Merge branch kvm-arm64/el2-kcfi into kvmarm/next

* kvm-arm64/el2-kcfi:
  : kCFI support in the EL2 hypervisor, courtesy of Pierre-Clément Tosi
  :
  : Enable the usage fo CONFIG_CFI_CLANG (kCFI) for hardening indirect
  : branches in the EL2 hypervisor. Unlike kernel support for the feature,
  : CFI failures at EL2 are always fatal.
  KVM: arm64: nVHE: Support CONFIG_CFI_CLANG at EL2
  KVM: arm64: Introduce print_nvhe_hyp_panic helper
  arm64: Introduce esr_brk_comment, esr_is_cfi_brk
  KVM: arm64: VHE: Mark __hyp_call_panic __noreturn
  KVM: arm64: nVHE: gen-hyprel: Skip R_AARCH64_ABS32
  KVM: arm64: nVHE: Simplify invalid_host_el2_vect
  KVM: arm64: Fix __pkvm_init_switch_pgd call ABI
  KVM: arm64: Fix clobbered ELR in sync abort/SError
Signed-off-by: Oliver Upton <oliver.upton@linux.dev>

arch/arm64/include/asm/esr.h

@@ -380,6 +380,11 @@
 #ifndef __ASSEMBLY__
 #include <asm/types.h>
 
+static inline unsigned long esr_brk_comment(unsigned long esr)
+{
+	return esr & ESR_ELx_BRK64_ISS_COMMENT_MASK;
+}
+
 static inline bool esr_is_data_abort(unsigned long esr)
 {
 	const unsigned long ec = ESR_ELx_EC(esr);
@@ -387,6 +392,12 @@ static inline bool esr_is_data_abort(unsigned long esr)
 	return ec == ESR_ELx_EC_DABT_LOW || ec == ESR_ELx_EC_DABT_CUR;
 }
 
+static inline bool esr_is_cfi_brk(unsigned long esr)
+{
+	return ESR_ELx_EC(esr) == ESR_ELx_EC_BRK64 &&
+	       (esr_brk_comment(esr) & ~CFI_BRK_IMM_MASK) == CFI_BRK_IMM_BASE;
+}
+
 static inline bool esr_fsc_is_translation_fault(unsigned long esr)
 {
 	/* Translation fault, level -1 */

arch/arm64/include/asm/kvm_hyp.h

@@ -124,8 +124,8 @@ void __noreturn __hyp_do_panic(struct kvm_cpu_context *host_ctxt, u64 spsr,
 #endif
 
 #ifdef __KVM_NVHE_HYPERVISOR__
-void __pkvm_init_switch_pgd(phys_addr_t phys, unsigned long size,
-			    phys_addr_t pgd, void *sp, void *cont_fn);
+void __pkvm_init_switch_pgd(phys_addr_t pgd, unsigned long sp,
+		void (*fn)(void));
 int __pkvm_init(phys_addr_t phys, unsigned long size, unsigned long nr_cpus,
 		unsigned long *per_cpu_base, u32 hyp_va_bits);
 void __noreturn __host_enter(struct kvm_cpu_context *host_ctxt);

arch/arm64/kernel/asm-offsets.c

@@ -128,6 +128,7 @@ int main(void)
   DEFINE(VCPU_FAULT_DISR,	offsetof(struct kvm_vcpu, arch.fault.disr_el1));
   DEFINE(VCPU_HCR_EL2,		offsetof(struct kvm_vcpu, arch.hcr_el2));
   DEFINE(CPU_USER_PT_REGS,	offsetof(struct kvm_cpu_context, regs));
+  DEFINE(CPU_ELR_EL2,		offsetof(struct kvm_cpu_context, sys_regs[ELR_EL2]));
   DEFINE(CPU_RGSR_EL1,		offsetof(struct kvm_cpu_context, sys_regs[RGSR_EL1]));
   DEFINE(CPU_GCR_EL1,		offsetof(struct kvm_cpu_context, sys_regs[GCR_EL1]));
   DEFINE(CPU_APIAKEYLO_EL1,	offsetof(struct kvm_cpu_context, sys_regs[APIAKEYLO_EL1]));

arch/arm64/kernel/debug-monitors.c

@@ -312,9 +312,7 @@ static int call_break_hook(struct pt_regs *regs, unsigned long esr)
 	 * entirely not preemptible, and we can use rcu list safely here.
 	 */
 	list_for_each_entry_rcu(hook, list, node) {
-		unsigned long comment = esr & ESR_ELx_BRK64_ISS_COMMENT_MASK;
-
-		if ((comment & ~hook->mask) == hook->imm)
+		if ((esr_brk_comment(esr) & ~hook->mask) == hook->imm)
 			fn = hook->fn;
 	}
 

arch/arm64/kernel/traps.c

@@ -1105,8 +1105,6 @@ static struct break_hook ubsan_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().
@@ -1115,15 +1113,15 @@ 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)
+	if (esr_is_cfi_brk(esr))
 		return cfi_handler(regs, esr) != DBG_HOOK_HANDLED;
 #endif
 #ifdef CONFIG_KASAN_SW_TAGS
-	if ((esr_comment(esr) & ~KASAN_BRK_MASK) == KASAN_BRK_IMM)
+	if ((esr_brk_comment(esr) & ~KASAN_BRK_MASK) == KASAN_BRK_IMM)
 		return kasan_handler(regs, esr) != DBG_HOOK_HANDLED;
 #endif
 #ifdef CONFIG_UBSAN_TRAP
-	if ((esr_comment(esr) & ~UBSAN_BRK_MASK) == UBSAN_BRK_IMM)
+	if ((esr_brk_comment(esr) & ~UBSAN_BRK_MASK) == UBSAN_BRK_IMM)
 		return ubsan_handler(regs, esr) != DBG_HOOK_HANDLED;
 #endif
 	return bug_handler(regs, esr) != DBG_HOOK_HANDLED;

arch/arm64/kvm/handle_exit.c

@@ -411,6 +411,20 @@ void handle_exit_early(struct kvm_vcpu *vcpu, int exception_index)
 		kvm_handle_guest_serror(vcpu, kvm_vcpu_get_esr(vcpu));
 }
 
+static void print_nvhe_hyp_panic(const char *name, u64 panic_addr)
+{
+	kvm_err("nVHE hyp %s at: [<%016llx>] %pB!\n", name, panic_addr,
+		(void *)(panic_addr + kaslr_offset()));
+}
+
+static void kvm_nvhe_report_cfi_failure(u64 panic_addr)
+{
+	print_nvhe_hyp_panic("CFI failure", panic_addr);
+
+	if (IS_ENABLED(CONFIG_CFI_PERMISSIVE))
+		kvm_err(" (CONFIG_CFI_PERMISSIVE ignored for hyp failures)\n");
+}
+
 void __noreturn __cold nvhe_hyp_panic_handler(u64 esr, u64 spsr,
 					      u64 elr_virt, u64 elr_phys,
 					      u64 par, uintptr_t vcpu,
@@ -423,7 +437,7 @@ void __noreturn __cold nvhe_hyp_panic_handler(u64 esr, u64 spsr,
 	if (mode != PSR_MODE_EL2t && mode != PSR_MODE_EL2h) {
 		kvm_err("Invalid host exception to nVHE hyp!\n");
 	} else if (ESR_ELx_EC(esr) == ESR_ELx_EC_BRK64 &&
-		   (esr & ESR_ELx_BRK64_ISS_COMMENT_MASK) == BUG_BRK_IMM) {
+		   esr_brk_comment(esr) == BUG_BRK_IMM) {
 		const char *file = NULL;
 		unsigned int line = 0;
 
@@ -439,11 +453,11 @@ void __noreturn __cold nvhe_hyp_panic_handler(u64 esr, u64 spsr,
 		if (file)
 			kvm_err("nVHE hyp BUG at: %s:%u!\n", file, line);
 		else
-			kvm_err("nVHE hyp BUG at: [<%016llx>] %pB!\n", panic_addr,
-					(void *)(panic_addr + kaslr_offset()));
+			print_nvhe_hyp_panic("BUG", panic_addr);
+	} else if (IS_ENABLED(CONFIG_CFI_CLANG) && esr_is_cfi_brk(esr)) {
+		kvm_nvhe_report_cfi_failure(panic_addr);
 	} else {
-		kvm_err("nVHE hyp panic at: [<%016llx>] %pB!\n", panic_addr,
-				(void *)(panic_addr + kaslr_offset()));
+		print_nvhe_hyp_panic("panic", panic_addr);
 	}
 
 	/* Dump the nVHE hypervisor backtrace */

arch/arm64/kvm/hyp/entry.S

@@ -83,6 +83,14 @@ alternative_else_nop_endif
 	eret
 	sb
 
+SYM_INNER_LABEL(__guest_exit_restore_elr_and_panic, SYM_L_GLOBAL)
+	// x2-x29,lr: vcpu regs
+	// vcpu x0-x1 on the stack
+
+	adr_this_cpu x0, kvm_hyp_ctxt, x1
+	ldr	x0, [x0, #CPU_ELR_EL2]
+	msr	elr_el2, x0
+
 SYM_INNER_LABEL(__guest_exit_panic, SYM_L_GLOBAL)
 	// x2-x29,lr: vcpu regs
 	// vcpu x0-x1 on the stack

arch/arm64/kvm/hyp/include/hyp/switch.h

@@ -693,7 +693,7 @@ static inline bool fixup_guest_exit(struct kvm_vcpu *vcpu, u64 *exit_code)
 
 static inline void __kvm_unexpected_el2_exception(void)
 {
-	extern char __guest_exit_panic[];
+	extern char __guest_exit_restore_elr_and_panic[];
 	unsigned long addr, fixup;
 	struct kvm_exception_table_entry *entry, *end;
 	unsigned long elr_el2 = read_sysreg(elr_el2);
@@ -715,7 +715,8 @@ static inline void __kvm_unexpected_el2_exception(void)
 	}
 
 	/* Trigger a panic after restoring the hyp context. */
-	write_sysreg(__guest_exit_panic, elr_el2);
+	this_cpu_ptr(&kvm_hyp_ctxt)->sys_regs[ELR_EL2] = elr_el2;
+	write_sysreg(__guest_exit_restore_elr_and_panic, elr_el2);
 }
 
 #endif /* __ARM64_KVM_HYP_SWITCH_H__ */

arch/arm64/kvm/hyp/nvhe/Makefile

@@ -89,9 +89,9 @@ quiet_cmd_hyprel = HYPREL  $@
 quiet_cmd_hypcopy = HYPCOPY $@
       cmd_hypcopy = $(OBJCOPY) --prefix-symbols=__kvm_nvhe_ $< $@
 
-# Remove ftrace, Shadow Call Stack, and CFI CFLAGS.
-# This is equivalent to the 'notrace', '__noscs', and '__nocfi' annotations.
-KBUILD_CFLAGS := $(filter-out $(CC_FLAGS_FTRACE) $(CC_FLAGS_SCS) $(CC_FLAGS_CFI), $(KBUILD_CFLAGS))
+# Remove ftrace and Shadow Call Stack CFLAGS.
+# This is equivalent to the 'notrace' and '__noscs' annotations.
+KBUILD_CFLAGS := $(filter-out $(CC_FLAGS_FTRACE) $(CC_FLAGS_SCS), $(KBUILD_CFLAGS))
 # Starting from 13.0.0 llvm emits SHT_REL section '.llvm.call-graph-profile'
 # when profile optimization is applied. gen-hyprel does not support SHT_REL and
 # causes a build failure. Remove profile optimization flags.

arch/arm64/kvm/hyp/nvhe/gen-hyprel.c

@@ -50,6 +50,9 @@
 #ifndef R_AARCH64_ABS64
 #define R_AARCH64_ABS64			257
 #endif
+#ifndef R_AARCH64_ABS32
+#define R_AARCH64_ABS32			258
+#endif
 #ifndef R_AARCH64_PREL64
 #define R_AARCH64_PREL64		260
 #endif
@@ -383,6 +386,9 @@ static void emit_rela_section(Elf64_Shdr *sh_rela)
 		case R_AARCH64_ABS64:
 			emit_rela_abs64(rela, sh_orig_name);
 			break;
+		/* Allow 32-bit absolute relocation, for kCFI type hashes. */
+		case R_AARCH64_ABS32:
+			break;
 		/* Allow position-relative data relocations. */
 		case R_AARCH64_PREL64:
 		case R_AARCH64_PREL32:

arch/arm64/kvm/hyp/nvhe/host.S

@@ -197,12 +197,6 @@ SYM_FUNC_END(__host_hvc)
 	sub	x0, sp, x0			// x0'' = sp' - x0' = (sp + x0) - sp = x0
 	sub	sp, sp, x0			// sp'' = sp' - x0 = (sp + x0) - x0 = sp
 
-	/* If a guest is loaded, panic out of it. */
-	stp	x0, x1, [sp, #-16]!
-	get_loaded_vcpu x0, x1
-	cbnz	x0, __guest_exit_panic
-	add	sp, sp, #16
-
 	/*
 	 * The panic may not be clean if the exception is taken before the host
 	 * context has been saved by __host_exit or after the hyp context has

arch/arm64/kvm/hyp/nvhe/hyp-init.S

@@ -5,6 +5,7 @@
  */
 
 #include <linux/arm-smccc.h>
+#include <linux/cfi_types.h>
 #include <linux/linkage.h>
 
 #include <asm/alternative.h>
@@ -265,33 +266,38 @@ alternative_else_nop_endif
 
 SYM_CODE_END(__kvm_handle_stub_hvc)
 
-SYM_FUNC_START(__pkvm_init_switch_pgd)
+/*
+ * void __pkvm_init_switch_pgd(phys_addr_t pgd, unsigned long sp,
+ *                             void (*fn)(void));
+ *
+ * SYM_TYPED_FUNC_START() allows C to call this ID-mapped function indirectly
+ * using a physical pointer without triggering a kCFI failure.
+ */
+SYM_TYPED_FUNC_START(__pkvm_init_switch_pgd)
 	/* Turn the MMU off */
 	pre_disable_mmu_workaround
-	mrs	x2, sctlr_el2
-	bic	x3, x2, #SCTLR_ELx_M
-	msr	sctlr_el2, x3
+	mrs	x3, sctlr_el2
+	bic	x4, x3, #SCTLR_ELx_M
+	msr	sctlr_el2, x4
 	isb
 
 	tlbi	alle2
 
 	/* Install the new pgtables */
-	ldr	x3, [x0, #NVHE_INIT_PGD_PA]
-	phys_to_ttbr x4, x3
+	phys_to_ttbr x5, x0
 alternative_if ARM64_HAS_CNP
-	orr	x4, x4, #TTBR_CNP_BIT
+	orr	x5, x5, #TTBR_CNP_BIT
 alternative_else_nop_endif
-	msr	ttbr0_el2, x4
+	msr	ttbr0_el2, x5
 
 	/* Set the new stack pointer */
-	ldr	x0, [x0, #NVHE_INIT_STACK_HYP_VA]
-	mov	sp, x0
+	mov	sp, x1
 
 	/* And turn the MMU back on! */
 	dsb	nsh
 	isb
-	set_sctlr_el2	x2
-	ret	x1
+	set_sctlr_el2	x3
+	ret	x2
 SYM_FUNC_END(__pkvm_init_switch_pgd)
 
 	.popsection

arch/arm64/kvm/hyp/nvhe/setup.c

@@ -339,7 +339,7 @@ int __pkvm_init(phys_addr_t phys, unsigned long size, unsigned long nr_cpus,
 {
 	struct kvm_nvhe_init_params *params;
 	void *virt = hyp_phys_to_virt(phys);
-	void (*fn)(phys_addr_t params_pa, void *finalize_fn_va);
+	typeof(__pkvm_init_switch_pgd) *fn;
 	int ret;
 
 	BUG_ON(kvm_check_pvm_sysreg_table());
@@ -363,7 +363,7 @@ int __pkvm_init(phys_addr_t phys, unsigned long size, unsigned long nr_cpus,
 	/* Jump in the idmap page to switch to the new page-tables */
 	params = this_cpu_ptr(&kvm_init_params);
 	fn = (typeof(fn))__hyp_pa(__pkvm_init_switch_pgd);
-	fn(__hyp_pa(params), __pkvm_init_finalise);
+	fn(params->pgd_pa, params->stack_hyp_va, __pkvm_init_finalise);
 
 	unreachable();
 }

arch/arm64/kvm/hyp/vhe/switch.c

@@ -437,7 +437,7 @@ int __kvm_vcpu_run(struct kvm_vcpu *vcpu)
 	return ret;
 }
 
-static void __hyp_call_panic(u64 spsr, u64 elr, u64 par)
+static void __noreturn __hyp_call_panic(u64 spsr, u64 elr, u64 par)
 {
 	struct kvm_cpu_context *host_ctxt;
 	struct kvm_vcpu *vcpu;
@@ -462,7 +462,6 @@ void __noreturn hyp_panic(void)
 	u64 par = read_sysreg_par();
 
 	__hyp_call_panic(spsr, elr, par);
-	unreachable();
 }
 
 asmlinkage void kvm_unexpected_el2_exception(void)