diff options
author | Ingo Molnar <mingo@elte.hu> | 2008-06-25 12:27:29 +0200 |
---|---|---|
committer | Ingo Molnar <mingo@elte.hu> | 2008-06-25 12:27:29 +0200 |
commit | 5ce001b0e56638c726270d4f9e05d46d4250dfbb (patch) | |
tree | c21cf007ddef99d5e8b23dde9621bd9152e676a8 /arch/x86 | |
parent | 7c9f8861e6c9c839f913e49b98c3854daca18f27 (diff) | |
parent | 543cf4cb3fe6f6cae3651ba918b9c56200b257d0 (diff) |
Merge branch 'linus' into stackprotector
Diffstat (limited to 'arch/x86')
55 files changed, 698 insertions, 521 deletions
diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig index 0cd1695c24f..09a28a36ff2 100644 --- a/arch/x86/Kconfig +++ b/arch/x86/Kconfig @@ -383,6 +383,7 @@ config VMI config KVM_CLOCK bool "KVM paravirtualized clock" select PARAVIRT + select PARAVIRT_CLOCK depends on !(X86_VISWS || X86_VOYAGER) help Turning on this option will allow you to run a paravirtualized clock @@ -410,6 +411,10 @@ config PARAVIRT over full virtualization. However, when run without a hypervisor the kernel is theoretically slower and slightly larger. +config PARAVIRT_CLOCK + bool + default n + endif config MEMTEST_BOOTPARAM @@ -1505,13 +1510,13 @@ config PCI_GOMMCONFIG config PCI_GODIRECT bool "Direct" -config PCI_GOANY - bool "Any" - config PCI_GOOLPC bool "OLPC" depends on OLPC +config PCI_GOANY + bool "Any" + endchoice config PCI_BIOS @@ -1528,9 +1533,8 @@ config PCI_MMCONFIG depends on X86_32 && PCI && ACPI && (PCI_GOMMCONFIG || PCI_GOANY) config PCI_OLPC - bool - depends on PCI && PCI_GOOLPC - default y + def_bool y + depends on PCI && OLPC && (PCI_GOOLPC || PCI_GOANY) config PCI_DOMAINS def_bool y diff --git a/arch/x86/Kconfig.debug b/arch/x86/Kconfig.debug index b5c5b55d043..a8d3c7e0414 100644 --- a/arch/x86/Kconfig.debug +++ b/arch/x86/Kconfig.debug @@ -6,15 +6,19 @@ config TRACE_IRQFLAGS_SUPPORT source "lib/Kconfig.debug" config NONPROMISC_DEVMEM - bool "Disable promiscuous /dev/mem" + bool "Filter access to /dev/mem" help - The /dev/mem file by default only allows userspace access to PCI - space and the BIOS code and data regions. This is sufficient for - dosemu and X and all common users of /dev/mem. With this config - option, you allow userspace access to all of memory, including - kernel and userspace memory. Accidental access to this is - obviously disasterous, but specific access can be used by people - debugging the kernel. + If this option is left off, you allow userspace access to all + of memory, including kernel and userspace memory. Accidental + access to this is obviously disastrous, but specific access can + be used by people debugging the kernel. + + If this option is switched on, the /dev/mem file only allows + userspace access to PCI space and the BIOS code and data regions. + This is sufficient for dosemu and X and all common users of + /dev/mem. + + If in doubt, say Y. config EARLY_PRINTK bool "Early printk" if EMBEDDED diff --git a/arch/x86/boot/a20.c b/arch/x86/boot/a20.c index 90943f83e84..e01aafd03bd 100644 --- a/arch/x86/boot/a20.c +++ b/arch/x86/boot/a20.c @@ -115,8 +115,6 @@ static void enable_a20_fast(void) int enable_a20(void) { - int loops = A20_ENABLE_LOOPS; - #if defined(CONFIG_X86_ELAN) /* Elan croaks if we try to touch the KBC */ enable_a20_fast(); @@ -128,6 +126,7 @@ int enable_a20(void) enable_a20_kbc(); return 0; #else + int loops = A20_ENABLE_LOOPS; while (loops--) { /* First, check to see if A20 is already enabled (legacy free, etc.) */ diff --git a/arch/x86/kernel/Makefile b/arch/x86/kernel/Makefile index 8161e5a91ca..d001739d8b0 100644 --- a/arch/x86/kernel/Makefile +++ b/arch/x86/kernel/Makefile @@ -83,6 +83,7 @@ obj-$(CONFIG_VMI) += vmi_32.o vmiclock_32.o obj-$(CONFIG_KVM_GUEST) += kvm.o obj-$(CONFIG_KVM_CLOCK) += kvmclock.o obj-$(CONFIG_PARAVIRT) += paravirt.o paravirt_patch_$(BITS).o +obj-$(CONFIG_PARAVIRT_CLOCK) += pvclock.o obj-$(CONFIG_PCSPKR_PLATFORM) += pcspeaker.o diff --git a/arch/x86/kernel/acpi/boot.c b/arch/x86/kernel/acpi/boot.c index c49ebcc6c41..33c5216fd3e 100644 --- a/arch/x86/kernel/acpi/boot.c +++ b/arch/x86/kernel/acpi/boot.c @@ -242,12 +242,19 @@ static int __init acpi_parse_madt(struct acpi_table_header *table) static void __cpuinit acpi_register_lapic(int id, u8 enabled) { + unsigned int ver = 0; + if (!enabled) { ++disabled_cpus; return; } - generic_processor_info(id, 0); +#ifdef CONFIG_X86_32 + if (boot_cpu_physical_apicid != -1U) + ver = apic_version[boot_cpu_physical_apicid]; +#endif + + generic_processor_info(id, ver); } static int __init @@ -767,8 +774,13 @@ static void __init acpi_register_lapic_address(unsigned long address) mp_lapic_addr = address; set_fixmap_nocache(FIX_APIC_BASE, address); - if (boot_cpu_physical_apicid == -1U) + if (boot_cpu_physical_apicid == -1U) { boot_cpu_physical_apicid = GET_APIC_ID(read_apic_id()); +#ifdef CONFIG_X86_32 + apic_version[boot_cpu_physical_apicid] = + GET_APIC_VERSION(apic_read(APIC_LVR)); +#endif + } } static int __init early_acpi_parse_madt_lapic_addr_ovr(void) diff --git a/arch/x86/kernel/entry_32.S b/arch/x86/kernel/entry_32.S index 2a609dc3271..c778e4fa55a 100644 --- a/arch/x86/kernel/entry_32.S +++ b/arch/x86/kernel/entry_32.S @@ -248,6 +248,7 @@ ENTRY(resume_userspace) DISABLE_INTERRUPTS(CLBR_ANY) # make sure we don't miss an interrupt # setting need_resched or sigpending # between sampling and the iret + TRACE_IRQS_OFF movl TI_flags(%ebp), %ecx andl $_TIF_WORK_MASK, %ecx # is there any work to be done on # int/exception return? diff --git a/arch/x86/kernel/geode_32.c b/arch/x86/kernel/geode_32.c index e8edd63ab00..9b08e852fd1 100644 --- a/arch/x86/kernel/geode_32.c +++ b/arch/x86/kernel/geode_32.c @@ -166,6 +166,8 @@ int geode_has_vsa2(void) static int has_vsa2 = -1; if (has_vsa2 == -1) { + u16 val; + /* * The VSA has virtual registers that we can query for a * signature. @@ -173,7 +175,8 @@ int geode_has_vsa2(void) outw(VSA_VR_UNLOCK, VSA_VRC_INDEX); outw(VSA_VR_SIGNATURE, VSA_VRC_INDEX); - has_vsa2 = (inw(VSA_VRC_DATA) == VSA_SIG); + val = inw(VSA_VRC_DATA); + has_vsa2 = (val == AMD_VSA_SIG || val == GSW_VSA_SIG); } return has_vsa2; diff --git a/arch/x86/kernel/head_32.S b/arch/x86/kernel/head_32.S index b2cc73768a9..f7357cc0162 100644 --- a/arch/x86/kernel/head_32.S +++ b/arch/x86/kernel/head_32.S @@ -189,7 +189,7 @@ default_entry: * this stage. */ -#define KPMDS ((0x100000000-__PAGE_OFFSET) >> 30) /* Number of kernel PMDs */ +#define KPMDS (((-__PAGE_OFFSET) >> 30) & 3) /* Number of kernel PMDs */ xorl %ebx,%ebx /* %ebx is kept at zero */ diff --git a/arch/x86/kernel/i387.c b/arch/x86/kernel/i387.c index e03cc952f23..eb9ddd8efb8 100644 --- a/arch/x86/kernel/i387.c +++ b/arch/x86/kernel/i387.c @@ -56,6 +56,11 @@ void __cpuinit mxcsr_feature_mask_init(void) void __init init_thread_xstate(void) { + if (!HAVE_HWFP) { + xstate_size = sizeof(struct i387_soft_struct); + return; + } + if (cpu_has_fxsr) xstate_size = sizeof(struct i387_fxsave_struct); #ifdef CONFIG_X86_32 @@ -94,7 +99,7 @@ void __cpuinit fpu_init(void) int init_fpu(struct task_struct *tsk) { if (tsk_used_math(tsk)) { - if (tsk == current) + if (HAVE_HWFP && tsk == current) unlazy_fpu(tsk); return 0; } @@ -109,6 +114,15 @@ int init_fpu(struct task_struct *tsk) return -ENOMEM; } +#ifdef CONFIG_X86_32 + if (!HAVE_HWFP) { + memset(tsk->thread.xstate, 0, xstate_size); + finit(); + set_stopped_child_used_math(tsk); + return 0; + } +#endif + if (cpu_has_fxsr) { struct i387_fxsave_struct *fx = &tsk->thread.xstate->fxsave; @@ -330,13 +344,13 @@ int fpregs_get(struct task_struct *target, const struct user_regset *regset, struct user_i387_ia32_struct env; int ret; - if (!HAVE_HWFP) - return fpregs_soft_get(target, regset, pos, count, kbuf, ubuf); - ret = init_fpu(target); if (ret) return ret; + if (!HAVE_HWFP) + return fpregs_soft_get(target, regset, pos, count, kbuf, ubuf); + if (!cpu_has_fxsr) { return user_regset_copyout(&pos, &count, &kbuf, &ubuf, &target->thread.xstate->fsave, 0, @@ -360,15 +374,15 @@ int fpregs_set(struct task_struct *target, const struct user_regset *regset, struct user_i387_ia32_struct env; int ret; - if (!HAVE_HWFP) - return fpregs_soft_set(target, regset, pos, count, kbuf, ubuf); - ret = init_fpu(target); if (ret) return ret; set_stopped_child_used_math(target); + if (!HAVE_HWFP) + return fpregs_soft_set(target, regset, pos, count, kbuf, ubuf); + if (!cpu_has_fxsr) { return user_regset_copyin(&pos, &count, &kbuf, &ubuf, &target->thread.xstate->fsave, 0, -1); @@ -474,18 +488,18 @@ static int restore_i387_fxsave(struct _fpstate_ia32 __user *buf) int restore_i387_ia32(struct _fpstate_ia32 __user *buf) { int err; + struct task_struct *tsk = current; - if (HAVE_HWFP) { - struct task_struct *tsk = current; - + if (HAVE_HWFP) clear_fpu(tsk); - if (!used_math()) { - err = init_fpu(tsk); - if (err) - return err; - } + if (!used_math()) { + err = init_fpu(tsk); + if (err) + return err; + } + if (HAVE_HWFP) { if (cpu_has_fxsr) err = restore_i387_fxsave(buf); else diff --git a/arch/x86/kernel/io_apic_32.c b/arch/x86/kernel/io_apic_32.c index a40d54fc1fd..4dc8600d9d2 100644 --- a/arch/x86/kernel/io_apic_32.c +++ b/arch/x86/kernel/io_apic_32.c @@ -2130,14 +2130,10 @@ static inline void __init check_timer(void) { int apic1, pin1, apic2, pin2; int vector; - unsigned int ver; unsigned long flags; local_irq_save(flags); - ver = apic_read(APIC_LVR); - ver = GET_APIC_VERSION(ver); - /* * get/set the timer IRQ vector: */ @@ -2150,15 +2146,11 @@ static inline void __init check_timer(void) * mode for the 8259A whenever interrupts are routed * through I/O APICs. Also IRQ0 has to be enabled in * the 8259A which implies the virtual wire has to be - * disabled in the local APIC. Finally timer interrupts - * need to be acknowledged manually in the 8259A for - * timer_interrupt() and for the i82489DX when using - * the NMI watchdog. + * disabled in the local APIC. */ apic_write_around(APIC_LVT0, APIC_LVT_MASKED | APIC_DM_EXTINT); init_8259A(1); - timer_ack = !cpu_has_tsc; - timer_ack |= (nmi_watchdog == NMI_IO_APIC && !APIC_INTEGRATED(ver)); + timer_ack = 1; if (timer_over_8254 > 0) enable_8259A_irq(0); diff --git a/arch/x86/kernel/kvmclock.c b/arch/x86/kernel/kvmclock.c index 08a30986d47..87edf1ceb1d 100644 --- a/arch/x86/kernel/kvmclock.c +++ b/arch/x86/kernel/kvmclock.c @@ -18,6 +18,7 @@ #include <linux/clocksource.h> #include <linux/kvm_para.h> +#include <asm/pvclock.h> #include <asm/arch_hooks.h> #include <asm/msr.h> #include <asm/apic.h> @@ -36,18 +37,9 @@ static int parse_no_kvmclock(char *arg) early_param("no-kvmclock", parse_no_kvmclock); /* The hypervisor will put information about time periodically here */ -static DEFINE_PER_CPU_SHARED_ALIGNED(struct kvm_vcpu_time_info, hv_clock); -#define get_clock(cpu, field) per_cpu(hv_clock, cpu).field +static DEFINE_PER_CPU_SHARED_ALIGNED(struct pvclock_vcpu_time_info, hv_clock); +static struct pvclock_wall_clock wall_clock; -static inline u64 kvm_get_delta(u64 last_tsc) -{ - int cpu = smp_processor_id(); - u64 delta = native_read_tsc() - last_tsc; - return (delta * get_clock(cpu, tsc_to_system_mul)) >> KVM_SCALE; -} - -static struct kvm_wall_clock wall_clock; -static cycle_t kvm_clock_read(void); /* * The wallclock is the time of day when we booted. Since then, some time may * have elapsed since the hypervisor wrote the data. So we try to account for @@ -55,64 +47,37 @@ static cycle_t kvm_clock_read(void); */ static unsigned long kvm_get_wallclock(void) { - u32 wc_sec, wc_nsec; - u64 delta; + struct pvclock_vcpu_time_info *vcpu_time; struct timespec ts; - int version, nsec; int low, high; low = (int)__pa(&wall_clock); high = ((u64)__pa(&wall_clock) >> 32); + native_write_msr(MSR_KVM_WALL_CLOCK, low, high); - delta = kvm_clock_read(); + vcpu_time = &get_cpu_var(hv_clock); + pvclock_read_wallclock(&wall_clock, vcpu_time, &ts); + put_cpu_var(hv_clock); - native_write_msr(MSR_KVM_WALL_CLOCK, low, high); - do { - version = wall_clock.wc_version; - rmb(); - wc_sec = wall_clock.wc_sec; - wc_nsec = wall_clock.wc_nsec; - rmb(); - } while ((wall_clock.wc_version != version) || (version & 1)); - - delta = kvm_clock_read() - delta; - delta += wc_nsec; - nsec = do_div(delta, NSEC_PER_SEC); - set_normalized_timespec(&ts, wc_sec + delta, nsec); - /* - * Of all mechanisms of time adjustment I've tested, this one - * was the champion! - */ - return ts.tv_sec + 1; + return ts.tv_sec; } static int kvm_set_wallclock(unsigned long now) { - return 0; + return -1; } -/* - * This is our read_clock function. The host puts an tsc timestamp each time - * it updates a new time. Without the tsc adjustment, we can have a situation - * in which a vcpu starts to run earlier (smaller system_time), but probes - * time later (compared to another vcpu), leading to backwards time - */ static cycle_t kvm_clock_read(void) { - u64 last_tsc, now; - int cpu; + struct pvclock_vcpu_time_info *src; + cycle_t ret; - preempt_disable(); - cpu = smp_processor_id(); - - last_tsc = get_clock(cpu, tsc_timestamp); - now = get_clock(cpu, system_time); - - now += kvm_get_delta(last_tsc); - preempt_enable(); - - return now; + src = &get_cpu_var(hv_clock); + ret = pvclock_clocksource_read(src); + put_cpu_var(hv_clock); + return ret; } + static struct clocksource kvm_clock = { .name = "kvm-clock", .read = kvm_clock_read, @@ -123,13 +88,14 @@ static struct clocksource kvm_clock = { .flags = CLOCK_SOURCE_IS_CONTINUOUS, }; -static int kvm_register_clock(void) +static int kvm_register_clock(char *txt) { int cpu = smp_processor_id(); int low, high; low = (int)__pa(&per_cpu(hv_clock, cpu)) | 1; high = ((u64)__pa(&per_cpu(hv_clock, cpu)) >> 32); - + printk(KERN_INFO "kvm-clock: cpu %d, msr %x:%x, %s\n", + cpu, high, low, txt); return native_write_msr_safe(MSR_KVM_SYSTEM_TIME, low, high); } @@ -140,12 +106,20 @@ static void kvm_setup_secondary_clock(void) * Now that the first cpu already had this clocksource initialized, * we shouldn't fail. */ - WARN_ON(kvm_register_clock()); + WARN_ON(kvm_register_clock("secondary cpu clock")); /* ok, done with our trickery, call native */ setup_secondary_APIC_clock(); } #endif +#ifdef CONFIG_SMP +void __init kvm_smp_prepare_boot_cpu(void) +{ + WARN_ON(kvm_register_clock("primary cpu clock")); + native_smp_prepare_boot_cpu(); +} +#endif + /* * After the clock is registered, the host will keep writing to the * registered memory location. If the guest happens to shutdown, this memory @@ -174,7 +148,7 @@ void __init kvmclock_init(void) return; if (kvmclock && kvm_para_has_feature(KVM_FEATURE_CLOCKSOURCE)) { - if (kvm_register_clock()) + if (kvm_register_clock("boot clock")) return; pv_time_ops.get_wallclock = kvm_get_wallclock; pv_time_ops.set_wallclock = kvm_set_wallclock; @@ -182,6 +156,9 @@ void __init kvmclock_init(void) #ifdef CONFIG_X86_LOCAL_APIC pv_apic_ops.setup_secondary_clock = kvm_setup_secondary_clock; #endif +#ifdef CONFIG_SMP + smp_ops.smp_prepare_boot_cpu = kvm_smp_prepare_boot_cpu; +#endif machine_ops.shutdown = kvm_shutdown; #ifdef CONFIG_KEXEC machine_ops.crash_shutdown = kvm_crash_shutdown; diff --git a/arch/x86/kernel/mfgpt_32.c b/arch/x86/kernel/mfgpt_32.c index 3cad17fe026..07c0f828f48 100644 --- a/arch/x86/kernel/mfgpt_32.c +++ b/arch/x86/kernel/mfgpt_32.c @@ -155,6 +155,7 @@ int geode_mfgpt_toggle_event(int timer, int cmp, int event, int enable) wrmsr(msr, value, dummy); return 0; } +EXPORT_SYMBOL_GPL(geode_mfgpt_toggle_event); int geode_mfgpt_set_irq(int timer, int cmp, int irq, int enable) { @@ -222,6 +223,7 @@ int geode_mfgpt_alloc_timer(int timer, int domain) /* No timers available - too bad */ return -1; } +EXPORT_SYMBOL_GPL(geode_mfgpt_alloc_timer); #ifdef CONFIG_GEODE_MFGPT_TIMER diff --git a/arch/x86/kernel/nmi_32.c b/arch/x86/kernel/nmi_32.c index 11b14bbaa61..84160f74eeb 100644 --- a/arch/x86/kernel/nmi_32.c +++ b/arch/x86/kernel/nmi_32.c @@ -26,7 +26,6 @@ #include <asm/smp.h> #include <asm/nmi.h> -#include <asm/timer.h> #include "mach_traps.h" @@ -82,7 +81,7 @@ int __init check_nmi_watchdog(void) prev_nmi_count = kmalloc(NR_CPUS * sizeof(int), GFP_KERNEL); if (!prev_nmi_count) - goto error; + return -1; printk(KERN_INFO "Testing NMI watchdog ... "); @@ -119,7 +118,7 @@ int __init check_nmi_watchdog(void) if (!atomic_read(&nmi_active)) { kfree(prev_nmi_count); atomic_set(&nmi_active, -1); - goto error; + return -1; } printk("OK.\n"); @@ -130,10 +129,6 @@ int __init check_nmi_watchdog(void) kfree(prev_nmi_count); return 0; -error: - timer_ack = !cpu_has_tsc; - - return -1; } static int __init setup_nmi_watchdog(char *str) diff --git a/arch/x86/kernel/pci-dma.c b/arch/x86/kernel/pci-dma.c index c5ef1af8e79..dc00a1331ac 100644 --- a/arch/x86/kernel/pci-dma.c +++ b/arch/x86/kernel/pci-dma.c @@ -378,6 +378,7 @@ dma_alloc_coherent(struct device *dev, size_t size, dma_addr_t *dma_handle, struct page *page; unsigned long dma_mask = 0; dma_addr_t bus; + int noretry = 0; /* ignore region specifiers */ gfp &= ~(__GFP_DMA | __GFP_HIGHMEM | __GFP_DMA32); @@ -397,20 +398,25 @@ dma_alloc_coherent(struct device *dev, size_t size, dma_addr_t *dma_handle, if (dev->dma_mask == NULL) return NULL; - /* Don't invoke OOM killer */ - gfp |= __GFP_NORETRY; + /* Don't invoke OOM killer or retry in lower 16MB DMA zone */ + if (gfp & __GFP_DMA) + noretry = 1; #ifdef CONFIG_X86_64 /* Why <=? Even when the mask is smaller than 4GB it is often larger than 16MB and in this case we have a chance of finding fitting memory in the next higher zone first. If not retry with true GFP_DMA. -AK */ - if (dma_mask <= DMA_32BIT_MASK && !(gfp & GFP_DMA)) + if (dma_mask <= DMA_32BIT_MASK && !(gfp & GFP_DMA)) { gfp |= GFP_DMA32; + if (dma_mask < DMA_32BIT_MASK) + noretry = 1; + } #endif again: - page = dma_alloc_pages(dev, gfp, get_order(size)); + page = dma_alloc_pages(dev, + noretry ? gfp | __GFP_NORETRY : gfp, get_order(size)); if (page == NULL) return NULL; diff --git a/arch/x86/kernel/pci-gart_64.c b/arch/x86/kernel/pci-gart_64.c index c07455d1695..aa8ec928caa 100644 --- a/arch/x86/kernel/pci-gart_64.c +++ b/arch/x86/kernel/pci-gart_64.c @@ -26,6 +26,7 @@ #include <linux/kdebug.h> #include <linux/scatterlist.h> #include <linux/iommu-helper.h> +#include <linux/sysdev.h> #include <asm/atomic.h> #include <asm/io.h> #include <asm/mtrr.h> @@ -548,6 +549,28 @@ static __init unsigned read_aperture(struct pci_dev *dev, u32 *size) return aper_base; } +static int gart_resume(struct sys_device *dev) +{ + return 0; +} + +static int gart_suspend(struct sys_device *dev, pm_message_t state) +{ + return -EINVAL; +} + +static struct sysdev_class gart_sysdev_class = { + .name = "gart", + .suspend = gart_suspend, + .resume = gart_resume, + +}; + +static struct sys_device device_gart = { + .id = 0, + .cls = &gart_sysdev_class, +}; + /* * Private Northbridge GATT initialization in case we cannot use the * AGP driver for some reason. |