diff --git a/arch/x86/kernel/fpu/xstate.c b/arch/x86/kernel/fpu/xstate.c
index 80dcf0417f30..80836b94189e 100644
--- a/arch/x86/kernel/fpu/xstate.c
+++ b/arch/x86/kernel/fpu/xstate.c
@@ -1084,20 +1084,10 @@ static inline bool xfeatures_mxcsr_quirk(u64 xfeatures)
 	return true;
 }
 
-static void fill_gap(struct membuf *to, unsigned *last, unsigned offset)
+static void copy_feature(bool from_xstate, struct membuf *to, void *xstate,
+			 void *init_xstate, unsigned int size)
 {
-	if (*last >= offset)
-		return;
-	membuf_write(to, (void *)&init_fpstate.xsave + *last, offset - *last);
-	*last = offset;
-}
-
-static void copy_part(struct membuf *to, unsigned *last, unsigned offset,
-		      unsigned size, void *from)
-{
-	fill_gap(to, last, offset);
-	membuf_write(to, from, size);
-	*last = offset + size;
+	membuf_write(to, from_xstate ? xstate : init_xstate, size);
 }
 
 /*
@@ -1109,10 +1099,10 @@ static void copy_part(struct membuf *to, unsigned *last, unsigned offset,
  */
 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 size = to.left;
-	unsigned last = 0;
+	unsigned int zerofrom;
 	int i;
 
 	/*
@@ -1122,41 +1112,68 @@ void copy_xstate_to_kernel(struct membuf to, struct xregs_state *xsave)
 	header.xfeatures = xsave->header.xfeatures;
 	header.xfeatures &= xfeatures_mask_user();
 
-	if (header.xfeatures & XFEATURE_MASK_FP)
-		copy_part(&to, &last, 0, off_mxcsr, &xsave->i387);
-	if (header.xfeatures & (XFEATURE_MASK_SSE | XFEATURE_MASK_YMM))
-		copy_part(&to, &last, off_mxcsr,
-			  MXCSR_AND_FLAGS_SIZE, &xsave->i387.mxcsr);
-	if (header.xfeatures & XFEATURE_MASK_FP)
-		copy_part(&to, &last, offsetof(struct fxregs_state, st_space),
-			  128, &xsave->i387.st_space);
-	if (header.xfeatures & XFEATURE_MASK_SSE)
-		copy_part(&to, &last, xstate_offsets[XFEATURE_SSE],
-			  256, &xsave->i387.xmm_space);
-	/*
-	 * Fill xsave->i387.sw_reserved value for ptrace frame:
-	 */
-	copy_part(&to, &last, offsetof(struct fxregs_state, sw_reserved),
-		  48, xstate_fx_sw_bytes);
-	/*
-	 * Copy xregs_state->header:
-	 */
-	copy_part(&to, &last, offsetof(struct xregs_state, header),
-		  sizeof(header), &header);
+	/* 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(&to, &last, xstate_offsets[i],
-				  xstate_sizes[i], src);
-		}
+		/*
+		 * 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);
 
+		copy_feature(header.xfeatures & BIT_ULL(i), &to,
+			     __raw_xsave_addr(xsave, i),
+			     __raw_xsave_addr(xinit, i),
+			     xstate_sizes[i]);
+
+		/*
+		 * Keep track of the last copied state in the non-compacted
+		 * target buffer for gap zeroing.
+		 */
+		zerofrom = xstate_offsets[i] + xstate_sizes[i];
 	}
-	fill_gap(&to, &last, size);
+
+	if (to.left)
+		membuf_zero(&to, to.left);
 }
 
 /*