arm64: head: move assignment of idmap_t0sz to C code

Setting idmap_t0sz involves fiddling with the caches if done with the
MMU off. Since we will be creating an initial ID map with the MMU and
caches off, and the permanent ID map with the MMU and caches on, let's
move this assignment of idmap_t0sz out of the startup code, and replace
it with a macro that simply issues the three instructions needed to
calculate the value wherever it is needed before the MMU is turned on.
Signed-off-by: Ard Biesheuvel <ardb@kernel.org>
Link: https://lore.kernel.org/r/20220624150651.1358849-4-ardb@kernel.orgSigned-off-by: Will Deacon <will@kernel.org>

arch/arm64/include/asm/assembler.h

@@ -359,6 +359,20 @@ 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/mmu_context.h

@@ -60,7 +60,7 @@ static inline void cpu_switch_mm(pgd_t *pgd, struct mm_struct *mm)
  * TCR_T0SZ(VA_BITS), unless system RAM is positioned very high in
  * physical memory, in which case it will be smaller.
  */
-extern u64 idmap_t0sz;
+extern int idmap_t0sz;
 extern u64 idmap_ptrs_per_pgd;
 
 /*

arch/arm64/kernel/head.S

@@ -299,22 +299,11 @@ SYM_FUNC_START_LOCAL(__create_page_tables)
 	 * physical address space. So for the ID map, use an extended virtual
 	 * range in that case, and configure an additional translation level
 	 * if needed.
-	 *
-	 * 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 __idmap_text_end.
 	 */
-	adrp	x5, __idmap_text_end
-	clz	x5, x5
+	idmap_get_t0sz x5
 	cmp	x5, TCR_T0SZ(VA_BITS_MIN) // default T0SZ small enough?
 	b.ge	1f			// .. then skip VA range extension
 
-	adr_l	x6, idmap_t0sz
-	str	x5, [x6]
-	dmb	sy
-	dc	ivac, x6		// Invalidate potentially stale cache line
-
 #if (VA_BITS < 48)
 #define EXTRA_SHIFT	(PGDIR_SHIFT + PAGE_SHIFT - 3)
 #define EXTRA_PTRS	(1 << (PHYS_MASK_SHIFT - EXTRA_SHIFT))

arch/arm64/mm/mmu.c

@@ -43,7 +43,7 @@
 #define NO_CONT_MAPPINGS	BIT(1)
 #define NO_EXEC_MAPPINGS	BIT(2)	/* assumes FEAT_HPDS is not used */
 
-u64 idmap_t0sz = TCR_T0SZ(VA_BITS_MIN);
+int idmap_t0sz __ro_after_init;
 u64 idmap_ptrs_per_pgd = PTRS_PER_PGD;
 
 #if VA_BITS > 48
@@ -771,6 +771,8 @@ void __init paging_init(void)
 {
 	pgd_t *pgdp = pgd_set_fixmap(__pa_symbol(swapper_pg_dir));
 
+	idmap_t0sz = 63UL - __fls(__pa_symbol(_end) | GENMASK(VA_BITS_MIN - 1, 0));
+
 	map_kernel(pgdp);
 	map_mem(pgdp);
 

arch/arm64/mm/proc.S

@@ -469,7 +469,7 @@ SYM_FUNC_START(__cpu_setup)
 	add		x9, x9, #64
 	tcr_set_t1sz	tcr, x9
 #else
-	ldr_l		x9, idmap_t0sz
+	idmap_get_t0sz	x9
 #endif
 	tcr_set_t0sz	tcr, x9