livepatch: arm64: add support for livepatch on arm64

Livepatch can reuse the relocation codes of module loader, this patch extract it.

Signed-off-by Li Bin <[email protected]>

---
 arch/arm64/include/asm/module.h |    3 +
 arch/arm64/kernel/module.c      |  360 ++++++++++++++++++++-------------------
 2 files changed, 187 insertions(+), 176 deletions(-)

arch/arm64/include/asm/module.h +3 -0

index e80e232..78ac36e 100644
@@ -20,4 +20,7 @@
 
 #define MODULE_ARCH_VERMAGIC	"aarch64"
 
+extern int static_relocate(struct module *mod, unsigned long type,
+			   void * loc, unsigned long value);
+
 #endif /* __ASM_MODULE_H */

arch/arm64/kernel/module.c +184 -176

index f4bc779..6d1a1e3 100644
@@ -203,6 +203,184 @@ static int reloc_insn_imm(enum aarch64_reloc_op op, void *place, u64 val,
 	return 0;
 }
 
+int static_relocate(struct module *me, unsigned long type, void *loc,
+		    unsigned long val)
+{
+	int ovf = 0;
+	bool overflow_check = true;
+	/* Perform the static relocation. */
+	switch (type) {
+	/* Null relocations. */
+	case R_ARM_NONE:
+	case R_AARCH64_NONE:
+		ovf = 0;
+		break;
+
+		/* Data relocations. */
+	case R_AARCH64_ABS64:
+		overflow_check = false;
+		ovf = reloc_data(RELOC_OP_ABS, loc, val, 64);
+		break;
+	case R_AARCH64_ABS32:
+		ovf = reloc_data(RELOC_OP_ABS, loc, val, 32);
+		break;
+	case R_AARCH64_ABS16:
+		ovf = reloc_data(RELOC_OP_ABS, loc, val, 16);
+		break;
+	case R_AARCH64_PREL64:
+		overflow_check = false;
+		ovf = reloc_data(RELOC_OP_PREL, loc, val, 64);
+		break;
+	case R_AARCH64_PREL32:
+		ovf = reloc_data(RELOC_OP_PREL, loc, val, 32);
+		break;
+	case R_AARCH64_PREL16:
+		ovf = reloc_data(RELOC_OP_PREL, loc, val, 16);
+		break;
+
+		/* MOVW instruction relocations. */
+	case R_AARCH64_MOVW_UABS_G0_NC:
+		overflow_check = false;
+	case R_AARCH64_MOVW_UABS_G0:
+		ovf = reloc_insn_movw(RELOC_OP_ABS, loc, val, 0,
+				      AARCH64_INSN_IMM_16);
+		break;
+	case R_AARCH64_MOVW_UABS_G1_NC:
+		overflow_check = false;
+	case R_AARCH64_MOVW_UABS_G1:
+		ovf = reloc_insn_movw(RELOC_OP_ABS, loc, val, 16,
+				      AARCH64_INSN_IMM_16);
+		break;
+	case R_AARCH64_MOVW_UABS_G2_NC:
+		overflow_check = false;
+	case R_AARCH64_MOVW_UABS_G2:
+		ovf = reloc_insn_movw(RELOC_OP_ABS, loc, val, 32,
+				      AARCH64_INSN_IMM_16);
+		break;
+	case R_AARCH64_MOVW_UABS_G3:
+		/* We're using the top bits so we can't overflow. */
+		overflow_check = false;
+		ovf = reloc_insn_movw(RELOC_OP_ABS, loc, val, 48,
+				      AARCH64_INSN_IMM_16);
+		break;
+	case R_AARCH64_MOVW_SABS_G0:
+		ovf = reloc_insn_movw(RELOC_OP_ABS, loc, val, 0,
+				      AARCH64_INSN_IMM_MOVNZ);
+		break;
+	case R_AARCH64_MOVW_SABS_G1:
+		ovf = reloc_insn_movw(RELOC_OP_ABS, loc, val, 16,
+				      AARCH64_INSN_IMM_MOVNZ);
+		break;
+	case R_AARCH64_MOVW_SABS_G2:
+		ovf = reloc_insn_movw(RELOC_OP_ABS, loc, val, 32,
+				      AARCH64_INSN_IMM_MOVNZ);
+		break;
+	case R_AARCH64_MOVW_PREL_G0_NC:
+		overflow_check = false;
+		ovf = reloc_insn_movw(RELOC_OP_PREL, loc, val, 0,
+				      AARCH64_INSN_IMM_MOVK);
+		break;
+	case R_AARCH64_MOVW_PREL_G0:
+		ovf = reloc_insn_movw(RELOC_OP_PREL, loc, val, 0,
+				      AARCH64_INSN_IMM_MOVNZ);
+		break;
+	case R_AARCH64_MOVW_PREL_G1_NC:
+		overflow_check = false;
+		ovf = reloc_insn_movw(RELOC_OP_PREL, loc, val, 16,
+				      AARCH64_INSN_IMM_MOVK);
+		break;
+	case R_AARCH64_MOVW_PREL_G1:
+		ovf = reloc_insn_movw(RELOC_OP_PREL, loc, val, 16,
+				      AARCH64_INSN_IMM_MOVNZ);
+		break;
+	case R_AARCH64_MOVW_PREL_G2_NC:
+		overflow_check = false;
+		ovf = reloc_insn_movw(RELOC_OP_PREL, loc, val, 32,
+				      AARCH64_INSN_IMM_MOVK);
+		break;
+	case R_AARCH64_MOVW_PREL_G2:
+		ovf = reloc_insn_movw(RELOC_OP_PREL, loc, val, 32,
+				      AARCH64_INSN_IMM_MOVNZ);
+		break;
+	case R_AARCH64_MOVW_PREL_G3:
+		/* We're using the top bits so we can't overflow. */
+		overflow_check = false;
+		ovf = reloc_insn_movw(RELOC_OP_PREL, loc, val, 48,
+				      AARCH64_INSN_IMM_MOVNZ);
+		break;
+
+		/* Immediate instruction relocations. */
+	case R_AARCH64_LD_PREL_LO19:
+		ovf = reloc_insn_imm(RELOC_OP_PREL, loc, val, 2, 19,
+				     AARCH64_INSN_IMM_19);
+		break;
+	case R_AARCH64_ADR_PREL_LO21:
+		ovf = reloc_insn_imm(RELOC_OP_PREL, loc, val, 0, 21,
+				     AARCH64_INSN_IMM_ADR);
+		break;
+#ifndef CONFIG_ARM64_ERRATUM_843419
+	case R_AARCH64_ADR_PREL_PG_HI21_NC:
+		overflow_check = false;
+	case R_AARCH64_ADR_PREL_PG_HI21:
+		ovf = reloc_insn_imm(RELOC_OP_PAGE, loc, val, 12, 21,
+				     AARCH64_INSN_IMM_ADR);
+		break;
+#endif
+	case R_AARCH64_ADD_ABS_LO12_NC:
+	case R_AARCH64_LDST8_ABS_LO12_NC:
+		overflow_check = false;
+		ovf = reloc_insn_imm(RELOC_OP_ABS, loc, val, 0, 12,
+				     AARCH64_INSN_IMM_12);
+		break;
+	case R_AARCH64_LDST16_ABS_LO12_NC:
+		overflow_check = false;
+		ovf = reloc_insn_imm(RELOC_OP_ABS, loc, val, 1, 11,
+				     AARCH64_INSN_IMM_12);
+		break;
+	case R_AARCH64_LDST32_ABS_LO12_NC:
+		overflow_check = false;
+		ovf = reloc_insn_imm(RELOC_OP_ABS, loc, val, 2, 10,
+				     AARCH64_INSN_IMM_12);
+		break;
+	case R_AARCH64_LDST64_ABS_LO12_NC:
+		overflow_check = false;
+		ovf = reloc_insn_imm(RELOC_OP_ABS, loc, val, 3, 9,
+				     AARCH64_INSN_IMM_12);
+		break;
+	case R_AARCH64_LDST128_ABS_LO12_NC:
+		overflow_check = false;
+		ovf = reloc_insn_imm(RELOC_OP_ABS, loc, val, 4, 8,
+				     AARCH64_INSN_IMM_12);
+		break;
+	case R_AARCH64_TSTBR14:
+		ovf = reloc_insn_imm(RELOC_OP_PREL, loc, val, 2, 14,
+				     AARCH64_INSN_IMM_14);
+		break;
+	case R_AARCH64_CONDBR19:
+		ovf = reloc_insn_imm(RELOC_OP_PREL, loc, val, 2, 19,
+				     AARCH64_INSN_IMM_19);
+		break;
+	case R_AARCH64_JUMP26:
+	case R_AARCH64_CALL26:
+		ovf = reloc_insn_imm(RELOC_OP_PREL, loc, val, 2, 26,
+				     AARCH64_INSN_IMM_26);
+		break;
+
+	default:
+		pr_err("module %s: unsupported RELA relocation: %lu\n",
+			me->name, type);
+		return -ENOEXEC;
+	}
+
+	if (overflow_check && ovf == -ERANGE) {
+		pr_err("module %s: overflow in relocation type %lu val %lx\n",
+			me->name, type, val);
+		return -ENOEXEC;
+	}
+
+	return 0;
+}
+
 int apply_relocate_add(Elf64_Shdr *sechdrs,
 		       const char *strtab,
 		       unsigned int symindex,

@@ -210,12 +388,11 @@ int apply_relocate_add(Elf64_Shdr *sechdrs,
 		       struct module *me)
 {
 	unsigned int i;
-	int ovf;
-	bool overflow_check;
 	Elf64_Sym *sym;
 	void *loc;
 	u64 val;
 	Elf64_Rela *rel = (void *)sechdrs[relsec].sh_addr;
+	int type, ret;
 
 	for (i = 0; i < sechdrs[relsec].sh_size / sizeof(*rel); i++) {
 		/* loc corresponds to P in the AArch64 ELF document. */

@@ -229,184 +406,15 @@ int apply_relocate_add(Elf64_Shdr *sechdrs,
 		/* val corresponds to (S + A) in the AArch64 ELF document. */
 		val = sym->st_value + rel[i].r_addend;
 
-		/* Check for overflow by default. */
-		overflow_check = true;
-
-		/* Perform the static relocation. */
-		switch (ELF64_R_TYPE(rel[i].r_info)) {
-		/* Null relocations. */
-		case R_ARM_NONE:
-		case R_AARCH64_NONE:
-			ovf = 0;
-			break;
-
-		/* Data relocations. */
-		case R_AARCH64_ABS64:
-			overflow_check = false;
-			ovf = reloc_data(RELOC_OP_ABS, loc, val, 64);
-			break;
-		case R_AARCH64_ABS32:
-			ovf = reloc_data(RELOC_OP_ABS, loc, val, 32);
-			break;
-		case R_AARCH64_ABS16:
-			ovf = reloc_data(RELOC_OP_ABS, loc, val, 16);
-			break;
-		case R_AARCH64_PREL64:
-			overflow_check = false;
-			ovf = reloc_data(RELOC_OP_PREL, loc, val, 64);
-			break;
-		case R_AARCH64_PREL32:
-			ovf = reloc_data(RELOC_OP_PREL, loc, val, 32);
-			break;
-		case R_AARCH64_PREL16:
-			ovf = reloc_data(RELOC_OP_PREL, loc, val, 16);
-			break;
-
-		/* MOVW instruction relocations. */
-		case R_AARCH64_MOVW_UABS_G0_NC:
-			overflow_check = false;
-		case R_AARCH64_MOVW_UABS_G0:
-			ovf = reloc_insn_movw(RELOC_OP_ABS, loc, val, 0,
-					      AARCH64_INSN_IMM_16);
-			break;
-		case R_AARCH64_MOVW_UABS_G1_NC:
-			overflow_check = false;
-		case R_AARCH64_MOVW_UABS_G1:
-			ovf = reloc_insn_movw(RELOC_OP_ABS, loc, val, 16,
-					      AARCH64_INSN_IMM_16);
-			break;
-		case R_AARCH64_MOVW_UABS_G2_NC:
-			overflow_check = false;
-		case R_AARCH64_MOVW_UABS_G2:
-			ovf = reloc_insn_movw(RELOC_OP_ABS, loc, val, 32,
-					      AARCH64_INSN_IMM_16);
-			break;
-		case R_AARCH64_MOVW_UABS_G3:
-			/* We're using the top bits so we can't overflow. */
-			overflow_check = false;
-			ovf = reloc_insn_movw(RELOC_OP_ABS, loc, val, 48,
-					      AARCH64_INSN_IMM_16);
-			break;
-		case R_AARCH64_MOVW_SABS_G0:
-			ovf = reloc_insn_movw(RELOC_OP_ABS, loc, val, 0,
-					      AARCH64_INSN_IMM_MOVNZ);
-			break;
-		case R_AARCH64_MOVW_SABS_G1:
-			ovf = reloc_insn_movw(RELOC_OP_ABS, loc, val, 16,
-					      AARCH64_INSN_IMM_MOVNZ);
-			break;
-		case R_AARCH64_MOVW_SABS_G2:
-			ovf = reloc_insn_movw(RELOC_OP_ABS, loc, val, 32,
-					      AARCH64_INSN_IMM_MOVNZ);
-			break;
-		case R_AARCH64_MOVW_PREL_G0_NC:
-			overflow_check = false;
-			ovf = reloc_insn_movw(RELOC_OP_PREL, loc, val, 0,
-					      AARCH64_INSN_IMM_MOVK);
-			break;
-		case R_AARCH64_MOVW_PREL_G0:
-			ovf = reloc_insn_movw(RELOC_OP_PREL, loc, val, 0,
-					      AARCH64_INSN_IMM_MOVNZ);
-			break;
-		case R_AARCH64_MOVW_PREL_G1_NC:
-			overflow_check = false;
-			ovf = reloc_insn_movw(RELOC_OP_PREL, loc, val, 16,
-					      AARCH64_INSN_IMM_MOVK);
-			break;
-		case R_AARCH64_MOVW_PREL_G1:
-			ovf = reloc_insn_movw(RELOC_OP_PREL, loc, val, 16,
-					      AARCH64_INSN_IMM_MOVNZ);
-			break;
-		case R_AARCH64_MOVW_PREL_G2_NC:
-			overflow_check = false;
-			ovf = reloc_insn_movw(RELOC_OP_PREL, loc, val, 32,
-					      AARCH64_INSN_IMM_MOVK);
-			break;
-		case R_AARCH64_MOVW_PREL_G2:
-			ovf = reloc_insn_movw(RELOC_OP_PREL, loc, val, 32,
-					      AARCH64_INSN_IMM_MOVNZ);
-			break;
-		case R_AARCH64_MOVW_PREL_G3:
-			/* We're using the top bits so we can't overflow. */
-			overflow_check = false;
-			ovf = reloc_insn_movw(RELOC_OP_PREL, loc, val, 48,
-					      AARCH64_INSN_IMM_MOVNZ);
-			break;
-
-		/* Immediate instruction relocations. */
-		case R_AARCH64_LD_PREL_LO19:
-			ovf = reloc_insn_imm(RELOC_OP_PREL, loc, val, 2, 19,
-					     AARCH64_INSN_IMM_19);
-			break;
-		case R_AARCH64_ADR_PREL_LO21:
-			ovf = reloc_insn_imm(RELOC_OP_PREL, loc, val, 0, 21,
-					     AARCH64_INSN_IMM_ADR);
-			break;
-#ifndef CONFIG_ARM64_ERRATUM_843419
-		case R_AARCH64_ADR_PREL_PG_HI21_NC:
-			overflow_check = false;
-		case R_AARCH64_ADR_PREL_PG_HI21:
-			ovf = reloc_insn_imm(RELOC_OP_PAGE, loc, val, 12, 21,
-					     AARCH64_INSN_IMM_ADR);
-			break;
-#endif
-		case R_AARCH64_ADD_ABS_LO12_NC:
-		case R_AARCH64_LDST8_ABS_LO12_NC:
-			overflow_check = false;
-			ovf = reloc_insn_imm(RELOC_OP_ABS, loc, val, 0, 12,
-					     AARCH64_INSN_IMM_12);
-			break;
-		case R_AARCH64_LDST16_ABS_LO12_NC:
-			overflow_check = false;
-			ovf = reloc_insn_imm(RELOC_OP_ABS, loc, val, 1, 11,
-					     AARCH64_INSN_IMM_12);
-			break;
-		case R_AARCH64_LDST32_ABS_LO12_NC:
-			overflow_check = false;
-			ovf = reloc_insn_imm(RELOC_OP_ABS, loc, val, 2, 10,
-					     AARCH64_INSN_IMM_12);
-			break;
-		case R_AARCH64_LDST64_ABS_LO12_NC:
-			overflow_check = false;
-			ovf = reloc_insn_imm(RELOC_OP_ABS, loc, val, 3, 9,
-					     AARCH64_INSN_IMM_12);
-			break;
-		case R_AARCH64_LDST128_ABS_LO12_NC:
-			overflow_check = false;
-			ovf = reloc_insn_imm(RELOC_OP_ABS, loc, val, 4, 8,
-					     AARCH64_INSN_IMM_12);
-			break;
-		case R_AARCH64_TSTBR14:
-			ovf = reloc_insn_imm(RELOC_OP_PREL, loc, val, 2, 14,
-					     AARCH64_INSN_IMM_14);
-			break;
-		case R_AARCH64_CONDBR19:
-			ovf = reloc_insn_imm(RELOC_OP_PREL, loc, val, 2, 19,
-					     AARCH64_INSN_IMM_19);
-			break;
-		case R_AARCH64_JUMP26:
-		case R_AARCH64_CALL26:
-			ovf = reloc_insn_imm(RELOC_OP_PREL, loc, val, 2, 26,
-					     AARCH64_INSN_IMM_26);
-			break;
-
-		default:
-			pr_err("module %s: unsupported RELA relocation: %llu\n",
-			       me->name, ELF64_R_TYPE(rel[i].r_info));
-			return -ENOEXEC;
-		}
-
-		if (overflow_check && ovf == -ERANGE)
-			goto overflow;
+		type = ELF64_R_TYPE(rel[i].r_info);
 
+		/* Check for overflow by default. */
+		ret = static_relocate(me, type, loc, val);
+		if (ret)
+			return ret;
 	}
 
 	return 0;
-
-overflow:
-	pr_err("module %s: overflow in relocation type %d val %Lx\n",
-	       me->name, (int)ELF64_R_TYPE(rel[i].r_info), val);
-	return -ENOEXEC;
 }
 
 int module_finalize(const Elf_Ehdr *hdr,

Signature · 1 line

1.7.1

This patchset depends on the on-going gcc feature "-fprolog-pad=N", which will generate a pad of N nops at the beginning of each function.

Livepatch on arm64 can using the feature (that always placing one nop at the beginning of the function). And when enable/disable func patching, just modify the pad code to nop or branch. And that NOP and B instruction are both safe instructions on arm64 which called "concurrent modification and execution of instructions", that can be executed by one thread of execution as they are being modified by another thread of execution without requiring explicit synchronization.

And this method will improve performance significantly compared with the method based on ftrace, especially for the critical function being frequently called.

This patchset depends on the on-going gcc feature "-fprolog-pad=N", which will generate a pad of N nops at the beginning of each function.

Livepatch on arm64 can using the feature (that always placing one nop at the beginning of the function). And when enable/disable func patching, just modify the pad code to nop or branch. And that NOP and B instruction are both safe instructions on arm64 which called "concurrent modification and execution of instructions", that can be executed by one thread of execution as they are being modified by another thread of execution without requiring explicit synchronization.

And this method will improve performance significantly compared with the method based on ftrace, especially for the critical function being frequently called.

Quoted 11 lines · Li Bin

This patchset depends on the on-going gcc feature "-fprolog-pad=N", which will generate a pad of N nops at the beginning of each function.

Livepatch on arm64 can using the feature (that always placing one nop at the beginning of the function). And when enable/disable func patching, just modify the pad code to nop or branch. And that NOP and B instruction are both safe instructions on arm64 which called "concurrent modification and execution of instructions", that can be executed by one thread of execution as they are being modified by another thread of execution without requiring explicit synchronization.

Quoted 3 lines

And this method will improve performance significantly compared with the method based on ftrace, especially for the critical function being frequently called.

It sounds like a great feature for ftrace. If the new prologue is usable for LivePatching, it should be usable to call the ftrace handler as well. If you teach ftrace to use the new prologue, you will not need all these crazy arch-specific hacks for LivePatching. Then both ftrace and livepatch will benefit from the feature.

I suggest to read the ftrace documentation in Documentation/trace/, especially ftrace-design.txt. I have never ported ftrace to a new architecture. I guess that you need to teach scripts/recordmcount.c
to find the new location. Also you might need to update
arch/arm/kernel/ftrace.c. Also please make sure that ftrace supports DYNAMIC_FTRACE_WITH_REGS on Arm.

It is harder but the right way to go. Your current patch set looks like a hack.

Best Regards,
Petr

.

Quoted 21 lines · Petr Mladek

Quoted 11 lines · Li Bin

This patchset depends on the on-going gcc feature "-fprolog-pad=N", which will generate a pad of N nops at the beginning of each function.

Livepatch on arm64 can using the feature (that always placing one nop at the beginning of the function). And when enable/disable func patching, just modify the pad code to nop or branch. And that NOP and B instruction are both safe instructions on arm64 which called "concurrent modification and execution of instructions", that can be executed by one thread of execution as they are being modified by another thread of execution without requiring explicit synchronization.

Quoted 3 lines

And this method will improve performance significantly compared with the method based on ftrace, especially for the critical function being frequently called.

It sounds like a great feature for ftrace. If the new prologue is usable for LivePatching, it should be usable to call the ftrace handler as well. If you teach ftrace to use the new prologue, you will not need all these crazy arch-specific hacks for LivePatching. Then both ftrace and livepatch will benefit from the feature.

Quoted 6 lines

I suggest to read the ftrace documentation in Documentation/trace/, especially ftrace-design.txt. I have never ported ftrace to a new architecture. I guess that you need to teach scripts/recordmcount.c
to find the new location. Also you might need to update
arch/arm/kernel/ftrace.c. Also please make sure that ftrace supports DYNAMIC_FTRACE_WITH_REGS on Arm.

Hi Petr,
I had posted one method for livepatch implementaion on arm64 based on ftrace with DYNAMIC_FTRACE_WITH_REGS.
https://lwn.net/Articles/646317/

This requires GCC changes to support it, and I propose a method that implement -mfentry feature which following some other arch such as x86/mips/s390 etc. This method is architecture-specific, and Maxim Kuvyrkov propose a new method for gcc that implement a target-independent option -fprolog-pad=N, which will generate a pad of N nops at the beginning of each function.
https://gcc.gnu.org/ml/gcc/2015-05/msg00267.html

And based on this, DYNAMIC_FTRACE_WITH_REGS feature can be implemented as mentioned in:
http://lists.infradead.org/pipermail/linux-arm-kernel/2015-November/386815.html

And in this patchset, I only concern the performance for livepatch on arm64, and I hope this also can be resolved by improving ftrace, and thanks to Steve that he pointed that he is working on a way to make ftrace a bit better for livepatch.