diff mbox series

[v7,27/33] arm64: head: Move early kernel mapping routines into C code

Message ID 20221111171201.2088501-28-ardb@kernel.org (mailing list archive)
State New, archived
Headers show
Series arm64: robustify boot sequence and add support for WXN | expand

Commit Message

Ard Biesheuvel Nov. 11, 2022, 5:11 p.m. UTC
The asm version of the kernel mapping code works fine for creating a
coarse grained identity map, but for mapping the kernel down to its
exact boundaries with the right attributes, it is not suitable. This is
why we create a preliminary RWX kernel mapping first, and then rebuild
it from scratch later on.

So let's reimplement this in C, in a way that will make it unnecessary
to create the kernel page tables yet another time in paging_init().

Signed-off-by: Ard Biesheuvel <ardb@kernel.org>
---
 arch/arm64/include/asm/scs.h          |  32 +--
 arch/arm64/kernel/head.S              |  52 +---
 arch/arm64/kernel/image-vars.h        |  16 ++
 arch/arm64/kernel/pi/Makefile         |   2 +-
 arch/arm64/kernel/pi/idreg-override.c |  24 +-
 arch/arm64/kernel/pi/kaslr_early.c    |  12 +-
 arch/arm64/kernel/pi/map_kernel.c     | 277 ++++++++++++++++++++
 arch/arm64/kernel/pi/patch-scs.c      |  16 +-
 arch/arm64/kernel/pi/pi.h             |  12 +
 arch/arm64/kernel/pi/relocate.c       |   2 +
 arch/arm64/kernel/setup.c             |   7 -
 arch/arm64/kernel/vmlinux.lds.S       |   6 +-
 arch/arm64/mm/proc.S                  |   1 +
 13 files changed, 338 insertions(+), 121 deletions(-)
diff mbox series

Patch

diff --git a/arch/arm64/include/asm/scs.h b/arch/arm64/include/asm/scs.h
index d20dcb2a1a5284ce..74744f4d6820f5e1 100644
--- a/arch/arm64/include/asm/scs.h
+++ b/arch/arm64/include/asm/scs.h
@@ -32,37 +32,11 @@ 
 #include <asm/cpufeature.h>
 
 #ifdef CONFIG_UNWIND_PATCH_PAC_INTO_SCS
-static inline bool should_patch_pac_into_scs(void)
-{
-	u64 reg;
-
-	/*
-	 * We only enable the shadow call stack dynamically if we are running
-	 * on a system that does not implement PAC or BTI. PAC and SCS provide
-	 * roughly the same level of protection, and BTI relies on the PACIASP
-	 * instructions serving as landing pads, preventing us from patching
-	 * those instructions into something else.
-	 */
-	reg = read_sysreg_s(SYS_ID_AA64ISAR1_EL1);
-	if (SYS_FIELD_GET(ID_AA64ISAR1_EL1, APA, reg) |
-	    SYS_FIELD_GET(ID_AA64ISAR1_EL1, API, reg))
-		return false;
-
-	reg = read_sysreg_s(SYS_ID_AA64ISAR2_EL1);
-	if (SYS_FIELD_GET(ID_AA64ISAR2_EL1, APA3, reg))
-		return false;
-
-	if (IS_ENABLED(CONFIG_ARM64_BTI_KERNEL)) {
-		reg = read_sysreg_s(SYS_ID_AA64PFR1_EL1);
-		if (reg & (0xf << ID_AA64PFR1_EL1_BT_SHIFT))
-			return false;
-	}
-	return true;
-}
-
 static inline void dynamic_scs_init(void)
 {
-	if (should_patch_pac_into_scs()) {
+	extern bool __pi_dynamic_scs_is_enabled;
+
+	if (__pi_dynamic_scs_is_enabled) {
 		pr_info("Enabling dynamic shadow call stack\n");
 		static_branch_enable(&dynamic_scs_enabled);
 	}
diff --git a/arch/arm64/kernel/head.S b/arch/arm64/kernel/head.S
index 4b88ca8766133fd3..6e730a0be1e8196d 100644
--- a/arch/arm64/kernel/head.S
+++ b/arch/arm64/kernel/head.S
@@ -80,7 +80,6 @@ 
 	 *  x20        primary_entry() .. __primary_switch()    CPU boot mode
 	 *  x21        primary_entry() .. start_kernel()        FDT pointer passed at boot in x0
 	 *  x22        create_idmap() .. start_kernel()         ID map VA of the DT blob
-	 *  x23        __primary_switch()                       physical misalignment/KASLR offset
 	 *  x25        primary_entry() .. start_kernel()        supported VA size
 	 *  x28        create_idmap()                           callee preserved temp register
 	 */
@@ -356,24 +355,6 @@  SYM_FUNC_START_LOCAL(create_idmap)
 	ret	x28
 SYM_FUNC_END(create_idmap)
 
-SYM_FUNC_START_LOCAL(create_kernel_mapping)
-	adrp	x0, init_pg_dir
-	mov_q	x5, KIMAGE_VADDR		// compile time __va(_text)
-#ifdef CONFIG_RELOCATABLE
-	add	x5, x5, x23			// add KASLR displacement
-#endif
-	adrp	x6, _end			// runtime __pa(_end)
-	adrp	x3, _text			// runtime __pa(_text)
-	sub	x6, x6, x3			// _end - _text
-	add	x6, x6, x5			// runtime __va(_end)
-	mov	x7, SWAPPER_RW_MMUFLAGS
-
-	map_memory x0, x1, x5, x6, x7, x3, (VA_BITS - PGDIR_SHIFT), x10, x11, x12, x13, x14
-
-	dsb	ishst				// sync with page table walker
-	ret
-SYM_FUNC_END(create_kernel_mapping)
-
 	/*
 	 * Initialize CPU registers with task-specific and cpu-specific context.
 	 *
@@ -678,44 +659,13 @@  SYM_FUNC_START_LOCAL(__primary_switch)
 	adrp	x2, init_idmap_pg_dir
 	bl	__enable_mmu
 
-	// Clear BSS
-	adrp	x0, __bss_start
-	mov	x1, xzr
-	adrp	x2, init_pg_end
-	sub	x2, x2, x0
-	bl	__pi_memset
-	dsb	ishst				// Make zero page visible to PTW
-
 	adrp	x1, early_init_stack
 	mov	sp, x1
 	mov	x29, xzr
 	mov	x0, x20				// pass the full boot status
 	mov	x1, x22				// pass the low FDT mapping
-	bl	__pi_init_feature_override	// Parse cpu feature overrides
-
-#ifdef CONFIG_RELOCATABLE
-	adrp	x23, KERNEL_START
-	and	x23, x23, MIN_KIMG_ALIGN - 1
-#ifdef CONFIG_RANDOMIZE_BASE
-	mov	x0, x22
-	bl	__pi_kaslr_early_init
-	bic	x0, x0, #SZ_2M - 1
-	orr	x23, x23, x0			// record kernel offset
-#endif
-#endif
-	bl	create_kernel_mapping
+	bl	__pi_early_map_kernel		// Map and relocate the kernel
 
-	adrp	x1, init_pg_dir
-	load_ttbr1 x1, x1, x2
-#ifdef CONFIG_RELOCATABLE
-	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/image-vars.h b/arch/arm64/kernel/image-vars.h
index 6c6dd100a9cbadf8..88f864f28f03630c 100644
--- a/arch/arm64/kernel/image-vars.h
+++ b/arch/arm64/kernel/image-vars.h
@@ -51,8 +51,24 @@  PROVIDE(__pi_id_aa64pfr1_override	= id_aa64pfr1_override);
 PROVIDE(__pi_id_aa64smfr0_override	= id_aa64smfr0_override);
 PROVIDE(__pi_id_aa64zfr0_override	= id_aa64zfr0_override);
 PROVIDE(__pi_arm64_sw_feature_override	= arm64_sw_feature_override);
+PROVIDE(__pi_arm64_use_ng_mappings	= arm64_use_ng_mappings);
 PROVIDE(__pi__ctype			= _ctype);
 
+PROVIDE(__pi_init_pg_dir		= init_pg_dir);
+PROVIDE(__pi_init_pg_end		= init_pg_end);
+PROVIDE(__pi__end			= _end);
+
+PROVIDE(__pi__text			= _text);
+PROVIDE(__pi__stext               	= _stext);
+PROVIDE(__pi__etext               	= _etext);
+PROVIDE(__pi___start_rodata       	= __start_rodata);
+PROVIDE(__pi___inittext_begin     	= __inittext_begin);
+PROVIDE(__pi___inittext_end       	= __inittext_end);
+PROVIDE(__pi___initdata_begin     	= __initdata_begin);
+PROVIDE(__pi___initdata_end       	= __initdata_end);
+PROVIDE(__pi__data                	= _data);
+PROVIDE(__pi___bss_start		= __bss_start);
+
 #ifdef CONFIG_KVM
 
 /*
diff --git a/arch/arm64/kernel/pi/Makefile b/arch/arm64/kernel/pi/Makefile
index 293a04a5dc3ef516..ac27f1cac6b89684 100644
--- a/arch/arm64/kernel/pi/Makefile
+++ b/arch/arm64/kernel/pi/Makefile
@@ -38,7 +38,7 @@  $(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 \
+obj-y					:= idreg-override.pi.o map_kernel.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
diff --git a/arch/arm64/kernel/pi/idreg-override.c b/arch/arm64/kernel/pi/idreg-override.c
index e524d36d8fc1526f..d0ce3dc4e07aaf4d 100644
--- a/arch/arm64/kernel/pi/idreg-override.c
+++ b/arch/arm64/kernel/pi/idreg-override.c
@@ -15,6 +15,8 @@ 
 #include <asm/cpufeature.h>
 #include <asm/setup.h>
 
+#include "pi.h"
+
 #define FTR_DESC_NAME_LEN	20	// must remain multiple of 4
 #define FTR_DESC_FIELD_LEN	10	// must remain multiple of 4 +/- 2
 #define FTR_ALIAS_NAME_LEN	30
@@ -296,37 +298,35 @@  static __init void __parse_cmdline(const char *cmdline, bool parse_aliases)
 	} while (1);
 }
 
-static __init const u8 *get_bootargs_cmdline(const void *fdt)
+static __init const u8 *get_bootargs_cmdline(const void *fdt, int node)
 {
+	static char const bootargs[] __initconst = "bootargs";
 	const u8 *prop;
-	int node;
 
-	node = fdt_path_offset(fdt, "/chosen");
 	if (node < 0)
 		return NULL;
 
-	prop = fdt_getprop(fdt, node, "bootargs", NULL);
+	prop = fdt_getprop(fdt, node, bootargs, NULL);
 	if (!prop)
 		return NULL;
 
 	return strlen(prop) ? prop : NULL;
 }
 
-static __init void parse_cmdline(const void *fdt)
+static __init void parse_cmdline(const void *fdt, int chosen)
 {
-	const u8 *prop = get_bootargs_cmdline(fdt);
+	static char const cmdline[] __initconst = CONFIG_CMDLINE;
+	const u8 *prop = get_bootargs_cmdline(fdt, chosen);
 
 	if (IS_ENABLED(CONFIG_CMDLINE_FORCE) || !prop)
-		__parse_cmdline(CONFIG_CMDLINE, true);
+		__parse_cmdline(cmdline, true);
 
 	if (!IS_ENABLED(CONFIG_CMDLINE_FORCE) && prop)
 		__parse_cmdline(prop, true);
 }
 
-/* Keep checkers quiet */
-void init_feature_override(u64 boot_status, const void *fdt);
-
-asmlinkage void __init init_feature_override(u64 boot_status, const void *fdt)
+void __init init_feature_override(u64 boot_status, const void *fdt,
+				  int chosen)
 {
 	int i;
 
@@ -337,7 +337,7 @@  asmlinkage void __init init_feature_override(u64 boot_status, const void *fdt)
 
 	__boot_status = boot_status;
 
-	parse_cmdline(fdt);
+	parse_cmdline(fdt, chosen);
 
 	for (i = 0; i < ARRAY_SIZE(regs); i++) {
 		dcache_clean_inval_poc((unsigned long)reg_override(i),
diff --git a/arch/arm64/kernel/pi/kaslr_early.c b/arch/arm64/kernel/pi/kaslr_early.c
index c46bccd593f2ff6b..965515f7f1809808 100644
--- a/arch/arm64/kernel/pi/kaslr_early.c
+++ b/arch/arm64/kernel/pi/kaslr_early.c
@@ -15,17 +15,17 @@ 
 #include <asm/archrandom.h>
 #include <asm/memory.h>
 
+#include "pi.h"
+
 extern u16 memstart_offset_seed;
 
-static u64 __init get_kaslr_seed(void *fdt)
+static u64 __init get_kaslr_seed(void *fdt, int node)
 {
-	static char const chosen_str[] __initconst = "chosen";
 	static char const seed_str[] __initconst = "kaslr-seed";
-	int node, len;
 	fdt64_t *prop;
 	u64 ret;
+	int len;
 
-	node = fdt_path_offset(fdt, chosen_str);
 	if (node < 0)
 		return 0;
 
@@ -38,7 +38,7 @@  static u64 __init get_kaslr_seed(void *fdt)
 	return ret;
 }
 
-asmlinkage u64 __init kaslr_early_init(void *fdt)
+u64 __init kaslr_early_init(void *fdt, int chosen)
 {
 	u64 seed;
 
@@ -46,7 +46,7 @@  asmlinkage u64 __init kaslr_early_init(void *fdt)
 						 ARM64_SW_FEATURE_OVERRIDE_NOKASLR))
 		return 0;
 
-	seed = get_kaslr_seed(fdt);
+	seed = get_kaslr_seed(fdt, chosen);
 	if (!seed) {
 		if (!__early_cpu_has_rndr() ||
 		    !__arm64_rndr((unsigned long *)&seed))
diff --git a/arch/arm64/kernel/pi/map_kernel.c b/arch/arm64/kernel/pi/map_kernel.c
new file mode 100644
index 0000000000000000..c5c6eebef684f81d
--- /dev/null
+++ b/arch/arm64/kernel/pi/map_kernel.c
@@ -0,0 +1,277 @@ 
+// SPDX-License-Identifier: GPL-2.0-only
+// Copyright 2022 Google LLC
+// Author: Ard Biesheuvel <ardb@google.com>
+
+#include <linux/init.h>
+#include <linux/libfdt.h>
+#include <linux/linkage.h>
+#include <linux/types.h>
+#include <linux/sizes.h>
+#include <linux/string.h>
+
+#include <asm/memory.h>
+#include <asm/pgalloc.h>
+#include <asm/pgtable.h>
+#include <asm/tlbflush.h>
+
+#include "pi.h"
+
+extern const u8 __eh_frame_start[], __eh_frame_end[];
+
+extern void idmap_cpu_replace_ttbr1(void *pgdir);
+
+static void __init map_range(pgd_t **pgd, u64 start, u64 end, u64 pa,
+			     pgprot_t prot, int level, pte_t *tbl,
+			     bool may_use_cont)
+{
+	u64 cmask = (level == 3) ? CONT_PTE_SIZE - 1 : U64_MAX;
+	u64 protval = pgprot_val(prot) & ~PTE_TYPE_MASK;
+	int lshift = (3 - level) * (PAGE_SHIFT - 3);
+	u64 lmask = (PAGE_SIZE << lshift) - 1;
+
+	/* Advance tbl to the entry that covers start */
+	tbl += (start >> (lshift + PAGE_SHIFT)) % BIT(PAGE_SHIFT - 3);
+
+	/*
+	 * Set the right block/page bits for this level unless we are
+	 * clearing the mapping
+	 */
+	if (protval)
+		protval |= (level < 3) ? PMD_TYPE_SECT : PTE_TYPE_PAGE;
+
+	while (start < end) {
+		u64 next = min((start | lmask) + 1, end);
+
+		if (level < 3 && (start | next | pa) & lmask) {
+			/*
+			 * This chunk needs a finer grained mapping. Put down
+			 * a table mapping if necessary and recurse.
+			 */
+			if (pte_none(*tbl)) {
+				*tbl = __pte(__phys_to_pte_val((u64)*pgd) |
+					     PMD_TYPE_TABLE | PMD_TABLE_UXN);
+				*pgd += PTRS_PER_PTE;
+			}
+			map_range(pgd, start, next, pa, prot, level + 1,
+				  (pte_t *)__pte_to_phys(*tbl), may_use_cont);
+		} else {
+			/*
+			 * Start a contiguous range if start and pa are
+			 * suitably aligned
+			 */
+			if (((start | pa) & cmask) == 0 && may_use_cont)
+				protval |= PTE_CONT;
+
+			/*
+			 * Clear the contiguous attribute if the remaining
+			 * range does not cover a contiguous block
+			 */
+			if ((end & ~cmask) <= start)
+				protval &= ~PTE_CONT;
+
+			/* Put down a block or page mapping */
+			*tbl = __pte(__phys_to_pte_val(pa) | protval);
+		}
+		pa += next - start;
+		start = next;
+		tbl++;
+	}
+}
+
+static void __init map_segment(pgd_t **pgd, u64 va_offset, void *start,
+			       void *end, pgprot_t prot, bool may_use_cont)
+{
+	map_range(pgd, ((u64)start + va_offset) & ~PAGE_OFFSET,
+		  ((u64)end + va_offset) & ~PAGE_OFFSET, (u64)start,
+		  prot, 4 - CONFIG_PGTABLE_LEVELS, (pte_t *)init_pg_dir,
+		  may_use_cont);
+}
+
+static void __init unmap_segment(u64 va_offset, void *start, void *end)
+{
+	map_range(NULL, ((u64)start + va_offset) & ~PAGE_OFFSET,
+		  ((u64)end + va_offset) & ~PAGE_OFFSET, (u64)start,
+		  __pgprot(0), 4 - CONFIG_PGTABLE_LEVELS, (pte_t *)init_pg_dir,
+		  false);
+}
+
+static bool __init arm64_early_this_cpu_has_bti(void)
+{
+	u64 pfr1;
+
+	if (!IS_ENABLED(CONFIG_ARM64_BTI_KERNEL))
+		return false;
+
+	pfr1 = read_sysreg(ID_AA64PFR1_EL1);
+	pfr1 &= ~id_aa64pfr1_override.mask;
+	pfr1 |= id_aa64pfr1_override.val;
+
+	return cpuid_feature_extract_unsigned_field(pfr1,
+						    ID_AA64PFR1_EL1_BT_SHIFT);
+}
+
+static bool __init arm64_early_this_cpu_has_e0pd(void)
+{
+	u64 mmfr2;
+
+	if (!IS_ENABLED(CONFIG_ARM64_E0PD))
+		return false;
+
+	mmfr2 = read_sysreg_s(SYS_ID_AA64MMFR2_EL1);
+	return cpuid_feature_extract_unsigned_field(mmfr2,
+						    ID_AA64MMFR2_EL1_E0PD_SHIFT);
+}
+
+static bool __init arm64_early_this_cpu_has_pac(void)
+{
+	u64 isar1, isar2;
+	u8 feat;
+
+	if (!IS_ENABLED(CONFIG_ARM64_PTR_AUTH_KERNEL))
+		return false;
+
+	isar1 = read_sysreg(ID_AA64ISAR1_EL1);
+	isar1 &= ~id_aa64isar1_override.mask;
+	isar1 |= id_aa64isar1_override.val;
+	feat = cpuid_feature_extract_unsigned_field(isar1,
+						    ID_AA64ISAR1_EL1_APA_SHIFT);
+	if (feat)
+		return true;
+
+	feat = cpuid_feature_extract_unsigned_field(isar1,
+						    ID_AA64ISAR1_EL1_API_SHIFT);
+	if (feat)
+		return true;
+
+	isar2 = read_sysreg_s(SYS_ID_AA64ISAR2_EL1);
+	isar2 &= ~id_aa64isar2_override.mask;
+	isar2 |= id_aa64isar2_override.val;
+	feat = cpuid_feature_extract_unsigned_field(isar2,
+						    ID_AA64ISAR2_EL1_APA3_SHIFT);
+	return feat;
+}
+
+static void __init map_kernel(u64 kaslr_offset, u64 va_offset)
+{
+	bool enable_scs = IS_ENABLED(CONFIG_UNWIND_PATCH_PAC_INTO_SCS);
+	bool twopass = IS_ENABLED(CONFIG_RELOCATABLE);
+	pgd_t *pgdp = (void *)init_pg_dir + PAGE_SIZE;
+	pgprot_t text_prot = PAGE_KERNEL_ROX;
+	pgprot_t data_prot = PAGE_KERNEL;
+	pgprot_t prot;
+
+	/*
+	 * External debuggers may need to write directly to the text mapping to
+	 * install SW breakpoints. Allow this (only) when explicitly requested
+	 * with rodata=off.
+	 */
+	if (cpuid_feature_extract_unsigned_field(arm64_sw_feature_override.val,
+						 ARM64_SW_FEATURE_OVERRIDE_RODATA_OFF))
+		text_prot = PAGE_KERNEL_EXEC;
+
+	/*
+	 * We only enable the shadow call stack dynamically if we are running
+	 * on a system that does not implement PAC or BTI. PAC and SCS provide
+	 * roughly the same level of protection, and BTI relies on the PACIASP
+	 * instructions serving as landing pads, preventing us from patching
+	 * those instructions into something else.
+	 */
+	if (arm64_early_this_cpu_has_pac())
+		enable_scs = false;
+
+	if (arm64_early_this_cpu_has_bti()) {
+		enable_scs = false;
+
+		/*
+		 * If we have a CPU that supports BTI and a kernel built for
+		 * BTI then mark the kernel executable text as guarded pages
+		 * now so we don't have to rewrite the page tables later.
+		 */
+		text_prot = __pgprot_modify(text_prot, PTE_GP, PTE_GP);
+	}
+
+	/* Map all code read-write on the first pass if needed */
+	twopass |= enable_scs;
+	prot = twopass ? data_prot : text_prot;
+
+	map_segment(&pgdp, va_offset, _stext, _etext, prot, !twopass);
+	map_segment(&pgdp, va_offset, __start_rodata, __inittext_begin, data_prot, false);
+	map_segment(&pgdp, va_offset, __inittext_begin, __inittext_end, prot, false);
+	map_segment(&pgdp, va_offset, __initdata_begin, __initdata_end, data_prot, false);
+	map_segment(&pgdp, va_offset, _data, _end, data_prot, true);
+	dsb(ishst);
+
+	idmap_cpu_replace_ttbr1(init_pg_dir);
+
+	if (twopass) {
+		if (IS_ENABLED(CONFIG_RELOCATABLE))
+			relocate_kernel(kaslr_offset);
+
+		if (enable_scs) {
+			scs_patch(__eh_frame_start + va_offset,
+				  __eh_frame_end - __eh_frame_start);
+			asm("ic ialluis");
+
+			dynamic_scs_is_enabled = true;
+		}
+
+		/*
+		 * Unmap the text region before remapping it, to avoid
+		 * potential TLB conflicts when creating the contiguous
+		 * descriptors.
+		 */
+		unmap_segment(va_offset, _stext, _etext);
+		dsb(ishst);
+		isb();
+		__tlbi(vmalle1);
+		isb();
+
+		/*
+		 * Remap these segments with different permissions
+		 * No new page table allocations should be needed
+		 */
+		map_segment(NULL, va_offset, _stext, _etext, text_prot, true);
+		map_segment(NULL, va_offset, __inittext_begin, __inittext_end,
+			    text_prot, false);
+		dsb(ishst);
+	}
+}
+
+asmlinkage void __init early_map_kernel(u64 boot_status, void *fdt)
+{
+	static char const chosen_str[] __initconst = "/chosen";
+	int chosen = fdt_path_offset(fdt, chosen_str);
+	u64 va_base, pa_base = (u64)&_text;
+	u64 kaslr_offset = pa_base % MIN_KIMG_ALIGN;
+
+	/* Clear BSS and the initial page tables */
+	memset(__bss_start, 0, (u64)init_pg_end - (u64)__bss_start);
+
+	/* Parse the command line for CPU feature overrides */
+	init_feature_override(boot_status, fdt, chosen);
+
+	/*
+	 * The virtual KASLR displacement modulo 2MiB is decided by the
+	 * physical placement of the image, as otherwise, we might not be able
+	 * to create the early kernel mapping using 2 MiB block descriptors. So
+	 * take the low bits of the KASLR offset from the physical address, and
+	 * fill in the high bits from the seed.
+	 */
+	if (IS_ENABLED(CONFIG_RANDOMIZE_BASE)) {
+		u64 kaslr_seed = kaslr_early_init(fdt, chosen);
+
+		kaslr_offset |= kaslr_seed & ~(MIN_KIMG_ALIGN - 1);
+
+		/*
+		 * Assume that any CPU that does not implement E0PD needs KPTI
+		 * to ensure that KASLR randomized addresses will not leak.
+		 * This means we need to use non-global mappings for the kernel
+		 * text and data.
+		 */
+		if (kaslr_seed && !arm64_early_this_cpu_has_e0pd())
+			arm64_use_ng_mappings = true;
+	}
+
+	va_base = KIMAGE_VADDR + kaslr_offset;
+	map_kernel(kaslr_offset, va_base - pa_base);
+}
diff --git a/arch/arm64/kernel/pi/patch-scs.c b/arch/arm64/kernel/pi/patch-scs.c
index d15833df10d3d4c6..bfeeaffc1e233083 100644
--- a/arch/arm64/kernel/pi/patch-scs.c
+++ b/arch/arm64/kernel/pi/patch-scs.c
@@ -11,6 +11,10 @@ 
 
 #include <asm/scs.h>
 
+#include "pi.h"
+
+bool dynamic_scs_is_enabled;
+
 //
 // This minimal DWARF CFI parser is partially based on the code in
 // arch/arc/kernel/unwind.c, and on the document below:
@@ -46,8 +50,6 @@ 
 #define DW_CFA_GNU_negative_offset_extended 0x2f
 #define DW_CFA_hi_user                      0x3f
 
-extern const u8 __eh_frame_start[], __eh_frame_end[];
-
 enum {
 	PACIASP		= 0xd503233f,
 	AUTIASP		= 0xd50323bf,
@@ -245,13 +247,3 @@  int scs_patch(const u8 eh_frame[], int size)
 	}
 	return 0;
 }
-
-asmlinkage void __init scs_patch_vmlinux(const u8 start[], const u8 end[])
-{
-	if (!should_patch_pac_into_scs())
-		return;
-
-	scs_patch(start, end - start);
-	asm("ic ialluis");
-	isb();
-}
diff --git a/arch/arm64/kernel/pi/pi.h b/arch/arm64/kernel/pi/pi.h
new file mode 100644
index 0000000000000000..c0b00199e3dc80e0
--- /dev/null
+++ b/arch/arm64/kernel/pi/pi.h
@@ -0,0 +1,12 @@ 
+// SPDX-License-Identifier: GPL-2.0-only
+// Copyright 2022 Google LLC
+// Author: Ard Biesheuvel <ardb@google.com>
+
+#include <linux/types.h>
+
+extern bool dynamic_scs_is_enabled;
+
+void init_feature_override(u64 boot_status, const void *fdt, int chosen);
+u64 kaslr_early_init(void *fdt, int chosen);
+void relocate_kernel(u64 offset);
+int scs_patch(const u8 eh_frame[], int size);
diff --git a/arch/arm64/kernel/pi/relocate.c b/arch/arm64/kernel/pi/relocate.c
index c35cb918fa2a004a..06e3cc6cdd6a68ca 100644
--- a/arch/arm64/kernel/pi/relocate.c
+++ b/arch/arm64/kernel/pi/relocate.c
@@ -6,6 +6,8 @@ 
 #include <linux/init.h>
 #include <linux/types.h>
 
+#include "pi.h"
+
 extern const Elf64_Rela rela_start[], rela_end[];
 extern const u64 relr_start[], relr_end[];
 
diff --git a/arch/arm64/kernel/setup.c b/arch/arm64/kernel/setup.c
index 37e0ba95afc3e045..149e7c3ee1321363 100644
--- a/arch/arm64/kernel/setup.c
+++ b/arch/arm64/kernel/setup.c
@@ -280,13 +280,6 @@  void __init __no_sanitize_address setup_arch(char **cmdline_p)
 
 	*cmdline_p = boot_command_line;
 
-	/*
-	 * If know now we are going to need KPTI then use non-global
-	 * mappings from the start, avoiding the cost of rewriting
-	 * everything later.
-	 */
-	arm64_use_ng_mappings = kaslr_requires_kpti();
-
 	early_fixmap_init();
 	early_ioremap_init();
 
diff --git a/arch/arm64/kernel/vmlinux.lds.S b/arch/arm64/kernel/vmlinux.lds.S
index 3f86a0db2952600c..33c3e59233f6fa6e 100644
--- a/arch/arm64/kernel/vmlinux.lds.S
+++ b/arch/arm64/kernel/vmlinux.lds.S
@@ -124,9 +124,9 @@  jiffies = jiffies_64;
 #ifdef CONFIG_UNWIND_TABLES
 #define UNWIND_DATA_SECTIONS				\
 	.eh_frame : {					\
-		__eh_frame_start = .;			\
+		__pi___eh_frame_start = .;		\
 		*(.eh_frame)				\
-		__eh_frame_end = .;			\
+		__pi___eh_frame_end = .;		\
 	}
 #else
 #define UNWIND_DATA_SECTIONS
@@ -313,7 +313,7 @@  SECTIONS
 
 	BSS_SECTION(SBSS_ALIGN, 0, 0)
 
-	. = ALIGN(PAGE_SIZE);
+	. = ALIGN(SEGMENT_ALIGN);
 	init_pg_dir = .;
 	. += INIT_DIR_SIZE;
 	init_pg_end = .;
diff --git a/arch/arm64/mm/proc.S b/arch/arm64/mm/proc.S
index b9ecbbae1e1abca1..f0db2c05e797aeed 100644
--- a/arch/arm64/mm/proc.S
+++ b/arch/arm64/mm/proc.S
@@ -201,6 +201,7 @@  SYM_TYPED_FUNC_START(idmap_cpu_replace_ttbr1)
 
 	ret
 SYM_FUNC_END(idmap_cpu_replace_ttbr1)
+SYM_FUNC_ALIAS(__pi_idmap_cpu_replace_ttbr1, idmap_cpu_replace_ttbr1)
 	.popsection
 
 #ifdef CONFIG_UNMAP_KERNEL_AT_EL0