arm64: head: move dynamic shadow call stack patching into early C runtime

Once we update the early kernel mapping code to only map the kernel once
with the right permissions, we can no longer perform code patching via
this mapping.

So move this code to an earlier stage of the boot, right after applying
the relocations.

Signed-off-by: Ard Biesheuvel <ardb@kernel.org>
Link: https://lore.kernel.org/r/20240214122845.2033971-54-ardb+git@google.com
Signed-off-by: Catalin Marinas <catalin.marinas@arm.com>

6 files changed, 27 insertions, 31 deletions

diff --git a/arch/arm64/include/asm/scs.h b/arch/arm64/include/asm/scs.h
index 3fdae5fe3142..eca2ba5a6276 100644
--- a/arch/arm64/include/asm/scs.h
+++ b/arch/arm64/include/asm/scs.h
@@ -72,8 +72,8 @@ static inline void dynamic_scs_init(void)
 static inline void dynamic_scs_init(void) {}
 #endif
 
-int scs_patch(const u8 eh_frame[], int size);
-asmlinkage void scs_patch_vmlinux(void);
+int __pi_scs_patch(const u8 eh_frame[], int size);
+asmlinkage void __pi_scs_patch_vmlinux(void);
 
 #endif /* __ASSEMBLY __ */
 
diff --git a/arch/arm64/kernel/Makefile b/arch/arm64/kernel/Makefile
index 4236f1e0fffa..14b4a179bad3 100644
--- a/arch/arm64/kernel/Makefile
+++ b/arch/arm64/kernel/Makefile
@@ -71,14 +71,6 @@ obj-$(CONFIG_ARM64_PTR_AUTH)		+= pointer_auth.o
 obj-$(CONFIG_ARM64_MTE)			+= mte.o
 obj-y					+= vdso-wrap.o
 obj-$(CONFIG_COMPAT_VDSO)		+= vdso32-wrap.o
-obj-$(CONFIG_UNWIND_PATCH_PAC_INTO_SCS)	+= patch-scs.o
-
-# We need to prevent the SCS patching code from patching itself. Using
-# -mbranch-protection=none here to avoid the patchable PAC opcodes from being
-# generated triggers an issue with full LTO on Clang, which stops emitting PAC
-# instructions altogether. So disable LTO as well for the compilation unit.
-CFLAGS_patch-scs.o			+= -mbranch-protection=none
-CFLAGS_REMOVE_patch-scs.o		+= $(CC_FLAGS_LTO)
 
 # Force dependency (vdso*-wrap.S includes vdso.so through incbin)
 $(obj)/vdso-wrap.o: $(obj)/vdso/vdso.so
diff --git a/arch/arm64/kernel/head.S b/arch/arm64/kernel/head.S
index 865ecc1f8255..b320702032a7 100644
--- a/arch/arm64/kernel/head.S
+++ b/arch/arm64/kernel/head.S
@@ -491,9 +491,6 @@ SYM_FUNC_START_LOCAL(__primary_switched)
 #if defined(CONFIG_KASAN_GENERIC) || defined(CONFIG_KASAN_SW_TAGS)
 	bl	kasan_early_init
 #endif
-#ifdef CONFIG_UNWIND_PATCH_PAC_INTO_SCS
-	bl	scs_patch_vmlinux
-#endif
 	mov	x0, x20
 	bl	finalise_el2			// Prefer VHE if possible
 	ldp	x29, x30, [sp], #16
@@ -795,6 +792,11 @@ SYM_FUNC_START_LOCAL(__primary_switch)
 	mov	x0, x23
 	bl	__pi_relocate_kernel
 #endif
+#ifdef CONFIG_UNWIND_PATCH_PAC_INTO_SCS
+	ldr	x0, =__eh_frame_start
+	ldr	x1, =__eh_frame_end
+	bl	__pi_scs_patch_vmlinux
+#endif
 	ldr	x8, =__primary_switched
 	adrp	x0, KERNEL_START		// __pa(KERNEL_START)
 	br	x8
diff --git a/arch/arm64/kernel/module.c b/arch/arm64/kernel/module.c
index dd851297596e..47e0be610bb6 100644
--- a/arch/arm64/kernel/module.c
+++ b/arch/arm64/kernel/module.c
@@ -595,7 +595,7 @@ int module_finalize(const Elf_Ehdr *hdr,
 	if (scs_is_dynamic()) {
 		s = find_section(hdr, sechdrs, ".init.eh_frame");
 		if (s)
-			scs_patch((void *)s->sh_addr, s->sh_size);
+			__pi_scs_patch((void *)s->sh_addr, s->sh_size);
 	}
 
 	return module_init_ftrace_plt(hdr, sechdrs, me);
diff --git a/arch/arm64/kernel/pi/Makefile b/arch/arm64/kernel/pi/Makefile
index 7f6dfce893c3..a8b302245f15 100644
--- a/arch/arm64/kernel/pi/Makefile
+++ b/arch/arm64/kernel/pi/Makefile
@@ -38,7 +38,9 @@ $(obj)/lib-%.pi.o: OBJCOPYFLAGS += --prefix-alloc-sections=.init
 $(obj)/lib-%.o: $(srctree)/lib/%.c FORCE
 	$(call if_changed_rule,cc_o_c)
 
-obj-y				:= idreg-override.pi.o lib-fdt.pi.o lib-fdt_ro.pi.o
-obj-$(CONFIG_RELOCATABLE)	+= relocate.pi.o
-obj-$(CONFIG_RANDOMIZE_BASE)	+= kaslr_early.pi.o
-extra-y				:= $(patsubst %.pi.o,%.o,$(obj-y))
+obj-y					:= idreg-override.pi.o \
+					   lib-fdt.pi.o lib-fdt_ro.pi.o
+obj-$(CONFIG_RELOCATABLE)		+= relocate.pi.o
+obj-$(CONFIG_RANDOMIZE_BASE)		+= kaslr_early.pi.o
+obj-$(CONFIG_UNWIND_PATCH_PAC_INTO_SCS)	+= patch-scs.pi.o
+extra-y					:= $(patsubst %.pi.o,%.o,$(obj-y))
diff --git a/arch/arm64/kernel/patch-scs.c b/arch/arm64/kernel/pi/patch-scs.c
index a1fe4b4ff591..c65ef40d1e6b 100644
--- a/arch/arm64/kernel/patch-scs.c
+++ b/arch/arm64/kernel/pi/patch-scs.c
@@ -4,14 +4,11 @@
  * Author: Ard Biesheuvel <ardb@google.com>
  */
 
-#include <linux/bug.h>
 #include <linux/errno.h>
 #include <linux/init.h>
 #include <linux/linkage.h>
-#include <linux/printk.h>
 #include <linux/types.h>
 
-#include <asm/cacheflush.h>
 #include <asm/scs.h>
 
 //
@@ -81,7 +78,11 @@ static void __always_inline scs_patch_loc(u64 loc)
 		 */
 		return;
 	}
-	dcache_clean_pou(loc, loc + sizeof(u32));
+	if (IS_ENABLED(CONFIG_ARM64_WORKAROUND_CLEAN_CACHE))
+		asm("dc civac, %0" :: "r"(loc));
+	else
+		asm(ALTERNATIVE("dc cvau, %0", "nop", ARM64_HAS_CACHE_IDC)
+		    :: "r"(loc));
 }
 
 /*
@@ -128,10 +129,10 @@ struct eh_frame {
 	};
 };
 
-static int noinstr scs_handle_fde_frame(const struct eh_frame *frame,
-					bool fde_has_augmentation_data,
-					int code_alignment_factor,
-					bool dry_run)
+static int scs_handle_fde_frame(const struct eh_frame *frame,
+				bool fde_has_augmentation_data,
+				int code_alignment_factor,
+				bool dry_run)
 {
 	int size = frame->size - offsetof(struct eh_frame, opcodes) + 4;
 	u64 loc = (u64)offset_to_ptr(&frame->initial_loc);
@@ -198,14 +199,13 @@ static int noinstr scs_handle_fde_frame(const struct eh_frame *frame,
 			break;
 
 		default:
-			pr_err("unhandled opcode: %02x in FDE frame %lx\n", opcode[-1], (uintptr_t)frame);
 			return -ENOEXEC;
 		}
 	}
 	return 0;
 }
 
-int noinstr scs_patch(const u8 eh_frame[], int size)
+int scs_patch(const u8 eh_frame[], int size)
 {
 	const u8 *p = eh_frame;
 
@@ -251,12 +251,12 @@ int noinstr scs_patch(const u8 eh_frame[], int size)
 	return 0;
 }
 
-asmlinkage void __init scs_patch_vmlinux(void)
+asmlinkage void __init scs_patch_vmlinux(const u8 start[], const u8 end[])
 {
 	if (!should_patch_pac_into_scs())
 		return;
 
-	WARN_ON(scs_patch(__eh_frame_start, __eh_frame_end - __eh_frame_start));
-	icache_inval_all_pou();
+	scs_patch(start, end - start);
+	asm("ic ialluis");
 	isb();
 }