Commit f05e798a authored by David Howells's avatar David Howells

Disintegrate asm/system.h for X86

Disintegrate asm/system.h for X86.
Signed-off-by: default avatarDavid Howells <dhowells@redhat.com>
Acked-by: default avatarH. Peter Anvin <hpa@zytor.com>
cc: x86@kernel.org
parent 778aae84
......@@ -26,7 +26,6 @@
#include <linux/init.h>
#include <linux/jiffies.h>
#include <asm/system.h>
#include <asm/uaccess.h>
#include <asm/pgalloc.h>
#include <asm/cacheflush.h>
......
......@@ -11,7 +11,6 @@
#include <linux/atomic.h>
#include <asm/fixmap.h>
#include <asm/mpspec.h>
#include <asm/system.h>
#include <asm/msr.h>
#define ARCH_APICTIMER_STOPS_ON_C3 1
......
......@@ -9,4 +9,11 @@
#endif
#define AT_SYSINFO_EHDR 33
/* entries in ARCH_DLINFO: */
#if defined(CONFIG_IA32_EMULATION) || !defined(CONFIG_X86_64)
# define AT_VECTOR_SIZE_ARCH 2
#else /* else it's non-compat x86-64 */
# define AT_VECTOR_SIZE_ARCH 1
#endif
#endif /* _ASM_X86_AUXVEC_H */
#ifndef _ASM_X86_BARRIER_H
#define _ASM_X86_BARRIER_H
#include <asm/alternative.h>
#include <asm/nops.h>
/*
* Force strict CPU ordering.
* And yes, this is required on UP too when we're talking
* to devices.
*/
#ifdef CONFIG_X86_32
/*
* Some non-Intel clones support out of order store. wmb() ceases to be a
* nop for these.
*/
#define mb() alternative("lock; addl $0,0(%%esp)", "mfence", X86_FEATURE_XMM2)
#define rmb() alternative("lock; addl $0,0(%%esp)", "lfence", X86_FEATURE_XMM2)
#define wmb() alternative("lock; addl $0,0(%%esp)", "sfence", X86_FEATURE_XMM)
#else
#define mb() asm volatile("mfence":::"memory")
#define rmb() asm volatile("lfence":::"memory")
#define wmb() asm volatile("sfence" ::: "memory")
#endif
/**
* read_barrier_depends - Flush all pending reads that subsequents reads
* depend on.
*
* No data-dependent reads from memory-like regions are ever reordered
* over this barrier. All reads preceding this primitive are guaranteed
* to access memory (but not necessarily other CPUs' caches) before any
* reads following this primitive that depend on the data return by
* any of the preceding reads. This primitive is much lighter weight than
* rmb() on most CPUs, and is never heavier weight than is
* rmb().
*
* These ordering constraints are respected by both the local CPU
* and the compiler.
*
* Ordering is not guaranteed by anything other than these primitives,
* not even by data dependencies. See the documentation for
* memory_barrier() for examples and URLs to more information.
*
* For example, the following code would force ordering (the initial
* value of "a" is zero, "b" is one, and "p" is "&a"):
*
* <programlisting>
* CPU 0 CPU 1
*
* b = 2;
* memory_barrier();
* p = &b; q = p;
* read_barrier_depends();
* d = *q;
* </programlisting>
*
* because the read of "*q" depends on the read of "p" and these
* two reads are separated by a read_barrier_depends(). However,
* the following code, with the same initial values for "a" and "b":
*
* <programlisting>
* CPU 0 CPU 1
*
* a = 2;
* memory_barrier();
* b = 3; y = b;
* read_barrier_depends();
* x = a;
* </programlisting>
*
* does not enforce ordering, since there is no data dependency between
* the read of "a" and the read of "b". Therefore, on some CPUs, such
* as Alpha, "y" could be set to 3 and "x" to 0. Use rmb()
* in cases like this where there are no data dependencies.
**/
#define read_barrier_depends() do { } while (0)
#ifdef CONFIG_SMP
#define smp_mb() mb()
#ifdef CONFIG_X86_PPRO_FENCE
# define smp_rmb() rmb()
#else
# define smp_rmb() barrier()
#endif
#ifdef CONFIG_X86_OOSTORE
# define smp_wmb() wmb()
#else
# define smp_wmb() barrier()
#endif
#define smp_read_barrier_depends() read_barrier_depends()
#define set_mb(var, value) do { (void)xchg(&var, value); } while (0)
#else
#define smp_mb() barrier()
#define smp_rmb() barrier()
#define smp_wmb() barrier()
#define smp_read_barrier_depends() do { } while (0)
#define set_mb(var, value) do { var = value; barrier(); } while (0)
#endif
/*
* Stop RDTSC speculation. This is needed when you need to use RDTSC
* (or get_cycles or vread that possibly accesses the TSC) in a defined
* code region.
*
* (Could use an alternative three way for this if there was one.)
*/
static __always_inline void rdtsc_barrier(void)
{
alternative(ASM_NOP3, "mfence", X86_FEATURE_MFENCE_RDTSC);
alternative(ASM_NOP3, "lfence", X86_FEATURE_LFENCE_RDTSC);
}
#endif /* _ASM_X86_BARRIER_H */
......@@ -36,4 +36,8 @@ do { \
#endif /* !CONFIG_BUG */
#include <asm-generic/bug.h>
extern void show_regs_common(void);
#endif /* _ASM_X86_BUG_H */
......@@ -3,6 +3,7 @@
/* Caches aren't brain-dead on the intel. */
#include <asm-generic/cacheflush.h>
#include <asm/special_insns.h>
#ifdef CONFIG_X86_PAT
/*
......
......@@ -84,7 +84,6 @@ extern unsigned int vdso_enabled;
(((x)->e_machine == EM_386) || ((x)->e_machine == EM_486))
#include <asm/processor.h>
#include <asm/system.h>
#ifdef CONFIG_X86_32
#include <asm/desc.h>
......
/* define arch_align_stack() here */
......@@ -9,7 +9,6 @@
#include <asm/asm.h>
#include <asm/errno.h>
#include <asm/processor.h>
#include <asm/system.h>
#define __futex_atomic_op1(insn, ret, oldval, uaddr, oparg) \
asm volatile("1:\t" insn "\n" \
......
......@@ -14,7 +14,6 @@
#include <linux/sched.h>
#include <linux/hardirq.h>
#include <asm/system.h>
struct pt_regs;
struct user_i387_struct;
......
......@@ -3,7 +3,6 @@
#include <linux/percpu.h>
#include <asm/system.h>
#include <linux/atomic.h>
#include <asm/asm.h>
......
......@@ -5,7 +5,6 @@
#define _ASM_X86_MC146818RTC_H
#include <asm/io.h>
#include <asm/system.h>
#include <asm/processor.h>
#include <linux/mc146818rtc.h>
......
......@@ -14,13 +14,13 @@ struct mm_struct;
#include <asm/sigcontext.h>
#include <asm/current.h>
#include <asm/cpufeature.h>
#include <asm/system.h>
#include <asm/page.h>
#include <asm/pgtable_types.h>
#include <asm/percpu.h>
#include <asm/msr.h>
#include <asm/desc_defs.h>
#include <asm/nops.h>
#include <asm/special_insns.h>
#include <linux/personality.h>
#include <linux/cpumask.h>
......@@ -29,6 +29,15 @@ struct mm_struct;
#include <linux/math64.h>
#include <linux/init.h>
#include <linux/err.h>
#include <linux/irqflags.h>
/*
* We handle most unaligned accesses in hardware. On the other hand
* unaligned DMA can be quite expensive on some Nehalem processors.
*
* Based on this we disable the IP header alignment in network drivers.
*/
#define NET_IP_ALIGN 0
#define HBP_NUM 4
/*
......@@ -1022,4 +1031,24 @@ extern bool cpu_has_amd_erratum(const int *);
#define cpu_has_amd_erratum(x) (false)
#endif /* CONFIG_CPU_SUP_AMD */
#ifdef CONFIG_X86_32
/*
* disable hlt during certain critical i/o operations
*/
#define HAVE_DISABLE_HLT
#endif
void disable_hlt(void);
void enable_hlt(void);
void cpu_idle_wait(void);
extern unsigned long arch_align_stack(unsigned long sp);
extern void free_init_pages(char *what, unsigned long begin, unsigned long end);
void default_idle(void);
bool set_pm_idle_to_default(void);
void stop_this_cpu(void *dummy);
#endif /* _ASM_X86_PROCESSOR_H */
......@@ -212,7 +212,61 @@
#ifdef __KERNEL__
#ifndef __ASSEMBLY__
extern const char early_idt_handlers[NUM_EXCEPTION_VECTORS][10];
#endif
#endif
/*
* Load a segment. Fall back on loading the zero
* segment if something goes wrong..
*/
#define loadsegment(seg, value) \
do { \
unsigned short __val = (value); \
\
asm volatile(" \n" \
"1: movl %k0,%%" #seg " \n" \
\
".section .fixup,\"ax\" \n" \
"2: xorl %k0,%k0 \n" \
" jmp 1b \n" \
".previous \n" \
\
_ASM_EXTABLE(1b, 2b) \
\
: "+r" (__val) : : "memory"); \
} while (0)
/*
* Save a segment register away
*/
#define savesegment(seg, value) \
asm("mov %%" #seg ",%0":"=r" (value) : : "memory")
/*
* x86_32 user gs accessors.
*/
#ifdef CONFIG_X86_32
#ifdef CONFIG_X86_32_LAZY_GS
#define get_user_gs(regs) (u16)({unsigned long v; savesegment(gs, v); v;})
#define set_user_gs(regs, v) loadsegment(gs, (unsigned long)(v))
#define task_user_gs(tsk) ((tsk)->thread.gs)
#define lazy_save_gs(v) savesegment(gs, (v))
#define lazy_load_gs(v) loadsegment(gs, (v))
#else /* X86_32_LAZY_GS */
#define get_user_gs(regs) (u16)((regs)->gs)
#define set_user_gs(regs, v) do { (regs)->gs = (v); } while (0)
#define task_user_gs(tsk) (task_pt_regs(tsk)->gs)
#define lazy_save_gs(v) do { } while (0)
#define lazy_load_gs(v) do { } while (0)
#endif /* X86_32_LAZY_GS */
#endif /* X86_32 */
static inline unsigned long get_limit(unsigned long segment)
{
unsigned long __limit;
asm("lsll %1,%0" : "=r" (__limit) : "r" (segment));
return __limit + 1;
}
#endif /* !__ASSEMBLY__ */
#endif /* __KERNEL__ */
#endif /* _ASM_X86_SEGMENT_H */
#ifndef _ASM_X86_SPECIAL_INSNS_H
#define _ASM_X86_SPECIAL_INSNS_H
#ifdef __KERNEL__
static inline void native_clts(void)
{
asm volatile("clts");
}
/*
* Volatile isn't enough to prevent the compiler from reordering the
* read/write functions for the control registers and messing everything up.
* A memory clobber would solve the problem, but would prevent reordering of
* all loads stores around it, which can hurt performance. Solution is to
* use a variable and mimic reads and writes to it to enforce serialization
*/
static unsigned long __force_order;
static inline unsigned long native_read_cr0(void)
{
unsigned long val;
asm volatile("mov %%cr0,%0\n\t" : "=r" (val), "=m" (__force_order));
return val;
}
static inline void native_write_cr0(unsigned long val)
{
asm volatile("mov %0,%%cr0": : "r" (val), "m" (__force_order));
}
static inline unsigned long native_read_cr2(void)
{
unsigned long val;
asm volatile("mov %%cr2,%0\n\t" : "=r" (val), "=m" (__force_order));
return val;
}
static inline void native_write_cr2(unsigned long val)
{
asm volatile("mov %0,%%cr2": : "r" (val), "m" (__force_order));
}
static inline unsigned long native_read_cr3(void)
{
unsigned long val;
asm volatile("mov %%cr3,%0\n\t" : "=r" (val), "=m" (__force_order));
return val;
}
static inline void native_write_cr3(unsigned long val)
{
asm volatile("mov %0,%%cr3": : "r" (val), "m" (__force_order));
}
static inline unsigned long native_read_cr4(void)
{
unsigned long val;
asm volatile("mov %%cr4,%0\n\t" : "=r" (val), "=m" (__force_order));
return val;
}
static inline unsigned long native_read_cr4_safe(void)
{
unsigned long val;
/* This could fault if %cr4 does not exist. In x86_64, a cr4 always
* exists, so it will never fail. */
#ifdef CONFIG_X86_32
asm volatile("1: mov %%cr4, %0\n"
"2:\n"
_ASM_EXTABLE(1b, 2b)
: "=r" (val), "=m" (__force_order) : "0" (0));
#else
val = native_read_cr4();
#endif
return val;
}
static inline void native_write_cr4(unsigned long val)
{
asm volatile("mov %0,%%cr4": : "r" (val), "m" (__force_order));
}
#ifdef CONFIG_X86_64
static inline unsigned long native_read_cr8(void)
{
unsigned long cr8;
asm volatile("movq %%cr8,%0" : "=r" (cr8));
return cr8;
}
static inline void native_write_cr8(unsigned long val)
{
asm volatile("movq %0,%%cr8" :: "r" (val) : "memory");
}
#endif
static inline void native_wbinvd(void)
{
asm volatile("wbinvd": : :"memory");
}
extern void native_load_gs_index(unsigned);
#ifdef CONFIG_PARAVIRT
#include <asm/paravirt.h>
#else
static inline unsigned long read_cr0(void)
{
return native_read_cr0();
}
static inline void write_cr0(unsigned long x)
{
native_write_cr0(x);
}
static inline unsigned long read_cr2(void)
{
return native_read_cr2();
}
static inline void write_cr2(unsigned long x)
{
native_write_cr2(x);
}
static inline unsigned long read_cr3(void)
{
return native_read_cr3();
}
static inline void write_cr3(unsigned long x)
{
native_write_cr3(x);
}
static inline unsigned long read_cr4(void)
{
return native_read_cr4();
}
static inline unsigned long read_cr4_safe(void)
{
return native_read_cr4_safe();
}
static inline void write_cr4(unsigned long x)
{
native_write_cr4(x);
}
static inline void wbinvd(void)
{
native_wbinvd();
}
#ifdef CONFIG_X86_64
static inline unsigned long read_cr8(void)
{
return native_read_cr8();
}
static inline void write_cr8(unsigned long x)
{
native_write_cr8(x);
}
static inline void load_gs_index(unsigned selector)
{
native_load_gs_index(selector);
}
#endif
/* Clear the 'TS' bit */
static inline void clts(void)
{
native_clts();
}
#endif/* CONFIG_PARAVIRT */
#define stts() write_cr0(read_cr0() | X86_CR0_TS)
static inline void clflush(volatile void *__p)
{
asm volatile("clflush %0" : "+m" (*(volatile char __force *)__p));
}
#define nop() asm volatile ("nop")
#endif /* __KERNEL__ */
#endif /* _ASM_X86_SPECIAL_INSNS_H */
......@@ -38,7 +38,6 @@
#include <asm/tsc.h>
#include <asm/processor.h>
#include <asm/percpu.h>
#include <asm/system.h>
#include <asm/desc.h>
#include <linux/random.h>
......
#ifndef _ASM_X86_SWITCH_TO_H
#define _ASM_X86_SWITCH_TO_H
struct task_struct; /* one of the stranger aspects of C forward declarations */
struct task_struct *__switch_to(struct task_struct *prev,
struct task_struct *next);
struct tss_struct;
void __switch_to_xtra(struct task_struct *prev_p, struct task_struct *next_p,
struct tss_struct *tss);
#ifdef CONFIG_X86_32
#ifdef CONFIG_CC_STACKPROTECTOR
#define __switch_canary \
"movl %P[task_canary](%[next]), %%ebx\n\t" \
"movl %%ebx, "__percpu_arg([stack_canary])"\n\t"
#define __switch_canary_oparam \
, [stack_canary] "=m" (stack_canary.canary)
#define __switch_canary_iparam \
, [task_canary] "i" (offsetof(struct task_struct, stack_canary))
#else /* CC_STACKPROTECTOR */
#define __switch_canary
#define __switch_canary_oparam
#define __switch_canary_iparam
#endif /* CC_STACKPROTECTOR */
/*
* Saving eflags is important. It switches not only IOPL between tasks,
* it also protects other tasks from NT leaking through sysenter etc.
*/
#define switch_to(prev, next, last) \
do { \
/* \
* Context-switching clobbers all registers, so we clobber \
* them explicitly, via unused output variables. \
* (EAX and EBP is not listed because EBP is saved/restored \
* explicitly for wchan access and EAX is the return value of \
* __switch_to()) \
*/ \
unsigned long ebx, ecx, edx, esi, edi; \
\
asm volatile("pushfl\n\t" /* save flags */ \
"pushl %%ebp\n\t" /* save EBP */ \
"movl %%esp,%[prev_sp]\n\t" /* save ESP */ \
"movl %[next_sp],%%esp\n\t" /* restore ESP */ \
"movl $1f,%[prev_ip]\n\t" /* save EIP */ \
"pushl %[next_ip]\n\t" /* restore EIP */ \
__switch_canary \
"jmp __switch_to\n" /* regparm call */ \
"1:\t" \
"popl %%ebp\n\t" /* restore EBP */ \
"popfl\n" /* restore flags */ \
\
/* output parameters */ \
: [prev_sp] "=m" (prev->thread.sp), \
[prev_ip] "=m" (prev->thread.ip), \
"=a" (last), \
\
/* clobbered output registers: */ \
"=b" (ebx), "=c" (ecx), "=d" (edx), \
"=S" (esi), "=D" (edi) \
\
__switch_canary_oparam \
\
/* input parameters: */ \
: [next_sp] "m" (next->thread.sp), \
[next_ip] "m" (next->thread.ip), \
\
/* regparm parameters for __switch_to(): */ \
[prev] "a" (prev), \
[next] "d" (next) \
\
__switch_canary_iparam \
\
: /* reloaded segment registers */ \
"memory"); \
} while (0)
#else /* CONFIG_X86_32 */
/* frame pointer must be last for get_wchan */
#define SAVE_CONTEXT "pushf ; pushq %%rbp ; movq %%rsi,%%rbp\n\t"
#define RESTORE_CONTEXT "movq %%rbp,%%rsi ; popq %%rbp ; popf\t"
#define __EXTRA_CLOBBER \
, "rcx", "rbx", "rdx", "r8", "r9", "r10", "r11", \
"r12", "r13", "r14", "r15"
#ifdef CONFIG_CC_STACKPROTECTOR
#define __switch_canary \
"movq %P[task_canary](%%rsi),%%r8\n\t" \
"movq %%r8,"__percpu_arg([gs_canary])"\n\t"
#define __switch_canary_oparam \
, [gs_canary] "=m" (irq_stack_union.stack_canary)
#define __switch_canary_iparam \
, [task_canary] "i" (offsetof(struct task_struct, stack_canary))
#else /* CC_STACKPROTECTOR */
#define __switch_canary
#define __switch_canary_oparam
#define __switch_canary_iparam
#endif /* CC_STACKPROTECTOR */
/* Save restore flags to clear handle leaking NT */
#define switch_to(prev, next, last) \
asm volatile(SAVE_CONTEXT \
"movq %%rsp,%P[threadrsp](%[prev])\n\t" /* save RSP */ \
"movq %P[threadrsp](%[next]),%%rsp\n\t" /* restore RSP */ \
"call __switch_to\n\t" \
"movq "__percpu_arg([current_task])",%%rsi\n\t" \
__switch_canary \
"movq %P[thread_info](%%rsi),%%r8\n\t" \
"movq %%rax,%%rdi\n\t" \
"testl %[_tif_fork],%P[ti_flags](%%r8)\n\t" \
"jnz ret_from_fork\n\t" \
RESTORE_CONTEXT \
: "=a" (last) \
__switch_canary_oparam \
: [next] "S" (next), [prev] "D" (prev), \
[threadrsp] "i" (offsetof(struct task_struct, thread.sp)), \
[ti_flags] "i" (offsetof(struct thread_info, flags)), \
[_tif_fork] "i" (_TIF_FORK), \
[thread_info] "i" (offsetof(struct task_struct, stack)), \
[current_task] "m" (current_task) \
__switch_canary_iparam \
: "memory", "cc" __EXTRA_CLOBBER)
#endif /* CONFIG_X86_32 */
#endif /* _ASM_X86_SWITCH_TO_H */
This diff is collapsed.
......@@ -5,7 +5,7 @@
#include <linux/sched.h>
#include <asm/processor.h>
#include <asm/system.h>
#include <asm/special_insns.h>
#ifdef CONFIG_PARAVIRT
#include <asm/paravirt.h>
......
......@@ -16,7 +16,6 @@
#define _ASM_X86_VIRTEX_H
#include <asm/processor.h>
#include <asm/system.h>
#include <asm/vmx.h>
#include <asm/svm.h>
......
......@@ -14,6 +14,7 @@
#include <acpi/processor.h>
#include <asm/acpi.h>
#include <asm/mwait.h>
#include <asm/special_insns.h>
/*
* Initialize bm_flags based on the CPU cache properties
......
......@@ -231,7 +231,6 @@
#include <linux/syscore_ops.h>
#include <linux/i8253.h>
#include <asm/system.h>
#include <asm/uaccess.h>
#include <asm/desc.h>
#include <asm/olpc.h>
......
......@@ -9,7 +9,6 @@
#include <linux/smp.h>
#include <asm/processor.h>
#include <asm/system.h>
#include <asm/mce.h>
#include <asm/msr.h>
......
......@@ -25,7 +25,6 @@
#include <linux/cpu.h>
#include <asm/processor.h>
#include <asm/system.h>
#include <asm/apic.h>
#include <asm/idle.h>
#include <asm/mce.h>
......