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

Author: torvalds

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.
 

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/
 

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 */

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 ||
@@ -357,38 +371,38 @@ 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.  */
 	case R_390_GOTOFF64:	/* 64 bit offset to GOT. */
 		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)

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)

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)
+{
+}

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