diff options
Diffstat (limited to 'arch/x86')
29 files changed, 329 insertions, 348 deletions
diff --git a/arch/x86/boot/compressed/relocs.c b/arch/x86/boot/compressed/relocs.c index bbeb0c3fbd90..89bbf4e4d05d 100644 --- a/arch/x86/boot/compressed/relocs.c +++ b/arch/x86/boot/compressed/relocs.c @@ -9,6 +9,9 @@ #include <byteswap.h> #define USE_BSD #include <endian.h> +#include <regex.h> + +static void die(char *fmt, ...); #define ARRAY_SIZE(x) (sizeof(x) / sizeof((x)[0])) static Elf32_Ehdr ehdr; @@ -30,25 +33,47 @@ static struct section *secs; * the address for which it has been compiled. Don't warn user about * absolute relocations present w.r.t these symbols. */ -static const char* safe_abs_relocs[] = { - "xen_irq_disable_direct_reloc", - "xen_save_fl_direct_reloc", -}; +static const char abs_sym_regex[] = + "^(xen_irq_disable_direct_reloc$|" + "xen_save_fl_direct_reloc$|" + "VDSO|" + "__crc_)"; +static regex_t abs_sym_regex_c; +static int is_abs_reloc(const char *sym_name) +{ + return !regexec(&abs_sym_regex_c, sym_name, 0, NULL, 0); +} -static int is_safe_abs_reloc(const char* sym_name) +/* + * These symbols are known to be relative, even if the linker marks them + * as absolute (typically defined outside any section in the linker script.) + */ +static const char rel_sym_regex[] = + "^_end$"; +static regex_t rel_sym_regex_c; +static int is_rel_reloc(const char *sym_name) { - int i; + return !regexec(&rel_sym_regex_c, sym_name, 0, NULL, 0); +} - for (i = 0; i < ARRAY_SIZE(safe_abs_relocs); i++) { - if (!strcmp(sym_name, safe_abs_relocs[i])) - /* Match found */ - return 1; - } - if (strncmp(sym_name, "VDSO", 4) == 0) - return 1; - if (strncmp(sym_name, "__crc_", 6) == 0) - return 1; - return 0; +static void regex_init(void) +{ + char errbuf[128]; + int err; + + err = regcomp(&abs_sym_regex_c, abs_sym_regex, + REG_EXTENDED|REG_NOSUB); + if (err) { + regerror(err, &abs_sym_regex_c, errbuf, sizeof errbuf); + die("%s", errbuf); + } + + err = regcomp(&rel_sym_regex_c, rel_sym_regex, + REG_EXTENDED|REG_NOSUB); + if (err) { + regerror(err, &rel_sym_regex_c, errbuf, sizeof errbuf); + die("%s", errbuf); + } } static void die(char *fmt, ...) @@ -131,7 +156,7 @@ static const char *rel_type(unsigned type) #undef REL_TYPE }; const char *name = "unknown type rel type name"; - if (type < ARRAY_SIZE(type_name)) { + if (type < ARRAY_SIZE(type_name) && type_name[type]) { name = type_name[type]; } return name; @@ -448,7 +473,7 @@ static void print_absolute_relocs(void) * Before warning check if this absolute symbol * relocation is harmless. */ - if (is_safe_abs_reloc(name)) + if (is_abs_reloc(name) || is_rel_reloc(name)) continue; if (!printed) { @@ -501,21 +526,26 @@ static void walk_relocs(void (*visit)(Elf32_Rel *rel, Elf32_Sym *sym)) sym = &sh_symtab[ELF32_R_SYM(rel->r_info)]; r_type = ELF32_R_TYPE(rel->r_info); /* Don't visit relocations to absolute symbols */ - if (sym->st_shndx == SHN_ABS) { + if (sym->st_shndx == SHN_ABS && + !is_rel_reloc(sym_name(sym_strtab, sym))) { continue; } - if (r_type == R_386_NONE || r_type == R_386_PC32) { + switch (r_type) { + case R_386_NONE: + case R_386_PC32: /* * NONE can be ignored and and PC relative * relocations don't need to be adjusted. */ - } - else if (r_type == R_386_32) { + break; + case R_386_32: /* Visit relocations that need to be adjusted */ visit(rel, sym); - } - else { - die("Unsupported relocation type: %d\n", r_type); + break; + default: + die("Unsupported relocation type: %s (%d)\n", + rel_type(r_type), r_type); + break; } } } @@ -571,16 +601,15 @@ static void emit_relocs(int as_text) } else { unsigned char buf[4]; - buf[0] = buf[1] = buf[2] = buf[3] = 0; /* Print a stop */ - printf("%c%c%c%c", buf[0], buf[1], buf[2], buf[3]); + fwrite("\0\0\0\0", 4, 1, stdout); /* Now print each relocation */ for (i = 0; i < reloc_count; i++) { buf[0] = (relocs[i] >> 0) & 0xff; buf[1] = (relocs[i] >> 8) & 0xff; buf[2] = (relocs[i] >> 16) & 0xff; buf[3] = (relocs[i] >> 24) & 0xff; - printf("%c%c%c%c", buf[0], buf[1], buf[2], buf[3]); + fwrite(buf, 4, 1, stdout); } } } @@ -598,6 +627,8 @@ int main(int argc, char **argv) FILE *fp; int i; + regex_init(); + show_absolute_syms = 0; show_absolute_relocs = 0; as_text = 0; diff --git a/arch/x86/include/asm/dma-mapping.h b/arch/x86/include/asm/dma-mapping.h index 0f6c02f3b7d4..ac91eed21061 100644 --- a/arch/x86/include/asm/dma-mapping.h +++ b/arch/x86/include/asm/dma-mapping.h @@ -67,7 +67,7 @@ static inline bool dma_capable(struct device *dev, dma_addr_t addr, size_t size) if (!dev->dma_mask) return 0; - return addr + size <= *dev->dma_mask; + return addr + size - 1 <= *dev->dma_mask; } static inline dma_addr_t phys_to_dma(struct device *dev, phys_addr_t paddr) diff --git a/arch/x86/include/asm/elf.h b/arch/x86/include/asm/elf.h index 8a024babe5e6..b4501ee223ad 100644 --- a/arch/x86/include/asm/elf.h +++ b/arch/x86/include/asm/elf.h @@ -239,7 +239,6 @@ extern int force_personality32; #endif /* !CONFIG_X86_32 */ #define CORE_DUMP_USE_REGSET -#define USE_ELF_CORE_DUMP #define ELF_EXEC_PAGESIZE 4096 /* This is the location that an ET_DYN program is loaded if exec'ed. Typical diff --git a/arch/x86/include/asm/ptrace.h b/arch/x86/include/asm/ptrace.h index 3d11fd0f44c5..9d369f680321 100644 --- a/arch/x86/include/asm/ptrace.h +++ b/arch/x86/include/asm/ptrace.h @@ -292,6 +292,8 @@ extern void user_enable_block_step(struct task_struct *); #define arch_has_block_step() (boot_cpu_data.x86 >= 6) #endif +#define ARCH_HAS_USER_SINGLE_STEP_INFO + struct user_desc; extern int do_get_thread_area(struct task_struct *p, int idx, struct user_desc __user *info); diff --git a/arch/x86/include/asm/swiotlb.h b/arch/x86/include/asm/swiotlb.h index 87ffcb12a1b8..8085277e1b8b 100644 --- a/arch/x86/include/asm/swiotlb.h +++ b/arch/x86/include/asm/swiotlb.h @@ -5,13 +5,17 @@ #ifdef CONFIG_SWIOTLB extern int swiotlb; -extern int pci_swiotlb_init(void); +extern int __init pci_swiotlb_detect(void); +extern void __init pci_swiotlb_init(void); #else #define swiotlb 0 -static inline int pci_swiotlb_init(void) +static inline int pci_swiotlb_detect(void) { return 0; } +static inline void pci_swiotlb_init(void) +{ +} #endif static inline void dma_mark_clean(void *addr, size_t size) {} diff --git a/arch/x86/include/asm/sys_ia32.h b/arch/x86/include/asm/sys_ia32.h index 4a5a089e1c62..d5f69045c100 100644 --- a/arch/x86/include/asm/sys_ia32.h +++ b/arch/x86/include/asm/sys_ia32.h @@ -30,7 +30,6 @@ struct mmap_arg_struct; asmlinkage long sys32_mmap(struct mmap_arg_struct __user *); asmlinkage long sys32_mprotect(unsigned long, size_t, unsigned long); -asmlinkage long sys32_pipe(int __user *); struct sigaction32; struct old_sigaction32; asmlinkage long sys32_rt_sigaction(int, struct sigaction32 __user *, diff --git a/arch/x86/include/asm/syscalls.h b/arch/x86/include/asm/syscalls.h index 1bb6e395881c..8868b9420b0e 100644 --- a/arch/x86/include/asm/syscalls.h +++ b/arch/x86/include/asm/syscalls.h @@ -18,16 +18,24 @@ /* Common in X86_32 and X86_64 */ /* kernel/ioport.c */ asmlinkage long sys_ioperm(unsigned long, unsigned long, int); +long sys_iopl(unsigned int, struct pt_regs *); /* kernel/process.c */ int sys_fork(struct pt_regs *); int sys_vfork(struct pt_regs *); +long sys_execve(char __user *, char __user * __user *, + char __user * __user *, struct pt_regs *); +long sys_clone(unsigned long, unsigned long, void __user *, + void __user *, struct pt_regs *); /* kernel/ldt.c */ asmlinkage int sys_modify_ldt(int, void __user *, unsigned long); /* kernel/signal.c */ long sys_rt_sigreturn(struct pt_regs *); +long sys_sigaltstack(const stack_t __user *, stack_t __user *, + struct pt_regs *); + /* kernel/tls.c */ asmlinkage int sys_set_thread_area(struct user_desc __user *); @@ -35,18 +43,11 @@ asmlinkage int sys_get_thread_area(struct user_desc __user *); /* X86_32 only */ #ifdef CONFIG_X86_32 -/* kernel/ioport.c */ -long sys_iopl(struct pt_regs *); - -/* kernel/process_32.c */ -int sys_clone(struct pt_regs *); -int sys_execve(struct pt_regs *); /* kernel/signal.c */ asmlinkage int sys_sigsuspend(int, int, old_sigset_t); asmlinkage int sys_sigaction(int, const struct old_sigaction __user *, struct old_sigaction __user *); -int sys_sigaltstack(struct pt_regs *); unsigned long sys_sigreturn(struct pt_regs *); /* kernel/sys_i386_32.c */ @@ -62,28 +63,15 @@ asmlinkage int sys_uname(struct old_utsname __user *); asmlinkage int sys_olduname(struct oldold_utsname __user *); /* kernel/vm86_32.c */ -int sys_vm86old(struct pt_regs *); -int sys_vm86(struct pt_regs *); +int sys_vm86old(struct vm86_struct __user *, struct pt_regs *); +int sys_vm86(unsigned long, unsigned long, struct pt_regs *); #else /* CONFIG_X86_32 */ /* X86_64 only */ -/* kernel/ioport.c */ -asmlinkage long sys_iopl(unsigned int, struct pt_regs *); - /* kernel/process_64.c */ -asmlinkage long sys_clone(unsigned long, unsigned long, - void __user *, void __user *, - struct pt_regs *); -asmlinkage long sys_execve(char __user *, char __user * __user *, - char __user * __user *, - struct pt_regs *); long sys_arch_prctl(int, unsigned long); -/* kernel/signal.c */ -asmlinkage long sys_sigaltstack(const stack_t __user *, stack_t __user *, - struct pt_regs *); - /* kernel/sys_x86_64.c */ struct new_utsname; diff --git a/arch/x86/include/asm/uv/bios.h b/arch/x86/include/asm/uv/bios.h index 7ed17ff502b9..2751f3075d8b 100644 --- a/arch/x86/include/asm/uv/bios.h +++ b/arch/x86/include/asm/uv/bios.h @@ -76,15 +76,6 @@ union partition_info_u { }; }; -union uv_watchlist_u { - u64 val; - struct { - u64 blade : 16, - size : 32, - filler : 16; - }; -}; - enum uv_memprotect { UV_MEMPROT_RESTRICT_ACCESS, UV_MEMPROT_ALLOW_AMO, @@ -100,7 +91,7 @@ extern s64 uv_bios_call_reentrant(enum uv_bios_cmd, u64, u64, u64, u64, u64); extern s64 uv_bios_get_sn_info(int, int *, long *, long *, long *); extern s64 uv_bios_freq_base(u64, u64 *); -extern int uv_bios_mq_watchlist_alloc(int, unsigned long, unsigned int, +extern int uv_bios_mq_watchlist_alloc(unsigned long, unsigned int, unsigned long *); extern int uv_bios_mq_watchlist_free(int, int); extern s64 uv_bios_change_memprotect(u64, u64, enum uv_memprotect); diff --git a/arch/x86/include/asm/uv/uv_hub.h b/arch/x86/include/asm/uv/uv_hub.h index d1414af98559..811bfabc80b7 100644 --- a/arch/x86/include/asm/uv/uv_hub.h +++ b/arch/x86/include/asm/uv/uv_hub.h @@ -172,6 +172,8 @@ DECLARE_PER_CPU(struct uv_hub_info_s, __uv_hub_info); #define UV_LOCAL_MMR_SIZE (64UL * 1024 * 1024) #define UV_GLOBAL_MMR32_SIZE (64UL * 1024 * 1024) +#define UV_GLOBAL_GRU_MMR_BASE 0x4000000 + #define UV_GLOBAL_MMR32_PNODE_SHIFT 15 #define UV_GLOBAL_MMR64_PNODE_SHIFT 26 @@ -232,6 +234,26 @@ static inline unsigned long uv_gpa(void *v) return uv_soc_phys_ram_to_gpa(__pa(v)); } +/* Top two bits indicate the requested address is in MMR space. */ +static inline int +uv_gpa_in_mmr_space(unsigned long gpa) +{ + return (gpa >> 62) == 0x3UL; +} + +/* UV global physical address --> socket phys RAM */ +static inline unsigned long uv_gpa_to_soc_phys_ram(unsigned long gpa) +{ + unsigned long paddr = gpa & uv_hub_info->gpa_mask; + unsigned long remap_base = uv_hub_info->lowmem_remap_base; + unsigned long remap_top = uv_hub_info->lowmem_remap_top; + + if (paddr >= remap_base && paddr < remap_base + remap_top) + paddr -= remap_base; + return paddr; +} + + /* gnode -> pnode */ static inline unsigned long uv_gpa_to_gnode(unsigned long gpa) { @@ -308,6 +330,15 @@ static inline unsigned long uv_read_global_mmr64(int pnode, } /* + * Global MMR space addresses when referenced by the GRU. (GRU does + * NOT use socket addressing). + */ +static inline unsigned long uv_global_gru_mmr_address(int pnode, unsigned long offset) +{ + return UV_GLOBAL_GRU_MMR_BASE | offset | (pnode << uv_hub_info->m_val); +} + +/* * Access hub local MMRs. Faster than using global space but only local MMRs * are accessible. */ @@ -434,6 +465,14 @@ static inline void uv_set_cpu_scir_bits(int cpu, unsigned char value) } } +static unsigned long uv_hub_ipi_value(int apicid, int vector, int mode) +{ + return (1UL << UVH_IPI_INT_SEND_SHFT) | + ((apicid) << UVH_IPI_INT_APIC_ID_SHFT) | + (mode << UVH_IPI_INT_DELIVERY_MODE_SHFT) | + (vector << UVH_IPI_INT_VECTOR_SHFT); +} + static inline void uv_hub_send_ipi(int pnode, int apicid, int vector) { unsigned long val; @@ -442,10 +481,7 @@ static inline void uv_hub_send_ipi(int pnode, int apicid, int vector) if (vector == NMI_VECTOR) dmode = dest_NMI; - val = (1UL << UVH_IPI_INT_SEND_SHFT) | - ((apicid) << UVH_IPI_INT_APIC_ID_SHFT) | - (dmode << UVH_IPI_INT_DELIVERY_MODE_SHFT) | - (vector << UVH_IPI_INT_VECTOR_SHFT); + val = uv_hub_ipi_value(apicid, vector, dmode); uv_write_global_mmr64(pnode, UVH_IPI_INT, val); } diff --git a/arch/x86/kernel/amd_iommu.c b/arch/x86/kernel/amd_iommu.c index b990b5cc9541..23824fef789c 100644 --- a/arch/x86/kernel/amd_iommu.c +++ b/arch/x86/kernel/amd_iommu.c @@ -19,7 +19,7 @@ #include <linux/pci.h> #include <linux/gfp.h> -#include <linux/bitops.h> +#include <linux/bitmap.h> #include <linux/debugfs.h> #include <linux/scatterlist.h> #include <linux/dma-mapping.h> @@ -1162,7 +1162,7 @@ static void dma_ops_free_addresses(struct dma_ops_domain *dom, address = (address % APERTURE_RANGE_SIZE) >> PAGE_SHIFT; - iommu_area_free(range->bitmap, address, pages); + bitmap_clear(range->bitmap, address, pages); } diff --git a/arch/x86/kernel/bios_uv.c b/arch/x86/kernel/bios_uv.c index 63a88e1f987d..b0206a211b09 100644 --- a/arch/x86/kernel/bios_uv.c +++ b/arch/x86/kernel/bios_uv.c @@ -101,21 +101,17 @@ s64 uv_bios_get_sn_info(int fc, int *uvtype, long *partid, long *coher, } int -uv_bios_mq_watchlist_alloc(int blade, unsigned long addr, unsigned int mq_size, +uv_bios_mq_watchlist_alloc(unsigned long addr, unsigned int mq_size, unsigned long *intr_mmr_offset) { - union uv_watchlist_u size_blade; u64 watchlist; s64 ret; - size_blade.size = mq_size; - size_blade.blade = blade; - /* * bios returns watchlist number or negative error number. */ ret = (int)uv_bios_call_irqsave(UV_BIOS_WATCHLIST_ALLOC, addr, - size_blade.val, (u64)intr_mmr_offset, + mq_size, (u64)intr_mmr_offset, (u64)&watchlist, 0); if (ret < BIOS_STATUS_SUCCESS) return ret; diff --git a/arch/x86/kernel/cpu/mcheck/mce-inject.c b/arch/x86/kernel/cpu/mcheck/mce-inject.c index 472763d92098..73734baa50f2 100644 --- a/arch/x86/kernel/cpu/mcheck/mce-inject.c +++ b/arch/x86/kernel/cpu/mcheck/mce-inject.c @@ -74,7 +74,7 @@ static void raise_exception(struct mce *m, struct pt_regs *pregs) m->finished = 0; } -static cpumask_t mce_inject_cpumask; +static cpumask_var_t mce_inject_cpumask; static int mce_raise_notify(struct notifier_block *self, unsigned long val, void *data) @@ -82,9 +82,9 @@ static int mce_raise_notify(struct notifier_block *self, struct die_args *args = (struct die_args *)data; int cpu = smp_processor_id(); struct mce *m = &__get_cpu_var(injectm); - if (val != DIE_NMI_IPI || !cpu_isset(cpu, mce_inject_cpumask)) + if (val != DIE_NMI_IPI || !cpumask_test_cpu(cpu, mce_inject_cpumask)) return NOTIFY_DONE; - cpu_clear(cpu, mce_inject_cpumask); + cpumask_clear_cpu(cpu, mce_inject_cpumask); if (m->inject_flags & MCJ_EXCEPTION) raise_exception(m, args->regs); else if (m->status) @@ -148,22 +148,22 @@ static void raise_mce(struct mce *m) unsigned long start; int cpu; get_online_cpus(); - mce_inject_cpumask = cpu_online_map; - cpu_clear(get_cpu(), mce_inject_cpumask); + cpumask_copy(mce_inject_cpumask, cpu_online_mask); + cpumask_clear_cpu(get_cpu(), mce_inject_cpumask); for_each_online_cpu(cpu) { struct mce *mcpu = &per_cpu(injectm, cpu); if (!mcpu->finished || MCJ_CTX(mcpu->inject_flags) != MCJ_CTX_RANDOM) - cpu_clear(cpu, mce_inject_cpumask); + cpumask_clear_cpu(cpu, mce_inject_cpumask); } - if (!cpus_empty(mce_inject_cpumask)) - apic->send_IPI_mask(&mce_inject_cpumask, NMI_VECTOR); + if (!cpumask_empty(mce_inject_cpumask)) + apic->send_IPI_mask(mce_inject_cpumask, NMI_VECTOR); start = jiffies; - while (!cpus_empty(mce_inject_cpumask)) { + while (!cpumask_empty(mce_inject_cpumask)) { if (!time_before(jiffies, start + 2*HZ)) { printk(KERN_ERR "Timeout waiting for mce inject NMI %lx\n", - *cpus_addr(mce_inject_cpumask)); + *cpumask_bits(mce_inject_cpumask)); break; } cpu_relax(); @@ -210,6 +210,8 @@ static ssize_t mce_write(struct file *filp, const char __user *ubuf, static int inject_init(void) { + if (!alloc_cpumask_var(&mce_inject_cpumask, GFP_KERNEL)) + return -ENOMEM; printk(KERN_INFO "Machine check injector initialized\n"); mce_chrdev_ops.write = mce_write; register_die_notifier(&mce_raise_nb); diff --git a/arch/x86/kernel/entry_32.S b/arch/x86/kernel/entry_32.S index 50b9c220e121..44a8e0dc6737 100644 --- a/arch/x86/kernel/entry_32.S +++ b/arch/x86/kernel/entry_32.S @@ -725,22 +725,61 @@ END(syscall_badsys) /* * System calls that need a pt_regs pointer. */ -#define PTREGSCALL(name) \ +#define PTREGSCALL0(name) \ ALIGN; \ ptregs_##name: \ leal 4(%esp),%eax; \ jmp sys_##name; -PTREGSCALL(iopl) -PTREGSCALL(fork) -PTREGSCALL(clone) -PTREGSCALL(vfork) -PTREGSCALL(execve) -PTREGSCALL(sigaltstack) -PTREGSCALL(sigreturn) -PTREGSCALL(rt_sigreturn) -PTREGSCALL(vm86) -PTREGSCALL(vm86old) +#define PTREGSCALL1(name) \ + ALIGN; \ +ptregs_##name: \ + leal 4(%esp),%edx; \ + movl (PT_EBX+4)(%esp),%eax; \ + jmp sys_##name; + +#define PTREGSCALL2(name) \ + ALIGN; \ +ptregs_##name: \ + leal 4(%esp),%ecx; \ + movl (PT_ECX+4)(%esp),%edx; \ + movl (PT_EBX+4)(%esp),%eax; \ + jmp sys_##name; + +#define PTREGSCALL3(name) \ + ALIGN; \ +ptregs_##name: \ + leal 4(%esp),%eax; \ + pushl %eax; \ + movl PT_EDX(%eax),%ecx; \ + movl PT_ECX(%eax),%edx; \ + movl PT_EBX(%eax),%eax; \ + call sys_##name; \ + addl $4,%esp; \ + ret + +PTREGSCALL1(iopl) +PTREGSCALL0(fork) +PTREGSCALL0(vfork) +PTREGSCALL3(execve) +PTREGSCALL2(sigaltstack) +PTREGSCALL0(sigreturn) +PTREGSCALL0(rt_sigreturn) +PTREGSCALL2(vm86) +PTREGSCALL1(vm86old) + +/* Clone is an oddball. The 4th arg is in %edi */ + ALIGN; +ptregs_clone: + leal 4(%esp),%eax + pushl %eax + pushl PT_EDI(%eax) + movl PT_EDX(%eax),%ecx + movl PT_ECX(%eax),%edx + movl PT_EBX(%eax),%eax + call sys_clone + addl $8,%esp + ret .macro FIXUP_ESPFIX_STACK /* @@ -1008,12 +1047,8 @@ END(spurious_interrupt_bug) ENTRY(kernel_thread_helper) pushl $0 # fake return address for unwinder CFI_STARTPROC - movl %edx,%eax - push %edx - CFI_ADJUST_CFA_OFFSET 4 - call *%ebx - push %eax - CFI_ADJUST_CFA_OFFSET 4 + movl %edi,%eax + call *%esi call do_exit ud2 # padding for call trace CFI_ENDPROC diff --git a/arch/x86/kernel/entry_64.S b/arch/x86/kernel/entry_64.S index 673f693fb451..0697ff139837 100644 --- a/arch/x86/kernel/entry_64.S +++ b/arch/x86/kernel/entry_64.S @@ -1166,63 +1166,20 @@ bad_gs: jmp 2b .previous -/* - * Create a kernel thread. - * - * C extern interface: - * extern long kernel_thread(int (*fn)(void *), void * arg, unsigned long flags) - * - * asm input arguments: - * rdi: fn, rsi: arg, rdx: flags - */ -ENTRY(kernel_thread) - CFI_STARTPROC - FAKE_STACK_FRAME $child_rip - SAVE_ALL - - # rdi: flags, rsi: usp, rdx: will be &pt_regs - movq %rdx,%rdi - orq kernel_thread_flags(%rip),%rdi - movq $-1, %rsi - movq %rsp, %rdx - - xorl %r8d,%r8d - xorl %r9d,%r9d - - # clone now - call do_fork - movq %rax,RAX(%rsp) - xorl %edi,%edi - - /* - * It isn't worth to check for reschedule here, - * so internally to the x86_64 port you can rely on kernel_thread() - * not to reschedule the child before returning, this avoids the need - * of hacks for example to fork off the per-CPU idle tasks. - * [Hopefully no generic code relies on the reschedule -AK] - */ - RESTORE_ALL - UNFAKE_STACK_FRAME - ret - CFI_ENDPROC -END(kernel_thread) - -ENTRY(child_rip) +ENTRY(kernel_thread_helper) pushq $0 # fake return address CFI_STARTPROC /* * Here we are in the child and the registers are set as they were * at kernel_thread() invocation in the parent. */ - movq %rdi, %rax - movq %rsi, %rdi - call *%rax + call *%rsi # exit mov %eax, %edi call do_exit ud2 # padding for call trace CFI_ENDPROC -END(child_rip) +END(kernel_thread_helper) /* * execve(). This function needs to use IRET, not SYSRET, to set up all state properly. diff --git a/arch/x86/kernel/ioport.c b/arch/x86/kernel/ioport.c index 99c4d308f16b..8eec0ec59af2 100644 --- a/arch/x86/kernel/ioport.c +++ b/arch/x86/kernel/ioport.c @@ -103,9 +103,10 @@ asmlinkage long sys_ioperm(unsigned long from, unsigned long num, int turn_on) * on system-call entry - see also fork() and the signal handling * code. */ -static int do_iopl(unsigned int level, struct pt_regs *regs) +long sys_iopl(unsigned int level, struct pt_regs *regs) { unsigned int old = (regs->flags >> 12) & 3; + struct thread_struct *t = ¤t->thread; if (level > 3) return -EINVAL; @@ -115,29 +116,8 @@ static int do_iopl(unsigned int level, struct pt_regs *regs) return -EPERM; } regs->flags = (regs->flags & ~X86_EFLAGS_IOPL) | (level << 12); - - return 0; -} - -#ifdef CONFIG_X86_32 -long sys_iopl(struct pt_regs *regs) -{ - unsigned int level = regs->bx; - struct thread_struct *t = ¤t->thread; - int rc; - - rc = do_iopl(level, regs); - if (rc < 0) - goto out; - t->iopl = level << 12; set_iopl_mask(t->iopl); -out: - return rc; -} -#else -asmlinkage long sys_iopl(unsigned int level, struct pt_regs *regs) -{ - return do_iopl(level, regs); + + return 0; } -#endif diff --git a/arch/x86/kernel/msr.c b/arch/x86/kernel/msr.c index 553449951b84..572b07eee3f4 100644 --- a/arch/x86/kernel/msr.c +++ b/arch/x86/kernel/msr.c @@ -172,11 +172,10 @@ static long msr_ioctl(struct file *file, unsigned int ioc, unsigned long arg) static int msr_open(struct inode *inode, struct file *file) { - unsigned int cpu = iminor(file->f_path.dentry->d_inode); - struct cpuinfo_x86 *c = &cpu_data(cpu); + unsigned int cpu; + struct cpuinfo_x86 *c; cpu = iminor(file->f_path.dentry->d_inode); - if (cpu >= nr_cpu_ids || !cpu_online(cpu)) return -ENXIO; /* No such CPU */ diff --git a/arch/x86/kernel/pci-calgary_64.c b/arch/x86/kernel/pci-calgary_64.c index c563e4c8ff39..2bbde6078143 100644 --- a/arch/x86/kernel/pci-calgary_64.c +++ b/arch/x86/kernel/pci-calgary_64.c @@ -31,7 +31,7 @@ #include <linux/string.h> #include <linux/crash_dump.h> #include <linux/dma-mapping.h> -#include <linux/bitops.h> +#include <linux/bitmap.h> #include <linux/pci_ids.h> #include <linux/pci.h> #include <linux/delay.h> @@ -212,7 +212,7 @@ static void iommu_range_reserve(struct iommu_table *tbl, spin_lock_irqsave(&tbl->it_lock, flags); - iommu_area_reserve(tbl->it_map, index, npages); + bitmap_set(tbl->it_map, index, npages); spin_unlock_irqrestore(&tbl->it_lock, flags); } @@ -303,7 +303,7 @@ static void iommu_free(struct iommu_table *tbl, dma_addr_t dma_addr, spin_lock_irqsave(&tbl->it_lock, flags); - iommu_area_free(tbl->it_map, entry, npages); + bitmap_clear(tbl->it_map, entry, npages); spin_unlock_irqrestore(&tbl->it_lock, flags); } diff --git a/arch/x86/kernel/pci-dma.c b/arch/x86/kernel/pci-dma.c index fcc2f2bfa39c..75e14e21f61a 100644 --- a/arch/x86/kernel/pci-dma.c +++ b/arch/x86/kernel/pci-dma.c @@ -120,15 +120,12 @@ static void __init dma32_free_bootmem(void) void __init pci_iommu_alloc(void) { - int use_swiotlb; - - use_swiotlb = pci_swiotlb_init(); #ifdef CONFIG_X86_64 /* free the range so iommu could get some range less than 4G */ dma32_free_bootmem(); #endif - if (use_swiotlb) - return; + if (pci_swiotlb_detect()) + goto out; gart_iommu_hole_init(); @@ -138,6 +135,8 @@ void __init pci_iommu_alloc(void) /* needs to be called after gart_iommu_hole_init */ amd_iommu_detect(); +out: + pci_swiotlb_init(); } void *dma_generic_alloc_coherent(struct device *dev, size_t size, diff --git a/arch/x86/kernel/pci-gart_64.c b/arch/x86/kernel/pci-gart_64.c index 56c0e730d3fe..34de53b46f87 100644 --- a/arch/x86/kernel/pci-gart_64.c +++ b/arch/x86/kernel/pci-gart_64.c @@ -23,7 +23,7 @@ #include <linux/module.h> #include <linux/topology.h> #include <linux/interrupt.h> -#include <linux/bitops.h> +#include <linux/bitmap.h> #include <linux/kdebug.h> #include <linux/scatterlist.h> #include <linux/iommu-helper.h> @@ -126,7 +126,7 @@ static void free_iommu(unsigned long offset, int size) unsigned long flags; spin_lock_irqsave(&iommu_bitmap_lock, flags); - iommu_area_free(iommu_gart_bitmap, offset, size); + bitmap_clear(iommu_gart_bitmap, offset, size); if (offset >= next_bit) next_bit = offset + size; spin_unlock_irqrestore(&iommu_bitmap_lock, flags); @@ -792,7 +792,7 @@ int __init gart_iommu_init(void) * Out of IOMMU space handling. * Reserve some invalid pages at the beginning of the GART. */ - iommu_area_reserve(iommu_gart_bitmap, 0, EMERGENCY_PAGES); + bitmap_set(iommu_gart_bitmap, 0, EMERGENCY_PAGES); pr_info("PCI-DMA: Reserving %luMB of IOMMU area in the AGP aperture\n", iommu_size >> 20); diff --git a/arch/x86/kernel/pci-swiotlb.c b/arch/x86/kernel/pci-swiotlb.c index e3c0a66b9e77..7d2829dde20e 100644 --- a/arch/x86/kernel/pci-swiotlb.c +++ b/arch/x86/kernel/pci-swiotlb.c @@ -43,12 +43,12 @@ static struct dma_map_ops swiotlb_dma_ops = { }; /* - * pci_swiotlb_init - initialize swiotlb if necessary + * pci_swiotlb_detect - set swiotlb to 1 if necessary * * This returns non-zero if we are forced to use swiotlb (by the boot * option). */ -int __init pci_swiotlb_init(void) +int __init pci_swiotlb_detect(void) { int use_swiotlb = swiotlb | swiotlb_force; @@ -60,10 +60,13 @@ int __init pci_swiotlb_init(void) if (swiotlb_force) swiotlb = 1; + return use_swiotlb; +} + +void __init pci_swiotlb_init(void) +{ if (swiotlb) { swiotlb_init(0); dma_ops = &swiotlb_dma_ops; } - - return use_swiotlb; } diff --git a/arch/x86/kernel/process.c b/arch/x86/kernel/process.c index 7a7bd4e3ec49..98c2cdeb599e 100644 --- a/arch/x86/kernel/process.c +++ b/arch/x86/kernel/process.c @@ -255,6 +255,76 @@ int sys_vfork(struct pt_regs *regs) NULL, NULL); } +long +sys_clone(unsigned long clone_flags, unsigned long newsp, + void __user *parent_tid, void __user *child_tid, struct pt_regs *regs) +{ + if (!newsp) + newsp = regs->sp; + return do_fork(clone_flags, newsp, regs, 0, parent_tid, child_tid); +} + +/* + * This gets run with %si containing the + * function to call, and %di containing + * the "args". + */ +extern void kernel_thread_helper(void); + +/* + * Create a kernel thread + */ +int kernel_thread(int (*fn)(void *), void *arg, unsigned long flags) +{ + struct pt_regs regs; + + memset(®s, 0, sizeof(regs)); + + regs.si = (unsigned long) fn; + regs.di = (unsigned long) arg; + +#ifdef CONFIG_X86_32 + regs.ds = __USER_DS; + regs.es = __USER_DS; + regs.fs = __KERNEL_PERCPU; + regs.gs = __KERNEL_STACK_CANARY; +#endif + + regs.orig_ax = -1; + regs.ip = (unsigned long) kernel_thread_helper; + regs.cs = __KERNEL_CS | get_kernel_rpl(); + regs.flags = X86_EFLAGS_IF | 0x2; + + /* Ok, create the new process.. */ + return do_fork(flags | CLONE_VM | CLONE_UNTRACED, 0, ®s, 0, NULL, NULL); +} +EXPORT_SYMBOL(kernel_thread); + +/* + * sys_execve() executes a new program. + */ +long sys_execve(char __user *name, char __user * __user *argv, + char __user * __user *envp, struct pt_regs *regs) +{ + long error; + char *filename; + + filename = getname(name); + error = PTR_ERR(filename); + if (IS_ERR(filename)) + return error; + error = do_execve(filename, argv, envp, regs); + +#ifdef CONFIG_X86_32 + if (error == 0) { + /* Make sure we don't return using sysenter.. */ + set_thread_flag(TIF_IRET); + } +#endif + + putname(filename); + return error; +} /* * Idle related variables and functions diff --git a/arch/x86/kernel/process_32.c b/arch/x86/kernel/process_32.c index 120b88797a75..9c517b5858f0 100644 --- a/arch/x86/kernel/process_32.c +++ b/arch/x86/kernel/process_32.c @@ -180,39 +180,6 @@ void show_regs(struct pt_regs *regs) show_trace(NULL, regs, ®s->sp, regs->bp); } -/* - * This gets run with %bx containing the - * function to call, and %dx containing - * the "args". - */ -extern void kernel_thread_helper(void); - -/* - * Create a kernel thread - */ -int kernel_thread(int (*fn)(void *), void *arg, unsigned long flags) -{ - struct pt_regs regs; - - memset(®s, 0, sizeof(regs)); - - regs.bx = (unsigned long) fn; - regs.dx = (unsigned long) arg; - - regs.ds = __USER_DS; - regs.es = __USER_DS; - regs.fs = __KERNEL_PERCPU; - regs.gs = __KERNEL_STACK_CANARY; - regs.orig_ax = -1; - regs.ip = (unsigned long) kernel_thread_helper; - regs.cs = __KERNEL_CS | get_kernel_rpl(); - regs.flags = X86_EFLAGS_IF | X86_EFLAGS_SF | X86_EFLAGS_PF | 0x2; - - /* Ok, create the new process.. */ - return do_fork(flags | CLONE_VM | CLONE_UNTRACED, 0, ®s, 0, NULL, NULL); -} -EXPORT_SYMBOL(kernel_thread); - void release_thread(struct task_struct *dead_task) { BUG_ON(dead_task->mm); @@ -424,46 +391,6 @@ __switch_to(struct task_struct *prev_p, struct task_struct *next_p) return prev_p; } -int sys_clone(struct pt_regs *regs) -{ - unsigned long clone_flags; - unsigned long newsp; - int __user *parent_tidptr, *child_tidptr; - - clone_flags = regs->bx; - newsp = regs->cx; - parent_tidptr = (int __user *)regs->dx; - child_tidptr = (int __user *)regs->di; - if (!newsp) - newsp = regs->sp; - return do_fork(clone_flags, newsp, regs, 0, parent_tidptr, child_tidptr); -} - -/* - * sys_execve() executes a new program. - */ -int sys_execve(struct pt_regs *regs) -{ - int error; - char *filename; - - filename = getname((char __user *) regs->bx); - error = PTR_ERR(filename); - if (IS_ERR(filename)) - goto out; - error = do_execve(filename, - (char __user * __user *) regs->cx, - (char __user * __user *) regs->dx, - regs); - if (error == 0) { - /* Make sure we don't return using sysenter.. */ - set_thread_flag(TIF_IRET); - } - putname(filename); -out: - return error; -} - #define top_esp (THREAD_SIZE - sizeof(unsigned long)) #define top_ebp (THREAD_SIZE - 2*sizeof(unsigned long)) diff --git a/arch/x86/kernel/process_64.c b/arch/x86/kernel/process_64.c index e5ab0cd0ef36..52fbd0c60198 100644 --- a/arch/x86/kernel/process_64.c +++ b/arch/x86/kernel/process_64.c @@ -57,8 +57,6 @@ asmlinkage extern void ret_from_fork(void); DEFINE_PER_CPU(unsigned long, old_rsp); static DEFINE_PER_CPU(unsigned char, is_idle); -unsigned long kernel_thread_flags = CLONE_VM | CLONE_UNTRACED; - static ATOMIC_NOTIFIER_HEAD(idle_notifier); void idle_notifier_register(struct notifier_block *n) @@ -273,8 +271,9 @@ int copy_thread(unsigned long clone_flags, unsigned long sp, *childregs = *regs; childregs->ax = 0; - childregs->sp = sp; - if (sp == ~0UL) + if (user_mode(regs)) + childregs->sp = sp; + else childregs->sp = (unsigned long)childregs; p->thread.sp = (unsigned long) childregs; @@ -508,25 +507,6 @@ __switch_to(struct task_struct *prev_p, struct task_struct *next_p) return prev_p; } -/* - * sys_execve() executes a new program. - */ -asmlinkage -long sys_execve(char __user *name, char __user * __user *argv, - char __user * __user *envp, struct pt_regs *regs) -{ - long error; - char *filename; - - filename = getname(name); - error = PTR_ERR(filename); - if (IS_ERR(filename)) - return error; - error = do_execve(filename, argv, envp, regs); - putname(filename); - return error; -} - void set_personality_64bit(void) { /* inherit personality from parent */ @@ -541,15 +521,6 @@ void set_personality_64bit(void) current->personality &= ~READ_IMPLIES_EXEC; } -asmlinkage long -sys_clone(unsigned long clone_flags, unsigned long newsp, - void __user *parent_tid, void __user *child_tid, struct pt_regs *regs) -{ - if (!newsp) - newsp = regs->sp; - return do_fork(clone_flags, newsp, regs, 0, parent_tid, child_tid); -} - unsigned long get_wchan(struct task_struct *p) { unsigned long stack; diff --git a/arch/x86/kernel/ptrace.c b/arch/x86/kernel/ptrace.c index 7079ddaf0731..2779321046bd 100644 --- a/arch/x86/kernel/ptrace.c +++ b/arch/x86/kernel/ptrace.c @@ -1676,21 +1676,33 @@ const struct user_regset_view *task_user_regset_view(struct task_struct *task) #endif } -void send_sigtrap(struct task_struct *tsk, struct pt_regs *regs, - int error_code, int si_code) +static void fill_sigtrap_info(struct task_struct *tsk, + struct pt_regs *regs, + int error_code, int si_code, + struct siginfo *info) { - struct siginfo info; - tsk->thread.trap_no = 1; tsk->thread.error_code = error_code; - memset(&info, 0, sizeof(info)); - info.si_signo = SIGTRAP; - info.si_code = si_code; + memset(info, 0, sizeof(*info)); + info->si_signo = SIGTRAP; + info->si_code = si_code; + info->si_addr = user_mode_vm(regs) ? (void __user *)regs->ip : NULL; +} - /* User-mode ip? */ - info.si_addr = user_mode_vm(regs) ? (void __user *) regs->ip : NULL; +void user_single_step_siginfo(struct task_struct *tsk, + struct pt_regs *regs, + struct siginfo *info) +{ + fill_sigtrap_info(tsk, regs, 0, TRAP_BRKPT, info); +} +void send_sigtrap(struct task_struct *tsk, struct pt_regs *regs, + int error_code, int si_code) +{ + struct siginfo info; + + fill_sigtrap_info(tsk, regs, error_code, si_code, &info); /* Send us the fake SIGTRAP */ force_sig_info(SIGTRAP, &info, tsk); } @@ -1755,29 +1767,22 @@ asmregparm long syscall_trace_enter(struct pt_regs *regs) asmregparm void syscall_trace_leave(struct pt_regs *regs) { + bool step; + if (unlikely(current->audit_context)) audit_syscall_exit(AUDITSC_RESULT(regs->ax), regs->ax); if (unlikely(test_thread_flag(TIF_SYSCALL_TRACEPOINT))) trace_sys_exit(regs, regs->ax); - if (test_thread_flag(TIF_SYSCALL_TRACE)) - tracehook_report_syscall_exit(regs, 0); - /* * If TIF_SYSCALL_EMU is set, we only get here because of * TIF_SINGLESTEP (i.e. this is PTRACE_SYSEMU_SINGLESTEP). * We already reported this syscall instruction in - * syscall_trace_enter(), so don't do any more now. - */ - if (unlikely(test_thread_flag(TIF_SYSCALL_EMU))) - return; - - /* - * If we are single-stepping, synthesize a trap to follow the - * system call instruction. + * syscall_trace_enter(). */ - if (test_thread_flag(TIF_SINGLESTEP) && - tracehook_consider_fatal_signal(current, SIGTRAP)) - send_sigtrap(current, regs, 0, TRAP_BRKPT); + step = unlikely(test_thread_flag(TIF_SINGLESTEP)) && + !test_thread_flag(TIF_SYSCALL_EMU); + if (step || test_thread_flag(TIF_SYSCALL_TRACE)) + tracehook_report_syscall_exit(regs, step); } diff --git a/arch/x86/kernel/signal.c b/arch/x86/kernel/signal.c index 74fe6d86dc5d..4fd173cd8e57 100644 --- a/arch/x86/kernel/signal.c +++ b/arch/x86/kernel/signal.c @@ -545,22 +545,12 @@ sys_sigaction(int sig, const struct old_sigaction __user *act, } #endif /* CONFIG_X86_32 */ -#ifdef CONFIG_X86_32 -int sys_sigaltstack(struct pt_regs *regs) -{ - const stack_t __user *uss = (const stack_t __user *)regs->bx; - stack_t __user *uoss = (stack_t __user *)regs->cx; - - return do_sigaltstack(uss, uoss, regs->sp); -} -#else /* !CONFIG_X86_32 */ -asmlinkage long +long sys_sigaltstack(const stack_t __user *uss, stack_t __user *uoss, struct pt_regs *regs) { return do_sigaltstack(uss, uoss, regs->sp); } -#endif /* CONFIG_X86_32 */ /* * Do a signal return; undo the signal stack. diff --git a/arch/x86/kernel/vm86_32.c b/arch/x86/kernel/vm86_32.c index 9c4e62539058..5ffb5622f793 100644 --- a/arch/x86/kernel/vm86_32.c +++ b/arch/x86/kernel/vm86_32.c @@ -197,9 +197,8 @@ out: static int do_vm86_irq_handling(int subfunction, int irqnumber); static void do_sys_vm86(struct kernel_vm86_struct *info, struct task_struct *tsk); -int sys_vm86old(struct pt_regs *regs) +int sys_vm86old(struct vm86_struct __user *v86, struct pt_regs *regs) { - struct vm86_struct __user *v86 = (struct vm86_struct __user *)regs->bx; struct kernel_vm86_struct info; /* declare this _on top_, * this avoids wasting of stack space. * This remains on the stack until we @@ -227,7 +226,7 @@ out: } -int sys_vm86(struct pt_regs *regs) +int sys_vm86(unsigned long cmd, unsigned long arg, struct pt_regs *regs) { struct kernel_vm86_struct info; /* declare this _on top_, * this avoids wasting of stack space. @@ -239,12 +238,12 @@ int sys_vm86(struct pt_regs *regs) struct vm86plus_struct __user *v86; tsk = current; - switch (regs->bx) { + switch (cmd) { case VM86_REQUEST_IRQ: case VM86_FREE_IRQ: case VM86_GET_IRQ_BITS: case VM86_GET_AND_RESET_IRQ: - ret = do_vm86_irq_handling(regs->bx, (int)regs->cx); + ret = do_vm86_irq_handling(cmd, (int)arg); goto out; case VM86_PLUS_INSTALL_CHECK: /* @@ -261,7 +260,7 @@ int sys_vm86(struct pt_regs *regs) ret = -EPERM; if (tsk->thread.saved_sp0) goto out; - v86 = (struct vm86plus_struct __user *)regs->cx; + v86 = (struct vm86plus_struct __user *)arg; tmp = copy_vm86_regs_from_user(&info.regs, &v86->regs, offsetof(struct kernel_vm86_struct, regs32) - sizeof(info.regs)); diff --git a/arch/x86/kernel/vmlinux.lds.S b/arch/x86/kernel/vmlinux.lds.S index f3f2104408d9..f92a0da608cb 100644 --- a/arch/x86/kernel/vmlinux.lds.S +++ b/arch/x86/kernel/vmlinux.lds.S @@ -319,9 +319,7 @@ SECTIONS __brk_limit = .; } - .end : AT(ADDR(.end) - LOAD_OFFSET) { - _end = .; - } + _end = .; STABS_DEBUG DWARF_DEBUG diff --git a/arch/x86/kernel/x8664_ksyms_64.c b/arch/x86/kernel/x8664_ksyms_64.c index a1029769b6f2..619f7f88b8cc 100644 --- a/arch/x86/kernel/x8664_ksyms_64.c +++ b/arch/x86/kernel/x8664_ksyms_64.c @@ -17,8 +17,6 @@ EXPORT_SYMBOL(mcount); #endif -EXPORT_SYMBOL(kernel_thread); - EXPORT_SYMBOL(__get_user_1); EXPORT_SYMBOL(__get_user_2); EXPORT_SYMBOL(__get_user_4); @@ -56,4 +54,6 @@ EXPORT_SYMBOL(__memcpy); EXPORT_SYMBOL(empty_zero_page); EXPORT_SYMBOL(init_level4_pgt); -EXPORT_SYMBOL(load_gs_index); +#ifndef CONFIG_PARAVIRT +EXPORT_SYMBOL(native_load_gs_index); +#endif diff --git a/arch/x86/tools/gen-insn-attr-x86.awk b/arch/x86/tools/gen-insn-attr-x86.awk index e34e92a28eb6..7a6850683c34 100644 --- a/arch/x86/tools/gen-insn-attr-x86.awk +++ b/arch/x86/tools/gen-insn-attr-x86.awk @@ -226,12 +226,12 @@ function add_flags(old,new) { } # convert operands to flags. -function convert_operands(opnd, i,imm,mod) +function convert_operands(count,opnd, i,j,imm,mod) { imm = null mod = null - for (i in opnd) { - i = opnd[i] + for (j = 1; j <= count; j++) { + i = opnd[j] if (match(i, imm_expr) == 1) { if (!imm_flag[i]) semantic_error("Unknown imm opnd: " i) @@ -282,8 +282,8 @@ function convert_operands(opnd, i,imm,mod) # parse one opcode if (match($i, opnd_expr)) { opnd = $i - split($(i++), opnds, ",") - flags = convert_operands(opnds) + count = split($(i++), opnds, ",") + flags = convert_operands(count, opnds) } if (match($i, ext_expr)) ext = $(i++) |
