Adding upstream version 5.10.209.upstream/5.10.209

Signed-off-by: Daniel Baumann <daniel.baumann@progress-linux.org>

7 files changed, 1238 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..8b9bfaad6
--- /dev/null
+++ b/arch/x86/include/asm/fpu/api.h
@@ -0,0 +1,84 @@
+/* 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>
+
+/*
+ * 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)
+{
+	kernel_fpu_begin_mask(KFPU_387 | KFPU_MXCSR);
+}
+
+/*
+ * Use fpregs_lock() while editing CPU's FPU registers or fpu->state.
+ * A context switch will (and softirq might) save CPU's FPU registers to
+ * fpu->state and set TIF_NEED_FPU_LOAD leaving CPU's FPU registers in
+ * a random state.
+ */
+static inline void fpregs_lock(void)
+{
+	preempt_disable();
+	local_bh_disable();
+}
+
+static inline void fpregs_unlock(void)
+{
+	local_bh_enable();
+	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);
+
+/*
+ * Tasks that are not using SVA have mm->pasid set to zero to note that they
+ * will not have the valid bit set in MSR_IA32_PASID while they are running.
+ */
+#define PASID_DISABLED	0
+
+static inline void update_pasid(void) { }
+
+#endif /* _ASM_X86_FPU_API_H */
diff --git a/arch/x86/include/asm/fpu/internal.h b/arch/x86/include/asm/fpu/internal.h
new file mode 100644
index 000000000..94c07151a
--- /dev/null
+++ b/arch/x86/include/asm/fpu/internal.h
@@ -0,0 +1,590 @@
+/* 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_INTERNAL_H
+#define _ASM_X86_FPU_INTERNAL_H
+
+#include <linux/compat.h>
+#include <linux/sched.h>
+#include <linux/slab.h>
+#include <linux/mm.h>
+
+#include <asm/user.h>
+#include <asm/fpu/api.h>
+#include <asm/fpu/xstate.h>
+#include <asm/fpu/xcr.h>
+#include <asm/cpufeature.h>
+#include <asm/trace/fpu.h>
+
+/*
+ * High level FPU state handling functions:
+ */
+extern void fpu__prepare_read(struct fpu *fpu);
+extern void fpu__prepare_write(struct fpu *fpu);
+extern void fpu__save(struct fpu *fpu);
+extern int  fpu__restore_sig(void __user *buf, int ia32_frame);
+extern void fpu__drop(struct fpu *fpu);
+extern int  fpu__copy(struct task_struct *dst, struct task_struct *src);
+extern void fpu__clear_user_states(struct fpu *fpu);
+extern void fpu__clear_all(struct fpu *fpu);
+extern int  fpu__exception_code(struct fpu *fpu, int trap_nr);
+
+/*
+ * Boot time FPU initialization functions:
+ */
+extern void fpu__init_cpu(void);
+extern void fpu__init_system_xstate(void);
+extern void fpu__init_cpu_xstate(void);
+extern void fpu__init_system(void);
+extern void fpu__init_check_bugs(void);
+extern void fpu__resume_cpu(void);
+extern u64 fpu__get_supported_xfeatures_mask(void);
+
+/*
+ * Debugging facility:
+ */
+#ifdef CONFIG_X86_DEBUG_FPU
+# define WARN_ON_FPU(x) WARN_ON_ONCE(x)
+#else
+# define WARN_ON_FPU(x) ({ (void)(x); 0; })
+#endif
+
+/*
+ * FPU related CPU feature flag helper routines:
+ */
+static __always_inline __pure bool use_xsaveopt(void)
+{
+	return static_cpu_has(X86_FEATURE_XSAVEOPT);
+}
+
+static __always_inline __pure bool use_xsave(void)
+{
+	return static_cpu_has(X86_FEATURE_XSAVE);
+}
+
+static __always_inline __pure bool use_fxsr(void)
+{
+	return static_cpu_has(X86_FEATURE_FXSR);
+}
+
+/*
+ * fpstate handling functions:
+ */
+
+extern union fpregs_state init_fpstate;
+
+extern void fpstate_init(union fpregs_state *state);
+#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
+
+static inline void fpstate_init_xstate(struct xregs_state *xsave)
+{
+	/*
+	 * XRSTORS requires these bits set in xcomp_bv, or it will
+	 * trigger #GP:
+	 */
+	xsave->header.xcomp_bv = XCOMP_BV_COMPACTED_FORMAT | xfeatures_mask_all;
+}
+
+static inline void fpstate_init_fxstate(struct fxregs_state *fx)
+{
+	fx->cwd = 0x37f;
+	fx->mxcsr = MXCSR_DEFAULT;
+}
+extern void fpstate_sanitize_xstate(struct fpu *fpu);
+
+/* Returns 0 or the negated trap number, which results in -EFAULT for #PF */
+#define user_insn(insn, output, input...)				\
+({									\
+	int err;							\
+									\
+	might_fault();							\
+									\
+	asm volatile(ASM_STAC "\n"					\
+		     "1: " #insn "\n"					\
+		     "2: " ASM_CLAC "\n"				\
+		     ".section .fixup,\"ax\"\n"				\
+		     "3:  negl %%eax\n"					\
+		     "    jmp  2b\n"					\
+		     ".previous\n"					\
+		     _ASM_EXTABLE_FAULT(1b, 3b)				\
+		     : [err] "=a" (err), output				\
+		     : "0"(0), input);					\
+	err;								\
+})
+
+#define kernel_insn_err(insn, output, input...)				\
+({									\
+	int err;							\
+	asm volatile("1:" #insn "\n\t"					\
+		     "2:\n"						\
+		     ".section .fixup,\"ax\"\n"				\
+		     "3:  movl $-1,%[err]\n"				\
+		     "    jmp  2b\n"					\
+		     ".previous\n"					\
+		     _ASM_EXTABLE(1b, 3b)				\
+		     : [err] "=r" (err), output				\
+		     : "0"(0), input);					\
+	err;								\
+})
+
+#define kernel_insn(insn, output, input...)				\
+	asm volatile("1:" #insn "\n\t"					\
+		     "2:\n"						\
+		     _ASM_EXTABLE_HANDLE(1b, 2b, ex_handler_fprestore)	\
+		     : output : input)
+
+static inline int copy_fregs_to_user(struct fregs_state __user *fx)
+{
+	return user_insn(fnsave %[fx]; fwait,  [fx] "=m" (*fx), "m" (*fx));
+}
+
+static inline int copy_fxregs_to_user(struct fxregs_state __user *fx)
+{
+	if (IS_ENABLED(CONFIG_X86_32))
+		return user_insn(fxsave %[fx], [fx] "=m" (*fx), "m" (*fx));
+	else
+		return user_insn(fxsaveq %[fx], [fx] "=m" (*fx), "m" (*fx));
+
+}
+
+static inline void copy_kernel_to_fxregs(struct fxregs_state *fx)
+{
+	if (IS_ENABLED(CONFIG_X86_32))
+		kernel_insn(fxrstor %[fx], "=m" (*fx), [fx] "m" (*fx));
+	else
+		kernel_insn(fxrstorq %[fx], "=m" (*fx), [fx] "m" (*fx));
+}
+
+static inline int copy_kernel_to_fxregs_err(struct fxregs_state *fx)
+{
+	if (IS_ENABLED(CONFIG_X86_32))
+		return kernel_insn_err(fxrstor %[fx], "=m" (*fx), [fx] "m" (*fx));
+	else
+		return kernel_insn_err(fxrstorq %[fx], "=m" (*fx), [fx] "m" (*fx));
+}
+
+static inline int copy_user_to_fxregs(struct fxregs_state __user *fx)
+{
+	if (IS_ENABLED(CONFIG_X86_32))
+		return user_insn(fxrstor %[fx], "=m" (*fx), [fx] "m" (*fx));
+	else
+		return user_insn(fxrstorq %[fx], "=m" (*fx), [fx] "m" (*fx));
+}
+
+static inline void copy_kernel_to_fregs(struct fregs_state *fx)
+{
+	kernel_insn(frstor %[fx], "=m" (*fx), [fx] "m" (*fx));
+}
+
+static inline int copy_kernel_to_fregs_err(struct fregs_state *fx)
+{
+	return kernel_insn_err(frstor %[fx], "=m" (*fx), [fx] "m" (*fx));
+}
+
+static inline int copy_user_to_fregs(struct fregs_state __user *fx)
+{
+	return user_insn(frstor %[fx], "=m" (*fx), [fx] "m" (*fx));
+}
+
+static inline void copy_fxregs_to_kernel(struct fpu *fpu)
+{
+	if (IS_ENABLED(CONFIG_X86_32))
+		asm volatile( "fxsave %[fx]" : [fx] "=m" (fpu->state.fxsave));
+	else
+		asm volatile("fxsaveq %[fx]" : [fx] "=m" (fpu->state.fxsave));
+}
+
+static inline void fxsave(struct fxregs_state *fx)
+{
+	if (IS_ENABLED(CONFIG_X86_32))
+		asm volatile( "fxsave %[fx]" : [fx] "=m" (*fx));
+	else
+		asm volatile("fxsaveq %[fx]" : [fx] "=m" (*fx));
+}
+
+/* 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 XSAVES		".byte " REX_PREFIX "0x0f,0xc7,0x2f"
+#define XRSTOR		".byte " REX_PREFIX "0x0f,0xae,0x2f"
+#define XRSTORS		".byte " REX_PREFIX "0x0f,0xc7,0x1f"
+
+/*
+ * After this @err contains 0 on success or the negated trap number when
+ * the operation raises an exception. For faults this results in -EFAULT.
+ */
+#define XSTATE_OP(op, st, lmask, hmask, err)				\
+	asm volatile("1:" op "\n\t"					\
+		     "xor %[err], %[err]\n"				\
+		     "2:\n\t"						\
+		     ".pushsection .fixup,\"ax\"\n\t"			\
+		     "3: negl %%eax\n\t"				\
+		     "jmp 2b\n\t"					\
+		     ".popsection\n\t"					\
+		     _ASM_EXTABLE_FAULT(1b, 3b)				\
+		     : [err] "=a" (err)					\
+		     : "D" (st), "m" (*st), "a" (lmask), "d" (hmask)	\
+		     : "memory")
+
+/*
+ * If XSAVES is enabled, it replaces XSAVEOPT because it supports a compact
+ * format and supervisor states in addition to modified optimization in
+ * XSAVEOPT.
+ *
+ * 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.
+ */
+#define XSTATE_XSAVE(st, lmask, hmask, err)				\
+	asm volatile(ALTERNATIVE_2(XSAVE,				\
+				   XSAVEOPT, X86_FEATURE_XSAVEOPT,	\
+				   XSAVES,   X86_FEATURE_XSAVES)	\
+		     "\n"						\
+		     "xor %[err], %[err]\n"				\
+		     "3:\n"						\
+		     ".pushsection .fixup,\"ax\"\n"			\
+		     "4: movl $-2, %[err]\n"				\
+		     "jmp 3b\n"						\
+		     ".popsection\n"					\
+		     _ASM_EXTABLE(661b, 4b)				\
+		     : [err] "=r" (err)					\
+		     : "D" (st), "m" (*st), "a" (lmask), "d" (hmask)	\
+		     : "memory")
+
+/*
+ * Use XRSTORS to restore context if it is enabled. XRSTORS supports compact
+ * XSAVE area format.
+ */
+#define XSTATE_XRESTORE(st, lmask, hmask)				\
+	asm volatile(ALTERNATIVE(XRSTOR,				\
+				 XRSTORS, X86_FEATURE_XSAVES)		\
+		     "\n"						\
+		     "3:\n"						\
+		     _ASM_EXTABLE_HANDLE(661b, 3b, ex_handler_fprestore)\
+		     :							\
+		     : "D" (st), "m" (*st), "a" (lmask), "d" (hmask)	\
+		     : "memory")
+
+/*
+ * This function is called only during boot time when x86 caps are not set
+ * up and alternative can not be used yet.
+ */
+static inline void copy_kernel_to_xregs_booting(struct xregs_state *xstate)
+{
+	u64 mask = -1;
+	u32 lmask = mask;
+	u32 hmask = mask >> 32;
+	int err;
+
+	WARN_ON(system_state != SYSTEM_BOOTING);
+
+	if (boot_cpu_has(X86_FEATURE_XSAVES))
+		XSTATE_OP(XRSTORS, xstate, lmask, hmask, err);
+	else
+		XSTATE_OP(XRSTOR, xstate, lmask, hmask, err);
+
+	/*
+	 * We should never fault when copying from a kernel buffer, and the FPU
+	 * state we set at boot time should be valid.
+	 */
+	WARN_ON_FPU(err);
+}
+
+/*
+ * Save processor xstate to xsave area.
+ */
+static inline void copy_xregs_to_kernel(struct xregs_state *xstate)
+{
+	u64 mask = xfeatures_mask_all;
+	u32 lmask = mask;
+	u32 hmask = mask >> 32;
+	int err;
+
+	WARN_ON_FPU(!alternatives_patched);
+
+	XSTATE_XSAVE(xstate, lmask, hmask, err);
+
+	/* We should never fault when copying to a kernel buffer: */
+	WARN_ON_FPU(err);
+}
+
+/*
+ * Restore processor xstate from xsave area.
+ */
+static inline void copy_kernel_to_xregs(struct xregs_state *xstate, u64 mask)
+{
+	u32 lmask = mask;
+	u32 hmask = mask >> 32;
+
+	XSTATE_XRESTORE(xstate, lmask, hmask);
+}
+
+/*
+ * Save xstate to user space xsave area.
+ *
+ * We don't use modified optimization because xrstor/xrstors might track
+ * a different application.
+ *
+ * We don't use compacted format xsave area for
+ * backward compatibility for old applications which don't understand
+ * compacted format of xsave area.
+ */
+static inline int copy_xregs_to_user(struct xregs_state __user *buf)
+{
+	u64 mask = xfeatures_mask_user();
+	u32 lmask = mask;
+	u32 hmask = mask >> 32;
+	int err;
+
+	/*
+	 * Clear the xsave header first, so that reserved fields are
+	 * initialized to zero.
+	 */
+	err = __clear_user(&buf->header, sizeof(buf->header));
+	if (unlikely(err))
+		return -EFAULT;
+
+	stac();
+	XSTATE_OP(XSAVE, buf, lmask, hmask, err);
+	clac();
+
+	return err;
+}
+
+/*
+ * Restore xstate from user space xsave area.
+ */
+static inline int copy_user_to_xregs(struct xregs_state __user *buf, u64 mask)
+{
+	struct xregs_state *xstate = ((__force struct xregs_state *)buf);
+	u32 lmask = mask;
+	u32 hmask = mask >> 32;
+	int err;
+
+	stac();
+	XSTATE_OP(XRSTOR, xstate, lmask, hmask, err);
+	clac();
+
+	return err;
+}
+
+/*
+ * Restore xstate from kernel space xsave area, return an error code instead of
+ * an exception.
+ */
+static inline int copy_kernel_to_xregs_err(struct xregs_state *xstate, u64 mask)
+{
+	u32 lmask = mask;
+	u32 hmask = mask >> 32;
+	int err;
+
+	if (static_cpu_has(X86_FEATURE_XSAVES))
+		XSTATE_OP(XRSTORS, xstate, lmask, hmask, err);
+	else
+		XSTATE_OP(XRSTOR, xstate, lmask, hmask, err);
+
+	return err;
+}
+
+extern int copy_fpregs_to_fpstate(struct fpu *fpu);
+
+static inline void __copy_kernel_to_fpregs(union fpregs_state *fpstate, u64 mask)
+{
+	if (use_xsave()) {
+		copy_kernel_to_xregs(&fpstate->xsave, mask);
+	} else {
+		if (use_fxsr())
+			copy_kernel_to_fxregs(&fpstate->fxsave);
+		else
+			copy_kernel_to_fregs(&fpstate->fsave);
+	}
+}
+
+static inline void copy_kernel_to_fpregs(union fpregs_state *fpstate)
+{
+	/*
+	 * AMD K7/K8 CPUs don't save/restore FDP/FIP/FOP unless an exception is
+	 * pending. Clear the x87 state here by setting it to fixed values.
+	 * "m" is a random variable that should be in L1.
+	 */
+	if (unlikely(static_cpu_has_bug(X86_BUG_FXSAVE_LEAK))) {
+		asm volatile(
+			"fnclex\n\t"
+			"emms\n\t"
+			"fildl %P[addr]"	/* set F?P to defined value */
+			: : [addr] "m" (fpstate));
+	}
+
+	__copy_kernel_to_fpregs(fpstate, -1);
+}
+
+extern int copy_fpstate_to_sigframe(void __user *buf, void __user *fp, int size);
+
+/*
+ * FPU context switch related helper methods:
+ */
+
+DECLARE_PER_CPU(struct fpu *, fpu_fpregs_owner_ctx);
+
+/*
+ * The in-register FPU state for an FPU context on a CPU is assumed to be
+ * valid if the fpu->last_cpu matches the CPU, and the fpu_fpregs_owner_ctx
+ * matches the FPU.
+ *
+ * If the FPU register state is valid, the kernel can skip restoring the
+ * FPU state from memory.
+ *
+ * Any code that clobbers the FPU registers or updates the in-memory
+ * 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
+ * (with preemption disabled), FPU for the current task, or a task that
+ * is prevented from running by the current task.
+ */
+static inline void __cpu_invalidate_fpregs_state(void)
+{
+	__this_cpu_write(fpu_fpregs_owner_ctx, NULL);
+}
+
+static inline void __fpu_invalidate_fpregs_state(struct fpu *fpu)
+{
+	fpu->last_cpu = -1;
+}
+
+static inline int fpregs_state_valid(struct fpu *fpu, unsigned int cpu)
+{
+	return fpu == this_cpu_read(fpu_fpregs_owner_ctx) && cpu == fpu->last_cpu;
+}
+
+/*
+ * These generally need preemption protection to work,
+ * do try to avoid using these on their own:
+ */
+static inline void fpregs_deactivate(struct fpu *fpu)
+{
+	this_cpu_write(fpu_fpregs_owner_ctx, NULL);
+	trace_x86_fpu_regs_deactivated(fpu);
+}
+
+static inline void fpregs_activate(struct fpu *fpu)
+{
+	this_cpu_write(fpu_fpregs_owner_ctx, fpu);
+	trace_x86_fpu_regs_activated(fpu);
+}
+
+/*
+ * Internal helper, do not use directly. Use switch_fpu_return() instead.
+ */
+static inline void __fpregs_load_activate(void)
+{
+	struct fpu *fpu = &current->thread.fpu;
+	int cpu = smp_processor_id();
+
+	if (WARN_ON_ONCE(current->flags & PF_KTHREAD))
+		return;
+
+	if (!fpregs_state_valid(fpu, cpu)) {
+		copy_kernel_to_fpregs(&fpu->state);
+		fpregs_activate(fpu);
+		fpu->last_cpu = cpu;
+	}
+	clear_thread_flag(TIF_NEED_FPU_LOAD);
+}
+
+/*
+ * 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 task_struct *prev, int cpu)
+{
+	struct fpu *old_fpu = &prev->thread.fpu;
+
+	if (static_cpu_has(X86_FEATURE_FPU) && !(prev->flags & PF_KTHREAD)) {
+		if (!copy_fpregs_to_fpstate(old_fpu))
+			old_fpu->last_cpu = -1;
+		else
+			old_fpu->last_cpu = cpu;
+
+		/* But leave fpu_fpregs_owner_ctx! */
+		trace_x86_fpu_regs_deactivated(old_fpu);
+	}
+}
+
+/*
+ * Misc helper functions:
+ */
+
+/*
+ * Load PKRU from the FPU context if available. Delay loading of the
+ * complete FPU state until the return to userland.
+ */
+static inline void switch_fpu_finish(struct task_struct *next)
+{
+	u32 pkru_val = init_pkru_value;
+	struct pkru_state *pk;
+	struct fpu *next_fpu = &next->thread.fpu;
+
+	if (!static_cpu_has(X86_FEATURE_FPU))
+		return;
+
+	set_thread_flag(TIF_NEED_FPU_LOAD);
+
+	if (!cpu_feature_enabled(X86_FEATURE_OSPKE))
+		return;
+
+	/*
+	 * PKRU state is switched eagerly because it needs to be valid before we
+	 * return to userland e.g. for a copy_to_user() operation.
+	 */
+	if (!(next->flags & PF_KTHREAD)) {
+		/*
+		 * If the PKRU bit in xsave.header.xfeatures is not set,
+		 * then the PKRU component was in init state, which means
+		 * XRSTOR will set PKRU to 0. If the bit is not set then
+		 * get_xsave_addr() will return NULL because the PKRU value
+		 * in memory is not valid. This means pkru_val has to be
+		 * set to 0 and not to init_pkru_value.
+		 */
+		pk = get_xsave_addr(&next_fpu->state.xsave, XFEATURE_PKRU);
+		pkru_val = pk ? pk->pkru : 0;
+	}
+	__write_pkru(pkru_val);
+}
+
+#endif /* _ASM_X86_FPU_INTERNAL_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/signal.h b/arch/x86/include/asm/fpu/signal.h
new file mode 100644
index 000000000..7fb516b68
--- /dev/null
+++ b/arch/x86/include/asm/fpu/signal.h
@@ -0,0 +1,34 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * x86 FPU signal frame handling methods:
+ */
+#ifndef _ASM_X86_FPU_SIGNAL_H
+#define _ASM_X86_FPU_SIGNAL_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);
+
+extern void fpu__init_prepare_fx_sw_frame(void);
+
+#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..f5a38a5f3
--- /dev/null
+++ b/arch/x86/include/asm/fpu/types.h
@@ -0,0 +1,355 @@
+/* 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_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_FPSSE		(XFEATURE_MASK_FP | XFEATURE_MASK_SSE)
+#define XFEATURE_MASK_AVX512		(XFEATURE_MASK_OPMASK \
+					 | XFEATURE_MASK_ZMM_Hi256 \
+					 | XFEATURE_MASK_Hi16_ZMM)
+
+#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];
+};
+
+/*
+ * 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[];
+} __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];
+};
+
+/*
+ * 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;
+
+	/*
+	 * @state:
+	 *
+	 * In-memory copy of all FPU registers that we save/restore
+	 * over context switches. If the task is using the FPU then
+	 * the registers in the FPU are more recent than this state
+	 * copy. If the task context-switches away then they get
+	 * saved here and represent the FPU state.
+	 */
+	union fpregs_state		state;
+	/*
+	 * WARNING: 'state' is dynamically-sized.  Do not put
+	 * anything after it here.
+	 */
+};
+
+#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..1c7ab8d95
--- /dev/null
+++ b/arch/x86/include/asm/fpu/xcr.h
@@ -0,0 +1,34 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _ASM_X86_FPU_XCR_H
+#define _ASM_X86_FPU_XCR_H
+
+/*
+ * MXCSR and XCR definitions:
+ */
+
+static inline void ldmxcsr(u32 mxcsr)
+{
+	asm volatile("ldmxcsr %0" :: "m" (mxcsr));
+}
+
+extern unsigned int mxcsr_feature_mask;
+
+#define XCR_XFEATURE_ENABLED_MASK	0x00000000
+
+static 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));
+}
+
+#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..47a92232d
--- /dev/null
+++ b/arch/x86/include/asm/fpu/xstate.h
@@ -0,0 +1,119 @@
+/* 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/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 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)
+
+/* 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 dynamic supervisor features are set in this mask.
+ *
+ * Unlike the existing supported supervisor features, a dynamic 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 a dynamic 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 dynamic supervisor feature in
+ *   IA32_XSS at run time, since it has been set at boot time.
+ */
+#define XFEATURE_MASK_DYNAMIC (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_DYNAMIC | \
+				      XFEATURE_MASK_SUPERVISOR_UNSUPPORTED)
+
+#ifdef CONFIG_X86_64
+#define REX_PREFIX	"0x48, "
+#else
+#define REX_PREFIX
+#endif
+
+extern u64 xfeatures_mask_all;
+
+static inline u64 xfeatures_mask_supervisor(void)
+{
+	return xfeatures_mask_all & XFEATURE_MASK_SUPERVISOR_SUPPORTED;
+}
+
+static inline u64 xfeatures_mask_user(void)
+{
+	return xfeatures_mask_all & XFEATURE_MASK_USER_SUPPORTED;
+}
+
+static inline u64 xfeatures_mask_dynamic(void)
+{
+	if (!boot_cpu_has(X86_FEATURE_ARCH_LBR))
+		return XFEATURE_MASK_DYNAMIC & ~XFEATURE_MASK_LBR;
+
+	return XFEATURE_MASK_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);
+
+void *get_xsave_addr(struct xregs_state *xsave, int xfeature_nr);
+const void *get_xsave_field_ptr(int xfeature_nr);
+int using_compacted_format(void);
+int xfeature_size(int xfeature_nr);
+struct membuf;
+void copy_xstate_to_kernel(struct membuf to, struct xregs_state *xsave);
+int copy_kernel_to_xstate(struct xregs_state *xsave, const void *kbuf);
+int copy_user_to_xstate(struct xregs_state *xsave, const void __user *ubuf);
+void copy_supervisor_to_kernel(struct xregs_state *xsave);
+void copy_dynamic_supervisor_to_kernel(struct xregs_state *xstate, u64 mask);
+void copy_kernel_to_dynamic_supervisor(struct xregs_state *xstate, u64 mask);
+
+
+/* Validate an xstate header supplied by userspace (ptrace or sigreturn) */
+int validate_user_xstate_header(const struct xstate_header *hdr);
+
+#endif