Update Linux to v5.10.109

Sourced from [1]

[1] https://cdn.kernel.org/pub/linux/kernel/v5.x/linux-5.10.109.tar.xz

Change-Id: I19bca9fc6762d4e63bcf3e4cba88bbe560d9c76c
Signed-off-by: Olivier Deprez <olivier.deprez@arm.com>
diff --git a/arch/x86/kernel/fpu/core.c b/arch/x86/kernel/fpu/core.c
index 8c9b202..571220a 100644
--- a/arch/x86/kernel/fpu/core.c
+++ b/arch/x86/kernel/fpu/core.c
@@ -82,6 +82,45 @@
 }
 EXPORT_SYMBOL(irq_fpu_usable);
 
+/*
+ * These must be called with preempt disabled. Returns
+ * 'true' if the FPU state is still intact and we can
+ * keep registers active.
+ *
+ * The legacy FNSAVE instruction cleared all FPU state
+ * unconditionally, so registers are essentially destroyed.
+ * Modern FPU state can be kept in registers, if there are
+ * no pending FP exceptions.
+ */
+int copy_fpregs_to_fpstate(struct fpu *fpu)
+{
+	if (likely(use_xsave())) {
+		copy_xregs_to_kernel(&fpu->state.xsave);
+
+		/*
+		 * AVX512 state is tracked here because its use is
+		 * known to slow the max clock speed of the core.
+		 */
+		if (fpu->state.xsave.header.xfeatures & XFEATURE_MASK_AVX512)
+			fpu->avx512_timestamp = jiffies;
+		return 1;
+	}
+
+	if (likely(use_fxsr())) {
+		copy_fxregs_to_kernel(fpu);
+		return 1;
+	}
+
+	/*
+	 * Legacy FPU register saving, FNSAVE always clears FPU registers,
+	 * so we have to mark them inactive:
+	 */
+	asm volatile("fnsave %[fp]; fwait" : [fp] "=m" (fpu->state.fsave));
+
+	return 0;
+}
+EXPORT_SYMBOL(copy_fpregs_to_fpstate);
+
 void kernel_fpu_begin_mask(unsigned int kfpu_mask)
 {
 	preempt_disable();
@@ -298,15 +337,13 @@
 }
 
 /*
- * Clear FPU registers by setting them up from
- * the init fpstate:
+ * Clear FPU registers by setting them up from the init fpstate.
+ * Caller must do fpregs_[un]lock() around it.
  */
-static inline void copy_init_fpstate_to_fpregs(void)
+static inline void copy_init_fpstate_to_fpregs(u64 features_mask)
 {
-	fpregs_lock();
-
 	if (use_xsave())
-		copy_kernel_to_xregs(&init_fpstate.xsave, -1);
+		copy_kernel_to_xregs(&init_fpstate.xsave, features_mask);
 	else if (static_cpu_has(X86_FEATURE_FXSR))
 		copy_kernel_to_fxregs(&init_fpstate.fxsave);
 	else
@@ -314,9 +351,6 @@
 
 	if (boot_cpu_has(X86_FEATURE_OSPKE))
 		copy_init_pkru_to_fpregs();
-
-	fpregs_mark_activate();
-	fpregs_unlock();
 }
 
 /*
@@ -325,18 +359,40 @@
  * Called by sys_execve(), by the signal handler code and by various
  * error paths.
  */
-void fpu__clear(struct fpu *fpu)
+static void fpu__clear(struct fpu *fpu, bool user_only)
 {
-	WARN_ON_FPU(fpu != &current->thread.fpu); /* Almost certainly an anomaly */
+	WARN_ON_FPU(fpu != &current->thread.fpu);
 
-	fpu__drop(fpu);
+	if (!static_cpu_has(X86_FEATURE_FPU)) {
+		fpu__drop(fpu);
+		fpu__initialize(fpu);
+		return;
+	}
 
-	/*
-	 * Make sure fpstate is cleared and initialized.
-	 */
-	fpu__initialize(fpu);
-	if (static_cpu_has(X86_FEATURE_FPU))
-		copy_init_fpstate_to_fpregs();
+	fpregs_lock();
+
+	if (user_only) {
+		if (!fpregs_state_valid(fpu, smp_processor_id()) &&
+		    xfeatures_mask_supervisor())
+			copy_kernel_to_xregs(&fpu->state.xsave,
+					     xfeatures_mask_supervisor());
+		copy_init_fpstate_to_fpregs(xfeatures_mask_user());
+	} else {
+		copy_init_fpstate_to_fpregs(xfeatures_mask_all);
+	}
+
+	fpregs_mark_activate();
+	fpregs_unlock();
+}
+
+void fpu__clear_user_states(struct fpu *fpu)
+{
+	fpu__clear(fpu, true);
+}
+
+void fpu__clear_all(struct fpu *fpu)
+{
+	fpu__clear(fpu, false);
 }
 
 /*
diff --git a/arch/x86/kernel/fpu/init.c b/arch/x86/kernel/fpu/init.c
index b271da0..701f196 100644
--- a/arch/x86/kernel/fpu/init.c
+++ b/arch/x86/kernel/fpu/init.c
@@ -5,7 +5,6 @@
 #include <asm/fpu/internal.h>
 #include <asm/tlbflush.h>
 #include <asm/setup.h>
-#include <asm/cmdline.h>
 
 #include <linux/sched.h>
 #include <linux/sched/task.h>
@@ -224,7 +223,8 @@
  */
 u64 __init fpu__get_supported_xfeatures_mask(void)
 {
-	return XCNTXT_MASK;
+	return XFEATURE_MASK_USER_SUPPORTED |
+	       XFEATURE_MASK_SUPERVISOR_SUPPORTED;
 }
 
 /* Legacy code to initialize eager fpu mode. */
@@ -237,65 +237,11 @@
 }
 
 /*
- * We parse fpu parameters early because fpu__init_system() is executed
- * before parse_early_param().
- */
-static void __init fpu__init_parse_early_param(void)
-{
-	char arg[128];
-	char *argptr = arg;
-	int arglen, res, bit;
-
-#ifdef CONFIG_X86_32
-	if (cmdline_find_option_bool(boot_command_line, "no387"))
-#ifdef CONFIG_MATH_EMULATION
-		setup_clear_cpu_cap(X86_FEATURE_FPU);
-#else
-		pr_err("Option 'no387' required CONFIG_MATH_EMULATION enabled.\n");
-#endif
-
-	if (cmdline_find_option_bool(boot_command_line, "nofxsr"))
-		setup_clear_cpu_cap(X86_FEATURE_FXSR);
-#endif
-
-	if (cmdline_find_option_bool(boot_command_line, "noxsave"))
-		setup_clear_cpu_cap(X86_FEATURE_XSAVE);
-
-	if (cmdline_find_option_bool(boot_command_line, "noxsaveopt"))
-		setup_clear_cpu_cap(X86_FEATURE_XSAVEOPT);
-
-	if (cmdline_find_option_bool(boot_command_line, "noxsaves"))
-		setup_clear_cpu_cap(X86_FEATURE_XSAVES);
-
-	arglen = cmdline_find_option(boot_command_line, "clearcpuid", arg, sizeof(arg));
-	if (arglen <= 0)
-		return;
-
-	pr_info("Clearing CPUID bits:");
-	do {
-		res = get_option(&argptr, &bit);
-		if (res == 0 || res == 3)
-			break;
-
-		/* If the argument was too long, the last bit may be cut off */
-		if (res == 1 && arglen >= sizeof(arg))
-			break;
-
-		if (bit >= 0 && bit < NCAPINTS * 32) {
-			pr_cont(" " X86_CAP_FMT, x86_cap_flag(bit));
-			setup_clear_cpu_cap(bit);
-		}
-	} while (res == 2);
-	pr_cont("\n");
-}
-
-/*
  * Called on the boot CPU once per system bootup, to set up the initial
  * FPU state that is later cloned into all processes:
  */
 void __init fpu__init_system(struct cpuinfo_x86 *c)
 {
-	fpu__init_parse_early_param();
 	fpu__init_system_early_generic(c);
 
 	/*
diff --git a/arch/x86/kernel/fpu/regset.c b/arch/x86/kernel/fpu/regset.c
index 68e1fb6..6bb8744 100644
--- a/arch/x86/kernel/fpu/regset.c
+++ b/arch/x86/kernel/fpu/regset.c
@@ -27,8 +27,7 @@
 }
 
 int xfpregs_get(struct task_struct *target, const struct user_regset *regset,
-		unsigned int pos, unsigned int count,
-		void *kbuf, void __user *ubuf)
+		struct membuf to)
 {
 	struct fpu *fpu = &target->thread.fpu;
 
@@ -38,8 +37,7 @@
 	fpu__prepare_read(fpu);
 	fpstate_sanitize_xstate(fpu);
 
-	return user_regset_copyout(&pos, &count, &kbuf, &ubuf,
-				   &fpu->state.fxsave, 0, -1);
+	return membuf_write(&to, &fpu->state.fxsave, sizeof(struct fxregs_state));
 }
 
 int xfpregs_set(struct task_struct *target, const struct user_regset *regset,
@@ -74,12 +72,10 @@
 }
 
 int xstateregs_get(struct task_struct *target, const struct user_regset *regset,
-		unsigned int pos, unsigned int count,
-		void *kbuf, void __user *ubuf)
+		struct membuf to)
 {
 	struct fpu *fpu = &target->thread.fpu;
 	struct xregs_state *xsave;
-	int ret;
 
 	if (!boot_cpu_has(X86_FEATURE_XSAVE))
 		return -ENODEV;
@@ -89,10 +85,8 @@
 	fpu__prepare_read(fpu);
 
 	if (using_compacted_format()) {
-		if (kbuf)
-			ret = copy_xstate_to_kernel(kbuf, xsave, pos, count);
-		else
-			ret = copy_xstate_to_user(ubuf, xsave, pos, count);
+		copy_xstate_to_kernel(to, xsave);
+		return 0;
 	} else {
 		fpstate_sanitize_xstate(fpu);
 		/*
@@ -105,9 +99,8 @@
 		/*
 		 * Copy the xstate memory layout.
 		 */
-		ret = user_regset_copyout(&pos, &count, &kbuf, &ubuf, xsave, 0, -1);
+		return membuf_write(&to, xsave, fpu_user_xstate_size);
 	}
-	return ret;
 }
 
 int xstateregs_set(struct task_struct *target, const struct user_regset *regset,
@@ -139,7 +132,7 @@
 	} else {
 		ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf, xsave, 0, -1);
 		if (!ret)
-			ret = validate_xstate_header(&xsave->header);
+			ret = validate_user_xstate_header(&xsave->header);
 	}
 
 	/*
@@ -293,8 +286,7 @@
 }
 
 int fpregs_get(struct task_struct *target, const struct user_regset *regset,
-	       unsigned int pos, unsigned int count,
-	       void *kbuf, void __user *ubuf)
+	       struct membuf to)
 {
 	struct fpu *fpu = &target->thread.fpu;
 	struct user_i387_ia32_struct env;
@@ -302,23 +294,22 @@
 	fpu__prepare_read(fpu);
 
 	if (!boot_cpu_has(X86_FEATURE_FPU))
-		return fpregs_soft_get(target, regset, pos, count, kbuf, ubuf);
+		return fpregs_soft_get(target, regset, to);
 
-	if (!boot_cpu_has(X86_FEATURE_FXSR))
-		return user_regset_copyout(&pos, &count, &kbuf, &ubuf,
-					   &fpu->state.fsave, 0,
-					   -1);
+	if (!boot_cpu_has(X86_FEATURE_FXSR)) {
+		return membuf_write(&to, &fpu->state.fsave,
+				    sizeof(struct fregs_state));
+	}
 
 	fpstate_sanitize_xstate(fpu);
 
-	if (kbuf && pos == 0 && count == sizeof(env)) {
-		convert_from_fxsr(kbuf, target);
+	if (to.left == sizeof(env)) {
+		convert_from_fxsr(to.p, target);
 		return 0;
 	}
 
 	convert_from_fxsr(&env, target);
-
-	return user_regset_copyout(&pos, &count, &kbuf, &ubuf, &env, 0, -1);
+	return membuf_write(&to, &env, sizeof(env));
 }
 
 int fpregs_set(struct task_struct *target, const struct user_regset *regset,
@@ -356,20 +347,4 @@
 	return ret;
 }
 
-/*
- * FPU state for core dumps.
- * This is only used for a.out dumps now.
- * It is declared generically using elf_fpregset_t (which is
- * struct user_i387_struct) but is in fact only used for 32-bit
- * dumps, so on 64-bit it is really struct user_i387_ia32_struct.
- */
-int dump_fpu(struct pt_regs *regs, struct user_i387_struct *ufpu)
-{
-	struct task_struct *tsk = current;
-
-	return !fpregs_get(tsk, NULL, 0, sizeof(struct user_i387_ia32_struct),
-			   ufpu, NULL);
-}
-EXPORT_SYMBOL(dump_fpu);
-
 #endif	/* CONFIG_X86_32 || CONFIG_IA32_EMULATION */
diff --git a/arch/x86/kernel/fpu/signal.c b/arch/x86/kernel/fpu/signal.c
index ab2f9c2..b7b92cd 100644
--- a/arch/x86/kernel/fpu/signal.c
+++ b/arch/x86/kernel/fpu/signal.c
@@ -170,14 +170,15 @@
 	ia32_fxstate &= (IS_ENABLED(CONFIG_X86_32) ||
 			 IS_ENABLED(CONFIG_IA32_EMULATION));
 
+	if (!static_cpu_has(X86_FEATURE_FPU)) {
+		struct user_i387_ia32_struct fp;
+		fpregs_soft_get(current, NULL, (struct membuf){.p = &fp,
+						.left = sizeof(fp)});
+		return copy_to_user(buf, &fp, sizeof(fp)) ? -EFAULT : 0;
+	}
+
 	if (!access_ok(buf, size))
 		return -EACCES;
-
-	if (!static_cpu_has(X86_FEATURE_FPU))
-		return fpregs_soft_get(current, NULL, 0,
-			sizeof(struct user_i387_ia32_struct), NULL,
-			(struct _fpstate_32 __user *) buf) ? -1 : 1;
-
 retry:
 	/*
 	 * Load the FPU registers if they are not valid for the current task.
@@ -211,28 +212,27 @@
 }
 
 static inline void
-sanitize_restored_xstate(union fpregs_state *state,
-			 struct user_i387_ia32_struct *ia32_env,
-			 u64 xfeatures, int fx_only)
+sanitize_restored_user_xstate(union fpregs_state *state,
+			      struct user_i387_ia32_struct *ia32_env,
+			      u64 user_xfeatures, int fx_only)
 {
 	struct xregs_state *xsave = &state->xsave;
 	struct xstate_header *header = &xsave->header;
 
 	if (use_xsave()) {
 		/*
-		 * Note: we don't need to zero the reserved bits in the
-		 * xstate_header here because we either didn't copy them at all,
-		 * or we checked earlier that they aren't set.
+		 * Clear all feature bits which are not set in
+		 * user_xfeatures and clear all extended features
+		 * for fx_only mode.
 		 */
+		u64 mask = fx_only ? XFEATURE_MASK_FPSSE : user_xfeatures;
 
 		/*
-		 * Init the state that is not present in the memory
-		 * layout and not enabled by the OS.
+		 * Supervisor state has to be preserved. The sigframe
+		 * restore can only modify user features, i.e. @mask
+		 * cannot contain them.
 		 */
-		if (fx_only)
-			header->xfeatures = XFEATURE_MASK_FPSSE;
-		else
-			header->xfeatures &= xfeatures;
+		header->xfeatures &= mask | xfeatures_mask_supervisor();
 	}
 
 	if (use_fxsr()) {
@@ -252,16 +252,24 @@
  */
 static int copy_user_to_fpregs_zeroing(void __user *buf, u64 xbv, int fx_only)
 {
+	u64 init_bv;
+	int r;
+
 	if (use_xsave()) {
 		if (fx_only) {
-			u64 init_bv = xfeatures_mask & ~XFEATURE_MASK_FPSSE;
-			copy_kernel_to_xregs(&init_fpstate.xsave, init_bv);
-			return copy_user_to_fxregs(buf);
-		} else {
-			u64 init_bv = xfeatures_mask & ~xbv;
-			if (unlikely(init_bv))
+			init_bv = xfeatures_mask_user() & ~XFEATURE_MASK_FPSSE;
+
+			r = copy_user_to_fxregs(buf);
+			if (!r)
 				copy_kernel_to_xregs(&init_fpstate.xsave, init_bv);
-			return copy_user_to_xregs(buf, xbv);
+			return r;
+		} else {
+			init_bv = xfeatures_mask_user() & ~xbv;
+
+			r = copy_user_to_xregs(buf, xbv);
+			if (!r && unlikely(init_bv))
+				copy_kernel_to_xregs(&init_fpstate.xsave, init_bv);
+			return r;
 		}
 	} else if (use_fxsr()) {
 		return copy_user_to_fxregs(buf);
@@ -277,7 +285,7 @@
 	struct task_struct *tsk = current;
 	struct fpu *fpu = &tsk->thread.fpu;
 	struct user_i387_ia32_struct env;
-	u64 xfeatures = 0;
+	u64 user_xfeatures = 0;
 	int fx_only = 0;
 	int ret = 0;
 
@@ -285,7 +293,7 @@
 			 IS_ENABLED(CONFIG_IA32_EMULATION));
 
 	if (!buf) {
-		fpu__clear(fpu);
+		fpu__clear_user_states(fpu);
 		return 0;
 	}
 
@@ -314,32 +322,14 @@
 			trace_x86_fpu_xstate_check_failed(fpu);
 		} else {
 			state_size = fx_sw_user.xstate_size;
-			xfeatures = fx_sw_user.xfeatures;
+			user_xfeatures = fx_sw_user.xfeatures;
 		}
 	}
 
-	/*
-	 * The current state of the FPU registers does not matter. By setting
-	 * TIF_NEED_FPU_LOAD unconditionally it is ensured that the our xstate
-	 * is not modified on context switch and that the xstate is considered
-	 * to be loaded again on return to userland (overriding last_cpu avoids
-	 * the optimisation).
-	 */
-	set_thread_flag(TIF_NEED_FPU_LOAD);
-	__fpu_invalidate_fpregs_state(fpu);
-
 	if ((unsigned long)buf_fx % 64)
 		fx_only = 1;
-	/*
-	 * For 32-bit frames with fxstate, copy the fxstate so it can be
-	 * reconstructed later.
-	 */
-	if (ia32_fxstate) {
-		ret = __copy_from_user(&env, buf, sizeof(env));
-		if (ret)
-			goto out;
-		envp = &env;
-	} else {
+
+	if (!ia32_fxstate) {
 		/*
 		 * Attempt to restore the FPU registers directly from user
 		 * memory. For that to succeed, the user access cannot cause
@@ -349,38 +339,102 @@
 		 */
 		fpregs_lock();
 		pagefault_disable();
-		ret = copy_user_to_fpregs_zeroing(buf_fx, xfeatures, fx_only);
+		ret = copy_user_to_fpregs_zeroing(buf_fx, user_xfeatures, fx_only);
 		pagefault_enable();
 		if (!ret) {
+
+			/*
+			 * Restore supervisor states: previous context switch
+			 * etc has done XSAVES and saved the supervisor states
+			 * in the kernel buffer from which they can be restored
+			 * now.
+			 *
+			 * We cannot do a single XRSTORS here - which would
+			 * be nice - because the rest of the FPU registers are
+			 * being restored from a user buffer directly. The
+			 * single XRSTORS happens below, when the user buffer
+			 * has been copied to the kernel one.
+			 */
+			if (test_thread_flag(TIF_NEED_FPU_LOAD) &&
+			    xfeatures_mask_supervisor())
+				copy_kernel_to_xregs(&fpu->state.xsave,
+						     xfeatures_mask_supervisor());
 			fpregs_mark_activate();
 			fpregs_unlock();
 			return 0;
 		}
-		fpregs_deactivate(fpu);
+
+		/*
+		 * The above did an FPU restore operation, restricted to
+		 * the user portion of the registers, and failed, but the
+		 * microcode might have modified the FPU registers
+		 * nevertheless.
+		 *
+		 * If the FPU registers do not belong to current, then
+		 * invalidate the FPU register state otherwise the task might
+		 * preempt current and return to user space with corrupted
+		 * FPU registers.
+		 *
+		 * In case current owns the FPU registers then no further
+		 * action is required. The fixup below will handle it
+		 * correctly.
+		 */
+		if (test_thread_flag(TIF_NEED_FPU_LOAD))
+			__cpu_invalidate_fpregs_state();
+
 		fpregs_unlock();
+	} else {
+		/*
+		 * For 32-bit frames with fxstate, copy the fxstate so it can
+		 * be reconstructed later.
+		 */
+		ret = __copy_from_user(&env, buf, sizeof(env));
+		if (ret)
+			goto out;
+		envp = &env;
 	}
 
+	/*
+	 * By setting TIF_NEED_FPU_LOAD it is ensured that our xstate is
+	 * not modified on context switch and that the xstate is considered
+	 * to be loaded again on return to userland (overriding last_cpu avoids
+	 * the optimisation).
+	 */
+	fpregs_lock();
+
+	if (!test_thread_flag(TIF_NEED_FPU_LOAD)) {
+
+		/*
+		 * Supervisor states are not modified by user space input.  Save
+		 * current supervisor states first and invalidate the FPU regs.
+		 */
+		if (xfeatures_mask_supervisor())
+			copy_supervisor_to_kernel(&fpu->state.xsave);
+		set_thread_flag(TIF_NEED_FPU_LOAD);
+	}
+	__fpu_invalidate_fpregs_state(fpu);
+	fpregs_unlock();
 
 	if (use_xsave() && !fx_only) {
-		u64 init_bv = xfeatures_mask & ~xfeatures;
+		u64 init_bv = xfeatures_mask_user() & ~user_xfeatures;
 
-		if (using_compacted_format()) {
-			ret = copy_user_to_xstate(&fpu->state.xsave, buf_fx);
-		} else {
-			ret = __copy_from_user(&fpu->state.xsave, buf_fx, state_size);
-
-			if (!ret && state_size > offsetof(struct xregs_state, header))
-				ret = validate_xstate_header(&fpu->state.xsave.header);
-		}
+		ret = copy_user_to_xstate(&fpu->state.xsave, buf_fx);
 		if (ret)
 			goto out;
 
-		sanitize_restored_xstate(&fpu->state, envp, xfeatures, fx_only);
+		sanitize_restored_user_xstate(&fpu->state, envp, user_xfeatures,
+					      fx_only);
 
 		fpregs_lock();
 		if (unlikely(init_bv))
 			copy_kernel_to_xregs(&init_fpstate.xsave, init_bv);
-		ret = copy_kernel_to_xregs_err(&fpu->state.xsave, xfeatures);
+
+		/*
+		 * Restore previously saved supervisor xstates along with
+		 * copied-in user xstates.
+		 */
+		ret = copy_kernel_to_xregs_err(&fpu->state.xsave,
+					       user_xfeatures | xfeatures_mask_supervisor());
 
 	} else if (use_fxsr()) {
 		ret = __copy_from_user(&fpu->state.fxsave, buf_fx, state_size);
@@ -389,11 +443,14 @@
 			goto out;
 		}
 
-		sanitize_restored_xstate(&fpu->state, envp, xfeatures, fx_only);
+		sanitize_restored_user_xstate(&fpu->state, envp, user_xfeatures,
+					      fx_only);
 
 		fpregs_lock();
 		if (use_xsave()) {
-			u64 init_bv = xfeatures_mask & ~XFEATURE_MASK_FPSSE;
+			u64 init_bv;
+
+			init_bv = xfeatures_mask_user() & ~XFEATURE_MASK_FPSSE;
 			copy_kernel_to_xregs(&init_fpstate.xsave, init_bv);
 		}
 
@@ -414,7 +471,7 @@
 
 out:
 	if (ret)
-		fpu__clear(fpu);
+		fpu__clear_user_states(fpu);
 	return ret;
 }
 
@@ -469,7 +526,7 @@
 
 	fx_sw_reserved.magic1 = FP_XSTATE_MAGIC1;
 	fx_sw_reserved.extended_size = size;
-	fx_sw_reserved.xfeatures = xfeatures_mask;
+	fx_sw_reserved.xfeatures = xfeatures_mask_user();
 	fx_sw_reserved.xstate_size = fpu_user_xstate_size;
 
 	if (IS_ENABLED(CONFIG_IA32_EMULATION) ||
diff --git a/arch/x86/kernel/fpu/xstate.c b/arch/x86/kernel/fpu/xstate.c
index 046782d..80836b9 100644
--- a/arch/x86/kernel/fpu/xstate.c
+++ b/arch/x86/kernel/fpu/xstate.c
@@ -37,6 +37,7 @@
 	"AVX-512 ZMM_Hi256"		,
 	"Processor Trace (unused)"	,
 	"Protection Keys User registers",
+	"PASID state",
 	"unknown xstate feature"	,
 };
 
@@ -51,16 +52,19 @@
 	X86_FEATURE_AVX512F,
 	X86_FEATURE_INTEL_PT,
 	X86_FEATURE_PKU,
+	X86_FEATURE_ENQCMD,
 };
 
 /*
- * Mask of xstate features supported by the CPU and the kernel:
+ * This represents the full set of bits that should ever be set in a kernel
+ * XSAVE buffer, both supervisor and user xstates.
  */
-u64 xfeatures_mask __read_mostly;
+u64 xfeatures_mask_all __read_mostly;
 
 static unsigned int xstate_offsets[XFEATURE_MAX] = { [ 0 ... XFEATURE_MAX - 1] = -1};
 static unsigned int xstate_sizes[XFEATURE_MAX]   = { [ 0 ... XFEATURE_MAX - 1] = -1};
-static unsigned int xstate_comp_offsets[sizeof(xfeatures_mask)*8];
+static unsigned int xstate_comp_offsets[XFEATURE_MAX] = { [ 0 ... XFEATURE_MAX - 1] = -1};
+static unsigned int xstate_supervisor_only_offsets[XFEATURE_MAX] = { [ 0 ... XFEATURE_MAX - 1] = -1};
 
 /*
  * The XSAVE area of kernel can be in standard or compacted format;
@@ -76,7 +80,7 @@
  */
 int cpu_has_xfeatures(u64 xfeatures_needed, const char **feature_name)
 {
-	u64 xfeatures_missing = xfeatures_needed & ~xfeatures_mask;
+	u64 xfeatures_missing = xfeatures_needed & ~xfeatures_mask_all;
 
 	if (unlikely(feature_name)) {
 		long xfeature_idx, max_idx;
@@ -107,25 +111,17 @@
 }
 EXPORT_SYMBOL_GPL(cpu_has_xfeatures);
 
-static int xfeature_is_supervisor(int xfeature_nr)
+static bool xfeature_is_supervisor(int xfeature_nr)
 {
 	/*
-	 * We currently do not support supervisor states, but if
-	 * we did, we could find out like this.
-	 *
-	 * SDM says: If state component 'i' is a user state component,
-	 * ECX[0] return 0; if state component i is a supervisor
-	 * state component, ECX[0] returns 1.
+	 * Extended State Enumeration Sub-leaves (EAX = 0DH, ECX = n, n > 1)
+	 * returns ECX[0] set to (1) for a supervisor state, and cleared (0)
+	 * for a user state.
 	 */
 	u32 eax, ebx, ecx, edx;
 
 	cpuid_count(XSTATE_CPUID, xfeature_nr, &eax, &ebx, &ecx, &edx);
-	return !!(ecx & 1);
-}
-
-static int xfeature_is_user(int xfeature_nr)
-{
-	return !xfeature_is_supervisor(xfeature_nr);
+	return ecx & 1;
 }
 
 /*
@@ -158,7 +154,7 @@
 	 * None of the feature bits are in init state. So nothing else
 	 * to do for us, as the memory layout is up to date.
 	 */
-	if ((xfeatures & xfeatures_mask) == xfeatures_mask)
+	if ((xfeatures & xfeatures_mask_all) == xfeatures_mask_all)
 		return;
 
 	/*
@@ -185,7 +181,7 @@
 	 * in a special way already:
 	 */
 	feature_bit = 0x2;
-	xfeatures = (xfeatures_mask & ~xfeatures) >> 2;
+	xfeatures = (xfeatures_mask_user() & ~xfeatures) >> 2;
 
 	/*
 	 * Update all the remaining memory layouts according to their
@@ -213,30 +209,41 @@
  */
 void fpu__init_cpu_xstate(void)
 {
-	if (!boot_cpu_has(X86_FEATURE_XSAVE) || !xfeatures_mask)
+	u64 unsup_bits;
+
+	if (!boot_cpu_has(X86_FEATURE_XSAVE) || !xfeatures_mask_all)
 		return;
 	/*
-	 * Make it clear that XSAVES supervisor states are not yet
-	 * implemented should anyone expect it to work by changing
-	 * bits in XFEATURE_MASK_* macros and XCR0.
+	 * Unsupported supervisor xstates should not be found in
+	 * the xfeatures mask.
 	 */
-	WARN_ONCE((xfeatures_mask & XFEATURE_MASK_SUPERVISOR),
-		"x86/fpu: XSAVES supervisor states are not yet implemented.\n");
+	unsup_bits = xfeatures_mask_all & XFEATURE_MASK_SUPERVISOR_UNSUPPORTED;
+	WARN_ONCE(unsup_bits, "x86/fpu: Found unsupported supervisor xstates: 0x%llx\n",
+		  unsup_bits);
 
-	xfeatures_mask &= ~XFEATURE_MASK_SUPERVISOR;
+	xfeatures_mask_all &= ~XFEATURE_MASK_SUPERVISOR_UNSUPPORTED;
 
 	cr4_set_bits(X86_CR4_OSXSAVE);
-	xsetbv(XCR_XFEATURE_ENABLED_MASK, xfeatures_mask);
+
+	/*
+	 * XCR_XFEATURE_ENABLED_MASK (aka. XCR0) sets user features
+	 * managed by XSAVE{C, OPT, S} and XRSTOR{S}.  Only XSAVE user
+	 * states can be set here.
+	 */
+	xsetbv(XCR_XFEATURE_ENABLED_MASK, xfeatures_mask_user());
+
+	/*
+	 * MSR_IA32_XSS sets supervisor states managed by XSAVES.
+	 */
+	if (boot_cpu_has(X86_FEATURE_XSAVES)) {
+		wrmsrl(MSR_IA32_XSS, xfeatures_mask_supervisor() |
+				     xfeatures_mask_dynamic());
+	}
 }
 
-/*
- * Note that in the future we will likely need a pair of
- * functions here: one for user xstates and the other for
- * system xstates.  For now, they are the same.
- */
-static int xfeature_enabled(enum xfeature xfeature)
+static bool xfeature_enabled(enum xfeature xfeature)
 {
-	return !!(xfeatures_mask & (1UL << xfeature));
+	return xfeatures_mask_all & BIT_ULL(xfeature);
 }
 
 /*
@@ -254,10 +261,13 @@
 	 * in the fixed offsets in the xsave area in either compacted form
 	 * or standard form.
 	 */
-	xstate_offsets[0] = 0;
-	xstate_sizes[0] = offsetof(struct fxregs_state, xmm_space);
-	xstate_offsets[1] = xstate_sizes[0];
-	xstate_sizes[1] = FIELD_SIZEOF(struct fxregs_state, xmm_space);
+	xstate_offsets[XFEATURE_FP]	= 0;
+	xstate_sizes[XFEATURE_FP]	= offsetof(struct fxregs_state,
+						   xmm_space);
+
+	xstate_offsets[XFEATURE_SSE]	= xstate_sizes[XFEATURE_FP];
+	xstate_sizes[XFEATURE_SSE]	= sizeof_field(struct fxregs_state,
+						       xmm_space);
 
 	for (i = FIRST_EXTENDED_XFEATURE; i < XFEATURE_MAX; i++) {
 		if (!xfeature_enabled(i))
@@ -265,21 +275,25 @@
 
 		cpuid_count(XSTATE_CPUID, i, &eax, &ebx, &ecx, &edx);
 
-		/*
-		 * If an xfeature is supervisor state, the offset
-		 * in EBX is invalid. We leave it to -1.
-		 */
-		if (xfeature_is_user(i))
-			xstate_offsets[i] = ebx;
-
 		xstate_sizes[i] = eax;
+
 		/*
-		 * In our xstate size checks, we assume that the
-		 * highest-numbered xstate feature has the
-		 * highest offset in the buffer.  Ensure it does.
+		 * If an xfeature is supervisor state, the offset in EBX is
+		 * invalid, leave it to -1.
+		 */
+		if (xfeature_is_supervisor(i))
+			continue;
+
+		xstate_offsets[i] = 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);
+			  "x86/fpu: misordered xstate at %d\n", last_good_offset);
+
 		last_good_offset = xstate_offsets[i];
 	}
 }
@@ -306,6 +320,7 @@
 	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);
 }
 
 /*
@@ -326,6 +341,13 @@
 	u32 eax, ebx, ecx, edx;
 
 	CHECK_XFEATURE(xfeature_nr);
+
+	if (!xfeature_enabled(xfeature_nr)) {
+		WARN_ONCE(1, "Checking alignment of disabled xfeature %d\n",
+			  xfeature_nr);
+		return 0;
+	}
+
 	cpuid_count(XSTATE_CPUID, xfeature_nr, &eax, &ebx, &ecx, &edx);
 	/*
 	 * The value returned by ECX[1] indicates the alignment
@@ -338,11 +360,11 @@
 /*
  * This function sets up offsets and sizes of all extended states in
  * xsave area. This supports both standard format and compacted format
- * of the xsave aread.
+ * of the xsave area.
  */
-static void __init setup_xstate_comp(void)
+static void __init setup_xstate_comp_offsets(void)
 {
-	unsigned int xstate_comp_sizes[sizeof(xfeatures_mask)*8];
+	unsigned int next_offset;
 	int i;
 
 	/*
@@ -350,36 +372,56 @@
 	 * in the fixed offsets in the xsave area in either compacted form
 	 * or standard form.
 	 */
-	xstate_comp_offsets[0] = 0;
-	xstate_comp_offsets[1] = offsetof(struct fxregs_state, xmm_space);
+	xstate_comp_offsets[XFEATURE_FP] = 0;
+	xstate_comp_offsets[XFEATURE_SSE] = offsetof(struct fxregs_state,
+						     xmm_space);
 
 	if (!boot_cpu_has(X86_FEATURE_XSAVES)) {
 		for (i = FIRST_EXTENDED_XFEATURE; i < XFEATURE_MAX; i++) {
-			if (xfeature_enabled(i)) {
+			if (xfeature_enabled(i))
 				xstate_comp_offsets[i] = xstate_offsets[i];
-				xstate_comp_sizes[i] = xstate_sizes[i];
-			}
 		}
 		return;
 	}
 
-	xstate_comp_offsets[FIRST_EXTENDED_XFEATURE] =
-		FXSAVE_SIZE + XSAVE_HDR_SIZE;
+	next_offset = FXSAVE_SIZE + XSAVE_HDR_SIZE;
 
 	for (i = FIRST_EXTENDED_XFEATURE; i < XFEATURE_MAX; i++) {
-		if (xfeature_enabled(i))
-			xstate_comp_sizes[i] = xstate_sizes[i];
-		else
-			xstate_comp_sizes[i] = 0;
+		if (!xfeature_enabled(i))
+			continue;
 
-		if (i > FIRST_EXTENDED_XFEATURE) {
-			xstate_comp_offsets[i] = xstate_comp_offsets[i-1]
-					+ xstate_comp_sizes[i-1];
+		if (xfeature_is_aligned(i))
+			next_offset = ALIGN(next_offset, 64);
 
-			if (xfeature_is_aligned(i))
-				xstate_comp_offsets[i] =
-					ALIGN(xstate_comp_offsets[i], 64);
-		}
+		xstate_comp_offsets[i] = next_offset;
+		next_offset += xstate_sizes[i];
+	}
+}
+
+/*
+ * Setup offsets of a supervisor-state-only XSAVES buffer:
+ *
+ * The offsets stored in xstate_comp_offsets[] only work for one specific
+ * value of the Requested Feature BitMap (RFBM).  In cases where a different
+ * RFBM value is used, a different set of offsets is required.  This set of
+ * offsets is for when RFBM=xfeatures_mask_supervisor().
+ */
+static void __init setup_supervisor_only_offsets(void)
+{
+	unsigned int next_offset;
+	int i;
+
+	next_offset = FXSAVE_SIZE + XSAVE_HDR_SIZE;
+
+	for (i = FIRST_EXTENDED_XFEATURE; i < XFEATURE_MAX; i++) {
+		if (!xfeature_enabled(i) || !xfeature_is_supervisor(i))
+			continue;
+
+		if (xfeature_is_aligned(i))
+			next_offset = ALIGN(next_offset, 64);
+
+		xstate_supervisor_only_offsets[i] = next_offset;
+		next_offset += xstate_sizes[i];
 	}
 }
 
@@ -414,7 +456,8 @@
 	 XFEATURE_MASK_Hi16_ZMM	 |		\
 	 XFEATURE_MASK_PKRU |			\
 	 XFEATURE_MASK_BNDREGS |		\
-	 XFEATURE_MASK_BNDCSR)
+	 XFEATURE_MASK_BNDCSR |			\
+	 XFEATURE_MASK_PASID)
 
 /*
  * setup the xstate image representing the init state
@@ -423,7 +466,9 @@
 {
 	static int on_boot_cpu __initdata = 1;
 
-	BUILD_BUG_ON(XCNTXT_MASK != XFEATURES_INIT_FPSTATE_HANDLED);
+	BUILD_BUG_ON((XFEATURE_MASK_USER_SUPPORTED |
+		      XFEATURE_MASK_SUPERVISOR_SUPPORTED) !=
+		     XFEATURES_INIT_FPSTATE_HANDLED);
 
 	WARN_ON_FPU(!on_boot_cpu);
 	on_boot_cpu = 0;
@@ -435,7 +480,8 @@
 	print_xstate_features();
 
 	if (boot_cpu_has(X86_FEATURE_XSAVES))
-		init_fpstate.xsave.header.xcomp_bv = (u64)1 << 63 | xfeatures_mask;
+		init_fpstate.xsave.header.xcomp_bv = XCOMP_BV_COMPACTED_FORMAT |
+						     xfeatures_mask_all;
 
 	/*
 	 * Init all the features state with header.xfeatures being 0x0
@@ -470,7 +516,7 @@
 	 * format. Checking a supervisor state's uncompacted offset is
 	 * an error.
 	 */
-	if (XFEATURE_MASK_SUPERVISOR & BIT_ULL(xfeature_nr)) {
+	if (XFEATURE_MASK_SUPERVISOR_ALL & BIT_ULL(xfeature_nr)) {
 		WARN_ONCE(1, "No fixed offset for xstate %d\n", xfeature_nr);
 		return -1;
 	}
@@ -480,7 +526,7 @@
 	return ebx;
 }
 
-static int xfeature_size(int xfeature_nr)
+int xfeature_size(int xfeature_nr)
 {
 	u32 eax, ebx, ecx, edx;
 
@@ -504,10 +550,10 @@
 }
 
 /* Validate an xstate header supplied by userspace (ptrace or sigreturn) */
-int validate_xstate_header(const struct xstate_header *hdr)
+int validate_user_xstate_header(const struct xstate_header *hdr)
 {
 	/* No unknown or supervisor features may be set */
-	if (hdr->xfeatures & (~xfeatures_mask | XFEATURE_MASK_SUPERVISOR))
+	if (hdr->xfeatures & ~xfeatures_mask_user())
 		return -EINVAL;
 
 	/* Userspace must use the uncompacted format */
@@ -584,6 +630,7 @@
 	XCHECK_SZ(sz, nr, XFEATURE_ZMM_Hi256, struct avx_512_zmm_uppers_state);
 	XCHECK_SZ(sz, nr, XFEATURE_Hi16_ZMM,  struct avx_512_hi16_state);
 	XCHECK_SZ(sz, nr, XFEATURE_PKRU,      struct pkru_state);
+	XCHECK_SZ(sz, nr, XFEATURE_PASID,     struct ia32_pasid_state);
 
 	/*
 	 * Make *SURE* to add any feature numbers in below if
@@ -592,7 +639,8 @@
 	 */
 	if ((nr < XFEATURE_YMM) ||
 	    (nr >= XFEATURE_MAX) ||
-	    (nr == XFEATURE_PT_UNIMPLEMENTED_SO_FAR)) {
+	    (nr == XFEATURE_PT_UNIMPLEMENTED_SO_FAR) ||
+	    ((nr >= XFEATURE_RSRVD_COMP_11) && (nr <= XFEATURE_LBR))) {
 		WARN_ONCE(1, "no structure for xstate: %d\n", nr);
 		XSTATE_WARN_ON(1);
 	}
@@ -602,6 +650,10 @@
  * This essentially double-checks what the cpu told us about
  * how large the XSAVE buffer needs to be.  We are recalculating
  * it to be safe.
+ *
+ * Dynamic XSAVE features allocate their own buffers and are not
+ * covered by these checks. Only the size of the buffer for task->fpu
+ * is checked here.
  */
 static void do_extra_xstate_size_checks(void)
 {
@@ -642,15 +694,12 @@
 
 
 /*
- * Get total size of enabled xstates in XCR0/xfeatures_mask.
+ * Get total size of enabled xstates in XCR0 | IA32_XSS.
  *
  * Note the SDM's wording here.  "sub-function 0" only enumerates
  * the size of the *user* states.  If we use it to size a buffer
  * that we use 'XSAVES' on, we could potentially overflow the
  * buffer because 'XSAVES' saves system states too.
- *
- * Note that we do not currently set any bits on IA32_XSS so
- * 'XCR0 | IA32_XSS == XCR0' for now.
  */
 static unsigned int __init get_xsaves_size(void)
 {
@@ -667,6 +716,33 @@
 	return ebx;
 }
 
+/*
+ * Get the total size of the enabled xstates without the dynamic supervisor
+ * features.
+ */
+static unsigned int __init get_xsaves_size_no_dynamic(void)
+{
+	u64 mask = xfeatures_mask_dynamic();
+	unsigned int size;
+
+	if (!mask)
+		return get_xsaves_size();
+
+	/* Disable dynamic features. */
+	wrmsrl(MSR_IA32_XSS, xfeatures_mask_supervisor());
+
+	/*
+	 * Ask the hardware what size is required of the buffer.
+	 * This is the size required for the task->fpu buffer.
+	 */
+	size = get_xsaves_size();
+
+	/* Re-enable dynamic features so XSAVES will work on them again. */
+	wrmsrl(MSR_IA32_XSS, xfeatures_mask_supervisor() | mask);
+
+	return size;
+}
+
 static unsigned int __init get_xsave_size(void)
 {
 	unsigned int eax, ebx, ecx, edx;
@@ -704,7 +780,7 @@
 	xsave_size = get_xsave_size();
 
 	if (boot_cpu_has(X86_FEATURE_XSAVES))
-		possible_xstate_size = get_xsaves_size();
+		possible_xstate_size = get_xsaves_size_no_dynamic();
 	else
 		possible_xstate_size = xsave_size;
 
@@ -732,7 +808,7 @@
  */
 static void fpu__init_disable_system_xstate(void)
 {
-	xfeatures_mask = 0;
+	xfeatures_mask_all = 0;
 	cr4_clear_bits(X86_CR4_OSXSAVE);
 	setup_clear_cpu_cap(X86_FEATURE_XSAVE);
 }
@@ -767,16 +843,26 @@
 		return;
 	}
 
+	/*
+	 * Find user xstates supported by the processor.
+	 */
 	cpuid_count(XSTATE_CPUID, 0, &eax, &ebx, &ecx, &edx);
-	xfeatures_mask = eax + ((u64)edx << 32);
+	xfeatures_mask_all = eax + ((u64)edx << 32);
 
-	if ((xfeatures_mask & XFEATURE_MASK_FPSSE) != XFEATURE_MASK_FPSSE) {
+	/*
+	 * Find supervisor xstates supported by the processor.
+	 */
+	cpuid_count(XSTATE_CPUID, 1, &eax, &ebx, &ecx, &edx);
+	xfeatures_mask_all |= ecx + ((u64)edx << 32);
+
+	if ((xfeatures_mask_user() & XFEATURE_MASK_FPSSE) != XFEATURE_MASK_FPSSE) {
 		/*
 		 * This indicates that something really unexpected happened
 		 * with the enumeration.  Disable XSAVE and try to continue
 		 * booting without it.  This is too early to BUG().
 		 */
-		pr_err("x86/fpu: FP/SSE not present amongst the CPU's xstate features: 0x%llx.\n", xfeatures_mask);
+		pr_err("x86/fpu: FP/SSE not present amongst the CPU's xstate features: 0x%llx.\n",
+		       xfeatures_mask_all);
 		goto out_disable;
 	}
 
@@ -785,10 +871,10 @@
 	 */
 	for (i = 0; i < ARRAY_SIZE(xsave_cpuid_features); i++) {
 		if (!boot_cpu_has(xsave_cpuid_features[i]))
-			xfeatures_mask &= ~BIT(i);
+			xfeatures_mask_all &= ~BIT_ULL(i);
 	}
 
-	xfeatures_mask &= fpu__get_supported_xfeatures_mask();
+	xfeatures_mask_all &= fpu__get_supported_xfeatures_mask();
 
 	/* Enable xstate instructions to be able to continue with initialization: */
 	fpu__init_cpu_xstate();
@@ -800,15 +886,16 @@
 	 * Update info used for ptrace frames; use standard-format size and no
 	 * supervisor xstates:
 	 */
-	update_regset_xstate_info(fpu_user_xstate_size,	xfeatures_mask & ~XFEATURE_MASK_SUPERVISOR);
+	update_regset_xstate_info(fpu_user_xstate_size, xfeatures_mask_user());
 
 	fpu__init_prepare_fx_sw_frame();
 	setup_init_fpu_buf();
-	setup_xstate_comp();
+	setup_xstate_comp_offsets();
+	setup_supervisor_only_offsets();
 	print_xstate_offset_size();
 
 	pr_info("x86/fpu: Enabled xstate features 0x%llx, context size is %d bytes, using '%s' format.\n",
-		xfeatures_mask,
+		xfeatures_mask_all,
 		fpu_kernel_xstate_size,
 		boot_cpu_has(X86_FEATURE_XSAVES) ? "compacted" : "standard");
 	return;
@@ -827,7 +914,16 @@
 	 * Restore XCR0 on xsave capable CPUs:
 	 */
 	if (boot_cpu_has(X86_FEATURE_XSAVE))
-		xsetbv(XCR_XFEATURE_ENABLED_MASK, xfeatures_mask);
+		xsetbv(XCR_XFEATURE_ENABLED_MASK, xfeatures_mask_user());
+
+	/*
+	 * Restore IA32_XSS. The same CPUID bit enumerates support
+	 * of XSAVES and MSR_IA32_XSS.
+	 */
+	if (boot_cpu_has(X86_FEATURE_XSAVES)) {
+		wrmsrl(MSR_IA32_XSS, xfeatures_mask_supervisor()  |
+				     xfeatures_mask_dynamic());
+	}
 }
 
 /*
@@ -872,10 +968,9 @@
 
 	/*
 	 * We should not ever be requesting features that we
-	 * have not enabled.  Remember that pcntxt_mask is
-	 * what we write to the XCR0 register.
+	 * have not enabled.
 	 */
-	WARN_ONCE(!(xfeatures_mask & BIT_ULL(xfeature_nr)),
+	WARN_ONCE(!(xfeatures_mask_all & BIT_ULL(xfeature_nr)),
 		  "get of unsupported state");
 	/*
 	 * This assumes the last 'xsave*' instruction to
@@ -989,32 +1084,10 @@
 	return true;
 }
 
-static void fill_gap(unsigned to, void **kbuf, unsigned *pos, unsigned *count)
+static void copy_feature(bool from_xstate, struct membuf *to, void *xstate,
+			 void *init_xstate, unsigned int size)
 {
-	if (*pos < to) {
-		unsigned size = to - *pos;
-
-		if (size > *count)
-			size = *count;
-		memcpy(*kbuf, (void *)&init_fpstate.xsave + *pos, size);
-		*kbuf += size;
-		*pos += size;
-		*count -= size;
-	}
-}
-
-static void copy_part(unsigned offset, unsigned size, void *from,
-			void **kbuf, unsigned *pos, unsigned *count)
-{
-	fill_gap(offset, kbuf, pos, count);
-	if (size > *count)
-		size = *count;
-	if (size) {
-		memcpy(*kbuf, from, size);
-		*kbuf += size;
-		*pos += size;
-		*count -= size;
-	}
+	membuf_write(to, from_xstate ? xstate : init_xstate, size);
 }
 
 /*
@@ -1024,154 +1097,83 @@
  * It supports partial copy but pos always starts from zero. This is called
  * from xstateregs_get() and there we check the CPU has XSAVES.
  */
-int copy_xstate_to_kernel(void *kbuf, struct xregs_state *xsave, unsigned int offset_start, unsigned int size_total)
+void copy_xstate_to_kernel(struct membuf to, struct xregs_state *xsave)
 {
+	const unsigned int off_mxcsr = offsetof(struct fxregs_state, mxcsr);
+	struct xregs_state *xinit = &init_fpstate.xsave;
 	struct xstate_header header;
-	const unsigned off_mxcsr = offsetof(struct fxregs_state, mxcsr);
-	unsigned count = size_total;
+	unsigned int zerofrom;
 	int i;
 
 	/*
-	 * Currently copy_regset_to_user() starts from pos 0:
-	 */
-	if (unlikely(offset_start != 0))
-		return -EFAULT;
-
-	/*
 	 * The destination is a ptrace buffer; we put in only user xstates:
 	 */
 	memset(&header, 0, sizeof(header));
 	header.xfeatures = xsave->header.xfeatures;
-	header.xfeatures &= ~XFEATURE_MASK_SUPERVISOR;
+	header.xfeatures &= xfeatures_mask_user();
 
-	if (header.xfeatures & XFEATURE_MASK_FP)
-		copy_part(0, off_mxcsr,
-			  &xsave->i387, &kbuf, &offset_start, &count);
-	if (header.xfeatures & (XFEATURE_MASK_SSE | XFEATURE_MASK_YMM))
-		copy_part(off_mxcsr, MXCSR_AND_FLAGS_SIZE,
-			  &xsave->i387.mxcsr, &kbuf, &offset_start, &count);
-	if (header.xfeatures & XFEATURE_MASK_FP)
-		copy_part(offsetof(struct fxregs_state, st_space), 128,
-			  &xsave->i387.st_space, &kbuf, &offset_start, &count);
-	if (header.xfeatures & XFEATURE_MASK_SSE)
-		copy_part(xstate_offsets[XFEATURE_SSE], 256,
-			  &xsave->i387.xmm_space, &kbuf, &offset_start, &count);
-	/*
-	 * Fill xsave->i387.sw_reserved value for ptrace frame:
-	 */
-	copy_part(offsetof(struct fxregs_state, sw_reserved), 48,
-		  xstate_fx_sw_bytes, &kbuf, &offset_start, &count);
-	/*
-	 * Copy xregs_state->header:
-	 */
-	copy_part(offsetof(struct xregs_state, header), sizeof(header),
-		  &header, &kbuf, &offset_start, &count);
+	/* Copy FP state up to MXCSR */
+	copy_feature(header.xfeatures & XFEATURE_MASK_FP, &to, &xsave->i387,
+		     &xinit->i387, off_mxcsr);
+
+	/* Copy MXCSR when SSE or YMM are set in the feature mask */
+	copy_feature(header.xfeatures & (XFEATURE_MASK_SSE | XFEATURE_MASK_YMM),
+		     &to, &xsave->i387.mxcsr, &xinit->i387.mxcsr,
+		     MXCSR_AND_FLAGS_SIZE);
+
+	/* Copy the remaining FP state */
+	copy_feature(header.xfeatures & XFEATURE_MASK_FP,
+		     &to, &xsave->i387.st_space, &xinit->i387.st_space,
+		     sizeof(xsave->i387.st_space));
+
+	/* Copy the SSE state - shared with YMM, but independently managed */
+	copy_feature(header.xfeatures & XFEATURE_MASK_SSE,
+		     &to, &xsave->i387.xmm_space, &xinit->i387.xmm_space,
+		     sizeof(xsave->i387.xmm_space));
+
+	/* Zero the padding area */
+	membuf_zero(&to, sizeof(xsave->i387.padding));
+
+	/* Copy xsave->i387.sw_reserved */
+	membuf_write(&to, xstate_fx_sw_bytes, sizeof(xsave->i387.sw_reserved));
+
+	/* Copy the user space relevant state of @xsave->header */
+	membuf_write(&to, &header, sizeof(header));
+
+	zerofrom = offsetof(struct xregs_state, extended_state_area);
 
 	for (i = FIRST_EXTENDED_XFEATURE; i < XFEATURE_MAX; i++) {
 		/*
-		 * Copy only in-use xstates:
+		 * The ptrace buffer is in non-compacted XSAVE format.
+		 * In non-compacted format disabled features still occupy
+		 * state space, but there is no state to copy from in the
+		 * compacted init_fpstate. The gap tracking will zero this
+		 * later.
 		 */
-		if ((header.xfeatures >> i) & 1) {
-			void *src = __raw_xsave_addr(xsave, i);
+		if (!(xfeatures_mask_user() & BIT_ULL(i)))
+			continue;
 
-			copy_part(xstate_offsets[i], xstate_sizes[i],
-				  src, &kbuf, &offset_start, &count);
-		}
-
-	}
-	fill_gap(size_total, &kbuf, &offset_start, &count);
-
-	return 0;
-}
-
-static inline int
-__copy_xstate_to_user(void __user *ubuf, const void *data, unsigned int offset, unsigned int size, unsigned int size_total)
-{
-	if (!size)
-		return 0;
-
-	if (offset < size_total) {
-		unsigned int copy = min(size, size_total - offset);
-
-		if (__copy_to_user(ubuf + offset, data, copy))
-			return -EFAULT;
-	}
-	return 0;
-}
-
-/*
- * Convert from kernel XSAVES compacted format to standard format and copy
- * to a user-space buffer. It supports partial copy but pos always starts from
- * zero. This is called from xstateregs_get() and there we check the CPU
- * has XSAVES.
- */
-int copy_xstate_to_user(void __user *ubuf, struct xregs_state *xsave, unsigned int offset_start, unsigned int size_total)
-{
-	unsigned int offset, size;
-	int ret, i;
-	struct xstate_header header;
-
-	/*
-	 * Currently copy_regset_to_user() starts from pos 0:
-	 */
-	if (unlikely(offset_start != 0))
-		return -EFAULT;
-
-	/*
-	 * The destination is a ptrace buffer; we put in only user xstates:
-	 */
-	memset(&header, 0, sizeof(header));
-	header.xfeatures = xsave->header.xfeatures;
-	header.xfeatures &= ~XFEATURE_MASK_SUPERVISOR;
-
-	/*
-	 * Copy xregs_state->header:
-	 */
-	offset = offsetof(struct xregs_state, header);
-	size = sizeof(header);
-
-	ret = __copy_xstate_to_user(ubuf, &header, offset, size, size_total);
-	if (ret)
-		return ret;
-
-	for (i = 0; i < XFEATURE_MAX; i++) {
 		/*
-		 * Copy only in-use xstates:
+		 * If there was a feature or alignment gap, zero the space
+		 * in the destination buffer.
 		 */
-		if ((header.xfeatures >> i) & 1) {
-			void *src = __raw_xsave_addr(xsave, i);
+		if (zerofrom < xstate_offsets[i])
+			membuf_zero(&to, xstate_offsets[i] - zerofrom);
 
-			offset = xstate_offsets[i];
-			size = xstate_sizes[i];
+		copy_feature(header.xfeatures & BIT_ULL(i), &to,
+			     __raw_xsave_addr(xsave, i),
+			     __raw_xsave_addr(xinit, i),
+			     xstate_sizes[i]);
 
-			/* The next component has to fit fully into the output buffer: */
-			if (offset + size > size_total)
-				break;
-
-			ret = __copy_xstate_to_user(ubuf, src, offset, size, size_total);
-			if (ret)
-				return ret;
-		}
-
+		/*
+		 * Keep track of the last copied state in the non-compacted
+		 * target buffer for gap zeroing.
+		 */
+		zerofrom = xstate_offsets[i] + xstate_sizes[i];
 	}
 
-	if (xfeatures_mxcsr_quirk(header.xfeatures)) {
-		offset = offsetof(struct fxregs_state, mxcsr);
-		size = MXCSR_AND_FLAGS_SIZE;
-		__copy_xstate_to_user(ubuf, &xsave->i387.mxcsr, offset, size, size_total);
-	}
-
-	/*
-	 * Fill xsave->i387.sw_reserved value for ptrace frame:
-	 */
-	offset = offsetof(struct fxregs_state, sw_reserved);
-	size = sizeof(xstate_fx_sw_bytes);
-
-	ret = __copy_xstate_to_user(ubuf, xstate_fx_sw_bytes, offset, size, size_total);
-	if (ret)
-		return ret;
-
-	return 0;
+	if (to.left)
+		membuf_zero(&to, to.left);
 }
 
 /*
@@ -1189,7 +1191,7 @@
 
 	memcpy(&hdr, kbuf + offset, size);
 
-	if (validate_xstate_header(&hdr))
+	if (validate_user_xstate_header(&hdr))
 		return -EINVAL;
 
 	for (i = 0; i < XFEATURE_MAX; i++) {
@@ -1215,7 +1217,7 @@
 	 * The state that came in from userspace was user-state only.
 	 * Mask all the user states out of 'xfeatures':
 	 */
-	xsave->header.xfeatures &= XFEATURE_MASK_SUPERVISOR;
+	xsave->header.xfeatures &= XFEATURE_MASK_SUPERVISOR_ALL;
 
 	/*
 	 * Add back in the features that came in from userspace:
@@ -1243,7 +1245,7 @@
 	if (__copy_from_user(&hdr, ubuf + offset, size))
 		return -EFAULT;
 
-	if (validate_xstate_header(&hdr))
+	if (validate_user_xstate_header(&hdr))
 		return -EINVAL;
 
 	for (i = 0; i < XFEATURE_MAX; i++) {
@@ -1271,7 +1273,7 @@
 	 * The state that came in from userspace was user-state only.
 	 * Mask all the user states out of 'xfeatures':
 	 */
-	xsave->header.xfeatures &= XFEATURE_MASK_SUPERVISOR;
+	xsave->header.xfeatures &= XFEATURE_MASK_SUPERVISOR_ALL;
 
 	/*
 	 * Add back in the features that came in from userspace:
@@ -1281,6 +1283,133 @@
 	return 0;
 }
 
+/*
+ * Save only supervisor states to the kernel buffer.  This blows away all
+ * old states, and is intended to be used only in __fpu__restore_sig(), where
+ * user states are restored from the user buffer.
+ */
+void copy_supervisor_to_kernel(struct xregs_state *xstate)
+{
+	struct xstate_header *header;
+	u64 max_bit, min_bit;
+	u32 lmask, hmask;
+	int err, i;
+
+	if (WARN_ON(!boot_cpu_has(X86_FEATURE_XSAVES)))
+		return;
+
+	if (!xfeatures_mask_supervisor())
+		return;
+
+	max_bit = __fls(xfeatures_mask_supervisor());
+	min_bit = __ffs(xfeatures_mask_supervisor());
+
+	lmask = xfeatures_mask_supervisor();
+	hmask = xfeatures_mask_supervisor() >> 32;
+	XSTATE_OP(XSAVES, xstate, lmask, hmask, err);
+
+	/* We should never fault when copying to a kernel buffer: */
+	if (WARN_ON_FPU(err))
+		return;
+
+	/*
+	 * At this point, the buffer has only supervisor states and must be
+	 * converted back to normal kernel format.
+	 */
+	header = &xstate->header;
+	header->xcomp_bv |= xfeatures_mask_all;
+
+	/*
+	 * This only moves states up in the buffer.  Start with
+	 * the last state and move backwards so that states are
+	 * not overwritten until after they are moved.  Note:
+	 * memmove() allows overlapping src/dst buffers.
+	 */
+	for (i = max_bit; i >= min_bit; i--) {
+		u8 *xbuf = (u8 *)xstate;
+
+		if (!((header->xfeatures >> i) & 1))
+			continue;
+
+		/* Move xfeature 'i' into its normal location */
+		memmove(xbuf + xstate_comp_offsets[i],
+			xbuf + xstate_supervisor_only_offsets[i],
+			xstate_sizes[i]);
+	}
+}
+
+/**
+ * copy_dynamic_supervisor_to_kernel() - Save dynamic supervisor states to
+ *                                       an xsave area
+ * @xstate: A pointer to an xsave area
+ * @mask: Represent the dynamic supervisor features saved into the xsave area
+ *
+ * Only the dynamic supervisor states sets in the mask are saved into the xsave
+ * area (See the comment in XFEATURE_MASK_DYNAMIC for the details of dynamic
+ * supervisor feature). Besides the dynamic supervisor states, the legacy
+ * region and XSAVE header are also saved into the xsave area. The supervisor
+ * features in the XFEATURE_MASK_SUPERVISOR_SUPPORTED and
+ * XFEATURE_MASK_SUPERVISOR_UNSUPPORTED are not saved.
+ *
+ * The xsave area must be 64-bytes aligned.
+ */
+void copy_dynamic_supervisor_to_kernel(struct xregs_state *xstate, u64 mask)
+{
+	u64 dynamic_mask = xfeatures_mask_dynamic() & mask;
+	u32 lmask, hmask;
+	int err;
+
+	if (WARN_ON_FPU(!boot_cpu_has(X86_FEATURE_XSAVES)))
+		return;
+
+	if (WARN_ON_FPU(!dynamic_mask))
+		return;
+
+	lmask = dynamic_mask;
+	hmask = dynamic_mask >> 32;
+
+	XSTATE_OP(XSAVES, xstate, lmask, hmask, err);
+
+	/* Should never fault when copying to a kernel buffer */
+	WARN_ON_FPU(err);
+}
+
+/**
+ * copy_kernel_to_dynamic_supervisor() - Restore dynamic supervisor states from
+ *                                       an xsave area
+ * @xstate: A pointer to an xsave area
+ * @mask: Represent the dynamic supervisor features restored from the xsave area
+ *
+ * Only the dynamic supervisor states sets in the mask are restored from the
+ * xsave area (See the comment in XFEATURE_MASK_DYNAMIC for the details of
+ * dynamic supervisor feature). Besides the dynamic supervisor states, the
+ * legacy region and XSAVE header are also restored from the xsave area. The
+ * supervisor features in the XFEATURE_MASK_SUPERVISOR_SUPPORTED and
+ * XFEATURE_MASK_SUPERVISOR_UNSUPPORTED are not restored.
+ *
+ * The xsave area must be 64-bytes aligned.
+ */
+void copy_kernel_to_dynamic_supervisor(struct xregs_state *xstate, u64 mask)
+{
+	u64 dynamic_mask = xfeatures_mask_dynamic() & mask;
+	u32 lmask, hmask;
+	int err;
+
+	if (WARN_ON_FPU(!boot_cpu_has(X86_FEATURE_XSAVES)))
+		return;
+
+	if (WARN_ON_FPU(!dynamic_mask))
+		return;
+
+	lmask = dynamic_mask;
+	hmask = dynamic_mask >> 32;
+
+	XSTATE_OP(XRSTORS, xstate, lmask, hmask, err);
+
+	/* Should never fault when copying from a kernel buffer */
+	WARN_ON_FPU(err);
+}
+
 #ifdef CONFIG_PROC_PID_ARCH_STATUS
 /*
  * Report the amount of time elapsed in millisecond since last AVX512