | X86_EFLAGS_FIXED; - p->fpu_counter = 0; + p->thread.fpu_counter = 0; p->thread.io_bitmap_ptr = NULL; memset(p->thread.ptrace_bps, 0, sizeof(p->thread.ptrace_bps)); return 0; @@ -166,7 +166,7 @@ int copy_thread(unsigned long clone_flags, unsigned long sp, p->thread.ip = (unsigned long) ret_from_fork; task_user_gs(p) = get_user_gs(current_pt_regs()); - p->fpu_counter = 0; + p->thread.fpu_counter = 0; p->thread.io_bitmap_ptr = NULL; tsk = current; err = -ENOMEM; diff --git a/arch/x86/kernel/process_64.c b/arch/x86/kernel/process_64.c index 176ad94e1d57..9c0280f93d05 100644 --- a/arch/x86/kernel/process_64.c +++ b/arch/x86/kernel/process_64.c @@ -163,7 +163,7 @@ int copy_thread(unsigned long clone_flags, unsigned long sp, p->thread.sp = (unsigned long) childregs; p->thread.usersp = me->thread.usersp; set_tsk_thread_flag(p, TIF_FORK); - p->fpu_counter = 0; + p->thread.fpu_counter = 0; p->thread.io_bitmap_ptr = NULL; savesegment(gs, p->thread.gsindex); diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c index 918d489fa53d..cb233bc9dee3 100644 --- a/arch/x86/kernel/setup.c +++ b/arch/x86/kernel/setup.c @@ -1121,8 +1121,6 @@ void __init setup_arch(char **cmdline_p) acpi_initrd_override((void *)initrd_start, initrd_end - initrd_start); #endif - reserve_crashkernel(); - vsmp_init(); io_delay_init(); @@ -1135,6 +1133,13 @@ void __init setup_arch(char **cmdline_p) early_acpi_boot_init(); initmem_init(); + + /* + * Reserve memory for crash kernel after SRAT is parsed so that it + * won't consume hotpluggable memory. + */ + reserve_crashkernel(); + memblock_find_dma_reserve(); #ifdef CONFIG_KVM_GUEST diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c index 2a165580fa16..85dc05a3aa02 100644 --- a/arch/x86/kernel/smpboot.c +++ b/arch/x86/kernel/smpboot.c @@ -81,27 +81,6 @@ /* State of each CPU */ DEFINE_PER_CPU(int, cpu_state) = { 0 }; -#ifdef CONFIG_HOTPLUG_CPU -/* - * We need this for trampoline_base protection from concurrent accesses when - * off- and onlining cores wildly. - */ -static DEFINE_MUTEX(x86_cpu_hotplug_driver_mutex); - -void cpu_hotplug_driver_lock(void) -{ - mutex_lock(&x86_cpu_hotplug_driver_mutex); -} - -void cpu_hotplug_driver_unlock(void) -{ - mutex_unlock(&x86_cpu_hotplug_driver_mutex); -} - -ssize_t arch_cpu_probe(const char *buf, size_t count) { return -1; } -ssize_t arch_cpu_release(const char *buf, size_t count) { return -1; } -#endif - /* Number of siblings per CPU package */ int smp_num_siblings = 1; EXPORT_SYMBOL(smp_num_siblings); diff --git a/arch/x86/kernel/topology.c b/arch/x86/kernel/topology.c index 6e60b5fe2244..649b010da00b 100644 --- a/arch/x86/kernel/topology.c +++ b/arch/x86/kernel/topology.c @@ -65,29 +65,32 @@ int __ref _debug_hotplug_cpu(int cpu, int action) if (!cpu_is_hotpluggable(cpu)) return -EINVAL; - cpu_hotplug_driver_lock(); + lock_device_hotplug(); switch (action) { case 0: ret = cpu_down(cpu); if (!ret) { pr_info("CPU %u is now offline\n", cpu); + dev->offline = true; kobject_uevent(&dev->kobj, KOBJ_OFFLINE); } else pr_debug("Can't offline CPU%d.\n", cpu); break; case 1: ret = cpu_up(cpu); - if (!ret) + if (!ret) { + dev->offline = false; kobject_uevent(&dev->kobj, KOBJ_ONLINE); - else + } else { pr_debug("Can't online CPU%d.\n", cpu); + } break; default: ret = -EINVAL; } - cpu_hotplug_driver_unlock(); + unlock_device_hotplug(); return ret; } diff --git a/arch/x86/kernel/traps.c b/arch/x86/kernel/traps.c index 729aa779ff75..b857ed890b4c 100644 --- a/arch/x86/kernel/traps.c +++ b/arch/x86/kernel/traps.c @@ -653,7 +653,7 @@ void math_state_restore(void) return; } - tsk->fpu_counter++; + tsk->thread.fpu_counter++; } EXPORT_SYMBOL_GPL(math_state_restore); @@ -713,7 +713,7 @@ void __init early_trap_init(void) /* int3 can be called from all */ set_system_intr_gate_ist(X86_TRAP_BP, &int3, DEBUG_STACK); #ifdef CONFIG_X86_32 - set_intr_gate(X86_TRAP_PF, &page_fault); + set_intr_gate(X86_TRAP_PF, page_fault); #endif load_idt(&idt_descr); } @@ -721,7 +721,7 @@ void __init early_trap_init(void) void __init early_trap_pf_init(void) { #ifdef CONFIG_X86_64 - set_intr_gate(X86_TRAP_PF, &page_fault); + set_intr_gate(X86_TRAP_PF, page_fault); #endif } @@ -737,30 +737,30 @@ void __init trap_init(void) early_iounmap(p, 4); #endif - set_intr_gate(X86_TRAP_DE, ÷_error); + set_intr_gate(X86_TRAP_DE, divide_error); set_intr_gate_ist(X86_TRAP_NMI, &nmi, NMI_STACK); /* int4 can be called from all */ set_system_intr_gate(X86_TRAP_OF, &overflow); - set_intr_gate(X86_TRAP_BR, &bounds); - set_intr_gate(X86_TRAP_UD, &invalid_op); - set_intr_gate(X86_TRAP_NM, &device_not_available); + set_intr_gate(X86_TRAP_BR, bounds); + set_intr_gate(X86_TRAP_UD, invalid_op); + set_intr_gate(X86_TRAP_NM, device_not_available); #ifdef CONFIG_X86_32 set_task_gate(X86_TRAP_DF, GDT_ENTRY_DOUBLEFAULT_TSS); #else set_intr_gate_ist(X86_TRAP_DF, &double_fault, DOUBLEFAULT_STACK); #endif - set_intr_gate(X86_TRAP_OLD_MF, &coprocessor_segment_overrun); - set_intr_gate(X86_TRAP_TS, &invalid_TSS); - set_intr_gate(X86_TRAP_NP, &segment_not_present); + set_intr_gate(X86_TRAP_OLD_MF, coprocessor_segment_overrun); + set_intr_gate(X86_TRAP_TS, invalid_TSS); + set_intr_gate(X86_TRAP_NP, segment_not_present); set_intr_gate_ist(X86_TRAP_SS, &stack_segment, STACKFAULT_STACK); - set_intr_gate(X86_TRAP_GP, &general_protection); - set_intr_gate(X86_TRAP_SPURIOUS, &spurious_interrupt_bug); - set_intr_gate(X86_TRAP_MF, &coprocessor_error); - set_intr_gate(X86_TRAP_AC, &alignment_check); + set_intr_gate(X86_TRAP_GP, general_protection); + set_intr_gate(X86_TRAP_SPURIOUS, spurious_interrupt_bug); + set_intr_gate(X86_TRAP_MF, coprocessor_error); + set_intr_gate(X86_TRAP_AC, alignment_check); #ifdef CONFIG_X86_MCE set_intr_gate_ist(X86_TRAP_MC, &machine_check, MCE_STACK); #endif - set_intr_gate(X86_TRAP_XF, &simd_coprocessor_error); + set_intr_gate(X86_TRAP_XF, simd_coprocessor_error); /* Reserve all the builtin and the syscall vector: */ for (i = 0; i < FIRST_EXTERNAL_VECTOR; i++) diff --git a/arch/x86/kernel/x86_init.c b/arch/x86/kernel/x86_init.c index 8ce0072cd700..021783b1f46a 100644 --- a/arch/x86/kernel/x86_init.c +++ b/arch/x86/kernel/x86_init.c @@ -116,6 +116,8 @@ struct x86_msi_ops x86_msi = { .teardown_msi_irqs = default_teardown_msi_irqs, .restore_msi_irqs = default_restore_msi_irqs, .setup_hpet_msi = default_setup_hpet_msi, + .msi_mask_irq = default_msi_mask_irq, + .msix_mask_irq = default_msix_mask_irq, }; /* MSI arch specific hooks */ @@ -138,6 +140,14 @@ void arch_restore_msi_irqs(struct pci_dev *dev, int irq) { x86_msi.restore_msi_irqs(dev, irq); } +u32 arch_msi_mask_irq(struct msi_desc *desc, u32 mask, u32 flag) +{ + return x86_msi.msi_mask_irq(desc, mask, flag); +} +u32 arch_msix_mask_irq(struct msi_desc *desc, u32 flag) +{ + return x86_msi.msix_mask_irq(desc, flag); +} #endif struct x86_io_apic_ops x86_io_apic_ops = { diff --git a/arch/x86/lib/msr-smp.c b/arch/x86/lib/msr-smp.c index a6b1b86d2253..518532e6a3fa 100644 --- a/arch/x86/lib/msr-smp.c +++ b/arch/x86/lib/msr-smp.c @@ -47,6 +47,21 @@ int rdmsr_on_cpu(unsigned int cpu, u32 msr_no, u32 *l, u32 *h) } EXPORT_SYMBOL(rdmsr_on_cpu); +int rdmsrl_on_cpu(unsigned int cpu, u32 msr_no, u64 *q) +{ + int err; + struct msr_info rv; + + memset(&rv, 0, sizeof(rv)); + + rv.msr_no = msr_no; + err = smp_call_function_single(cpu, __rdmsr_on_cpu, &rv, 1); + *q = rv.reg.q; + + return err; +} +EXPORT_SYMBOL(rdmsrl_on_cpu); + int wrmsr_on_cpu(unsigned int cpu, u32 msr_no, u32 l, u32 h) { int err; @@ -63,6 +78,22 @@ int wrmsr_on_cpu(unsigned int cpu, u32 msr_no, u32 l, u32 h) } EXPORT_SYMBOL(wrmsr_on_cpu); +int wrmsrl_on_cpu(unsigned int cpu, u32 msr_no, u64 q) +{ + int err; + struct msr_info rv; + + memset(&rv, 0, sizeof(rv)); + + rv.msr_no = msr_no; + rv.reg.q = q; + + err = smp_call_function_single(cpu, __wrmsr_on_cpu, &rv, 1); + + return err; +} +EXPORT_SYMBOL(wrmsrl_on_cpu); + static void __rwmsr_on_cpus(const struct cpumask *mask, u32 msr_no, struct msr *msrs, void (*msr_func) (void *info)) @@ -159,6 +190,37 @@ int wrmsr_safe_on_cpu(unsigned int cpu, u32 msr_no, u32 l, u32 h) } EXPORT_SYMBOL(wrmsr_safe_on_cpu); +int wrmsrl_safe_on_cpu(unsigned int cpu, u32 msr_no, u64 q) +{ + int err; + struct msr_info rv; + + memset(&rv, 0, sizeof(rv)); + + rv.msr_no = msr_no; + rv.reg.q = q; + + err = smp_call_function_single(cpu, __wrmsr_safe_on_cpu, &rv, 1); + + return err ? err : rv.err; +} +EXPORT_SYMBOL(wrmsrl_safe_on_cpu); + +int rdmsrl_safe_on_cpu(unsigned int cpu, u32 msr_no, u64 *q) +{ + int err; + struct msr_info rv; + + memset(&rv, 0, sizeof(rv)); + + rv.msr_no = msr_no; + err = smp_call_function_single(cpu, __rdmsr_safe_on_cpu, &rv, 1); + *q = rv.reg.q; + + return err ? err : rv.err; +} +EXPORT_SYMBOL(rdmsrl_safe_on_cpu); + /* * These variants are significantly slower, but allows control over * the entire 32-bit GPR set. diff --git a/arch/x86/mm/Makefile b/arch/x86/mm/Makefile index 23d8e5fecf76..6a19ad9f370d 100644 --- a/arch/x86/mm/Makefile +++ b/arch/x86/mm/Makefile @@ -6,6 +6,8 @@ nostackp := $(call cc-option, -fno-stack-protector) CFLAGS_physaddr.o := $(nostackp) CFLAGS_setup_nx.o := $(nostackp) +CFLAGS_fault.o := -I$(src)/../include/asm/trace + obj-$(CONFIG_X86_PAT) += pat_rbtree.o obj-$(CONFIG_SMP) += tlb.o diff --git a/arch/x86/mm/fault.c b/arch/x86/mm/fault.c index e7e1cac74e8d..9ff85bb8dd69 100644 --- a/arch/x86/mm/fault.c +++ b/arch/x86/mm/fault.c @@ -20,6 +20,9 @@ #include <asm/kmemcheck.h> /* kmemcheck_*(), ... */ #include <asm/fixmap.h> /* VSYSCALL_START */ +#define CREATE_TRACE_POINTS +#include <asm/trace/exceptions.h> + /* * Page fault error code bits: * @@ -1232,3 +1235,23 @@ do_page_fault(struct pt_regs *regs, unsigned long error_code) __do_page_fault(regs, error_code); exception_exit(prev_state); } + +static void trace_page_fault_entries(struct pt_regs *regs, + unsigned long error_code) +{ + if (user_mode(regs)) + trace_page_fault_user(read_cr2(), regs, error_code); + else + trace_page_fault_kernel(read_cr2(), regs, error_code); +} + +dotraplinkage void __kprobes +trace_do_page_fault(struct pt_regs *regs, unsigned long error_code) +{ + enum ctx_state prev_state; + + prev_state = exception_enter(); + trace_page_fault_entries(regs, error_code); + __do_page_fault(regs, error_code); + exception_exit(prev_state); +} diff --git a/arch/x86/mm/init.c b/arch/x86/mm/init.c index ce32017c5e38..f97130618113 100644 --- a/arch/x86/mm/init.c +++ b/arch/x86/mm/init.c @@ -53,12 +53,12 @@ __ref void *alloc_low_pages(unsigned int num) if ((pgt_buf_end + num) > pgt_buf_top || !can_use_brk_pgt) { unsigned long ret; if (min_pfn_mapped >= max_pfn_mapped) - panic("alloc_low_page: ran out of memory"); + panic("alloc_low_pages: ran out of memory"); ret = memblock_find_in_range(min_pfn_mapped << PAGE_SHIFT, max_pfn_mapped << PAGE_SHIFT, PAGE_SIZE * num , PAGE_SIZE); if (!ret) - panic("alloc_low_page: can not alloc memory"); + panic("alloc_low_pages: can not alloc memory"); memblock_reserve(ret, PAGE_SIZE * num); pfn = ret >> PAGE_SHIFT; } else { @@ -418,27 +418,27 @@ static unsigned long __init get_new_step_size(unsigned long step_size) return step_size << 5; } -void __init init_mem_mapping(void) +/** + * memory_map_top_down - Map [map_start, map_end) top down + * @map_start: start address of the target memory range + * @map_end: end address of the target memory range + * + * This function will setup direct mapping for memory range + * [map_start, map_end) in top-down. That said, the page tables + * will be allocated at the end of the memory, and we map the + * memory in top-down. + */ +static void __init memory_map_top_down(unsigned long map_start, + unsigned long map_end) { - unsigned long end, real_end, start, last_start; + unsigned long real_end, start, last_start; unsigned long step_size; unsigned long addr; unsigned long mapped_ram_size = 0; unsigned long new_mapped_ram_size; - probe_page_size_mask(); - -#ifdef CONFIG_X86_64 - end = max_pfn << PAGE_SHIFT; -#else - end = max_low_pfn << PAGE_SHIFT; -#endif - - /* the ISA range is always mapped regardless of memory holes */ - init_memory_mapping(0, ISA_END_ADDRESS); - /* xen has big range in reserved near end of ram, skip it at first.*/ - addr = memblock_find_in_range(ISA_END_ADDRESS, end, PMD_SIZE, PMD_SIZE); + addr = memblock_find_in_range(map_start, map_end, PMD_SIZE, PMD_SIZE); real_end = addr + PMD_SIZE; /* step_size need to be small so pgt_buf from BRK could cover it */ @@ -453,13 +453,13 @@ void __init init_mem_mapping(void) * end of RAM in [min_pfn_mapped, max_pfn_mapped) used as new pages * for page table. */ - while (last_start > ISA_END_ADDRESS) { + while (last_start > map_start) { if (last_start > step_size) { start = round_down(last_start - 1, step_size); - if (start < ISA_END_ADDRESS) - start = ISA_END_ADDRESS; + if (start < map_start) + start = map_start; } else - start = ISA_END_ADDRESS; + start = map_start; new_mapped_ram_size = init_range_memory_mapping(start, last_start); last_start = start; @@ -470,8 +470,89 @@ void __init init_mem_mapping(void) mapped_ram_size += new_mapped_ram_size; } - if (real_end < end) - init_range_memory_mapping(real_end, end); + if (real_end < map_end) + init_range_memory_mapping(real_end, map_end); +} + +/** + * memory_map_bottom_up - Map [map_start, map_end) bottom up + * @map_start: start address of the target memory range + * @map_end: end address of the target memory range + * + * This function will setup direct mapping for memory range + * [map_start, map_end) in bottom-up. Since we have limited the + * bottom-up allocation above the kernel, the page tables will + * be allocated just above the kernel and we map the memory + * in [map_start, map_end) in bottom-up. + */ +static void __init memory_map_bottom_up(unsigned long map_start, + unsigned long map_end) +{ + unsigned long next, new_mapped_ram_size, start; + unsigned long mapped_ram_size = 0; + /* step_size need to be small so pgt_buf from BRK could cover it */ + unsigned long step_size = PMD_SIZE; + + start = map_start; + min_pfn_mapped = start >> PAGE_SHIFT; + + /* + * We start from the bottom (@map_start) and go to the top (@map_end). + * The memblock_find_in_range() gets us a block of RAM from the + * end of RAM in [min_pfn_mapped, max_pfn_mapped) used as new pages + * for page table. + */ + while (start < map_end) { + if (map_end - start > step_size) { + next = round_up(start + 1, step_size); + if (next > map_end) + next = map_end; + } else + next = map_end; + + new_mapped_ram_size = init_range_memory_mapping(start, next); + start = next; + + if (new_mapped_ram_size > mapped_ram_size) + step_size = get_new_step_size(step_size); + mapped_ram_size += new_mapped_ram_size; + } +} + +void __init init_mem_mapping(void) +{ + unsigned long end; + + probe_page_size_mask(); + +#ifdef CONFIG_X86_64 + end = max_pfn << PAGE_SHIFT; +#else + end = max_low_pfn << PAGE_SHIFT; +#endif + + /* the ISA range is always mapped regardless of memory holes */ + init_memory_mapping(0, ISA_END_ADDRESS); + + /* + * If the allocation is in bottom-up direction, we setup direct mapping + * in bottom-up, otherwise we setup direct mapping in top-down. + */ + if (memblock_bottom_up()) { + unsigned long kernel_end = __pa_symbol(_end); + + /* + * we need two separate calls here. This is because we want to + * allocate page tables above the kernel. So we first map + * [kernel_end, end) to make memory above the kernel be mapped + * as soon as possible. And then use page tables allocated above + * the kernel to map [ISA_END_ADDRESS, kernel_end). + */ + memory_map_bottom_up(kernel_end, end); + memory_map_bottom_up(ISA_END_ADDRESS, kernel_end); + } else { + memory_map_top_down(ISA_END_ADDRESS, end); + } #ifdef CONFIG_X86_64 if (max_pfn > max_low_pfn) { diff --git a/arch/x86/mm/numa.c b/arch/x86/mm/numa.c index 8bf93bae1f13..24aec58d6afd 100644 --- a/arch/x86/mm/numa.c +++ b/arch/x86/mm/numa.c @@ -567,6 +567,17 @@ static int __init numa_init(int (*init_func)(void)) ret = init_func(); if (ret < 0) return ret; + + /* + * We reset memblock back to the top-down direction + * here because if we configured ACPI_NUMA, we have + * parsed SRAT in init_func(). It is ok to have the + * reset here even if we did't configure ACPI_NUMA + * or acpi numa init fails and fallbacks to dummy + * numa init. + */ + memblock_set_bottom_up(false); + ret = numa_cleanup_meminfo(&numa_meminfo); if (ret < 0) return ret; diff --git a/arch/x86/net/bpf_jit_comp.c b/arch/x86/net/bpf_jit_comp.c index 516593e1ce33..26328e800869 100644 --- a/arch/x86/net/bpf_jit_comp.c +++ b/arch/x86/net/bpf_jit_comp.c @@ -788,5 +788,7 @@ void bpf_jit_free(struct sk_filter *fp) if (fp->bpf_func != sk_run_filter) { INIT_WORK(&fp->work, bpf_jit_free_deferred); schedule_work(&fp->work); + } else { + kfree(fp); } } diff --git a/arch/x86/pci/acpi.c b/arch/x86/pci/acpi.c index b30e937689d6..7fb24e53d4c8 100644 --- a/arch/x86/pci/acpi.c +++ b/arch/x86/pci/acpi.c @@ -354,12 +354,12 @@ static void coalesce_windows(struct pci_root_info *info, unsigned long type) * the kernel resource tree doesn't allow overlaps. */ if (resource_overlaps(res1, res2)) { - res1->start = min(res1->start, res2->start); - res1->end = max(res1->end, res2->end); + res2->start = min(res1->start, res2->start); + res2->end = max(res1->end, res2->end); dev_info(&info->bridge->dev, "host bridge window expanded to %pR; %pR ignored\n", - res1, res2); - res2->flags = 0; + res2, res1); + res1->flags = 0; } } } diff --git a/arch/x86/pci/fixup.c b/arch/x86/pci/fixup.c index f5809fa2753e..b046e070e088 100644 --- a/arch/x86/pci/fixup.c +++ b/arch/x86/pci/fixup.c @@ -231,7 +231,7 @@ static int quirk_pcie_aspm_write(struct pci_bus *bus, unsigned int devfn, int wh offset = quirk_aspm_offset[GET_INDEX(bus->self->device, devfn)]; if ((offset) && (where == offset)) - value = value & 0xfffffffc; + value = value & ~PCI_EXP_LNKCTL_ASPMC; return raw_pci_write(pci_domain_nr(bus), bus->number, devfn, where, size, value); @@ -252,7 +252,7 @@ static struct pci_ops quirk_pcie_aspm_ops = { */ static void pcie_rootport_aspm_quirk(struct pci_dev *pdev) { - int cap_base, i; + int i; struct pci_bus *pbus; struct pci_dev *dev; @@ -278,7 +278,7 @@ static void pcie_rootport_aspm_quirk(struct pci_dev *pdev) for (i = GET_INDEX(pdev->device, 0); i <= GET_INDEX(pdev->device, 7); ++i) quirk_aspm_offset[i] = 0; - pbus->ops = pbus->parent->ops; + pci_bus_set_ops(pbus, pbus->parent->ops); } else { /* * If devices are attached to the root port at power-up or @@ -286,13 +286,15 @@ static void pcie_rootport_aspm_quirk(struct pci_dev *pdev) * each root port to save the register offsets and replace the * bus ops. */ - list_for_each_entry(dev, &pbus->devices, bus_list) { + list_for_each_entry(dev, &pbus->devices, bus_list) /* There are 0 to 8 devices attached to this bus */ - cap_base = pci_find_capability(dev, PCI_CAP_ID_EXP); - quirk_aspm_offset[GET_INDEX(pdev->device, dev->devfn)] = cap_base + 0x10; - } - pbus->ops = &quirk_pcie_aspm_ops; + quirk_aspm_offset[GET_INDEX(pdev->device, dev->devfn)] = + dev->pcie_cap + PCI_EXP_LNKCTL; + + pci_bus_set_ops(pbus, &quirk_pcie_aspm_ops); + dev_info(&pbus->dev, "writes to ASPM control bits will be ignored\n"); } + } DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_MCH_PA, pcie_rootport_aspm_quirk); DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_MCH_PA1, pcie_rootport_aspm_quirk); diff --git a/arch/x86/pci/xen.c b/arch/x86/pci/xen.c index 48e8461057ba..5eee4959785d 100644 --- a/arch/x86/pci/xen.c +++ b/arch/x86/pci/xen.c @@ -382,7 +382,14 @@ static void xen_teardown_msi_irq(unsigned int irq) { xen_destroy_irq(irq); } - +static u32 xen_nop_msi_mask_irq(struct msi_desc *desc, u32 mask, u32 flag) +{ + return 0; +} +static u32 xen_nop_msix_mask_irq(struct msi_desc *desc, u32 flag) +{ + return 0; +} #endif int __init pci_xen_init(void) @@ -406,6 +413,8 @@ int __init pci_xen_init(void) x86_msi.setup_msi_irqs = xen_setup_msi_irqs; x86_msi.teardown_msi_irq = xen_teardown_msi_irq; x86_msi.teardown_msi_irqs = xen_teardown_msi_irqs; + x86_msi.msi_mask_irq = xen_nop_msi_mask_irq; + x86_msi.msix_mask_irq = xen_nop_msix_mask_irq; #endif return 0; } @@ -485,6 +494,8 @@ int __init pci_xen_initial_domain(void) x86_msi.setup_msi_irqs = xen_initdom_setup_msi_irqs; x86_msi.teardown_msi_irq = xen_teardown_msi_irq; x86_msi.restore_msi_irqs = xen_initdom_restore_msi_irqs; + x86_msi.msi_mask_irq = xen_nop_msi_mask_irq; + x86_msi.msix_mask_irq = xen_nop_msix_mask_irq; #endif xen_setup_acpi_sci(); __acpi_register_gsi = acpi_register_gsi_xen; diff --git a/arch/x86/platform/olpc/olpc-xo15-sci.c b/arch/x86/platform/olpc/olpc-xo15-sci.c index fef7d0ba7e3a..649a12befba9 100644 --- a/arch/x86/platform/olpc/olpc-xo15-sci.c +++ b/arch/x86/platform/olpc/olpc-xo15-sci.c @@ -40,16 +40,9 @@ static bool lid_wake_on_close; */ static int set_lid_wake_behavior(bool wake_on_close) { - struct acpi_object_list arg_list; - union acpi_object arg; acpi_status status; - arg_list.count = 1; - arg_list.pointer = &arg; - arg.type = ACPI_TYPE_INTEGER; - arg.integer.value = wake_on_close; - - status = acpi_evaluate_object(NULL, "\\_SB.PCI0.LID.LIDW", &arg_list, NULL); + status = acpi_execute_simple_method(NULL, "\\_SB.PCI0.LID.LIDW", wake_on_close); if (ACPI_FAILURE(status)) { pr_warning(PFX "failed to set lid behavior\n"); return 1; diff --git a/arch/x86/um/elfcore.c b/arch/x86/um/elfcore.c index 6bb49b687c97..7bb89a27a5e4 100644 --- a/arch/x86/um/elfcore.c +++ b/arch/x86/um/elfcore.c @@ -11,8 +11,7 @@ Elf32_Half elf_core_extra_phdrs(void) return vsyscall_ehdr ? (((struct elfhdr *)vsyscall_ehdr)->e_phnum) : 0; } -int elf_core_write_extra_phdrs(struct file *file, loff_t offset, size_t *size, - unsigned long limit) +int elf_core_write_extra_phdrs(struct coredump_params *cprm, loff_t offset) { if ( vsyscall_ehdr ) { const struct elfhdr *const ehdrp = @@ -32,17 +31,14 @@ int elf_core_write_extra_phdrs(struct file *file, loff_t offset, size_t *size, phdr.p_offset += ofs; } phdr.p_paddr = 0; /* match other core phdrs */ - *size += sizeof(phdr); - if (*size > limit - || !dump_write(file, &phdr, sizeof(phdr))) + if (!dump_emit(cprm, &phdr, sizeof(phdr))) return 0; } } return 1; } -int elf_core_write_extra_data(struct file *file, size_t *size, - unsigned long limit) +int elf_core_write_extra_data(struct coredump_params *cprm) { if ( vsyscall_ehdr ) { const struct elfhdr *const ehdrp = @@ -55,10 +51,7 @@ int elf_core_write_extra_data(struct file *file, size_t *size, if (phdrp[i].p_type == PT_LOAD) { void *addr = (void *) phdrp[i].p_vaddr; size_t filesz = phdrp[i].p_filesz; - - *size += filesz; - if (*size > limit - || !dump_write(file, addr, filesz)) + if (!dump_emit(cprm, addr, filesz)) return 0; } } diff --git a/arch/x86/vdso/vclock_gettime.c b/arch/x86/vdso/vclock_gettime.c index 72074d528400..2ada505067cc 100644 --- a/arch/x86/vdso/vclock_gettime.c +++ b/arch/x86/vdso/vclock_gettime.c @@ -178,7 +178,7 @@ notrace static int __always_inline do_realtime(struct timespec *ts) ts->tv_nsec = 0; do { - seq = read_seqcount_begin(>od->seq); + seq = read_seqcount_begin_no_lockdep(>od->seq); mode = gtod->clock.vclock_mode; ts->tv_sec = gtod->wall_time_sec; ns = gtod->wall_time_snsec; @@ -198,7 +198,7 @@ notrace static int do_monotonic(struct timespec *ts) ts->tv_nsec = 0; do { - seq = read_seqcount_begin(>od->seq); + seq = read_seqcount_begin_no_lockdep(>od->seq); mode = gtod->clock.vclock_mode; ts->tv_sec = gtod->monotonic_time_sec; ns = gtod->monotonic_time_snsec; @@ -214,7 +214,7 @@ notrace static int do_realtime_coarse(struct timespec *ts) { unsigned long seq; do { - seq = read_seqcount_begin(>od->seq); + seq = read_seqcount_begin_no_lockdep(>od->seq); ts->tv_sec = gtod->wall_time_coarse.tv_sec; ts->tv_nsec = gtod->wall_time_coarse.tv_nsec; } while (unlikely(read_seqcount_retry(>od->seq, seq))); @@ -225,7 +225,7 @@ notrace static int do_monotonic_coarse(struct timespec *ts) { unsigned long seq; do { - seq = read_seqcount_begin(>od->seq); + seq = read_seqcount_begin_no_lockdep(>od->seq); ts->tv_sec = gtod->monotonic_time_coarse.tv_sec; ts->tv_nsec = gtod->monotonic_time_coarse.tv_nsec; } while (unlikely(read_seqcount_retry(>od->seq, seq))); |