diff options
Diffstat (limited to 'arch/x86/um')
| -rw-r--r-- | arch/x86/um/Kconfig | 12 | ||||
| -rw-r--r-- | arch/x86/um/Makefile | 3 | ||||
| -rw-r--r-- | arch/x86/um/asm/barrier.h | 75 | ||||
| -rw-r--r-- | arch/x86/um/asm/processor.h | 10 | ||||
| -rw-r--r-- | arch/x86/um/asm/processor_32.h | 10 | ||||
| -rw-r--r-- | arch/x86/um/asm/processor_64.h | 10 | ||||
| -rw-r--r-- | arch/x86/um/asm/system.h | 135 | ||||
| -rw-r--r-- | arch/x86/um/bugs_32.c | 4 | ||||
| -rw-r--r-- | arch/x86/um/mem_32.c | 8 | ||||
| -rw-r--r-- | arch/x86/um/shared/sysdep/ptrace.h | 10 | ||||
| -rw-r--r-- | arch/x86/um/sys_call_table_32.S | 26 | ||||
| -rw-r--r-- | arch/x86/um/sys_call_table_32.c | 55 | ||||
| -rw-r--r-- | arch/x86/um/sys_call_table_64.c | 36 | ||||
| -rw-r--r-- | arch/x86/um/user-offsets.c | 17 | ||||
| -rw-r--r-- | arch/x86/um/vdso/vma.c | 3 |
15 files changed, 189 insertions, 225 deletions
diff --git a/arch/x86/um/Kconfig b/arch/x86/um/Kconfig index 1d97bd8..9926e11 100644 --- a/arch/x86/um/Kconfig +++ b/arch/x86/um/Kconfig @@ -6,14 +6,6 @@ menu "UML-specific options" menu "Host processor type and features" -config CMPXCHG_LOCAL - bool - default n - -config CMPXCHG_DOUBLE - bool - default n - source "arch/x86/Kconfig.cpu" endmenu @@ -23,8 +15,8 @@ config UML_X86 select GENERIC_FIND_FIRST_BIT config 64BIT - bool - default SUBARCH = "x86_64" + bool "64-bit kernel" if SUBARCH = "x86" + default SUBARCH != "i386" config X86_32 def_bool !64BIT diff --git a/arch/x86/um/Makefile b/arch/x86/um/Makefile index 8fb5840..5d065b2 100644 --- a/arch/x86/um/Makefile +++ b/arch/x86/um/Makefile @@ -37,7 +37,8 @@ subarch-$(CONFIG_MODULES) += ../kernel/module.o USER_OBJS := bugs_$(BITS).o ptrace_user.o fault.o extra-y += user-offsets.s -$(obj)/user-offsets.s: c_flags = -Wp,-MD,$(depfile) $(USER_CFLAGS) +$(obj)/user-offsets.s: c_flags = -Wp,-MD,$(depfile) $(USER_CFLAGS) \ + -Iarch/x86/include/generated UNPROFILE_OBJS := stub_segv.o CFLAGS_stub_segv.o := $(CFLAGS_NO_HARDENING) diff --git a/arch/x86/um/asm/barrier.h b/arch/x86/um/asm/barrier.h new file mode 100644 index 0000000..7d01b8c --- /dev/null +++ b/arch/x86/um/asm/barrier.h @@ -0,0 +1,75 @@ +#ifndef _ASM_UM_BARRIER_H_ +#define _ASM_UM_BARRIER_H_ + +#include <asm/asm.h> +#include <asm/segment.h> +#include <asm/cpufeature.h> +#include <asm/cmpxchg.h> +#include <asm/nops.h> + +#include <linux/kernel.h> +#include <linux/irqflags.h> + +/* + * Force strict CPU ordering. + * And yes, this is required on UP too when we're talking + * to devices. + */ +#ifdef CONFIG_X86_32 + +#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 /* CONFIG_X86_32 */ + +#define mb() asm volatile("mfence" : : : "memory") +#define rmb() asm volatile("lfence" : : : "memory") +#define wmb() asm volatile("sfence" : : : "memory") + +#endif /* CONFIG_X86_32 */ + +#define read_barrier_depends() do { } while (0) + +#ifdef CONFIG_SMP + +#define smp_mb() mb() +#ifdef CONFIG_X86_PPRO_FENCE +#define smp_rmb() rmb() +#else /* CONFIG_X86_PPRO_FENCE */ +#define smp_rmb() barrier() +#endif /* CONFIG_X86_PPRO_FENCE */ + +#ifdef CONFIG_X86_OOSTORE +#define smp_wmb() wmb() +#else /* CONFIG_X86_OOSTORE */ +#define smp_wmb() barrier() +#endif /* CONFIG_X86_OOSTORE */ + +#define smp_read_barrier_depends() read_barrier_depends() +#define set_mb(var, value) do { (void)xchg(&var, value); } while (0) + +#else /* CONFIG_SMP */ + +#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 /* CONFIG_SMP */ + +/* + * 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 inline void rdtsc_barrier(void) +{ + alternative(ASM_NOP3, "mfence", X86_FEATURE_MFENCE_RDTSC); + alternative(ASM_NOP3, "lfence", X86_FEATURE_LFENCE_RDTSC); +} + +#endif diff --git a/arch/x86/um/asm/processor.h b/arch/x86/um/asm/processor.h index 2c32df6..04f82e0 100644 --- a/arch/x86/um/asm/processor.h +++ b/arch/x86/um/asm/processor.h @@ -17,6 +17,16 @@ #define ARCH_IS_STACKGROW(address) \ (address + 65536 + 32 * sizeof(unsigned long) >= UPT_SP(¤t->thread.regs.regs)) +#include <asm/user.h> + +/* REP NOP (PAUSE) is a good thing to insert into busy-wait loops. */ +static inline void rep_nop(void) +{ + __asm__ __volatile__("rep;nop": : :"memory"); +} + +#define cpu_relax() rep_nop() + #include <asm/processor-generic.h> #endif diff --git a/arch/x86/um/asm/processor_32.h b/arch/x86/um/asm/processor_32.h index 018f732..6c6689e 100644 --- a/arch/x86/um/asm/processor_32.h +++ b/arch/x86/um/asm/processor_32.h @@ -45,16 +45,6 @@ static inline void arch_copy_thread(struct arch_thread *from, memcpy(&to->tls_array, &from->tls_array, sizeof(from->tls_array)); } -#include <asm/user.h> - -/* REP NOP (PAUSE) is a good thing to insert into busy-wait loops. */ -static inline void rep_nop(void) -{ - __asm__ __volatile__("rep;nop": : :"memory"); -} - -#define cpu_relax() rep_nop() - /* * Default implementation of macro that returns current * instruction pointer ("program counter"). Stolen diff --git a/arch/x86/um/asm/processor_64.h b/arch/x86/um/asm/processor_64.h index 61de92d..4b02a84 100644 --- a/arch/x86/um/asm/processor_64.h +++ b/arch/x86/um/asm/processor_64.h @@ -14,14 +14,6 @@ struct arch_thread { struct faultinfo faultinfo; }; -/* REP NOP (PAUSE) is a good thing to insert into busy-wait loops. */ -static inline void rep_nop(void) -{ - __asm__ __volatile__("rep;nop": : :"memory"); -} - -#define cpu_relax() rep_nop() - #define INIT_ARCH_THREAD { .debugregs = { [ 0 ... 7 ] = 0 }, \ .debugregs_seq = 0, \ .fs = 0, \ @@ -37,8 +29,6 @@ static inline void arch_copy_thread(struct arch_thread *from, to->fs = from->fs; } -#include <asm/user.h> - #define current_text_addr() \ ({ void *pc; __asm__("movq $1f,%0\n1:":"=g" (pc)); pc; }) diff --git a/arch/x86/um/asm/system.h b/arch/x86/um/asm/system.h deleted file mode 100644 index a459fd9..0000000 --- a/arch/x86/um/asm/system.h +++ /dev/null @@ -1,135 +0,0 @@ -#ifndef _ASM_X86_SYSTEM_H_ -#define _ASM_X86_SYSTEM_H_ - -#include <asm/asm.h> -#include <asm/segment.h> -#include <asm/cpufeature.h> -#include <asm/cmpxchg.h> -#include <asm/nops.h> - -#include <linux/kernel.h> -#include <linux/irqflags.h> - -/* entries in ARCH_DLINFO: */ -#ifdef CONFIG_IA32_EMULATION -# define AT_VECTOR_SIZE_ARCH 2 -#else -# define AT_VECTOR_SIZE_ARCH 1 -#endif - -extern unsigned long arch_align_stack(unsigned long sp); - -void default_idle(void); - -/* - * 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 inline void rdtsc_barrier(void) -{ - alternative(ASM_NOP3, "mfence", X86_FEATURE_MFENCE_RDTSC); - alternative(ASM_NOP3, "lfence", X86_FEATURE_LFENCE_RDTSC); -} - -extern void *_switch_to(void *prev, void *next, void *last); -#define switch_to(prev, next, last) prev = _switch_to(prev, next, last) - -#endif diff --git a/arch/x86/um/bugs_32.c b/arch/x86/um/bugs_32.c index a1fba5f..17d88cf 100644 --- a/arch/x86/um/bugs_32.c +++ b/arch/x86/um/bugs_32.c @@ -13,8 +13,6 @@ static int host_has_cmov = 1; static jmp_buf cmov_test_return; -#define TASK_PID(task) *((int *) &(((char *) (task))[HOST_TASK_PID])) - static void cmov_sigill_test_handler(int sig) { host_has_cmov = 0; @@ -51,7 +49,7 @@ void arch_examine_signal(int sig, struct uml_pt_regs *regs) * This is testing for a cmov (0x0f 0x4x) instruction causing a * SIGILL in init. */ - if ((sig != SIGILL) || (TASK_PID(get_current()) != 1)) + if ((sig != SIGILL) || (get_current_pid() != 1)) return; if (copy_from_user_proc(tmp, (void *) UPT_IP(regs), 2)) { diff --git a/arch/x86/um/mem_32.c b/arch/x86/um/mem_32.c index 639900a..f40281e 100644 --- a/arch/x86/um/mem_32.c +++ b/arch/x86/um/mem_32.c @@ -23,14 +23,6 @@ static int __init gate_vma_init(void) gate_vma.vm_flags = VM_READ | VM_MAYREAD | VM_EXEC | VM_MAYEXEC; gate_vma.vm_page_prot = __P101; - /* - * Make sure the vDSO gets into every core dump. - * Dumping its contents makes post-mortem fully interpretable later - * without matching up the same kernel and hardware config to see - * what PC values meant. - */ - gate_vma.vm_flags |= VM_ALWAYSDUMP; - return 0; } __initcall(gate_vma_init); diff --git a/arch/x86/um/shared/sysdep/ptrace.h b/arch/x86/um/shared/sysdep/ptrace.h index 711b162..2bbe1ec2 100644 --- a/arch/x86/um/shared/sysdep/ptrace.h +++ b/arch/x86/um/shared/sysdep/ptrace.h @@ -1,5 +1,15 @@ +#ifndef __SYSDEP_X86_PTRACE_H +#define __SYSDEP_X86_PTRACE_H + #ifdef __i386__ #include "ptrace_32.h" #else #include "ptrace_64.h" #endif + +static inline long regs_return_value(struct uml_pt_regs *regs) +{ + return UPT_SYSCALL_RET(regs); +} + +#endif /* __SYSDEP_X86_PTRACE_H */ diff --git a/arch/x86/um/sys_call_table_32.S b/arch/x86/um/sys_call_table_32.S deleted file mode 100644 index a7ca80d..0000000 --- a/arch/x86/um/sys_call_table_32.S +++ /dev/null @@ -1,26 +0,0 @@ -#include <linux/linkage.h> -/* Steal i386 syscall table for our purposes, but with some slight changes.*/ - -#define sys_iopl sys_ni_syscall -#define sys_ioperm sys_ni_syscall - -#define sys_vm86old sys_ni_syscall -#define sys_vm86 sys_ni_syscall - -#define old_mmap sys_old_mmap - -#define ptregs_fork sys_fork -#define ptregs_execve sys_execve -#define ptregs_iopl sys_iopl -#define ptregs_vm86old sys_vm86old -#define ptregs_clone sys_clone -#define ptregs_vm86 sys_vm86 -#define ptregs_sigaltstack sys_sigaltstack -#define ptregs_vfork sys_vfork - -.section .rodata,"a" - -#include "../kernel/syscall_table_32.S" - -ENTRY(syscall_table_size) -.long .-sys_call_table diff --git a/arch/x86/um/sys_call_table_32.c b/arch/x86/um/sys_call_table_32.c new file mode 100644 index 0000000..416bd40 --- /dev/null +++ b/arch/x86/um/sys_call_table_32.c @@ -0,0 +1,55 @@ +/* + * System call table for UML/i386, copied from arch/x86/kernel/syscall_*.c + * with some changes for UML. + */ + +#include <linux/linkage.h> +#include <linux/sys.h> +#include <linux/cache.h> +#include <generated/user_constants.h> + +#define __NO_STUBS + +/* + * Below you can see, in terms of #define's, the differences between the x86-64 + * and the UML syscall table. + */ + +/* Not going to be implemented by UML, since we have no hardware. */ +#define sys_iopl sys_ni_syscall +#define sys_ioperm sys_ni_syscall + +#define sys_vm86old sys_ni_syscall +#define sys_vm86 sys_ni_syscall + +#define old_mmap sys_old_mmap + +#define ptregs_fork sys_fork +#define ptregs_execve sys_execve +#define ptregs_iopl sys_iopl +#define ptregs_vm86old sys_vm86old +#define ptregs_clone sys_clone +#define ptregs_vm86 sys_vm86 +#define ptregs_sigaltstack sys_sigaltstack +#define ptregs_vfork sys_vfork + +#define __SYSCALL_I386(nr, sym, compat) extern asmlinkage void sym(void) ; +#include <asm/syscalls_32.h> + +#undef __SYSCALL_I386 +#define __SYSCALL_I386(nr, sym, compat) [ nr ] = sym, + +typedef void (*sys_call_ptr_t)(void); + +extern void sys_ni_syscall(void); + +const sys_call_ptr_t sys_call_table[] __cacheline_aligned = { + /* + * Smells like a compiler bug -- it doesn't work + * when the & below is removed. + */ + [0 ... __NR_syscall_max] = &sys_ni_syscall, +#include <asm/syscalls_32.h> +}; + +int syscall_table_size = sizeof(sys_call_table); diff --git a/arch/x86/um/sys_call_table_64.c b/arch/x86/um/sys_call_table_64.c index 99522f7..9924776 100644 --- a/arch/x86/um/sys_call_table_64.c +++ b/arch/x86/um/sys_call_table_64.c @@ -1,11 +1,12 @@ /* - * System call table for UML/x86-64, copied from arch/x86_64/kernel/syscall.c + * System call table for UML/x86-64, copied from arch/x86/kernel/syscall_*.c * with some changes for UML. */ #include <linux/linkage.h> #include <linux/sys.h> #include <linux/cache.h> +#include <generated/user_constants.h> #define __NO_STUBS @@ -34,31 +35,26 @@ #define stub_sigaltstack sys_sigaltstack #define stub_rt_sigreturn sys_rt_sigreturn -#define __SYSCALL(nr, sym) extern asmlinkage void sym(void) ; -#undef _ASM_X86_UNISTD_64_H -#include "../../x86/include/asm/unistd_64.h" +#define __SYSCALL_COMMON(nr, sym, compat) __SYSCALL_64(nr, sym, compat) +#define __SYSCALL_X32(nr, sym, compat) /* Not supported */ -#undef __SYSCALL -#define __SYSCALL(nr, sym) [ nr ] = sym, -#undef _ASM_X86_UNISTD_64_H +#define __SYSCALL_64(nr, sym, compat) extern asmlinkage void sym(void) ; +#include <asm/syscalls_64.h> + +#undef __SYSCALL_64 +#define __SYSCALL_64(nr, sym, compat) [ nr ] = sym, typedef void (*sys_call_ptr_t)(void); extern void sys_ni_syscall(void); -/* - * We used to have a trick here which made sure that holes in the - * x86_64 table were filled in with sys_ni_syscall, but a comment in - * unistd_64.h says that holes aren't allowed, so the trick was - * removed. - * The trick looked like this - * [0 ... UM_NR_syscall_max] = &sys_ni_syscall - * before including unistd_64.h - the later initializations overwrote - * the sys_ni_syscall filler. - */ - -sys_call_ptr_t sys_call_table[] __cacheline_aligned = { -#include <asm/unistd_64.h> +const sys_call_ptr_t sys_call_table[] __cacheline_aligned = { + /* + * Smells like a compiler bug -- it doesn't work + * when the & below is removed. + */ + [0 ... __NR_syscall_max] = &sys_ni_syscall, +#include <asm/syscalls_64.h> }; int syscall_table_size = sizeof(sys_call_table); diff --git a/arch/x86/um/user-offsets.c b/arch/x86/um/user-offsets.c index ca49be8..ce7e360 100644 --- a/arch/x86/um/user-offsets.c +++ b/arch/x86/um/user-offsets.c @@ -8,6 +8,20 @@ #include <asm/ptrace.h> #include <asm/types.h> +#ifdef __i386__ +#define __SYSCALL_I386(nr, sym, compat) [nr] = 1, +static char syscalls[] = { +#include <asm/syscalls_32.h> +}; +#else +#define __SYSCALL_64(nr, sym, compat) [nr] = 1, +#define __SYSCALL_COMMON(nr, sym, compat) [nr] = 1, +#define __SYSCALL_X32(nr, sym, compat) /* Not supported */ +static char syscalls[] = { +#include <asm/syscalls_64.h> +}; +#endif + #define DEFINE(sym, val) \ asm volatile("\n->" #sym " %0 " #val : : "i" (val)) @@ -77,4 +91,7 @@ void foo(void) DEFINE(UM_PROT_READ, PROT_READ); DEFINE(UM_PROT_WRITE, PROT_WRITE); DEFINE(UM_PROT_EXEC, PROT_EXEC); + + DEFINE(__NR_syscall_max, sizeof(syscalls) - 1); + DEFINE(NR_syscalls, sizeof(syscalls)); } diff --git a/arch/x86/um/vdso/vma.c b/arch/x86/um/vdso/vma.c index 91f4ec9..af91901 100644 --- a/arch/x86/um/vdso/vma.c +++ b/arch/x86/um/vdso/vma.c @@ -64,8 +64,7 @@ int arch_setup_additional_pages(struct linux_binprm *bprm, int uses_interp) err = install_special_mapping(mm, um_vdso_addr, PAGE_SIZE, VM_READ|VM_EXEC| - VM_MAYREAD|VM_MAYWRITE|VM_MAYEXEC| - VM_ALWAYSDUMP, + VM_MAYREAD|VM_MAYWRITE|VM_MAYEXEC, vdsop); up_write(&mm->mmap_sem); |