Merge branch 'WIP.x86/fpu' into x86/fpu, because it's ready

Signed-off-by: Ingo Molnar <[email protected]>

Author: Ingo Molnar

arch/x86/ia32/ia32_signal.c

@@ -231,7 +231,7 @@ static void __user *get_sigframe(struct ksignal *ksig, struct pt_regs *regs,
 		 ksig->ka.sa.sa_restorer)
 		sp = (unsigned long) ksig->ka.sa.sa_restorer;
 
-	if (fpu->fpstate_active) {
+	if (fpu->initialized) {
 		unsigned long fx_aligned, math_size;
 
 		sp = fpu__alloc_mathframe(sp, 1, &fx_aligned, &math_size);

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

@@ -23,11 +23,9 @@
 /*
  * High level FPU state handling functions:
  */
-extern void fpu__activate_curr(struct fpu *fpu);
-extern void fpu__activate_fpstate_read(struct fpu *fpu);
-extern void fpu__activate_fpstate_write(struct fpu *fpu);
-extern void fpu__current_fpstate_write_begin(void);
-extern void fpu__current_fpstate_write_end(void);
+extern void fpu__initialize(struct fpu *fpu);
+extern void fpu__prepare_read(struct fpu *fpu);
+extern void fpu__prepare_write(struct fpu *fpu);
 extern void fpu__save(struct fpu *fpu);
 extern void fpu__restore(struct fpu *fpu);
 extern int  fpu__restore_sig(void __user *buf, int ia32_frame);
@@ -120,20 +118,11 @@ extern void fpstate_sanitize_xstate(struct fpu *fpu);
 	err;								\
 })
 
-#define check_insn(insn, output, input...)				\
-({									\
-	int err;							\
+#define kernel_insn(insn, output, input...)				\
 	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;								\
-})
+		     _ASM_EXTABLE_HANDLE(1b, 2b, ex_handler_fprestore)	\
+		     : output : input)
 
 static inline int copy_fregs_to_user(struct fregs_state __user *fx)
 {
@@ -153,20 +142,16 @@ static inline int copy_fxregs_to_user(struct fxregs_state __user *fx)
 
 static inline void copy_kernel_to_fxregs(struct fxregs_state *fx)
 {
-	int err;
-
 	if (IS_ENABLED(CONFIG_X86_32)) {
-		err = check_insn(fxrstor %[fx], "=m" (*fx), [fx] "m" (*fx));
+		kernel_insn(fxrstor %[fx], "=m" (*fx), [fx] "m" (*fx));
 	} else {
 		if (IS_ENABLED(CONFIG_AS_FXSAVEQ)) {
-			err = check_insn(fxrstorq %[fx], "=m" (*fx), [fx] "m" (*fx));
+			kernel_insn(fxrstorq %[fx], "=m" (*fx), [fx] "m" (*fx));
 		} else {
 			/* See comment in copy_fxregs_to_kernel() below. */
-			err = check_insn(rex64/fxrstor (%[fx]), "=m" (*fx), [fx] "R" (fx), "m" (*fx));
+			kernel_insn(rex64/fxrstor (%[fx]), "=m" (*fx), [fx] "R" (fx), "m" (*fx));
 		}
 	}
-	/* Copying from a kernel buffer to FPU registers should never fail: */
-	WARN_ON_FPU(err);
 }
 
 static inline int copy_user_to_fxregs(struct fxregs_state __user *fx)
@@ -183,9 +168,7 @@ static inline int copy_user_to_fxregs(struct fxregs_state __user *fx)
 
 static inline void copy_kernel_to_fregs(struct fregs_state *fx)
 {
-	int err = check_insn(frstor %[fx], "=m" (*fx), [fx] "m" (*fx));
-
-	WARN_ON_FPU(err);
+	kernel_insn(frstor %[fx], "=m" (*fx), [fx] "m" (*fx));
 }
 
 static inline int copy_user_to_fregs(struct fregs_state __user *fx)
@@ -281,18 +264,13 @@ static inline void copy_fxregs_to_kernel(struct fpu *fpu)
  * Use XRSTORS to restore context if it is enabled. XRSTORS supports compact
  * XSAVE area format.
  */
-#define XSTATE_XRESTORE(st, lmask, hmask, err)				\
+#define XSTATE_XRESTORE(st, lmask, hmask)				\
 	asm volatile(ALTERNATIVE(XRSTOR,				\
 				 XRSTORS, 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)					\
+		     _ASM_EXTABLE_HANDLE(661b, 3b, ex_handler_fprestore)\
+		     :							\
 		     : "D" (st), "m" (*st), "a" (lmask), "d" (hmask)	\
 		     : "memory")
 
@@ -336,7 +314,10 @@ static inline void copy_kernel_to_xregs_booting(struct xregs_state *xstate)
 	else
 		XSTATE_OP(XRSTOR, xstate, lmask, hmask, err);
 
-	/* We should never fault when copying from a kernel buffer: */
+	/*
+	 * 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);
 }
 
@@ -350,7 +331,7 @@ static inline void copy_xregs_to_kernel(struct xregs_state *xstate)
 	u32 hmask = mask >> 32;
 	int err;
 
-	WARN_ON(!alternatives_patched);
+	WARN_ON_FPU(!alternatives_patched);
 
 	XSTATE_XSAVE(xstate, lmask, hmask, err);
 
@@ -365,12 +346,8 @@ static inline void copy_kernel_to_xregs(struct xregs_state *xstate, u64 mask)
 {
 	u32 lmask = mask;
 	u32 hmask = mask >> 32;
-	int err;
-
-	XSTATE_XRESTORE(xstate, lmask, hmask, err);
 
-	/* We should never fault when copying from a kernel buffer: */
-	WARN_ON_FPU(err);
+	XSTATE_XRESTORE(xstate, lmask, hmask);
 }
 
 /*
@@ -526,37 +503,16 @@ static inline int fpregs_state_valid(struct fpu *fpu, unsigned int cpu)
  */
 static inline void fpregs_deactivate(struct fpu *fpu)
 {
-	WARN_ON_FPU(!fpu->fpregs_active);
-
-	fpu->fpregs_active = 0;
 	this_cpu_write(fpu_fpregs_owner_ctx, NULL);
 	trace_x86_fpu_regs_deactivated(fpu);
 }
 
 static inline void fpregs_activate(struct fpu *fpu)
 {
-	WARN_ON_FPU(fpu->fpregs_active);
-
-	fpu->fpregs_active = 1;
 	this_cpu_write(fpu_fpregs_owner_ctx, fpu);
 	trace_x86_fpu_regs_activated(fpu);
 }
 
-/*
- * The question "does this thread have fpu access?"
- * is slightly racy, since preemption could come in
- * and revoke it immediately after the test.
- *
- * However, even in that very unlikely scenario,
- * we can just assume we have FPU access - typically
- * to save the FP state - we'll just take a #NM
- * fault and get the FPU access back.
- */
-static inline int fpregs_active(void)
-{
-	return current->thread.fpu.fpregs_active;
-}
-
 /*
  * FPU state switching for scheduling.
  *
@@ -571,14 +527,13 @@ static inline int fpregs_active(void)
 static inline void
 switch_fpu_prepare(struct fpu *old_fpu, int cpu)
 {
-	if (old_fpu->fpregs_active) {
+	if (old_fpu->initialized) {
 		if (!copy_fpregs_to_fpstate(old_fpu))
 			old_fpu->last_cpu = -1;
 		else
 			old_fpu->last_cpu = cpu;
 
 		/* But leave fpu_fpregs_owner_ctx! */
-		old_fpu->fpregs_active = 0;
 		trace_x86_fpu_regs_deactivated(old_fpu);
 	} else
 		old_fpu->last_cpu = -1;
@@ -595,7 +550,7 @@ switch_fpu_prepare(struct fpu *old_fpu, int cpu)
 static inline void switch_fpu_finish(struct fpu *new_fpu, int cpu)
 {
 	bool preload = static_cpu_has(X86_FEATURE_FPU) &&
-		       new_fpu->fpstate_active;
+		       new_fpu->initialized;
 
 	if (preload) {
 		if (!fpregs_state_valid(new_fpu, cpu))
@@ -617,8 +572,7 @@ static inline void user_fpu_begin(void)
 	struct fpu *fpu = &current->thread.fpu;
 
 	preempt_disable();
-	if (!fpregs_active())
-		fpregs_activate(fpu);
+	fpregs_activate(fpu);
 	preempt_enable();
 }
 

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

@@ -68,6 +68,9 @@ struct fxregs_state {
 /* 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:
@@ -290,36 +293,13 @@ struct fpu {
 	unsigned int			last_cpu;
 
 	/*
-	 * @fpstate_active:
+	 * @initialized:
 	 *
-	 * This flag indicates whether this context is active: if the task
+	 * This flag indicates whether this context is initialized: if the task
 	 * is not running then we can restore from this context, if the task
 	 * is running then we should save into this context.
 	 */
-	unsigned char			fpstate_active;
-
-	/*
-	 * @fpregs_active:
-	 *
-	 * This flag determines whether a given context is actively
-	 * loaded into the FPU's registers and that those registers
-	 * represent the task's current FPU state.
-	 *
-	 * Note the interaction with fpstate_active:
-	 *
-	 *   # task does not use the FPU:
-	 *   fpstate_active == 0
-	 *
-	 *   # task uses the FPU and regs are active:
-	 *   fpstate_active == 1 && fpregs_active == 1
-	 *
-	 *   # the regs are inactive but still match fpstate:
-	 *   fpstate_active == 1 && fpregs_active == 0 && fpregs_owner == fpu
-	 *
-	 * The third state is what we use for the lazy restore optimization
-	 * on lazy-switching CPUs.
-	 */
-	unsigned char			fpregs_active;
+	unsigned char			initialized;
 
 	/*
 	 * @state:

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

@@ -48,8 +48,12 @@ void fpu__xstate_clear_all_cpu_caps(void);
 void *get_xsave_addr(struct xregs_state *xsave, int xstate);
 const void *get_xsave_field_ptr(int xstate_field);
 int using_compacted_format(void);
-int copyout_from_xsaves(unsigned int pos, unsigned int count, void *kbuf,
-			void __user *ubuf, struct xregs_state *xsave);
-int copyin_to_xsaves(const void *kbuf, const void __user *ubuf,
-		     struct xregs_state *xsave);
+int copy_xstate_to_kernel(void *kbuf, struct xregs_state *xsave, unsigned int offset, unsigned int size);
+int copy_xstate_to_user(void __user *ubuf, struct xregs_state *xsave, unsigned int offset, unsigned int size);
+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);
+
+/* Validate an xstate header supplied by userspace (ptrace or sigreturn) */
+extern int validate_xstate_header(const struct xstate_header *hdr);
+
 #endif

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

@@ -12,25 +12,22 @@ DECLARE_EVENT_CLASS(x86_fpu,
 
 	TP_STRUCT__entry(
 		__field(struct fpu *, fpu)
-		__field(bool, fpregs_active)
-		__field(bool, fpstate_active)
+		__field(bool, initialized)
 		__field(u64, xfeatures)
 		__field(u64, xcomp_bv)
 		),
 
 	TP_fast_assign(
 		__entry->fpu		= fpu;
-		__entry->fpregs_active	= fpu->fpregs_active;
-		__entry->fpstate_active	= fpu->fpstate_active;
+		__entry->initialized	= fpu->initialized;
 		if (boot_cpu_has(X86_FEATURE_OSXSAVE)) {
 			__entry->xfeatures = fpu->state.xsave.header.xfeatures;
 			__entry->xcomp_bv  = fpu->state.xsave.header.xcomp_bv;
 		}
 	),
-	TP_printk("x86/fpu: %p fpregs_active: %d fpstate_active: %d xfeatures: %llx xcomp_bv: %llx",
+	TP_printk("x86/fpu: %p initialized: %d xfeatures: %llx xcomp_bv: %llx",
 			__entry->fpu,
-			__entry->fpregs_active,
-			__entry->fpstate_active,
+			__entry->initialized,
 			__entry->xfeatures,
 			__entry->xcomp_bv
 	)