diff options
Diffstat (limited to 'arch/x86/kernel')
| -rw-r--r-- | arch/x86/kernel/cpu/perf_event.c | 6 | ||||
| -rw-r--r-- | arch/x86/kernel/entry_32.S | 1 | ||||
| -rw-r--r-- | arch/x86/kernel/entry_64.S | 7 | ||||
| -rw-r--r-- | arch/x86/kernel/head_32.S | 9 | ||||
| -rw-r--r-- | arch/x86/kernel/kvm.c | 12 | ||||
| -rw-r--r-- | arch/x86/kernel/msr.c | 3 | ||||
| -rw-r--r-- | arch/x86/kernel/pci-dma.c | 2 | ||||
| -rw-r--r-- | arch/x86/kernel/reboot.c | 2 | ||||
| -rw-r--r-- | arch/x86/kernel/setup.c | 108 | ||||
| -rw-r--r-- | arch/x86/kernel/step.c | 9 |
10 files changed, 124 insertions, 35 deletions
diff --git a/arch/x86/kernel/cpu/perf_event.c b/arch/x86/kernel/cpu/perf_event.c index 4428fd178bce..6774c17a5576 100644 --- a/arch/x86/kernel/cpu/perf_event.c +++ b/arch/x86/kernel/cpu/perf_event.c @@ -340,9 +340,6 @@ int x86_setup_perfctr(struct perf_event *event) /* BTS is currently only allowed for user-mode. */ if (!attr->exclude_kernel) return -EOPNOTSUPP; - - if (!attr->exclude_guest) - return -EOPNOTSUPP; } hwc->config |= config; @@ -385,9 +382,6 @@ int x86_pmu_hw_config(struct perf_event *event) if (event->attr.precise_ip) { int precise = 0; - if (!event->attr.exclude_guest) - return -EOPNOTSUPP; - /* Support for constant skid */ if (x86_pmu.pebs_active && !x86_pmu.pebs_broken) { precise++; diff --git a/arch/x86/kernel/entry_32.S b/arch/x86/kernel/entry_32.S index ff84d5469d77..6ed91d9980e2 100644 --- a/arch/x86/kernel/entry_32.S +++ b/arch/x86/kernel/entry_32.S @@ -1065,7 +1065,6 @@ ENTRY(xen_failsafe_callback) lea 16(%esp),%esp CFI_ADJUST_CFA_OFFSET -16 jz 5f - addl $16,%esp jmp iret_exc 5: pushl_cfi $-1 /* orig_ax = -1 => not a system call */ SAVE_ALL diff --git a/arch/x86/kernel/entry_64.S b/arch/x86/kernel/entry_64.S index 07a7a04529bc..cb3c591339aa 100644 --- a/arch/x86/kernel/entry_64.S +++ b/arch/x86/kernel/entry_64.S @@ -1781,6 +1781,7 @@ first_nmi: * Leave room for the "copied" frame */ subq $(5*8), %rsp + CFI_ADJUST_CFA_OFFSET 5*8 /* Copy the stack frame to the Saved frame */ .rept 5 @@ -1863,10 +1864,8 @@ end_repeat_nmi: nmi_swapgs: SWAPGS_UNSAFE_STACK nmi_restore: - RESTORE_ALL 8 - - /* Pop the extra iret frame */ - addq $(5*8), %rsp + /* Pop the extra iret frame at once */ + RESTORE_ALL 6*8 /* Clear the NMI executing stack variable */ movq $0, 5*8(%rsp) diff --git a/arch/x86/kernel/head_32.S b/arch/x86/kernel/head_32.S index 8e7f6556028f..c8932c79e78b 100644 --- a/arch/x86/kernel/head_32.S +++ b/arch/x86/kernel/head_32.S @@ -300,6 +300,12 @@ ENTRY(startup_32_smp) leal -__PAGE_OFFSET(%ecx),%esp default_entry: +#define CR0_STATE (X86_CR0_PE | X86_CR0_MP | X86_CR0_ET | \ + X86_CR0_NE | X86_CR0_WP | X86_CR0_AM | \ + X86_CR0_PG) + movl $(CR0_STATE & ~X86_CR0_PG),%eax + movl %eax,%cr0 + /* * New page tables may be in 4Mbyte page mode and may * be using the global pages. @@ -364,8 +370,7 @@ default_entry: */ movl $pa(initial_page_table), %eax movl %eax,%cr3 /* set the page table pointer.. */ - movl %cr0,%eax - orl $X86_CR0_PG,%eax + movl $CR0_STATE,%eax movl %eax,%cr0 /* ..and set paging (PG) bit */ ljmp $__BOOT_CS,$1f /* Clear prefetch and normalize %eip */ 1: diff --git a/arch/x86/kernel/kvm.c b/arch/x86/kernel/kvm.c index 08b973f64032..9c2bd8bd4b4c 100644 --- a/arch/x86/kernel/kvm.c +++ b/arch/x86/kernel/kvm.c @@ -43,6 +43,7 @@ #include <asm/apicdef.h> #include <asm/hypervisor.h> #include <asm/kvm_guest.h> +#include <asm/context_tracking.h> static int kvmapf = 1; @@ -121,6 +122,8 @@ void kvm_async_pf_task_wait(u32 token) struct kvm_task_sleep_node n, *e; DEFINE_WAIT(wait); + rcu_irq_enter(); + spin_lock(&b->lock); e = _find_apf_task(b, token); if (e) { @@ -128,6 +131,8 @@ void kvm_async_pf_task_wait(u32 token) hlist_del(&e->link); kfree(e); spin_unlock(&b->lock); + + rcu_irq_exit(); return; } @@ -152,13 +157,16 @@ void kvm_async_pf_task_wait(u32 token) /* * We cannot reschedule. So halt. */ + rcu_irq_exit(); native_safe_halt(); + rcu_irq_enter(); local_irq_disable(); } } if (!n.halted) finish_wait(&n.wq, &wait); + rcu_irq_exit(); return; } EXPORT_SYMBOL_GPL(kvm_async_pf_task_wait); @@ -252,10 +260,10 @@ do_async_page_fault(struct pt_regs *regs, unsigned long error_code) break; case KVM_PV_REASON_PAGE_NOT_PRESENT: /* page is swapped out by the host. */ - rcu_irq_enter(); + exception_enter(regs); exit_idle(); kvm_async_pf_task_wait((u32)read_cr2()); - rcu_irq_exit(); + exception_exit(regs); break; case KVM_PV_REASON_PAGE_READY: rcu_irq_enter(); diff --git a/arch/x86/kernel/msr.c b/arch/x86/kernel/msr.c index a7c5661f8496..4929502c1372 100644 --- a/arch/x86/kernel/msr.c +++ b/arch/x86/kernel/msr.c @@ -174,6 +174,9 @@ static int msr_open(struct inode *inode, struct file *file) unsigned int cpu; struct cpuinfo_x86 *c; + if (!capable(CAP_SYS_RAWIO)) + return -EPERM; + cpu = iminor(file->f_path.dentry->d_inode); if (cpu >= nr_cpu_ids || !cpu_online(cpu)) return -ENXIO; /* No such CPU */ diff --git a/arch/x86/kernel/pci-dma.c b/arch/x86/kernel/pci-dma.c index 0f5dec5c80e0..872079a67e4d 100644 --- a/arch/x86/kernel/pci-dma.c +++ b/arch/x86/kernel/pci-dma.c @@ -56,7 +56,7 @@ struct device x86_dma_fallback_dev = { EXPORT_SYMBOL(x86_dma_fallback_dev); /* Number of entries preallocated for DMA-API debugging */ -#define PREALLOC_DMA_DEBUG_ENTRIES 32768 +#define PREALLOC_DMA_DEBUG_ENTRIES 65536 int dma_set_mask(struct device *dev, u64 mask) { diff --git a/arch/x86/kernel/reboot.c b/arch/x86/kernel/reboot.c index 4e8ba39eaf0f..76fa1e9a2b39 100644 --- a/arch/x86/kernel/reboot.c +++ b/arch/x86/kernel/reboot.c @@ -584,7 +584,7 @@ static void native_machine_emergency_restart(void) break; case BOOT_EFI: - if (efi_enabled) + if (efi_enabled(EFI_RUNTIME_SERVICES)) efi.reset_system(reboot_mode ? EFI_RESET_WARM : EFI_RESET_COLD, diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c index 23ddd558fbd5..8b24289cc10c 100644 --- a/arch/x86/kernel/setup.c +++ b/arch/x86/kernel/setup.c @@ -610,6 +610,83 @@ static __init void reserve_ibft_region(void) static unsigned reserve_low = CONFIG_X86_RESERVE_LOW << 10; +static bool __init snb_gfx_workaround_needed(void) +{ +#ifdef CONFIG_PCI + int i; + u16 vendor, devid; + static const __initconst u16 snb_ids[] = { + 0x0102, + 0x0112, + 0x0122, + 0x0106, + 0x0116, + 0x0126, + 0x010a, + }; + + /* Assume no if something weird is going on with PCI */ + if (!early_pci_allowed()) + return false; + + vendor = read_pci_config_16(0, 2, 0, PCI_VENDOR_ID); + if (vendor != 0x8086) + return false; + + devid = read_pci_config_16(0, 2, 0, PCI_DEVICE_ID); + for (i = 0; i < ARRAY_SIZE(snb_ids); i++) + if (devid == snb_ids[i]) + return true; +#endif + + return false; +} + +/* + * Sandy Bridge graphics has trouble with certain ranges, exclude + * them from allocation. + */ +static void __init trim_snb_memory(void) +{ + static const __initconst unsigned long bad_pages[] = { + 0x20050000, + 0x20110000, + 0x20130000, + 0x20138000, + 0x40004000, + }; + int i; + + if (!snb_gfx_workaround_needed()) + return; + + printk(KERN_DEBUG "reserving inaccessible SNB gfx pages\n"); + + /* + * Reserve all memory below the 1 MB mark that has not + * already been reserved. + */ + memblock_reserve(0, 1<<20); + + for (i = 0; i < ARRAY_SIZE(bad_pages); i++) { + if (memblock_reserve(bad_pages[i], PAGE_SIZE)) + printk(KERN_WARNING "failed to reserve 0x%08lx\n", + bad_pages[i]); + } +} + +/* + * Here we put platform-specific memory range workarounds, i.e. + * memory known to be corrupt or otherwise in need to be reserved on + * specific platforms. + * + * If this gets used more widely it could use a real dispatch mechanism. + */ +static void __init trim_platform_memory_ranges(void) +{ + trim_snb_memory(); +} + static void __init trim_bios_range(void) { /* @@ -630,6 +707,7 @@ static void __init trim_bios_range(void) * take them out. */ e820_remove_range(BIOS_BEGIN, BIOS_END - BIOS_BEGIN, E820_RAM, 1); + sanitize_e820_map(e820.map, ARRAY_SIZE(e820.map), &e820.nr_map); } @@ -729,15 +807,15 @@ void __init setup_arch(char **cmdline_p) #ifdef CONFIG_EFI if (!strncmp((char *)&boot_params.efi_info.efi_loader_signature, "EL32", 4)) { - efi_enabled = 1; - efi_64bit = false; + set_bit(EFI_BOOT, &x86_efi_facility); } else if (!strncmp((char *)&boot_params.efi_info.efi_loader_signature, "EL64", 4)) { - efi_enabled = 1; - efi_64bit = true; + set_bit(EFI_BOOT, &x86_efi_facility); + set_bit(EFI_64BIT, &x86_efi_facility); } - if (efi_enabled && efi_memblock_x86_reserve_range()) - efi_enabled = 0; + + if (efi_enabled(EFI_BOOT)) + efi_memblock_x86_reserve_range(); #endif x86_init.oem.arch_setup(); @@ -810,7 +888,7 @@ void __init setup_arch(char **cmdline_p) finish_e820_parsing(); - if (efi_enabled) + if (efi_enabled(EFI_BOOT)) efi_init(); dmi_scan_machine(); @@ -893,7 +971,7 @@ void __init setup_arch(char **cmdline_p) * The EFI specification says that boot service code won't be called * after ExitBootServices(). This is, in fact, a lie. */ - if (efi_enabled) + if (efi_enabled(EFI_MEMMAP)) efi_reserve_boot_services(); /* preallocate 4k for mptable mpc */ @@ -908,6 +986,8 @@ void __init setup_arch(char **cmdline_p) setup_real_mode(); + trim_platform_memory_ranges(); + init_gbpages(); /* max_pfn_mapped is updated here */ @@ -1034,7 +1114,7 @@ void __init setup_arch(char **cmdline_p) #ifdef CONFIG_VT #if defined(CONFIG_VGA_CONSOLE) - if (!efi_enabled || (efi_mem_type(0xa0000) != EFI_CONVENTIONAL_MEMORY)) + if (!efi_enabled(EFI_BOOT) || (efi_mem_type(0xa0000) != EFI_CONVENTIONAL_MEMORY)) conswitchp = &vga_con; #elif defined(CONFIG_DUMMY_CONSOLE) conswitchp = &dummy_con; @@ -1051,14 +1131,14 @@ void __init setup_arch(char **cmdline_p) register_refined_jiffies(CLOCK_TICK_RATE); #ifdef CONFIG_EFI - /* Once setup is done above, disable efi_enabled on mismatched - * firmware/kernel archtectures since there is no support for - * runtime services. + /* Once setup is done above, unmap the EFI memory map on + * mismatched firmware/kernel archtectures since there is no + * support for runtime services. */ - if (efi_enabled && IS_ENABLED(CONFIG_X86_64) != efi_64bit) { + if (efi_enabled(EFI_BOOT) && + IS_ENABLED(CONFIG_X86_64) != efi_enabled(EFI_64BIT)) { pr_info("efi: Setup done, disabling due to 32/64-bit mismatch\n"); efi_unmap_memmap(); - efi_enabled = 0; } #endif } diff --git a/arch/x86/kernel/step.c b/arch/x86/kernel/step.c index cd3b2438a980..9b4d51d0c0d0 100644 --- a/arch/x86/kernel/step.c +++ b/arch/x86/kernel/step.c @@ -165,10 +165,11 @@ void set_task_blockstep(struct task_struct *task, bool on) * Ensure irq/preemption can't change debugctl in between. * Note also that both TIF_BLOCKSTEP and debugctl should * be changed atomically wrt preemption. - * FIXME: this means that set/clear TIF_BLOCKSTEP is simply - * wrong if task != current, SIGKILL can wakeup the stopped - * tracee and set/clear can play with the running task, this - * can confuse the next __switch_to_xtra(). + * + * NOTE: this means that set/clear TIF_BLOCKSTEP is only safe if + * task is current or it can't be running, otherwise we can race + * with __switch_to_xtra(). We rely on ptrace_freeze_traced() but + * PTRACE_KILL is not safe. */ local_irq_disable(); debugctl = get_debugctlmsr(); |