arm64: kernel: Create initial ID map from C code

The asm code that creates the initial ID map is rather intricate and
hard to follow. This is problematic because it makes adding support for
things like LPA2 or WXN more difficult than necessary. Also, it is
parameterized like the rest of the MM code to run with a configurable
number of levels, which is rather pointless, given that all AArch64 CPUs
implement support for 48-bit virtual addressing, and that many systems
exist with DRAM located outside of the 39-bit addressable range, which
is the only smaller VA size that is widely used, and we need additional
tricks to make things work in that combination.

So let's bite the bullet, and rip out all the asm macros, and fiddly
code, and replace it with a C implementation based on the newly added
routines for creating the early kernel VA mappings. And while at it,
create the initial ID map based on 48-bit virtual addressing as well,
regardless of the number of configured levels for the kernel proper.

Note that this code may execute with the MMU and caches disabled, and is
therefore not permitted to make unaligned accesses. This shouldn't
generally happen in any case for the algorithm as implemented, but to be
sure, let's pass -mstrict-align to the compiler just in case.

Signed-off-by: Ard Biesheuvel <[email protected]>
Link: https://lore.kernel.org/r/[email protected]
Signed-off-by: Catalin Marinas <[email protected]>

Author: ardbiesheuvel

arch/arm64/include/asm/assembler.h

@@ -345,20 +345,6 @@ alternative_cb_end
 	bfi	\valreg, \t1sz, #TCR_T1SZ_OFFSET, #TCR_TxSZ_WIDTH
 	.endm
 
-/*
- * idmap_get_t0sz - get the T0SZ value needed to cover the ID map
- *
- * Calculate the maximum allowed value for TCR_EL1.T0SZ so that the
- * entire ID map region can be mapped. As T0SZ == (64 - #bits used),
- * this number conveniently equals the number of leading zeroes in
- * the physical address of _end.
- */
-	.macro	idmap_get_t0sz, reg
-	adrp	\reg, _end
-	orr	\reg, \reg, #(1 << VA_BITS_MIN) - 1
-	clz	\reg, \reg
-	.endm
-
 /*
  * tcr_compute_pa_size - set TCR.(I)PS to the highest supported
  * ID_AA64MMFR0_EL1.PARange value

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

@@ -29,6 +29,7 @@
 #define SWAPPER_TABLE_SHIFT	(SWAPPER_BLOCK_SHIFT + PAGE_SHIFT - 3)
 
 #define SWAPPER_PGTABLE_LEVELS		(CONFIG_PGTABLE_LEVELS - SWAPPER_SKIP_LEVEL)
+#define INIT_IDMAP_PGTABLE_LEVELS	(IDMAP_LEVELS - SWAPPER_SKIP_LEVEL)
 
 #define IDMAP_VA_BITS		48
 #define IDMAP_LEVELS		ARM64_HW_PGTABLE_LEVELS(IDMAP_VA_BITS)
@@ -48,44 +49,39 @@
 #define EARLY_ENTRIES(vstart, vend, shift, add) \
 	(SPAN_NR_ENTRIES(vstart, vend, shift) + (add))
 
-#define EARLY_LEVEL(lvl, vstart, vend, add)	\
-	(SWAPPER_PGTABLE_LEVELS > lvl ? EARLY_ENTRIES(vstart, vend, SWAPPER_BLOCK_SHIFT + lvl * (PAGE_SHIFT - 3), add) : 0)
+#define EARLY_LEVEL(lvl, lvls, vstart, vend, add)	\
+	(lvls > lvl ? EARLY_ENTRIES(vstart, vend, SWAPPER_BLOCK_SHIFT + lvl * (PAGE_SHIFT - 3), add) : 0)
 
-#define EARLY_PAGES(vstart, vend, add) (1 	/* PGDIR page */				\
-	+ EARLY_LEVEL(3, (vstart), (vend), add) /* each entry needs a next level page table */	\
-	+ EARLY_LEVEL(2, (vstart), (vend), add)	/* each entry needs a next level page table */	\
-	+ EARLY_LEVEL(1, (vstart), (vend), add))/* each entry needs a next level page table */
-#define INIT_DIR_SIZE (PAGE_SIZE * (EARLY_PAGES(KIMAGE_VADDR, _end, EXTRA_PAGE) + EARLY_SEGMENT_EXTRA_PAGES))
+#define EARLY_PAGES(lvls, vstart, vend, add) (1 	/* PGDIR page */				\
+	+ EARLY_LEVEL(3, (lvls), (vstart), (vend), add) /* each entry needs a next level page table */	\
+	+ EARLY_LEVEL(2, (lvls), (vstart), (vend), add)	/* each entry needs a next level page table */	\
+	+ EARLY_LEVEL(1, (lvls), (vstart), (vend), add))/* each entry needs a next level page table */
+#define INIT_DIR_SIZE (PAGE_SIZE * (EARLY_PAGES(SWAPPER_PGTABLE_LEVELS, KIMAGE_VADDR, _end, EXTRA_PAGE) \
+				    + EARLY_SEGMENT_EXTRA_PAGES))
 
-/* the initial ID map may need two extra pages if it needs to be extended */
-#if VA_BITS < 48
-#define INIT_IDMAP_DIR_SIZE	((INIT_IDMAP_DIR_PAGES + 2) * PAGE_SIZE)
-#else
-#define INIT_IDMAP_DIR_SIZE	(INIT_IDMAP_DIR_PAGES * PAGE_SIZE)
-#endif
-#define INIT_IDMAP_DIR_PAGES	EARLY_PAGES(KIMAGE_VADDR, _end + MAX_FDT_SIZE + SWAPPER_BLOCK_SIZE, 1)
+#define INIT_IDMAP_DIR_PAGES	(EARLY_PAGES(INIT_IDMAP_PGTABLE_LEVELS, KIMAGE_VADDR, _end, 1))
+#define INIT_IDMAP_DIR_SIZE	((INIT_IDMAP_DIR_PAGES + EARLY_IDMAP_EXTRA_PAGES) * PAGE_SIZE)
+
+#define INIT_IDMAP_FDT_PAGES	(EARLY_PAGES(INIT_IDMAP_PGTABLE_LEVELS, 0UL, UL(MAX_FDT_SIZE), 1) - 1)
+#define INIT_IDMAP_FDT_SIZE	((INIT_IDMAP_FDT_PAGES + EARLY_IDMAP_EXTRA_FDT_PAGES) * PAGE_SIZE)
 
 /* The number of segments in the kernel image (text, rodata, inittext, initdata, data+bss) */
 #define KERNEL_SEGMENT_COUNT	5
 
 #if SWAPPER_BLOCK_SIZE > SEGMENT_ALIGN
 #define EARLY_SEGMENT_EXTRA_PAGES (KERNEL_SEGMENT_COUNT + 1)
-#else
-#define EARLY_SEGMENT_EXTRA_PAGES 0
-#endif
-
 /*
- * Initial memory map attributes.
+ * The initial ID map consists of the kernel image, mapped as two separate
+ * segments, and may appear misaligned wrt the swapper block size. This means
+ * we need 3 additional pages. The DT could straddle a swapper block boundary,
+ * so it may need 2.
  */
-#define SWAPPER_PTE_FLAGS	(PTE_TYPE_PAGE | PTE_AF | PTE_SHARED | PTE_UXN)
-#define SWAPPER_PMD_FLAGS	(PMD_TYPE_SECT | PMD_SECT_AF | PMD_SECT_S | PTE_UXN)
-
-#ifdef CONFIG_ARM64_4K_PAGES
-#define SWAPPER_RW_MMUFLAGS	(PMD_ATTRINDX(MT_NORMAL) | SWAPPER_PMD_FLAGS | PTE_WRITE)
-#define SWAPPER_RX_MMUFLAGS	(SWAPPER_RW_MMUFLAGS | PMD_SECT_RDONLY)
+#define EARLY_IDMAP_EXTRA_PAGES		3
+#define EARLY_IDMAP_EXTRA_FDT_PAGES	2
 #else
-#define SWAPPER_RW_MMUFLAGS	(PTE_ATTRINDX(MT_NORMAL) | SWAPPER_PTE_FLAGS | PTE_WRITE)
-#define SWAPPER_RX_MMUFLAGS	(SWAPPER_RW_MMUFLAGS | PTE_RDONLY)
+#define EARLY_SEGMENT_EXTRA_PAGES	0
+#define EARLY_IDMAP_EXTRA_PAGES		0
+#define EARLY_IDMAP_EXTRA_FDT_PAGES	0
 #endif
 
 #endif	/* __ASM_KERNEL_PGTABLE_H */

arch/arm64/include/asm/mmu_context.h

@@ -61,11 +61,9 @@ static inline void cpu_switch_mm(pgd_t *pgd, struct mm_struct *mm)
 }
 
 /*
- * TCR.T0SZ value to use when the ID map is active. Usually equals
- * TCR_T0SZ(VA_BITS), unless system RAM is positioned very high in
- * physical memory, in which case it will be smaller.
+ * TCR.T0SZ value to use when the ID map is active.
  */
-extern int idmap_t0sz;
+#define idmap_t0sz	TCR_T0SZ(IDMAP_VA_BITS)
 
 /*
  * Ensure TCR.T0SZ is set to the provided value.