arm64: head: Move early kernel mapping routines into C code

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>
Link: https://lore.kernel.org/r/20240214122845.2033971-63-ardb+git@google.com
Signed-off-by: Catalin Marinas <catalin.marinas@arm.com>

8 files changed, 289 insertions, 30 deletions

diff --git a/arch/arm64/kernel/pi/Makefile b/arch/arm64/kernel/pi/Makefile
index a8b302245f15..8c2f80a46b93 100644
--- a/arch/arm64/kernel/pi/Makefile
+++ b/arch/arm64/kernel/pi/Makefile
@@ -39,6 +39,7 @@ $(obj)/lib-%.o: $(srctree)/lib/%.c FORCE
 	$(call if_changed_rule,cc_o_c)
 
 obj-y					:= idreg-override.pi.o \
+					   map_kernel.pi.o map_range.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 e4bcabcc6860..1884bd936c0d 100644
--- a/arch/arm64/kernel/pi/idreg-override.c
+++ b/arch/arm64/kernel/pi/idreg-override.c
@@ -308,37 +308,35 @@ 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)
 {
 	struct arm64_ftr_override *override;
 	const struct ftr_set_desc *reg;
@@ -354,7 +352,7 @@ 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++) {
 		reg = prel64_pointer(regs[i].reg);
diff --git a/arch/arm64/kernel/pi/kaslr_early.c b/arch/arm64/kernel/pi/kaslr_early.c
index eeecee7ffd6f..0257b43819db 100644
--- a/arch/arm64/kernel/pi/kaslr_early.c
+++ b/arch/arm64/kernel/pi/kaslr_early.c
@@ -16,17 +16,17 @@
 #include <asm/memory.h>
 #include <asm/pgtable.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;
 
@@ -39,14 +39,14 @@ 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, range;
 
 	if (kaslr_disabled_cmdline())
 		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 000000000000..f206373b28b0
--- /dev/null
+++ b/arch/arm64/kernel/pi/map_kernel.c
@@ -0,0 +1,164 @@
+// SPDX-License-Identifier: GPL-2.0-only
+// Copyright 2023 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_segment(pgd_t *pg_dir, u64 *pgd, u64 va_offset,
+			       void *start, void *end, pgprot_t prot,
+			       bool may_use_cont, int root_level)
+{
+	map_range(pgd, ((u64)start + va_offset) & ~PAGE_OFFSET,
+		  ((u64)end + va_offset) & ~PAGE_OFFSET, (u64)start,
+		  prot, root_level, (pte_t *)pg_dir, may_use_cont, 0);
+}
+
+static void __init unmap_segment(pgd_t *pg_dir, u64 va_offset, void *start,
+				 void *end, int root_level)
+{
+	map_segment(pg_dir, NULL, va_offset, start, end, __pgprot(0),
+		    false, root_level);
+}
+
+static void __init map_kernel(u64 kaslr_offset, u64 va_offset, int root_level)
+{
+	bool enable_scs = IS_ENABLED(CONFIG_UNWIND_PATCH_PAC_INTO_SCS);
+	bool twopass = IS_ENABLED(CONFIG_RELOCATABLE);
+	u64 pgdp = (u64)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 (arm64_test_sw_feature_override(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 (IS_ENABLED(CONFIG_ARM64_PTR_AUTH_KERNEL) && cpu_has_pac())
+		enable_scs = false;
+
+	if (IS_ENABLED(CONFIG_ARM64_BTI_KERNEL) && 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(init_pg_dir, &pgdp, va_offset, _stext, _etext, prot,
+		    !twopass, root_level);
+	map_segment(init_pg_dir, &pgdp, va_offset, __start_rodata,
+		    __inittext_begin, data_prot, false, root_level);
+	map_segment(init_pg_dir, &pgdp, va_offset, __inittext_begin,
+		    __inittext_end, prot, false, root_level);
+	map_segment(init_pg_dir, &pgdp, va_offset, __initdata_begin,
+		    __initdata_end, data_prot, false, root_level);
+	map_segment(init_pg_dir, &pgdp, va_offset, _data, _end, data_prot,
+		    true, root_level);
+	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(init_pg_dir, va_offset, _stext, _etext,
+			      root_level);
+		dsb(ishst);
+		isb();
+		__tlbi(vmalle1);
+		isb();
+
+		/*
+		 * Remap these segments with different permissions
+		 * No new page table allocations should be needed
+		 */
+		map_segment(init_pg_dir, NULL, va_offset, _stext, _etext,
+			    text_prot, true, root_level);
+		map_segment(init_pg_dir, NULL, va_offset, __inittext_begin,
+			    __inittext_end, text_prot, false, root_level);
+		dsb(ishst);
+	}
+}
+
+asmlinkage void __init early_map_kernel(u64 boot_status, void *fdt)
+{
+	static char const chosen_str[] __initconst = "/chosen";
+	u64 va_base, pa_base = (u64)&_text;
+	u64 kaslr_offset = pa_base % MIN_KIMG_ALIGN;
+	int root_level = 4 - CONFIG_PGTABLE_LEVELS;
+	int chosen;
+
+	/* 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 */
+	chosen = fdt_path_offset(fdt, chosen_str);
+	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);
+
+		if (kaslr_seed && kaslr_requires_kpti())
+			arm64_use_ng_mappings = true;
+
+		kaslr_offset |= kaslr_seed & ~(MIN_KIMG_ALIGN - 1);
+	}
+
+	va_base = KIMAGE_VADDR + kaslr_offset;
+	map_kernel(kaslr_offset, va_base - pa_base, root_level);
+}
diff --git a/arch/arm64/kernel/pi/map_range.c b/arch/arm64/kernel/pi/map_range.c
new file mode 100644
index 000000000000..c31feda18f47
--- /dev/null
+++ b/arch/arm64/kernel/pi/map_range.c
@@ -0,0 +1,88 @@
+// SPDX-License-Identifier: GPL-2.0-only
+// Copyright 2023 Google LLC
+// Author: Ard Biesheuvel <ardb@google.com>
+
+#include <linux/types.h>
+#include <linux/sizes.h>
+
+#include <asm/memory.h>
+#include <asm/pgalloc.h>
+#include <asm/pgtable.h>
+
+#include "pi.h"
+
+/**
+ * map_range - Map a contiguous range of physical pages into virtual memory
+ *
+ * @pte:		Address of physical pointer to array of pages to
+ *			allocate page tables from
+ * @start:		Virtual address of the start of the range
+ * @end:		Virtual address of the end of the range (exclusive)
+ * @pa:			Physical address of the start of the range
+ * @prot:		Access permissions of the range
+ * @level:		Translation level for the mapping
+ * @tbl:		The level @level page table to create the mappings in
+ * @may_use_cont:	Whether the use of the contiguous attribute is allowed
+ * @va_offset:		Offset between a physical page and its current mapping
+ * 			in the VA space
+ */
+void __init map_range(u64 *pte, u64 start, u64 end, u64 pa, pgprot_t prot,
+		      int level, pte_t *tbl, bool may_use_cont, u64 va_offset)
+{
+	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;
+
+	start	&= PAGE_MASK;
+	pa	&= PAGE_MASK;
+
+	/* Advance tbl to the entry that covers start */
+	tbl += (start >> (lshift + PAGE_SHIFT)) % PTRS_PER_PTE;
+
+	/*
+	 * 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, PAGE_ALIGN(end));
+
+		if (level < 3 && (start | next | pa) & lmask) {
+			/*
+			 * This chunk needs a finer grained mapping. Create a
+			 * table mapping if necessary and recurse.
+			 */
+			if (pte_none(*tbl)) {
+				*tbl = __pte(__phys_to_pte_val(*pte) |
+					     PMD_TYPE_TABLE | PMD_TABLE_UXN);
+				*pte += PTRS_PER_PTE * sizeof(pte_t);
+			}
+			map_range(pte, start, next, pa, prot, level + 1,
+				  (pte_t *)(__pte_to_phys(*tbl) + va_offset),
+				  may_use_cont, va_offset);
+		} 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++;
+	}
+}
diff --git a/arch/arm64/kernel/pi/patch-scs.c b/arch/arm64/kernel/pi/patch-scs.c
index c65ef40d1e6b..49d8b40e61bc 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,
@@ -250,13 +252,3 @@ 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
index 7c2d9bbf0ff9..d307c58e9741 100644
--- a/arch/arm64/kernel/pi/pi.h
+++ b/arch/arm64/kernel/pi/pi.h
@@ -2,6 +2,8 @@
 // Copyright 2023 Google LLC
 // Author: Ard Biesheuvel <ardb@google.com>
 
+#include <linux/types.h>
+
 #define __prel64_initconst	__section(".init.rodata.prel64")
 
 #define PREL64(type, name)	union { type *name; prel64_t name ## _prel; }
@@ -16,3 +18,15 @@ static inline void *prel64_to_pointer(const prel64_t *offset)
 		return NULL;
 	return (void *)offset + *offset;
 }
+
+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);
+
+void map_range(u64 *pgd, u64 start, u64 end, u64 pa, pgprot_t prot,
+	       int level, pte_t *tbl, bool may_use_cont, u64 va_offset);
+
+asmlinkage void early_map_kernel(u64 boot_status, void *fdt);
diff --git a/arch/arm64/kernel/pi/relocate.c b/arch/arm64/kernel/pi/relocate.c
index 1853408ea76b..2407d2696398 100644
--- a/arch/arm64/kernel/pi/relocate.c
+++ b/arch/arm64/kernel/pi/relocate.c
@@ -7,6 +7,8 @@
 #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[];