diff options
Diffstat (limited to 'arch/x86')
46 files changed, 418 insertions, 290 deletions
diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig index 4a88cf7..6c70fed 100644 --- a/arch/x86/Kconfig +++ b/arch/x86/Kconfig @@ -21,7 +21,8 @@ config X86 select HAVE_IDE select HAVE_OPROFILE select HAVE_KPROBES - select HAVE_KVM + select HAVE_KRETPROBES + select HAVE_KVM if ((X86_32 && !X86_VOYAGER && !X86_VISWS && !X86_NUMAQ) || X86_64) config GENERIC_LOCKBREAK @@ -65,9 +66,6 @@ config MMU config ZONE_DMA def_bool y -config QUICKLIST - def_bool X86_32 - config SBUS bool @@ -1261,7 +1259,7 @@ menuconfig APM machines with more than one CPU. In order to use APM, you will need supporting software. For location - and more information, read <file:Documentation/pm.txt> and the + and more information, read <file:Documentation/power/pm.txt> and the Battery Powered Linux mini-HOWTO, available from <http://www.tldp.org/docs.html#howto>. diff --git a/arch/x86/Kconfig.cpu b/arch/x86/Kconfig.cpu index e09a6b7..9304bfb 100644 --- a/arch/x86/Kconfig.cpu +++ b/arch/x86/Kconfig.cpu @@ -377,6 +377,19 @@ config X86_OOSTORE def_bool y depends on (MWINCHIP3D || MWINCHIP2 || MWINCHIPC6) && MTRR +# +# P6_NOPs are a relatively minor optimization that require a family >= +# 6 processor, except that it is broken on certain VIA chips. +# Furthermore, AMD chips prefer a totally different sequence of NOPs +# (which work on all CPUs). As a result, disallow these if we're +# compiling X86_GENERIC but not X86_64 (these NOPs do work on all +# x86-64 capable chips); the list of processors in the right-hand clause +# are the cores that benefit from this optimization. +# +config X86_P6_NOP + def_bool y + depends on (X86_64 || !X86_GENERIC) && (M686 || MPENTIUMII || MPENTIUMIII || MPENTIUMM || MCORE2 || MPENTIUM4) + config X86_TSC def_bool y depends on ((MWINCHIP3D || MWINCHIP2 || MCRUSOE || MEFFICEON || MCYRIXIII || MK7 || MK6 || MPENTIUM4 || MPENTIUMM || MPENTIUMIII || MPENTIUMII || M686 || M586MMX || M586TSC || MK8 || MVIAC3_2 || MVIAC7 || MGEODEGX1 || MGEODE_LX || MCORE2) && !X86_NUMAQ) || X86_64 @@ -390,6 +403,7 @@ config X86_CMOV config X86_MINIMUM_CPU_FAMILY int default "64" if X86_64 + default "6" if X86_32 && X86_P6_NOP default "4" if X86_32 && (X86_XADD || X86_CMPXCHG || X86_BSWAP || X86_WP_WORKS_OK) default "3" diff --git a/arch/x86/boot/memory.c b/arch/x86/boot/memory.c index 3783539..e77d89f 100644 --- a/arch/x86/boot/memory.c +++ b/arch/x86/boot/memory.c @@ -37,6 +37,12 @@ static int detect_memory_e820(void) "=m" (*desc) : "D" (desc), "d" (SMAP), "a" (0xe820)); + /* BIOSes which terminate the chain with CF = 1 as opposed + to %ebx = 0 don't always report the SMAP signature on + the final, failing, probe. */ + if (err) + break; + /* Some BIOSes stop returning SMAP in the middle of the search loop. We don't know exactly how the BIOS screwed up the map at that point, we might have a @@ -47,9 +53,6 @@ static int detect_memory_e820(void) break; } - if (err) - break; - count++; desc++; } while (next && count < E820MAX); diff --git a/arch/x86/boot/vesa.h b/arch/x86/boot/vesa.h index ff5b73c..468e444 100644 --- a/arch/x86/boot/vesa.h +++ b/arch/x86/boot/vesa.h @@ -26,17 +26,10 @@ struct vesa_general_info { far_ptr video_mode_ptr; /* 14 */ u16 total_memory; /* 18 */ - u16 oem_software_rev; /* 20 */ - far_ptr oem_vendor_name_ptr; /* 22 */ - far_ptr oem_product_name_ptr; /* 26 */ - far_ptr oem_product_rev_ptr; /* 30 */ - - u8 reserved[222]; /* 34 */ - u8 oem_data[256]; /* 256 */ + u8 reserved[236]; /* 20 */ } __attribute__ ((packed)); #define VESA_MAGIC ('V' + ('E' << 8) + ('S' << 16) + ('A' << 24)) -#define VBE2_MAGIC ('V' + ('B' << 8) + ('E' << 16) + ('2' << 24)) struct vesa_mode_info { u16 mode_attr; /* 0 */ diff --git a/arch/x86/boot/video-vesa.c b/arch/x86/boot/video-vesa.c index 662dd2f..419b5c2 100644 --- a/arch/x86/boot/video-vesa.c +++ b/arch/x86/boot/video-vesa.c @@ -37,8 +37,6 @@ static int vesa_probe(void) video_vesa.modes = GET_HEAP(struct mode_info, 0); - vginfo.signature = VBE2_MAGIC; - ax = 0x4f00; di = (size_t)&vginfo; asm(INT10 diff --git a/arch/x86/ia32/ia32_signal.c b/arch/x86/ia32/ia32_signal.c index 1c0503b..5e7771a 100644 --- a/arch/x86/ia32/ia32_signal.c +++ b/arch/x86/ia32/ia32_signal.c @@ -500,7 +500,7 @@ int ia32_setup_frame(int sig, struct k_sigaction *ka, regs->ss = __USER32_DS; set_fs(USER_DS); - regs->flags &= ~X86_EFLAGS_TF; + regs->flags &= ~(X86_EFLAGS_TF | X86_EFLAGS_DF); if (test_thread_flag(TIF_SINGLESTEP)) ptrace_notify(SIGTRAP); @@ -600,7 +600,7 @@ int ia32_setup_rt_frame(int sig, struct k_sigaction *ka, siginfo_t *info, regs->ss = __USER32_DS; set_fs(USER_DS); - regs->flags &= ~X86_EFLAGS_TF; + regs->flags &= ~(X86_EFLAGS_TF | X86_EFLAGS_DF); if (test_thread_flag(TIF_SINGLESTEP)) ptrace_notify(SIGTRAP); diff --git a/arch/x86/kernel/asm-offsets_32.c b/arch/x86/kernel/asm-offsets_32.c index a33d530..8ea0401 100644 --- a/arch/x86/kernel/asm-offsets_32.c +++ b/arch/x86/kernel/asm-offsets_32.c @@ -128,13 +128,11 @@ void foo(void) OFFSET(XEN_vcpu_info_pending, vcpu_info, evtchn_upcall_pending); #endif -#ifdef CONFIG_LGUEST_GUEST +#if defined(CONFIG_LGUEST) || defined(CONFIG_LGUEST_GUEST) || defined(CONFIG_LGUEST_MODULE) BLANK(); OFFSET(LGUEST_DATA_irq_enabled, lguest_data, irq_enabled); OFFSET(LGUEST_DATA_pgdir, lguest_data, pgdir); -#endif -#ifdef CONFIG_LGUEST BLANK(); OFFSET(LGUEST_PAGES_host_gdt_desc, lguest_pages, state.host_gdt_desc); OFFSET(LGUEST_PAGES_host_idt_desc, lguest_pages, state.host_idt_desc); diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c index f86a3c4..a38aafae 100644 --- a/arch/x86/kernel/cpu/common.c +++ b/arch/x86/kernel/cpu/common.c @@ -504,7 +504,7 @@ void __cpuinit identify_cpu(struct cpuinfo_x86 *c) /* Clear all flags overriden by options */ for (i = 0; i < NCAPINTS; i++) - c->x86_capability[i] ^= cleared_cpu_caps[i]; + c->x86_capability[i] &= ~cleared_cpu_caps[i]; /* Init Machine Check Exception if available. */ mcheck_init(c); diff --git a/arch/x86/kernel/cpu/cpufreq/e_powersaver.c b/arch/x86/kernel/cpu/cpufreq/e_powersaver.c index 39f8cb1..c2f930d 100644 --- a/arch/x86/kernel/cpu/cpufreq/e_powersaver.c +++ b/arch/x86/kernel/cpu/cpufreq/e_powersaver.c @@ -55,7 +55,6 @@ static int eps_set_state(struct eps_cpu_data *centaur, { struct cpufreq_freqs freqs; u32 lo, hi; - u8 current_multiplier, current_voltage; int err = 0; int i; @@ -95,6 +94,10 @@ postchange: rdmsr(MSR_IA32_PERF_STATUS, lo, hi); freqs.new = centaur->fsb * ((lo >> 8) & 0xff); +#ifdef DEBUG + { + u8 current_multiplier, current_voltage; + /* Print voltage and multiplier */ rdmsr(MSR_IA32_PERF_STATUS, lo, hi); current_voltage = lo & 0xff; @@ -103,7 +106,8 @@ postchange: current_multiplier = (lo >> 8) & 0xff; printk(KERN_INFO "eps: Current multiplier = %d\n", current_multiplier); - + } +#endif cpufreq_notify_transition(&freqs, CPUFREQ_POSTCHANGE); return err; } diff --git a/arch/x86/kernel/cpu/mtrr/main.c b/arch/x86/kernel/cpu/mtrr/main.c index b6e136f..be83336 100644 --- a/arch/x86/kernel/cpu/mtrr/main.c +++ b/arch/x86/kernel/cpu/mtrr/main.c @@ -43,6 +43,7 @@ #include <asm/uaccess.h> #include <asm/processor.h> #include <asm/msr.h> +#include <asm/kvm_para.h> #include "mtrr.h" u32 num_var_ranges = 0; @@ -649,6 +650,7 @@ static __init int amd_special_default_mtrr(void) /** * mtrr_trim_uncached_memory - trim RAM not covered by MTRRs + * @end_pfn: ending page frame number * * Some buggy BIOSes don't setup the MTRRs properly for systems with certain * memory configurations. This routine checks that the highest MTRR matches @@ -688,8 +690,11 @@ int __init mtrr_trim_uncached_memory(unsigned long end_pfn) /* kvm/qemu doesn't have mtrr set right, don't trim them all */ if (!highest_pfn) { - printk(KERN_WARNING "WARNING: strange, CPU MTRRs all blank?\n"); - WARN_ON(1); + if (!kvm_para_available()) { + printk(KERN_WARNING + "WARNING: strange, CPU MTRRs all blank?\n"); + WARN_ON(1); + } return 0; } diff --git a/arch/x86/kernel/cpu/transmeta.c b/arch/x86/kernel/cpu/transmeta.c index 200fb3f..e8b422c 100644 --- a/arch/x86/kernel/cpu/transmeta.c +++ b/arch/x86/kernel/cpu/transmeta.c @@ -76,13 +76,6 @@ static void __cpuinit init_transmeta(struct cpuinfo_x86 *c) /* All Transmeta CPUs have a constant TSC */ set_bit(X86_FEATURE_CONSTANT_TSC, c->x86_capability); - /* If we can run i686 user-space code, call us an i686 */ -#define USER686 ((1 << X86_FEATURE_TSC)|\ - (1 << X86_FEATURE_CX8)|\ - (1 << X86_FEATURE_CMOV)) - if (c->x86 == 5 && (c->x86_capability[0] & USER686) == USER686) - c->x86 = 6; - #ifdef CONFIG_SYSCTL /* randomize_va_space slows us down enormously; it probably triggers retranslation of x86->native bytecode */ diff --git a/arch/x86/kernel/entry_64.S b/arch/x86/kernel/entry_64.S index 2ad9a1b..c20c9e7 100644 --- a/arch/x86/kernel/entry_64.S +++ b/arch/x86/kernel/entry_64.S @@ -453,6 +453,7 @@ ENTRY(stub_execve) CFI_REGISTER rip, r11 SAVE_REST FIXUP_TOP_OF_STACK %r11 + movq %rsp, %rcx call sys_execve RESTORE_TOP_OF_STACK %r11 movq %rax,RAX(%rsp) @@ -1036,15 +1037,16 @@ ENDPROC(child_rip) * rdi: name, rsi: argv, rdx: envp * * We want to fallback into: - * extern long sys_execve(char *name, char **argv,char **envp, struct pt_regs regs) + * extern long sys_execve(char *name, char **argv,char **envp, struct pt_regs *regs) * * do_sys_execve asm fallback arguments: - * rdi: name, rsi: argv, rdx: envp, fake frame on the stack + * rdi: name, rsi: argv, rdx: envp, rcx: fake frame on the stack */ ENTRY(kernel_execve) CFI_STARTPROC FAKE_STACK_FRAME $0 SAVE_ALL + movq %rsp,%rcx call sys_execve movq %rax, RAX(%rsp) RESTORE_REST diff --git a/arch/x86/kernel/head_32.S b/arch/x86/kernel/head_32.S index 25eb985..fd8ca53 100644 --- a/arch/x86/kernel/head_32.S +++ b/arch/x86/kernel/head_32.S @@ -606,7 +606,7 @@ ENTRY(_stext) .section ".bss.page_aligned","wa" .align PAGE_SIZE_asm #ifdef CONFIG_X86_PAE -ENTRY(swapper_pg_pmd) +swapper_pg_pmd: .fill 1024*KPMDS,4,0 #else ENTRY(swapper_pg_dir) diff --git a/arch/x86/kernel/head_64.S b/arch/x86/kernel/head_64.S index eb41504..a007454 100644 --- a/arch/x86/kernel/head_64.S +++ b/arch/x86/kernel/head_64.S @@ -379,18 +379,24 @@ NEXT_PAGE(level2_ident_pgt) /* Since I easily can, map the first 1G. * Don't set NX because code runs from these pages. */ - PMDS(0x0000000000000000, __PAGE_KERNEL_LARGE_EXEC, PTRS_PER_PMD) + PMDS(0, __PAGE_KERNEL_LARGE_EXEC, PTRS_PER_PMD) NEXT_PAGE(level2_kernel_pgt) - /* 40MB kernel mapping. The kernel code cannot be bigger than that. - When you change this change KERNEL_TEXT_SIZE in page.h too. */ - /* (2^48-(2*1024*1024*1024)-((2^39)*511)-((2^30)*510)) = 0 */ - PMDS(0x0000000000000000, __PAGE_KERNEL_LARGE_EXEC|_PAGE_GLOBAL, KERNEL_TEXT_SIZE/PMD_SIZE) - /* Module mapping starts here */ - .fill (PTRS_PER_PMD - (KERNEL_TEXT_SIZE/PMD_SIZE)),8,0 + /* + * 128 MB kernel mapping. We spend a full page on this pagetable + * anyway. + * + * The kernel code+data+bss must not be bigger than that. + * + * (NOTE: at +128MB starts the module area, see MODULES_VADDR. + * If you want to increase this then increase MODULES_VADDR + * too.) + */ + PMDS(0, __PAGE_KERNEL_LARGE_EXEC|_PAGE_GLOBAL, + KERNEL_IMAGE_SIZE/PMD_SIZE) NEXT_PAGE(level2_spare_pgt) - .fill 512,8,0 + .fill 512, 8, 0 #undef PMDS #undef NEXT_PAGE diff --git a/arch/x86/kernel/hpet.c b/arch/x86/kernel/hpet.c index 429d084..235fd6c 100644 --- a/arch/x86/kernel/hpet.c +++ b/arch/x86/kernel/hpet.c @@ -368,8 +368,8 @@ static int hpet_clocksource_register(void) return 0; } -/* - * Try to setup the HPET timer +/** + * hpet_enable - Try to setup the HPET timer. Returns 1 on success. */ int __init hpet_enable(void) { diff --git a/arch/x86/kernel/i387.c b/arch/x86/kernel/i387.c index 763dfc4..d2e39e6 100644 --- a/arch/x86/kernel/i387.c +++ b/arch/x86/kernel/i387.c @@ -132,7 +132,7 @@ int xfpregs_get(struct task_struct *target, const struct user_regset *regset, if (!cpu_has_fxsr) return -ENODEV; - unlazy_fpu(target); + init_fpu(target); return user_regset_copyout(&pos, &count, &kbuf, &ubuf, &target->thread.i387.fxsave, 0, -1); @@ -147,7 +147,7 @@ int xfpregs_set(struct task_struct *target, const struct user_regset *regset, if (!cpu_has_fxsr) return -ENODEV; - unlazy_fpu(target); + init_fpu(target); set_stopped_child_used_math(target); ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf, @@ -261,7 +261,7 @@ static void convert_from_fxsr(struct user_i387_ia32_struct *env, } #else env->fip = fxsave->fip; - env->fcs = fxsave->fcs; + env->fcs = (u16) fxsave->fcs | ((u32) fxsave->fop << 16); env->foo = fxsave->foo; env->fos = fxsave->fos; #endif @@ -307,7 +307,7 @@ int fpregs_get(struct task_struct *target, const struct user_regset *regset, if (!HAVE_HWFP) return fpregs_soft_get(target, regset, pos, count, kbuf, ubuf); - unlazy_fpu(target); + init_fpu(target); if (!cpu_has_fxsr) return user_regset_copyout(&pos, &count, &kbuf, &ubuf, @@ -332,7 +332,7 @@ int fpregs_set(struct task_struct *target, const struct user_regset *regset, if (!HAVE_HWFP) return fpregs_soft_set(target, regset, pos, count, kbuf, ubuf); - unlazy_fpu(target); + init_fpu(target); set_stopped_child_used_math(target); if (!cpu_has_fxsr) diff --git a/arch/x86/kernel/init_task.c b/arch/x86/kernel/init_task.c index 5b3ce79..3d01e47 100644 --- a/arch/x86/kernel/init_task.c +++ b/arch/x86/kernel/init_task.c @@ -15,6 +15,7 @@ static struct files_struct init_files = INIT_FILES; static struct signal_struct init_signals = INIT_SIGNALS(init_signals); static struct sighand_struct init_sighand = INIT_SIGHAND(init_sighand); struct mm_struct init_mm = INIT_MM(init_mm); +EXPORT_UNUSED_SYMBOL(init_mm); /* will be removed in 2.6.26 */ /* * Initial thread structure. diff --git a/arch/x86/kernel/process_32.c b/arch/x86/kernel/process_32.c index a7d50a5..be3c7a2 100644 --- a/arch/x86/kernel/process_32.c +++ b/arch/x86/kernel/process_32.c @@ -603,11 +603,13 @@ __switch_to_xtra(struct task_struct *prev_p, struct task_struct *next_p, } #endif +#ifdef X86_BTS if (test_tsk_thread_flag(prev_p, TIF_BTS_TRACE_TS)) ptrace_bts_take_timestamp(prev_p, BTS_TASK_DEPARTS); if (test_tsk_thread_flag(next_p, TIF_BTS_TRACE_TS)) ptrace_bts_take_timestamp(next_p, BTS_TASK_ARRIVES); +#endif if (!test_tsk_thread_flag(next_p, TIF_IO_BITMAP)) { diff --git a/arch/x86/kernel/process_64.c b/arch/x86/kernel/process_64.c index b0cc8f0..3baf9b9 100644 --- a/arch/x86/kernel/process_64.c +++ b/arch/x86/kernel/process_64.c @@ -604,11 +604,13 @@ static inline void __switch_to_xtra(struct task_struct *prev_p, memset(tss->io_bitmap, 0xff, prev->io_bitmap_max); } +#ifdef X86_BTS if (test_tsk_thread_flag(prev_p, TIF_BTS_TRACE_TS)) ptrace_bts_take_timestamp(prev_p, BTS_TASK_DEPARTS); if (test_tsk_thread_flag(next_p, TIF_BTS_TRACE_TS)) ptrace_bts_take_timestamp(next_p, BTS_TASK_ARRIVES); +#endif } /* @@ -730,16 +732,16 @@ __switch_to(struct task_struct *prev_p, struct task_struct *next_p) */ asmlinkage long sys_execve(char __user *name, char __user * __user *argv, - char __user * __user *envp, struct pt_regs regs) + char __user * __user *envp, struct pt_regs *regs) { long error; char * filename; filename = getname(name); error = PTR_ERR(filename); - if (IS_ERR(filename)) + if (IS_ERR(filename)) return error; - error = do_execve(filename, argv, envp, ®s); + error = do_execve(filename, argv, envp, regs); putname(filename); return error; } diff --git a/arch/x86/kernel/ptrace.c b/arch/x86/kernel/ptrace.c index d862e39..d5904ee 100644 --- a/arch/x86/kernel/ptrace.c +++ b/arch/x86/kernel/ptrace.c @@ -323,6 +323,16 @@ static int putreg(struct task_struct *child, return set_flags(child, value); #ifdef CONFIG_X86_64 + /* + * Orig_ax is really just a flag with small positive and + * negative values, so make sure to always sign-extend it + * from 32 bits so that it works correctly regardless of + * whether we come from a 32-bit environment or not. + */ + case offsetof(struct user_regs_struct, orig_ax): + value = (long) (s32) value; + break; + case offsetof(struct user_regs_struct,fs_base): if (value >= TASK_SIZE_OF(child)) return -EIO; @@ -544,6 +554,8 @@ static int ptrace_set_debugreg(struct task_struct *child, return 0; } +#ifdef X86_BTS + static int ptrace_bts_get_size(struct task_struct *child) { if (!child->thread.ds_area_msr) @@ -826,6 +838,7 @@ void ptrace_bts_take_timestamp(struct task_struct *tsk, ptrace_bts_write_record(tsk, &rec); } +#endif /* X86_BTS */ /* * Called by kernel/ptrace.c when detaching.. @@ -839,7 +852,9 @@ void ptrace_disable(struct task_struct *child) clear_tsk_thread_flag(child, TIF_SYSCALL_EMU); #endif if (child->thread.ds_area_msr) { +#ifdef X86_BTS ptrace_bts_realloc(child, 0, 0); +#endif child->thread.debugctlmsr &= ~ds_debugctl_mask(); if (!child->thread.debugctlmsr) clear_tsk_thread_flag(child, TIF_DEBUGCTLMSR); @@ -961,6 +976,10 @@ long arch_ptrace(struct task_struct *child, long request, long addr, long data) break; #endif + /* + * These bits need more cooking - not enabled yet: + */ +#ifdef X86_BTS case PTRACE_BTS_CONFIG: ret = ptrace_bts_config (child, data, (struct ptrace_bts_config __user *)addr); @@ -988,6 +1007,7 @@ long arch_ptrace(struct task_struct *child, long request, long addr, long data) ret = ptrace_bts_drain (child, data, (struct bts_struct __user *) addr); break; +#endif default: ret = ptrace_request(child, request, addr, data); @@ -1035,10 +1055,17 @@ static int putreg32(struct task_struct *child, unsigned regno, u32 value) R32(esi, si); R32(ebp, bp); R32(eax, ax); - R32(orig_eax, orig_ax); R32(eip, ip); R32(esp, sp); + case offsetof(struct user32, regs.orig_eax): + /* + * Sign-extend the value so that orig_eax = -1 + * causes (long)orig_ax < 0 tests to fire correctly. + */ + regs->orig_ax = (long) (s32) value; + break; + case offsetof(struct user32, regs.eflags): return set_flags(child, value); @@ -1226,12 +1253,14 @@ asmlinkage long sys32_ptrace(long request, u32 pid, u32 addr, u32 data) case PTRACE_SETOPTIONS: case PTRACE_SET_THREAD_AREA: case PTRACE_GET_THREAD_AREA: +#ifdef X86_BTS case PTRACE_BTS_CONFIG: case PTRACE_BTS_STATUS: case PTRACE_BTS_SIZE: case PTRACE_BTS_GET: case PTRACE_BTS_CLEAR: case PTRACE_BTS_DRAIN: +#endif return sys_ptrace(request, pid, addr, data); default: diff --git a/arch/x86/kernel/reboot.c b/arch/x86/kernel/reboot.c index 7fd6ac4..55ceb8c 100644 --- a/arch/x86/kernel/reboot.c +++ b/arch/x86/kernel/reboot.c @@ -326,6 +326,10 @@ static inline void kb_wait(void) } } +void __attribute__((weak)) mach_reboot_fixups(void) +{ +} + static void native_machine_emergency_restart(void) { int i; @@ -337,6 +341,8 @@ static void native_machine_emergency_restart(void) /* Could also try the reset bit in the Hammer NB */ switch (reboot_type) { case BOOT_KBD: + mach_reboot_fixups(); /* for board specific fixups */ + for (i = 0; i < 10; i++) { kb_wait(); udelay(50); diff --git a/arch/x86/kernel/setup_64.c b/arch/x86/kernel/setup_64.c index 6fd804f..7637dc9 100644 --- a/arch/x86/kernel/setup_64.c +++ b/arch/x86/kernel/setup_64.c @@ -1021,7 +1021,7 @@ void __cpuinit identify_cpu(struct cpuinfo_x86 *c) /* Clear all flags overriden by options */ for (i = 0; i < NCAPINTS; i++) - c->x86_capability[i] ^= cleared_cpu_caps[i]; + c->x86_capability[i] &= ~cleared_cpu_caps[i]; #ifdef CONFIG_X86_MCE mcheck_init(c); diff --git a/arch/x86/kernel/signal_32.c b/arch/x86/kernel/signal_32.c index caee1f0..0157a6f 100644 --- a/arch/x86/kernel/signal_32.c +++ b/arch/x86/kernel/signal_32.c @@ -407,7 +407,7 @@ static int setup_frame(int sig, struct k_sigaction *ka, * The tracer may want to single-step inside the * handler too. */ - regs->flags &= ~TF_MASK; + regs->flags &= ~(TF_MASK | X86_EFLAGS_DF); if (test_thread_flag(TIF_SINGLESTEP)) ptrace_notify(SIGTRAP); @@ -500,7 +500,7 @@ static int setup_rt_frame(int sig, struct k_sigaction *ka, siginfo_t *info, * The tracer may want to single-step inside the * handler too. */ - regs->flags &= ~TF_MASK; + regs->flags &= ~(TF_MASK | X86_EFLAGS_DF); if (test_thread_flag(TIF_SINGLESTEP)) ptrace_notify(SIGTRAP); diff --git a/arch/x86/kernel/signal_64.c b/arch/x86/kernel/signal_64.c index 7347bb1..1c83e51 100644 --- a/arch/x86/kernel/signal_64.c +++ b/arch/x86/kernel/signal_64.c @@ -295,7 +295,7 @@ static int setup_rt_frame(int sig, struct k_sigaction *ka, siginfo_t *info, see include/asm-x86_64/uaccess.h for details. */ set_fs(USER_DS); - regs->flags &= ~X86_EFLAGS_TF; + regs->flags &= ~(X86_EFLAGS_TF | X86_EFLAGS_DF); if (test_thread_flag(TIF_SINGLESTEP)) ptrace_notify(SIGTRAP); #ifdef DEBUG_SIG @@ -311,6 +311,35 @@ give_sigsegv: } /* + * Return -1L or the syscall number that @regs is executing. + */ +static long current_syscall(struct pt_regs *regs) +{ + /* + * We always sign-extend a -1 value being set here, + * so this is always either -1L or a syscall number. + */ + return regs->orig_ax; +} + +/* + * Return a value that is -EFOO if the system call in @regs->orig_ax + * returned an error. This only works for @regs from @current. + */ +static long current_syscall_ret(struct pt_regs *regs) +{ +#ifdef CONFIG_IA32_EMULATION + if (test_thread_flag(TIF_IA32)) + /* + * Sign-extend the value so (int)-EFOO becomes (long)-EFOO + * and will match correctly in comparisons. + */ + return (int) regs->ax; +#endif + return regs->ax; +} + +/* * OK, we're invoking a handler */ @@ -327,9 +356,9 @@ handle_signal(unsigned long sig, siginfo_t *info, struct k_sigaction *ka, #endif /* Are we from a system call? */ - if ((long)regs->orig_ax >= 0) { + if (current_syscall(regs) >= 0) { /* If so, check system call restarting.. */ - switch (regs->ax) { + switch (current_syscall_ret(regs)) { case -ERESTART_RESTARTBLOCK: case -ERESTARTNOHAND: regs->ax = -EINTR; @@ -426,10 +455,9 @@ static void do_signal(struct pt_regs *regs) } /* Did we come from a system call? */ - if ((long)regs->orig_ax >= 0) { + if (current_syscall(regs) >= 0) { /* Restart the system call - no handlers present */ - long res = regs->ax; - switch (res) { + switch (current_syscall_ret(regs)) { case -ERESTARTNOHAND: case -ERESTARTSYS: case -ERESTARTNOINTR: diff --git a/arch/x86/kernel/smpboot_64.c b/arch/x86/kernel/smpboot_64.c index d53bd6f..0880f2c 100644 --- a/arch/x86/kernel/smpboot_64.c +++ b/arch/x86/kernel/smpboot_64.c @@ -554,10 +554,10 @@ static int __cpuinit do_boot_cpu(int cpu, int apicid) int timeout; unsigned long start_rip; struct create_idle c_idle = { - .work = __WORK_INITIALIZER(c_idle.work, do_fork_idle), .cpu = cpu, .done = COMPLETION_INITIALIZER_ONSTACK(c_idle.done), }; + INIT_WORK(&c_idle.work, do_fork_idle); /* allocate memory for gdts of secondary cpus. Hotplug is considered */ if (!cpu_gdt_descr[cpu].address && diff --git a/arch/x86/kernel/stacktrace.c b/arch/x86/kernel/stacktrace.c index 02f0f61..c28c342 100644 --- a/arch/x86/kernel/stacktrace.c +++ b/arch/x86/kernel/stacktrace.c @@ -25,6 +25,8 @@ static int save_stack_stack(void *data, char *name) static void save_stack_address(void *data, unsigned long addr, int reliable) { struct stack_trace *trace = data; + if (!reliable) + return; if (trace->skip > 0) { trace->skip--; return; @@ -37,6 +39,8 @@ static void save_stack_address_nosched(void *data, unsigned long addr, int reliable) { struct stack_trace *trace = (struct stack_trace *)data; + if (!reliable) + return; if (in_sched_functions(addr)) return; if (trace->skip > 0) { diff --git a/arch/x86/kernel/step.c b/arch/x86/kernel/step.c index 2ef1a5f..9d406cd 100644 --- a/arch/x86/kernel/step.c +++ b/arch/x86/kernel/step.c @@ -166,7 +166,7 @@ static void enable_step(struct task_struct *child, bool block) child->thread.debugctlmsr | DEBUGCTLMSR_BTF); } else { write_debugctlmsr(child, - child->thread.debugctlmsr & ~TIF_DEBUGCTLMSR); + child->thread.debugctlmsr & ~DEBUGCTLMSR_BTF); if (!child->thread.debugctlmsr) clear_tsk_thread_flag(child, TIF_DEBUGCTLMSR); @@ -189,7 +189,7 @@ void user_disable_single_step(struct task_struct *child) * Make sure block stepping (BTF) is disabled. */ write_debugctlmsr(child, - child->thread.debugctlmsr & ~TIF_DEBUGCTLMSR); + child->thread.debugctlmsr & ~DEBUGCTLMSR_BTF); if (!child->thread.debugctlmsr) clear_tsk_thread_flag(child, TIF_DEBUGCTLMSR); diff --git a/arch/x86/kernel/tls.c b/arch/x86/kernel/tls.c index 6dfd4e7..022bcaa 100644 --- a/arch/x86/kernel/tls.c +++ b/arch/x86/kernel/tls.c @@ -91,7 +91,9 @@ int do_set_thread_area(struct task_struct *p, int idx, asmlinkage int sys_set_thread_area(struct user_desc __user *u_info) { - return do_set_thread_area(current, -1, u_info, 1); + int ret = do_set_thread_area(current, -1, u_info, 1); + prevent_tail_call(ret); + return ret; } @@ -139,7 +141,9 @@ int do_get_thread_area(struct task_struct *p, int idx, asmlinkage int sys_get_thread_area(struct user_desc __user *u_info) { - return do_get_thread_area(current, -1, u_info); + int ret = do_get_thread_area(current, -1, u_info); + prevent_tail_call(ret); + return ret; } int regset_tls_active(struct task_struct *target, diff --git a/arch/x86/kernel/tsc_32.c b/arch/x86/kernel/tsc_32.c index 43517e3..f14cfd9 100644 --- a/arch/x86/kernel/tsc_32.c +++ b/arch/x86/kernel/tsc_32.c @@ -28,7 +28,8 @@ EXPORT_SYMBOL_GPL(tsc_khz); static int __init tsc_setup(char *str) { printk(KERN_WARNING "notsc: Kernel compiled with CONFIG_X86_TSC, " - "cannot disable TSC.\n"); + "cannot disable TSC completely.\n"); + mark_tsc_unstable("user disabled TSC"); return 1; } #else diff --git a/arch/x86/kernel/vsyscall_64.c b/arch/x86/kernel/vsyscall_64.c index 3f82427..edff4c9 100644 --- a/arch/x86/kernel/vsyscall_64.c +++ b/arch/x86/kernel/vsyscall_64.c @@ -44,11 +44,6 @@ #define __vsyscall(nr) __attribute__ ((unused,__section__(".vsyscall_" #nr))) #define __syscall_clobber "r11","cx","memory" -#define __pa_vsymbol(x) \ - ({unsigned long v; \ - extern char __vsyscall_0; \ - asm("" : "=r" (v) : "0" (x)); \ - ((v - VSYSCALL_START) + __pa_symbol(&__vsyscall_0)); }) /* * vsyscall_gtod_data contains data that is : @@ -102,7 +97,7 @@ static __always_inline void do_get_tz(struct timezone * tz) static __always_inline int gettimeofday(struct timeval *tv, struct timezone *tz) { int ret; - asm volatile("vsysc2: syscall" + asm volatile("syscall" : "=a" (ret) : "0" (__NR_gettimeofday),"D" (tv),"S" (tz) : __syscall_clobber ); @@ -112,7 +107,7 @@ static __always_inline int gettimeofday(struct timeval *tv, struct timezone *tz) static __always_inline long time_syscall(long *t) { long secs; - asm volatile("vsysc1: syscall" + asm volatile("syscall" : "=a" (secs) : "0" (__NR_time),"D" (t) : __syscall_clobber); return secs; @@ -228,42 +223,11 @@ long __vsyscall(3) venosys_1(void) #ifdef CONFIG_SYSCTL -#define SYSCALL 0x050f -#define NOP2 0x9090 - -/* - * NOP out syscall in vsyscall page when not needed. - */ -static int vsyscall_sysctl_change(ctl_table *ctl, int write, struct file * filp, - void __user *buffer, size_t *lenp, loff_t *ppos) +static int +vsyscall_sysctl_change(ctl_table *ctl, int write, struct file * filp, + void __user *buffer, size_t *lenp, loff_t *ppos) { - extern u16 vsysc1, vsysc2; - u16 __iomem *map1; - u16 __iomem *map2; - int ret = proc_dointvec(ctl, write, filp, buffer, lenp, ppos); - if (!write) - return ret; - /* gcc has some trouble with __va(__pa()), so just do it this - way. */ - map1 = ioremap(__pa_vsymbol(&vsysc1), 2); - if (!map1) - return -ENOMEM; - map2 = ioremap(__pa_vsymbol(&vsysc2), 2); - if (!map2) { - ret = -ENOMEM; - goto out; - } - if (!vsyscall_gtod_data.sysctl_enabled) { - writew(SYSCALL, map1); - writew(SYSCALL, map2); - } else { - writew(NOP2, map1); - writew(NOP2, map2); - } - iounmap(map2); -out: - iounmap(map1); - return ret; + return proc_dointvec(ctl, write, filp, buffer, lenp, ppos); } static ctl_table kernel_table2[] = { @@ -279,7 +243,6 @@ static ctl_table kernel_root_table2[] = { .child = kernel_table2 }, {} }; - #endif /* Assume __initcall executes before all user space. Hopefully kmod diff --git a/arch/x86/kvm/lapic.c b/arch/x86/kvm/lapic.c index 2cbee94..68a6b15 100644 --- a/arch/x86/kvm/lapic.c +++ b/arch/x86/kvm/lapic.c @@ -647,6 +647,10 @@ static void start_apic_timer(struct kvm_lapic *apic) apic->timer.period = apic_get_reg(apic, APIC_TMICT) * APIC_BUS_CYCLE_NS * apic->timer.divide_count; atomic_set(&apic->timer.pending, 0); + + if (!apic->timer.period) + return; + hrtimer_start(&apic->timer.dev, ktime_add_ns(now, apic->timer.period), HRTIMER_MODE_ABS); diff --git a/arch/x86/kvm/mmu.c b/arch/x86/kvm/mmu.c index 8efdcdb..d8172aa 100644 --- a/arch/x86/kvm/mmu.c +++ b/arch/x86/kvm/mmu.c @@ -681,8 +681,7 @@ static struct kvm_mmu_page *kvm_mmu_get_page(struct kvm_vcpu *vcpu, unsigned level, int metaphysical, unsigned access, - u64 *parent_pte, - bool *new_page) + u64 *parent_pte) { union kvm_mmu_page_role role; unsigned index; @@ -722,8 +721,6 @@ static struct kvm_mmu_page *kvm_mmu_get_page(struct kvm_vcpu *vcpu, vcpu->arch.mmu.prefetch_page(vcpu, sp); if (!metaphysical) rmap_write_protect(vcpu->kvm, gfn); - if (new_page) - *new_page = 1; return sp; } @@ -876,11 +873,18 @@ static void page_header_update_slot(struct kvm *kvm, void *pte, gfn_t gfn) struct page *gva_to_page(struct kvm_vcpu *vcpu, gva_t gva) { + struct page *page; + gpa_t gpa = vcpu->arch.mmu.gva_to_gpa(vcpu, gva); if (gpa == UNMAPPED_GVA) return NULL; - return gfn_to_page(vcpu->kvm, gpa >> PAGE_SHIFT); + + down_read(¤t->mm->mmap_sem); + page = gfn_to_page(vcpu->kvm, gpa >> PAGE_SHIFT); + up_read(¤t->mm->mmap_sem); + + return page; } static void mmu_set_spte(struct kvm_vcpu *vcpu, u64 *shadow_pte, @@ -999,8 +1003,7 @@ static int __nonpaging_map(struct kvm_vcpu *vcpu, gva_t v, int write, >> PAGE_SHIFT; new_table = kvm_mmu_get_page(vcpu, pseudo_gfn, v, level - 1, - 1, ACC_ALL, &table[index], - NULL); + 1, ACC_ALL, &table[index]); if (!new_table) { pgprintk("nonpaging_map: ENOMEM\n"); kvm_release_page_clean(page); @@ -1020,15 +1023,18 @@ static int nonpaging_map(struct kvm_vcpu *vcpu, gva_t v, int write, gfn_t gfn) struct page *page; + down_read(&vcpu->kvm->slots_lock); + down_read(¤t->mm->mmap_sem); page = gfn_to_page(vcpu->kvm, gfn); + up_read(¤t->mm->mmap_sem); spin_lock(&vcpu->kvm->mmu_lock); kvm_mmu_free_some_pages(vcpu); r = __nonpaging_map(vcpu, v, write, gfn, page); spin_unlock(&vcpu->kvm->mmu_lock); - up_read(¤t->mm->mmap_sem); + up_read(&vcpu->kvm->slots_lock); return r; } @@ -1090,7 +1096,7 @@ static void mmu_alloc_roots(struct kvm_vcpu *vcpu) ASSERT(!VALID_PAGE(root)); sp = kvm_mmu_get_page(vcpu, root_gfn, 0, - PT64_ROOT_LEVEL, 0, ACC_ALL, NULL, NULL); + PT64_ROOT_LEVEL, 0, ACC_ALL, NULL); root = __pa(sp->spt); ++sp->root_count; vcpu->arch.mmu.root_hpa = root; @@ -1111,7 +1117,7 @@ static void mmu_alloc_roots(struct kvm_vcpu *vcpu) root_gfn = 0; sp = kvm_mmu_get_page(vcpu, root_gfn, i << 30, PT32_ROOT_LEVEL, !is_paging(vcpu), - ACC_ALL, NULL, NULL); + ACC_ALL, NULL); root = __pa(sp->spt); ++sp->root_count; vcpu->arch.mmu.pae_root[i] = root | PT_PRESENT_MASK; @@ -1172,7 +1178,7 @@ void kvm_mmu_flush_tlb(struct kvm_vcpu *vcpu) static void paging_new_cr3(struct kvm_vcpu *vcpu) { - pgprintk("%s: cr3 %lx\n", __FUNCTION__, vcpu->cr3); + pgprintk("%s: cr3 %lx\n", __FUNCTION__, vcpu->arch.cr3); mmu_free_roots(vcpu); } @@ -1362,6 +1368,7 @@ static void mmu_guess_page_from_pte_write(struct kvm_vcpu *vcpu, gpa_t gpa, gfn_t gfn; int r; u64 gpte = 0; + struct page *page; if (bytes != 4 && bytes != 8) return; @@ -1389,6 +1396,11 @@ static void mmu_guess_page_from_pte_write(struct kvm_vcpu *vcpu, gpa_t gpa, if (!is_present_pte(gpte)) return; gfn = (gpte & PT64_BASE_ADDR_MASK) >> PAGE_SHIFT; + + down_read(¤t->mm->mmap_sem); + page = gfn_to_page(vcpu->kvm, gfn); + up_read(¤t->mm->mmap_sem); + vcpu->arch.update_pte.gfn = gfn; vcpu->arch.update_pte.page = gfn_to_page(vcpu->kvm, gfn); } @@ -1496,9 +1508,9 @@ int kvm_mmu_unprotect_page_virt(struct kvm_vcpu *vcpu, gva_t gva) gpa_t gpa; int r; - down_read(¤t->mm->mmap_sem); + down_read(&vcpu->kvm->slots_lock); gpa = vcpu->arch.mmu.gva_to_gpa(vcpu, gva); - up_read(¤t->mm->mmap_sem); + up_read(&vcpu->kvm->slots_lock); spin_lock(&vcpu->kvm->mmu_lock); r = kvm_mmu_unprotect_page(vcpu->kvm, gpa >> PAGE_SHIFT); diff --git a/arch/x86/kvm/paging_tmpl.h b/arch/x86/kvm/paging_tmpl.h index 03ba860..ecc0856 100644 --- a/arch/x86/kvm/paging_tmpl.h +++ b/arch/x86/kvm/paging_tmpl.h @@ -91,7 +91,10 @@ static bool FNAME(cmpxchg_gpte)(struct kvm *kvm, pt_element_t *table; struct page *page; + down_read(¤t->mm->mmap_sem); page = gfn_to_page(kvm, table_gfn); + up_read(¤t->mm->mmap_sem); + table = kmap_atomic(page, KM_USER0); ret = CMPXCHG(&table[index], orig_pte, new_pte); @@ -140,7 +143,7 @@ walk: } #endif ASSERT((!is_long_mode(vcpu) && is_pae(vcpu)) || - (vcpu->cr3 & CR3_NONPAE_RESERVED_BITS) == 0); + (vcpu->arch.cr3 & CR3_NONPAE_RESERVED_BITS) == 0); pt_access = ACC_ALL; @@ -297,7 +300,6 @@ static u64 *FNAME(fetch)(struct kvm_vcpu *vcpu, gva_t addr, u64 shadow_pte; int metaphysical; gfn_t table_gfn; - bool new_page = 0; shadow_ent = ((u64 *)__va(shadow_addr)) + index; if (level == PT_PAGE_TABLE_LEVEL) @@ -319,8 +321,8 @@ static u64 *FNAME(fetch)(struct kvm_vcpu *vcpu, gva_t addr, } shadow_page = kvm_mmu_get_page(vcpu, table_gfn, addr, level-1, metaphysical, access, - shadow_ent, &new_page); - if (new_page && !metaphysical) { + shadow_ent); + if (!metaphysical) { int r; pt_element_t curr_pte; r = kvm_read_guest_atomic(vcpu->kvm, @@ -378,7 +380,7 @@ static int FNAME(page_fault)(struct kvm_vcpu *vcpu, gva_t addr, if (r) return r; - down_read(¤t->mm->mmap_sem); + down_read(&vcpu->kvm->slots_lock); /* * Look up the shadow pte for the faulting address. */ @@ -392,11 +394,13 @@ static int FNAME(page_fault)(struct kvm_vcpu *vcpu, gva_t addr, pgprintk("%s: guest page fault\n", __FUNCTION__); inject_page_fault(vcpu, addr, walker.error_code); vcpu->arch.last_pt_write_count = 0; /* reset fork detector */ - up_read(¤t->mm->mmap_sem); + up_read(&vcpu->kvm->slots_lock); return 0; } + down_read(¤t->mm->mmap_sem); page = gfn_to_page(vcpu->kvm, walker.gfn); + up_read(¤t->mm->mmap_sem); spin_lock(&vcpu->kvm->mmu_lock); kvm_mmu_free_some_pages(vcpu); @@ -413,14 +417,14 @@ static int FNAME(page_fault)(struct kvm_vcpu *vcpu, gva_t addr, */ if (shadow_pte && is_io_pte(*shadow_pte)) { spin_unlock(&vcpu->kvm->mmu_lock); - up_read(¤t->mm->mmap_sem); + up_read(&vcpu->kvm->slots_lock); return 1; } ++vcpu->stat.pf_fixed; kvm_mmu_audit(vcpu, "post page fault (fixed)"); spin_unlock(&vcpu->kvm->mmu_lock); - up_read(¤t->mm->mmap_sem); + up_read(&vcpu->kvm->slots_lock); return write_pt; } diff --git a/arch/x86/kvm/svm.c b/arch/x86/kvm/svm.c index de755cb..1a582f1 100644 --- a/arch/x86/kvm/svm.c +++ b/arch/x86/kvm/svm.c @@ -792,6 +792,10 @@ static void svm_set_cr0(struct kvm_vcpu *vcpu, unsigned long cr0) vcpu->arch.cr0 = cr0; cr0 |= X86_CR0_PG | X86_CR0_WP; cr0 &= ~(X86_CR0_CD | X86_CR0_NW); + if (!vcpu->fpu_active) { + svm->vmcb->control.intercept_exceptions |= (1 << NM_VECTOR); + cr0 |= X86_CR0_TS; + } svm->vmcb->save.cr0 = cr0; } @@ -1096,6 +1100,24 @@ static int svm_get_msr(struct kvm_vcpu *vcpu, unsigned ecx, u64 *data) case MSR_IA32_SYSENTER_ESP: *data = svm->vmcb->save.sysenter_esp; break; + /* Nobody will change the following 5 values in the VMCB so + we can safely return them on rdmsr. They will always be 0 + until LBRV is implemented. */ + case MSR_IA32_DEBUGCTLMSR: + *data = svm->vmcb->save.dbgctl; + break; + case MSR_IA32_LASTBRANCHFROMIP: + *data = svm->vmcb->save.br_from; + break; + case MSR_IA32_LASTBRANCHTOIP: + *data = svm->vmcb->save.br_to; + break; + case MSR_IA32_LASTINTFROMIP: + *data = svm->vmcb->save.last_excp_from; + break; + case MSR_IA32_LASTINTTOIP: + *data = svm->vmcb->save.last_excp_to; + break; default: return kvm_get_msr_common(vcpu, ecx, data); } @@ -1156,6 +1178,10 @@ static int svm_set_msr(struct kvm_vcpu *vcpu, unsigned ecx, u64 data) case MSR_IA32_SYSENTER_ESP: svm->vmcb->save.sysenter_esp = data; break; + case MSR_IA32_DEBUGCTLMSR: + pr_unimpl(vcpu, "%s: MSR_IA32_DEBUGCTLMSR 0x%llx, nop\n", + __FUNCTION__, data); + break; case MSR_K7_EVNTSEL0: case MSR_K7_EVNTSEL1: case MSR_K7_EVNTSEL2: diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c index ad36447..94ea724 100644 --- a/arch/x86/kvm/vmx.c +++ b/arch/x86/kvm/vmx.c @@ -638,6 +638,7 @@ static void setup_msrs(struct vcpu_vmx *vmx) { int save_nmsrs; + vmx_load_host_state(vmx); save_nmsrs = 0; #ifdef CONFIG_X86_64 if (is_long_mode(&vmx->vcpu)) { @@ -1477,7 +1478,7 @@ static int alloc_apic_access_page(struct kvm *kvm) struct kvm_userspace_memory_region kvm_userspace_mem; int r = 0; - down_write(¤t->mm->mmap_sem); + down_write(&kvm->slots_lock); if (kvm->arch.apic_access_page) goto out; kvm_userspace_mem.slot = APIC_ACCESS_PAGE_PRIVATE_MEMSLOT; @@ -1487,9 +1488,12 @@ static int alloc_apic_access_page(struct kvm *kvm) r = __kvm_set_memory_region(kvm, &kvm_userspace_mem, 0); if (r) goto out; + + down_read(¤t->mm->mmap_sem); kvm->arch.apic_access_page = gfn_to_page(kvm, 0xfee00); + up_read(¤t->mm->mmap_sem); out: - up_write(¤t->mm->mmap_sem); + up_write(&kvm->slots_lock); return r; } @@ -1602,9 +1606,6 @@ static int vmx_vcpu_setup(struct vcpu_vmx *vmx) vmcs_writel(CR0_GUEST_HOST_MASK, ~0UL); vmcs_writel(CR4_GUEST_HOST_MASK, KVM_GUEST_CR4_MASK); - if (vm_need_virtualize_apic_accesses(vmx->vcpu.kvm)) - if (alloc_apic_access_page(vmx->vcpu.kvm) != 0) - return -ENOMEM; return 0; } @@ -2534,6 +2535,9 @@ static struct kvm_vcpu *vmx_create_vcpu(struct kvm *kvm, unsigned int id) put_cpu(); if (err) goto free_vmcs; + if (vm_need_virtualize_apic_accesses(kvm)) + if (alloc_apic_access_page(kvm) != 0) + goto free_vmcs; return &vmx->vcpu; diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index cf53081..6b01552 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -46,6 +46,9 @@ #define VM_STAT(x) offsetof(struct kvm, stat.x), KVM_STAT_VM #define VCPU_STAT(x) offsetof(struct kvm_vcpu, stat.x), KVM_STAT_VCPU +static int kvm_dev_ioctl_get_supported_cpuid(struct kvm_cpuid2 *cpuid, + struct kvm_cpuid_entry2 __user *entries); + struct kvm_x86_ops *kvm_x86_ops; struct kvm_stats_debugfs_item debugfs_entries[] = { @@ -181,7 +184,7 @@ int load_pdptrs(struct kvm_vcpu *vcpu, unsigned long cr3) int ret; u64 pdpte[ARRAY_SIZE(vcpu->arch.pdptrs)]; - down_read(¤t->mm->mmap_sem); + down_read(&vcpu->kvm->slots_lock); ret = kvm_read_guest_page(vcpu->kvm, pdpt_gfn, pdpte, offset * sizeof(u64), sizeof(pdpte)); if (ret < 0) { @@ -198,7 +201,7 @@ int load_pdptrs(struct kvm_vcpu *vcpu, unsigned long cr3) memcpy(vcpu->arch.pdptrs, pdpte, sizeof(vcpu->arch.pdptrs)); out: - up_read(¤t->mm->mmap_sem); + up_read(&vcpu->kvm->slots_lock); return ret; } @@ -212,13 +215,13 @@ static bool pdptrs_changed(struct kvm_vcpu *vcpu) if (is_long_mode(vcpu) || !is_pae(vcpu)) return false; - down_read(¤t->mm->mmap_sem); + down_read(&vcpu->kvm->slots_lock); r = kvm_read_guest(vcpu->kvm, vcpu->arch.cr3 & ~31u, pdpte, sizeof(pdpte)); if (r < 0) goto out; changed = memcmp(pdpte, vcpu->arch.pdptrs, sizeof(pdpte)) != 0; out: - up_read(¤t->mm->mmap_sem); + up_read(&vcpu->kvm->slots_lock); return changed; } @@ -356,7 +359,7 @@ void set_cr3(struct kvm_vcpu *vcpu, unsigned long cr3) */ } - down_read(¤t->mm->mmap_sem); + down_read(&vcpu->kvm->slots_lock); /* * Does the new cr3 value map to physical memory? (Note, we * catch an invalid cr3 even in real-mode, because it would @@ -372,7 +375,7 @@ void set_cr3(struct kvm_vcpu *vcpu, unsigned long cr3) vcpu->arch.cr3 = cr3; vcpu->arch.mmu.new_cr3(vcpu); } - up_read(¤t->mm->mmap_sem); + up_read(&vcpu->kvm->slots_lock); } EXPORT_SYMBOL_GPL(set_cr3); @@ -484,6 +487,10 @@ int kvm_set_msr_common(struct kvm_vcpu *vcpu, u32 msr, u64 data) pr_unimpl(vcpu, "%s: MSR_IA32_MCG_STATUS 0x%llx, nop\n", __FUNCTION__, data); break; + case MSR_IA32_MCG_CTL: + pr_unimpl(vcpu, "%s: MSR_IA32_MCG_CTL 0x%llx, nop\n", + __FUNCTION__, data); + break; case MSR_IA32_UCODE_REV: case MSR_IA32_UCODE_WRITE: case 0x200 ... 0x2ff: /* MTRRs */ @@ -526,6 +533,7 @@ int kvm_get_msr_common(struct kvm_vcpu *vcpu, u32 msr, u64 *pdata) case MSR_IA32_MC0_CTL: case MSR_IA32_MCG_STATUS: case MSR_IA32_MCG_CAP: + case MSR_IA32_MCG_CTL: case MSR_IA32_MC0_MISC: case MSR_IA32_MC0_MISC+4: case MSR_IA32_MC0_MISC+8: @@ -727,6 +735,24 @@ long kvm_arch_dev_ioctl(struct file *filp, r = 0; break; } + case KVM_GET_SUPPORTED_CPUID: { + struct kvm_cpuid2 __user *cpuid_arg = argp; + struct kvm_cpuid2 cpuid; + + r = -EFAULT; + if (copy_from_user(&cpuid, cpuid_arg, sizeof cpuid)) + goto out; + r = kvm_dev_ioctl_get_supported_cpuid(&cpuid, + cpuid_arg->entries); + if (r) + goto out; + + r = -EFAULT; + if (copy_to_user(cpuid_arg, &cpuid, sizeof cpuid)) + goto out; + r = 0; + break; + } default: r = -EINVAL; } @@ -974,8 +1000,7 @@ static void do_cpuid_ent(struct kvm_cpuid_entry2 *entry, u32 function, put_cpu(); } -static int kvm_vm_ioctl_get_supported_cpuid(struct kvm *kvm, - struct kvm_cpuid2 *cpuid, +static int kvm_dev_ioctl_get_supported_cpuid(struct kvm_cpuid2 *cpuid, struct kvm_cpuid_entry2 __user *entries) { struct kvm_cpuid_entry2 *cpuid_entries; @@ -1207,12 +1232,12 @@ static int kvm_vm_ioctl_set_nr_mmu_pages(struct kvm *kvm, if (kvm_nr_mmu_pages < KVM_MIN_ALLOC_MMU_PAGES) return -EINVAL; - down_write(¤t->mm->mmap_sem); + down_write(&kvm->slots_lock); kvm_mmu_change_mmu_pages(kvm, kvm_nr_mmu_pages); kvm->arch.n_requested_mmu_pages = kvm_nr_mmu_pages; - up_write(¤t->mm->mmap_sem); + up_write(&kvm->slots_lock); return 0; } @@ -1261,7 +1286,7 @@ static int kvm_vm_ioctl_set_memory_alias(struct kvm *kvm, < alias->target_phys_addr) goto out; - down_write(¤t->mm->mmap_sem); + down_write(&kvm->slots_lock); p = &kvm->arch.aliases[alias->slot]; p->base_gfn = alias->guest_phys_addr >> PAGE_SHIFT; @@ -1275,7 +1300,7 @@ static int kvm_vm_ioctl_set_memory_alias(struct kvm *kvm, kvm_mmu_zap_all(kvm); - up_write(¤t->mm->mmap_sem); + up_write(&kvm->slots_lock); return 0; @@ -1351,7 +1376,7 @@ int kvm_vm_ioctl_get_dirty_log(struct kvm *kvm, struct kvm_memory_slot *memslot; int is_dirty = 0; - down_write(¤t->mm->mmap_sem); + down_write(&kvm->slots_lock); r = kvm_get_dirty_log(kvm, log, &is_dirty); if (r) @@ -1367,7 +1392,7 @@ int kvm_vm_ioctl_get_dirty_log(struct kvm *kvm, } r = 0; out: - up_write(¤t->mm->mmap_sem); + up_write(&kvm->slots_lock); return r; } @@ -1487,24 +1512,6 @@ long kvm_arch_vm_ioctl(struct file *filp, r = 0; break; } - case KVM_GET_SUPPORTED_CPUID: { - struct kvm_cpuid2 __user *cpuid_arg = argp; - struct kvm_cpuid2 cpuid; - - r = -EFAULT; - if (copy_from_user(&cpuid, cpuid_arg, sizeof cpuid)) - goto out; - r = kvm_vm_ioctl_get_supported_cpuid(kvm, &cpuid, - cpuid_arg->entries); - if (r) - goto out; - - r = -EFAULT; - if (copy_to_user(cpuid_arg, &cpuid, sizeof cpuid)) - goto out; - r = 0; - break; - } default: ; } @@ -1563,7 +1570,7 @@ int emulator_read_std(unsigned long addr, void *data = val; int r = X86EMUL_CONTINUE; - down_read(¤t->mm->mmap_sem); + down_read(&vcpu->kvm->slots_lock); while (bytes) { gpa_t gpa = vcpu->arch.mmu.gva_to_gpa(vcpu, addr); unsigned offset = addr & (PAGE_SIZE-1); @@ -1585,7 +1592,7 @@ int emulator_read_std(unsigned long addr, addr += tocopy; } out: - up_read(¤t->mm->mmap_sem); + up_read(&vcpu->kvm->slots_lock); return r; } EXPORT_SYMBOL_GPL(emulator_read_std); @@ -1604,9 +1611,9 @@ static int emulator_read_emulated(unsigned long addr, return X86EMUL_CONTINUE; } - down_read(¤t->mm->mmap_sem); + down_read(&vcpu->kvm->slots_lock); gpa = vcpu->arch.mmu.gva_to_gpa(vcpu, addr); - up_read(¤t->mm->mmap_sem); + up_read(&vcpu->kvm->slots_lock); /* For APIC access vmexit */ if ((gpa & PAGE_MASK) == APIC_DEFAULT_PHYS_BASE) @@ -1644,14 +1651,14 @@ static int emulator_write_phys(struct kvm_vcpu *vcpu, gpa_t gpa, { int ret; - down_read(¤t->mm->mmap_sem); + down_read(&vcpu->kvm->slots_lock); ret = kvm_write_guest(vcpu->kvm, gpa, val, bytes); if (ret < 0) { - up_read(¤t->mm->mmap_sem); + up_read(&vcpu->kvm->slots_lock); return 0; } kvm_mmu_pte_write(vcpu, gpa, val, bytes); - up_read(¤t->mm->mmap_sem); + up_read(&vcpu->kvm->slots_lock); return 1; } @@ -1663,9 +1670,9 @@ static int emulator_write_emulated_onepage(unsigned long addr, struct kvm_io_device *mmio_dev; gpa_t gpa; - down_read(¤t->mm->mmap_sem); + down_read(&vcpu->kvm->slots_lock); gpa = vcpu->arch.mmu.gva_to_gpa(vcpu, addr); - up_read(¤t->mm->mmap_sem); + up_read(&vcpu->kvm->slots_lock); if (gpa == UNMAPPED_GVA) { kvm_inject_page_fault(vcpu, addr, 2); @@ -1742,7 +1749,7 @@ static int emulator_cmpxchg_emulated(unsigned long addr, char *kaddr; u64 val; - down_read(¤t->mm->mmap_sem); + down_read(&vcpu->kvm->slots_lock); gpa = vcpu->arch.mmu.gva_to_gpa(vcpu, addr); if (gpa == UNMAPPED_GVA || @@ -1753,13 +1760,17 @@ static int emulator_cmpxchg_emulated(unsigned long addr, goto emul_write; val = *(u64 *)new; + + down_read(¤t->mm->mmap_sem); page = gfn_to_page(vcpu->kvm, gpa >> PAGE_SHIFT); + up_read(¤t->mm->mmap_sem); + kaddr = kmap_atomic(page, KM_USER0); set_64bit((u64 *)(kaddr + offset_in_page(gpa)), val); kunmap_atomic(kaddr, KM_USER0); kvm_release_page_dirty(page); emul_write: - up_read(¤t->mm->mmap_sem); + up_read(&vcpu->kvm->slots_lock); } #endif @@ -2152,10 +2163,10 @@ int kvm_emulate_pio_string(struct kvm_vcpu *vcpu, struct kvm_run *run, int in, kvm_x86_ops->skip_emulated_instruction(vcpu); for (i = 0; i < nr_pages; ++i) { - down_read(¤t->mm->mmap_sem); + down_read(&vcpu->kvm->slots_lock); page = gva_to_page(vcpu, address + i * PAGE_SIZE); vcpu->arch.pio.guest_pages[i] = page; - up_read(¤t->mm->mmap_sem); + up_read(&vcpu->kvm->slots_lock); if (!page) { kvm_inject_gp(vcpu, 0); free_pio_guest_pages(vcpu); @@ -2478,8 +2489,9 @@ static void vapic_enter(struct kvm_vcpu *vcpu) down_read(¤t->mm->mmap_sem); page = gfn_to_page(vcpu->kvm, apic->vapic_addr >> PAGE_SHIFT); - vcpu->arch.apic->vapic_page = page; up_read(¤t->mm->mmap_sem); + + vcpu->arch.apic->vapic_page = page; } static void vapic_exit(struct kvm_vcpu *vcpu) @@ -2861,8 +2873,8 @@ int kvm_arch_vcpu_ioctl_set_sregs(struct kvm_vcpu *vcpu, kvm_x86_ops->decache_cr4_guest_bits(vcpu); mmu_reset_needed |= vcpu->arch.cr0 != sregs->cr0; - vcpu->arch.cr0 = sregs->cr0; kvm_x86_ops->set_cr0(vcpu, sregs->cr0); + vcpu->arch.cr0 = sregs->cr0; mmu_reset_needed |= vcpu->arch.cr4 != sregs->cr4; kvm_x86_ops->set_cr4(vcpu, sregs->cr4); @@ -2952,9 +2964,9 @@ int kvm_arch_vcpu_ioctl_translate(struct kvm_vcpu *vcpu, gpa_t gpa; vcpu_load(vcpu); - down_read(¤t->mm->mmap_sem); + down_read(&vcpu->kvm->slots_lock); gpa = vcpu->arch.mmu.gva_to_gpa(vcpu, vaddr); - up_read(¤t->mm->mmap_sem); + up_read(&vcpu->kvm->slots_lock); tr->physical_address = gpa; tr->valid = gpa != UNMAPPED_GVA; tr->writeable = 1; @@ -3227,11 +3239,13 @@ int kvm_arch_set_memory_region(struct kvm *kvm, */ if (!user_alloc) { if (npages && !old.rmap) { + down_write(¤t->mm->mmap_sem); memslot->userspace_addr = do_mmap(NULL, 0, npages * PAGE_SIZE, PROT_READ | PROT_WRITE, MAP_SHARED | MAP_ANONYMOUS, 0); + up_write(¤t->mm->mmap_sem); if (IS_ERR((void *)memslot->userspace_addr)) return PTR_ERR((void *)memslot->userspace_addr); @@ -3239,8 +3253,10 @@ int kvm_arch_set_memory_region(struct kvm *kvm, if (!old.user_alloc && old.rmap) { int ret; + down_write(¤t->mm->mmap_sem); ret = do_munmap(current->mm, 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: " diff --git a/arch/x86/lguest/boot.c b/arch/x86/lguest/boot.c index 5afdde4..a104c53 100644 --- a/arch/x86/lguest/boot.c +++ b/arch/x86/lguest/boot.c @@ -57,6 +57,7 @@ #include <linux/lguest_launcher.h> #include <linux/virtio_console.h> #include <linux/pm.h> +#include <asm/lguest.h> #include <asm/paravirt.h> #include <asm/param.h> #include <asm/page.h> @@ -75,15 +76,6 @@ * behaving in simplified but equivalent ways. In particular, the Guest is the * same kernel as the Host (or at least, built from the same source code). :*/ -/* Declarations for definitions in lguest_guest.S */ -extern char lguest_noirq_start[], lguest_noirq_end[]; -extern const char lgstart_cli[], lgend_cli[]; -extern const char lgstart_sti[], lgend_sti[]; -extern const char lgstart_popf[], lgend_popf[]; -extern const char lgstart_pushf[], lgend_pushf[]; -extern const char lgstart_iret[], lgend_iret[]; -extern void lguest_iret(void); - struct lguest_data lguest_data = { .hcall_status = { [0 ... LHCALL_RING_SIZE-1] = 0xFF }, .noirq_start = (u32)lguest_noirq_start, @@ -92,7 +84,6 @@ struct lguest_data lguest_data = { .blocked_interrupts = { 1 }, /* Block timer interrupts */ .syscall_vec = SYSCALL_VECTOR, }; -static cycle_t clock_base; /*G:037 async_hcall() is pretty simple: I'm quite proud of it really. We have a * ring buffer of stored hypercalls which the Host will run though next time we @@ -335,8 +326,8 @@ static void lguest_cpuid(unsigned int *ax, unsigned int *bx, case 1: /* Basic feature request. */ /* We only allow kernel to see SSE3, CMPXCHG16B and SSSE3 */ *cx &= 0x00002201; - /* SSE, SSE2, FXSR, MMX, CMOV, CMPXCHG8B, FPU. */ - *dx &= 0x07808101; + /* SSE, SSE2, FXSR, MMX, CMOV, CMPXCHG8B, TSC, FPU. */ + *dx &= 0x07808111; /* The Host can do a nice optimization if it knows that the * kernel mappings (addresses above 0xC0000000 or whatever * PAGE_OFFSET is set to) haven't changed. But Linux calls @@ -603,19 +594,25 @@ static unsigned long lguest_get_wallclock(void) return lguest_data.time.tv_sec; } +/* The TSC is a Time Stamp Counter. The Host tells us what speed it runs at, + * or 0 if it's unusable as a reliable clock source. This matches what we want + * here: if we return 0 from this function, the x86 TSC clock will not register + * itself. */ +static unsigned long lguest_cpu_khz(void) +{ + return lguest_data.tsc_khz; +} + +/* If we can't use the TSC, the kernel falls back to our "lguest_clock", where + * we read the time value given to us by the Host. */ static cycle_t lguest_clock_read(void) { unsigned long sec, nsec; - /* If the Host tells the TSC speed, we can trust that. */ - if (lguest_data.tsc_khz) - return native_read_tsc(); - - /* If we can't use the TSC, we read the time value written by the Host. - * Since it's in two parts (seconds and nanoseconds), we risk reading - * it just as it's changing from 99 & 0.999999999 to 100 and 0, and - * getting 99 and 0. As Linux tends to come apart under the stress of - * time travel, we must be careful: */ + /* Since the time is in two parts (seconds and nanoseconds), we risk + * reading it just as it's changing from 99 & 0.999999999 to 100 and 0, + * and getting 99 and 0. As Linux tends to come apart under the stress + * of time travel, we must be careful: */ do { /* First we read the seconds part. */ sec = lguest_data.time.tv_sec; @@ -630,14 +627,14 @@ static cycle_t lguest_clock_read(void) /* Now if the seconds part has changed, try again. */ } while (unlikely(lguest_data.time.tv_sec != sec)); - /* Our non-TSC clock is in real nanoseconds. */ + /* Our lguest clock is in real nanoseconds. */ return sec*1000000000ULL + nsec; } -/* This is what we tell the kernel is our clocksource. */ +/* This is the fallback clocksource: lower priority than the TSC clocksource. */ static struct clocksource lguest_clock = { .name = "lguest", - .rating = 400, + .rating = 200, .read = lguest_clock_read, .mask = CLOCKSOURCE_MASK(64), .mult = 1 << 22, @@ -645,12 +642,6 @@ static struct clocksource lguest_clock = { .flags = CLOCK_SOURCE_IS_CONTINUOUS, }; -/* The "scheduler clock" is just our real clock, adjusted to start at zero */ -static unsigned long long lguest_sched_clock(void) -{ - return cyc2ns(&lguest_clock, lguest_clock_read() - clock_base); -} - /* We also need a "struct clock_event_device": Linux asks us to set it to go * off some time in the future. Actually, James Morris figured all this out, I * just applied the patch. */ @@ -720,19 +711,8 @@ static void lguest_time_init(void) /* Set up the timer interrupt (0) to go to our simple timer routine */ set_irq_handler(0, lguest_time_irq); - /* Our clock structure looks like arch/x86/kernel/tsc_32.c if we can - * use the TSC, otherwise it's a dumb nanosecond-resolution clock. - * Either way, the "rating" is set so high that it's always chosen over - * any other clocksource. */ - if (lguest_data.tsc_khz) - lguest_clock.mult = clocksource_khz2mult(lguest_data.tsc_khz, - lguest_clock.shift); - clock_base = lguest_clock_read(); clocksource_register(&lguest_clock); - /* Now we've set up our clock, we can use it as the scheduler clock */ - pv_time_ops.sched_clock = lguest_sched_clock; - /* We can't set cpumask in the initializer: damn C limitations! Set it * here and register our timer device. */ lguest_clockevent.cpumask = cpumask_of_cpu(0); @@ -1003,6 +983,7 @@ __init void lguest_init(void) /* time operations */ pv_time_ops.get_wallclock = lguest_get_wallclock; pv_time_ops.time_init = lguest_time_init; + pv_time_ops.get_cpu_khz = lguest_cpu_khz; /* Now is a good time to look at the implementations of these functions * before returning to the rest of lguest_init(). */ diff --git a/arch/x86/mm/init_64.c b/arch/x86/mm/init_64.c index bb652f5..a02a14f 100644 --- a/arch/x86/mm/init_64.c +++ b/arch/x86/mm/init_64.c @@ -172,8 +172,9 @@ set_pte_phys(unsigned long vaddr, unsigned long phys, pgprot_t prot) } /* - * The head.S code sets up the kernel high mapping from: - * __START_KERNEL_map to __START_KERNEL_map + KERNEL_TEXT_SIZE + * The head.S code sets up the kernel high mapping: + * + * from __START_KERNEL_map to __START_KERNEL_map + size (== _end-_text) * * phys_addr holds the negative offset to the kernel, which is added * to the compile time generated pmds. This results in invalid pmds up @@ -515,14 +516,6 @@ void __init mem_init(void) /* clear_bss() already clear the empty_zero_page */ - /* temporary debugging - double check it's true: */ - { - int i; - - for (i = 0; i < 1024; i++) - WARN_ON_ONCE(empty_zero_page[i]); - } - reservedpages = 0; /* this will put all low memory onto the freelists */ diff --git a/arch/x86/mm/ioremap.c b/arch/x86/mm/ioremap.c index 882328e..8fe576b 100644 --- a/arch/x86/mm/ioremap.c +++ b/arch/x86/mm/ioremap.c @@ -134,8 +134,6 @@ static void __iomem *__ioremap(unsigned long phys_addr, unsigned long size, return NULL; } - WARN_ON_ONCE(page_is_ram(pfn)); - switch (mode) { case IOR_MODE_UNCACHED: default: @@ -162,7 +160,7 @@ static void __iomem *__ioremap(unsigned long phys_addr, unsigned long size, area->phys_addr = phys_addr; vaddr = (unsigned long) area->addr; if (ioremap_page_range(vaddr, vaddr + size, phys_addr, prot)) { - remove_vm_area((void *)(vaddr & PAGE_MASK)); + free_vm_area(area); return NULL; } diff --git a/arch/x86/mm/numa_64.c b/arch/x86/mm/numa_64.c index 59898fb..8ccfee1 100644 --- a/arch/x86/mm/numa_64.c +++ b/arch/x86/mm/numa_64.c @@ -622,13 +622,17 @@ void __init init_cpu_to_node(void) int i; for (i = 0; i < NR_CPUS; i++) { + int node; u16 apicid = x86_cpu_to_apicid_init[i]; if (apicid == BAD_APICID) continue; - if (apicid_to_node[apicid] == NUMA_NO_NODE) + node = apicid_to_node[apicid]; + if (node == NUMA_NO_NODE) continue; - numa_set_node(i, apicid_to_node[apicid]); + if (!node_online(node)) + continue; + numa_set_node(i, node); } } diff --git a/arch/x86/mm/pageattr.c b/arch/x86/mm/pageattr.c index 464d8fc..14e48b5 100644 --- a/arch/x86/mm/pageattr.c +++ b/arch/x86/mm/pageattr.c @@ -44,6 +44,12 @@ static inline unsigned long highmap_end_pfn(void) #endif +#ifdef CONFIG_DEBUG_PAGEALLOC +# define debug_pagealloc 1 +#else +# define debug_pagealloc 0 +#endif + static inline int within(unsigned long addr, unsigned long start, unsigned long end) { @@ -355,45 +361,48 @@ out_unlock: static LIST_HEAD(page_pool); static unsigned long pool_size, pool_pages, pool_low; -static unsigned long pool_used, pool_failed, pool_refill; +static unsigned long pool_used, pool_failed; -static void cpa_fill_pool(void) +static void cpa_fill_pool(struct page **ret) { - struct page *p; gfp_t gfp = GFP_KERNEL; + unsigned long flags; + struct page *p; - /* Do not allocate from interrupt context */ - if (in_irq() || irqs_disabled()) - return; /* - * Check unlocked. I does not matter when we have one more - * page in the pool. The bit lock avoids recursive pool - * allocations: + * Avoid recursion (on debug-pagealloc) and also signal + * our priority to get to these pagetables: */ - if (pool_pages >= pool_size || test_and_set_bit_lock(0, &pool_refill)) + if (current->flags & PF_MEMALLOC) return; + current->flags |= PF_MEMALLOC; -#ifdef CONFIG_DEBUG_PAGEALLOC /* - * We could do: - * gfp = in_atomic() ? GFP_ATOMIC : GFP_KERNEL; - * but this fails on !PREEMPT kernels + * Allocate atomically from atomic contexts: */ - gfp = GFP_ATOMIC | __GFP_NORETRY | __GFP_NOWARN; -#endif + if (in_atomic() || irqs_disabled() || debug_pagealloc) + gfp = GFP_ATOMIC | __GFP_NORETRY | __GFP_NOWARN; - while (pool_pages < pool_size) { + while (pool_pages < pool_size || (ret && !*ret)) { p = alloc_pages(gfp, 0); if (!p) { pool_failed++; break; } - spin_lock_irq(&pgd_lock); + /* + * If the call site needs a page right now, provide it: + */ + if (ret && !*ret) { + *ret = p; + continue; + } + spin_lock_irqsave(&pgd_lock, flags); list_add(&p->lru, &page_pool); pool_pages++; - spin_unlock_irq(&pgd_lock); + spin_unlock_irqrestore(&pgd_lock, flags); } - clear_bit_unlock(0, &pool_refill); + + current->flags &= ~PF_MEMALLOC; } #define SHIFT_MB (20 - PAGE_SHIFT) @@ -414,11 +423,15 @@ void __init cpa_init(void) * GiB. Shift MiB to Gib and multiply the result by * POOL_PAGES_PER_GB: */ - gb = ((si.totalram >> SHIFT_MB) + ROUND_MB_GB) >> SHIFT_MB_GB; - pool_size = POOL_PAGES_PER_GB * gb; + if (debug_pagealloc) { + gb = ((si.totalram >> SHIFT_MB) + ROUND_MB_GB) >> SHIFT_MB_GB; + pool_size = POOL_PAGES_PER_GB * gb; + } else { + pool_size = 1; + } pool_low = pool_size; - cpa_fill_pool(); + cpa_fill_pool(NULL); printk(KERN_DEBUG "CPA: page pool initialized %lu of %lu pages preallocated\n", pool_pages, pool_size); @@ -440,16 +453,20 @@ static int split_large_page(pte_t *kpte, unsigned long address) spin_lock_irqsave(&pgd_lock, flags); if (list_empty(&page_pool)) { spin_unlock_irqrestore(&pgd_lock, flags); - return -ENOMEM; + base = NULL; + cpa_fill_pool(&base); + if (!base) + return -ENOMEM; + spin_lock_irqsave(&pgd_lock, flags); + } else { + base = list_first_entry(&page_pool, struct page, lru); + list_del(&base->lru); + pool_pages--; + + if (pool_pages < pool_low) + pool_low = pool_pages; } - base = list_first_entry(&page_pool, struct page, lru); - list_del(&base->lru); - pool_pages--; - - if (pool_pages < pool_low) - pool_low = pool_pages; - /* * Check for races, another CPU might have split this page * up for us already: @@ -734,7 +751,8 @@ static int change_page_attr_set_clr(unsigned long addr, int numpages, cpa_flush_all(cache); out: - cpa_fill_pool(); + cpa_fill_pool(NULL); + return ret; } @@ -897,7 +915,7 @@ void kernel_map_pages(struct page *page, int numpages, int enable) * Try to refill the page pool here. We can do this only after * the tlb flush. */ - cpa_fill_pool(); + cpa_fill_pool(NULL); } #ifdef CONFIG_HIBERNATION diff --git a/arch/x86/mm/pgtable_32.c b/arch/x86/mm/pgtable_32.c index 73aba71..2f9e9af 100644 --- a/arch/x86/mm/pgtable_32.c +++ b/arch/x86/mm/pgtable_32.c @@ -342,12 +342,16 @@ static void pgd_mop_up_pmds(struct mm_struct *mm, pgd_t *pgdp) pgd_t *pgd_alloc(struct mm_struct *mm) { - pgd_t *pgd = quicklist_alloc(0, GFP_KERNEL, pgd_ctor); + pgd_t *pgd = (pgd_t *)__get_free_page(GFP_KERNEL | __GFP_ZERO); - mm->pgd = pgd; /* so that alloc_pd can use it */ + /* so that alloc_pd can use it */ + mm->pgd = pgd; + if (pgd) + pgd_ctor(pgd); if (pgd && !pgd_prepopulate_pmd(mm, pgd)) { - quicklist_free(0, pgd_dtor, pgd); + pgd_dtor(pgd); + free_page((unsigned long)pgd); pgd = NULL; } @@ -357,12 +361,8 @@ pgd_t *pgd_alloc(struct mm_struct *mm) void pgd_free(struct mm_struct *mm, pgd_t *pgd) { pgd_mop_up_pmds(mm, pgd); - quicklist_free(0, pgd_dtor, pgd); -} - -void check_pgt_cache(void) -{ - quicklist_trim(0, pgd_dtor, 25, 16); + pgd_dtor(pgd); + free_page((unsigned long)pgd); } void __pte_free_tlb(struct mmu_gather *tlb, struct page *pte) diff --git a/arch/x86/pci/pcbios.c b/arch/x86/pci/pcbios.c index 10ac8c3..2f7109a 100644 --- a/arch/x86/pci/pcbios.c +++ b/arch/x86/pci/pcbios.c @@ -198,6 +198,11 @@ static int pci_bios_read(unsigned int seg, unsigned int bus, "b" (bx), "D" ((long)reg), "S" (&pci_indirect)); + /* + * Zero-extend the result beyond 8 bits, do not trust the + * BIOS having done it: + */ + *value &= 0xff; break; case 2: __asm__("lcall *(%%esi); cld\n\t" @@ -210,6 +215,11 @@ static int pci_bios_read(unsigned int seg, unsigned int bus, "b" (bx), "D" ((long)reg), "S" (&pci_indirect)); + /* + * Zero-extend the result beyond 16 bits, do not trust the + * BIOS having done it: + */ + *value &= 0xffff; break; case 4: __asm__("lcall *(%%esi); cld\n\t" diff --git a/arch/x86/vdso/Makefile b/arch/x86/vdso/Makefile index f385a4b..0a8f474 100644 --- a/arch/x86/vdso/Makefile +++ b/arch/x86/vdso/Makefile @@ -50,7 +50,9 @@ obj-$(VDSO64-y) += vdso-syms.lds sed-vdsosym := -e 's/^00*/0/' \ -e 's/^\([0-9a-fA-F]*\) . \(VDSO[a-zA-Z0-9_]*\)$$/\2 = 0x\1;/p' quiet_cmd_vdsosym = VDSOSYM $@ - cmd_vdsosym = $(NM) $< | sed -n $(sed-vdsosym) | LC_ALL=C sort > $@ +define cmd_vdsosym + $(NM) $< | LC_ALL=C sed -n $(sed-vdsosym) | LC_ALL=C sort > $@ +endef $(obj)/%-syms.lds: $(obj)/%.so.dbg FORCE $(call if_changed,vdsosym) diff --git a/arch/x86/xen/enlighten.c b/arch/x86/xen/enlighten.c index 49e5358..8b9ee27 100644 --- a/arch/x86/xen/enlighten.c +++ b/arch/x86/xen/enlighten.c @@ -153,6 +153,7 @@ static void xen_cpuid(unsigned int *ax, unsigned int *bx, if (*ax == 1) maskedx = ~((1 << X86_FEATURE_APIC) | /* disable APIC */ (1 << X86_FEATURE_ACPI) | /* disable ACPI */ + (1 << X86_FEATURE_SEP) | /* disable SEP */ (1 << X86_FEATURE_ACC)); /* thermal monitoring */ asm(XEN_EMULATE_PREFIX "cpuid" diff --git a/arch/x86/xen/setup.c b/arch/x86/xen/setup.c index 3bad477..2341492 100644 --- a/arch/x86/xen/setup.c +++ b/arch/x86/xen/setup.c @@ -38,7 +38,8 @@ char * __init xen_memory_setup(void) unsigned long max_pfn = xen_start_info->nr_pages; e820.nr_map = 0; - add_memory_region(0, PFN_PHYS(max_pfn), E820_RAM); + add_memory_region(0, LOWMEMSIZE(), E820_RAM); + add_memory_region(HIGH_MEMORY, PFN_PHYS(max_pfn)-HIGH_MEMORY, E820_RAM); return "Xen"; } |
