diff --git a/arch/x86/crypto/camellia_aesni_avx2_glue.c b/arch/x86/crypto/camellia_aesni_avx2_glue.c
index d844569..c54536d 100644
--- a/arch/x86/crypto/camellia_aesni_avx2_glue.c
+++ b/arch/x86/crypto/camellia_aesni_avx2_glue.c
@@ -206,6 +206,20 @@
 	bool fpu_enabled;
 };
 
+#ifdef CONFIG_PREEMPT_RT_FULL
+static void camellia_fpu_end_rt(struct crypt_priv *ctx)
+{
+       bool fpu_enabled = ctx->fpu_enabled;
+
+       if (!fpu_enabled)
+               return;
+       camellia_fpu_end(fpu_enabled);
+       ctx->fpu_enabled = false;
+}
+#else
+static void camellia_fpu_end_rt(struct crypt_priv *ctx) { }
+#endif
+
 static void encrypt_callback(void *priv, u8 *srcdst, unsigned int nbytes)
 {
 	const unsigned int bsize = CAMELLIA_BLOCK_SIZE;
@@ -221,16 +235,19 @@
 	}
 
 	if (nbytes >= CAMELLIA_AESNI_PARALLEL_BLOCKS * bsize) {
+		kernel_fpu_resched();
 		camellia_ecb_enc_16way(ctx->ctx, srcdst, srcdst);
 		srcdst += bsize * CAMELLIA_AESNI_PARALLEL_BLOCKS;
 		nbytes -= bsize * CAMELLIA_AESNI_PARALLEL_BLOCKS;
 	}
 
 	while (nbytes >= CAMELLIA_PARALLEL_BLOCKS * bsize) {
+		kernel_fpu_resched();
 		camellia_enc_blk_2way(ctx->ctx, srcdst, srcdst);
 		srcdst += bsize * CAMELLIA_PARALLEL_BLOCKS;
 		nbytes -= bsize * CAMELLIA_PARALLEL_BLOCKS;
 	}
+	camellia_fpu_end_rt(ctx);
 
 	for (i = 0; i < nbytes / bsize; i++, srcdst += bsize)
 		camellia_enc_blk(ctx->ctx, srcdst, srcdst);
@@ -251,16 +268,19 @@
 	}
 
 	if (nbytes >= CAMELLIA_AESNI_PARALLEL_BLOCKS * bsize) {
+		kernel_fpu_resched();
 		camellia_ecb_dec_16way(ctx->ctx, srcdst, srcdst);
 		srcdst += bsize * CAMELLIA_AESNI_PARALLEL_BLOCKS;
 		nbytes -= bsize * CAMELLIA_AESNI_PARALLEL_BLOCKS;
 	}
 
 	while (nbytes >= CAMELLIA_PARALLEL_BLOCKS * bsize) {
+		kernel_fpu_resched();
 		camellia_dec_blk_2way(ctx->ctx, srcdst, srcdst);
 		srcdst += bsize * CAMELLIA_PARALLEL_BLOCKS;
 		nbytes -= bsize * CAMELLIA_PARALLEL_BLOCKS;
 	}
+	camellia_fpu_end_rt(ctx);
 
 	for (i = 0; i < nbytes / bsize; i++, srcdst += bsize)
 		camellia_dec_blk(ctx->ctx, srcdst, srcdst);
diff --git a/arch/x86/crypto/camellia_aesni_avx_glue.c b/arch/x86/crypto/camellia_aesni_avx_glue.c
index 93d8f29..a1666a5 100644
--- a/arch/x86/crypto/camellia_aesni_avx_glue.c
+++ b/arch/x86/crypto/camellia_aesni_avx_glue.c
@@ -210,6 +210,21 @@
 	bool fpu_enabled;
 };
 
+#ifdef CONFIG_PREEMPT_RT_FULL
+static void camellia_fpu_end_rt(struct crypt_priv *ctx)
+{
+	bool fpu_enabled = ctx->fpu_enabled;
+
+	if (!fpu_enabled)
+		return;
+	camellia_fpu_end(fpu_enabled);
+	ctx->fpu_enabled = false;
+}
+
+#else
+static void camellia_fpu_end_rt(struct crypt_priv *ctx) { }
+#endif
+
 static void encrypt_callback(void *priv, u8 *srcdst, unsigned int nbytes)
 {
 	const unsigned int bsize = CAMELLIA_BLOCK_SIZE;
@@ -225,10 +240,12 @@
 	}
 
 	while (nbytes >= CAMELLIA_PARALLEL_BLOCKS * bsize) {
+		kernel_fpu_resched();
 		camellia_enc_blk_2way(ctx->ctx, srcdst, srcdst);
 		srcdst += bsize * CAMELLIA_PARALLEL_BLOCKS;
 		nbytes -= bsize * CAMELLIA_PARALLEL_BLOCKS;
 	}
+	camellia_fpu_end_rt(ctx);
 
 	for (i = 0; i < nbytes / bsize; i++, srcdst += bsize)
 		camellia_enc_blk(ctx->ctx, srcdst, srcdst);
@@ -249,10 +266,12 @@
 	}
 
 	while (nbytes >= CAMELLIA_PARALLEL_BLOCKS * bsize) {
+		kernel_fpu_resched();
 		camellia_dec_blk_2way(ctx->ctx, srcdst, srcdst);
 		srcdst += bsize * CAMELLIA_PARALLEL_BLOCKS;
 		nbytes -= bsize * CAMELLIA_PARALLEL_BLOCKS;
 	}
+	camellia_fpu_end_rt(ctx);
 
 	for (i = 0; i < nbytes / bsize; i++, srcdst += bsize)
 		camellia_dec_blk(ctx->ctx, srcdst, srcdst);
diff --git a/arch/x86/crypto/cast6_avx_glue.c b/arch/x86/crypto/cast6_avx_glue.c
index fca4595..9eb469b9 100644
--- a/arch/x86/crypto/cast6_avx_glue.c
+++ b/arch/x86/crypto/cast6_avx_glue.c
@@ -205,19 +205,33 @@
 	bool fpu_enabled;
 };
 
+#ifdef CONFIG_PREEMPT_RT_FULL
+static void cast6_fpu_end_rt(struct crypt_priv *ctx)
+{
+	bool fpu_enabled = ctx->fpu_enabled;
+
+	if (!fpu_enabled)
+		return;
+	cast6_fpu_end(fpu_enabled);
+	ctx->fpu_enabled = false;
+}
+
+#else
+static void cast6_fpu_end_rt(struct crypt_priv *ctx) { }
+#endif
+
 static void encrypt_callback(void *priv, u8 *srcdst, unsigned int nbytes)
 {
 	const unsigned int bsize = CAST6_BLOCK_SIZE;
 	struct crypt_priv *ctx = priv;
 	int i;
 
-	ctx->fpu_enabled = cast6_fpu_begin(ctx->fpu_enabled, nbytes);
-
 	if (nbytes == bsize * CAST6_PARALLEL_BLOCKS) {
+		ctx->fpu_enabled = cast6_fpu_begin(ctx->fpu_enabled, nbytes);
 		cast6_ecb_enc_8way(ctx->ctx, srcdst, srcdst);
+		cast6_fpu_end_rt(ctx);
 		return;
 	}
-
 	for (i = 0; i < nbytes / bsize; i++, srcdst += bsize)
 		__cast6_encrypt(ctx->ctx, srcdst, srcdst);
 }
@@ -228,10 +242,10 @@
 	struct crypt_priv *ctx = priv;
 	int i;
 
-	ctx->fpu_enabled = cast6_fpu_begin(ctx->fpu_enabled, nbytes);
-
 	if (nbytes == bsize * CAST6_PARALLEL_BLOCKS) {
+		ctx->fpu_enabled = cast6_fpu_begin(ctx->fpu_enabled, nbytes);
 		cast6_ecb_dec_8way(ctx->ctx, srcdst, srcdst);
+		cast6_fpu_end_rt(ctx);
 		return;
 	}
 
diff --git a/arch/x86/crypto/chacha20_glue.c b/arch/x86/crypto/chacha20_glue.c
index 722bace..0e3eb53 100644
--- a/arch/x86/crypto/chacha20_glue.c
+++ b/arch/x86/crypto/chacha20_glue.c
@@ -80,22 +80,24 @@
 
 	crypto_chacha20_init(state, crypto_blkcipher_ctx(desc->tfm), walk.iv);
 
-	kernel_fpu_begin();
-
 	while (walk.nbytes >= CHACHA20_BLOCK_SIZE) {
+		kernel_fpu_begin();
+
 		chacha20_dosimd(state, walk.dst.virt.addr, walk.src.virt.addr,
 				rounddown(walk.nbytes, CHACHA20_BLOCK_SIZE));
+		kernel_fpu_end();
 		err = blkcipher_walk_done(desc, &walk,
 					  walk.nbytes % CHACHA20_BLOCK_SIZE);
 	}
 
 	if (walk.nbytes) {
+		kernel_fpu_begin();
 		chacha20_dosimd(state, walk.dst.virt.addr, walk.src.virt.addr,
 				walk.nbytes);
+		kernel_fpu_end();
 		err = blkcipher_walk_done(desc, &walk, 0);
 	}
 
-	kernel_fpu_end();
 
 	return err;
 }
diff --git a/arch/x86/crypto/serpent_avx2_glue.c b/arch/x86/crypto/serpent_avx2_glue.c
index 6d19834..0954bae 100644
--- a/arch/x86/crypto/serpent_avx2_glue.c
+++ b/arch/x86/crypto/serpent_avx2_glue.c
@@ -184,6 +184,21 @@
 	bool fpu_enabled;
 };
 
+#ifdef CONFIG_PREEMPT_RT_FULL
+static void serpent_fpu_end_rt(struct crypt_priv *ctx)
+{
+       bool fpu_enabled = ctx->fpu_enabled;
+
+       if (!fpu_enabled)
+               return;
+       serpent_fpu_end(fpu_enabled);
+       ctx->fpu_enabled = false;
+}
+
+#else
+static void serpent_fpu_end_rt(struct crypt_priv *ctx) { }
+#endif
+
 static void encrypt_callback(void *priv, u8 *srcdst, unsigned int nbytes)
 {
 	const unsigned int bsize = SERPENT_BLOCK_SIZE;
@@ -199,10 +214,12 @@
 	}
 
 	while (nbytes >= SERPENT_PARALLEL_BLOCKS * bsize) {
+		kernel_fpu_resched();
 		serpent_ecb_enc_8way_avx(ctx->ctx, srcdst, srcdst);
 		srcdst += bsize * SERPENT_PARALLEL_BLOCKS;
 		nbytes -= bsize * SERPENT_PARALLEL_BLOCKS;
 	}
+	serpent_fpu_end_rt(ctx);
 
 	for (i = 0; i < nbytes / bsize; i++, srcdst += bsize)
 		__serpent_encrypt(ctx->ctx, srcdst, srcdst);
@@ -223,10 +240,12 @@
 	}
 
 	while (nbytes >= SERPENT_PARALLEL_BLOCKS * bsize) {
+		kernel_fpu_resched();
 		serpent_ecb_dec_8way_avx(ctx->ctx, srcdst, srcdst);
 		srcdst += bsize * SERPENT_PARALLEL_BLOCKS;
 		nbytes -= bsize * SERPENT_PARALLEL_BLOCKS;
 	}
+	serpent_fpu_end_rt(ctx);
 
 	for (i = 0; i < nbytes / bsize; i++, srcdst += bsize)
 		__serpent_decrypt(ctx->ctx, srcdst, srcdst);
diff --git a/arch/x86/crypto/serpent_avx_glue.c b/arch/x86/crypto/serpent_avx_glue.c
index 5dc3702..8c812a0 100644
--- a/arch/x86/crypto/serpent_avx_glue.c
+++ b/arch/x86/crypto/serpent_avx_glue.c
@@ -218,16 +218,31 @@
 	bool fpu_enabled;
 };
 
+#ifdef CONFIG_PREEMPT_RT_FULL
+static void serpent_fpu_end_rt(struct crypt_priv *ctx)
+{
+	bool fpu_enabled = ctx->fpu_enabled;
+
+	if (!fpu_enabled)
+		return;
+	serpent_fpu_end(fpu_enabled);
+	ctx->fpu_enabled = false;
+}
+
+#else
+static void serpent_fpu_end_rt(struct crypt_priv *ctx) { }
+#endif
+
 static void encrypt_callback(void *priv, u8 *srcdst, unsigned int nbytes)
 {
 	const unsigned int bsize = SERPENT_BLOCK_SIZE;
 	struct crypt_priv *ctx = priv;
 	int i;
 
-	ctx->fpu_enabled = serpent_fpu_begin(ctx->fpu_enabled, nbytes);
-
 	if (nbytes == bsize * SERPENT_PARALLEL_BLOCKS) {
+		ctx->fpu_enabled = serpent_fpu_begin(ctx->fpu_enabled, nbytes);
 		serpent_ecb_enc_8way_avx(ctx->ctx, srcdst, srcdst);
+		serpent_fpu_end_rt(ctx);
 		return;
 	}
 
@@ -241,10 +256,10 @@
 	struct crypt_priv *ctx = priv;
 	int i;
 
-	ctx->fpu_enabled = serpent_fpu_begin(ctx->fpu_enabled, nbytes);
-
 	if (nbytes == bsize * SERPENT_PARALLEL_BLOCKS) {
+		ctx->fpu_enabled = serpent_fpu_begin(ctx->fpu_enabled, nbytes);
 		serpent_ecb_dec_8way_avx(ctx->ctx, srcdst, srcdst);
+		serpent_fpu_end_rt(ctx);
 		return;
 	}
 
diff --git a/arch/x86/crypto/serpent_sse2_glue.c b/arch/x86/crypto/serpent_sse2_glue.c
index 3643dd5..1ef09f8 100644
--- a/arch/x86/crypto/serpent_sse2_glue.c
+++ b/arch/x86/crypto/serpent_sse2_glue.c
@@ -187,16 +187,31 @@
 	bool fpu_enabled;
 };
 
+#ifdef CONFIG_PREEMPT_RT_FULL
+static void serpent_fpu_end_rt(struct crypt_priv *ctx)
+{
+	bool fpu_enabled = ctx->fpu_enabled;
+
+	if (!fpu_enabled)
+		return;
+	serpent_fpu_end(fpu_enabled);
+	ctx->fpu_enabled = false;
+}
+
+#else
+static void serpent_fpu_end_rt(struct crypt_priv *ctx) { }
+#endif
+
 static void encrypt_callback(void *priv, u8 *srcdst, unsigned int nbytes)
 {
 	const unsigned int bsize = SERPENT_BLOCK_SIZE;
 	struct crypt_priv *ctx = priv;
 	int i;
 
-	ctx->fpu_enabled = serpent_fpu_begin(ctx->fpu_enabled, nbytes);
-
 	if (nbytes == bsize * SERPENT_PARALLEL_BLOCKS) {
+		ctx->fpu_enabled = serpent_fpu_begin(ctx->fpu_enabled, nbytes);
 		serpent_enc_blk_xway(ctx->ctx, srcdst, srcdst);
+		serpent_fpu_end_rt(ctx);
 		return;
 	}
 
@@ -210,10 +225,10 @@
 	struct crypt_priv *ctx = priv;
 	int i;
 
-	ctx->fpu_enabled = serpent_fpu_begin(ctx->fpu_enabled, nbytes);
-
 	if (nbytes == bsize * SERPENT_PARALLEL_BLOCKS) {
+		ctx->fpu_enabled = serpent_fpu_begin(ctx->fpu_enabled, nbytes);
 		serpent_dec_blk_xway(ctx->ctx, srcdst, srcdst);
+		serpent_fpu_end_rt(ctx);
 		return;
 	}
 
diff --git a/arch/x86/crypto/twofish_avx_glue.c b/arch/x86/crypto/twofish_avx_glue.c
index b7a3904..de00fe2 100644
--- a/arch/x86/crypto/twofish_avx_glue.c
+++ b/arch/x86/crypto/twofish_avx_glue.c
@@ -218,6 +218,21 @@
 	bool fpu_enabled;
 };
 
+#ifdef CONFIG_PREEMPT_RT_FULL
+static void twofish_fpu_end_rt(struct crypt_priv *ctx)
+{
+	bool fpu_enabled = ctx->fpu_enabled;
+
+	if (!fpu_enabled)
+		return;
+	twofish_fpu_end(fpu_enabled);
+	ctx->fpu_enabled = false;
+}
+
+#else
+static void twofish_fpu_end_rt(struct crypt_priv *ctx) { }
+#endif
+
 static void encrypt_callback(void *priv, u8 *srcdst, unsigned int nbytes)
 {
 	const unsigned int bsize = TF_BLOCK_SIZE;
@@ -228,12 +243,16 @@
 
 	if (nbytes == bsize * TWOFISH_PARALLEL_BLOCKS) {
 		twofish_ecb_enc_8way(ctx->ctx, srcdst, srcdst);
+		twofish_fpu_end_rt(ctx);
 		return;
 	}
 
-	for (i = 0; i < nbytes / (bsize * 3); i++, srcdst += bsize * 3)
+	for (i = 0; i < nbytes / (bsize * 3); i++, srcdst += bsize * 3) {
+		kernel_fpu_resched();
 		twofish_enc_blk_3way(ctx->ctx, srcdst, srcdst);
+	}
 
+	twofish_fpu_end_rt(ctx);
 	nbytes %= bsize * 3;
 
 	for (i = 0; i < nbytes / bsize; i++, srcdst += bsize)
@@ -250,11 +269,15 @@
 
 	if (nbytes == bsize * TWOFISH_PARALLEL_BLOCKS) {
 		twofish_ecb_dec_8way(ctx->ctx, srcdst, srcdst);
+		twofish_fpu_end_rt(ctx);
 		return;
 	}
 
-	for (i = 0; i < nbytes / (bsize * 3); i++, srcdst += bsize * 3)
+	for (i = 0; i < nbytes / (bsize * 3); i++, srcdst += bsize * 3) {
+		kernel_fpu_resched();
 		twofish_dec_blk_3way(ctx->ctx, srcdst, srcdst);
+	}
+	twofish_fpu_end_rt(ctx);
 
 	nbytes %= bsize * 3;
 
diff --git a/arch/x86/include/asm/fpu/api.h b/arch/x86/include/asm/fpu/api.h
index 1429a7c..85428df 100644
--- a/arch/x86/include/asm/fpu/api.h
+++ b/arch/x86/include/asm/fpu/api.h
@@ -24,6 +24,7 @@
 extern void __kernel_fpu_end(void);
 extern void kernel_fpu_begin(void);
 extern void kernel_fpu_end(void);
+extern void kernel_fpu_resched(void);
 extern bool irq_fpu_usable(void);
 
 /*
diff --git a/arch/x86/kernel/fpu/core.c b/arch/x86/kernel/fpu/core.c
index d25097c..67ae18a 100644
--- a/arch/x86/kernel/fpu/core.c
+++ b/arch/x86/kernel/fpu/core.c
@@ -149,6 +149,18 @@
 }
 EXPORT_SYMBOL_GPL(kernel_fpu_end);
 
+void kernel_fpu_resched(void)
+{
+	WARN_ON_FPU(!this_cpu_read(in_kernel_fpu));
+
+	if (should_resched(PREEMPT_OFFSET)) {
+		kernel_fpu_end();
+		cond_resched();
+		kernel_fpu_begin();
+	}
+}
+EXPORT_SYMBOL_GPL(kernel_fpu_resched);
+
 /*
  * CR0::TS save/restore functions:
  */