Merge branch 'x86/fpu' into x86/core, to merge dependent commits

Prepare to resolve conflicts with an upstream series of fixes that conflict with pending x86 changes: 6f5bf947ba Merge tag 'its-for-linus-20250509' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip Signed-off-by: Ingo Molnar <mingo@kernel.org>
2026-04-05 05:59:10 +08:00 · 2025-05-13 10:37:29 +02:00
parent 2fb8414e64 32d5fa804d
commit ec8f353f52
31 changed files with 294 additions and 236 deletions
--- a/arch/x86/include/asm/cpufeatures.h
+++ b/arch/x86/include/asm/cpufeatures.h
@@ -481,6 +481,7 @@
 #define X86_FEATURE_AMD_HTR_CORES	(21*32+ 6) /* Heterogeneous Core Topology */
 #define X86_FEATURE_AMD_WORKLOAD_CLASS	(21*32+ 7) /* Workload Classification */
 #define X86_FEATURE_PREFER_YMM		(21*32+ 8) /* Avoid ZMM registers due to downclocking */
+#define X86_FEATURE_APX			(21*32+ 9) /* Advanced Performance Extensions */

 /*
 * BUG word(s)
--- a/arch/x86/include/asm/entry-common.h
+++ b/arch/x86/include/asm/entry-common.h
@@ -53,7 +53,6 @@ static inline void arch_exit_work(unsigned long ti_work)
 	if (unlikely(ti_work & _TIF_IO_BITMAP))
 		tss_update_io_bitmap();

-	fpregs_assert_state_consistent();
 	if (unlikely(ti_work & _TIF_NEED_FPU_LOAD))
 		switch_fpu_return();
 }
@@ -61,7 +60,9 @@ static inline void arch_exit_work(unsigned long ti_work)
 static inline void arch_exit_to_user_mode_prepare(struct pt_regs *regs,
 						  unsigned long ti_work)
 {
-	if (IS_ENABLED(CONFIG_X86_DEBUG_FPU) || unlikely(ti_work))
+	fpregs_assert_state_consistent();
+
+	if (unlikely(ti_work))
 		arch_exit_work(ti_work);

 	fred_update_rsp0();
--- a/arch/x86/include/asm/fpu/api.h
+++ b/arch/x86/include/asm/fpu/api.h
@@ -136,7 +136,7 @@ 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);

--- 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 */
--- a/arch/x86/include/asm/fpu/types.h
+++ b/arch/x86/include/asm/fpu/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 \
@@ -303,6 +305,13 @@ struct xtile_data {
 	struct reg_1024_byte		tmm;
 } __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
@@ -524,13 +535,6 @@ 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.
 	 */
--- a/arch/x86/include/asm/fpu/xstate.h
+++ b/arch/x86/include/asm/fpu/xstate.h
@@ -32,7 +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.
--- a/arch/x86/include/asm/processor.h
+++ b/arch/x86/include/asm/processor.h
@@ -514,15 +514,14 @@ struct thread_struct {

 	struct thread_shstk	shstk;
 #endif
-
-	/* Floating point and extended processor state */
-	struct fpu		fpu;
-	/*
-	 * WARNING: 'fpu' is dynamically-sized.  It *MUST* be at
-	 * the end.
-	 */
 };

+#ifdef CONFIG_X86_DEBUG_FPU
+extern struct fpu *x86_task_fpu(struct task_struct *task);
+#else
+# define x86_task_fpu(task)	((struct fpu *)((void *)(task) + sizeof(*(task))))
+#endif
+
 extern void fpu_thread_struct_whitelist(unsigned long *offset, unsigned long *size);

 static inline void arch_thread_struct_whitelist(unsigned long *offset,
--- a/arch/x86/include/asm/trace/fpu.h
+++ b/arch/x86/include/asm/trace/fpu.h
@@ -74,11 +74,6 @@ DEFINE_EVENT(x86_fpu, x86_fpu_dropped,
 	TP_ARGS(fpu)
 );

-DEFINE_EVENT(x86_fpu, x86_fpu_copy_src,
-	TP_PROTO(struct fpu *fpu),
-	TP_ARGS(fpu)
-);
-
 DEFINE_EVENT(x86_fpu, x86_fpu_copy_dst,
 	TP_PROTO(struct fpu *fpu),
 	TP_ARGS(fpu)
--- a/arch/x86/kernel/cpu/cpuid-deps.c
+++ b/arch/x86/kernel/cpu/cpuid-deps.c
@@ -28,6 +28,7 @@ static const struct cpuid_dep cpuid_deps[] = {
 	{ X86_FEATURE_PKU,			X86_FEATURE_XSAVE     },
 	{ X86_FEATURE_MPX,			X86_FEATURE_XSAVE     },
 	{ X86_FEATURE_XGETBV1,			X86_FEATURE_XSAVE     },
+	{ X86_FEATURE_APX,			X86_FEATURE_XSAVE     },
 	{ X86_FEATURE_CMOV,			X86_FEATURE_FXSR      },
 	{ X86_FEATURE_MMX,			X86_FEATURE_FXSR      },
 	{ X86_FEATURE_MMXEXT,			X86_FEATURE_MMX       },
--- a/arch/x86/kernel/cpu/scattered.c
+++ b/arch/x86/kernel/cpu/scattered.c
@@ -27,6 +27,7 @@ static const struct cpuid_bit cpuid_bits[] = {
 	{ X86_FEATURE_APERFMPERF,		CPUID_ECX,  0, 0x00000006, 0 },
 	{ X86_FEATURE_EPB,			CPUID_ECX,  3, 0x00000006, 0 },
 	{ X86_FEATURE_INTEL_PPIN,		CPUID_EBX,  0, 0x00000007, 1 },
+	{ X86_FEATURE_APX,			CPUID_EDX, 21, 0x00000007, 1 },
 	{ X86_FEATURE_RRSBA_CTRL,		CPUID_EDX,  2, 0x00000007, 2 },
 	{ X86_FEATURE_BHI_CTRL,			CPUID_EDX,  4, 0x00000007, 2 },
 	{ X86_FEATURE_CQM_LLC,			CPUID_EDX,  1, 0x0000000f, 0 },
--- a/arch/x86/kernel/fpu/context.h
+++ b/arch/x86/kernel/fpu/context.h
@@ -53,7 +53,7 @@ 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 = &current->thread.fpu;
+	struct fpu *fpu = x86_task_fpu(current);
 	int cpu = smp_processor_id();

 	if (WARN_ON_ONCE(current->flags & (PF_KTHREAD | PF_USER_WORKER)))
@@ -67,7 +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().
 		 */
--- a/arch/x86/kernel/fpu/core.c
+++ b/arch/x86/kernel/fpu/core.c
@@ -51,6 +51,16 @@ static DEFINE_PER_CPU(bool, in_kernel_fpu);
 */
 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?
@@ -202,7 +212,7 @@ void fpu_reset_from_exception_fixup(void)
 #if IS_ENABLED(CONFIG_KVM)
 static void __fpstate_reset(struct fpstate *fpstate, u64 xfd);

-static void fpu_init_guest_permissions(struct fpu_guest *gfpu)
+static void fpu_lock_guest_permissions(void)
 {
 	struct fpu_state_perm *fpuperm;
 	u64 perm;
@@ -211,15 +221,13 @@ static void fpu_init_guest_permissions(struct fpu_guest *gfpu)
 		return;

 	spin_lock_irq(&current->sighand->siglock);
-	fpuperm = &current->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(&current->sighand->siglock);
-
-	gfpu->perm = perm & ~FPU_GUEST_PERM_LOCKED;
 }

 bool fpu_alloc_guest_fpstate(struct fpu_guest *gfpu)
@@ -240,7 +248,6 @@ bool fpu_alloc_guest_fpstate(struct fpu_guest *gfpu)

 	gfpu->fpstate		= fpstate;
 	gfpu->xfeatures		= fpu_kernel_cfg.default_features;
-	gfpu->perm		= fpu_kernel_cfg.default_features;

 	/*
 	 * KVM sets the FP+SSE bits in the XSAVE header when copying FPU state
@@ -255,7 +262,7 @@ 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;
 }
@@ -263,16 +270,16 @@ EXPORT_SYMBOL_GPL(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);

@@ -323,12 +330,12 @@ 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);
+		rdmsrl(MSR_IA32_XFD, fpstate->xfd);
+		__this_cpu_write(xfd_state, fpstate->xfd);
 	}
 }
 EXPORT_SYMBOL_GPL(fpu_sync_guest_vmexit_xfd_state);
@@ -337,7 +344,7 @@ EXPORT_SYMBOL_GPL(fpu_sync_guest_vmexit_xfd_state);
 int fpu_swap_kvm_fpstate(struct fpu_guest *guest_fpu, bool enter_guest)
 {
 	struct fpstate *guest_fps = guest_fpu->fpstate;
-	struct fpu *fpu = &current->thread.fpu;
+	struct fpu *fpu = x86_task_fpu(current);
 	struct fpstate *cur_fps = fpu->fpstate;

 	fpregs_lock();
@@ -438,7 +445,7 @@ void kernel_fpu_begin_mask(unsigned int kfpu_mask)
 	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(&current->thread.fpu);
+		save_fpregs_to_fpstate(x86_task_fpu(current));
 	}
 	__cpu_invalidate_fpregs_state();

@@ -467,7 +474,7 @@ EXPORT_SYMBOL_GPL(kernel_fpu_end);
 */
 void fpu_sync_fpstate(struct fpu *fpu)
 {
-	WARN_ON_FPU(fpu != &current->thread.fpu);
+	WARN_ON_FPU(fpu != x86_task_fpu(current));

 	fpregs_lock();
 	trace_x86_fpu_before_save(fpu);
@@ -552,7 +559,7 @@ void fpstate_reset(struct fpu *fpu)
 static inline void fpu_inherit_perms(struct fpu *dst_fpu)
 {
 	if (fpu_state_size_dynamic()) {
-		struct fpu *src_fpu = &current->group_leader->thread.fpu;
+		struct fpu *src_fpu = x86_task_fpu(current->group_leader);

 		spin_lock_irq(&current->sighand->siglock);
 		/* Fork also inherits the permissions of the parent */
@@ -572,7 +579,7 @@ static int update_fpu_shstk(struct task_struct *dst, unsigned long ssp)
 	if (!ssp)
 		return 0;

-	xstate = get_xsave_addr(&dst->thread.fpu.fpstate->regs.xsave,
+	xstate = get_xsave_addr(&x86_task_fpu(dst)->fpstate->regs.xsave,
 				XFEATURE_CET_USER);

 	/*
@@ -593,8 +600,16 @@ static int update_fpu_shstk(struct task_struct *dst, unsigned long ssp)
 int fpu_clone(struct task_struct *dst, unsigned long clone_flags, bool minimal,
 	      unsigned long ssp)
 {
-	struct fpu *src_fpu = &current->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;
@@ -657,19 +672,22 @@ int fpu_clone(struct task_struct *dst, unsigned long clone_flags, bool minimal,
 	if (update_fpu_shstk(dst, ssp))
 		return 1;

-	trace_x86_fpu_copy_src(src_fpu);
 	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;
 }

@@ -682,11 +700,18 @@ 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 == &current->thread.fpu) {
+	if (fpu == x86_task_fpu(current)) {
 		/* Ignore delayed exceptions from user space */
 		asm volatile("1: fwait\n"
 			     "2:\n"
@@ -718,9 +743,9 @@ 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 = &current->thread.fpu;
+	struct fpu *fpu = x86_task_fpu(current);

 	fpregs_lock();
 	__fpu_invalidate_fpregs_state(fpu);
@@ -749,11 +774,11 @@ static void fpu_reset_fpregs(void)
 */
 void fpu__clear_user_states(struct fpu *fpu)
 {
-	WARN_ON_FPU(fpu != &current->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;
 	}
@@ -782,8 +807,8 @@ void fpu__clear_user_states(struct fpu *fpu)

 void fpu_flush_thread(void)
 {
-	fpstate_reset(&current->thread.fpu);
-	fpu_reset_fpregs();
+	fpstate_reset(x86_task_fpu(current));
+	fpu_reset_fpstate_regs();
 }
 /*
 * Load FPU context before returning to userspace.
@@ -823,7 +848,7 @@ void fpregs_lock_and_load(void)
 */
 void fpregs_assert_state_consistent(void)
 {
-	struct fpu *fpu = &current->thread.fpu;
+	struct fpu *fpu = x86_task_fpu(current);

 	if (test_thread_flag(TIF_NEED_FPU_LOAD))
 		return;
@@ -835,7 +860,7 @@ EXPORT_SYMBOL_GPL(fpregs_assert_state_consistent);

 void fpregs_mark_activate(void)
 {
-	struct fpu *fpu = &current->thread.fpu;
+	struct fpu *fpu = x86_task_fpu(current);

 	fpregs_activate(fpu);
 	fpu->last_cpu = smp_processor_id();
--- 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(&current->thread.fpu.fpstate->regs.soft);
+		;
 	else
 #endif
 		asm volatile ("fninit");
@@ -73,6 +73,8 @@ static bool __init fpu__probe_without_cpuid(void)

 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 +96,6 @@ static void __init fpu__init_system_early_generic(void)
 * 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 +151,13 @@ 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 +167,9 @@ 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;
 }
@@ -204,7 +202,6 @@ 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(&current->thread.fpu);
 }

 /*
@@ -213,7 +210,6 @@ static void __init fpu__init_system_xstate_size_legacy(void)
 */
 void __init fpu__init_system(void)
 {
-	fpstate_reset(&current->thread.fpu);
 	fpu__init_system_early_generic();

 	/*
--- a/arch/x86/kernel/fpu/regset.c
+++ b/arch/x86/kernel/fpu/regset.c
@@ -45,7 +45,7 @@ int regset_xregset_fpregs_active(struct task_struct *target, const struct user_r
 */
 static void sync_fpstate(struct fpu *fpu)
 {
-	if (fpu == &current->thread.fpu)
+	if (fpu == x86_task_fpu(current))
 		fpu_sync_fpstate(fpu);
 }

@@ -63,7 +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 == &current->thread.fpu);
+	WARN_ON_FPU(fpu == x86_task_fpu(current));

 	__fpu_invalidate_fpregs_state(fpu);
 }
@@ -71,7 +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;
@@ -91,7 +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;

@@ -133,7 +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;
@@ -143,7 +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;

@@ -187,7 +187,7 @@ int ssp_active(struct task_struct *target, const struct user_regset *regset)
 int ssp_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 cet_user_state *cetregs;

 	if (!cpu_feature_enabled(X86_FEATURE_USER_SHSTK) ||
@@ -214,7 +214,7 @@ 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 = &target->thread.fpu;
+	struct fpu *fpu = x86_task_fpu(target);
 	struct xregs_state *xsave = &fpu->fpstate->regs.xsave;
 	struct cet_user_state *cetregs;
 	unsigned long user_ssp;
@@ -368,7 +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,
@@ -401,7 +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;

@@ -433,7 +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;

--- a/arch/x86/kernel/fpu/signal.c
+++ b/arch/x86/kernel/fpu/signal.c
@@ -43,13 +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 + current->thread.fpu.fpstate->user_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(&current->thread.fpu);
+	trace_x86_fpu_xstate_check_failed(x86_task_fpu(current));

 	/* Set the parameters for fx only state */
 	fx_sw->magic1 = 0;
@@ -64,13 +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);
@@ -114,7 +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. */
@@ -127,12 +126,6 @@ static inline bool save_xstate_epilog(void __user *buf, int ia32_frame,
 	err |= __put_user(FP_XSTATE_MAGIC2,
 			  (__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
@@ -144,9 +137,7 @@ 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;
 }
@@ -184,7 +175,7 @@ static inline int copy_fpregs_to_sigframe(struct xregs_state __user *buf, u32 pk
 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;

@@ -272,7 +263,7 @@ static int __restore_fpregs_from_user(void __user *buf, u64 ufeatures,
 */
 static bool restore_fpregs_from_user(void __user *buf, u64 xrestore, bool fx_only)
 {
-	struct fpu *fpu = &current->thread.fpu;
+	struct fpu *fpu = x86_task_fpu(current);
 	int ret;

 	/* Restore enabled features only. */
@@ -332,7 +323,7 @@ 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;
@@ -452,7 +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 = &current->thread.fpu;
+	struct fpu *fpu = x86_task_fpu(current);
 	void __user *buf_fx = buf;
 	bool ia32_fxstate = false;
 	bool success = false;
@@ -499,7 +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()) {
--- a/arch/x86/kernel/fpu/xstate.c
+++ b/arch/x86/kernel/fpu/xstate.c
@@ -14,6 +14,7 @@
 #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>
@@ -62,6 +63,7 @@ static const char *xfeature_names[] =
 	"unknown xstate feature",
 	"AMX Tile config",
 	"AMX Tile data",
+	"APX registers",
 	"unknown xstate feature",
 };

@@ -80,6 +82,7 @@ static unsigned short xsave_cpuid_features[] __initdata = {
 	[XFEATURE_CET_USER]			= 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 =
@@ -88,6 +91,31 @@ 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)

@@ -209,16 +237,20 @@ 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
@@ -232,31 +264,30 @@ 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(CPUID_LEAF_XSTATE, 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;
 	}
+
+	/*
+	 * 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);
 }

 /*
@@ -340,7 +371,8 @@ static __init void os_xrstor_booting(struct xregs_state *xstate)
 	 XFEATURE_MASK_BNDCSR |			\
 	 XFEATURE_MASK_PASID |			\
 	 XFEATURE_MASK_CET_USER |		\
-	 XFEATURE_MASK_XTILE)
+	 XFEATURE_MASK_XTILE |			\
+	 XFEATURE_MASK_APX)

 /*
 * setup the xstate image representing the init state
@@ -540,6 +572,7 @@ static bool __init check_xstate_against_struct(int nr)
 	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_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);
@@ -552,13 +585,20 @@ static bool __init check_xstate_against_struct(int nr)
 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];
 }

@@ -711,6 +751,8 @@ 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);
@@ -727,7 +769,7 @@ static void __init fpu__init_disable_system_xstate(unsigned int legacy_size)
 	 */
 	init_fpstate.xfd = 0;

-	fpstate_reset(&current->thread.fpu);
+	fpstate_reset(x86_task_fpu(current));
 }

 /*
@@ -775,6 +817,17 @@ 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;

@@ -834,9 +887,6 @@ void __init fpu__init_system_xstate(unsigned int legacy_size)
 	if (err)
 		goto out_disable;

-	/* Reset the state for the current task */
-	fpstate_reset(&current->thread.fpu);
-
 	/*
 	 * Update info used for ptrace frames; use standard-format size and no
 	 * supervisor xstates:
@@ -852,7 +902,7 @@ 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;
 	}
@@ -864,7 +914,7 @@ 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;
 	}
@@ -909,7 +959,7 @@ void fpu__resume_cpu(void)
 	}

 	if (fpu_state_size_dynamic())
-		wrmsrl(MSR_IA32_XFD, current->thread.fpu.fpstate->xfd);
+		wrmsrl(MSR_IA32_XFD, x86_task_fpu(current)->fpstate->xfd);
 }

 /*
@@ -1071,10 +1121,9 @@ void __copy_xstate_to_uabi_buf(struct membuf to, struct fpstate *fpstate,
 	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;
@@ -1143,15 +1192,16 @@ void __copy_xstate_to_uabi_buf(struct membuf to, struct fpstate *fpstate,
 	 */
 	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
@@ -1161,14 +1211,14 @@ void __copy_xstate_to_uabi_buf(struct membuf to, struct fpstate *fpstate,
 			membuf_write(&to, &pkru, sizeof(pkru));
 		} else {
 			membuf_write(&to,
-				     __raw_xsave_addr(xsave, i),
-				     xstate_sizes[i]);
+				     __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:
@@ -1191,8 +1241,8 @@ 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,
-				  tsk->thread.fpu.fpstate->user_xfeatures,
+	__copy_xstate_to_uabi_buf(to, x86_task_fpu(tsk)->fpstate,
+				  x86_task_fpu(tsk)->fpstate->user_xfeatures,
 				  tsk->thread.pkru, copy_mode);
 }

@@ -1332,7 +1382,7 @@ 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)
@@ -1398,9 +1448,9 @@ 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]);
@@ -1426,7 +1476,7 @@ 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;

 	/*
@@ -1503,7 +1553,7 @@ 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 = &current->thread.fpu;
+	struct fpu *fpu = x86_task_fpu(current);
 	struct fpstate *curfps, *newfps = NULL;
 	unsigned int fpsize;
 	bool in_use;
@@ -1596,7 +1646,7 @@ static int __xstate_request_perm(u64 permitted, u64 requested, bool guest)
 	 * AVX512.
 	 */
 	bool compacted = cpu_feature_enabled(X86_FEATURE_XCOMPACTED);
-	struct fpu *fpu = &current->group_leader->thread.fpu;
+	struct fpu *fpu = x86_task_fpu(current->group_leader);
 	struct fpu_state_perm *perm;
 	unsigned int ksize, usize;
 	u64 mask;
@@ -1606,16 +1656,20 @@ 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);
@@ -1699,7 +1753,7 @@ int __xfd_enable_feature(u64 xfd_err, struct fpu_guest *guest_fpu)
 		return -EPERM;
 	}

-	fpu = &current->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;
@@ -1804,7 +1858,7 @@ long fpu_xstate_prctl(int option, unsigned long arg2)
 */
 static void avx512_status(struct seq_file *m, struct task_struct *task)
 {
-	unsigned long timestamp = READ_ONCE(task->thread.fpu.avx512_timestamp);
+	unsigned long timestamp = READ_ONCE(x86_task_fpu(task)->avx512_timestamp);
 	long delta;

 	if (!timestamp) {
--- a/arch/x86/kernel/fpu/xstate.h
+++ b/arch/x86/kernel/fpu/xstate.h
@@ -22,7 +22,7 @@ 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 = &current->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() */
@@ -69,21 +69,31 @@ static inline u64 xfeatures_mask_independent(void)
 	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, u64 mask, u32 pkru)
+static inline int update_pkru_in_sigframe(struct xregs_state __user *buf, u32 pkru)
 {
-	u64 xstate_bv;
 	int err;

 	if (unlikely(!cpu_feature_enabled(X86_FEATURE_OSPKE)))
 		return 0;

 	/* Mark PKRU as in-use so that it is restored correctly. */
-	xstate_bv = (mask & xfeatures_in_use()) | XFEATURE_MASK_PKRU;
-
-	err =  __put_user(xstate_bv, &buf->header.xfeatures);
+	err = set_xfeature_in_sigframe(buf, XFEATURE_MASK_PKRU);
 	if (err)
 		return err;

@@ -288,7 +298,7 @@ static inline int xsave_to_user_sigframe(struct xregs_state __user *buf, u32 pkr
 	 * 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;
@@ -307,7 +317,7 @@ static inline int xsave_to_user_sigframe(struct xregs_state __user *buf, u32 pkr
 	clac();

 	if (!err)
-		err = update_pkru_in_sigframe(buf, mask, pkru);
+		err = update_pkru_in_sigframe(buf, pkru);

 	return err;
 }
@@ -322,7 +332,7 @@ 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);
--- a/arch/x86/kernel/process.c
+++ b/arch/x86/kernel/process.c
@@ -93,17 +93,12 @@ EXPORT_PER_CPU_SYMBOL_GPL(__tss_limit_invalid);
 */
 int arch_dup_task_struct(struct task_struct *dst, struct task_struct *src)
 {
-	/* init_task is not dynamically sized (incomplete FPU state) */
-	if (unlikely(src == &init_task))
-		memcpy_and_pad(dst, arch_task_struct_size, src, sizeof(init_task), 0);
-	else
-		memcpy(dst, src, arch_task_struct_size);
+	/* fpu_clone() will initialize the "dst_fpu" memory */
+	memcpy_and_pad(dst, arch_task_struct_size, src, sizeof(*dst), 0);

 #ifdef CONFIG_VM86
 	dst->thread.vm86 = NULL;
 #endif
-	/* Drop the copied pointer to current's fpstate */
-	dst->thread.fpu.fpstate = NULL;

 	return 0;
 }
@@ -111,8 +106,8 @@ int arch_dup_task_struct(struct task_struct *dst, struct task_struct *src)
 #ifdef CONFIG_X86_64
 void arch_release_task_struct(struct task_struct *tsk)
 {
-	if (fpu_state_size_dynamic())
-		fpstate_free(&tsk->thread.fpu);
+	if (fpu_state_size_dynamic() && !(tsk->flags & (PF_KTHREAD | PF_USER_WORKER)))
+		fpstate_free(x86_task_fpu(tsk));
 }
 #endif

@@ -122,7 +117,6 @@ void arch_release_task_struct(struct task_struct *tsk)
 void exit_thread(struct task_struct *tsk)
 {
 	struct thread_struct *t = &tsk->thread;
-	struct fpu *fpu = &t->fpu;

 	if (test_thread_flag(TIF_IO_BITMAP))
 		io_bitmap_exit(tsk);
@@ -130,7 +124,7 @@ void exit_thread(struct task_struct *tsk)
 	free_vm86(t);

 	shstk_free(tsk);
-	fpu__drop(fpu);
+	fpu__drop(tsk);
 }

 static int set_new_tls(struct task_struct *p, unsigned long tls)
--- a/arch/x86/kernel/process_32.c
+++ b/arch/x86/kernel/process_32.c
@@ -160,8 +160,7 @@ __switch_to(struct task_struct *prev_p, struct task_struct *next_p)

 	/* never put a printk in __switch_to... printk() calls wake_up*() indirectly */

-	if (!test_tsk_thread_flag(prev_p, TIF_NEED_FPU_LOAD))
-		switch_fpu_prepare(prev_p, cpu);
+	switch_fpu(prev_p, cpu);

 	/*
 	 * Save away %gs. No need to save %fs, as it was saved on the
@@ -208,8 +207,6 @@ __switch_to(struct task_struct *prev_p, struct task_struct *next_p)

 	raw_cpu_write(current_task, next_p);

-	switch_fpu_finish(next_p);
-
 	/* Load the Intel cache allocation PQR MSR. */
 	resctrl_sched_in(next_p);

--- a/arch/x86/kernel/process_64.c
+++ b/arch/x86/kernel/process_64.c
@@ -616,8 +616,7 @@ __switch_to(struct task_struct *prev_p, struct task_struct *next_p)
 	WARN_ON_ONCE(IS_ENABLED(CONFIG_DEBUG_ENTRY) &&
 		     this_cpu_read(hardirq_stack_inuse));

-	if (!test_tsk_thread_flag(prev_p, TIF_NEED_FPU_LOAD))
-		switch_fpu_prepare(prev_p, cpu);
+	switch_fpu(prev_p, cpu);

 	/* We must save %fs and %gs before load_TLS() because
 	 * %fs and %gs may be cleared by load_TLS().
@@ -671,8 +670,6 @@ __switch_to(struct task_struct *prev_p, struct task_struct *next_p)
 	raw_cpu_write(current_task, next_p);
 	raw_cpu_write(cpu_current_top_of_stack, task_top_of_stack(next_p));

-	switch_fpu_finish(next_p);
-
 	/* Reload sp0. */
 	update_task_stack(next_p);

--- a/arch/x86/kernel/signal.c
+++ b/arch/x86/kernel/signal.c
@@ -255,7 +255,7 @@ static void
 handle_signal(struct ksignal *ksig, struct pt_regs *regs)
 {
 	bool stepping, failed;
-	struct fpu *fpu = &current->thread.fpu;
+	struct fpu *fpu = x86_task_fpu(current);

 	if (v8086_mode(regs))
 		save_v86_state((struct kernel_vm86_regs *) regs, VM86_SIGNAL);
@@ -423,14 +423,14 @@ bool sigaltstack_size_valid(size_t ss_size)
 	if (!fpu_state_size_dynamic() && !strict_sigaltstack_size)
 		return true;

-	fsize += current->group_leader->thread.fpu.perm.__user_state_size;
+	fsize += x86_task_fpu(current->group_leader)->perm.__user_state_size;
 	if (likely(ss_size > fsize))
 		return true;

 	if (strict_sigaltstack_size)
 		return ss_size > fsize;

-	mask = current->group_leader->thread.fpu.perm.__state_perm;
+	mask = x86_task_fpu(current->group_leader)->perm.__state_perm;
 	if (mask & XFEATURE_MASK_USER_DYNAMIC)
 		return ss_size > fsize;

--- a/arch/x86/kernel/traps.c
+++ b/arch/x86/kernel/traps.c
@@ -1295,7 +1295,7 @@ DEFINE_IDTENTRY_RAW(exc_debug)
 static void math_error(struct pt_regs *regs, int trapnr)
 {
 	struct task_struct *task = current;
-	struct fpu *fpu = &task->thread.fpu;
+	struct fpu *fpu = x86_task_fpu(task);
 	int si_code;
 	char *str = (trapnr == X86_TRAP_MF) ? "fpu exception" :
 						"simd exception";
--- a/arch/x86/math-emu/fpu_aux.c
+++ b/arch/x86/math-emu/fpu_aux.c
@@ -53,7 +53,7 @@ void fpstate_init_soft(struct swregs_state *soft)

 void finit(void)
 {
-	fpstate_init_soft(&current->thread.fpu.fpstate->regs.soft);
+	fpstate_init_soft(&x86_task_fpu(current)->fpstate->regs.soft);
 }

 /*
--- a/arch/x86/math-emu/fpu_entry.c
+++ b/arch/x86/math-emu/fpu_entry.c
@@ -641,7 +641,7 @@ int fpregs_soft_set(struct task_struct *target,
 		    unsigned int pos, unsigned int count,
 		    const void *kbuf, const void __user *ubuf)
 {
-	struct swregs_state *s387 = &target->thread.fpu.fpstate->regs.soft;
+	struct swregs_state *s387 = &x86_task_fpu(target)->fpstate->regs.soft;
 	void *space = s387->st_space;
 	int ret;
 	int offset, other, i, tags, regnr, tag, newtop;
@@ -692,7 +692,7 @@ int fpregs_soft_get(struct task_struct *target,
 		    const struct user_regset *regset,
 		    struct membuf to)
 {
-	struct swregs_state *s387 = &target->thread.fpu.fpstate->regs.soft;
+	struct swregs_state *s387 = &x86_task_fpu(target)->fpstate->regs.soft;
 	const void *space = s387->st_space;
 	int offset = (S387->ftop & 7) * 10, other = 80 - offset;

--- a/arch/x86/math-emu/fpu_system.h
+++ b/arch/x86/math-emu/fpu_system.h
@@ -73,7 +73,7 @@ static inline bool seg_writable(struct desc_struct *d)
 	return (d->type & SEG_TYPE_EXECUTE_MASK) == SEG_TYPE_WRITABLE;
 }

-#define I387			(&current->thread.fpu.fpstate->regs)
+#define I387			(&x86_task_fpu(current)->fpstate->regs)
 #define FPU_info		(I387->soft.info)

 #define FPU_CS			(*(unsigned short *) &(FPU_info->regs->cs))
--- a/arch/x86/mm/extable.c
+++ b/arch/x86/mm/extable.c
@@ -111,7 +111,7 @@ static bool ex_handler_sgx(const struct exception_table_entry *fixup,

 /*
 * Handler for when we fail to restore a task's FPU state.  We should never get
- * here because the FPU state of a task using the FPU (task->thread.fpu.state)
+ * here because the FPU state of a task using the FPU (struct fpu::fpstate)
 * should always be valid.  However, past bugs have allowed userspace to set
 * reserved bits in the XSAVE area using PTRACE_SETREGSET or sys_rt_sigreturn().
 * These caused XRSTOR to fail when switching to the task, leaking the FPU
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -1646,22 +1646,15 @@ struct task_struct {
 	struct user_event_mm		*user_event_mm;
 #endif

+	/* CPU-specific state of this task: */
+	struct thread_struct		thread;
+
 	/*
 	 * New fields for task_struct should be added above here, so that
 	 * they are included in the randomized portion of task_struct.
 	 */
 	randomized_struct_fields_end
-
-	/* CPU-specific state of this task: */
-	struct thread_struct		thread;
-
-	/*
-	 * WARNING: on x86, 'thread_struct' contains a variable-sized
-	 * structure.  It *MUST* be at the end of 'task_struct'.
-	 *
-	 * Do not put anything below here!
-	 */
-};
+} __attribute__ ((aligned (64)));

 #define TASK_REPORT_IDLE	(TASK_REPORT + 1)
 #define TASK_REPORT_MAX		(TASK_REPORT_IDLE << 1)
--- a/tools/testing/selftests/x86/Makefile
+++ b/tools/testing/selftests/x86/Makefile
@@ -19,7 +19,7 @@ TARGETS_C_32BIT_ONLY := entry_from_vm86 test_syscall_vdso unwind_vdso \
 			test_FCMOV test_FCOMI test_FISTTP \
 			vdso_restorer
 TARGETS_C_64BIT_ONLY := fsgsbase sysret_rip syscall_numbering \
-			corrupt_xstate_header amx lam test_shadow_stack avx
+			corrupt_xstate_header amx lam test_shadow_stack avx apx
 # Some selftests require 32bit support enabled also on 64bit systems
 TARGETS_C_32BIT_NEEDED := ldt_gdt ptrace_syscall

@@ -136,3 +136,4 @@ $(OUTPUT)/nx_stack_64: CFLAGS += -Wl,-z,noexecstack
 $(OUTPUT)/avx_64: CFLAGS += -mno-avx -mno-avx512f
 $(OUTPUT)/amx_64: EXTRA_FILES += xstate.c
 $(OUTPUT)/avx_64: EXTRA_FILES += xstate.c
+$(OUTPUT)/apx_64: EXTRA_FILES += xstate.c
--- a/tools/testing/selftests/x86/apx.c
+++ b/tools/testing/selftests/x86/apx.c
@@ -0,0 +1,10 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#define _GNU_SOURCE
+
+#include "xstate.h"
+
+int main(void)
+{
+	test_xstate(XFEATURE_APX);
+}
--- a/tools/testing/selftests/x86/xstate.c
+++ b/tools/testing/selftests/x86/xstate.c
@@ -31,7 +31,8 @@
 	 (1 << XFEATURE_OPMASK)	|	\
 	 (1 << XFEATURE_ZMM_Hi256) |	\
 	 (1 << XFEATURE_Hi16_ZMM) |	\
-	 (1 << XFEATURE_XTILEDATA))
+	 (1 << XFEATURE_XTILEDATA) |	\
+	 (1 << XFEATURE_APX))

 static inline uint64_t xgetbv(uint32_t index)
 {
--- a/tools/testing/selftests/x86/xstate.h
+++ b/tools/testing/selftests/x86/xstate.h
@@ -33,6 +33,7 @@ enum xfeature {
 	XFEATURE_RSRVD_COMP_16,
 	XFEATURE_XTILECFG,
 	XFEATURE_XTILEDATA,
+	XFEATURE_APX,

 	XFEATURE_MAX,
 };
@@ -59,6 +60,7 @@ static const char *xfeature_names[] =
 	"unknown xstate feature",
 	"AMX Tile config",
 	"AMX Tile data",
+	"APX registers",
 	"unknown xstate feature",
 };