diff --git a/.gitignore b/.gitignore
index 67d2f350312832c8e1997af553974a85598a53d1..372e57abbf4172b06a3372221b70cac1ee6fb1ee 100644
--- a/.gitignore
+++ b/.gitignore
@@ -41,6 +41,7 @@
 *.so.dbg
 *.su
 *.symtypes
+*.symversions
 *.tab.[ch]
 *.tar
 *.xz
diff --git a/Makefile b/Makefile
index 2f2224fda1dbaefa7c75e43dcfd54e23cf110d22..d365d287a990f37330eda9477d6294f18643613e 100644
--- a/Makefile
+++ b/Makefile
@@ -856,12 +856,8 @@ KBUILD_CFLAGS += $(DEBUG_CFLAGS)
 export DEBUG_CFLAGS
 
 ifdef CONFIG_FUNCTION_TRACER
-ifdef CONFIG_FTRACE_MCOUNT_RECORD
-  # gcc 5 supports generating the mcount tables directly
-  ifeq ($(call cc-option-yn,-mrecord-mcount),y)
-    CC_FLAGS_FTRACE	+= -mrecord-mcount
-    export CC_USING_RECORD_MCOUNT := 1
-  endif
+ifdef CONFIG_FTRACE_MCOUNT_USE_CC
+  CC_FLAGS_FTRACE	+= -mrecord-mcount
   ifdef CONFIG_HAVE_NOP_MCOUNT
     ifeq ($(call cc-option-yn, -mnop-mcount),y)
       CC_FLAGS_FTRACE	+= -mnop-mcount
@@ -869,6 +865,12 @@ ifdef CONFIG_FTRACE_MCOUNT_RECORD
     endif
   endif
 endif
+ifdef CONFIG_FTRACE_MCOUNT_USE_RECORDMCOUNT
+  ifdef CONFIG_HAVE_C_RECORDMCOUNT
+    BUILD_C_RECORDMCOUNT := y
+    export BUILD_C_RECORDMCOUNT
+  endif
+endif
 ifdef CONFIG_HAVE_FENTRY
   ifeq ($(call cc-option-yn, -mfentry),y)
     CC_FLAGS_FTRACE	+= -mfentry
@@ -878,12 +880,6 @@ endif
 export CC_FLAGS_FTRACE
 KBUILD_CFLAGS	+= $(CC_FLAGS_FTRACE) $(CC_FLAGS_USING)
 KBUILD_AFLAGS	+= $(CC_FLAGS_USING)
-ifdef CONFIG_DYNAMIC_FTRACE
-	ifdef CONFIG_HAVE_C_RECORDMCOUNT
-		BUILD_C_RECORDMCOUNT := y
-		export BUILD_C_RECORDMCOUNT
-	endif
-endif
 endif
 
 # We trigger additional mismatches with less inlining
@@ -902,6 +898,41 @@ KBUILD_CFLAGS	+= $(CC_FLAGS_SCS)
 export CC_FLAGS_SCS
 endif
 
+ifdef CONFIG_LTO_CLANG
+ifdef CONFIG_LTO_CLANG_THIN
+CC_FLAGS_LTO	:= -flto=thin -fsplit-lto-unit
+KBUILD_LDFLAGS	+= --thinlto-cache-dir=$(extmod-prefix).thinlto-cache
+else
+CC_FLAGS_LTO	:= -flto
+endif
+CC_FLAGS_LTO	+= -fvisibility=hidden
+
+# Limit inlining across translation units to reduce binary size
+KBUILD_LDFLAGS += -mllvm -import-instr-limit=5
+endif
+
+ifdef CONFIG_LTO
+KBUILD_CFLAGS	+= $(CC_FLAGS_LTO)
+export CC_FLAGS_LTO
+endif
+
+ifdef CONFIG_CFI_CLANG
+CC_FLAGS_CFI	:= -fsanitize=cfi \
+		   -fsanitize-cfi-cross-dso \
+		   -fno-sanitize-cfi-canonical-jump-tables \
+		   -fno-sanitize-trap=cfi \
+		   -fno-sanitize-blacklist
+
+ifdef CONFIG_CFI_PERMISSIVE
+CC_FLAGS_CFI	+= -fsanitize-recover=cfi
+endif
+
+# If LTO flags are filtered out, we must also filter out CFI.
+CC_FLAGS_LTO	+= $(CC_FLAGS_CFI)
+KBUILD_CFLAGS	+= $(CC_FLAGS_CFI)
+export CC_FLAGS_CFI
+endif
+
 ifdef CONFIG_DEBUG_FORCE_FUNCTION_ALIGN_32B
 KBUILD_CFLAGS += -falign-functions=32
 endif
@@ -1487,7 +1518,7 @@ endif # CONFIG_MODULES
 # Directories & files removed with 'make clean'
 CLEAN_FILES += include/ksym vmlinux.symvers modules-only.symvers \
 	       modules.builtin modules.builtin.modinfo modules.nsdeps \
-	       compile_commands.json
+	       compile_commands.json .thinlto-cache
 
 # Directories & files removed with 'make mrproper'
 MRPROPER_FILES += include/config include/generated          \
@@ -1747,7 +1778,7 @@ PHONY += compile_commands.json
 
 clean-dirs := $(KBUILD_EXTMOD)
 clean: rm-files := $(KBUILD_EXTMOD)/Module.symvers $(KBUILD_EXTMOD)/modules.nsdeps \
-	$(KBUILD_EXTMOD)/compile_commands.json
+	$(KBUILD_EXTMOD)/compile_commands.json $(KBUILD_EXTMOD)/.thinlto-cache
 
 PHONY += help
 help:
@@ -1844,7 +1875,8 @@ clean: $(clean-dirs)
 		-o -name '.tmp_*.o.*' \
 		-o -name '*.c.[012]*.*' \
 		-o -name '*.ll' \
-		-o -name '*.gcno' \) -type f -print | xargs rm -f
+		-o -name '*.gcno' \
+		-o -name '*.*.symversions' \) -type f -print | xargs rm -f
 
 # Generate tags for editors
 # ---------------------------------------------------------------------------
diff --git a/arch/Kconfig b/arch/Kconfig
index 632d60e13494c636d603737766d76ea99ec1dbf4..6b3684d95a531f5b26b8232bba9abc2a1fece6b7 100644
--- a/arch/Kconfig
+++ b/arch/Kconfig
@@ -614,6 +614,141 @@ config SHADOW_CALL_STACK
 	  reading and writing arbitrary memory may be able to locate them
 	  and hijack control flow by modifying the stacks.
 
+config LTO
+	bool
+	help
+	  Selected if the kernel will be built using the compiler's LTO feature.
+
+config LTO_CLANG
+	bool
+	select LTO
+	help
+	  Selected if the kernel will be built using Clang's LTO feature.
+
+config ARCH_SUPPORTS_LTO_CLANG
+	bool
+	help
+	  An architecture should select this option if it supports:
+	  - compiling with Clang,
+	  - compiling inline assembly with Clang's integrated assembler,
+	  - and linking with LLD.
+
+config ARCH_SUPPORTS_LTO_CLANG_THIN
+	bool
+	help
+	  An architecture should select this option if it can support Clang's
+	  ThinLTO mode.
+
+config HAS_LTO_CLANG
+	def_bool y
+	# Clang >= 11: https://github.com/ClangBuiltLinux/linux/issues/510
+	depends on CC_IS_CLANG && CLANG_VERSION >= 110000 && LD_IS_LLD
+	depends on $(success,test $(LLVM) -eq 1)
+	depends on $(success,test $(LLVM_IAS) -eq 1)
+	depends on $(success,$(NM) --help | head -n 1 | grep -qi llvm)
+	depends on $(success,$(AR) --help | head -n 1 | grep -qi llvm)
+	depends on ARCH_SUPPORTS_LTO_CLANG
+	depends on !FTRACE_MCOUNT_USE_RECORDMCOUNT
+	depends on !KASAN
+	depends on !GCOV_KERNEL
+	help
+	  The compiler and Kconfig options support building with Clang's
+	  LTO.
+
+choice
+	prompt "Link Time Optimization (LTO)"
+	default LTO_NONE
+	help
+	  This option enables Link Time Optimization (LTO), which allows the
+	  compiler to optimize binaries globally.
+
+	  If unsure, select LTO_NONE. Note that LTO is very resource-intensive
+	  so it's disabled by default.
+
+config LTO_NONE
+	bool "None"
+	help
+	  Build the kernel normally, without Link Time Optimization (LTO).
+
+config LTO_CLANG_FULL
+	bool "Clang Full LTO (EXPERIMENTAL)"
+	depends on HAS_LTO_CLANG
+	depends on !COMPILE_TEST
+	select LTO_CLANG
+	help
+          This option enables Clang's full Link Time Optimization (LTO), which
+          allows the compiler to optimize the kernel globally. If you enable
+          this option, the compiler generates LLVM bitcode instead of ELF
+          object files, and the actual compilation from bitcode happens at
+          the LTO link step, which may take several minutes depending on the
+          kernel configuration. More information can be found from LLVM's
+          documentation:
+
+	    https://llvm.org/docs/LinkTimeOptimization.html
+
+	  During link time, this option can use a large amount of RAM, and
+	  may take much longer than the ThinLTO option.
+
+config LTO_CLANG_THIN
+	bool "Clang ThinLTO (EXPERIMENTAL)"
+	depends on HAS_LTO_CLANG && ARCH_SUPPORTS_LTO_CLANG_THIN
+	select LTO_CLANG
+	help
+	  This option enables Clang's ThinLTO, which allows for parallel
+	  optimization and faster incremental compiles compared to the
+	  CONFIG_LTO_CLANG_FULL option. More information can be found
+	  from Clang's documentation:
+
+	    https://clang.llvm.org/docs/ThinLTO.html
+
+	  If unsure, say Y.
+endchoice
+
+config ARCH_SUPPORTS_CFI_CLANG
+	bool
+	help
+	  An architecture should select this option if it can support Clang's
+	  Control-Flow Integrity (CFI) checking.
+
+config CFI_CLANG
+	bool "Use Clang's Control Flow Integrity (CFI)"
+	depends on LTO_CLANG && ARCH_SUPPORTS_CFI_CLANG
+	# Clang >= 12:
+	# - https://bugs.llvm.org/show_bug.cgi?id=46258
+	# - https://bugs.llvm.org/show_bug.cgi?id=47479
+	depends on CLANG_VERSION >= 120000
+	select KALLSYMS
+	help
+	  This option enables Clang’s forward-edge Control Flow Integrity
+	  (CFI) checking, where the compiler injects a runtime check to each
+	  indirect function call to ensure the target is a valid function with
+	  the correct static type. This restricts possible call targets and
+	  makes it more difficult for an attacker to exploit bugs that allow
+	  the modification of stored function pointers. More information can be
+	  found from Clang's documentation:
+
+	    https://clang.llvm.org/docs/ControlFlowIntegrity.html
+
+config CFI_CLANG_SHADOW
+	bool "Use CFI shadow to speed up cross-module checks"
+	default y
+	depends on CFI_CLANG && MODULES
+	help
+	  If you select this option, the kernel builds a fast look-up table of
+	  CFI check functions in loaded modules to reduce performance overhead.
+
+	  If unsure, say Y.
+
+config CFI_PERMISSIVE
+	bool "Use CFI in permissive mode"
+	depends on CFI_CLANG
+	help
+	  When selected, Control Flow Integrity (CFI) violations result in a
+	  warning instead of a kernel panic. This option should only be used
+	  for finding indirect call type mismatches during development.
+
+	  If unsure, say N.
+
 config HAVE_ARCH_WITHIN_STACK_FRAMES
 	bool
 	help
diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig
index 3462acc2bd99767909a3bd3a9a178475d9e7de8c..d94efb7ffe7e1b37ebfa6d481b3f120a9613b1a8 100644
--- a/arch/arm64/Kconfig
+++ b/arch/arm64/Kconfig
@@ -73,6 +73,9 @@ config ARM64
 	select ARCH_USE_SYM_ANNOTATIONS
 	select ARCH_SUPPORTS_MEMORY_FAILURE
 	select ARCH_SUPPORTS_SHADOW_CALL_STACK if CC_HAVE_SHADOW_CALL_STACK
+	select ARCH_SUPPORTS_LTO_CLANG if CPU_LITTLE_ENDIAN
+	select ARCH_SUPPORTS_LTO_CLANG_THIN
+	select ARCH_SUPPORTS_CFI_CLANG
 	select ARCH_SUPPORTS_ATOMIC_RMW
 	select ARCH_SUPPORTS_INT128 if CC_HAS_INT128 && (GCC_VERSION >= 50000 || CC_IS_CLANG)
 	select ARCH_SUPPORTS_NUMA_BALANCING
@@ -159,6 +162,8 @@ config ARM64
 	select HAVE_DYNAMIC_FTRACE
 	select HAVE_DYNAMIC_FTRACE_WITH_REGS \
 		if $(cc-option,-fpatchable-function-entry=2)
+	select FTRACE_MCOUNT_USE_PATCHABLE_FUNCTION_ENTRY \
+		if DYNAMIC_FTRACE_WITH_REGS
 	select HAVE_EFFICIENT_UNALIGNED_ACCESS
 	select HAVE_FAST_GUP
 	select HAVE_FTRACE_MCOUNT_RECORD
diff --git a/arch/arm64/include/asm/ftrace.h b/arch/arm64/include/asm/ftrace.h
index 91fa4baa1a936859a82a837a7a629624749582b2..347b0cc68f07195e9e00c791333e08ccab4c4eee 100644
--- a/arch/arm64/include/asm/ftrace.h
+++ b/arch/arm64/include/asm/ftrace.h
@@ -15,7 +15,7 @@
 #ifdef CONFIG_DYNAMIC_FTRACE_WITH_REGS
 #define ARCH_SUPPORTS_FTRACE_OPS 1
 #else
-#define MCOUNT_ADDR		((unsigned long)_mcount)
+#define MCOUNT_ADDR		((unsigned long)function_nocfi(_mcount))
 #endif
 
 /* The BL at the callsite's adjusted rec->ip */
diff --git a/arch/arm64/include/asm/memory.h b/arch/arm64/include/asm/memory.h
index 505bdd75b5411258be7d70951c25371abb4e1ab5..07b9e7a8451aa51b076f77198e7cb724d029c7a0 100644
--- a/arch/arm64/include/asm/memory.h
+++ b/arch/arm64/include/asm/memory.h
@@ -299,6 +299,22 @@ static inline void *phys_to_virt(phys_addr_t x)
 #define virt_to_pfn(x)		__phys_to_pfn(__virt_to_phys((unsigned long)(x)))
 #define sym_to_pfn(x)		__phys_to_pfn(__pa_symbol(x))
 
+#ifdef CONFIG_CFI_CLANG
+/*
+ * With CONFIG_CFI_CLANG, the compiler replaces function address
+ * references with the address of the function's CFI jump table
+ * entry. The function_nocfi macro always returns the address of the
+ * actual function instead.
+ */
+#define function_nocfi(x) ({						\
+	void *addr;							\
+	asm("adrp %0, " __stringify(x) "\n\t"				\
+	    "add  %0, %0, :lo12:" __stringify(x)			\
+	    : "=r" (addr));						\
+	addr;								\
+})
+#endif
+
 /*
  *  virt_to_page(x)	convert a _valid_ virtual address to struct page *
  *  virt_addr_valid(x)	indicates whether a virtual address is valid
diff --git a/arch/arm64/include/asm/mmu_context.h b/arch/arm64/include/asm/mmu_context.h
index 5a54a5ab5f928bab4a199b40e599191e22b837b6..835a4edd9d3a453833b68d31e6a92c22a39b7eac 100644
--- a/arch/arm64/include/asm/mmu_context.h
+++ b/arch/arm64/include/asm/mmu_context.h
@@ -134,7 +134,7 @@ static inline void cpu_install_idmap(void)
  * Atomically replaces the active TTBR1_EL1 PGD with a new VA-compatible PGD,
  * avoiding the possibility of conflicting TLB entries being allocated.
  */
-static inline void cpu_replace_ttbr1(pgd_t *pgdp)
+static inline void __nocfi cpu_replace_ttbr1(pgd_t *pgdp)
 {
 	typedef void (ttbr_replace_func)(phys_addr_t);
 	extern ttbr_replace_func idmap_cpu_replace_ttbr1;
@@ -155,7 +155,7 @@ static inline void cpu_replace_ttbr1(pgd_t *pgdp)
 		ttbr1 |= TTBR_CNP_BIT;
 	}
 
-	replace_phys = (void *)__pa_symbol(idmap_cpu_replace_ttbr1);
+	replace_phys = (void *)__pa_symbol(function_nocfi(idmap_cpu_replace_ttbr1));
 
 	cpu_install_idmap();
 	replace_phys(ttbr1);
diff --git a/arch/arm64/kernel/acpi_parking_protocol.c b/arch/arm64/kernel/acpi_parking_protocol.c
index e7c941d8340dcb71eeaf667d99e976be4e6a4d88..bfeeb5319abf9851c5b6fca759e3de03e39c0b41 100644
--- a/arch/arm64/kernel/acpi_parking_protocol.c
+++ b/arch/arm64/kernel/acpi_parking_protocol.c
@@ -99,7 +99,8 @@ static int acpi_parking_protocol_cpu_boot(unsigned int cpu)
 	 * that read this address need to convert this address to the
 	 * Boot-Loader's endianness before jumping.
 	 */
-	writeq_relaxed(__pa_symbol(secondary_entry), &mailbox->entry_point);
+	writeq_relaxed(__pa_symbol(function_nocfi(secondary_entry)),
+		       &mailbox->entry_point);
 	writel_relaxed(cpu_entry->gic_cpu_id, &mailbox->cpu_id);
 
 	arch_send_wakeup_ipi_mask(cpumask_of(cpu));
diff --git a/arch/arm64/kernel/alternative.c b/arch/arm64/kernel/alternative.c
index 73039949b5ce2f6227f11d0d1591967c38bda8f6..a50fb1d332e13d41eaa2ea9955aa51b1b5a613a2 100644
--- a/arch/arm64/kernel/alternative.c
+++ b/arch/arm64/kernel/alternative.c
@@ -132,8 +132,8 @@ static void clean_dcache_range_nopatch(u64 start, u64 end)
 	} while (cur += d_size, cur < end);
 }
 
-static void __apply_alternatives(void *alt_region,  bool is_module,
-				 unsigned long *feature_mask)
+static void __nocfi __apply_alternatives(void *alt_region,  bool is_module,
+					 unsigned long *feature_mask)
 {
 	struct alt_instr *alt;
 	struct alt_region *region = alt_region;
diff --git a/arch/arm64/kernel/cpu-reset.h b/arch/arm64/kernel/cpu-reset.h
index ed50e9587ad813ceb82bafbae46c07891cc3c6f3..9a7b1262ef17a3a6462ffc31d2974f199f5a31c1 100644
--- a/arch/arm64/kernel/cpu-reset.h
+++ b/arch/arm64/kernel/cpu-reset.h
@@ -13,16 +13,16 @@
 void __cpu_soft_restart(unsigned long el2_switch, unsigned long entry,
 	unsigned long arg0, unsigned long arg1, unsigned long arg2);
 
-static inline void __noreturn cpu_soft_restart(unsigned long entry,
-					       unsigned long arg0,
-					       unsigned long arg1,
-					       unsigned long arg2)
+static inline void __noreturn __nocfi cpu_soft_restart(unsigned long entry,
+						       unsigned long arg0,
+						       unsigned long arg1,
+						       unsigned long arg2)
 {
 	typeof(__cpu_soft_restart) *restart;
 
 	unsigned long el2_switch = !is_kernel_in_hyp_mode() &&
 		is_hyp_mode_available();
-	restart = (void *)__pa_symbol(__cpu_soft_restart);
+	restart = (void *)__pa_symbol(function_nocfi(__cpu_soft_restart));
 
 	cpu_install_idmap();
 	restart(el2_switch, entry, arg0, arg1, arg2);
diff --git a/arch/arm64/kernel/cpufeature.c b/arch/arm64/kernel/cpufeature.c
index ec8ed4fc3281fd9de0d924c3e7834cb12ab12d4a..0757bfe769e0934791ee1482929ca86323d1647a 100644
--- a/arch/arm64/kernel/cpufeature.c
+++ b/arch/arm64/kernel/cpufeature.c
@@ -1408,7 +1408,7 @@ static bool unmap_kernel_at_el0(const struct arm64_cpu_capabilities *entry,
 }
 
 #ifdef CONFIG_UNMAP_KERNEL_AT_EL0
-static void
+static void __nocfi
 kpti_install_ng_mappings(const struct arm64_cpu_capabilities *__unused)
 {
 	typedef void (kpti_remap_fn)(int, int, phys_addr_t);
@@ -1431,7 +1431,7 @@ kpti_install_ng_mappings(const struct arm64_cpu_capabilities *__unused)
 	if (arm64_use_ng_mappings)
 		return;
 
-	remap_fn = (void *)__pa_symbol(idmap_kpti_install_ng_mappings);
+	remap_fn = (void *)__pa_symbol(function_nocfi(idmap_kpti_install_ng_mappings));
 
 	cpu_install_idmap();
 	remap_fn(cpu, num_online_cpus(), __pa_symbol(swapper_pg_dir));
diff --git a/arch/arm64/kernel/ftrace.c b/arch/arm64/kernel/ftrace.c
index 86a5cf9bc19a1e8ac7d47f529fc2492d072857bc..b5d3ddaf69d9e9b0c58c5ae1bf21fdb80b364b99 100644
--- a/arch/arm64/kernel/ftrace.c
+++ b/arch/arm64/kernel/ftrace.c
@@ -55,7 +55,7 @@ int ftrace_update_ftrace_func(ftrace_func_t func)
 	unsigned long pc;
 	u32 new;
 
-	pc = (unsigned long)&ftrace_call;
+	pc = (unsigned long)function_nocfi(ftrace_call);
 	new = aarch64_insn_gen_branch_imm(pc, (unsigned long)func,
 					  AARCH64_INSN_BRANCH_LINK);
 
diff --git a/arch/arm64/kernel/psci.c b/arch/arm64/kernel/psci.c
index 62d2bda7adb807010439282fc956e63a5d269095..ab7f4c4761046a38adfaec8dcfe38db5db405210 100644
--- a/arch/arm64/kernel/psci.c
+++ b/arch/arm64/kernel/psci.c
@@ -38,7 +38,8 @@ static int __init cpu_psci_cpu_prepare(unsigned int cpu)
 
 static int cpu_psci_cpu_boot(unsigned int cpu)
 {
-	int err = psci_ops.cpu_on(cpu_logical_map(cpu), __pa_symbol(secondary_entry));
+	phys_addr_t pa_secondary_entry = __pa_symbol(function_nocfi(secondary_entry));
+	int err = psci_ops.cpu_on(cpu_logical_map(cpu), pa_secondary_entry);
 	if (err)
 		pr_err("failed to boot CPU%d (%d)\n", cpu, err);
 
diff --git a/arch/arm64/kernel/smp_spin_table.c b/arch/arm64/kernel/smp_spin_table.c
index 056772c2609851bf7ec93cdb0db0292f9c5904a3..c45a835128057ac6f904e9770138005c08efdfbb 100644
--- a/arch/arm64/kernel/smp_spin_table.c
+++ b/arch/arm64/kernel/smp_spin_table.c
@@ -66,6 +66,7 @@ static int smp_spin_table_cpu_init(unsigned int cpu)
 static int smp_spin_table_cpu_prepare(unsigned int cpu)
 {
 	__le64 __iomem *release_addr;
+	phys_addr_t pa_holding_pen = __pa_symbol(function_nocfi(secondary_holding_pen));
 
 	if (!cpu_release_addr[cpu])
 		return -ENODEV;
@@ -88,7 +89,7 @@ static int smp_spin_table_cpu_prepare(unsigned int cpu)
 	 * boot-loader's endianness before jumping. This is mandated by
 	 * the boot protocol.
 	 */
-	writeq_relaxed(__pa_symbol(secondary_holding_pen), release_addr);
+	writeq_relaxed(pa_holding_pen, release_addr);
 	__flush_dcache_area((__force void *)release_addr,
 			    sizeof(*release_addr));
 
diff --git a/arch/arm64/kernel/vdso/Makefile b/arch/arm64/kernel/vdso/Makefile
index d65f52264abaeb9edb0566037665a0e970f49ade..50fe49fb4d958a9cd638dccb28e1abc564695e6d 100644
--- a/arch/arm64/kernel/vdso/Makefile
+++ b/arch/arm64/kernel/vdso/Makefile
@@ -30,7 +30,8 @@ ldflags-y := -shared -nostdlib -soname=linux-vdso.so.1 --hash-style=sysv	\
 ccflags-y := -fno-common -fno-builtin -fno-stack-protector -ffixed-x18
 ccflags-y += -DDISABLE_BRANCH_PROFILING
 
-CFLAGS_REMOVE_vgettimeofday.o = $(CC_FLAGS_FTRACE) -Os $(CC_FLAGS_SCS) $(GCC_PLUGINS_CFLAGS)
+CFLAGS_REMOVE_vgettimeofday.o = $(CC_FLAGS_FTRACE) -Os $(CC_FLAGS_SCS) $(GCC_PLUGINS_CFLAGS) \
+				$(CC_FLAGS_LTO)
 KASAN_SANITIZE			:= n
 UBSAN_SANITIZE			:= n
 OBJECT_FILES_NON_STANDARD	:= y
diff --git a/arch/arm64/kvm/hyp/nvhe/Makefile b/arch/arm64/kvm/hyp/nvhe/Makefile
index ddde15fe85f2fc65087f0d77fa5bc26855f635eb..4b9ac577729ab741b60bf8be5e8bb9fb9e0ee7d2 100644
--- a/arch/arm64/kvm/hyp/nvhe/Makefile
+++ b/arch/arm64/kvm/hyp/nvhe/Makefile
@@ -51,9 +51,9 @@ $(obj)/kvm_nvhe.o: $(obj)/kvm_nvhe.tmp.o FORCE
 quiet_cmd_hypcopy = HYPCOPY $@
       cmd_hypcopy = $(OBJCOPY) --prefix-symbols=__kvm_nvhe_ $< $@
 
-# Remove ftrace and Shadow Call Stack CFLAGS.
-# This is equivalent to the 'notrace' and '__noscs' annotations.
-KBUILD_CFLAGS := $(filter-out $(CC_FLAGS_FTRACE) $(CC_FLAGS_SCS), $(KBUILD_CFLAGS))
+# Remove ftrace, Shadow Call Stack, and CFI CFLAGS.
+# This is equivalent to the 'notrace', '__noscs', and '__nocfi' annotations.
+KBUILD_CFLAGS := $(filter-out $(CC_FLAGS_FTRACE) $(CC_FLAGS_SCS) $(CC_FLAGS_CFI), $(KBUILD_CFLAGS))
 
 # KVM nVHE code is run at a different exception code with a different map, so
 # compiler instrumentation that inserts callbacks or checks into the code may
diff --git a/arch/parisc/Kconfig b/arch/parisc/Kconfig
index 14f3252f2da03ddf2effdfb6b10309f0dcb02af5..ecfd7af35094688f13f1e02a421249fa07347729 100644
--- a/arch/parisc/Kconfig
+++ b/arch/parisc/Kconfig
@@ -61,6 +61,7 @@ config PARISC
 	select HAVE_KRETPROBES
 	select HAVE_DYNAMIC_FTRACE if $(cc-option,-fpatchable-function-entry=1,1)
 	select HAVE_FTRACE_MCOUNT_RECORD if HAVE_DYNAMIC_FTRACE
+	select FTRACE_MCOUNT_USE_PATCHABLE_FUNCTION_ENTRY if DYNAMIC_FTRACE
 	select HAVE_KPROBES_ON_FTRACE
 	select HAVE_DYNAMIC_FTRACE_WITH_REGS
 	select SET_FS
diff --git a/drivers/firmware/efi/libstub/Makefile b/drivers/firmware/efi/libstub/Makefile
index a2ae9c3b95793821c305c4c3e8d125cbce783bd7..d0537573501e9353446bd45dcf6bf7da026551d1 100644
--- a/drivers/firmware/efi/libstub/Makefile
+++ b/drivers/firmware/efi/libstub/Makefile
@@ -39,6 +39,8 @@ KBUILD_CFLAGS			:= $(cflags-y) -Os -DDISABLE_BRANCH_PROFILING \
 
 # remove SCS flags from all objects in this directory
 KBUILD_CFLAGS := $(filter-out $(CC_FLAGS_SCS), $(KBUILD_CFLAGS))
+# disable LTO
+KBUILD_CFLAGS := $(filter-out $(CC_FLAGS_LTO), $(KBUILD_CFLAGS))
 
 GCOV_PROFILE			:= n
 # Sanitizer runtimes are unavailable and cannot be linked here.
diff --git a/drivers/firmware/psci/psci.c b/drivers/firmware/psci/psci.c
index 00af99b6f97c1516347f61de8eab3311794602f3..db7e357aa34d4c432299da6c4c32fe796b13487a 100644
--- a/drivers/firmware/psci/psci.c
+++ b/drivers/firmware/psci/psci.c
@@ -289,8 +289,9 @@ static int __init psci_features(u32 psci_func_id)
 static int psci_suspend_finisher(unsigned long state)
 {
 	u32 power_state = state;
+	phys_addr_t pa_cpu_resume = __pa_symbol(function_nocfi(cpu_resume));
 
-	return psci_ops.cpu_suspend(power_state, __pa_symbol(cpu_resume));
+	return psci_ops.cpu_suspend(power_state, pa_cpu_resume);
 }
 
 int psci_cpu_suspend_enter(u32 state)
@@ -308,8 +309,10 @@ int psci_cpu_suspend_enter(u32 state)
 
 static int psci_system_suspend(unsigned long unused)
 {
+	phys_addr_t pa_cpu_resume = __pa_symbol(function_nocfi(cpu_resume));
+
 	return invoke_psci_fn(PSCI_FN_NATIVE(1_0, SYSTEM_SUSPEND),
-			      __pa_symbol(cpu_resume), 0, 0);
+			      pa_cpu_resume, 0, 0);
 }
 
 static int psci_system_suspend_enter(suspend_state_t state)
diff --git a/drivers/misc/lkdtm/Makefile b/drivers/misc/lkdtm/Makefile
index 30c8ac24635d4cb14ef9f8534687f9611ce09ce7..73fb627f0e723f726c404acda4fa805b9e2c8b4f 100644
--- a/drivers/misc/lkdtm/Makefile
+++ b/drivers/misc/lkdtm/Makefile
@@ -13,6 +13,7 @@ lkdtm-$(CONFIG_LKDTM)		+= cfi.o
 
 KASAN_SANITIZE_stackleak.o	:= n
 KCOV_INSTRUMENT_rodata.o	:= n
+CFLAGS_REMOVE_rodata.o		+= $(CC_FLAGS_LTO)
 
 OBJCOPYFLAGS :=
 OBJCOPYFLAGS_rodata_objcopy.o	:= \
diff --git a/drivers/misc/lkdtm/usercopy.c b/drivers/misc/lkdtm/usercopy.c
index 109e8d4302c11332decb0334c55854fa8b390a01..15d220ef35a5695194cf5a212bd166ef2c6f7544 100644
--- a/drivers/misc/lkdtm/usercopy.c
+++ b/drivers/misc/lkdtm/usercopy.c
@@ -314,7 +314,7 @@ void lkdtm_USERCOPY_KERNEL(void)
 
 	pr_info("attempting bad copy_to_user from kernel text: %px\n",
 		vm_mmap);
-	if (copy_to_user((void __user *)user_addr, vm_mmap,
+	if (copy_to_user((void __user *)user_addr, function_nocfi(vm_mmap),
 			 unconst + PAGE_SIZE)) {
 		pr_warn("copy_to_user failed, but lacked Oops\n");
 		goto free_user;
diff --git a/include/asm-generic/bug.h b/include/asm-generic/bug.h
index 76a10e0dca9fc7559ad57268c155fbf665583f73..b402494883b682e8d0fdea0a702a37ee93078632 100644
--- a/include/asm-generic/bug.h
+++ b/include/asm-generic/bug.h
@@ -241,6 +241,22 @@ void __warn(const char *file, int line, void *caller, unsigned taint,
 # define WARN_ON_SMP(x)			({0;})
 #endif
 
+/*
+ * WARN_ON_FUNCTION_MISMATCH() warns if a value doesn't match a
+ * function address, and can be useful for catching issues with
+ * callback functions, for example.
+ *
+ * With CONFIG_CFI_CLANG, the warning is disabled because the
+ * compiler replaces function addresses taken in C code with
+ * local jump table addresses, which breaks cross-module function
+ * address equality.
+ */
+#if defined(CONFIG_CFI_CLANG) && defined(CONFIG_MODULES)
+# define WARN_ON_FUNCTION_MISMATCH(x, fn) ({ 0; })
+#else
+# define WARN_ON_FUNCTION_MISMATCH(x, fn) WARN_ON_ONCE((x) != (fn))
+#endif
+
 #endif /* __ASSEMBLY__ */
 
 #endif
diff --git a/include/asm-generic/vmlinux.lds.h b/include/asm-generic/vmlinux.lds.h
index 274692c8b1059d26756d646f98b035f2646ec5ff..24709c120d0bf891b6fd37c67741f7bda1096659 100644
--- a/include/asm-generic/vmlinux.lds.h
+++ b/include/asm-generic/vmlinux.lds.h
@@ -90,15 +90,18 @@
  * .data. We don't want to pull in .data..other sections, which Linux
  * has defined. Same for text and bss.
  *
+ * With LTO_CLANG, the linker also splits sections by default, so we need
+ * these macros to combine the sections during the final link.
+ *
  * RODATA_MAIN is not used because existing code already defines .rodata.x
  * sections to be brought in with rodata.
  */
-#ifdef CONFIG_LD_DEAD_CODE_DATA_ELIMINATION
+#if defined(CONFIG_LD_DEAD_CODE_DATA_ELIMINATION) || defined(CONFIG_LTO_CLANG)
 #define TEXT_MAIN .text .text.[0-9a-zA-Z_]*
-#define DATA_MAIN .data .data.[0-9a-zA-Z_]* .data..LPBX*
+#define DATA_MAIN .data .data.[0-9a-zA-Z_]* .data..L* .data..compoundliteral*
 #define SDATA_MAIN .sdata .sdata.[0-9a-zA-Z_]*
-#define RODATA_MAIN .rodata .rodata.[0-9a-zA-Z_]*
-#define BSS_MAIN .bss .bss.[0-9a-zA-Z_]*
+#define RODATA_MAIN .rodata .rodata.[0-9a-zA-Z_]* .rodata..L*
+#define BSS_MAIN .bss .bss.[0-9a-zA-Z_]* .bss..compoundliteral*
 #define SBSS_MAIN .sbss .sbss.[0-9a-zA-Z_]*
 #else
 #define TEXT_MAIN .text
@@ -573,6 +576,22 @@
 	. = ALIGN((align));						\
 	__end_rodata = .;
 
+
+/*
+ * .text..L.cfi.jumptable.* contain Control-Flow Integrity (CFI)
+ * jump table entries.
+ */
+#ifdef CONFIG_CFI_CLANG
+#define TEXT_CFI_JT							\
+		. = ALIGN(PMD_SIZE);					\
+		__cfi_jt_start = .;					\
+		*(.text..L.cfi.jumptable .text..L.cfi.jumptable.*)	\
+		. = ALIGN(PMD_SIZE);					\
+		__cfi_jt_end = .;
+#else
+#define TEXT_CFI_JT
+#endif
+
 /*
  * Non-instrumentable text section
  */
@@ -600,6 +619,7 @@
 		*(.text..refcount)					\
 		*(.ref.text)						\
 		*(.text.asan.* .text.tsan.*)				\
+		TEXT_CFI_JT						\
 	MEM_KEEP(init.text*)						\
 	MEM_KEEP(exit.text*)						\
 
@@ -1004,7 +1024,8 @@
  * keep any .init_array.* sections.
  * https://bugs.llvm.org/show_bug.cgi?id=46478
  */
-#if defined(CONFIG_GCOV_KERNEL) || defined(CONFIG_KASAN_GENERIC) || defined(CONFIG_KCSAN)
+#if defined(CONFIG_GCOV_KERNEL) || defined(CONFIG_KASAN_GENERIC) || defined(CONFIG_KCSAN) || \
+	defined(CONFIG_CFI_CLANG)
 # ifdef CONFIG_CONSTRUCTORS
 #  define SANITIZER_DISCARDS						\
 	*(.eh_frame)
diff --git a/include/linux/bpf.h b/include/linux/bpf.h
index 1596d281957ab79bdacb5e60a2fa0d444c72efdf..a8b2625e54a46b73f3303aa1257123492ebf7e57 100644
--- a/include/linux/bpf.h
+++ b/include/linux/bpf.h
@@ -711,7 +711,7 @@ struct bpf_dispatcher {
 	struct bpf_ksym ksym;
 };
 
-static __always_inline unsigned int bpf_dispatcher_nop_func(
+static __always_inline __nocfi unsigned int bpf_dispatcher_nop_func(
 	const void *ctx,
 	const struct bpf_insn *insnsi,
 	unsigned int (*bpf_func)(const void *,
@@ -740,7 +740,7 @@ int arch_prepare_bpf_dispatcher(void *image, s64 *funcs, int num_funcs);
 }
 
 #define DEFINE_BPF_DISPATCHER(name)					\
-	noinline unsigned int bpf_dispatcher_##name##_func(		\
+	noinline __nocfi unsigned int bpf_dispatcher_##name##_func(	\
 		const void *ctx,					\
 		const struct bpf_insn *insnsi,				\
 		unsigned int (*bpf_func)(const void *,			\
diff --git a/include/linux/cfi.h b/include/linux/cfi.h
new file mode 100644
index 0000000000000000000000000000000000000000..879744aaa6e0f667c3e9ca1f4681267247e1cefc
--- /dev/null
+++ b/include/linux/cfi.h
@@ -0,0 +1,41 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Clang Control Flow Integrity (CFI) support.
+ *
+ * Copyright (C) 2021 Google LLC
+ */
+#ifndef _LINUX_CFI_H
+#define _LINUX_CFI_H
+
+#ifdef CONFIG_CFI_CLANG
+typedef void (*cfi_check_fn)(uint64_t id, void *ptr, void *diag);
+
+/* Compiler-generated function in each module, and the kernel */
+extern void __cfi_check(uint64_t id, void *ptr, void *diag);
+
+/*
+ * Force the compiler to generate a CFI jump table entry for a function
+ * and store the jump table address to __cfi_jt_<function>.
+ */
+#define __CFI_ADDRESSABLE(fn, __attr) \
+	const void *__cfi_jt_ ## fn __visible __attr = (void *)&fn
+
+#ifdef CONFIG_CFI_CLANG_SHADOW
+
+extern void cfi_module_add(struct module *mod, unsigned long base_addr);
+extern void cfi_module_remove(struct module *mod, unsigned long base_addr);
+
+#else
+
+static inline void cfi_module_add(struct module *mod, unsigned long base_addr) {}
+static inline void cfi_module_remove(struct module *mod, unsigned long base_addr) {}
+
+#endif /* CONFIG_CFI_CLANG_SHADOW */
+
+#else /* !CONFIG_CFI_CLANG */
+
+#define __CFI_ADDRESSABLE(fn, __attr)
+
+#endif /* CONFIG_CFI_CLANG */
+
+#endif /* _LINUX_CFI_H */
diff --git a/include/linux/compiler-clang.h b/include/linux/compiler-clang.h
index 9ba951e3a6c22f81d049fb7932164655606bba00..8a26cd96674120adf30c49b2a9e25f1c0d509073 100644
--- a/include/linux/compiler-clang.h
+++ b/include/linux/compiler-clang.h
@@ -88,3 +88,6 @@
 #if __has_feature(shadow_call_stack)
 # define __noscs	__attribute__((__no_sanitize__("shadow-call-stack")))
 #endif
+
+#define __nocfi		__attribute__((__no_sanitize__("cfi")))
+#define __cficanonical	__attribute__((__cfi_canonical_jump_table__))
diff --git a/include/linux/compiler_types.h b/include/linux/compiler_types.h
index 2a1c202baa1fe3d403a7a22a83239bb5b4f6e8b3..2a31195cb50f374f2bab01eb444ba10de7e1cdfc 100644
--- a/include/linux/compiler_types.h
+++ b/include/linux/compiler_types.h
@@ -237,6 +237,14 @@ struct ftrace_likely_data {
 # define __noscs
 #endif
 
+#ifndef __nocfi
+# define __nocfi
+#endif
+
+#ifndef __cficanonical
+# define __cficanonical
+#endif
+
 #ifndef asm_volatile_goto
 #define asm_volatile_goto(x...) asm goto(x)
 #endif
diff --git a/include/linux/init.h b/include/linux/init.h
index 7b53cb3092ee9956866e79a677c97cb5235dd96c..e83a6cfc33ee2812923cd08034662040fd316565 100644
--- a/include/linux/init.h
+++ b/include/linux/init.h
@@ -47,7 +47,7 @@
 
 /* These are for everybody (although not all archs will actually
    discard it in modules) */
-#define __init		__section(".init.text") __cold  __latent_entropy __noinitretpoline
+#define __init		__section(".init.text") __cold  __latent_entropy __noinitretpoline __nocfi
 #define __initdata	__section(".init.data")
 #define __initconst	__section(".init.rodata")
 #define __exitdata	__section(".exit.data")
@@ -184,19 +184,80 @@ extern bool initcall_debug;
  * as KEEP() in the linker script.
  */
 
+/* Format: <modname>__<counter>_<line>_<fn> */
+#define __initcall_id(fn)					\
+	__PASTE(__KBUILD_MODNAME,				\
+	__PASTE(__,						\
+	__PASTE(__COUNTER__,					\
+	__PASTE(_,						\
+	__PASTE(__LINE__,					\
+	__PASTE(_, fn))))))
+
+/* Format: __<prefix>__<iid><id> */
+#define __initcall_name(prefix, __iid, id)			\
+	__PASTE(__,						\
+	__PASTE(prefix,						\
+	__PASTE(__,						\
+	__PASTE(__iid, id))))
+
+#ifdef CONFIG_LTO_CLANG
+/*
+ * With LTO, the compiler doesn't necessarily obey link order for
+ * initcalls. In order to preserve the correct order, we add each
+ * variable into its own section and generate a linker script (in
+ * scripts/link-vmlinux.sh) to specify the order of the sections.
+ */
+#define __initcall_section(__sec, __iid)			\
+	#__sec ".init.." #__iid
+
+/*
+ * With LTO, the compiler can rename static functions to avoid
+ * global naming collisions. We use a global stub function for
+ * initcalls to create a stable symbol name whose address can be
+ * taken in inline assembly when PREL32 relocations are used.
+ */
+#define __initcall_stub(fn, __iid, id)				\
+	__initcall_name(initstub, __iid, id)
+
+#define __define_initcall_stub(__stub, fn)			\
+	int __init __cficanonical __stub(void);			\
+	int __init __cficanonical __stub(void)			\
+	{ 							\
+		return fn();					\
+	}							\
+	__ADDRESSABLE(__stub)
+#else
+#define __initcall_section(__sec, __iid)			\
+	#__sec ".init"
+
+#define __initcall_stub(fn, __iid, id)	fn
+
+#define __define_initcall_stub(__stub, fn)			\
+	__ADDRESSABLE(fn)
+#endif
+
 #ifdef CONFIG_HAVE_ARCH_PREL32_RELOCATIONS
-#define ___define_initcall(fn, id, __sec)			\
-	__ADDRESSABLE(fn)					\
-	asm(".section	\"" #__sec ".init\", \"a\"	\n"	\
-	"__initcall_" #fn #id ":			\n"	\
-	    ".long	" #fn " - .			\n"	\
+#define ____define_initcall(fn, __stub, __name, __sec)		\
+	__define_initcall_stub(__stub, fn)			\
+	asm(".section	\"" __sec "\", \"a\"		\n"	\
+	    __stringify(__name) ":			\n"	\
+	    ".long	" __stringify(__stub) " - .	\n"	\
 	    ".previous					\n");
 #else
-#define ___define_initcall(fn, id, __sec) \
-	static initcall_t __initcall_##fn##id __used \
-		__attribute__((__section__(#__sec ".init"))) = fn;
+#define ____define_initcall(fn, __unused, __name, __sec)	\
+	static initcall_t __name __used 			\
+		__attribute__((__section__(__sec))) = fn;
 #endif
 
+#define __unique_initcall(fn, id, __sec, __iid)			\
+	____define_initcall(fn,					\
+		__initcall_stub(fn, __iid, id),			\
+		__initcall_name(initcall, __iid, id),		\
+		__initcall_section(__sec, __iid))
+
+#define ___define_initcall(fn, id, __sec)			\
+	__unique_initcall(fn, id, __sec, __initcall_id(fn))
+
 #define __define_initcall(fn, id) ___define_initcall(fn, id, .initcall##id)
 
 /*
@@ -236,7 +297,7 @@ extern bool initcall_debug;
 #define __exitcall(fn)						\
 	static exitcall_t __exitcall_##fn __exit_call = fn
 
-#define console_initcall(fn)	___define_initcall(fn,, .con_initcall)
+#define console_initcall(fn)	___define_initcall(fn, con, .con_initcall)
 
 struct obs_kernel_param {
 	const char *str;
diff --git a/include/linux/mm.h b/include/linux/mm.h
index 40ca6f122b9d7b6cf239c1a14e5b058f72e84fdd..53fb5144588131ad8cdb3c25a00deeb330990e48 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -123,6 +123,16 @@ extern int mmap_rnd_compat_bits __read_mostly;
 #define lm_alias(x)	__va(__pa_symbol(x))
 #endif
 
+/*
+ * With CONFIG_CFI_CLANG, the compiler replaces function addresses in
+ * instrumented C code with jump table addresses. Architectures that
+ * support CFI can define this macro to return the actual function address
+ * when needed.
+ */
+#ifndef function_nocfi
+#define function_nocfi(x) (x)
+#endif
+
 /*
  * To prevent common memory management code establishing
  * a zero page mapping on a read fault.
diff --git a/include/linux/module.h b/include/linux/module.h
index 6264617bab4d46c542f86803a860d5a0a51c6214..0c9466d2aaeb3b79b53f16e5080dbaf0fc243638 100644
--- a/include/linux/module.h
+++ b/include/linux/module.h
@@ -26,6 +26,7 @@
 #include <linux/tracepoint-defs.h>
 #include <linux/srcu.h>
 #include <linux/static_call_types.h>
+#include <linux/cfi.h>
 
 #include <linux/percpu.h>
 #include <asm/module.h>
@@ -131,13 +132,17 @@ extern void cleanup_module(void);
 #define module_init(initfn)					\
 	static inline initcall_t __maybe_unused __inittest(void)		\
 	{ return initfn; }					\
-	int init_module(void) __copy(initfn) __attribute__((alias(#initfn)));
+	int init_module(void) __copy(initfn)			\
+		__attribute__((alias(#initfn)));		\
+	__CFI_ADDRESSABLE(init_module, __initdata);
 
 /* This is only required if you want to be unloadable. */
 #define module_exit(exitfn)					\
 	static inline exitcall_t __maybe_unused __exittest(void)		\
 	{ return exitfn; }					\
-	void cleanup_module(void) __copy(exitfn) __attribute__((alias(#exitfn)));
+	void cleanup_module(void) __copy(exitfn)		\
+		__attribute__((alias(#exitfn)));		\
+	__CFI_ADDRESSABLE(cleanup_module, __exitdata);
 
 #endif
 
@@ -379,6 +384,10 @@ struct module {
 	const s32 *crcs;
 	unsigned int num_syms;
 
+#ifdef CONFIG_CFI_CLANG
+	cfi_check_fn cfi_check;
+#endif
+
 	/* Kernel parameters. */
 #ifdef CONFIG_SYSFS
 	struct mutex param_lock;
diff --git a/include/linux/pci.h b/include/linux/pci.h
index 7a23dea6cb75beda8530a8243ec6f63e8a8db0cb..a5788ef380d0910e09155dda17b100ea6723fb77 100644
--- a/include/linux/pci.h
+++ b/include/linux/pci.h
@@ -1916,7 +1916,7 @@ enum pci_fixup_pass {
 };
 
 #ifdef CONFIG_HAVE_ARCH_PREL32_RELOCATIONS
-#define __DECLARE_PCI_FIXUP_SECTION(sec, name, vendor, device, class,	\
+#define ___DECLARE_PCI_FIXUP_SECTION(sec, name, vendor, device, class,	\
 				    class_shift, hook)			\
 	__ADDRESSABLE(hook)						\
 	asm(".section "	#sec ", \"a\"				\n"	\
@@ -1925,10 +1925,33 @@ enum pci_fixup_pass {
 	    ".long "	#class ", " #class_shift "		\n"	\
 	    ".long "	#hook " - .				\n"	\
 	    ".previous						\n");
+
+/*
+ * Clang's LTO may rename static functions in C, but has no way to
+ * handle such renamings when referenced from inline asm. To work
+ * around this, create global C stubs for these cases.
+ */
+#ifdef CONFIG_LTO_CLANG
+#define __DECLARE_PCI_FIXUP_SECTION(sec, name, vendor, device, class,	\
+				  class_shift, hook, stub)		\
+	void __cficanonical stub(struct pci_dev *dev);			\
+	void __cficanonical stub(struct pci_dev *dev)			\
+	{ 								\
+		hook(dev); 						\
+	}								\
+	___DECLARE_PCI_FIXUP_SECTION(sec, name, vendor, device, class,	\
+				  class_shift, stub)
+#else
+#define __DECLARE_PCI_FIXUP_SECTION(sec, name, vendor, device, class,	\
+				  class_shift, hook, stub)		\
+	___DECLARE_PCI_FIXUP_SECTION(sec, name, vendor, device, class,	\
+				  class_shift, hook)
+#endif
+
 #define DECLARE_PCI_FIXUP_SECTION(sec, name, vendor, device, class,	\
 				  class_shift, hook)			\
 	__DECLARE_PCI_FIXUP_SECTION(sec, name, vendor, device, class,	\
-				  class_shift, hook)
+				  class_shift, hook, __UNIQUE_ID(hook))
 #else
 /* Anonymous variables would be nice... */
 #define DECLARE_PCI_FIXUP_SECTION(section, name, vendor, device, class,	\
diff --git a/init/Kconfig b/init/Kconfig
index 23db5012fe920e369cf47a635f2078ee6dbf80fd..7acf079f960964aba6ef7ce9add6953d9639f687 100644
--- a/init/Kconfig
+++ b/init/Kconfig
@@ -2402,7 +2402,7 @@ endif # MODULES
 
 config MODULES_TREE_LOOKUP
 	def_bool y
-	depends on PERF_EVENTS || TRACING
+	depends on PERF_EVENTS || TRACING || CFI_CLANG
 
 config INIT_ALL_POSSIBLE
 	bool
diff --git a/kernel/Makefile b/kernel/Makefile
index e7905bdf6e972c60aa26ab879d1772002e5e870a..6ee614db171787f840be147c9ce28028e4cee605 100644
--- a/kernel/Makefile
+++ b/kernel/Makefile
@@ -38,6 +38,9 @@ KASAN_SANITIZE_kcov.o := n
 KCSAN_SANITIZE_kcov.o := n
 CFLAGS_kcov.o := $(call cc-option, -fno-conserve-stack) -fno-stack-protector
 
+# Don't instrument error handlers
+CFLAGS_REMOVE_cfi.o := $(CC_FLAGS_CFI)
+
 obj-y += sched/
 obj-y += locking/
 obj-y += power/
@@ -108,6 +111,7 @@ obj-$(CONFIG_BPF) += bpf/
 obj-$(CONFIG_KCSAN) += kcsan/
 obj-$(CONFIG_SHADOW_CALL_STACK) += scs.o
 obj-$(CONFIG_HAVE_STATIC_CALL_INLINE) += static_call.o
+obj-$(CONFIG_CFI_CLANG) += cfi.o
 
 obj-$(CONFIG_PERF_EVENTS) += events/
 
diff --git a/kernel/cfi.c b/kernel/cfi.c
new file mode 100644
index 0000000000000000000000000000000000000000..08102d19ec15a2e402c10ad8d22743caafe47d68
--- /dev/null
+++ b/kernel/cfi.c
@@ -0,0 +1,339 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Clang Control Flow Integrity (CFI) error and slowpath handling.
+ *
+ * Copyright (C) 2021 Google LLC
+ */
+
+#include <linux/hardirq.h>
+#include <linux/kallsyms.h>
+#include <linux/module.h>
+#include <linux/mutex.h>
+#include <linux/printk.h>
+#include <linux/ratelimit.h>
+#include <linux/rcupdate.h>
+#include <linux/vmalloc.h>
+#include <asm/cacheflush.h>
+#include <asm/set_memory.h>
+
+/* Compiler-defined handler names */
+#ifdef CONFIG_CFI_PERMISSIVE
+#define cfi_failure_handler	__ubsan_handle_cfi_check_fail
+#else
+#define cfi_failure_handler	__ubsan_handle_cfi_check_fail_abort
+#endif
+
+static inline void handle_cfi_failure(void *ptr)
+{
+	if (IS_ENABLED(CONFIG_CFI_PERMISSIVE))
+		WARN_RATELIMIT(1, "CFI failure (target: %pS):\n", ptr);
+	else
+		panic("CFI failure (target: %pS)\n", ptr);
+}
+
+#ifdef CONFIG_MODULES
+#ifdef CONFIG_CFI_CLANG_SHADOW
+/*
+ * Index type. A 16-bit index can address at most (2^16)-2 pages (taking
+ * into account SHADOW_INVALID), i.e. ~256M with 4k pages.
+ */
+typedef u16 shadow_t;
+#define SHADOW_INVALID		((shadow_t)~0UL)
+
+struct cfi_shadow {
+	/* Page index for the beginning of the shadow */
+	unsigned long base;
+	/* An array of __cfi_check locations (as indices to the shadow) */
+	shadow_t shadow[1];
+} __packed;
+
+/*
+ * The shadow covers ~128M from the beginning of the module region. If
+ * the region is larger, we fall back to __module_address for the rest.
+ */
+#define __SHADOW_RANGE		(_UL(SZ_128M) >> PAGE_SHIFT)
+
+/* The in-memory size of struct cfi_shadow, always at least one page */
+#define __SHADOW_PAGES		((__SHADOW_RANGE * sizeof(shadow_t)) >> PAGE_SHIFT)
+#define SHADOW_PAGES		max(1UL, __SHADOW_PAGES)
+#define SHADOW_SIZE		(SHADOW_PAGES << PAGE_SHIFT)
+
+/* The actual size of the shadow array, minus metadata */
+#define SHADOW_ARR_SIZE		(SHADOW_SIZE - offsetof(struct cfi_shadow, shadow))
+#define SHADOW_ARR_SLOTS	(SHADOW_ARR_SIZE / sizeof(shadow_t))
+
+static DEFINE_MUTEX(shadow_update_lock);
+static struct cfi_shadow __rcu *cfi_shadow __read_mostly;
+
+/* Returns the index in the shadow for the given address */
+static inline int ptr_to_shadow(const struct cfi_shadow *s, unsigned long ptr)
+{
+	unsigned long index;
+	unsigned long page = ptr >> PAGE_SHIFT;
+
+	if (unlikely(page < s->base))
+		return -1; /* Outside of module area */
+
+	index = page - s->base;
+
+	if (index >= SHADOW_ARR_SLOTS)
+		return -1; /* Cannot be addressed with shadow */
+
+	return (int)index;
+}
+
+/* Returns the page address for an index in the shadow */
+static inline unsigned long shadow_to_ptr(const struct cfi_shadow *s,
+	int index)
+{
+	if (unlikely(index < 0 || index >= SHADOW_ARR_SLOTS))
+		return 0;
+
+	return (s->base + index) << PAGE_SHIFT;
+}
+
+/* Returns the __cfi_check function address for the given shadow location */
+static inline unsigned long shadow_to_check_fn(const struct cfi_shadow *s,
+	int index)
+{
+	if (unlikely(index < 0 || index >= SHADOW_ARR_SLOTS))
+		return 0;
+
+	if (unlikely(s->shadow[index] == SHADOW_INVALID))
+		return 0;
+
+	/* __cfi_check is always page aligned */
+	return (s->base + s->shadow[index]) << PAGE_SHIFT;
+}
+
+static void prepare_next_shadow(const struct cfi_shadow __rcu *prev,
+		struct cfi_shadow *next)
+{
+	int i, index, check;
+
+	/* Mark everything invalid */
+	memset(next->shadow, 0xFF, SHADOW_ARR_SIZE);
+
+	if (!prev)
+		return; /* No previous shadow */
+
+	/* If the base address didn't change, an update is not needed */
+	if (prev->base == next->base) {
+		memcpy(next->shadow, prev->shadow, SHADOW_ARR_SIZE);
+		return;
+	}
+
+	/* Convert the previous shadow to the new address range */
+	for (i = 0; i < SHADOW_ARR_SLOTS; ++i) {
+		if (prev->shadow[i] == SHADOW_INVALID)
+			continue;
+
+		index = ptr_to_shadow(next, shadow_to_ptr(prev, i));
+		if (index < 0)
+			continue;
+
+		check = ptr_to_shadow(next,
+				shadow_to_check_fn(prev, prev->shadow[i]));
+		if (check < 0)
+			continue;
+
+		next->shadow[index] = (shadow_t)check;
+	}
+}
+
+static void add_module_to_shadow(struct cfi_shadow *s, struct module *mod,
+			unsigned long min_addr, unsigned long max_addr)
+{
+	int check_index;
+	unsigned long check = (unsigned long)mod->cfi_check;
+	unsigned long ptr;
+
+	if (unlikely(!PAGE_ALIGNED(check))) {
+		pr_warn("cfi: not using shadow for module %s\n", mod->name);
+		return;
+	}
+
+	check_index = ptr_to_shadow(s, check);
+	if (check_index < 0)
+		return; /* Module not addressable with shadow */
+
+	/* For each page, store the check function index in the shadow */
+	for (ptr = min_addr; ptr <= max_addr; ptr += PAGE_SIZE) {
+		int index = ptr_to_shadow(s, ptr);
+
+		if (index >= 0) {
+			/* Each page must only contain one module */
+			WARN_ON_ONCE(s->shadow[index] != SHADOW_INVALID);
+			s->shadow[index] = (shadow_t)check_index;
+		}
+	}
+}
+
+static void remove_module_from_shadow(struct cfi_shadow *s, struct module *mod,
+		unsigned long min_addr, unsigned long max_addr)
+{
+	unsigned long ptr;
+
+	for (ptr = min_addr; ptr <= max_addr; ptr += PAGE_SIZE) {
+		int index = ptr_to_shadow(s, ptr);
+
+		if (index >= 0)
+			s->shadow[index] = SHADOW_INVALID;
+	}
+}
+
+typedef void (*update_shadow_fn)(struct cfi_shadow *, struct module *,
+			unsigned long min_addr, unsigned long max_addr);
+
+static void update_shadow(struct module *mod, unsigned long base_addr,
+		update_shadow_fn fn)
+{
+	struct cfi_shadow *prev;
+	struct cfi_shadow *next;
+	unsigned long min_addr, max_addr;
+
+	next = vmalloc(SHADOW_SIZE);
+
+	mutex_lock(&shadow_update_lock);
+	prev = rcu_dereference_protected(cfi_shadow,
+					 mutex_is_locked(&shadow_update_lock));
+
+	if (next) {
+		next->base = base_addr >> PAGE_SHIFT;
+		prepare_next_shadow(prev, next);
+
+		min_addr = (unsigned long)mod->core_layout.base;
+		max_addr = min_addr + mod->core_layout.text_size;
+		fn(next, mod, min_addr & PAGE_MASK, max_addr & PAGE_MASK);
+
+		set_memory_ro((unsigned long)next, SHADOW_PAGES);
+	}
+
+	rcu_assign_pointer(cfi_shadow, next);
+	mutex_unlock(&shadow_update_lock);
+	synchronize_rcu();
+
+	if (prev) {
+		set_memory_rw((unsigned long)prev, SHADOW_PAGES);
+		vfree(prev);
+	}
+}
+
+void cfi_module_add(struct module *mod, unsigned long base_addr)
+{
+	update_shadow(mod, base_addr, add_module_to_shadow);
+}
+
+void cfi_module_remove(struct module *mod, unsigned long base_addr)
+{
+	update_shadow(mod, base_addr, remove_module_from_shadow);
+}
+
+static inline cfi_check_fn ptr_to_check_fn(const struct cfi_shadow __rcu *s,
+	unsigned long ptr)
+{
+	int index;
+
+	if (unlikely(!s))
+		return NULL; /* No shadow available */
+
+	index = ptr_to_shadow(s, ptr);
+	if (index < 0)
+		return NULL; /* Cannot be addressed with shadow */
+
+	return (cfi_check_fn)shadow_to_check_fn(s, index);
+}
+
+static inline cfi_check_fn find_shadow_check_fn(unsigned long ptr)
+{
+	cfi_check_fn fn;
+
+	rcu_read_lock_sched_notrace();
+	fn = ptr_to_check_fn(rcu_dereference_sched(cfi_shadow), ptr);
+	rcu_read_unlock_sched_notrace();
+
+	return fn;
+}
+
+#else /* !CONFIG_CFI_CLANG_SHADOW */
+
+static inline cfi_check_fn find_shadow_check_fn(unsigned long ptr)
+{
+	return NULL;
+}
+
+#endif /* CONFIG_CFI_CLANG_SHADOW */
+
+static inline cfi_check_fn find_module_check_fn(unsigned long ptr)
+{
+	cfi_check_fn fn = NULL;
+	struct module *mod;
+
+	rcu_read_lock_sched_notrace();
+	mod = __module_address(ptr);
+	if (mod)
+		fn = mod->cfi_check;
+	rcu_read_unlock_sched_notrace();
+
+	return fn;
+}
+
+static inline cfi_check_fn find_check_fn(unsigned long ptr)
+{
+	cfi_check_fn fn = NULL;
+	unsigned long flags;
+	bool rcu_idle;
+
+	if (is_kernel_text(ptr))
+		return __cfi_check;
+
+	/*
+	 * Indirect call checks can happen when RCU is not watching. Both
+	 * the shadow and __module_address use RCU, so we need to wake it
+	 * up if necessary.
+	 */
+	rcu_idle = !rcu_is_watching();
+	if (rcu_idle) {
+		local_irq_save(flags);
+		rcu_irq_enter();
+	}
+
+	if (IS_ENABLED(CONFIG_CFI_CLANG_SHADOW))
+		fn = find_shadow_check_fn(ptr);
+	if (!fn)
+		fn = find_module_check_fn(ptr);
+
+	if (rcu_idle) {
+		rcu_irq_exit();
+		local_irq_restore(flags);
+	}
+
+	return fn;
+}
+
+void __cfi_slowpath_diag(uint64_t id, void *ptr, void *diag)
+{
+	cfi_check_fn fn = find_check_fn((unsigned long)ptr);
+
+	if (likely(fn))
+		fn(id, ptr, diag);
+	else /* Don't allow unchecked modules */
+		handle_cfi_failure(ptr);
+}
+EXPORT_SYMBOL(__cfi_slowpath_diag);
+
+#else /* !CONFIG_MODULES */
+
+void __cfi_slowpath_diag(uint64_t id, void *ptr, void *diag)
+{
+	handle_cfi_failure(ptr); /* No modules */
+}
+EXPORT_SYMBOL(__cfi_slowpath_diag);
+
+#endif /* CONFIG_MODULES */
+
+void cfi_failure_handler(void *data, void *ptr, void *vtable)
+{
+	handle_cfi_failure(ptr);
+}
+EXPORT_SYMBOL(cfi_failure_handler);
diff --git a/kernel/kallsyms.c b/kernel/kallsyms.c
index fe9de067771c34eb89d021df40579c38d8974298..52023c8934c397a4dee9012b704925d2118ca0fb 100644
--- a/kernel/kallsyms.c
+++ b/kernel/kallsyms.c
@@ -161,6 +161,27 @@ static unsigned long kallsyms_sym_address(int idx)
 	return kallsyms_relative_base - 1 - kallsyms_offsets[idx];
 }
 
+#if defined(CONFIG_CFI_CLANG) && defined(CONFIG_LTO_CLANG_THIN)
+/*
+ * LLVM appends a hash to static function names when ThinLTO and CFI are
+ * both enabled, i.e. foo() becomes foo$707af9a22804d33c81801f27dcfe489b.
+ * This causes confusion and potentially breaks user space tools, so we
+ * strip the suffix from expanded symbol names.
+ */
+static inline bool cleanup_symbol_name(char *s)
+{
+	char *res;
+
+	res = strrchr(s, '$');
+	if (res)
+		*res = '\0';
+
+	return res != NULL;
+}
+#else
+static inline bool cleanup_symbol_name(char *s) { return false; }
+#endif
+
 /* Lookup the address for this symbol. Returns 0 if not found. */
 unsigned long kallsyms_lookup_name(const char *name)
 {
@@ -173,6 +194,9 @@ unsigned long kallsyms_lookup_name(const char *name)
 
 		if (strcmp(namebuf, name) == 0)
 			return kallsyms_sym_address(i);
+
+		if (cleanup_symbol_name(namebuf) && strcmp(namebuf, name) == 0)
+			return kallsyms_sym_address(i);
 	}
 	return module_kallsyms_lookup_name(name);
 }
@@ -297,7 +321,9 @@ const char *kallsyms_lookup(unsigned long addr,
 				       namebuf, KSYM_NAME_LEN);
 		if (modname)
 			*modname = NULL;
-		return namebuf;
+
+		ret = namebuf;
+		goto found;
 	}
 
 	/* See if it's in a module or a BPF JITed image. */
@@ -310,11 +336,16 @@ const char *kallsyms_lookup(unsigned long addr,
 	if (!ret)
 		ret = ftrace_mod_address_lookup(addr, symbolsize,
 						offset, modname, namebuf);
+
+found:
+	cleanup_symbol_name(namebuf);
 	return ret;
 }
 
 int lookup_symbol_name(unsigned long addr, char *symname)
 {
+	int res;
+
 	symname[0] = '\0';
 	symname[KSYM_NAME_LEN - 1] = '\0';
 
@@ -325,15 +356,23 @@ int lookup_symbol_name(unsigned long addr, char *symname)
 		/* Grab name */
 		kallsyms_expand_symbol(get_symbol_offset(pos),
 				       symname, KSYM_NAME_LEN);
-		return 0;
+		goto found;
 	}
 	/* See if it's in a module. */
-	return lookup_module_symbol_name(addr, symname);
+	res = lookup_module_symbol_name(addr, symname);
+	if (res)
+		return res;
+
+found:
+	cleanup_symbol_name(symname);
+	return 0;
 }
 
 int lookup_symbol_attrs(unsigned long addr, unsigned long *size,
 			unsigned long *offset, char *modname, char *name)
 {
+	int res;
+
 	name[0] = '\0';
 	name[KSYM_NAME_LEN - 1] = '\0';
 
@@ -345,10 +384,16 @@ int lookup_symbol_attrs(unsigned long addr, unsigned long *size,
 		kallsyms_expand_symbol(get_symbol_offset(pos),
 				       name, KSYM_NAME_LEN);
 		modname[0] = '\0';
-		return 0;
+		goto found;
 	}
 	/* See if it's in a module. */
-	return lookup_module_symbol_attrs(addr, size, offset, modname, name);
+	res = lookup_module_symbol_attrs(addr, size, offset, modname, name);
+	if (res)
+		return res;
+
+found:
+	cleanup_symbol_name(name);
+	return 0;
 }
 
 /* Look up a kernel symbol and return it in a text buffer. */
diff --git a/kernel/kthread.c b/kernel/kthread.c
index 508fe52782857838909559077ab28a7008b42ab8..5e60843350ad235d6adcdbfab7172de55b3ed883 100644
--- a/kernel/kthread.c
+++ b/kernel/kthread.c
@@ -957,7 +957,8 @@ static void __kthread_queue_delayed_work(struct kthread_worker *worker,
 	struct timer_list *timer = &dwork->timer;
 	struct kthread_work *work = &dwork->work;
 
-	WARN_ON_ONCE(timer->function != kthread_delayed_work_timer_fn);
+	WARN_ON_FUNCTION_MISMATCH(timer->function,
+				  kthread_delayed_work_timer_fn);
 
 	/*
 	 * If @delay is 0, queue @dwork->work immediately.  This is for
diff --git a/kernel/module.c b/kernel/module.c
index 185b2655bc206b35b07cc2bf5866adc9af462a1f..8f48af2e27a1a3e019bb314b070bc6967c265ed2 100644
--- a/kernel/module.c
+++ b/kernel/module.c
@@ -2213,6 +2213,8 @@ void __weak module_arch_freeing_init(struct module *mod)
 {
 }
 
+static void cfi_cleanup(struct module *mod);
+
 /* Free a module, remove from lists, etc. */
 static void free_module(struct module *mod)
 {
@@ -2252,6 +2254,9 @@ static void free_module(struct module *mod)
 	synchronize_rcu();
 	mutex_unlock(&module_mutex);
 
+	/* Clean up CFI for the module. */
+	cfi_cleanup(mod);
+
 	/* This may be empty, but that's OK */
 	module_arch_freeing_init(mod);
 	module_memfree(mod->init_layout.base);
@@ -3931,6 +3936,8 @@ static int unknown_module_param_cb(char *param, char *val, const char *modname,
 	return 0;
 }
 
+static void cfi_init(struct module *mod);
+
 /* Allocate and load the module: note that size of section 0 is always
    zero, and we rely on this for optional sections. */
 static int load_module(struct load_info *info, const char __user *uargs,
@@ -4058,6 +4065,9 @@ static int load_module(struct load_info *info, const char __user *uargs,
 
 	flush_module_icache(mod);
 
+	/* Setup CFI for the module. */
+	cfi_init(mod);
+
 	/* Now copy in args */
 	mod->args = strndup_user(uargs, ~0UL >> 1);
 	if (IS_ERR(mod->args)) {
@@ -4131,6 +4141,7 @@ static int load_module(struct load_info *info, const char __user *uargs,
 	synchronize_rcu();
 	kfree(mod->args);
  free_arch_cleanup:
+	cfi_cleanup(mod);
 	module_arch_cleanup(mod);
  free_modinfo:
 	free_modinfo(mod);
@@ -4468,6 +4479,40 @@ int module_kallsyms_on_each_symbol(int (*fn)(void *, const char *,
 }
 #endif /* CONFIG_KALLSYMS */
 
+static void cfi_init(struct module *mod)
+{
+#ifdef CONFIG_CFI_CLANG
+	initcall_t *init;
+	exitcall_t *exit;
+
+	rcu_read_lock_sched();
+	mod->cfi_check = (cfi_check_fn)
+		find_kallsyms_symbol_value(mod, "__cfi_check");
+	init = (initcall_t *)
+		find_kallsyms_symbol_value(mod, "__cfi_jt_init_module");
+	exit = (exitcall_t *)
+		find_kallsyms_symbol_value(mod, "__cfi_jt_cleanup_module");
+	rcu_read_unlock_sched();
+
+	/* Fix init/exit functions to point to the CFI jump table */
+	if (init)
+		mod->init = *init;
+#ifdef CONFIG_MODULE_UNLOAD
+	if (exit)
+		mod->exit = *exit;
+#endif
+
+	cfi_module_add(mod, module_addr_min);
+#endif
+}
+
+static void cfi_cleanup(struct module *mod)
+{
+#ifdef CONFIG_CFI_CLANG
+	cfi_module_remove(mod, module_addr_min);
+#endif
+}
+
 /* Maximum number of characters written by module_flags() */
 #define MODULE_FLAGS_BUF_SIZE (TAINT_FLAGS_COUNT + 4)
 
diff --git a/kernel/trace/Kconfig b/kernel/trace/Kconfig
index 29db703f68806b9234c077c9efa1342b635521a4..c49467fb169420dfeef92e632924ff6055bec82e 100644
--- a/kernel/trace/Kconfig
+++ b/kernel/trace/Kconfig
@@ -595,6 +595,22 @@ config FTRACE_MCOUNT_RECORD
 	depends on DYNAMIC_FTRACE
 	depends on HAVE_FTRACE_MCOUNT_RECORD
 
+config FTRACE_MCOUNT_USE_PATCHABLE_FUNCTION_ENTRY
+	bool
+	depends on FTRACE_MCOUNT_RECORD
+
+config FTRACE_MCOUNT_USE_CC
+	def_bool y
+	depends on $(cc-option,-mrecord-mcount)
+	depends on !FTRACE_MCOUNT_USE_PATCHABLE_FUNCTION_ENTRY
+	depends on FTRACE_MCOUNT_RECORD
+
+config FTRACE_MCOUNT_USE_RECORDMCOUNT
+	def_bool y
+	depends on !FTRACE_MCOUNT_USE_PATCHABLE_FUNCTION_ENTRY
+	depends on !FTRACE_MCOUNT_USE_CC
+	depends on FTRACE_MCOUNT_RECORD
+
 config TRACING_MAP
 	bool
 	depends on ARCH_HAVE_NMI_SAFE_CMPXCHG
diff --git a/kernel/workqueue.c b/kernel/workqueue.c
index fdf5fa4bf4448d8b953eece052f21a5e3150c17a..10088c2fea277bd90cefeeeb54785674147cfa96 100644
--- a/kernel/workqueue.c
+++ b/kernel/workqueue.c
@@ -1637,7 +1637,7 @@ static void __queue_delayed_work(int cpu, struct workqueue_struct *wq,
 	struct work_struct *work = &dwork->work;
 
 	WARN_ON_ONCE(!wq);
-	WARN_ON_ONCE(timer->function != delayed_work_timer_fn);
+	WARN_ON_FUNCTION_MISMATCH(timer->function, delayed_work_timer_fn);
 	WARN_ON_ONCE(timer_pending(timer));
 	WARN_ON_ONCE(!list_empty(&work->entry));
 
diff --git a/scripts/Makefile.build b/scripts/Makefile.build
index 8bd4e673383f3269b6a53bd1bc1c704a8723ada8..d7cfd330a6d43b87000e9c6aefa6561f50efe288 100644
--- a/scripts/Makefile.build
+++ b/scripts/Makefile.build
@@ -111,7 +111,7 @@ endif
 # ---------------------------------------------------------------------------
 
 quiet_cmd_cc_s_c = CC $(quiet_modtag)  $@
-      cmd_cc_s_c = $(CC) $(filter-out $(DEBUG_CFLAGS), $(c_flags)) -fverbose-asm -S -o $@ $<
+      cmd_cc_s_c = $(CC) $(filter-out $(DEBUG_CFLAGS) $(CC_FLAGS_LTO), $(c_flags)) -fverbose-asm -S -o $@ $<
 
 $(obj)/%.s: $(src)/%.c FORCE
 	$(call if_changed_dep,cc_s_c)
@@ -166,6 +166,15 @@ ifdef CONFIG_MODVERSIONS
 #   the actual value of the checksum generated by genksyms
 # o remove .tmp_<file>.o to <file>.o
 
+ifdef CONFIG_LTO_CLANG
+# Generate .o.symversions files for each .o with exported symbols, and link these
+# to the kernel and/or modules at the end.
+cmd_modversions_c =								\
+	if $(NM) $@ 2>/dev/null | grep -q __ksymtab; then			\
+		$(call cmd_gensymtypes_c,$(KBUILD_SYMTYPES),$(@:.o=.symtypes))	\
+		    > $@.symversions;						\
+	fi;
+else
 cmd_modversions_c =								\
 	if $(OBJDUMP) -h $@ | grep -q __ksymtab; then				\
 		$(call cmd_gensymtypes_c,$(KBUILD_SYMTYPES),$(@:.o=.symtypes))	\
@@ -177,9 +186,9 @@ cmd_modversions_c =								\
 		rm -f $(@D)/.tmp_$(@F:.o=.ver);					\
 	fi
 endif
+endif
 
-ifdef CONFIG_FTRACE_MCOUNT_RECORD
-ifndef CC_USING_RECORD_MCOUNT
+ifdef CONFIG_FTRACE_MCOUNT_USE_RECORDMCOUNT
 # compiler will not generate __mcount_loc use recordmcount or recordmcount.pl
 ifdef BUILD_C_RECORDMCOUNT
 ifeq ("$(origin RECORDMCOUNT_WARN)", "command line")
@@ -206,8 +215,7 @@ recordmcount_source := $(srctree)/scripts/recordmcount.pl
 endif # BUILD_C_RECORDMCOUNT
 cmd_record_mcount = $(if $(findstring $(strip $(CC_FLAGS_FTRACE)),$(_c_flags)),	\
 	$(sub_cmd_record_mcount))
-endif # CC_USING_RECORD_MCOUNT
-endif # CONFIG_FTRACE_MCOUNT_RECORD
+endif # CONFIG_FTRACE_MCOUNT_USE_RECORDMCOUNT
 
 ifdef CONFIG_STACK_VALIDATION
 ifneq ($(SKIP_STACK_VALIDATION),1)
@@ -389,6 +397,18 @@ $(obj)/%.asn1.c $(obj)/%.asn1.h: $(src)/%.asn1 $(objtree)/scripts/asn1_compiler
 $(subdir-builtin): $(obj)/%/built-in.a: $(obj)/% ;
 $(subdir-modorder): $(obj)/%/modules.order: $(obj)/% ;
 
+# combine symversions for later processing
+quiet_cmd_update_lto_symversions = SYMVER  $@
+ifeq ($(CONFIG_LTO_CLANG) $(CONFIG_MODVERSIONS),y y)
+      cmd_update_lto_symversions =					\
+	rm -f $@.symversions						\
+	$(foreach n, $(filter-out FORCE,$^),				\
+		$(if $(shell test -s $(n).symversions && echo y),	\
+			; cat $(n).symversions >> $@.symversions))
+else
+      cmd_update_lto_symversions = echo >/dev/null
+endif
+
 #
 # Rule to compile a set of .o files into one .a file (without symbol table)
 #
@@ -396,8 +416,11 @@ $(subdir-modorder): $(obj)/%/modules.order: $(obj)/% ;
 quiet_cmd_ar_builtin = AR      $@
       cmd_ar_builtin = rm -f $@; $(AR) cDPrST $@ $(real-prereqs)
 
+quiet_cmd_ar_and_symver = AR      $@
+      cmd_ar_and_symver = $(cmd_update_lto_symversions); $(cmd_ar_builtin)
+
 $(obj)/built-in.a: $(real-obj-y) FORCE
-	$(call if_changed,ar_builtin)
+	$(call if_changed,ar_and_symver)
 
 #
 # Rule to create modules.order file
@@ -417,15 +440,26 @@ $(obj)/modules.order: $(obj-m) FORCE
 #
 # Rule to compile a set of .o files into one .a file (with symbol table)
 #
+quiet_cmd_ar_lib = AR      $@
+      cmd_ar_lib = $(cmd_update_lto_symversions); $(cmd_ar)
+
 $(obj)/lib.a: $(lib-y) FORCE
-	$(call if_changed,ar)
+	$(call if_changed,ar_lib)
 
 # NOTE:
 # Do not replace $(filter %.o,^) with $(real-prereqs). When a single object
 # module is turned into a multi object module, $^ will contain header file
 # dependencies recorded in the .*.cmd file.
+ifdef CONFIG_LTO_CLANG
+quiet_cmd_link_multi-m = AR [M]  $@
+cmd_link_multi-m =						\
+	$(cmd_update_lto_symversions);				\
+	rm -f $@; 						\
+	$(AR) cDPrsT $@ $(filter %.o,$^)
+else
 quiet_cmd_link_multi-m = LD [M]  $@
       cmd_link_multi-m = $(LD) $(ld_flags) -r -o $@ $(filter %.o,$^)
+endif
 
 $(multi-used-m): FORCE
 	$(call if_changed,link_multi-m)
diff --git a/scripts/Makefile.lib b/scripts/Makefile.lib
index 94133708889d7f0357f6b3c59a3f65f61c61b3b4..53aa3e18ce8a8c6cdf14d5481a2ceff0eda8f2ca 100644
--- a/scripts/Makefile.lib
+++ b/scripts/Makefile.lib
@@ -117,9 +117,11 @@ target-stem = $(basename $(patsubst $(obj)/%,%,$@))
 # These flags are needed for modversions and compiling, so we define them here
 # $(modname_flags) defines KBUILD_MODNAME as the name of the module it will
 # end up in (or would, if it gets compiled in)
-name-fix = $(call stringify,$(subst $(comma),_,$(subst -,_,$1)))
+name-fix-token = $(subst $(comma),_,$(subst -,_,$1))
+name-fix = $(call stringify,$(call name-fix-token,$1))
 basename_flags = -DKBUILD_BASENAME=$(call name-fix,$(basetarget))
-modname_flags  = -DKBUILD_MODNAME=$(call name-fix,$(modname))
+modname_flags  = -DKBUILD_MODNAME=$(call name-fix,$(modname)) \
+		 -D__KBUILD_MODNAME=kmod_$(call name-fix-token,$(modname))
 modfile_flags  = -DKBUILD_MODFILE=$(call stringify,$(modfile))
 
 _c_flags       = $(filter-out $(CFLAGS_REMOVE_$(target-stem).o), \
diff --git a/scripts/Makefile.modfinal b/scripts/Makefile.modfinal
index ae01baf96f4e8038583d994df2348a0b53b8a565..c7d1650a48f99fa69a3a530feda1fdad2dfe5521 100644
--- a/scripts/Makefile.modfinal
+++ b/scripts/Makefile.modfinal
@@ -22,13 +22,19 @@ modname = $(notdir $(@:.mod.o=))
 part-of-module = y
 
 quiet_cmd_cc_o_c = CC [M]  $@
-      cmd_cc_o_c = $(CC) $(c_flags) -c -o $@ $<
+      cmd_cc_o_c = $(CC) $(filter-out $(CC_FLAGS_CFI), $(c_flags)) -c -o $@ $<
 
 %.mod.o: %.mod.c FORCE
 	$(call if_changed_dep,cc_o_c)
 
 ARCH_POSTLINK := $(wildcard $(srctree)/arch/$(SRCARCH)/Makefile.postlink)
 
+ifdef CONFIG_LTO_CLANG
+# With CONFIG_LTO_CLANG, reuse the object file we compiled for modpost to
+# avoid a second slow LTO link
+prelink-ext := .lto
+endif
+
 quiet_cmd_ld_ko_o = LD [M]  $@
       cmd_ld_ko_o =                                                     \
 	$(LD) -r $(KBUILD_LDFLAGS)					\
@@ -36,7 +42,7 @@ quiet_cmd_ld_ko_o = LD [M]  $@
 		-T scripts/module.lds -o $@ $(filter %.o, $^);		\
 	$(if $(ARCH_POSTLINK), $(MAKE) -f $(ARCH_POSTLINK) $@, true)
 
-$(modules): %.ko: %.o %.mod.o scripts/module.lds FORCE
+$(modules): %.ko: %$(prelink-ext).o %.mod.o scripts/module.lds FORCE
 	+$(call if_changed,ld_ko_o)
 
 targets += $(modules) $(modules:.ko=.mod.o)
diff --git a/scripts/Makefile.modpost b/scripts/Makefile.modpost
index 12a87be0fb44681c3d7e1e87a85041c91a69c9f4..4ca5579af4e4a4e67f0c4966c2d960663fd9049f 100644
--- a/scripts/Makefile.modpost
+++ b/scripts/Makefile.modpost
@@ -43,6 +43,9 @@ __modpost:
 include include/config/auto.conf
 include scripts/Kbuild.include
 
+# for ld_flags
+include scripts/Makefile.lib
+
 MODPOST = scripts/mod/modpost								\
 	$(if $(CONFIG_MODVERSIONS),-m)							\
 	$(if $(CONFIG_MODULE_SRCVERSION_ALL),-a)					\
@@ -115,12 +118,30 @@ $(input-symdump):
 	@echo >&2 'WARNING: Symbol version dump "$@" is missing.'
 	@echo >&2 '         Modules may not have dependencies or modversions.'
 
+ifdef CONFIG_LTO_CLANG
+# With CONFIG_LTO_CLANG, .o files might be LLVM bitcode, so we need to run
+# LTO to compile them into native code before running modpost
+prelink-ext := .lto
+
+quiet_cmd_cc_lto_link_modules = LTO [M] $@
+cmd_cc_lto_link_modules =						\
+	$(LD) $(ld_flags) -r -o $@					\
+		$(shell [ -s $(@:.lto.o=.o.symversions) ] &&		\
+			echo -T $(@:.lto.o=.o.symversions))		\
+		--whole-archive $^
+
+%.lto.o: %.o
+	$(call if_changed,cc_lto_link_modules)
+endif
+
+modules := $(sort $(shell cat $(MODORDER)))
+
 # Read out modules.order to pass in modpost.
 # Otherwise, allmodconfig would fail with "Argument list too long".
 quiet_cmd_modpost = MODPOST $@
-      cmd_modpost = sed 's/ko$$/o/' $< | $(MODPOST) -T -
+      cmd_modpost = sed 's/\.ko$$/$(prelink-ext)\.o/' $< | $(MODPOST) -T -
 
-$(output-symdump): $(MODORDER) $(input-symdump) FORCE
+$(output-symdump): $(MODORDER) $(input-symdump) $(modules:.ko=$(prelink-ext).o) FORCE
 	$(call if_changed,modpost)
 
 targets += $(output-symdump)
diff --git a/scripts/gen_autoksyms.sh b/scripts/gen_autoksyms.sh
index d54dfba15bf25b2d25692cc8f229f1ace0fe2c03..da320151e7c39cd900dabac81c0ab0202c500bfb 100755
--- a/scripts/gen_autoksyms.sh
+++ b/scripts/gen_autoksyms.sh
@@ -19,7 +19,26 @@ esac
 # We need access to CONFIG_ symbols
 . include/config/auto.conf
 
-ksym_wl=/dev/null
+needed_symbols=
+
+# Special case for modversions (see modpost.c)
+if [ -n "$CONFIG_MODVERSIONS" ]; then
+	needed_symbols="$needed_symbols module_layout"
+fi
+
+# With CONFIG_LTO_CLANG, LLVM bitcode has not yet been compiled into a binary
+# when the .mod files are generated, which means they don't yet contain
+# references to certain symbols that will be present in the final binaries.
+if [ -n "$CONFIG_LTO_CLANG" ]; then
+	# intrinsic functions
+	needed_symbols="$needed_symbols memcpy memmove memset"
+	# ftrace
+	needed_symbols="$needed_symbols _mcount"
+	# stack protector symbols
+	needed_symbols="$needed_symbols __stack_chk_fail __stack_chk_guard"
+fi
+
+ksym_wl=
 if [ -n "$CONFIG_UNUSED_KSYMS_WHITELIST" ]; then
 	# Use 'eval' to expand the whitelist path and check if it is relative
 	eval ksym_wl="$CONFIG_UNUSED_KSYMS_WHITELIST"
@@ -40,16 +59,14 @@ cat > "$output_file" << EOT
 EOT
 
 [ -f modules.order ] && modlist=modules.order || modlist=/dev/null
-sed 's/ko$/mod/' $modlist |
-xargs -n1 sed -n -e '2{s/ /\n/g;/^$/!p;}' -- |
-cat - "$ksym_wl" |
+
+{
+	sed 's/ko$/mod/' $modlist | xargs -n1 sed -n -e '2p'
+	echo "$needed_symbols"
+	[ -n "$ksym_wl" ] && cat "$ksym_wl"
+} | sed -e 's/ /\n/g' | sed -n -e '/^$/!p' |
 # Remove the dot prefix for ppc64; symbol names with a dot (.) hold entry
 # point addresses.
 sed -e 's/^\.//' |
 sort -u |
 sed -e 's/\(.*\)/#define __KSYM_\1 1/' >> "$output_file"
-
-# Special case for modversions (see modpost.c)
-if [ -n "$CONFIG_MODVERSIONS" ]; then
-	echo "#define __KSYM_module_layout 1" >> "$output_file"
-fi
diff --git a/scripts/generate_initcall_order.pl b/scripts/generate_initcall_order.pl
new file mode 100755
index 0000000000000000000000000000000000000000..1a88d3f1b91339b7c832ef72919b4501415c1fed
--- /dev/null
+++ b/scripts/generate_initcall_order.pl
@@ -0,0 +1,270 @@
+#!/usr/bin/env perl
+# SPDX-License-Identifier: GPL-2.0
+#
+# Generates a linker script that specifies the correct initcall order.
+#
+# Copyright (C) 2019 Google LLC
+
+use strict;
+use warnings;
+use IO::Handle;
+use IO::Select;
+use POSIX ":sys_wait_h";
+
+my $nm = $ENV{'NM'} || die "$0: ERROR: NM not set?";
+my $objtree = $ENV{'objtree'} || '.';
+
+## currently active child processes
+my $jobs = {};		# child process pid -> file handle
+## results from child processes
+my $results = {};	# object index -> [ { level, secname }, ... ]
+
+## reads _NPROCESSORS_ONLN to determine the maximum number of processes to
+## start
+sub get_online_processors {
+	open(my $fh, "getconf _NPROCESSORS_ONLN 2>/dev/null |")
+		or die "$0: ERROR: failed to execute getconf: $!";
+	my $procs = <$fh>;
+	close($fh);
+
+	if (!($procs =~ /^\d+$/)) {
+		return 1;
+	}
+
+	return int($procs);
+}
+
+## writes results to the parent process
+## format: <file index> <initcall level> <base initcall section name>
+sub write_results {
+	my ($index, $initcalls) = @_;
+
+	# sort by the counter value to ensure the order of initcalls within
+	# each object file is correct
+	foreach my $counter (sort { $a <=> $b } keys(%{$initcalls})) {
+		my $level = $initcalls->{$counter}->{'level'};
+
+		# section name for the initcall function
+		my $secname = $initcalls->{$counter}->{'module'} . '__' .
+			      $counter . '_' .
+			      $initcalls->{$counter}->{'line'} . '_' .
+			      $initcalls->{$counter}->{'function'};
+
+		print "$index $level $secname\n";
+	}
+}
+
+## reads a result line from a child process and adds it to the $results array
+sub read_results{
+	my ($fh) = @_;
+
+	# each child prints out a full line w/ autoflush and exits after the
+	# last line, so even if buffered I/O blocks here, it shouldn't block
+	# very long
+	my $data = <$fh>;
+
+	if (!defined($data)) {
+		return 0;
+	}
+
+	chomp($data);
+
+	my ($index, $level, $secname) = $data =~
+		/^(\d+)\ ([^\ ]+)\ (.*)$/;
+
+	if (!defined($index) ||
+		!defined($level) ||
+		!defined($secname)) {
+		die "$0: ERROR: child process returned invalid data: $data\n";
+	}
+
+	$index = int($index);
+
+	if (!exists($results->{$index})) {
+		$results->{$index} = [];
+	}
+
+	push (@{$results->{$index}}, {
+		'level'   => $level,
+		'secname' => $secname
+	});
+
+	return 1;
+}
+
+## finds initcalls from an object file or all object files in an archive, and
+## writes results back to the parent process
+sub find_initcalls {
+	my ($index, $file) = @_;
+
+	die "$0: ERROR: file $file doesn't exist?" if (! -f $file);
+
+	open(my $fh, "\"$nm\" --defined-only \"$file\" 2>/dev/null |")
+		or die "$0: ERROR: failed to execute \"$nm\": $!";
+
+	my $initcalls = {};
+
+	while (<$fh>) {
+		chomp;
+
+		# check for the start of a new object file (if processing an
+		# archive)
+		my ($path)= $_ =~ /^(.+)\:$/;
+
+		if (defined($path)) {
+			write_results($index, $initcalls);
+			$initcalls = {};
+			next;
+		}
+
+		# look for an initcall
+		my ($module, $counter, $line, $symbol) = $_ =~
+			/[a-z]\s+__initcall__(\S*)__(\d+)_(\d+)_(.*)$/;
+
+		if (!defined($module)) {
+			$module = ''
+		}
+
+		if (!defined($counter) ||
+			!defined($line) ||
+			!defined($symbol)) {
+			next;
+		}
+
+		# parse initcall level
+		my ($function, $level) = $symbol =~
+			/^(.*)((early|rootfs|con|[0-9])s?)$/;
+
+		die "$0: ERROR: invalid initcall name $symbol in $file($path)"
+			if (!defined($function) || !defined($level));
+
+		$initcalls->{$counter} = {
+			'module'   => $module,
+			'line'     => $line,
+			'function' => $function,
+			'level'    => $level,
+		};
+	}
+
+	close($fh);
+	write_results($index, $initcalls);
+}
+
+## waits for any child process to complete, reads the results, and adds them to
+## the $results array for later processing
+sub wait_for_results {
+	my ($select) = @_;
+
+	my $pid = 0;
+	do {
+		# unblock children that may have a full write buffer
+		foreach my $fh ($select->can_read(0)) {
+			read_results($fh);
+		}
+
+		# check for children that have exited, read the remaining data
+		# from them, and clean up
+		$pid = waitpid(-1, WNOHANG);
+		if ($pid > 0) {
+			if (!exists($jobs->{$pid})) {
+				next;
+			}
+
+			my $fh = $jobs->{$pid};
+			$select->remove($fh);
+
+			while (read_results($fh)) {
+				# until eof
+			}
+
+			close($fh);
+			delete($jobs->{$pid});
+		}
+	} while ($pid > 0);
+}
+
+## forks a child to process each file passed in the command line and collects
+## the results
+sub process_files {
+	my $index = 0;
+	my $njobs = $ENV{'PARALLELISM'} || get_online_processors();
+	my $select = IO::Select->new();
+
+	while (my $file = shift(@ARGV)) {
+		# fork a child process and read it's stdout
+		my $pid = open(my $fh, '-|');
+
+		if (!defined($pid)) {
+			die "$0: ERROR: failed to fork: $!";
+		} elsif ($pid) {
+			# save the child process pid and the file handle
+			$select->add($fh);
+			$jobs->{$pid} = $fh;
+		} else {
+			# in the child process
+			STDOUT->autoflush(1);
+			find_initcalls($index, "$objtree/$file");
+			exit;
+		}
+
+		$index++;
+
+		# limit the number of children to $njobs
+		if (scalar(keys(%{$jobs})) >= $njobs) {
+			wait_for_results($select);
+		}
+	}
+
+	# wait for the remaining children to complete
+	while (scalar(keys(%{$jobs})) > 0) {
+		wait_for_results($select);
+	}
+}
+
+sub generate_initcall_lds() {
+	process_files();
+
+	my $sections = {};	# level -> [ secname, ...]
+
+	# sort results to retain link order and split to sections per
+	# initcall level
+	foreach my $index (sort { $a <=> $b } keys(%{$results})) {
+		foreach my $result (@{$results->{$index}}) {
+			my $level = $result->{'level'};
+
+			if (!exists($sections->{$level})) {
+				$sections->{$level} = [];
+			}
+
+			push(@{$sections->{$level}}, $result->{'secname'});
+		}
+	}
+
+	die "$0: ERROR: no initcalls?" if (!keys(%{$sections}));
+
+	# print out a linker script that defines the order of initcalls for
+	# each level
+	print "SECTIONS {\n";
+
+	foreach my $level (sort(keys(%{$sections}))) {
+		my $section;
+
+		if ($level eq 'con') {
+			$section = '.con_initcall.init';
+		} else {
+			$section = ".initcall${level}.init";
+		}
+
+		print "\t${section} : {\n";
+
+		foreach my $secname (@{$sections->{$level}}) {
+			print "\t\t*(${section}..${secname}) ;\n";
+		}
+
+		print "\t}\n";
+	}
+
+	print "}\n";
+}
+
+generate_initcall_lds();
diff --git a/scripts/link-vmlinux.sh b/scripts/link-vmlinux.sh
index 6eded325c8378c8cff94c379a180060c0b154ec4..4ad9fbddf9d53c5ee8197baeed40575bc42fa974 100755
--- a/scripts/link-vmlinux.sh
+++ b/scripts/link-vmlinux.sh
@@ -43,11 +43,37 @@ info()
 	fi
 }
 
+# Generate a linker script to ensure correct ordering of initcalls.
+gen_initcalls()
+{
+	info GEN .tmp_initcalls.lds
+
+	${PYTHON3} ${srctree}/scripts/jobserver-exec		\
+	${PERL} ${srctree}/scripts/generate_initcall_order.pl	\
+		${KBUILD_VMLINUX_OBJS} ${KBUILD_VMLINUX_LIBS}	\
+		> .tmp_initcalls.lds
+}
+
+# If CONFIG_LTO_CLANG is selected, collect generated symbol versions into
+# .tmp_symversions.lds
+gen_symversions()
+{
+	info GEN .tmp_symversions.lds
+	rm -f .tmp_symversions.lds
+
+	for o in ${KBUILD_VMLINUX_OBJS} ${KBUILD_VMLINUX_LIBS}; do
+		if [ -f ${o}.symversions ]; then
+			cat ${o}.symversions >> .tmp_symversions.lds
+		fi
+	done
+}
+
 # Link of vmlinux.o used for section mismatch analysis
 # ${1} output file
 modpost_link()
 {
 	local objects
+	local lds=""
 
 	objects="--whole-archive				\
 		${KBUILD_VMLINUX_OBJS}				\
@@ -56,7 +82,23 @@ modpost_link()
 		${KBUILD_VMLINUX_LIBS}				\
 		--end-group"
 
-	${LD} ${KBUILD_LDFLAGS} -r -o ${1} ${objects}
+	if [ -n "${CONFIG_LTO_CLANG}" ]; then
+		gen_initcalls
+		lds="-T .tmp_initcalls.lds"
+
+		if [ -n "${CONFIG_MODVERSIONS}" ]; then
+			gen_symversions
+			lds="${lds} -T .tmp_symversions.lds"
+		fi
+
+		# This might take a while, so indicate that we're doing
+		# an LTO link
+		info LTO ${1}
+	else
+		info LD ${1}
+	fi
+
+	${LD} ${KBUILD_LDFLAGS} -r -o ${1} ${lds} ${objects}
 }
 
 objtool_link()
@@ -103,13 +145,22 @@ vmlinux_link()
 	fi
 
 	if [ "${SRCARCH}" != "um" ]; then
-		objects="--whole-archive			\
-			${KBUILD_VMLINUX_OBJS}			\
-			--no-whole-archive			\
-			--start-group				\
-			${KBUILD_VMLINUX_LIBS}			\
-			--end-group				\
-			${@}"
+		if [ -n "${CONFIG_LTO_CLANG}" ]; then
+			# Use vmlinux.o instead of performing the slow LTO
+			# link again.
+			objects="--whole-archive		\
+				vmlinux.o 			\
+				--no-whole-archive		\
+				${@}"
+		else
+			objects="--whole-archive		\
+				${KBUILD_VMLINUX_OBJS}		\
+				--no-whole-archive		\
+				--start-group			\
+				${KBUILD_VMLINUX_LIBS}		\
+				--end-group			\
+				${@}"
+		fi
 
 		${LD} ${KBUILD_LDFLAGS} ${LDFLAGS_vmlinux}	\
 			${strip_debug#-Wl,}			\
@@ -225,6 +276,8 @@ cleanup()
 {
 	rm -f .btf.*
 	rm -f .tmp_System.map
+	rm -f .tmp_initcalls.lds
+	rm -f .tmp_symversions.lds
 	rm -f .tmp_vmlinux*
 	rm -f System.map
 	rm -f vmlinux
@@ -274,7 +327,6 @@ fi;
 ${MAKE} -f "${srctree}/scripts/Makefile.build" obj=init need-builtin=1
 
 #link vmlinux.o
-info LD vmlinux.o
 modpost_link vmlinux.o
 objtool_link vmlinux.o
 
diff --git a/scripts/mod/Makefile b/scripts/mod/Makefile
index 78071681d924225d7b6083de13c7c58b031fe07d..c9e38ad937fd4549ceb716e05067f0339005ee56 100644
--- a/scripts/mod/Makefile
+++ b/scripts/mod/Makefile
@@ -1,5 +1,6 @@
 # SPDX-License-Identifier: GPL-2.0
 OBJECT_FILES_NON_STANDARD := y
+CFLAGS_REMOVE_empty.o += $(CC_FLAGS_LTO)
 
 hostprogs-always-y	+= modpost mk_elfconfig
 always-y		+= empty.o
diff --git a/scripts/mod/modpost.c b/scripts/mod/modpost.c
index e08f75aed4293335aee5382a606b27bb08f85488..34aa32c698275c66528b55f2709d7483050bbc4d 100644
--- a/scripts/mod/modpost.c
+++ b/scripts/mod/modpost.c
@@ -80,14 +80,6 @@ modpost_log(enum loglevel loglevel, const char *fmt, ...)
 		exit(1);
 }
 
-static inline bool strends(const char *str, const char *postfix)
-{
-	if (strlen(str) < strlen(postfix))
-		return false;
-
-	return strcmp(str + strlen(str) - strlen(postfix), postfix) == 0;
-}
-
 void *do_nofail(void *ptr, const char *expr)
 {
 	if (!ptr)
@@ -1984,6 +1976,10 @@ static char *remove_dot(char *s)
 		size_t m = strspn(s + n + 1, "0123456789");
 		if (m && (s[n + m] == '.' || s[n + m] == 0))
 			s[n] = 0;
+
+		/* strip trailing .lto */
+		if (strends(s, ".lto"))
+			s[strlen(s) - 4] = '\0';
 	}
 	return s;
 }
@@ -2007,6 +2003,9 @@ static void read_symbols(const char *modname)
 		/* strip trailing .o */
 		tmp = NOFAIL(strdup(modname));
 		tmp[strlen(tmp) - 2] = '\0';
+		/* strip trailing .lto */
+		if (strends(tmp, ".lto"))
+			tmp[strlen(tmp) - 4] = '\0';
 		mod = new_module(tmp);
 		free(tmp);
 	}
diff --git a/scripts/mod/modpost.h b/scripts/mod/modpost.h
index 3aa052722233b59376f16b7007ed44bc59b21cc8..fab30d201f9e4e8cef5ad42e8cd7095bdfcb5879 100644
--- a/scripts/mod/modpost.h
+++ b/scripts/mod/modpost.h
@@ -2,6 +2,7 @@
 #include <stdio.h>
 #include <stdlib.h>
 #include <stdarg.h>
+#include <stdbool.h>
 #include <string.h>
 #include <sys/types.h>
 #include <sys/stat.h>
@@ -180,6 +181,14 @@ static inline unsigned int get_secindex(const struct elf_info *info,
 	return info->symtab_shndx_start[sym - info->symtab_start];
 }
 
+static inline bool strends(const char *str, const char *postfix)
+{
+	if (strlen(str) < strlen(postfix))
+		return false;
+
+	return strcmp(str + strlen(str) - strlen(postfix), postfix) == 0;
+}
+
 /* file2alias.c */
 extern unsigned int cross_build;
 void handle_moddevtable(struct module *mod, struct elf_info *info,
diff --git a/scripts/mod/sumversion.c b/scripts/mod/sumversion.c
index d587f40f11177ddb81f724757809c633b77195e5..760e6baa7eda0d2583e25db792caf2053fad222f 100644
--- a/scripts/mod/sumversion.c
+++ b/scripts/mod/sumversion.c
@@ -391,10 +391,14 @@ void get_src_version(const char *modname, char sum[], unsigned sumlen)
 	struct md4_ctx md;
 	char *fname;
 	char filelist[PATH_MAX + 1];
+	int postfix_len = 1;
+
+	if (strends(modname, ".lto.o"))
+		postfix_len = 5;
 
 	/* objects for a module are listed in the first line of *.mod file. */
 	snprintf(filelist, sizeof(filelist), "%.*smod",
-		 (int)strlen(modname) - 1, modname);
+		 (int)strlen(modname) - postfix_len, modname);
 
 	buf = read_text_file(filelist);
 
diff --git a/scripts/module.lds.S b/scripts/module.lds.S
index 088a5a2c446d24058ec116ffe2273acb168ac6a0..1c77d9356c20c5ed30a04076b51ff0dae27dc944 100644
--- a/scripts/module.lds.S
+++ b/scripts/module.lds.S
@@ -3,11 +3,21 @@
  * Archs are free to supply their own linker scripts.  ld will
  * combine them automatically.
  */
+#ifdef CONFIG_CFI_CLANG
+# include <asm/page.h>
+# define ALIGN_CFI 		ALIGN(PAGE_SIZE)
+# define SANITIZER_DISCARDS	*(.eh_frame)
+#else
+# define ALIGN_CFI
+# define SANITIZER_DISCARDS
+#endif
+
 SECTIONS {
 	/DISCARD/ : {
 		*(.discard)
 		*(.discard.*)
 		*(*.discard.*)
+		SANITIZER_DISCARDS
 	}
 
 	__ksymtab		0 : { *(SORT(___ksymtab+*)) }
@@ -24,6 +34,39 @@ SECTIONS {
 	.init_array		0 : ALIGN(8) { *(SORT(.init_array.*)) *(.init_array) }
 
 	__jump_table		0 : ALIGN(8) { KEEP(*(__jump_table)) }
+
+	__patchable_function_entries : { *(__patchable_function_entries) }
+
+#ifdef CONFIG_LTO_CLANG
+	/*
+	 * With CONFIG_LTO_CLANG, LLD always enables -fdata-sections and
+	 * -ffunction-sections, which increases the size of the final module.
+	 * Merge the split sections in the final binary.
+	 */
+	.bss : {
+		*(.bss .bss.[0-9a-zA-Z_]*)
+		*(.bss..L*)
+	}
+
+	.data : {
+		*(.data .data.[0-9a-zA-Z_]*)
+		*(.data..L*)
+	}
+
+	.rodata : {
+		*(.rodata .rodata.[0-9a-zA-Z_]*)
+		*(.rodata..L*)
+	}
+
+	/*
+	 * With CONFIG_CFI_CLANG, we assume __cfi_check is at the beginning
+	 * of the .text section, and is aligned to PAGE_SIZE.
+	 */
+	.text : ALIGN_CFI {
+		*(.text.__cfi_check)
+		*(.text .text.[0-9a-zA-Z_]* .text..L.cfi*)
+	}
+#endif
 }
 
 /* bring in arch-specific sections */