diff options
Diffstat (limited to 'arch/x86/include/asm/fpu')
| -rw-r--r-- | arch/x86/include/asm/fpu/api.h | 23 | ||||
| -rw-r--r-- | arch/x86/include/asm/fpu/sched.h | 38 | ||||
| -rw-r--r-- | arch/x86/include/asm/fpu/signal.h | 2 | ||||
| -rw-r--r-- | arch/x86/include/asm/fpu/types.h | 37 | ||||
| -rw-r--r-- | arch/x86/include/asm/fpu/xstate.h | 7 |
5 files changed, 50 insertions, 57 deletions
diff --git a/arch/x86/include/asm/fpu/api.h b/arch/x86/include/asm/fpu/api.h index a2be3aefff9f..cd6f194a912b 100644 --- a/arch/x86/include/asm/fpu/api.h +++ b/arch/x86/include/asm/fpu/api.h @@ -16,10 +16,9 @@ /* * Use kernel_fpu_begin/end() if you intend to use FPU in kernel context. It - * disables preemption so be careful if you intend to use it for long periods - * of time. - * If you intend to use the FPU in irq/softirq you need to check first with - * irq_fpu_usable() if it is possible. + * disables preemption and softirq processing, so be careful if you intend to + * use it for long periods of time. Kernel-mode FPU cannot be used in all + * contexts -- see irq_fpu_usable() for details. */ /* Kernel FPU states to initialize in kernel_fpu_begin_mask() */ @@ -50,10 +49,10 @@ static inline void kernel_fpu_begin(void) } /* - * Use fpregs_lock() while editing CPU's FPU registers or fpu->fpstate. - * A context switch will (and softirq might) save CPU's FPU registers to - * fpu->fpstate.regs and set TIF_NEED_FPU_LOAD leaving CPU's FPU registers in - * a random state. + * Use fpregs_lock() while editing CPU's FPU registers or fpu->fpstate, or while + * using the FPU in kernel mode. A context switch will (and softirq might) save + * CPU's FPU registers to fpu->fpstate.regs and set TIF_NEED_FPU_LOAD leaving + * CPU's FPU registers in a random state. * * local_bh_disable() protects against both preemption and soft interrupts * on !RT kernels. @@ -63,8 +62,6 @@ static inline void kernel_fpu_begin(void) * preemptible. Disabling preemption is the right choice here as bottom * half processing is always in thread context on RT kernels so it * implicitly prevents bottom half processing as well. - * - * Disabling preemption also serializes against kernel_fpu_begin(). */ static inline void fpregs_lock(void) { @@ -129,6 +126,7 @@ static inline void fpstate_init_soft(struct swregs_state *soft) {} #endif /* State tracking */ +DECLARE_PER_CPU(bool, kernel_fpu_allowed); DECLARE_PER_CPU(struct fpu *, fpu_fpregs_owner_ctx); /* Process cleanup */ @@ -139,10 +137,13 @@ static inline void fpstate_free(struct fpu *fpu) { } #endif /* fpstate-related functions which are exported to KVM */ -extern void fpstate_clear_xstate_component(struct fpstate *fps, unsigned int xfeature); +extern void fpstate_clear_xstate_component(struct fpstate *fpstate, unsigned int xfeature); extern u64 xstate_get_guest_group_perm(void); +extern void *get_xsave_addr(struct xregs_state *xsave, int xfeature_nr); + + /* KVM specific functions */ extern bool fpu_alloc_guest_fpstate(struct fpu_guest *gfpu); extern void fpu_free_guest_fpstate(struct fpu_guest *gfpu); diff --git a/arch/x86/include/asm/fpu/sched.h b/arch/x86/include/asm/fpu/sched.h index c485f1944c5f..c060549c6c94 100644 --- a/arch/x86/include/asm/fpu/sched.h +++ b/arch/x86/include/asm/fpu/sched.h @@ -10,7 +10,7 @@ #include <asm/trace/fpu.h> extern void save_fpregs_to_fpstate(struct fpu *fpu); -extern void fpu__drop(struct fpu *fpu); +extern void fpu__drop(struct task_struct *tsk); extern int fpu_clone(struct task_struct *dst, unsigned long clone_flags, bool minimal, unsigned long shstk_addr); extern void fpu_flush_thread(void); @@ -18,31 +18,25 @@ extern void fpu_flush_thread(void); /* * FPU state switching for scheduling. * - * This is a two-stage process: + * switch_fpu() saves the old state and sets TIF_NEED_FPU_LOAD if + * TIF_NEED_FPU_LOAD is not set. This is done within the context + * of the old process. * - * - switch_fpu_prepare() saves the old state. - * This is done within the context of the old process. - * - * - switch_fpu_finish() sets TIF_NEED_FPU_LOAD; the floating point state - * will get loaded on return to userspace, or when the kernel needs it. - * - * If TIF_NEED_FPU_LOAD is cleared then the CPU's FPU registers - * are saved in the current thread's FPU register state. - * - * If TIF_NEED_FPU_LOAD is set then CPU's FPU registers may not - * hold current()'s FPU registers. It is required to load the + * Once TIF_NEED_FPU_LOAD is set, it is required to load the * registers before returning to userland or using the content * otherwise. * * The FPU context is only stored/restored for a user task and * PF_KTHREAD is used to distinguish between kernel and user threads. */ -static inline void switch_fpu_prepare(struct task_struct *old, int cpu) +static inline void switch_fpu(struct task_struct *old, int cpu) { - if (cpu_feature_enabled(X86_FEATURE_FPU) && + if (!test_tsk_thread_flag(old, TIF_NEED_FPU_LOAD) && + cpu_feature_enabled(X86_FEATURE_FPU) && !(old->flags & (PF_KTHREAD | PF_USER_WORKER))) { - struct fpu *old_fpu = &old->thread.fpu; + struct fpu *old_fpu = x86_task_fpu(old); + set_tsk_thread_flag(old, TIF_NEED_FPU_LOAD); save_fpregs_to_fpstate(old_fpu); /* * The save operation preserved register state, so the @@ -50,7 +44,7 @@ static inline void switch_fpu_prepare(struct task_struct *old, int cpu) * current CPU number in @old_fpu, so the next return * to user space can avoid the FPU register restore * when is returns on the same CPU and still owns the - * context. + * context. See fpregs_restore_userregs(). */ old_fpu->last_cpu = cpu; @@ -58,14 +52,4 @@ static inline void switch_fpu_prepare(struct task_struct *old, int cpu) } } -/* - * Delay loading of the complete FPU state until the return to userland. - * PKRU is handled separately. - */ -static inline void switch_fpu_finish(struct task_struct *new) -{ - if (cpu_feature_enabled(X86_FEATURE_FPU)) - set_tsk_thread_flag(new, TIF_NEED_FPU_LOAD); -} - #endif /* _ASM_X86_FPU_SCHED_H */ diff --git a/arch/x86/include/asm/fpu/signal.h b/arch/x86/include/asm/fpu/signal.h index 611fa41711af..eccc75bc9c4f 100644 --- a/arch/x86/include/asm/fpu/signal.h +++ b/arch/x86/include/asm/fpu/signal.h @@ -29,7 +29,7 @@ fpu__alloc_mathframe(unsigned long sp, int ia32_frame, unsigned long fpu__get_fpstate_size(void); -extern bool copy_fpstate_to_sigframe(void __user *buf, void __user *fp, int size); +extern bool copy_fpstate_to_sigframe(void __user *buf, void __user *fp, int size, u32 pkru); extern void fpu__clear_user_states(struct fpu *fpu); extern bool fpu__restore_sig(void __user *buf, int ia32_frame); diff --git a/arch/x86/include/asm/fpu/types.h b/arch/x86/include/asm/fpu/types.h index ace9aa3b78a3..1c94121acd3d 100644 --- a/arch/x86/include/asm/fpu/types.h +++ b/arch/x86/include/asm/fpu/types.h @@ -2,8 +2,8 @@ /* * FPU data structures: */ -#ifndef _ASM_X86_FPU_H -#define _ASM_X86_FPU_H +#ifndef _ASM_X86_FPU_TYPES_H +#define _ASM_X86_FPU_TYPES_H #include <asm/page_types.h> @@ -125,6 +125,7 @@ enum xfeature { XFEATURE_RSRVD_COMP_16, XFEATURE_XTILE_CFG, XFEATURE_XTILE_DATA, + XFEATURE_APX, XFEATURE_MAX, }; @@ -145,6 +146,7 @@ enum xfeature { #define XFEATURE_MASK_LBR (1 << XFEATURE_LBR) #define XFEATURE_MASK_XTILE_CFG (1 << XFEATURE_XTILE_CFG) #define XFEATURE_MASK_XTILE_DATA (1 << XFEATURE_XTILE_DATA) +#define XFEATURE_MASK_APX (1 << XFEATURE_APX) #define XFEATURE_MASK_FPSSE (XFEATURE_MASK_FP | XFEATURE_MASK_SSE) #define XFEATURE_MASK_AVX512 (XFEATURE_MASK_OPMASK \ @@ -304,6 +306,13 @@ struct xtile_data { } __packed; /* + * State component 19: 8B extended general purpose register. + */ +struct apx_state { + u64 egpr[16]; +} __packed; + +/* * State component 10 is supervisor state used for context-switching the * PASID state. */ @@ -407,9 +416,11 @@ struct fpu_state_perm { /* * @__state_perm: * - * This bitmap indicates the permission for state components, which - * are available to a thread group. The permission prctl() sets the - * enabled state bits in thread_group_leader()->thread.fpu. + * This bitmap indicates the permission for state components + * available to a thread group, including both user and supervisor + * components and software-defined bits like FPU_GUEST_PERM_LOCKED. + * The permission prctl() sets the enabled state bits in + * thread_group_leader()->thread.fpu. * * All run time operations use the per thread information in the * currently active fpu.fpstate which contains the xfeature masks @@ -525,13 +536,6 @@ struct fpu_guest { u64 xfeatures; /* - * @perm: xfeature bitmap of features which are - * permitted to be enabled for the guest - * vCPU. - */ - u64 perm; - - /* * @xfd_err: Save the guest value. */ u64 xfd_err; @@ -591,9 +595,16 @@ struct fpu_state_config { * even without XSAVE support, i.e. legacy features FP + SSE */ u64 legacy_features; + /* + * @independent_features: + * + * Features that are supported by XSAVES, but not managed as part of + * the FPU core, such as LBR + */ + u64 independent_features; }; /* FPU state configuration information */ extern struct fpu_state_config fpu_kernel_cfg, fpu_user_cfg; -#endif /* _ASM_X86_FPU_H */ +#endif /* _ASM_X86_FPU_TYPES_H */ diff --git a/arch/x86/include/asm/fpu/xstate.h b/arch/x86/include/asm/fpu/xstate.h index d4427b88ee12..b308a76afbb7 100644 --- a/arch/x86/include/asm/fpu/xstate.h +++ b/arch/x86/include/asm/fpu/xstate.h @@ -12,10 +12,6 @@ /* Bit 63 of XCR0 is reserved for future expansion */ #define XFEATURE_MASK_EXTEND (~(XFEATURE_MASK_FPSSE | (1ULL << 63))) -#define XSTATE_CPUID 0x0000000d - -#define TILE_CPUID 0x0000001d - #define FXSAVE_SIZE 512 #define XSAVE_HDR_SIZE 64 @@ -36,7 +32,8 @@ XFEATURE_MASK_PKRU | \ XFEATURE_MASK_BNDREGS | \ XFEATURE_MASK_BNDCSR | \ - XFEATURE_MASK_XTILE) + XFEATURE_MASK_XTILE | \ + XFEATURE_MASK_APX) /* * Features which are restored when returning to user space. |