diff options
Diffstat (limited to 'arch/x86/kernel')
-rw-r--r-- | arch/x86/kernel/alternative.c | 4 | ||||
-rw-r--r-- | arch/x86/kernel/cpu/feat_ctl.c | 1 | ||||
-rw-r--r-- | arch/x86/kernel/cpu/umwait.c | 1 | ||||
-rw-r--r-- | arch/x86/kernel/cpu/vmware.c | 229 | ||||
-rw-r--r-- | arch/x86/kernel/fpu/xstate.c | 75 | ||||
-rw-r--r-- | arch/x86/kernel/ioport.c | 1 | ||||
-rw-r--r-- | arch/x86/kernel/irqinit.c | 18 | ||||
-rw-r--r-- | arch/x86/kernel/jump_label.c | 2 | ||||
-rw-r--r-- | arch/x86/kernel/nmi.c | 4 | ||||
-rw-r--r-- | arch/x86/kernel/reboot.c | 2 | ||||
-rw-r--r-- | arch/x86/kernel/setup.c | 1 | ||||
-rw-r--r-- | arch/x86/kernel/signal.c | 399 | ||||
-rw-r--r-- | arch/x86/kernel/smpboot.c | 2 | ||||
-rw-r--r-- | arch/x86/kernel/stacktrace.c | 6 | ||||
-rw-r--r-- | arch/x86/kernel/time.c | 15 | ||||
-rw-r--r-- | arch/x86/kernel/tsc.c | 2 | ||||
-rw-r--r-- | arch/x86/kernel/tsc_sync.c | 2 | ||||
-rw-r--r-- | arch/x86/kernel/vm86_32.c | 115 | ||||
-rw-r--r-- | arch/x86/kernel/vmlinux.lds.S | 8 |
19 files changed, 531 insertions, 356 deletions
diff --git a/arch/x86/kernel/alternative.c b/arch/x86/kernel/alternative.c index 15ac0d5f4b40..7867dfb3963e 100644 --- a/arch/x86/kernel/alternative.c +++ b/arch/x86/kernel/alternative.c @@ -1167,8 +1167,8 @@ static void text_poke_bp_batch(struct text_poke_loc *tp, unsigned int nr_entries atomic_cond_read_acquire(&desc.refs, !VAL); } -void text_poke_loc_init(struct text_poke_loc *tp, void *addr, - const void *opcode, size_t len, const void *emulate) +static void text_poke_loc_init(struct text_poke_loc *tp, void *addr, + const void *opcode, size_t len, const void *emulate) { struct insn insn; diff --git a/arch/x86/kernel/cpu/feat_ctl.c b/arch/x86/kernel/cpu/feat_ctl.c index 0268185bef94..29a3bedabd06 100644 --- a/arch/x86/kernel/cpu/feat_ctl.c +++ b/arch/x86/kernel/cpu/feat_ctl.c @@ -5,6 +5,7 @@ #include <asm/msr-index.h> #include <asm/processor.h> #include <asm/vmx.h> +#include "cpu.h" #undef pr_fmt #define pr_fmt(fmt) "x86/cpu: " fmt diff --git a/arch/x86/kernel/cpu/umwait.c b/arch/x86/kernel/cpu/umwait.c index c222f283b456..300e3fd5ade3 100644 --- a/arch/x86/kernel/cpu/umwait.c +++ b/arch/x86/kernel/cpu/umwait.c @@ -4,6 +4,7 @@ #include <linux/cpu.h> #include <asm/msr.h> +#include <asm/mwait.h> #define UMWAIT_C02_ENABLE 0 diff --git a/arch/x86/kernel/cpu/vmware.c b/arch/x86/kernel/cpu/vmware.c index 46d732696c1c..9b6fafa69be9 100644 --- a/arch/x86/kernel/cpu/vmware.c +++ b/arch/x86/kernel/cpu/vmware.c @@ -25,6 +25,8 @@ #include <linux/init.h> #include <linux/export.h> #include <linux/clocksource.h> +#include <linux/cpu.h> +#include <linux/reboot.h> #include <asm/div64.h> #include <asm/x86_init.h> #include <asm/hypervisor.h> @@ -47,6 +49,11 @@ #define VMWARE_CMD_GETVCPU_INFO 68 #define VMWARE_CMD_LEGACY_X2APIC 3 #define VMWARE_CMD_VCPU_RESERVED 31 +#define VMWARE_CMD_STEALCLOCK 91 + +#define STEALCLOCK_NOT_AVAILABLE (-1) +#define STEALCLOCK_DISABLED 0 +#define STEALCLOCK_ENABLED 1 #define VMWARE_PORT(cmd, eax, ebx, ecx, edx) \ __asm__("inl (%%dx), %%eax" : \ @@ -86,6 +93,18 @@ } \ } while (0) +struct vmware_steal_time { + union { + uint64_t clock; /* stolen time counter in units of vtsc */ + struct { + /* only for little-endian */ + uint32_t clock_low; + uint32_t clock_high; + }; + }; + uint64_t reserved[7]; +}; + static unsigned long vmware_tsc_khz __ro_after_init; static u8 vmware_hypercall_mode __ro_after_init; @@ -103,15 +122,25 @@ static unsigned long vmware_get_tsc_khz(void) #ifdef CONFIG_PARAVIRT static struct cyc2ns_data vmware_cyc2ns __ro_after_init; -static int vmw_sched_clock __initdata = 1; +static bool vmw_sched_clock __initdata = true; +static DEFINE_PER_CPU_DECRYPTED(struct vmware_steal_time, vmw_steal_time) __aligned(64); +static bool has_steal_clock; +static bool steal_acc __initdata = true; /* steal time accounting */ static __init int setup_vmw_sched_clock(char *s) { - vmw_sched_clock = 0; + vmw_sched_clock = false; return 0; } early_param("no-vmw-sched-clock", setup_vmw_sched_clock); +static __init int parse_no_stealacc(char *arg) +{ + steal_acc = false; + return 0; +} +early_param("no-steal-acc", parse_no_stealacc); + static unsigned long long notrace vmware_sched_clock(void) { unsigned long long ns; @@ -122,7 +151,7 @@ static unsigned long long notrace vmware_sched_clock(void) return ns; } -static void __init vmware_sched_clock_setup(void) +static void __init vmware_cyc2ns_setup(void) { struct cyc2ns_data *d = &vmware_cyc2ns; unsigned long long tsc_now = rdtsc(); @@ -132,17 +161,201 @@ static void __init vmware_sched_clock_setup(void) d->cyc2ns_offset = mul_u64_u32_shr(tsc_now, d->cyc2ns_mul, d->cyc2ns_shift); - pv_ops.time.sched_clock = vmware_sched_clock; - pr_info("using sched offset of %llu ns\n", d->cyc2ns_offset); + pr_info("using clock offset of %llu ns\n", d->cyc2ns_offset); +} + +static int vmware_cmd_stealclock(uint32_t arg1, uint32_t arg2) +{ + uint32_t result, info; + + asm volatile (VMWARE_HYPERCALL : + "=a"(result), + "=c"(info) : + "a"(VMWARE_HYPERVISOR_MAGIC), + "b"(0), + "c"(VMWARE_CMD_STEALCLOCK), + "d"(0), + "S"(arg1), + "D"(arg2) : + "memory"); + return result; +} + +static bool stealclock_enable(phys_addr_t pa) +{ + return vmware_cmd_stealclock(upper_32_bits(pa), + lower_32_bits(pa)) == STEALCLOCK_ENABLED; +} + +static int __stealclock_disable(void) +{ + return vmware_cmd_stealclock(0, 1); +} + +static void stealclock_disable(void) +{ + __stealclock_disable(); +} + +static bool vmware_is_stealclock_available(void) +{ + return __stealclock_disable() != STEALCLOCK_NOT_AVAILABLE; +} + +/** + * vmware_steal_clock() - read the per-cpu steal clock + * @cpu: the cpu number whose steal clock we want to read + * + * The function reads the steal clock if we are on a 64-bit system, otherwise + * reads it in parts, checking that the high part didn't change in the + * meantime. + * + * Return: + * The steal clock reading in ns. + */ +static uint64_t vmware_steal_clock(int cpu) +{ + struct vmware_steal_time *steal = &per_cpu(vmw_steal_time, cpu); + uint64_t clock; + + if (IS_ENABLED(CONFIG_64BIT)) + clock = READ_ONCE(steal->clock); + else { + uint32_t initial_high, low, high; + + do { + initial_high = READ_ONCE(steal->clock_high); + /* Do not reorder initial_high and high readings */ + virt_rmb(); + low = READ_ONCE(steal->clock_low); + /* Keep low reading in between */ + virt_rmb(); + high = READ_ONCE(steal->clock_high); + } while (initial_high != high); + + clock = ((uint64_t)high << 32) | low; + } + + return mul_u64_u32_shr(clock, vmware_cyc2ns.cyc2ns_mul, + vmware_cyc2ns.cyc2ns_shift); +} + +static void vmware_register_steal_time(void) +{ + int cpu = smp_processor_id(); + struct vmware_steal_time *st = &per_cpu(vmw_steal_time, cpu); + + if (!has_steal_clock) + return; + + if (!stealclock_enable(slow_virt_to_phys(st))) { + has_steal_clock = false; + return; + } + + pr_info("vmware-stealtime: cpu %d, pa %llx\n", + cpu, (unsigned long long) slow_virt_to_phys(st)); } +static void vmware_disable_steal_time(void) +{ + if (!has_steal_clock) + return; + + stealclock_disable(); +} + +static void vmware_guest_cpu_init(void) +{ + if (has_steal_clock) + vmware_register_steal_time(); +} + +static void vmware_pv_guest_cpu_reboot(void *unused) +{ + vmware_disable_steal_time(); +} + +static int vmware_pv_reboot_notify(struct notifier_block *nb, + unsigned long code, void *unused) +{ + if (code == SYS_RESTART) + on_each_cpu(vmware_pv_guest_cpu_reboot, NULL, 1); + return NOTIFY_DONE; +} + +static struct notifier_block vmware_pv_reboot_nb = { + .notifier_call = vmware_pv_reboot_notify, +}; + +#ifdef CONFIG_SMP +static void __init vmware_smp_prepare_boot_cpu(void) +{ + vmware_guest_cpu_init(); + native_smp_prepare_boot_cpu(); +} + +static int vmware_cpu_online(unsigned int cpu) +{ + local_irq_disable(); + vmware_guest_cpu_init(); + local_irq_enable(); + return 0; +} + +static int vmware_cpu_down_prepare(unsigned int cpu) +{ + local_irq_disable(); + vmware_disable_steal_time(); + local_irq_enable(); + return 0; +} +#endif + +static __init int activate_jump_labels(void) +{ + if (has_steal_clock) { + static_key_slow_inc(¶virt_steal_enabled); + if (steal_acc) + static_key_slow_inc(¶virt_steal_rq_enabled); + } + + return 0; +} +arch_initcall(activate_jump_labels); + static void __init vmware_paravirt_ops_setup(void) { pv_info.name = "VMware hypervisor"; pv_ops.cpu.io_delay = paravirt_nop; - if (vmware_tsc_khz && vmw_sched_clock) - vmware_sched_clock_setup(); + if (vmware_tsc_khz == 0) + return; + + vmware_cyc2ns_setup(); + + if (vmw_sched_clock) + pv_ops.time.sched_clock = vmware_sched_clock; + + if (vmware_is_stealclock_available()) { + has_steal_clock = true; + pv_ops.time.steal_clock = vmware_steal_clock; + + /* We use reboot notifier only to disable steal clock */ + register_reboot_notifier(&vmware_pv_reboot_nb); + +#ifdef CONFIG_SMP + smp_ops.smp_prepare_boot_cpu = + vmware_smp_prepare_boot_cpu; + if (cpuhp_setup_state_nocalls(CPUHP_AP_ONLINE_DYN, + "x86/vmware:online", + vmware_cpu_online, + vmware_cpu_down_prepare) < 0) + pr_err("vmware_guest: Failed to install cpu hotplug callbacks\n"); +#else + vmware_guest_cpu_init(); +#endif + } } #else #define vmware_paravirt_ops_setup() do {} while (0) @@ -213,7 +426,7 @@ static void __init vmware_platform_setup(void) vmware_set_capabilities(); } -static u8 vmware_select_hypercall(void) +static u8 __init vmware_select_hypercall(void) { int eax, ebx, ecx, edx; diff --git a/arch/x86/kernel/fpu/xstate.c b/arch/x86/kernel/fpu/xstate.c index a1806598aaa4..32b153d38748 100644 --- a/arch/x86/kernel/fpu/xstate.c +++ b/arch/x86/kernel/fpu/xstate.c @@ -120,11 +120,6 @@ static bool xfeature_is_supervisor(int xfeature_nr) return ecx & 1; } -static bool xfeature_is_user(int xfeature_nr) -{ - return !xfeature_is_supervisor(xfeature_nr); -} - /* * When executing XSAVEOPT (or other optimized XSAVE instructions), if * a processor implementation detects that an FPU state component is still @@ -265,21 +260,25 @@ static void __init setup_xstate_features(void) cpuid_count(XSTATE_CPUID, i, &eax, &ebx, &ecx, &edx); + xstate_sizes[i] = eax; + /* - * If an xfeature is supervisor state, the offset - * in EBX is invalid. We leave it to -1. + * If an xfeature is supervisor state, the offset in EBX is + * invalid, leave it to -1. */ - if (xfeature_is_user(i)) - xstate_offsets[i] = ebx; + if (xfeature_is_supervisor(i)) + continue; + + xstate_offsets[i] = ebx; - xstate_sizes[i] = eax; /* - * In our xstate size checks, we assume that the - * highest-numbered xstate feature has the - * highest offset in the buffer. Ensure it does. + * In our xstate size checks, we assume that the highest-numbered + * xstate feature has the highest offset in the buffer. Ensure + * it does. */ WARN_ONCE(last_good_offset > xstate_offsets[i], - "x86/fpu: misordered xstate at %d\n", last_good_offset); + "x86/fpu: misordered xstate at %d\n", last_good_offset); + last_good_offset = xstate_offsets[i]; } } @@ -326,6 +325,13 @@ static int xfeature_is_aligned(int xfeature_nr) u32 eax, ebx, ecx, edx; CHECK_XFEATURE(xfeature_nr); + + if (!xfeature_enabled(xfeature_nr)) { + WARN_ONCE(1, "Checking alignment of disabled xfeature %d\n", + xfeature_nr); + return 0; + } + cpuid_count(XSTATE_CPUID, xfeature_nr, &eax, &ebx, &ecx, &edx); /* * The value returned by ECX[1] indicates the alignment @@ -338,11 +344,11 @@ static int xfeature_is_aligned(int xfeature_nr) /* * This function sets up offsets and sizes of all extended states in * xsave area. This supports both standard format and compacted format - * of the xsave aread. + * of the xsave area. */ -static void __init setup_xstate_comp(void) +static void __init setup_xstate_comp_offsets(void) { - unsigned int xstate_comp_sizes[XFEATURE_MAX]; + unsigned int next_offset; int i; /* @@ -356,31 +362,23 @@ static void __init setup_xstate_comp(void) if (!boot_cpu_has(X86_FEATURE_XSAVES)) { for (i = FIRST_EXTENDED_XFEATURE; i < XFEATURE_MAX; i++) { - if (xfeature_enabled(i)) { + if (xfeature_enabled(i)) xstate_comp_offsets[i] = xstate_offsets[i]; - xstate_comp_sizes[i] = xstate_sizes[i]; - } } return; } - xstate_comp_offsets[FIRST_EXTENDED_XFEATURE] = - FXSAVE_SIZE + XSAVE_HDR_SIZE; + next_offset = FXSAVE_SIZE + XSAVE_HDR_SIZE; for (i = FIRST_EXTENDED_XFEATURE; i < XFEATURE_MAX; i++) { - if (xfeature_enabled(i)) - xstate_comp_sizes[i] = xstate_sizes[i]; - else - xstate_comp_sizes[i] = 0; + if (!xfeature_enabled(i)) + continue; - if (i > FIRST_EXTENDED_XFEATURE) { - xstate_comp_offsets[i] = xstate_comp_offsets[i-1] - + xstate_comp_sizes[i-1]; + if (xfeature_is_aligned(i)) + next_offset = ALIGN(next_offset, 64); - if (xfeature_is_aligned(i)) - xstate_comp_offsets[i] = - ALIGN(xstate_comp_offsets[i], 64); - } + xstate_comp_offsets[i] = next_offset; + next_offset += xstate_sizes[i]; } } @@ -774,7 +772,7 @@ void __init fpu__init_system_xstate(void) fpu__init_prepare_fx_sw_frame(); setup_init_fpu_buf(); - setup_xstate_comp(); + setup_xstate_comp_offsets(); print_xstate_offset_size(); pr_info("x86/fpu: Enabled xstate features 0x%llx, context size is %d bytes, using '%s' format.\n", @@ -897,8 +895,6 @@ const void *get_xsave_field_ptr(int xfeature_nr) #ifdef CONFIG_ARCH_HAS_PKEYS -#define NR_VALID_PKRU_BITS (CONFIG_NR_PROTECTION_KEYS * 2) -#define PKRU_VALID_MASK (NR_VALID_PKRU_BITS - 1) /* * This will go out and modify PKRU register to set the access * rights for @pkey to @init_val. @@ -917,6 +913,13 @@ int arch_set_user_pkey_access(struct task_struct *tsk, int pkey, if (!boot_cpu_has(X86_FEATURE_OSPKE)) return -EINVAL; + /* + * This code should only be called with valid 'pkey' + * values originating from in-kernel users. Complain + * if a bad value is observed. + */ + WARN_ON_ONCE(pkey >= arch_max_pkey()); + /* Set the bits we need in PKRU: */ if (init_val & PKEY_DISABLE_ACCESS) new_pkru_bits |= PKRU_AD_BIT; diff --git a/arch/x86/kernel/ioport.c b/arch/x86/kernel/ioport.c index 8abeee0dd7bf..a53e7b4a7419 100644 --- a/arch/x86/kernel/ioport.c +++ b/arch/x86/kernel/ioport.c @@ -13,6 +13,7 @@ #include <asm/io_bitmap.h> #include <asm/desc.h> +#include <asm/syscalls.h> #ifdef CONFIG_X86_IOPL_IOPERM diff --git a/arch/x86/kernel/irqinit.c b/arch/x86/kernel/irqinit.c index 16919a9671fa..5aa523c2d573 100644 --- a/arch/x86/kernel/irqinit.c +++ b/arch/x86/kernel/irqinit.c @@ -44,15 +44,6 @@ * (these are usually mapped into the 0x30-0xff vector range) */ -/* - * IRQ2 is cascade interrupt to second interrupt controller - */ -static struct irqaction irq2 = { - .handler = no_action, - .name = "cascade", - .flags = IRQF_NO_THREAD, -}; - DEFINE_PER_CPU(vector_irq_t, vector_irq) = { [0 ... NR_VECTORS - 1] = VECTOR_UNUSED, }; @@ -84,7 +75,7 @@ void __init init_IRQ(void) * On cpu 0, Assign ISA_IRQ_VECTOR(irq) to IRQ 0..15. * If these IRQ's are handled by legacy interrupt-controllers like PIC, * then this configuration will likely be static after the boot. If - * these IRQ's are handled by more mordern controllers like IO-APIC, + * these IRQs are handled by more modern controllers like IO-APIC, * then this vector space can be freed and re-used dynamically as the * irq's migrate etc. */ @@ -104,6 +95,9 @@ void __init native_init_IRQ(void) idt_setup_apic_and_irq_gates(); lapic_assign_system_vectors(); - if (!acpi_ioapic && !of_ioapic && nr_legacy_irqs()) - setup_irq(2, &irq2); + if (!acpi_ioapic && !of_ioapic && nr_legacy_irqs()) { + /* IRQ2 is cascade interrupt to second interrupt controller */ + if (request_irq(2, no_action, IRQF_NO_THREAD, "cascade", NULL)) + pr_err("%s: request_irq() failed\n", "cascade"); + } } diff --git a/arch/x86/kernel/jump_label.c b/arch/x86/kernel/jump_label.c index 9c4498ea0b3c..5ba8477c2cb7 100644 --- a/arch/x86/kernel/jump_label.c +++ b/arch/x86/kernel/jump_label.c @@ -58,7 +58,7 @@ __jump_label_set_jump_code(struct jump_entry *entry, enum jump_label_type type, return code; } -static void inline __jump_label_transform(struct jump_entry *entry, +static inline void __jump_label_transform(struct jump_entry *entry, enum jump_label_type type, int init) { diff --git a/arch/x86/kernel/nmi.c b/arch/x86/kernel/nmi.c index 54c21d6abd5a..6407ea21fa1b 100644 --- a/arch/x86/kernel/nmi.c +++ b/arch/x86/kernel/nmi.c @@ -403,9 +403,9 @@ static void default_do_nmi(struct pt_regs *regs) * a 'real' unknown NMI. For example, while processing * a perf NMI another perf NMI comes in along with a * 'real' unknown NMI. These two NMIs get combined into - * one (as descibed above). When the next NMI gets + * one (as described above). When the next NMI gets * processed, it will be flagged by perf as handled, but - * noone will know that there was a 'real' unknown NMI sent + * no one will know that there was a 'real' unknown NMI sent * also. As a result it gets swallowed. Or if the first * perf NMI returns two events handled then the second * NMI will get eaten by the logic below, again losing a diff --git a/arch/x86/kernel/reboot.c b/arch/x86/kernel/reboot.c index 0cc7c0b106bb..3ca43be4f9cf 100644 --- a/arch/x86/kernel/reboot.c +++ b/arch/x86/kernel/reboot.c @@ -531,7 +531,7 @@ static void emergency_vmx_disable_all(void) /* * We need to disable VMX on all CPUs before rebooting, otherwise - * we risk hanging up the machine, because the CPU ignore INIT + * we risk hanging up the machine, because the CPU ignores INIT * signals when VMX is enabled. * * We can't take any locks and we may be on an inconsistent diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c index a74262c71484..e6b545047f38 100644 --- a/arch/x86/kernel/setup.c +++ b/arch/x86/kernel/setup.c @@ -64,7 +64,6 @@ RESERVE_BRK(dmi_alloc, 65536); * at link time, with RESERVE_BRK*() facility reserving additional * chunks. */ -static __initdata unsigned long _brk_start = (unsigned long)__brk_base; unsigned long _brk_end = (unsigned long)__brk_base; diff --git a/arch/x86/kernel/signal.c b/arch/x86/kernel/signal.c index 0364f8c3bee3..83b74fb38c8f 100644 --- a/arch/x86/kernel/signal.c +++ b/arch/x86/kernel/signal.c @@ -45,24 +45,6 @@ #include <asm/sigframe.h> #include <asm/signal.h> -#define COPY(x) do { \ - get_user_ex(regs->x, &sc->x); \ -} while (0) - -#define GET_SEG(seg) ({ \ - unsigned short tmp; \ - get_user_ex(tmp, &sc->seg); \ - tmp; \ -}) - -#define COPY_SEG(seg) do { \ - regs->seg = GET_SEG(seg); \ -} while (0) - -#define COPY_SEG_CPL3(seg) do { \ - regs->seg = GET_SEG(seg) | 3; \ -} while (0) - #ifdef CONFIG_X86_64 /* * If regs->ss will cause an IRET fault, change it. Otherwise leave it @@ -90,53 +72,58 @@ static void force_valid_ss(struct pt_regs *regs) ar != (AR_DPL3 | AR_S | AR_P | AR_TYPE_RWDATA_EXPDOWN)) regs->ss = __USER_DS; } +# define CONTEXT_COPY_SIZE offsetof(struct sigcontext, reserved1) +#else +# define CONTEXT_COPY_SIZE sizeof(struct sigcontext) #endif static int restore_sigcontext(struct pt_regs *regs, - struct sigcontext __user *sc, + struct sigcontext __user *usc, unsigned long uc_flags) { - unsigned long buf_val; - void __user *buf; - unsigned int tmpflags; - unsigned int err = 0; + struct sigcontext sc; /* Always make any pending restarted system calls return -EINTR */ current->restart_block.fn = do_no_restart_syscall; - get_user_try { + if (copy_from_user(&sc, usc, CONTEXT_COPY_SIZE)) + return -EFAULT; #ifdef CONFIG_X86_32 - set_user_gs(regs, GET_SEG(gs)); - COPY_SEG(fs); - COPY_SEG(es); - COPY_SEG(ds); + set_user_gs(regs, sc.gs); + regs->fs = sc.fs; + regs->es = sc.es; + regs->ds = sc.ds; #endif /* CONFIG_X86_32 */ - COPY(di); COPY(si); COPY(bp); COPY(sp); COPY(bx); - COPY(dx); COPY(cx); COPY(ip); COPY(ax); + regs->bx = sc.bx; + regs->cx = sc.cx; + regs->dx = sc.dx; + regs->si = sc.si; + regs->di = sc.di; + regs->bp = sc.bp; + regs->ax = sc.ax; + regs->sp = sc.sp; + regs->ip = sc.ip; #ifdef CONFIG_X86_64 - COPY(r8); - COPY(r9); - COPY(r10); - COPY(r11); - COPY(r12); - COPY(r13); - COPY(r14); - COPY(r15); + regs->r8 = sc.r8; + regs->r9 = sc.r9; + regs->r10 = sc.r10; + regs->r11 = sc.r11; + regs->r12 = sc.r12; + regs->r13 = sc.r13; + regs->r14 = sc.r14; + regs->r15 = sc.r15; #endif /* CONFIG_X86_64 */ - COPY_SEG_CPL3(cs); - COPY_SEG_CPL3(ss); - - get_user_ex(tmpflags, &sc->flags); - regs->flags = (regs->flags & ~FIX_EFLAGS) | (tmpflags & FIX_EFLAGS); - regs->orig_ax = -1; /* disable syscall checks */ + /* Get CS/SS and force CPL3 */ + regs->cs = sc.cs | 0x03; + regs->ss = sc.ss | 0x03; - get_user_ex(buf_val, &sc->fpstate); - buf = (void __user *)buf_val; - } get_user_catch(err); + regs->flags = (regs->flags & ~FIX_EFLAGS) | (sc.flags & FIX_EFLAGS); + /* disable syscall checks */ + regs->orig_ax = -1; #ifdef CONFIG_X86_64 /* @@ -147,70 +134,78 @@ static int restore_sigcontext(struct pt_regs *regs, force_valid_ss(regs); #endif - err |= fpu__restore_sig(buf, IS_ENABLED(CONFIG_X86_32)); - - return err; + return fpu__restore_sig((void __user *)sc.fpstate, + IS_ENABLED(CONFIG_X86_32)); } -int setup_sigcontext(struct sigcontext __user *sc, void __user *fpstate, +static __always_inline int +__unsafe_setup_sigcontext(struct sigcontext __user *sc, void __user *fpstate, struct pt_regs *regs, unsigned long mask) { - int err = 0; - - put_user_try { - #ifdef CONFIG_X86_32 - put_user_ex(get_user_gs(regs), (unsigned int __user *)&sc->gs); - put_user_ex(regs->fs, (unsigned int __user *)&sc->fs); - put_user_ex(regs->es, (unsigned int __user *)&sc->es); - put_user_ex(regs->ds, (unsigned int __user *)&sc->ds); + unsafe_put_user(get_user_gs(regs), + (unsigned int __user *)&sc->gs, Efault); + unsafe_put_user(regs->fs, (unsigned int __user *)&sc->fs, Efault); + unsafe_put_user(regs->es, (unsigned int __user *)&sc->es, Efault); + unsafe_put_user(regs->ds, (unsigned int __user *)&sc->ds, Efault); #endif /* CONFIG_X86_32 */ - put_user_ex(regs->di, &sc->di); - put_user_ex(regs->si, &sc->si); - put_user_ex(regs->bp, &sc->bp); - put_user_ex(regs->sp, &sc->sp); - put_user_ex(regs->bx, &sc->bx); - put_user_ex(regs->dx, &sc->dx); - put_user_ex(regs->cx, &sc->cx); - put_user_ex(regs->ax, &sc->ax); + unsafe_put_user(regs->di, &sc->di, Efault); + unsafe_put_user(regs->si, &sc->si, Efault); + unsafe_put_user(regs->bp, &sc->bp, Efault); + unsafe_put_user(regs->sp, &sc->sp, Efault); + unsafe_put_user(regs->bx, &sc->bx, Efault); + unsafe_put_user(regs->dx, &sc->dx, Efault); + unsafe_put_user(regs->cx, &sc->cx, Efault); + unsafe_put_user(regs->ax, &sc->ax, Efault); #ifdef CONFIG_X86_64 - put_user_ex(regs->r8, &sc->r8); - put_user_ex(regs->r9, &sc->r9); - put_user_ex(regs->r10, &sc->r10); - put_user_ex(regs->r11, &sc->r11); - put_user_ex(regs->r12, &sc->r12); - put_user_ex(regs->r13, &sc->r13); - put_user_ex(regs->r14, &sc->r14); - put_user_ex(regs->r15, &sc->r15); + unsafe_put_user(regs->r8, &sc->r8, Efault); + unsafe_put_user(regs->r9, &sc->r9, Efault); + unsafe_put_user(regs->r10, &sc->r10, Efault); + unsafe_put_user(regs->r11, &sc->r11, Efault); + unsafe_put_user(regs->r12, &sc->r12, Efault); + unsafe_put_user(regs->r13, &sc->r13, Efault); + unsafe_put_user(regs->r14, &sc->r14, Efault); + unsafe_put_user(regs->r15, &sc->r15, Efault); #endif /* CONFIG_X86_64 */ - put_user_ex(current->thread.trap_nr, &sc->trapno); - put_user_ex(current->thread.error_code, &sc->err); - put_user_ex(regs->ip, &sc->ip); + unsafe_put_user(current->thread.trap_nr, &sc->trapno, Efault); + unsafe_put_user(current->thread.error_code, &sc->err, Efault); + unsafe_put_user(regs->ip, &sc->ip, Efault); #ifdef CONFIG_X86_32 - put_user_ex(regs->cs, (unsigned int __user *)&sc->cs); - put_user_ex(regs->flags, &sc->flags); - put_user_ex(regs->sp, &sc->sp_at_signal); - put_user_ex(regs->ss, (unsigned int __user *)&sc->ss); + unsafe_put_user(regs->cs, (unsigned int __user *)&sc->cs, Efault); + unsafe_put_user(regs->flags, &sc->flags, Efault); + unsafe_put_user(regs->sp, &sc->sp_at_signal, Efault); + unsafe_put_user(regs->ss, (unsigned int __user *)&sc->ss, Efault); #else /* !CONFIG_X86_32 */ - put_user_ex(regs->flags, &sc->flags); - put_user_ex(regs->cs, &sc->cs); - put_user_ex(0, &sc->gs); - put_user_ex(0, &sc->fs); - put_user_ex(regs->ss, &sc->ss); + unsafe_put_user(regs->flags, &sc->flags, Efault); + unsafe_put_user(regs->cs, &sc->cs, Efault); + unsafe_put_user(0, &sc->gs, Efault); + unsafe_put_user(0, &sc->fs, Efault); + unsafe_put_user(regs->ss, &sc->ss, Efault); #endif /* CONFIG_X86_32 */ - put_user_ex(fpstate, (unsigned long __user *)&sc->fpstate); + unsafe_put_user(fpstate, (unsigned long __user *)&sc->fpstate, Efault); - /* non-iBCS2 extensions.. */ - put_user_ex(mask, &sc->oldmask); - put_user_ex(current->thread.cr2, &sc->cr2); - } put_user_catch(err); - - return err; + /* non-iBCS2 extensions.. */ + unsafe_put_user(mask, &sc->oldmask, Efault); + unsafe_put_user(current->thread.cr2, &sc->cr2, Efault); + return 0; +Efault: + return -EFAULT; } +#define unsafe_put_sigcontext(sc, fp, regs, set, label) \ +do { \ + if (__unsafe_setup_sigcontext(sc, fp, regs, set->sig[0])) \ + goto label; \ +} while(0); + +#define unsafe_put_sigmask(set, frame, label) \ + unsafe_put_user(*(__u64 *)(set), \ + (__u64 __user *)&(frame)->uc.uc_sigmask, \ + label) + /* * Set up a signal frame. */ @@ -310,26 +305,16 @@ __setup_frame(int sig, struct ksignal *ksig, sigset_t *set, { struct sigframe __user *frame; void __user *restorer; - int err = 0; - void __user *fpstate = NULL; - - frame = get_sigframe(&ksig->ka, regs, sizeof(*frame), &fpstate); + void __user *fp = NULL; - if (!access_ok(frame, sizeof(*frame))) - return -EFAULT; + frame = get_sigframe(&ksig->ka, regs, sizeof(*frame), &fp); - if (__put_user(sig, &frame->sig)) + if (!user_access_begin(frame, sizeof(*frame))) return -EFAULT; - if (setup_sigcontext(&frame->sc, fpstate, regs, set->sig[0])) - return -EFAULT; - - if (_NSIG_WORDS > 1) { - if (__copy_to_user(&frame->extramask, &set->sig[1], - sizeof(frame->extramask))) - return -EFAULT; - } - + unsafe_put_user(sig, &frame->sig, Efault); + unsafe_put_sigcontext(&frame->sc, fp, regs, set, Efault); + unsafe_put_user(set->sig[1], &frame->extramask[0], Efault); if (current->mm->context.vdso) restorer = current->mm->context.vdso + vdso_image_32.sym___kernel_sigreturn; @@ -339,7 +324,7 @@ __setup_frame(int sig, struct ksignal *ksig, sigset_t *set, restorer = ksig->ka.sa.sa_restorer; /* Set up to return from userspace. */ - err |= __put_user(restorer, &frame->pretcode); + unsafe_put_user(restorer, &frame->pretcode, Efault); /* * This is popl %eax ; movl $__NR_sigreturn, %eax ; int $0x80 @@ -348,10 +333,8 @@ __setup_frame(int sig, struct ksignal *ksig, sigset_t *set, * reasons and because gdb uses it as a signature to notice * signal handler stack frames. */ - err |= __put_user(*((u64 *)&retcode), (u64 *)frame->retcode); - - if (err) - return -EFAULT; + unsafe_put_user(*((u64 *)&retcode), (u64 *)frame->retcode, Efault); + user_access_end(); /* Set up registers for signal handler */ regs->sp = (unsigned long)frame; @@ -366,6 +349,10 @@ __setup_frame(int sig, struct ksignal *ksig, sigset_t *set, regs->cs = __USER_CS; return 0; + +Efault: + user_access_end(); + return -EFAULT; } static int __setup_rt_frame(int sig, struct ksignal *ksig, @@ -373,50 +360,45 @@ static int __setup_rt_frame(int sig, struct ksignal *ksig, { struct rt_sigframe __user *frame; void __user *restorer; - int err = 0; - void __user *fpstate = NULL; + void __user *fp = NULL; - frame = get_sigframe(&ksig->ka, regs, sizeof(*frame), &fpstate); + frame = get_sigframe(&ksig->ka, regs, sizeof(*frame), &fp); - if (!access_ok(frame, sizeof(*frame))) + if (!user_access_begin(frame, sizeof(*frame))) return -EFAULT; - put_user_try { - put_user_ex(sig, &frame->sig); - put_user_ex(&frame->info, &frame->pinfo); - put_user_ex(&frame->uc, &frame->puc); + unsafe_put_user(sig, &frame->sig, Efault); + unsafe_put_user(&frame->info, &frame->pinfo, Efault); + unsafe_put_user(&frame->uc, &frame->puc, Efault); - /* Create the ucontext. */ - if (static_cpu_has(X86_FEATURE_XSAVE)) - put_user_ex(UC_FP_XSTATE, &frame->uc.uc_flags); - else - put_user_ex(0, &frame->uc.uc_flags); - put_user_ex(0, &frame->uc.uc_link); - save_altstack_ex(&frame->uc.uc_stack, regs->sp); + /* Create the ucontext. */ + if (static_cpu_has(X86_FEATURE_XSAVE)) + unsafe_put_user(UC_FP_XSTATE, &frame->uc.uc_flags, Efault); + else + unsafe_put_user(0, &frame->uc.uc_flags, Efault); + unsafe_put_user(0, &frame->uc.uc_link, Efault); + unsafe_save_altstack(&frame->uc.uc_stack, regs->sp, Efault); - /* Set up to return from userspace. */ - restorer = current->mm->context.vdso + - vdso_image_32.sym___kernel_rt_sigreturn; - if (ksig->ka.sa.sa_flags & SA_RESTORER) - restorer = ksig->ka.sa.sa_restorer; - put_user_ex(restorer, &frame->pretcode); + /* Set up to return from userspace. */ + restorer = current->mm->context.vdso + + vdso_image_32.sym___kernel_rt_sigreturn; + if (ksig->ka.sa.sa_flags & SA_RESTORER) + restorer = ksig->ka.sa.sa_restorer; + unsafe_put_user(restorer, &frame->pretcode, Efault); - /* - * This is movl $__NR_rt_sigreturn, %ax ; int $0x80 - * - * WE DO NOT USE IT ANY MORE! It's only left here for historical - * reasons and because gdb uses it as a signature to notice - * signal handler stack frames. - */ - put_user_ex(*((u64 *)&rt_retcode), (u64 *)frame->retcode); - } put_user_catch(err); + /* + * This is movl $__NR_rt_sigreturn, %ax ; int $0x80 + * + * WE DO NOT USE IT ANY MORE! It's only left here for historical + * reasons and because gdb uses it as a signature to notice + * signal handler stack frames. + */ + unsafe_put_user(*((u64 *)&rt_retcode), (u64 *)frame->retcode, Efault); + unsafe_put_sigcontext(&frame->uc.uc_mcontext, fp, regs, set, Efault); + unsafe_put_sigmask(set, frame, Efault); + user_access_end(); - err |= copy_siginfo_to_user(&frame->info, &ksig->info); - err |= setup_sigcontext(&frame->uc.uc_mcontext, fpstate, - regs, set->sig[0]); - err |= __copy_to_user(&frame->uc.uc_sigmask, set, sizeof(*set)); - - if (err) + if (copy_siginfo_to_user(&frame->info, &ksig->info)) return -EFAULT; /* Set up registers for signal handler */ @@ -432,6 +414,9 @@ static int __setup_rt_frame(int sig, struct ksignal *ksig, regs->cs = __USER_CS; return 0; +Efault: + user_access_end(); + return -EFAULT; } #else /* !CONFIG_X86_32 */ static unsigned long frame_uc_flags(struct pt_regs *regs) @@ -455,43 +440,34 @@ static int __setup_rt_frame(int sig, struct ksignal *ksig, struct rt_sigframe __user *frame; void __user *fp = NULL; unsigned long uc_flags; - int err = 0; + + /* x86-64 should always use SA_RESTORER. */ + if (!(ksig->ka.sa.sa_flags & SA_RESTORER)) + return -EFAULT; frame = get_sigframe(&ksig->ka, regs, sizeof(struct rt_sigframe), &fp); + uc_flags = frame_uc_flags(regs); - if (!access_ok(frame, sizeof(*frame))) + if (!user_access_begin(frame, sizeof(*frame))) return -EFAULT; + /* Create the ucontext. */ + unsafe_put_user(uc_flags, &frame->uc.uc_flags, Efault); + unsafe_put_user(0, &frame->uc.uc_link, Efault); + unsafe_save_altstack(&frame->uc.uc_stack, regs->sp, Efault); + + /* Set up to return from userspace. If provided, use a stub + already in userspace. */ + unsafe_put_user(ksig->ka.sa.sa_restorer, &frame->pretcode, Efault); + unsafe_put_sigcontext(&frame->uc.uc_mcontext, fp, regs, set, Efault); + unsafe_put_sigmask(set, frame, Efault); + user_access_end(); + if (ksig->ka.sa.sa_flags & SA_SIGINFO) { if (copy_siginfo_to_user(&frame->info, &ksig->info)) return -EFAULT; } - uc_flags = frame_uc_flags(regs); - - put_user_try { - /* Create the ucontext. */ - put_user_ex(uc_flags, &frame->uc.uc_flags); - put_user_ex(0, &frame->uc.uc_link); - save_altstack_ex(&frame->uc.uc_stack, regs->sp); - - /* Set up to return from userspace. If provided, use a stub - already in userspace. */ - /* x86-64 should always use SA_RESTORER. */ - if (ksig->ka.sa.sa_flags & SA_RESTORER) { - put_user_ex(ksig->ka.sa.sa_restorer, &frame->pretcode); - } else { - /* could use a vstub here */ - err |= -EFAULT; - } - } put_user_catch(err); - - err |= setup_sigcontext(&frame->uc.uc_mcontext, fp, regs, set->sig[0]); - err |= __copy_to_user(&frame->uc.uc_sigmask, set, sizeof(*set)); - - if (err) - return -EFAULT; - /* Set up registers for signal handler */ regs->di = sig; /* In case the signal handler was declared without prototypes */ @@ -528,6 +504,10 @@ static int __setup_rt_frame(int sig, struct ksignal *ksig, force_valid_ss(regs); return 0; + +Efault: + user_access_end(); + return -EFAULT; } #endif /* CONFIG_X86_32 */ @@ -539,44 +519,33 @@ static int x32_setup_rt_frame(struct ksignal *ksig, struct rt_sigframe_x32 __user *frame; unsigned long uc_flags; void __user *restorer; - int err = 0; - void __user *fpstate = NULL; - - frame = get_sigframe(&ksig->ka, regs, sizeof(*frame), &fpstate); + void __user *fp = NULL; - if (!access_ok(frame, sizeof(*frame))) + if (!(ksig->ka.sa.sa_flags & SA_RESTORER)) return -EFAULT; - if (ksig->ka.sa.sa_flags & SA_SIGINFO) { - if (__copy_siginfo_to_user32(&frame->info, &ksig->info, true)) - return -EFAULT; - } + frame = get_sigframe(&ksig->ka, regs, sizeof(*frame), &fp); uc_flags = frame_uc_flags(regs); - put_user_try { - /* Create the ucontext. */ - put_user_ex(uc_flags, &frame->uc.uc_flags); - put_user_ex(0, &frame->uc.uc_link); - compat_save_altstack_ex(&frame->uc.uc_stack, regs->sp); - put_user_ex(0, &frame->uc.uc__pad0); - - if (ksig->ka.sa.sa_flags & SA_RESTORER) { - restorer = ksig->ka.sa.sa_restorer; - } else { - /* could use a vstub here */ - restorer = NULL; - err |= -EFAULT; - } - put_user_ex(restorer, (unsigned long __user *)&frame->pretcode); - } put_user_catch(err); + if (!user_access_begin(frame, sizeof(*frame))) + return -EFAULT; - err |= setup_sigcontext(&frame->uc.uc_mcontext, fpstate, - regs, set->sig[0]); - err |= __copy_to_user(&frame->uc.uc_sigmask, set, sizeof(*set)); + /* Create the ucontext. */ + unsafe_put_user(uc_flags, &frame->uc.uc_flags, Efault); + unsafe_put_user(0, &frame->uc.uc_link, Efault); + unsafe_compat_save_altstack(&frame->uc.uc_stack, regs->sp, Efault); + unsafe_put_user(0, &frame->uc.uc__pad0, Efault); + restorer = ksig->ka.sa.sa_restorer; + unsafe_put_user(restorer, (unsigned long __user *)&frame->pretcode, Efault); + unsafe_put_sigcontext(&frame->uc.uc_mcontext, fp, regs, set, Efault); + unsafe_put_sigmask(set, frame, Efault); + user_access_end(); - if (err) - return -EFAULT; + if (ksig->ka.sa.sa_flags & SA_SIGINFO) { + if (__copy_siginfo_to_user32(&frame->info, &ksig->info, true)) + return -EFAULT; + } /* Set up registers for signal handler */ regs->sp = (unsigned long) frame; @@ -595,6 +564,11 @@ static int x32_setup_rt_frame(struct ksignal *ksig, #endif /* CONFIG_X86_X32_ABI */ return 0; +#ifdef CONFIG_X86_X32_ABI +Efault: + user_access_end(); + return -EFAULT; +#endif } /* @@ -611,9 +585,8 @@ SYSCALL_DEFINE0(sigreturn) if (!access_ok(frame, sizeof(*frame))) goto badframe; - if (__get_user(set.sig[0], &frame->sc.oldmask) || (_NSIG_WORDS > 1 - && __copy_from_user(&set.sig[1], &frame->extramask, - sizeof(frame->extramask)))) + if (__get_user(set.sig[0], &frame->sc.oldmask) || + __get_user(set.sig[1], &frame->extramask[0])) goto badframe; set_current_blocked(&set); @@ -643,7 +616,7 @@ SYSCALL_DEFINE0(rt_sigreturn) frame = (struct rt_sigframe __user *)(regs->sp - sizeof(long)); if (!access_ok(frame, sizeof(*frame))) goto badframe; - if (__copy_from_user(&set, &frame->uc.uc_sigmask, sizeof(set))) + if (__get_user(*(__u64 *)&set, (__u64 __user *)&frame->uc.uc_sigmask)) goto badframe; if (__get_user(uc_flags, &frame->uc.uc_flags)) goto badframe; @@ -868,7 +841,7 @@ COMPAT_SYSCALL_DEFINE0(x32_rt_sigreturn) if (!access_ok(frame, sizeof(*frame))) goto badframe; - if (__copy_from_user(&set, &frame->uc.uc_sigmask, sizeof(set))) + if (__get_user(set.sig[0], (__u64 __user *)&frame->uc.uc_sigmask)) goto badframe; if (__get_user(uc_flags, &frame->uc.uc_flags)) goto badframe; diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c index d59525d2ead3..fe3ab9632f3b 100644 --- a/arch/x86/kernel/smpboot.c +++ b/arch/x86/kernel/smpboot.c @@ -1438,7 +1438,7 @@ early_param("possible_cpus", _setup_possible_cpus); /* * cpu_possible_mask should be static, it cannot change as cpu's * are onlined, or offlined. The reason is per-cpu data-structures - * are allocated by some modules at init time, and dont expect to + * are allocated by some modules at init time, and don't expect to * do this dynamically on cpu arrival/departure. * cpu_present_mask on the other hand can change dynamically. * In case when cpu_hotplug is not compiled, then we resort to current diff --git a/arch/x86/kernel/stacktrace.c b/arch/x86/kernel/stacktrace.c index 2d6898c2cb64..6ad43fc44556 100644 --- a/arch/x86/kernel/stacktrace.c +++ b/arch/x86/kernel/stacktrace.c @@ -96,7 +96,8 @@ struct stack_frame_user { }; static int -copy_stack_frame(const void __user *fp, struct stack_frame_user *frame) +copy_stack_frame(const struct stack_frame_user __user *fp, + struct stack_frame_user *frame) { int ret; @@ -105,7 +106,8 @@ copy_stack_frame(const void __user *fp, struct stack_frame_user *frame) ret = 1; pagefault_disable(); - if (__copy_from_user_inatomic(frame, fp, sizeof(*frame))) + if (__get_user(frame->next_fp, &fp->next_fp) || + __get_user(frame->ret_addr, &fp->ret_addr)) ret = 0; pagefault_enable(); diff --git a/arch/x86/kernel/time.c b/arch/x86/kernel/time.c index 4d545db52efc..106e7f87f534 100644 --- a/arch/x86/kernel/time.c +++ b/arch/x86/kernel/time.c @@ -62,19 +62,16 @@ static irqreturn_t timer_interrupt(int irq, void *dev_id) return IRQ_HANDLED; } -static struct irqaction irq0 = { - .handler = timer_interrupt, - .flags = IRQF_NOBALANCING | IRQF_IRQPOLL | IRQF_TIMER, - .name = "timer" -}; - static void __init setup_default_timer_irq(void) { + unsigned long flags = IRQF_NOBALANCING | IRQF_IRQPOLL | IRQF_TIMER; + /* - * Unconditionally register the legacy timer; even without legacy - * PIC/PIT we need this for the HPET0 in legacy replacement mode. + * Unconditionally register the legacy timer interrupt; even + * without legacy PIC/PIT we need this for the HPET0 in legacy + * replacement mode. */ - if (setup_irq(0, &irq0)) + if (request_irq(0, timer_interrupt, flags, "timer", NULL)) pr_info("Failed to register legacy timer interrupt\n"); } diff --git a/arch/x86/kernel/tsc.c b/arch/x86/kernel/tsc.c index 971d6f0216df..fdd4c1078632 100644 --- a/arch/x86/kernel/tsc.c +++ b/arch/x86/kernel/tsc.c @@ -477,7 +477,7 @@ static unsigned long pit_calibrate_tsc(u32 latch, unsigned long ms, int loopmin) * transition from one expected value to another with a fairly * high accuracy, and we didn't miss any events. We can thus * use the TSC value at the transitions to calculate a pretty - * good value for the TSC frequencty. + * good value for the TSC frequency. */ static inline int pit_verify_msb(unsigned char val) { diff --git a/arch/x86/kernel/tsc_sync.c b/arch/x86/kernel/tsc_sync.c index 32a818764e03..3d3c761eb74a 100644 --- a/arch/x86/kernel/tsc_sync.c +++ b/arch/x86/kernel/tsc_sync.c @@ -295,7 +295,7 @@ static cycles_t check_tsc_warp(unsigned int timeout) * But as the TSC is per-logical CPU and can potentially be modified wrongly * by the bios, TSC sync test for smaller duration should be able * to catch such errors. Also this will catch the condition where all the - * cores in the socket doesn't get reset at the same time. + * cores in the socket don't get reset at the same time. */ static inline unsigned int loop_timeout(int cpu) { diff --git a/arch/x86/kernel/vm86_32.c b/arch/x86/kernel/vm86_32.c index 91d55454e702..47a8676c7395 100644 --- a/arch/x86/kernel/vm86_32.c +++ b/arch/x86/kernel/vm86_32.c @@ -98,7 +98,6 @@ void save_v86_state(struct kernel_vm86_regs *regs, int retval) struct task_struct *tsk = current; struct vm86plus_struct __user *user; struct vm86 *vm86 = current->thread.vm86; - long err = 0; /* * This gets called from entry.S with interrupts disabled, but @@ -114,37 +113,30 @@ void save_v86_state(struct kernel_vm86_regs *regs, int retval) set_flags(regs->pt.flags, VEFLAGS, X86_EFLAGS_VIF | vm86->veflags_mask); user = vm86->user_vm86; - if (!access_ok(user, vm86->vm86plus.is_vm86pus ? + if (!user_access_begin(user, vm86->vm86plus.is_vm86pus ? sizeof(struct vm86plus_struct) : - sizeof(struct vm86_struct))) { - pr_alert("could not access userspace vm86 info\n"); - do_exit(SIGSEGV); - } - - put_user_try { - put_user_ex(regs->pt.bx, &user->regs.ebx); - put_user_ex(regs->pt.cx, &user->regs.ecx); - put_user_ex(regs->pt.dx, &user->regs.edx); - put_user_ex(regs->pt.si, &user->regs.esi); - put_user_ex(regs->pt.di, &user->regs.edi); - put_user_ex(regs->pt.bp, &user->regs.ebp); - put_user_ex(regs->pt.ax, &user->regs.eax); - put_user_ex(regs->pt.ip, &user->regs.eip); - put_user_ex(regs->pt.cs, &user->regs.cs); - put_user_ex(regs->pt.flags, &user->regs.eflags); - put_user_ex(regs->pt.sp, &user->regs.esp); - put_user_ex(regs->pt.ss, &user->regs.ss); - put_user_ex(regs->es, &user->regs.es); - put_user_ex(regs->ds, &user->regs.ds); - put_user_ex(regs->fs, &user->regs.fs); - put_user_ex(regs->gs, &user->regs.gs); - - put_user_ex(vm86->screen_bitmap, &user->screen_bitmap); - } put_user_catch(err); - if (err) { - pr_alert("could not access userspace vm86 info\n"); - do_exit(SIGSEGV); - } + sizeof(struct vm86_struct))) + goto Efault; + + unsafe_put_user(regs->pt.bx, &user->regs.ebx, Efault_end); + unsafe_put_user(regs->pt.cx, &user->regs.ecx, Efault_end); + unsafe_put_user(regs->pt.dx, &user->regs.edx, Efault_end); + unsafe_put_user(regs->pt.si, &user->regs.esi, Efault_end); + unsafe_put_user(regs->pt.di, &user->regs.edi, Efault_end); + unsafe_put_user(regs->pt.bp, &user->regs.ebp, Efault_end); + unsafe_put_user(regs->pt.ax, &user->regs.eax, Efault_end); + unsafe_put_user(regs->pt.ip, &user->regs.eip, Efault_end); + unsafe_put_user(regs->pt.cs, &user->regs.cs, Efault_end); + unsafe_put_user(regs->pt.flags, &user->regs.eflags, Efault_end); + unsafe_put_user(regs->pt.sp, &user->regs.esp, Efault_end); + unsafe_put_user(regs->pt.ss, &user->regs.ss, Efault_end); + unsafe_put_user(regs->es, &user->regs.es, Efault_end); + unsafe_put_user(regs->ds, &user->regs.ds, Efault_end); + unsafe_put_user(regs->fs, &user->regs.fs, Efault_end); + unsafe_put_user(regs->gs, &user->regs.gs, Efault_end); + unsafe_put_user(vm86->screen_bitmap, &user->screen_bitmap, Efault_end); + + user_access_end(); preempt_disable(); tsk->thread.sp0 = vm86->saved_sp0; @@ -159,6 +151,13 @@ void save_v86_state(struct kernel_vm86_regs *regs, int retval) lazy_load_gs(vm86->regs32.gs); regs->pt.ax = retval; + return; + +Efault_end: + user_access_end(); +Efault: + pr_alert("could not access userspace vm86 info\n"); + do_exit(SIGSEGV); } static void mark_screen_rdonly(struct mm_struct *mm) @@ -243,6 +242,7 @@ static long do_sys_vm86(struct vm86plus_struct __user *user_vm86, bool plus) struct kernel_vm86_regs vm86regs; struct pt_regs *regs = current_pt_regs(); unsigned long err = 0; + struct vm86_struct v; err = security_mmap_addr(0); if (err) { @@ -278,39 +278,32 @@ static long do_sys_vm86(struct vm86plus_struct __user *user_vm86, bool plus) if (vm86->saved_sp0) return -EPERM; - if (!access_ok(user_vm86, plus ? - sizeof(struct vm86_struct) : - sizeof(struct vm86plus_struct))) + if (copy_from_user(&v, user_vm86, + offsetof(struct vm86_struct, int_revectored))) return -EFAULT; memset(&vm86regs, 0, sizeof(vm86regs)); - get_user_try { - unsigned short seg; - get_user_ex(vm86regs.pt.bx, &user_vm86->regs.ebx); - get_user_ex(vm86regs.pt.cx, &user_vm86->regs.ecx); - get_user_ex(vm86regs.pt.dx, &user_vm86->regs.edx); - get_user_ex(vm86regs.pt.si, &user_vm86->regs.esi); - get_user_ex(vm86regs.pt.di, &user_vm86->regs.edi); - get_user_ex(vm86regs.pt.bp, &user_vm86->regs.ebp); - get_user_ex(vm86regs.pt.ax, &user_vm86->regs.eax); - get_user_ex(vm86regs.pt.ip, &user_vm86->regs.eip); - get_user_ex(seg, &user_vm86->regs.cs); - vm86regs.pt.cs = seg; - get_user_ex(vm86regs.pt.flags, &user_vm86->regs.eflags); - get_user_ex(vm86regs.pt.sp, &user_vm86->regs.esp); - get_user_ex(seg, &user_vm86->regs.ss); - vm86regs.pt.ss = seg; - get_user_ex(vm86regs.es, &user_vm86->regs.es); - get_user_ex(vm86regs.ds, &user_vm86->regs.ds); - get_user_ex(vm86regs.fs, &user_vm86->regs.fs); - get_user_ex(vm86regs.gs, &user_vm86->regs.gs); - - get_user_ex(vm86->flags, &user_vm86->flags); - get_user_ex(vm86->screen_bitmap, &user_vm86->screen_bitmap); - get_user_ex(vm86->cpu_type, &user_vm86->cpu_type); - } get_user_catch(err); - if (err) - return err; + + vm86regs.pt.bx = v.regs.ebx; + vm86regs.pt.cx = v.regs.ecx; + vm86regs.pt.dx = v.regs.edx; + vm86regs.pt.si = v.regs.esi; + vm86regs.pt.di = v.regs.edi; + vm86regs.pt.bp = v.regs.ebp; + vm86regs.pt.ax = v.regs.eax; + vm86regs.pt.ip = v.regs.eip; + vm86regs.pt.cs = v.regs.cs; + vm86regs.pt.flags = v.regs.eflags; + vm86regs.pt.sp = v.regs.esp; + vm86regs.pt.ss = v.regs.ss; + vm86regs.es = v.regs.es; + vm86regs.ds = v.regs.ds; + vm86regs.fs = v.regs.fs; + vm86regs.gs = v.regs.gs; + + vm86->flags = v.flags; + vm86->screen_bitmap = v.screen_bitmap; + vm86->cpu_type = v.cpu_type; if (copy_from_user(&vm86->int_revectored, &user_vm86->int_revectored, diff --git a/arch/x86/kernel/vmlinux.lds.S b/arch/x86/kernel/vmlinux.lds.S index e3296aa028fe..1bf7e312361f 100644 --- a/arch/x86/kernel/vmlinux.lds.S +++ b/arch/x86/kernel/vmlinux.lds.S @@ -21,6 +21,7 @@ #define LOAD_OFFSET __START_KERNEL_map #endif +#define RUNTIME_DISCARD_EXIT #define EMITS_PT_NOTE #define RO_EXCEPTION_TABLE_ALIGN 16 @@ -313,8 +314,8 @@ SECTIONS . = ALIGN(8); /* - * .exit.text is discard at runtime, not link time, to deal with - * references from .altinstructions and .eh_frame + * .exit.text is discarded at runtime, not link time, to deal with + * references from .altinstructions */ .exit.text : AT(ADDR(.exit.text) - LOAD_OFFSET) { EXIT_TEXT @@ -412,9 +413,6 @@ SECTIONS DWARF_DEBUG DISCARDS - /DISCARD/ : { - *(.eh_frame) - } } |