diff --git a/.gitignore b/.gitignore
index fa3e5f1d0808..b17dcd217d83 100644
--- a/.gitignore
+++ b/.gitignore
@@ -33,6 +33,7 @@
 *.lzo
 *.patch
 *.gcno
+*.ll
 modules.builtin
 Module.symvers
 *.dwo
diff --git a/Kbuild b/Kbuild
index f55cefd9bf29..f56ed561a284 100644
--- a/Kbuild
+++ b/Kbuild
@@ -6,31 +6,6 @@
 # 3) Generate asm-offsets.h (may need bounds.h and timeconst.h)
 # 4) Check for missing system calls
 
-# Default sed regexp - multiline due to syntax constraints
-define sed-y
-	"/^->/{s:->#\(.*\):/* \1 */:; \
-	s:^->\([^ ]*\) [\$$#]*\([-0-9]*\) \(.*\):#define \1 \2 /* \3 */:; \
-	s:^->\([^ ]*\) [\$$#]*\([^ ]*\) \(.*\):#define \1 \2 /* \3 */:; \
-	s:->::; p;}"
-endef
-
-# Use filechk to avoid rebuilds when a header changes, but the resulting file
-# does not
-define filechk_offsets
-	(set -e; \
-	 echo "#ifndef $2"; \
-	 echo "#define $2"; \
-	 echo "/*"; \
-	 echo " * DO NOT MODIFY."; \
-	 echo " *"; \
-	 echo " * This file was generated by Kbuild"; \
-	 echo " */"; \
-	 echo ""; \
-	 sed -ne $(sed-y); \
-	 echo ""; \
-	 echo "#endif" )
-endef
-
 #####
 # 1) Generate bounds.h
 
diff --git a/Makefile b/Makefile
index 12969e3e06f6..b74265c18087 100644
--- a/Makefile
+++ b/Makefile
@@ -301,7 +301,7 @@ CONFIG_SHELL := $(shell if [ -x "$$BASH" ]; then echo $$BASH; \
 
 HOSTCC       = gcc
 HOSTCXX      = g++
-HOSTCFLAGS   = -Wall -Wmissing-prototypes -Wstrict-prototypes -O2 -fomit-frame-pointer -std=gnu89
+HOSTCFLAGS   := -Wall -Wmissing-prototypes -Wstrict-prototypes -O2 -fomit-frame-pointer -std=gnu89
 HOSTCXXFLAGS = -O2
 
 ifeq ($(shell $(HOSTCC) -v 2>&1 | grep -c "clang version"), 1)
@@ -624,7 +624,7 @@ KBUILD_CFLAGS	+= $(call cc-disable-warning, format-overflow)
 KBUILD_CFLAGS	+= $(call cc-disable-warning, int-in-bool-context)
 
 ifdef CONFIG_CC_OPTIMIZE_FOR_SIZE
-KBUILD_CFLAGS	+= -Os
+KBUILD_CFLAGS	+= $(call cc-option,-Oz,-Os)
 else
 ifdef CONFIG_PROFILE_ALL_BRANCHES
 KBUILD_CFLAGS	+= -O2
@@ -694,11 +694,22 @@ endif
 KBUILD_CFLAGS += $(stackp-flag)
 
 ifeq ($(cc-name),clang)
+ifneq ($(CROSS_COMPILE),)
+CLANG_TRIPLE    ?= $(CROSS_COMPILE)
+CLANG_TARGET	:= -target $(notdir $(CLANG_TRIPLE:%-=%))
+GCC_TOOLCHAIN	:= $(realpath $(dir $(shell which $(LD)))/..)
+endif
+ifneq ($(GCC_TOOLCHAIN),)
+CLANG_GCC_TC	:= -gcc-toolchain $(GCC_TOOLCHAIN)
+endif
+KBUILD_CFLAGS += $(CLANG_TARGET) $(CLANG_GCC_TC)
+KBUILD_AFLAGS += $(CLANG_TARGET) $(CLANG_GCC_TC)
 KBUILD_CPPFLAGS += $(call cc-option,-Qunused-arguments,)
-KBUILD_CPPFLAGS += $(call cc-option,-Wno-unknown-warning-option,)
 KBUILD_CFLAGS += $(call cc-disable-warning, unused-variable)
 KBUILD_CFLAGS += $(call cc-disable-warning, format-invalid-specifier)
 KBUILD_CFLAGS += $(call cc-disable-warning, gnu)
+KBUILD_CFLAGS += $(call cc-disable-warning, address-of-packed-member)
+KBUILD_CFLAGS += $(call cc-disable-warning, duplicate-decl-specifier)
 # Quiet clang warning: comparison of unsigned expression < 0 is always false
 KBUILD_CFLAGS += $(call cc-disable-warning, tautological-compare)
 # CLANG uses a _MergedGlobals as optimization, but this breaks modpost, as the
@@ -706,6 +717,8 @@ KBUILD_CFLAGS += $(call cc-disable-warning, tautological-compare)
 # See modpost pattern 2
 KBUILD_CFLAGS += $(call cc-option, -mno-global-merge,)
 KBUILD_CFLAGS += $(call cc-option, -fcatch-undefined-behavior)
+KBUILD_CFLAGS += $(call cc-option, -no-integrated-as)
+KBUILD_AFLAGS += $(call cc-option, -no-integrated-as)
 else
 
 # These warnings generated too much noise in a regular build.
@@ -1281,6 +1294,8 @@ help:
 	@echo  '                    (default: $$(INSTALL_MOD_PATH)/lib/firmware)'
 	@echo  '  dir/            - Build all files in dir and below'
 	@echo  '  dir/file.[ois]  - Build specified target only'
+	@echo  '  dir/file.ll     - Build the LLVM assembly file'
+	@echo  '                    (requires compiler support for LLVM assembly generation)'
 	@echo  '  dir/file.lst    - Build specified mixed source/assembly target only'
 	@echo  '                    (requires a recent binutils and recent build (System.map))'
 	@echo  '  dir/file.ko     - Build module including final link'
@@ -1456,6 +1471,7 @@ clean: $(clean-dirs)
 		-o -name '.*.d' -o -name '.*.tmp' -o -name '*.mod.c' \
 		-o -name '*.symtypes' -o -name 'modules.order' \
 		-o -name modules.builtin -o -name '.tmp_*.o.*' \
+		-o -name '*.ll' \
 		-o -name '*.gcno' \) -type f -print | xargs rm -f
 
 # Generate tags for editors
@@ -1559,6 +1575,8 @@ endif
 	$(Q)$(MAKE) $(build)=$(build-dir) $(target-dir)$(notdir $@)
 %.symtypes: %.c prepare scripts FORCE
 	$(Q)$(MAKE) $(build)=$(build-dir) $(target-dir)$(notdir $@)
+%.ll: %.c prepare scripts FORCE
+	$(Q)$(MAKE) $(build)=$(build-dir) $(target-dir)$(notdir $@)
 
 # Modules
 /: prepare scripts FORCE
diff --git a/arch/arm64/Makefile b/arch/arm64/Makefile
index ba55698f71e8..c3bc092fc128 100644
--- a/arch/arm64/Makefile
+++ b/arch/arm64/Makefile
@@ -30,7 +30,14 @@ $(warning LSE atomics not supported by binutils)
   endif
 endif
 
-KBUILD_CFLAGS	+= -mgeneral-regs-only $(lseinstr)
+ifeq ($(cc-name),clang)
+# This is a workaround for https://bugs.llvm.org/show_bug.cgi?id=30792.
+# TODO: revert when this is fixed in LLVM.
+KBUILD_CFLAGS	+= -mno-implicit-float
+else
+KBUILD_CFLAGS	+= -mgeneral-regs-only
+endif
+KBUILD_CFLAGS	+= $(lseinstr)
 KBUILD_CFLAGS	+= -fno-pic
 KBUILD_CFLAGS	+= -fno-asynchronous-unwind-tables
 KBUILD_CFLAGS	+= $(call cc-option, -mpc-relative-literal-loads)
@@ -66,6 +73,10 @@ else
 TEXT_OFFSET := 0x00080000
 endif
 
+ifeq ($(cc-name),clang)
+KBUILD_CFLAGS += $(call cc-disable-warning, asm-operand-widths)
+endif
+
 # KASAN_SHADOW_OFFSET = VA_START + (1 << (VA_BITS - 3)) - (1 << 61)
 # in 32-bit arithmetic
 KASAN_SHADOW_OFFSET := $(shell printf "0x%08x00000000\n" $$(( \
diff --git a/arch/arm64/crypto/sha1-ce-core.S b/arch/arm64/crypto/sha1-ce-core.S
index c98e7e849f06..8550408735a0 100644
--- a/arch/arm64/crypto/sha1-ce-core.S
+++ b/arch/arm64/crypto/sha1-ce-core.S
@@ -82,7 +82,8 @@ ENTRY(sha1_ce_transform)
 	ldr		dgb, [x0, #16]
 
 	/* load sha1_ce_state::finalize */
-	ldr		w4, [x0, #:lo12:sha1_ce_offsetof_finalize]
+	ldr_l		w4, sha1_ce_offsetof_finalize, x4
+	ldr		w4, [x0, x4]
 
 	/* load input */
 0:	ld1		{v8.4s-v11.4s}, [x1], #64
@@ -132,7 +133,8 @@ CPU_LE(	rev32		v11.16b, v11.16b	)
 	 * the padding is handled by the C code in that case.
 	 */
 	cbz		x4, 3f
-	ldr		x4, [x0, #:lo12:sha1_ce_offsetof_count]
+	ldr_l		w4, sha1_ce_offsetof_count, x4
+	ldr		x4, [x0, x4]
 	movi		v9.2d, #0
 	mov		x8, #0x80000000
 	movi		v10.2d, #0
diff --git a/arch/arm64/crypto/sha1-ce-glue.c b/arch/arm64/crypto/sha1-ce-glue.c
index aefda9868627..ea319c055f5d 100644
--- a/arch/arm64/crypto/sha1-ce-glue.c
+++ b/arch/arm64/crypto/sha1-ce-glue.c
@@ -17,9 +17,6 @@
 #include <linux/crypto.h>
 #include <linux/module.h>
 
-#define ASM_EXPORT(sym, val) \
-	asm(".globl " #sym "; .set " #sym ", %0" :: "I"(val));
-
 MODULE_DESCRIPTION("SHA1 secure hash using ARMv8 Crypto Extensions");
 MODULE_AUTHOR("Ard Biesheuvel <ard.biesheuvel@linaro.org>");
 MODULE_LICENSE("GPL v2");
@@ -32,6 +29,9 @@ struct sha1_ce_state {
 asmlinkage void sha1_ce_transform(struct sha1_ce_state *sst, u8 const *src,
 				  int blocks);
 
+const u32 sha1_ce_offsetof_count = offsetof(struct sha1_ce_state, sst.count);
+const u32 sha1_ce_offsetof_finalize = offsetof(struct sha1_ce_state, finalize);
+
 static int sha1_ce_update(struct shash_desc *desc, const u8 *data,
 			  unsigned int len)
 {
@@ -52,11 +52,6 @@ static int sha1_ce_finup(struct shash_desc *desc, const u8 *data,
 	struct sha1_ce_state *sctx = shash_desc_ctx(desc);
 	bool finalize = !sctx->sst.count && !(len % SHA1_BLOCK_SIZE);
 
-	ASM_EXPORT(sha1_ce_offsetof_count,
-		   offsetof(struct sha1_ce_state, sst.count));
-	ASM_EXPORT(sha1_ce_offsetof_finalize,
-		   offsetof(struct sha1_ce_state, finalize));
-
 	/*
 	 * Allow the asm code to perform the finalization if there is no
 	 * partial data and the input is a round multiple of the block size.
diff --git a/arch/arm64/crypto/sha2-ce-core.S b/arch/arm64/crypto/sha2-ce-core.S
index 01cfee066837..679c6c002f4f 100644
--- a/arch/arm64/crypto/sha2-ce-core.S
+++ b/arch/arm64/crypto/sha2-ce-core.S
@@ -88,7 +88,8 @@ ENTRY(sha2_ce_transform)
 	ld1		{dgav.4s, dgbv.4s}, [x0]
 
 	/* load sha256_ce_state::finalize */
-	ldr		w4, [x0, #:lo12:sha256_ce_offsetof_finalize]
+	ldr_l		w4, sha256_ce_offsetof_finalize, x4
+	ldr		w4, [x0, x4]
 
 	/* load input */
 0:	ld1		{v16.4s-v19.4s}, [x1], #64
@@ -136,7 +137,8 @@ CPU_LE(	rev32		v19.16b, v19.16b	)
 	 * the padding is handled by the C code in that case.
 	 */
 	cbz		x4, 3f
-	ldr		x4, [x0, #:lo12:sha256_ce_offsetof_count]
+	ldr_l		w4, sha256_ce_offsetof_count, x4
+	ldr		x4, [x0, x4]
 	movi		v17.2d, #0
 	mov		x8, #0x80000000
 	movi		v18.2d, #0
diff --git a/arch/arm64/crypto/sha2-ce-glue.c b/arch/arm64/crypto/sha2-ce-glue.c
index 7cd587564a41..0ed9486f75dd 100644
--- a/arch/arm64/crypto/sha2-ce-glue.c
+++ b/arch/arm64/crypto/sha2-ce-glue.c
@@ -17,9 +17,6 @@
 #include <linux/crypto.h>
 #include <linux/module.h>
 
-#define ASM_EXPORT(sym, val) \
-	asm(".globl " #sym "; .set " #sym ", %0" :: "I"(val));
-
 MODULE_DESCRIPTION("SHA-224/SHA-256 secure hash using ARMv8 Crypto Extensions");
 MODULE_AUTHOR("Ard Biesheuvel <ard.biesheuvel@linaro.org>");
 MODULE_LICENSE("GPL v2");
@@ -32,6 +29,11 @@ struct sha256_ce_state {
 asmlinkage void sha2_ce_transform(struct sha256_ce_state *sst, u8 const *src,
 				  int blocks);
 
+const u32 sha256_ce_offsetof_count = offsetof(struct sha256_ce_state,
+					      sst.count);
+const u32 sha256_ce_offsetof_finalize = offsetof(struct sha256_ce_state,
+						 finalize);
+
 static int sha256_ce_update(struct shash_desc *desc, const u8 *data,
 			    unsigned int len)
 {
@@ -52,11 +54,6 @@ static int sha256_ce_finup(struct shash_desc *desc, const u8 *data,
 	struct sha256_ce_state *sctx = shash_desc_ctx(desc);
 	bool finalize = !sctx->sst.count && !(len % SHA256_BLOCK_SIZE);
 
-	ASM_EXPORT(sha256_ce_offsetof_count,
-		   offsetof(struct sha256_ce_state, sst.count));
-	ASM_EXPORT(sha256_ce_offsetof_finalize,
-		   offsetof(struct sha256_ce_state, finalize));
-
 	/*
 	 * Allow the asm code to perform the finalization if there is no
 	 * partial data and the input is a round multiple of the block size.
diff --git a/arch/ia64/kernel/Makefile b/arch/ia64/kernel/Makefile
index 3686d6abafde..9edda5466020 100644
--- a/arch/ia64/kernel/Makefile
+++ b/arch/ia64/kernel/Makefile
@@ -50,32 +50,10 @@ CFLAGS_traps.o  += -mfixed-range=f2-f5,f16-f31
 # The gate DSO image is built using a special linker script.
 include $(src)/Makefile.gate
 
-# Calculate NR_IRQ = max(IA64_NATIVE_NR_IRQS, XEN_NR_IRQS, ...) based on config
-define sed-y
-	"/^->/{s:^->\([^ ]*\) [\$$#]*\([^ ]*\) \(.*\):#define \1 \2 /* \3 */:; s:->::; p;}"
-endef
-quiet_cmd_nr_irqs = GEN     $@
-define cmd_nr_irqs
-	(set -e; \
-	 echo "#ifndef __ASM_NR_IRQS_H__"; \
-	 echo "#define __ASM_NR_IRQS_H__"; \
-	 echo "/*"; \
-	 echo " * DO NOT MODIFY."; \
-	 echo " *"; \
-	 echo " * This file was generated by Kbuild"; \
-	 echo " *"; \
-	 echo " */"; \
-	 echo ""; \
-	 sed -ne $(sed-y) $<; \
-	 echo ""; \
-	 echo "#endif" ) > $@
-endef
-
 # We use internal kbuild rules to avoid the "is up to date" message from make
 arch/$(SRCARCH)/kernel/nr-irqs.s: arch/$(SRCARCH)/kernel/nr-irqs.c
 	$(Q)mkdir -p $(dir $@)
 	$(call if_changed_dep,cc_s_c)
 
-include/generated/nr-irqs.h: arch/$(SRCARCH)/kernel/nr-irqs.s
-	$(Q)mkdir -p $(dir $@)
-	$(call cmd,nr_irqs)
+include/generated/nr-irqs.h: arch/$(SRCARCH)/kernel/nr-irqs.s FORCE
+	$(call filechk,offsets,__ASM_NR_IRQS_H__)
diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index cc9dbc5aa80f..412166ac999f 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -296,11 +296,6 @@ config X86_32_LAZY_GS
 	def_bool y
 	depends on X86_32 && !CC_STACKPROTECTOR
 
-config ARCH_HWEIGHT_CFLAGS
-	string
-	default "-fcall-saved-ecx -fcall-saved-edx" if X86_32
-	default "-fcall-saved-rdi -fcall-saved-rsi -fcall-saved-rdx -fcall-saved-rcx -fcall-saved-r8 -fcall-saved-r9 -fcall-saved-r10 -fcall-saved-r11" if X86_64
-
 config ARCH_SUPPORTS_UPROBES
 	def_bool y
 
diff --git a/arch/x86/Makefile b/arch/x86/Makefile
index 53949c886341..0048d9886725 100644
--- a/arch/x86/Makefile
+++ b/arch/x86/Makefile
@@ -11,6 +11,16 @@ else
         KBUILD_DEFCONFIG := $(ARCH)_defconfig
 endif
 
+# For gcc stack alignment is specified with -mpreferred-stack-boundary,
+# clang has the option -mstack-alignment for that purpose.
+ifneq ($(call cc-option, -mpreferred-stack-boundary=4),)
+      cc_stack_align4 := -mpreferred-stack-boundary=2
+      cc_stack_align8 := -mpreferred-stack-boundary=3
+else ifneq ($(call cc-option, -mstack-alignment=16),)
+      cc_stack_align4 := -mstack-alignment=4
+      cc_stack_align8 := -mstack-alignment=8
+endif
+
 # How to compile the 16-bit code.  Note we always compile for -march=i386;
 # that way we can complain to the user if the CPU is insufficient.
 #
@@ -24,10 +34,11 @@ REALMODE_CFLAGS	:= $(M16_CFLAGS) -g -Os -D__KERNEL__ \
 		   -DDISABLE_BRANCH_PROFILING \
 		   -Wall -Wstrict-prototypes -march=i386 -mregparm=3 \
 		   -fno-strict-aliasing -fomit-frame-pointer -fno-pic \
-		   -mno-mmx -mno-sse \
-		   $(call cc-option, -ffreestanding) \
-		   $(call cc-option, -fno-stack-protector) \
-		   $(call cc-option, -mpreferred-stack-boundary=2)
+		   -mno-mmx -mno-sse
+
+REALMODE_CFLAGS += $(call __cc-option, $(CC), $(REALMODE_CFLAGS), -ffreestanding)
+REALMODE_CFLAGS += $(call __cc-option, $(CC), $(REALMODE_CFLAGS), -fno-stack-protector)
+REALMODE_CFLAGS += $(call __cc-option, $(CC), $(REALMODE_CFLAGS), $(cc_stack_align4))
 export REALMODE_CFLAGS
 
 # BITS is used as extension for files which are available in a 32 bit
@@ -64,8 +75,10 @@ ifeq ($(CONFIG_X86_32),y)
         # with nonstandard options
         KBUILD_CFLAGS += -fno-pic
 
-        # prevent gcc from keeping the stack 16 byte aligned
-        KBUILD_CFLAGS += $(call cc-option,-mpreferred-stack-boundary=2)
+        # Align the stack to the register width instead of using the default
+        # alignment of 16 bytes. This reduces stack usage and the number of
+        # alignment instructions.
+        KBUILD_CFLAGS += $(call cc-option,$(cc_stack_align4))
 
         # Disable unit-at-a-time mode on pre-gcc-4.0 compilers, it makes gcc use
         # a lot more stack due to the lack of sharing of stacklots:
@@ -88,10 +101,10 @@ else
         KBUILD_CFLAGS += -m64
 
         # Align jump targets to 1 byte, not the default 16 bytes:
-        KBUILD_CFLAGS += -falign-jumps=1
+        KBUILD_CFLAGS += $(call cc-option,-falign-jumps=1)
 
         # Pack loops tightly as well:
-        KBUILD_CFLAGS += -falign-loops=1
+        KBUILD_CFLAGS += $(call cc-option,-falign-loops=1)
 
         # Don't autogenerate traditional x87 instructions
         KBUILD_CFLAGS += $(call cc-option,-mno-80387)
@@ -99,8 +112,14 @@ else
 
         KBUILD_CFLAGS += -fno-pic
 
-	# Use -mpreferred-stack-boundary=3 if supported.
-	KBUILD_CFLAGS += $(call cc-option,-mpreferred-stack-boundary=3)
+        # By default gcc and clang use a stack alignment of 16 bytes for x86.
+        # However the standard kernel entry on x86-64 leaves the stack on an
+        # 8-byte boundary. If the compiler isn't informed about the actual
+        # alignment it will generate extra alignment instructions for the
+        # default alignment which keep the stack *mis*aligned.
+        # Furthermore an alignment to the register width reduces stack usage
+        # and the number of alignment instructions.
+        KBUILD_CFLAGS += $(call cc-option,$(cc_stack_align8))
 
 	# Use -mskip-rax-setup if supported.
 	KBUILD_CFLAGS += $(call cc-option,-mskip-rax-setup)
diff --git a/arch/x86/boot/compressed/aslr.c b/arch/x86/boot/compressed/aslr.c
index 6a9b96b4624d..4a5fbd2da658 100644
--- a/arch/x86/boot/compressed/aslr.c
+++ b/arch/x86/boot/compressed/aslr.c
@@ -94,7 +94,7 @@ static unsigned long get_random_long(void)
 	}
 
 	/* Circular multiply for better bit diffusion */
-	asm("mul %3"
+	asm(_ASM_MUL "%3"
 	    : "=a" (random), "=d" (raw)
 	    : "a" (random), "rm" (mix_const));
 	random += raw;
diff --git a/arch/x86/boot/string.c b/arch/x86/boot/string.c
index 06ceddb3a22e..1d56adea8a7c 100644
--- a/arch/x86/boot/string.c
+++ b/arch/x86/boot/string.c
@@ -16,6 +16,15 @@
 #include "ctype.h"
 #include "string.h"
 
+/*
+ * Undef these macros so that the functions that we provide
+ * here will have the correct names regardless of how string.h
+ * may have chosen to #define them.
+ */
+#undef memcpy
+#undef memset
+#undef memcmp
+
 int memcmp(const void *s1, const void *s2, size_t len)
 {
 	u8 diff;
diff --git a/arch/x86/crypto/aes_ctrby8_avx-x86_64.S b/arch/x86/crypto/aes_ctrby8_avx-x86_64.S
index a916c4a61165..5f6a5af9c489 100644
--- a/arch/x86/crypto/aes_ctrby8_avx-x86_64.S
+++ b/arch/x86/crypto/aes_ctrby8_avx-x86_64.S
@@ -65,7 +65,6 @@
 #include <linux/linkage.h>
 #include <asm/inst.h>
 
-#define CONCAT(a,b)	a##b
 #define VMOVDQ		vmovdqu
 
 #define xdata0		%xmm0
@@ -92,8 +91,6 @@
 #define num_bytes	%r8
 
 #define tmp		%r10
-#define	DDQ(i)		CONCAT(ddq_add_,i)
-#define	XMM(i)		CONCAT(%xmm, i)
 #define	DDQ_DATA	0
 #define	XDATA		1
 #define KEY_128		1
@@ -131,12 +128,12 @@ ddq_add_8:
 /* generate a unique variable for ddq_add_x */
 
 .macro setddq n
-	var_ddq_add = DDQ(\n)
+	var_ddq_add = ddq_add_\n
 .endm
 
 /* generate a unique variable for xmm register */
 .macro setxdata n
-	var_xdata = XMM(\n)
+	var_xdata = %xmm\n
 .endm
 
 /* club the numeric 'id' to the symbol 'name' */
diff --git a/arch/x86/include/asm/arch_hweight.h b/arch/x86/include/asm/arch_hweight.h
index 259a7c1ef709..44f825c80ed5 100644
--- a/arch/x86/include/asm/arch_hweight.h
+++ b/arch/x86/include/asm/arch_hweight.h
@@ -2,8 +2,8 @@
 #define _ASM_X86_HWEIGHT_H
 
 #ifdef CONFIG_64BIT
-/* popcnt %edi, %eax -- redundant REX prefix for alignment */
-#define POPCNT32 ".byte 0xf3,0x40,0x0f,0xb8,0xc7"
+/* popcnt %edi, %eax */
+#define POPCNT32 ".byte 0xf3,0x0f,0xb8,0xc7"
 /* popcnt %rdi, %rax */
 #define POPCNT64 ".byte 0xf3,0x48,0x0f,0xb8,0xc7"
 #define REG_IN "D"
@@ -15,19 +15,15 @@
 #define REG_OUT "a"
 #endif
 
-/*
- * __sw_hweightXX are called from within the alternatives below
- * and callee-clobbered registers need to be taken care of. See
- * ARCH_HWEIGHT_CFLAGS in <arch/x86/Kconfig> for the respective
- * compiler switches.
- */
+#define __HAVE_ARCH_SW_HWEIGHT
+
 static __always_inline unsigned int __arch_hweight32(unsigned int w)
 {
-	unsigned int res = 0;
+	unsigned int res;
 
 	asm (ALTERNATIVE("call __sw_hweight32", POPCNT32, X86_FEATURE_POPCNT)
-		     : "="REG_OUT (res)
-		     : REG_IN (w));
+			 : "="REG_OUT (res)
+			 : REG_IN (w));
 
 	return res;
 }
@@ -51,11 +47,11 @@ static inline unsigned long __arch_hweight64(__u64 w)
 #else
 static __always_inline unsigned long __arch_hweight64(__u64 w)
 {
-	unsigned long res = 0;
+	unsigned long res;
 
 	asm (ALTERNATIVE("call __sw_hweight64", POPCNT64, X86_FEATURE_POPCNT)
-		     : "="REG_OUT (res)
-		     : REG_IN (w));
+			 : "="REG_OUT (res)
+			 : REG_IN (w));
 
 	return res;
 }
diff --git a/arch/x86/include/asm/asm.h b/arch/x86/include/asm/asm.h
index 189679aba703..1f16ec50abeb 100644
--- a/arch/x86/include/asm/asm.h
+++ b/arch/x86/include/asm/asm.h
@@ -32,6 +32,7 @@
 #define _ASM_ADD	__ASM_SIZE(add)
 #define _ASM_SUB	__ASM_SIZE(sub)
 #define _ASM_XADD	__ASM_SIZE(xadd)
+#define _ASM_MUL	__ASM_SIZE(mul)
 
 #define _ASM_AX		__ASM_REG(ax)
 #define _ASM_BX		__ASM_REG(bx)
diff --git a/arch/x86/kernel/i386_ksyms_32.c b/arch/x86/kernel/i386_ksyms_32.c
index 64341aa485ae..d40ee8a38fed 100644
--- a/arch/x86/kernel/i386_ksyms_32.c
+++ b/arch/x86/kernel/i386_ksyms_32.c
@@ -42,3 +42,5 @@ EXPORT_SYMBOL(empty_zero_page);
 EXPORT_SYMBOL(___preempt_schedule);
 EXPORT_SYMBOL(___preempt_schedule_notrace);
 #endif
+
+EXPORT_SYMBOL(__sw_hweight32);
diff --git a/arch/x86/kernel/x8664_ksyms_64.c b/arch/x86/kernel/x8664_ksyms_64.c
index a0695be19864..c7efd394c42b 100644
--- a/arch/x86/kernel/x8664_ksyms_64.c
+++ b/arch/x86/kernel/x8664_ksyms_64.c
@@ -42,6 +42,9 @@ EXPORT_SYMBOL(clear_page);
 
 EXPORT_SYMBOL(csum_partial);
 
+EXPORT_SYMBOL(__sw_hweight32);
+EXPORT_SYMBOL(__sw_hweight64);
+
 /*
  * Export string functions. We normally rely on gcc builtin for most of these,
  * but gcc sometimes decides not to inline them.
diff --git a/arch/x86/lib/Makefile b/arch/x86/lib/Makefile
index f2587888d987..db4a1c6ea785 100644
--- a/arch/x86/lib/Makefile
+++ b/arch/x86/lib/Makefile
@@ -22,7 +22,7 @@ lib-y += memcpy_$(BITS).o
 lib-$(CONFIG_RWSEM_XCHGADD_ALGORITHM) += rwsem.o
 lib-$(CONFIG_INSTRUCTION_DECODER) += insn.o inat.o
 
-obj-y += msr.o msr-reg.o msr-reg-export.o
+obj-y += msr.o msr-reg.o msr-reg-export.o hweight.o
 
 ifeq ($(CONFIG_X86_32),y)
         obj-y += atomic64_32.o
diff --git a/arch/x86/lib/hweight.S b/arch/x86/lib/hweight.S
new file mode 100644
index 000000000000..8a602a1e404a
--- /dev/null
+++ b/arch/x86/lib/hweight.S
@@ -0,0 +1,79 @@
+#include <linux/linkage.h>
+
+#include <asm/asm.h>
+
+/*
+ * unsigned int __sw_hweight32(unsigned int w)
+ * %rdi: w
+ */
+ENTRY(__sw_hweight32)
+
+#ifdef CONFIG_X86_64
+	movl %edi, %eax				# w
+#endif
+	__ASM_SIZE(push,) %__ASM_REG(dx)
+	movl %eax, %edx				# w -> t
+	shrl %edx				# t >>= 1
+	andl $0x55555555, %edx			# t &= 0x55555555
+	subl %edx, %eax				# w -= t
+
+	movl %eax, %edx				# w -> t
+	shrl $2, %eax				# w_tmp >>= 2
+	andl $0x33333333, %edx			# t	&= 0x33333333
+	andl $0x33333333, %eax			# w_tmp &= 0x33333333
+	addl %edx, %eax				# w = w_tmp + t
+
+	movl %eax, %edx				# w -> t
+	shrl $4, %edx				# t >>= 4
+	addl %edx, %eax				# w_tmp += t
+	andl  $0x0f0f0f0f, %eax			# w_tmp &= 0x0f0f0f0f
+	imull $0x01010101, %eax, %eax		# w_tmp *= 0x01010101
+	shrl $24, %eax				# w = w_tmp >> 24
+	__ASM_SIZE(pop,) %__ASM_REG(dx)
+	ret
+ENDPROC(__sw_hweight32)
+
+ENTRY(__sw_hweight64)
+#ifdef CONFIG_X86_64
+	pushq   %rdi
+	pushq   %rdx
+
+	movq    %rdi, %rdx                      # w -> t
+	movabsq $0x5555555555555555, %rax
+	shrq    %rdx                            # t >>= 1
+	andq    %rdx, %rax                      # t &= 0x5555555555555555
+	movabsq $0x3333333333333333, %rdx
+	subq    %rax, %rdi                      # w -= t
+
+	movq    %rdi, %rax                      # w -> t
+	shrq    $2, %rdi                        # w_tmp >>= 2
+	andq    %rdx, %rax                      # t     &= 0x3333333333333333
+	andq    %rdi, %rdx                      # w_tmp &= 0x3333333333333333
+	addq    %rdx, %rax                      # w = w_tmp + t
+
+	movq    %rax, %rdx                      # w -> t
+	shrq    $4, %rdx                        # t >>= 4
+	addq    %rdx, %rax                      # w_tmp += t
+	movabsq $0x0f0f0f0f0f0f0f0f, %rdx
+	andq    %rdx, %rax                      # w_tmp &= 0x0f0f0f0f0f0f0f0f
+	movabsq $0x0101010101010101, %rdx
+	imulq   %rdx, %rax                      # w_tmp *= 0x0101010101010101
+	shrq    $56, %rax                       # w = w_tmp >> 56
+
+	popq    %rdx
+	popq    %rdi
+	ret
+#else /* CONFIG_X86_32 */
+	/* We're getting an u64 arg in (%eax,%edx): unsigned long hweight64(__u64 w) */
+	pushl   %ecx
+
+	call    __sw_hweight32
+	movl    %eax, %ecx                      # stash away result
+	movl    %edx, %eax                      # second part of input
+	call    __sw_hweight32
+	addl    %ecx, %eax                      # result
+
+	popl    %ecx
+	ret
+#endif
+ENDPROC(__sw_hweight64)
diff --git a/drivers/firmware/efi/libstub/Makefile b/drivers/firmware/efi/libstub/Makefile
index 68bdd9f23e13..d1f1bde85d3f 100644
--- a/drivers/firmware/efi/libstub/Makefile
+++ b/drivers/firmware/efi/libstub/Makefile
@@ -10,7 +10,7 @@ cflags-$(CONFIG_X86)		+= -m$(BITS) -D__KERNEL__ $(LINUX_INCLUDE) -O2 \
 				   -fPIC -fno-strict-aliasing -mno-red-zone \
 				   -mno-mmx -mno-sse
 
-cflags-$(CONFIG_ARM64)		:= $(subst -pg,,$(KBUILD_CFLAGS))
+cflags-$(CONFIG_ARM64)		:= $(subst -pg,,$(KBUILD_CFLAGS)) -fpie
 cflags-$(CONFIG_ARM)		:= $(subst -pg,,$(KBUILD_CFLAGS)) \
 				   -fno-builtin -fpic -mno-single-pic-base
 
diff --git a/drivers/firmware/efi/libstub/arm64-stub.c b/drivers/firmware/efi/libstub/arm64-stub.c
index e0e6b74fef8f..1b78215d6cd2 100644
--- a/drivers/firmware/efi/libstub/arm64-stub.c
+++ b/drivers/firmware/efi/libstub/arm64-stub.c
@@ -9,9 +9,17 @@
  * published by the Free Software Foundation.
  *
  */
+
+/*
+ * To prevent the compiler from emitting GOT-indirected (and thus absolute)
+ * references to the section markers, override their visibility as 'hidden'
+ */
+#pragma GCC visibility push(hidden)
+#include <asm/sections.h>
+#pragma GCC visibility pop
+
 #include <linux/efi.h>
 #include <asm/efi.h>
-#include <asm/sections.h>
 
 #include "efistub.h"
 
diff --git a/include/linux/compiler-clang.h b/include/linux/compiler-clang.h
index d1e49d52b640..de179993e039 100644
--- a/include/linux/compiler-clang.h
+++ b/include/linux/compiler-clang.h
@@ -10,3 +10,8 @@
 #undef uninitialized_var
 #define uninitialized_var(x) x = *(&(x))
 #endif
+
+/* same as gcc, this was present in clang-2.6 so we can assume it works
+ * with any version that can compile the kernel
+ */
+#define __UNIQUE_ID(prefix) __PASTE(__PASTE(__UNIQUE_ID_, prefix), __COUNTER__)
diff --git a/include/linux/compiler-gcc.h b/include/linux/compiler-gcc.h
index 287e698c28de..557dae96ce74 100644
--- a/include/linux/compiler-gcc.h
+++ b/include/linux/compiler-gcc.h
@@ -66,18 +66,22 @@
 
 /*
  * Force always-inline if the user requests it so via the .config,
- * or if gcc is too old:
+ * or if gcc is too old.
+ * GCC does not warn about unused static inline functions for
+ * -Wunused-function.  This turns out to avoid the need for complex #ifdef
+ * directives.  Suppress the warning in clang as well by using "unused"
+ * function attribute, which is redundant but not harmful for gcc.
  */
 #if !defined(CONFIG_ARCH_SUPPORTS_OPTIMIZED_INLINING) ||		\
     !defined(CONFIG_OPTIMIZE_INLINING) || (__GNUC__ < 4)
-#define inline		inline		__attribute__((always_inline)) notrace
-#define __inline__	__inline__	__attribute__((always_inline)) notrace
-#define __inline	__inline	__attribute__((always_inline)) notrace
+#define inline inline		__attribute__((always_inline,unused)) notrace
+#define __inline__ __inline__	__attribute__((always_inline,unused)) notrace
+#define __inline __inline	__attribute__((always_inline,unused)) notrace
 #else
 /* A lot of inline functions can cause havoc with function tracing */
-#define inline		inline		notrace
-#define __inline__	__inline__	notrace
-#define __inline	__inline	notrace
+#define inline inline		__attribute__((unused)) notrace
+#define __inline__ __inline__	__attribute__((unused)) notrace
+#define __inline __inline	__attribute__((unused)) notrace
 #endif
 
 #define __always_inline	inline __attribute__((always_inline))
diff --git a/include/linux/kbuild.h b/include/linux/kbuild.h
index 22a72198c14b..4e80f3a9ad58 100644
--- a/include/linux/kbuild.h
+++ b/include/linux/kbuild.h
@@ -2,14 +2,14 @@
 #define __LINUX_KBUILD_H
 
 #define DEFINE(sym, val) \
-        asm volatile("\n->" #sym " %0 " #val : : "i" (val))
+	asm volatile("\n.ascii \"->" #sym " %0 " #val "\"" : : "i" (val))
 
-#define BLANK() asm volatile("\n->" : : )
+#define BLANK() asm volatile("\n.ascii \"->\"" : : )
 
 #define OFFSET(sym, str, mem) \
 	DEFINE(sym, offsetof(struct str, mem))
 
 #define COMMENT(x) \
-	asm volatile("\n->#" x)
+	asm volatile("\n.ascii \"->#" x "\"")
 
 #endif
diff --git a/include/linux/module.h b/include/linux/module.h
index b229a9961d02..e2324653c8ef 100644
--- a/include/linux/module.h
+++ b/include/linux/module.h
@@ -125,13 +125,13 @@ extern void cleanup_module(void);
 
 /* Each module must use one module_init(). */
 #define module_init(initfn)					\
-	static inline initcall_t __inittest(void)		\
+	static inline initcall_t __maybe_unused __inittest(void)		\
 	{ return initfn; }					\
 	int init_module(void) __attribute__((alias(#initfn)));
 
 /* This is only required if you want to be unloadable. */
 #define module_exit(exitfn)					\
-	static inline exitcall_t __exittest(void)		\
+	static inline exitcall_t __maybe_unused __exittest(void)		\
 	{ return exitfn; }					\
 	void cleanup_module(void) __attribute__((alias(#exitfn)));
 
diff --git a/lib/Makefile b/lib/Makefile
index 7f1de26613d2..cb4f6aa95013 100644
--- a/lib/Makefile
+++ b/lib/Makefile
@@ -58,8 +58,6 @@ obj-$(CONFIG_HAS_IOMEM) += iomap_copy.o devres.o
 obj-$(CONFIG_CHECK_SIGNATURE) += check_signature.o
 obj-$(CONFIG_DEBUG_LOCKING_API_SELFTESTS) += locking-selftest.o
 
-GCOV_PROFILE_hweight.o := n
-CFLAGS_hweight.o = $(subst $(quote),,$(CONFIG_ARCH_HWEIGHT_CFLAGS))
 obj-$(CONFIG_GENERIC_HWEIGHT) += hweight.o
 
 obj-$(CONFIG_BTREE) += btree.o
diff --git a/lib/hweight.c b/lib/hweight.c
index 9a5c1f221558..43273a7d83cf 100644
--- a/lib/hweight.c
+++ b/lib/hweight.c
@@ -9,6 +9,7 @@
  * The Hamming Weight of a number is the total number of bits set in it.
  */
 
+#ifndef __HAVE_ARCH_SW_HWEIGHT
 unsigned int __sw_hweight32(unsigned int w)
 {
 #ifdef CONFIG_ARCH_HAS_FAST_MULTIPLIER
@@ -25,6 +26,7 @@ unsigned int __sw_hweight32(unsigned int w)
 #endif
 }
 EXPORT_SYMBOL(__sw_hweight32);
+#endif
 
 unsigned int __sw_hweight16(unsigned int w)
 {
@@ -43,6 +45,7 @@ unsigned int __sw_hweight8(unsigned int w)
 }
 EXPORT_SYMBOL(__sw_hweight8);
 
+#ifndef __HAVE_ARCH_SW_HWEIGHT
 unsigned long __sw_hweight64(__u64 w)
 {
 #if BITS_PER_LONG == 32
@@ -65,3 +68,4 @@ unsigned long __sw_hweight64(__u64 w)
 #endif
 }
 EXPORT_SYMBOL(__sw_hweight64);
+#endif
diff --git a/scripts/Kbuild.include b/scripts/Kbuild.include
index 1db6d73c8dd2..8a1bb64f1dcd 100644
--- a/scripts/Kbuild.include
+++ b/scripts/Kbuild.include
@@ -107,16 +107,30 @@ as-option = $(call try-run,\
 as-instr = $(call try-run,\
 	printf "%b\n" "$(1)" | $(CC) $(KBUILD_AFLAGS) -c -x assembler -o "$$TMP" -,$(2),$(3))
 
+# __cc-option
+# Usage: MY_CFLAGS += $(call __cc-option,$(CC),$(MY_CFLAGS),-march=winchip-c6,-march=i586)
+__cc-option = $(call try-run,\
+	$(1) -Werror $(2) $(3) -c -x c /dev/null -o "$$TMP",$(3),$(4))
+
+# Do not attempt to build with gcc plugins during cc-option tests.
+# (And this uses delayed resolution so the flags will be up to date.)
+CC_OPTION_CFLAGS = $(filter-out $(GCC_PLUGINS_CFLAGS),$(KBUILD_CFLAGS))
+
 # cc-option
 # Usage: cflags-y += $(call cc-option,-march=winchip-c6,-march=i586)
 
-cc-option = $(call try-run,\
-	$(CC) $(KBUILD_CPPFLAGS) $(KBUILD_CFLAGS) $(1) -c -x c /dev/null -o "$$TMP",$(1),$(2))
+cc-option = $(call __cc-option, $(CC),\
+	$(KBUILD_CPPFLAGS) $(KBUILD_CFLAGS),$(1),$(2))
+
+# hostcc-option
+# Usage: cflags-y += $(call hostcc-option,-march=winchip-c6,-march=i586)
+hostcc-option = $(call __cc-option, $(HOSTCC),\
+	$(HOSTCFLAGS) $(HOST_EXTRACFLAGS),$(1),$(2))
 
 # cc-option-yn
 # Usage: flag := $(call cc-option-yn,-march=winchip-c6)
 cc-option-yn = $(call try-run,\
-	$(CC) $(KBUILD_CPPFLAGS) $(KBUILD_CFLAGS) $(1) -c -x c /dev/null -o "$$TMP",y,n)
+	$(CC) -Werror $(KBUILD_CPPFLAGS) $(KBUILD_CFLAGS) $(1) -c -x c /dev/null -o "$$TMP",y,n)
 
 # cc-option-align
 # Prefix align with either -falign or -malign
@@ -126,7 +140,7 @@ cc-option-align = $(subst -functions=0,,\
 # cc-disable-warning
 # Usage: cflags-y += $(call cc-disable-warning,unused-but-set-variable)
 cc-disable-warning = $(call try-run,\
-	$(CC) $(KBUILD_CPPFLAGS) $(KBUILD_CFLAGS) -W$(strip $(1)) -c -x c /dev/null -o "$$TMP",-Wno-$(strip $(1)))
+	$(CC) -Werror $(KBUILD_CPPFLAGS) $(KBUILD_CFLAGS) -W$(strip $(1)) -c -x c /dev/null -o "$$TMP",-Wno-$(strip $(1)))
 
 # cc-name
 # Expands to either gcc or clang
diff --git a/scripts/Makefile.build b/scripts/Makefile.build
index 01df30af4d4a..411281c36898 100644
--- a/scripts/Makefile.build
+++ b/scripts/Makefile.build
@@ -174,6 +174,14 @@ cmd_cc_symtypes_c =                                                         \
 $(obj)/%.symtypes : $(src)/%.c FORCE
 	$(call cmd,cc_symtypes_c)
 
+# LLVM assembly
+# Generate .ll files from .c
+quiet_cmd_cc_ll_c = CC $(quiet_modtag)  $@
+      cmd_cc_ll_c = $(CC) $(c_flags) -emit-llvm -S -o $@ $<
+
+$(obj)/%.ll: $(src)/%.c FORCE
+	$(call if_changed_dep,cc_ll_c)
+
 # C (.c) files
 # The C file is compiled and updated dependency information is generated.
 # (See cmd_cc_o_c + relevant part of rule_cc_o_c)
diff --git a/scripts/Makefile.extrawarn b/scripts/Makefile.extrawarn
index da3386a9d244..abe5f47b1ab0 100644
--- a/scripts/Makefile.extrawarn
+++ b/scripts/Makefile.extrawarn
@@ -61,7 +61,6 @@ ifeq ($(cc-name),clang)
 KBUILD_CFLAGS += $(call cc-disable-warning, initializer-overrides)
 KBUILD_CFLAGS += $(call cc-disable-warning, unused-value)
 KBUILD_CFLAGS += $(call cc-disable-warning, format)
-KBUILD_CFLAGS += $(call cc-disable-warning, unknown-warning-option)
 KBUILD_CFLAGS += $(call cc-disable-warning, sign-compare)
 KBUILD_CFLAGS += $(call cc-disable-warning, format-zero-length)
 KBUILD_CFLAGS += $(call cc-disable-warning, uninitialized)
diff --git a/scripts/Makefile.lib b/scripts/Makefile.lib
index c84080885ad4..c3b3c94e2446 100644
--- a/scripts/Makefile.lib
+++ b/scripts/Makefile.lib
@@ -394,3 +394,34 @@ quiet_cmd_xzmisc = XZMISC  $@
 cmd_xzmisc = (cat $(filter-out FORCE,$^) | \
 	xz --check=crc32 --lzma2=dict=1MiB) > $@ || \
 	(rm -f $@ ; false)
+
+# ASM offsets
+# ---------------------------------------------------------------------------
+
+# Default sed regexp - multiline due to syntax constraints
+#
+# Use [:space:] because LLVM's integrated assembler inserts <tab> around
+# the .ascii directive whereas GCC keeps the <space> as-is.
+define sed-offsets
+	's:^[[:space:]]*\.ascii[[:space:]]*"\(.*\)".*:\1:; \
+	/^->/{s:->#\(.*\):/* \1 */:; \
+	s:^->\([^ ]*\) [\$$#]*\([^ ]*\) \(.*\):#define \1 \2 /* \3 */:; \
+	s:->::; p;}'
+endef
+
+# Use filechk to avoid rebuilds when a header changes, but the resulting file
+# does not
+define filechk_offsets
+	(set -e; \
+	 echo "#ifndef $2"; \
+	 echo "#define $2"; \
+	 echo "/*"; \
+	 echo " * DO NOT MODIFY."; \
+	 echo " *"; \
+	 echo " * This file was generated by Kbuild"; \
+	 echo " */"; \
+	 echo ""; \
+	 sed -ne $(sed-offsets); \
+	 echo ""; \
+	 echo "#endif" )
+endef
diff --git a/scripts/mod/Makefile b/scripts/mod/Makefile
index c11212ff3510..e0cb2e4a3b15 100644
--- a/scripts/mod/Makefile
+++ b/scripts/mod/Makefile
@@ -5,32 +5,8 @@ modpost-objs	:= modpost.o file2alias.o sumversion.o
 
 devicetable-offsets-file := devicetable-offsets.h
 
-define sed-y
-	"/^->/{s:->#\(.*\):/* \1 */:; \
-	s:^->\([^ ]*\) [\$$#]*\([-0-9]*\) \(.*\):#define \1 \2 /* \3 */:; \
-	s:^->\([^ ]*\) [\$$#]*\([^ ]*\) \(.*\):#define \1 \2 /* \3 */:; \
-	s:->::; p;}"
-endef
-
-quiet_cmd_offsets = GEN     $@
-define cmd_offsets
-	(set -e; \
-	 echo "#ifndef __DEVICETABLE_OFFSETS_H__"; \
-	 echo "#define __DEVICETABLE_OFFSETS_H__"; \
-	 echo "/*"; \
-	 echo " * DO NOT MODIFY."; \
-	 echo " *"; \
-	 echo " * This file was generated by Kbuild"; \
-	 echo " *"; \
-	 echo " */"; \
-	 echo ""; \
-	 sed -ne $(sed-y) $<; \
-	 echo ""; \
-	 echo "#endif" ) > $@
-endef
-
-$(obj)/$(devicetable-offsets-file): $(obj)/devicetable-offsets.s
-	$(call if_changed,offsets)
+$(obj)/$(devicetable-offsets-file): $(obj)/devicetable-offsets.s FORCE
+	$(call filechk,offsets,__DEVICETABLE_OFFSETS_H__)
 
 targets += $(devicetable-offsets-file) devicetable-offsets.s