diff options
Diffstat (limited to 'arch/x86/kernel')
-rw-r--r-- | arch/x86/kernel/apic/apic_numachip.c | 2 | ||||
-rw-r--r-- | arch/x86/kernel/apic/x2apic_uv_x.c | 2 | ||||
-rw-r--r-- | arch/x86/kernel/cpu/common.c | 4 | ||||
-rw-r--r-- | arch/x86/kernel/cpu/intel.c | 32 | ||||
-rw-r--r-- | arch/x86/kernel/cpu/mcheck/therm_throt.c | 4 | ||||
-rw-r--r-- | arch/x86/kernel/cpu/microcode/amd_early.c | 2 | ||||
-rw-r--r-- | arch/x86/kernel/cpu/microcode/intel.c | 4 | ||||
-rw-r--r-- | arch/x86/kernel/cpu/microcode/intel_early.c | 10 | ||||
-rw-r--r-- | arch/x86/kernel/cpu/mtrr/main.c | 6 | ||||
-rw-r--r-- | arch/x86/kernel/e820.c | 7 | ||||
-rw-r--r-- | arch/x86/kernel/entry_64.S | 51 | ||||
-rw-r--r-- | arch/x86/kernel/iosf_mbi.c | 91 | ||||
-rw-r--r-- | arch/x86/kernel/machine_kexec_32.c | 3 | ||||
-rw-r--r-- | arch/x86/kernel/pmc_atom.c | 11 | ||||
-rw-r--r-- | arch/x86/kernel/process.c | 16 | ||||
-rw-r--r-- | arch/x86/kernel/process_32.c | 6 | ||||
-rw-r--r-- | arch/x86/kernel/process_64.c | 3 | ||||
-rw-r--r-- | arch/x86/kernel/ptrace.c | 165 | ||||
-rw-r--r-- | arch/x86/kernel/quirks.c | 18 | ||||
-rw-r--r-- | arch/x86/kernel/setup.c | 9 | ||||
-rw-r--r-- | arch/x86/kernel/signal.c | 5 | ||||
-rw-r--r-- | arch/x86/kernel/vsyscall_64.c | 2 | ||||
-rw-r--r-- | arch/x86/kernel/xsave.c | 7 |
23 files changed, 351 insertions, 109 deletions
diff --git a/arch/x86/kernel/apic/apic_numachip.c b/arch/x86/kernel/apic/apic_numachip.c index ae915391ebec..4128b5fcb559 100644 --- a/arch/x86/kernel/apic/apic_numachip.c +++ b/arch/x86/kernel/apic/apic_numachip.c @@ -32,7 +32,7 @@ static int numachip_system __read_mostly; -static const struct apic apic_numachip __read_mostly; +static const struct apic apic_numachip; static unsigned int get_apic_id(unsigned long x) { diff --git a/arch/x86/kernel/apic/x2apic_uv_x.c b/arch/x86/kernel/apic/x2apic_uv_x.c index 004f017aa7b9..8e9dcfd630e4 100644 --- a/arch/x86/kernel/apic/x2apic_uv_x.c +++ b/arch/x86/kernel/apic/x2apic_uv_x.c @@ -204,7 +204,6 @@ EXPORT_SYMBOL(sn_rtc_cycles_per_second); static int uv_wakeup_secondary(int phys_apicid, unsigned long start_rip) { -#ifdef CONFIG_SMP unsigned long val; int pnode; @@ -223,7 +222,6 @@ static int uv_wakeup_secondary(int phys_apicid, unsigned long start_rip) uv_write_global_mmr64(pnode, UVH_IPI_INT, val); atomic_set(&init_deasserted, 1); -#endif return 0; } diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c index 8b699bff0099..3eff36f719fb 100644 --- a/arch/x86/kernel/cpu/common.c +++ b/arch/x86/kernel/cpu/common.c @@ -1186,7 +1186,7 @@ void syscall_init(void) /* Flags to clear on syscall */ wrmsrl(MSR_SYSCALL_MASK, X86_EFLAGS_TF|X86_EFLAGS_DF|X86_EFLAGS_IF| - X86_EFLAGS_IOPL|X86_EFLAGS_AC); + X86_EFLAGS_IOPL|X86_EFLAGS_AC|X86_EFLAGS_NT); } /* @@ -1400,7 +1400,7 @@ void cpu_init(void) printk(KERN_INFO "Initializing CPU#%d\n", cpu); - if (cpu_has_vme || cpu_has_tsc || cpu_has_de) + if (cpu_feature_enabled(X86_FEATURE_VME) || cpu_has_tsc || cpu_has_de) clear_in_cr4(X86_CR4_VME|X86_CR4_PVI|X86_CR4_TSD|X86_CR4_DE); load_current_idt(); diff --git a/arch/x86/kernel/cpu/intel.c b/arch/x86/kernel/cpu/intel.c index 74e804ddc5c7..1ef456273172 100644 --- a/arch/x86/kernel/cpu/intel.c +++ b/arch/x86/kernel/cpu/intel.c @@ -144,6 +144,21 @@ static void early_init_intel(struct cpuinfo_x86 *c) setup_clear_cpu_cap(X86_FEATURE_ERMS); } } + + /* + * Intel Quark Core DevMan_001.pdf section 6.4.11 + * "The operating system also is required to invalidate (i.e., flush) + * the TLB when any changes are made to any of the page table entries. + * The operating system must reload CR3 to cause the TLB to be flushed" + * + * As a result cpu_has_pge() in arch/x86/include/asm/tlbflush.h should + * be false so that __flush_tlb_all() causes CR3 insted of CR4.PGE + * to be modified + */ + if (c->x86 == 5 && c->x86_model == 9) { + pr_info("Disabling PGE capability bit\n"); + setup_clear_cpu_cap(X86_FEATURE_PGE); + } } #ifdef CONFIG_X86_32 @@ -382,6 +397,13 @@ static void init_intel(struct cpuinfo_x86 *c) } l2 = init_intel_cacheinfo(c); + + /* Detect legacy cache sizes if init_intel_cacheinfo did not */ + if (l2 == 0) { + cpu_detect_cache_sizes(c); + l2 = c->x86_cache_size; + } + if (c->cpuid_level > 9) { unsigned eax = cpuid_eax(10); /* Check for version and the number of counters */ @@ -485,6 +507,13 @@ static unsigned int intel_size_cache(struct cpuinfo_x86 *c, unsigned int size) */ if ((c->x86 == 6) && (c->x86_model == 11) && (size == 0)) size = 256; + + /* + * Intel Quark SoC X1000 contains a 4-way set associative + * 16K cache with a 16 byte cache line and 256 lines per tag + */ + if ((c->x86 == 5) && (c->x86_model == 9)) + size = 16; return size; } #endif @@ -686,7 +715,8 @@ static const struct cpu_dev intel_cpu_dev = { [3] = "OverDrive PODP5V83", [4] = "Pentium MMX", [7] = "Mobile Pentium 75 - 200", - [8] = "Mobile Pentium MMX" + [8] = "Mobile Pentium MMX", + [9] = "Quark SoC X1000", } }, { .family = 6, .model_names = diff --git a/arch/x86/kernel/cpu/mcheck/therm_throt.c b/arch/x86/kernel/cpu/mcheck/therm_throt.c index 36a1bb6d1ee0..1af51b1586d7 100644 --- a/arch/x86/kernel/cpu/mcheck/therm_throt.c +++ b/arch/x86/kernel/cpu/mcheck/therm_throt.c @@ -498,8 +498,8 @@ void intel_init_thermal(struct cpuinfo_x86 *c) if ((l & MSR_IA32_MISC_ENABLE_TM1) && (h & APIC_DM_SMI)) { - printk(KERN_DEBUG - "CPU%d: Thermal monitoring handled by SMI\n", cpu); + if (system_state == SYSTEM_BOOTING) + printk(KERN_DEBUG "CPU%d: Thermal monitoring handled by SMI\n", cpu); return; } diff --git a/arch/x86/kernel/cpu/microcode/amd_early.c b/arch/x86/kernel/cpu/microcode/amd_early.c index 617a9e284245..7aa1acc79789 100644 --- a/arch/x86/kernel/cpu/microcode/amd_early.c +++ b/arch/x86/kernel/cpu/microcode/amd_early.c @@ -27,7 +27,7 @@ static u32 ucode_new_rev; u8 amd_ucode_patch[PATCH_MAX_SIZE]; static u16 this_equiv_id; -struct cpio_data ucode_cpio; +static struct cpio_data ucode_cpio; /* * Microcode patch container file is prepended to the initrd in cpio format. diff --git a/arch/x86/kernel/cpu/microcode/intel.c b/arch/x86/kernel/cpu/microcode/intel.c index a276fa75d9b5..c6826d1e8082 100644 --- a/arch/x86/kernel/cpu/microcode/intel.c +++ b/arch/x86/kernel/cpu/microcode/intel.c @@ -127,7 +127,7 @@ static int get_matching_mc(struct microcode_intel *mc_intel, int cpu) return get_matching_microcode(csig, cpf, mc_intel, crev); } -int apply_microcode(int cpu) +static int apply_microcode_intel(int cpu) { struct microcode_intel *mc_intel; struct ucode_cpu_info *uci; @@ -314,7 +314,7 @@ static struct microcode_ops microcode_intel_ops = { .request_microcode_user = request_microcode_user, .request_microcode_fw = request_microcode_fw, .collect_cpu_info = collect_cpu_info, - .apply_microcode = apply_microcode, + .apply_microcode = apply_microcode_intel, .microcode_fini_cpu = microcode_fini_cpu, }; diff --git a/arch/x86/kernel/cpu/microcode/intel_early.c b/arch/x86/kernel/cpu/microcode/intel_early.c index 18f739129e72..b88343f7a3b3 100644 --- a/arch/x86/kernel/cpu/microcode/intel_early.c +++ b/arch/x86/kernel/cpu/microcode/intel_early.c @@ -28,8 +28,8 @@ #include <asm/tlbflush.h> #include <asm/setup.h> -unsigned long mc_saved_in_initrd[MAX_UCODE_COUNT]; -struct mc_saved_data { +static unsigned long mc_saved_in_initrd[MAX_UCODE_COUNT]; +static struct mc_saved_data { unsigned int mc_saved_count; struct microcode_intel **mc_saved; } mc_saved_data; @@ -415,7 +415,7 @@ static void __ref show_saved_mc(void) struct ucode_cpu_info uci; if (mc_saved_data.mc_saved_count == 0) { - pr_debug("no micorcode data saved.\n"); + pr_debug("no microcode data saved.\n"); return; } pr_debug("Total microcode saved: %d\n", mc_saved_data.mc_saved_count); @@ -506,7 +506,7 @@ int save_mc_for_early(u8 *mc) if (mc_saved && mc_saved_count) memcpy(mc_saved_tmp, mc_saved, - mc_saved_count * sizeof(struct mirocode_intel *)); + mc_saved_count * sizeof(struct microcode_intel *)); /* * Save the microcode patch mc in mc_save_tmp structure if it's a newer * version. @@ -526,7 +526,7 @@ int save_mc_for_early(u8 *mc) show_saved_mc(); /* - * Free old saved microcod data. + * Free old saved microcode data. */ if (mc_saved) { for (i = 0; i < mc_saved_count_init; i++) diff --git a/arch/x86/kernel/cpu/mtrr/main.c b/arch/x86/kernel/cpu/mtrr/main.c index f961de9964c7..ea5f363a1948 100644 --- a/arch/x86/kernel/cpu/mtrr/main.c +++ b/arch/x86/kernel/cpu/mtrr/main.c @@ -707,7 +707,7 @@ void __init mtrr_bp_init(void) } else { switch (boot_cpu_data.x86_vendor) { case X86_VENDOR_AMD: - if (cpu_has_k6_mtrr) { + if (cpu_feature_enabled(X86_FEATURE_K6_MTRR)) { /* Pre-Athlon (K6) AMD CPU MTRRs */ mtrr_if = mtrr_ops[X86_VENDOR_AMD]; size_or_mask = SIZE_OR_MASK_BITS(32); @@ -715,14 +715,14 @@ void __init mtrr_bp_init(void) } break; case X86_VENDOR_CENTAUR: - if (cpu_has_centaur_mcr) { + if (cpu_feature_enabled(X86_FEATURE_CENTAUR_MCR)) { mtrr_if = mtrr_ops[X86_VENDOR_CENTAUR]; size_or_mask = SIZE_OR_MASK_BITS(32); size_and_mask = 0; } break; case X86_VENDOR_CYRIX: - if (cpu_has_cyrix_arr) { + if (cpu_feature_enabled(X86_FEATURE_CYRIX_ARR)) { mtrr_if = mtrr_ops[X86_VENDOR_CYRIX]; size_or_mask = SIZE_OR_MASK_BITS(32); size_and_mask = 0; diff --git a/arch/x86/kernel/e820.c b/arch/x86/kernel/e820.c index 988c00a1f60d..49f886481615 100644 --- a/arch/x86/kernel/e820.c +++ b/arch/x86/kernel/e820.c @@ -682,15 +682,14 @@ void __init parse_e820_ext(u64 phys_addr, u32 data_len) * hibernation (32 bit) or software suspend and suspend to RAM (64 bit). * * This function requires the e820 map to be sorted and without any - * overlapping entries and assumes the first e820 area to be RAM. + * overlapping entries. */ void __init e820_mark_nosave_regions(unsigned long limit_pfn) { int i; - unsigned long pfn; + unsigned long pfn = 0; - pfn = PFN_DOWN(e820.map[0].addr + e820.map[0].size); - for (i = 1; i < e820.nr_map; i++) { + for (i = 0; i < e820.nr_map; i++) { struct e820entry *ei = &e820.map[i]; if (pfn < PFN_UP(ei->addr)) diff --git a/arch/x86/kernel/entry_64.S b/arch/x86/kernel/entry_64.S index 2fac1343a90b..df088bb03fb3 100644 --- a/arch/x86/kernel/entry_64.S +++ b/arch/x86/kernel/entry_64.S @@ -404,8 +404,8 @@ GLOBAL(system_call_after_swapgs) * and short: */ ENABLE_INTERRUPTS(CLBR_NONE) - SAVE_ARGS 8,0 - movq %rax,ORIG_RAX-ARGOFFSET(%rsp) + SAVE_ARGS 8, 0, rax_enosys=1 + movq_cfi rax,(ORIG_RAX-ARGOFFSET) movq %rcx,RIP-ARGOFFSET(%rsp) CFI_REL_OFFSET rip,RIP-ARGOFFSET testl $_TIF_WORK_SYSCALL_ENTRY,TI_flags+THREAD_INFO(%rsp,RIP-ARGOFFSET) @@ -417,7 +417,7 @@ system_call_fastpath: andl $__SYSCALL_MASK,%eax cmpl $__NR_syscall_max,%eax #endif - ja badsys + ja ret_from_sys_call /* and return regs->ax */ movq %r10,%rcx call *sys_call_table(,%rax,8) # XXX: rip relative movq %rax,RAX-ARGOFFSET(%rsp) @@ -476,28 +476,8 @@ sysret_signal: FIXUP_TOP_OF_STACK %r11, -ARGOFFSET jmp int_check_syscall_exit_work -badsys: - movq $-ENOSYS,RAX-ARGOFFSET(%rsp) - jmp ret_from_sys_call - #ifdef CONFIG_AUDITSYSCALL /* - * Fast path for syscall audit without full syscall trace. - * We just call __audit_syscall_entry() directly, and then - * jump back to the normal fast path. - */ -auditsys: - movq %r10,%r9 /* 6th arg: 4th syscall arg */ - movq %rdx,%r8 /* 5th arg: 3rd syscall arg */ - movq %rsi,%rcx /* 4th arg: 2nd syscall arg */ - movq %rdi,%rdx /* 3rd arg: 1st syscall arg */ - movq %rax,%rsi /* 2nd arg: syscall number */ - movl $AUDIT_ARCH_X86_64,%edi /* 1st arg: audit arch */ - call __audit_syscall_entry - LOAD_ARGS 0 /* reload call-clobbered registers */ - jmp system_call_fastpath - - /* * Return fast path for syscall audit. Call __audit_syscall_exit() * directly and then jump back to the fast path with TIF_SYSCALL_AUDIT * masked off. @@ -514,18 +494,25 @@ sysret_audit: /* Do syscall tracing */ tracesys: -#ifdef CONFIG_AUDITSYSCALL - testl $(_TIF_WORK_SYSCALL_ENTRY & ~_TIF_SYSCALL_AUDIT),TI_flags+THREAD_INFO(%rsp,RIP-ARGOFFSET) - jz auditsys -#endif + leaq -REST_SKIP(%rsp), %rdi + movq $AUDIT_ARCH_X86_64, %rsi + call syscall_trace_enter_phase1 + test %rax, %rax + jnz tracesys_phase2 /* if needed, run the slow path */ + LOAD_ARGS 0 /* else restore clobbered regs */ + jmp system_call_fastpath /* and return to the fast path */ + +tracesys_phase2: SAVE_REST - movq $-ENOSYS,RAX(%rsp) /* ptrace can change this for a bad syscall */ FIXUP_TOP_OF_STACK %rdi - movq %rsp,%rdi - call syscall_trace_enter + movq %rsp, %rdi + movq $AUDIT_ARCH_X86_64, %rsi + movq %rax,%rdx + call syscall_trace_enter_phase2 + /* * Reload arg registers from stack in case ptrace changed them. - * We don't reload %rax because syscall_trace_enter() returned + * We don't reload %rax because syscall_trace_entry_phase2() returned * the value it wants us to use in the table lookup. */ LOAD_ARGS ARGOFFSET, 1 @@ -536,7 +523,7 @@ tracesys: andl $__SYSCALL_MASK,%eax cmpl $__NR_syscall_max,%eax #endif - ja int_ret_from_sys_call /* RAX(%rsp) set to -ENOSYS above */ + ja int_ret_from_sys_call /* RAX(%rsp) is already set */ movq %r10,%rcx /* fixup for C */ call *sys_call_table(,%rax,8) movq %rax,RAX-ARGOFFSET(%rsp) diff --git a/arch/x86/kernel/iosf_mbi.c b/arch/x86/kernel/iosf_mbi.c index 9030e83db6ee..82f8d02f0df2 100644 --- a/arch/x86/kernel/iosf_mbi.c +++ b/arch/x86/kernel/iosf_mbi.c @@ -22,10 +22,13 @@ #include <linux/init.h> #include <linux/spinlock.h> #include <linux/pci.h> +#include <linux/debugfs.h> +#include <linux/capability.h> #include <asm/iosf_mbi.h> #define PCI_DEVICE_ID_BAYTRAIL 0x0F00 +#define PCI_DEVICE_ID_BRASWELL 0x2280 #define PCI_DEVICE_ID_QUARK_X1000 0x0958 static DEFINE_SPINLOCK(iosf_mbi_lock); @@ -187,6 +190,89 @@ bool iosf_mbi_available(void) } EXPORT_SYMBOL(iosf_mbi_available); +#ifdef CONFIG_IOSF_MBI_DEBUG +static u32 dbg_mdr; +static u32 dbg_mcr; +static u32 dbg_mcrx; + +static int mcr_get(void *data, u64 *val) +{ + *val = *(u32 *)data; + return 0; +} + +static int mcr_set(void *data, u64 val) +{ + u8 command = ((u32)val & 0xFF000000) >> 24, + port = ((u32)val & 0x00FF0000) >> 16, + offset = ((u32)val & 0x0000FF00) >> 8; + int err; + + *(u32 *)data = val; + + if (!capable(CAP_SYS_RAWIO)) + return -EACCES; + + if (command & 1u) + err = iosf_mbi_write(port, + command, + dbg_mcrx | offset, + dbg_mdr); + else + err = iosf_mbi_read(port, + command, + dbg_mcrx | offset, + &dbg_mdr); + + return err; +} +DEFINE_SIMPLE_ATTRIBUTE(iosf_mcr_fops, mcr_get, mcr_set , "%llx\n"); + +static struct dentry *iosf_dbg; + +static void iosf_sideband_debug_init(void) +{ + struct dentry *d; + + iosf_dbg = debugfs_create_dir("iosf_sb", NULL); + if (IS_ERR_OR_NULL(iosf_dbg)) + return; + + /* mdr */ + d = debugfs_create_x32("mdr", 0660, iosf_dbg, &dbg_mdr); + if (IS_ERR_OR_NULL(d)) + goto cleanup; + + /* mcrx */ + debugfs_create_x32("mcrx", 0660, iosf_dbg, &dbg_mcrx); + if (IS_ERR_OR_NULL(d)) + goto cleanup; + + /* mcr - initiates mailbox tranaction */ + debugfs_create_file("mcr", 0660, iosf_dbg, &dbg_mcr, &iosf_mcr_fops); + if (IS_ERR_OR_NULL(d)) + goto cleanup; + + return; + +cleanup: + debugfs_remove_recursive(d); +} + +static void iosf_debugfs_init(void) +{ + iosf_sideband_debug_init(); +} + +static void iosf_debugfs_remove(void) +{ + debugfs_remove_recursive(iosf_dbg); +} +#else +static inline void iosf_debugfs_init(void) { } +static inline void iosf_debugfs_remove(void) { } +#endif /* CONFIG_IOSF_MBI_DEBUG */ + static int iosf_mbi_probe(struct pci_dev *pdev, const struct pci_device_id *unused) { @@ -204,6 +290,7 @@ static int iosf_mbi_probe(struct pci_dev *pdev, static const struct pci_device_id iosf_mbi_pci_ids[] = { { PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_BAYTRAIL) }, + { PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_BRASWELL) }, { PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_QUARK_X1000) }, { 0, }, }; @@ -217,11 +304,15 @@ static struct pci_driver iosf_mbi_pci_driver = { static int __init iosf_mbi_init(void) { + iosf_debugfs_init(); + return pci_register_driver(&iosf_mbi_pci_driver); } static void __exit iosf_mbi_exit(void) { + iosf_debugfs_remove(); + pci_unregister_driver(&iosf_mbi_pci_driver); if (mbi_pdev) { pci_dev_put(mbi_pdev); diff --git a/arch/x86/kernel/machine_kexec_32.c b/arch/x86/kernel/machine_kexec_32.c index 1667b1de8d5d..72e8e310258d 100644 --- a/arch/x86/kernel/machine_kexec_32.c +++ b/arch/x86/kernel/machine_kexec_32.c @@ -247,7 +247,8 @@ void machine_kexec(struct kimage *image) /* now call it */ image->start = relocate_kernel_ptr((unsigned long)image->head, (unsigned long)page_list, - image->start, cpu_has_pae, + image->start, + boot_cpu_has(X86_FEATURE_PAE), image->preserve_context); #ifdef CONFIG_KEXEC_JUMP diff --git a/arch/x86/kernel/pmc_atom.c b/arch/x86/kernel/pmc_atom.c index 0c424a67985d..0ee5025e0fa4 100644 --- a/arch/x86/kernel/pmc_atom.c +++ b/arch/x86/kernel/pmc_atom.c @@ -235,6 +235,11 @@ err: pmc_dbgfs_unregister(pmc); return -ENODEV; } +#else +static int pmc_dbgfs_register(struct pmc_dev *pmc, struct pci_dev *pdev) +{ + return 0; +} #endif /* CONFIG_DEBUG_FS */ static int pmc_setup_dev(struct pci_dev *pdev) @@ -262,14 +267,12 @@ static int pmc_setup_dev(struct pci_dev *pdev) /* PMC hardware registers setup */ pmc_hw_reg_setup(pmc); -#ifdef CONFIG_DEBUG_FS ret = pmc_dbgfs_register(pmc, pdev); if (ret) { iounmap(pmc->regmap); - return ret; } -#endif /* CONFIG_DEBUG_FS */ - return 0; + + return ret; } /* diff --git a/arch/x86/kernel/process.c b/arch/x86/kernel/process.c index f804dc935d2a..e127ddaa2d5a 100644 --- a/arch/x86/kernel/process.c +++ b/arch/x86/kernel/process.c @@ -64,14 +64,16 @@ EXPORT_SYMBOL_GPL(task_xstate_cachep); */ int arch_dup_task_struct(struct task_struct *dst, struct task_struct *src) { - int ret; - *dst = *src; - if (fpu_allocated(&src->thread.fpu)) { - memset(&dst->thread.fpu, 0, sizeof(dst->thread.fpu)); - ret = fpu_alloc(&dst->thread.fpu); - if (ret) - return ret; + + dst->thread.fpu_counter = 0; + dst->thread.fpu.has_fpu = 0; + dst->thread.fpu.last_cpu = ~0; + dst->thread.fpu.state = NULL; + if (tsk_used_math(src)) { + int err = fpu_alloc(&dst->thread.fpu); + if (err) + return err; fpu_copy(dst, src); } return 0; diff --git a/arch/x86/kernel/process_32.c b/arch/x86/kernel/process_32.c index 7bc86bbe7485..8f3ebfe710d0 100644 --- a/arch/x86/kernel/process_32.c +++ b/arch/x86/kernel/process_32.c @@ -138,6 +138,7 @@ int copy_thread(unsigned long clone_flags, unsigned long sp, p->thread.sp = (unsigned long) childregs; p->thread.sp0 = (unsigned long) (childregs+1); + memset(p->thread.ptrace_bps, 0, sizeof(p->thread.ptrace_bps)); if (unlikely(p->flags & PF_KTHREAD)) { /* kernel thread */ @@ -152,9 +153,7 @@ int copy_thread(unsigned long clone_flags, unsigned long sp, childregs->orig_ax = -1; childregs->cs = __KERNEL_CS | get_kernel_rpl(); childregs->flags = X86_EFLAGS_IF | X86_EFLAGS_FIXED; - p->thread.fpu_counter = 0; p->thread.io_bitmap_ptr = NULL; - memset(p->thread.ptrace_bps, 0, sizeof(p->thread.ptrace_bps)); return 0; } *childregs = *current_pt_regs(); @@ -165,13 +164,10 @@ int copy_thread(unsigned long clone_flags, unsigned long sp, p->thread.ip = (unsigned long) ret_from_fork; task_user_gs(p) = get_user_gs(current_pt_regs()); - p->thread.fpu_counter = 0; p->thread.io_bitmap_ptr = NULL; tsk = current; err = -ENOMEM; - memset(p->thread.ptrace_bps, 0, sizeof(p->thread.ptrace_bps)); - if (unlikely(test_tsk_thread_flag(tsk, TIF_IO_BITMAP))) { p->thread.io_bitmap_ptr = kmemdup(tsk->thread.io_bitmap_ptr, IO_BITMAP_BYTES, GFP_KERNEL); diff --git a/arch/x86/kernel/process_64.c b/arch/x86/kernel/process_64.c index ca5b02d405c3..3ed4a68d4013 100644 --- a/arch/x86/kernel/process_64.c +++ b/arch/x86/kernel/process_64.c @@ -163,7 +163,6 @@ int copy_thread(unsigned long clone_flags, unsigned long sp, p->thread.sp = (unsigned long) childregs; p->thread.usersp = me->thread.usersp; set_tsk_thread_flag(p, TIF_FORK); - p->thread.fpu_counter = 0; p->thread.io_bitmap_ptr = NULL; savesegment(gs, p->thread.gsindex); @@ -193,8 +192,6 @@ int copy_thread(unsigned long clone_flags, unsigned long sp, childregs->sp = sp; err = -ENOMEM; - memset(p->thread.ptrace_bps, 0, sizeof(p->thread.ptrace_bps)); - if (unlikely(test_tsk_thread_flag(me, TIF_IO_BITMAP))) { p->thread.io_bitmap_ptr = kmemdup(me->thread.io_bitmap_ptr, IO_BITMAP_BYTES, GFP_KERNEL); diff --git a/arch/x86/kernel/ptrace.c b/arch/x86/kernel/ptrace.c index 678c0ada3b3c..29576c244699 100644 --- a/arch/x86/kernel/ptrace.c +++ b/arch/x86/kernel/ptrace.c @@ -1441,24 +1441,126 @@ void send_sigtrap(struct task_struct *tsk, struct pt_regs *regs, force_sig_info(SIGTRAP, &info, tsk); } - -#ifdef CONFIG_X86_32 -# define IS_IA32 1 -#elif defined CONFIG_IA32_EMULATION -# define IS_IA32 is_compat_task() -#else -# define IS_IA32 0 +static void do_audit_syscall_entry(struct pt_regs *regs, u32 arch) +{ +#ifdef CONFIG_X86_64 + if (arch == AUDIT_ARCH_X86_64) { + audit_syscall_entry(arch, regs->orig_ax, regs->di, + regs->si, regs->dx, regs->r10); + } else #endif + { + audit_syscall_entry(arch, regs->orig_ax, regs->bx, + regs->cx, regs->dx, regs->si); + } +} /* - * We must return the syscall number to actually look up in the table. - * This can be -1L to skip running any syscall at all. + * We can return 0 to resume the syscall or anything else to go to phase + * 2. If we resume the syscall, we need to put something appropriate in + * regs->orig_ax. + * + * NB: We don't have full pt_regs here, but regs->orig_ax and regs->ax + * are fully functional. + * + * For phase 2's benefit, our return value is: + * 0: resume the syscall + * 1: go to phase 2; no seccomp phase 2 needed + * anything else: go to phase 2; pass return value to seccomp */ -long syscall_trace_enter(struct pt_regs *regs) +unsigned long syscall_trace_enter_phase1(struct pt_regs *regs, u32 arch) +{ + unsigned long ret = 0; + u32 work; + + BUG_ON(regs != task_pt_regs(current)); + + work = ACCESS_ONCE(current_thread_info()->flags) & + _TIF_WORK_SYSCALL_ENTRY; + + /* + * If TIF_NOHZ is set, we are required to call user_exit() before + * doing anything that could touch RCU. + */ + if (work & _TIF_NOHZ) { + user_exit(); + work &= ~TIF_NOHZ; + } + +#ifdef CONFIG_SECCOMP + /* + * Do seccomp first -- it should minimize exposure of other + * code, and keeping seccomp fast is probably more valuable + * than the rest of this. + */ + if (work & _TIF_SECCOMP) { + struct seccomp_data sd; + + sd.arch = arch; + sd.nr = regs->orig_ax; + sd.instruction_pointer = regs->ip; +#ifdef CONFIG_X86_64 + if (arch == AUDIT_ARCH_X86_64) { + sd.args[0] = regs->di; + sd.args[1] = regs->si; + sd.args[2] = regs->dx; + sd.args[3] = regs->r10; + sd.args[4] = regs->r8; + sd.args[5] = regs->r9; + } else +#endif + { + sd.args[0] = regs->bx; + sd.args[1] = regs->cx; + sd.args[2] = regs->dx; + sd.args[3] = regs->si; + sd.args[4] = regs->di; + sd.args[5] = regs->bp; + } + + BUILD_BUG_ON(SECCOMP_PHASE1_OK != 0); + BUILD_BUG_ON(SECCOMP_PHASE1_SKIP != 1); + + ret = seccomp_phase1(&sd); + if (ret == SECCOMP_PHASE1_SKIP) { + regs->orig_ax = -1; + ret = 0; + } else if (ret != SECCOMP_PHASE1_OK) { + return ret; /* Go directly to phase 2 */ + } + + work &= ~_TIF_SECCOMP; + } +#endif + + /* Do our best to finish without phase 2. */ + if (work == 0) + return ret; /* seccomp and/or nohz only (ret == 0 here) */ + +#ifdef CONFIG_AUDITSYSCALL + if (work == _TIF_SYSCALL_AUDIT) { + /* + * If there is no more work to be done except auditing, + * then audit in phase 1. Phase 2 always audits, so, if + * we audit here, then we can't go on to phase 2. + */ + do_audit_syscall_entry(regs, arch); + return 0; + } +#endif + + return 1; /* Something is enabled that we can't handle in phase 1 */ +} + +/* Returns the syscall nr to run (which should match regs->orig_ax). */ +long syscall_trace_enter_phase2(struct pt_regs *regs, u32 arch, + unsigned long phase1_result) { long ret = 0; + u32 work = ACCESS_ONCE(current_thread_info()->flags) & + _TIF_WORK_SYSCALL_ENTRY; - user_exit(); + BUG_ON(regs != task_pt_regs(current)); /* * If we stepped into a sysenter/syscall insn, it trapped in @@ -1467,17 +1569,21 @@ long syscall_trace_enter(struct pt_regs *regs) * do_debug() and we need to set it again to restore the user * state. If we entered on the slow path, TF was already set. */ - if (test_thread_flag(TIF_SINGLESTEP)) + if (work & _TIF_SINGLESTEP) regs->flags |= X86_EFLAGS_TF; - /* do the secure computing check first */ - if (secure_computing(regs->orig_ax)) { +#ifdef CONFIG_SECCOMP + /* + * Call seccomp_phase2 before running the other hooks so that + * they can see any changes made by a seccomp tracer. + */ + if (phase1_result > 1 && seccomp_phase2(phase1_result)) { /* seccomp failures shouldn't expose any additional code. */ - ret = -1L; - goto out; + return -1; } +#endif - if (unlikely(test_thread_flag(TIF_SYSCALL_EMU))) + if (unlikely(work & _TIF_SYSCALL_EMU)) ret = -1L; if ((ret || test_thread_flag(TIF_SYSCALL_TRACE)) && @@ -1487,23 +1593,22 @@ long syscall_trace_enter(struct pt_regs *regs) if (unlikely(test_thread_flag(TIF_SYSCALL_TRACEPOINT))) trace_sys_enter(regs, regs->orig_ax); - if (IS_IA32) - audit_syscall_entry(AUDIT_ARCH_I386, - regs->orig_ax, - regs->bx, regs->cx, - regs->dx, regs->si); -#ifdef CONFIG_X86_64 - else - audit_syscall_entry(AUDIT_ARCH_X86_64, - regs->orig_ax, - regs->di, regs->si, - regs->dx, regs->r10); -#endif + do_audit_syscall_entry(regs, arch); -out: return ret ?: regs->orig_ax; } +long syscall_trace_enter(struct pt_regs *regs) +{ + u32 arch = is_ia32_task() ? AUDIT_ARCH_I386 : AUDIT_ARCH_X86_64; + unsigned long phase1_result = syscall_trace_enter_phase1(regs, arch); + + if (phase1_result == 0) + return regs->orig_ax; + else + return syscall_trace_enter_phase2(regs, arch, phase1_result); +} + void syscall_trace_leave(struct pt_regs *regs) { bool step; diff --git a/arch/x86/kernel/quirks.c b/arch/x86/kernel/quirks.c index ff898bbf579d..176a0f99d4da 100644 --- a/arch/x86/kernel/quirks.c +++ b/arch/x86/kernel/quirks.c @@ -498,6 +498,24 @@ void force_hpet_resume(void) } /* + * According to the datasheet e6xx systems have the HPET hardwired to + * 0xfed00000 + */ +static void e6xx_force_enable_hpet(struct pci_dev *dev) +{ + if (hpet_address || force_hpet_address) + return; + + force_hpet_address = 0xFED00000; + force_hpet_resume_type = NONE_FORCE_HPET_RESUME; + dev_printk(KERN_DEBUG, &dev->dev, "Force enabled HPET at " + "0x%lx\n", force_hpet_address); + return; +} +DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_E6XX_CU, + e6xx_force_enable_hpet); + +/* * HPET MSI on some boards (ATI SB700/SB800) has side effect on * floppy DMA. Disable HPET MSI on such platforms. * See erratum #27 (Misinterpreted MSI Requests May Result in diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c index 41ead8d3bc0b..235cfd39e0d7 100644 --- a/arch/x86/kernel/setup.c +++ b/arch/x86/kernel/setup.c @@ -879,6 +879,15 @@ void __init setup_arch(char **cmdline_p) KERNEL_PGD_PTRS); load_cr3(swapper_pg_dir); + /* + * Note: Quark X1000 CPUs advertise PGE incorrectly and require + * a cr3 based tlb flush, so the following __flush_tlb_all() + * will not flush anything because the cpu quirk which clears + * X86_FEATURE_PGE has not been invoked yet. Though due to the + * load_cr3() above the TLB has been flushed already. The + * quirk is invoked before subsequent calls to __flush_tlb_all() + * so proper operation is guaranteed. + */ __flush_tlb_all(); #else printk(KERN_INFO "Command line: %s\n", boot_command_line); diff --git a/arch/x86/kernel/signal.c b/arch/x86/kernel/signal.c index 2851d63c1202..ed37a768d0fc 100644 --- a/arch/x86/kernel/signal.c +++ b/arch/x86/kernel/signal.c @@ -675,6 +675,11 @@ handle_signal(struct ksignal *ksig, struct pt_regs *regs) * handler too. */ regs->flags &= ~(X86_EFLAGS_DF|X86_EFLAGS_RF|X86_EFLAGS_TF); + /* + * Ensure the signal handler starts with the new fpu state. + */ + if (used_math()) + drop_init_fpu(current); } signal_setup_done(failed, ksig, test_thread_flag(TIF_SINGLESTEP)); } diff --git a/arch/x86/kernel/vsyscall_64.c b/arch/x86/kernel/vsyscall_64.c index e1e1e80fc6a6..957779f4eb40 100644 --- a/arch/x86/kernel/vsyscall_64.c +++ b/arch/x86/kernel/vsyscall_64.c @@ -216,7 +216,7 @@ bool emulate_vsyscall(struct pt_regs *regs, unsigned long address) */ regs->orig_ax = syscall_nr; regs->ax = -ENOSYS; - tmp = secure_computing(syscall_nr); + tmp = secure_computing(); if ((!tmp && regs->orig_ax != syscall_nr) || regs->ip != address) { warn_bad_vsyscall(KERN_DEBUG, regs, "seccomp tried to change syscall nr or ip"); diff --git a/arch/x86/kernel/xsave.c b/arch/x86/kernel/xsave.c index 940b142cc11f..4c540c4719d8 100644 --- a/arch/x86/kernel/xsave.c +++ b/arch/x86/kernel/xsave.c @@ -271,8 +271,6 @@ int save_xstate_sig(void __user *buf, void __user *buf_fx, int size) if (use_fxsr() && save_xstate_epilog(buf_fx, ia32_fxstate)) return -1; - drop_init_fpu(tsk); /* trigger finit */ - return 0; } @@ -402,8 +400,11 @@ int __restore_xstate_sig(void __user *buf, void __user *buf_fx, int size) set_used_math(); } - if (use_eager_fpu()) + if (use_eager_fpu()) { + preempt_disable(); math_state_restore(); + preempt_enable(); + } return err; } else { |