1
0
Fork 0
alistair23-linux/arch/x86/include/asm/processor.h

981 lines
24 KiB
C
Raw Normal View History

#ifndef _ASM_X86_PROCESSOR_H
#define _ASM_X86_PROCESSOR_H
#include <asm/processor-flags.h>
/* Forward declaration, a strange C thing */
struct task_struct;
struct mm_struct;
#include <asm/vm86.h>
#include <asm/math_emu.h>
#include <asm/segment.h>
#include <asm/types.h>
#include <asm/sigcontext.h>
#include <asm/current.h>
#include <asm/cpufeature.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>
#include <linux/cache.h>
#include <linux/threads.h>
#include <linux/math64.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
/*
* Default implementation of macro that returns current
* instruction pointer ("program counter").
*/
static inline void *current_text_addr(void)
{
void *pc;
asm volatile("mov $1f, %0; 1:":"=r" (pc));
return pc;
}
#ifdef CONFIG_X86_VSMP
# define ARCH_MIN_TASKALIGN (1 << INTERNODE_CACHE_SHIFT)
# define ARCH_MIN_MMSTRUCT_ALIGN (1 << INTERNODE_CACHE_SHIFT)
#else
# define ARCH_MIN_TASKALIGN 16
# define ARCH_MIN_MMSTRUCT_ALIGN 0
#endif
enum tlb_infos {
ENTRIES,
NR_INFO
};
extern u16 __read_mostly tlb_lli_4k[NR_INFO];
extern u16 __read_mostly tlb_lli_2m[NR_INFO];
extern u16 __read_mostly tlb_lli_4m[NR_INFO];
extern u16 __read_mostly tlb_lld_4k[NR_INFO];
extern u16 __read_mostly tlb_lld_2m[NR_INFO];
extern u16 __read_mostly tlb_lld_4m[NR_INFO];
extern u16 __read_mostly tlb_lld_1g[NR_INFO];
/*
* CPU type and hardware bug flags. Kept separately for each CPU.
* Members of this structure are referenced in head.S, so think twice
* before touching them. [mj]
*/
struct cpuinfo_x86 {
__u8 x86; /* CPU family */
__u8 x86_vendor; /* CPU vendor */
__u8 x86_model;
__u8 x86_mask;
#ifdef CONFIG_X86_32
char wp_works_ok; /* It doesn't on 386's */
/* Problems on some 486Dx4's and old 386's: */
char rfu;
char pad0;
char pad1;
#else
/* Number of 4K pages in DTLB/ITLB combined(in pages): */
int x86_tlbsize;
#endif
__u8 x86_virt_bits;
__u8 x86_phys_bits;
/* CPUID returned core id bits: */
__u8 x86_coreid_bits;
/* Max extended CPUID function supported: */
__u32 extended_cpuid_level;
/* Maximum supported CPUID level, -1=no CPUID: */
int cpuid_level;
__u32 x86_capability[NCAPINTS + NBUGINTS];
char x86_vendor_id[16];
char x86_model_id[64];
/* in KB - valid for CPUS which support this call: */
int x86_cache_size;
int x86_cache_alignment; /* In bytes */
int x86_power;
unsigned long loops_per_jiffy;
/* cpuid returned max cores value: */
u16 x86_max_cores;
u16 apicid;
u16 initial_apicid;
u16 x86_clflush_size;
/* number of cores as seen by the OS: */
u16 booted_cores;
/* Physical processor id: */
u16 phys_proc_id;
/* Core id: */
u16 cpu_core_id;
/* Compute unit id */
u8 compute_unit_id;
/* Index into per_cpu list: */
u16 cpu_index;
u32 microcode;
};
#define X86_VENDOR_INTEL 0
#define X86_VENDOR_CYRIX 1
#define X86_VENDOR_AMD 2
#define X86_VENDOR_UMC 3
#define X86_VENDOR_CENTAUR 5
#define X86_VENDOR_TRANSMETA 7
#define X86_VENDOR_NSC 8
#define X86_VENDOR_NUM 9
#define X86_VENDOR_UNKNOWN 0xff
/*
* capabilities of CPUs
*/
extern struct cpuinfo_x86 boot_cpu_data;
extern struct cpuinfo_x86 new_cpu_data;
extern struct tss_struct doublefault_tss;
extern __u32 cpu_caps_cleared[NCAPINTS];
extern __u32 cpu_caps_set[NCAPINTS];
#ifdef CONFIG_SMP
DECLARE_PER_CPU_READ_MOSTLY(struct cpuinfo_x86, cpu_info);
#define cpu_data(cpu) per_cpu(cpu_info, cpu)
#else
#define cpu_info boot_cpu_data
#define cpu_data(cpu) boot_cpu_data
#endif
extern const struct seq_operations cpuinfo_op;
#define cache_line_size() (boot_cpu_data.x86_cache_alignment)
extern void cpu_detect(struct cpuinfo_x86 *c);
x86: delete __cpuinit usage from all x86 files The __cpuinit type of throwaway sections might have made sense some time ago when RAM was more constrained, but now the savings do not offset the cost and complications. For example, the fix in commit 5e427ec2d0 ("x86: Fix bit corruption at CPU resume time") is a good example of the nasty type of bugs that can be created with improper use of the various __init prefixes. After a discussion on LKML[1] it was decided that cpuinit should go the way of devinit and be phased out. Once all the users are gone, we can then finally remove the macros themselves from linux/init.h. Note that some harmless section mismatch warnings may result, since notify_cpu_starting() and cpu_up() are arch independent (kernel/cpu.c) are flagged as __cpuinit -- so if we remove the __cpuinit from arch specific callers, we will also get section mismatch warnings. As an intermediate step, we intend to turn the linux/init.h cpuinit content into no-ops as early as possible, since that will get rid of these warnings. In any case, they are temporary and harmless. This removes all the arch/x86 uses of the __cpuinit macros from all C files. x86 only had the one __CPUINIT used in assembly files, and it wasn't paired off with a .previous or a __FINIT, so we can delete it directly w/o any corresponding additional change there. [1] https://lkml.org/lkml/2013/5/20/589 Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Ingo Molnar <mingo@redhat.com> Cc: "H. Peter Anvin" <hpa@zytor.com> Cc: x86@kernel.org Acked-by: Ingo Molnar <mingo@kernel.org> Acked-by: Thomas Gleixner <tglx@linutronix.de> Acked-by: H. Peter Anvin <hpa@linux.intel.com> Signed-off-by: Paul Gortmaker <paul.gortmaker@windriver.com>
2013-06-18 16:23:59 -06:00
extern void fpu_detect(struct cpuinfo_x86 *c);
extern void early_cpu_init(void);
extern void identify_boot_cpu(void);
extern void identify_secondary_cpu(struct cpuinfo_x86 *);
extern void print_cpu_info(struct cpuinfo_x86 *);
void print_cpu_msr(struct cpuinfo_x86 *);
extern void init_scattered_cpuid_features(struct cpuinfo_x86 *c);
extern unsigned int init_intel_cacheinfo(struct cpuinfo_x86 *c);
extern void init_amd_cacheinfo(struct cpuinfo_x86 *c);
extern void detect_extended_topology(struct cpuinfo_x86 *c);
extern void detect_ht(struct cpuinfo_x86 *c);
#ifdef CONFIG_X86_32
extern int have_cpuid_p(void);
#else
static inline int have_cpuid_p(void)
{
return 1;
}
#endif
static inline void native_cpuid(unsigned int *eax, unsigned int *ebx,
unsigned int *ecx, unsigned int *edx)
{
/* ecx is often an input as well as an output. */
asm volatile("cpuid"
: "=a" (*eax),
"=b" (*ebx),
"=c" (*ecx),
"=d" (*edx)
: "0" (*eax), "2" (*ecx)
: "memory");
}
static inline void load_cr3(pgd_t *pgdir)
{
write_cr3(__pa(pgdir));
}
#ifdef CONFIG_X86_32
/* This is the TSS defined by the hardware. */
struct x86_hw_tss {
unsigned short back_link, __blh;
unsigned long sp0;
unsigned short ss0, __ss0h;
unsigned long sp1;
/* ss1 caches MSR_IA32_SYSENTER_CS: */
unsigned short ss1, __ss1h;
unsigned long sp2;
unsigned short ss2, __ss2h;
unsigned long __cr3;
unsigned long ip;
unsigned long flags;
unsigned long ax;
unsigned long cx;
unsigned long dx;
unsigned long bx;
unsigned long sp;
unsigned long bp;
unsigned long si;
unsigned long di;
unsigned short es, __esh;
unsigned short cs, __csh;
unsigned short ss, __ssh;
unsigned short ds, __dsh;
unsigned short fs, __fsh;
unsigned short gs, __gsh;
unsigned short ldt, __ldth;
unsigned short trace;
unsigned short io_bitmap_base;
} __attribute__((packed));
#else
struct x86_hw_tss {
u32 reserved1;
u64 sp0;
u64 sp1;
u64 sp2;
u64 reserved2;
u64 ist[7];
u32 reserved3;
u32 reserved4;
u16 reserved5;
u16 io_bitmap_base;
} __attribute__((packed)) ____cacheline_aligned;
#endif
/*
* IO-bitmap sizes:
*/
#define IO_BITMAP_BITS 65536
#define IO_BITMAP_BYTES (IO_BITMAP_BITS/8)
#define IO_BITMAP_LONGS (IO_BITMAP_BYTES/sizeof(long))
#define IO_BITMAP_OFFSET offsetof(struct tss_struct, io_bitmap)
#define INVALID_IO_BITMAP_OFFSET 0x8000
struct tss_struct {
/*
* The hardware state:
*/
struct x86_hw_tss x86_tss;
/*
* The extra 1 is there because the CPU will access an
* additional byte beyond the end of the IO permission
* bitmap. The extra byte must be all 1 bits, and must
* be within the limit.
*/
unsigned long io_bitmap[IO_BITMAP_LONGS + 1];
/*
* .. and then another 0x100 bytes for the emergency kernel stack:
*/
unsigned long stack[64];
} ____cacheline_aligned;
DECLARE_PER_CPU_SHARED_ALIGNED(struct tss_struct, init_tss);
/*
* Save the original ist values for checking stack pointers during debugging
*/
struct orig_ist {
unsigned long ist[7];
};
#define MXCSR_DEFAULT 0x1f80
struct i387_fsave_struct {
u32 cwd; /* FPU Control Word */
u32 swd; /* FPU Status Word */
u32 twd; /* FPU Tag Word */
u32 fip; /* FPU IP Offset */
u32 fcs; /* FPU IP Selector */
u32 foo; /* FPU Operand Pointer Offset */
u32 fos; /* FPU Operand Pointer Selector */
/* 8*10 bytes for each FP-reg = 80 bytes: */
u32 st_space[20];
/* Software status information [not touched by FSAVE ]: */
u32 status;
};
struct i387_fxsave_struct {
u16 cwd; /* Control Word */
u16 swd; /* Status Word */
u16 twd; /* Tag Word */
u16 fop; /* Last Instruction Opcode */
union {
struct {
u64 rip; /* Instruction Pointer */
u64 rdp; /* Data Pointer */
};
struct {
u32 fip; /* FPU IP Offset */
u32 fcs; /* FPU IP Selector */
u32 foo; /* FPU Operand Offset */
u32 fos; /* FPU Operand Selector */
};
};
u32 mxcsr; /* MXCSR Register State */
u32 mxcsr_mask; /* MXCSR Mask */
/* 8*16 bytes for each FP-reg = 128 bytes: */
u32 st_space[32];
/* 16*16 bytes for each XMM-reg = 256 bytes: */
u32 xmm_space[64];
u32 padding[12];
union {
u32 padding1[12];
u32 sw_reserved[12];
};
} __attribute__((aligned(16)));
struct i387_soft_struct {
u32 cwd;
u32 swd;
u32 twd;
u32 fip;
u32 fcs;
u32 foo;
u32 fos;
/* 8*10 bytes for each FP-reg = 80 bytes: */
u32 st_space[20];
u8 ftop;
u8 changed;
u8 lookahead;
u8 no_update;
u8 rm;
u8 alimit;
struct math_emu_info *info;
u32 entry_eip;
};
struct ymmh_struct {
/* 16 * 16 bytes for each YMMH-reg = 256 bytes */
u32 ymmh_space[64];
};
/* We don't support LWP yet: */
struct lwp_struct {
u8 reserved[128];
};
struct bndreg {
u64 lower_bound;
u64 upper_bound;
} __packed;
struct bndcsr {
u64 bndcfgu;
u64 bndstatus;
} __packed;
struct xsave_hdr_struct {
u64 xstate_bv;
u64 xcomp_bv;
u64 reserved[6];
} __attribute__((packed));
struct xsave_struct {
struct i387_fxsave_struct i387;
struct xsave_hdr_struct xsave_hdr;
struct ymmh_struct ymmh;
struct lwp_struct lwp;
struct bndreg bndreg[4];
struct bndcsr bndcsr;
/* new processor state extensions will go here */
} __attribute__ ((packed, aligned (64)));
union thread_xstate {
struct i387_fsave_struct fsave;
struct i387_fxsave_struct fxsave;
struct i387_soft_struct soft;
struct xsave_struct xsave;
};
struct fpu {
i387: support lazy restore of FPU state This makes us recognize when we try to restore FPU state that matches what we already have in the FPU on this CPU, and avoids the restore entirely if so. To do this, we add two new data fields: - a percpu 'fpu_owner_task' variable that gets written any time we update the "has_fpu" field, and thus acts as a kind of back-pointer to the task that owns the CPU. The exception is when we save the FPU state as part of a context switch - if the save can keep the FPU state around, we leave the 'fpu_owner_task' variable pointing at the task whose FP state still remains on the CPU. - a per-thread 'last_cpu' field, that indicates which CPU that thread used its FPU on last. We update this on every context switch (writing an invalid CPU number if the last context switch didn't leave the FPU in a lazily usable state), so we know that *that* thread has done nothing else with the FPU since. These two fields together can be used when next switching back to the task to see if the CPU still matches: if 'fpu_owner_task' matches the task we are switching to, we know that no other task (or kernel FPU usage) touched the FPU on this CPU in the meantime, and if the current CPU number matches the 'last_cpu' field, we know that this thread did no other FP work on any other CPU, so the FPU state on the CPU must match what was saved on last context switch. In that case, we can avoid the 'f[x]rstor' entirely, and just clear the CR0.TS bit. Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2012-02-19 14:27:00 -07:00
unsigned int last_cpu;
unsigned int has_fpu;
union thread_xstate *state;
};
#ifdef CONFIG_X86_64
DECLARE_PER_CPU(struct orig_ist, orig_ist);
union irq_stack_union {
char irq_stack[IRQ_STACK_SIZE];
/*
* GCC hardcodes the stack canary as %gs:40. Since the
* irq_stack is the object at %gs:0, we reserve the bottom
* 48 bytes of the irq stack for the canary.
*/
struct {
char gs_base[40];
unsigned long stack_canary;
};
};
DECLARE_PER_CPU_FIRST(union irq_stack_union, irq_stack_union) __visible;
DECLARE_INIT_PER_CPU(irq_stack_union);
DECLARE_PER_CPU(char *, irq_stack_ptr);
DECLARE_PER_CPU(unsigned int, irq_count);
extern asmlinkage void ignore_sysret(void);
#else /* X86_64 */
#ifdef CONFIG_CC_STACKPROTECTOR
/*
* Make sure stack canary segment base is cached-aligned:
* "For Intel Atom processors, avoid non zero segment base address
* that is not aligned to cache line boundary at all cost."
* (Optim Ref Manual Assembly/Compiler Coding Rule 15.)
*/
struct stack_canary {
char __pad[20]; /* canary at %gs:20 */
unsigned long canary;
};
DECLARE_PER_CPU_ALIGNED(struct stack_canary, stack_canary);
#endif
/*
* per-CPU IRQ handling stacks
*/
struct irq_stack {
u32 stack[THREAD_SIZE/sizeof(u32)];
} __aligned(THREAD_SIZE);
DECLARE_PER_CPU(struct irq_stack *, hardirq_stack);
DECLARE_PER_CPU(struct irq_stack *, softirq_stack);
#endif /* X86_64 */
extern unsigned int xstate_size;
extern void free_thread_xstate(struct task_struct *);
extern struct kmem_cache *task_xstate_cachep;
hw-breakpoints: Rewrite the hw-breakpoints layer on top of perf events This patch rebase the implementation of the breakpoints API on top of perf events instances. Each breakpoints are now perf events that handle the register scheduling, thread/cpu attachment, etc.. The new layering is now made as follows: ptrace kgdb ftrace perf syscall \ | / / \ | / / / Core breakpoint API / / | / | / Breakpoints perf events | | Breakpoints PMU ---- Debug Register constraints handling (Part of core breakpoint API) | | Hardware debug registers Reasons of this rewrite: - Use the centralized/optimized pmu registers scheduling, implying an easier arch integration - More powerful register handling: perf attributes (pinned/flexible events, exclusive/non-exclusive, tunable period, etc...) Impact: - New perf ABI: the hardware breakpoints counters - Ptrace breakpoints setting remains tricky and still needs some per thread breakpoints references. Todo (in the order): - Support breakpoints perf counter events for perf tools (ie: implement perf_bpcounter_event()) - Support from perf tools Changes in v2: - Follow the perf "event " rename - The ptrace regression have been fixed (ptrace breakpoint perf events weren't released when a task ended) - Drop the struct hw_breakpoint and store generic fields in perf_event_attr. - Separate core and arch specific headers, drop asm-generic/hw_breakpoint.h and create linux/hw_breakpoint.h - Use new generic len/type for breakpoint - Handle off case: when breakpoints api is not supported by an arch Changes in v3: - Fix broken CONFIG_KVM, we need to propagate the breakpoint api changes to kvm when we exit the guest and restore the bp registers to the host. Changes in v4: - Drop the hw_breakpoint_restore() stub as it is only used by KVM - EXPORT_SYMBOL_GPL hw_breakpoint_restore() as KVM can be built as a module - Restore the breakpoints unconditionally on kvm guest exit: TIF_DEBUG_THREAD doesn't anymore cover every cases of running breakpoints and vcpu->arch.switch_db_regs might not always be set when the guest used debug registers. (Waiting for a reliable optimization) Changes in v5: - Split-up the asm-generic/hw-breakpoint.h moving to linux/hw_breakpoint.h into a separate patch - Optimize the breakpoints restoring while switching from kvm guest to host. We only want to restore the state if we have active breakpoints to the host, otherwise we don't care about messed-up address registers. - Add asm/hw_breakpoint.h to Kbuild - Fix bad breakpoint type in trace_selftest.c Changes in v6: - Fix wrong header inclusion in trace.h (triggered a build error with CONFIG_FTRACE_SELFTEST Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com> Cc: Prasad <prasad@linux.vnet.ibm.com> Cc: Alan Stern <stern@rowland.harvard.edu> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Steven Rostedt <rostedt@goodmis.org> Cc: Ingo Molnar <mingo@elte.hu> Cc: Jan Kiszka <jan.kiszka@web.de> Cc: Jiri Slaby <jirislaby@gmail.com> Cc: Li Zefan <lizf@cn.fujitsu.com> Cc: Avi Kivity <avi@redhat.com> Cc: Paul Mackerras <paulus@samba.org> Cc: Mike Galbraith <efault@gmx.de> Cc: Masami Hiramatsu <mhiramat@redhat.com> Cc: Paul Mundt <lethal@linux-sh.org>
2009-09-09 11:22:48 -06:00
struct perf_event;
struct thread_struct {
/* Cached TLS descriptors: */
struct desc_struct tls_array[GDT_ENTRY_TLS_ENTRIES];
unsigned long sp0;
unsigned long sp;
#ifdef CONFIG_X86_32
unsigned long sysenter_cs;
#else
unsigned long usersp; /* Copy from PDA */
unsigned short es;
unsigned short ds;
unsigned short fsindex;
unsigned short gsindex;
#endif
#ifdef CONFIG_X86_32
unsigned long ip;
#endif
#ifdef CONFIG_X86_64
unsigned long fs;
#endif
unsigned long gs;
hw-breakpoints: Rewrite the hw-breakpoints layer on top of perf events This patch rebase the implementation of the breakpoints API on top of perf events instances. Each breakpoints are now perf events that handle the register scheduling, thread/cpu attachment, etc.. The new layering is now made as follows: ptrace kgdb ftrace perf syscall \ | / / \ | / / / Core breakpoint API / / | / | / Breakpoints perf events | | Breakpoints PMU ---- Debug Register constraints handling (Part of core breakpoint API) | | Hardware debug registers Reasons of this rewrite: - Use the centralized/optimized pmu registers scheduling, implying an easier arch integration - More powerful register handling: perf attributes (pinned/flexible events, exclusive/non-exclusive, tunable period, etc...) Impact: - New perf ABI: the hardware breakpoints counters - Ptrace breakpoints setting remains tricky and still needs some per thread breakpoints references. Todo (in the order): - Support breakpoints perf counter events for perf tools (ie: implement perf_bpcounter_event()) - Support from perf tools Changes in v2: - Follow the perf "event " rename - The ptrace regression have been fixed (ptrace breakpoint perf events weren't released when a task ended) - Drop the struct hw_breakpoint and store generic fields in perf_event_attr. - Separate core and arch specific headers, drop asm-generic/hw_breakpoint.h and create linux/hw_breakpoint.h - Use new generic len/type for breakpoint - Handle off case: when breakpoints api is not supported by an arch Changes in v3: - Fix broken CONFIG_KVM, we need to propagate the breakpoint api changes to kvm when we exit the guest and restore the bp registers to the host. Changes in v4: - Drop the hw_breakpoint_restore() stub as it is only used by KVM - EXPORT_SYMBOL_GPL hw_breakpoint_restore() as KVM can be built as a module - Restore the breakpoints unconditionally on kvm guest exit: TIF_DEBUG_THREAD doesn't anymore cover every cases of running breakpoints and vcpu->arch.switch_db_regs might not always be set when the guest used debug registers. (Waiting for a reliable optimization) Changes in v5: - Split-up the asm-generic/hw-breakpoint.h moving to linux/hw_breakpoint.h into a separate patch - Optimize the breakpoints restoring while switching from kvm guest to host. We only want to restore the state if we have active breakpoints to the host, otherwise we don't care about messed-up address registers. - Add asm/hw_breakpoint.h to Kbuild - Fix bad breakpoint type in trace_selftest.c Changes in v6: - Fix wrong header inclusion in trace.h (triggered a build error with CONFIG_FTRACE_SELFTEST Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com> Cc: Prasad <prasad@linux.vnet.ibm.com> Cc: Alan Stern <stern@rowland.harvard.edu> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Steven Rostedt <rostedt@goodmis.org> Cc: Ingo Molnar <mingo@elte.hu> Cc: Jan Kiszka <jan.kiszka@web.de> Cc: Jiri Slaby <jirislaby@gmail.com> Cc: Li Zefan <lizf@cn.fujitsu.com> Cc: Avi Kivity <avi@redhat.com> Cc: Paul Mackerras <paulus@samba.org> Cc: Mike Galbraith <efault@gmx.de> Cc: Masami Hiramatsu <mhiramat@redhat.com> Cc: Paul Mundt <lethal@linux-sh.org>
2009-09-09 11:22:48 -06:00
/* Save middle states of ptrace breakpoints */
struct perf_event *ptrace_bps[HBP_NUM];
/* Debug status used for traps, single steps, etc... */
unsigned long debugreg6;
/* Keep track of the exact dr7 value set by the user */
unsigned long ptrace_dr7;
/* Fault info: */
unsigned long cr2;
unsigned long trap_nr;
unsigned long error_code;
/* floating point and extended processor state */
struct fpu fpu;
#ifdef CONFIG_X86_32
/* Virtual 86 mode info */
struct vm86_struct __user *vm86_info;
unsigned long screen_bitmap;
unsigned long v86flags;
unsigned long v86mask;
unsigned long saved_sp0;
unsigned int saved_fs;
unsigned int saved_gs;
#endif
/* IO permissions: */
unsigned long *io_bitmap_ptr;
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;
};
/*
* Set IOPL bits in EFLAGS from given mask
*/
static inline void native_set_iopl_mask(unsigned mask)
{
#ifdef CONFIG_X86_32
unsigned int reg;
asm volatile ("pushfl;"
"popl %0;"
"andl %1, %0;"
"orl %2, %0;"
"pushl %0;"
"popfl"
: "=&r" (reg)
: "i" (~X86_EFLAGS_IOPL), "r" (mask));
#endif
}
static inline void
native_load_sp0(struct tss_struct *tss, struct thread_struct *thread)
{
tss->x86_tss.sp0 = thread->sp0;
#ifdef CONFIG_X86_32
/* Only happens when SEP is enabled, no need to test "SEP"arately: */
if (unlikely(tss->x86_tss.ss1 != thread->sysenter_cs)) {
tss->x86_tss.ss1 = thread->sysenter_cs;
wrmsr(MSR_IA32_SYSENTER_CS, thread->sysenter_cs, 0);
}
#endif
}
static inline void native_swapgs(void)
{
#ifdef CONFIG_X86_64
asm volatile("swapgs" ::: "memory");
#endif
}
static inline unsigned long this_cpu_sp0(void)
{
return this_cpu_read_stable(init_tss.x86_tss.sp0);
}
#ifdef CONFIG_PARAVIRT
#include <asm/paravirt.h>
#else
#define __cpuid native_cpuid
#define paravirt_enabled() 0
static inline void load_sp0(struct tss_struct *tss,
struct thread_struct *thread)
{
native_load_sp0(tss, thread);
}
#define set_iopl_mask native_set_iopl_mask
#endif /* CONFIG_PARAVIRT */
typedef struct {
unsigned long seg;
} mm_segment_t;
/* Free all resources held by a thread. */
extern void release_thread(struct task_struct *);
unsigned long get_wchan(struct task_struct *p);
/*
* Generic CPUID function
* clear %ecx since some cpus (Cyrix MII) do not set or clear %ecx
* resulting in stale register contents being returned.
*/
static inline void cpuid(unsigned int op,
unsigned int *eax, unsigned int *ebx,
unsigned int *ecx, unsigned int *edx)
{
*eax = op;
*ecx = 0;
__cpuid(eax, ebx, ecx, edx);
}
/* Some CPUID calls want 'count' to be placed in ecx */
static inline void cpuid_count(unsigned int op, int count,
unsigned int *eax, unsigned int *ebx,
unsigned int *ecx, unsigned int *edx)
{
*eax = op;
*ecx = count;
__cpuid(eax, ebx, ecx, edx);
}
/*
* CPUID functions returning a single datum
*/
static inline unsigned int cpuid_eax(unsigned int op)
{
unsigned int eax, ebx, ecx, edx;
cpuid(op, &eax, &ebx, &ecx, &edx);
return eax;
}
static inline unsigned int cpuid_ebx(unsigned int op)
{
unsigned int eax, ebx, ecx, edx;
cpuid(op, &eax, &ebx, &ecx, &edx);
return ebx;
}
static inline unsigned int cpuid_ecx(unsigned int op)
{
unsigned int eax, ebx, ecx, edx;
cpuid(op, &eax, &ebx, &ecx, &edx);
return ecx;
}
static inline unsigned int cpuid_edx(unsigned int op)
{
unsigned int eax, ebx, ecx, edx;
cpuid(op, &eax, &ebx, &ecx, &edx);
return edx;
}
/* REP NOP (PAUSE) is a good thing to insert into busy-wait loops. */
static inline void rep_nop(void)
{
asm volatile("rep; nop" ::: "memory");
}
static inline void cpu_relax(void)
{
rep_nop();
}
arch, locking: Ciao arch_mutex_cpu_relax() The arch_mutex_cpu_relax() function, introduced by 34b133f, is hacky and ugly. It was added a few years ago to address the fact that common cpu_relax() calls include yielding on s390, and thus impact the optimistic spinning functionality of mutexes. Nowadays we use this function well beyond mutexes: rwsem, qrwlock, mcs and lockref. Since the macro that defines the call is in the mutex header, any users must include mutex.h and the naming is misleading as well. This patch (i) renames the call to cpu_relax_lowlatency ("relax, but only if you can do it with very low latency") and (ii) defines it in each arch's asm/processor.h local header, just like for regular cpu_relax functions. On all archs, except s390, cpu_relax_lowlatency is simply cpu_relax, and thus we can take it out of mutex.h. While this can seem redundant, I believe it is a good choice as it allows us to move out arch specific logic from generic locking primitives and enables future(?) archs to transparently define it, similarly to System Z. Signed-off-by: Davidlohr Bueso <davidlohr@hp.com> Signed-off-by: Peter Zijlstra <peterz@infradead.org> Cc: Andrew Morton <akpm@linux-foundation.org> Cc: Anton Blanchard <anton@samba.org> Cc: Aurelien Jacquiot <a-jacquiot@ti.com> Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org> Cc: Bharat Bhushan <r65777@freescale.com> Cc: Catalin Marinas <catalin.marinas@arm.com> Cc: Chen Liqin <liqin.linux@gmail.com> Cc: Chris Metcalf <cmetcalf@tilera.com> Cc: Christian Borntraeger <borntraeger@de.ibm.com> Cc: Chris Zankel <chris@zankel.net> Cc: David Howells <dhowells@redhat.com> Cc: David S. Miller <davem@davemloft.net> Cc: Deepthi Dharwar <deepthi@linux.vnet.ibm.com> Cc: Dominik Dingel <dingel@linux.vnet.ibm.com> Cc: Fenghua Yu <fenghua.yu@intel.com> Cc: Geert Uytterhoeven <geert@linux-m68k.org> Cc: Guan Xuetao <gxt@mprc.pku.edu.cn> Cc: Haavard Skinnemoen <hskinnemoen@gmail.com> Cc: Hans-Christian Egtvedt <egtvedt@samfundet.no> Cc: Heiko Carstens <heiko.carstens@de.ibm.com> Cc: Helge Deller <deller@gmx.de> Cc: Hirokazu Takata <takata@linux-m32r.org> Cc: Ivan Kokshaysky <ink@jurassic.park.msu.ru> Cc: James E.J. Bottomley <jejb@parisc-linux.org> Cc: James Hogan <james.hogan@imgtec.com> Cc: Jason Wang <jasowang@redhat.com> Cc: Jesper Nilsson <jesper.nilsson@axis.com> Cc: Joe Perches <joe@perches.com> Cc: Jonas Bonn <jonas@southpole.se> Cc: Joseph Myers <joseph@codesourcery.com> Cc: Kees Cook <keescook@chromium.org> Cc: Koichi Yasutake <yasutake.koichi@jp.panasonic.com> Cc: Lennox Wu <lennox.wu@gmail.com> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Mark Salter <msalter@redhat.com> Cc: Martin Schwidefsky <schwidefsky@de.ibm.com> Cc: Matt Turner <mattst88@gmail.com> Cc: Max Filippov <jcmvbkbc@gmail.com> Cc: Michael Neuling <mikey@neuling.org> Cc: Michal Simek <monstr@monstr.eu> Cc: Mikael Starvik <starvik@axis.com> Cc: Nicolas Pitre <nico@linaro.org> Cc: Paolo Bonzini <pbonzini@redhat.com> Cc: Paul Burton <paul.burton@imgtec.com> Cc: Paul E. McKenney <paulmck@linux.vnet.ibm.com> Cc: Paul Gortmaker <paul.gortmaker@windriver.com> Cc: Paul Mackerras <paulus@samba.org> Cc: Qais Yousef <qais.yousef@imgtec.com> Cc: Qiaowei Ren <qiaowei.ren@intel.com> Cc: Rafael Wysocki <rafael.j.wysocki@intel.com> Cc: Ralf Baechle <ralf@linux-mips.org> Cc: Richard Henderson <rth@twiddle.net> Cc: Richard Kuo <rkuo@codeaurora.org> Cc: Russell King <linux@arm.linux.org.uk> Cc: Steven Miao <realmz6@gmail.com> Cc: Steven Rostedt <srostedt@redhat.com> Cc: Stratos Karafotis <stratosk@semaphore.gr> Cc: Tim Chen <tim.c.chen@linux.intel.com> Cc: Tony Luck <tony.luck@intel.com> Cc: Vasily Kulikov <segoon@openwall.com> Cc: Vineet Gupta <vgupta@synopsys.com> Cc: Vineet Gupta <Vineet.Gupta1@synopsys.com> Cc: Waiman Long <Waiman.Long@hp.com> Cc: Will Deacon <will.deacon@arm.com> Cc: Wolfram Sang <wsa@the-dreams.de> Cc: adi-buildroot-devel@lists.sourceforge.net Cc: linux390@de.ibm.com Cc: linux-alpha@vger.kernel.org Cc: linux-am33-list@redhat.com Cc: linux-arm-kernel@lists.infradead.org Cc: linux-c6x-dev@linux-c6x.org Cc: linux-cris-kernel@axis.com Cc: linux-hexagon@vger.kernel.org Cc: linux-ia64@vger.kernel.org Cc: linux@lists.openrisc.net Cc: linux-m32r-ja@ml.linux-m32r.org Cc: linux-m32r@ml.linux-m32r.org Cc: linux-m68k@lists.linux-m68k.org Cc: linux-metag@vger.kernel.org Cc: linux-mips@linux-mips.org Cc: linux-parisc@vger.kernel.org Cc: linuxppc-dev@lists.ozlabs.org Cc: linux-s390@vger.kernel.org Cc: linux-sh@vger.kernel.org Cc: linux-xtensa@linux-xtensa.org Cc: sparclinux@vger.kernel.org Link: http://lkml.kernel.org/r/1404079773.2619.4.camel@buesod1.americas.hpqcorp.net Signed-off-by: Ingo Molnar <mingo@kernel.org>
2014-06-29 16:09:33 -06:00
#define cpu_relax_lowlatency() cpu_relax()
/* Stop speculative execution and prefetching of modified code. */
static inline void sync_core(void)
{
int tmp;
#ifdef CONFIG_M486
/*
* Do a CPUID if available, otherwise do a jump. The jump
* can conveniently enough be the jump around CPUID.
*/
asm volatile("cmpl %2,%1\n\t"
"jl 1f\n\t"
"cpuid\n"
"1:"
: "=a" (tmp)
: "rm" (boot_cpu_data.cpuid_level), "ri" (0), "0" (1)
: "ebx", "ecx", "edx", "memory");
#else
/*
* CPUID is a barrier to speculative execution.
* Prefetched instructions are automatically
* invalidated when modified.
*/
asm volatile("cpuid"
: "=a" (tmp)
: "0" (1)
: "ebx", "ecx", "edx", "memory");
#endif
}
extern void select_idle_routine(const struct cpuinfo_x86 *c);
extern void init_amd_e400_c1e_mask(void);
extern unsigned long boot_option_idle_override;
extern bool amd_e400_c1e_detected;
enum idle_boot_override {IDLE_NO_OVERRIDE=0, IDLE_HALT, IDLE_NOMWAIT,
IDLE_POLL};
extern void enable_sep_cpu(void);
extern int sysenter_setup(void);
extern void early_trap_init(void);
x86, 64bit: Use a #PF handler to materialize early mappings on demand Linear mode (CR0.PG = 0) is mutually exclusive with 64-bit mode; all 64-bit code has to use page tables. This makes it awkward before we have first set up properly all-covering page tables to access objects that are outside the static kernel range. So far we have dealt with that simply by mapping a fixed amount of low memory, but that fails in at least two upcoming use cases: 1. We will support load and run kernel, struct boot_params, ramdisk, command line, etc. above the 4 GiB mark. 2. need to access ramdisk early to get microcode to update that as early possible. We could use early_iomap to access them too, but it will make code to messy and hard to be unified with 32 bit. Hence, set up a #PF table and use a fixed number of buffers to set up page tables on demand. If the buffers fill up then we simply flush them and start over. These buffers are all in __initdata, so it does not increase RAM usage at runtime. Thus, with the help of the #PF handler, we can set the final kernel mapping from blank, and switch to init_level4_pgt later. During the switchover in head_64.S, before #PF handler is available, we use three pages to handle kernel crossing 1G, 512G boundaries with sharing page by playing games with page aliasing: the same page is mapped twice in the higher-level tables with appropriate wraparound. The kernel region itself will be properly mapped; other mappings may be spurious. early_make_pgtable is using kernel high mapping address to access pages to set page table. -v4: Add phys_base offset to make kexec happy, and add init_mapping_kernel() - Yinghai -v5: fix compiling with xen, and add back ident level3 and level2 for xen also move back init_level4_pgt from BSS to DATA again. because we have to clear it anyway. - Yinghai -v6: switch to init_level4_pgt in init_mem_mapping. - Yinghai -v7: remove not needed clear_page for init_level4_page it is with fill 512,8,0 already in head_64.S - Yinghai -v8: we need to keep that handler alive until init_mem_mapping and don't let early_trap_init to trash that early #PF handler. So split early_trap_pf_init out and move it down. - Yinghai -v9: switchover only cover kernel space instead of 1G so could avoid touch possible mem holes. - Yinghai -v11: change far jmp back to far return to initial_code, that is needed to fix failure that is reported by Konrad on AMD systems. - Yinghai Signed-off-by: Yinghai Lu <yinghai@kernel.org> Link: http://lkml.kernel.org/r/1359058816-7615-12-git-send-email-yinghai@kernel.org Signed-off-by: H. Peter Anvin <hpa@linux.intel.com>
2013-01-24 13:19:52 -07:00
void early_trap_pf_init(void);
/* Defined in head.S */
extern struct desc_ptr early_gdt_descr;
extern void cpu_set_gdt(int);
extern void switch_to_new_gdt(int);
extern void load_percpu_segment(int);
extern void cpu_init(void);
static inline unsigned long get_debugctlmsr(void)
{
unsigned long debugctlmsr = 0;
#ifndef CONFIG_X86_DEBUGCTLMSR
if (boot_cpu_data.x86 < 6)
return 0;
#endif
rdmsrl(MSR_IA32_DEBUGCTLMSR, debugctlmsr);
return debugctlmsr;
}
static inline void update_debugctlmsr(unsigned long debugctlmsr)
{
#ifndef CONFIG_X86_DEBUGCTLMSR
if (boot_cpu_data.x86 < 6)
return;
#endif
wrmsrl(MSR_IA32_DEBUGCTLMSR, debugctlmsr);
}
extern void set_task_blockstep(struct task_struct *task, bool on);
/*
* from system description table in BIOS. Mostly for MCA use, but
* others may find it useful:
*/
extern unsigned int machine_id;
extern unsigned int machine_submodel_id;
extern unsigned int BIOS_revision;
/* Boot loader type from the setup header: */
extern int bootloader_type;
extern int bootloader_version;
extern char ignore_fpu_irq;
#define HAVE_ARCH_PICK_MMAP_LAYOUT 1
#define ARCH_HAS_PREFETCHW
#define ARCH_HAS_SPINLOCK_PREFETCH
#ifdef CONFIG_X86_32
# define BASE_PREFETCH ""
# define ARCH_HAS_PREFETCH
#else
# define BASE_PREFETCH "prefetcht0 %P1"
#endif
/*
* Prefetch instructions for Pentium III (+) and AMD Athlon (+)
*
* It's not worth to care about 3dnow prefetches for the K6
* because they are microcoded there and very slow.
*/
static inline void prefetch(const void *x)
{
alternative_input(BASE_PREFETCH, "prefetchnta %P1",
X86_FEATURE_XMM,
"m" (*(const char *)x));
}
/*
* 3dnow prefetch to get an exclusive cache line.
* Useful for spinlocks to avoid one state transition in the
* cache coherency protocol:
*/
static inline void prefetchw(const void *x)
{
alternative_input(BASE_PREFETCH, "prefetchw %P1",
X86_FEATURE_3DNOWPREFETCH,
"m" (*(const char *)x));
}
static inline void spin_lock_prefetch(const void *x)
{
prefetchw(x);
}
#ifdef CONFIG_X86_32
/*
* User space process size: 3GB (default).
*/
#define TASK_SIZE PAGE_OFFSET
#define TASK_SIZE_MAX TASK_SIZE
#define STACK_TOP TASK_SIZE
#define STACK_TOP_MAX STACK_TOP
#define INIT_THREAD { \
.sp0 = sizeof(init_stack) + (long)&init_stack, \
.vm86_info = NULL, \
.sysenter_cs = __KERNEL_CS, \
.io_bitmap_ptr = NULL, \
}
/*
* Note that the .io_bitmap member must be extra-big. This is because
* the CPU will access an additional byte beyond the end of the IO
* permission bitmap. The extra byte must be all 1 bits, and must
* be within the limit.
*/
#define INIT_TSS { \
.x86_tss = { \
.sp0 = sizeof(init_stack) + (long)&init_stack, \
.ss0 = __KERNEL_DS, \
.ss1 = __KERNEL_CS, \
.io_bitmap_base = INVALID_IO_BITMAP_OFFSET, \
}, \
.io_bitmap = { [0 ... IO_BITMAP_LONGS] = ~0 }, \
}
extern unsigned long thread_saved_pc(struct task_struct *tsk);
#define THREAD_SIZE_LONGS (THREAD_SIZE/sizeof(unsigned long))
#define KSTK_TOP(info) \
({ \
unsigned long *__ptr = (unsigned long *)(info); \
(unsigned long)(&__ptr[THREAD_SIZE_LONGS]); \
})
/*
* The below -8 is to reserve 8 bytes on top of the ring0 stack.
* This is necessary to guarantee that the entire "struct pt_regs"
* is accessible even if the CPU haven't stored the SS/ESP registers
* on the stack (interrupt gate does not save these registers
* when switching to the same priv ring).
* Therefore beware: accessing the ss/esp fields of the
* "struct pt_regs" is possible, but they may contain the
* completely wrong values.
*/
#define task_pt_regs(task) \
({ \
struct pt_regs *__regs__; \
__regs__ = (struct pt_regs *)(KSTK_TOP(task_stack_page(task))-8); \
__regs__ - 1; \
})
#define KSTK_ESP(task) (task_pt_regs(task)->sp)
#else
/*
* User space process size. 47bits minus one guard page. The guard
* page is necessary on Intel CPUs: if a SYSCALL instruction is at
* the highest possible canonical userspace address, then that
* syscall will enter the kernel with a non-canonical return
* address, and SYSRET will explode dangerously. We avoid this
* particular problem by preventing anything from being mapped
* at the maximum canonical address.
*/
#define TASK_SIZE_MAX ((1UL << 47) - PAGE_SIZE)
/* This decides where the kernel will search for a free chunk of vm
* space during mmap's.
*/
#define IA32_PAGE_OFFSET ((current->personality & ADDR_LIMIT_3GB) ? \
0xc0000000 : 0xFFFFe000)
#define TASK_SIZE (test_thread_flag(TIF_ADDR32) ? \
IA32_PAGE_OFFSET : TASK_SIZE_MAX)
#define TASK_SIZE_OF(child) ((test_tsk_thread_flag(child, TIF_ADDR32)) ? \
IA32_PAGE_OFFSET : TASK_SIZE_MAX)
#define STACK_TOP TASK_SIZE
#define STACK_TOP_MAX TASK_SIZE_MAX
#define INIT_THREAD { \
.sp0 = (unsigned long)&init_stack + sizeof(init_stack) \
}
#define INIT_TSS { \
.x86_tss.sp0 = (unsigned long)&init_stack + sizeof(init_stack) \
}
/*
* Return saved PC of a blocked thread.
* What is this good for? it will be always the scheduler or ret_from_fork.
*/
#define thread_saved_pc(t) (*(unsigned long *)((t)->thread.sp - 8))
#define task_pt_regs(tsk) ((struct pt_regs *)(tsk)->thread.sp0 - 1)
extern unsigned long KSTK_ESP(struct task_struct *task);
/*
* User space RSP while inside the SYSCALL fast path
*/
DECLARE_PER_CPU(unsigned long, old_rsp);
#endif /* CONFIG_X86_64 */
extern void start_thread(struct pt_regs *regs, unsigned long new_ip,
unsigned long new_sp);
/*
* This decides where the kernel will search for a free chunk of vm
* space during mmap's.
*/
#define TASK_UNMAPPED_BASE (PAGE_ALIGN(TASK_SIZE / 3))
#define KSTK_EIP(task) (task_pt_regs(task)->ip)
/* Get/set a process' ability to use the timestamp counter instruction */
#define GET_TSC_CTL(adr) get_tsc_mode((adr))
#define SET_TSC_CTL(val) set_tsc_mode((val))
extern int get_tsc_mode(unsigned long adr);
extern int set_tsc_mode(unsigned int val);
x86, mpx: On-demand kernel allocation of bounds tables This is really the meat of the MPX patch set. If there is one patch to review in the entire series, this is the one. There is a new ABI here and this kernel code also interacts with userspace memory in a relatively unusual manner. (small FAQ below). Long Description: This patch adds two prctl() commands to provide enable or disable the management of bounds tables in kernel, including on-demand kernel allocation (See the patch "on-demand kernel allocation of bounds tables") and cleanup (See the patch "cleanup unused bound tables"). Applications do not strictly need the kernel to manage bounds tables and we expect some applications to use MPX without taking advantage of this kernel support. This means the kernel can not simply infer whether an application needs bounds table management from the MPX registers. The prctl() is an explicit signal from userspace. PR_MPX_ENABLE_MANAGEMENT is meant to be a signal from userspace to require kernel's help in managing bounds tables. PR_MPX_DISABLE_MANAGEMENT is the opposite, meaning that userspace don't want kernel's help any more. With PR_MPX_DISABLE_MANAGEMENT, the kernel won't allocate and free bounds tables even if the CPU supports MPX. PR_MPX_ENABLE_MANAGEMENT will fetch the base address of the bounds directory out of a userspace register (bndcfgu) and then cache it into a new field (->bd_addr) in the 'mm_struct'. PR_MPX_DISABLE_MANAGEMENT will set "bd_addr" to an invalid address. Using this scheme, we can use "bd_addr" to determine whether the management of bounds tables in kernel is enabled. Also, the only way to access that bndcfgu register is via an xsaves, which can be expensive. Caching "bd_addr" like this also helps reduce the cost of those xsaves when doing table cleanup at munmap() time. Unfortunately, we can not apply this optimization to #BR fault time because we need an xsave to get the value of BNDSTATUS. ==== Why does the hardware even have these Bounds Tables? ==== MPX only has 4 hardware registers for storing bounds information. If MPX-enabled code needs more than these 4 registers, it needs to spill them somewhere. It has two special instructions for this which allow the bounds to be moved between the bounds registers and some new "bounds tables". They are similar conceptually to a page fault and will be raised by the MPX hardware during both bounds violations or when the tables are not present. This patch handles those #BR exceptions for not-present tables by carving the space out of the normal processes address space (essentially calling the new mmap() interface indroduced earlier in this patch set.) and then pointing the bounds-directory over to it. The tables *need* to be accessed and controlled by userspace because the instructions for moving bounds in and out of them are extremely frequent. They potentially happen every time a register pointing to memory is dereferenced. Any direct kernel involvement (like a syscall) to access the tables would obviously destroy performance. ==== Why not do this in userspace? ==== This patch is obviously doing this allocation in the kernel. However, MPX does not strictly *require* anything in the kernel. It can theoretically be done completely from userspace. Here are a few ways this *could* be done. I don't think any of them are practical in the real-world, but here they are. Q: Can virtual space simply be reserved for the bounds tables so that we never have to allocate them? A: As noted earlier, these tables are *HUGE*. An X-GB virtual area needs 4*X GB of virtual space, plus 2GB for the bounds directory. If we were to preallocate them for the 128TB of user virtual address space, we would need to reserve 512TB+2GB, which is larger than the entire virtual address space today. This means they can not be reserved ahead of time. Also, a single process's pre-popualated bounds directory consumes 2GB of virtual *AND* physical memory. IOW, it's completely infeasible to prepopulate bounds directories. Q: Can we preallocate bounds table space at the same time memory is allocated which might contain pointers that might eventually need bounds tables? A: This would work if we could hook the site of each and every memory allocation syscall. This can be done for small, constrained applications. But, it isn't practical at a larger scale since a given app has no way of controlling how all the parts of the app might allocate memory (think libraries). The kernel is really the only place to intercept these calls. Q: Could a bounds fault be handed to userspace and the tables allocated there in a signal handler instead of in the kernel? A: (thanks to tglx) mmap() is not on the list of safe async handler functions and even if mmap() would work it still requires locking or nasty tricks to keep track of the allocation state there. Having ruled out all of the userspace-only approaches for managing bounds tables that we could think of, we create them on demand in the kernel. Based-on-patch-by: Qiaowei Ren <qiaowei.ren@intel.com> Signed-off-by: Dave Hansen <dave.hansen@linux.intel.com> Cc: linux-mm@kvack.org Cc: linux-mips@linux-mips.org Cc: Dave Hansen <dave@sr71.net> Link: http://lkml.kernel.org/r/20141114151829.AD4310DE@viggo.jf.intel.com Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
2014-11-14 08:18:29 -07:00
/* Register/unregister a process' MPX related resource */
#define MPX_ENABLE_MANAGEMENT(tsk) mpx_enable_management((tsk))
#define MPX_DISABLE_MANAGEMENT(tsk) mpx_disable_management((tsk))
#ifdef CONFIG_X86_INTEL_MPX
extern int mpx_enable_management(struct task_struct *tsk);
extern int mpx_disable_management(struct task_struct *tsk);
#else
static inline int mpx_enable_management(struct task_struct *tsk)
{
return -EINVAL;
}
static inline int mpx_disable_management(struct task_struct *tsk)
{
return -EINVAL;
}
#endif /* CONFIG_X86_INTEL_MPX */
extern u16 amd_get_nb_id(int cpu);
static inline uint32_t hypervisor_cpuid_base(const char *sig, uint32_t leaves)
{
uint32_t base, eax, signature[3];
for (base = 0x40000000; base < 0x40010000; base += 0x100) {
cpuid(base, &eax, &signature[0], &signature[1], &signature[2]);
if (!memcmp(sig, signature, 12) &&
(leaves == 0 || ((eax - base) >= leaves)))
return base;
}
return 0;
}
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);
#ifdef CONFIG_XEN
bool xen_set_default_idle(void);
#else
#define xen_set_default_idle 0
#endif
void stop_this_cpu(void *dummy);
void df_debug(struct pt_regs *regs, long error_code);
#endif /* _ASM_X86_PROCESSOR_H */