diff options
Diffstat (limited to 'arch/x86/um')
34 files changed, 477 insertions, 402 deletions
diff --git a/arch/x86/um/Kconfig b/arch/x86/um/Kconfig index 986045d5e638..44b12e45f9a0 100644 --- a/arch/x86/um/Kconfig +++ b/arch/x86/um/Kconfig @@ -8,9 +8,12 @@ endmenu config UML_X86 def_bool y - select ARCH_BINFMT_ELF_EXTRA_PHDRS if X86_32 + select ARCH_USE_QUEUED_RWLOCKS + select ARCH_SUPPORTS_ATOMIC_RMW + select ARCH_USE_QUEUED_SPINLOCKS select DCACHE_WORD_ACCESS select HAVE_EFFICIENT_UNALIGNED_ACCESS + select UML_SUBARCH_SUPPORTS_SMP if X86_CX8 config 64BIT bool "64-bit kernel" if "$(SUBARCH)" = "x86" @@ -32,8 +35,5 @@ config X86_64 config ARCH_HAS_SC_SIGNALS def_bool !64BIT -config ARCH_REUSE_HOST_VSYSCALL_AREA - def_bool !64BIT - config GENERIC_HWEIGHT def_bool y diff --git a/arch/x86/um/Makefile b/arch/x86/um/Makefile index b42c31cd2390..f9ea75bf43ac 100644 --- a/arch/x86/um/Makefile +++ b/arch/x86/um/Makefile @@ -13,12 +13,11 @@ obj-y = bugs_$(BITS).o delay.o fault.o \ ptrace.o ptrace_$(BITS).o ptrace_user.o setjmp_$(BITS).o signal.o \ stub_segv.o \ sys_call_table_$(BITS).o sysrq_$(BITS).o tls_$(BITS).o \ - mem_$(BITS).o subarch.o os-Linux/ + subarch.o os-Linux/ ifeq ($(CONFIG_X86_32),y) obj-y += syscalls_32.o -obj-$(CONFIG_ELF_CORE) += elfcore.o subarch-y = ../lib/string_32.o ../lib/atomic64_32.o ../lib/atomic64_cx8_32.o subarch-y += ../lib/cmpxchg8b_emu.o ../lib/atomic64_386_32.o @@ -27,7 +26,7 @@ subarch-y += ../kernel/sys_ia32.o else -obj-y += syscalls_64.o vdso/ +obj-y += mem_64.o syscalls_64.o vdso/ subarch-y = ../lib/csum-partial_64.o ../lib/memcpy_64.o \ ../lib/memmove_64.o ../lib/memset_64.o diff --git a/arch/x86/um/asm/archparam.h b/arch/x86/um/asm/archparam.h deleted file mode 100644 index c17cf68dda0f..000000000000 --- a/arch/x86/um/asm/archparam.h +++ /dev/null @@ -1,20 +0,0 @@ -/* - * Copyright (C) 2000 - 2003 Jeff Dike (jdike@addtoit.com) - * Copyright 2003 PathScale, Inc. - * Licensed under the GPL - */ - -#ifndef __UM_ARCHPARAM_H -#define __UM_ARCHPARAM_H - -#ifdef CONFIG_X86_32 - -#ifdef CONFIG_X86_PAE -#define LAST_PKMAP 512 -#else -#define LAST_PKMAP 1024 -#endif - -#endif - -#endif diff --git a/arch/x86/um/asm/barrier.h b/arch/x86/um/asm/barrier.h index 4da336965698..b51aefd6ec2b 100644 --- a/arch/x86/um/asm/barrier.h +++ b/arch/x86/um/asm/barrier.h @@ -12,9 +12,9 @@ */ #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) +#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 */ diff --git a/arch/x86/um/asm/checksum.h b/arch/x86/um/asm/checksum.h index b07824500363..ddc144657efa 100644 --- a/arch/x86/um/asm/checksum.h +++ b/arch/x86/um/asm/checksum.h @@ -20,6 +20,9 @@ */ extern __wsum csum_partial(const void *buff, int len, __wsum sum); +/* Do not call this directly. Declared for export type visibility. */ +extern __visible __wsum csum_partial_copy_generic(const void *src, void *dst, int len); + /** * csum_fold - Fold and invert a 32bit checksum. * sum: 32bit unfolded sum diff --git a/arch/x86/um/asm/elf.h b/arch/x86/um/asm/elf.h index 62ed5d68a978..22d0111b543b 100644 --- a/arch/x86/um/asm/elf.h +++ b/arch/x86/um/asm/elf.h @@ -68,35 +68,7 @@ pr_reg[16] = PT_REGS_SS(regs); \ } while (0); -extern char * elf_aux_platform; -#define ELF_PLATFORM (elf_aux_platform) - -extern unsigned long vsyscall_ehdr; -extern unsigned long vsyscall_end; -extern unsigned long __kernel_vsyscall; - -/* - * This is the range that is readable by user mode, and things - * acting like user mode such as get_user_pages. - */ -#define FIXADDR_USER_START vsyscall_ehdr -#define FIXADDR_USER_END vsyscall_end - - -/* - * Architecture-neutral AT_ values in 0-17, leave some room - * for more of them, start the x86-specific ones at 32. - */ -#define AT_SYSINFO 32 -#define AT_SYSINFO_EHDR 33 - -#define ARCH_DLINFO \ -do { \ - if ( vsyscall_ehdr ) { \ - NEW_AUX_ENT(AT_SYSINFO, __kernel_vsyscall); \ - NEW_AUX_ENT(AT_SYSINFO_EHDR, vsyscall_ehdr); \ - } \ -} while (0) +#define ELF_PLATFORM_FALLBACK "i586" #else @@ -177,11 +149,7 @@ do { \ (pr_reg)[25] = 0; \ (pr_reg)[26] = 0; -#define ELF_PLATFORM "x86_64" - -/* No user-accessible fixmap addresses, i.e. vsyscall */ -#define FIXADDR_USER_START 0 -#define FIXADDR_USER_END 0 +#define ELF_PLATFORM_FALLBACK "x86_64" #define ARCH_HAS_SETUP_ADDITIONAL_PAGES 1 struct linux_binprm; @@ -210,6 +178,9 @@ struct task_struct; extern long elf_aux_hwcap; #define ELF_HWCAP (elf_aux_hwcap) +extern char *elf_aux_platform; +#define ELF_PLATFORM (elf_aux_platform ?: ELF_PLATFORM_FALLBACK) + #define SET_PERSONALITY(ex) do {} while(0) #endif diff --git a/arch/x86/um/asm/module.h b/arch/x86/um/asm/module.h deleted file mode 100644 index a3b061d66082..000000000000 --- a/arch/x86/um/asm/module.h +++ /dev/null @@ -1,24 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -#ifndef __UM_MODULE_H -#define __UM_MODULE_H - -/* UML is simple */ -struct mod_arch_specific -{ -}; - -#ifdef CONFIG_X86_32 - -#define Elf_Shdr Elf32_Shdr -#define Elf_Sym Elf32_Sym -#define Elf_Ehdr Elf32_Ehdr - -#else - -#define Elf_Shdr Elf64_Shdr -#define Elf_Sym Elf64_Sym -#define Elf_Ehdr Elf64_Ehdr - -#endif - -#endif diff --git a/arch/x86/um/asm/processor.h b/arch/x86/um/asm/processor.h index 478710384b34..e222d2ae28fd 100644 --- a/arch/x86/um/asm/processor.h +++ b/arch/x86/um/asm/processor.h @@ -21,10 +21,10 @@ #include <asm/user.h> -/* REP NOP (PAUSE) is a good thing to insert into busy-wait loops. */ -static __always_inline void rep_nop(void) +/* PAUSE is a good thing to insert into busy-wait loops. */ +static __always_inline void native_pause(void) { - __asm__ __volatile__("rep;nop": : :"memory"); + __asm__ __volatile__("pause": : :"memory"); } static __always_inline void cpu_relax(void) @@ -33,7 +33,7 @@ static __always_inline void cpu_relax(void) time_travel_mode == TT_MODE_EXTERNAL) time_travel_ndelay(1); else - rep_nop(); + native_pause(); } #define task_pt_regs(t) (&(t)->thread.regs) diff --git a/arch/x86/um/asm/spinlock.h b/arch/x86/um/asm/spinlock.h new file mode 100644 index 000000000000..20fc77514214 --- /dev/null +++ b/arch/x86/um/asm/spinlock.h @@ -0,0 +1,8 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef __ASM_UM_SPINLOCK_H +#define __ASM_UM_SPINLOCK_H + +#include <asm/qspinlock.h> +#include <asm/qrwlock.h> + +#endif /* __ASM_UM_SPINLOCK_H */ diff --git a/arch/x86/um/asm/syscall.h b/arch/x86/um/asm/syscall.h index 56a2f0913e3c..d6208d0fad51 100644 --- a/arch/x86/um/asm/syscall.h +++ b/arch/x86/um/asm/syscall.h @@ -9,6 +9,8 @@ typedef asmlinkage long (*sys_call_ptr_t)(unsigned long, unsigned long, unsigned long, unsigned long, unsigned long, unsigned long); +extern const sys_call_ptr_t sys_call_table[]; + static inline int syscall_get_arch(struct task_struct *task) { #ifdef CONFIG_X86_32 diff --git a/arch/x86/um/asm/vm-flags.h b/arch/x86/um/asm/vm-flags.h index df7a3896f5dd..622d36d6ddff 100644 --- a/arch/x86/um/asm/vm-flags.h +++ b/arch/x86/um/asm/vm-flags.h @@ -9,11 +9,11 @@ #ifdef CONFIG_X86_32 -#define VM_DATA_DEFAULT_FLAGS VM_DATA_FLAGS_TSK_EXEC +#define VMA_DATA_DEFAULT_FLAGS VMA_DATA_FLAGS_TSK_EXEC #else -#define VM_STACK_DEFAULT_FLAGS (VM_GROWSDOWN | VM_DATA_FLAGS_EXEC) +#define VMA_STACK_DEFAULT_FLAGS append_vma_flags(VMA_DATA_FLAGS_EXEC, VMA_GROWSDOWN_BIT) #endif #endif diff --git a/arch/x86/um/elfcore.c b/arch/x86/um/elfcore.c deleted file mode 100644 index ef50662fc40d..000000000000 --- a/arch/x86/um/elfcore.c +++ /dev/null @@ -1,78 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0 -#include <linux/elf.h> -#include <linux/elfcore.h> -#include <linux/coredump.h> -#include <linux/fs.h> -#include <linux/mm.h> - -#include <asm/elf.h> - - -Elf32_Half elf_core_extra_phdrs(struct coredump_params *cprm) -{ - return vsyscall_ehdr ? (((struct elfhdr *)vsyscall_ehdr)->e_phnum) : 0; -} - -int elf_core_write_extra_phdrs(struct coredump_params *cprm, loff_t offset) -{ - if ( vsyscall_ehdr ) { - const struct elfhdr *const ehdrp = - (struct elfhdr *) vsyscall_ehdr; - const struct elf_phdr *const phdrp = - (const struct elf_phdr *) (vsyscall_ehdr + ehdrp->e_phoff); - int i; - Elf32_Off ofs = 0; - - for (i = 0; i < ehdrp->e_phnum; ++i) { - struct elf_phdr phdr = phdrp[i]; - - if (phdr.p_type == PT_LOAD) { - ofs = phdr.p_offset = offset; - offset += phdr.p_filesz; - } else { - phdr.p_offset += ofs; - } - phdr.p_paddr = 0; /* match other core phdrs */ - if (!dump_emit(cprm, &phdr, sizeof(phdr))) - return 0; - } - } - return 1; -} - -int elf_core_write_extra_data(struct coredump_params *cprm) -{ - if ( vsyscall_ehdr ) { - const struct elfhdr *const ehdrp = - (struct elfhdr *) vsyscall_ehdr; - const struct elf_phdr *const phdrp = - (const struct elf_phdr *) (vsyscall_ehdr + ehdrp->e_phoff); - int i; - - for (i = 0; i < ehdrp->e_phnum; ++i) { - if (phdrp[i].p_type == PT_LOAD) { - void *addr = (void *) phdrp[i].p_vaddr; - size_t filesz = phdrp[i].p_filesz; - if (!dump_emit(cprm, addr, filesz)) - return 0; - } - } - } - return 1; -} - -size_t elf_core_extra_data_size(struct coredump_params *cprm) -{ - if ( vsyscall_ehdr ) { - const struct elfhdr *const ehdrp = - (struct elfhdr *)vsyscall_ehdr; - const struct elf_phdr *const phdrp = - (const struct elf_phdr *) (vsyscall_ehdr + ehdrp->e_phoff); - int i; - - for (i = 0; i < ehdrp->e_phnum; ++i) - if (phdrp[i].p_type == PT_LOAD) - return (size_t) phdrp[i].p_filesz; - } - return 0; -} diff --git a/arch/x86/um/mem_32.c b/arch/x86/um/mem_32.c deleted file mode 100644 index 29b2203bc82c..000000000000 --- a/arch/x86/um/mem_32.c +++ /dev/null @@ -1,50 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0-only -/* - * Copyright (C) 2011 Richard Weinberger <richrd@nod.at> - */ - -#include <linux/mm.h> -#include <asm/elf.h> - -static struct vm_area_struct gate_vma; - -static int __init gate_vma_init(void) -{ - if (!FIXADDR_USER_START) - return 0; - - vma_init(&gate_vma, NULL); - gate_vma.vm_start = FIXADDR_USER_START; - gate_vma.vm_end = FIXADDR_USER_END; - vm_flags_init(&gate_vma, VM_READ | VM_MAYREAD | VM_EXEC | VM_MAYEXEC); - gate_vma.vm_page_prot = PAGE_READONLY; - - return 0; -} -__initcall(gate_vma_init); - -struct vm_area_struct *get_gate_vma(struct mm_struct *mm) -{ - return FIXADDR_USER_START ? &gate_vma : NULL; -} - -int in_gate_area_no_mm(unsigned long addr) -{ - if (!FIXADDR_USER_START) - return 0; - - if ((addr >= FIXADDR_USER_START) && (addr < FIXADDR_USER_END)) - return 1; - - return 0; -} - -int in_gate_area(struct mm_struct *mm, unsigned long addr) -{ - struct vm_area_struct *vma = get_gate_vma(mm); - - if (!vma) - return 0; - - return (addr >= vma->vm_start) && (addr < vma->vm_end); -} diff --git a/arch/x86/um/os-Linux/mcontext.c b/arch/x86/um/os-Linux/mcontext.c index e80ab7d28117..b1580df80b3f 100644 --- a/arch/x86/um/os-Linux/mcontext.c +++ b/arch/x86/um/os-Linux/mcontext.c @@ -1,9 +1,19 @@ // SPDX-License-Identifier: GPL-2.0 -#include <sys/ucontext.h> #define __FRAME_OFFSETS +#include <linux/errno.h> +#include <linux/string.h> +#include <sys/ucontext.h> #include <asm/ptrace.h> +/* + * musl defines struct sigcontext in <bits/signal.h>. Rename the kernel's + * copy to avoid redefinition while keeping the FP-state types available. + */ +#define sigcontext __kernel_sigcontext +#include <asm/sigcontext.h> +#undef sigcontext #include <sysdep/ptrace.h> #include <sysdep/mcontext.h> +#include <arch.h> void get_regs_from_mc(struct uml_pt_regs *regs, mcontext_t *mc) { @@ -17,6 +27,10 @@ void get_regs_from_mc(struct uml_pt_regs *regs, mcontext_t *mc) COPY2(UESP, ESP); /* sic */ COPY(EBX); COPY(EDX); COPY(ECX); COPY(EAX); COPY(EIP); COPY_SEG_CPL3(CS); COPY(EFL); COPY_SEG_CPL3(SS); +#undef COPY2 +#undef COPY +#undef COPY_SEG +#undef COPY_SEG_CPL3 #else #define COPY2(X,Y) regs->gp[X/sizeof(unsigned long)] = mc->gregs[REG_##Y] #define COPY(X) regs->gp[X/sizeof(unsigned long)] = mc->gregs[REG_##X] @@ -27,7 +41,226 @@ void get_regs_from_mc(struct uml_pt_regs *regs, mcontext_t *mc) COPY(RIP); COPY2(EFLAGS, EFL); COPY2(CS, CSGSFS); - regs->gp[CS / sizeof(unsigned long)] &= 0xffff; - regs->gp[CS / sizeof(unsigned long)] |= 3; + regs->gp[SS / sizeof(unsigned long)] = mc->gregs[REG_CSGSFS] >> 48; +#undef COPY2 +#undef COPY +#endif +} + +void mc_set_rip(void *_mc, void *target) +{ + mcontext_t *mc = _mc; + +#ifdef __i386__ + mc->gregs[REG_EIP] = (unsigned long)target; +#else + mc->gregs[REG_RIP] = (unsigned long)target; #endif } + +/* Same thing, but the copy macros are turned around. */ +void get_mc_from_regs(struct uml_pt_regs *regs, mcontext_t *mc, int single_stepping) +{ +#ifdef __i386__ +#define COPY2(X,Y) mc->gregs[REG_##Y] = regs->gp[X] +#define COPY(X) mc->gregs[REG_##X] = regs->gp[X] +#define COPY_SEG(X) mc->gregs[REG_##X] = regs->gp[X] & 0xffff; +#define COPY_SEG_CPL3(X) mc->gregs[REG_##X] = (regs->gp[X] & 0xffff) | 3; + COPY_SEG(GS); COPY_SEG(FS); COPY_SEG(ES); COPY_SEG(DS); + COPY(EDI); COPY(ESI); COPY(EBP); + COPY2(UESP, ESP); /* sic */ + COPY(EBX); COPY(EDX); COPY(ECX); COPY(EAX); + COPY(EIP); COPY_SEG_CPL3(CS); COPY(EFL); COPY_SEG_CPL3(SS); +#else +#define COPY2(X,Y) mc->gregs[REG_##Y] = regs->gp[X/sizeof(unsigned long)] +#define COPY(X) mc->gregs[REG_##X] = regs->gp[X/sizeof(unsigned long)] + COPY(R8); COPY(R9); COPY(R10); COPY(R11); + COPY(R12); COPY(R13); COPY(R14); COPY(R15); + COPY(RDI); COPY(RSI); COPY(RBP); COPY(RBX); + COPY(RDX); COPY(RAX); COPY(RCX); COPY(RSP); + COPY(RIP); + COPY2(EFLAGS, EFL); + mc->gregs[REG_CSGSFS] = mc->gregs[REG_CSGSFS] & 0xffffffffffffl; + mc->gregs[REG_CSGSFS] |= (regs->gp[SS / sizeof(unsigned long)] & 0xffff) << 48; +#endif + + if (single_stepping) + mc->gregs[REG_EFL] |= X86_EFLAGS_TF; + else + mc->gregs[REG_EFL] &= ~X86_EFLAGS_TF; +} + +#ifdef CONFIG_X86_32 +struct _xstate_64 { + struct _fpstate_64 fpstate; + struct _header xstate_hdr; + struct _ymmh_state ymmh; + /* New processor state extensions go here: */ +}; + +/* Not quite the right structures as these contain more information */ +int um_i387_from_fxsr(struct _fpstate_32 *i387, + const struct _fpstate_64 *fxsave); +int um_fxsr_from_i387(struct _fpstate_64 *fxsave, + const struct _fpstate_32 *from); +#else +#define _xstate_64 _xstate +#endif + +static struct _fpstate *get_fpstate(struct stub_data *data, + mcontext_t *mcontext, + int *fp_size) +{ + struct _fpstate *res; + + /* Assume floating point registers are on the same page */ + res = (void *)(((unsigned long)mcontext->fpregs & + (UM_KERN_PAGE_SIZE - 1)) + + (unsigned long)&data->sigstack[0]); + + if ((void *)res + sizeof(struct _fpstate) > + (void *)data->sigstack + sizeof(data->sigstack)) + return NULL; + + if (res->sw_reserved.magic1 != FP_XSTATE_MAGIC1) { + *fp_size = sizeof(struct _fpstate); + } else { + char *magic2_addr; + + magic2_addr = (void *)res; + magic2_addr += res->sw_reserved.extended_size; + magic2_addr -= FP_XSTATE_MAGIC2_SIZE; + + /* We still need to be within our stack */ + if ((void *)magic2_addr > + (void *)data->sigstack + sizeof(data->sigstack)) + return NULL; + + /* If we do not read MAGIC2, then we did something wrong */ + if (*(__u32 *)magic2_addr != FP_XSTATE_MAGIC2) + return NULL; + + /* Remove MAGIC2 from the size, we do not save/restore it */ + *fp_size = res->sw_reserved.extended_size - + FP_XSTATE_MAGIC2_SIZE; + } + + return res; +} + +int get_stub_state(struct uml_pt_regs *regs, struct stub_data *data, + unsigned long *fp_size_out) +{ + mcontext_t *mcontext; + struct _fpstate *fpstate_stub; + struct _xstate_64 *xstate_stub; + int fp_size, xstate_size; + + /* mctx_offset is verified by wait_stub_done_seccomp */ + mcontext = (void *)&data->sigstack[data->mctx_offset]; + + get_regs_from_mc(regs, mcontext); + + fpstate_stub = get_fpstate(data, mcontext, &fp_size); + if (!fpstate_stub) + return -EINVAL; + +#ifdef CONFIG_X86_32 + xstate_stub = (void *)&fpstate_stub->_fxsr_env; + xstate_size = fp_size - offsetof(struct _fpstate_32, _fxsr_env); +#else + xstate_stub = (void *)fpstate_stub; + xstate_size = fp_size; +#endif + + if (fp_size_out) + *fp_size_out = xstate_size; + + if (xstate_size > host_fp_size) + return -ENOSPC; + + memcpy(®s->fp, xstate_stub, xstate_size); + + /* We do not need to read the x86_64 FS_BASE/GS_BASE registers as + * we do not permit userspace to set them directly. + */ + +#ifdef CONFIG_X86_32 + /* Read the i387 legacy FP registers */ + if (um_fxsr_from_i387((void *)®s->fp, fpstate_stub)) + return -EINVAL; +#endif + + return 0; +} + +/* Copied because we cannot include regset.h here. */ +struct task_struct; +struct user_regset; +struct membuf { + void *p; + size_t left; +}; + +int fpregs_legacy_get(struct task_struct *target, + const struct user_regset *regset, + struct membuf to); + +int set_stub_state(struct uml_pt_regs *regs, struct stub_data *data, + int single_stepping) +{ + mcontext_t *mcontext; + struct _fpstate *fpstate_stub; + struct _xstate_64 *xstate_stub; + int fp_size, xstate_size; + + /* mctx_offset is verified by wait_stub_done_seccomp */ + mcontext = (void *)&data->sigstack[data->mctx_offset]; + + if ((unsigned long)mcontext < (unsigned long)data->sigstack || + (unsigned long)mcontext > + (unsigned long) data->sigstack + + sizeof(data->sigstack) - sizeof(*mcontext)) + return -EINVAL; + + get_mc_from_regs(regs, mcontext, single_stepping); + + fpstate_stub = get_fpstate(data, mcontext, &fp_size); + if (!fpstate_stub) + return -EINVAL; + +#ifdef CONFIG_X86_32 + xstate_stub = (void *)&fpstate_stub->_fxsr_env; + xstate_size = fp_size - offsetof(struct _fpstate_32, _fxsr_env); +#else + xstate_stub = (void *)fpstate_stub; + xstate_size = fp_size; +#endif + + memcpy(xstate_stub, ®s->fp, xstate_size); + +#ifdef __i386__ + /* + * On x86, the GDT entries are updated by arch_set_tls. + */ + + /* Store the i387 legacy FP registers which the host will use */ + if (um_i387_from_fxsr(fpstate_stub, (void *)®s->fp)) + return -EINVAL; +#else + /* + * On x86_64, we need to sync the FS_BASE/GS_BASE registers using the + * arch specific data. + */ + if (data->arch_data.fs_base != regs->gp[FS_BASE / sizeof(unsigned long)]) { + data->arch_data.fs_base = regs->gp[FS_BASE / sizeof(unsigned long)]; + data->arch_data.sync |= STUB_SYNC_FS_BASE; + } + if (data->arch_data.gs_base != regs->gp[GS_BASE / sizeof(unsigned long)]) { + data->arch_data.gs_base = regs->gp[GS_BASE / sizeof(unsigned long)]; + data->arch_data.sync |= STUB_SYNC_GS_BASE; + } +#endif + + return 0; +} diff --git a/arch/x86/um/os-Linux/registers.c b/arch/x86/um/os-Linux/registers.c index 76eaeb93928c..eb1cdadc8a61 100644 --- a/arch/x86/um/os-Linux/registers.c +++ b/arch/x86/um/os-Linux/registers.c @@ -18,6 +18,7 @@ #include <registers.h> #include <sys/mman.h> +static unsigned long ptrace_regset; unsigned long host_fp_size; int get_fp_registers(int pid, unsigned long *regs) @@ -27,7 +28,7 @@ int get_fp_registers(int pid, unsigned long *regs) .iov_len = host_fp_size, }; - if (ptrace(PTRACE_GETREGSET, pid, NT_X86_XSTATE, &iov) < 0) + if (ptrace(PTRACE_GETREGSET, pid, ptrace_regset, &iov) < 0) return -errno; return 0; } @@ -39,7 +40,7 @@ int put_fp_registers(int pid, unsigned long *regs) .iov_len = host_fp_size, }; - if (ptrace(PTRACE_SETREGSET, pid, NT_X86_XSTATE, &iov) < 0) + if (ptrace(PTRACE_SETREGSET, pid, ptrace_regset, &iov) < 0) return -errno; return 0; } @@ -58,9 +59,23 @@ int arch_init_registers(int pid) return -ENOMEM; /* GDB has x86_xsave_length, which uses x86_cpuid_count */ - ret = ptrace(PTRACE_GETREGSET, pid, NT_X86_XSTATE, &iov); + ptrace_regset = NT_X86_XSTATE; + ret = ptrace(PTRACE_GETREGSET, pid, ptrace_regset, &iov); if (ret) ret = -errno; + + if (ret == -ENODEV) { +#ifdef CONFIG_X86_32 + ptrace_regset = NT_PRXFPREG; +#else + ptrace_regset = NT_PRFPREG; +#endif + iov.iov_len = 2 * 1024 * 1024; + ret = ptrace(PTRACE_GETREGSET, pid, ptrace_regset, &iov); + if (ret) + ret = -errno; + } + munmap(iov.iov_base, 2 * 1024 * 1024); host_fp_size = iov.iov_len; diff --git a/arch/x86/um/ptrace.c b/arch/x86/um/ptrace.c index 57c504fd5626..2635ca2595a3 100644 --- a/arch/x86/um/ptrace.c +++ b/arch/x86/um/ptrace.c @@ -25,7 +25,8 @@ static inline unsigned short twd_i387_to_fxsr(unsigned short twd) return tmp; } -static inline unsigned long twd_fxsr_to_i387(struct user_fxsr_struct *fxsave) +static inline unsigned long +twd_fxsr_to_i387(const struct user_fxsr_struct *fxsave) { struct _fpxreg *st = NULL; unsigned long twd = (unsigned long) fxsave->twd; @@ -69,12 +70,16 @@ static inline unsigned long twd_fxsr_to_i387(struct user_fxsr_struct *fxsave) return ret; } -/* Get/set the old 32bit i387 registers (pre-FPX) */ -static int fpregs_legacy_get(struct task_struct *target, - const struct user_regset *regset, - struct membuf to) +/* + * Get/set the old 32bit i387 registers (pre-FPX) + * + * We provide simple wrappers for mcontext.c, they are only defined locally + * because mcontext.c is userspace facing and needs to a different definition + * of the structures. + */ +static int _um_i387_from_fxsr(struct membuf to, + const struct user_fxsr_struct *fxsave) { - struct user_fxsr_struct *fxsave = (void *)target->thread.regs.regs.fp; int i; membuf_store(&to, (unsigned long)fxsave->cwd | 0xffff0000ul); @@ -91,23 +96,36 @@ static int fpregs_legacy_get(struct task_struct *target, return 0; } -static int fpregs_legacy_set(struct task_struct *target, +int um_i387_from_fxsr(struct user_i387_struct *i387, + const struct user_fxsr_struct *fxsave); + +int um_i387_from_fxsr(struct user_i387_struct *i387, + const struct user_fxsr_struct *fxsave) +{ + struct membuf to = { + .p = i387, + .left = sizeof(*i387), + }; + + return _um_i387_from_fxsr(to, fxsave); +} + +static int fpregs_legacy_get(struct task_struct *target, const struct user_regset *regset, - unsigned int pos, unsigned int count, - const void *kbuf, const void __user *ubuf) + struct membuf to) { struct user_fxsr_struct *fxsave = (void *)target->thread.regs.regs.fp; - const struct user_i387_struct *from; - struct user_i387_struct buf; - int i; - if (ubuf) { - if (copy_from_user(&buf, ubuf, sizeof(buf))) - return -EFAULT; - from = &buf; - } else { - from = kbuf; - } + return _um_i387_from_fxsr(to, fxsave); +} + +int um_fxsr_from_i387(struct user_fxsr_struct *fxsave, + const struct user_i387_struct *from); + +int um_fxsr_from_i387(struct user_fxsr_struct *fxsave, + const struct user_i387_struct *from) +{ + int i; fxsave->cwd = (unsigned short)(from->cwd & 0xffff); fxsave->swd = (unsigned short)(from->swd & 0xffff); @@ -125,6 +143,26 @@ static int fpregs_legacy_set(struct task_struct *target, return 0; } + +static int fpregs_legacy_set(struct task_struct *target, + const struct user_regset *regset, + unsigned int pos, unsigned int count, + const void *kbuf, const void __user *ubuf) +{ + struct user_fxsr_struct *fxsave = (void *)target->thread.regs.regs.fp; + const struct user_i387_struct *from; + struct user_i387_struct buf; + + if (ubuf) { + if (copy_from_user(&buf, ubuf, sizeof(buf))) + return -EFAULT; + from = &buf; + } else { + from = kbuf; + } + + return um_fxsr_from_i387(fxsave, from); +} #endif static int genregs_get(struct task_struct *target, @@ -198,7 +236,7 @@ static int generic_fpregs_set(struct task_struct *target, static struct user_regset uml_regsets[] __ro_after_init = { [REGSET_GENERAL] = { - .core_note_type = NT_PRSTATUS, + USER_REGSET_NOTE_TYPE(PRSTATUS), .n = sizeof(struct user_regs_struct) / sizeof(long), .size = sizeof(long), .align = sizeof(long), @@ -208,7 +246,7 @@ static struct user_regset uml_regsets[] __ro_after_init = { #ifdef CONFIG_X86_32 /* Old FP registers, they are needed in signal frames */ [REGSET_FP_LEGACY] = { - .core_note_type = NT_PRFPREG, + USER_REGSET_NOTE_TYPE(PRFPREG), .n = sizeof(struct user_i387_ia32_struct) / sizeof(long), .size = sizeof(long), .align = sizeof(long), @@ -219,10 +257,10 @@ static struct user_regset uml_regsets[] __ro_after_init = { #endif [REGSET_FP] = { #ifdef CONFIG_X86_32 - .core_note_type = NT_PRXFPREG, + USER_REGSET_NOTE_TYPE(PRXFPREG), .n = sizeof(struct user32_fxsr_struct) / sizeof(long), #else - .core_note_type = NT_PRFPREG, + USER_REGSET_NOTE_TYPE(PRFPREG), .n = sizeof(struct user_i387_struct) / sizeof(long), #endif .size = sizeof(long), @@ -232,7 +270,7 @@ static struct user_regset uml_regsets[] __ro_after_init = { .set = generic_fpregs_set, }, [REGSET_XSTATE] = { - .core_note_type = NT_X86_XSTATE, + USER_REGSET_NOTE_TYPE(X86_XSTATE), .size = sizeof(long), .align = sizeof(long), .active = generic_fpregs_active, diff --git a/arch/x86/um/shared/sysdep/faultinfo_32.h b/arch/x86/um/shared/sysdep/faultinfo_32.h index b6f2437ec29c..9193a7790a71 100644 --- a/arch/x86/um/shared/sysdep/faultinfo_32.h +++ b/arch/x86/um/shared/sysdep/faultinfo_32.h @@ -29,4 +29,16 @@ struct faultinfo { #define PTRACE_FULL_FAULTINFO 0 +#define ___backtrack_faulted(_faulted) \ + asm volatile ( \ + "movl $__get_kernel_nofault_faulted_%=,%1\n" \ + "mov $0, %0\n" \ + "jmp _end_%=\n" \ + "__get_kernel_nofault_faulted_%=:\n" \ + "mov $1, %0;" \ + "_end_%=:" \ + : "=r" (_faulted), \ + "=m" (current->thread.segv_continue) :: \ + ) + #endif diff --git a/arch/x86/um/shared/sysdep/faultinfo_64.h b/arch/x86/um/shared/sysdep/faultinfo_64.h index ee88f88974ea..61e4ca1e0ab5 100644 --- a/arch/x86/um/shared/sysdep/faultinfo_64.h +++ b/arch/x86/um/shared/sysdep/faultinfo_64.h @@ -29,4 +29,16 @@ struct faultinfo { #define PTRACE_FULL_FAULTINFO 1 +#define ___backtrack_faulted(_faulted) \ + asm volatile ( \ + "movq $__get_kernel_nofault_faulted_%=,%1\n" \ + "mov $0, %0\n" \ + "jmp _end_%=\n" \ + "__get_kernel_nofault_faulted_%=:\n" \ + "mov $1, %0;" \ + "_end_%=:" \ + : "=r" (_faulted), \ + "=m" (current->thread.segv_continue) :: \ + ) + #endif diff --git a/arch/x86/um/shared/sysdep/kernel-offsets.h b/arch/x86/um/shared/sysdep/kernel-offsets.h deleted file mode 100644 index 48de3a71f845..000000000000 --- a/arch/x86/um/shared/sysdep/kernel-offsets.h +++ /dev/null @@ -1,15 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -#include <linux/stddef.h> -#include <linux/sched.h> -#include <linux/elf.h> -#include <linux/crypto.h> -#include <linux/kbuild.h> -#include <asm/mman.h> - -/* workaround for a warning with -Wmissing-prototypes */ -void foo(void); - -void foo(void) -{ -#include <common-offsets.h> -} diff --git a/arch/x86/um/shared/sysdep/mcontext.h b/arch/x86/um/shared/sysdep/mcontext.h index b724c54da316..6fe490cc5b98 100644 --- a/arch/x86/um/shared/sysdep/mcontext.h +++ b/arch/x86/um/shared/sysdep/mcontext.h @@ -6,7 +6,16 @@ #ifndef __SYS_SIGCONTEXT_X86_H #define __SYS_SIGCONTEXT_X86_H +#include <stub-data.h> + extern void get_regs_from_mc(struct uml_pt_regs *, mcontext_t *); +extern void get_mc_from_regs(struct uml_pt_regs *regs, mcontext_t *mc, + int single_stepping); + +extern int get_stub_state(struct uml_pt_regs *regs, struct stub_data *data, + unsigned long *fp_size_out); +extern int set_stub_state(struct uml_pt_regs *regs, struct stub_data *data, + int single_stepping); #ifdef __i386__ diff --git a/arch/x86/um/shared/sysdep/ptrace.h b/arch/x86/um/shared/sysdep/ptrace.h index 2dd4ca6713f8..572ea2d79131 100644 --- a/arch/x86/um/shared/sysdep/ptrace.h +++ b/arch/x86/um/shared/sysdep/ptrace.h @@ -44,18 +44,6 @@ #include "ptrace_64.h" #endif -struct syscall_args { - unsigned long args[6]; -}; - -#define SYSCALL_ARGS(r) ((struct syscall_args) \ - { .args = { UPT_SYSCALL_ARG1(r), \ - UPT_SYSCALL_ARG2(r), \ - UPT_SYSCALL_ARG3(r), \ - UPT_SYSCALL_ARG4(r), \ - UPT_SYSCALL_ARG5(r), \ - UPT_SYSCALL_ARG6(r) } } ) - extern unsigned long host_fp_size; struct uml_pt_regs { @@ -74,8 +62,6 @@ struct uml_pt_regs { #define UPT_FAULTINFO(r) (&(r)->faultinfo) #define UPT_IS_USER(r) ((r)->is_user) -extern int user_context(unsigned long sp); - extern int arch_init_registers(int pid); #endif /* __SYSDEP_X86_PTRACE_H */ diff --git a/arch/x86/um/shared/sysdep/stub-data.h b/arch/x86/um/shared/sysdep/stub-data.h new file mode 100644 index 000000000000..82b1b7f8ac3d --- /dev/null +++ b/arch/x86/um/shared/sysdep/stub-data.h @@ -0,0 +1,23 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef __ARCH_STUB_DATA_H +#define __ARCH_STUB_DATA_H + +#ifdef __i386__ +#include <generated/asm-offsets.h> +#include <asm/ldt.h> + +struct stub_data_arch { + int sync; + struct user_desc tls[UM_KERN_GDT_ENTRY_TLS_ENTRIES]; +}; +#else +#define STUB_SYNC_FS_BASE (1 << 0) +#define STUB_SYNC_GS_BASE (1 << 1) +struct stub_data_arch { + int sync; + unsigned long fs_base; + unsigned long gs_base; +}; +#endif + +#endif /* __ARCH_STUB_DATA_H */ diff --git a/arch/x86/um/shared/sysdep/stub.h b/arch/x86/um/shared/sysdep/stub.h index dc89f4423454..4fa58f5b4fca 100644 --- a/arch/x86/um/shared/sysdep/stub.h +++ b/arch/x86/um/shared/sysdep/stub.h @@ -13,3 +13,5 @@ extern void stub_segv_handler(int, siginfo_t *, void *); extern void stub_syscall_handler(void); +extern void stub_signal_interrupt(int, siginfo_t *, void *); +extern void stub_signal_restorer(void); diff --git a/arch/x86/um/shared/sysdep/stub_32.h b/arch/x86/um/shared/sysdep/stub_32.h index 390988132c0a..9dc2efaf5df1 100644 --- a/arch/x86/um/shared/sysdep/stub_32.h +++ b/arch/x86/um/shared/sysdep/stub_32.h @@ -129,6 +129,19 @@ static __always_inline void *get_stub_data(void) "subl %0,%%esp ;" \ "movl %1, %%eax ; " \ "call *%%eax ;" \ - :: "i" ((1 + STUB_DATA_PAGES) * UM_KERN_PAGE_SIZE), \ + :: "i" (STUB_SIZE), \ "i" (&fn)) + +static __always_inline void +stub_seccomp_restore_state(struct stub_data_arch *arch) +{ + for (int i = 0; i < sizeof(arch->tls) / sizeof(arch->tls[0]); i++) { + if (arch->sync & (1 << i)) + stub_syscall1(__NR_set_thread_area, + (unsigned long) &arch->tls[i]); + } + + arch->sync = 0; +} + #endif diff --git a/arch/x86/um/shared/sysdep/stub_64.h b/arch/x86/um/shared/sysdep/stub_64.h index 294affbec742..9fd56954e2e0 100644 --- a/arch/x86/um/shared/sysdep/stub_64.h +++ b/arch/x86/um/shared/sysdep/stub_64.h @@ -10,6 +10,7 @@ #include <sysdep/ptrace_user.h> #include <generated/asm-offsets.h> #include <linux/stddef.h> +#include <asm/prctl.h> #define STUB_MMAP_NR __NR_mmap #define MMAP_OFFSET(o) (o) @@ -132,6 +133,22 @@ static __always_inline void *get_stub_data(void) "subq %0,%%rsp ;" \ "movq %1,%%rax ;" \ "call *%%rax ;" \ - :: "i" ((1 + STUB_DATA_PAGES) * UM_KERN_PAGE_SIZE), \ + :: "i" (STUB_SIZE), \ "i" (&fn)) + +static __always_inline void +stub_seccomp_restore_state(struct stub_data_arch *arch) +{ + /* + * We could use _writefsbase_u64/_writegsbase_u64 if the host reports + * support in the hwcaps (HWCAP2_FSGSBASE). + */ + if (arch->sync & STUB_SYNC_FS_BASE) + stub_syscall2(__NR_arch_prctl, ARCH_SET_FS, arch->fs_base); + if (arch->sync & STUB_SYNC_GS_BASE) + stub_syscall2(__NR_arch_prctl, ARCH_SET_GS, arch->gs_base); + + arch->sync = 0; +} + #endif diff --git a/arch/x86/um/shared/sysdep/syscalls.h b/arch/x86/um/shared/sysdep/syscalls.h deleted file mode 100644 index b2060ac707f0..000000000000 --- a/arch/x86/um/shared/sysdep/syscalls.h +++ /dev/null @@ -1,6 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -#ifdef __i386__ -#include "syscalls_32.h" -#else -#include "syscalls_64.h" -#endif diff --git a/arch/x86/um/shared/sysdep/syscalls_32.h b/arch/x86/um/shared/sysdep/syscalls_32.h deleted file mode 100644 index f6e9f84397e7..000000000000 --- a/arch/x86/um/shared/sysdep/syscalls_32.h +++ /dev/null @@ -1,14 +0,0 @@ -/* - * Copyright (C) 2000 - 2008 Jeff Dike (jdike@{addtoit,linux.intel}.com) - * Licensed under the GPL - */ - -#include <asm/unistd.h> -#include <sysdep/ptrace.h> - -typedef long syscall_handler_t(struct syscall_args); - -extern syscall_handler_t *sys_call_table[]; - -#define EXECUTE_SYSCALL(syscall, regs) \ - ((*sys_call_table[syscall]))(SYSCALL_ARGS(®s->regs)) diff --git a/arch/x86/um/shared/sysdep/syscalls_64.h b/arch/x86/um/shared/sysdep/syscalls_64.h deleted file mode 100644 index b6b997225841..000000000000 --- a/arch/x86/um/shared/sysdep/syscalls_64.h +++ /dev/null @@ -1,28 +0,0 @@ -/* - * Copyright 2003 PathScale, Inc. - * - * Licensed under the GPL - */ - -#ifndef __SYSDEP_X86_64_SYSCALLS_H__ -#define __SYSDEP_X86_64_SYSCALLS_H__ - -#include <linux/msg.h> -#include <linux/shm.h> - -typedef long syscall_handler_t(long, long, long, long, long, long); - -extern syscall_handler_t *sys_call_table[]; - -#define EXECUTE_SYSCALL(syscall, regs) \ - (((*sys_call_table[syscall]))(UPT_SYSCALL_ARG1(®s->regs), \ - UPT_SYSCALL_ARG2(®s->regs), \ - UPT_SYSCALL_ARG3(®s->regs), \ - UPT_SYSCALL_ARG4(®s->regs), \ - UPT_SYSCALL_ARG5(®s->regs), \ - UPT_SYSCALL_ARG6(®s->regs))) - -extern syscall_handler_t sys_modify_ldt; -extern syscall_handler_t sys_arch_prctl; - -#endif diff --git a/arch/x86/um/signal.c b/arch/x86/um/signal.c index 75087e85b6fd..2934e170b0fe 100644 --- a/arch/x86/um/signal.c +++ b/arch/x86/um/signal.c @@ -187,7 +187,12 @@ static int copy_sc_to_user(struct sigcontext __user *to, * Put magic/size values for userspace. We do not bother to verify them * later on, however, userspace needs them should it try to read the * XSTATE data. And ptrace does not fill in these parts. + * + * Skip this if we do not have an XSTATE frame. */ + if (host_fp_size <= sizeof(to_fp64->fpstate)) + return 0; + BUILD_BUG_ON(sizeof(int) != FP_XSTATE_MAGIC2_SIZE); #ifdef CONFIG_X86_32 __put_user(offsetof(struct _fpstate_32, _fxsr_env) + @@ -367,11 +372,13 @@ int setup_signal_stack_si(unsigned long stack_top, struct ksignal *ksig, int err = 0, sig = ksig->sig; unsigned long fp_to; - frame = (struct rt_sigframe __user *) - round_down(stack_top - sizeof(struct rt_sigframe), 16); + frame = (void __user *)stack_top - sizeof(struct rt_sigframe); /* Add required space for math frame */ - frame = (struct rt_sigframe __user *)((unsigned long)frame - math_size); + frame = (void __user *)((unsigned long)frame - math_size); + + /* ABI requires 16 byte boundary alignment */ + frame = (void __user *)round_down((unsigned long)frame, 16); /* Subtract 128 for a red zone and 8 for proper alignment */ frame = (struct rt_sigframe __user *) ((unsigned long) frame - 128 - 8); diff --git a/arch/x86/um/tls_32.c b/arch/x86/um/tls_32.c index fbb129023080..1909c2e640b2 100644 --- a/arch/x86/um/tls_32.c +++ b/arch/x86/um/tls_32.c @@ -12,6 +12,7 @@ #include <skas.h> #include <sysdep/tls.h> #include <asm/desc.h> +#include <stub-data.h> /* * If needed we can detect when it's uninitialized. @@ -21,14 +22,25 @@ static int host_supports_tls = -1; int host_gdt_entry_tls_min; -static int do_set_thread_area(struct user_desc *info) +static int do_set_thread_area(struct task_struct* task, struct user_desc *info) { int ret; - u32 cpu; - cpu = get_cpu(); - ret = os_set_thread_area(info, userspace_pid[cpu]); - put_cpu(); + if (info->entry_number < host_gdt_entry_tls_min || + info->entry_number >= host_gdt_entry_tls_min + GDT_ENTRY_TLS_ENTRIES) + return -EINVAL; + + if (using_seccomp) { + int idx = info->entry_number - host_gdt_entry_tls_min; + struct stub_data *data = (void *)task->mm->context.id.stack; + + data->arch_data.tls[idx] = *info; + data->arch_data.sync |= BIT(idx); + + return 0; + } + + ret = os_set_thread_area(info, task->mm->context.id.pid); if (ret) printk(KERN_ERR "PTRACE_SET_THREAD_AREA failed, err = %d, " @@ -97,7 +109,7 @@ static int load_TLS(int flags, struct task_struct *to) if (!(flags & O_FORCE) && curr->flushed) continue; - ret = do_set_thread_area(&curr->tls); + ret = do_set_thread_area(current, &curr->tls); if (ret) goto out; @@ -174,7 +186,7 @@ int arch_switch_tls(struct task_struct *to) /* * We have no need whatsoever to switch TLS for kernel threads; beyond * that, that would also result in us calling os_set_thread_area with - * userspace_pid[cpu] == 0, which gives an error. + * task->mm == NULL, which would cause a crash. */ if (likely(to->mm)) return load_TLS(O_FORCE, to); @@ -275,7 +287,7 @@ SYSCALL_DEFINE1(set_thread_area, struct user_desc __user *, user_desc) return -EFAULT; } - ret = do_set_thread_area(&info); + ret = do_set_thread_area(current, &info); if (ret) return ret; return set_tls_entry(current, &info, idx, 1); diff --git a/arch/x86/um/vdso/Makefile b/arch/x86/um/vdso/Makefile index 7478d11dacb7..7664cbedbe30 100644 --- a/arch/x86/um/vdso/Makefile +++ b/arch/x86/um/vdso/Makefile @@ -3,16 +3,11 @@ # Building vDSO images for x86. # -VDSO64-y := y - -vdso-install-$(VDSO64-y) += vdso.so - - # files to link into the vdso vobjs-y := vdso-note.o um_vdso.o # files to link into kernel -obj-$(VDSO64-y) += vdso.o vma.o +obj-y += vdso.o vma.o vobjs := $(foreach F,$(vobjs-y),$(obj)/$F) diff --git a/arch/x86/um/vdso/um_vdso.c b/arch/x86/um/vdso/um_vdso.c index cbae2584124f..ca1468865b14 100644 --- a/arch/x86/um/vdso/um_vdso.c +++ b/arch/x86/um/vdso/um_vdso.c @@ -9,17 +9,11 @@ /* Disable profiling for userspace code */ #define DISABLE_BRANCH_PROFILING +#include <vdso/gettime.h> #include <linux/time.h> -#include <linux/getcpu.h> #include <asm/unistd.h> -/* workaround for -Wmissing-prototypes warnings */ -int __vdso_clock_gettime(clockid_t clock, struct __kernel_old_timespec *ts); -int __vdso_gettimeofday(struct __kernel_old_timeval *tv, struct timezone *tz); -__kernel_old_time_t __vdso_time(__kernel_old_time_t *t); -long __vdso_getcpu(unsigned int *cpu, unsigned int *node, struct getcpu_cache *unused); - -int __vdso_clock_gettime(clockid_t clock, struct __kernel_old_timespec *ts) +int __vdso_clock_gettime(clockid_t clock, struct __kernel_timespec *ts) { long ret; @@ -30,7 +24,7 @@ int __vdso_clock_gettime(clockid_t clock, struct __kernel_old_timespec *ts) return ret; } -int clock_gettime(clockid_t, struct __kernel_old_timespec *) +int clock_gettime(clockid_t, struct __kernel_timespec *) __attribute__((weak, alias("__vdso_clock_gettime"))); int __vdso_gettimeofday(struct __kernel_old_timeval *tv, struct timezone *tz) @@ -58,21 +52,3 @@ __kernel_old_time_t __vdso_time(__kernel_old_time_t *t) return secs; } __kernel_old_time_t time(__kernel_old_time_t *t) __attribute__((weak, alias("__vdso_time"))); - -long -__vdso_getcpu(unsigned int *cpu, unsigned int *node, struct getcpu_cache *unused) -{ - /* - * UML does not support SMP, we can cheat here. :) - */ - - if (cpu) - *cpu = 0; - if (node) - *node = 0; - - return 0; -} - -long getcpu(unsigned int *cpu, unsigned int *node, struct getcpu_cache *tcache) - __attribute__((weak, alias("__vdso_getcpu"))); diff --git a/arch/x86/um/vdso/vdso.lds.S b/arch/x86/um/vdso/vdso.lds.S index 73c508587a98..401600effc0a 100644 --- a/arch/x86/um/vdso/vdso.lds.S +++ b/arch/x86/um/vdso/vdso.lds.S @@ -22,8 +22,6 @@ VERSION { __vdso_clock_gettime; gettimeofday; __vdso_gettimeofday; - getcpu; - __vdso_getcpu; time; __vdso_time; local: *; diff --git a/arch/x86/um/vdso/vma.c b/arch/x86/um/vdso/vma.c index f238f7b33cdd..51a2b9f2eca9 100644 --- a/arch/x86/um/vdso/vma.c +++ b/arch/x86/um/vdso/vma.c @@ -10,43 +10,25 @@ #include <asm/elf.h> #include <linux/init.h> -static unsigned int __read_mostly vdso_enabled = 1; unsigned long um_vdso_addr; +static struct page *um_vdso; extern unsigned long task_size; extern char vdso_start[], vdso_end[]; -static struct page **vdsop; - static int __init init_vdso(void) { - struct page *um_vdso; - BUG_ON(vdso_end - vdso_start > PAGE_SIZE); um_vdso_addr = task_size - PAGE_SIZE; - vdsop = kmalloc(sizeof(struct page *), GFP_KERNEL); - if (!vdsop) - goto oom; - um_vdso = alloc_page(GFP_KERNEL); - if (!um_vdso) { - kfree(vdsop); - - goto oom; - } + if (!um_vdso) + panic("Cannot allocate vdso\n"); copy_page(page_address(um_vdso), vdso_start); - *vdsop = um_vdso; return 0; - -oom: - printk(KERN_ERR "Cannot allocate vdso\n"); - vdso_enabled = 0; - - return -ENOMEM; } subsys_initcall(init_vdso); @@ -56,15 +38,12 @@ int arch_setup_additional_pages(struct linux_binprm *bprm, int uses_interp) struct mm_struct *mm = current->mm; static struct vm_special_mapping vdso_mapping = { .name = "[vdso]", + .pages = &um_vdso, }; - if (!vdso_enabled) - return 0; - if (mmap_write_lock_killable(mm)) return -EINTR; - vdso_mapping.pages = vdsop; vma = _install_special_mapping(mm, um_vdso_addr, PAGE_SIZE, VM_READ|VM_EXEC| VM_MAYREAD|VM_MAYWRITE|VM_MAYEXEC, |