diff options
Diffstat (limited to 'arch/x86/kernel/fpu')
| -rw-r--r-- | arch/x86/kernel/fpu/bugs.c | 3 | ||||
| -rw-r--r-- | arch/x86/kernel/fpu/context.h | 9 | ||||
| -rw-r--r-- | arch/x86/kernel/fpu/core.c | 281 | ||||
| -rw-r--r-- | arch/x86/kernel/fpu/init.c | 30 | ||||
| -rw-r--r-- | arch/x86/kernel/fpu/internal.h | 2 | ||||
| -rw-r--r-- | arch/x86/kernel/fpu/regset.c | 100 | ||||
| -rw-r--r-- | arch/x86/kernel/fpu/signal.c | 60 | ||||
| -rw-r--r-- | arch/x86/kernel/fpu/xstate.c | 540 | ||||
| -rw-r--r-- | arch/x86/kernel/fpu/xstate.h | 112 |
9 files changed, 773 insertions, 364 deletions
diff --git a/arch/x86/kernel/fpu/bugs.c b/arch/x86/kernel/fpu/bugs.c index 794e70151203..edbafc5940e3 100644 --- a/arch/x86/kernel/fpu/bugs.c +++ b/arch/x86/kernel/fpu/bugs.c @@ -2,6 +2,9 @@ /* * x86 FPU bug checks: */ +#include <linux/printk.h> + +#include <asm/cpufeature.h> #include <asm/fpu/api.h> /* diff --git a/arch/x86/kernel/fpu/context.h b/arch/x86/kernel/fpu/context.h index 958accf2ccf0..10d0a720659c 100644 --- a/arch/x86/kernel/fpu/context.h +++ b/arch/x86/kernel/fpu/context.h @@ -19,8 +19,7 @@ * FPU state for a task MUST let the rest of the kernel know that the * FPU registers are no longer valid for this task. * - * Either one of these invalidation functions is enough. Invalidate - * a resource you control: CPU if using the CPU for something else + * Invalidate a resource you control: CPU if using the CPU for something else * (with preemption disabled), FPU for the current task, or a task that * is prevented from running by the current task. */ @@ -54,10 +53,10 @@ static inline void fpregs_activate(struct fpu *fpu) /* Internal helper for switch_fpu_return() and signal frame setup */ static inline void fpregs_restore_userregs(void) { - struct fpu *fpu = ¤t->thread.fpu; + struct fpu *fpu = x86_task_fpu(current); int cpu = smp_processor_id(); - if (WARN_ON_ONCE(current->flags & PF_KTHREAD)) + if (WARN_ON_ONCE(current->flags & (PF_KTHREAD | PF_USER_WORKER))) return; if (!fpregs_state_valid(fpu, cpu)) { @@ -68,7 +67,7 @@ static inline void fpregs_restore_userregs(void) * If PKRU is enabled, then the PKRU value is already * correct because it was either set in switch_to() or in * flush_thread(). So it is excluded because it might be - * not up to date in current->thread.fpu.xsave state. + * not up to date in current->thread.fpu->xsave state. * * XFD state is handled in restore_fpregs_from_fpstate(). */ diff --git a/arch/x86/kernel/fpu/core.c b/arch/x86/kernel/fpu/core.c index 9baa89a8877d..da233f20ae6f 100644 --- a/arch/x86/kernel/fpu/core.c +++ b/arch/x86/kernel/fpu/core.c @@ -11,12 +11,14 @@ #include <asm/fpu/sched.h> #include <asm/fpu/signal.h> #include <asm/fpu/types.h> +#include <asm/msr.h> #include <asm/traps.h> #include <asm/irq_regs.h> #include <uapi/asm/kvm.h> #include <linux/hardirq.h> +#include <linux/kvm_types.h> #include <linux/pkeys.h> #include <linux/vmalloc.h> @@ -36,6 +38,7 @@ DEFINE_PER_CPU(u64, xfd_state); /* The FPU state configuration data for kernel and user space */ struct fpu_state_config fpu_kernel_cfg __ro_after_init; struct fpu_state_config fpu_user_cfg __ro_after_init; +struct vcpu_fpu_config guest_default_cfg __ro_after_init; /* * Represents the initial FPU state. It's mostly (but not completely) zeroes, @@ -43,14 +46,27 @@ struct fpu_state_config fpu_user_cfg __ro_after_init; */ struct fpstate init_fpstate __ro_after_init; -/* Track in-kernel FPU usage */ -static DEFINE_PER_CPU(bool, in_kernel_fpu); +/* + * Track FPU initialization and kernel-mode usage. 'true' means the FPU is + * initialized and is not currently being used by the kernel: + */ +DEFINE_PER_CPU(bool, kernel_fpu_allowed); /* * Track which context is using the FPU on the CPU: */ DEFINE_PER_CPU(struct fpu *, fpu_fpregs_owner_ctx); +#ifdef CONFIG_X86_DEBUG_FPU +struct fpu *x86_task_fpu(struct task_struct *task) +{ + if (WARN_ON_ONCE(task->flags & PF_KTHREAD)) + return NULL; + + return (void *)task + sizeof(*task); +} +#endif + /* * Can we use the FPU in kernel mode with the * whole "kernel_fpu_begin/end()" sequence? @@ -60,8 +76,18 @@ bool irq_fpu_usable(void) if (WARN_ON_ONCE(in_nmi())) return false; - /* In kernel FPU usage already active? */ - if (this_cpu_read(in_kernel_fpu)) + /* + * Return false in the following cases: + * + * - FPU is not yet initialized. This can happen only when the call is + * coming from CPU onlining, for example for microcode checksumming. + * - The kernel is already using the FPU, either because of explicit + * nesting (which should never be done), or because of implicit + * nesting when a hardirq interrupted a kernel-mode FPU section. + * + * The single boolean check below handles both cases: + */ + if (!this_cpu_read(kernel_fpu_allowed)) return false; /* @@ -145,8 +171,8 @@ void restore_fpregs_from_fpstate(struct fpstate *fpstate, u64 mask) asm volatile( "fnclex\n\t" "emms\n\t" - "fildl %P[addr]" /* set F?P to defined value */ - : : [addr] "m" (fpstate)); + "fildl %[addr]" /* set F?P to defined value */ + : : [addr] "m" (*fpstate)); } if (use_xsave()) { @@ -193,9 +219,9 @@ void fpu_reset_from_exception_fixup(void) } #if IS_ENABLED(CONFIG_KVM) -static void __fpstate_reset(struct fpstate *fpstate, u64 xfd); +static void __fpstate_reset(struct fpstate *fpstate); -static void fpu_init_guest_permissions(struct fpu_guest *gfpu) +static void fpu_lock_guest_permissions(void) { struct fpu_state_perm *fpuperm; u64 perm; @@ -204,15 +230,13 @@ static void fpu_init_guest_permissions(struct fpu_guest *gfpu) return; spin_lock_irq(¤t->sighand->siglock); - fpuperm = ¤t->group_leader->thread.fpu.guest_perm; + fpuperm = &x86_task_fpu(current->group_leader)->guest_perm; perm = fpuperm->__state_perm; /* First fpstate allocation locks down permissions. */ WRITE_ONCE(fpuperm->__state_perm, perm | FPU_GUEST_PERM_LOCKED); spin_unlock_irq(¤t->sighand->siglock); - - gfpu->perm = perm & ~FPU_GUEST_PERM_LOCKED; } bool fpu_alloc_guest_fpstate(struct fpu_guest *gfpu) @@ -220,20 +244,21 @@ bool fpu_alloc_guest_fpstate(struct fpu_guest *gfpu) struct fpstate *fpstate; unsigned int size; - size = fpu_user_cfg.default_size + ALIGN(offsetof(struct fpstate, regs), 64); + size = guest_default_cfg.size + ALIGN(offsetof(struct fpstate, regs), 64); + fpstate = vzalloc(size); if (!fpstate) return false; - /* Leave xfd to 0 (the reset value defined by spec) */ - __fpstate_reset(fpstate, 0); - fpstate_init_user(fpstate); + /* Initialize indicators to reflect properties of the fpstate */ fpstate->is_valloc = true; fpstate->is_guest = true; + __fpstate_reset(fpstate); + fpstate_init_user(fpstate); + gfpu->fpstate = fpstate; - gfpu->xfeatures = fpu_user_cfg.default_features; - gfpu->perm = fpu_user_cfg.default_features; + gfpu->xfeatures = guest_default_cfg.features; /* * KVM sets the FP+SSE bits in the XSAVE header when copying FPU state @@ -248,26 +273,26 @@ bool fpu_alloc_guest_fpstate(struct fpu_guest *gfpu) if (WARN_ON_ONCE(fpu_user_cfg.default_size > gfpu->uabi_size)) gfpu->uabi_size = fpu_user_cfg.default_size; - fpu_init_guest_permissions(gfpu); + fpu_lock_guest_permissions(); return true; } -EXPORT_SYMBOL_GPL(fpu_alloc_guest_fpstate); +EXPORT_SYMBOL_FOR_KVM(fpu_alloc_guest_fpstate); void fpu_free_guest_fpstate(struct fpu_guest *gfpu) { - struct fpstate *fps = gfpu->fpstate; + struct fpstate *fpstate = gfpu->fpstate; - if (!fps) + if (!fpstate) return; - if (WARN_ON_ONCE(!fps->is_valloc || !fps->is_guest || fps->in_use)) + if (WARN_ON_ONCE(!fpstate->is_valloc || !fpstate->is_guest || fpstate->in_use)) return; gfpu->fpstate = NULL; - vfree(fps); + vfree(fpstate); } -EXPORT_SYMBOL_GPL(fpu_free_guest_fpstate); +EXPORT_SYMBOL_FOR_KVM(fpu_free_guest_fpstate); /* * fpu_enable_guest_xfd_features - Check xfeatures against guest perm and enable @@ -289,7 +314,7 @@ int fpu_enable_guest_xfd_features(struct fpu_guest *guest_fpu, u64 xfeatures) return __xfd_enable_feature(xfeatures, guest_fpu); } -EXPORT_SYMBOL_GPL(fpu_enable_guest_xfd_features); +EXPORT_SYMBOL_FOR_KVM(fpu_enable_guest_xfd_features); #ifdef CONFIG_X86_64 void fpu_update_guest_xfd(struct fpu_guest *guest_fpu, u64 xfd) @@ -300,7 +325,7 @@ void fpu_update_guest_xfd(struct fpu_guest *guest_fpu, u64 xfd) xfd_update_state(guest_fpu->fpstate); fpregs_unlock(); } -EXPORT_SYMBOL_GPL(fpu_update_guest_xfd); +EXPORT_SYMBOL_FOR_KVM(fpu_update_guest_xfd); /** * fpu_sync_guest_vmexit_xfd_state - Synchronize XFD MSR and software state @@ -308,7 +333,7 @@ EXPORT_SYMBOL_GPL(fpu_update_guest_xfd); * Must be invoked from KVM after a VMEXIT before enabling interrupts when * XFD write emulation is disabled. This is required because the guest can * freely modify XFD and the state at VMEXIT is not guaranteed to be the - * same as the state on VMENTER. So software state has to be udpated before + * same as the state on VMENTER. So software state has to be updated before * any operation which depends on it can take place. * * Note: It can be invoked unconditionally even when write emulation is @@ -316,21 +341,21 @@ EXPORT_SYMBOL_GPL(fpu_update_guest_xfd); */ void fpu_sync_guest_vmexit_xfd_state(void) { - struct fpstate *fps = current->thread.fpu.fpstate; + struct fpstate *fpstate = x86_task_fpu(current)->fpstate; lockdep_assert_irqs_disabled(); if (fpu_state_size_dynamic()) { - rdmsrl(MSR_IA32_XFD, fps->xfd); - __this_cpu_write(xfd_state, fps->xfd); + rdmsrq(MSR_IA32_XFD, fpstate->xfd); + __this_cpu_write(xfd_state, fpstate->xfd); } } -EXPORT_SYMBOL_GPL(fpu_sync_guest_vmexit_xfd_state); +EXPORT_SYMBOL_FOR_KVM(fpu_sync_guest_vmexit_xfd_state); #endif /* CONFIG_X86_64 */ int fpu_swap_kvm_fpstate(struct fpu_guest *guest_fpu, bool enter_guest) { struct fpstate *guest_fps = guest_fpu->fpstate; - struct fpu *fpu = ¤t->thread.fpu; + struct fpu *fpu = x86_task_fpu(current); struct fpstate *cur_fps = fpu->fpstate; fpregs_lock(); @@ -366,17 +391,18 @@ int fpu_swap_kvm_fpstate(struct fpu_guest *guest_fpu, bool enter_guest) fpregs_unlock(); return 0; } -EXPORT_SYMBOL_GPL(fpu_swap_kvm_fpstate); +EXPORT_SYMBOL_FOR_KVM(fpu_swap_kvm_fpstate); void fpu_copy_guest_fpstate_to_uabi(struct fpu_guest *gfpu, void *buf, - unsigned int size, u32 pkru) + unsigned int size, u64 xfeatures, u32 pkru) { struct fpstate *kstate = gfpu->fpstate; union fpregs_state *ustate = buf; struct membuf mb = { .p = buf, .left = size }; if (cpu_feature_enabled(X86_FEATURE_XSAVE)) { - __copy_xstate_to_uabi_buf(mb, kstate, pkru, XSTATE_COPY_XSAVE); + __copy_xstate_to_uabi_buf(mb, kstate, xfeatures, pkru, + XSTATE_COPY_XSAVE); } else { memcpy(&ustate->fxsave, &kstate->regs.fxsave, sizeof(ustate->fxsave)); @@ -384,7 +410,7 @@ void fpu_copy_guest_fpstate_to_uabi(struct fpu_guest *gfpu, void *buf, ustate->xsave.header.xfeatures = XFEATURE_MASK_FPSSE; } } -EXPORT_SYMBOL_GPL(fpu_copy_guest_fpstate_to_uabi); +EXPORT_SYMBOL_FOR_KVM(fpu_copy_guest_fpstate_to_uabi); int fpu_copy_uabi_to_guest_fpstate(struct fpu_guest *gfpu, const void *buf, u64 xcr0, u32 *vpkru) @@ -414,22 +440,24 @@ int fpu_copy_uabi_to_guest_fpstate(struct fpu_guest *gfpu, const void *buf, return copy_uabi_from_kernel_to_xstate(kstate, ustate, vpkru); } -EXPORT_SYMBOL_GPL(fpu_copy_uabi_to_guest_fpstate); +EXPORT_SYMBOL_FOR_KVM(fpu_copy_uabi_to_guest_fpstate); #endif /* CONFIG_KVM */ void kernel_fpu_begin_mask(unsigned int kfpu_mask) { - preempt_disable(); + if (!irqs_disabled()) + fpregs_lock(); WARN_ON_FPU(!irq_fpu_usable()); - WARN_ON_FPU(this_cpu_read(in_kernel_fpu)); - this_cpu_write(in_kernel_fpu, true); + /* Toggle kernel_fpu_allowed to false: */ + WARN_ON_FPU(!this_cpu_read(kernel_fpu_allowed)); + this_cpu_write(kernel_fpu_allowed, false); - if (!(current->flags & PF_KTHREAD) && + if (!(current->flags & (PF_KTHREAD | PF_USER_WORKER)) && !test_thread_flag(TIF_NEED_FPU_LOAD)) { set_thread_flag(TIF_NEED_FPU_LOAD); - save_fpregs_to_fpstate(¤t->thread.fpu); + save_fpregs_to_fpstate(x86_task_fpu(current)); } __cpu_invalidate_fpregs_state(); @@ -444,10 +472,12 @@ EXPORT_SYMBOL_GPL(kernel_fpu_begin_mask); void kernel_fpu_end(void) { - WARN_ON_FPU(!this_cpu_read(in_kernel_fpu)); + /* Toggle kernel_fpu_allowed back to true: */ + WARN_ON_FPU(this_cpu_read(kernel_fpu_allowed)); + this_cpu_write(kernel_fpu_allowed, true); - this_cpu_write(in_kernel_fpu, false); - preempt_enable(); + if (!irqs_disabled()) + fpregs_unlock(); } EXPORT_SYMBOL_GPL(kernel_fpu_end); @@ -457,7 +487,7 @@ EXPORT_SYMBOL_GPL(kernel_fpu_end); */ void fpu_sync_fpstate(struct fpu *fpu) { - WARN_ON_FPU(fpu != ¤t->thread.fpu); + WARN_ON_FPU(fpu != x86_task_fpu(current)); fpregs_lock(); trace_x86_fpu_before_save(fpu); @@ -498,7 +528,7 @@ static inline void fpstate_init_fstate(struct fpstate *fpstate) /* * Used in two places: * 1) Early boot to setup init_fpstate for non XSAVE systems - * 2) fpu_init_fpstate_user() which is invoked from KVM + * 2) fpu_alloc_guest_fpstate() which is invoked from KVM */ void fpstate_init_user(struct fpstate *fpstate) { @@ -515,34 +545,56 @@ void fpstate_init_user(struct fpstate *fpstate) fpstate_init_fstate(fpstate); } -static void __fpstate_reset(struct fpstate *fpstate, u64 xfd) +static void __fpstate_reset(struct fpstate *fpstate) { - /* Initialize sizes and feature masks */ - fpstate->size = fpu_kernel_cfg.default_size; + /* + * Supervisor features (and thus sizes) may diverge between guest + * FPUs and host FPUs, as some supervisor features are supported + * for guests despite not being utilized by the host. User + * features and sizes are always identical, which allows for + * common guest and userspace ABI. + * + * For the host, set XFD to the kernel's desired initialization + * value. For guests, set XFD to its architectural RESET value. + */ + if (fpstate->is_guest) { + fpstate->size = guest_default_cfg.size; + fpstate->xfeatures = guest_default_cfg.features; + fpstate->xfd = 0; + } else { + fpstate->size = fpu_kernel_cfg.default_size; + fpstate->xfeatures = fpu_kernel_cfg.default_features; + fpstate->xfd = init_fpstate.xfd; + } + fpstate->user_size = fpu_user_cfg.default_size; - fpstate->xfeatures = fpu_kernel_cfg.default_features; fpstate->user_xfeatures = fpu_user_cfg.default_features; - fpstate->xfd = xfd; } void fpstate_reset(struct fpu *fpu) { /* Set the fpstate pointer to the default fpstate */ fpu->fpstate = &fpu->__fpstate; - __fpstate_reset(fpu->fpstate, init_fpstate.xfd); + __fpstate_reset(fpu->fpstate); /* Initialize the permission related info in fpu */ fpu->perm.__state_perm = fpu_kernel_cfg.default_features; fpu->perm.__state_size = fpu_kernel_cfg.default_size; fpu->perm.__user_state_size = fpu_user_cfg.default_size; - /* Same defaults for guests */ - fpu->guest_perm = fpu->perm; + + fpu->guest_perm.__state_perm = guest_default_cfg.features; + fpu->guest_perm.__state_size = guest_default_cfg.size; + /* + * User features and sizes are always identical between host and + * guest FPUs, which allows for common guest and userspace ABI. + */ + fpu->guest_perm.__user_state_size = fpu_user_cfg.default_size; } static inline void fpu_inherit_perms(struct fpu *dst_fpu) { if (fpu_state_size_dynamic()) { - struct fpu *src_fpu = ¤t->group_leader->thread.fpu; + struct fpu *src_fpu = x86_task_fpu(current->group_leader); spin_lock_irq(¤t->sighand->siglock); /* Fork also inherits the permissions of the parent */ @@ -552,11 +604,47 @@ static inline void fpu_inherit_perms(struct fpu *dst_fpu) } } +/* A passed ssp of zero will not cause any update */ +static int update_fpu_shstk(struct task_struct *dst, unsigned long ssp) +{ +#ifdef CONFIG_X86_USER_SHADOW_STACK + struct cet_user_state *xstate; + + /* If ssp update is not needed. */ + if (!ssp) + return 0; + + xstate = get_xsave_addr(&x86_task_fpu(dst)->fpstate->regs.xsave, + XFEATURE_CET_USER); + + /* + * If there is a non-zero ssp, then 'dst' must be configured with a shadow + * stack and the fpu state should be up to date since it was just copied + * from the parent in fpu_clone(). So there must be a valid non-init CET + * state location in the buffer. + */ + if (WARN_ON_ONCE(!xstate)) + return 1; + + xstate->user_ssp = (u64)ssp; +#endif + return 0; +} + /* Clone current's FPU state on fork */ -int fpu_clone(struct task_struct *dst, unsigned long clone_flags, bool minimal) +int fpu_clone(struct task_struct *dst, u64 clone_flags, bool minimal, + unsigned long ssp) { - struct fpu *src_fpu = ¤t->thread.fpu; - struct fpu *dst_fpu = &dst->thread.fpu; + /* + * We allocate the new FPU structure right after the end of the task struct. + * task allocation size already took this into account. + * + * This is safe because task_struct size is a multiple of cacheline size, + * thus x86_task_fpu() will always be cacheline aligned as well. + */ + struct fpu *dst_fpu = (void *)dst + sizeof(*dst); + + BUILD_BUG_ON(sizeof(*dst) % SMP_CACHE_BYTES != 0); /* The new task's FPU state cannot be valid in the hardware. */ dst_fpu->last_cpu = -1; @@ -613,19 +701,28 @@ int fpu_clone(struct task_struct *dst, unsigned long clone_flags, bool minimal) if (use_xsave()) dst_fpu->fpstate->regs.xsave.header.xfeatures &= ~XFEATURE_MASK_PASID; - trace_x86_fpu_copy_src(src_fpu); + /* + * Update shadow stack pointer, in case it changed during clone. + */ + if (update_fpu_shstk(dst, ssp)) + return 1; + trace_x86_fpu_copy_dst(dst_fpu); return 0; } /* - * Whitelist the FPU register state embedded into task_struct for hardened - * usercopy. + * While struct fpu is no longer part of struct thread_struct, it is still + * allocated after struct task_struct in the "task_struct" kmem cache. But + * since FPU is expected to be part of struct thread_struct, we have to + * adjust for it here. */ void fpu_thread_struct_whitelist(unsigned long *offset, unsigned long *size) { - *offset = offsetof(struct thread_struct, fpu.__fpstate.regs); + /* The allocation follows struct task_struct. */ + *offset = sizeof(struct task_struct) - offsetof(struct task_struct, thread); + *offset += offsetof(struct fpu, __fpstate.regs); *size = fpu_kernel_cfg.default_size; } @@ -638,11 +735,18 @@ void fpu_thread_struct_whitelist(unsigned long *offset, unsigned long *size) * a state-restore is coming: either an explicit one, * or a reschedule. */ -void fpu__drop(struct fpu *fpu) +void fpu__drop(struct task_struct *tsk) { + struct fpu *fpu; + + if (test_tsk_thread_flag(tsk, TIF_NEED_FPU_LOAD)) + return; + + fpu = x86_task_fpu(tsk); + preempt_disable(); - if (fpu == ¤t->thread.fpu) { + if (fpu == x86_task_fpu(current)) { /* Ignore delayed exceptions from user space */ asm volatile("1: fwait\n" "2:\n" @@ -674,12 +778,12 @@ static inline void restore_fpregs_from_init_fpstate(u64 features_mask) /* * Reset current->fpu memory state to the init values. */ -static void fpu_reset_fpregs(void) +static void fpu_reset_fpstate_regs(void) { - struct fpu *fpu = ¤t->thread.fpu; + struct fpu *fpu = x86_task_fpu(current); fpregs_lock(); - fpu__drop(fpu); + __fpu_invalidate_fpregs_state(fpu); /* * This does not change the actual hardware registers. It just * resets the memory image and sets TIF_NEED_FPU_LOAD so a @@ -705,11 +809,11 @@ static void fpu_reset_fpregs(void) */ void fpu__clear_user_states(struct fpu *fpu) { - WARN_ON_FPU(fpu != ¤t->thread.fpu); + WARN_ON_FPU(fpu != x86_task_fpu(current)); fpregs_lock(); if (!cpu_feature_enabled(X86_FEATURE_FPU)) { - fpu_reset_fpregs(); + fpu_reset_fpstate_regs(); fpregs_unlock(); return; } @@ -722,6 +826,9 @@ void fpu__clear_user_states(struct fpu *fpu) !fpregs_state_valid(fpu, smp_processor_id())) os_xrstor_supervisor(fpu->fpstate); + /* Ensure XFD state is in sync before reloading XSTATE */ + xfd_update_state(fpu->fpstate); + /* Reset user states in registers. */ restore_fpregs_from_init_fpstate(XFEATURE_MASK_USER_RESTORE); @@ -738,8 +845,8 @@ void fpu__clear_user_states(struct fpu *fpu) void fpu_flush_thread(void) { - fpstate_reset(¤t->thread.fpu); - fpu_reset_fpregs(); + fpstate_reset(x86_task_fpu(current)); + fpu_reset_fpstate_regs(); } /* * Load FPU context before returning to userspace. @@ -751,7 +858,25 @@ void switch_fpu_return(void) fpregs_restore_userregs(); } -EXPORT_SYMBOL_GPL(switch_fpu_return); +EXPORT_SYMBOL_FOR_KVM(switch_fpu_return); + +void fpregs_lock_and_load(void) +{ + /* + * fpregs_lock() only disables preemption (mostly). So modifying state + * in an interrupt could screw up some in progress fpregs operation. + * Warn about it. + */ + WARN_ON_ONCE(!irq_fpu_usable()); + WARN_ON_ONCE(current->flags & PF_KTHREAD); + + fpregs_lock(); + + fpregs_assert_state_consistent(); + + if (test_thread_flag(TIF_NEED_FPU_LOAD)) + fpregs_restore_userregs(); +} #ifdef CONFIG_X86_DEBUG_FPU /* @@ -761,19 +886,19 @@ EXPORT_SYMBOL_GPL(switch_fpu_return); */ void fpregs_assert_state_consistent(void) { - struct fpu *fpu = ¤t->thread.fpu; + struct fpu *fpu = x86_task_fpu(current); if (test_thread_flag(TIF_NEED_FPU_LOAD)) return; WARN_ON_FPU(!fpregs_state_valid(fpu, smp_processor_id())); } -EXPORT_SYMBOL_GPL(fpregs_assert_state_consistent); +EXPORT_SYMBOL_FOR_KVM(fpregs_assert_state_consistent); #endif void fpregs_mark_activate(void) { - struct fpu *fpu = ¤t->thread.fpu; + struct fpu *fpu = x86_task_fpu(current); fpregs_activate(fpu); fpu->last_cpu = smp_processor_id(); @@ -853,12 +978,12 @@ int fpu__exception_code(struct fpu *fpu, int trap_nr) * Initialize register state that may prevent from entering low-power idle. * This function will be invoked from the cpuidle driver only when needed. */ -void fpu_idle_fpregs(void) +noinstr void fpu_idle_fpregs(void) { /* Note: AMX_TILE being enabled implies XGETBV1 support */ if (cpu_feature_enabled(X86_FEATURE_AMX_TILE) && (xfeatures_in_use() & XFEATURE_MASK_XTILE)) { tile_release(); - fpregs_deactivate(¤t->thread.fpu); + __this_cpu_write(fpu_fpregs_owner_ctx, NULL); } } diff --git a/arch/x86/kernel/fpu/init.c b/arch/x86/kernel/fpu/init.c index 851eb13edc01..ff988b9ea39f 100644 --- a/arch/x86/kernel/fpu/init.c +++ b/arch/x86/kernel/fpu/init.c @@ -38,7 +38,7 @@ static void fpu__init_cpu_generic(void) /* Flush out any pending x87 state: */ #ifdef CONFIG_MATH_EMULATION if (!boot_cpu_has(X86_FEATURE_FPU)) - fpstate_init_soft(¤t->thread.fpu.fpstate->regs.soft); + ; else #endif asm volatile ("fninit"); @@ -51,9 +51,12 @@ void fpu__init_cpu(void) { fpu__init_cpu_generic(); fpu__init_cpu_xstate(); + + /* Start allowing kernel-mode FPU: */ + this_cpu_write(kernel_fpu_allowed, true); } -static bool fpu__probe_without_cpuid(void) +static bool __init fpu__probe_without_cpuid(void) { unsigned long cr0; u16 fsw, fcw; @@ -71,8 +74,10 @@ static bool fpu__probe_without_cpuid(void) return fsw == 0 && (fcw & 0x103f) == 0x003f; } -static void fpu__init_system_early_generic(struct cpuinfo_x86 *c) +static void __init fpu__init_system_early_generic(void) { + set_thread_flag(TIF_NEED_FPU_LOAD); + if (!boot_cpu_has(X86_FEATURE_CPUID) && !test_bit(X86_FEATURE_FPU, (unsigned long *)cpu_caps_cleared)) { if (fpu__probe_without_cpuid()) @@ -94,7 +99,6 @@ static void fpu__init_system_early_generic(struct cpuinfo_x86 *c) * Boot time FPU feature detection code: */ unsigned int mxcsr_feature_mask __ro_after_init = 0xffffffffu; -EXPORT_SYMBOL_GPL(mxcsr_feature_mask); static void __init fpu__init_system_mxcsr(void) { @@ -150,11 +154,13 @@ static void __init fpu__init_task_struct_size(void) { int task_size = sizeof(struct task_struct); + task_size += sizeof(struct fpu); + /* * Subtract off the static size of the register state. * It potentially has a bunch of padding. */ - task_size -= sizeof(current->thread.fpu.__fpstate.regs); + task_size -= sizeof(union fpregs_state); /* * Add back the dynamically-calculated register state @@ -164,14 +170,9 @@ static void __init fpu__init_task_struct_size(void) /* * We dynamically size 'struct fpu', so we require that - * it be at the end of 'thread_struct' and that - * 'thread_struct' be at the end of 'task_struct'. If - * you hit a compile error here, check the structure to - * see if something got added to the end. + * 'state' be at the end of 'it: */ CHECK_MEMBER_AT_END_OF(struct fpu, __fpstate); - CHECK_MEMBER_AT_END_OF(struct thread_struct, fpu); - CHECK_MEMBER_AT_END_OF(struct task_struct, thread); arch_task_struct_size = task_size; } @@ -204,17 +205,16 @@ static void __init fpu__init_system_xstate_size_legacy(void) fpu_kernel_cfg.default_size = size; fpu_user_cfg.max_size = size; fpu_user_cfg.default_size = size; - fpstate_reset(¤t->thread.fpu); + guest_default_cfg.size = size; } /* * Called on the boot CPU once per system bootup, to set up the initial * FPU state that is later cloned into all processes: */ -void __init fpu__init_system(struct cpuinfo_x86 *c) +void __init fpu__init_system(void) { - fpstate_reset(¤t->thread.fpu); - fpu__init_system_early_generic(c); + fpu__init_system_early_generic(); /* * The FPU has to be operational for some of the diff --git a/arch/x86/kernel/fpu/internal.h b/arch/x86/kernel/fpu/internal.h index dbdb31f55fc7..975de070c9c9 100644 --- a/arch/x86/kernel/fpu/internal.h +++ b/arch/x86/kernel/fpu/internal.h @@ -18,7 +18,7 @@ static __always_inline __pure bool use_fxsr(void) #ifdef CONFIG_X86_DEBUG_FPU # define WARN_ON_FPU(x) WARN_ON_ONCE(x) #else -# define WARN_ON_FPU(x) ({ (void)(x); 0; }) +# define WARN_ON_FPU(x) ({ BUILD_BUG_ON_INVALID(x); 0; }) #endif /* Used in init.c */ diff --git a/arch/x86/kernel/fpu/regset.c b/arch/x86/kernel/fpu/regset.c index 6d056b68f4ed..0986c2200adc 100644 --- a/arch/x86/kernel/fpu/regset.c +++ b/arch/x86/kernel/fpu/regset.c @@ -8,6 +8,7 @@ #include <asm/fpu/api.h> #include <asm/fpu/signal.h> #include <asm/fpu/regset.h> +#include <asm/prctl.h> #include "context.h" #include "internal.h" @@ -44,7 +45,7 @@ int regset_xregset_fpregs_active(struct task_struct *target, const struct user_r */ static void sync_fpstate(struct fpu *fpu) { - if (fpu == ¤t->thread.fpu) + if (fpu == x86_task_fpu(current)) fpu_sync_fpstate(fpu); } @@ -62,7 +63,7 @@ static void fpu_force_restore(struct fpu *fpu) * Only stopped child tasks can be used to modify the FPU * state in the fpstate buffer: */ - WARN_ON_FPU(fpu == ¤t->thread.fpu); + WARN_ON_FPU(fpu == x86_task_fpu(current)); __fpu_invalidate_fpregs_state(fpu); } @@ -70,7 +71,7 @@ static void fpu_force_restore(struct fpu *fpu) int xfpregs_get(struct task_struct *target, const struct user_regset *regset, struct membuf to) { - struct fpu *fpu = &target->thread.fpu; + struct fpu *fpu = x86_task_fpu(target); if (!cpu_feature_enabled(X86_FEATURE_FXSR)) return -ENODEV; @@ -90,7 +91,7 @@ int xfpregs_set(struct task_struct *target, const struct user_regset *regset, unsigned int pos, unsigned int count, const void *kbuf, const void __user *ubuf) { - struct fpu *fpu = &target->thread.fpu; + struct fpu *fpu = x86_task_fpu(target); struct fxregs_state newstate; int ret; @@ -132,7 +133,7 @@ int xstateregs_get(struct task_struct *target, const struct user_regset *regset, if (!cpu_feature_enabled(X86_FEATURE_XSAVE)) return -ENODEV; - sync_fpstate(&target->thread.fpu); + sync_fpstate(x86_task_fpu(target)); copy_xstate_to_uabi_buf(to, target, XSTATE_COPY_XSAVE); return 0; @@ -142,7 +143,7 @@ int xstateregs_set(struct task_struct *target, const struct user_regset *regset, unsigned int pos, unsigned int count, const void *kbuf, const void __user *ubuf) { - struct fpu *fpu = &target->thread.fpu; + struct fpu *fpu = x86_task_fpu(target); struct xregs_state *tmpbuf = NULL; int ret; @@ -174,6 +175,87 @@ out: return ret; } +#ifdef CONFIG_X86_USER_SHADOW_STACK +int ssp_active(struct task_struct *target, const struct user_regset *regset) +{ + if (target->thread.features & ARCH_SHSTK_SHSTK) + return regset->n; + + return 0; +} + +int ssp_get(struct task_struct *target, const struct user_regset *regset, + struct membuf to) +{ + struct fpu *fpu = x86_task_fpu(target); + struct cet_user_state *cetregs; + + if (!cpu_feature_enabled(X86_FEATURE_USER_SHSTK) || + !ssp_active(target, regset)) + return -ENODEV; + + sync_fpstate(fpu); + cetregs = get_xsave_addr(&fpu->fpstate->regs.xsave, XFEATURE_CET_USER); + if (WARN_ON(!cetregs)) { + /* + * This shouldn't ever be NULL because shadow stack was + * verified to be enabled above. This means + * MSR_IA32_U_CET.CET_SHSTK_EN should be 1 and so + * XFEATURE_CET_USER should not be in the init state. + */ + return -ENODEV; + } + + return membuf_write(&to, (unsigned long *)&cetregs->user_ssp, + sizeof(cetregs->user_ssp)); +} + +int ssp_set(struct task_struct *target, const struct user_regset *regset, + unsigned int pos, unsigned int count, + const void *kbuf, const void __user *ubuf) +{ + struct fpu *fpu = x86_task_fpu(target); + struct xregs_state *xsave = &fpu->fpstate->regs.xsave; + struct cet_user_state *cetregs; + unsigned long user_ssp; + int r; + + if (!cpu_feature_enabled(X86_FEATURE_USER_SHSTK) || + !ssp_active(target, regset)) + return -ENODEV; + + if (pos != 0 || count != sizeof(user_ssp)) + return -EINVAL; + + r = user_regset_copyin(&pos, &count, &kbuf, &ubuf, &user_ssp, 0, -1); + if (r) + return r; + + /* + * Some kernel instructions (IRET, etc) can cause exceptions in the case + * of disallowed CET register values. Just prevent invalid values. + */ + if (user_ssp >= TASK_SIZE_MAX || !IS_ALIGNED(user_ssp, 8)) + return -EINVAL; + + fpu_force_restore(fpu); + + cetregs = get_xsave_addr(xsave, XFEATURE_CET_USER); + if (WARN_ON(!cetregs)) { + /* + * This shouldn't ever be NULL because shadow stack was + * verified to be enabled above. This means + * MSR_IA32_U_CET.CET_SHSTK_EN should be 1 and so + * XFEATURE_CET_USER should not be in the init state. + */ + return -ENODEV; + } + + cetregs->user_ssp = user_ssp; + return 0; +} +#endif /* CONFIG_X86_USER_SHADOW_STACK */ + #if defined CONFIG_X86_32 || defined CONFIG_IA32_EMULATION /* @@ -286,7 +368,7 @@ static void __convert_from_fxsr(struct user_i387_ia32_struct *env, void convert_from_fxsr(struct user_i387_ia32_struct *env, struct task_struct *tsk) { - __convert_from_fxsr(env, tsk, &tsk->thread.fpu.fpstate->regs.fxsave); + __convert_from_fxsr(env, tsk, &x86_task_fpu(tsk)->fpstate->regs.fxsave); } void convert_to_fxsr(struct fxregs_state *fxsave, @@ -319,7 +401,7 @@ void convert_to_fxsr(struct fxregs_state *fxsave, int fpregs_get(struct task_struct *target, const struct user_regset *regset, struct membuf to) { - struct fpu *fpu = &target->thread.fpu; + struct fpu *fpu = x86_task_fpu(target); struct user_i387_ia32_struct env; struct fxregs_state fxsave, *fx; @@ -351,7 +433,7 @@ int fpregs_set(struct task_struct *target, const struct user_regset *regset, unsigned int pos, unsigned int count, const void *kbuf, const void __user *ubuf) { - struct fpu *fpu = &target->thread.fpu; + struct fpu *fpu = x86_task_fpu(target); struct user_i387_ia32_struct env; int ret; diff --git a/arch/x86/kernel/fpu/signal.c b/arch/x86/kernel/fpu/signal.c index 558076dbde5b..c3ec2512f2bb 100644 --- a/arch/x86/kernel/fpu/signal.c +++ b/arch/x86/kernel/fpu/signal.c @@ -27,19 +27,14 @@ static inline bool check_xstate_in_sigframe(struct fxregs_state __user *fxbuf, struct _fpx_sw_bytes *fx_sw) { - int min_xstate_size = sizeof(struct fxregs_state) + - sizeof(struct xstate_header); void __user *fpstate = fxbuf; unsigned int magic2; if (__copy_from_user(fx_sw, &fxbuf->sw_reserved[0], sizeof(*fx_sw))) return false; - /* Check for the first magic field and other error scenarios. */ - if (fx_sw->magic1 != FP_XSTATE_MAGIC1 || - fx_sw->xstate_size < min_xstate_size || - fx_sw->xstate_size > current->thread.fpu.fpstate->user_size || - fx_sw->xstate_size > fx_sw->extended_size) + /* Check for the first magic field */ + if (fx_sw->magic1 != FP_XSTATE_MAGIC1) goto setfx; /* @@ -48,13 +43,13 @@ static inline bool check_xstate_in_sigframe(struct fxregs_state __user *fxbuf, * fpstate layout with out copying the extended state information * in the memory layout. */ - if (__get_user(magic2, (__u32 __user *)(fpstate + fx_sw->xstate_size))) + if (__get_user(magic2, (__u32 __user *)(fpstate + x86_task_fpu(current)->fpstate->user_size))) return false; if (likely(magic2 == FP_XSTATE_MAGIC2)) return true; setfx: - trace_x86_fpu_xstate_check_failed(¤t->thread.fpu); + trace_x86_fpu_xstate_check_failed(x86_task_fpu(current)); /* Set the parameters for fx only state */ fx_sw->magic1 = 0; @@ -69,13 +64,13 @@ setfx: static inline bool save_fsave_header(struct task_struct *tsk, void __user *buf) { if (use_fxsr()) { - struct xregs_state *xsave = &tsk->thread.fpu.fpstate->regs.xsave; + struct xregs_state *xsave = &x86_task_fpu(tsk)->fpstate->regs.xsave; struct user_i387_ia32_struct env; struct _fpstate_32 __user *fp = buf; fpregs_lock(); if (!test_thread_flag(TIF_NEED_FPU_LOAD)) - fxsave(&tsk->thread.fpu.fpstate->regs.fxsave); + fxsave(&x86_task_fpu(tsk)->fpstate->regs.fxsave); fpregs_unlock(); convert_from_fxsr(&env, tsk); @@ -119,7 +114,6 @@ static inline bool save_xstate_epilog(void __user *buf, int ia32_frame, { struct xregs_state __user *x = buf; struct _fpx_sw_bytes sw_bytes = {}; - u32 xfeatures; int err; /* Setup the bytes not touched by the [f]xsave and reserved for SW. */ @@ -133,12 +127,6 @@ static inline bool save_xstate_epilog(void __user *buf, int ia32_frame, (__u32 __user *)(buf + fpstate->user_size)); /* - * Read the xfeatures which we copied (directly from the cpu or - * from the state in task struct) to the user buffers. - */ - err |= __get_user(xfeatures, (__u32 __user *)&x->header.xfeatures); - - /* * For legacy compatible, we always set FP/SSE bits in the bit * vector while saving the state to the user context. This will * enable us capturing any changes(during sigreturn) to @@ -149,17 +137,16 @@ static inline bool save_xstate_epilog(void __user *buf, int ia32_frame, * header as well as change any contents in the memory layout. * xrestore as part of sigreturn will capture all the changes. */ - xfeatures |= XFEATURE_MASK_FPSSE; - - err |= __put_user(xfeatures, (__u32 __user *)&x->header.xfeatures); + err |= set_xfeature_in_sigframe(x, XFEATURE_MASK_FPSSE); return !err; } -static inline int copy_fpregs_to_sigframe(struct xregs_state __user *buf) +static inline int copy_fpregs_to_sigframe(struct xregs_state __user *buf, u32 pkru) { if (use_xsave()) - return xsave_to_user_sigframe(buf); + return xsave_to_user_sigframe(buf, pkru); + if (use_fxsr()) return fxsave_to_user_sigframe((struct fxregs_state __user *) buf); else @@ -185,10 +172,10 @@ static inline int copy_fpregs_to_sigframe(struct xregs_state __user *buf) * For [f]xsave state, update the SW reserved fields in the [f]xsave frame * indicating the absence/presence of the extended state to the user. */ -bool copy_fpstate_to_sigframe(void __user *buf, void __user *buf_fx, int size) +bool copy_fpstate_to_sigframe(void __user *buf, void __user *buf_fx, int size, u32 pkru) { struct task_struct *tsk = current; - struct fpstate *fpstate = tsk->thread.fpu.fpstate; + struct fpstate *fpstate = x86_task_fpu(tsk)->fpstate; bool ia32_fxstate = (buf != buf_fx); int ret; @@ -228,7 +215,7 @@ retry: fpregs_restore_userregs(); pagefault_disable(); - ret = copy_fpregs_to_sigframe(buf_fx); + ret = copy_fpregs_to_sigframe(buf_fx, pkru); pagefault_enable(); fpregs_unlock(); @@ -274,12 +261,13 @@ static int __restore_fpregs_from_user(void __user *buf, u64 ufeatures, * Attempt to restore the FPU registers directly from user memory. * Pagefaults are handled and any errors returned are fatal. */ -static bool restore_fpregs_from_user(void __user *buf, u64 xrestore, - bool fx_only, unsigned int size) +static bool restore_fpregs_from_user(void __user *buf, u64 xrestore, bool fx_only) { - struct fpu *fpu = ¤t->thread.fpu; + struct fpu *fpu = x86_task_fpu(current); int ret; + /* Restore enabled features only. */ + xrestore &= fpu->fpstate->user_xfeatures; retry: fpregs_lock(); /* Ensure that XFD is up to date */ @@ -309,7 +297,7 @@ retry: if (ret != X86_TRAP_PF) return false; - if (!fault_in_readable(buf, size)) + if (!fault_in_readable(buf, fpu->fpstate->user_size)) goto retry; return false; } @@ -335,11 +323,10 @@ static bool __fpu_restore_sig(void __user *buf, void __user *buf_fx, bool ia32_fxstate) { struct task_struct *tsk = current; - struct fpu *fpu = &tsk->thread.fpu; + struct fpu *fpu = x86_task_fpu(tsk); struct user_i387_ia32_struct env; bool success, fx_only = false; union fpregs_state *fpregs; - unsigned int state_size; u64 user_xfeatures = 0; if (use_xsave()) { @@ -349,17 +336,14 @@ static bool __fpu_restore_sig(void __user *buf, void __user *buf_fx, return false; fx_only = !fx_sw_user.magic1; - state_size = fx_sw_user.xstate_size; user_xfeatures = fx_sw_user.xfeatures; } else { user_xfeatures = XFEATURE_MASK_FPSSE; - state_size = fpu->fpstate->user_size; } if (likely(!ia32_fxstate)) { /* Restore the FPU registers directly from user memory. */ - return restore_fpregs_from_user(buf_fx, user_xfeatures, fx_only, - state_size); + return restore_fpregs_from_user(buf_fx, user_xfeatures, fx_only); } /* @@ -459,7 +443,7 @@ static inline unsigned int xstate_sigframe_size(struct fpstate *fpstate) */ bool fpu__restore_sig(void __user *buf, int ia32_frame) { - struct fpu *fpu = ¤t->thread.fpu; + struct fpu *fpu = x86_task_fpu(current); void __user *buf_fx = buf; bool ia32_fxstate = false; bool success = false; @@ -506,7 +490,7 @@ unsigned long fpu__alloc_mathframe(unsigned long sp, int ia32_frame, unsigned long *buf_fx, unsigned long *size) { - unsigned long frame_size = xstate_sigframe_size(current->thread.fpu.fpstate); + unsigned long frame_size = xstate_sigframe_size(x86_task_fpu(current)->fpstate); *buf_fx = sp = round_down(sp - frame_size, 64); if (ia32_frame && use_fxsr()) { diff --git a/arch/x86/kernel/fpu/xstate.c b/arch/x86/kernel/fpu/xstate.c index 714166cc25f2..48113c5193aa 100644 --- a/arch/x86/kernel/fpu/xstate.c +++ b/arch/x86/kernel/fpu/xstate.c @@ -8,21 +8,28 @@ #include <linux/compat.h> #include <linux/cpu.h> #include <linux/mman.h> +#include <linux/kvm_types.h> #include <linux/nospec.h> #include <linux/pkeys.h> #include <linux/seq_file.h> #include <linux/proc_fs.h> #include <linux/vmalloc.h> +#include <linux/coredump.h> +#include <linux/sort.h> #include <asm/fpu/api.h> #include <asm/fpu/regset.h> #include <asm/fpu/signal.h> #include <asm/fpu/xcr.h> +#include <asm/cpuid/api.h> +#include <asm/msr.h> #include <asm/tlbflush.h> #include <asm/prctl.h> #include <asm/elf.h> +#include <uapi/asm/elf.h> + #include "context.h" #include "internal.h" #include "legacy.h" @@ -39,26 +46,27 @@ */ static const char *xfeature_names[] = { - "x87 floating point registers" , - "SSE registers" , - "AVX registers" , - "MPX bounds registers" , - "MPX CSR" , - "AVX-512 opmask" , - "AVX-512 Hi256" , - "AVX-512 ZMM_Hi256" , - "Processor Trace (unused)" , + "x87 floating point registers", + "SSE registers", + "AVX registers", + "MPX bounds registers", + "MPX CSR", + "AVX-512 opmask", + "AVX-512 Hi256", + "AVX-512 ZMM_Hi256", + "Processor Trace (unused)", "Protection Keys User registers", "PASID state", - "unknown xstate feature" , - "unknown xstate feature" , - "unknown xstate feature" , - "unknown xstate feature" , - "unknown xstate feature" , - "unknown xstate feature" , - "AMX Tile config" , - "AMX Tile data" , - "unknown xstate feature" , + "Control-flow User registers", + "Control-flow Kernel registers (KVM only)", + "unknown xstate feature", + "unknown xstate feature", + "unknown xstate feature", + "unknown xstate feature", + "AMX Tile config", + "AMX Tile data", + "APX registers", + "unknown xstate feature", }; static unsigned short xsave_cpuid_features[] __initdata = { @@ -71,10 +79,13 @@ static unsigned short xsave_cpuid_features[] __initdata = { [XFEATURE_ZMM_Hi256] = X86_FEATURE_AVX512F, [XFEATURE_Hi16_ZMM] = X86_FEATURE_AVX512F, [XFEATURE_PT_UNIMPLEMENTED_SO_FAR] = X86_FEATURE_INTEL_PT, - [XFEATURE_PKRU] = X86_FEATURE_PKU, + [XFEATURE_PKRU] = X86_FEATURE_OSPKE, [XFEATURE_PASID] = X86_FEATURE_ENQCMD, + [XFEATURE_CET_USER] = X86_FEATURE_SHSTK, + [XFEATURE_CET_KERNEL] = X86_FEATURE_SHSTK, [XFEATURE_XTILE_CFG] = X86_FEATURE_AMX_TILE, [XFEATURE_XTILE_DATA] = X86_FEATURE_AMX_TILE, + [XFEATURE_APX] = X86_FEATURE_APX, }; static unsigned int xstate_offsets[XFEATURE_MAX] __ro_after_init = @@ -83,6 +94,31 @@ static unsigned int xstate_sizes[XFEATURE_MAX] __ro_after_init = { [ 0 ... XFEATURE_MAX - 1] = -1}; static unsigned int xstate_flags[XFEATURE_MAX] __ro_after_init; +/* + * Ordering of xstate components in uncompacted format: The xfeature + * number does not necessarily indicate its position in the XSAVE buffer. + * This array defines the traversal order of xstate features. + */ +static unsigned int xfeature_uncompact_order[XFEATURE_MAX] __ro_after_init = + { [ 0 ... XFEATURE_MAX - 1] = -1}; + +static inline unsigned int next_xfeature_order(unsigned int i, u64 mask) +{ + for (; xfeature_uncompact_order[i] != -1; i++) { + if (mask & BIT_ULL(xfeature_uncompact_order[i])) + break; + } + + return i; +} + +/* Iterate xstate features in uncompacted order: */ +#define for_each_extended_xfeature_in_order(i, mask) \ + for (i = 0; \ + i = next_xfeature_order(i, mask), \ + xfeature_uncompact_order[i] != -1; \ + i++) + #define XSTATE_FLAG_SUPERVISOR BIT(0) #define XSTATE_FLAG_ALIGNED64 BIT(1) @@ -177,10 +213,11 @@ void fpu__init_cpu_xstate(void) * Must happen after CR4 setup and before xsetbv() to allow KVM * lazy passthrough. Write independent of the dynamic state static * key as that does not work on the boot CPU. This also ensures - * that any stale state is wiped out from XFD. + * that any stale state is wiped out from XFD. Reset the per CPU + * xfd cache too. */ if (cpu_feature_enabled(X86_FEATURE_XFD)) - wrmsrl(MSR_IA32_XFD, init_fpstate.xfd); + xfd_set_state(init_fpstate.xfd); /* * XCR_XFEATURE_ENABLED_MASK (aka. XCR0) sets user features @@ -193,7 +230,7 @@ void fpu__init_cpu_xstate(void) * MSR_IA32_XSS sets supervisor states managed by XSAVES. */ if (boot_cpu_has(X86_FEATURE_XSAVES)) { - wrmsrl(MSR_IA32_XSS, xfeatures_mask_supervisor() | + wrmsrq(MSR_IA32_XSS, xfeatures_mask_supervisor() | xfeatures_mask_independent()); } } @@ -203,16 +240,20 @@ static bool xfeature_enabled(enum xfeature xfeature) return fpu_kernel_cfg.max_features & BIT_ULL(xfeature); } +static int compare_xstate_offsets(const void *xfeature1, const void *xfeature2) +{ + return xstate_offsets[*(unsigned int *)xfeature1] - + xstate_offsets[*(unsigned int *)xfeature2]; +} + /* * Record the offsets and sizes of various xstates contained - * in the XSAVE state memory layout. + * in the XSAVE state memory layout. Also, create an ordered + * list of xfeatures for handling out-of-order offsets. */ static void __init setup_xstate_cache(void) { - u32 eax, ebx, ecx, edx, i; - /* start at the beginning of the "extended state" */ - unsigned int last_good_offset = offsetof(struct xregs_state, - extended_state_area); + u32 eax, ebx, ecx, edx, xfeature, i = 0; /* * The FP xstates and SSE xstates are legacy states. They are always * in the fixed offsets in the xsave area in either compacted form @@ -226,39 +267,30 @@ static void __init setup_xstate_cache(void) xstate_sizes[XFEATURE_SSE] = sizeof_field(struct fxregs_state, xmm_space); - for_each_extended_xfeature(i, fpu_kernel_cfg.max_features) { - cpuid_count(XSTATE_CPUID, i, &eax, &ebx, &ecx, &edx); + for_each_extended_xfeature(xfeature, fpu_kernel_cfg.max_features) { + cpuid_count(CPUID_LEAF_XSTATE, xfeature, &eax, &ebx, &ecx, &edx); - xstate_sizes[i] = eax; - xstate_flags[i] = ecx; + xstate_sizes[xfeature] = eax; + xstate_flags[xfeature] = ecx; /* * If an xfeature is supervisor state, the offset in EBX is * invalid, leave it to -1. */ - if (xfeature_is_supervisor(i)) + if (xfeature_is_supervisor(xfeature)) continue; - xstate_offsets[i] = ebx; + xstate_offsets[xfeature] = ebx; - /* - * 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); - - last_good_offset = xstate_offsets[i]; + /* Populate the list of xfeatures before sorting */ + xfeature_uncompact_order[i++] = xfeature; } -} - -static void __init print_xstate_feature(u64 xstate_mask) -{ - const char *feature_name; - if (cpu_has_xfeatures(xstate_mask, &feature_name)) - pr_info("x86/fpu: Supporting XSAVE feature 0x%03Lx: '%s'\n", xstate_mask, feature_name); + /* + * Sort xfeatures by their offsets to support out-of-order + * offsets in the uncompacted format. + */ + sort(xfeature_uncompact_order, i, sizeof(unsigned int), compare_xstate_offsets, NULL); } /* @@ -266,18 +298,15 @@ static void __init print_xstate_feature(u64 xstate_mask) */ static void __init print_xstate_features(void) { - print_xstate_feature(XFEATURE_MASK_FP); - print_xstate_feature(XFEATURE_MASK_SSE); - print_xstate_feature(XFEATURE_MASK_YMM); - print_xstate_feature(XFEATURE_MASK_BNDREGS); - print_xstate_feature(XFEATURE_MASK_BNDCSR); - print_xstate_feature(XFEATURE_MASK_OPMASK); - print_xstate_feature(XFEATURE_MASK_ZMM_Hi256); - print_xstate_feature(XFEATURE_MASK_Hi16_ZMM); - print_xstate_feature(XFEATURE_MASK_PKRU); - print_xstate_feature(XFEATURE_MASK_PASID); - print_xstate_feature(XFEATURE_MASK_XTILE_CFG); - print_xstate_feature(XFEATURE_MASK_XTILE_DATA); + int i; + + for (i = 0; i < XFEATURE_MAX; i++) { + u64 mask = BIT_ULL(i); + const char *name; + + if (cpu_has_xfeatures(mask, &name)) + pr_info("x86/fpu: Supporting XSAVE feature 0x%03Lx: '%s'\n", mask, name); + } } /* @@ -344,7 +373,10 @@ static __init void os_xrstor_booting(struct xregs_state *xstate) XFEATURE_MASK_BNDREGS | \ XFEATURE_MASK_BNDCSR | \ XFEATURE_MASK_PASID | \ - XFEATURE_MASK_XTILE) + XFEATURE_MASK_CET_USER | \ + XFEATURE_MASK_CET_KERNEL | \ + XFEATURE_MASK_XTILE | \ + XFEATURE_MASK_APX) /* * setup the xstate image representing the init state @@ -391,7 +423,7 @@ int xfeature_size(int xfeature_nr) u32 eax, ebx, ecx, edx; CHECK_XFEATURE(xfeature_nr); - cpuid_count(XSTATE_CPUID, xfeature_nr, &eax, &ebx, &ecx, &edx); + cpuid_count(CPUID_LEAF_XSTATE, xfeature_nr, &eax, &ebx, &ecx, &edx); return eax; } @@ -434,9 +466,9 @@ static void __init __xstate_dump_leaves(void) * just in case there are some goodies up there */ for (i = 0; i < XFEATURE_MAX + 10; i++) { - cpuid_count(XSTATE_CPUID, i, &eax, &ebx, &ecx, &edx); + cpuid_count(CPUID_LEAF_XSTATE, i, &eax, &ebx, &ecx, &edx); pr_warn("CPUID[%02x, %02x]: eax=%08x ebx=%08x ecx=%08x edx=%08x\n", - XSTATE_CPUID, i, eax, ebx, ecx, edx); + CPUID_LEAF_XSTATE, i, eax, ebx, ecx, edx); } } @@ -446,14 +478,15 @@ static void __init __xstate_dump_leaves(void) } \ } while (0) -#define XCHECK_SZ(sz, nr, nr_macro, __struct) do { \ - if ((nr == nr_macro) && \ - WARN_ONCE(sz != sizeof(__struct), \ - "%s: struct is %zu bytes, cpu state %d bytes\n", \ - __stringify(nr_macro), sizeof(__struct), sz)) { \ +#define XCHECK_SZ(sz, nr, __struct) ({ \ + if (WARN_ONCE(sz != sizeof(__struct), \ + "[%s]: struct is %zu bytes, cpu state %d bytes\n", \ + xfeature_names[nr], sizeof(__struct), sz)) { \ __xstate_dump_leaves(); \ } \ -} while (0) + true; \ +}) + /** * check_xtile_data_against_struct - Check tile data state size. @@ -476,7 +509,7 @@ static int __init check_xtile_data_against_struct(int size) * Check the maximum palette id: * eax: the highest numbered palette subleaf. */ - cpuid_count(TILE_CPUID, 0, &max_palid, &ebx, &ecx, &edx); + cpuid_count(CPUID_LEAF_TILE, 0, &max_palid, &ebx, &ecx, &edx); /* * Cross-check each tile size and find the maximum number of @@ -490,7 +523,7 @@ static int __init check_xtile_data_against_struct(int size) * eax[31:16]: bytes per title * ebx[31:16]: the max names (or max number of tiles) */ - cpuid_count(TILE_CPUID, palid, &eax, &ebx, &edx, &edx); + cpuid_count(CPUID_LEAF_TILE, palid, &eax, &ebx, &edx, &edx); tile_size = eax >> 16; max = ebx >> 16; @@ -527,49 +560,50 @@ static bool __init check_xstate_against_struct(int nr) * Ask the CPU for the size of the state. */ int sz = xfeature_size(nr); + /* * Match each CPU state with the corresponding software * structure. */ - XCHECK_SZ(sz, nr, XFEATURE_YMM, struct ymmh_struct); - XCHECK_SZ(sz, nr, XFEATURE_BNDREGS, struct mpx_bndreg_state); - XCHECK_SZ(sz, nr, XFEATURE_BNDCSR, struct mpx_bndcsr_state); - XCHECK_SZ(sz, nr, XFEATURE_OPMASK, struct avx_512_opmask_state); - XCHECK_SZ(sz, nr, XFEATURE_ZMM_Hi256, struct avx_512_zmm_uppers_state); - XCHECK_SZ(sz, nr, XFEATURE_Hi16_ZMM, struct avx_512_hi16_state); - XCHECK_SZ(sz, nr, XFEATURE_PKRU, struct pkru_state); - XCHECK_SZ(sz, nr, XFEATURE_PASID, struct ia32_pasid_state); - XCHECK_SZ(sz, nr, XFEATURE_XTILE_CFG, struct xtile_cfg); - - /* The tile data size varies between implementations. */ - if (nr == XFEATURE_XTILE_DATA) - check_xtile_data_against_struct(sz); - - /* - * Make *SURE* to add any feature numbers in below if - * there are "holes" in the xsave state component - * numbers. - */ - if ((nr < XFEATURE_YMM) || - (nr >= XFEATURE_MAX) || - (nr == XFEATURE_PT_UNIMPLEMENTED_SO_FAR) || - ((nr >= XFEATURE_RSRVD_COMP_11) && (nr <= XFEATURE_RSRVD_COMP_16))) { + switch (nr) { + case XFEATURE_YMM: return XCHECK_SZ(sz, nr, struct ymmh_struct); + case XFEATURE_BNDREGS: return XCHECK_SZ(sz, nr, struct mpx_bndreg_state); + case XFEATURE_BNDCSR: return XCHECK_SZ(sz, nr, struct mpx_bndcsr_state); + case XFEATURE_OPMASK: return XCHECK_SZ(sz, nr, struct avx_512_opmask_state); + case XFEATURE_ZMM_Hi256: return XCHECK_SZ(sz, nr, struct avx_512_zmm_uppers_state); + case XFEATURE_Hi16_ZMM: return XCHECK_SZ(sz, nr, struct avx_512_hi16_state); + case XFEATURE_PKRU: return XCHECK_SZ(sz, nr, struct pkru_state); + case XFEATURE_PASID: return XCHECK_SZ(sz, nr, struct ia32_pasid_state); + case XFEATURE_XTILE_CFG: return XCHECK_SZ(sz, nr, struct xtile_cfg); + case XFEATURE_CET_USER: return XCHECK_SZ(sz, nr, struct cet_user_state); + case XFEATURE_CET_KERNEL: return XCHECK_SZ(sz, nr, struct cet_supervisor_state); + case XFEATURE_APX: return XCHECK_SZ(sz, nr, struct apx_state); + case XFEATURE_XTILE_DATA: check_xtile_data_against_struct(sz); return true; + default: XSTATE_WARN_ON(1, "No structure for xstate: %d\n", nr); return false; } + return true; } static unsigned int xstate_calculate_size(u64 xfeatures, bool compacted) { unsigned int topmost = fls64(xfeatures) - 1; - unsigned int offset = xstate_offsets[topmost]; + unsigned int offset, i; if (topmost <= XFEATURE_SSE) return sizeof(struct xregs_state); - if (compacted) + if (compacted) { offset = xfeature_get_offset(xfeatures, topmost); + } else { + /* Walk through the xfeature order to pick the last */ + for_each_extended_xfeature_in_order(i, xfeatures) + topmost = xfeature_uncompact_order[i]; + offset = xstate_offsets[topmost]; + } + return offset + xstate_sizes[topmost]; } @@ -633,7 +667,7 @@ static unsigned int __init get_compacted_size(void) * are no supervisor states, but XSAVEC still uses compacted * format. */ - cpuid_count(XSTATE_CPUID, 1, &eax, &ebx, &ecx, &edx); + cpuid_count(CPUID_LEAF_XSTATE, 1, &eax, &ebx, &ecx, &edx); return ebx; } @@ -650,7 +684,7 @@ static unsigned int __init get_xsave_compacted_size(void) return get_compacted_size(); /* Disable independent features. */ - wrmsrl(MSR_IA32_XSS, xfeatures_mask_supervisor()); + wrmsrq(MSR_IA32_XSS, xfeatures_mask_supervisor()); /* * Ask the hardware what size is required of the buffer. @@ -659,7 +693,7 @@ static unsigned int __init get_xsave_compacted_size(void) size = get_compacted_size(); /* Re-enable independent features so XSAVES will work on them again. */ - wrmsrl(MSR_IA32_XSS, xfeatures_mask_supervisor() | mask); + wrmsrq(MSR_IA32_XSS, xfeatures_mask_supervisor() | mask); return size; } @@ -674,7 +708,7 @@ static unsigned int __init get_xsave_size_user(void) * containing all the *user* state components * corresponding to bits currently set in XCR0. */ - cpuid_count(XSTATE_CPUID, 0, &eax, &ebx, &ecx, &edx); + cpuid_count(CPUID_LEAF_XSTATE, 0, &eax, &ebx, &ecx, &edx); return ebx; } @@ -713,6 +747,9 @@ static int __init init_xstate_size(void) fpu_user_cfg.default_size = xstate_calculate_size(fpu_user_cfg.default_features, false); + guest_default_cfg.size = + xstate_calculate_size(guest_default_cfg.features, compacted); + return 0; } @@ -722,6 +759,8 @@ static int __init init_xstate_size(void) */ static void __init fpu__init_disable_system_xstate(unsigned int legacy_size) { + pr_info("x86/fpu: XSAVE disabled\n"); + fpu_kernel_cfg.max_features = 0; cr4_clear_bits(X86_CR4_OSXSAVE); setup_clear_cpu_cap(X86_FEATURE_XSAVE); @@ -731,6 +770,7 @@ static void __init fpu__init_disable_system_xstate(unsigned int legacy_size) fpu_kernel_cfg.default_size = legacy_size; fpu_user_cfg.max_size = legacy_size; fpu_user_cfg.default_size = legacy_size; + guest_default_cfg.size = legacy_size; /* * Prevent enabling the static branch which enables writes to the @@ -738,7 +778,25 @@ static void __init fpu__init_disable_system_xstate(unsigned int legacy_size) */ init_fpstate.xfd = 0; - fpstate_reset(¤t->thread.fpu); + fpstate_reset(x86_task_fpu(current)); +} + +static u64 __init host_default_mask(void) +{ + /* + * Exclude dynamic features (require userspace opt-in) and features + * that are supported only for KVM guests. + */ + return ~((u64)XFEATURE_MASK_USER_DYNAMIC | XFEATURE_MASK_GUEST_SUPERVISOR); +} + +static u64 __init guest_default_mask(void) +{ + /* + * Exclude dynamic features, which require userspace opt-in even + * for KVM guests. + */ + return ~(u64)XFEATURE_MASK_USER_DYNAMIC; } /* @@ -763,21 +821,16 @@ void __init fpu__init_system_xstate(unsigned int legacy_size) return; } - if (boot_cpu_data.cpuid_level < XSTATE_CPUID) { - WARN_ON_FPU(1); - return; - } - /* * Find user xstates supported by the processor. */ - cpuid_count(XSTATE_CPUID, 0, &eax, &ebx, &ecx, &edx); + cpuid_count(CPUID_LEAF_XSTATE, 0, &eax, &ebx, &ecx, &edx); fpu_kernel_cfg.max_features = eax + ((u64)edx << 32); /* * Find supervisor xstates supported by the processor. */ - cpuid_count(XSTATE_CPUID, 1, &eax, &ebx, &ecx, &edx); + cpuid_count(CPUID_LEAF_XSTATE, 1, &eax, &ebx, &ecx, &edx); fpu_kernel_cfg.max_features |= ecx + ((u64)edx << 32); if ((fpu_kernel_cfg.max_features & XFEATURE_MASK_FPSSE) != XFEATURE_MASK_FPSSE) { @@ -791,6 +844,20 @@ void __init fpu__init_system_xstate(unsigned int legacy_size) goto out_disable; } + if (fpu_kernel_cfg.max_features & XFEATURE_MASK_APX && + fpu_kernel_cfg.max_features & (XFEATURE_MASK_BNDREGS | XFEATURE_MASK_BNDCSR)) { + /* + * This is a problematic CPU configuration where two + * conflicting state components are both enumerated. + */ + pr_err("x86/fpu: Both APX/MPX present in the CPU's xstate features: 0x%llx.\n", + fpu_kernel_cfg.max_features); + goto out_disable; + } + + fpu_kernel_cfg.independent_features = fpu_kernel_cfg.max_features & + XFEATURE_MASK_INDEPENDENT; + /* * Clear XSAVE features that are disabled in the normal CPUID. */ @@ -814,12 +881,13 @@ void __init fpu__init_system_xstate(unsigned int legacy_size) fpu_user_cfg.max_features = fpu_kernel_cfg.max_features; fpu_user_cfg.max_features &= XFEATURE_MASK_USER_SUPPORTED; - /* Clean out dynamic features from default */ - fpu_kernel_cfg.default_features = fpu_kernel_cfg.max_features; - fpu_kernel_cfg.default_features &= ~XFEATURE_MASK_USER_DYNAMIC; - - fpu_user_cfg.default_features = fpu_user_cfg.max_features; - fpu_user_cfg.default_features &= ~XFEATURE_MASK_USER_DYNAMIC; + /* + * Now, given maximum feature set, determine default values by + * applying default masks. + */ + fpu_kernel_cfg.default_features = fpu_kernel_cfg.max_features & host_default_mask(); + fpu_user_cfg.default_features = fpu_user_cfg.max_features & host_default_mask(); + guest_default_cfg.features = fpu_kernel_cfg.max_features & guest_default_mask(); /* Store it for paranoia check at the end */ xfeatures = fpu_kernel_cfg.max_features; @@ -847,9 +915,6 @@ void __init fpu__init_system_xstate(unsigned int legacy_size) if (err) goto out_disable; - /* Reset the state for the current task */ - fpstate_reset(¤t->thread.fpu); - /* * Update info used for ptrace frames; use standard-format size and no * supervisor xstates: @@ -865,7 +930,7 @@ void __init fpu__init_system_xstate(unsigned int legacy_size) init_fpstate.xfeatures = fpu_kernel_cfg.default_features; if (init_fpstate.size > sizeof(init_fpstate.regs)) { - pr_warn("x86/fpu: init_fpstate buffer too small (%zu < %d), disabling XSAVE\n", + pr_warn("x86/fpu: init_fpstate buffer too small (%zu < %d)\n", sizeof(init_fpstate.regs), init_fpstate.size); goto out_disable; } @@ -877,11 +942,18 @@ void __init fpu__init_system_xstate(unsigned int legacy_size) * xfeatures mask. */ if (xfeatures != fpu_kernel_cfg.max_features) { - pr_err("x86/fpu: xfeatures modified from 0x%016llx to 0x%016llx during init, disabling XSAVE\n", + pr_err("x86/fpu: xfeatures modified from 0x%016llx to 0x%016llx during init\n", xfeatures, fpu_kernel_cfg.max_features); goto out_disable; } + /* + * CPU capabilities initialization runs before FPU init. So + * X86_FEATURE_OSXSAVE is not set. Now that XSAVE is completely + * functional, set the feature bit so depending code works. + */ + setup_force_cpu_cap(X86_FEATURE_OSXSAVE); + print_xstate_offset_size(); pr_info("x86/fpu: Enabled xstate features 0x%llx, context size is %d bytes, using '%s' format.\n", fpu_kernel_cfg.max_features, @@ -910,12 +982,12 @@ void fpu__resume_cpu(void) * of XSAVES and MSR_IA32_XSS. */ if (cpu_feature_enabled(X86_FEATURE_XSAVES)) { - wrmsrl(MSR_IA32_XSS, xfeatures_mask_supervisor() | + wrmsrq(MSR_IA32_XSS, xfeatures_mask_supervisor() | xfeatures_mask_independent()); } if (fpu_state_size_dynamic()) - wrmsrl(MSR_IA32_XFD, current->thread.fpu.fpstate->xfd); + wrmsrq(MSR_IA32_XFD, x86_task_fpu(current)->fpstate->xfd); } /* @@ -987,6 +1059,20 @@ void *get_xsave_addr(struct xregs_state *xsave, int xfeature_nr) return __raw_xsave_addr(xsave, xfeature_nr); } +EXPORT_SYMBOL_FOR_KVM(get_xsave_addr); + +/* + * Given an xstate feature nr, calculate where in the xsave buffer the state is. + * The xsave buffer should be in standard format, not compacted (e.g. user mode + * signal frames). + */ +void __user *get_xsave_addr_user(struct xregs_state __user *xsave, int xfeature_nr) +{ + if (WARN_ON_ONCE(!xfeature_enabled(xfeature_nr))) + return NULL; + + return (void __user *)xsave + xstate_offsets[xfeature_nr]; +} #ifdef CONFIG_ARCH_HAS_PKEYS @@ -1046,6 +1132,7 @@ static void copy_feature(bool from_xstate, struct membuf *to, void *xstate, * __copy_xstate_to_uabi_buf - Copy kernel saved xstate to a UABI buffer * @to: membuf descriptor * @fpstate: The fpstate buffer from which to copy + * @xfeatures: The mask of xfeatures to save (XSAVE mode only) * @pkru_val: The PKRU value to store in the PKRU component * @copy_mode: The requested copy mode * @@ -1056,15 +1143,15 @@ static void copy_feature(bool from_xstate, struct membuf *to, void *xstate, * It supports partial copy but @to.pos always starts from zero. */ void __copy_xstate_to_uabi_buf(struct membuf to, struct fpstate *fpstate, - u32 pkru_val, enum xstate_copy_mode copy_mode) + u64 xfeatures, u32 pkru_val, + enum xstate_copy_mode copy_mode) { const unsigned int off_mxcsr = offsetof(struct fxregs_state, mxcsr); struct xregs_state *xinit = &init_fpstate.regs.xsave; struct xregs_state *xsave = &fpstate->regs.xsave; + unsigned int zerofrom, i, xfeature; struct xstate_header header; - unsigned int zerofrom; u64 mask; - int i; memset(&header, 0, sizeof(header)); header.xfeatures = xsave->header.xfeatures; @@ -1080,7 +1167,7 @@ void __copy_xstate_to_uabi_buf(struct membuf to, struct fpstate *fpstate, break; case XSTATE_COPY_XSAVE: - header.xfeatures &= fpstate->user_xfeatures; + header.xfeatures &= fpstate->user_xfeatures & xfeatures; break; } @@ -1118,31 +1205,31 @@ void __copy_xstate_to_uabi_buf(struct membuf to, struct fpstate *fpstate, zerofrom = offsetof(struct xregs_state, extended_state_area); /* - * The ptrace buffer is in non-compacted XSAVE format. In - * non-compacted format disabled features still occupy state space, - * but there is no state to copy from in the compacted - * init_fpstate. The gap tracking will zero these states. - */ - mask = fpstate->user_xfeatures; - - /* - * Dynamic features are not present in init_fpstate. When they are - * in an all zeros init state, remove those from 'mask' to zero - * those features in the user buffer instead of retrieving them - * from init_fpstate. + * This 'mask' indicates which states to copy from fpstate. + * Those extended states that are not present in fpstate are + * either disabled or initialized: + * + * In non-compacted format, disabled features still occupy + * state space but there is no state to copy from in the + * compacted init_fpstate. The gap tracking will zero these + * states. + * + * The extended features have an all zeroes init state. Thus, + * remove them from 'mask' to zero those features in the user + * buffer instead of retrieving them from init_fpstate. */ - if (fpu_state_size_dynamic()) - mask &= (header.xfeatures | xinit->header.xcomp_bv); + mask = header.xfeatures; - for_each_extended_xfeature(i, mask) { + for_each_extended_xfeature_in_order(i, mask) { + xfeature = xfeature_uncompact_order[i]; /* * If there was a feature or alignment gap, zero the space * in the destination buffer. */ - if (zerofrom < xstate_offsets[i]) - membuf_zero(&to, xstate_offsets[i] - zerofrom); + if (zerofrom < xstate_offsets[xfeature]) + membuf_zero(&to, xstate_offsets[xfeature] - zerofrom); - if (i == XFEATURE_PKRU) { + if (xfeature == XFEATURE_PKRU) { struct pkru_state pkru = {0}; /* * PKRU is not necessarily up to date in the @@ -1151,16 +1238,15 @@ void __copy_xstate_to_uabi_buf(struct membuf to, struct fpstate *fpstate, pkru.pkru = pkru_val; membuf_write(&to, &pkru, sizeof(pkru)); } else { - copy_feature(header.xfeatures & BIT_ULL(i), &to, - __raw_xsave_addr(xsave, i), - __raw_xsave_addr(xinit, i), - xstate_sizes[i]); + membuf_write(&to, + __raw_xsave_addr(xsave, xfeature), + xstate_sizes[xfeature]); } /* * Keep track of the last copied state in the non-compacted * target buffer for gap zeroing. */ - zerofrom = xstate_offsets[i] + xstate_sizes[i]; + zerofrom = xstate_offsets[xfeature] + xstate_sizes[xfeature]; } out: @@ -1183,7 +1269,8 @@ out: void copy_xstate_to_uabi_buf(struct membuf to, struct task_struct *tsk, enum xstate_copy_mode copy_mode) { - __copy_xstate_to_uabi_buf(to, tsk->thread.fpu.fpstate, + __copy_xstate_to_uabi_buf(to, x86_task_fpu(tsk)->fpstate, + x86_task_fpu(tsk)->fpstate->user_xfeatures, tsk->thread.pkru, copy_mode); } @@ -1323,7 +1410,7 @@ int copy_uabi_from_kernel_to_xstate(struct fpstate *fpstate, const void *kbuf, u int copy_sigframe_from_user_to_xstate(struct task_struct *tsk, const void __user *ubuf) { - return copy_uabi_to_xstate(tsk->thread.fpu.fpstate, NULL, ubuf, &tsk->thread.pkru); + return copy_uabi_to_xstate(x86_task_fpu(tsk)->fpstate, NULL, ubuf, &tsk->thread.pkru); } static bool validate_independent_components(u64 mask) @@ -1389,14 +1476,14 @@ void xrstors(struct xregs_state *xstate, u64 mask) } #if IS_ENABLED(CONFIG_KVM) -void fpstate_clear_xstate_component(struct fpstate *fps, unsigned int xfeature) +void fpstate_clear_xstate_component(struct fpstate *fpstate, unsigned int xfeature) { - void *addr = get_xsave_addr(&fps->regs.xsave, xfeature); + void *addr = get_xsave_addr(&fpstate->regs.xsave, xfeature); if (addr) memset(addr, 0, xstate_sizes[xfeature]); } -EXPORT_SYMBOL_GPL(fpstate_clear_xstate_component); +EXPORT_SYMBOL_FOR_KVM(fpstate_clear_xstate_component); #endif #ifdef CONFIG_X86_64 @@ -1417,7 +1504,7 @@ static bool xstate_op_valid(struct fpstate *fpstate, u64 mask, bool rstor) * The XFD MSR does not match fpstate->xfd. That's invalid when * the passed in fpstate is current's fpstate. */ - if (fpstate->xfd == current->thread.fpu.fpstate->xfd) + if (fpstate->xfd == x86_task_fpu(current)->fpstate->xfd) return false; /* @@ -1429,8 +1516,8 @@ static bool xstate_op_valid(struct fpstate *fpstate, u64 mask, bool rstor) return rstor; /* - * XSAVE(S): clone(), fpu_swap_kvm_fpu() - * XRSTORS(S): fpu_swap_kvm_fpu() + * XSAVE(S): clone(), fpu_swap_kvm_fpstate() + * XRSTORS(S): fpu_swap_kvm_fpstate() */ /* @@ -1494,7 +1581,7 @@ void fpstate_free(struct fpu *fpu) static int fpstate_realloc(u64 xfeatures, unsigned int ksize, unsigned int usize, struct fpu_guest *guest_fpu) { - struct fpu *fpu = ¤t->thread.fpu; + struct fpu *fpu = x86_task_fpu(current); struct fpstate *curfps, *newfps = NULL; unsigned int fpsize; bool in_use; @@ -1535,10 +1622,7 @@ static int fpstate_realloc(u64 xfeatures, unsigned int ksize, fpregs_restore_userregs(); newfps->xfeatures = curfps->xfeatures | xfeatures; - - if (!guest_fpu) - newfps->user_xfeatures = curfps->user_xfeatures | xfeatures; - + newfps->user_xfeatures = curfps->user_xfeatures | xfeatures; newfps->xfd = curfps->xfd & ~xfeatures; /* Do the final updates within the locked region */ @@ -1590,7 +1674,7 @@ static int __xstate_request_perm(u64 permitted, u64 requested, bool guest) * AVX512. */ bool compacted = cpu_feature_enabled(X86_FEATURE_XCOMPACTED); - struct fpu *fpu = ¤t->group_leader->thread.fpu; + struct fpu *fpu = x86_task_fpu(current->group_leader); struct fpu_state_perm *perm; unsigned int ksize, usize; u64 mask; @@ -1600,16 +1684,20 @@ static int __xstate_request_perm(u64 permitted, u64 requested, bool guest) if ((permitted & requested) == requested) return 0; - /* Calculate the resulting kernel state size */ + /* + * Calculate the resulting kernel state size. Note, @permitted also + * contains supervisor xfeatures even though supervisor are always + * permitted for kernel and guest FPUs, and never permitted for user + * FPUs. + */ mask = permitted | requested; - /* Take supervisor states into account on the host */ - if (!guest) - mask |= xfeatures_mask_supervisor(); ksize = xstate_calculate_size(mask, compacted); - /* Calculate the resulting user state size */ - mask &= XFEATURE_MASK_USER_SUPPORTED; - usize = xstate_calculate_size(mask, false); + /* + * Calculate the resulting user state size. Take care not to clobber + * the supervisor xfeatures in the new mask! + */ + usize = xstate_calculate_size(mask & XFEATURE_MASK_USER_SUPPORTED, false); if (!guest) { ret = validate_sigaltstack(usize); @@ -1693,7 +1781,7 @@ int __xfd_enable_feature(u64 xfd_err, struct fpu_guest *guest_fpu) return -EPERM; } - fpu = ¤t->group_leader->thread.fpu; + fpu = x86_task_fpu(current->group_leader); perm = guest_fpu ? &fpu->guest_perm : &fpu->perm; ksize = perm->__state_size; usize = perm->__user_state_size; @@ -1731,11 +1819,10 @@ u64 xstate_get_guest_group_perm(void) { return xstate_get_group_perm(true); } -EXPORT_SYMBOL_GPL(xstate_get_guest_group_perm); +EXPORT_SYMBOL_FOR_KVM(xstate_get_guest_group_perm); /** * fpu_xstate_prctl - xstate permission operations - * @tsk: Redundant pointer to current * @option: A subfunction of arch_prctl() * @arg2: option argument * Return: 0 if successful; otherwise, an error code @@ -1795,19 +1882,20 @@ long fpu_xstate_prctl(int option, unsigned long arg2) #ifdef CONFIG_PROC_PID_ARCH_STATUS /* * Report the amount of time elapsed in millisecond since last AVX512 - * use in the task. + * use in the task. Report -1 if no AVX-512 usage. */ static void avx512_status(struct seq_file *m, struct task_struct *task) { - unsigned long timestamp = READ_ONCE(task->thread.fpu.avx512_timestamp); - long delta; + unsigned long timestamp; + long delta = -1; - if (!timestamp) { - /* - * Report -1 if no AVX512 usage - */ - delta = -1; - } else { + /* AVX-512 usage is not tracked for kernel threads. Don't report anything. */ + if (task->flags & (PF_KTHREAD | PF_USER_WORKER)) + return; + + timestamp = READ_ONCE(x86_task_fpu(task)->avx512_timestamp); + + if (timestamp) { delta = (long)(jiffies - timestamp); /* * Cap to LONG_MAX if time difference > LONG_MAX @@ -1836,3 +1924,89 @@ int proc_pid_arch_status(struct seq_file *m, struct pid_namespace *ns, return 0; } #endif /* CONFIG_PROC_PID_ARCH_STATUS */ + +#ifdef CONFIG_COREDUMP +static const char owner_name[] = "LINUX"; + +/* + * Dump type, size, offset and flag values for every xfeature that is present. + */ +static int dump_xsave_layout_desc(struct coredump_params *cprm) +{ + int num_records = 0; + int i; + + for_each_extended_xfeature(i, fpu_user_cfg.max_features) { + struct x86_xfeat_component xc = { + .type = i, + .size = xstate_sizes[i], + .offset = xstate_offsets[i], + /* reserved for future use */ + .flags = 0, + }; + + if (!dump_emit(cprm, &xc, sizeof(xc))) + return 0; + + num_records++; + } + return num_records; +} + +static u32 get_xsave_desc_size(void) +{ + u32 cnt = 0; + u32 i; + + for_each_extended_xfeature(i, fpu_user_cfg.max_features) + cnt++; + + return cnt * (sizeof(struct x86_xfeat_component)); +} + +int elf_coredump_extra_notes_write(struct coredump_params *cprm) +{ + int num_records = 0; + struct elf_note en; + + if (!fpu_user_cfg.max_features) + return 0; + + en.n_namesz = sizeof(owner_name); + en.n_descsz = get_xsave_desc_size(); + en.n_type = NT_X86_XSAVE_LAYOUT; + + if (!dump_emit(cprm, &en, sizeof(en))) + return 1; + if (!dump_emit(cprm, owner_name, en.n_namesz)) + return 1; + if (!dump_align(cprm, 4)) + return 1; + + num_records = dump_xsave_layout_desc(cprm); + if (!num_records) + return 1; + + /* Total size should be equal to the number of records */ + if ((sizeof(struct x86_xfeat_component) * num_records) != en.n_descsz) + return 1; + + return 0; +} + +int elf_coredump_extra_notes_size(void) +{ + int size; + + if (!fpu_user_cfg.max_features) + return 0; + + /* .note header */ + size = sizeof(struct elf_note); + /* Name plus alignment to 4 bytes */ + size += roundup(sizeof(owner_name), 4); + size += get_xsave_desc_size(); + + return size; +} +#endif /* CONFIG_COREDUMP */ diff --git a/arch/x86/kernel/fpu/xstate.h b/arch/x86/kernel/fpu/xstate.h index a4ecb04d8d64..52ce19289989 100644 --- a/arch/x86/kernel/fpu/xstate.h +++ b/arch/x86/kernel/fpu/xstate.h @@ -5,6 +5,7 @@ #include <asm/cpufeature.h> #include <asm/fpu/xstate.h> #include <asm/fpu/xcr.h> +#include <asm/msr.h> #ifdef CONFIG_X86_64 DECLARE_PER_CPU(u64, xfd_state); @@ -22,7 +23,7 @@ static inline void xstate_init_xcomp_bv(struct xregs_state *xsave, u64 mask) static inline u64 xstate_get_group_perm(bool guest) { - struct fpu *fpu = ¤t->group_leader->thread.fpu; + struct fpu *fpu = x86_task_fpu(current->group_leader); struct fpu_state_perm *perm; /* Pairs with WRITE_ONCE() in xstate_request_perm() */ @@ -43,7 +44,8 @@ enum xstate_copy_mode { struct membuf; extern void __copy_xstate_to_uabi_buf(struct membuf to, struct fpstate *fpstate, - u32 pkru_val, enum xstate_copy_mode copy_mode); + u64 xfeatures, u32 pkru_val, + enum xstate_copy_mode copy_mode); extern void copy_xstate_to_uabi_buf(struct membuf to, struct task_struct *tsk, enum xstate_copy_mode mode); extern int copy_uabi_from_kernel_to_xstate(struct fpstate *fpstate, const void *kbuf, u32 *pkru); @@ -53,7 +55,7 @@ extern int copy_sigframe_from_user_to_xstate(struct task_struct *tsk, const void extern void fpu__init_cpu_xstate(void); extern void fpu__init_system_xstate(unsigned int legacy_size); -extern void *get_xsave_addr(struct xregs_state *xsave, int xfeature_nr); +extern void __user *get_xsave_addr_user(struct xregs_state __user *xsave, int xfeature_nr); static inline u64 xfeatures_mask_supervisor(void) { @@ -63,38 +65,73 @@ static inline u64 xfeatures_mask_supervisor(void) static inline u64 xfeatures_mask_independent(void) { if (!cpu_feature_enabled(X86_FEATURE_ARCH_LBR)) - return XFEATURE_MASK_INDEPENDENT & ~XFEATURE_MASK_LBR; + return fpu_kernel_cfg.independent_features & ~XFEATURE_MASK_LBR; - return XFEATURE_MASK_INDEPENDENT; + return fpu_kernel_cfg.independent_features; +} + +static inline int set_xfeature_in_sigframe(struct xregs_state __user *xbuf, u64 mask) +{ + u64 xfeatures; + int err; + + /* Read the xfeatures value already saved in the user buffer */ + err = __get_user(xfeatures, &xbuf->header.xfeatures); + xfeatures |= mask; + err |= __put_user(xfeatures, &xbuf->header.xfeatures); + + return err; +} + +/* + * Update the value of PKRU register that was already pushed onto the signal frame. + */ +static inline int update_pkru_in_sigframe(struct xregs_state __user *buf, u32 pkru) +{ + int err; + + if (unlikely(!cpu_feature_enabled(X86_FEATURE_OSPKE))) + return 0; + + /* Mark PKRU as in-use so that it is restored correctly. */ + err = set_xfeature_in_sigframe(buf, XFEATURE_MASK_PKRU); + if (err) + return err; + + /* Update PKRU value in the userspace xsave buffer. */ + return __put_user(pkru, (unsigned int __user *)get_xsave_addr_user(buf, XFEATURE_PKRU)); } /* XSAVE/XRSTOR wrapper functions */ #ifdef CONFIG_X86_64 -#define REX_PREFIX "0x48, " +#define REX_SUFFIX "64" #else -#define REX_PREFIX +#define REX_SUFFIX #endif -/* These macros all use (%edi)/(%rdi) as the single memory argument. */ -#define XSAVE ".byte " REX_PREFIX "0x0f,0xae,0x27" -#define XSAVEOPT ".byte " REX_PREFIX "0x0f,0xae,0x37" -#define XSAVEC ".byte " REX_PREFIX "0x0f,0xc7,0x27" -#define XSAVES ".byte " REX_PREFIX "0x0f,0xc7,0x2f" -#define XRSTOR ".byte " REX_PREFIX "0x0f,0xae,0x2f" -#define XRSTORS ".byte " REX_PREFIX "0x0f,0xc7,0x1f" +#define XSAVE "xsave" REX_SUFFIX " %[xa]" +#define XSAVEOPT "xsaveopt" REX_SUFFIX " %[xa]" +#define XSAVEC "xsavec" REX_SUFFIX " %[xa]" +#define XSAVES "xsaves" REX_SUFFIX " %[xa]" +#define XRSTOR "xrstor" REX_SUFFIX " %[xa]" +#define XRSTORS "xrstors" REX_SUFFIX " %[xa]" /* * After this @err contains 0 on success or the trap number when the * operation raises an exception. + * + * The [xa] input parameter below represents the struct xregs_state pointer + * and the asm symbolic name for the argument used in the XSAVE/XRSTOR insns + * above. */ #define XSTATE_OP(op, st, lmask, hmask, err) \ asm volatile("1:" op "\n\t" \ "xor %[err], %[err]\n" \ - "2:\n\t" \ + "2:\n" \ _ASM_EXTABLE_TYPE(1b, 2b, EX_TYPE_FAULT_MCE_SAFE) \ : [err] "=a" (err) \ - : "D" (st), "m" (*st), "a" (lmask), "d" (hmask) \ + : [xa] "m" (*(st)), "a" (lmask), "d" (hmask) \ : "memory") /* @@ -107,23 +144,19 @@ static inline u64 xfeatures_mask_independent(void) * Otherwise, if XSAVEOPT is enabled, XSAVEOPT replaces XSAVE because XSAVEOPT * supports modified optimization which is not supported by XSAVE. * - * We use XSAVE as a fallback. - * - * The 661 label is defined in the ALTERNATIVE* macros as the address of the - * original instruction which gets replaced. We need to use it here as the - * address of the instruction where we might get an exception at. + * Use XSAVE as a fallback. */ #define XSTATE_XSAVE(st, lmask, hmask, err) \ - asm volatile(ALTERNATIVE_3(XSAVE, \ + asm volatile("1: " ALTERNATIVE_3(XSAVE, \ XSAVEOPT, X86_FEATURE_XSAVEOPT, \ XSAVEC, X86_FEATURE_XSAVEC, \ XSAVES, X86_FEATURE_XSAVES) \ - "\n" \ + "\n\t" \ "xor %[err], %[err]\n" \ "3:\n" \ - _ASM_EXTABLE_TYPE_REG(661b, 3b, EX_TYPE_EFAULT_REG, %[err]) \ + _ASM_EXTABLE_TYPE_REG(1b, 3b, EX_TYPE_EFAULT_REG, %[err]) \ : [err] "=r" (err) \ - : "D" (st), "m" (*st), "a" (lmask), "d" (hmask) \ + : [xa] "m" (*(st)), "a" (lmask), "d" (hmask) \ : "memory") /* @@ -131,13 +164,13 @@ static inline u64 xfeatures_mask_independent(void) * XSAVE area format. */ #define XSTATE_XRESTORE(st, lmask, hmask) \ - asm volatile(ALTERNATIVE(XRSTOR, \ + asm volatile("1: " ALTERNATIVE(XRSTOR, \ XRSTORS, X86_FEATURE_XSAVES) \ "\n" \ "3:\n" \ - _ASM_EXTABLE_TYPE(661b, 3b, EX_TYPE_FPU_RESTORE) \ + _ASM_EXTABLE_TYPE(1b, 3b, EX_TYPE_FPU_RESTORE) \ : \ - : "D" (st), "m" (*st), "a" (lmask), "d" (hmask) \ + : [xa] "m" (*(st)), "a" (lmask), "d" (hmask) \ : "memory") #if defined(CONFIG_X86_64) && defined(CONFIG_X86_DEBUG_FPU) @@ -147,20 +180,26 @@ static inline void xfd_validate_state(struct fpstate *fpstate, u64 mask, bool rs #endif #ifdef CONFIG_X86_64 +static inline void xfd_set_state(u64 xfd) +{ + wrmsrq(MSR_IA32_XFD, xfd); + __this_cpu_write(xfd_state, xfd); +} + static inline void xfd_update_state(struct fpstate *fpstate) { if (fpu_state_size_dynamic()) { u64 xfd = fpstate->xfd; - if (__this_cpu_read(xfd_state) != xfd) { - wrmsrl(MSR_IA32_XFD, xfd); - __this_cpu_write(xfd_state, xfd); - } + if (__this_cpu_read(xfd_state) != xfd) + xfd_set_state(xfd); } } extern int __xfd_enable_feature(u64 which, struct fpu_guest *guest_fpu); #else +static inline void xfd_set_state(u64 xfd) { } + static inline void xfd_update_state(struct fpstate *fpstate) { } static inline int __xfd_enable_feature(u64 which, struct fpu_guest *guest_fpu) { @@ -253,14 +292,14 @@ static inline u64 xfeatures_need_sigframe_write(void) * The caller has to zero buf::header before calling this because XSAVE* * does not touch the reserved fields in the header. */ -static inline int xsave_to_user_sigframe(struct xregs_state __user *buf) +static inline int xsave_to_user_sigframe(struct xregs_state __user *buf, u32 pkru) { /* * Include the features which are not xsaved/rstored by the kernel * internally, e.g. PKRU. That's user space ABI and also required * to allow the signal handler to modify PKRU. */ - struct fpstate *fpstate = current->thread.fpu.fpstate; + struct fpstate *fpstate = x86_task_fpu(current)->fpstate; u64 mask = fpstate->user_xfeatures; u32 lmask; u32 hmask; @@ -278,6 +317,9 @@ static inline int xsave_to_user_sigframe(struct xregs_state __user *buf) XSTATE_OP(XSAVE, buf, lmask, hmask, err); clac(); + if (!err) + err = update_pkru_in_sigframe(buf, pkru); + return err; } @@ -291,7 +333,7 @@ static inline int xrstor_from_user_sigframe(struct xregs_state __user *buf, u64 u32 hmask = mask >> 32; int err; - xfd_validate_state(current->thread.fpu.fpstate, mask, true); + xfd_validate_state(x86_task_fpu(current)->fpstate, mask, true); stac(); XSTATE_OP(XRSTOR, xstate, lmask, hmask, err); |