Merge tag 'kcfi-v6.1-rc1' of git://git.kernel.org/pub/scm/linux/kerne…

…l/git/kees/linux

Pull kcfi updates from Kees Cook:
 "This replaces the prior support for Clang's standard Control Flow
  Integrity (CFI) instrumentation, which has required a lot of special
  conditions (e.g. LTO) and work-arounds.

  The new implementation ("Kernel CFI") is specific to C, directly
  designed for the Linux kernel, and takes advantage of architectural
  features like x86's IBT. This series retains arm64 support and adds
  x86 support.

  GCC support is expected in the future[1], and additional "generic"
  architectural support is expected soon[2].

  Summary:

   - treewide: Remove old CFI support details

   - arm64: Replace Clang CFI support with Clang KCFI support

   - x86: Introduce Clang KCFI support"

Link: https://gcc.gnu.org/bugzilla/show_bug.cgi?id=107048 [1]
Link: https://github.com/samitolvanen/llvm-project/commits/kcfi_generic [2]

* tag 'kcfi-v6.1-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/kees/linux: (22 commits)
  x86: Add support for CONFIG_CFI_CLANG
  x86/purgatory: Disable CFI
  x86: Add types to indirectly called assembly functions
  x86/tools/relocs: Ignore __kcfi_typeid_ relocations
  kallsyms: Drop CONFIG_CFI_CLANG workarounds
  objtool: Disable CFI warnings
  objtool: Preserve special st_shndx indexes in elf_update_symbol
  treewide: Drop __cficanonical
  treewide: Drop WARN_ON_FUNCTION_MISMATCH
  treewide: Drop function_nocfi
  init: Drop __nocfi from __init
  arm64: Drop unneeded __nocfi attributes
  arm64: Add CFI error handling
  arm64: Add types to indirect called assembly functions
  psci: Fix the function type for psci_initcall_t
  lkdtm: Emit an indirect call for CFI tests
  cfi: Add type helper macros
  cfi: Switch to -fsanitize=kcfi
  cfi: Drop __CFI_ADDRESSABLE
  cfi: Remove CONFIG_CFI_CLANG_SHADOW
  ...

Makefile

@@ -1001,18 +1001,7 @@ 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)
+CC_FLAGS_CFI	:= -fsanitize=kcfi
 KBUILD_CFLAGS	+= $(CC_FLAGS_CFI)
 export CC_FLAGS_CFI
 endif

arch/Kconfig

@@ -744,11 +744,13 @@ config ARCH_SUPPORTS_CFI_CLANG
 	  An architecture should select this option if it can support Clang's
 	  Control-Flow Integrity (CFI) checking.
 
+config ARCH_USES_CFI_TRAPS
+	bool
+
 config CFI_CLANG
 	bool "Use Clang's Control Flow Integrity (CFI)"
-	depends on LTO_CLANG && ARCH_SUPPORTS_CFI_CLANG
-	depends on CLANG_VERSION >= 140000
-	select KALLSYMS
+	depends on ARCH_SUPPORTS_CFI_CLANG
+	depends on $(cc-option,-fsanitize=kcfi)
 	help
 	  This option enables Clang’s forward-edge Control Flow Integrity
 	  (CFI) checking, where the compiler injects a runtime check to each
@@ -760,16 +762,6 @@ config CFI_CLANG
 
 	    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

arch/arm64/crypto/ghash-ce-core.S

@@ -6,6 +6,7 @@
  */
 
 #include <linux/linkage.h>
+#include <linux/cfi_types.h>
 #include <asm/assembler.h>
 
 	SHASH		.req	v0
@@ -350,11 +351,11 @@ CPU_LE(	rev64		T1.16b, T1.16b	)
 	 * void pmull_ghash_update(int blocks, u64 dg[], const char *src,
 	 *			   struct ghash_key const *k, const char *head)
 	 */
-SYM_FUNC_START(pmull_ghash_update_p64)
+SYM_TYPED_FUNC_START(pmull_ghash_update_p64)
 	__pmull_ghash	p64
 SYM_FUNC_END(pmull_ghash_update_p64)
 
-SYM_FUNC_START(pmull_ghash_update_p8)
+SYM_TYPED_FUNC_START(pmull_ghash_update_p8)
 	__pmull_ghash	p8
 SYM_FUNC_END(pmull_ghash_update_p8)
 

arch/arm64/crypto/sm3-ce-core.S

@@ -6,6 +6,7 @@
  */
 
 #include <linux/linkage.h>
+#include <linux/cfi_types.h>
 #include <asm/assembler.h>
 
 	.irp		b, 0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12
@@ -73,7 +74,7 @@
 	 *                       int blocks)
 	 */
 	.text
-SYM_FUNC_START(sm3_ce_transform)
+SYM_TYPED_FUNC_START(sm3_ce_transform)
 	/* load state */
 	ld1		{v8.4s-v9.4s}, [x0]
 	rev64		v8.4s, v8.4s

arch/arm64/include/asm/brk-imm.h

@@ -17,6 +17,7 @@
  * 0x401: for compile time BRK instruction
  * 0x800: kernel-mode BUG() and WARN() traps
  * 0x9xx: tag-based KASAN trap (allowed values 0x900 - 0x9ff)
+ * 0x8xxx: Control-Flow Integrity traps
  */
 #define KPROBES_BRK_IMM			0x004
 #define UPROBES_BRK_IMM			0x005
@@ -28,4 +29,9 @@
 #define KASAN_BRK_IMM			0x900
 #define KASAN_BRK_MASK			0x0ff
 
+#define CFI_BRK_IMM_TARGET		GENMASK(4, 0)
+#define CFI_BRK_IMM_TYPE		GENMASK(9, 5)
+#define CFI_BRK_IMM_BASE		0x8000
+#define CFI_BRK_IMM_MASK		(CFI_BRK_IMM_TARGET | CFI_BRK_IMM_TYPE)
+
 #endif

arch/arm64/include/asm/ftrace.h

@@ -26,7 +26,7 @@
 #ifdef CONFIG_DYNAMIC_FTRACE_WITH_REGS
 #define ARCH_SUPPORTS_FTRACE_OPS 1
 #else
-#define MCOUNT_ADDR		((unsigned long)function_nocfi(_mcount))
+#define MCOUNT_ADDR		((unsigned long)_mcount)
 #endif
 
 /* The BL at the callsite's adjusted rec->ip */

arch/arm64/include/asm/linkage.h

@@ -39,4 +39,8 @@
 	SYM_START(name, SYM_L_WEAK, SYM_A_NONE)		\
 	bti c ;
 
+#define SYM_TYPED_FUNC_START(name)				\
+	SYM_TYPED_START(name, SYM_L_GLOBAL, SYM_A_ALIGN)	\
+	bti c ;
+
 #endif

arch/arm64/include/asm/mmu_context.h

@@ -147,7 +147,7 @@ static inline void cpu_install_ttbr0(phys_addr_t ttbr0, unsigned long t0sz)
  * 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 __nocfi cpu_replace_ttbr1(pgd_t *pgdp, pgd_t *idmap)
+static inline void cpu_replace_ttbr1(pgd_t *pgdp, pgd_t *idmap)
 {
 	typedef void (ttbr_replace_func)(phys_addr_t);
 	extern ttbr_replace_func idmap_cpu_replace_ttbr1;
@@ -168,7 +168,7 @@ static inline void __nocfi cpu_replace_ttbr1(pgd_t *pgdp, pgd_t *idmap)
 		ttbr1 |= TTBR_CNP_BIT;
 	}
 
-	replace_phys = (void *)__pa_symbol(function_nocfi(idmap_cpu_replace_ttbr1));
+	replace_phys = (void *)__pa_symbol(idmap_cpu_replace_ttbr1);
 
 	__cpu_install_idmap(idmap);
 	replace_phys(ttbr1);

arch/arm64/kernel/acpi_parking_protocol.c

@@ -99,7 +99,7 @@ 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(function_nocfi(secondary_entry)),
+	writeq_relaxed(__pa_symbol(secondary_entry),
 		       &mailbox->entry_point);
 	writel_relaxed(cpu_entry->gic_cpu_id, &mailbox->cpu_id);
 

arch/arm64/kernel/alternative.c

@@ -133,7 +133,7 @@ static void clean_dcache_range_nopatch(u64 start, u64 end)
 	} while (cur += d_size, cur < end);
 }
 
-static void __nocfi __apply_alternatives(struct alt_region *region, bool is_module,
+static void __apply_alternatives(struct alt_region *region, bool is_module,
 				 unsigned long *feature_mask)
 {
 	struct alt_instr *alt;

arch/arm64/kernel/cpu-reset.S

@@ -8,6 +8,7 @@
  */
 
 #include <linux/linkage.h>
+#include <linux/cfi_types.h>
 #include <asm/assembler.h>
 #include <asm/sysreg.h>
 #include <asm/virt.h>
@@ -28,7 +29,7 @@
  * branch to what would be the reset vector. It must be executed with the
  * flat identity mapping.
  */
-SYM_CODE_START(cpu_soft_restart)
+SYM_TYPED_FUNC_START(cpu_soft_restart)
 	mov_q	x12, INIT_SCTLR_EL1_MMU_OFF
 	pre_disable_mmu_workaround
 	/*
@@ -47,6 +48,6 @@ SYM_CODE_START(cpu_soft_restart)
 	mov	x1, x3				// arg1
 	mov	x2, x4				// arg2
 	br	x8
-SYM_CODE_END(cpu_soft_restart)
+SYM_FUNC_END(cpu_soft_restart)
 
 .popsection

arch/arm64/kernel/cpufeature.c

@@ -1685,7 +1685,7 @@ static phys_addr_t kpti_ng_pgd_alloc(int shift)
 	return kpti_ng_temp_alloc;
 }
 
-static void __nocfi
+static void
 kpti_install_ng_mappings(const struct arm64_cpu_capabilities *__unused)
 {
 	typedef void (kpti_remap_fn)(int, int, phys_addr_t, unsigned long);
@@ -1713,7 +1713,7 @@ kpti_install_ng_mappings(const struct arm64_cpu_capabilities *__unused)
 	if (arm64_use_ng_mappings)
 		return;
 
-	remap_fn = (void *)__pa_symbol(function_nocfi(idmap_kpti_install_ng_mappings));
+	remap_fn = (void *)__pa_symbol(idmap_kpti_install_ng_mappings);
 
 	if (!cpu) {
 		alloc = __get_free_pages(GFP_ATOMIC | __GFP_ZERO, order);

arch/arm64/kernel/ftrace.c

@@ -56,7 +56,7 @@ int ftrace_update_ftrace_func(ftrace_func_t func)
 	unsigned long pc;
 	u32 new;
 
-	pc = (unsigned long)function_nocfi(ftrace_call);
+	pc = (unsigned long)ftrace_call;
 	new = aarch64_insn_gen_branch_imm(pc, (unsigned long)func,
 					  AARCH64_INSN_BRANCH_LINK);
 

arch/arm64/kernel/machine_kexec.c

@@ -204,7 +204,7 @@ void machine_kexec(struct kimage *kimage)
 		typeof(cpu_soft_restart) *restart;
 
 		cpu_install_idmap();
-		restart = (void *)__pa_symbol(function_nocfi(cpu_soft_restart));
+		restart = (void *)__pa_symbol(cpu_soft_restart);
 		restart(is_hyp_nvhe(), kimage->start, kimage->arch.dtb_mem,
 			0, 0);
 	} else {

arch/arm64/kernel/psci.c

@@ -38,7 +38,7 @@ static int __init cpu_psci_cpu_prepare(unsigned int cpu)
 
 static int cpu_psci_cpu_boot(unsigned int cpu)
 {
-	phys_addr_t pa_secondary_entry = __pa_symbol(function_nocfi(secondary_entry));
+	phys_addr_t pa_secondary_entry = __pa_symbol(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);

arch/arm64/kernel/smp_spin_table.c

@@ -66,7 +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));
+	phys_addr_t pa_holding_pen = __pa_symbol(secondary_holding_pen);
 
 	if (!cpu_release_addr[cpu])
 		return -ENODEV;

arch/arm64/kernel/traps.c

@@ -26,6 +26,7 @@
 #include <linux/syscalls.h>
 #include <linux/mm_types.h>
 #include <linux/kasan.h>
+#include <linux/cfi.h>
 
 #include <asm/atomic.h>
 #include <asm/bug.h>
@@ -991,6 +992,38 @@ static struct break_hook bug_break_hook = {
 	.imm = BUG_BRK_IMM,
 };
 
+#ifdef CONFIG_CFI_CLANG
+static int cfi_handler(struct pt_regs *regs, unsigned long esr)
+{
+	unsigned long target;
+	u32 type;
+
+	target = pt_regs_read_reg(regs, FIELD_GET(CFI_BRK_IMM_TARGET, esr));
+	type = (u32)pt_regs_read_reg(regs, FIELD_GET(CFI_BRK_IMM_TYPE, esr));
+
+	switch (report_cfi_failure(regs, regs->pc, &target, type)) {
+	case BUG_TRAP_TYPE_BUG:
+		die("Oops - CFI", regs, 0);
+		break;
+
+	case BUG_TRAP_TYPE_WARN:
+		break;
+
+	default:
+		return DBG_HOOK_ERROR;
+	}
+
+	arm64_skip_faulting_instruction(regs, AARCH64_INSN_SIZE);
+	return DBG_HOOK_HANDLED;
+}
+
+static struct break_hook cfi_break_hook = {
+	.fn = cfi_handler,
+	.imm = CFI_BRK_IMM_BASE,
+	.mask = CFI_BRK_IMM_MASK,
+};
+#endif /* CONFIG_CFI_CLANG */
+
 static int reserved_fault_handler(struct pt_regs *regs, unsigned long esr)
 {
 	pr_err("%s generated an invalid instruction at %pS!\n",
@@ -1052,17 +1085,22 @@ static struct break_hook kasan_break_hook = {
 };
 #endif
 
+
+#define esr_comment(esr) ((esr) & ESR_ELx_BRK64_ISS_COMMENT_MASK)
+
 /*
  * Initial handler for AArch64 BRK exceptions
  * This handler only used until debug_traps_init().
  */
 int __init early_brk64(unsigned long addr, unsigned long esr,
 		struct pt_regs *regs)
 {
+#ifdef CONFIG_CFI_CLANG
+	if ((esr_comment(esr) & ~CFI_BRK_IMM_MASK) == CFI_BRK_IMM_BASE)
+		return cfi_handler(regs, esr) != DBG_HOOK_HANDLED;
+#endif
 #ifdef CONFIG_KASAN_SW_TAGS
-	unsigned long comment = esr & ESR_ELx_BRK64_ISS_COMMENT_MASK;
-
-	if ((comment & ~KASAN_BRK_MASK) == KASAN_BRK_IMM)
+	if ((esr_comment(esr) & ~KASAN_BRK_MASK) == KASAN_BRK_IMM)
 		return kasan_handler(regs, esr) != DBG_HOOK_HANDLED;
 #endif
 	return bug_handler(regs, esr) != DBG_HOOK_HANDLED;
@@ -1071,6 +1109,9 @@ int __init early_brk64(unsigned long addr, unsigned long esr,
 void __init trap_init(void)
 {
 	register_kernel_break_hook(&bug_break_hook);
+#ifdef CONFIG_CFI_CLANG
+	register_kernel_break_hook(&cfi_break_hook);
+#endif
 	register_kernel_break_hook(&fault_break_hook);
 #ifdef CONFIG_KASAN_SW_TAGS
 	register_kernel_break_hook(&kasan_break_hook);

arch/arm64/kernel/vdso/Makefile

@@ -40,7 +40,8 @@ ccflags-y += -DDISABLE_BRANCH_PROFILING -DBUILD_VDSO
 # kernel with CONFIG_WERROR enabled.
 CFLAGS_REMOVE_vgettimeofday.o = $(CC_FLAGS_FTRACE) -Os $(CC_FLAGS_SCS) \
 				$(RANDSTRUCT_CFLAGS) $(GCC_PLUGINS_CFLAGS) \
-				$(CC_FLAGS_LTO) -Wmissing-prototypes -Wmissing-declarations
+				$(CC_FLAGS_LTO) $(CC_FLAGS_CFI) \
+				-Wmissing-prototypes -Wmissing-declarations
 KASAN_SANITIZE			:= n
 KCSAN_SANITIZE			:= n
 UBSAN_SANITIZE			:= n

arch/arm64/mm/proc.S

@@ -10,6 +10,7 @@
 #include <linux/init.h>
 #include <linux/linkage.h>
 #include <linux/pgtable.h>
+#include <linux/cfi_types.h>
 #include <asm/assembler.h>
 #include <asm/asm-offsets.h>
 #include <asm/asm_pointer_auth.h>
@@ -185,7 +186,7 @@ SYM_FUNC_END(cpu_do_resume)
  * This is the low-level counterpart to cpu_replace_ttbr1, and should not be
  * called by anything else. It can only be executed from a TTBR0 mapping.
  */
-SYM_FUNC_START(idmap_cpu_replace_ttbr1)
+SYM_TYPED_FUNC_START(idmap_cpu_replace_ttbr1)
 	save_and_disable_daif flags=x2
 
 	__idmap_cpu_set_reserved_ttbr1 x1, x3
@@ -253,7 +254,7 @@ SYM_FUNC_END(idmap_cpu_replace_ttbr1)
 SYM_DATA(__idmap_kpti_flag, .long 1)
 	.popsection
 
-SYM_FUNC_START(idmap_kpti_install_ng_mappings)
+SYM_TYPED_FUNC_START(idmap_kpti_install_ng_mappings)
 	cpu		.req	w0
 	temp_pte	.req	x0
 	num_cpus	.req	w1

arch/x86/Kconfig

@@ -107,6 +107,8 @@ config X86
 	select ARCH_SUPPORTS_PAGE_TABLE_CHECK	if X86_64
 	select ARCH_SUPPORTS_NUMA_BALANCING	if X86_64
 	select ARCH_SUPPORTS_KMAP_LOCAL_FORCE_MAP	if NR_CPUS <= 4096
+	select ARCH_SUPPORTS_CFI_CLANG		if X86_64
+	select ARCH_USES_CFI_TRAPS		if X86_64 && CFI_CLANG
 	select ARCH_SUPPORTS_LTO_CLANG
 	select ARCH_SUPPORTS_LTO_CLANG_THIN
 	select ARCH_USE_BUILTIN_BSWAP

arch/x86/crypto/blowfish-x86_64-asm_64.S

@@ -6,6 +6,7 @@
  */
 
 #include <linux/linkage.h>
+#include <linux/cfi_types.h>
 
 .file "blowfish-x86_64-asm.S"
 .text
@@ -141,7 +142,7 @@ SYM_FUNC_START(__blowfish_enc_blk)
 	RET;
 SYM_FUNC_END(__blowfish_enc_blk)
 
-SYM_FUNC_START(blowfish_dec_blk)
+SYM_TYPED_FUNC_START(blowfish_dec_blk)
 	/* input:
 	 *	%rdi: ctx
 	 *	%rsi: dst
@@ -332,7 +333,7 @@ SYM_FUNC_START(__blowfish_enc_blk_4way)
 	RET;
 SYM_FUNC_END(__blowfish_enc_blk_4way)
 
-SYM_FUNC_START(blowfish_dec_blk_4way)
+SYM_TYPED_FUNC_START(blowfish_dec_blk_4way)
 	/* input:
 	 *	%rdi: ctx
 	 *	%rsi: dst