diff options
Diffstat (limited to 'arch/x86')
58 files changed, 717 insertions, 512 deletions
diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig index 1d14cc6..c9866b0 100644 --- a/arch/x86/Kconfig +++ b/arch/x86/Kconfig @@ -81,7 +81,7 @@ config X86 select CLKEVT_I8253 select ARCH_HAVE_NMI_SAFE_CMPXCHG select GENERIC_IOMAP - select DCACHE_WORD_ACCESS if !DEBUG_PAGEALLOC + select DCACHE_WORD_ACCESS config INSTRUCTION_DECODER def_bool (KPROBES || PERF_EVENTS) diff --git a/arch/x86/Makefile b/arch/x86/Makefile index 41a7237..94e91e4 100644 --- a/arch/x86/Makefile +++ b/arch/x86/Makefile @@ -134,6 +134,9 @@ KBUILD_CFLAGS += $(call cc-option,-mno-avx,) KBUILD_CFLAGS += $(mflags-y) KBUILD_AFLAGS += $(mflags-y) +archscripts: + $(Q)$(MAKE) $(build)=arch/x86/tools relocs + ### # Syscall table generation diff --git a/arch/x86/Makefile.um b/arch/x86/Makefile.um index 4be406a..36b62bc 100644 --- a/arch/x86/Makefile.um +++ b/arch/x86/Makefile.um @@ -14,6 +14,9 @@ LINK-y += $(call cc-option,-m32) export LDFLAGS +LDS_EXTRA := -Ui386 +export LDS_EXTRA + # First of all, tune CFLAGS for the specific CPU. This actually sets cflags-y. include $(srctree)/arch/x86/Makefile_32.cpu diff --git a/arch/x86/boot/compressed/Makefile b/arch/x86/boot/compressed/Makefile index fd55a2f..e398bb5 100644 --- a/arch/x86/boot/compressed/Makefile +++ b/arch/x86/boot/compressed/Makefile @@ -40,13 +40,12 @@ OBJCOPYFLAGS_vmlinux.bin := -R .comment -S $(obj)/vmlinux.bin: vmlinux FORCE $(call if_changed,objcopy) +targets += vmlinux.bin.all vmlinux.relocs -targets += vmlinux.bin.all vmlinux.relocs relocs -hostprogs-$(CONFIG_X86_NEED_RELOCS) += relocs - +CMD_RELOCS = arch/x86/tools/relocs quiet_cmd_relocs = RELOCS $@ - cmd_relocs = $(obj)/relocs $< > $@;$(obj)/relocs --abs-relocs $< -$(obj)/vmlinux.relocs: vmlinux $(obj)/relocs FORCE + cmd_relocs = $(CMD_RELOCS) $< > $@;$(CMD_RELOCS) --abs-relocs $< +$(obj)/vmlinux.relocs: vmlinux FORCE $(call if_changed,relocs) vmlinux.bin.all-y := $(obj)/vmlinux.bin diff --git a/arch/x86/boot/compressed/head_32.S b/arch/x86/boot/compressed/head_32.S index a055993..c85e3ac 100644 --- a/arch/x86/boot/compressed/head_32.S +++ b/arch/x86/boot/compressed/head_32.S @@ -33,6 +33,9 @@ __HEAD ENTRY(startup_32) #ifdef CONFIG_EFI_STUB + jmp preferred_addr + + .balign 0x10 /* * We don't need the return address, so set up the stack so * efi_main() can find its arugments. @@ -41,12 +44,17 @@ ENTRY(startup_32) call efi_main cmpl $0, %eax - je preferred_addr movl %eax, %esi - call 1f + jne 2f 1: + /* EFI init failed, so hang. */ + hlt + jmp 1b +2: + call 3f +3: popl %eax - subl $1b, %eax + subl $3b, %eax subl BP_pref_address(%esi), %eax add BP_code32_start(%esi), %eax leal preferred_addr(%eax), %eax diff --git a/arch/x86/boot/compressed/head_64.S b/arch/x86/boot/compressed/head_64.S index 558d76c..87e03a1 100644 --- a/arch/x86/boot/compressed/head_64.S +++ b/arch/x86/boot/compressed/head_64.S @@ -200,18 +200,28 @@ ENTRY(startup_64) * entire text+data+bss and hopefully all of memory. */ #ifdef CONFIG_EFI_STUB - pushq %rsi + /* + * The entry point for the PE/COFF executable is 0x210, so only + * legacy boot loaders will execute this jmp. + */ + jmp preferred_addr + + .org 0x210 mov %rcx, %rdi mov %rdx, %rsi call efi_main - popq %rsi - cmpq $0,%rax - je preferred_addr movq %rax,%rsi - call 1f + cmpq $0,%rax + jne 2f 1: + /* EFI init failed, so hang. */ + hlt + jmp 1b +2: + call 3f +3: popq %rax - subq $1b, %rax + subq $3b, %rax subq BP_pref_address(%rsi), %rax add BP_code32_start(%esi), %eax leaq preferred_addr(%rax), %rax diff --git a/arch/x86/boot/tools/build.c b/arch/x86/boot/tools/build.c index ed54976..24443a3 100644 --- a/arch/x86/boot/tools/build.c +++ b/arch/x86/boot/tools/build.c @@ -205,8 +205,13 @@ int main(int argc, char ** argv) put_unaligned_le32(file_sz, &buf[pe_header + 0x50]); #ifdef CONFIG_X86_32 - /* Address of entry point */ - put_unaligned_le32(i, &buf[pe_header + 0x28]); + /* + * Address of entry point. + * + * The EFI stub entry point is +16 bytes from the start of + * the .text section. + */ + put_unaligned_le32(i + 16, &buf[pe_header + 0x28]); /* .text size */ put_unaligned_le32(file_sz, &buf[pe_header + 0xb0]); @@ -217,9 +222,11 @@ int main(int argc, char ** argv) /* * Address of entry point. startup_32 is at the beginning and * the 64-bit entry point (startup_64) is always 512 bytes - * after. + * after. The EFI stub entry point is 16 bytes after that, as + * the first instruction allows legacy loaders to jump over + * the EFI stub initialisation */ - put_unaligned_le32(i + 512, &buf[pe_header + 0x28]); + put_unaligned_le32(i + 528, &buf[pe_header + 0x28]); /* .text size */ put_unaligned_le32(file_sz, &buf[pe_header + 0xc0]); diff --git a/arch/x86/ia32/ia32_aout.c b/arch/x86/ia32/ia32_aout.c index d511d95..07b3a68 100644 --- a/arch/x86/ia32/ia32_aout.c +++ b/arch/x86/ia32/ia32_aout.c @@ -119,9 +119,7 @@ static void set_brk(unsigned long start, unsigned long end) end = PAGE_ALIGN(end); if (end <= start) return; - down_write(¤t->mm->mmap_sem); - do_brk(start, end - start); - up_write(¤t->mm->mmap_sem); + vm_brk(start, end - start); } #ifdef CORE_DUMP @@ -296,8 +294,7 @@ static int load_aout_binary(struct linux_binprm *bprm, struct pt_regs *regs) /* OK, This is the point of no return */ set_personality(PER_LINUX); - set_thread_flag(TIF_IA32); - current->mm->context.ia32_compat = 1; + set_personality_ia32(false); setup_new_exec(bprm); @@ -332,9 +329,7 @@ static int load_aout_binary(struct linux_binprm *bprm, struct pt_regs *regs) pos = 32; map_size = ex.a_text+ex.a_data; - down_write(¤t->mm->mmap_sem); - error = do_brk(text_addr & PAGE_MASK, map_size); - up_write(¤t->mm->mmap_sem); + error = vm_brk(text_addr & PAGE_MASK, map_size); if (error != (text_addr & PAGE_MASK)) { send_sig(SIGKILL, current, 0); @@ -373,9 +368,7 @@ static int load_aout_binary(struct linux_binprm *bprm, struct pt_regs *regs) if (!bprm->file->f_op->mmap || (fd_offset & ~PAGE_MASK) != 0) { loff_t pos = fd_offset; - down_write(¤t->mm->mmap_sem); - do_brk(N_TXTADDR(ex), ex.a_text+ex.a_data); - up_write(¤t->mm->mmap_sem); + vm_brk(N_TXTADDR(ex), ex.a_text+ex.a_data); bprm->file->f_op->read(bprm->file, (char __user *)N_TXTADDR(ex), ex.a_text+ex.a_data, &pos); @@ -385,26 +378,22 @@ static int load_aout_binary(struct linux_binprm *bprm, struct pt_regs *regs) goto beyond_if; } - down_write(¤t->mm->mmap_sem); - error = do_mmap(bprm->file, N_TXTADDR(ex), ex.a_text, + error = vm_mmap(bprm->file, N_TXTADDR(ex), ex.a_text, PROT_READ | PROT_EXEC, MAP_FIXED | MAP_PRIVATE | MAP_DENYWRITE | MAP_EXECUTABLE | MAP_32BIT, fd_offset); - up_write(¤t->mm->mmap_sem); if (error != N_TXTADDR(ex)) { send_sig(SIGKILL, current, 0); return error; } - down_write(¤t->mm->mmap_sem); - error = do_mmap(bprm->file, N_DATADDR(ex), ex.a_data, + error = vm_mmap(bprm->file, N_DATADDR(ex), ex.a_data, PROT_READ | PROT_WRITE | PROT_EXEC, MAP_FIXED | MAP_PRIVATE | MAP_DENYWRITE | MAP_EXECUTABLE | MAP_32BIT, fd_offset + ex.a_text); - up_write(¤t->mm->mmap_sem); if (error != N_DATADDR(ex)) { send_sig(SIGKILL, current, 0); return error; @@ -476,9 +465,7 @@ static int load_aout_library(struct file *file) error_time = jiffies; } #endif - down_write(¤t->mm->mmap_sem); - do_brk(start_addr, ex.a_text + ex.a_data + ex.a_bss); - up_write(¤t->mm->mmap_sem); + vm_brk(start_addr, ex.a_text + ex.a_data + ex.a_bss); file->f_op->read(file, (char __user *)start_addr, ex.a_text + ex.a_data, &pos); @@ -490,12 +477,10 @@ static int load_aout_library(struct file *file) goto out; } /* Now use mmap to map the library into memory. */ - down_write(¤t->mm->mmap_sem); - error = do_mmap(file, start_addr, ex.a_text + ex.a_data, + error = vm_mmap(file, start_addr, ex.a_text + ex.a_data, PROT_READ | PROT_WRITE | PROT_EXEC, MAP_FIXED | MAP_PRIVATE | MAP_DENYWRITE | MAP_32BIT, N_TXTOFF(ex)); - up_write(¤t->mm->mmap_sem); retval = error; if (error != start_addr) goto out; @@ -503,9 +488,7 @@ static int load_aout_library(struct file *file) len = PAGE_ALIGN(ex.a_text + ex.a_data); bss = ex.a_text + ex.a_data + ex.a_bss; if (bss > len) { - down_write(¤t->mm->mmap_sem); - error = do_brk(start_addr + len, bss - len); - up_write(¤t->mm->mmap_sem); + error = vm_brk(start_addr + len, bss - len); retval = error; if (error != start_addr + len) goto out; diff --git a/arch/x86/include/asm/cmpxchg.h b/arch/x86/include/asm/cmpxchg.h index b3b7332..99480e5 100644 --- a/arch/x86/include/asm/cmpxchg.h +++ b/arch/x86/include/asm/cmpxchg.h @@ -43,7 +43,7 @@ extern void __add_wrong_size(void) switch (sizeof(*(ptr))) { \ case __X86_CASE_B: \ asm volatile (lock #op "b %b0, %1\n" \ - : "+r" (__ret), "+m" (*(ptr)) \ + : "+q" (__ret), "+m" (*(ptr)) \ : : "memory", "cc"); \ break; \ case __X86_CASE_W: \ @@ -173,7 +173,7 @@ extern void __add_wrong_size(void) switch (sizeof(*(ptr))) { \ case __X86_CASE_B: \ asm volatile (lock "addb %b1, %0\n" \ - : "+m" (*(ptr)) : "ri" (inc) \ + : "+m" (*(ptr)) : "qi" (inc) \ : "memory", "cc"); \ break; \ case __X86_CASE_W: \ diff --git a/arch/x86/include/asm/kvm_para.h b/arch/x86/include/asm/kvm_para.h index 734c376..183922e 100644 --- a/arch/x86/include/asm/kvm_para.h +++ b/arch/x86/include/asm/kvm_para.h @@ -170,6 +170,9 @@ static inline int kvm_para_available(void) unsigned int eax, ebx, ecx, edx; char signature[13]; + if (boot_cpu_data.cpuid_level < 0) + return 0; /* So we don't blow up on old processors */ + cpuid(KVM_CPUID_SIGNATURE, &eax, &ebx, &ecx, &edx); memcpy(signature + 0, &ebx, 4); memcpy(signature + 4, &ecx, 4); diff --git a/arch/x86/include/asm/posix_types.h b/arch/x86/include/asm/posix_types.h index 3427b77..7ef7c30 100644 --- a/arch/x86/include/asm/posix_types.h +++ b/arch/x86/include/asm/posix_types.h @@ -7,9 +7,9 @@ #else # ifdef __i386__ # include "posix_types_32.h" -# elif defined(__LP64__) -# include "posix_types_64.h" -# else +# elif defined(__ILP32__) # include "posix_types_x32.h" +# else +# include "posix_types_64.h" # endif #endif diff --git a/arch/x86/include/asm/sigcontext.h b/arch/x86/include/asm/sigcontext.h index 4a08538..5ca71c0 100644 --- a/arch/x86/include/asm/sigcontext.h +++ b/arch/x86/include/asm/sigcontext.h @@ -257,7 +257,7 @@ struct sigcontext { __u64 oldmask; __u64 cr2; struct _fpstate __user *fpstate; /* zero when no FPU context */ -#ifndef __LP64__ +#ifdef __ILP32__ __u32 __fpstate_pad; #endif __u64 reserved1[8]; diff --git a/arch/x86/include/asm/siginfo.h b/arch/x86/include/asm/siginfo.h index fc1aa55..34c47b3 100644 --- a/arch/x86/include/asm/siginfo.h +++ b/arch/x86/include/asm/siginfo.h @@ -2,7 +2,13 @@ #define _ASM_X86_SIGINFO_H #ifdef __x86_64__ -# define __ARCH_SI_PREAMBLE_SIZE (4 * sizeof(int)) +# ifdef __ILP32__ /* x32 */ +typedef long long __kernel_si_clock_t __attribute__((aligned(4))); +# define __ARCH_SI_CLOCK_T __kernel_si_clock_t +# define __ARCH_SI_ATTRIBUTES __attribute__((aligned(8))) +# else /* x86-64 */ +# define __ARCH_SI_PREAMBLE_SIZE (4 * sizeof(int)) +# endif #endif #include <asm-generic/siginfo.h> diff --git a/arch/x86/include/asm/uaccess.h b/arch/x86/include/asm/uaccess.h index 8be5f54..e054459 100644 --- a/arch/x86/include/asm/uaccess.h +++ b/arch/x86/include/asm/uaccess.h @@ -557,6 +557,8 @@ struct __large_struct { unsigned long buf[100]; }; extern unsigned long copy_from_user_nmi(void *to, const void __user *from, unsigned long n); +extern __must_check long +strncpy_from_user(char *dst, const char __user *src, long count); /* * movsl can be slow when source and dest are not both 8-byte aligned diff --git a/arch/x86/include/asm/uaccess_32.h b/arch/x86/include/asm/uaccess_32.h index 566e803..8084bc7 100644 --- a/arch/x86/include/asm/uaccess_32.h +++ b/arch/x86/include/asm/uaccess_32.h @@ -213,11 +213,6 @@ static inline unsigned long __must_check copy_from_user(void *to, return n; } -long __must_check strncpy_from_user(char *dst, const char __user *src, - long count); -long __must_check __strncpy_from_user(char *dst, - const char __user *src, long count); - /** * strlen_user: - Get the size of a string in user space. * @str: The string to measure. diff --git a/arch/x86/include/asm/uaccess_64.h b/arch/x86/include/asm/uaccess_64.h index 1c66d30..fcd4b6f 100644 --- a/arch/x86/include/asm/uaccess_64.h +++ b/arch/x86/include/asm/uaccess_64.h @@ -208,10 +208,6 @@ int __copy_in_user(void __user *dst, const void __user *src, unsigned size) } } -__must_check long -strncpy_from_user(char *dst, const char __user *src, long count); -__must_check long -__strncpy_from_user(char *dst, const char __user *src, long count); __must_check long strnlen_user(const char __user *str, long n); __must_check long __strnlen_user(const char __user *str, long n); __must_check long strlen_user(const char __user *str); diff --git a/arch/x86/include/asm/unistd.h b/arch/x86/include/asm/unistd.h index 37cdc9d..4437001 100644 --- a/arch/x86/include/asm/unistd.h +++ b/arch/x86/include/asm/unistd.h @@ -63,10 +63,10 @@ #else # ifdef __i386__ # include <asm/unistd_32.h> -# elif defined(__LP64__) -# include <asm/unistd_64.h> -# else +# elif defined(__ILP32__) # include <asm/unistd_x32.h> +# else +# include <asm/unistd_64.h> # endif #endif diff --git a/arch/x86/include/asm/word-at-a-time.h b/arch/x86/include/asm/word-at-a-time.h index 6fe6767..e58f03b 100644 --- a/arch/x86/include/asm/word-at-a-time.h +++ b/arch/x86/include/asm/word-at-a-time.h @@ -43,4 +43,37 @@ static inline unsigned long has_zero(unsigned long a) return ((a - REPEAT_BYTE(0x01)) & ~a) & REPEAT_BYTE(0x80); } +/* + * Load an unaligned word from kernel space. + * + * In the (very unlikely) case of the word being a page-crosser + * and the next page not being mapped, take the exception and + * return zeroes in the non-existing part. + */ +static inline unsigned long load_unaligned_zeropad(const void *addr) +{ + unsigned long ret, dummy; + + asm( + "1:\tmov %2,%0\n" + "2:\n" + ".section .fixup,\"ax\"\n" + "3:\t" + "lea %2,%1\n\t" + "and %3,%1\n\t" + "mov (%1),%0\n\t" + "leal %2,%%ecx\n\t" + "andl %4,%%ecx\n\t" + "shll $3,%%ecx\n\t" + "shr %%cl,%0\n\t" + "jmp 2b\n" + ".previous\n" + _ASM_EXTABLE(1b, 3b) + :"=&r" (ret),"=&c" (dummy) + :"m" (*(unsigned long *)addr), + "i" (-sizeof(unsigned long)), + "i" (sizeof(unsigned long)-1)); + return ret; +} + #endif /* _ASM_WORD_AT_A_TIME_H */ diff --git a/arch/x86/include/asm/x86_init.h b/arch/x86/include/asm/x86_init.h index baaca8d..764b66a 100644 --- a/arch/x86/include/asm/x86_init.h +++ b/arch/x86/include/asm/x86_init.h @@ -195,6 +195,5 @@ extern struct x86_msi_ops x86_msi; extern void x86_init_noop(void); extern void x86_init_uint_noop(unsigned int unused); -extern void x86_default_fixup_cpu_id(struct cpuinfo_x86 *c, int node); #endif diff --git a/arch/x86/kernel/acpi/boot.c b/arch/x86/kernel/acpi/boot.c index a415b1f..7c439fe 100644 --- a/arch/x86/kernel/acpi/boot.c +++ b/arch/x86/kernel/acpi/boot.c @@ -593,7 +593,7 @@ void __init acpi_set_irq_model_ioapic(void) #ifdef CONFIG_ACPI_HOTPLUG_CPU #include <acpi/processor.h> -static void __cpuinitdata acpi_map_cpu2node(acpi_handle handle, int cpu, int physid) +static void __cpuinit acpi_map_cpu2node(acpi_handle handle, int cpu, int physid) { #ifdef CONFIG_ACPI_NUMA int nid; diff --git a/arch/x86/kernel/acpi/sleep.c b/arch/x86/kernel/acpi/sleep.c index 103b6ab..146a49c 100644 --- a/arch/x86/kernel/acpi/sleep.c +++ b/arch/x86/kernel/acpi/sleep.c @@ -24,6 +24,10 @@ unsigned long acpi_realmode_flags; static char temp_stack[4096]; #endif +asmlinkage void acpi_enter_s3(void) +{ + acpi_enter_sleep_state(3, wake_sleep_flags); +} /** * acpi_suspend_lowlevel - save kernel state * diff --git a/arch/x86/kernel/acpi/sleep.h b/arch/x86/kernel/acpi/sleep.h index 416d4be..d68677a 100644 --- a/arch/x86/kernel/acpi/sleep.h +++ b/arch/x86/kernel/acpi/sleep.h @@ -3,12 +3,16 @@ */ #include <asm/trampoline.h> +#include <linux/linkage.h> extern unsigned long saved_video_mode; extern long saved_magic; extern int wakeup_pmode_return; +extern u8 wake_sleep_flags; +extern asmlinkage void acpi_enter_s3(void); + extern unsigned long acpi_copy_wakeup_routine(unsigned long); extern void wakeup_long64(void); diff --git a/arch/x86/kernel/acpi/wakeup_32.S b/arch/x86/kernel/acpi/wakeup_32.S index 13ab7205..7261083 100644 --- a/arch/x86/kernel/acpi/wakeup_32.S +++ b/arch/x86/kernel/acpi/wakeup_32.S @@ -74,9 +74,7 @@ restore_registers: ENTRY(do_suspend_lowlevel) call save_processor_state call save_registers - pushl $3 - call acpi_enter_sleep_state - addl $4, %esp + call acpi_enter_s3 # In case of S3 failure, we'll emerge here. Jump # to ret_point to recover diff --git a/arch/x86/kernel/acpi/wakeup_64.S b/arch/x86/kernel/acpi/wakeup_64.S index 8ea5164..014d1d2 100644 --- a/arch/x86/kernel/acpi/wakeup_64.S +++ b/arch/x86/kernel/acpi/wakeup_64.S @@ -71,9 +71,7 @@ ENTRY(do_suspend_lowlevel) movq %rsi, saved_rsi addq $8, %rsp - movl $3, %edi - xorl %eax, %eax - call acpi_enter_sleep_state + call acpi_enter_s3 /* in case something went wrong, restore the machine status and go on */ jmp resume_point diff --git a/arch/x86/kernel/apic/apic.c b/arch/x86/kernel/apic/apic.c index 11544d8..edc2448 100644 --- a/arch/x86/kernel/apic/apic.c +++ b/arch/x86/kernel/apic/apic.c @@ -1637,9 +1637,11 @@ static int __init apic_verify(void) mp_lapic_addr = APIC_DEFAULT_PHYS_BASE; /* The BIOS may have set up the APIC at some other address */ - rdmsr(MSR_IA32_APICBASE, l, h); - if (l & MSR_IA32_APICBASE_ENABLE) - mp_lapic_addr = l & MSR_IA32_APICBASE_BASE; + if (boot_cpu_data.x86 >= 6) { + rdmsr(MSR_IA32_APICBASE, l, h); + if (l & MSR_IA32_APICBASE_ENABLE) + mp_lapic_addr = l & MSR_IA32_APICBASE_BASE; + } pr_info("Found and enabled local APIC!\n"); return 0; @@ -1657,13 +1659,15 @@ int __init apic_force_enable(unsigned long addr) * MSR. This can only be done in software for Intel P6 or later * and AMD K7 (Model > 1) or later. */ - rdmsr(MSR_IA32_APICBASE, l, h); - if (!(l & MSR_IA32_APICBASE_ENABLE)) { - pr_info("Local APIC disabled by BIOS -- reenabling.\n"); - l &= ~MSR_IA32_APICBASE_BASE; - l |= MSR_IA32_APICBASE_ENABLE | addr; - wrmsr(MSR_IA32_APICBASE, l, h); - enabled_via_apicbase = 1; + if (boot_cpu_data.x86 >= 6) { + rdmsr(MSR_IA32_APICBASE, l, h); + if (!(l & MSR_IA32_APICBASE_ENABLE)) { + pr_info("Local APIC disabled by BIOS -- reenabling.\n"); + l &= ~MSR_IA32_APICBASE_BASE; + l |= MSR_IA32_APICBASE_ENABLE | addr; + wrmsr(MSR_IA32_APICBASE, l, h); + enabled_via_apicbase = 1; + } } return apic_verify(); } @@ -2209,10 +2213,12 @@ static void lapic_resume(void) * FIXME! This will be wrong if we ever support suspend on * SMP! We'll need to do this as part of the CPU restore! */ - rdmsr(MSR_IA32_APICBASE, l, h); - l &= ~MSR_IA32_APICBASE_BASE; - l |= MSR_IA32_APICBASE_ENABLE | mp_lapic_addr; - wrmsr(MSR_IA32_APICBASE, l, h); + if (boot_cpu_data.x86 >= 6) { + rdmsr(MSR_IA32_APICBASE, l, h); + l &= ~MSR_IA32_APICBASE_BASE; + l |= MSR_IA32_APICBASE_ENABLE | mp_lapic_addr; + wrmsr(MSR_IA32_APICBASE, l, h); + } } maxlvt = lapic_get_maxlvt(); diff --git a/arch/x86/kernel/apic/apic_numachip.c b/arch/x86/kernel/apic/apic_numachip.c index 899803e..23e7542 100644 --- a/arch/x86/kernel/apic/apic_numachip.c +++ b/arch/x86/kernel/apic/apic_numachip.c @@ -207,8 +207,11 @@ static void __init map_csrs(void) static void fixup_cpu_id(struct cpuinfo_x86 *c, int node) { - c->phys_proc_id = node; - per_cpu(cpu_llc_id, smp_processor_id()) = node; + + if (c->phys_proc_id != node) { + c->phys_proc_id = node; + per_cpu(cpu_llc_id, smp_processor_id()) = node; + } } static int __init numachip_system_init(void) diff --git a/arch/x86/kernel/apic/x2apic_phys.c b/arch/x86/kernel/apic/x2apic_phys.c index 8a778db..991e315 100644 --- a/arch/x86/kernel/apic/x2apic_phys.c +++ b/arch/x86/kernel/apic/x2apic_phys.c @@ -24,6 +24,12 @@ static int x2apic_acpi_madt_oem_check(char *oem_id, char *oem_table_id) { if (x2apic_phys) return x2apic_enabled(); + else if ((acpi_gbl_FADT.header.revision >= FADT2_REVISION_ID) && + (acpi_gbl_FADT.flags & ACPI_FADT_APIC_PHYSICAL) && + x2apic_enabled()) { + printk(KERN_DEBUG "System requires x2apic physical mode\n"); + return 1; + } else return 0; } diff --git a/arch/x86/kernel/cpu/amd.c b/arch/x86/kernel/cpu/amd.c index 0a44b90..146bb62 100644 --- a/arch/x86/kernel/cpu/amd.c +++ b/arch/x86/kernel/cpu/amd.c @@ -26,7 +26,8 @@ * contact AMD for precise details and a CPU swap. * * See http://www.multimania.com/poulot/k6bug.html - * http://www.amd.com/K6/k6docs/revgd.html + * and section 2.6.2 of "AMD-K6 Processor Revision Guide - Model 6" + * (Publication # 21266 Issue Date: August 1998) * * The following test is erm.. interesting. AMD neglected to up * the chip setting when fixing the bug but they also tweaked some @@ -94,7 +95,6 @@ static void __cpuinit init_amd_k6(struct cpuinfo_x86 *c) "system stability may be impaired when more than 32 MB are used.\n"); else printk(KERN_CONT "probably OK (after B9730xxxx).\n"); - printk(KERN_INFO "Please see http://membres.lycos.fr/poulot/k6bug.html\n"); } /* K6 with old style WHCR */ @@ -353,10 +353,11 @@ static void __cpuinit srat_detect_node(struct cpuinfo_x86 *c) node = per_cpu(cpu_llc_id, cpu); /* - * If core numbers are inconsistent, it's likely a multi-fabric platform, - * so invoke platform-specific handler + * On multi-fabric platform (e.g. Numascale NumaChip) a + * platform-specific handler needs to be called to fixup some + * IDs of the CPU. */ - if (c->phys_proc_id != node) + if (x86_cpuinit.fixup_cpu_id) x86_cpuinit.fixup_cpu_id(c, node); if (!node_online(node)) { @@ -579,6 +580,24 @@ static void __cpuinit init_amd(struct cpuinfo_x86 *c) } } + /* re-enable TopologyExtensions if switched off by BIOS */ + if ((c->x86 == 0x15) && + (c->x86_model >= 0x10) && (c->x86_model <= 0x1f) && + !cpu_has(c, X86_FEATURE_TOPOEXT)) { + u64 val; + + if (!rdmsrl_amd_safe(0xc0011005, &val)) { + val |= 1ULL << 54; + wrmsrl_amd_safe(0xc0011005, val); + rdmsrl(0xc0011005, val); + if (val & (1ULL << 54)) { + set_cpu_cap(c, X86_FEATURE_TOPOEXT); + printk(KERN_INFO FW_INFO "CPU: Re-enabling " + "disabled Topology Extensions Support\n"); + } + } + } + cpu_detect_cache_sizes(c); /* Multi core CPU? */ diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c index 67e2583..cf79302 100644 --- a/arch/x86/kernel/cpu/common.c +++ b/arch/x86/kernel/cpu/common.c @@ -1163,15 +1163,6 @@ static void dbg_restore_debug_regs(void) #endif /* ! CONFIG_KGDB */ /* - * Prints an error where the NUMA and configured core-number mismatch and the - * platform didn't override this to fix it up - */ -void __cpuinit x86_default_fixup_cpu_id(struct cpuinfo_x86 *c, int node) -{ - pr_err("NUMA core number %d differs from configured core number %d\n", node, c->phys_proc_id); -} - -/* * cpu_init() initializes state that is per-CPU. Some data is already * initialized (naturally) in the bootstrap process, such as the GDT * and IDT. We reload them nevertheless, this function acts as a diff --git a/arch/x86/kernel/cpu/intel_cacheinfo.c b/arch/x86/kernel/cpu/intel_cacheinfo.c index 73d08ed..b8f3653 100644 --- a/arch/x86/kernel/cpu/intel_cacheinfo.c +++ b/arch/x86/kernel/cpu/intel_cacheinfo.c @@ -433,14 +433,14 @@ int amd_set_l3_disable_slot(struct amd_northbridge *nb, int cpu, unsigned slot, /* check if @slot is already used or the index is already disabled */ ret = amd_get_l3_disable_slot(nb, slot); if (ret >= 0) - return -EINVAL; + return -EEXIST; if (index > nb->l3_cache.indices) return -EINVAL; /* check whether the other slot has disabled the same index already */ if (index == amd_get_l3_disable_slot(nb, !slot)) - return -EINVAL; + return -EEXIST; amd_l3_disable_index(nb, cpu, slot, index); @@ -468,8 +468,8 @@ static ssize_t store_cache_disable(struct _cpuid4_info *this_leaf, err = amd_set_l3_disable_slot(this_leaf->base.nb, cpu, slot, val); if (err) { if (err == -EEXIST) - printk(KERN_WARNING "L3 disable slot %d in use!\n", - slot); + pr_warning("L3 slot %d in use/index already disabled!\n", + slot); return err; } return count; diff --git a/arch/x86/kernel/cpu/mcheck/mce.c b/arch/x86/kernel/cpu/mcheck/mce.c index d086a09..11c9166 100644 --- a/arch/x86/kernel/cpu/mcheck/mce.c +++ b/arch/x86/kernel/cpu/mcheck/mce.c @@ -945,9 +945,10 @@ struct mce_info { atomic_t inuse; struct task_struct *t; __u64 paddr; + int restartable; } mce_info[MCE_INFO_MAX]; -static void mce_save_info(__u64 addr) +static void mce_save_info(__u64 addr, int c) { struct mce_info *mi; @@ -955,6 +956,7 @@ static void mce_save_info(__u64 addr) if (atomic_cmpxchg(&mi->inuse, 0, 1) == 0) { mi->t = current; mi->paddr = addr; + mi->restartable = c; return; } } @@ -1130,7 +1132,7 @@ void do_machine_check(struct pt_regs *regs, long error_code) mce_panic("Fatal machine check on current CPU", &m, msg); if (worst == MCE_AR_SEVERITY) { /* schedule action before return to userland */ - mce_save_info(m.addr); + mce_save_info(m.addr, m.mcgstatus & MCG_STATUS_RIPV); set_thread_flag(TIF_MCE_NOTIFY); } else if (kill_it) { force_sig(SIGBUS, current); @@ -1179,7 +1181,13 @@ void mce_notify_process(void) pr_err("Uncorrected hardware memory error in user-access at %llx", mi->paddr); - if (memory_failure(pfn, MCE_VECTOR, MF_ACTION_REQUIRED) < 0) { + /* + * We must call memory_failure() here even if the current process is + * doomed. We still need to mark the page as poisoned and alert any + * other users of the page. + */ + if (memory_failure(pfn, MCE_VECTOR, MF_ACTION_REQUIRED) < 0 || + mi->restartable == 0) { pr_err("Memory error not recovered"); force_sig(SIGBUS, current); } diff --git a/arch/x86/kernel/i387.c b/arch/x86/kernel/i387.c index 7734bcb..2d6e649 100644 --- a/arch/x86/kernel/i387.c +++ b/arch/x86/kernel/i387.c @@ -235,6 +235,7 @@ int init_fpu(struct task_struct *tsk) if (tsk_used_math(tsk)) { if (HAVE_HWFP && tsk == current) unlazy_fpu(tsk); + tsk->thread.fpu.last_cpu = ~0; return 0; } diff --git a/arch/x86/kernel/kvm.c b/arch/x86/kernel/kvm.c index b8ba6e4..e554e5a 100644 --- a/arch/x86/kernel/kvm.c +++ b/arch/x86/kernel/kvm.c @@ -79,7 +79,6 @@ struct kvm_task_sleep_node { u32 token; int cpu; bool halted; - struct mm_struct *mm; }; static struct kvm_task_sleep_head { @@ -126,9 +125,7 @@ void kvm_async_pf_task_wait(u32 token) n.token = token; n.cpu = smp_processor_id(); - n.mm = current->active_mm; n.halted = idle || preempt_count() > 1; - atomic_inc(&n.mm->mm_count); init_waitqueue_head(&n.wq); hlist_add_head(&n.link, &b->list); spin_unlock(&b->lock); @@ -161,9 +158,6 @@ EXPORT_SYMBOL_GPL(kvm_async_pf_task_wait); static void apf_task_wake_one(struct kvm_task_sleep_node *n) { hlist_del_init(&n->link); - if (!n->mm) - return; - mmdrop(n->mm); if (n->halted) smp_send_reschedule(n->cpu); else if (waitqueue_active(&n->wq)) @@ -207,7 +201,7 @@ again: * async PF was not yet handled. * Add dummy entry for the token. */ - n = kmalloc(sizeof(*n), GFP_ATOMIC); + n = kzalloc(sizeof(*n), GFP_ATOMIC); if (!n) { /* * Allocation failed! Busy wait while other cpu @@ -219,7 +213,6 @@ again: } n->token = token; n->cpu = smp_processor_id(); - n->mm = NULL; init_waitqueue_head(&n->wq); hlist_add_head(&n->link, &b->list); } else diff --git a/arch/x86/kernel/microcode_amd.c b/arch/x86/kernel/microcode_amd.c index 73465aa..8a2ce8f 100644 --- a/arch/x86/kernel/microcode_amd.c +++ b/arch/x86/kernel/microcode_amd.c @@ -82,11 +82,6 @@ static int collect_cpu_info_amd(int cpu, struct cpu_signature *csig) { struct cpuinfo_x86 *c = &cpu_data(cpu); - if (c->x86_vendor != X86_VENDOR_AMD || c->x86 < 0x10) { - pr_warning("CPU%d: family %d not supported\n", cpu, c->x86); - return -1; - } - csig->rev = c->microcode; pr_info("CPU%d: patch_level=0x%08x\n", cpu, csig->rev); @@ -380,6 +375,13 @@ static struct microcode_ops microcode_amd_ops = { struct microcode_ops * __init init_amd_microcode(void) { + struct cpuinfo_x86 *c = &cpu_data(0); + + if (c->x86_vendor != X86_VENDOR_AMD || c->x86 < 0x10) { + pr_warning("AMD CPU family 0x%x not supported\n", c->x86); + return NULL; + } + patch = (void *)get_zeroed_page(GFP_KERNEL); if (!patch) return NULL; diff --git a/arch/x86/kernel/microcode_core.c b/arch/x86/kernel/microcode_core.c index 87a0f86..c9bda6d 100644 --- a/arch/x86/kernel/microcode_core.c +++ b/arch/x86/kernel/microcode_core.c @@ -419,10 +419,8 @@ static int mc_device_add(struct device *dev, struct subsys_interface *sif) if (err) return err; - if (microcode_init_cpu(cpu) == UCODE_ERROR) { - sysfs_remove_group(&dev->kobj, &mc_attr_group); + if (microcode_init_cpu(cpu) == UCODE_ERROR) return -EINVAL; - } return err; } @@ -528,11 +526,11 @@ static int __init microcode_init(void) microcode_ops = init_intel_microcode(); else if (c->x86_vendor == X86_VENDOR_AMD) microcode_ops = init_amd_microcode(); - - if (!microcode_ops) { + else pr_err("no support for this CPU vendor\n"); + + if (!microcode_ops) return -ENODEV; - } microcode_pdev = platform_device_register_simple("microcode", -1, NULL, 0); diff --git a/arch/x86/kernel/microcode_intel.c b/arch/x86/kernel/microcode_intel.c index 3ca42d0..0327e2b 100644 --- a/arch/x86/kernel/microcode_intel.c +++ b/arch/x86/kernel/microcode_intel.c @@ -147,12 +147,6 @@ static int collect_cpu_info(int cpu_num, struct cpu_signature *csig) memset(csig, 0, sizeof(*csig)); - if (c->x86_vendor != X86_VENDOR_INTEL || c->x86 < 6 || - cpu_has(c, X86_FEATURE_IA64)) { - pr_err("CPU%d not a capable Intel processor\n", cpu_num); - return -1; - } - csig->sig = cpuid_eax(0x00000001); if ((c->x86_model >= 5) || (c->x86 > 6)) { @@ -463,6 +457,14 @@ static struct microcode_ops microcode_intel_ops = { struct microcode_ops * __init init_intel_microcode(void) { + struct cpuinfo_x86 *c = &cpu_data(0); + + if (c->x86_vendor != X86_VENDOR_INTEL || c->x86 < 6 || + cpu_has(c, X86_FEATURE_IA64)) { + pr_err("Intel CPU family 0x%x not supported\n", c->x86); + return NULL; + } + return µcode_intel_ops; } diff --git a/arch/x86/kernel/process_64.c b/arch/x86/kernel/process_64.c index 733ca39..43d8b48 100644 --- a/arch/x86/kernel/process_64.c +++ b/arch/x86/kernel/process_64.c @@ -423,6 +423,7 @@ void set_personality_ia32(bool x32) current_thread_info()->status |= TS_COMPAT; } } +EXPORT_SYMBOL_GPL(set_personality_ia32); unsigned long get_wchan(struct task_struct *p) { diff --git a/arch/x86/kernel/setup_percpu.c b/arch/x86/kernel/setup_percpu.c index 71f4727..5a98aa2 100644 --- a/arch/x86/kernel/setup_percpu.c +++ b/arch/x86/kernel/setup_percpu.c @@ -185,10 +185,22 @@ void __init setup_per_cpu_areas(void) #endif rc = -EINVAL; if (pcpu_chosen_fc != PCPU_FC_PAGE) { - const size_t atom_size = cpu_has_pse ? PMD_SIZE : PAGE_SIZE; const size_t dyn_size = PERCPU_MODULE_RESERVE + PERCPU_DYNAMIC_RESERVE - PERCPU_FIRST_CHUNK_RESERVE; + size_t atom_size; + /* + * On 64bit, use PMD_SIZE for atom_size so that embedded + * percpu areas are aligned to PMD. This, in the future, + * can also allow using PMD mappings in vmalloc area. Use + * PAGE_SIZE on 32bit as vmalloc space is highly contended + * and large vmalloc area allocs can easily fail. + */ +#ifdef CONFIG_X86_64 + atom_size = PMD_SIZE; +#else + atom_size = PAGE_SIZE; +#endif rc = pcpu_embed_first_chunk(PERCPU_FIRST_CHUNK_RESERVE, dyn_size, atom_size, pcpu_cpu_distance, diff --git a/arch/x86/kernel/vsyscall_64.c b/arch/x86/kernel/vsyscall_64.c index f386dc4..7515cf0e 100644 --- a/arch/x86/kernel/vsyscall_64.c +++ b/arch/x86/kernel/vsyscall_64.c @@ -216,9 +216,9 @@ bool emulate_vsyscall(struct pt_regs *regs, unsigned long address) current_thread_info()->sig_on_uaccess_error = 1; /* - * 0 is a valid user pointer (in the access_ok sense) on 32-bit and + * NULL is a valid user pointer (in the access_ok sense) on 32-bit and * 64-bit, so we don't need to special-case it here. For all the - * vsyscalls, 0 means "don't write anything" not "write it at + * vsyscalls, NULL means "don't write anything" not "write it at * address 0". */ ret = -EFAULT; @@ -247,7 +247,7 @@ bool emulate_vsyscall(struct pt_regs *regs, unsigned long address) ret = sys_getcpu((unsigned __user *)regs->di, (unsigned __user *)regs->si, - 0); + NULL); break; } diff --git a/arch/x86/kernel/x86_init.c b/arch/x86/kernel/x86_init.c index e9f265f..9cf71d0 100644 --- a/arch/x86/kernel/x86_init.c +++ b/arch/x86/kernel/x86_init.c @@ -93,7 +93,6 @@ struct x86_init_ops x86_init __initdata = { struct x86_cpuinit_ops x86_cpuinit __cpuinitdata = { .early_percpu_clock_init = x86_init_noop, .setup_percpu_clockev = setup_secondary_APIC_clock, - .fixup_cpu_id = x86_default_fixup_cpu_id, }; static void default_nmi_init(void) { }; diff --git a/arch/x86/kvm/pmu.c b/arch/x86/kvm/pmu.c index 173df38..2e88438 100644 --- a/arch/x86/kvm/pmu.c +++ b/arch/x86/kvm/pmu.c @@ -459,17 +459,17 @@ void kvm_pmu_cpuid_update(struct kvm_vcpu *vcpu) pmu->available_event_types = ~entry->ebx & ((1ull << bitmap_len) - 1); if (pmu->version == 1) { - pmu->global_ctrl = (1 << pmu->nr_arch_gp_counters) - 1; - return; + pmu->nr_arch_fixed_counters = 0; + } else { + pmu->nr_arch_fixed_counters = min((int)(entry->edx & 0x1f), + X86_PMC_MAX_FIXED); + pmu->counter_bitmask[KVM_PMC_FIXED] = + ((u64)1 << ((entry->edx >> 5) & 0xff)) - 1; } - pmu->nr_arch_fixed_counters = min((int)(entry->edx & 0x1f), - X86_PMC_MAX_FIXED); - pmu->counter_bitmask[KVM_PMC_FIXED] = - ((u64)1 << ((entry->edx >> 5) & 0xff)) - 1; - pmu->global_ctrl_mask = ~(((1 << pmu->nr_arch_gp_counters) - 1) - | (((1ull << pmu->nr_arch_fixed_counters) - 1) - << X86_PMC_IDX_FIXED)); + pmu->global_ctrl = ((1 << pmu->nr_arch_gp_counters) - 1) | + (((1ull << pmu->nr_arch_fixed_counters) - 1) << X86_PMC_IDX_FIXED); + pmu->global_ctrl_mask = ~pmu->global_ctrl; } void kvm_pmu_init(struct kvm_vcpu *vcpu) diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c index ad85adf..4ff0ab9 100644 --- a/arch/x86/kvm/vmx.c +++ b/arch/x86/kvm/vmx.c @@ -2210,9 +2210,12 @@ static int vmx_set_msr(struct kvm_vcpu *vcpu, u32 msr_index, u64 data) msr = find_msr_entry(vmx, msr_index); if (msr) { msr->data = data; - if (msr - vmx->guest_msrs < vmx->save_nmsrs) + if (msr - vmx->guest_msrs < vmx->save_nmsrs) { + preempt_disable(); kvm_set_shared_msr(msr->index, msr->data, msr->mask); + preempt_enable(); + } break; } ret = kvm_set_msr_common(vcpu, msr_index, data); diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index 4044ce0..185a2b8 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -6336,13 +6336,11 @@ int kvm_arch_prepare_memory_region(struct kvm *kvm, if (npages && !old.rmap) { unsigned long userspace_addr; - down_write(¤t->mm->mmap_sem); - userspace_addr = do_mmap(NULL, 0, + userspace_addr = vm_mmap(NULL, 0, npages * PAGE_SIZE, PROT_READ | PROT_WRITE, map_flags, 0); - up_write(¤t->mm->mmap_sem); if (IS_ERR((void *)userspace_addr)) return PTR_ERR((void *)userspace_addr); @@ -6366,10 +6364,8 @@ void kvm_arch_commit_memory_region(struct kvm *kvm, if (!user_alloc && !old.user_alloc && old.rmap && !npages) { int ret; - down_write(¤t->mm->mmap_sem); - ret = do_munmap(current->mm, old.userspace_addr, + ret = vm_munmap(old.userspace_addr, old.npages * PAGE_SIZE); - up_write(¤t->mm->mmap_sem); if (ret < 0) printk(KERN_WARNING "kvm_vm_ioctl_set_memory_region: " @@ -6585,6 +6581,7 @@ void kvm_arch_async_page_present(struct kvm_vcpu *vcpu, kvm_inject_page_fault(vcpu, &fault); } vcpu->arch.apf.halted = false; + vcpu->arch.mp_state = KVM_MP_STATE_RUNNABLE; } bool kvm_arch_can_inject_async_page_present(struct kvm_vcpu *vcpu) diff --git a/arch/x86/lib/insn.c b/arch/x86/lib/insn.c index 25feb1a..b1e6c4b 100644 --- a/arch/x86/lib/insn.c +++ b/arch/x86/lib/insn.c @@ -379,8 +379,8 @@ err_out: return; } -/* Decode moffset16/32/64 */ -static void __get_moffset(struct insn *insn) +/* Decode moffset16/32/64. Return 0 if failed */ +static int __get_moffset(struct insn *insn) { switch (insn->addr_bytes) { case 2: @@ -397,15 +397,19 @@ static void __get_moffset(struct insn *insn) insn->moffset2.value = get_next(int, insn); insn->moffset2.nbytes = 4; break; + default: /* opnd_bytes must be modified manually */ + goto err_out; } insn->moffset1.got = insn->moffset2.got = 1; + return 1; + err_out: - return; + return 0; } -/* Decode imm v32(Iz) */ -static void __get_immv32(struct insn *insn) +/* Decode imm v32(Iz). Return 0 if failed */ +static int __get_immv32(struct insn *insn) { switch (insn->opnd_bytes) { case 2: @@ -417,14 +421,18 @@ static void __get_immv32(struct insn *insn) insn->immediate.value = get_next(int, insn); insn->immediate.nbytes = 4; break; + default: /* opnd_bytes must be modified manually */ + goto err_out; } + return 1; + err_out: - return; + return 0; } -/* Decode imm v64(Iv/Ov) */ -static void __get_immv(struct insn *insn) +/* Decode imm v64(Iv/Ov), Return 0 if failed */ +static int __get_immv(struct insn *insn) { switch (insn->opnd_bytes) { case 2: @@ -441,15 +449,18 @@ static void __get_immv(struct insn *insn) insn->immediate2.value = get_next(int, insn); insn->immediate2.nbytes = 4; break; + default: /* opnd_bytes must be modified manually */ + goto err_out; } insn->immediate1.got = insn->immediate2.got = 1; + return 1; err_out: - return; + return 0; } /* Decode ptr16:16/32(Ap) */ -static void __get_immptr(struct insn *insn) +static int __get_immptr(struct insn *insn) { switch (insn->opnd_bytes) { case 2: @@ -462,14 +473,17 @@ static void __get_immptr(struct insn *insn) break; case 8: /* ptr16:64 is not exist (no segment) */ - return; + return 0; + default: /* opnd_bytes must be modified manually */ + goto err_out; } insn->immediate2.value = get_next(unsigned short, insn); insn->immediate2.nbytes = 2; insn->immediate1.got = insn->immediate2.got = 1; + return 1; err_out: - return; + return 0; } /** @@ -489,7 +503,8 @@ void insn_get_immediate(struct insn *insn) insn_get_displacement(insn); if (inat_has_moffset(insn->attr)) { - __get_moffset(insn); + if (!__get_moffset(insn)) + goto err_out; goto done; } @@ -517,16 +532,20 @@ void insn_get_immediate(struct insn *insn) insn->immediate2.nbytes = 4; break; case INAT_IMM_PTR: - __get_immptr(insn); + if (!__get_immptr(insn)) + goto err_out; break; case INAT_IMM_VWORD32: - __get_immv32(insn); + if (!__get_immv32(insn)) + goto err_out; break; case INAT_IMM_VWORD: - __get_immv(insn); + if (!__get_immv(insn)) + goto err_out; break; default: - break; + /* Here, insn must have an immediate, but failed */ + goto err_out; } if (inat_has_second_immediate(insn->attr)) { insn->immediate2.value = get_next(char, insn); diff --git a/arch/x86/lib/usercopy.c b/arch/x86/lib/usercopy.c index 97be9cb..d6ae30b 100644 --- a/arch/x86/lib/usercopy.c +++ b/arch/x86/lib/usercopy.c @@ -7,6 +7,8 @@ #include <linux/highmem.h> #include <linux/module.h> +#include <asm/word-at-a-time.h> + /* * best effort, GUP based copy_from_user() that is NMI-safe */ @@ -41,3 +43,104 @@ copy_from_user_nmi(void *to, const void __user *from, unsigned long n) return len; } EXPORT_SYMBOL_GPL(copy_from_user_nmi); + +static inline unsigned long count_bytes(unsigned long mask) +{ + mask = (mask - 1) & ~mask; + mask >>= 7; + return count_masked_bytes(mask); +} + +/* + * Do a strncpy, return length of string without final '\0'. + * 'count' is the user-supplied count (return 'count' if we + * hit it), 'max' is the address space maximum (and we return + * -EFAULT if we hit it). + */ +static inline long do_strncpy_from_user(char *dst, const char __user *src, long count, unsigned long max) +{ + long res = 0; + + /* + * Truncate 'max' to the user-specified limit, so that + * we only have one limit we need to check in the loop + */ + if (max > count) + max = count; + + while (max >= sizeof(unsigned long)) { + unsigned long c; + + /* Fall back to byte-at-a-time if we get a page fault */ + if (unlikely(__get_user(c,(unsigned long __user *)(src+res)))) + break; + /* This can write a few bytes past the NUL character, but that's ok */ + *(unsigned long *)(dst+res) = c; + c = has_zero(c); + if (c) + return res + count_bytes(c); + res += sizeof(unsigned long); + max -= sizeof(unsigned long); + } + + while (max) { + char c; + + if (unlikely(__get_user(c,src+res))) + return -EFAULT; + dst[res] = c; + if (!c) + return res; + res++; + max--; + } + + /* + * Uhhuh. We hit 'max'. But was that the user-specified maximum + * too? If so, that's ok - we got as much as the user asked for. + */ + if (res >= count) + return res; + + /* + * Nope: we hit the address space limit, and we still had more + * characters the caller would have wanted. That's an EFAULT. + */ + return -EFAULT; +} + +/** + * strncpy_from_user: - Copy a NUL terminated string from userspace. + * @dst: Destination address, in kernel space. This buffer must be at + * least @count bytes long. + * @src: Source address, in user space. + * @count: Maximum number of bytes to copy, including the trailing NUL. + * + * Copies a NUL-terminated string from userspace to kernel space. + * + * On success, returns the length of the string (not including the trailing + * NUL). + * + * If access to userspace fails, returns -EFAULT (some data may have been + * copied). + * + * If @count is smaller than the length of the string, copies @count bytes + * and returns @count. + */ +long +strncpy_from_user(char *dst, const char __user *src, long count) +{ + unsigned long max_addr, src_addr; + + if (unlikely(count <= 0)) + return 0; + + max_addr = current_thread_info()->addr_limit.seg; + src_addr = (unsigned long)src; + if (likely(src_addr < max_addr)) { + unsigned long max = max_addr - src_addr; + return do_strncpy_from_user(dst, src, count, max); + } + return -EFAULT; +} +EXPORT_SYMBOL(strncpy_from_user); diff --git a/arch/x86/lib/usercopy_32.c b/arch/x86/lib/usercopy_32.c index d9b094c..ef2a6a5 100644 --- a/arch/x86/lib/usercopy_32.c +++ b/arch/x86/lib/usercopy_32.c @@ -33,93 +33,6 @@ static inline int __movsl_is_ok(unsigned long a1, unsigned long a2, unsigned lon __movsl_is_ok((unsigned long)(a1), (unsigned long)(a2), (n)) /* - * Copy a null terminated string from userspace. - */ - -#define __do_strncpy_from_user(dst, src, count, res) \ -do { \ - int __d0, __d1, __d2; \ - might_fault(); \ - __asm__ __volatile__( \ - " testl %1,%1\n" \ - " jz 2f\n" \ - "0: lodsb\n" \ - " stosb\n" \ - " testb %%al,%%al\n" \ - " jz 1f\n" \ - " decl %1\n" \ - " jnz 0b\n" \ - "1: subl %1,%0\n" \ - "2:\n" \ - ".section .fixup,\"ax\"\n" \ - "3: movl %5,%0\n" \ - " jmp 2b\n" \ - ".previous\n" \ - _ASM_EXTABLE(0b,3b) \ - : "=&d"(res), "=&c"(count), "=&a" (__d0), "=&S" (__d1), \ - "=&D" (__d2) \ - : "i"(-EFAULT), "0"(count), "1"(count), "3"(src), "4"(dst) \ - : "memory"); \ -} while (0) - -/** - * __strncpy_from_user: - Copy a NUL terminated string from userspace, with less checking. - * @dst: Destination address, in kernel space. This buffer must be at - * least @count bytes long. - * @src: Source address, in user space. - * @count: Maximum number of bytes to copy, including the trailing NUL. - * - * Copies a NUL-terminated string from userspace to kernel space. - * Caller must check the specified block with access_ok() before calling - * this function. - * - * On success, returns the length of the string (not including the trailing - * NUL). - * - * If access to userspace fails, returns -EFAULT (some data may have been - * copied). - * - * If @count is smaller than the length of the string, copies @count bytes - * and returns @count. - */ -long -__strncpy_from_user(char *dst, const char __user *src, long count) -{ - long res; - __do_strncpy_from_user(dst, src, count, res); - return res; -} -EXPORT_SYMBOL(__strncpy_from_user); - -/** - * strncpy_from_user: - Copy a NUL terminated string from userspace. - * @dst: Destination address, in kernel space. This buffer must be at - * least @count bytes long. - * @src: Source address, in user space. - * @count: Maximum number of bytes to copy, including the trailing NUL. - * - * Copies a NUL-terminated string from userspace to kernel space. - * - * On success, returns the length of the string (not including the trailing - * NUL). - * - * If access to userspace fails, returns -EFAULT (some data may have been - * copied). - * - * If @count is smaller than the length of the string, copies @count bytes - * and returns @count. - */ -long -strncpy_from_user(char *dst, const char __user *src, long count) -{ - long res = -EFAULT; - if (access_ok(VERIFY_READ, src, 1)) - __do_strncpy_from_user(dst, src, count, res); - return res; -} -EXPORT_SYMBOL(strncpy_from_user); - -/* * Zero Userspace */ diff --git a/arch/x86/lib/usercopy_64.c b/arch/x86/lib/usercopy_64.c index b7c2849..0d0326f 100644 --- a/arch/x86/lib/usercopy_64.c +++ b/arch/x86/lib/usercopy_64.c @@ -9,55 +9,6 @@ #include <asm/uaccess.h> /* - * Copy a null terminated string from userspace. - */ - -#define __do_strncpy_from_user(dst,src,count,res) \ -do { \ - long __d0, __d1, __d2; \ - might_fault(); \ - __asm__ __volatile__( \ - " testq %1,%1\n" \ - " jz 2f\n" \ - "0: lodsb\n" \ - " stosb\n" \ - " testb %%al,%%al\n" \ - " jz 1f\n" \ - " decq %1\n" \ - " jnz 0b\n" \ - "1: subq %1,%0\n" \ - "2:\n" \ - ".section .fixup,\"ax\"\n" \ - "3: movq %5,%0\n" \ - " jmp 2b\n" \ - ".previous\n" \ - _ASM_EXTABLE(0b,3b) \ - : "=&r"(res), "=&c"(count), "=&a" (__d0), "=&S" (__d1), \ - "=&D" (__d2) \ - : "i"(-EFAULT), "0"(count), "1"(count), "3"(src), "4"(dst) \ - : "memory"); \ -} while (0) - -long -__strncpy_from_user(char *dst, const char __user *src, long count) -{ - long res; - __do_strncpy_from_user(dst, src, count, res); - return res; -} -EXPORT_SYMBOL(__strncpy_from_user); - -long -strncpy_from_user(char *dst, const char __user *src, long count) -{ - long res = -EFAULT; - if (access_ok(VERIFY_READ, src, 1)) - return __strncpy_from_user(dst, src, count); - return res; -} -EXPORT_SYMBOL(strncpy_from_user); - -/* * Zero Userspace */ diff --git a/arch/x86/platform/geode/net5501.c b/arch/x86/platform/geode/net5501.c index 66d377e..646e3b5 100644 --- a/arch/x86/platform/geode/net5501.c +++ b/arch/x86/platform/geode/net5501.c @@ -63,7 +63,7 @@ static struct gpio_led net5501_leds[] = { .name = "net5501:1", .gpio = 6, .default_trigger = "default-on", - .active_low = 1, + .active_low = 0, }, }; diff --git a/arch/x86/platform/mrst/mrst.c b/arch/x86/platform/mrst/mrst.c index e0a3723..e31bcd8 100644 --- a/arch/x86/platform/mrst/mrst.c +++ b/arch/x86/platform/mrst/mrst.c @@ -805,7 +805,7 @@ void intel_scu_devices_create(void) } else i2c_register_board_info(i2c_bus[i], i2c_devs[i], 1); } - intel_scu_notifier_post(SCU_AVAILABLE, 0L); + intel_scu_notifier_post(SCU_AVAILABLE, NULL); } EXPORT_SYMBOL_GPL(intel_scu_devices_create); @@ -814,7 +814,7 @@ void intel_scu_devices_destroy(void) { int i; - intel_scu_notifier_post(SCU_DOWN, 0L); + intel_scu_notifier_post(SCU_DOWN, NULL); for (i = 0; i < ipc_next_dev; i++) platform_device_del(ipc_devs[i]); diff --git a/arch/x86/tools/.gitignore b/arch/x86/tools/.gitignore new file mode 100644 index 0000000..be0ed06 --- /dev/null +++ b/arch/x86/tools/.gitignore @@ -0,0 +1 @@ +relocs diff --git a/arch/x86/tools/Makefile b/arch/x86/tools/Makefile index d511aa9..733057b 100644 --- a/arch/x86/tools/Makefile +++ b/arch/x86/tools/Makefile @@ -36,3 +36,7 @@ HOSTCFLAGS_insn_sanity.o := -Wall -I$(objtree)/arch/x86/lib/ -I$(srctree)/arch/x $(obj)/test_get_len.o: $(srctree)/arch/x86/lib/insn.c $(srctree)/arch/x86/lib/inat.c $(srctree)/arch/x86/include/asm/inat_types.h $(srctree)/arch/x86/include/asm/inat.h $(srctree)/arch/x86/include/asm/insn.h $(objtree)/arch/x86/lib/inat-tables.c $(obj)/insn_sanity.o: $(srctree)/arch/x86/lib/insn.c $(srctree)/arch/x86/lib/inat.c $(srctree)/arch/x86/include/asm/inat_types.h $(srctree)/arch/x86/include/asm/inat.h $(srctree)/arch/x86/include/asm/insn.h $(objtree)/arch/x86/lib/inat-tables.c + +HOST_EXTRACFLAGS += -I$(srctree)/tools/include +hostprogs-y += relocs +relocs: $(obj)/relocs diff --git a/arch/x86/boot/compressed/relocs.c b/arch/x86/tools/relocs.c index d3c0b02..b43cfcd 100644 --- a/arch/x86/boot/compressed/relocs.c +++ b/arch/x86/tools/relocs.c @@ -18,6 +18,8 @@ static void die(char *fmt, ...); static Elf32_Ehdr ehdr; static unsigned long reloc_count, reloc_idx; static unsigned long *relocs; +static unsigned long reloc16_count, reloc16_idx; +static unsigned long *relocs16; struct section { Elf32_Shdr shdr; @@ -28,52 +30,86 @@ struct section { }; static struct section *secs; +enum symtype { + S_ABS, + S_REL, + S_SEG, + S_LIN, + S_NSYMTYPES +}; + +static const char * const sym_regex_kernel[S_NSYMTYPES] = { /* * Following symbols have been audited. There values are constant and do * not change if bzImage is loaded at a different physical address than * the address for which it has been compiled. Don't warn user about * absolute relocations present w.r.t these symbols. */ -static const char abs_sym_regex[] = + [S_ABS] = "^(xen_irq_disable_direct_reloc$|" "xen_save_fl_direct_reloc$|" "VDSO|" - "__crc_)"; -static regex_t abs_sym_regex_c; -static int is_abs_reloc(const char *sym_name) -{ - return !regexec(&abs_sym_regex_c, sym_name, 0, NULL, 0); -} + "__crc_)", /* * These symbols are known to be relative, even if the linker marks them * as absolute (typically defined outside any section in the linker script.) */ -static const char rel_sym_regex[] = - "^_end$"; -static regex_t rel_sym_regex_c; -static int is_rel_reloc(const char *sym_name) + [S_REL] = + "^(__init_(begin|end)|" + "__x86_cpu_dev_(start|end)|" + "(__parainstructions|__alt_instructions)(|_end)|" + "(__iommu_table|__apicdrivers|__smp_locks)(|_end)|" + "_end)$" +}; + + +static const char * const sym_regex_realmode[S_NSYMTYPES] = { +/* + * These are 16-bit segment symbols when compiling 16-bit code. + */ + [S_SEG] = + "^real_mode_seg$", + +/* + * These are offsets belonging to segments, as opposed to linear addresses, + * when compiling 16-bit code. + */ + [S_LIN] = + "^pa_", +}; + +static const char * const *sym_regex; + +static regex_t sym_regex_c[S_NSYMTYPES]; +static int is_reloc(enum symtype type, const char *sym_name) { - return !regexec(&rel_sym_regex_c, sym_name, 0, NULL, 0); + return sym_regex[type] && + !regexec(&sym_regex_c[type], sym_name, 0, NULL, 0); } -static void regex_init(void) +static void regex_init(int use_real_mode) { 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); - } + int i; + + if (use_real_mode) + sym_regex = sym_regex_realmode; + else + sym_regex = sym_regex_kernel; - 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); + for (i = 0; i < S_NSYMTYPES; i++) { + if (!sym_regex[i]) + continue; + + err = regcomp(&sym_regex_c[i], sym_regex[i], + REG_EXTENDED|REG_NOSUB); + + if (err) { + regerror(err, &sym_regex_c[i], errbuf, sizeof errbuf); + die("%s", errbuf); + } } } @@ -154,6 +190,10 @@ static const char *rel_type(unsigned type) REL_TYPE(R_386_RELATIVE), REL_TYPE(R_386_GOTOFF), REL_TYPE(R_386_GOTPC), + REL_TYPE(R_386_8), + REL_TYPE(R_386_PC8), + REL_TYPE(R_386_16), + REL_TYPE(R_386_PC16), #undef REL_TYPE }; const char *name = "unknown type rel type name"; @@ -189,7 +229,7 @@ static const char *sym_name(const char *sym_strtab, Elf32_Sym *sym) name = sym_strtab + sym->st_name; } else { - name = sec_name(secs[sym->st_shndx].shdr.sh_name); + name = sec_name(sym->st_shndx); } return name; } @@ -403,13 +443,11 @@ static void print_absolute_symbols(void) for (i = 0; i < ehdr.e_shnum; i++) { struct section *sec = &secs[i]; char *sym_strtab; - Elf32_Sym *sh_symtab; int j; if (sec->shdr.sh_type != SHT_SYMTAB) { continue; } - sh_symtab = sec->symtab; sym_strtab = sec->link->strtab; for (j = 0; j < sec->shdr.sh_size/sizeof(Elf32_Sym); j++) { Elf32_Sym *sym; @@ -474,7 +512,7 @@ static void print_absolute_relocs(void) * Before warning check if this absolute symbol * relocation is harmless. */ - if (is_abs_reloc(name) || is_rel_reloc(name)) + if (is_reloc(S_ABS, name) || is_reloc(S_REL, name)) continue; if (!printed) { @@ -498,7 +536,8 @@ static void print_absolute_relocs(void) printf("\n"); } -static void walk_relocs(void (*visit)(Elf32_Rel *rel, Elf32_Sym *sym)) +static void walk_relocs(void (*visit)(Elf32_Rel *rel, Elf32_Sym *sym), + int use_real_mode) { int i; /* Walk through the relocations */ @@ -523,30 +562,67 @@ static void walk_relocs(void (*visit)(Elf32_Rel *rel, Elf32_Sym *sym)) Elf32_Rel *rel; Elf32_Sym *sym; unsigned r_type; + const char *symname; + int shn_abs; + rel = &sec->reltab[j]; 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 && - !is_rel_reloc(sym_name(sym_strtab, sym))) { - continue; - } + + shn_abs = sym->st_shndx == SHN_ABS; + switch (r_type) { case R_386_NONE: case R_386_PC32: + case R_386_PC16: + case R_386_PC8: /* * NONE can be ignored and and PC relative * relocations don't need to be adjusted. */ break; + + case R_386_16: + symname = sym_name(sym_strtab, sym); + if (!use_real_mode) + goto bad; + if (shn_abs) { + if (is_reloc(S_ABS, symname)) + break; + else if (!is_reloc(S_SEG, symname)) + goto bad; + } else { + if (is_reloc(S_LIN, symname)) + goto bad; + else + break; + } + visit(rel, sym); + break; + case R_386_32: - /* Visit relocations that need to be adjusted */ + symname = sym_name(sym_strtab, sym); + if (shn_abs) { + if (is_reloc(S_ABS, symname)) + break; + else if (!is_reloc(S_REL, symname)) + goto bad; + } else { + if (use_real_mode && + !is_reloc(S_LIN, symname)) + break; + } visit(rel, sym); break; default: die("Unsupported relocation type: %s (%d)\n", rel_type(r_type), r_type); break; + bad: + symname = sym_name(sym_strtab, sym); + die("Invalid %s %s relocation: %s\n", + shn_abs ? "absolute" : "relative", + rel_type(r_type), symname); } } } @@ -554,13 +630,19 @@ static void walk_relocs(void (*visit)(Elf32_Rel *rel, Elf32_Sym *sym)) static void count_reloc(Elf32_Rel *rel, Elf32_Sym *sym) { - reloc_count += 1; + if (ELF32_R_TYPE(rel->r_info) == R_386_16) + reloc16_count++; + else + reloc_count++; } static void collect_reloc(Elf32_Rel *rel, Elf32_Sym *sym) { /* Remember the address that needs to be adjusted. */ - relocs[reloc_idx++] = rel->r_offset; + if (ELF32_R_TYPE(rel->r_info) == R_386_16) + relocs16[reloc16_idx++] = rel->r_offset; + else + relocs[reloc_idx++] = rel->r_offset; } static int cmp_relocs(const void *va, const void *vb) @@ -570,23 +652,41 @@ static int cmp_relocs(const void *va, const void *vb) return (*a == *b)? 0 : (*a > *b)? 1 : -1; } -static void emit_relocs(int as_text) +static int write32(unsigned int v, FILE *f) +{ + unsigned char buf[4]; + + put_unaligned_le32(v, buf); + return fwrite(buf, 1, 4, f) == 4 ? 0 : -1; +} + +static void emit_relocs(int as_text, int use_real_mode) { int i; /* Count how many relocations I have and allocate space for them. */ reloc_count = 0; - walk_relocs(count_reloc); + walk_relocs(count_reloc, use_real_mode); relocs = malloc(reloc_count * sizeof(relocs[0])); if (!relocs) { die("malloc of %d entries for relocs failed\n", reloc_count); } + + relocs16 = malloc(reloc16_count * sizeof(relocs[0])); + if (!relocs16) { + die("malloc of %d entries for relocs16 failed\n", + reloc16_count); + } /* Collect up the relocations */ reloc_idx = 0; - walk_relocs(collect_reloc); + walk_relocs(collect_reloc, use_real_mode); + + if (reloc16_count && !use_real_mode) + die("Segment relocations found but --realmode not specified\n"); /* Order the relocations for more efficient processing */ qsort(relocs, reloc_count, sizeof(relocs[0]), cmp_relocs); + qsort(relocs16, reloc16_count, sizeof(relocs16[0]), cmp_relocs); /* Print the relocations */ if (as_text) { @@ -595,58 +695,83 @@ static void emit_relocs(int as_text) */ printf(".section \".data.reloc\",\"a\"\n"); printf(".balign 4\n"); - for (i = 0; i < reloc_count; i++) { - printf("\t .long 0x%08lx\n", relocs[i]); + if (use_real_mode) { + printf("\t.long %lu\n", reloc16_count); + for (i = 0; i < reloc16_count; i++) + printf("\t.long 0x%08lx\n", relocs16[i]); + printf("\t.long %lu\n", reloc_count); + for (i = 0; i < reloc_count; i++) { + printf("\t.long 0x%08lx\n", relocs[i]); + } + } else { + /* Print a stop */ + printf("\t.long 0x%08lx\n", (unsigned long)0); + for (i = 0; i < reloc_count; i++) { + printf("\t.long 0x%08lx\n", relocs[i]); + } } + printf("\n"); } else { - unsigned char buf[4]; - /* Print a stop */ - fwrite("\0\0\0\0", 4, 1, stdout); - /* Now print each relocation */ - for (i = 0; i < reloc_count; i++) { - put_unaligned_le32(relocs[i], buf); - fwrite(buf, 4, 1, stdout); + if (use_real_mode) { + write32(reloc16_count, stdout); + for (i = 0; i < reloc16_count; i++) + write32(relocs16[i], stdout); + write32(reloc_count, stdout); + + /* Now print each relocation */ + for (i = 0; i < reloc_count; i++) + write32(relocs[i], stdout); + } else { + /* Print a stop */ + write32(0, stdout); + + /* Now print each relocation */ + for (i = 0; i < reloc_count; i++) { + write32(relocs[i], stdout); + } } } } static void usage(void) { - die("relocs [--abs-syms |--abs-relocs | --text] vmlinux\n"); + die("relocs [--abs-syms|--abs-relocs|--text|--realmode] vmlinux\n"); } int main(int argc, char **argv) { int show_absolute_syms, show_absolute_relocs; - int as_text; + int as_text, use_real_mode; const char *fname; FILE *fp; int i; - regex_init(); - show_absolute_syms = 0; show_absolute_relocs = 0; as_text = 0; + use_real_mode = 0; fname = NULL; for (i = 1; i < argc; i++) { char *arg = argv[i]; if (*arg == '-') { - if (strcmp(argv[1], "--abs-syms") == 0) { + if (strcmp(arg, "--abs-syms") == 0) { show_absolute_syms = 1; continue; } - - if (strcmp(argv[1], "--abs-relocs") == 0) { + if (strcmp(arg, "--abs-relocs") == 0) { show_absolute_relocs = 1; continue; } - else if (strcmp(argv[1], "--text") == 0) { + if (strcmp(arg, "--text") == 0) { as_text = 1; continue; } + if (strcmp(arg, "--realmode") == 0) { + use_real_mode = 1; + continue; + } } else if (!fname) { fname = arg; @@ -657,6 +782,7 @@ int main(int argc, char **argv) if (!fname) { usage(); } + regex_init(use_real_mode); fp = fopen(fname, "r"); if (!fp) { die("Cannot open %s: %s\n", @@ -675,6 +801,6 @@ int main(int argc, char **argv) print_absolute_relocs(); return 0; } - emit_relocs(as_text); + emit_relocs(as_text, use_real_mode); return 0; } 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/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/xen/enlighten.c b/arch/x86/xen/enlighten.c index 4f51beb..95dccce 100644 --- a/arch/x86/xen/enlighten.c +++ b/arch/x86/xen/enlighten.c @@ -63,6 +63,7 @@ #include <asm/stackprotector.h> #include <asm/hypervisor.h> #include <asm/mwait.h> +#include <asm/pci_x86.h> #ifdef CONFIG_ACPI #include <linux/acpi.h> @@ -261,7 +262,8 @@ static void xen_cpuid(unsigned int *ax, unsigned int *bx, static bool __init xen_check_mwait(void) { -#ifdef CONFIG_ACPI +#if defined(CONFIG_ACPI) && !defined(CONFIG_ACPI_PROCESSOR_AGGREGATOR) && \ + !defined(CONFIG_ACPI_PROCESSOR_AGGREGATOR_MODULE) struct xen_platform_op op = { .cmd = XENPF_set_processor_pminfo, .u.set_pminfo.id = -1, @@ -349,7 +351,6 @@ static void __init xen_init_cpuid_mask(void) /* Xen will set CR4.OSXSAVE if supported and not disabled by force */ if ((cx & xsave_mask) != xsave_mask) cpuid_leaf1_ecx_mask &= ~xsave_mask; /* disable XSAVE & OSXSAVE */ - if (xen_check_mwait()) cpuid_leaf1_ecx_set_mask = (1 << (X86_FEATURE_MWAIT % 32)); } @@ -809,9 +810,40 @@ static void xen_io_delay(void) } #ifdef CONFIG_X86_LOCAL_APIC +static unsigned long xen_set_apic_id(unsigned int x) +{ + WARN_ON(1); + return x; +} +static unsigned int xen_get_apic_id(unsigned long x) +{ + return ((x)>>24) & 0xFFu; +} static u32 xen_apic_read(u32 reg) { - return 0; + struct xen_platform_op op = { + .cmd = XENPF_get_cpuinfo, + .interface_version = XENPF_INTERFACE_VERSION, + .u.pcpu_info.xen_cpuid = 0, + }; + int ret = 0; + + /* Shouldn't need this as APIC is turned off for PV, and we only + * get called on the bootup processor. But just in case. */ + if (!xen_initial_domain() || smp_processor_id()) + return 0; + + if (reg == APIC_LVR) + return 0x10; + + if (reg != APIC_ID) + return 0; + + ret = HYPERVISOR_dom0_op(&op); + if (ret) + return 0; + + return op.u.pcpu_info.apic_id << 24; } static void xen_apic_write(u32 reg, u32 val) @@ -849,6 +881,8 @@ static void set_xen_basic_apic_ops(void) apic->icr_write = xen_apic_icr_write; apic->wait_icr_idle = xen_apic_wait_icr_idle; apic->safe_wait_icr_idle = xen_safe_apic_wait_icr_idle; + apic->set_apic_id = xen_set_apic_id; + apic->get_apic_id = xen_get_apic_id; } #endif @@ -1365,8 +1399,10 @@ asmlinkage void __init xen_start_kernel(void) /* Make sure ACS will be enabled */ pci_request_acs(); } - - +#ifdef CONFIG_PCI + /* PCI BIOS service won't work from a PV guest. */ + pci_probe &= ~PCI_PROBE_BIOS; +#endif xen_raw_console_write("about to get started...\n"); xen_setup_runstate_info(0); diff --git a/arch/x86/xen/mmu.c b/arch/x86/xen/mmu.c index b8e2794..69f5857 100644 --- a/arch/x86/xen/mmu.c +++ b/arch/x86/xen/mmu.c @@ -353,8 +353,13 @@ static pteval_t pte_mfn_to_pfn(pteval_t val) { if (val & _PAGE_PRESENT) { unsigned long mfn = (val & PTE_PFN_MASK) >> PAGE_SHIFT; + unsigned long pfn = mfn_to_pfn(mfn); + pteval_t flags = val & PTE_FLAGS_MASK; - val = ((pteval_t)mfn_to_pfn(mfn) << PAGE_SHIFT) | flags; + if (unlikely(pfn == ~0)) + val = flags & ~_PAGE_PRESENT; + else + val = ((pteval_t)pfn << PAGE_SHIFT) | flags; } return val; diff --git a/arch/x86/xen/smp.c b/arch/x86/xen/smp.c index 5fac691..0503c0c 100644 --- a/arch/x86/xen/smp.c +++ b/arch/x86/xen/smp.c @@ -178,6 +178,7 @@ static void __init xen_fill_possible_map(void) static void __init xen_filter_cpu_maps(void) { int i, rc; + unsigned int subtract = 0; if (!xen_initial_domain()) return; @@ -192,8 +193,22 @@ static void __init xen_filter_cpu_maps(void) } else { set_cpu_possible(i, false); set_cpu_present(i, false); + subtract++; } } +#ifdef CONFIG_HOTPLUG_CPU + /* This is akin to using 'nr_cpus' on the Linux command line. + * Which is OK as when we use 'dom0_max_vcpus=X' we can only + * have up to X, while nr_cpu_ids is greater than X. This + * normally is not a problem, except when CPU hotplugging + * is involved and then there might be more than X CPUs + * in the guest - which will not work as there is no + * hypercall to expand the max number of VCPUs an already + * running guest has. So cap it up to X. */ + if (subtract) + nr_cpu_ids = nr_cpu_ids - subtract; +#endif + } static void __init xen_smp_prepare_boot_cpu(void) diff --git a/arch/x86/xen/xen-asm.S b/arch/x86/xen/xen-asm.S index 79d7362..3e45aa0 100644 --- a/arch/x86/xen/xen-asm.S +++ b/arch/x86/xen/xen-asm.S @@ -96,7 +96,7 @@ ENTRY(xen_restore_fl_direct) /* check for unmasked and pending */ cmpw $0x0001, PER_CPU_VAR(xen_vcpu_info) + XEN_vcpu_info_pending - jz 1f + jnz 1f 2: call check_events 1: ENDPATCH(xen_restore_fl_direct) |