diff options
Diffstat (limited to 'arch/x86')
38 files changed, 273 insertions, 138 deletions
diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig index 1d14cc6b79ad..c9866b0b77d8 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/boot/compressed/head_32.S b/arch/x86/boot/compressed/head_32.S index a0559930a180..c85e3ac99bba 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 558d76ce23bc..87e03a13d8e3 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/compressed/relocs.c b/arch/x86/boot/compressed/relocs.c index d3c0b0277666..fb7117a4ade1 100644 --- a/arch/x86/boot/compressed/relocs.c +++ b/arch/x86/boot/compressed/relocs.c @@ -403,13 +403,11 @@ 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; diff --git a/arch/x86/boot/tools/build.c b/arch/x86/boot/tools/build.c index ed549767a231..24443a332083 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 d511d951a052..07b3a68d2d29 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/posix_types.h b/arch/x86/include/asm/posix_types.h index 3427b7798dbc..7ef7c3020e5c 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 4a085383af27..5ca71c065eef 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 fc1aa5535646..34c47b3341c0 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/unistd.h b/arch/x86/include/asm/unistd.h index 37cdc9d99bb1..4437001d8e3d 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 6fe6767b7124..e58f03b206c3 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 baaca8defec8..764b66a4cf89 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/sleep.c b/arch/x86/kernel/acpi/sleep.c index 103b6ab368d3..146a49c763a4 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 416d4be13fef..d68677a2a010 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 13ab720573e3..72610839f03b 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 8ea5164cbd04..014d1d28c397 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 11544d8f1e97..edc24480469f 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 899803e03214..23e75422e013 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 8a778db45e3a..991e315f4227 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 0a44b90602b0..146bb6218eec 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 67e258362a3d..cf79302198a6 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 73d08ed98a64..b8f3653dddbc 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/i387.c b/arch/x86/kernel/i387.c index 7734bcbb5a3a..2d6e6498c176 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 b8ba6e4a27e4..e554e5ad2fe8 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 73465aab28f8..8a2ce8fd41c0 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 87a0f8688301..c9bda6d6035c 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/process_64.c b/arch/x86/kernel/process_64.c index 733ca39f367e..43d8b48b23e6 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 71f4727da373..5a98aa272184 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/x86_init.c b/arch/x86/kernel/x86_init.c index e9f265fd79ae..9cf71d0b2d37 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 173df38dbda5..2e88438ffd83 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 ad85adfef843..4ff0ab9bc3c8 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 4044ce0bf7c1..185a2b823a2d 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/platform/geode/net5501.c b/arch/x86/platform/geode/net5501.c index 66d377e334f7..646e3b5b4bb6 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 e0a37233c0af..e31bcd8f2eee 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/xen/enlighten.c b/arch/x86/xen/enlighten.c index 4f51bebac02c..95dccce8e979 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 b8e279479a6b..69f5857660ac 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 5fac6919b957..0503c0c493a9 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 79d7362ad6d1..3e45aa000718 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) |