Merge branch 'core-objtool-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull 'objtool' stack frame validation from Ingo Molnar:
 "This tree adds a new kernel build-time object file validation feature
  (ONFIG_STACK_VALIDATION=y): kernel stack frame correctness validation.
  It was written by and is maintained by Josh Poimboeuf.

  The motivation: there's a category of hard to find kernel bugs, most
  of them in assembly code (but also occasionally in C code), that
  degrades the quality of kernel stack dumps/backtraces.  These bugs are
  hard to detect at the source code level.  Such bugs result in
  incorrect/incomplete backtraces most of time - but can also in some
  rare cases result in crashes or other undefined behavior.

  The build time correctness checking is done via the new 'objtool'
  user-space utility that was written for this purpose and which is
  hosted in the kernel repository in tools/objtool/.  The tool's (very
  simple) UI and source code design is shaped after Git and perf and
  shares quite a bit of infrastructure with tools/perf (which tooling
  infrastructure sharing effort got merged via perf and is already
  upstream).  Objtool follows the well-known kernel coding style.

  Objtool does not try to check .c or .S files, it instead analyzes the
  resulting .o generated machine code from first principles: it decodes
  the instruction stream and interprets it.  (Right now objtool supports
  the x86-64 architecture.)

  From tools/objtool/Documentation/stack-validation.txt:

   "The kernel CONFIG_STACK_VALIDATION option enables a host tool named
    objtool which runs at compile time.  It has a "check" subcommand
    which analyzes every .o file and ensures the validity of its stack
    metadata.  It enforces a set of rules on asm code and C inline
    assembly code so that stack traces can be reliable.

    Currently it only checks frame pointer usage, but there are plans to
    add CFI validation for C files and CFI generation for asm files.

    For each function, it recursively follows all possible code paths
    and validates the correct frame pointer state at each instruction.

    It also follows code paths involving special sections, like
    .altinstructions, __jump_table, and __ex_table, which can add
    alternative execution paths to a given instruction (or set of
    instructions).  Similarly, it knows how to follow switch statements,
    for which gcc sometimes uses jump tables."

  When this new kernel option is enabled (it's disabled by default), the
  tool, if it finds any suspicious assembly code pattern, outputs
  warnings in compiler warning format:

    warning: objtool: rtlwifi_rate_mapping()+0x2e7: frame pointer state mismatch
    warning: objtool: cik_tiling_mode_table_init()+0x6ce: call without frame pointer save/setup
    warning: objtool:__schedule()+0x3c0: duplicate frame pointer save
    warning: objtool:__schedule()+0x3fd: sibling call from callable instruction with changed frame pointer

  ... so that scripts that pick up compiler warnings will notice them.
  All known warnings triggered by the tool are fixed by the tree, most
  of the commits in fact prepare the kernel to be warning-free.  Most of
  them are bugfixes or cleanups that stand on their own, but there are
  also some annotations of 'special' stack frames for justified cases
  such entries to JIT-ed code (BPF) or really special boot time code.

  There are two other long-term motivations behind this tool as well:

   - To improve the quality and reliability of kernel stack frames, so
     that they can be used for optimized live patching.

   - To create independent infrastructure to check the correctness of
     CFI stack frames at build time.  CFI debuginfo is notoriously
     unreliable and we cannot use it in the kernel as-is without extra
     checking done both on the kernel side and on the build side.

  The quality of kernel stack frames matters to debuggability as well,
  so IMO we can merge this without having to consider the live patching
  or CFI debuginfo angle"

* 'core-objtool-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (52 commits)
  objtool: Only print one warning per function
  objtool: Add several performance improvements
  tools: Copy hashtable.h into tools directory
  objtool: Fix false positive warnings for functions with multiple switch statements
  objtool: Rename some variables and functions
  objtool: Remove superflous INIT_LIST_HEAD
  objtool: Add helper macros for traversing instructions
  objtool: Fix false positive warnings related to sibling calls
  objtool: Compile with debugging symbols
  objtool: Detect infinite recursion
  objtool: Prevent infinite recursion in noreturn detection
  objtool: Detect and warn if libelf is missing and don't break the build
  tools: Support relative directory path for 'O='
  objtool: Support CROSS_COMPILE
  x86/asm/decoder: Use explicitly signed chars
  objtool: Enable stack metadata validation on 64-bit x86
  objtool: Add CONFIG_STACK_VALIDATION option
  objtool: Add tool to perform compile-time stack metadata validation
  x86/kprobes: Mark kretprobe_trampoline() stack frame as non-standard
  sched: Always inline context_switch()
  ...

43 files changed, 358 insertions, 185 deletions

diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index 3c74b54..d07cca6 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -155,6 +155,7 @@ config X86
 	select VIRT_TO_BUS
 	select X86_DEV_DMA_OPS			if X86_64
 	select X86_FEATURE_NAMES		if PROC_FS
+	select HAVE_STACK_VALIDATION		if X86_64
 
 config INSTRUCTION_DECODER
 	def_bool y
diff --git a/arch/x86/boot/Makefile b/arch/x86/boot/Makefile
index bbe1a62..0bf6749 100644
--- a/arch/x86/boot/Makefile
+++ b/arch/x86/boot/Makefile
@@ -9,7 +9,8 @@
 # Changed by many, many contributors over the years.
 #
 
-KASAN_SANITIZE := n
+KASAN_SANITIZE			:= n
+OBJECT_FILES_NON_STANDARD	:= y
 
 # If you want to preset the SVGA mode, uncomment the next line and
 # set SVGA_MODE to whatever number you want.
diff --git a/arch/x86/boot/compressed/Makefile b/arch/x86/boot/compressed/Makefile
index f9ce75d..5e1d26e 100644
--- a/arch/x86/boot/compressed/Makefile
+++ b/arch/x86/boot/compressed/Makefile
@@ -16,7 +16,8 @@
 #	(see scripts/Makefile.lib size_append)
 #	compressed vmlinux.bin.all + u32 size of vmlinux.bin.all
 
-KASAN_SANITIZE := n
+KASAN_SANITIZE			:= n
+OBJECT_FILES_NON_STANDARD	:= y
 
 targets := vmlinux vmlinux.bin vmlinux.bin.gz vmlinux.bin.bz2 vmlinux.bin.lzma \
 	vmlinux.bin.xz vmlinux.bin.lzo vmlinux.bin.lz4
diff --git a/arch/x86/crypto/aesni-intel_asm.S b/arch/x86/crypto/aesni-intel_asm.S
index 6bd2c6c..383a6f8 100644
--- a/arch/x86/crypto/aesni-intel_asm.S
+++ b/arch/x86/crypto/aesni-intel_asm.S
@@ -31,6 +31,7 @@
 
 #include <linux/linkage.h>
 #include <asm/inst.h>
+#include <asm/frame.h>
 
 /*
  * The following macros are used to move an (un)aligned 16 byte value to/from
@@ -1800,11 +1801,12 @@ ENDPROC(_key_expansion_256b)
  *                   unsigned int key_len)
  */
 ENTRY(aesni_set_key)
+	FRAME_BEGIN
 #ifndef __x86_64__
 	pushl KEYP
-	movl 8(%esp), KEYP		# ctx
-	movl 12(%esp), UKEYP		# in_key
-	movl 16(%esp), %edx		# key_len
+	movl (FRAME_OFFSET+8)(%esp), KEYP	# ctx
+	movl (FRAME_OFFSET+12)(%esp), UKEYP	# in_key
+	movl (FRAME_OFFSET+16)(%esp), %edx	# key_len
 #endif
 	movups (UKEYP), %xmm0		# user key (first 16 bytes)
 	movaps %xmm0, (KEYP)
@@ -1905,6 +1907,7 @@ ENTRY(aesni_set_key)
 #ifndef __x86_64__
 	popl KEYP
 #endif
+	FRAME_END
 	ret
 ENDPROC(aesni_set_key)
 
@@ -1912,12 +1915,13 @@ ENDPROC(aesni_set_key)
  * void aesni_enc(struct crypto_aes_ctx *ctx, u8 *dst, const u8 *src)
  */
 ENTRY(aesni_enc)
+	FRAME_BEGIN
 #ifndef __x86_64__
 	pushl KEYP
 	pushl KLEN
-	movl 12(%esp), KEYP
-	movl 16(%esp), OUTP
-	movl 20(%esp), INP
+	movl (FRAME_OFFSET+12)(%esp), KEYP	# ctx
+	movl (FRAME_OFFSET+16)(%esp), OUTP	# dst
+	movl (FRAME_OFFSET+20)(%esp), INP	# src
 #endif
 	movl 480(KEYP), KLEN		# key length
 	movups (INP), STATE		# input
@@ -1927,6 +1931,7 @@ ENTRY(aesni_enc)
 	popl KLEN
 	popl KEYP
 #endif
+	FRAME_END
 	ret
 ENDPROC(aesni_enc)
 
@@ -2101,12 +2106,13 @@ ENDPROC(_aesni_enc4)
  * void aesni_dec (struct crypto_aes_ctx *ctx, u8 *dst, const u8 *src)
  */
 ENTRY(aesni_dec)
+	FRAME_BEGIN
 #ifndef __x86_64__
 	pushl KEYP
 	pushl KLEN
-	movl 12(%esp), KEYP
-	movl 16(%esp), OUTP
-	movl 20(%esp), INP
+	movl (FRAME_OFFSET+12)(%esp), KEYP	# ctx
+	movl (FRAME_OFFSET+16)(%esp), OUTP	# dst
+	movl (FRAME_OFFSET+20)(%esp), INP	# src
 #endif
 	mov 480(KEYP), KLEN		# key length
 	add $240, KEYP
@@ -2117,6 +2123,7 @@ ENTRY(aesni_dec)
 	popl KLEN
 	popl KEYP
 #endif
+	FRAME_END
 	ret
 ENDPROC(aesni_dec)
 
@@ -2292,14 +2299,15 @@ ENDPROC(_aesni_dec4)
  *		      size_t len)
  */
 ENTRY(aesni_ecb_enc)
+	FRAME_BEGIN
 #ifndef __x86_64__
 	pushl LEN
 	pushl KEYP
 	pushl KLEN
-	movl 16(%esp), KEYP
-	movl 20(%esp), OUTP
-	movl 24(%esp), INP
-	movl 28(%esp), LEN
+	movl (FRAME_OFFSET+16)(%esp), KEYP	# ctx
+	movl (FRAME_OFFSET+20)(%esp), OUTP	# dst
+	movl (FRAME_OFFSET+24)(%esp), INP	# src
+	movl (FRAME_OFFSET+28)(%esp), LEN	# len
 #endif
 	test LEN, LEN		# check length
 	jz .Lecb_enc_ret
@@ -2342,6 +2350,7 @@ ENTRY(aesni_ecb_enc)
 	popl KEYP
 	popl LEN
 #endif
+	FRAME_END
 	ret
 ENDPROC(aesni_ecb_enc)
 
@@ -2350,14 +2359,15 @@ ENDPROC(aesni_ecb_enc)
  *		      size_t len);
  */
 ENTRY(aesni_ecb_dec)
+	FRAME_BEGIN
 #ifndef __x86_64__
 	pushl LEN
 	pushl KEYP
 	pushl KLEN
-	movl 16(%esp), KEYP
-	movl 20(%esp), OUTP
-	movl 24(%esp), INP
-	movl 28(%esp), LEN
+	movl (FRAME_OFFSET+16)(%esp), KEYP	# ctx
+	movl (FRAME_OFFSET+20)(%esp), OUTP	# dst
+	movl (FRAME_OFFSET+24)(%esp), INP	# src
+	movl (FRAME_OFFSET+28)(%esp), LEN	# len
 #endif
 	test LEN, LEN
 	jz .Lecb_dec_ret
@@ -2401,6 +2411,7 @@ ENTRY(aesni_ecb_dec)
 	popl KEYP
 	popl LEN
 #endif
+	FRAME_END
 	ret
 ENDPROC(aesni_ecb_dec)
 
@@ -2409,16 +2420,17 @@ ENDPROC(aesni_ecb_dec)
  *		      size_t len, u8 *iv)
  */
 ENTRY(aesni_cbc_enc)
+	FRAME_BEGIN
 #ifndef __x86_64__
 	pushl IVP
 	pushl LEN
 	pushl KEYP
 	pushl KLEN
-	movl 20(%esp), KEYP
-	movl 24(%esp), OUTP
-	movl 28(%esp), INP
-	movl 32(%esp), LEN
-	movl 36(%esp), IVP
+	movl (FRAME_OFFSET+20)(%esp), KEYP	# ctx
+	movl (FRAME_OFFSET+24)(%esp), OUTP	# dst
+	movl (FRAME_OFFSET+28)(%esp), INP	# src
+	movl (FRAME_OFFSET+32)(%esp), LEN	# len
+	movl (FRAME_OFFSET+36)(%esp), IVP	# iv
 #endif
 	cmp $16, LEN
 	jb .Lcbc_enc_ret
@@ -2443,6 +2455,7 @@ ENTRY(aesni_cbc_enc)
 	popl LEN
 	popl IVP
 #endif
+	FRAME_END
 	ret
 ENDPROC(aesni_cbc_enc)
 
@@ -2451,16 +2464,17 @@ ENDPROC(aesni_cbc_enc)
  *		      size_t len, u8 *iv)
  */
 ENTRY(aesni_cbc_dec)
+	FRAME_BEGIN
 #ifndef __x86_64__
 	pushl IVP
 	pushl LEN
 	pushl KEYP
 	pushl KLEN
-	movl 20(%esp), KEYP
-	movl 24(%esp), OUTP
-	movl 28(%esp), INP
-	movl 32(%esp), LEN
-	movl 36(%esp), IVP
+	movl (FRAME_OFFSET+20)(%esp), KEYP	# ctx
+	movl (FRAME_OFFSET+24)(%esp), OUTP	# dst
+	movl (FRAME_OFFSET+28)(%esp), INP	# src
+	movl (FRAME_OFFSET+32)(%esp), LEN	# len
+	movl (FRAME_OFFSET+36)(%esp), IVP	# iv
 #endif
 	cmp $16, LEN
 	jb .Lcbc_dec_just_ret
@@ -2534,13 +2548,16 @@ ENTRY(aesni_cbc_dec)
 	popl LEN
 	popl IVP
 #endif
+	FRAME_END
 	ret
 ENDPROC(aesni_cbc_dec)
 
 #ifdef __x86_64__
+.pushsection .rodata
 .align 16
 .Lbswap_mask:
 	.byte 15, 14, 13, 12, 11, 10, 9, 8, 7, 6, 5, 4, 3, 2, 1, 0
+.popsection
 
 /*
  * _aesni_inc_init:	internal ABI
@@ -2598,6 +2615,7 @@ ENDPROC(_aesni_inc)
  *		      size_t len, u8 *iv)
  */
 ENTRY(aesni_ctr_enc)
+	FRAME_BEGIN
 	cmp $16, LEN
 	jb .Lctr_enc_just_ret
 	mov 480(KEYP), KLEN
@@ -2651,6 +2669,7 @@ ENTRY(aesni_ctr_enc)
 .Lctr_enc_ret:
 	movups IV, (IVP)
 .Lctr_enc_just_ret:
+	FRAME_END
 	ret
 ENDPROC(aesni_ctr_enc)
 
@@ -2677,6 +2696,7 @@ ENDPROC(aesni_ctr_enc)
  *			 bool enc, u8 *iv)
  */
 ENTRY(aesni_xts_crypt8)
+	FRAME_BEGIN
 	cmpb $0, %cl
 	movl $0, %ecx
 	movl $240, %r10d
@@ -2777,6 +2797,7 @@ ENTRY(aesni_xts_crypt8)
 	pxor INC, STATE4
 	movdqu STATE4, 0x70(OUTP)
 
+	FRAME_END
 	ret
 ENDPROC(aesni_xts_crypt8)
 
diff --git a/arch/x86/crypto/camellia-aesni-avx-asm_64.S b/arch/x86/crypto/camellia-aesni-avx-asm_64.S
index ce71f92..aa9e8bd 100644
--- a/arch/x86/crypto/camellia-aesni-avx-asm_64.S
+++ b/arch/x86/crypto/camellia-aesni-avx-asm_64.S
@@ -16,6 +16,7 @@
  */
 
 #include <linux/linkage.h>
+#include <asm/frame.h>
 
 #define CAMELLIA_TABLE_BYTE_LEN 272
 
@@ -726,6 +727,7 @@ __camellia_enc_blk16:
 	 *	%xmm0..%xmm15: 16 encrypted blocks, order swapped:
 	 *       7, 8, 6, 5, 4, 3, 2, 1, 0, 15, 14, 13, 12, 11, 10, 9, 8
 	 */
+	FRAME_BEGIN
 
 	leaq 8 * 16(%rax), %rcx;
 
@@ -780,6 +782,7 @@ __camellia_enc_blk16:
 		    %xmm8, %xmm9, %xmm10, %xmm11, %xmm12, %xmm13, %xmm14,
 		    %xmm15, (key_table)(CTX, %r8, 8), (%rax), 1 * 16(%rax));
 
+	FRAME_END
 	ret;
 
 .align 8
@@ -812,6 +815,7 @@ __camellia_dec_blk16:
 	 *	%xmm0..%xmm15: 16 plaintext blocks, order swapped:
 	 *       7, 8, 6, 5, 4, 3, 2, 1, 0, 15, 14, 13, 12, 11, 10, 9, 8
 	 */
+	FRAME_BEGIN
 
 	leaq 8 * 16(%rax), %rcx;
 
@@ -865,6 +869,7 @@ __camellia_dec_blk16:
 		    %xmm8, %xmm9, %xmm10, %xmm11, %xmm12, %xmm13, %xmm14,
 		    %xmm15, (key_table)(CTX), (%rax), 1 * 16(%rax));
 
+	FRAME_END
 	ret;
 
 .align 8
@@ -890,6 +895,7 @@ ENTRY(camellia_ecb_enc_16way)
 	 *	%rsi: dst (16 blocks)
 	 *	%rdx: src (16 blocks)
 	 */
+	 FRAME_BEGIN
 
 	inpack16_pre(%xmm0, %xmm1, %xmm2, %xmm3, %xmm4, %xmm5, %xmm6, %xmm7,
 		     %xmm8, %xmm9, %xmm10, %xmm11, %xmm12, %xmm13, %xmm14,
@@ -904,6 +910,7 @@ ENTRY(camellia_ecb_enc_16way)
 		     %xmm15, %xmm14, %xmm13, %xmm12, %xmm11, %xmm10, %xmm9,
 		     %xmm8, %rsi);
 
+	FRAME_END
 	ret;
 ENDPROC(camellia_ecb_enc_16way)
 
@@ -913,6 +920,7 @@ ENTRY(camellia_ecb_dec_16way)
 	 *	%rsi: dst (16 blocks)
 	 *	%rdx: src (16 blocks)
 	 */
+	 FRAME_BEGIN
 
 	cmpl $16, key_length(CTX);
 	movl $32, %r8d;
@@ -932,6 +940,7 @@ ENTRY(camellia_ecb_dec_16way)
 		     %xmm15, %xmm14, %xmm13, %xmm12, %xmm11, %xmm10, %xmm9,
 		     %xmm8, %rsi);
 
+	FRAME_END
 	ret;
 ENDPROC(camellia_ecb_dec_16way)
 
@@ -941,6 +950,7 @@ ENTRY(camellia_cbc_dec_16way)
 	 *	%rsi: dst (16 blocks)
 	 *	%rdx: src (16 blocks)
 	 */
+	FRAME_BEGIN
 
 	cmpl $16, key_length(CTX);
 	movl $32, %r8d;
@@ -981,6 +991,7 @@ ENTRY(camellia_cbc_dec_16way)
 		     %xmm15, %xmm14, %xmm13, %xmm12, %xmm11, %xmm10, %xmm9,
 		     %xmm8, %rsi);
 
+	FRAME_END
 	ret;
 ENDPROC(camellia_cbc_dec_16way)
 
@@ -997,6 +1008,7 @@ ENTRY(camellia_ctr_16way)
 	 *	%rdx: src (16 blocks)
 	 *	%rcx: iv (little endian, 128bit)
 	 */
+	FRAME_BEGIN
 
 	subq $(16 * 16), %rsp;
 	movq %rsp, %rax;
@@ -1092,6 +1104,7 @@ ENTRY(camellia_ctr_16way)
 		     %xmm15, %xmm14, %xmm13, %xmm12, %xmm11, %xmm10, %xmm9,
 		     %xmm8, %rsi);
 
+	FRAME_END
 	ret;
 ENDPROC(camellia_ctr_16way)
 
@@ -1112,6 +1125,7 @@ camellia_xts_crypt_16way:
 	 *	%r8: index for input whitening key
 	 *	%r9: pointer to  __camellia_enc_blk16 or __camellia_dec_blk16
 	 */
+	FRAME_BEGIN
 
 	subq $(16 * 16), %rsp;
 	movq %rsp, %rax;
@@ -1234,6 +1248,7 @@ camellia_xts_crypt_16way:
 		     %xmm15, %xmm14, %xmm13, %xmm12, %xmm11, %xmm10, %xmm9,
 		     %xmm8, %rsi);
 
+	FRAME_END
 	ret;
 ENDPROC(camellia_xts_crypt_16way)
 
diff --git a/arch/x86/crypto/camellia-aesni-avx2-asm_64.S b/arch/x86/crypto/camellia-aesni-avx2-asm_64.S
index 0e0b886..16186c1 100644
--- a/arch/x86/crypto/camellia-aesni-avx2-asm_64.S
+++ b/arch/x86/crypto/camellia-aesni-avx2-asm_64.S
@@ -11,6 +11,7 @@
  */
 
 #include <linux/linkage.h>
+#include <asm/frame.h>
 
 #define CAMELLIA_TABLE_BYTE_LEN 272
 
@@ -766,6 +767,7 @@ __camellia_enc_blk32:
 	 *	%ymm0..%ymm15: 32 encrypted blocks, order swapped:
 	 *       7, 8, 6, 5, 4, 3, 2, 1, 0, 15, 14, 13, 12, 11, 10, 9, 8
 	 */
+	FRAME_BEGIN
 
 	leaq 8 * 32(%rax), %rcx;
 
@@ -820,6 +822,7 @@ __camellia_enc_blk32:
 		    %ymm8, %ymm9, %ymm10, %ymm11, %ymm12, %ymm13, %ymm14,
 		    %ymm15, (key_table)(CTX, %r8, 8), (%rax), 1 * 32(%rax));
 
+	FRAME_END
 	ret;
 
 .align 8
@@ -852,6 +855,7 @@ __camellia_dec_blk32:
 	 *	%ymm0..%ymm15: 16 plaintext blocks, order swapped:
 	 *       7, 8, 6, 5, 4, 3, 2, 1, 0, 15, 14, 13, 12, 11, 10, 9, 8
 	 */
+	FRAME_BEGIN
 
 	leaq 8 * 32(%rax), %rcx;
 
@@ -905,6 +909,7 @@ __camellia_dec_blk32:
 		    %ymm8, %ymm9, %ymm10, %ymm11, %ymm12, %ymm13, %ymm14,
 		    %ymm15, (key_table)(CTX), (%rax), 1 * 32(%rax));
 
+	FRAME_END
 	ret;
 
 .align 8
@@ -930,6 +935,7 @@ ENTRY(camellia_ecb_enc_32way)
 	 *	%rsi: dst (32 blocks)
 	 *	%rdx: src (32 blocks)
 	 */
+	FRAME_BEGIN
 
 	vzeroupper;
 
@@ -948,6 +954,7 @@ ENTRY(camellia_ecb_enc_32way)
 
 	vzeroupper;
 
+	FRAME_END
 	ret;
 ENDPROC(camellia_ecb_enc_32way)
 
@@ -957,6 +964,7 @@ ENTRY(camellia_ecb_dec_32way)
 	 *	%rsi: dst (32 blocks)
 	 *	%rdx: src (32 blocks)
 	 */
+	FRAME_BEGIN
 
 	vzeroupper;
 
@@ -980,6 +988,7 @@ ENTRY(camellia_ecb_dec_32way)
 
 	vzeroupper;
 
+	FRAME_END
 	ret;
 ENDPROC(camellia_ecb_dec_32way)
 
@@ -989,6 +998,7 @@ ENTRY(camellia_cbc_dec_32way)
 	 *	%rsi: dst (32 blocks)
 	 *	%rdx: src (32 blocks)
 	 */
+	FRAME_BEGIN
 
 	vzeroupper;
 
@@ -1046,6 +1056,7 @@ ENTRY(camellia_cbc_dec_32way)
 
 	vzeroupper;
 
+	FRAME_END
 	ret;
 ENDPROC(camellia_cbc_dec_32way)
 
@@ -1070,6 +1081,7 @@ ENTRY(camellia_ctr_32way)
 	 *	%rdx: src (32 blocks)
 	 *	%rcx: iv (little endian, 128bit)
 	 */
+	FRAME_BEGIN
 
 	vzeroupper;
 
@@ -1184,6 +1196,7 @@ ENTRY(camellia_ctr_32way)
 
 	vzeroupper;
 
+	FRAME_END
 	ret;
 ENDPROC(camellia_ctr_32way)
 
@@ -1216,6 +1229,7 @@ camellia_xts_crypt_32way:
 	 *	%r8: index for input whitening key
 	 *	%r9: pointer to  __camellia_enc_blk32 or __camellia_dec_blk32
 	 */
+	FRAME_BEGIN
 
 	vzeroupper;
 
@@ -1349,6 +1363,7 @@ camellia_xts_crypt_32way:
 
 	vzeroupper;
 
+	FRAME_END
 	ret;
 ENDPROC(camellia_xts_crypt_32way)
 
diff --git a/arch/x86/crypto/cast5-avx-x86_64-asm_64.S b/arch/x86/crypto/cast5-avx-x86_64-asm_64.S
index c35fd5d..14fa196 100644
--- a/arch/x86/crypto/cast5-avx-x86_64-asm_64.S
+++ b/arch/x86/crypto/cast5-avx-x86_64-asm_64.S
@@ -24,6 +24,7 @@
  */
 
 #include <linux/linkage.h>
+#include <asm/frame.h>
 
 .file "cast5-avx-x86_64-asm_64.S"
 
@@ -365,6 +366,7 @@ ENTRY(cast5_ecb_enc_16way)
 	 *	%rsi: dst
 	 *	%rdx: src
 	 */
+	FRAME_BEGIN
 
 	movq %rsi, %r11;
 
@@ -388,6 +390,7 @@ ENTRY(cast5_ecb_enc_16way)
 	vmovdqu RR4, (6*4*4)(%r11);
 	vmovdqu RL4, (7*4*4)(%r11);
 
+	FRAME_END
 	ret;
 ENDPROC(cast5_ecb_enc_16way)
 
@@ -398,6 +401,7 @@ ENTRY(cast5_ecb_dec_16way)
 	 *	%rdx: src
 	 */
 
+	FRAME_BEGIN
 	movq %rsi, %r11;
 
 	vmovdqu (0*4*4)(%rdx), RL1;
@@ -420,6 +424,7 @@ ENTRY(cast5_ecb_dec_16way)
 	vmovdqu RR4, (6*4*4)(%r11);
 	vmovdqu RL4, (7*4*4)(%r11);
 
+	FRAME_END
 	ret;
 ENDPROC(cast5_ecb_dec_16way)
 
@@ -429,6 +434,7 @@ ENTRY(cast5_cbc_dec_16way)
 	 *	%rsi: dst
 	 *	%rdx: src
 	 */
+	FRAME_BEGIN
 
 	pushq %r12;
 
@@ -469,6 +475,7 @@ ENTRY(cast5_cbc_dec_16way)
 
 	popq %r12;
 
+	FRAME_END
 	ret;
 ENDPROC(cast5_cbc_dec_16way)
 
@@ -479,6 +486,7 @@ ENTRY(cast5_ctr_16way)
 	 *	%rdx: src
 	 *	%rcx: iv (big endian, 64bit)
 	 */
+	FRAME_BEGIN
 
 	pushq %r12;
 
@@ -542,5 +550,6 @@ ENTRY(cast5_ctr_16way)
 
 	popq %r12;
 
+	FRAME_END
 	ret;
 ENDPROC(cast5_ctr_16way)
diff --git a/arch/x86/crypto/cast6-avx-x86_64-asm_64.S b/arch/x86/crypto/cast6-avx-x86_64-asm_64.S
index e3531f8..c419389 100644
--- a/arch/x86/crypto/cast6-avx-x86_64-asm_64.S
+++ b/arch/x86/crypto/cast6-avx-x86_64-asm_64.S
@@ -24,6 +24,7 @@
  */
 
 #include <linux/linkage.h>
+#include <asm/frame.h>
 #include "glue_helper-asm-avx.S"
 
 .file "cast6-avx-x86_64-asm_64.S"
@@ -349,6 +350,7 @@ ENTRY(cast6_ecb_enc_8way)
 	 *	%rsi: dst
 	 *	%rdx: src
 	 */
+	FRAME_BEGIN
 
 	movq %rsi, %r11;
 
@@ -358,6 +360,7 @@ ENTRY(cast6_ecb_enc_8way)
 
 	store_8way(%r11, RA1, RB1, RC1, RD1, RA2, RB2, RC2, RD2);
 
+	FRAME_END
 	ret;
 ENDPROC(cast6_ecb_enc_8way)
 
@@ -367,6 +370,7 @@ ENTRY(cast6_ecb_dec_8way)
 	 *	%rsi: dst
 	 *	%rdx: src
 	 */
+	FRAME_BEGIN
 
 	movq %rsi, %r11;
 
@@ -376,6 +380,7 @@ ENTRY(cast6_ecb_dec_8way)
 
 	store_8way(%r11, RA1, RB1, RC1, RD1, RA2, RB2, RC2, RD2);
 
+	FRAME_END
 	ret;
 ENDPROC(cast6_ecb_dec_8way)
 
@@ -385,6 +390,7 @@ ENTRY(cast6_cbc_dec_8way)
 	 *	%rsi: dst
 	 *	%rdx: src
 	 */
+	FRAME_BEGIN
 
 	pushq %r12;
 
@@ -399,6 +405,7 @@ ENTRY(cast6_cbc_dec_8way)
 
 	popq %r12;
 
+	FRAME_END
 	ret;
 ENDPROC(cast6_cbc_dec_8way)
 
@@ -409,6 +416,7 @@ ENTRY(cast6_ctr_8way)
 	 *	%rdx: src
 	 *	%rcx: iv (little endian, 128bit)
 	 */
+	FRAME_BEGIN
 
 	pushq %r12;
 
@@ -424,6 +432,7 @@ ENTRY(cast6_ctr_8way)
 
 	popq %r12;
 
+	FRAME_END
 	ret;
 ENDPROC(cast6_ctr_8way)
 
@@ -434,6 +443,7 @@ ENTRY(cast6_xts_enc_8way)
 	 *	%rdx: src
 	 *	%rcx: iv (t ⊕ αⁿ ∈ GF(2¹²⁸))
 	 */
+	FRAME_BEGIN
 
 	movq %rsi, %r11;
 
@@ -446,6 +456,7 @@ ENTRY(cast6_xts_enc_8way)
 	/* dst <= regs xor IVs(in dst) */
 	store_xts_8way(%r11, RA1, RB1, RC1, RD1, RA2, RB2, RC2, RD2);
 
+	FRAME_END
 	ret;
 ENDPROC(cast6_xts_enc_8way)
 
@@ -456,6 +467,7 @@ ENTRY(cast6_xts_dec_8way)
 	 *	%rdx: src
 	 *	%rcx: iv (t ⊕ αⁿ ∈ GF(2¹²⁸))
 	 */
+	FRAME_BEGIN
 
 	movq %rsi, %r11;
 
@@ -468,5 +480,6 @@ ENTRY(cast6_xts_dec_8way)
 	/* dst <= regs xor IVs(in dst) */
 	store_xts_8way(%r11, RA1, RB1, RC1, RD1, RA2, RB2, RC2, RD2);
 
+	FRAME_END
 	ret;
 ENDPROC(cast6_xts_dec_8way)
diff --git a/arch/x86/crypto/crc32c-pcl-intel-asm_64.S b/arch/x86/crypto/crc32c-pcl-intel-asm_64.S
index 4fe27e0..dc05f01 100644
--- a/arch/x86/crypto/crc32c-pcl-intel-asm_64.S
+++ b/arch/x86/crypto/crc32c-pcl-intel-asm_64.S
@@ -170,8 +170,8 @@ continue_block:
 	## branch into array
 	lea	jump_table(%rip), bufp
 	movzxw  (bufp, %rax, 2), len
-	offset=crc_array-jump_table
-	lea     offset(bufp, len, 1), bufp
+	lea	crc_array(%rip), bufp
+	lea     (bufp, len, 1), bufp
 	jmp     *bufp
 
 	################################################################
@@ -310,7 +310,9 @@ do_return:
 	popq    %rdi
 	popq    %rbx
         ret
+ENDPROC(crc_pcl)
 
+.section	.rodata, "a", %progbits
         ################################################################
         ## jump table        Table is 129 entries x 2 bytes each
         ################################################################
@@ -324,13 +326,11 @@ JMPTBL_ENTRY %i
 	i=i+1
 .endr
 
-ENDPROC(crc_pcl)
 
 	################################################################
 	## PCLMULQDQ tables
 	## Table is 128 entries x 2 words (8 bytes) each
 	################################################################
-.section	.rodata, "a", %progbits
 .align 8
 K_table:
 	.long 0x493c7d27, 0x00000001
diff --git a/arch/x86/crypto/ghash-clmulni-intel_asm.S b/arch/x86/crypto/ghash-clmulni-intel_asm.S
index 5d1e007..eed55c8 100644
--- a/arch/x86/crypto/ghash-clmulni-intel_asm.S
+++ b/arch/x86/crypto/ghash-clmulni-intel_asm.S
@@ -18,6 +18,7 @@
 
 #include <linux/linkage.h>
 #include <asm/inst.h>
+#include <asm/frame.h>
 
 .data
 
@@ -94,6 +95,7 @@ ENDPROC(__clmul_gf128mul_ble)
 
 /* void clmul_ghash_mul(char *dst, const u128 *shash) */
 ENTRY(clmul_ghash_mul)
+	FRAME_BEGIN
 	movups (%rdi), DATA
 	movups (%rsi), SHASH
 	movaps .Lbswap_mask, BSWAP
@@ -101,6 +103,7 @@ ENTRY(clmul_ghash_mul)
 	call __clmul_gf128mul_ble
 	PSHUFB_XMM BSWAP DATA
 	movups DATA, (%rdi)
+	FRAME_END
 	ret
 ENDPROC(clmul_ghash_mul)
 
@@ -109,6 +112,7 @@ ENDPROC(clmul_ghash_mul)
  *			   const u128 *shash);
  */
 ENTRY(clmul_ghash_update)
+	FRAME_BEGIN
 	cmp $16, %rdx
 	jb .Lupdate_just_ret	# check length
 	movaps .Lbswap_mask, BSWAP
@@ -128,5 +132,6 @@ ENTRY(clmul_ghash_update)
 	PSHUFB_XMM BSWAP DATA
 	movups DATA, (%rdi)
 .Lupdate_just_ret:
+	FRAME_END
 	ret
 ENDPROC(clmul_ghash_update)
diff --git a/arch/x86/crypto/serpent-avx-x86_64-asm_64.S b/arch/x86/crypto/serpent-avx-x86_64-asm_64.S
index 2f202f4..8be5718 100644
--- a/arch/x86/crypto/serpent-avx-x86_64-asm_64.S
+++ b/arch/x86/crypto/serpent-avx-x86_64-asm_64.S
@@ -24,6 +24,7 @@
  */
 
 #include <linux/linkage.h>
+#include <asm/frame.h>
 #include "glue_helper-asm-avx.S"
 
 .file "serpent-avx-x86_64-asm_64.S"
@@ -681,6 +682,7 @@ ENTRY(serpent_ecb_enc_8way_avx)
 	 *	%rsi: dst
 	 *	%rdx: src
 	 */
+	FRAME_BEGIN
 
 	load_8way(%rdx, RA1, RB1, RC1, RD1, RA2, RB2, RC2, RD2);
 
@@ -688,6 +690,7 @@ ENTRY(serpent_ecb_enc_8way_avx)
 
 	store_8way(%rsi, RA1, RB1, RC1, RD1, RA2, RB2, RC2, RD2);
 
+	FRAME_END
 	ret;
 ENDPROC(serpent_ecb_enc_8way_avx)
 
@@ -697,6 +700,7 @@ ENTRY(serpent_ecb_dec_8way_avx)
 	 *	%rsi: dst
 	 *	%rdx: src
 	 */
+	FRAME_BEGIN
 
 	load_8way(%rdx, RA1, RB1, RC1, RD1, RA2, RB2, RC2, RD2);
 
@@ -704,6 +708,7 @@ ENTRY(serpent_ecb_dec_8way_avx)
 
 	store_8way(%rsi, RC1, RD1, RB1, RE1, RC2, RD2, RB2, RE2);
 
+	FRAME_END
 	ret;
 ENDPROC(serpent_ecb_dec_8way_avx)
 
@@ -713,6 +718,7 @@ ENTRY(serpent_cbc_dec_8way_avx)
 	 *	%rsi: dst
 	 *	%rdx: src
 	 */
+	FRAME_BEGIN
 
 	load_8way(%rdx, RA1, RB1, RC1, RD1, RA2, RB2, RC2, RD2);
 
@@ -720,6 +726,7 @@ ENTRY(serpent_cbc_dec_8way_avx)
 
 	store_cbc_8way(%rdx, %rsi, RC1, RD1, RB1, RE1, RC2, RD2, RB2, RE2);
 
+	FRAME_END
 	ret;
 ENDPROC(serpent_cbc_dec_8way_avx)
 
@@ -730,6 +737,7 @@ ENTRY(serpent_ctr_8way_avx)
 	 *	%rdx: src
 	 *	%rcx: iv (little endian, 128bit)
 	 */
+	FRAME_BEGIN
 
 	load_ctr_8way(%rcx, .Lbswap128_mask, RA1, RB1, RC1, RD1, RA2, RB2, RC2,
 		      RD2, RK0, RK1, RK2);
@@ -738,6 +746,7 @@ ENTRY(serpent_ctr_8way_avx)
 
 	store_ctr_8way(%rdx, %rsi, RA1, RB1, RC1, RD1, RA2, RB2, RC2, RD2);
 
+	FRAME_END
 	ret;
 ENDPROC(serpent_ctr_8way_avx)
 
@@ -748,6 +757,7 @@ ENTRY(serpent_xts_enc_8way_avx)
 	 *	%rdx: src
 	 *	%rcx: iv (t ⊕ αⁿ ∈ GF(2¹²⁸))
 	 */
+	FRAME_BEGIN
 
 	/* regs <= src, dst <= IVs, regs <= regs xor IVs */
 	load_xts_8way(%rcx, %rdx, %rsi, RA1, RB1, RC1, RD1, RA2, RB2, RC2, RD2,
@@ -758,6 +768,7 @@ ENTRY(serpent_xts_enc_8way_avx)
 	/* dst <= regs xor IVs(in dst) */
 	store_xts_8way(%rsi, RA1, RB1, RC1, RD1, RA2, RB2, RC2, RD2);
 
+	FRAME_END
 	ret;
 ENDPROC(serpent_xts_enc_8way_avx)
 
@@ -768,6 +779,7 @@ ENTRY(serpent_xts_dec_8way_avx)
 	 *	%rdx: src
 	 *	%rcx: iv (t ⊕ αⁿ ∈ GF(2¹²⁸))
 	 */
+	FRAME_BEGIN
 
 	/* regs <= src, dst <= IVs, regs <= regs xor IVs */
 	load_xts_8way(%rcx, %rdx, %rsi, RA1, RB1, RC1, RD1, RA2, RB2, RC2, RD2,
@@ -778,5 +790,6 @@ ENTRY(serpent_xts_dec_8way_avx)
 	/* dst <= regs xor IVs(in dst) */
 	store_xts_8way(%rsi, RC1, RD1, RB1, RE1, RC2, RD2, RB2, RE2);
 
+	FRAME_END
 	ret;
 ENDPROC(serpent_xts_dec_8way_avx)
diff --git a/arch/x86/crypto/serpent-avx2-asm_64.S b/arch/x86/crypto/serpent-avx2-asm_64.S
index b222085..97c48ad 100644
--- a/arch/x86/crypto/serpent-avx2-asm_64.S
+++ b/arch/x86/crypto/serpent-avx2-asm_64.S
@@ -15,6 +15,7 @@
  */
 
 #include <linux/linkage.h>
+#include <asm/frame.h>
 #include "glue_helper-asm-avx2.S"
 
 .file "serpent-avx2-asm_64.S"
@@ -673,6 +674,7 @@ ENTRY(serpent_ecb_enc_16way)
 	 *	%rsi: dst
 	 *	%rdx: src
 	 */
+	FRAME_BEGIN
 
 	vzeroupper;
 
@@ -684,6 +686,7 @@ ENTRY(serpent_ecb_enc_16way)
 
 	vzeroupper;
 
+	FRAME_END
 	ret;
 ENDPROC(serpent_ecb_enc_16way)
 
@@ -693,6 +696,7 @@ ENTRY(serpent_ecb_dec_16way)
 	 *	%rsi: dst
 	 *	%rdx: src
 	 */
+	FRAME_BEGIN
 
 	vzeroupper;
 
@@ -704,6 +708,7 @@ ENTRY(serpent_ecb_dec_16way)
 
 	vzeroupper;
 
+	FRAME_END
 	ret;
 ENDPROC(serpent_ecb_dec_16way)
 
@@ -713,6 +718,7 @@ ENTRY(serpent_cbc_dec_16way)
 	 *	%rsi: dst
 	 *	%rdx: src
 	 */
+	FRAME_BEGIN
 
 	vzeroupper;
 
@@ -725,6 +731,7 @@ ENTRY(serpent_cbc_dec_16way)
 
 	vzeroupper;
 
+	FRAME_END
 	ret;
 ENDPROC(serpent_cbc_dec_16way)
 
@@ -735,6 +742,7 @@ ENTRY(serpent_ctr_16way)
 	 *	%rdx: src (16 blocks)
 	 *	%rcx: iv (little endian, 128bit)
 	 */
+	FRAME_BEGIN
 
 	vzeroupper;
 
@@ -748,6 +756,7 @@ ENTRY(serpent_ctr_16way)
 
 	vzeroupper;
 
+	FRAME_END
 	ret;
 ENDPROC(serpent_ctr_16way)
 
@@ -758,6 +767,7 @@ ENTRY(serpent_xts_enc_16way)
 	 *	%rdx: src (16 blocks)
 	 *	%rcx: iv (t ⊕ αⁿ ∈ GF(2¹²⁸))
 	 */
+	FRAME_BEGIN
 
 	vzeroupper;
 
@@ -772,6 +782,7 @@ ENTRY(serpent_xts_enc_16way)
 
 	vzeroupper;
 
+	FRAME_END
 	ret;
 ENDPROC(serpent_xts_enc_16way)
 
@@ -782,6 +793,7 @@ ENTRY(serpent_xts_dec_16way)
 	 *	%rdx: src (16 blocks)
 	 *	%rcx: iv (t ⊕ αⁿ ∈ GF(2¹²⁸))
 	 */
+	FRAME_BEGIN
 
 	vzeroupper;
 
@@ -796,5 +808,6 @@ ENTRY(serpent_xts_dec_16way)
 
 	vzeroupper;
 
+	FRAME_END
 	ret;
 ENDPROC(serpent_xts_dec_16way)
diff --git a/arch/x86/crypto/sha-mb/sha1_mb_mgr_flush_avx2.S b/arch/x86/crypto/sha-mb/sha1_mb_mgr_flush_avx2.S
index 85c4e1c..96df6a3 100644
--- a/arch/x86/crypto/sha-mb/sha1_mb_mgr_flush_avx2.S
+++ b/arch/x86/crypto/sha-mb/sha1_mb_mgr_flush_avx2.S
@@ -52,6 +52,7 @@
  * OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
  */
 #include <linux/linkage.h>
+#include <asm/frame.h>
 #include "sha1_mb_mgr_datastruct.S"
 
 
@@ -86,16 +87,6 @@
 #define extra_blocks    %arg2
 #define p               %arg2
 
-
-# STACK_SPACE needs to be an odd multiple of 8
-_XMM_SAVE_SIZE  = 10*16
-_GPR_SAVE_SIZE  = 8*8
-_ALIGN_SIZE     = 8
-
-_XMM_SAVE       = 0
-_GPR_SAVE       = _XMM_SAVE + _XMM_SAVE_SIZE
-STACK_SPACE     = _GPR_SAVE + _GPR_SAVE_SIZE + _ALIGN_SIZE
-
 .macro LABEL prefix n
 \prefix\n\():
 .endm
@@ -113,16 +104,8 @@ offset = \_offset
 # JOB* sha1_mb_mgr_flush_avx2(MB_MGR *state)
 # arg 1 : rcx : state
 ENTRY(sha1_mb_mgr_flush_avx2)
-	mov	%rsp, %r10
-	sub     $STACK_SPACE, %rsp
-	and     $~31, %rsp
-	mov     %rbx, _GPR_SAVE(%rsp)
-	mov     %r10, _GPR_SAVE+8*1(%rsp) #save rsp
-	mov	%rbp, _GPR_SAVE+8*3(%rsp)
-	mov	%r12, _GPR_SAVE+8*4(%rsp)
-	mov	%r13, _GPR_SAVE+8*5(%rsp)
-	mov	%r14, _GPR_SAVE+8*6(%rsp)
-	mov	%r15, _GPR_SAVE+8*7(%rsp)
+	FRAME_BEGIN
+	push	%rbx
 
 	# If bit (32+3) is set, then all lanes are empty
 	mov     _unused_lanes(state), unused_lanes
@@ -230,16 +213,8 @@ len_is_0:
 	mov     tmp2_w, offset(job_rax)
 
 return:
-
-	mov     _GPR_SAVE(%rsp), %rbx
-	mov     _GPR_SAVE+8*1(%rsp), %r10 #saved rsp
-	mov	_GPR_SAVE+8*3(%rsp), %rbp
-	mov	_GPR_SAVE+8*4(%rsp), %r12
-	mov	_GPR_SAVE+8*5(%rsp), %r13
-	mov	_GPR_SAVE+8*6(%rsp), %r14
-	mov	_GPR_SAVE+8*7(%rsp), %r15
-	mov     %r10, %rsp
-
+	pop	%rbx
+	FRAME_END
 	ret
 
 return_null:
diff --git a/arch/x86/crypto/sha-mb/sha1_mb_mgr_submit_avx2.S b/arch/x86/crypto/sha-mb/sha1_mb_mgr_submit_avx2.S
index c420d89..63a0d9c 100644
--- a/arch/x86/crypto/sha-mb/sha1_mb_mgr_submit_avx2.S
+++ b/arch/x86/crypto/sha-mb/sha1_mb_mgr_submit_avx2.S
@@ -53,6 +53,7 @@
  */
 
 #include <linux/linkage.h>
+#include <asm/frame.h>
 #include "sha1_mb_mgr_datastruct.S"
 
 
@@ -86,33 +87,21 @@ job_rax         = %rax
 len             = %rax
 DWORD_len	= %eax
 
-lane            = %rbp
-tmp3            = %rbp
+lane            = %r12
+tmp3            = %r12
 
 tmp             = %r9
 DWORD_tmp	= %r9d
 
 lane_data       = %r10
 
-# STACK_SPACE needs to be an odd multiple of 8
-STACK_SPACE     = 8*8 + 16*10 + 8
-
 # JOB* submit_mb_mgr_submit_avx2(MB_MGR *state, job_sha1 *job)
 # arg 1 : rcx : state
 # arg 2 : rdx : job
 ENTRY(sha1_mb_mgr_submit_avx2)
-
-	mov	%rsp, %r10
-	sub     $STACK_SPACE, %rsp
-	and	$~31, %rsp
-
-	mov     %rbx, (%rsp)
-	mov	%r10, 8*2(%rsp)	#save old rsp
-	mov     %rbp, 8*3(%rsp)
-	mov	%r12, 8*4(%rsp)
-	mov	%r13, 8*5(%rsp)
-	mov	%r14, 8*6(%rsp)
-	mov	%r15, 8*7(%rsp)
+	FRAME_BEGIN
+	push	%rbx
+	push	%r12
 
 	mov     _unused_lanes(state), unused_lanes
 	mov	unused_lanes, lane
@@ -203,16 +192,9 @@ len_is_0:
 	movl    DWORD_tmp, _result_digest+1*16(job_rax)
 
 return:
-
-	mov     (%rsp), %rbx
-	mov	8*2(%rsp), %r10	#save old rsp
-	mov     8*3(%rsp), %rbp
-	mov	8*4(%rsp), %r12
-	mov	8*5(%rsp), %r13
-	mov	8*6(%rsp), %r14
-	mov	8*7(%rsp), %r15
-	mov     %r10, %rsp
-
+	pop	%r12
+	pop	%rbx
+	FRAME_END
 	ret
 
 return_null:
diff --git a/arch/x86/crypto/twofish-avx-x86_64-asm_64.S b/arch/x86/crypto/twofish-avx-x86_64-asm_64.S
index 0505813..dc66273 100644
--- a/arch/x86/crypto/twofish-avx-x86_64-asm_64.S
+++ b/arch/x86/crypto/twofish-avx-x86_64-asm_64.S
@@ -24,6 +24,7 @@
  */
 
 #include <linux/linkage.h>
+#include <asm/frame.h>
 #include "glue_helper-asm-avx.S"
 
 .file "twofish-avx-x86_64-asm_64.S"
@@ -333,6 +334,7 @@ ENTRY(twofish_ecb_enc_8way)
 	 *	%rsi: dst
 	 *	%rdx: src
 	 */
+	FRAME_BEGIN
 
 	movq %rsi, %r11;
 
@@ -342,6 +344,7 @@ ENTRY(twofish_ecb_enc_8way)
 
 	store_8way(%r11, RC1, RD1, RA1, RB1, RC2, RD2, RA2, RB2);
 
+	FRAME_END
 	ret;
 ENDPROC(twofish_ecb_enc_8way)
 
@@ -351,6 +354,7 @@ ENTRY(twofish_ecb_dec_8way)
 	 *	%rsi: dst
 	 *	%rdx: src
 	 */
+	FRAME_BEGIN
 
 	movq %rsi, %r11;
 
@@ -360,6 +364,7 @@ ENTRY(twofish_ecb_dec_8way)
 
 	store_8way(%r11, RA1, RB1, RC1, RD1, RA2, RB2, RC2, RD2);
 
+	FRAME_END
 	ret;
 ENDPROC(twofish_ecb_dec_8way)
 
@@ -369,6 +374,7 @@ ENTRY(twofish_cbc_dec_8way)
 	 *	%rsi: dst
 	 *	%rdx: src
 	 */
+	FRAME_BEGIN
 
 	pushq %r12;
 
@@ -383,6 +389,7 @@ ENTRY(twofish_cbc_dec_8way)
 
 	popq %r12;
 
+	FRAME_END
 	ret;
 ENDPROC(twofish_cbc_dec_8way)
 
@@ -393,6 +400,7 @@ ENTRY(twofish_ctr_8way)
 	 *	%rdx: src
 	 *	%rcx: iv (little endian, 128bit)
 	 */
+	FRAME_BEGIN
 
 	pushq %r12;
 
@@ -408,6 +416,7 @@ ENTRY(twofish_ctr_8way)
 
 	popq %r12;
 
+	FRAME_END
 	ret;
 ENDPROC(twofish_ctr_8way)
 
@@ -418,6 +427,7 @@ ENTRY(twofish_xts_enc_8way)
 	 *	%rdx: src
 	 *	%rcx: iv (t ⊕ αⁿ ∈ GF(2¹²⁸))
 	 */
+	FRAME_BEGIN
 
 	movq %rsi, %r11;
 
@@ -430,6 +440,7 @@ ENTRY(twofish_xts_enc_8way)
 	/* dst <= regs xor IVs(in dst) */
 	store_xts_8way(%r11, RC1, RD1, RA1, RB1, RC2, RD2, RA2, RB2);
 
+	FRAME_END
 	ret;
 ENDPROC(twofish_xts_enc_8way)
 
@@ -440,6 +451,7 @@ ENTRY(twofish_xts_dec_8way)
 	 *	%rdx: src
 	 *	%rcx: iv (t ⊕ αⁿ ∈ GF(2¹²⁸))
 	 */
+	FRAME_BEGIN
 
 	movq %rsi, %r11;
 
@@ -452,5 +464,6 @@ ENTRY(twofish_xts_dec_8way)
 	/* dst <= regs xor IVs(in dst) */
 	store_xts_8way(%r11, RA1, RB1, RC1, RD1, RA2, RB2, RC2, RD2);
 
+	FRAME_END
 	ret;
 ENDPROC(twofish_xts_dec_8way)
diff --git a/arch/x86/entry/Makefile b/arch/x86/entry/Makefile
index bd55ded..fe91c25 100644
--- a/arch/x86/entry/Makefile
+++ b/arch/x86/entry/Makefile
@@ -1,6 +1,10 @@
 #
 # Makefile for the x86 low level entry code
 #
+
+OBJECT_FILES_NON_STANDARD_entry_$(BITS).o   := y
+OBJECT_FILES_NON_STANDARD_entry_64_compat.o := y
+
 obj-y				:= entry_$(BITS).o thunk_$(BITS).o syscall_$(BITS).o
 obj-y				+= common.o
 
diff --git a/arch/x86/entry/thunk_64.S b/arch/x86/entry/thunk_64.S
index efb2b93..98df1fa 100644
--- a/arch/x86/entry/thunk_64.S
+++ b/arch/x86/entry/thunk_64.S
@@ -8,11 +8,14 @@
 #include <linux/linkage.h>
 #include "calling.h"
 #include <asm/asm.h>
+#include <asm/frame.h>
 
 	/* rdi:	arg1 ... normal C conventions. rax is saved/restored. */
 	.macro THUNK name, func, put_ret_addr_in_rdi=0
 	.globl \name
+	.type \name, @function
 \name:
+	FRAME_BEGIN
 
 	/* this one pushes 9 elems, the next one would be %rIP */
 	pushq %rdi
@@ -62,6 +65,7 @@ restore:
 	popq %rdx
 	popq %rsi
 	popq %rdi
+	FRAME_END
 	ret
 	_ASM_NOKPROBE(restore)
 #endif
diff --git a/arch/x86/entry/vdso/Makefile b/arch/x86/entry/vdso/Makefile
index c854541..f9fb859 100644
--- a/arch/x86/entry/vdso/Makefile
+++ b/arch/x86/entry/vdso/Makefile
@@ -3,8 +3,9 @@
 #
 
 KBUILD_CFLAGS += $(DISABLE_LTO)
-KASAN_SANITIZE := n
-UBSAN_SANITIZE := n
+KASAN_SANITIZE			:= n
+UBSAN_SANITIZE			:= n
+OBJECT_FILES_NON_STANDARD	:= y
 
 VDSO64-$(CONFIG_X86_64)		:= y
 VDSOX32-$(CONFIG_X86_X32_ABI)	:= y
@@ -16,6 +17,7 @@ vobjs-y := vdso-note.o vclock_gettime.o vgetcpu.o
 
 # files to link into kernel
 obj-y				+= vma.o
+OBJECT_FILES_NON_STANDARD_vma.o	:= n
 
 # vDSO images to build
 vdso_img-$(VDSO64-y)		+= 64
diff --git a/arch/x86/include/asm/paravirt.h b/arch/x86/include/asm/paravirt.h
index f619250..601f1b8 100644
--- a/arch/x86/include/asm/paravirt.h
+++ b/arch/x86/include/asm/paravirt.h
@@ -13,6 +13,7 @@
 #include <linux/bug.h>
 #include <linux/types.h>
 #include <linux/cpumask.h>
+#include <asm/frame.h>
 
 static inline int paravirt_enabled(void)
 {
@@ -756,15 +757,19 @@ static __always_inline void __ticket_unlock_kick(struct arch_spinlock *lock,
  * call. The return value in rax/eax will not be saved, even for void
  * functions.
  */
+#define PV_THUNK_NAME(func) "__raw_callee_save_" #func
 #define PV_CALLEE_SAVE_REGS_THUNK(func)					\
 	extern typeof(func) __raw_callee_save_##func;			\
 									\
 	asm(".pushsection .text;"					\
-	    ".globl __raw_callee_save_" #func " ; "			\
-	    "__raw_callee_save_" #func ": "				\
+	    ".globl " PV_THUNK_NAME(func) ";"				\
+	    ".type " PV_THUNK_NAME(func) ", @function;"			\
+	    PV_THUNK_NAME(func) ":"					\
+	    FRAME_BEGIN							\
 	    PV_SAVE_ALL_CALLER_REGS					\
 	    "call " #func ";"						\
 	    PV_RESTORE_ALL_CALLER_REGS					\
+	    FRAME_END							\
 	    "ret;"							\
 	    ".popsection")
 
diff --git a/arch/x86/include/asm/paravirt_types.h b/arch/x86/include/asm/paravirt_types.h
index 77db561..e8c2326 100644
--- a/arch/x86/include/asm/paravirt_types.h
+++ b/arch/x86/include/asm/paravirt_types.h
@@ -466,8 +466,9 @@ int paravirt_disable_iospace(void);
  * makes sure the incoming and outgoing types are always correct.
  */
 #ifdef CONFIG_X86_32
-#define PVOP_VCALL_ARGS				\
-	unsigned long __eax = __eax, __edx = __edx, __ecx = __ecx
+#define PVOP_VCALL_ARGS							\
+	unsigned long __eax = __eax, __edx = __edx, __ecx = __ecx;	\
+	register void *__sp asm("esp")
 #define PVOP_CALL_ARGS			PVOP_VCALL_ARGS
 
 #define PVOP_CALL_ARG1(x)		"a" ((unsigned long)(x))
@@ -485,9 +486,10 @@ int paravirt_disable_iospace(void);
 #define VEXTRA_CLOBBERS
 #else  /* CONFIG_X86_64 */
 /* [re]ax isn't an arg, but the return val */
-#define PVOP_VCALL_ARGS					\
-	unsigned long __edi = __edi, __esi = __esi,	\
-		__edx = __edx, __ecx = __ecx, __eax = __eax
+#define PVOP_VCALL_ARGS						\
+	unsigned long __edi = __edi, __esi = __esi,		\
+		__edx = __edx, __ecx = __ecx, __eax = __eax;	\
+	register void *__sp asm("rsp")
 #define PVOP_CALL_ARGS		PVOP_VCALL_ARGS
 
 #define PVOP_CALL_ARG1(x)		"D" ((unsigned long)(x))
@@ -526,7 +528,7 @@ int paravirt_disable_iospace(void);
 			asm volatile(pre				\
 				     paravirt_alt(PARAVIRT_CALL)	\
 				     post				\
-				     : call_clbr			\
+				     : call_clbr, "+r" (__sp)		\
 				     : paravirt_type(op),		\
 				       paravirt_clobber(clbr),		\
 				       ##__VA_ARGS__			\
@@ -536,7 +538,7 @@ int paravirt_disable_iospace(void);
 			asm volatile(pre				\
 				     paravirt_alt(PARAVIRT_CALL)	\
 				     post				\
-				     : call_clbr			\
+				     : call_clbr, "+r" (__sp)		\
 				     : paravirt_type(op),		\
 				       paravirt_clobber(clbr),		\
 				       ##__VA_ARGS__			\
@@ -563,7 +565,7 @@ int paravirt_disable_iospace(void);
 		asm volatile(pre					\
 			     paravirt_alt(PARAVIRT_CALL)		\
 			     post					\
-			     : call_clbr				\
+			     : call_clbr, "+r" (__sp)			\
 			     : paravirt_type(op),			\
 			       paravirt_clobber(clbr),			\
 			       ##__VA_ARGS__				\
diff --git a/arch/x86/include/asm/preempt.h b/arch/x86/include/asm/preempt.h
index 01bcde8..d397deb 100644
--- a/arch/x86/include/asm/preempt.h
+++ b/arch/x86/include/asm/preempt.h
@@ -94,10 +94,19 @@ static __always_inline bool should_resched(int preempt_offset)
 
 #ifdef CONFIG_PREEMPT
   extern asmlinkage void ___preempt_schedule(void);
-# define __preempt_schedule() asm ("call ___preempt_schedule")
+# define __preempt_schedule()					\
+({								\
+	register void *__sp asm(_ASM_SP);			\
+	asm volatile ("call ___preempt_schedule" : "+r"(__sp));	\
+})
+
   extern asmlinkage void preempt_schedule(void);
   extern asmlinkage void ___preempt_schedule_notrace(void);
-# define __preempt_schedule_notrace() asm ("call ___preempt_schedule_notrace")
+# define __preempt_schedule_notrace()					\
+({									\
+	register void *__sp asm(_ASM_SP);				\
+	asm volatile ("call ___preempt_schedule_notrace" : "+r"(__sp));	\
+})
   extern asmlinkage void preempt_schedule_notrace(void);
 #endif
 
diff --git a/arch/x86/include/asm/qspinlock_paravirt.h b/arch/x86/include/asm/qspinlock_paravirt.h
index 9f92c18..9d55f9b 100644
--- a/arch/x86/include/asm/qspinlock_paravirt.h
+++ b/arch/x86/include/asm/qspinlock_paravirt.h
@@ -36,8 +36,10 @@ PV_CALLEE_SAVE_REGS_THUNK(__pv_queued_spin_unlock_slowpath);
  */
 asm    (".pushsection .text;"
 	".globl " PV_UNLOCK ";"
+	".type " PV_UNLOCK ", @function;"
 	".align 4,0x90;"
 	PV_UNLOCK ": "
+	FRAME_BEGIN
 	"push  %rdx;"
 	"mov   $0x1,%eax;"
 	"xor   %edx,%edx;"
@@ -45,6 +47,7 @@ asm    (".pushsection .text;"
 	"cmp   $0x1,%al;"
 	"jne   .slowpath;"
 	"pop   %rdx;"
+	FRAME_END
 	"ret;"
 	".slowpath: "
 	"push   %rsi;"
@@ -52,6 +55,7 @@ asm    (".pushsection .text;"
 	"call " PV_UNLOCK_SLOWPATH ";"
 	"pop    %rsi;"
 	"pop    %rdx;"
+	FRAME_END
 	"ret;"
 	".size " PV_UNLOCK ", .-" PV_UNLOCK ";"
 	".popsection");
diff --git a/arch/x86/include/asm/uaccess.h b/arch/x86/include/asm/uaccess.h
index c0f27d7..88bff6d 100644
--- a/arch/x86/include/asm/uaccess.h
+++ b/arch/x86/include/asm/uaccess.h
@@ -179,10 +179,11 @@ __typeof__(__builtin_choose_expr(sizeof(x) > sizeof(0UL), 0ULL, 0UL))
 ({									\
 	int __ret_gu;							\
 	register __inttype(*(ptr)) __val_gu asm("%"_ASM_DX);		\
+	register void *__sp asm(_ASM_SP);				\
 	__chk_user_ptr(ptr);						\
 	might_fault();							\
-	asm volatile("call __get_user_%P3"				\
-		     : "=a" (__ret_gu), "=r" (__val_gu)			\
+	asm volatile("call __get_user_%P4"				\
+		     : "=a" (__ret_gu), "=r" (__val_gu), "+r" (__sp)	\
 		     : "0" (ptr), "i" (sizeof(*(ptr))));		\
 	(x) = (__force __typeof__(*(ptr))) __val_gu;			\
 	__builtin_expect(__ret_gu, 0);					\
diff --git a/arch/x86/include/asm/xen/hypercall.h b/arch/x86/include/asm/xen/hypercall.h
index 3bcdcc8..a12a047 100644
--- a/arch/x86/include/asm/xen/hypercall.h
+++ b/arch/x86/include/asm/xen/hypercall.h
@@ -110,9 +110,10 @@ extern struct { char _entry[32]; } hypercall_page[];
 	register unsigned long __arg2 asm(__HYPERCALL_ARG2REG) = __arg2; \
 	register unsigned long __arg3 asm(__HYPERCALL_ARG3REG) = __arg3; \
 	register unsigned long __arg4 asm(__HYPERCALL_ARG4REG) = __arg4; \
-	register unsigned long __arg5 asm(__HYPERCALL_ARG5REG) = __arg5;
+	register unsigned long __arg5 asm(__HYPERCALL_ARG5REG) = __arg5; \
+	register void *__sp asm(_ASM_SP);
 
-#define __HYPERCALL_0PARAM	"=r" (__res)
+#define __HYPERCALL_0PARAM	"=r" (__res), "+r" (__sp)
 #define __HYPERCALL_1PARAM	__HYPERCALL_0PARAM, "+r" (__arg1)
 #define __HYPERCALL_2PARAM	__HYPERCALL_1PARAM, "+r" (__arg2)
 #define __HYPERCALL_3PARAM	__HYPERCALL_2PARAM, "+r" (__arg3)
diff --git a/arch/x86/kernel/Makefile b/arch/x86/kernel/Makefile
index b1b78ff..d5fb087 100644
--- a/arch/x86/kernel/Makefile
+++ b/arch/x86/kernel/Makefile
@@ -16,9 +16,14 @@ CFLAGS_REMOVE_ftrace.o = -pg
 CFLAGS_REMOVE_early_printk.o = -pg
 endif
 
-KASAN_SANITIZE_head$(BITS).o := n
-KASAN_SANITIZE_dumpstack.o := n
-KASAN_SANITIZE_dumpstack_$(BITS).o := n
+KASAN_SANITIZE_head$(BITS).o				:= n
+KASAN_SANITIZE_dumpstack.o				:= n
+KASAN_SANITIZE_dumpstack_$(BITS).o			:= n
+
+OBJECT_FILES_NON_STANDARD_head_$(BITS).o		:= y
+OBJECT_FILES_NON_STANDARD_relocate_kernel_$(BITS).o	:= y
+OBJECT_FILES_NON_STANDARD_mcount_$(BITS).o		:= y
+OBJECT_FILES_NON_STANDARD_test_nx.o			:= y
 
 CFLAGS_irq.o := -I$(src)/../include/asm/trace
 
diff --git a/arch/x86/kernel/acpi/wakeup_64.S b/arch/x86/kernel/acpi/wakeup_64.S
index 8c35df4..169963f 100644
--- a/arch/x86/kernel/acpi/wakeup_64.S
+++ b/arch/x86/kernel/acpi/wakeup_64.S
@@ -5,6 +5,7 @@
 #include <asm/page_types.h>
 #include <asm/msr.h>
 #include <asm/asm-offsets.h>
+#include <asm/frame.h>
 
 # Copyright 2003 Pavel Machek <pavel@suse.cz>, distribute under GPLv2
 
@@ -39,6 +40,7 @@ bogus_64_magic:
 	jmp	bogus_64_magic
 
 ENTRY(do_suspend_lowlevel)
+	FRAME_BEGIN
 	subq	$8, %rsp
 	xorl	%eax, %eax
 	call	save_processor_state
@@ -109,6 +111,7 @@ ENTRY(do_suspend_lowlevel)
 
 	xorl	%eax, %eax
 	addq	$8, %rsp
+	FRAME_END
 	jmp	restore_processor_state
 ENDPROC(do_suspend_lowlevel)
 
diff --git a/arch/x86/kernel/cpu/amd.c b/arch/x86/kernel/cpu/amd.c
index 97c59fd..5026a13 100644
--- a/arch/x86/kernel/cpu/amd.c
+++ b/arch/x86/kernel/cpu/amd.c
@@ -75,7 +75,10 @@ static inline int wrmsrl_amd_safe(unsigned msr, unsigned long long val)
  */
 
 extern __visible void vide(void);
-__asm__(".globl vide\n\t.align 4\nvide: ret");
+__asm__(".globl vide\n"
+	".type vide, @function\n"
+	".align 4\n"
+	"vide: ret\n");
 
 static void init_amd_k5(struct cpuinfo_x86 *c)
 {
diff --git a/arch/x86/kernel/kprobes/core.c b/arch/x86/kernel/kprobes/core.c
index 0f05dee..ae703ac 100644
--- a/arch/x86/kernel/kprobes/core.c
+++ b/arch/x86/kernel/kprobes/core.c
@@ -49,6 +49,7 @@
 #include <linux/kdebug.h>
 #include <linux/kallsyms.h>
 #include <linux/ftrace.h>
+#include <linux/frame.h>
 
 #include <asm/cacheflush.h>
 #include <asm/desc.h>
@@ -671,39 +672,39 @@ NOKPROBE_SYMBOL(kprobe_int3_handler);
  * When a retprobed function returns, this code saves registers and
  * calls trampoline_handler() runs, which calls the kretprobe's handler.
  */
-static void __used kretprobe_trampoline_holder(void)
-{
-	asm volatile (
-			".global kretprobe_trampoline\n"
-			"kretprobe_trampoline: \n"
+asm(
+	".global kretprobe_trampoline\n"
+	".type kretprobe_trampoline, @function\n"
+	"kretprobe_trampoline:\n"
 #ifdef CONFIG_X86_64
-			/* We don't bother saving the ss register */
-			"	pushq %rsp\n"
-			"	pushfq\n"
-			SAVE_REGS_STRING
-			"	movq %rsp, %rdi\n"
-			"	call trampoline_handler\n"
-			/* Replace saved sp with true return address. */
-			"	movq %rax, 152(%rsp)\n"
-			RESTORE_REGS_STRING
-			"	popfq\n"
+	/* We don't bother saving the ss register */
+	"	pushq %rsp\n"
+	"	pushfq\n"
+	SAVE_REGS_STRING
+	"	movq %rsp, %rdi\n"
+	"	call trampoline_handler\n"
+	/* Replace saved sp with true return address. */
+	"	movq %rax, 152(%rsp)\n"
+	RESTORE_REGS_STRING
+	"	popfq\n"
 #else
-			"	pushf\n"
-			SAVE_REGS_STRING
-			"	movl %esp, %eax\n"
-			"	call trampoline_handler\n"
-			/* Move flags to cs */
-			"	movl 56(%esp), %edx\n"
-			"	movl %edx, 52(%esp)\n"
-			/* Replace saved flags with true return address. */
-			"	movl %eax, 56(%esp)\n"
-			RESTORE_REGS_STRING
-			"	popf\n"
+	"	pushf\n"
+	SAVE_REGS_STRING
+	"	movl %esp, %eax\n"
+	"	call trampoline_handler\n"
+	/* Move flags to cs */
+	"	movl 56(%esp), %edx\n"
+	"	movl %edx, 52(%esp)\n"
+	/* Replace saved flags with true return address. */
+	"	movl %eax, 56(%esp)\n"
+	RESTORE_REGS_STRING
+	"	popf\n"
 #endif
-			"	ret\n");
-}
-NOKPROBE_SYMBOL(kretprobe_trampoline_holder);
+	"	ret\n"
+	".size kretprobe_trampoline, .-kretprobe_trampoline\n"
+);
 NOKPROBE_SYMBOL(kretprobe_trampoline);
+STACK_FRAME_NON_STANDARD(kretprobe_trampoline);
 
 /*
  * Called from kretprobe_trampoline
diff --git a/arch/x86/kernel/vmlinux.lds.S b/arch/x86/kernel/vmlinux.lds.S
index 6bb070e5..73de260 100644
--- a/arch/x86/kernel/vmlinux.lds.S
+++ b/arch/x86/kernel/vmlinux.lds.S
@@ -340,7 +340,10 @@ SECTIONS
 
 	/* Sections to be discarded */
 	DISCARDS
-	/DISCARD/ : { *(.eh_frame) }
+	/DISCARD/ : {
+		*(.eh_frame)
+		*(__func_stack_frame_non_standard)
+	}
 }
 
 
diff --git a/arch/x86/kvm/emulate.c b/arch/x86/kvm/emulate.c
index b9b09fe..0f62943 100644
--- a/arch/x86/kvm/emulate.c
+++ b/arch/x86/kvm/emulate.c
@@ -309,23 +309,29 @@ static void invalidate_registers(struct x86_emulate_ctxt *ctxt)
 
 static int fastop(struct x86_emulate_ctxt *ctxt, void (*fop)(struct fastop *));
 
-#define FOP_ALIGN ".align " __stringify(FASTOP_SIZE) " \n\t"
+#define FOP_FUNC(name) \
+	".align " __stringify(FASTOP_SIZE) " \n\t" \
+	".type " name ", @function \n\t" \
+	name ":\n\t"
+
 #define FOP_RET   "ret \n\t"
 
 #define FOP_START(op) \
 	extern void em_##op(struct fastop *fake); \
 	asm(".pushsection .text, \"ax\" \n\t" \
 	    ".global em_" #op " \n\t" \
-            FOP_ALIGN \
-	    "em_" #op ": \n\t"
+	    FOP_FUNC("em_" #op)
 
 #define FOP_END \
 	    ".popsection")
 
-#define FOPNOP() FOP_ALIGN FOP_RET
+#define FOPNOP() \
+	FOP_FUNC(__stringify(__UNIQUE_ID(nop))) \
+	FOP_RET
 
 #define FOP1E(op,  dst) \
-	FOP_ALIGN "10: " #op " %" #dst " \n\t" FOP_RET
+	FOP_FUNC(#op "_" #dst) \
+	"10: " #op " %" #dst " \n\t" FOP_RET
 
 #define FOP1EEX(op,  dst) \
 	FOP1E(op, dst) _ASM_EXTABLE(10b, kvm_fastop_exception)
@@ -357,7 +363,8 @@ static int fastop(struct x86_emulate_ctxt *ctxt, void (*fop)(struct fastop *));
 	FOP_END
 
 #define FOP2E(op,  dst, src)	   \
-	FOP_ALIGN #op " %" #src ", %" #dst " \n\t" FOP_RET
+	FOP_FUNC(#op "_" #dst "_" #src) \
+	#op " %" #src ", %" #dst " \n\t" FOP_RET
 
 #define FASTOP2(op) \
 	FOP_START(op) \
@@ -395,7 +402,8 @@ static int fastop(struct x86_emulate_ctxt *ctxt, void (*fop)(struct fastop *));
 	FOP_END
 
 #define FOP3E(op,  dst, src, src2) \
-	FOP_ALIGN #op " %" #src2 ", %" #src ", %" #dst " \n\t" FOP_RET
+	FOP_FUNC(#op "_" #dst "_" #src "_" #src2) \
+	#op " %" #src2 ", %" #src ", %" #dst " \n\t" FOP_RET
 
 /* 3-operand, word-only, src2=cl */
 #define FASTOP3WCL(op) \
@@ -407,7 +415,12 @@ static int fastop(struct x86_emulate_ctxt *ctxt, void (*fop)(struct fastop *));
 	FOP_END
 
 /* Special case for SETcc - 1 instruction per cc */
-#define FOP_SETCC(op) ".align 4; " #op " %al; ret \n\t"
+#define FOP_SETCC(op) \
+	".align 4 \n\t" \
+	".type " #op ", @function \n\t" \
+	#op ": \n\t" \
+	#op " %al \n\t" \
+	FOP_RET
 
 asm(".global kvm_fastop_exception \n"
     "kvm_fastop_exception: xor %esi, %esi; ret");
@@ -956,7 +969,7 @@ static int em_bsr_c(struct x86_emulate_ctxt *ctxt)
 	return fastop(ctxt, em_bsr);
 }
 
-static u8 test_cc(unsigned int condition, unsigned long flags)
+static __always_inline u8 test_cc(unsigned int condition, unsigned long flags)
 {
 	u8 rc;
 	void (*fop)(void) = (void *)em_setcc + 4 * (condition & 0xf);
diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c
index 5e45c27..75173ef 100644
--- a/arch/x86/kvm/vmx.c
+++ b/arch/x86/kvm/vmx.c
@@ -8385,6 +8385,7 @@ static void vmx_complete_atomic_exit(struct vcpu_vmx *vmx)
 static void vmx_handle_external_intr(struct kvm_vcpu *vcpu)
 {
 	u32 exit_intr_info = vmcs_read32(VM_EXIT_INTR_INFO);
+	register void *__sp asm(_ASM_SP);
 
 	/*
 	 * If external interrupt exists, IF bit is set in rflags/eflags on the
@@ -8417,8 +8418,9 @@ static void vmx_handle_external_intr(struct kvm_vcpu *vcpu)
 			"call *%[entry]\n\t"
 			:
 #ifdef CONFIG_X86_64
-			[sp]"=&r"(tmp)
+			[sp]"=&r"(tmp),
 #endif
+			"+r"(__sp)
 			:
 			[entry]"r"(entry),
 			[ss]"i"(__KERNEL_DS),
diff --git a/arch/x86/lib/insn.c b/arch/x86/lib/insn.c
index 8f72b33..1a41693 100644
--- a/arch/x86/lib/insn.c
+++ b/arch/x86/lib/insn.c
@@ -374,7 +374,7 @@ void insn_get_displacement(struct insn *insn)
 		if (mod == 3)
 			goto out;
 		if (mod == 1) {
-			insn->displacement.value = get_next(char, insn);
+			insn->displacement.value = get_next(signed char, insn);
 			insn->displacement.nbytes = 1;
 		} else if (insn->addr_bytes == 2) {
 			if ((mod == 0 && rm == 6) || mod == 2) {
@@ -532,7 +532,7 @@ void insn_get_immediate(struct insn *insn)
 
 	switch (inat_immediate_size(insn->attr)) {
 	case INAT_IMM_BYTE:
-		insn->immediate.value = get_next(char, insn);
+		insn->immediate.value = get_next(signed char, insn);
 		insn->immediate.nbytes = 1;
 		break;
 	case INAT_IMM_WORD:
@@ -566,7 +566,7 @@ void insn_get_immediate(struct insn *insn)
 		goto err_out;
 	}
 	if (inat_has_second_immediate(insn->attr)) {
-		insn->immediate2.value = get_next(char, insn);
+		insn->immediate2.value = get_next(signed char, insn);
 		insn->immediate2.nbytes = 1;
 	}
 done:
diff --git a/arch/x86/lib/rwsem.S b/arch/x86/lib/rwsem.S
index 40027db..be110ef 100644
--- a/arch/x86/lib/rwsem.S
+++ b/arch/x86/lib/rwsem.S
@@ -15,6 +15,7 @@
 
 #include <linux/linkage.h>
 #include <asm/alternative-asm.h>
+#include <asm/frame.h>
 
 #define __ASM_HALF_REG(reg)	__ASM_SEL(reg, e##reg)
 #define __ASM_HALF_SIZE(inst)	__ASM_SEL(inst##w, inst##l)
@@ -84,24 +85,29 @@
 
 /* Fix up special calling conventions */
 ENTRY(call_rwsem_down_read_failed)
+	FRAME_BEGIN
 	save_common_regs
 	__ASM_SIZE(push,) %__ASM_REG(dx)
 	movq %rax,%rdi
 	call rwsem_down_read_failed
 	__ASM_SIZE(pop,) %__ASM_REG(dx)
 	restore_common_regs
+	FRAME_END
 	ret
 ENDPROC(call_rwsem_down_read_failed)
 
 ENTRY(call_rwsem_down_write_failed)
+	FRAME_BEGIN
 	save_common_regs
 	movq %rax,%rdi
 	call rwsem_down_write_failed
 	restore_common_regs
+	FRAME_END
 	ret
 ENDPROC(call_rwsem_down_write_failed)
 
 ENTRY(call_rwsem_wake)
+	FRAME_BEGIN
 	/* do nothing if still outstanding active readers */
 	__ASM_HALF_SIZE(dec) %__ASM_HALF_REG(dx)
 	jnz 1f
@@ -109,15 +115,18 @@ ENTRY(call_rwsem_wake)
 	movq %rax,%rdi
 	call rwsem_wake
 	restore_common_regs
-1:	ret
+1:	FRAME_END
+	ret
 ENDPROC(call_rwsem_wake)
 
 ENTRY(call_rwsem_downgrade_wake)
+	FRAME_BEGIN
 	save_common_regs
 	__ASM_SIZE(push,) %__ASM_REG(dx)
 	movq %rax,%rdi
 	call rwsem_downgrade_wake
 	__ASM_SIZE(pop,) %__ASM_REG(dx)
 	restore_common_regs
+	FRAME_END
 	ret
 ENDPROC(call_rwsem_downgrade_wake)
diff --git a/arch/x86/net/bpf_jit.S b/arch/x86/net/bpf_jit.S
index 4093216..f2a7faf 100644
--- a/arch/x86/net/bpf_jit.S
+++ b/arch/x86/net/bpf_jit.S
@@ -8,6 +8,7 @@
  * of the License.
  */
 #include <linux/linkage.h>
+#include <asm/frame.h>
 
 /*
  * Calling convention :
@@ -22,15 +23,16 @@
 	32 /* space for rbx,r13,r14,r15 */ + \
 	8 /* space for skb_copy_bits */)
 
-sk_load_word:
-	.globl	sk_load_word
+#define FUNC(name) \
+	.globl name; \
+	.type name, @function; \
+	name:
 
+FUNC(sk_load_word)
 	test	%esi,%esi
 	js	bpf_slow_path_word_neg
 
-sk_load_word_positive_offset:
-	.globl	sk_load_word_positive_offset
-
+FUNC(sk_load_word_positive_offset)
 	mov	%r9d,%eax		# hlen
 	sub	%esi,%eax		# hlen - offset
 	cmp	$3,%eax
@@ -39,15 +41,11 @@ sk_load_word_positive_offset:
 	bswap   %eax  			/* ntohl() */
 	ret
 
-sk_load_half:
-	.globl	sk_load_half
-
+FUNC(sk_load_half)
 	test	%esi,%esi
 	js	bpf_slow_path_half_neg
 
-sk_load_half_positive_offset:
-	.globl	sk_load_half_positive_offset
-
+FUNC(sk_load_half_positive_offset)
 	mov	%r9d,%eax
 	sub	%esi,%eax		#	hlen - offset
 	cmp	$1,%eax
@@ -56,15 +54,11 @@ sk_load_half_positive_offset:
 	rol	$8,%ax			# ntohs()
 	ret
 
-sk_load_byte:
-	.globl	sk_load_byte
-
+FUNC(sk_load_byte)
 	test	%esi,%esi
 	js	bpf_slow_path_byte_neg
 
-sk_load_byte_positive_offset:
-	.globl	sk_load_byte_positive_offset
-
+FUNC(sk_load_byte_positive_offset)
 	cmp	%esi,%r9d   /* if (offset >= hlen) goto bpf_slow_path_byte */
 	jle	bpf_slow_path_byte
 	movzbl	(SKBDATA,%rsi),%eax
@@ -72,16 +66,18 @@ sk_load_byte_positive_offset:
 
 /* rsi contains offset and can be scratched */
 #define bpf_slow_path_common(LEN)		\
+	lea	-MAX_BPF_STACK + 32(%rbp), %rdx;\
+	FRAME_BEGIN;				\
 	mov	%rbx, %rdi; /* arg1 == skb */	\
 	push	%r9;				\
 	push	SKBDATA;			\
 /* rsi already has offset */			\
 	mov	$LEN,%ecx;	/* len */	\
-	lea	- MAX_BPF_STACK + 32(%rbp),%rdx;			\
 	call	skb_copy_bits;			\
 	test    %eax,%eax;			\
 	pop	SKBDATA;			\
-	pop	%r9;
+	pop	%r9;				\
+	FRAME_END
 
 
 bpf_slow_path_word:
@@ -106,6 +102,7 @@ bpf_slow_path_byte:
 	ret
 
 #define sk_negative_common(SIZE)				\
+	FRAME_BEGIN;						\
 	mov	%rbx, %rdi; /* arg1 == skb */			\
 	push	%r9;						\
 	push	SKBDATA;					\
@@ -115,13 +112,14 @@ bpf_slow_path_byte:
 	test	%rax,%rax;					\
 	pop	SKBDATA;					\
 	pop	%r9;						\
+	FRAME_END;						\
 	jz	bpf_error
 
 bpf_slow_path_word_neg:
 	cmp	SKF_MAX_NEG_OFF, %esi	/* test range */
 	jl	bpf_error	/* offset lower -> error  */
-sk_load_word_negative_offset:
-	.globl	sk_load_word_negative_offset
+
+FUNC(sk_load_word_negative_offset)
 	sk_negative_common(4)
 	mov	(%rax), %eax
 	bswap	%eax
@@ -130,8 +128,8 @@ sk_load_word_negative_offset:
 bpf_slow_path_half_neg:
 	cmp	SKF_MAX_NEG_OFF, %esi
 	jl	bpf_error
-sk_load_half_negative_offset:
-	.globl	sk_load_half_negative_offset
+
+FUNC(sk_load_half_negative_offset)
 	sk_negative_common(2)
 	mov	(%rax),%ax
 	rol	$8,%ax
@@ -141,8 +139,8 @@ sk_load_half_negative_offset:
 bpf_slow_path_byte_neg:
 	cmp	SKF_MAX_NEG_OFF, %esi
 	jl	bpf_error
-sk_load_byte_negative_offset:
-	.globl	sk_load_byte_negative_offset
+
+FUNC(sk_load_byte_negative_offset)
 	sk_negative_common(1)
 	movzbl	(%rax), %eax
 	ret
diff --git a/arch/x86/platform/efi/Makefile b/arch/x86/platform/efi/Makefile
index 2846aaa..066619b 100644
--- a/arch/x86/platform/efi/Makefile
+++ b/arch/x86/platform/efi/Makefile
@@ -1,3 +1,5 @@
+OBJECT_FILES_NON_STANDARD_efi_thunk_$(BITS).o := y
+
 obj-$(CONFIG_EFI) 		+= quirks.o efi.o efi_$(BITS).o efi_stub_$(BITS).o
 obj-$(CONFIG_ACPI_BGRT) += efi-bgrt.o
 obj-$(CONFIG_EARLY_PRINTK_EFI)	+= early_printk.o
diff --git a/arch/x86/platform/efi/efi_stub_64.S b/arch/x86/platform/efi/efi_stub_64.S
index 86d0f9e..0df2dcc 100644
--- a/arch/x86/platform/efi/efi_stub_64.S
+++ b/arch/x86/platform/efi/efi_stub_64.S
@@ -11,6 +11,7 @@
 #include <asm/msr.h>
 #include <asm/processor-flags.h>
 #include <asm/page_types.h>
+#include <asm/frame.h>
 
 #define SAVE_XMM			\
 	mov %rsp, %rax;			\
@@ -74,6 +75,7 @@
 	.endm
 
 ENTRY(efi_call)
+	FRAME_BEGIN
 	SAVE_XMM
 	mov (%rsp), %rax
 	mov 8(%rax), %rax
@@ -88,6 +90,7 @@ ENTRY(efi_call)
 	RESTORE_PGT
 	addq $48, %rsp
 	RESTORE_XMM
+	FRAME_END
 	ret
 ENDPROC(efi_call)
 
diff --git a/arch/x86/power/hibernate_asm_64.S b/arch/x86/power/hibernate_asm_64.S
index e2386cb..4400a43 100644
--- a/arch/x86/power/hibernate_asm_64.S
+++ b/arch/x86/power/hibernate_asm_64.S
@@ -21,8 +21,10 @@
 #include <asm/page_types.h>
 #include <asm/asm-offsets.h>
 #include <asm/processor-flags.h>
+#include <asm/frame.h>
 
 ENTRY(swsusp_arch_suspend)
+	FRAME_BEGIN
 	movq	$saved_context, %rax
 	movq	%rsp, pt_regs_sp(%rax)
 	movq	%rbp, pt_regs_bp(%rax)
@@ -50,7 +52,9 @@ ENTRY(swsusp_arch_suspend)
 	movq	%rax, restore_cr3(%rip)
 
 	call swsusp_save
+	FRAME_END
 	ret
+ENDPROC(swsusp_arch_suspend)
 
 ENTRY(restore_image)
 	/* switch to temporary page tables */
@@ -107,6 +111,7 @@ ENTRY(core_restore_code)
 	 */
 
 ENTRY(restore_registers)
+	FRAME_BEGIN
 	/* go back to the original page tables */
 	movq    %rbx, %cr3
 
@@ -147,4 +152,6 @@ ENTRY(restore_registers)
 	/* tell the hibernation core that we've just restored the memory */
 	movq	%rax, in_suspend(%rip)
 
+	FRAME_END
 	ret
+ENDPROC(restore_registers)
diff --git a/arch/x86/purgatory/Makefile b/arch/x86/purgatory/Makefile
index 2c835e3..92e3e1d 100644
--- a/arch/x86/purgatory/Makefile
+++ b/arch/x86/purgatory/Makefile
@@ -1,3 +1,5 @@
+OBJECT_FILES_NON_STANDARD := y
+
 purgatory-y := purgatory.o stack.o setup-x86_$(BITS).o sha256.o entry64.o string.o
 
 targets += $(purgatory-y)
diff --git a/arch/x86/realmode/Makefile b/arch/x86/realmode/Makefile
index e02c2c6..682c895 100644
--- a/arch/x86/realmode/Makefile
+++ b/arch/x86/realmode/Makefile
@@ -6,7 +6,9 @@
 # for more details.
 #
 #
-KASAN_SANITIZE := n
+KASAN_SANITIZE			:= n
+OBJECT_FILES_NON_STANDARD	:= y
+
 subdir- := rm
 
 obj-y += init.o
diff --git a/arch/x86/realmode/rm/Makefile b/arch/x86/realmode/rm/Makefile
index 3e75fcf..053abe7b0 100644
--- a/arch/x86/realmode/rm/Makefile
+++ b/arch/x86/realmode/rm/Makefile
@@ -6,7 +6,8 @@
 # for more details.
 #
 #
-KASAN_SANITIZE := n
+KASAN_SANITIZE			:= n
+OBJECT_FILES_NON_STANDARD	:= y
 
 always := realmode.bin realmode.relocs
 
diff --git a/arch/x86/xen/enlighten.c b/arch/x86/xen/enlighten.c
index 2c26108..2379a5a 100644
--- a/arch/x86/xen/enlighten.c
+++ b/arch/x86/xen/enlighten.c
@@ -32,6 +32,7 @@
 #include <linux/gfp.h>
 #include <linux/memblock.h>
 #include <linux/edd.h>
+#include <linux/frame.h>
 
 #ifdef CONFIG_KEXEC_CORE
 #include <linux/kexec.h>
@@ -351,8 +352,8 @@ static void xen_cpuid(unsigned int *ax, unsigned int *bx,
 	*cx &= maskecx;
 	*cx |= setecx;
 	*dx &= maskedx;
-
 }
+STACK_FRAME_NON_STANDARD(xen_cpuid); /* XEN_EMULATE_PREFIX */
 
 static bool __init xen_check_mwait(void)
 {
diff --git a/arch/x86/xen/xen-asm.S b/arch/x86/xen/xen-asm.S
index 3e45aa0..eff224d 100644
--- a/arch/x86/xen/xen-asm.S
+++ b/arch/x86/xen/xen-asm.S
@@ -14,6 +14,7 @@
 #include <asm/asm-offsets.h>
 #include <asm/percpu.h>
 #include <asm/processor-flags.h>
+#include <asm/frame.h>
 
 #include "xen-asm.h"
 
@@ -23,6 +24,7 @@
  * then enter the hypervisor to get them handled.
  */
 ENTRY(xen_irq_enable_direct)
+	FRAME_BEGIN
 	/* Unmask events */
 	movb $0, PER_CPU_VAR(xen_vcpu_info) + XEN_vcpu_info_mask
 
@@ -39,6 +41,7 @@ ENTRY(xen_irq_enable_direct)
 2:	call check_events
 1:
 ENDPATCH(xen_irq_enable_direct)
+	FRAME_END
 	ret
 	ENDPROC(xen_irq_enable_direct)
 	RELOC(xen_irq_enable_direct, 2b+1)
@@ -82,6 +85,7 @@ ENDPATCH(xen_save_fl_direct)
  * enters the hypervisor to get them delivered if so.
  */
 ENTRY(xen_restore_fl_direct)
+	FRAME_BEGIN
 #ifdef CONFIG_X86_64
 	testw $X86_EFLAGS_IF, %di
 #else
@@ -100,6 +104,7 @@ ENTRY(xen_restore_fl_direct)
 2:	call check_events
 1:
 ENDPATCH(xen_restore_fl_direct)
+	FRAME_END
 	ret
 	ENDPROC(xen_restore_fl_direct)
 	RELOC(xen_restore_fl_direct, 2b+1)
@@ -109,7 +114,8 @@ ENDPATCH(xen_restore_fl_direct)
  * Force an event check by making a hypercall, but preserve regs
  * before making the call.
  */
-check_events:
+ENTRY(check_events)
+	FRAME_BEGIN
 #ifdef CONFIG_X86_32
 	push %eax
 	push %ecx
@@ -139,4 +145,6 @@ check_events:
 	pop %rcx
 	pop %rax
 #endif
+	FRAME_END
 	ret
+ENDPROC(check_events)
diff --git a/arch/x86/xen/xen-asm_64.S b/arch/x86/xen/xen-asm_64.S
index cc8acc4..c3df431 100644
--- a/arch/x86/xen/xen-asm_64.S
+++ b/arch/x86/xen/xen-asm_64.S
@@ -26,6 +26,7 @@ ENTRY(xen_adjust_exception_frame)
 	mov 8+0(%rsp), %rcx
 	mov 8+8(%rsp), %r11
 	ret $16
+ENDPROC(xen_adjust_exception_frame)
 
 hypercall_iret = hypercall_page + __HYPERVISOR_iret * 32
 /*