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

Pull livepatching updates from Jiri Kosina:

 - simplifications and improvements for issues Peter Ziljstra found
   during his previous work on W^X cleanups.

   This allows us to remove livepatch arch-specific .klp.arch sections
   and add proper support for jump labels in patched code.

   Also, this patchset removes the last module_disable_ro() usage in the
   tree.

   Patches from Josh Poimboeuf and Peter Zijlstra

 - a few other minor cleanups

* 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/livepatching/livepatching:
  MAINTAINERS: add lib/livepatch to LIVE PATCHING
  livepatch: add arch-specific headers to MAINTAINERS
  livepatch: Make klp_apply_object_relocs static
  MAINTAINERS: adjust to livepatch .klp.arch removal
  module: Make module_enable_ro() static again
  x86/module: Use text_mutex in apply_relocate_add()
  module: Remove module_disable_ro()
  livepatch: Remove module_disable_ro() usage
  x86/module: Use text_poke() for late relocations
  s390/module: Use s390_kernel_write() for late relocations
  s390: Change s390_kernel_write() return type to match memcpy()
  livepatch: Prevent module-specific KLP rela sections from referencing vmlinux symbols
  livepatch: Remove .klp.arch
  livepatch: Apply vmlinux-specific KLP relocations early
  livepatch: Disallow vmlinux.ko

13 files changed, 283 insertions, 236 deletions

diff --git a/Documentation/livepatch/module-elf-format.rst b/Documentation/livepatch/module-elf-format.rst
index 2a591e6f8e6c..8c6b894c4661 100644
--- a/Documentation/livepatch/module-elf-format.rst
+++ b/Documentation/livepatch/module-elf-format.rst
@@ -14,8 +14,7 @@ This document outlines the Elf format requirements that livepatch modules must f
    4. Livepatch symbols
       4.1 A livepatch module's symbol table
       4.2 Livepatch symbol format
-   5. Architecture-specific sections
-   6. Symbol table and Elf section access
+   5. Symbol table and Elf section access
 
 1. Background and motivation
 ============================
@@ -298,17 +297,7 @@ Examples:
   Note that the 'Ndx' (Section index) for these symbols is SHN_LIVEPATCH (0xff20).
   "OS" means OS-specific.
 
-5. Architecture-specific sections
-=================================
-Architectures may override arch_klp_init_object_loaded() to perform
-additional arch-specific tasks when a target module loads, such as applying
-arch-specific sections. On x86 for example, we must apply per-object
-.altinstructions and .parainstructions sections when a target module loads.
-These sections must be prefixed with ".klp.arch.$objname." so that they can
-be easily identified when iterating through a patch module's Elf sections
-(See arch/x86/kernel/livepatch.c for a complete example).
-
-6. Symbol table and Elf section access
+5. Symbol table and Elf section access
 ======================================
 A livepatch module's symbol table is accessible through module->symtab.
 
diff --git a/MAINTAINERS b/MAINTAINERS
index 465210f17948..02cbbe88b65f 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -9936,10 +9936,12 @@ S:	Maintained
 T:	git git://git.kernel.org/pub/scm/linux/kernel/git/livepatching/livepatching.git
 F:	Documentation/ABI/testing/sysfs-kernel-livepatch
 F:	Documentation/livepatch/
+F:	arch/powerpc/include/asm/livepatch.h
+F:	arch/s390/include/asm/livepatch.h
 F:	arch/x86/include/asm/livepatch.h
-F:	arch/x86/kernel/livepatch.c
 F:	include/linux/livepatch.h
 F:	kernel/livepatch/
+F:	lib/livepatch/
 F:	samples/livepatch/
 F:	tools/testing/selftests/livepatch/
 
diff --git a/arch/s390/include/asm/uaccess.h b/arch/s390/include/asm/uaccess.h
index a470f1fa9f2a..324438889fe1 100644
--- a/arch/s390/include/asm/uaccess.h
+++ b/arch/s390/include/asm/uaccess.h
@@ -276,6 +276,6 @@ static inline unsigned long __must_check clear_user(void __user *to, unsigned lo
 }
 
 int copy_to_user_real(void __user *dest, void *src, unsigned long count);
-void s390_kernel_write(void *dst, const void *src, size_t size);
+void *s390_kernel_write(void *dst, const void *src, size_t size);
 
 #endif /* __S390_UACCESS_H */
diff --git a/arch/s390/kernel/module.c b/arch/s390/kernel/module.c
index ba8f19bb438b..4055f1c49814 100644
--- a/arch/s390/kernel/module.c
+++ b/arch/s390/kernel/module.c
@@ -19,6 +19,7 @@
 #include <linux/kasan.h>
 #include <linux/moduleloader.h>
 #include <linux/bug.h>
+#include <linux/memory.h>
 #include <asm/alternative.h>
 #include <asm/nospec-branch.h>
 #include <asm/facility.h>
@@ -174,10 +175,12 @@ int module_frob_arch_sections(Elf_Ehdr *hdr, Elf_Shdr *sechdrs,
 }
 
 static int apply_rela_bits(Elf_Addr loc, Elf_Addr val,
-			   int sign, int bits, int shift)
+			   int sign, int bits, int shift,
+			   void *(*write)(void *dest, const void *src, size_t len))
 {
 	unsigned long umax;
 	long min, max;
+	void *dest = (void *)loc;
 
 	if (val & ((1UL << shift) - 1))
 		return -ENOEXEC;
@@ -194,26 +197,33 @@ static int apply_rela_bits(Elf_Addr loc, Elf_Addr val,
 			return -ENOEXEC;
 	}
 
-	if (bits == 8)
-		*(unsigned char *) loc = val;
-	else if (bits == 12)
-		*(unsigned short *) loc = (val & 0xfff) |
+	if (bits == 8) {
+		unsigned char tmp = val;
+		write(dest, &tmp, 1);
+	} else if (bits == 12) {
+		unsigned short tmp = (val & 0xfff) |
 			(*(unsigned short *) loc & 0xf000);
-	else if (bits == 16)
-		*(unsigned short *) loc = val;
-	else if (bits == 20)
-		*(unsigned int *) loc = (val & 0xfff) << 16 |
-			(val & 0xff000) >> 4 |
-			(*(unsigned int *) loc & 0xf00000ff);
-	else if (bits == 32)
-		*(unsigned int *) loc = val;
-	else if (bits == 64)
-		*(unsigned long *) loc = val;
+		write(dest, &tmp, 2);
+	} else if (bits == 16) {
+		unsigned short tmp = val;
+		write(dest, &tmp, 2);
+	} else if (bits == 20) {
+		unsigned int tmp = (val & 0xfff) << 16 |
+			(val & 0xff000) >> 4 | (*(unsigned int *) loc & 0xf00000ff);
+		write(dest, &tmp, 4);
+	} else if (bits == 32) {
+		unsigned int tmp = val;
+		write(dest, &tmp, 4);
+	} else if (bits == 64) {
+		unsigned long tmp = val;
+		write(dest, &tmp, 8);
+	}
 	return 0;
 }
 
 static int apply_rela(Elf_Rela *rela, Elf_Addr base, Elf_Sym *symtab,
-		      const char *strtab, struct module *me)
+		      const char *strtab, struct module *me,
+		      void *(*write)(void *dest, const void *src, size_t len))
 {
 	struct mod_arch_syminfo *info;
 	Elf_Addr loc, val;
@@ -241,17 +251,17 @@ static int apply_rela(Elf_Rela *rela, Elf_Addr base, Elf_Sym *symtab,
 	case R_390_64:		/* Direct 64 bit.  */
 		val += rela->r_addend;
 		if (r_type == R_390_8)
-			rc = apply_rela_bits(loc, val, 0, 8, 0);
+			rc = apply_rela_bits(loc, val, 0, 8, 0, write);
 		else if (r_type == R_390_12)
-			rc = apply_rela_bits(loc, val, 0, 12, 0);
+			rc = apply_rela_bits(loc, val, 0, 12, 0, write);
 		else if (r_type == R_390_16)
-			rc = apply_rela_bits(loc, val, 0, 16, 0);
+			rc = apply_rela_bits(loc, val, 0, 16, 0, write);
 		else if (r_type == R_390_20)
-			rc = apply_rela_bits(loc, val, 1, 20, 0);
+			rc = apply_rela_bits(loc, val, 1, 20, 0, write);
 		else if (r_type == R_390_32)
-			rc = apply_rela_bits(loc, val, 0, 32, 0);
+			rc = apply_rela_bits(loc, val, 0, 32, 0, write);
 		else if (r_type == R_390_64)
-			rc = apply_rela_bits(loc, val, 0, 64, 0);
+			rc = apply_rela_bits(loc, val, 0, 64, 0, write);
 		break;
 	case R_390_PC16:	/* PC relative 16 bit.  */
 	case R_390_PC16DBL:	/* PC relative 16 bit shifted by 1.  */
@@ -260,15 +270,15 @@ static int apply_rela(Elf_Rela *rela, Elf_Addr base, Elf_Sym *symtab,
 	case R_390_PC64:	/* PC relative 64 bit.	*/
 		val += rela->r_addend - loc;
 		if (r_type == R_390_PC16)
-			rc = apply_rela_bits(loc, val, 1, 16, 0);
+			rc = apply_rela_bits(loc, val, 1, 16, 0, write);
 		else if (r_type == R_390_PC16DBL)
-			rc = apply_rela_bits(loc, val, 1, 16, 1);
+			rc = apply_rela_bits(loc, val, 1, 16, 1, write);
 		else if (r_type == R_390_PC32DBL)
-			rc = apply_rela_bits(loc, val, 1, 32, 1);
+			rc = apply_rela_bits(loc, val, 1, 32, 1, write);
 		else if (r_type == R_390_PC32)
-			rc = apply_rela_bits(loc, val, 1, 32, 0);
+			rc = apply_rela_bits(loc, val, 1, 32, 0, write);
 		else if (r_type == R_390_PC64)
-			rc = apply_rela_bits(loc, val, 1, 64, 0);
+			rc = apply_rela_bits(loc, val, 1, 64, 0, write);
 		break;
 	case R_390_GOT12:	/* 12 bit GOT offset.  */
 	case R_390_GOT16:	/* 16 bit GOT offset.  */
@@ -283,33 +293,33 @@ static int apply_rela(Elf_Rela *rela, Elf_Addr base, Elf_Sym *symtab,
 	case R_390_GOTPLT64:	/* 64 bit offset to jump slot.	*/
 	case R_390_GOTPLTENT:	/* 32 bit rel. offset to jump slot >> 1. */
 		if (info->got_initialized == 0) {
-			Elf_Addr *gotent;
+			Elf_Addr *gotent = me->core_layout.base +
+					   me->arch.got_offset +
+					   info->got_offset;
 
-			gotent = me->core_layout.base + me->arch.got_offset +
-				info->got_offset;
-			*gotent = val;
+			write(gotent, &val, sizeof(*gotent));
 			info->got_initialized = 1;
 		}
 		val = info->got_offset + rela->r_addend;
 		if (r_type == R_390_GOT12 ||
 		    r_type == R_390_GOTPLT12)
-			rc = apply_rela_bits(loc, val, 0, 12, 0);
+			rc = apply_rela_bits(loc, val, 0, 12, 0, write);
 		else if (r_type == R_390_GOT16 ||
 			 r_type == R_390_GOTPLT16)
-			rc = apply_rela_bits(loc, val, 0, 16, 0);
+			rc = apply_rela_bits(loc, val, 0, 16, 0, write);
 		else if (r_type == R_390_GOT20 ||
 			 r_type == R_390_GOTPLT20)
-			rc = apply_rela_bits(loc, val, 1, 20, 0);
+			rc = apply_rela_bits(loc, val, 1, 20, 0, write);
 		else if (r_type == R_390_GOT32 ||
 			 r_type == R_390_GOTPLT32)
-			rc = apply_rela_bits(loc, val, 0, 32, 0);
+			rc = apply_rela_bits(loc, val, 0, 32, 0, write);
 		else if (r_type == R_390_GOT64 ||
 			 r_type == R_390_GOTPLT64)
-			rc = apply_rela_bits(loc, val, 0, 64, 0);
+			rc = apply_rela_bits(loc, val, 0, 64, 0, write);
 		else if (r_type == R_390_GOTENT ||
 			 r_type == R_390_GOTPLTENT) {
 			val += (Elf_Addr) me->core_layout.base - loc;
-			rc = apply_rela_bits(loc, val, 1, 32, 1);
+			rc = apply_rela_bits(loc, val, 1, 32, 1, write);
 		}
 		break;
 	case R_390_PLT16DBL:	/* 16 bit PC rel. PLT shifted by 1.  */
@@ -320,25 +330,29 @@ static int apply_rela(Elf_Rela *rela, Elf_Addr base, Elf_Sym *symtab,
 	case R_390_PLTOFF32:	/* 32 bit offset from GOT to PLT. */
 	case R_390_PLTOFF64:	/* 16 bit offset from GOT to PLT. */
 		if (info->plt_initialized == 0) {
-			unsigned int *ip;
-			ip = me->core_layout.base + me->arch.plt_offset +
-				info->plt_offset;
-			ip[0] = 0x0d10e310;	/* basr 1,0  */
-			ip[1] = 0x100a0004;	/* lg	1,10(1) */
+			unsigned int insn[5];
+			unsigned int *ip = me->core_layout.base +
+					   me->arch.plt_offset +
+					   info->plt_offset;
+
+			insn[0] = 0x0d10e310;	/* basr 1,0  */
+			insn[1] = 0x100a0004;	/* lg	1,10(1) */
 			if (IS_ENABLED(CONFIG_EXPOLINE) && !nospec_disable) {
 				unsigned int *ij;
 				ij = me->core_layout.base +
 					me->arch.plt_offset +
 					me->arch.plt_size - PLT_ENTRY_SIZE;
-				ip[2] = 0xa7f40000 +	/* j __jump_r1 */
+				insn[2] = 0xa7f40000 +	/* j __jump_r1 */
 					(unsigned int)(u16)
 					(((unsigned long) ij - 8 -
 					  (unsigned long) ip) / 2);
 			} else {
-				ip[2] = 0x07f10000;	/* br %r1 */
+				insn[2] = 0x07f10000;	/* br %r1 */
 			}
-			ip[3] = (unsigned int) (val >> 32);
-			ip[4] = (unsigned int) val;
+			insn[3] = (unsigned int) (val >> 32);
+			insn[4] = (unsigned int) val;
+
+			write(ip, insn, sizeof(insn));
 			info->plt_initialized = 1;
 		}
 		if (r_type == R_390_PLTOFF16 ||
@@ -357,17 +371,17 @@ static int apply_rela(Elf_Rela *rela, Elf_Addr base, Elf_Sym *symtab,
 			val += rela->r_addend - loc;
 		}
 		if (r_type == R_390_PLT16DBL)
-			rc = apply_rela_bits(loc, val, 1, 16, 1);
+			rc = apply_rela_bits(loc, val, 1, 16, 1, write);
 		else if (r_type == R_390_PLTOFF16)
-			rc = apply_rela_bits(loc, val, 0, 16, 0);
+			rc = apply_rela_bits(loc, val, 0, 16, 0, write);
 		else if (r_type == R_390_PLT32DBL)
-			rc = apply_rela_bits(loc, val, 1, 32, 1);
+			rc = apply_rela_bits(loc, val, 1, 32, 1, write);
 		else if (r_type == R_390_PLT32 ||
 			 r_type == R_390_PLTOFF32)
-			rc = apply_rela_bits(loc, val, 0, 32, 0);
+			rc = apply_rela_bits(loc, val, 0, 32, 0, write);
 		else if (r_type == R_390_PLT64 ||
 			 r_type == R_390_PLTOFF64)
-			rc = apply_rela_bits(loc, val, 0, 64, 0);
+			rc = apply_rela_bits(loc, val, 0, 64, 0, write);
 		break;
 	case R_390_GOTOFF16:	/* 16 bit offset to GOT.  */
 	case R_390_GOTOFF32:	/* 32 bit offset to GOT.  */
@@ -375,20 +389,20 @@ static int apply_rela(Elf_Rela *rela, Elf_Addr base, Elf_Sym *symtab,
 		val = val + rela->r_addend -
 			((Elf_Addr) me->core_layout.base + me->arch.got_offset);
 		if (r_type == R_390_GOTOFF16)
-			rc = apply_rela_bits(loc, val, 0, 16, 0);
+			rc = apply_rela_bits(loc, val, 0, 16, 0, write);
 		else if (r_type == R_390_GOTOFF32)
-			rc = apply_rela_bits(loc, val, 0, 32, 0);
+			rc = apply_rela_bits(loc, val, 0, 32, 0, write);
 		else if (r_type == R_390_GOTOFF64)
-			rc = apply_rela_bits(loc, val, 0, 64, 0);
+			rc = apply_rela_bits(loc, val, 0, 64, 0, write);
 		break;
 	case R_390_GOTPC:	/* 32 bit PC relative offset to GOT. */
 	case R_390_GOTPCDBL:	/* 32 bit PC rel. off. to GOT shifted by 1. */
 		val = (Elf_Addr) me->core_layout.base + me->arch.got_offset +
 			rela->r_addend - loc;
 		if (r_type == R_390_GOTPC)
-			rc = apply_rela_bits(loc, val, 1, 32, 0);
+			rc = apply_rela_bits(loc, val, 1, 32, 0, write);
 		else if (r_type == R_390_GOTPCDBL)
-			rc = apply_rela_bits(loc, val, 1, 32, 1);
+			rc = apply_rela_bits(loc, val, 1, 32, 1, write);
 		break;
 	case R_390_COPY:
 	case R_390_GLOB_DAT:	/* Create GOT entry.  */
@@ -412,9 +426,10 @@ static int apply_rela(Elf_Rela *rela, Elf_Addr base, Elf_Sym *symtab,
 	return 0;
 }
 
-int apply_relocate_add(Elf_Shdr *sechdrs, const char *strtab,
+static int __apply_relocate_add(Elf_Shdr *sechdrs, const char *strtab,
 		       unsigned int symindex, unsigned int relsec,
-		       struct module *me)
+		       struct module *me,
+		       void *(*write)(void *dest, const void *src, size_t len))
 {
 	Elf_Addr base;
 	Elf_Sym *symtab;
@@ -430,13 +445,27 @@ int apply_relocate_add(Elf_Shdr *sechdrs, const char *strtab,
 	n = sechdrs[relsec].sh_size / sizeof(Elf_Rela);
 
 	for (i = 0; i < n; i++, rela++) {
-		rc = apply_rela(rela, base, symtab, strtab, me);
+		rc = apply_rela(rela, base, symtab, strtab, me, write);
 		if (rc)
 			return rc;
 	}
 	return 0;
 }
 
+int apply_relocate_add(Elf_Shdr *sechdrs, const char *strtab,
+		       unsigned int symindex, unsigned int relsec,
+		       struct module *me)
+{
+	bool early = me->state == MODULE_STATE_UNFORMED;
+	void *(*write)(void *, const void *, size_t) = memcpy;
+
+	if (!early)
+		write = s390_kernel_write;
+
+	return __apply_relocate_add(sechdrs, strtab, symindex, relsec, me,
+				    write);
+}
+
 int module_finalize(const Elf_Ehdr *hdr,
 		    const Elf_Shdr *sechdrs,
 		    struct module *me)
diff --git a/arch/s390/mm/maccess.c b/arch/s390/mm/maccess.c
index de7ca4b6718f..22a0be655f27 100644
--- a/arch/s390/mm/maccess.c
+++ b/arch/s390/mm/maccess.c
@@ -55,19 +55,22 @@ static notrace long s390_kernel_write_odd(void *dst, const void *src, size_t siz
  */
 static DEFINE_SPINLOCK(s390_kernel_write_lock);
 
-void notrace s390_kernel_write(void *dst, const void *src, size_t size)
+notrace void *s390_kernel_write(void *dst, const void *src, size_t size)
 {
+	void *tmp = dst;
 	unsigned long flags;
 	long copied;
 
 	spin_lock_irqsave(&s390_kernel_write_lock, flags);
 	while (size) {
-		copied = s390_kernel_write_odd(dst, src, size);
-		dst += copied;
+		copied = s390_kernel_write_odd(tmp, src, size);
+		tmp += copied;
 		src += copied;
 		size -= copied;
 	}
 	spin_unlock_irqrestore(&s390_kernel_write_lock, flags);
+
+	return dst;
 }
 
 static int __no_sanitize_address __memcpy_real(void *dest, void *src, size_t count)
diff --git a/arch/um/kernel/um_arch.c b/arch/um/kernel/um_arch.c
index 0f40eccbd759..375ab720e4aa 100644
--- a/arch/um/kernel/um_arch.c
+++ b/arch/um/kernel/um_arch.c
@@ -362,3 +362,19 @@ void __init check_bugs(void)
 void apply_alternatives(struct alt_instr *start, struct alt_instr *end)
 {
 }
+
+void *text_poke(void *addr, const void *opcode, size_t len)
+{
+	/*
+	 * In UML, the only reference to this function is in
+	 * apply_relocate_add(), which shouldn't ever actually call this
+	 * because UML doesn't have live patching.
+	 */
+	WARN_ON(1);
+
+	return memcpy(addr, opcode, len);
+}
+
+void text_poke_sync(void)
+{
+}
diff --git a/arch/x86/kernel/Makefile b/arch/x86/kernel/Makefile
index 2a7c3afa62e2..8ef4369a4f06 100644
--- a/arch/x86/kernel/Makefile
+++ b/arch/x86/kernel/Makefile
@@ -90,7 +90,6 @@ obj-$(CONFIG_X86_MPPARSE)	+= mpparse.o
 obj-y				+= apic/
 obj-$(CONFIG_X86_REBOOTFIXUPS)	+= reboot_fixups_32.o
 obj-$(CONFIG_DYNAMIC_FTRACE)	+= ftrace.o
-obj-$(CONFIG_LIVEPATCH)	+= livepatch.o
 obj-$(CONFIG_FUNCTION_TRACER)	+= ftrace_$(BITS).o
 obj-$(CONFIG_FUNCTION_GRAPH_TRACER) += ftrace.o
 obj-$(CONFIG_FTRACE_SYSCALLS)	+= ftrace.o
diff --git a/arch/x86/kernel/livepatch.c b/arch/x86/kernel/livepatch.c
deleted file mode 100644
index 6a68e41206e7..000000000000
--- a/arch/x86/kernel/livepatch.c
+++ /dev/null
@@ -1,53 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0-or-later
-/*
- * livepatch.c - x86-specific Kernel Live Patching Core
- */
-
-#include <linux/module.h>
-#include <linux/kallsyms.h>
-#include <linux/livepatch.h>
-#include <asm/text-patching.h>
-
-/* Apply per-object alternatives. Based on x86 module_finalize() */
-void arch_klp_init_object_loaded(struct klp_patch *patch,
-				 struct klp_object *obj)
-{
-	int cnt;
-	struct klp_modinfo *info;
-	Elf_Shdr *s, *alt = NULL, *para = NULL;
-	void *aseg, *pseg;
-	const char *objname;
-	char sec_objname[MODULE_NAME_LEN];
-	char secname[KSYM_NAME_LEN];
-
-	info = patch->mod->klp_info;
-	objname = obj->name ? obj->name : "vmlinux";
-
-	/* See livepatch core code for BUILD_BUG_ON() explanation */
-	BUILD_BUG_ON(MODULE_NAME_LEN < 56 || KSYM_NAME_LEN != 128);
-
-	for (s = info->sechdrs; s < info->sechdrs + info->hdr.e_shnum; s++) {
-		/* Apply per-object .klp.arch sections */
-		cnt = sscanf(info->secstrings + s->sh_name,
-			     ".klp.arch.%55[^.].%127s",
-			     sec_objname, secname);
-		if (cnt != 2)
-			continue;
-		if (strcmp(sec_objname, objname))
-			continue;
-		if (!strcmp(".altinstructions", secname))
-			alt = s;
-		if (!strcmp(".parainstructions", secname))
-			para = s;
-	}
-
-	if (alt) {
-		aseg = (void *) alt->sh_addr;
-		apply_alternatives(aseg, aseg + alt->sh_size);
-	}
-
-	if (para) {
-		pseg = (void *) para->sh_addr;
-		apply_paravirt(pseg, pseg + para->sh_size);
-	}
-}
diff --git a/arch/x86/kernel/module.c b/arch/x86/kernel/module.c
index d5c72cb877b3..23c95a53d20e 100644
--- a/arch/x86/kernel/module.c
+++ b/arch/x86/kernel/module.c
@@ -18,6 +18,7 @@
 #include <linux/gfp.h>
 #include <linux/jump_label.h>
 #include <linux/random.h>
+#include <linux/memory.h>
 
 #include <asm/text-patching.h>
 #include <asm/page.h>
@@ -126,11 +127,12 @@ int apply_relocate(Elf32_Shdr *sechdrs,
 	return 0;
 }
 #else /*X86_64*/
-int apply_relocate_add(Elf64_Shdr *sechdrs,
+static int __apply_relocate_add(Elf64_Shdr *sechdrs,
 		   const char *strtab,
 		   unsigned int symindex,
 		   unsigned int relsec,
-		   struct module *me)
+		   struct module *me,
+		   void *(*write)(void *dest, const void *src, size_t len))
 {
 	unsigned int i;
 	Elf64_Rela *rel = (void *)sechdrs[relsec].sh_addr;
@@ -162,19 +164,19 @@ int apply_relocate_add(Elf64_Shdr *sechdrs,
 		case R_X86_64_64:
 			if (*(u64 *)loc != 0)
 				goto invalid_relocation;
-			*(u64 *)loc = val;
+			write(loc, &val, 8);
 			break;
 		case R_X86_64_32:
 			if (*(u32 *)loc != 0)
 				goto invalid_relocation;
-			*(u32 *)loc = val;
+			write(loc, &val, 4);
 			if (val != *(u32 *)loc)
 				goto overflow;
 			break;
 		case R_X86_64_32S:
 			if (*(s32 *)loc != 0)
 				goto invalid_relocation;
-			*(s32 *)loc = val;
+			write(loc, &val, 4);
 			if ((s64)val != *(s32 *)loc)
 				goto overflow;
 			break;
@@ -183,7 +185,7 @@ int apply_relocate_add(Elf64_Shdr *sechdrs,
 			if (*(u32 *)loc != 0)
 				goto invalid_relocation;
 			val -= (u64)loc;
-			*(u32 *)loc = val;
+			write(loc, &val, 4);
 #if 0
 			if ((s64)val != *(s32 *)loc)
 				goto overflow;
@@ -193,7 +195,7 @@ int apply_relocate_add(Elf64_Shdr *sechdrs,
 			if (*(u64 *)loc != 0)
 				goto invalid_relocation;
 			val -= (u64)loc;
-			*(u64 *)loc = val;
+			write(loc, &val, 8);
 			break;
 		default:
 			pr_err("%s: Unknown rela relocation: %llu\n",
@@ -215,6 +217,33 @@ overflow:
 	       me->name);
 	return -ENOEXEC;
 }
+
+int apply_relocate_add(Elf64_Shdr *sechdrs,
+		   const char *strtab,
+		   unsigned int symindex,
+		   unsigned int relsec,
+		   struct module *me)
+{
+	int ret;
+	bool early = me->state == MODULE_STATE_UNFORMED;
+	void *(*write)(void *, const void *, size_t) = memcpy;
+
+	if (!early) {
+		write = text_poke;
+		mutex_lock(&text_mutex);
+	}
+
+	ret = __apply_relocate_add(sechdrs, strtab, symindex, relsec, me,
+				   write);
+
+	if (!early) {
+		text_poke_sync();
+		mutex_unlock(&text_mutex);
+	}
+
+	return ret;
+}
+
 #endif
 
 int module_finalize(const Elf_Ehdr *hdr,
diff --git a/include/linux/livepatch.h b/include/linux/livepatch.h
index e894e74905f3..2614247a9781 100644
--- a/include/linux/livepatch.h
+++ b/include/linux/livepatch.h
@@ -195,9 +195,6 @@ struct klp_patch {
 
 int klp_enable_patch(struct klp_patch *);
 
-void arch_klp_init_object_loaded(struct klp_patch *patch,
-				 struct klp_object *obj);
-
 /* Called from the module loader during module coming/going states */
 int klp_module_coming(struct module *mod);
 void klp_module_going(struct module *mod);
@@ -234,6 +231,11 @@ void klp_shadow_free_all(unsigned long id, klp_shadow_dtor_t dtor);
 struct klp_state *klp_get_state(struct klp_patch *patch, unsigned long id);
 struct klp_state *klp_get_prev_state(unsigned long id);
 
+int klp_apply_section_relocs(struct module *pmod, Elf_Shdr *sechdrs,
+			     const char *shstrtab, const char *strtab,
+			     unsigned int symindex, unsigned int secindex,
+			     const char *objname);
+
 #else /* !CONFIG_LIVEPATCH */
 
 static inline int klp_module_coming(struct module *mod) { return 0; }
@@ -242,6 +244,15 @@ static inline bool klp_patch_pending(struct task_struct *task) { return false; }
 static inline void klp_update_patch_state(struct task_struct *task) {}
 static inline void klp_copy_process(struct task_struct *child) {}
 
+static inline
+int klp_apply_section_relocs(struct module *pmod, Elf_Shdr *sechdrs,
+			     const char *shstrtab, const char *strtab,
+			     unsigned int symindex, unsigned int secindex,
+			     const char *objname)
+{
+	return 0;
+}
+
 #endif /* CONFIG_LIVEPATCH */
 
 #endif /* _LINUX_LIVEPATCH_H_ */
diff --git a/include/linux/module.h b/include/linux/module.h
index d849d06e4d44..2e6670860d27 100644
--- a/include/linux/module.h
+++ b/include/linux/module.h
@@ -866,14 +866,6 @@ extern int module_sysfs_initialized;
 
 #define __MODULE_STRING(x) __stringify(x)
 
-#ifdef CONFIG_STRICT_MODULE_RWX
-extern void module_enable_ro(const struct module *mod, bool after_init);
-extern void module_disable_ro(const struct module *mod);
-#else
-static inline void module_enable_ro(const struct module *mod, bool after_init) { }
-static inline void module_disable_ro(const struct module *mod) { }
-#endif
-
 #ifdef CONFIG_GENERIC_BUG
 void module_bug_finalize(const Elf_Ehdr *, const Elf_Shdr *,
 			 struct module *);
diff --git a/kernel/livepatch/core.c b/kernel/livepatch/core.c
index c3512e7e0801..f76fdb925532 100644
--- a/kernel/livepatch/core.c
+++ b/kernel/livepatch/core.c
@@ -191,18 +191,21 @@ static int klp_find_object_symbol(const char *objname, const char *name,
 	return -EINVAL;
 }
 
-static int klp_resolve_symbols(Elf_Shdr *relasec, struct module *pmod)
+static int klp_resolve_symbols(Elf64_Shdr *sechdrs, const char *strtab,
+			       unsigned int symndx, Elf_Shdr *relasec,
+			       const char *sec_objname)
 {
-	int i, cnt, vmlinux, ret;
-	char objname[MODULE_NAME_LEN];
-	char symname[KSYM_NAME_LEN];
-	char *strtab = pmod->core_kallsyms.strtab;
+	int i, cnt, ret;
+	char sym_objname[MODULE_NAME_LEN];
+	char sym_name[KSYM_NAME_LEN];
 	Elf_Rela *relas;
 	Elf_Sym *sym;
 	unsigned long sympos, addr;
+	bool sym_vmlinux;
+	bool sec_vmlinux = !strcmp(sec_objname, "vmlinux");
 
 	/*
-	 * Since the field widths for objname and symname in the sscanf()
+	 * Since the field widths for sym_objname and sym_name in the sscanf()
 	 * call are hard-coded and correspond to MODULE_NAME_LEN and
 	 * KSYM_NAME_LEN respectively, we must make sure that MODULE_NAME_LEN
 	 * and KSYM_NAME_LEN have the values we expect them to have.
@@ -216,27 +219,40 @@ static int klp_resolve_symbols(Elf_Shdr *relasec, struct module *pmod)
 	relas = (Elf_Rela *) relasec->sh_addr;
 	/* For each rela in this klp relocation section */
 	for (i = 0; i < relasec->sh_size / sizeof(Elf_Rela); i++) {
-		sym = pmod->core_kallsyms.symtab + ELF_R_SYM(relas[i].r_info);
+		sym = (Elf64_Sym *)sechdrs[symndx].sh_addr + ELF_R_SYM(relas[i].r_info);
 		if (sym->st_shndx != SHN_LIVEPATCH) {
 			pr_err("symbol %s is not marked as a livepatch symbol\n",
 			       strtab + sym->st_name);
 			return -EINVAL;
 		}
 
-		/* Format: .klp.sym.objname.symname,sympos */
+		/* Format: .klp.sym.sym_objname.sym_name,sympos */
 		cnt = sscanf(strtab + sym->st_name,
 			     ".klp.sym.%55[^.].%127[^,],%lu",
-			     objname, symname, &sympos);
+			     sym_objname, sym_name, &sympos);
 		if (cnt != 3) {
 			pr_err("symbol %s has an incorrectly formatted name\n",
 			       strtab + sym->st_name);
 			return -EINVAL;
 		}
 
+		sym_vmlinux = !strcmp(sym_objname, "vmlinux");
+
+		/*
+		 * Prevent module-specific KLP rela sections from referencing
+		 * vmlinux symbols.  This helps prevent ordering issues with
+		 * module special section initializations.  Presumably such
+		 * symbols are exported and normal relas can be used instead.
+		 */
+		if (!sec_vmlinux && sym_vmlinux) {
+			pr_err("invalid access to vmlinux symbol '%s' from module-specific livepatch relocation section",
+			       sym_name);
+			return -EINVAL;
+		}
+
 		/* klp_find_object_symbol() treats a NULL objname as vmlinux */
-		vmlinux = !strcmp(objname, "vmlinux");
-		ret = klp_find_object_symbol(vmlinux ? NULL : objname,
-					     symname, sympos, &addr);
+		ret = klp_find_object_symbol(sym_vmlinux ? NULL : sym_objname,
+					     sym_name, sympos, &addr);
 		if (ret)
 			return ret;
 
@@ -246,54 +262,59 @@ static int klp_resolve_symbols(Elf_Shdr *relasec, struct module *pmod)
 	return 0;
 }
 
-static int klp_write_object_relocations(struct module *pmod,
-					struct klp_object *obj)
+/*
+ * At a high-level, there are two types of klp relocation sections: those which
+ * reference symbols which live in vmlinux; and those which reference symbols
+ * which live in other modules.  This function is called for both types:
+ *
+ * 1) When a klp module itself loads, the module code calls this function to
+ *    write vmlinux-specific klp relocations (.klp.rela.vmlinux.* sections).
+ *    These relocations are written to the klp module text to allow the patched
+ *    code/data to reference unexported vmlinux symbols.  They're written as
+ *    early as possible to ensure that other module init code (.e.g.,
+ *    jump_label_apply_nops) can access any unexported vmlinux symbols which
+ *    might be referenced by the klp module's special sections.
+ *
+ * 2) When a to-be-patched module loads -- or is already loaded when a
+ *    corresponding klp module loads -- klp code calls this function to write
+ *    module-specific klp relocations (.klp.rela.{module}.* sections).  These
+ *    are written to the klp module text to allow the patched code/data to
+ *    reference symbols which live in the to-be-patched module or one of its
+ *    module dependencies.  Exported symbols are supported, in addition to
+ *    unexported symbols, in order to enable late module patching, which allows
+ *    the to-be-patched module to be loaded and patched sometime *after* the
+ *    klp module is loaded.
+ */
+int klp_apply_section_relocs(struct module *pmod, Elf_Shdr *sechdrs,
+			     const char *shstrtab, const char *strtab,
+			     unsigned int symndx, unsigned int secndx,
+			     const char *objname)
 {
-	int i, cnt, ret = 0;
-	const char *objname, *secname;
+	int cnt, ret;
 	char sec_objname[MODULE_NAME_LEN];
-	Elf_Shdr *sec;
+	Elf_Shdr *sec = sechdrs + secndx;
 
-	if (WARN_ON(!klp_is_object_loaded(obj)))
+	/*
+	 * Format: .klp.rela.sec_objname.section_name
+	 * See comment in klp_resolve_symbols() for an explanation
+	 * of the selected field width value.
+	 */
+	cnt = sscanf(shstrtab + sec->sh_name, ".klp.rela.%55[^.]",
+		     sec_objname);
+	if (cnt != 1) {
+		pr_err("section %s has an incorrectly formatted name\n",
+		       shstrtab + sec->sh_name);
 		return -EINVAL;
+	}
 
-	objname = klp_is_module(obj) ? obj->name : "vmlinux";
-
-	/* For each klp relocation section */
-	for (i = 1; i < pmod->klp_info->hdr.e_shnum; i++) {
-		sec = pmod->klp_info->sechdrs + i;
-		secname = pmod->klp_info->secstrings + sec->sh_name;
-		if (!(sec->sh_flags & SHF_RELA_LIVEPATCH))
-			continue;
-
-		/*
-		 * Format: .klp.rela.sec_objname.section_name
-		 * See comment in klp_resolve_symbols() for an explanation
-		 * of the selected field width value.
-		 */
-		cnt = sscanf(secname, ".klp.rela.%55[^.]", sec_objname);
-		if (cnt != 1) {
-			pr_err("section %s has an incorrectly formatted name\n",
-			       secname);
-			ret = -EINVAL;
-			break;
-		}
-
-		if (strcmp(objname, sec_objname))
-			continue;
-
-		ret = klp_resolve_symbols(sec, pmod);
-		if (ret)
-			break;
+	if (strcmp(objname ? objname : "vmlinux", sec_objname))
+		return 0;
 
-		ret = apply_relocate_add(pmod->klp_info->sechdrs,
-					 pmod->core_kallsyms.strtab,
-					 pmod->klp_info->symndx, i, pmod);
-		if (ret)
-			break;
-	}
+	ret = klp_resolve_symbols(sechdrs, strtab, symndx, sec, sec_objname);
+	if (ret)
+		return ret;
 
-	return ret;
+	return apply_relocate_add(sechdrs, strtab, symndx, secndx, pmod);
 }
 
 /*
@@ -724,10 +745,27 @@ static int klp_init_func(struct klp_object *obj, struct klp_func *func)
 			   func->old_sympos ? func->old_sympos : 1);
 }
 
-/* Arches may override this to finish any remaining arch-specific tasks */
-void __weak arch_klp_init_object_loaded(struct klp_patch *patch,
-					struct klp_object *obj)
+static int klp_apply_object_relocs(struct klp_patch *patch,
+				   struct klp_object *obj)
 {
+	int i, ret;
+	struct klp_modinfo *info = patch->mod->klp_info;
+
+	for (i = 1; i < info->hdr.e_shnum; i++) {
+		Elf_Shdr *sec = info->sechdrs + i;
+
+		if (!(sec->sh_flags & SHF_RELA_LIVEPATCH))
+			continue;
+
+		ret = klp_apply_section_relocs(patch->mod, info->sechdrs,
+					       info->secstrings,
+					       patch->mod->core_kallsyms.strtab,
+					       info->symndx, i, obj->name);
+		if (ret)
+			return ret;
+	}
+
+	return 0;
 }
 
 /* parts of the initialization that is done only when the object is loaded */
@@ -737,21 +775,18 @@ static int klp_init_object_loaded(struct klp_patch *patch,
 	struct klp_func *func;
 	int ret;
 
-	mutex_lock(&text_mutex);
-
-	module_disable_ro(patch->mod);
-	ret = klp_write_object_relocations(patch->mod, obj);
-	if (ret) {
-		module_enable_ro(patch->mod, true);
-		mutex_unlock(&text_mutex);
-		return ret;
+	if (klp_is_module(obj)) {
+		/*
+		 * Only write module-specific relocations here
+		 * (.klp.rela.{module}.*).  vmlinux-specific relocations were
+		 * written earlier during the initialization of the klp module
+		 * itself.
+		 */
+		ret = klp_apply_object_relocs(patch, obj);
+		if (ret)
+			return ret;
 	}
 
-	arch_klp_init_object_loaded(patch, obj);
-	module_enable_ro(patch->mod, true);
-
-	mutex_unlock(&text_mutex);
-
 	klp_for_each_func(obj, func) {
 		ret = klp_find_object_symbol(obj->name, func->old_name,
 					     func->old_sympos,
@@ -1139,6 +1174,11 @@ int klp_module_coming(struct module *mod)
 	if (WARN_ON(mod->state != MODULE_STATE_COMING))
 		return -EINVAL;
 
+	if (!strcmp(mod->name, "vmlinux")) {
+		pr_err("vmlinux.ko: invalid module name");
+		return -EINVAL;
+	}
+
 	mutex_lock(&klp_mutex);
 	/*
 	 * Each module has to know that klp_module_coming()
diff --git a/kernel/module.c b/kernel/module.c
index be5413903d20..bca993c5f1bc 100644
--- a/kernel/module.c
+++ b/kernel/module.c
@@ -2000,20 +2000,7 @@ static void frob_writable_data(const struct module_layout *layout,
 		   (layout->size - layout->ro_after_init_size) >> PAGE_SHIFT);
 }
 
-/* livepatching wants to disable read-only so it can frob module. */
-void module_disable_ro(const struct module *mod)
-{
-	if (!rodata_enabled)
-		return;
-
-	frob_text(&mod->core_layout, set_memory_rw);
-	frob_rodata(&mod->core_layout, set_memory_rw);
-	frob_ro_after_init(&mod->core_layout, set_memory_rw);
-	frob_text(&mod->init_layout, set_memory_rw);
-	frob_rodata(&mod->init_layout, set_memory_rw);
-}
-
-void module_enable_ro(const struct module *mod, bool after_init)
+static void module_enable_ro(const struct module *mod, bool after_init)
 {
 	if (!rodata_enabled)
 		return;
@@ -2041,6 +2028,7 @@ static void module_enable_nx(const struct module *mod)
 
 #else /* !CONFIG_STRICT_MODULE_RWX */
 static void module_enable_nx(const struct module *mod) { }
+static void module_enable_ro(const struct module *mod, bool after_init) {}
 #endif /*  CONFIG_STRICT_MODULE_RWX */
 static void module_enable_x(const struct module *mod)
 {
@@ -2337,11 +2325,13 @@ static int apply_relocations(struct module *mod, const struct load_info *info)
 		if (!(info->sechdrs[infosec].sh_flags & SHF_ALLOC))
 			continue;
 
-		/* Livepatch relocation sections are applied by livepatch */
 		if (info->sechdrs[i].sh_flags & SHF_RELA_LIVEPATCH)
-			continue;
-
-		if (info->sechdrs[i].sh_type == SHT_REL)
+			err = klp_apply_section_relocs(mod, info->sechdrs,
+						       info->secstrings,
+						       info->strtab,
+						       info->index.sym, i,
+						       NULL);
+		else if (info->sechdrs[i].sh_type == SHT_REL)
 			err = apply_relocate(info->sechdrs, info->strtab,
 					     info->index.sym, i, mod);
 		else if (info->sechdrs[i].sh_type == SHT_RELA)