summaryrefslogtreecommitdiffstats
path: root/arch/x86/include/asm/fpu
diff options
context:
space:
mode:
Diffstat (limited to 'arch/x86/include/asm/fpu')
-rw-r--r--arch/x86/include/asm/fpu/api.h170
-rw-r--r--arch/x86/include/asm/fpu/regset.h22
-rw-r--r--arch/x86/include/asm/fpu/sched.h68
-rw-r--r--arch/x86/include/asm/fpu/signal.h44
-rw-r--r--arch/x86/include/asm/fpu/types.h585
-rw-r--r--arch/x86/include/asm/fpu/xcr.h35
-rw-r--r--arch/x86/include/asm/fpu/xstate.h132
7 files changed, 1056 insertions, 0 deletions
diff --git a/arch/x86/include/asm/fpu/api.h b/arch/x86/include/asm/fpu/api.h
new file mode 100644
index 000000000..e829fa4c6
--- /dev/null
+++ b/arch/x86/include/asm/fpu/api.h
@@ -0,0 +1,170 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Copyright (C) 1994 Linus Torvalds
+ *
+ * Pentium III FXSR, SSE support
+ * General FPU state handling cleanups
+ * Gareth Hughes <gareth@valinux.com>, May 2000
+ * x86-64 work by Andi Kleen 2002
+ */
+
+#ifndef _ASM_X86_FPU_API_H
+#define _ASM_X86_FPU_API_H
+#include <linux/bottom_half.h>
+
+#include <asm/fpu/types.h>
+
+/*
+ * 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.
+ */
+
+/* Kernel FPU states to initialize in kernel_fpu_begin_mask() */
+#define KFPU_387 _BITUL(0) /* 387 state will be initialized */
+#define KFPU_MXCSR _BITUL(1) /* MXCSR will be initialized */
+
+extern void kernel_fpu_begin_mask(unsigned int kfpu_mask);
+extern void kernel_fpu_end(void);
+extern bool irq_fpu_usable(void);
+extern void fpregs_mark_activate(void);
+
+/* Code that is unaware of kernel_fpu_begin_mask() can use this */
+static inline void kernel_fpu_begin(void)
+{
+#ifdef CONFIG_X86_64
+ /*
+ * Any 64-bit code that uses 387 instructions must explicitly request
+ * KFPU_387.
+ */
+ kernel_fpu_begin_mask(KFPU_MXCSR);
+#else
+ /*
+ * 32-bit kernel code may use 387 operations as well as SSE2, etc,
+ * as long as it checks that the CPU has the required capability.
+ */
+ kernel_fpu_begin_mask(KFPU_387 | KFPU_MXCSR);
+#endif
+}
+
+/*
+ * 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.
+ *
+ * local_bh_disable() protects against both preemption and soft interrupts
+ * on !RT kernels.
+ *
+ * On RT kernels local_bh_disable() is not sufficient because it only
+ * serializes soft interrupt related sections via a local lock, but stays
+ * 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)
+{
+ if (!IS_ENABLED(CONFIG_PREEMPT_RT))
+ local_bh_disable();
+ else
+ preempt_disable();
+}
+
+static inline void fpregs_unlock(void)
+{
+ if (!IS_ENABLED(CONFIG_PREEMPT_RT))
+ local_bh_enable();
+ else
+ preempt_enable();
+}
+
+#ifdef CONFIG_X86_DEBUG_FPU
+extern void fpregs_assert_state_consistent(void);
+#else
+static inline void fpregs_assert_state_consistent(void) { }
+#endif
+
+/*
+ * Load the task FPU state before returning to userspace.
+ */
+extern void switch_fpu_return(void);
+
+/*
+ * Query the presence of one or more xfeatures. Works on any legacy CPU as well.
+ *
+ * If 'feature_name' is set then put a human-readable description of
+ * the feature there as well - this can be used to print error (or success)
+ * messages.
+ */
+extern int cpu_has_xfeatures(u64 xfeatures_mask, const char **feature_name);
+
+/* Trap handling */
+extern int fpu__exception_code(struct fpu *fpu, int trap_nr);
+extern void fpu_sync_fpstate(struct fpu *fpu);
+extern void fpu_reset_from_exception_fixup(void);
+
+/* Boot, hotplug and resume */
+extern void fpu__init_cpu(void);
+extern void fpu__init_system(void);
+extern void fpu__init_check_bugs(void);
+extern void fpu__resume_cpu(void);
+
+#ifdef CONFIG_MATH_EMULATION
+extern void fpstate_init_soft(struct swregs_state *soft);
+#else
+static inline void fpstate_init_soft(struct swregs_state *soft) {}
+#endif
+
+/* State tracking */
+DECLARE_PER_CPU(struct fpu *, fpu_fpregs_owner_ctx);
+
+/* Process cleanup */
+#ifdef CONFIG_X86_64
+extern void fpstate_free(struct fpu *fpu);
+#else
+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 u64 xstate_get_guest_group_perm(void);
+
+/* KVM specific functions */
+extern bool fpu_alloc_guest_fpstate(struct fpu_guest *gfpu);
+extern void fpu_free_guest_fpstate(struct fpu_guest *gfpu);
+extern int fpu_swap_kvm_fpstate(struct fpu_guest *gfpu, bool enter_guest);
+extern int fpu_enable_guest_xfd_features(struct fpu_guest *guest_fpu, u64 xfeatures);
+
+#ifdef CONFIG_X86_64
+extern void fpu_update_guest_xfd(struct fpu_guest *guest_fpu, u64 xfd);
+extern void fpu_sync_guest_vmexit_xfd_state(void);
+#else
+static inline void fpu_update_guest_xfd(struct fpu_guest *guest_fpu, u64 xfd) { }
+static inline void fpu_sync_guest_vmexit_xfd_state(void) { }
+#endif
+
+extern void fpu_copy_guest_fpstate_to_uabi(struct fpu_guest *gfpu, void *buf,
+ unsigned int size, u64 xfeatures, u32 pkru);
+extern int fpu_copy_uabi_to_guest_fpstate(struct fpu_guest *gfpu, const void *buf, u64 xcr0, u32 *vpkru);
+
+static inline void fpstate_set_confidential(struct fpu_guest *gfpu)
+{
+ gfpu->fpstate->is_confidential = true;
+}
+
+static inline bool fpstate_is_confidential(struct fpu_guest *gfpu)
+{
+ return gfpu->fpstate->is_confidential;
+}
+
+/* prctl */
+extern long fpu_xstate_prctl(int option, unsigned long arg2);
+
+extern void fpu_idle_fpregs(void);
+
+#endif /* _ASM_X86_FPU_API_H */
diff --git a/arch/x86/include/asm/fpu/regset.h b/arch/x86/include/asm/fpu/regset.h
new file mode 100644
index 000000000..4f928d6a3
--- /dev/null
+++ b/arch/x86/include/asm/fpu/regset.h
@@ -0,0 +1,22 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * FPU regset handling methods:
+ */
+#ifndef _ASM_X86_FPU_REGSET_H
+#define _ASM_X86_FPU_REGSET_H
+
+#include <linux/regset.h>
+
+extern user_regset_active_fn regset_fpregs_active, regset_xregset_fpregs_active;
+extern user_regset_get2_fn fpregs_get, xfpregs_get, fpregs_soft_get,
+ xstateregs_get;
+extern user_regset_set_fn fpregs_set, xfpregs_set, fpregs_soft_set,
+ xstateregs_set;
+
+/*
+ * xstateregs_active == regset_fpregs_active. Please refer to the comment
+ * at the definition of regset_fpregs_active.
+ */
+#define xstateregs_active regset_fpregs_active
+
+#endif /* _ASM_X86_FPU_REGSET_H */
diff --git a/arch/x86/include/asm/fpu/sched.h b/arch/x86/include/asm/fpu/sched.h
new file mode 100644
index 000000000..c2d6cd78e
--- /dev/null
+++ b/arch/x86/include/asm/fpu/sched.h
@@ -0,0 +1,68 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _ASM_X86_FPU_SCHED_H
+#define _ASM_X86_FPU_SCHED_H
+
+#include <linux/sched.h>
+
+#include <asm/cpufeature.h>
+#include <asm/fpu/types.h>
+
+#include <asm/trace/fpu.h>
+
+extern void save_fpregs_to_fpstate(struct fpu *fpu);
+extern void fpu__drop(struct fpu *fpu);
+extern int fpu_clone(struct task_struct *dst, unsigned long clone_flags, bool minimal);
+extern void fpu_flush_thread(void);
+
+/*
+ * FPU state switching for scheduling.
+ *
+ * This is a two-stage 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
+ * 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 fpu *old_fpu, int cpu)
+{
+ if (cpu_feature_enabled(X86_FEATURE_FPU) &&
+ !(current->flags & (PF_KTHREAD | PF_IO_WORKER))) {
+ save_fpregs_to_fpstate(old_fpu);
+ /*
+ * The save operation preserved register state, so the
+ * fpu_fpregs_owner_ctx is still @old_fpu. Store the
+ * 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.
+ */
+ old_fpu->last_cpu = cpu;
+
+ trace_x86_fpu_regs_deactivated(old_fpu);
+ }
+}
+
+/*
+ * Delay loading of the complete FPU state until the return to userland.
+ * PKRU is handled separately.
+ */
+static inline void switch_fpu_finish(void)
+{
+ if (cpu_feature_enabled(X86_FEATURE_FPU))
+ set_thread_flag(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
new file mode 100644
index 000000000..e1c9df910
--- /dev/null
+++ b/arch/x86/include/asm/fpu/signal.h
@@ -0,0 +1,44 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * x86 FPU signal frame handling methods:
+ */
+#ifndef _ASM_X86_FPU_SIGNAL_H
+#define _ASM_X86_FPU_SIGNAL_H
+
+#include <linux/compat.h>
+#include <linux/user.h>
+
+#include <asm/fpu/types.h>
+
+#ifdef CONFIG_X86_64
+# include <uapi/asm/sigcontext.h>
+# include <asm/user32.h>
+struct ksignal;
+int ia32_setup_rt_frame(int sig, struct ksignal *ksig,
+ compat_sigset_t *set, struct pt_regs *regs);
+int ia32_setup_frame(int sig, struct ksignal *ksig,
+ compat_sigset_t *set, struct pt_regs *regs);
+#else
+# define user_i387_ia32_struct user_i387_struct
+# define user32_fxsr_struct user_fxsr_struct
+# define ia32_setup_frame __setup_frame
+# define ia32_setup_rt_frame __setup_rt_frame
+#endif
+
+extern void convert_from_fxsr(struct user_i387_ia32_struct *env,
+ struct task_struct *tsk);
+extern void convert_to_fxsr(struct fxregs_state *fxsave,
+ const struct user_i387_ia32_struct *env);
+
+unsigned long
+fpu__alloc_mathframe(unsigned long sp, int ia32_frame,
+ unsigned long *buf_fx, unsigned long *size);
+
+unsigned long fpu__get_fpstate_size(void);
+
+extern bool copy_fpstate_to_sigframe(void __user *buf, void __user *fp, int size);
+extern void fpu__clear_user_states(struct fpu *fpu);
+extern bool fpu__restore_sig(void __user *buf, int ia32_frame);
+
+extern void restore_fpregs_from_fpstate(struct fpstate *fpstate, u64 mask);
+#endif /* _ASM_X86_FPU_SIGNAL_H */
diff --git a/arch/x86/include/asm/fpu/types.h b/arch/x86/include/asm/fpu/types.h
new file mode 100644
index 000000000..eb7cd1139
--- /dev/null
+++ b/arch/x86/include/asm/fpu/types.h
@@ -0,0 +1,585 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * FPU data structures:
+ */
+#ifndef _ASM_X86_FPU_H
+#define _ASM_X86_FPU_H
+
+/*
+ * The legacy x87 FPU state format, as saved by FSAVE and
+ * restored by the FRSTOR instructions:
+ */
+struct fregs_state {
+ u32 cwd; /* FPU Control Word */
+ u32 swd; /* FPU Status Word */
+ u32 twd; /* FPU Tag Word */
+ u32 fip; /* FPU IP Offset */
+ u32 fcs; /* FPU IP Selector */
+ u32 foo; /* FPU Operand Pointer Offset */
+ u32 fos; /* FPU Operand Pointer Selector */
+
+ /* 8*10 bytes for each FP-reg = 80 bytes: */
+ u32 st_space[20];
+
+ /* Software status information [not touched by FSAVE]: */
+ u32 status;
+};
+
+/*
+ * The legacy fx SSE/MMX FPU state format, as saved by FXSAVE and
+ * restored by the FXRSTOR instructions. It's similar to the FSAVE
+ * format, but differs in some areas, plus has extensions at
+ * the end for the XMM registers.
+ */
+struct fxregs_state {
+ u16 cwd; /* Control Word */
+ u16 swd; /* Status Word */
+ u16 twd; /* Tag Word */
+ u16 fop; /* Last Instruction Opcode */
+ union {
+ struct {
+ u64 rip; /* Instruction Pointer */
+ u64 rdp; /* Data Pointer */
+ };
+ struct {
+ u32 fip; /* FPU IP Offset */
+ u32 fcs; /* FPU IP Selector */
+ u32 foo; /* FPU Operand Offset */
+ u32 fos; /* FPU Operand Selector */
+ };
+ };
+ u32 mxcsr; /* MXCSR Register State */
+ u32 mxcsr_mask; /* MXCSR Mask */
+
+ /* 8*16 bytes for each FP-reg = 128 bytes: */
+ u32 st_space[32];
+
+ /* 16*16 bytes for each XMM-reg = 256 bytes: */
+ u32 xmm_space[64];
+
+ u32 padding[12];
+
+ union {
+ u32 padding1[12];
+ u32 sw_reserved[12];
+ };
+
+} __attribute__((aligned(16)));
+
+/* Default value for fxregs_state.mxcsr: */
+#define MXCSR_DEFAULT 0x1f80
+
+/* Copy both mxcsr & mxcsr_flags with a single u64 memcpy: */
+#define MXCSR_AND_FLAGS_SIZE sizeof(u64)
+
+/*
+ * Software based FPU emulation state. This is arbitrary really,
+ * it matches the x87 format to make it easier to understand:
+ */
+struct swregs_state {
+ u32 cwd;
+ u32 swd;
+ u32 twd;
+ u32 fip;
+ u32 fcs;
+ u32 foo;
+ u32 fos;
+ /* 8*10 bytes for each FP-reg = 80 bytes: */
+ u32 st_space[20];
+ u8 ftop;
+ u8 changed;
+ u8 lookahead;
+ u8 no_update;
+ u8 rm;
+ u8 alimit;
+ struct math_emu_info *info;
+ u32 entry_eip;
+};
+
+/*
+ * List of XSAVE features Linux knows about:
+ */
+enum xfeature {
+ XFEATURE_FP,
+ XFEATURE_SSE,
+ /*
+ * Values above here are "legacy states".
+ * Those below are "extended states".
+ */
+ XFEATURE_YMM,
+ XFEATURE_BNDREGS,
+ XFEATURE_BNDCSR,
+ XFEATURE_OPMASK,
+ XFEATURE_ZMM_Hi256,
+ XFEATURE_Hi16_ZMM,
+ XFEATURE_PT_UNIMPLEMENTED_SO_FAR,
+ XFEATURE_PKRU,
+ XFEATURE_PASID,
+ XFEATURE_RSRVD_COMP_11,
+ XFEATURE_RSRVD_COMP_12,
+ XFEATURE_RSRVD_COMP_13,
+ XFEATURE_RSRVD_COMP_14,
+ XFEATURE_LBR,
+ XFEATURE_RSRVD_COMP_16,
+ XFEATURE_XTILE_CFG,
+ XFEATURE_XTILE_DATA,
+
+ XFEATURE_MAX,
+};
+
+#define XFEATURE_MASK_FP (1 << XFEATURE_FP)
+#define XFEATURE_MASK_SSE (1 << XFEATURE_SSE)
+#define XFEATURE_MASK_YMM (1 << XFEATURE_YMM)
+#define XFEATURE_MASK_BNDREGS (1 << XFEATURE_BNDREGS)
+#define XFEATURE_MASK_BNDCSR (1 << XFEATURE_BNDCSR)
+#define XFEATURE_MASK_OPMASK (1 << XFEATURE_OPMASK)
+#define XFEATURE_MASK_ZMM_Hi256 (1 << XFEATURE_ZMM_Hi256)
+#define XFEATURE_MASK_Hi16_ZMM (1 << XFEATURE_Hi16_ZMM)
+#define XFEATURE_MASK_PT (1 << XFEATURE_PT_UNIMPLEMENTED_SO_FAR)
+#define XFEATURE_MASK_PKRU (1 << XFEATURE_PKRU)
+#define XFEATURE_MASK_PASID (1 << XFEATURE_PASID)
+#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_FPSSE (XFEATURE_MASK_FP | XFEATURE_MASK_SSE)
+#define XFEATURE_MASK_AVX512 (XFEATURE_MASK_OPMASK \
+ | XFEATURE_MASK_ZMM_Hi256 \
+ | XFEATURE_MASK_Hi16_ZMM)
+
+#ifdef CONFIG_X86_64
+# define XFEATURE_MASK_XTILE (XFEATURE_MASK_XTILE_DATA \
+ | XFEATURE_MASK_XTILE_CFG)
+#else
+# define XFEATURE_MASK_XTILE (0)
+#endif
+
+#define FIRST_EXTENDED_XFEATURE XFEATURE_YMM
+
+struct reg_128_bit {
+ u8 regbytes[128/8];
+};
+struct reg_256_bit {
+ u8 regbytes[256/8];
+};
+struct reg_512_bit {
+ u8 regbytes[512/8];
+};
+struct reg_1024_byte {
+ u8 regbytes[1024];
+};
+
+/*
+ * State component 2:
+ *
+ * There are 16x 256-bit AVX registers named YMM0-YMM15.
+ * The low 128 bits are aliased to the 16 SSE registers (XMM0-XMM15)
+ * and are stored in 'struct fxregs_state::xmm_space[]' in the
+ * "legacy" area.
+ *
+ * The high 128 bits are stored here.
+ */
+struct ymmh_struct {
+ struct reg_128_bit hi_ymm[16];
+} __packed;
+
+/* Intel MPX support: */
+
+struct mpx_bndreg {
+ u64 lower_bound;
+ u64 upper_bound;
+} __packed;
+/*
+ * State component 3 is used for the 4 128-bit bounds registers
+ */
+struct mpx_bndreg_state {
+ struct mpx_bndreg bndreg[4];
+} __packed;
+
+/*
+ * State component 4 is used for the 64-bit user-mode MPX
+ * configuration register BNDCFGU and the 64-bit MPX status
+ * register BNDSTATUS. We call the pair "BNDCSR".
+ */
+struct mpx_bndcsr {
+ u64 bndcfgu;
+ u64 bndstatus;
+} __packed;
+
+/*
+ * The BNDCSR state is padded out to be 64-bytes in size.
+ */
+struct mpx_bndcsr_state {
+ union {
+ struct mpx_bndcsr bndcsr;
+ u8 pad_to_64_bytes[64];
+ };
+} __packed;
+
+/* AVX-512 Components: */
+
+/*
+ * State component 5 is used for the 8 64-bit opmask registers
+ * k0-k7 (opmask state).
+ */
+struct avx_512_opmask_state {
+ u64 opmask_reg[8];
+} __packed;
+
+/*
+ * State component 6 is used for the upper 256 bits of the
+ * registers ZMM0-ZMM15. These 16 256-bit values are denoted
+ * ZMM0_H-ZMM15_H (ZMM_Hi256 state).
+ */
+struct avx_512_zmm_uppers_state {
+ struct reg_256_bit zmm_upper[16];
+} __packed;
+
+/*
+ * State component 7 is used for the 16 512-bit registers
+ * ZMM16-ZMM31 (Hi16_ZMM state).
+ */
+struct avx_512_hi16_state {
+ struct reg_512_bit hi16_zmm[16];
+} __packed;
+
+/*
+ * State component 9: 32-bit PKRU register. The state is
+ * 8 bytes long but only 4 bytes is used currently.
+ */
+struct pkru_state {
+ u32 pkru;
+ u32 pad;
+} __packed;
+
+/*
+ * State component 15: Architectural LBR configuration state.
+ * The size of Arch LBR state depends on the number of LBRs (lbr_depth).
+ */
+
+struct lbr_entry {
+ u64 from;
+ u64 to;
+ u64 info;
+};
+
+struct arch_lbr_state {
+ u64 lbr_ctl;
+ u64 lbr_depth;
+ u64 ler_from;
+ u64 ler_to;
+ u64 ler_info;
+ struct lbr_entry entries[];
+};
+
+/*
+ * State component 17: 64-byte tile configuration register.
+ */
+struct xtile_cfg {
+ u64 tcfg[8];
+} __packed;
+
+/*
+ * State component 18: 1KB tile data register.
+ * Each register represents 16 64-byte rows of the matrix
+ * data. But the number of registers depends on the actual
+ * implementation.
+ */
+struct xtile_data {
+ struct reg_1024_byte tmm;
+} __packed;
+
+/*
+ * State component 10 is supervisor state used for context-switching the
+ * PASID state.
+ */
+struct ia32_pasid_state {
+ u64 pasid;
+} __packed;
+
+struct xstate_header {
+ u64 xfeatures;
+ u64 xcomp_bv;
+ u64 reserved[6];
+} __attribute__((packed));
+
+/*
+ * xstate_header.xcomp_bv[63] indicates that the extended_state_area
+ * is in compacted format.
+ */
+#define XCOMP_BV_COMPACTED_FORMAT ((u64)1 << 63)
+
+/*
+ * This is our most modern FPU state format, as saved by the XSAVE
+ * and restored by the XRSTOR instructions.
+ *
+ * It consists of a legacy fxregs portion, an xstate header and
+ * subsequent areas as defined by the xstate header. Not all CPUs
+ * support all the extensions, so the size of the extended area
+ * can vary quite a bit between CPUs.
+ */
+struct xregs_state {
+ struct fxregs_state i387;
+ struct xstate_header header;
+ u8 extended_state_area[0];
+} __attribute__ ((packed, aligned (64)));
+
+/*
+ * This is a union of all the possible FPU state formats
+ * put together, so that we can pick the right one runtime.
+ *
+ * The size of the structure is determined by the largest
+ * member - which is the xsave area. The padding is there
+ * to ensure that statically-allocated task_structs (just
+ * the init_task today) have enough space.
+ */
+union fpregs_state {
+ struct fregs_state fsave;
+ struct fxregs_state fxsave;
+ struct swregs_state soft;
+ struct xregs_state xsave;
+ u8 __padding[PAGE_SIZE];
+};
+
+struct fpstate {
+ /* @kernel_size: The size of the kernel register image */
+ unsigned int size;
+
+ /* @user_size: The size in non-compacted UABI format */
+ unsigned int user_size;
+
+ /* @xfeatures: xfeatures for which the storage is sized */
+ u64 xfeatures;
+
+ /* @user_xfeatures: xfeatures valid in UABI buffers */
+ u64 user_xfeatures;
+
+ /* @xfd: xfeatures disabled to trap userspace use. */
+ u64 xfd;
+
+ /* @is_valloc: Indicator for dynamically allocated state */
+ unsigned int is_valloc : 1;
+
+ /* @is_guest: Indicator for guest state (KVM) */
+ unsigned int is_guest : 1;
+
+ /*
+ * @is_confidential: Indicator for KVM confidential mode.
+ * The FPU registers are restored by the
+ * vmentry firmware from encrypted guest
+ * memory. On vmexit the FPU registers are
+ * saved by firmware to encrypted guest memory
+ * and the registers are scrubbed before
+ * returning to the host. So there is no
+ * content which is worth saving and restoring.
+ * The fpstate has to be there so that
+ * preemption and softirq FPU usage works
+ * without special casing.
+ */
+ unsigned int is_confidential : 1;
+
+ /* @in_use: State is in use */
+ unsigned int in_use : 1;
+
+ /* @regs: The register state union for all supported formats */
+ union fpregs_state regs;
+
+ /* @regs is dynamically sized! Don't add anything after @regs! */
+} __aligned(64);
+
+#define FPU_GUEST_PERM_LOCKED BIT_ULL(63)
+
+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.
+ *
+ * All run time operations use the per thread information in the
+ * currently active fpu.fpstate which contains the xfeature masks
+ * and sizes for kernel and user space.
+ *
+ * This master permission field is only to be used when
+ * task.fpu.fpstate based checks fail to validate whether the task
+ * is allowed to expand it's xfeatures set which requires to
+ * allocate a larger sized fpstate buffer.
+ *
+ * Do not access this field directly. Use the provided helper
+ * function. Unlocked access is possible for quick checks.
+ */
+ u64 __state_perm;
+
+ /*
+ * @__state_size:
+ *
+ * The size required for @__state_perm. Only valid to access
+ * with sighand locked.
+ */
+ unsigned int __state_size;
+
+ /*
+ * @__user_state_size:
+ *
+ * The size required for @__state_perm user part. Only valid to
+ * access with sighand locked.
+ */
+ unsigned int __user_state_size;
+};
+
+/*
+ * Highest level per task FPU state data structure that
+ * contains the FPU register state plus various FPU
+ * state fields:
+ */
+struct fpu {
+ /*
+ * @last_cpu:
+ *
+ * Records the last CPU on which this context was loaded into
+ * FPU registers. (In the lazy-restore case we might be
+ * able to reuse FPU registers across multiple context switches
+ * this way, if no intermediate task used the FPU.)
+ *
+ * A value of -1 is used to indicate that the FPU state in context
+ * memory is newer than the FPU state in registers, and that the
+ * FPU state should be reloaded next time the task is run.
+ */
+ unsigned int last_cpu;
+
+ /*
+ * @avx512_timestamp:
+ *
+ * Records the timestamp of AVX512 use during last context switch.
+ */
+ unsigned long avx512_timestamp;
+
+ /*
+ * @fpstate:
+ *
+ * Pointer to the active struct fpstate. Initialized to
+ * point at @__fpstate below.
+ */
+ struct fpstate *fpstate;
+
+ /*
+ * @__task_fpstate:
+ *
+ * Pointer to an inactive struct fpstate. Initialized to NULL. Is
+ * used only for KVM support to swap out the regular task fpstate.
+ */
+ struct fpstate *__task_fpstate;
+
+ /*
+ * @perm:
+ *
+ * Permission related information
+ */
+ struct fpu_state_perm perm;
+
+ /*
+ * @guest_perm:
+ *
+ * Permission related information for guest pseudo FPUs
+ */
+ struct fpu_state_perm guest_perm;
+
+ /*
+ * @__fpstate:
+ *
+ * Initial in-memory storage for FPU registers which are saved in
+ * context switch and when the kernel uses the FPU. The registers
+ * are restored from this storage on return to user space if they
+ * are not longer containing the tasks FPU register state.
+ */
+ struct fpstate __fpstate;
+ /*
+ * WARNING: '__fpstate' is dynamically-sized. Do not put
+ * anything after it here.
+ */
+};
+
+/*
+ * Guest pseudo FPU container
+ */
+struct fpu_guest {
+ /*
+ * @xfeatures: xfeature bitmap of features which are
+ * currently enabled for the guest vCPU.
+ */
+ 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;
+
+ /*
+ * @uabi_size: Size required for save/restore
+ */
+ unsigned int uabi_size;
+
+ /*
+ * @fpstate: Pointer to the allocated guest fpstate
+ */
+ struct fpstate *fpstate;
+};
+
+/*
+ * FPU state configuration data. Initialized at boot time. Read only after init.
+ */
+struct fpu_state_config {
+ /*
+ * @max_size:
+ *
+ * The maximum size of the register state buffer. Includes all
+ * supported features except independent managed features.
+ */
+ unsigned int max_size;
+
+ /*
+ * @default_size:
+ *
+ * The default size of the register state buffer. Includes all
+ * supported features except independent managed features and
+ * features which have to be requested by user space before usage.
+ */
+ unsigned int default_size;
+
+ /*
+ * @max_features:
+ *
+ * The maximum supported features bitmap. Does not include
+ * independent managed features.
+ */
+ u64 max_features;
+
+ /*
+ * @default_features:
+ *
+ * The default supported features bitmap. Does not include
+ * independent managed features and features which have to
+ * be requested by user space before usage.
+ */
+ u64 default_features;
+ /*
+ * @legacy_features:
+ *
+ * Features which can be reported back to user space
+ * even without XSAVE support, i.e. legacy features FP + SSE
+ */
+ u64 legacy_features;
+};
+
+/* FPU state configuration information */
+extern struct fpu_state_config fpu_kernel_cfg, fpu_user_cfg;
+
+#endif /* _ASM_X86_FPU_H */
diff --git a/arch/x86/include/asm/fpu/xcr.h b/arch/x86/include/asm/fpu/xcr.h
new file mode 100644
index 000000000..9a710c060
--- /dev/null
+++ b/arch/x86/include/asm/fpu/xcr.h
@@ -0,0 +1,35 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _ASM_X86_FPU_XCR_H
+#define _ASM_X86_FPU_XCR_H
+
+#define XCR_XFEATURE_ENABLED_MASK 0x00000000
+#define XCR_XFEATURE_IN_USE_MASK 0x00000001
+
+static __always_inline u64 xgetbv(u32 index)
+{
+ u32 eax, edx;
+
+ asm volatile("xgetbv" : "=a" (eax), "=d" (edx) : "c" (index));
+ return eax + ((u64)edx << 32);
+}
+
+static inline void xsetbv(u32 index, u64 value)
+{
+ u32 eax = value;
+ u32 edx = value >> 32;
+
+ asm volatile("xsetbv" :: "a" (eax), "d" (edx), "c" (index));
+}
+
+/*
+ * Return a mask of xfeatures which are currently being tracked
+ * by the processor as being in the initial configuration.
+ *
+ * Callers should check X86_FEATURE_XGETBV1.
+ */
+static __always_inline u64 xfeatures_in_use(void)
+{
+ return xgetbv(XCR_XFEATURE_IN_USE_MASK);
+}
+
+#endif /* _ASM_X86_FPU_XCR_H */
diff --git a/arch/x86/include/asm/fpu/xstate.h b/arch/x86/include/asm/fpu/xstate.h
new file mode 100644
index 000000000..cd3dd170e
--- /dev/null
+++ b/arch/x86/include/asm/fpu/xstate.h
@@ -0,0 +1,132 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef __ASM_X86_XSAVE_H
+#define __ASM_X86_XSAVE_H
+
+#include <linux/uaccess.h>
+#include <linux/types.h>
+
+#include <asm/processor.h>
+#include <asm/fpu/api.h>
+#include <asm/user.h>
+
+/* 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
+#define XSAVE_HDR_OFFSET FXSAVE_SIZE
+
+#define XSAVE_YMM_SIZE 256
+#define XSAVE_YMM_OFFSET (XSAVE_HDR_SIZE + XSAVE_HDR_OFFSET)
+
+#define XSAVE_ALIGNMENT 64
+
+/* All currently supported user features */
+#define XFEATURE_MASK_USER_SUPPORTED (XFEATURE_MASK_FP | \
+ XFEATURE_MASK_SSE | \
+ XFEATURE_MASK_YMM | \
+ XFEATURE_MASK_OPMASK | \
+ XFEATURE_MASK_ZMM_Hi256 | \
+ XFEATURE_MASK_Hi16_ZMM | \
+ XFEATURE_MASK_PKRU | \
+ XFEATURE_MASK_BNDREGS | \
+ XFEATURE_MASK_BNDCSR | \
+ XFEATURE_MASK_XTILE)
+
+/*
+ * Features which are restored when returning to user space.
+ * PKRU is not restored on return to user space because PKRU
+ * is switched eagerly in switch_to() and flush_thread()
+ */
+#define XFEATURE_MASK_USER_RESTORE \
+ (XFEATURE_MASK_USER_SUPPORTED & ~XFEATURE_MASK_PKRU)
+
+/* Features which are dynamically enabled for a process on request */
+#define XFEATURE_MASK_USER_DYNAMIC XFEATURE_MASK_XTILE_DATA
+
+/* All currently supported supervisor features */
+#define XFEATURE_MASK_SUPERVISOR_SUPPORTED (XFEATURE_MASK_PASID)
+
+/*
+ * A supervisor state component may not always contain valuable information,
+ * and its size may be huge. Saving/restoring such supervisor state components
+ * at each context switch can cause high CPU and space overhead, which should
+ * be avoided. Such supervisor state components should only be saved/restored
+ * on demand. The on-demand supervisor features are set in this mask.
+ *
+ * Unlike the existing supported supervisor features, an independent supervisor
+ * feature does not allocate a buffer in task->fpu, and the corresponding
+ * supervisor state component cannot be saved/restored at each context switch.
+ *
+ * To support an independent supervisor feature, a developer should follow the
+ * dos and don'ts as below:
+ * - Do dynamically allocate a buffer for the supervisor state component.
+ * - Do manually invoke the XSAVES/XRSTORS instruction to save/restore the
+ * state component to/from the buffer.
+ * - Don't set the bit corresponding to the independent supervisor feature in
+ * IA32_XSS at run time, since it has been set at boot time.
+ */
+#define XFEATURE_MASK_INDEPENDENT (XFEATURE_MASK_LBR)
+
+/*
+ * Unsupported supervisor features. When a supervisor feature in this mask is
+ * supported in the future, move it to the supported supervisor feature mask.
+ */
+#define XFEATURE_MASK_SUPERVISOR_UNSUPPORTED (XFEATURE_MASK_PT)
+
+/* All supervisor states including supported and unsupported states. */
+#define XFEATURE_MASK_SUPERVISOR_ALL (XFEATURE_MASK_SUPERVISOR_SUPPORTED | \
+ XFEATURE_MASK_INDEPENDENT | \
+ XFEATURE_MASK_SUPERVISOR_UNSUPPORTED)
+
+/*
+ * The feature mask required to restore FPU state:
+ * - All user states which are not eagerly switched in switch_to()/exec()
+ * - The suporvisor states
+ */
+#define XFEATURE_MASK_FPSTATE (XFEATURE_MASK_USER_RESTORE | \
+ XFEATURE_MASK_SUPERVISOR_SUPPORTED)
+
+/*
+ * Features in this mask have space allocated in the signal frame, but may not
+ * have that space initialized when the feature is in its init state.
+ */
+#define XFEATURE_MASK_SIGFRAME_INITOPT (XFEATURE_MASK_XTILE | \
+ XFEATURE_MASK_USER_DYNAMIC)
+
+extern u64 xstate_fx_sw_bytes[USER_XSTATE_FX_SW_WORDS];
+
+extern void __init update_regset_xstate_info(unsigned int size,
+ u64 xstate_mask);
+
+int xfeature_size(int xfeature_nr);
+
+void xsaves(struct xregs_state *xsave, u64 mask);
+void xrstors(struct xregs_state *xsave, u64 mask);
+
+int xfd_enable_feature(u64 xfd_err);
+
+#ifdef CONFIG_X86_64
+DECLARE_STATIC_KEY_FALSE(__fpu_state_size_dynamic);
+#endif
+
+#ifdef CONFIG_X86_64
+DECLARE_STATIC_KEY_FALSE(__fpu_state_size_dynamic);
+
+static __always_inline __pure bool fpu_state_size_dynamic(void)
+{
+ return static_branch_unlikely(&__fpu_state_size_dynamic);
+}
+#else
+static __always_inline __pure bool fpu_state_size_dynamic(void)
+{
+ return false;
+}
+#endif
+
+#endif