Merge tag 'x86-fpu-2025-03-22' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull x86/fpu updates from Ingo Molnar:

 - Improve crypto performance by making kernel-mode FPU reliably usable
   in softirqs ((Eric Biggers)

 - Fully optimize out WARN_ON_FPU() (Eric Biggers)

 - Initial steps to support Support Intel APX (Advanced Performance
   Extensions) (Chang S. Bae)

 - Fix KASAN for arch_dup_task_struct() (Benjamin Berg)

 - Refine and simplify the FPU magic number check during signal return
   (Chang S. Bae)

 - Fix inconsistencies in guest FPU xfeatures (Chao Gao, Stanislav
   Spassov)

 - selftests/x86/xstate: Introduce common code for testing extended
   states (Chang S. Bae)

 - Misc fixes and cleanups (Borislav Petkov, Colin Ian King, Uros
   Bizjak)

* tag 'x86-fpu-2025-03-22' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
  x86/fpu/xstate: Fix inconsistencies in guest FPU xfeatures
  x86/fpu: Clarify the "xa" symbolic name used in the XSTATE* macros
  x86/fpu: Use XSAVE{,OPT,C,S} and XRSTOR{,S} mnemonics in xstate.h
  x86/fpu: Improve crypto performance by making kernel-mode FPU reliably usable in softirqs
  x86/fpu/xstate: Simplify print_xstate_features()
  x86/fpu: Refine and simplify the magic number check during signal return
  selftests/x86/xstate: Fix spelling mistake "hader" -> "header"
  x86/fpu: Avoid copying dynamic FP state from init_task in arch_dup_task_struct()
  vmlinux.lds.h: Remove entry to place init_task onto init_stack
  selftests/x86/avx: Add AVX tests
  selftests/x86/xstate: Clarify supported xstates
  selftests/x86/xstate: Consolidate test invocations into a single entry
  selftests/x86/xstate: Introduce signal ABI test
  selftests/x86/xstate: Refactor ptrace ABI test
  selftests/x86/xstate: Refactor context switching test
  selftests/x86/xstate: Enumerate and name xstate components
  selftests/x86/xstate: Refactor XSAVE helpers for general use
  selftests/x86: Consolidate redundant signal helper functions
  x86/fpu: Fix guest FPU state buffer allocation size
  x86/fpu: Fully optimize out WARN_ON_FPU()

Author: torvalds

arch/x86/include/asm/fpu/api.h

@@ -16,10 +16,9 @@
 
 /*
  * Use kernel_fpu_begin/end() if you intend to use FPU in kernel context. It
- * disables preemption so be careful if you intend to use it for long periods
- * of time.
- * If you intend to use the FPU in irq/softirq you need to check first with
- * irq_fpu_usable() if it is possible.
+ * disables preemption and softirq processing, so be careful if you intend to
+ * use it for long periods of time.  Kernel-mode FPU cannot be used in all
+ * contexts -- see irq_fpu_usable() for details.
  */
 
 /* Kernel FPU states to initialize in kernel_fpu_begin_mask() */
@@ -50,10 +49,10 @@ static inline void kernel_fpu_begin(void)
 }
 
 /*
- * Use fpregs_lock() while editing CPU's FPU registers or fpu->fpstate.
- * A context switch will (and softirq might) save CPU's FPU registers to
- * fpu->fpstate.regs and set TIF_NEED_FPU_LOAD leaving CPU's FPU registers in
- * a random state.
+ * Use fpregs_lock() while editing CPU's FPU registers or fpu->fpstate, or while
+ * using the FPU in kernel mode.  A context switch will (and softirq might) save
+ * CPU's FPU registers to fpu->fpstate.regs and set TIF_NEED_FPU_LOAD leaving
+ * CPU's FPU registers in a random state.
  *
  * local_bh_disable() protects against both preemption and soft interrupts
  * on !RT kernels.
@@ -63,8 +62,6 @@ static inline void kernel_fpu_begin(void)
  * preemptible. Disabling preemption is the right choice here as bottom
  * half processing is always in thread context on RT kernels so it
  * implicitly prevents bottom half processing as well.
- *
- * Disabling preemption also serializes against kernel_fpu_begin().
  */
 static inline void fpregs_lock(void)
 {

arch/x86/kernel/fpu/core.c

@@ -60,9 +60,16 @@ bool irq_fpu_usable(void)
 	if (WARN_ON_ONCE(in_nmi()))
 		return false;
 
-	/* In kernel FPU usage already active? */
-	if (this_cpu_read(in_kernel_fpu))
+	/*
+	 * In kernel FPU usage already active?  This detects any explicitly
+	 * nested usage in task or softirq context, which is unsupported.  It
+	 * also detects attempted usage in a hardirq that has interrupted a
+	 * kernel-mode FPU section.
+	 */
+	if (this_cpu_read(in_kernel_fpu)) {
+		WARN_ON_FPU(!in_hardirq());
 		return false;
+	}
 
 	/*
 	 * When not in NMI or hard interrupt context, FPU can be used in:
@@ -220,7 +227,7 @@ bool fpu_alloc_guest_fpstate(struct fpu_guest *gfpu)
 	struct fpstate *fpstate;
 	unsigned int size;
 
-	size = fpu_user_cfg.default_size + ALIGN(offsetof(struct fpstate, regs), 64);
+	size = fpu_kernel_cfg.default_size + ALIGN(offsetof(struct fpstate, regs), 64);
 	fpstate = vzalloc(size);
 	if (!fpstate)
 		return false;
@@ -232,8 +239,8 @@ bool fpu_alloc_guest_fpstate(struct fpu_guest *gfpu)
 	fpstate->is_guest	= true;
 
 	gfpu->fpstate		= fpstate;
-	gfpu->xfeatures		= fpu_user_cfg.default_features;
-	gfpu->perm		= fpu_user_cfg.default_features;
+	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
@@ -420,7 +427,8 @@ EXPORT_SYMBOL_GPL(fpu_copy_uabi_to_guest_fpstate);
 
 void kernel_fpu_begin_mask(unsigned int kfpu_mask)
 {
-	preempt_disable();
+	if (!irqs_disabled())
+		fpregs_lock();
 
 	WARN_ON_FPU(!irq_fpu_usable());
 	WARN_ON_FPU(this_cpu_read(in_kernel_fpu));
@@ -448,7 +456,8 @@ void kernel_fpu_end(void)
 	WARN_ON_FPU(!this_cpu_read(in_kernel_fpu));
 
 	this_cpu_write(in_kernel_fpu, false);
-	preempt_enable();
+	if (!irqs_disabled())
+		fpregs_unlock();
 }
 EXPORT_SYMBOL_GPL(kernel_fpu_end);
 

arch/x86/kernel/fpu/internal.h

@@ -18,7 +18,7 @@ static __always_inline __pure bool use_fxsr(void)
 #ifdef CONFIG_X86_DEBUG_FPU
 # define WARN_ON_FPU(x) WARN_ON_ONCE(x)
 #else
-# define WARN_ON_FPU(x) ({ (void)(x); 0; })
+# define WARN_ON_FPU(x) ({ BUILD_BUG_ON_INVALID(x); 0; })
 #endif
 
 /* Used in init.c */

arch/x86/kernel/fpu/signal.c

@@ -27,19 +27,14 @@
 static inline bool check_xstate_in_sigframe(struct fxregs_state __user *fxbuf,
 					    struct _fpx_sw_bytes *fx_sw)
 {
-	int min_xstate_size = sizeof(struct fxregs_state) +
-			      sizeof(struct xstate_header);
 	void __user *fpstate = fxbuf;
 	unsigned int magic2;
 
 	if (__copy_from_user(fx_sw, &fxbuf->sw_reserved[0], sizeof(*fx_sw)))
 		return false;
 
-	/* Check for the first magic field and other error scenarios. */
-	if (fx_sw->magic1 != FP_XSTATE_MAGIC1 ||
-	    fx_sw->xstate_size < min_xstate_size ||
-	    fx_sw->xstate_size > current->thread.fpu.fpstate->user_size ||
-	    fx_sw->xstate_size > fx_sw->extended_size)
+	/* Check for the first magic field */
+	if (fx_sw->magic1 != FP_XSTATE_MAGIC1)
 		goto setfx;
 
 	/*
@@ -48,7 +43,7 @@ static inline bool check_xstate_in_sigframe(struct fxregs_state __user *fxbuf,
 	 * fpstate layout with out copying the extended state information
 	 * in the memory layout.
 	 */
-	if (__get_user(magic2, (__u32 __user *)(fpstate + fx_sw->xstate_size)))
+	if (__get_user(magic2, (__u32 __user *)(fpstate + current->thread.fpu.fpstate->user_size)))
 		return false;
 
 	if (likely(magic2 == FP_XSTATE_MAGIC2))

arch/x86/kernel/fpu/xstate.c

@@ -259,32 +259,20 @@ static void __init setup_xstate_cache(void)
 	}
 }
 
-static void __init print_xstate_feature(u64 xstate_mask)
-{
-	const char *feature_name;
-
-	if (cpu_has_xfeatures(xstate_mask, &feature_name))
-		pr_info("x86/fpu: Supporting XSAVE feature 0x%03Lx: '%s'\n", xstate_mask, feature_name);
-}
-
 /*
  * Print out all the supported xstate features:
  */
 static void __init print_xstate_features(void)
 {
-	print_xstate_feature(XFEATURE_MASK_FP);
-	print_xstate_feature(XFEATURE_MASK_SSE);
-	print_xstate_feature(XFEATURE_MASK_YMM);
-	print_xstate_feature(XFEATURE_MASK_BNDREGS);
-	print_xstate_feature(XFEATURE_MASK_BNDCSR);
-	print_xstate_feature(XFEATURE_MASK_OPMASK);
-	print_xstate_feature(XFEATURE_MASK_ZMM_Hi256);
-	print_xstate_feature(XFEATURE_MASK_Hi16_ZMM);
-	print_xstate_feature(XFEATURE_MASK_PKRU);
-	print_xstate_feature(XFEATURE_MASK_PASID);
-	print_xstate_feature(XFEATURE_MASK_CET_USER);
-	print_xstate_feature(XFEATURE_MASK_XTILE_CFG);
-	print_xstate_feature(XFEATURE_MASK_XTILE_DATA);
+	int i;
+
+	for (i = 0; i < XFEATURE_MAX; i++) {
+		u64 mask = BIT_ULL(i);
+		const char *name;
+
+		if (cpu_has_xfeatures(mask, &name))
+			pr_info("x86/fpu: Supporting XSAVE feature 0x%03Lx: '%s'\n", mask, name);
+	}
 }
 
 /*

arch/x86/kernel/fpu/xstate.h

@@ -94,30 +94,33 @@ static inline int update_pkru_in_sigframe(struct xregs_state __user *buf, u64 ma
 /* XSAVE/XRSTOR wrapper functions */
 
 #ifdef CONFIG_X86_64
-#define REX_PREFIX	"0x48, "
+#define REX_SUFFIX	"64"
 #else
-#define REX_PREFIX
+#define REX_SUFFIX
 #endif
 
-/* These macros all use (%edi)/(%rdi) as the single memory argument. */
-#define XSAVE		".byte " REX_PREFIX "0x0f,0xae,0x27"
-#define XSAVEOPT	".byte " REX_PREFIX "0x0f,0xae,0x37"
-#define XSAVEC		".byte " REX_PREFIX "0x0f,0xc7,0x27"
-#define XSAVES		".byte " REX_PREFIX "0x0f,0xc7,0x2f"
-#define XRSTOR		".byte " REX_PREFIX "0x0f,0xae,0x2f"
-#define XRSTORS		".byte " REX_PREFIX "0x0f,0xc7,0x1f"
+#define XSAVE		"xsave" REX_SUFFIX " %[xa]"
+#define XSAVEOPT	"xsaveopt" REX_SUFFIX " %[xa]"
+#define XSAVEC		"xsavec" REX_SUFFIX " %[xa]"
+#define XSAVES		"xsaves" REX_SUFFIX " %[xa]"
+#define XRSTOR		"xrstor" REX_SUFFIX " %[xa]"
+#define XRSTORS		"xrstors" REX_SUFFIX " %[xa]"
 
 /*
  * After this @err contains 0 on success or the trap number when the
  * operation raises an exception.
+ *
+ * The [xa] input parameter below represents the struct xregs_state pointer
+ * and the asm symbolic name for the argument used in the XSAVE/XRSTOR insns
+ * above.
  */
 #define XSTATE_OP(op, st, lmask, hmask, err)				\
 	asm volatile("1:" op "\n\t"					\
 		     "xor %[err], %[err]\n"				\
-		     "2:\n\t"						\
+		     "2:\n"						\
 		     _ASM_EXTABLE_TYPE(1b, 2b, EX_TYPE_FAULT_MCE_SAFE)	\
 		     : [err] "=a" (err)					\
-		     : "D" (st), "m" (*st), "a" (lmask), "d" (hmask)	\
+		     : [xa] "m" (*(st)), "a" (lmask), "d" (hmask)	\
 		     : "memory")
 
 /*
@@ -137,12 +140,12 @@ static inline int update_pkru_in_sigframe(struct xregs_state __user *buf, u64 ma
 				   XSAVEOPT, X86_FEATURE_XSAVEOPT,	\
 				   XSAVEC,   X86_FEATURE_XSAVEC,	\
 				   XSAVES,   X86_FEATURE_XSAVES)	\
-		     "\n"						\
+		     "\n\t"						\
 		     "xor %[err], %[err]\n"				\
 		     "3:\n"						\
 		     _ASM_EXTABLE_TYPE_REG(1b, 3b, EX_TYPE_EFAULT_REG, %[err]) \
 		     : [err] "=r" (err)					\
-		     : "D" (st), "m" (*st), "a" (lmask), "d" (hmask)	\
+		     : [xa] "m" (*(st)), "a" (lmask), "d" (hmask)	\
 		     : "memory")
 
 /*
@@ -156,7 +159,7 @@ static inline int update_pkru_in_sigframe(struct xregs_state __user *buf, u64 ma
 		     "3:\n"						\
 		     _ASM_EXTABLE_TYPE(1b, 3b, EX_TYPE_FPU_RESTORE)	\
 		     :							\
-		     : "D" (st), "m" (*st), "a" (lmask), "d" (hmask)	\
+		     : [xa] "m" (*(st)), "a" (lmask), "d" (hmask)	\
 		     : "memory")
 
 #if defined(CONFIG_X86_64) && defined(CONFIG_X86_DEBUG_FPU)

arch/x86/kernel/process.c

@@ -93,7 +93,12 @@ EXPORT_PER_CPU_SYMBOL_GPL(__tss_limit_invalid);
  */
 int arch_dup_task_struct(struct task_struct *dst, struct task_struct *src)
 {
-	memcpy(dst, src, arch_task_struct_size);
+	/* 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);
+
 #ifdef CONFIG_VM86
 	dst->thread.vm86 = NULL;
 #endif

include/asm-generic/vmlinux.lds.h

@@ -409,7 +409,6 @@ defined(CONFIG_AUTOFDO_CLANG) || defined(CONFIG_PROPELLER_CLANG)
 	__start_init_stack = .;						\
 	init_thread_union = .;						\
 	init_stack = .;							\
-	KEEP(*(.data..init_task))					\
 	KEEP(*(.data..init_thread_info))				\
 	. = __start_init_stack + THREAD_SIZE;				\
 	__end_init_stack = .;

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
+			corrupt_xstate_header amx lam test_shadow_stack avx
 # Some selftests require 32bit support enabled also on 64bit systems
 TARGETS_C_32BIT_NEEDED := ldt_gdt ptrace_syscall
 
@@ -132,3 +132,7 @@ $(OUTPUT)/check_initial_reg_state_64: CFLAGS += -Wl,-ereal_start -static
 
 $(OUTPUT)/nx_stack_32: CFLAGS += -Wl,-z,noexecstack
 $(OUTPUT)/nx_stack_64: CFLAGS += -Wl,-z,noexecstack
+
+$(OUTPUT)/avx_64: CFLAGS += -mno-avx -mno-avx512f
+$(OUTPUT)/amx_64: EXTRA_FILES += xstate.c
+$(OUTPUT)/avx_64: EXTRA_FILES += xstate.c