arm64/mm: Separate boot-time page tables from swapper_pg_dir

Since the address of swapper_pg_dir is fixed for a given kernel image,
it is an attractive target for manipulation via an arbitrary write. To
mitigate this we'd like to make it read-only by moving it into the
rodata section.

We require that swapper_pg_dir is at a fixed offset from tramp_pg_dir
and reserved_ttbr0, so these will also need to move into rodata.
However, swapper_pg_dir is allocated along with some transient page
tables used for boot which we do not want to move into rodata.

As a step towards this, this patch separates the boot-time page tables
into a new init_pg_dir, and reduces swapper_pg_dir to the single page it
needs to be. This allows us to retain the relationship between
swapper_pg_dir, tramp_pg_dir, and swapper_pg_dir, while cleanly
separating these from the boot-time page tables.

The init_pg_dir holds all of the pgd/pud/pmd/pte levels needed during
boot, and all of these levels will be freed when we switch to the
swapper_pg_dir, which is initialized by the existing code in
paging_init(). Since we start off on the init_pg_dir, we no longer need
to allocate a transient page table in paging_init() in order to ensure
that swapper_pg_dir isn't live while we initialize it.

There should be no functional change as a result of this patch.

Signed-off-by: Jun Yao <yaojun8558363@gmail.com>
Reviewed-by: James Morse <james.morse@arm.com>
[Mark: place init_pg_dir after BSS, fold mm changes, commit message]
Signed-off-by: Mark Rutland <mark.rutland@arm.com>
Signed-off-by: Catalin Marinas <catalin.marinas@arm.com>

arch/arm64/include/asm/kernel-pgtable.h

@@ -97,7 +97,7 @@
 			+ EARLY_PGDS((vstart), (vend)) 	/* each PGDIR needs a next level page table */	\
 			+ EARLY_PUDS((vstart), (vend))	/* each PUD needs a next level page table */	\
 			+ EARLY_PMDS((vstart), (vend)))	/* each PMD needs a next level page table */
-#define SWAPPER_DIR_SIZE (PAGE_SIZE * EARLY_PAGES(KIMAGE_VADDR + TEXT_OFFSET, _end))
+#define INIT_DIR_SIZE (PAGE_SIZE * EARLY_PAGES(KIMAGE_VADDR + TEXT_OFFSET, _end))
 #define IDMAP_DIR_SIZE		(IDMAP_PGTABLE_LEVELS * PAGE_SIZE)
 
 #ifdef CONFIG_ARM64_SW_TTBR0_PAN

arch/arm64/include/asm/mmu.h

@@ -95,5 +95,8 @@ extern void create_pgd_mapping(struct mm_struct *mm, phys_addr_t phys,
 extern void *fixmap_remap_fdt(phys_addr_t dt_phys);
 extern void mark_linear_text_alias_ro(void);
 
+#define INIT_MM_CONTEXT(name)	\
+	.pgd = init_pg_dir,
+
 #endif	/* !__ASSEMBLY__ */
 #endif

arch/arm64/include/asm/pgtable.h

@@ -718,8 +718,9 @@ static inline pmd_t pmdp_establish(struct vm_area_struct *vma,
 }
 #endif
 
+extern pgd_t init_pg_dir[PTRS_PER_PGD];
+extern pgd_t init_pg_end[];
 extern pgd_t swapper_pg_dir[PTRS_PER_PGD];
-extern pgd_t swapper_pg_end[];
 extern pgd_t idmap_pg_dir[PTRS_PER_PGD];
 extern pgd_t tramp_pg_dir[PTRS_PER_PGD];
 

arch/arm64/kernel/head.S

@@ -291,7 +291,7 @@ __create_page_tables:
 	 * dirty cache lines being evicted.
 	 */
 	adrp	x0, idmap_pg_dir
-	adrp	x1, swapper_pg_end
+	adrp	x1, init_pg_end
 	sub	x1, x1, x0
 	bl	__inval_dcache_area
 
@@ -299,7 +299,7 @@ __create_page_tables:
 	 * Clear the idmap and swapper page tables.
 	 */
 	adrp	x0, idmap_pg_dir
-	adrp	x1, swapper_pg_end
+	adrp	x1, init_pg_end
 	sub	x1, x1, x0
 1:	stp	xzr, xzr, [x0], #16
 	stp	xzr, xzr, [x0], #16
@@ -373,7 +373,7 @@ __create_page_tables:
 	/*
 	 * Map the kernel image (starting with PHYS_OFFSET).
 	 */
-	adrp	x0, swapper_pg_dir
+	adrp	x0, init_pg_dir
 	mov_q	x5, KIMAGE_VADDR + TEXT_OFFSET	// compile time __va(_text)
 	add	x5, x5, x23			// add KASLR displacement
 	mov	x4, PTRS_PER_PGD
@@ -390,7 +390,7 @@ __create_page_tables:
 	 * tables again to remove any speculatively loaded cache lines.
 	 */
 	adrp	x0, idmap_pg_dir
-	adrp	x1, swapper_pg_end
+	adrp	x1, init_pg_end
 	sub	x1, x1, x0
 	dmb	sy
 	bl	__inval_dcache_area
@@ -824,7 +824,7 @@ __primary_switch:
 	mrs	x20, sctlr_el1			// preserve old SCTLR_EL1 value
 #endif
 
-	adrp	x1, swapper_pg_dir
+	adrp	x1, init_pg_dir
 	bl	__enable_mmu
 #ifdef CONFIG_RELOCATABLE
 	bl	__relocate_kernel

arch/arm64/kernel/vmlinux.lds.S

@@ -229,9 +229,13 @@ SECTIONS
 	. += RESERVED_TTBR0_SIZE;
 #endif
 	swapper_pg_dir = .;
-	. += SWAPPER_DIR_SIZE;
+	. += PAGE_SIZE;
 	swapper_pg_end = .;
 
+	init_pg_dir = .;
+	. += INIT_DIR_SIZE;
+	init_pg_end = .;
+
 	__pecoff_data_size = ABSOLUTE(. - __initdata_begin);
 	_end = .;
 

arch/arm64/mm/mmu.c

@@ -629,34 +629,14 @@ static void __init map_kernel(pgd_t *pgdp)
  */
 void __init paging_init(void)
 {
-	phys_addr_t pgd_phys = early_pgtable_alloc();
-	pgd_t *pgdp = pgd_set_fixmap(pgd_phys);
+	map_kernel(swapper_pg_dir);
+	map_mem(swapper_pg_dir);
 
-	map_kernel(pgdp);
-	map_mem(pgdp);
-
-	/*
-	 * We want to reuse the original swapper_pg_dir so we don't have to
-	 * communicate the new address to non-coherent secondaries in
-	 * secondary_entry, and so cpu_switch_mm can generate the address with
-	 * adrp+add rather than a load from some global variable.
-	 *
-	 * To do this we need to go via a temporary pgd.
-	 */
-	cpu_replace_ttbr1(__va(pgd_phys));
-	memcpy(swapper_pg_dir, pgdp, PGD_SIZE);
 	cpu_replace_ttbr1(lm_alias(swapper_pg_dir));
+	init_mm.pgd = swapper_pg_dir;
 
-	pgd_clear_fixmap();
-	memblock_free(pgd_phys, PAGE_SIZE);
-
-	/*
-	 * We only reuse the PGD from the swapper_pg_dir, not the pud + pmd
-	 * allocated with it.
-	 */
-	memblock_free(__pa_symbol(swapper_pg_dir) + PAGE_SIZE,
-		      __pa_symbol(swapper_pg_end) - __pa_symbol(swapper_pg_dir)
-		      - PAGE_SIZE);
+	memblock_free(__pa_symbol(init_pg_dir),
+		      __pa_symbol(init_pg_end) - __pa_symbol(init_pg_dir));
 }
 
 /*