Merge tag 'clang-lto-v5.12-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/kees/linux

Pull clang LTO updates from Kees Cook:
 "Clang Link Time Optimization.

  This is built on the work done preparing for LTO by arm64 folks,
  tracing folks, etc. This includes the core changes as well as the
  remaining pieces for arm64 (LTO has been the default build method on
  Android for about 3 years now, as it is the prerequisite for the
  Control Flow Integrity protections).

  While x86 LTO enablement is done, it depends on some pending objtool
  clean-ups. It's possible that I'll send a "part 2" pull request for
  LTO that includes x86 support.

  For merge log posterity, and as detailed in commit dc5723b02e52
  ("kbuild: add support for Clang LTO"), here is the lt;dr to do an LTO
  build:

        make LLVM=1 LLVM_IAS=1 defconfig
        scripts/config -e LTO_CLANG_THIN
        make LLVM=1 LLVM_IAS=1

  (To do a cross-compile of arm64, add "CROSS_COMPILE=aarch64-linux-gnu-"
  and "ARCH=arm64" to the "make" command lines.)

  Summary:

   - Clang LTO build infrastructure and arm64-specific enablement (Sami
     Tolvanen)

   - Recursive build CC_FLAGS_LTO fix (Alexander Lobakin)"

* tag 'clang-lto-v5.12-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/kees/linux:
  kbuild: prevent CC_FLAGS_LTO self-bloating on recursive rebuilds
  arm64: allow LTO to be selected
  arm64: disable recordmcount with DYNAMIC_FTRACE_WITH_REGS
  arm64: vdso: disable LTO
  drivers/misc/lkdtm: disable LTO for rodata.o
  efi/libstub: disable LTO
  scripts/mod: disable LTO for empty.c
  modpost: lto: strip .lto from module names
  PCI: Fix PREL32 relocations for LTO
  init: lto: fix PREL32 relocations
  init: lto: ensure initcall ordering
  kbuild: lto: add a default list of used symbols
  kbuild: lto: merge module sections
  kbuild: lto: limit inlining
  kbuild: lto: fix module versioning
  kbuild: add support for Clang LTO
  tracing: move function tracer options to Kconfig

3 files changed, 99 insertions, 12 deletions

diff --git a/include/asm-generic/vmlinux.lds.h b/include/asm-generic/vmlinux.lds.h
index 01a3fd6a64d2..d4bddfe75e4a 100644
--- a/include/asm-generic/vmlinux.lds.h
+++ b/include/asm-generic/vmlinux.lds.h
@@ -90,10 +90,13 @@
  * .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..L* .data..compoundliteral* .data.$__unnamed_* .data.$Lubsan_*
 #define SDATA_MAIN .sdata .sdata.[0-9a-zA-Z_]*
diff --git a/include/linux/init.h b/include/linux/init.h
index e668832ef66a..a01f01c1a5c5 100644
--- a/include/linux/init.h
+++ b/include/linux/init.h
@@ -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 __stub(void);				\
+	int __init __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/pci.h b/include/linux/pci.h
index 53f4904ee83d..86c799c97b77 100644
--- a/include/linux/pci.h
+++ b/include/linux/pci.h
@@ -1926,7 +1926,7 @@ 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"	\
@@ -1935,10 +1935,33 @@ 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 stub(struct pci_dev *dev);					\
+	void 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,	\