diff --git a/BUILD.generated.gni b/BUILD.generated.gni
index 07b6e91..8a29de6 100644
--- a/BUILD.generated.gni
+++ b/BUILD.generated.gni
@@ -60,6 +60,7 @@
   "src/crypto/chacha/chacha.c",
   "src/crypto/cipher_extra/cipher_extra.c",
   "src/crypto/cipher_extra/derive_key.c",
+  "src/crypto/cipher_extra/e_aesccm.c",
   "src/crypto/cipher_extra/e_aesctrhmac.c",
   "src/crypto/cipher_extra/e_aesgcmsiv.c",
   "src/crypto/cipher_extra/e_chacha20poly1305.c",
@@ -74,6 +75,7 @@
   "src/crypto/conf/conf.c",
   "src/crypto/conf/conf_def.h",
   "src/crypto/conf/internal.h",
+  "src/crypto/cpu-aarch64-fuchsia.c",
   "src/crypto/cpu-aarch64-linux.c",
   "src/crypto/cpu-arm-linux.c",
   "src/crypto/cpu-arm.c",
@@ -81,7 +83,6 @@
   "src/crypto/cpu-ppc64le.c",
   "src/crypto/crypto.c",
   "src/crypto/curve25519/spake25519.c",
-  "src/crypto/curve25519/x25519-x86_64.c",
   "src/crypto/dh/check.c",
   "src/crypto/dh/dh.c",
   "src/crypto/dh/dh_asn1.c",
@@ -344,6 +345,7 @@
   "src/ssl/d1_srtp.cc",
   "src/ssl/dtls_method.cc",
   "src/ssl/dtls_record.cc",
+  "src/ssl/handoff.cc",
   "src/ssl/handshake.cc",
   "src/ssl/handshake_client.cc",
   "src/ssl/handshake_server.cc",
@@ -462,7 +464,6 @@
   "linux-x86_64/crypto/fipsmodule/vpaes-x86_64.S",
   "linux-x86_64/crypto/fipsmodule/x86_64-mont.S",
   "linux-x86_64/crypto/fipsmodule/x86_64-mont5.S",
-  "src/crypto/curve25519/asm/x25519-asm-x86_64.S",
 ]
 
 crypto_sources_mac_x86 = [
@@ -499,7 +500,6 @@
   "mac-x86_64/crypto/fipsmodule/vpaes-x86_64.S",
   "mac-x86_64/crypto/fipsmodule/x86_64-mont.S",
   "mac-x86_64/crypto/fipsmodule/x86_64-mont5.S",
-  "src/crypto/curve25519/asm/x25519-asm-x86_64.S",
 ]
 
 crypto_sources_win_x86 = [
diff --git a/README b/README
index 10a7e7a..657a5d6 100644
--- a/README
+++ b/README
@@ -8,7 +8,7 @@
 
 at revision:
 
-a62dbf88d8a3c04446db833a1eb80a620cb1514d
+672f6fc2486745d0cabc3aaeb4e0a3cd13b37b12
 
 To roll boringssl forward, delete all but this file and the above mentioned
 files, checkout the new boringssl into a subdirectory called src/, and run the
diff --git a/err_data.c b/err_data.c
index dbb34a3..4dda17b 100644
--- a/err_data.c
+++ b/err_data.c
@@ -185,43 +185,43 @@
     0x28340c5e,
     0x283480ac,
     0x283500ea,
-    0x2c322cda,
+    0x2c322cf7,
     0x2c3292a5,
-    0x2c332ce8,
-    0x2c33acfa,
-    0x2c342d0e,
-    0x2c34ad20,
-    0x2c352d3b,
-    0x2c35ad4d,
-    0x2c362d60,
+    0x2c332d05,
+    0x2c33ad17,
+    0x2c342d2b,
+    0x2c34ad3d,
+    0x2c352d58,
+    0x2c35ad6a,
+    0x2c362d7d,
     0x2c36832d,
-    0x2c372d6d,
-    0x2c37ad7f,
-    0x2c382da4,
-    0x2c38adbb,
-    0x2c392dc9,
-    0x2c39add9,
-    0x2c3a2deb,
-    0x2c3aadff,
-    0x2c3b2e10,
-    0x2c3bae2f,
+    0x2c372d8a,
+    0x2c37ad9c,
+    0x2c382dc1,
+    0x2c38add8,
+    0x2c392de6,
+    0x2c39adf6,
+    0x2c3a2e08,
+    0x2c3aae1c,
+    0x2c3b2e2d,
+    0x2c3bae4c,
     0x2c3c12b7,
     0x2c3c92cd,
-    0x2c3d2e43,
+    0x2c3d2e60,
     0x2c3d92e6,
-    0x2c3e2e60,
-    0x2c3eae6e,
-    0x2c3f2e86,
-    0x2c3fae9e,
-    0x2c402eab,
+    0x2c3e2e7d,
+    0x2c3eae8b,
+    0x2c3f2ea3,
+    0x2c3faebb,
+    0x2c402ec8,
     0x2c4091b8,
-    0x2c412ebc,
-    0x2c41aecf,
+    0x2c412ed9,
+    0x2c41aeec,
     0x2c42117e,
-    0x2c42aee0,
+    0x2c42aefd,
     0x2c430720,
-    0x2c43ae21,
-    0x2c442d92,
+    0x2c43ae3e,
+    0x2c442daf,
     0x30320000,
     0x30328015,
     0x3033001f,
@@ -448,65 +448,65 @@
     0x405fa21e,
     0x4060222c,
     0x4060a24e,
-    0x40612292,
-    0x4061a2ca,
-    0x406222e1,
-    0x4062a2f2,
-    0x40632303,
-    0x4063a318,
-    0x4064232f,
-    0x4064a35b,
-    0x40652376,
-    0x4065a38d,
-    0x406623a5,
-    0x4066a3cf,
-    0x406723fa,
-    0x4067a41b,
-    0x40682463,
-    0x4068a484,
-    0x406924b6,
-    0x4069a4e4,
-    0x406a2505,
-    0x406aa525,
-    0x406b26ad,
-    0x406ba6d0,
-    0x406c26e6,
-    0x406ca961,
-    0x406d2990,
-    0x406da9b8,
-    0x406e29e6,
-    0x406eaa33,
-    0x406f2a52,
-    0x406faa8a,
-    0x40702a9d,
-    0x4070aaba,
+    0x406122af,
+    0x4061a2e7,
+    0x406222fe,
+    0x4062a30f,
+    0x40632320,
+    0x4063a335,
+    0x4064234c,
+    0x4064a378,
+    0x40652393,
+    0x4065a3aa,
+    0x406623c2,
+    0x4066a3ec,
+    0x40672417,
+    0x4067a438,
+    0x40682480,
+    0x4068a4a1,
+    0x406924d3,
+    0x4069a501,
+    0x406a2522,
+    0x406aa542,
+    0x406b26ca,
+    0x406ba6ed,
+    0x406c2703,
+    0x406ca97e,
+    0x406d29ad,
+    0x406da9d5,
+    0x406e2a03,
+    0x406eaa50,
+    0x406f2a6f,
+    0x406faaa7,
+    0x40702aba,
+    0x4070aad7,
     0x40710800,
-    0x4071aacc,
-    0x40722adf,
-    0x4072aaf8,
-    0x40732b10,
+    0x4071aae9,
+    0x40722afc,
+    0x4072ab15,
+    0x40732b2d,
     0x407394a4,
-    0x40742b24,
-    0x4074ab3e,
-    0x40752b4f,
-    0x4075ab63,
-    0x40762b71,
+    0x40742b41,
+    0x4074ab5b,
+    0x40752b6c,
+    0x4075ab80,
+    0x40762b8e,
     0x4076927b,
-    0x40772b96,
-    0x4077abb8,
-    0x40782bd3,
-    0x4078ac0c,
-    0x40792c23,
-    0x4079ac39,
-    0x407a2c45,
-    0x407aac58,
-    0x407b2c6d,
-    0x407bac7f,
-    0x407c2cb0,
-    0x407cacb9,
-    0x407d249f,
+    0x40772bb3,
+    0x4077abd5,
+    0x40782bf0,
+    0x4078ac29,
+    0x40792c40,
+    0x4079ac56,
+    0x407a2c62,
+    0x407aac75,
+    0x407b2c8a,
+    0x407bac9c,
+    0x407c2ccd,
+    0x407cacd6,
+    0x407d24bc,
     0x407d9eca,
-    0x407e2be8,
+    0x407e2c05,
     0x407ea0a3,
     0x407f1c93,
     0x407f9a53,
@@ -514,66 +514,67 @@
     0x40809cbb,
     0x40811f46,
     0x40819e7b,
-    0x408229d1,
+    0x408229ee,
     0x40829a39,
     0x4083207e,
-    0x4083a340,
+    0x4083a35d,
     0x40841ccf,
     0x4084a0db,
     0x40852160,
     0x4085a276,
     0x408621d2,
     0x40869ee4,
-    0x40872a17,
-    0x4087a2a7,
+    0x40872a34,
+    0x4087a2c4,
     0x40881a9a,
-    0x4088a42e,
+    0x4088a44b,
     0x40891ae9,
     0x40899a76,
-    0x408a2706,
+    0x408a2723,
     0x408a9884,
-    0x408b2c94,
-    0x408baa67,
+    0x408b2cb1,
+    0x408baa84,
     0x408c2170,
     0x408c98a0,
     0x408d1d12,
     0x408d9ce3,
     0x408e1e2c,
     0x408e9fe6,
-    0x408f2442,
-    0x41f425d8,
-    0x41f9266a,
-    0x41fe255d,
-    0x41fea752,
-    0x41ff2843,
-    0x420325f1,
-    0x42082613,
-    0x4208a64f,
-    0x42092541,
-    0x4209a689,
-    0x420a2598,
-    0x420aa578,
-    0x420b25b8,
-    0x420ba631,
-    0x420c285f,
-    0x420ca71f,
-    0x420d2739,
-    0x420da770,
-    0x4212278a,
-    0x42172826,
-    0x4217a7cc,
-    0x421c27ee,
-    0x421f27a9,
-    0x42212876,
-    0x42262809,
-    0x422b2945,
-    0x422ba8f3,
-    0x422c292d,
-    0x422ca8b2,
-    0x422d2891,
-    0x422da912,
-    0x422e28d8,
-    0x422ea9fe,
+    0x408f245f,
+    0x408fa292,
+    0x41f425f5,
+    0x41f92687,
+    0x41fe257a,
+    0x41fea76f,
+    0x41ff2860,
+    0x4203260e,
+    0x42082630,
+    0x4208a66c,
+    0x4209255e,
+    0x4209a6a6,
+    0x420a25b5,
+    0x420aa595,
+    0x420b25d5,
+    0x420ba64e,
+    0x420c287c,
+    0x420ca73c,
+    0x420d2756,
+    0x420da78d,
+    0x421227a7,
+    0x42172843,
+    0x4217a7e9,
+    0x421c280b,
+    0x421f27c6,
+    0x42212893,
+    0x42262826,
+    0x422b2962,
+    0x422ba910,
+    0x422c294a,
+    0x422ca8cf,
+    0x422d28ae,
+    0x422da92f,
+    0x422e28f5,
+    0x422eaa1b,
     0x4432072b,
     0x4432873a,
     0x44330746,
@@ -626,69 +627,69 @@
     0x4c4014c9,
     0x4c4092f7,
     0x4c4114ed,
-    0x50322ef2,
-    0x5032af01,
-    0x50332f0c,
-    0x5033af1c,
-    0x50342f35,
-    0x5034af4f,
-    0x50352f5d,
-    0x5035af73,
-    0x50362f85,
-    0x5036af9b,
-    0x50372fb4,
-    0x5037afc7,
-    0x50382fdf,
-    0x5038aff0,
-    0x50393005,
-    0x5039b019,
-    0x503a3039,
-    0x503ab04f,
-    0x503b3067,
-    0x503bb079,
-    0x503c3095,
-    0x503cb0ac,
-    0x503d30c5,
-    0x503db0db,
-    0x503e30e8,
-    0x503eb0fe,
-    0x503f3110,
+    0x50322f0f,
+    0x5032af1e,
+    0x50332f29,
+    0x5033af39,
+    0x50342f52,
+    0x5034af6c,
+    0x50352f7a,
+    0x5035af90,
+    0x50362fa2,
+    0x5036afb8,
+    0x50372fd1,
+    0x5037afe4,
+    0x50382ffc,
+    0x5038b00d,
+    0x50393022,
+    0x5039b036,
+    0x503a3056,
+    0x503ab06c,
+    0x503b3084,
+    0x503bb096,
+    0x503c30b2,
+    0x503cb0c9,
+    0x503d30e2,
+    0x503db0f8,
+    0x503e3105,
+    0x503eb11b,
+    0x503f312d,
     0x503f8382,
-    0x50403123,
-    0x5040b133,
-    0x5041314d,
-    0x5041b15c,
-    0x50423176,
-    0x5042b193,
-    0x504331a3,
-    0x5043b1b3,
-    0x504431c2,
+    0x50403140,
+    0x5040b150,
+    0x5041316a,
+    0x5041b179,
+    0x50423193,
+    0x5042b1b0,
+    0x504331c0,
+    0x5043b1d0,
+    0x504431df,
     0x5044843f,
-    0x504531d6,
-    0x5045b1f4,
-    0x50463207,
-    0x5046b21d,
-    0x5047322f,
-    0x5047b244,
-    0x5048326a,
-    0x5048b278,
-    0x5049328b,
-    0x5049b2a0,
-    0x504a32b6,
-    0x504ab2c6,
-    0x504b32e6,
-    0x504bb2f9,
-    0x504c331c,
-    0x504cb34a,
-    0x504d335c,
-    0x504db379,
-    0x504e3394,
-    0x504eb3b0,
-    0x504f33c2,
-    0x504fb3d9,
-    0x505033e8,
+    0x504531f3,
+    0x5045b211,
+    0x50463224,
+    0x5046b23a,
+    0x5047324c,
+    0x5047b261,
+    0x50483287,
+    0x5048b295,
+    0x504932a8,
+    0x5049b2bd,
+    0x504a32d3,
+    0x504ab2e3,
+    0x504b3303,
+    0x504bb316,
+    0x504c3339,
+    0x504cb367,
+    0x504d3379,
+    0x504db396,
+    0x504e33b1,
+    0x504eb3cd,
+    0x504f33df,
+    0x504fb3f6,
+    0x50503405,
     0x505086ef,
-    0x505133fb,
+    0x50513418,
     0x58320f3a,
     0x68320efc,
     0x68328c6a,
@@ -1166,6 +1167,7 @@
     "PEER_DID_NOT_RETURN_A_CERTIFICATE\0"
     "PEER_ERROR_UNSUPPORTED_CERTIFICATE_TYPE\0"
     "PRE_SHARED_KEY_MUST_BE_LAST\0"
+    "PRIVATE_KEY_OPERATION_FAILED\0"
     "PROTOCOL_IS_SHUTDOWN\0"
     "PSK_IDENTITY_BINDER_COUNT_MISMATCH\0"
     "PSK_IDENTITY_NOT_FOUND\0"
diff --git a/ios-arm/crypto/fipsmodule/aes-armv4.S b/ios-arm/crypto/fipsmodule/aes-armv4.S
index 8d43e36..9599324 100644
--- a/ios-arm/crypto/fipsmodule/aes-armv4.S
+++ b/ios-arm/crypto/fipsmodule/aes-armv4.S
@@ -179,7 +179,7 @@
 	adr	r3,.
 #endif
 	stmdb	sp!,{r1,r4-r12,lr}
-#ifdef	__APPLE__
+#if defined(__thumb2__) || defined(__APPLE__)
 	adr	r10,AES_Te
 #else
 	sub	r10,r3,#_asm_AES_encrypt-AES_Te	@ Te
@@ -462,7 +462,7 @@
 	mov	lr,r1			@ bits
 	mov	r11,r2			@ key
 
-#ifdef	__APPLE__
+#if defined(__thumb2__) || defined(__APPLE__)
 	adr	r10,AES_Te+1024				@ Te4
 #else
 	sub	r10,r3,#_armv4_AES_set_encrypt_key-AES_Te-1024	@ Te4
@@ -964,7 +964,7 @@
 	adr	r3,.
 #endif
 	stmdb	sp!,{r1,r4-r12,lr}
-#ifdef	__APPLE__
+#if defined(__thumb2__) || defined(__APPLE__)
 	adr	r10,AES_Td
 #else
 	sub	r10,r3,#_asm_AES_decrypt-AES_Td	@ Td
diff --git a/ios-arm/crypto/fipsmodule/bsaes-armv7.S b/ios-arm/crypto/fipsmodule/bsaes-armv7.S
index 5e2ebf0..6a0d4d3 100644
--- a/ios-arm/crypto/fipsmodule/bsaes-armv7.S
+++ b/ios-arm/crypto/fipsmodule/bsaes-armv7.S
@@ -13,8 +13,7 @@
 @ details see http://www.openssl.org/~appro/cryptogams/.
 @
 @ Specific modes and adaptation for Linux kernel by Ard Biesheuvel
-@ <ard.biesheuvel@linaro.org>. Permission to use under GPL terms is
-@ granted.
+@ of Linaro. Permission to use under GPL terms is granted.
 @ ====================================================================
 
 @ Bit-sliced AES for ARM NEON
@@ -48,10 +47,7 @@
 @						<appro@openssl.org>
 
 @ April-August 2013
-@
-@ Add CBC, CTR and XTS subroutines, adapt for kernel use.
-@
-@					<ard.biesheuvel@linaro.org>
+@ Add CBC, CTR and XTS subroutines and adapt for kernel use; courtesy of Ard.
 
 #ifndef __KERNEL__
 # include <openssl/arm_arch.h>
@@ -93,7 +89,7 @@
 _bsaes_decrypt8:
 	adr	r6,.
 	vldmia	r4!, {q9}		@ round 0 key
-#ifdef	__APPLE__
+#if defined(__thumb2__) || defined(__APPLE__)
 	adr	r6,LM0ISR
 #else
 	add	r6,r6,#LM0ISR-_bsaes_decrypt8
@@ -586,7 +582,7 @@
 _bsaes_encrypt8:
 	adr	r6,.
 	vldmia	r4!, {q9}		@ round 0 key
-#ifdef	__APPLE__
+#if defined(__thumb2__) || defined(__APPLE__)
 	adr	r6,LM0SR
 #else
 	sub	r6,r6,#_bsaes_encrypt8-LM0SR
@@ -1023,7 +1019,7 @@
 _bsaes_key_convert:
 	adr	r6,.
 	vld1.8	{q7},  [r4]!		@ load round 0 key
-#ifdef	__APPLE__
+#if defined(__thumb2__) || defined(__APPLE__)
 	adr	r6,LM0
 #else
 	sub	r6,r6,#_bsaes_key_convert-LM0
diff --git a/linux-arm/crypto/fipsmodule/aes-armv4.S b/linux-arm/crypto/fipsmodule/aes-armv4.S
index 5e49e08..3e2c97b 100644
--- a/linux-arm/crypto/fipsmodule/aes-armv4.S
+++ b/linux-arm/crypto/fipsmodule/aes-armv4.S
@@ -178,7 +178,7 @@
 	adr	r3,.
 #endif
 	stmdb	sp!,{r1,r4-r12,lr}
-#ifdef	__APPLE__
+#if defined(__thumb2__) || defined(__APPLE__)
 	adr	r10,AES_Te
 #else
 	sub	r10,r3,#asm_AES_encrypt-AES_Te	@ Te
@@ -457,7 +457,7 @@
 	mov	lr,r1			@ bits
 	mov	r11,r2			@ key
 
-#ifdef	__APPLE__
+#if defined(__thumb2__) || defined(__APPLE__)
 	adr	r10,AES_Te+1024				@ Te4
 #else
 	sub	r10,r3,#_armv4_AES_set_encrypt_key-AES_Te-1024	@ Te4
@@ -953,7 +953,7 @@
 	adr	r3,.
 #endif
 	stmdb	sp!,{r1,r4-r12,lr}
-#ifdef	__APPLE__
+#if defined(__thumb2__) || defined(__APPLE__)
 	adr	r10,AES_Td
 #else
 	sub	r10,r3,#asm_AES_decrypt-AES_Td	@ Td
diff --git a/linux-arm/crypto/fipsmodule/bsaes-armv7.S b/linux-arm/crypto/fipsmodule/bsaes-armv7.S
index f9c6de7..a0b1e82 100644
--- a/linux-arm/crypto/fipsmodule/bsaes-armv7.S
+++ b/linux-arm/crypto/fipsmodule/bsaes-armv7.S
@@ -14,8 +14,7 @@
 @ details see http://www.openssl.org/~appro/cryptogams/.
 @
 @ Specific modes and adaptation for Linux kernel by Ard Biesheuvel
-@ <ard.biesheuvel@linaro.org>. Permission to use under GPL terms is
-@ granted.
+@ of Linaro. Permission to use under GPL terms is granted.
 @ ====================================================================
 
 @ Bit-sliced AES for ARM NEON
@@ -49,10 +48,7 @@
 @						<appro@openssl.org>
 
 @ April-August 2013
-@
-@ Add CBC, CTR and XTS subroutines, adapt for kernel use.
-@
-@					<ard.biesheuvel@linaro.org>
+@ Add CBC, CTR and XTS subroutines and adapt for kernel use; courtesy of Ard.
 
 #ifndef __KERNEL__
 # include <openssl/arm_arch.h>
@@ -92,7 +88,7 @@
 _bsaes_decrypt8:
 	adr	r6,.
 	vldmia	r4!, {q9}		@ round 0 key
-#ifdef	__APPLE__
+#if defined(__thumb2__) || defined(__APPLE__)
 	adr	r6,.LM0ISR
 #else
 	add	r6,r6,#.LM0ISR-_bsaes_decrypt8
@@ -583,7 +579,7 @@
 _bsaes_encrypt8:
 	adr	r6,.
 	vldmia	r4!, {q9}		@ round 0 key
-#ifdef	__APPLE__
+#if defined(__thumb2__) || defined(__APPLE__)
 	adr	r6,.LM0SR
 #else
 	sub	r6,r6,#_bsaes_encrypt8-.LM0SR
@@ -1018,7 +1014,7 @@
 _bsaes_key_convert:
 	adr	r6,.
 	vld1.8	{q7},  [r4]!		@ load round 0 key
-#ifdef	__APPLE__
+#if defined(__thumb2__) || defined(__APPLE__)
 	adr	r6,.LM0
 #else
 	sub	r6,r6,#_bsaes_key_convert-.LM0
diff --git a/linux-x86_64/crypto/fipsmodule/aes-x86_64.S b/linux-x86_64/crypto/fipsmodule/aes-x86_64.S
index ff87f98..0928c17 100644
--- a/linux-x86_64/crypto/fipsmodule/aes-x86_64.S
+++ b/linux-x86_64/crypto/fipsmodule/aes-x86_64.S
@@ -332,13 +332,21 @@
 .type	asm_AES_encrypt,@function
 .hidden	asm_AES_encrypt
 asm_AES_encrypt:
+.cfi_startproc	
 	movq	%rsp,%rax
+.cfi_def_cfa_register	%rax
 	pushq	%rbx
+.cfi_offset	%rbx,-16
 	pushq	%rbp
+.cfi_offset	%rbp,-24
 	pushq	%r12
+.cfi_offset	%r12,-32
 	pushq	%r13
+.cfi_offset	%r13,-40
 	pushq	%r14
+.cfi_offset	%r14,-48
 	pushq	%r15
+.cfi_offset	%r15,-56
 
 
 	leaq	-63(%rdx),%rcx
@@ -351,6 +359,7 @@
 
 	movq	%rsi,16(%rsp)
 	movq	%rax,24(%rsp)
+.cfi_escape	0x0f,0x05,0x77,0x18,0x06,0x23,0x08
 .Lenc_prologue:
 
 	movq	%rdx,%r15
@@ -377,20 +386,29 @@
 
 	movq	16(%rsp),%r9
 	movq	24(%rsp),%rsi
+.cfi_def_cfa	%rsi,8
 	movl	%eax,0(%r9)
 	movl	%ebx,4(%r9)
 	movl	%ecx,8(%r9)
 	movl	%edx,12(%r9)
 
 	movq	-48(%rsi),%r15
+.cfi_restore	%r15
 	movq	-40(%rsi),%r14
+.cfi_restore	%r14
 	movq	-32(%rsi),%r13
+.cfi_restore	%r13
 	movq	-24(%rsi),%r12
+.cfi_restore	%r12
 	movq	-16(%rsi),%rbp
+.cfi_restore	%rbp
 	movq	-8(%rsi),%rbx
+.cfi_restore	%rbx
 	leaq	(%rsi),%rsp
+.cfi_def_cfa_register	%rsp
 .Lenc_epilogue:
 	.byte	0xf3,0xc3
+.cfi_endproc	
 .size	asm_AES_encrypt,.-asm_AES_encrypt
 .type	_x86_64_AES_decrypt,@function
 .align	16
@@ -778,13 +796,21 @@
 .type	asm_AES_decrypt,@function
 .hidden	asm_AES_decrypt
 asm_AES_decrypt:
+.cfi_startproc	
 	movq	%rsp,%rax
+.cfi_def_cfa_register	%rax
 	pushq	%rbx
+.cfi_offset	%rbx,-16
 	pushq	%rbp
+.cfi_offset	%rbp,-24
 	pushq	%r12
+.cfi_offset	%r12,-32
 	pushq	%r13
+.cfi_offset	%r13,-40
 	pushq	%r14
+.cfi_offset	%r14,-48
 	pushq	%r15
+.cfi_offset	%r15,-56
 
 
 	leaq	-63(%rdx),%rcx
@@ -797,6 +823,7 @@
 
 	movq	%rsi,16(%rsp)
 	movq	%rax,24(%rsp)
+.cfi_escape	0x0f,0x05,0x77,0x18,0x06,0x23,0x08
 .Ldec_prologue:
 
 	movq	%rdx,%r15
@@ -825,42 +852,69 @@
 
 	movq	16(%rsp),%r9
 	movq	24(%rsp),%rsi
+.cfi_def_cfa	%rsi,8
 	movl	%eax,0(%r9)
 	movl	%ebx,4(%r9)
 	movl	%ecx,8(%r9)
 	movl	%edx,12(%r9)
 
 	movq	-48(%rsi),%r15
+.cfi_restore	%r15
 	movq	-40(%rsi),%r14
+.cfi_restore	%r14
 	movq	-32(%rsi),%r13
+.cfi_restore	%r13
 	movq	-24(%rsi),%r12
+.cfi_restore	%r12
 	movq	-16(%rsi),%rbp
+.cfi_restore	%rbp
 	movq	-8(%rsi),%rbx
+.cfi_restore	%rbx
 	leaq	(%rsi),%rsp
+.cfi_def_cfa_register	%rsp
 .Ldec_epilogue:
 	.byte	0xf3,0xc3
+.cfi_endproc	
 .size	asm_AES_decrypt,.-asm_AES_decrypt
 .align	16
 .globl	asm_AES_set_encrypt_key
 .hidden asm_AES_set_encrypt_key
 .type	asm_AES_set_encrypt_key,@function
 asm_AES_set_encrypt_key:
+.cfi_startproc	
 	pushq	%rbx
+.cfi_adjust_cfa_offset	8
+.cfi_offset	%rbx,-16
 	pushq	%rbp
+.cfi_adjust_cfa_offset	8
+.cfi_offset	%rbp,-24
 	pushq	%r12
+.cfi_adjust_cfa_offset	8
+.cfi_offset	%r12,-32
 	pushq	%r13
+.cfi_adjust_cfa_offset	8
+.cfi_offset	%r13,-40
 	pushq	%r14
+.cfi_adjust_cfa_offset	8
+.cfi_offset	%r14,-48
 	pushq	%r15
+.cfi_adjust_cfa_offset	8
+.cfi_offset	%r15,-56
 	subq	$8,%rsp
+.cfi_adjust_cfa_offset	8
 .Lenc_key_prologue:
 
 	call	_x86_64_AES_set_encrypt_key
 
 	movq	40(%rsp),%rbp
+.cfi_restore	%rbp
 	movq	48(%rsp),%rbx
+.cfi_restore	%rbx
 	addq	$56,%rsp
+.cfi_adjust_cfa_offset	-56
 .Lenc_key_epilogue:
 	.byte	0xf3,0xc3
+.cfi_endproc	
 .size	asm_AES_set_encrypt_key,.-asm_AES_set_encrypt_key
 
 .type	_x86_64_AES_set_encrypt_key,@function
@@ -1107,13 +1161,27 @@
 .hidden asm_AES_set_decrypt_key
 .type	asm_AES_set_decrypt_key,@function
 asm_AES_set_decrypt_key:
+.cfi_startproc	
 	pushq	%rbx
+.cfi_adjust_cfa_offset	8
+.cfi_offset	%rbx,-16
 	pushq	%rbp
+.cfi_adjust_cfa_offset	8
+.cfi_offset	%rbp,-24
 	pushq	%r12
+.cfi_adjust_cfa_offset	8
+.cfi_offset	%r12,-32
 	pushq	%r13
+.cfi_adjust_cfa_offset	8
+.cfi_offset	%r13,-40
 	pushq	%r14
+.cfi_adjust_cfa_offset	8
+.cfi_offset	%r14,-48
 	pushq	%r15
+.cfi_adjust_cfa_offset	8
+.cfi_offset	%r15,-56
 	pushq	%rdx
+.cfi_adjust_cfa_offset	8
 .Ldec_key_prologue:
 
 	call	_x86_64_AES_set_encrypt_key
@@ -1281,14 +1349,22 @@
 	xorq	%rax,%rax
 .Labort:
 	movq	8(%rsp),%r15
+.cfi_restore	%r15
 	movq	16(%rsp),%r14
+.cfi_restore	%r14
 	movq	24(%rsp),%r13
+.cfi_restore	%r13
 	movq	32(%rsp),%r12
+.cfi_restore	%r12
 	movq	40(%rsp),%rbp
+.cfi_restore	%rbp
 	movq	48(%rsp),%rbx
+.cfi_restore	%rbx
 	addq	$56,%rsp
+.cfi_adjust_cfa_offset	-56
 .Ldec_key_epilogue:
 	.byte	0xf3,0xc3
+.cfi_endproc	
 .size	asm_AES_set_decrypt_key,.-asm_AES_set_decrypt_key
 .align	16
 .globl	asm_AES_cbc_encrypt
@@ -1298,15 +1374,30 @@
 .hidden OPENSSL_ia32cap_P
 .hidden	asm_AES_cbc_encrypt
 asm_AES_cbc_encrypt:
+.cfi_startproc	
 	cmpq	$0,%rdx
 	je	.Lcbc_epilogue
 	pushfq
+.cfi_adjust_cfa_offset	8
+.cfi_offset	49,-16
 	pushq	%rbx
+.cfi_adjust_cfa_offset	8
+.cfi_offset	%rbx,-24
 	pushq	%rbp
+.cfi_adjust_cfa_offset	8
+.cfi_offset	%rbp,-32
 	pushq	%r12
+.cfi_adjust_cfa_offset	8
+.cfi_offset	%r12,-40
 	pushq	%r13
+.cfi_adjust_cfa_offset	8
+.cfi_offset	%r13,-48
 	pushq	%r14
+.cfi_adjust_cfa_offset	8
+.cfi_offset	%r14,-56
 	pushq	%r15
+.cfi_adjust_cfa_offset	8
+.cfi_offset	%r15,-64
 .Lcbc_prologue:
 
 	cld
@@ -1352,8 +1443,10 @@
 .Lcbc_te_ok:
 
 	xchgq	%rsp,%r15
+.cfi_def_cfa_register	%r15
 
 	movq	%r15,16(%rsp)
+.cfi_escape	0x0f,0x05,0x77,0x10,0x06,0x23,0x40
 .Lcbc_fast_body:
 	movq	%rdi,24(%rsp)
 	movq	%rsi,32(%rsp)
@@ -1735,17 +1828,28 @@
 .align	16
 .Lcbc_exit:
 	movq	16(%rsp),%rsi
+.cfi_def_cfa	%rsi,64
 	movq	(%rsi),%r15
+.cfi_restore	%r15
 	movq	8(%rsi),%r14
+.cfi_restore	%r14
 	movq	16(%rsi),%r13
+.cfi_restore	%r13
 	movq	24(%rsi),%r12
+.cfi_restore	%r12
 	movq	32(%rsi),%rbp
+.cfi_restore	%rbp
 	movq	40(%rsi),%rbx
+.cfi_restore	%rbx
 	leaq	48(%rsi),%rsp
+.cfi_def_cfa	%rsp,16
 .Lcbc_popfq:
 	popfq
+.cfi_adjust_cfa_offset	-8
+.cfi_restore	49
 .Lcbc_epilogue:
 	.byte	0xf3,0xc3
+.cfi_endproc	
 .size	asm_AES_cbc_encrypt,.-asm_AES_cbc_encrypt
 .align	64
 .LAES_Te:
diff --git a/linux-x86_64/crypto/fipsmodule/aesni-x86_64.S b/linux-x86_64/crypto/fipsmodule/aesni-x86_64.S
index 0c980a3..53d594e 100644
--- a/linux-x86_64/crypto/fipsmodule/aesni-x86_64.S
+++ b/linux-x86_64/crypto/fipsmodule/aesni-x86_64.S
@@ -1003,6 +1003,7 @@
 .type	aesni_ctr32_encrypt_blocks,@function
 .align	16
 aesni_ctr32_encrypt_blocks:
+.cfi_startproc	
 	cmpq	$1,%rdx
 	jne	.Lctr32_bulk
 
@@ -1033,7 +1034,9 @@
 .align	16
 .Lctr32_bulk:
 	leaq	(%rsp),%r11
+.cfi_def_cfa_register	%r11
 	pushq	%rbp
+.cfi_offset	%rbp,-16
 	subq	$128,%rsp
 	andq	$-16,%rsp
 
@@ -1568,17 +1571,23 @@
 	movaps	%xmm0,112(%rsp)
 	pxor	%xmm15,%xmm15
 	movq	-8(%r11),%rbp
+.cfi_restore	%rbp
 	leaq	(%r11),%rsp
+.cfi_def_cfa_register	%rsp
 .Lctr32_epilogue:
 	.byte	0xf3,0xc3
+.cfi_endproc	
 .size	aesni_ctr32_encrypt_blocks,.-aesni_ctr32_encrypt_blocks
 .globl	aesni_xts_encrypt
 .hidden aesni_xts_encrypt
 .type	aesni_xts_encrypt,@function
 .align	16
 aesni_xts_encrypt:
+.cfi_startproc	
 	leaq	(%rsp),%r11
+.cfi_def_cfa_register	%r11
 	pushq	%rbp
+.cfi_offset	%rbp,-16
 	subq	$112,%rsp
 	andq	$-16,%rsp
 	movups	(%r9),%xmm2
@@ -2033,17 +2042,23 @@
 	pxor	%xmm14,%xmm14
 	pxor	%xmm15,%xmm15
 	movq	-8(%r11),%rbp
+.cfi_restore	%rbp
 	leaq	(%r11),%rsp
+.cfi_def_cfa_register	%rsp
 .Lxts_enc_epilogue:
 	.byte	0xf3,0xc3
+.cfi_endproc	
 .size	aesni_xts_encrypt,.-aesni_xts_encrypt
 .globl	aesni_xts_decrypt
 .hidden aesni_xts_decrypt
 .type	aesni_xts_decrypt,@function
 .align	16
 aesni_xts_decrypt:
+.cfi_startproc	
 	leaq	(%rsp),%r11
+.cfi_def_cfa_register	%r11
 	pushq	%rbp
+.cfi_offset	%rbp,-16
 	subq	$112,%rsp
 	andq	$-16,%rsp
 	movups	(%r9),%xmm2
@@ -2535,21 +2550,35 @@
 	pxor	%xmm14,%xmm14
 	pxor	%xmm15,%xmm15
 	movq	-8(%r11),%rbp
+.cfi_restore	%rbp
 	leaq	(%r11),%rsp
+.cfi_def_cfa_register	%rsp
 .Lxts_dec_epilogue:
 	.byte	0xf3,0xc3
+.cfi_endproc	
 .size	aesni_xts_decrypt,.-aesni_xts_decrypt
 .globl	aesni_ocb_encrypt
 .hidden aesni_ocb_encrypt
 .type	aesni_ocb_encrypt,@function
 .align	32
 aesni_ocb_encrypt:
+.cfi_startproc	
 	leaq	(%rsp),%rax
 	pushq	%rbx
+.cfi_adjust_cfa_offset	8
+.cfi_offset	%rbx,-16
 	pushq	%rbp
+.cfi_adjust_cfa_offset	8
+.cfi_offset	%rbp,-24
 	pushq	%r12
+.cfi_adjust_cfa_offset	8
+.cfi_offset	%r12,-32
 	pushq	%r13
+.cfi_adjust_cfa_offset	8
+.cfi_offset	%r13,-40
 	pushq	%r14
+.cfi_adjust_cfa_offset	8
+.cfi_offset	%r14,-48
 	movq	8(%rax),%rbx
 	movq	8+8(%rax),%rbp
 
@@ -2726,14 +2755,22 @@
 	pxor	%xmm14,%xmm14
 	pxor	%xmm15,%xmm15
 	leaq	40(%rsp),%rax
+.cfi_def_cfa	%rax,8
 	movq	-40(%rax),%r14
+.cfi_restore	%r14
 	movq	-32(%rax),%r13
+.cfi_restore	%r13
 	movq	-24(%rax),%r12
+.cfi_restore	%r12
 	movq	-16(%rax),%rbp
+.cfi_restore	%rbp
 	movq	-8(%rax),%rbx
+.cfi_restore	%rbx
 	leaq	(%rax),%rsp
+.cfi_def_cfa_register	%rsp
 .Locb_enc_epilogue:
 	.byte	0xf3,0xc3
+.cfi_endproc	
 .size	aesni_ocb_encrypt,.-aesni_ocb_encrypt
 
 .type	__ocb_encrypt6,@function
@@ -2947,12 +2984,23 @@
 .type	aesni_ocb_decrypt,@function
 .align	32
 aesni_ocb_decrypt:
+.cfi_startproc	
 	leaq	(%rsp),%rax
 	pushq	%rbx
+.cfi_adjust_cfa_offset	8
+.cfi_offset	%rbx,-16
 	pushq	%rbp
+.cfi_adjust_cfa_offset	8
+.cfi_offset	%rbp,-24
 	pushq	%r12
+.cfi_adjust_cfa_offset	8
+.cfi_offset	%r12,-32
 	pushq	%r13
+.cfi_adjust_cfa_offset	8
+.cfi_offset	%r13,-40
 	pushq	%r14
+.cfi_adjust_cfa_offset	8
+.cfi_offset	%r14,-48
 	movq	8(%rax),%rbx
 	movq	8+8(%rax),%rbp
 
@@ -3151,14 +3199,22 @@
 	pxor	%xmm14,%xmm14
 	pxor	%xmm15,%xmm15
 	leaq	40(%rsp),%rax
+.cfi_def_cfa	%rax,8
 	movq	-40(%rax),%r14
+.cfi_restore	%r14
 	movq	-32(%rax),%r13
+.cfi_restore	%r13
 	movq	-24(%rax),%r12
+.cfi_restore	%r12
 	movq	-16(%rax),%rbp
+.cfi_restore	%rbp
 	movq	-8(%rax),%rbx
+.cfi_restore	%rbx
 	leaq	(%rax),%rsp
+.cfi_def_cfa_register	%rsp
 .Locb_dec_epilogue:
 	.byte	0xf3,0xc3
+.cfi_endproc	
 .size	aesni_ocb_decrypt,.-aesni_ocb_decrypt
 
 .type	__ocb_decrypt6,@function
@@ -3360,6 +3416,7 @@
 .type	aesni_cbc_encrypt,@function
 .align	16
 aesni_cbc_encrypt:
+.cfi_startproc	
 	testq	%rdx,%rdx
 	jz	.Lcbc_ret
 
@@ -3453,7 +3510,9 @@
 .align	16
 .Lcbc_decrypt_bulk:
 	leaq	(%rsp),%r11
+.cfi_def_cfa_register	%r11
 	pushq	%rbp
+.cfi_offset	%rbp,-16
 	subq	$16,%rsp
 	andq	$-16,%rsp
 	movq	%rcx,%rbp
@@ -3938,16 +3997,21 @@
 	xorps	%xmm0,%xmm0
 	pxor	%xmm1,%xmm1
 	movq	-8(%r11),%rbp
+.cfi_restore	%rbp
 	leaq	(%r11),%rsp
+.cfi_def_cfa_register	%rsp
 .Lcbc_ret:
 	.byte	0xf3,0xc3
+.cfi_endproc	
 .size	aesni_cbc_encrypt,.-aesni_cbc_encrypt
 .globl	aesni_set_decrypt_key
 .hidden aesni_set_decrypt_key
 .type	aesni_set_decrypt_key,@function
 .align	16
 aesni_set_decrypt_key:
+.cfi_startproc	
 .byte	0x48,0x83,0xEC,0x08
+.cfi_adjust_cfa_offset	8
 	call	__aesni_set_encrypt_key
 	shll	$4,%esi
 	testl	%eax,%eax
@@ -3980,7 +4044,9 @@
 	pxor	%xmm0,%xmm0
 .Ldec_key_ret:
 	addq	$8,%rsp
+.cfi_adjust_cfa_offset	-8
 	.byte	0xf3,0xc3
+.cfi_endproc	
 .LSEH_end_set_decrypt_key:
 .size	aesni_set_decrypt_key,.-aesni_set_decrypt_key
 .globl	aesni_set_encrypt_key
@@ -3989,7 +4055,9 @@
 .align	16
 aesni_set_encrypt_key:
 __aesni_set_encrypt_key:
+.cfi_startproc	
 .byte	0x48,0x83,0xEC,0x08
+.cfi_adjust_cfa_offset	8
 	movq	$-1,%rax
 	testq	%rdi,%rdi
 	jz	.Lenc_key_ret
@@ -4283,7 +4351,9 @@
 	pxor	%xmm4,%xmm4
 	pxor	%xmm5,%xmm5
 	addq	$8,%rsp
+.cfi_adjust_cfa_offset	-8
 	.byte	0xf3,0xc3
+.cfi_endproc	
 .LSEH_end_set_encrypt_key:
 
 .align	16
diff --git a/linux-x86_64/crypto/fipsmodule/bsaes-x86_64.S b/linux-x86_64/crypto/fipsmodule/bsaes-x86_64.S
index 04b161c..7c293ef 100644
--- a/linux-x86_64/crypto/fipsmodule/bsaes-x86_64.S
+++ b/linux-x86_64/crypto/fipsmodule/bsaes-x86_64.S
@@ -1072,6 +1072,7 @@
 .type	bsaes_cbc_encrypt,@function
 .align	16
 bsaes_cbc_encrypt:
+.cfi_startproc	
 	cmpl	$0,%r9d
 	jne	asm_AES_cbc_encrypt
 	cmpq	$128,%rdx
@@ -1080,13 +1081,27 @@
 	movq	%rsp,%rax
 .Lcbc_dec_prologue:
 	pushq	%rbp
+.cfi_adjust_cfa_offset	8
+.cfi_offset	%rbp,-16
 	pushq	%rbx
+.cfi_adjust_cfa_offset	8
+.cfi_offset	%rbx,-24
 	pushq	%r12
+.cfi_adjust_cfa_offset	8
+.cfi_offset	%r12,-32
 	pushq	%r13
+.cfi_adjust_cfa_offset	8
+.cfi_offset	%r13,-40
 	pushq	%r14
+.cfi_adjust_cfa_offset	8
+.cfi_offset	%r14,-48
 	pushq	%r15
+.cfi_adjust_cfa_offset	8
+.cfi_offset	%r15,-56
 	leaq	-72(%rsp),%rsp
+.cfi_adjust_cfa_offset	0x48
 	movq	%rsp,%rbp
+.cfi_def_cfa_register	%rbp
 	movl	240(%rcx),%eax
 	movq	%rdi,%r12
 	movq	%rsi,%r13
@@ -1306,15 +1321,24 @@
 	ja	.Lcbc_dec_bzero
 
 	leaq	120(%rbp),%rax
+.cfi_def_cfa	%rax,8
 	movq	-48(%rax),%r15
+.cfi_restore	%r15
 	movq	-40(%rax),%r14
+.cfi_restore	%r14
 	movq	-32(%rax),%r13
+.cfi_restore	%r13
 	movq	-24(%rax),%r12
+.cfi_restore	%r12
 	movq	-16(%rax),%rbx
+.cfi_restore	%rbx
 	movq	-8(%rax),%rbp
+.cfi_restore	%rbp
 	leaq	(%rax),%rsp
+.cfi_def_cfa_register	%rsp
 .Lcbc_dec_epilogue:
 	.byte	0xf3,0xc3
+.cfi_endproc	
 .size	bsaes_cbc_encrypt,.-bsaes_cbc_encrypt
 
 .globl	bsaes_ctr32_encrypt_blocks
@@ -1322,16 +1346,31 @@
 .type	bsaes_ctr32_encrypt_blocks,@function
 .align	16
 bsaes_ctr32_encrypt_blocks:
+.cfi_startproc	
 	movq	%rsp,%rax
 .Lctr_enc_prologue:
 	pushq	%rbp
+.cfi_adjust_cfa_offset	8
+.cfi_offset	%rbp,-16
 	pushq	%rbx
+.cfi_adjust_cfa_offset	8
+.cfi_offset	%rbx,-24
 	pushq	%r12
+.cfi_adjust_cfa_offset	8
+.cfi_offset	%r12,-32
 	pushq	%r13
+.cfi_adjust_cfa_offset	8
+.cfi_offset	%r13,-40
 	pushq	%r14
+.cfi_adjust_cfa_offset	8
+.cfi_offset	%r14,-48
 	pushq	%r15
+.cfi_adjust_cfa_offset	8
+.cfi_offset	%r15,-56
 	leaq	-72(%rsp),%rsp
+.cfi_adjust_cfa_offset	0x48
 	movq	%rsp,%rbp
+.cfi_def_cfa_register	%rbp
 	movdqu	(%r8),%xmm0
 	movl	240(%rcx),%eax
 	movq	%rdi,%r12
@@ -1506,31 +1545,55 @@
 	ja	.Lctr_enc_bzero
 
 	leaq	120(%rbp),%rax
+.cfi_def_cfa	%rax,8
 	movq	-48(%rax),%r15
+.cfi_restore	%r15
 	movq	-40(%rax),%r14
+.cfi_restore	%r14
 	movq	-32(%rax),%r13
+.cfi_restore	%r13
 	movq	-24(%rax),%r12
+.cfi_restore	%r12
 	movq	-16(%rax),%rbx
+.cfi_restore	%rbx
 	movq	-8(%rax),%rbp
+.cfi_restore	%rbp
 	leaq	(%rax),%rsp
+.cfi_def_cfa_register	%rsp
 .Lctr_enc_epilogue:
 	.byte	0xf3,0xc3
+.cfi_endproc	
 .size	bsaes_ctr32_encrypt_blocks,.-bsaes_ctr32_encrypt_blocks
 .globl	bsaes_xts_encrypt
 .hidden bsaes_xts_encrypt
 .type	bsaes_xts_encrypt,@function
 .align	16
 bsaes_xts_encrypt:
+.cfi_startproc	
 	movq	%rsp,%rax
 .Lxts_enc_prologue:
 	pushq	%rbp
+.cfi_adjust_cfa_offset	8
+.cfi_offset	%rbp,-16
 	pushq	%rbx
+.cfi_adjust_cfa_offset	8
+.cfi_offset	%rbx,-24
 	pushq	%r12
+.cfi_adjust_cfa_offset	8
+.cfi_offset	%r12,-32
 	pushq	%r13
+.cfi_adjust_cfa_offset	8
+.cfi_offset	%r13,-40
 	pushq	%r14
+.cfi_adjust_cfa_offset	8
+.cfi_offset	%r14,-48
 	pushq	%r15
+.cfi_adjust_cfa_offset	8
+.cfi_offset	%r15,-56
 	leaq	-72(%rsp),%rsp
+.cfi_adjust_cfa_offset	0x48
 	movq	%rsp,%rbp
+.cfi_def_cfa_register	%rbp
 	movq	%rdi,%r12
 	movq	%rsi,%r13
 	movq	%rdx,%r14
@@ -1957,15 +2020,24 @@
 	ja	.Lxts_enc_bzero
 
 	leaq	120(%rbp),%rax
+.cfi_def_cfa	%rax,8
 	movq	-48(%rax),%r15
+.cfi_restore	%r15
 	movq	-40(%rax),%r14
+.cfi_restore	%r14
 	movq	-32(%rax),%r13
+.cfi_restore	%r13
 	movq	-24(%rax),%r12
+.cfi_restore	%r12
 	movq	-16(%rax),%rbx
+.cfi_restore	%rbx
 	movq	-8(%rax),%rbp
+.cfi_restore	%rbp
 	leaq	(%rax),%rsp
+.cfi_def_cfa_register	%rsp
 .Lxts_enc_epilogue:
 	.byte	0xf3,0xc3
+.cfi_endproc	
 .size	bsaes_xts_encrypt,.-bsaes_xts_encrypt
 
 .globl	bsaes_xts_decrypt
@@ -1973,15 +2045,29 @@
 .type	bsaes_xts_decrypt,@function
 .align	16
 bsaes_xts_decrypt:
+.cfi_startproc	
 	movq	%rsp,%rax
 .Lxts_dec_prologue:
 	pushq	%rbp
+.cfi_adjust_cfa_offset	8
+.cfi_offset	%rbp,-16
 	pushq	%rbx
+.cfi_adjust_cfa_offset	8
+.cfi_offset	%rbx,-24
 	pushq	%r12
+.cfi_adjust_cfa_offset	8
+.cfi_offset	%r12,-32
 	pushq	%r13
+.cfi_adjust_cfa_offset	8
+.cfi_offset	%r13,-40
 	pushq	%r14
+.cfi_adjust_cfa_offset	8
+.cfi_offset	%r14,-48
 	pushq	%r15
+.cfi_adjust_cfa_offset	8
+.cfi_offset	%r15,-56
 	leaq	-72(%rsp),%rsp
+.cfi_adjust_cfa_offset	0x48
 	movq	%rsp,%rbp
 	movq	%rdi,%r12
 	movq	%rsi,%r13
@@ -2435,15 +2521,24 @@
 	ja	.Lxts_dec_bzero
 
 	leaq	120(%rbp),%rax
+.cfi_def_cfa	%rax,8
 	movq	-48(%rax),%r15
+.cfi_restore	%r15
 	movq	-40(%rax),%r14
+.cfi_restore	%r14
 	movq	-32(%rax),%r13
+.cfi_restore	%r13
 	movq	-24(%rax),%r12
+.cfi_restore	%r12
 	movq	-16(%rax),%rbx
+.cfi_restore	%rbx
 	movq	-8(%rax),%rbp
+.cfi_restore	%rbp
 	leaq	(%rax),%rsp
+.cfi_def_cfa_register	%rsp
 .Lxts_dec_epilogue:
 	.byte	0xf3,0xc3
+.cfi_endproc	
 .size	bsaes_xts_decrypt,.-bsaes_xts_decrypt
 .type	_bsaes_const,@object
 .align	64
diff --git a/linux-x86_64/crypto/fipsmodule/p256-x86_64-asm.S b/linux-x86_64/crypto/fipsmodule/p256-x86_64-asm.S
index 6d21888..21e5471 100644
--- a/linux-x86_64/crypto/fipsmodule/p256-x86_64-asm.S
+++ b/linux-x86_64/crypto/fipsmodule/p256-x86_64-asm.S
@@ -24,8 +24,14 @@
 .type	ecp_nistz256_neg,@function
 .align	32
 ecp_nistz256_neg:
+.cfi_startproc	
 	pushq	%r12
+.cfi_adjust_cfa_offset	8
+.cfi_offset	%r12,-16
 	pushq	%r13
+.cfi_adjust_cfa_offset	8
+.cfi_offset	%r13,-24
+.Lneg_body:
 
 	xorq	%r8,%r8
 	xorq	%r9,%r9
@@ -59,9 +65,15 @@
 	movq	%r10,16(%rdi)
 	movq	%r11,24(%rdi)
 
-	popq	%r13
-	popq	%r12
+	movq	0(%rsp),%r13
+.cfi_restore	%r13
+	movq	8(%rsp),%r12
+.cfi_restore	%r12
+	leaq	16(%rsp),%rsp
+.cfi_adjust_cfa_offset	-16
+.Lneg_epilogue:
 	.byte	0xf3,0xc3
+.cfi_endproc	
 .size	ecp_nistz256_neg,.-ecp_nistz256_neg
 
 
@@ -74,13 +86,27 @@
 .type	ecp_nistz256_mul_mont,@function
 .align	32
 ecp_nistz256_mul_mont:
+.cfi_startproc	
 .Lmul_mont:
 	pushq	%rbp
+.cfi_adjust_cfa_offset	8
+.cfi_offset	%rbp,-16
 	pushq	%rbx
+.cfi_adjust_cfa_offset	8
+.cfi_offset	%rbx,-24
 	pushq	%r12
+.cfi_adjust_cfa_offset	8
+.cfi_offset	%r12,-32
 	pushq	%r13
+.cfi_adjust_cfa_offset	8
+.cfi_offset	%r13,-40
 	pushq	%r14
+.cfi_adjust_cfa_offset	8
+.cfi_offset	%r14,-48
 	pushq	%r15
+.cfi_adjust_cfa_offset	8
+.cfi_offset	%r15,-56
+.Lmul_body:
 	movq	%rdx,%rbx
 	movq	0(%rdx),%rax
 	movq	0(%rsi),%r9
@@ -90,13 +116,23 @@
 
 	call	__ecp_nistz256_mul_montq
 .Lmul_mont_done:
-	popq	%r15
-	popq	%r14
-	popq	%r13
-	popq	%r12
-	popq	%rbx
-	popq	%rbp
+	movq	0(%rsp),%r15
+.cfi_restore	%r15
+	movq	8(%rsp),%r14
+.cfi_restore	%r14
+	movq	16(%rsp),%r13
+.cfi_restore	%r13
+	movq	24(%rsp),%r12
+.cfi_restore	%r12
+	movq	32(%rsp),%rbx
+.cfi_restore	%rbx
+	movq	40(%rsp),%rbp
+.cfi_restore	%rbp
+	leaq	48(%rsp),%rsp
+.cfi_adjust_cfa_offset	-48
+.Lmul_epilogue:
 	.byte	0xf3,0xc3
+.cfi_endproc	
 .size	ecp_nistz256_mul_mont,.-ecp_nistz256_mul_mont
 
 .type	__ecp_nistz256_mul_montq,@function
@@ -327,12 +363,26 @@
 .type	ecp_nistz256_sqr_mont,@function
 .align	32
 ecp_nistz256_sqr_mont:
+.cfi_startproc	
 	pushq	%rbp
+.cfi_adjust_cfa_offset	8
+.cfi_offset	%rbp,-16
 	pushq	%rbx
+.cfi_adjust_cfa_offset	8
+.cfi_offset	%rbx,-24
 	pushq	%r12
+.cfi_adjust_cfa_offset	8
+.cfi_offset	%r12,-32
 	pushq	%r13
+.cfi_adjust_cfa_offset	8
+.cfi_offset	%r13,-40
 	pushq	%r14
+.cfi_adjust_cfa_offset	8
+.cfi_offset	%r14,-48
 	pushq	%r15
+.cfi_adjust_cfa_offset	8
+.cfi_offset	%r15,-56
+.Lsqr_body:
 	movq	0(%rsi),%rax
 	movq	8(%rsi),%r14
 	movq	16(%rsi),%r15
@@ -340,13 +390,23 @@
 
 	call	__ecp_nistz256_sqr_montq
 .Lsqr_mont_done:
-	popq	%r15
-	popq	%r14
-	popq	%r13
-	popq	%r12
-	popq	%rbx
-	popq	%rbp
+	movq	0(%rsp),%r15
+.cfi_restore	%r15
+	movq	8(%rsp),%r14
+.cfi_restore	%r14
+	movq	16(%rsp),%r13
+.cfi_restore	%r13
+	movq	24(%rsp),%r12
+.cfi_restore	%r12
+	movq	32(%rsp),%rbx
+.cfi_restore	%rbx
+	movq	40(%rsp),%rbp
+.cfi_restore	%rbp
+	leaq	48(%rsp),%rsp
+.cfi_adjust_cfa_offset	-48
+.Lsqr_epilogue:
 	.byte	0xf3,0xc3
+.cfi_endproc	
 .size	ecp_nistz256_sqr_mont,.-ecp_nistz256_sqr_mont
 
 .type	__ecp_nistz256_sqr_montq,@function
@@ -572,6 +632,7 @@
 	movdqu	%xmm6,64(%rdi)
 	movdqu	%xmm7,80(%rdi)
 	.byte	0xf3,0xc3
+.LSEH_end_ecp_nistz256_select_w5:
 .size	ecp_nistz256_select_w5,.-ecp_nistz256_select_w5
 
 
@@ -625,6 +686,7 @@
 	movdqu	%xmm4,32(%rdi)
 	movdqu	%xmm5,48(%rdi)
 	.byte	0xf3,0xc3
+.LSEH_end_ecp_nistz256_select_w7:
 .size	ecp_nistz256_select_w7,.-ecp_nistz256_select_w7
 
 
@@ -685,6 +747,7 @@
 	vmovdqu	%ymm4,64(%rdi)
 	vzeroupper
 	.byte	0xf3,0xc3
+.LSEH_end_ecp_nistz256_avx2_select_w5:
 .size	ecp_nistz256_avx2_select_w5,.-ecp_nistz256_avx2_select_w5
 
 
@@ -763,6 +826,7 @@
 	vmovdqu	%ymm3,32(%rdi)
 	vzeroupper
 	.byte	0xf3,0xc3
+.LSEH_end_ecp_nistz256_avx2_select_w7:
 .size	ecp_nistz256_avx2_select_w7,.-ecp_nistz256_avx2_select_w7
 .type	__ecp_nistz256_add_toq,@function
 .align	32
@@ -890,13 +954,28 @@
 .type	ecp_nistz256_point_double,@function
 .align	32
 ecp_nistz256_point_double:
+.cfi_startproc	
 	pushq	%rbp
+.cfi_adjust_cfa_offset	8
+.cfi_offset	%rbp,-16
 	pushq	%rbx
+.cfi_adjust_cfa_offset	8
+.cfi_offset	%rbx,-24
 	pushq	%r12
+.cfi_adjust_cfa_offset	8
+.cfi_offset	%r12,-32
 	pushq	%r13
+.cfi_adjust_cfa_offset	8
+.cfi_offset	%r13,-40
 	pushq	%r14
+.cfi_adjust_cfa_offset	8
+.cfi_offset	%r14,-48
 	pushq	%r15
+.cfi_adjust_cfa_offset	8
+.cfi_offset	%r15,-56
 	subq	$160+8,%rsp
+.cfi_adjust_cfa_offset	32*5+8
+.Lpoint_doubleq_body:
 
 .Lpoint_double_shortcutq:
 	movdqu	0(%rsi),%xmm0
@@ -1079,27 +1158,53 @@
 .byte	102,72,15,126,207
 	call	__ecp_nistz256_sub_fromq
 
-	addq	$160+8,%rsp
-	popq	%r15
-	popq	%r14
-	popq	%r13
-	popq	%r12
-	popq	%rbx
-	popq	%rbp
+	leaq	160+56(%rsp),%rsi
+.cfi_def_cfa	%rsi,8
+	movq	-48(%rsi),%r15
+.cfi_restore	%r15
+	movq	-40(%rsi),%r14
+.cfi_restore	%r14
+	movq	-32(%rsi),%r13
+.cfi_restore	%r13
+	movq	-24(%rsi),%r12
+.cfi_restore	%r12
+	movq	-16(%rsi),%rbx
+.cfi_restore	%rbx
+	movq	-8(%rsi),%rbp
+.cfi_restore	%rbp
+	leaq	(%rsi),%rsp
+.cfi_def_cfa_register	%rsp
+.Lpoint_doubleq_epilogue:
 	.byte	0xf3,0xc3
+.cfi_endproc	
 .size	ecp_nistz256_point_double,.-ecp_nistz256_point_double
 .globl	ecp_nistz256_point_add
 .hidden ecp_nistz256_point_add
 .type	ecp_nistz256_point_add,@function
 .align	32
 ecp_nistz256_point_add:
+.cfi_startproc	
 	pushq	%rbp
+.cfi_adjust_cfa_offset	8
+.cfi_offset	%rbp,-16
 	pushq	%rbx
+.cfi_adjust_cfa_offset	8
+.cfi_offset	%rbx,-24
 	pushq	%r12
+.cfi_adjust_cfa_offset	8
+.cfi_offset	%r12,-32
 	pushq	%r13
+.cfi_adjust_cfa_offset	8
+.cfi_offset	%r13,-40
 	pushq	%r14
+.cfi_adjust_cfa_offset	8
+.cfi_offset	%r14,-48
 	pushq	%r15
+.cfi_adjust_cfa_offset	8
+.cfi_offset	%r15,-56
 	subq	$576+8,%rsp
+.cfi_adjust_cfa_offset	32*18+8
+.Lpoint_addq_body:
 
 	movdqu	0(%rsi),%xmm0
 	movdqu	16(%rsi),%xmm1
@@ -1476,27 +1581,53 @@
 	movdqu	%xmm3,48(%rdi)
 
 .Ladd_doneq:
-	addq	$576+8,%rsp
-	popq	%r15
-	popq	%r14
-	popq	%r13
-	popq	%r12
-	popq	%rbx
-	popq	%rbp
+	leaq	576+56(%rsp),%rsi
+.cfi_def_cfa	%rsi,8
+	movq	-48(%rsi),%r15
+.cfi_restore	%r15
+	movq	-40(%rsi),%r14
+.cfi_restore	%r14
+	movq	-32(%rsi),%r13
+.cfi_restore	%r13
+	movq	-24(%rsi),%r12
+.cfi_restore	%r12
+	movq	-16(%rsi),%rbx
+.cfi_restore	%rbx
+	movq	-8(%rsi),%rbp
+.cfi_restore	%rbp
+	leaq	(%rsi),%rsp
+.cfi_def_cfa_register	%rsp
+.Lpoint_addq_epilogue:
 	.byte	0xf3,0xc3
+.cfi_endproc	
 .size	ecp_nistz256_point_add,.-ecp_nistz256_point_add
 .globl	ecp_nistz256_point_add_affine
 .hidden ecp_nistz256_point_add_affine
 .type	ecp_nistz256_point_add_affine,@function
 .align	32
 ecp_nistz256_point_add_affine:
+.cfi_startproc	
 	pushq	%rbp
+.cfi_adjust_cfa_offset	8
+.cfi_offset	%rbp,-16
 	pushq	%rbx
+.cfi_adjust_cfa_offset	8
+.cfi_offset	%rbx,-24
 	pushq	%r12
+.cfi_adjust_cfa_offset	8
+.cfi_offset	%r12,-32
 	pushq	%r13
+.cfi_adjust_cfa_offset	8
+.cfi_offset	%r13,-40
 	pushq	%r14
+.cfi_adjust_cfa_offset	8
+.cfi_offset	%r14,-48
 	pushq	%r15
+.cfi_adjust_cfa_offset	8
+.cfi_offset	%r15,-56
 	subq	$480+8,%rsp
+.cfi_adjust_cfa_offset	32*15+8
+.Ladd_affineq_body:
 
 	movdqu	0(%rsi),%xmm0
 	movq	%rdx,%rbx
@@ -1779,13 +1910,24 @@
 	movdqu	%xmm2,32(%rdi)
 	movdqu	%xmm3,48(%rdi)
 
-	addq	$480+8,%rsp
-	popq	%r15
-	popq	%r14
-	popq	%r13
-	popq	%r12
-	popq	%rbx
-	popq	%rbp
+	leaq	480+56(%rsp),%rsi
+.cfi_def_cfa	%rsi,8
+	movq	-48(%rsi),%r15
+.cfi_restore	%r15
+	movq	-40(%rsi),%r14
+.cfi_restore	%r14
+	movq	-32(%rsi),%r13
+.cfi_restore	%r13
+	movq	-24(%rsi),%r12
+.cfi_restore	%r12
+	movq	-16(%rsi),%rbx
+.cfi_restore	%rbx
+	movq	-8(%rsi),%rbp
+.cfi_restore	%rbp
+	leaq	(%rsi),%rsp
+.cfi_def_cfa_register	%rsp
+.Ladd_affineq_epilogue:
 	.byte	0xf3,0xc3
+.cfi_endproc	
 .size	ecp_nistz256_point_add_affine,.-ecp_nistz256_point_add_affine
 #endif
diff --git a/linux-x86_64/crypto/fipsmodule/x86_64-mont.S b/linux-x86_64/crypto/fipsmodule/x86_64-mont.S
index b32e2f0..1f673ef 100644
--- a/linux-x86_64/crypto/fipsmodule/x86_64-mont.S
+++ b/linux-x86_64/crypto/fipsmodule/x86_64-mont.S
@@ -212,8 +212,7 @@
 	movq	%r9,%r15
 	jmp	.Lsub
 .align	16
-.Lsub:
-	sbbq	(%rcx,%r14,8),%rax
+.Lsub:	sbbq	(%rcx,%r14,8),%rax
 	movq	%rax,(%rdi,%r14,8)
 	movq	8(%rsi,%r14,8),%rax
 	leaq	1(%r14),%r14
diff --git a/linux-x86_64/crypto/fipsmodule/x86_64-mont5.S b/linux-x86_64/crypto/fipsmodule/x86_64-mont5.S
index 208b1dc..1ec58ca 100644
--- a/linux-x86_64/crypto/fipsmodule/x86_64-mont5.S
+++ b/linux-x86_64/crypto/fipsmodule/x86_64-mont5.S
@@ -396,8 +396,7 @@
 	movq	%r9,%r15
 	jmp	.Lsub
 .align	16
-.Lsub:
-	sbbq	(%rcx,%r14,8),%rax
+.Lsub:	sbbq	(%rcx,%r14,8),%rax
 	movq	%rax,(%rdi,%r14,8)
 	movq	8(%rsi,%r14,8),%rax
 	leaq	1(%r14),%r14
diff --git a/mac-x86_64/crypto/fipsmodule/aes-x86_64.S b/mac-x86_64/crypto/fipsmodule/aes-x86_64.S
index c7c4829..f7b1b06 100644
--- a/mac-x86_64/crypto/fipsmodule/aes-x86_64.S
+++ b/mac-x86_64/crypto/fipsmodule/aes-x86_64.S
@@ -332,15 +332,23 @@
 
 .private_extern	_asm_AES_encrypt
 _asm_AES_encrypt:
+
 	movq	%rsp,%rax
+
 	pushq	%rbx
+
 	pushq	%rbp
+
 	pushq	%r12
+
 	pushq	%r13
+
 	pushq	%r14
+
 	pushq	%r15
 
 
+
 	leaq	-63(%rdx),%rcx
 	andq	$-64,%rsp
 	subq	%rsp,%rcx
@@ -351,6 +359,7 @@
 
 	movq	%rsi,16(%rsp)
 	movq	%rax,24(%rsp)
+
 L$enc_prologue:
 
 	movq	%rdx,%r15
@@ -377,22 +386,31 @@
 
 	movq	16(%rsp),%r9
 	movq	24(%rsp),%rsi
+
 	movl	%eax,0(%r9)
 	movl	%ebx,4(%r9)
 	movl	%ecx,8(%r9)
 	movl	%edx,12(%r9)
 
 	movq	-48(%rsi),%r15
+
 	movq	-40(%rsi),%r14
+
 	movq	-32(%rsi),%r13
+
 	movq	-24(%rsi),%r12
+
 	movq	-16(%rsi),%rbp
+
 	movq	-8(%rsi),%rbx
+
 	leaq	(%rsi),%rsp
+
 L$enc_epilogue:
 	.byte	0xf3,0xc3
 
 
+
 .p2align	4
 _x86_64_AES_decrypt:
 	xorl	0(%r15),%eax
@@ -778,15 +796,23 @@
 
 .private_extern	_asm_AES_decrypt
 _asm_AES_decrypt:
+
 	movq	%rsp,%rax
+
 	pushq	%rbx
+
 	pushq	%rbp
+
 	pushq	%r12
+
 	pushq	%r13
+
 	pushq	%r14
+
 	pushq	%r15
 
 
+
 	leaq	-63(%rdx),%rcx
 	andq	$-64,%rsp
 	subq	%rsp,%rcx
@@ -797,6 +823,7 @@
 
 	movq	%rsi,16(%rsp)
 	movq	%rax,24(%rsp)
+
 L$dec_prologue:
 
 	movq	%rdx,%r15
@@ -825,45 +852,66 @@
 
 	movq	16(%rsp),%r9
 	movq	24(%rsp),%rsi
+
 	movl	%eax,0(%r9)
 	movl	%ebx,4(%r9)
 	movl	%ecx,8(%r9)
 	movl	%edx,12(%r9)
 
 	movq	-48(%rsi),%r15
+
 	movq	-40(%rsi),%r14
+
 	movq	-32(%rsi),%r13
+
 	movq	-24(%rsi),%r12
+
 	movq	-16(%rsi),%rbp
+
 	movq	-8(%rsi),%rbx
+
 	leaq	(%rsi),%rsp
+
 L$dec_epilogue:
 	.byte	0xf3,0xc3
 
+
 .p2align	4
 .globl	_asm_AES_set_encrypt_key
 .private_extern _asm_AES_set_encrypt_key
 
 _asm_AES_set_encrypt_key:
+
 	pushq	%rbx
+
 	pushq	%rbp
+
 	pushq	%r12
+
 	pushq	%r13
+
 	pushq	%r14
+
 	pushq	%r15
+
 	subq	$8,%rsp
+
 L$enc_key_prologue:
 
 	call	_x86_64_AES_set_encrypt_key
 
 	movq	40(%rsp),%rbp
+
 	movq	48(%rsp),%rbx
+
 	addq	$56,%rsp
+
 L$enc_key_epilogue:
 	.byte	0xf3,0xc3
 
 
 
+
 .p2align	4
 _x86_64_AES_set_encrypt_key:
 	movl	%esi,%ecx
@@ -1107,13 +1155,21 @@
 .private_extern _asm_AES_set_decrypt_key
 
 _asm_AES_set_decrypt_key:
+
 	pushq	%rbx
+
 	pushq	%rbp
+
 	pushq	%r12
+
 	pushq	%r13
+
 	pushq	%r14
+
 	pushq	%r15
+
 	pushq	%rdx
+
 L$dec_key_prologue:
 
 	call	_x86_64_AES_set_encrypt_key
@@ -1281,15 +1337,23 @@
 	xorq	%rax,%rax
 L$abort:
 	movq	8(%rsp),%r15
+
 	movq	16(%rsp),%r14
+
 	movq	24(%rsp),%r13
+
 	movq	32(%rsp),%r12
+
 	movq	40(%rsp),%rbp
+
 	movq	48(%rsp),%rbx
+
 	addq	$56,%rsp
+
 L$dec_key_epilogue:
 	.byte	0xf3,0xc3
 
+
 .p2align	4
 .globl	_asm_AES_cbc_encrypt
 .private_extern _asm_AES_cbc_encrypt
@@ -1297,15 +1361,23 @@
 
 .private_extern	_asm_AES_cbc_encrypt
 _asm_AES_cbc_encrypt:
+
 	cmpq	$0,%rdx
 	je	L$cbc_epilogue
 	pushfq
+
 	pushq	%rbx
+
 	pushq	%rbp
+
 	pushq	%r12
+
 	pushq	%r13
+
 	pushq	%r14
+
 	pushq	%r15
+
 L$cbc_prologue:
 
 	cld
@@ -1352,7 +1424,9 @@
 
 	xchgq	%rsp,%r15
 
+
 	movq	%r15,16(%rsp)
+
 L$cbc_fast_body:
 	movq	%rdi,24(%rsp)
 	movq	%rsi,32(%rsp)
@@ -1734,18 +1808,28 @@
 .p2align	4
 L$cbc_exit:
 	movq	16(%rsp),%rsi
+
 	movq	(%rsi),%r15
+
 	movq	8(%rsi),%r14
+
 	movq	16(%rsi),%r13
+
 	movq	24(%rsi),%r12
+
 	movq	32(%rsi),%rbp
+
 	movq	40(%rsi),%rbx
+
 	leaq	48(%rsi),%rsp
+
 L$cbc_popfq:
 	popfq
+
 L$cbc_epilogue:
 	.byte	0xf3,0xc3
 
+
 .p2align	6
 L$AES_Te:
 .long	0xa56363c6,0xa56363c6
diff --git a/mac-x86_64/crypto/fipsmodule/aesni-x86_64.S b/mac-x86_64/crypto/fipsmodule/aesni-x86_64.S
index 4ee0dc4..6899800 100644
--- a/mac-x86_64/crypto/fipsmodule/aesni-x86_64.S
+++ b/mac-x86_64/crypto/fipsmodule/aesni-x86_64.S
@@ -1002,6 +1002,7 @@
 
 .p2align	4
 _aesni_ctr32_encrypt_blocks:
+
 	cmpq	$1,%rdx
 	jne	L$ctr32_bulk
 
@@ -1032,7 +1033,9 @@
 .p2align	4
 L$ctr32_bulk:
 	leaq	(%rsp),%r11
+
 	pushq	%rbp
+
 	subq	$128,%rsp
 	andq	$-16,%rsp
 
@@ -1567,17 +1570,23 @@
 	movaps	%xmm0,112(%rsp)
 	pxor	%xmm15,%xmm15
 	movq	-8(%r11),%rbp
+
 	leaq	(%r11),%rsp
+
 L$ctr32_epilogue:
 	.byte	0xf3,0xc3
 
+
 .globl	_aesni_xts_encrypt
 .private_extern _aesni_xts_encrypt
 
 .p2align	4
 _aesni_xts_encrypt:
+
 	leaq	(%rsp),%r11
+
 	pushq	%rbp
+
 	subq	$112,%rsp
 	andq	$-16,%rsp
 	movups	(%r9),%xmm2
@@ -2032,17 +2041,23 @@
 	pxor	%xmm14,%xmm14
 	pxor	%xmm15,%xmm15
 	movq	-8(%r11),%rbp
+
 	leaq	(%r11),%rsp
+
 L$xts_enc_epilogue:
 	.byte	0xf3,0xc3
 
+
 .globl	_aesni_xts_decrypt
 .private_extern _aesni_xts_decrypt
 
 .p2align	4
 _aesni_xts_decrypt:
+
 	leaq	(%rsp),%r11
+
 	pushq	%rbp
+
 	subq	$112,%rsp
 	andq	$-16,%rsp
 	movups	(%r9),%xmm2
@@ -2534,21 +2549,30 @@
 	pxor	%xmm14,%xmm14
 	pxor	%xmm15,%xmm15
 	movq	-8(%r11),%rbp
+
 	leaq	(%r11),%rsp
+
 L$xts_dec_epilogue:
 	.byte	0xf3,0xc3
 
+
 .globl	_aesni_ocb_encrypt
 .private_extern _aesni_ocb_encrypt
 
 .p2align	5
 _aesni_ocb_encrypt:
+
 	leaq	(%rsp),%rax
 	pushq	%rbx
+
 	pushq	%rbp
+
 	pushq	%r12
+
 	pushq	%r13
+
 	pushq	%r14
+
 	movq	8(%rax),%rbx
 	movq	8+8(%rax),%rbp
 
@@ -2725,17 +2749,25 @@
 	pxor	%xmm14,%xmm14
 	pxor	%xmm15,%xmm15
 	leaq	40(%rsp),%rax
+
 	movq	-40(%rax),%r14
+
 	movq	-32(%rax),%r13
+
 	movq	-24(%rax),%r12
+
 	movq	-16(%rax),%rbp
+
 	movq	-8(%rax),%rbx
+
 	leaq	(%rax),%rsp
+
 L$ocb_enc_epilogue:
 	.byte	0xf3,0xc3
 
 
 
+
 .p2align	5
 __ocb_encrypt6:
 	pxor	%xmm9,%xmm15
@@ -2946,12 +2978,18 @@
 
 .p2align	5
 _aesni_ocb_decrypt:
+
 	leaq	(%rsp),%rax
 	pushq	%rbx
+
 	pushq	%rbp
+
 	pushq	%r12
+
 	pushq	%r13
+
 	pushq	%r14
+
 	movq	8(%rax),%rbx
 	movq	8+8(%rax),%rbp
 
@@ -3150,17 +3188,25 @@
 	pxor	%xmm14,%xmm14
 	pxor	%xmm15,%xmm15
 	leaq	40(%rsp),%rax
+
 	movq	-40(%rax),%r14
+
 	movq	-32(%rax),%r13
+
 	movq	-24(%rax),%r12
+
 	movq	-16(%rax),%rbp
+
 	movq	-8(%rax),%rbx
+
 	leaq	(%rax),%rsp
+
 L$ocb_dec_epilogue:
 	.byte	0xf3,0xc3
 
 
 
+
 .p2align	5
 __ocb_decrypt6:
 	pxor	%xmm9,%xmm15
@@ -3359,6 +3405,7 @@
 
 .p2align	4
 _aesni_cbc_encrypt:
+
 	testq	%rdx,%rdx
 	jz	L$cbc_ret
 
@@ -3452,7 +3499,9 @@
 .p2align	4
 L$cbc_decrypt_bulk:
 	leaq	(%rsp),%r11
+
 	pushq	%rbp
+
 	subq	$16,%rsp
 	andq	$-16,%rsp
 	movq	%rcx,%rbp
@@ -3937,16 +3986,21 @@
 	xorps	%xmm0,%xmm0
 	pxor	%xmm1,%xmm1
 	movq	-8(%r11),%rbp
+
 	leaq	(%r11),%rsp
+
 L$cbc_ret:
 	.byte	0xf3,0xc3
 
+
 .globl	_aesni_set_decrypt_key
 .private_extern _aesni_set_decrypt_key
 
 .p2align	4
 _aesni_set_decrypt_key:
+
 .byte	0x48,0x83,0xEC,0x08
+
 	call	__aesni_set_encrypt_key
 	shll	$4,%esi
 	testl	%eax,%eax
@@ -3979,7 +4033,9 @@
 	pxor	%xmm0,%xmm0
 L$dec_key_ret:
 	addq	$8,%rsp
+
 	.byte	0xf3,0xc3
+
 L$SEH_end_set_decrypt_key:
 
 .globl	_aesni_set_encrypt_key
@@ -3988,7 +4044,9 @@
 .p2align	4
 _aesni_set_encrypt_key:
 __aesni_set_encrypt_key:
+
 .byte	0x48,0x83,0xEC,0x08
+
 	movq	$-1,%rax
 	testq	%rdi,%rdi
 	jz	L$enc_key_ret
@@ -4282,7 +4340,9 @@
 	pxor	%xmm4,%xmm4
 	pxor	%xmm5,%xmm5
 	addq	$8,%rsp
+
 	.byte	0xf3,0xc3
+
 L$SEH_end_set_encrypt_key:
 
 .p2align	4
diff --git a/mac-x86_64/crypto/fipsmodule/bsaes-x86_64.S b/mac-x86_64/crypto/fipsmodule/bsaes-x86_64.S
index 195abd3..91cd048 100644
--- a/mac-x86_64/crypto/fipsmodule/bsaes-x86_64.S
+++ b/mac-x86_64/crypto/fipsmodule/bsaes-x86_64.S
@@ -1069,6 +1069,7 @@
 
 .p2align	4
 _bsaes_cbc_encrypt:
+
 	cmpl	$0,%r9d
 	jne	_asm_AES_cbc_encrypt
 	cmpq	$128,%rdx
@@ -1077,13 +1078,21 @@
 	movq	%rsp,%rax
 L$cbc_dec_prologue:
 	pushq	%rbp
+
 	pushq	%rbx
+
 	pushq	%r12
+
 	pushq	%r13
+
 	pushq	%r14
+
 	pushq	%r15
+
 	leaq	-72(%rsp),%rsp
+
 	movq	%rsp,%rbp
+
 	movl	240(%rcx),%eax
 	movq	%rdi,%r12
 	movq	%rsi,%r13
@@ -1303,32 +1312,50 @@
 	ja	L$cbc_dec_bzero
 
 	leaq	120(%rbp),%rax
+
 	movq	-48(%rax),%r15
+
 	movq	-40(%rax),%r14
+
 	movq	-32(%rax),%r13
+
 	movq	-24(%rax),%r12
+
 	movq	-16(%rax),%rbx
+
 	movq	-8(%rax),%rbp
+
 	leaq	(%rax),%rsp
+
 L$cbc_dec_epilogue:
 	.byte	0xf3,0xc3
 
 
+
 .globl	_bsaes_ctr32_encrypt_blocks
 .private_extern _bsaes_ctr32_encrypt_blocks
 
 .p2align	4
 _bsaes_ctr32_encrypt_blocks:
+
 	movq	%rsp,%rax
 L$ctr_enc_prologue:
 	pushq	%rbp
+
 	pushq	%rbx
+
 	pushq	%r12
+
 	pushq	%r13
+
 	pushq	%r14
+
 	pushq	%r15
+
 	leaq	-72(%rsp),%rsp
+
 	movq	%rsp,%rbp
+
 	movdqu	(%r8),%xmm0
 	movl	240(%rcx),%eax
 	movq	%rdi,%r12
@@ -1503,31 +1530,49 @@
 	ja	L$ctr_enc_bzero
 
 	leaq	120(%rbp),%rax
+
 	movq	-48(%rax),%r15
+
 	movq	-40(%rax),%r14
+
 	movq	-32(%rax),%r13
+
 	movq	-24(%rax),%r12
+
 	movq	-16(%rax),%rbx
+
 	movq	-8(%rax),%rbp
+
 	leaq	(%rax),%rsp
+
 L$ctr_enc_epilogue:
 	.byte	0xf3,0xc3
 
+
 .globl	_bsaes_xts_encrypt
 .private_extern _bsaes_xts_encrypt
 
 .p2align	4
 _bsaes_xts_encrypt:
+
 	movq	%rsp,%rax
 L$xts_enc_prologue:
 	pushq	%rbp
+
 	pushq	%rbx
+
 	pushq	%r12
+
 	pushq	%r13
+
 	pushq	%r14
+
 	pushq	%r15
+
 	leaq	-72(%rsp),%rsp
+
 	movq	%rsp,%rbp
+
 	movq	%rdi,%r12
 	movq	%rsi,%r13
 	movq	%rdx,%r14
@@ -1954,31 +1999,48 @@
 	ja	L$xts_enc_bzero
 
 	leaq	120(%rbp),%rax
+
 	movq	-48(%rax),%r15
+
 	movq	-40(%rax),%r14
+
 	movq	-32(%rax),%r13
+
 	movq	-24(%rax),%r12
+
 	movq	-16(%rax),%rbx
+
 	movq	-8(%rax),%rbp
+
 	leaq	(%rax),%rsp
+
 L$xts_enc_epilogue:
 	.byte	0xf3,0xc3
 
 
+
 .globl	_bsaes_xts_decrypt
 .private_extern _bsaes_xts_decrypt
 
 .p2align	4
 _bsaes_xts_decrypt:
+
 	movq	%rsp,%rax
 L$xts_dec_prologue:
 	pushq	%rbp
+
 	pushq	%rbx
+
 	pushq	%r12
+
 	pushq	%r13
+
 	pushq	%r14
+
 	pushq	%r15
+
 	leaq	-72(%rsp),%rsp
+
 	movq	%rsp,%rbp
 	movq	%rdi,%r12
 	movq	%rsi,%r13
@@ -2432,17 +2494,26 @@
 	ja	L$xts_dec_bzero
 
 	leaq	120(%rbp),%rax
+
 	movq	-48(%rax),%r15
+
 	movq	-40(%rax),%r14
+
 	movq	-32(%rax),%r13
+
 	movq	-24(%rax),%r12
+
 	movq	-16(%rax),%rbx
+
 	movq	-8(%rax),%rbp
+
 	leaq	(%rax),%rsp
+
 L$xts_dec_epilogue:
 	.byte	0xf3,0xc3
 
 
+
 .p2align	6
 _bsaes_const:
 L$M0ISR:
diff --git a/mac-x86_64/crypto/fipsmodule/p256-x86_64-asm.S b/mac-x86_64/crypto/fipsmodule/p256-x86_64-asm.S
index f787577..8295346 100644
--- a/mac-x86_64/crypto/fipsmodule/p256-x86_64-asm.S
+++ b/mac-x86_64/crypto/fipsmodule/p256-x86_64-asm.S
@@ -23,9 +23,13 @@
 
 .p2align	5
 _ecp_nistz256_neg:
+
 	pushq	%r12
+
 	pushq	%r13
 
+L$neg_body:
+
 	xorq	%r8,%r8
 	xorq	%r9,%r9
 	xorq	%r10,%r10
@@ -58,8 +62,13 @@
 	movq	%r10,16(%rdi)
 	movq	%r11,24(%rdi)
 
-	popq	%r13
-	popq	%r12
+	movq	0(%rsp),%r13
+
+	movq	8(%rsp),%r12
+
+	leaq	16(%rsp),%rsp
+
+L$neg_epilogue:
 	.byte	0xf3,0xc3
 
 
@@ -68,18 +77,27 @@
 
 
 
+
 .globl	_ecp_nistz256_mul_mont
 .private_extern _ecp_nistz256_mul_mont
 
 .p2align	5
 _ecp_nistz256_mul_mont:
+
 L$mul_mont:
 	pushq	%rbp
+
 	pushq	%rbx
+
 	pushq	%r12
+
 	pushq	%r13
+
 	pushq	%r14
+
 	pushq	%r15
+
+L$mul_body:
 	movq	%rdx,%rbx
 	movq	0(%rdx),%rax
 	movq	0(%rsi),%r9
@@ -89,16 +107,26 @@
 
 	call	__ecp_nistz256_mul_montq
 L$mul_mont_done:
-	popq	%r15
-	popq	%r14
-	popq	%r13
-	popq	%r12
-	popq	%rbx
-	popq	%rbp
+	movq	0(%rsp),%r15
+
+	movq	8(%rsp),%r14
+
+	movq	16(%rsp),%r13
+
+	movq	24(%rsp),%r12
+
+	movq	32(%rsp),%rbx
+
+	movq	40(%rsp),%rbp
+
+	leaq	48(%rsp),%rsp
+
+L$mul_epilogue:
 	.byte	0xf3,0xc3
 
 
 
+
 .p2align	5
 __ecp_nistz256_mul_montq:
 
@@ -326,12 +354,20 @@
 
 .p2align	5
 _ecp_nistz256_sqr_mont:
+
 	pushq	%rbp
+
 	pushq	%rbx
+
 	pushq	%r12
+
 	pushq	%r13
+
 	pushq	%r14
+
 	pushq	%r15
+
+L$sqr_body:
 	movq	0(%rsi),%rax
 	movq	8(%rsi),%r14
 	movq	16(%rsi),%r15
@@ -339,16 +375,26 @@
 
 	call	__ecp_nistz256_sqr_montq
 L$sqr_mont_done:
-	popq	%r15
-	popq	%r14
-	popq	%r13
-	popq	%r12
-	popq	%rbx
-	popq	%rbp
+	movq	0(%rsp),%r15
+
+	movq	8(%rsp),%r14
+
+	movq	16(%rsp),%r13
+
+	movq	24(%rsp),%r12
+
+	movq	32(%rsp),%rbx
+
+	movq	40(%rsp),%rbp
+
+	leaq	48(%rsp),%rsp
+
+L$sqr_epilogue:
 	.byte	0xf3,0xc3
 
 
 
+
 .p2align	5
 __ecp_nistz256_sqr_montq:
 	movq	%rax,%r13
@@ -571,6 +617,7 @@
 	movdqu	%xmm6,64(%rdi)
 	movdqu	%xmm7,80(%rdi)
 	.byte	0xf3,0xc3
+L$SEH_end_ecp_nistz256_select_w5:
 
 
 
@@ -624,6 +671,7 @@
 	movdqu	%xmm4,32(%rdi)
 	movdqu	%xmm5,48(%rdi)
 	.byte	0xf3,0xc3
+L$SEH_end_ecp_nistz256_select_w7:
 
 
 
@@ -684,6 +732,7 @@
 	vmovdqu	%ymm4,64(%rdi)
 	vzeroupper
 	.byte	0xf3,0xc3
+L$SEH_end_ecp_nistz256_avx2_select_w5:
 
 
 
@@ -762,6 +811,7 @@
 	vmovdqu	%ymm3,32(%rdi)
 	vzeroupper
 	.byte	0xf3,0xc3
+L$SEH_end_ecp_nistz256_avx2_select_w7:
 
 
 .p2align	5
@@ -889,14 +939,23 @@
 
 .p2align	5
 _ecp_nistz256_point_double:
+
 	pushq	%rbp
+
 	pushq	%rbx
+
 	pushq	%r12
+
 	pushq	%r13
+
 	pushq	%r14
+
 	pushq	%r15
+
 	subq	$160+8,%rsp
 
+L$point_doubleq_body:
+
 L$point_double_shortcutq:
 	movdqu	0(%rsi),%xmm0
 	movq	%rsi,%rbx
@@ -1078,28 +1137,48 @@
 .byte	102,72,15,126,207
 	call	__ecp_nistz256_sub_fromq
 
-	addq	$160+8,%rsp
-	popq	%r15
-	popq	%r14
-	popq	%r13
-	popq	%r12
-	popq	%rbx
-	popq	%rbp
+	leaq	160+56(%rsp),%rsi
+
+	movq	-48(%rsi),%r15
+
+	movq	-40(%rsi),%r14
+
+	movq	-32(%rsi),%r13
+
+	movq	-24(%rsi),%r12
+
+	movq	-16(%rsi),%rbx
+
+	movq	-8(%rsi),%rbp
+
+	leaq	(%rsi),%rsp
+
+L$point_doubleq_epilogue:
 	.byte	0xf3,0xc3
 
+
 .globl	_ecp_nistz256_point_add
 .private_extern _ecp_nistz256_point_add
 
 .p2align	5
 _ecp_nistz256_point_add:
+
 	pushq	%rbp
+
 	pushq	%rbx
+
 	pushq	%r12
+
 	pushq	%r13
+
 	pushq	%r14
+
 	pushq	%r15
+
 	subq	$576+8,%rsp
 
+L$point_addq_body:
+
 	movdqu	0(%rsi),%xmm0
 	movdqu	16(%rsi),%xmm1
 	movdqu	32(%rsi),%xmm2
@@ -1475,28 +1554,48 @@
 	movdqu	%xmm3,48(%rdi)
 
 L$add_doneq:
-	addq	$576+8,%rsp
-	popq	%r15
-	popq	%r14
-	popq	%r13
-	popq	%r12
-	popq	%rbx
-	popq	%rbp
+	leaq	576+56(%rsp),%rsi
+
+	movq	-48(%rsi),%r15
+
+	movq	-40(%rsi),%r14
+
+	movq	-32(%rsi),%r13
+
+	movq	-24(%rsi),%r12
+
+	movq	-16(%rsi),%rbx
+
+	movq	-8(%rsi),%rbp
+
+	leaq	(%rsi),%rsp
+
+L$point_addq_epilogue:
 	.byte	0xf3,0xc3
 
+
 .globl	_ecp_nistz256_point_add_affine
 .private_extern _ecp_nistz256_point_add_affine
 
 .p2align	5
 _ecp_nistz256_point_add_affine:
+
 	pushq	%rbp
+
 	pushq	%rbx
+
 	pushq	%r12
+
 	pushq	%r13
+
 	pushq	%r14
+
 	pushq	%r15
+
 	subq	$480+8,%rsp
 
+L$add_affineq_body:
+
 	movdqu	0(%rsi),%xmm0
 	movq	%rdx,%rbx
 	movdqu	16(%rsi),%xmm1
@@ -1778,13 +1877,24 @@
 	movdqu	%xmm2,32(%rdi)
 	movdqu	%xmm3,48(%rdi)
 
-	addq	$480+8,%rsp
-	popq	%r15
-	popq	%r14
-	popq	%r13
-	popq	%r12
-	popq	%rbx
-	popq	%rbp
+	leaq	480+56(%rsp),%rsi
+
+	movq	-48(%rsi),%r15
+
+	movq	-40(%rsi),%r14
+
+	movq	-32(%rsi),%r13
+
+	movq	-24(%rsi),%r12
+
+	movq	-16(%rsi),%rbx
+
+	movq	-8(%rsi),%rbp
+
+	leaq	(%rsi),%rsp
+
+L$add_affineq_epilogue:
 	.byte	0xf3,0xc3
 
+
 #endif
diff --git a/mac-x86_64/crypto/fipsmodule/x86_64-mont.S b/mac-x86_64/crypto/fipsmodule/x86_64-mont.S
index 4904417..be3d13a 100644
--- a/mac-x86_64/crypto/fipsmodule/x86_64-mont.S
+++ b/mac-x86_64/crypto/fipsmodule/x86_64-mont.S
@@ -211,8 +211,7 @@
 	movq	%r9,%r15
 	jmp	L$sub
 .p2align	4
-L$sub:
-	sbbq	(%rcx,%r14,8),%rax
+L$sub:	sbbq	(%rcx,%r14,8),%rax
 	movq	%rax,(%rdi,%r14,8)
 	movq	8(%rsi,%r14,8),%rax
 	leaq	1(%r14),%r14
diff --git a/mac-x86_64/crypto/fipsmodule/x86_64-mont5.S b/mac-x86_64/crypto/fipsmodule/x86_64-mont5.S
index abc65f1..91980d8 100644
--- a/mac-x86_64/crypto/fipsmodule/x86_64-mont5.S
+++ b/mac-x86_64/crypto/fipsmodule/x86_64-mont5.S
@@ -395,8 +395,7 @@
 	movq	%r9,%r15
 	jmp	L$sub
 .p2align	4
-L$sub:
-	sbbq	(%rcx,%r14,8),%rax
+L$sub:	sbbq	(%rcx,%r14,8),%rax
 	movq	%rax,(%rdi,%r14,8)
 	movq	8(%rsi,%r14,8),%rax
 	leaq	1(%r14),%r14
diff --git a/win-x86_64/crypto/fipsmodule/aes-x86_64.asm b/win-x86_64/crypto/fipsmodule/aes-x86_64.asm
index f6a4edf..6b4c056 100644
--- a/win-x86_64/crypto/fipsmodule/aes-x86_64.asm
+++ b/win-x86_64/crypto/fipsmodule/aes-x86_64.asm
@@ -344,15 +344,23 @@
 	mov	rdx,r8
 
 
+
 	mov	rax,rsp
+
 	push	rbx
+
 	push	rbp
+
 	push	r12
+
 	push	r13
+
 	push	r14
+
 	push	r15
 
 
+
 	lea	rcx,[((-63))+rdx]
 	and	rsp,-64
 	sub	rcx,rsp
@@ -363,6 +371,7 @@
 
 	mov	QWORD[16+rsp],rsi
 	mov	QWORD[24+rsp],rax
+
 $L$enc_prologue:
 
 	mov	r15,rdx
@@ -389,22 +398,31 @@
 
 	mov	r9,QWORD[16+rsp]
 	mov	rsi,QWORD[24+rsp]
+
 	mov	DWORD[r9],eax
 	mov	DWORD[4+r9],ebx
 	mov	DWORD[8+r9],ecx
 	mov	DWORD[12+r9],edx
 
 	mov	r15,QWORD[((-48))+rsi]
+
 	mov	r14,QWORD[((-40))+rsi]
+
 	mov	r13,QWORD[((-32))+rsi]
+
 	mov	r12,QWORD[((-24))+rsi]
+
 	mov	rbp,QWORD[((-16))+rsi]
+
 	mov	rbx,QWORD[((-8))+rsi]
+
 	lea	rsp,[rsi]
+
 $L$enc_epilogue:
 	mov	rdi,QWORD[8+rsp]	;WIN64 epilogue
 	mov	rsi,QWORD[16+rsp]
 	DB	0F3h,0C3h		;repret
+
 $L$SEH_end_asm_AES_encrypt:
 
 ALIGN	16
@@ -800,15 +818,23 @@
 	mov	rdx,r8
 
 
+
 	mov	rax,rsp
+
 	push	rbx
+
 	push	rbp
+
 	push	r12
+
 	push	r13
+
 	push	r14
+
 	push	r15
 
 
+
 	lea	rcx,[((-63))+rdx]
 	and	rsp,-64
 	sub	rcx,rsp
@@ -819,6 +845,7 @@
 
 	mov	QWORD[16+rsp],rsi
 	mov	QWORD[24+rsp],rax
+
 $L$dec_prologue:
 
 	mov	r15,rdx
@@ -847,22 +874,31 @@
 
 	mov	r9,QWORD[16+rsp]
 	mov	rsi,QWORD[24+rsp]
+
 	mov	DWORD[r9],eax
 	mov	DWORD[4+r9],ebx
 	mov	DWORD[8+r9],ecx
 	mov	DWORD[12+r9],edx
 
 	mov	r15,QWORD[((-48))+rsi]
+
 	mov	r14,QWORD[((-40))+rsi]
+
 	mov	r13,QWORD[((-32))+rsi]
+
 	mov	r12,QWORD[((-24))+rsi]
+
 	mov	rbp,QWORD[((-16))+rsi]
+
 	mov	rbx,QWORD[((-8))+rsi]
+
 	lea	rsp,[rsi]
+
 $L$dec_epilogue:
 	mov	rdi,QWORD[8+rsp]	;WIN64 epilogue
 	mov	rsi,QWORD[16+rsp]
 	DB	0F3h,0C3h		;repret
+
 $L$SEH_end_asm_AES_decrypt:
 ALIGN	16
 global	asm_AES_set_encrypt_key
@@ -877,24 +913,36 @@
 	mov	rdx,r8
 
 
+
 	push	rbx
+
 	push	rbp
+
 	push	r12
+
 	push	r13
+
 	push	r14
+
 	push	r15
+
 	sub	rsp,8
+
 $L$enc_key_prologue:
 
 	call	_x86_64_AES_set_encrypt_key
 
 	mov	rbp,QWORD[40+rsp]
+
 	mov	rbx,QWORD[48+rsp]
+
 	add	rsp,56
+
 $L$enc_key_epilogue:
 	mov	rdi,QWORD[8+rsp]	;WIN64 epilogue
 	mov	rsi,QWORD[16+rsp]
 	DB	0F3h,0C3h		;repret
+
 $L$SEH_end_asm_AES_set_encrypt_key:
 
 
@@ -1149,13 +1197,21 @@
 	mov	rdx,r8
 
 
+
 	push	rbx
+
 	push	rbp
+
 	push	r12
+
 	push	r13
+
 	push	r14
+
 	push	r15
+
 	push	rdx
+
 $L$dec_key_prologue:
 
 	call	_x86_64_AES_set_encrypt_key
@@ -1323,16 +1379,24 @@
 	xor	rax,rax
 $L$abort:
 	mov	r15,QWORD[8+rsp]
+
 	mov	r14,QWORD[16+rsp]
+
 	mov	r13,QWORD[24+rsp]
+
 	mov	r12,QWORD[32+rsp]
+
 	mov	rbp,QWORD[40+rsp]
+
 	mov	rbx,QWORD[48+rsp]
+
 	add	rsp,56
+
 $L$dec_key_epilogue:
 	mov	rdi,QWORD[8+rsp]	;WIN64 epilogue
 	mov	rsi,QWORD[16+rsp]
 	DB	0F3h,0C3h		;repret
+
 $L$SEH_end_asm_AES_set_decrypt_key:
 ALIGN	16
 global	asm_AES_cbc_encrypt
@@ -1352,15 +1416,23 @@
 	mov	r9,QWORD[48+rsp]
 
 
+
 	cmp	rdx,0
 	je	NEAR $L$cbc_epilogue
 	pushfq
+
 	push	rbx
+
 	push	rbp
+
 	push	r12
+
 	push	r13
+
 	push	r14
+
 	push	r15
+
 $L$cbc_prologue:
 
 	cld
@@ -1407,7 +1479,9 @@
 
 	xchg	r15,rsp
 
+
 	mov	QWORD[16+rsp],r15
+
 $L$cbc_fast_body:
 	mov	QWORD[24+rsp],rdi
 	mov	QWORD[32+rsp],rsi
@@ -1789,19 +1863,29 @@
 ALIGN	16
 $L$cbc_exit:
 	mov	rsi,QWORD[16+rsp]
+
 	mov	r15,QWORD[rsi]
+
 	mov	r14,QWORD[8+rsi]
+
 	mov	r13,QWORD[16+rsi]
+
 	mov	r12,QWORD[24+rsi]
+
 	mov	rbp,QWORD[32+rsi]
+
 	mov	rbx,QWORD[40+rsi]
+
 	lea	rsp,[48+rsi]
+
 $L$cbc_popfq:
 	popfq
+
 $L$cbc_epilogue:
 	mov	rdi,QWORD[8+rsp]	;WIN64 epilogue
 	mov	rsi,QWORD[16+rsp]
 	DB	0F3h,0C3h		;repret
+
 $L$SEH_end_asm_AES_cbc_encrypt:
 ALIGN	64
 $L$AES_Te:
diff --git a/win-x86_64/crypto/fipsmodule/aesni-x86_64.asm b/win-x86_64/crypto/fipsmodule/aesni-x86_64.asm
index 13e9c5e..2a2980b 100644
--- a/win-x86_64/crypto/fipsmodule/aesni-x86_64.asm
+++ b/win-x86_64/crypto/fipsmodule/aesni-x86_64.asm
@@ -1100,6 +1100,7 @@
 	mov	r8,QWORD[40+rsp]
 
 
+
 	cmp	rdx,1
 	jne	NEAR $L$ctr32_bulk
 
@@ -1130,7 +1131,9 @@
 ALIGN	16
 $L$ctr32_bulk:
 	lea	r11,[rsp]
+
 	push	rbp
+
 	sub	rsp,288
 	and	rsp,-16
 	movaps	XMMWORD[(-168)+r11],xmm6
@@ -1686,11 +1689,14 @@
 	movaps	XMMWORD[96+rsp],xmm0
 	movaps	XMMWORD[112+rsp],xmm0
 	mov	rbp,QWORD[((-8))+r11]
+
 	lea	rsp,[r11]
+
 $L$ctr32_epilogue:
 	mov	rdi,QWORD[8+rsp]	;WIN64 epilogue
 	mov	rsi,QWORD[16+rsp]
 	DB	0F3h,0C3h		;repret
+
 $L$SEH_end_aesni_ctr32_encrypt_blocks:
 global	aesni_xts_encrypt
 
@@ -1708,8 +1714,11 @@
 	mov	r9,QWORD[48+rsp]
 
 
+
 	lea	r11,[rsp]
+
 	push	rbp
+
 	sub	rsp,272
 	and	rsp,-16
 	movaps	XMMWORD[(-168)+r11],xmm6
@@ -2185,11 +2194,14 @@
 	movaps	XMMWORD[80+rsp],xmm0
 	movaps	XMMWORD[96+rsp],xmm0
 	mov	rbp,QWORD[((-8))+r11]
+
 	lea	rsp,[r11]
+
 $L$xts_enc_epilogue:
 	mov	rdi,QWORD[8+rsp]	;WIN64 epilogue
 	mov	rsi,QWORD[16+rsp]
 	DB	0F3h,0C3h		;repret
+
 $L$SEH_end_aesni_xts_encrypt:
 global	aesni_xts_decrypt
 
@@ -2207,8 +2219,11 @@
 	mov	r9,QWORD[48+rsp]
 
 
+
 	lea	r11,[rsp]
+
 	push	rbp
+
 	sub	rsp,272
 	and	rsp,-16
 	movaps	XMMWORD[(-168)+r11],xmm6
@@ -2721,11 +2736,14 @@
 	movaps	XMMWORD[80+rsp],xmm0
 	movaps	XMMWORD[96+rsp],xmm0
 	mov	rbp,QWORD[((-8))+r11]
+
 	lea	rsp,[r11]
+
 $L$xts_dec_epilogue:
 	mov	rdi,QWORD[8+rsp]	;WIN64 epilogue
 	mov	rsi,QWORD[16+rsp]
 	DB	0F3h,0C3h		;repret
+
 $L$SEH_end_aesni_xts_decrypt:
 global	aesni_ocb_encrypt
 
@@ -2743,12 +2761,18 @@
 	mov	r9,QWORD[48+rsp]
 
 
+
 	lea	rax,[rsp]
 	push	rbx
+
 	push	rbp
+
 	push	r12
+
 	push	r13
+
 	push	r14
+
 	lea	rsp,[((-160))+rsp]
 	movaps	XMMWORD[rsp],xmm6
 	movaps	XMMWORD[16+rsp],xmm7
@@ -2949,15 +2973,22 @@
 	lea	rax,[((160+40))+rsp]
 $L$ocb_enc_pop:
 	mov	r14,QWORD[((-40))+rax]
+
 	mov	r13,QWORD[((-32))+rax]
+
 	mov	r12,QWORD[((-24))+rax]
+
 	mov	rbp,QWORD[((-16))+rax]
+
 	mov	rbx,QWORD[((-8))+rax]
+
 	lea	rsp,[rax]
+
 $L$ocb_enc_epilogue:
 	mov	rdi,QWORD[8+rsp]	;WIN64 epilogue
 	mov	rsi,QWORD[16+rsp]
 	DB	0F3h,0C3h		;repret
+
 $L$SEH_end_aesni_ocb_encrypt:
 
 
@@ -3182,12 +3213,18 @@
 	mov	r9,QWORD[48+rsp]
 
 
+
 	lea	rax,[rsp]
 	push	rbx
+
 	push	rbp
+
 	push	r12
+
 	push	r13
+
 	push	r14
+
 	lea	rsp,[((-160))+rsp]
 	movaps	XMMWORD[rsp],xmm6
 	movaps	XMMWORD[16+rsp],xmm7
@@ -3410,15 +3447,22 @@
 	lea	rax,[((160+40))+rsp]
 $L$ocb_dec_pop:
 	mov	r14,QWORD[((-40))+rax]
+
 	mov	r13,QWORD[((-32))+rax]
+
 	mov	r12,QWORD[((-24))+rax]
+
 	mov	rbp,QWORD[((-16))+rax]
+
 	mov	rbx,QWORD[((-8))+rax]
+
 	lea	rsp,[rax]
+
 $L$ocb_dec_epilogue:
 	mov	rdi,QWORD[8+rsp]	;WIN64 epilogue
 	mov	rsi,QWORD[16+rsp]
 	DB	0F3h,0C3h		;repret
+
 $L$SEH_end_aesni_ocb_decrypt:
 
 
@@ -3631,6 +3675,7 @@
 	mov	r9,QWORD[48+rsp]
 
 
+
 	test	rdx,rdx
 	jz	NEAR $L$cbc_ret
 
@@ -3724,7 +3769,9 @@
 ALIGN	16
 $L$cbc_decrypt_bulk:
 	lea	r11,[rsp]
+
 	push	rbp
+
 	sub	rsp,176
 	and	rsp,-16
 	movaps	XMMWORD[16+rsp],xmm6
@@ -4236,17 +4283,22 @@
 	movaps	xmm15,XMMWORD[160+rsp]
 	movaps	XMMWORD[160+rsp],xmm0
 	mov	rbp,QWORD[((-8))+r11]
+
 	lea	rsp,[r11]
+
 $L$cbc_ret:
 	mov	rdi,QWORD[8+rsp]	;WIN64 epilogue
 	mov	rsi,QWORD[16+rsp]
 	DB	0F3h,0C3h		;repret
+
 $L$SEH_end_aesni_cbc_encrypt:
 global	aesni_set_decrypt_key
 
 ALIGN	16
 aesni_set_decrypt_key:
+
 DB	0x48,0x83,0xEC,0x08
+
 	call	__aesni_set_encrypt_key
 	shl	edx,4
 	test	eax,eax
@@ -4279,7 +4331,9 @@
 	pxor	xmm0,xmm0
 $L$dec_key_ret:
 	add	rsp,8
+
 	DB	0F3h,0C3h		;repret
+
 $L$SEH_end_set_decrypt_key:
 
 global	aesni_set_encrypt_key
@@ -4287,7 +4341,9 @@
 ALIGN	16
 aesni_set_encrypt_key:
 __aesni_set_encrypt_key:
+
 DB	0x48,0x83,0xEC,0x08
+
 	mov	rax,-1
 	test	rcx,rcx
 	jz	NEAR $L$enc_key_ret
@@ -4581,7 +4637,9 @@
 	pxor	xmm4,xmm4
 	pxor	xmm5,xmm5
 	add	rsp,8
+
 	DB	0F3h,0C3h		;repret
+
 $L$SEH_end_set_encrypt_key:
 
 ALIGN	16
diff --git a/win-x86_64/crypto/fipsmodule/bsaes-x86_64.asm b/win-x86_64/crypto/fipsmodule/bsaes-x86_64.asm
index 9c6d129..9ea8253 100644
--- a/win-x86_64/crypto/fipsmodule/bsaes-x86_64.asm
+++ b/win-x86_64/crypto/fipsmodule/bsaes-x86_64.asm
@@ -1072,6 +1072,7 @@
 
 ALIGN	16
 bsaes_cbc_encrypt:
+
 	mov	r11d,DWORD[48+rsp]
 	cmp	r11d,0
 	jne	NEAR asm_AES_cbc_encrypt
@@ -1081,12 +1082,19 @@
 	mov	rax,rsp
 $L$cbc_dec_prologue:
 	push	rbp
+
 	push	rbx
+
 	push	r12
+
 	push	r13
+
 	push	r14
+
 	push	r15
+
 	lea	rsp,[((-72))+rsp]
+
 	mov	r10,QWORD[160+rsp]
 	lea	rsp,[((-160))+rsp]
 	movaps	XMMWORD[64+rsp],xmm6
@@ -1101,6 +1109,7 @@
 	movaps	XMMWORD[208+rsp],xmm15
 $L$cbc_dec_body:
 	mov	rbp,rsp
+
 	mov	eax,DWORD[240+r9]
 	mov	r12,rcx
 	mov	r13,rdx
@@ -1320,6 +1329,7 @@
 	ja	NEAR $L$cbc_dec_bzero
 
 	lea	rax,[120+rbp]
+
 	movaps	xmm6,XMMWORD[64+rbp]
 	movaps	xmm7,XMMWORD[80+rbp]
 	movaps	xmm8,XMMWORD[96+rbp]
@@ -1333,29 +1343,45 @@
 	lea	rax,[160+rax]
 $L$cbc_dec_tail:
 	mov	r15,QWORD[((-48))+rax]
+
 	mov	r14,QWORD[((-40))+rax]
+
 	mov	r13,QWORD[((-32))+rax]
+
 	mov	r12,QWORD[((-24))+rax]
+
 	mov	rbx,QWORD[((-16))+rax]
+
 	mov	rbp,QWORD[((-8))+rax]
+
 	lea	rsp,[rax]
+
 $L$cbc_dec_epilogue:
 	DB	0F3h,0C3h		;repret
 
 
+
 global	bsaes_ctr32_encrypt_blocks
 
 ALIGN	16
 bsaes_ctr32_encrypt_blocks:
+
 	mov	rax,rsp
 $L$ctr_enc_prologue:
 	push	rbp
+
 	push	rbx
+
 	push	r12
+
 	push	r13
+
 	push	r14
+
 	push	r15
+
 	lea	rsp,[((-72))+rsp]
+
 	mov	r10,QWORD[160+rsp]
 	lea	rsp,[((-160))+rsp]
 	movaps	XMMWORD[64+rsp],xmm6
@@ -1370,6 +1396,7 @@
 	movaps	XMMWORD[208+rsp],xmm15
 $L$ctr_enc_body:
 	mov	rbp,rsp
+
 	movdqu	xmm0,XMMWORD[r10]
 	mov	eax,DWORD[240+r9]
 	mov	r12,rcx
@@ -1544,6 +1571,7 @@
 	ja	NEAR $L$ctr_enc_bzero
 
 	lea	rax,[120+rbp]
+
 	movaps	xmm6,XMMWORD[64+rbp]
 	movaps	xmm7,XMMWORD[80+rbp]
 	movaps	xmm8,XMMWORD[96+rbp]
@@ -1557,28 +1585,44 @@
 	lea	rax,[160+rax]
 $L$ctr_enc_tail:
 	mov	r15,QWORD[((-48))+rax]
+
 	mov	r14,QWORD[((-40))+rax]
+
 	mov	r13,QWORD[((-32))+rax]
+
 	mov	r12,QWORD[((-24))+rax]
+
 	mov	rbx,QWORD[((-16))+rax]
+
 	mov	rbp,QWORD[((-8))+rax]
+
 	lea	rsp,[rax]
+
 $L$ctr_enc_epilogue:
 	DB	0F3h,0C3h		;repret
 
+
 global	bsaes_xts_encrypt
 
 ALIGN	16
 bsaes_xts_encrypt:
+
 	mov	rax,rsp
 $L$xts_enc_prologue:
 	push	rbp
+
 	push	rbx
+
 	push	r12
+
 	push	r13
+
 	push	r14
+
 	push	r15
+
 	lea	rsp,[((-72))+rsp]
+
 	mov	r10,QWORD[160+rsp]
 	mov	r11,QWORD[168+rsp]
 	lea	rsp,[((-160))+rsp]
@@ -1594,6 +1638,7 @@
 	movaps	XMMWORD[208+rsp],xmm15
 $L$xts_enc_body:
 	mov	rbp,rsp
+
 	mov	r12,rcx
 	mov	r13,rdx
 	mov	r14,r8
@@ -2020,6 +2065,7 @@
 	ja	NEAR $L$xts_enc_bzero
 
 	lea	rax,[120+rbp]
+
 	movaps	xmm6,XMMWORD[64+rbp]
 	movaps	xmm7,XMMWORD[80+rbp]
 	movaps	xmm8,XMMWORD[96+rbp]
@@ -2033,29 +2079,45 @@
 	lea	rax,[160+rax]
 $L$xts_enc_tail:
 	mov	r15,QWORD[((-48))+rax]
+
 	mov	r14,QWORD[((-40))+rax]
+
 	mov	r13,QWORD[((-32))+rax]
+
 	mov	r12,QWORD[((-24))+rax]
+
 	mov	rbx,QWORD[((-16))+rax]
+
 	mov	rbp,QWORD[((-8))+rax]
+
 	lea	rsp,[rax]
+
 $L$xts_enc_epilogue:
 	DB	0F3h,0C3h		;repret
 
 
+
 global	bsaes_xts_decrypt
 
 ALIGN	16
 bsaes_xts_decrypt:
+
 	mov	rax,rsp
 $L$xts_dec_prologue:
 	push	rbp
+
 	push	rbx
+
 	push	r12
+
 	push	r13
+
 	push	r14
+
 	push	r15
+
 	lea	rsp,[((-72))+rsp]
+
 	mov	r10,QWORD[160+rsp]
 	mov	r11,QWORD[168+rsp]
 	lea	rsp,[((-160))+rsp]
@@ -2523,6 +2585,7 @@
 	ja	NEAR $L$xts_dec_bzero
 
 	lea	rax,[120+rbp]
+
 	movaps	xmm6,XMMWORD[64+rbp]
 	movaps	xmm7,XMMWORD[80+rbp]
 	movaps	xmm8,XMMWORD[96+rbp]
@@ -2536,16 +2599,24 @@
 	lea	rax,[160+rax]
 $L$xts_dec_tail:
 	mov	r15,QWORD[((-48))+rax]
+
 	mov	r14,QWORD[((-40))+rax]
+
 	mov	r13,QWORD[((-32))+rax]
+
 	mov	r12,QWORD[((-24))+rax]
+
 	mov	rbx,QWORD[((-16))+rax]
+
 	mov	rbp,QWORD[((-8))+rax]
+
 	lea	rsp,[rax]
+
 $L$xts_dec_epilogue:
 	DB	0F3h,0C3h		;repret
 
 
+
 ALIGN	64
 _bsaes_const:
 $L$M0ISR:
diff --git a/win-x86_64/crypto/fipsmodule/p256-x86_64-asm.asm b/win-x86_64/crypto/fipsmodule/p256-x86_64-asm.asm
index 64db9d9..ec48141 100644
--- a/win-x86_64/crypto/fipsmodule/p256-x86_64-asm.asm
+++ b/win-x86_64/crypto/fipsmodule/p256-x86_64-asm.asm
@@ -34,9 +34,13 @@
 	mov	rsi,rdx
 
 
+
 	push	r12
+
 	push	r13
 
+$L$neg_body:
+
 	xor	r8,r8
 	xor	r9,r9
 	xor	r10,r10
@@ -69,11 +73,17 @@
 	mov	QWORD[16+rdi],r10
 	mov	QWORD[24+rdi],r11
 
-	pop	r13
-	pop	r12
+	mov	r13,QWORD[rsp]
+
+	mov	r12,QWORD[8+rsp]
+
+	lea	rsp,[16+rsp]
+
+$L$neg_epilogue:
 	mov	rdi,QWORD[8+rsp]	;WIN64 epilogue
 	mov	rsi,QWORD[16+rsp]
 	DB	0F3h,0C3h		;repret
+
 $L$SEH_end_ecp_nistz256_neg:
 
 
@@ -94,13 +104,21 @@
 	mov	rdx,r8
 
 
+
 $L$mul_mont:
 	push	rbp
+
 	push	rbx
+
 	push	r12
+
 	push	r13
+
 	push	r14
+
 	push	r15
+
+$L$mul_body:
 	mov	rbx,rdx
 	mov	rax,QWORD[rdx]
 	mov	r9,QWORD[rsi]
@@ -110,15 +128,25 @@
 
 	call	__ecp_nistz256_mul_montq
 $L$mul_mont_done:
-	pop	r15
-	pop	r14
-	pop	r13
-	pop	r12
-	pop	rbx
-	pop	rbp
+	mov	r15,QWORD[rsp]
+
+	mov	r14,QWORD[8+rsp]
+
+	mov	r13,QWORD[16+rsp]
+
+	mov	r12,QWORD[24+rsp]
+
+	mov	rbx,QWORD[32+rsp]
+
+	mov	rbp,QWORD[40+rsp]
+
+	lea	rsp,[48+rsp]
+
+$L$mul_epilogue:
 	mov	rdi,QWORD[8+rsp]	;WIN64 epilogue
 	mov	rsi,QWORD[16+rsp]
 	DB	0F3h,0C3h		;repret
+
 $L$SEH_end_ecp_nistz256_mul_mont:
 
 
@@ -356,12 +384,20 @@
 	mov	rsi,rdx
 
 
+
 	push	rbp
+
 	push	rbx
+
 	push	r12
+
 	push	r13
+
 	push	r14
+
 	push	r15
+
+$L$sqr_body:
 	mov	rax,QWORD[rsi]
 	mov	r14,QWORD[8+rsi]
 	mov	r15,QWORD[16+rsi]
@@ -369,15 +405,25 @@
 
 	call	__ecp_nistz256_sqr_montq
 $L$sqr_mont_done:
-	pop	r15
-	pop	r14
-	pop	r13
-	pop	r12
-	pop	rbx
-	pop	rbp
+	mov	r15,QWORD[rsp]
+
+	mov	r14,QWORD[8+rsp]
+
+	mov	r13,QWORD[16+rsp]
+
+	mov	r12,QWORD[24+rsp]
+
+	mov	rbx,QWORD[32+rsp]
+
+	mov	rbp,QWORD[40+rsp]
+
+	lea	rsp,[48+rsp]
+
+$L$sqr_epilogue:
 	mov	rdi,QWORD[8+rsp]	;WIN64 epilogue
 	mov	rsi,QWORD[16+rsp]
 	DB	0F3h,0C3h		;repret
+
 $L$SEH_end_ecp_nistz256_sqr_mont:
 
 
@@ -625,8 +671,8 @@
 	movaps	xmm14,XMMWORD[128+rsp]
 	movaps	xmm15,XMMWORD[144+rsp]
 	lea	rsp,[168+rsp]
-$L$SEH_end_ecp_nistz256_select_w5:
 	DB	0F3h,0C3h		;repret
+$L$SEH_end_ecp_nistz256_select_w5:
 
 
 
@@ -702,8 +748,8 @@
 	movaps	xmm14,XMMWORD[128+rsp]
 	movaps	xmm15,XMMWORD[144+rsp]
 	lea	rsp,[168+rsp]
-$L$SEH_end_ecp_nistz256_select_w7:
 	DB	0F3h,0C3h		;repret
+$L$SEH_end_ecp_nistz256_select_w7:
 
 
 
@@ -713,6 +759,7 @@
 $L$avx2_select_w5:
 	vzeroupper
 	lea	rax,[((-136))+rsp]
+	mov	r11,rsp
 $L$SEH_begin_ecp_nistz256_avx2_select_w5:
 DB	0x48,0x8d,0x60,0xe0
 DB	0xc5,0xf8,0x29,0x70,0xe0
@@ -786,9 +833,9 @@
 	movaps	xmm13,XMMWORD[112+rsp]
 	movaps	xmm14,XMMWORD[128+rsp]
 	movaps	xmm15,XMMWORD[144+rsp]
-	lea	rsp,[168+rsp]
-$L$SEH_end_ecp_nistz256_avx2_select_w5:
+	lea	rsp,[r11]
 	DB	0F3h,0C3h		;repret
+$L$SEH_end_ecp_nistz256_avx2_select_w5:
 
 
 
@@ -799,6 +846,7 @@
 ecp_nistz256_avx2_select_w7:
 $L$avx2_select_w7:
 	vzeroupper
+	mov	r11,rsp
 	lea	rax,[((-136))+rsp]
 $L$SEH_begin_ecp_nistz256_avx2_select_w7:
 DB	0x48,0x8d,0x60,0xe0
@@ -888,9 +936,9 @@
 	movaps	xmm13,XMMWORD[112+rsp]
 	movaps	xmm14,XMMWORD[128+rsp]
 	movaps	xmm15,XMMWORD[144+rsp]
-	lea	rsp,[168+rsp]
-$L$SEH_end_ecp_nistz256_avx2_select_w7:
+	lea	rsp,[r11]
 	DB	0F3h,0C3h		;repret
+$L$SEH_end_ecp_nistz256_avx2_select_w7:
 
 
 ALIGN	32
@@ -1025,14 +1073,23 @@
 	mov	rsi,rdx
 
 
+
 	push	rbp
+
 	push	rbx
+
 	push	r12
+
 	push	r13
+
 	push	r14
+
 	push	r15
+
 	sub	rsp,32*5+8
 
+$L$point_doubleq_body:
+
 $L$point_double_shortcutq:
 	movdqu	xmm0,XMMWORD[rsi]
 	mov	rbx,rsi
@@ -1214,16 +1271,27 @@
 DB	102,72,15,126,207
 	call	__ecp_nistz256_sub_fromq
 
-	add	rsp,32*5+8
-	pop	r15
-	pop	r14
-	pop	r13
-	pop	r12
-	pop	rbx
-	pop	rbp
+	lea	rsi,[((160+56))+rsp]
+
+	mov	r15,QWORD[((-48))+rsi]
+
+	mov	r14,QWORD[((-40))+rsi]
+
+	mov	r13,QWORD[((-32))+rsi]
+
+	mov	r12,QWORD[((-24))+rsi]
+
+	mov	rbx,QWORD[((-16))+rsi]
+
+	mov	rbp,QWORD[((-8))+rsi]
+
+	lea	rsp,[rsi]
+
+$L$point_doubleq_epilogue:
 	mov	rdi,QWORD[8+rsp]	;WIN64 epilogue
 	mov	rsi,QWORD[16+rsp]
 	DB	0F3h,0C3h		;repret
+
 $L$SEH_end_ecp_nistz256_point_double:
 global	ecp_nistz256_point_add
 
@@ -1238,14 +1306,23 @@
 	mov	rdx,r8
 
 
+
 	push	rbp
+
 	push	rbx
+
 	push	r12
+
 	push	r13
+
 	push	r14
+
 	push	r15
+
 	sub	rsp,32*18+8
 
+$L$point_addq_body:
+
 	movdqu	xmm0,XMMWORD[rsi]
 	movdqu	xmm1,XMMWORD[16+rsi]
 	movdqu	xmm2,XMMWORD[32+rsi]
@@ -1621,16 +1698,27 @@
 	movdqu	XMMWORD[48+rdi],xmm3
 
 $L$add_doneq:
-	add	rsp,32*18+8
-	pop	r15
-	pop	r14
-	pop	r13
-	pop	r12
-	pop	rbx
-	pop	rbp
+	lea	rsi,[((576+56))+rsp]
+
+	mov	r15,QWORD[((-48))+rsi]
+
+	mov	r14,QWORD[((-40))+rsi]
+
+	mov	r13,QWORD[((-32))+rsi]
+
+	mov	r12,QWORD[((-24))+rsi]
+
+	mov	rbx,QWORD[((-16))+rsi]
+
+	mov	rbp,QWORD[((-8))+rsi]
+
+	lea	rsp,[rsi]
+
+$L$point_addq_epilogue:
 	mov	rdi,QWORD[8+rsp]	;WIN64 epilogue
 	mov	rsi,QWORD[16+rsp]
 	DB	0F3h,0C3h		;repret
+
 $L$SEH_end_ecp_nistz256_point_add:
 global	ecp_nistz256_point_add_affine
 
@@ -1645,14 +1733,23 @@
 	mov	rdx,r8
 
 
+
 	push	rbp
+
 	push	rbx
+
 	push	r12
+
 	push	r13
+
 	push	r14
+
 	push	r15
+
 	sub	rsp,32*15+8
 
+$L$add_affineq_body:
+
 	movdqu	xmm0,XMMWORD[rsi]
 	mov	rbx,rdx
 	movdqu	xmm1,XMMWORD[16+rsi]
@@ -1934,14 +2031,257 @@
 	movdqu	XMMWORD[32+rdi],xmm2
 	movdqu	XMMWORD[48+rdi],xmm3
 
-	add	rsp,32*15+8
+	lea	rsi,[((480+56))+rsp]
+
+	mov	r15,QWORD[((-48))+rsi]
+
+	mov	r14,QWORD[((-40))+rsi]
+
+	mov	r13,QWORD[((-32))+rsi]
+
+	mov	r12,QWORD[((-24))+rsi]
+
+	mov	rbx,QWORD[((-16))+rsi]
+
+	mov	rbp,QWORD[((-8))+rsi]
+
+	lea	rsp,[rsi]
+
+$L$add_affineq_epilogue:
+	mov	rdi,QWORD[8+rsp]	;WIN64 epilogue
+	mov	rsi,QWORD[16+rsp]
+	DB	0F3h,0C3h		;repret
+
+$L$SEH_end_ecp_nistz256_point_add_affine:
+EXTERN	__imp_RtlVirtualUnwind
+
+
+ALIGN	16
+short_handler:
+	push	rsi
+	push	rdi
+	push	rbx
+	push	rbp
+	push	r12
+	push	r13
+	push	r14
+	push	r15
+	pushfq
+	sub	rsp,64
+
+	mov	rax,QWORD[120+r8]
+	mov	rbx,QWORD[248+r8]
+
+	mov	rsi,QWORD[8+r9]
+	mov	r11,QWORD[56+r9]
+
+	mov	r10d,DWORD[r11]
+	lea	r10,[r10*1+rsi]
+	cmp	rbx,r10
+	jb	NEAR $L$common_seh_tail
+
+	mov	rax,QWORD[152+r8]
+
+	mov	r10d,DWORD[4+r11]
+	lea	r10,[r10*1+rsi]
+	cmp	rbx,r10
+	jae	NEAR $L$common_seh_tail
+
+	lea	rax,[16+rax]
+
+	mov	r12,QWORD[((-8))+rax]
+	mov	r13,QWORD[((-16))+rax]
+	mov	QWORD[216+r8],r12
+	mov	QWORD[224+r8],r13
+
+	jmp	NEAR $L$common_seh_tail
+
+
+
+ALIGN	16
+full_handler:
+	push	rsi
+	push	rdi
+	push	rbx
+	push	rbp
+	push	r12
+	push	r13
+	push	r14
+	push	r15
+	pushfq
+	sub	rsp,64
+
+	mov	rax,QWORD[120+r8]
+	mov	rbx,QWORD[248+r8]
+
+	mov	rsi,QWORD[8+r9]
+	mov	r11,QWORD[56+r9]
+
+	mov	r10d,DWORD[r11]
+	lea	r10,[r10*1+rsi]
+	cmp	rbx,r10
+	jb	NEAR $L$common_seh_tail
+
+	mov	rax,QWORD[152+r8]
+
+	mov	r10d,DWORD[4+r11]
+	lea	r10,[r10*1+rsi]
+	cmp	rbx,r10
+	jae	NEAR $L$common_seh_tail
+
+	mov	r10d,DWORD[8+r11]
+	lea	rax,[r10*1+rax]
+
+	mov	rbp,QWORD[((-8))+rax]
+	mov	rbx,QWORD[((-16))+rax]
+	mov	r12,QWORD[((-24))+rax]
+	mov	r13,QWORD[((-32))+rax]
+	mov	r14,QWORD[((-40))+rax]
+	mov	r15,QWORD[((-48))+rax]
+	mov	QWORD[144+r8],rbx
+	mov	QWORD[160+r8],rbp
+	mov	QWORD[216+r8],r12
+	mov	QWORD[224+r8],r13
+	mov	QWORD[232+r8],r14
+	mov	QWORD[240+r8],r15
+
+$L$common_seh_tail:
+	mov	rdi,QWORD[8+rax]
+	mov	rsi,QWORD[16+rax]
+	mov	QWORD[152+r8],rax
+	mov	QWORD[168+r8],rsi
+	mov	QWORD[176+r8],rdi
+
+	mov	rdi,QWORD[40+r9]
+	mov	rsi,r8
+	mov	ecx,154
+	DD	0xa548f3fc
+
+	mov	rsi,r9
+	xor	rcx,rcx
+	mov	rdx,QWORD[8+rsi]
+	mov	r8,QWORD[rsi]
+	mov	r9,QWORD[16+rsi]
+	mov	r10,QWORD[40+rsi]
+	lea	r11,[56+rsi]
+	lea	r12,[24+rsi]
+	mov	QWORD[32+rsp],r10
+	mov	QWORD[40+rsp],r11
+	mov	QWORD[48+rsp],r12
+	mov	QWORD[56+rsp],rcx
+	call	QWORD[__imp_RtlVirtualUnwind]
+
+	mov	eax,1
+	add	rsp,64
+	popfq
 	pop	r15
 	pop	r14
 	pop	r13
 	pop	r12
-	pop	rbx
 	pop	rbp
-	mov	rdi,QWORD[8+rsp]	;WIN64 epilogue
-	mov	rsi,QWORD[16+rsp]
+	pop	rbx
+	pop	rdi
+	pop	rsi
 	DB	0F3h,0C3h		;repret
-$L$SEH_end_ecp_nistz256_point_add_affine:
+
+
+section	.pdata rdata align=4
+ALIGN	4
+	DD	$L$SEH_begin_ecp_nistz256_neg wrt ..imagebase
+	DD	$L$SEH_end_ecp_nistz256_neg wrt ..imagebase
+	DD	$L$SEH_info_ecp_nistz256_neg wrt ..imagebase
+
+	DD	$L$SEH_begin_ecp_nistz256_mul_mont wrt ..imagebase
+	DD	$L$SEH_end_ecp_nistz256_mul_mont wrt ..imagebase
+	DD	$L$SEH_info_ecp_nistz256_mul_mont wrt ..imagebase
+
+	DD	$L$SEH_begin_ecp_nistz256_sqr_mont wrt ..imagebase
+	DD	$L$SEH_end_ecp_nistz256_sqr_mont wrt ..imagebase
+	DD	$L$SEH_info_ecp_nistz256_sqr_mont wrt ..imagebase
+
+	DD	$L$SEH_begin_ecp_nistz256_select_w5 wrt ..imagebase
+	DD	$L$SEH_end_ecp_nistz256_select_w5 wrt ..imagebase
+	DD	$L$SEH_info_ecp_nistz256_select_wX wrt ..imagebase
+
+	DD	$L$SEH_begin_ecp_nistz256_select_w7 wrt ..imagebase
+	DD	$L$SEH_end_ecp_nistz256_select_w7 wrt ..imagebase
+	DD	$L$SEH_info_ecp_nistz256_select_wX wrt ..imagebase
+	DD	$L$SEH_begin_ecp_nistz256_avx2_select_w5 wrt ..imagebase
+	DD	$L$SEH_end_ecp_nistz256_avx2_select_w5 wrt ..imagebase
+	DD	$L$SEH_info_ecp_nistz256_avx2_select_wX wrt ..imagebase
+
+	DD	$L$SEH_begin_ecp_nistz256_avx2_select_w7 wrt ..imagebase
+	DD	$L$SEH_end_ecp_nistz256_avx2_select_w7 wrt ..imagebase
+	DD	$L$SEH_info_ecp_nistz256_avx2_select_wX wrt ..imagebase
+	DD	$L$SEH_begin_ecp_nistz256_point_double wrt ..imagebase
+	DD	$L$SEH_end_ecp_nistz256_point_double wrt ..imagebase
+	DD	$L$SEH_info_ecp_nistz256_point_double wrt ..imagebase
+
+	DD	$L$SEH_begin_ecp_nistz256_point_add wrt ..imagebase
+	DD	$L$SEH_end_ecp_nistz256_point_add wrt ..imagebase
+	DD	$L$SEH_info_ecp_nistz256_point_add wrt ..imagebase
+
+	DD	$L$SEH_begin_ecp_nistz256_point_add_affine wrt ..imagebase
+	DD	$L$SEH_end_ecp_nistz256_point_add_affine wrt ..imagebase
+	DD	$L$SEH_info_ecp_nistz256_point_add_affine wrt ..imagebase
+
+section	.xdata rdata align=8
+ALIGN	8
+$L$SEH_info_ecp_nistz256_neg:
+DB	9,0,0,0
+	DD	short_handler wrt ..imagebase
+	DD	$L$neg_body wrt ..imagebase,$L$neg_epilogue wrt ..imagebase
+$L$SEH_info_ecp_nistz256_mul_mont:
+DB	9,0,0,0
+	DD	full_handler wrt ..imagebase
+	DD	$L$mul_body wrt ..imagebase,$L$mul_epilogue wrt ..imagebase
+	DD	48,0
+$L$SEH_info_ecp_nistz256_sqr_mont:
+DB	9,0,0,0
+	DD	full_handler wrt ..imagebase
+	DD	$L$sqr_body wrt ..imagebase,$L$sqr_epilogue wrt ..imagebase
+	DD	48,0
+$L$SEH_info_ecp_nistz256_select_wX:
+DB	0x01,0x33,0x16,0x00
+DB	0x33,0xf8,0x09,0x00
+DB	0x2e,0xe8,0x08,0x00
+DB	0x29,0xd8,0x07,0x00
+DB	0x24,0xc8,0x06,0x00
+DB	0x1f,0xb8,0x05,0x00
+DB	0x1a,0xa8,0x04,0x00
+DB	0x15,0x98,0x03,0x00
+DB	0x10,0x88,0x02,0x00
+DB	0x0c,0x78,0x01,0x00
+DB	0x08,0x68,0x00,0x00
+DB	0x04,0x01,0x15,0x00
+ALIGN	8
+$L$SEH_info_ecp_nistz256_avx2_select_wX:
+DB	0x01,0x36,0x17,0x0b
+DB	0x36,0xf8,0x09,0x00
+DB	0x31,0xe8,0x08,0x00
+DB	0x2c,0xd8,0x07,0x00
+DB	0x27,0xc8,0x06,0x00
+DB	0x22,0xb8,0x05,0x00
+DB	0x1d,0xa8,0x04,0x00
+DB	0x18,0x98,0x03,0x00
+DB	0x13,0x88,0x02,0x00
+DB	0x0e,0x78,0x01,0x00
+DB	0x09,0x68,0x00,0x00
+DB	0x04,0x01,0x15,0x00
+DB	0x00,0xb3,0x00,0x00
+ALIGN	8
+$L$SEH_info_ecp_nistz256_point_double:
+DB	9,0,0,0
+	DD	full_handler wrt ..imagebase
+	DD	$L$point_doubleq_body wrt ..imagebase,$L$point_doubleq_epilogue wrt ..imagebase
+	DD	32*5+56,0
+$L$SEH_info_ecp_nistz256_point_add:
+DB	9,0,0,0
+	DD	full_handler wrt ..imagebase
+	DD	$L$point_addq_body wrt ..imagebase,$L$point_addq_epilogue wrt ..imagebase
+	DD	32*18+56,0
+$L$SEH_info_ecp_nistz256_point_add_affine:
+DB	9,0,0,0
+	DD	full_handler wrt ..imagebase
+	DD	$L$add_affineq_body wrt ..imagebase,$L$add_affineq_epilogue wrt ..imagebase
+	DD	32*15+56,0
diff --git a/win-x86_64/crypto/fipsmodule/x86_64-mont.asm b/win-x86_64/crypto/fipsmodule/x86_64-mont.asm
index dd93341..1a9da51 100644
--- a/win-x86_64/crypto/fipsmodule/x86_64-mont.asm
+++ b/win-x86_64/crypto/fipsmodule/x86_64-mont.asm
@@ -226,8 +226,7 @@
 	mov	r15,r9
 	jmp	NEAR $L$sub
 ALIGN	16
-$L$sub:
-	sbb	rax,QWORD[r14*8+rcx]
+$L$sub:	sbb	rax,QWORD[r14*8+rcx]
 	mov	QWORD[r14*8+rdi],rax
 	mov	rax,QWORD[8+r14*8+rsi]
 	lea	r14,[1+r14]
diff --git a/win-x86_64/crypto/fipsmodule/x86_64-mont5.asm b/win-x86_64/crypto/fipsmodule/x86_64-mont5.asm
index 1bcbc5d..b330641 100644
--- a/win-x86_64/crypto/fipsmodule/x86_64-mont5.asm
+++ b/win-x86_64/crypto/fipsmodule/x86_64-mont5.asm
@@ -410,8 +410,7 @@
 	mov	r15,r9
 	jmp	NEAR $L$sub
 ALIGN	16
-$L$sub:
-	sbb	rax,QWORD[r14*8+rcx]
+$L$sub:	sbb	rax,QWORD[r14*8+rcx]
 	mov	QWORD[r14*8+rdi],rax
 	mov	rax,QWORD[8+r14*8+rsi]
 	lea	r14,[1+r14]