Merge branch 'for-next/boot' into for-next/core

* for-next/boot: (34 commits)
  arm64: fix KASAN_INLINE
  arm64: Add an override for ID_AA64SMFR0_EL1.FA64
  arm64: Add the arm64.nosve command line option
  arm64: Add the arm64.nosme command line option
  arm64: Expose a __check_override primitive for oddball features
  arm64: Allow the idreg override to deal with variable field width
  arm64: Factor out checking of a feature against the override into a macro
  arm64: Allow sticky E2H when entering EL1
  arm64: Save state of HCR_EL2.E2H before switch to EL1
  arm64: Rename the VHE switch to "finalise_el2"
  arm64: mm: fix booting with 52-bit address space
  arm64: head: remove __PHYS_OFFSET
  arm64: lds: use PROVIDE instead of conditional definitions
  arm64: setup: drop early FDT pointer helpers
  arm64: head: avoid relocating the kernel twice for KASLR
  arm64: kaslr: defer initialization to initcall where permitted
  arm64: head: record CPU boot mode after enabling the MMU
  arm64: head: populate kernel page tables with MMU and caches on
  arm64: head: factor out TTBR1 assignment into a macro
  arm64: idreg-override: use early FDT mapping in ID map
  ...

3 files changed, 62 insertions, 12 deletions

diff --git a/arch/arm64/mm/kasan_init.c b/arch/arm64/mm/kasan_init.c
index c12cd700598f..e969e68de005 100644
--- a/arch/arm64/mm/kasan_init.c
+++ b/arch/arm64/mm/kasan_init.c
@@ -236,7 +236,7 @@ static void __init kasan_init_shadow(void)
 	 */
 	memcpy(tmp_pg_dir, swapper_pg_dir, sizeof(tmp_pg_dir));
 	dsb(ishst);
-	cpu_replace_ttbr1(lm_alias(tmp_pg_dir));
+	cpu_replace_ttbr1(lm_alias(tmp_pg_dir), idmap_pg_dir);
 
 	clear_pgds(KASAN_SHADOW_START, KASAN_SHADOW_END);
 
@@ -280,7 +280,7 @@ static void __init kasan_init_shadow(void)
 				PAGE_KERNEL_RO));
 
 	memset(kasan_early_shadow_page, KASAN_SHADOW_INIT, PAGE_SIZE);
-	cpu_replace_ttbr1(lm_alias(swapper_pg_dir));
+	cpu_replace_ttbr1(lm_alias(swapper_pg_dir), idmap_pg_dir);
 }
 
 static void __init kasan_init_depth(void)
diff --git a/arch/arm64/mm/mmu.c b/arch/arm64/mm/mmu.c
index 19feb6fe05b2..db7c4e6ae57b 100644
--- a/arch/arm64/mm/mmu.c
+++ b/arch/arm64/mm/mmu.c
@@ -43,15 +43,27 @@
 #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);
-u64 idmap_ptrs_per_pgd = PTRS_PER_PGD;
+int idmap_t0sz __ro_after_init;
 
-u64 __section(".mmuoff.data.write") vabits_actual;
+#if VA_BITS > 48
+u64 vabits_actual __ro_after_init = VA_BITS_MIN;
 EXPORT_SYMBOL(vabits_actual);
+#endif
+
+u64 kimage_vaddr __ro_after_init = (u64)&_text;
+EXPORT_SYMBOL(kimage_vaddr);
 
 u64 kimage_voffset __ro_after_init;
 EXPORT_SYMBOL(kimage_voffset);
 
+u32 __boot_cpu_mode[] = { BOOT_CPU_MODE_EL2, BOOT_CPU_MODE_EL1 };
+
+/*
+ * The booting CPU updates the failed status @__early_cpu_boot_status,
+ * with MMU turned off.
+ */
+long __section(".mmuoff.data.write") __early_cpu_boot_status;
+
 /*
  * Empty_zero_page is a special page that is used for zero-initialized data
  * and COW.
@@ -763,22 +775,57 @@ static void __init map_kernel(pgd_t *pgdp)
 	kasan_copy_shadow(pgdp);
 }
 
+static void __init create_idmap(void)
+{
+	u64 start = __pa_symbol(__idmap_text_start);
+	u64 size = __pa_symbol(__idmap_text_end) - start;
+	pgd_t *pgd = idmap_pg_dir;
+	u64 pgd_phys;
+
+	/* check if we need an additional level of translation */
+	if (VA_BITS < 48 && idmap_t0sz < (64 - VA_BITS_MIN)) {
+		pgd_phys = early_pgtable_alloc(PAGE_SHIFT);
+		set_pgd(&idmap_pg_dir[start >> VA_BITS],
+			__pgd(pgd_phys | P4D_TYPE_TABLE));
+		pgd = __va(pgd_phys);
+	}
+	__create_pgd_mapping(pgd, start, start, size, PAGE_KERNEL_ROX,
+			     early_pgtable_alloc, 0);
+
+	if (IS_ENABLED(CONFIG_UNMAP_KERNEL_AT_EL0)) {
+		extern u32 __idmap_kpti_flag;
+		u64 pa = __pa_symbol(&__idmap_kpti_flag);
+
+		/*
+		 * The KPTI G-to-nG conversion code needs a read-write mapping
+		 * of its synchronization flag in the ID map.
+		 */
+		__create_pgd_mapping(pgd, pa, pa, sizeof(u32), PAGE_KERNEL,
+				     early_pgtable_alloc, 0);
+	}
+}
+
 void __init paging_init(void)
 {
 	pgd_t *pgdp = pgd_set_fixmap(__pa_symbol(swapper_pg_dir));
+	extern pgd_t init_idmap_pg_dir[];
+
+	idmap_t0sz = 63UL - __fls(__pa_symbol(_end) | GENMASK(VA_BITS_MIN - 1, 0));
 
 	map_kernel(pgdp);
 	map_mem(pgdp);
 
 	pgd_clear_fixmap();
 
-	cpu_replace_ttbr1(lm_alias(swapper_pg_dir));
+	cpu_replace_ttbr1(lm_alias(swapper_pg_dir), init_idmap_pg_dir);
 	init_mm.pgd = swapper_pg_dir;
 
 	memblock_phys_free(__pa_symbol(init_pg_dir),
 			   __pa_symbol(init_pg_end) - __pa_symbol(init_pg_dir));
 
 	memblock_allow_resize();
+
+	create_idmap();
 }
 
 /*
diff --git a/arch/arm64/mm/proc.S b/arch/arm64/mm/proc.S
index 972ce8d7f2c5..7837a69524c5 100644
--- a/arch/arm64/mm/proc.S
+++ b/arch/arm64/mm/proc.S
@@ -249,8 +249,10 @@ SYM_FUNC_END(idmap_cpu_replace_ttbr1)
  *
  * Called exactly once from stop_machine context by each CPU found during boot.
  */
-__idmap_kpti_flag:
-	.long	1
+	.pushsection	".data", "aw", %progbits
+SYM_DATA(__idmap_kpti_flag, .long 1)
+	.popsection
+
 SYM_FUNC_START(idmap_kpti_install_ng_mappings)
 	cpu		.req	w0
 	temp_pte	.req	x0
@@ -273,7 +275,7 @@ SYM_FUNC_START(idmap_kpti_install_ng_mappings)
 
 	mov	x5, x3				// preserve temp_pte arg
 	mrs	swapper_ttb, ttbr1_el1
-	adr	flag_ptr, __idmap_kpti_flag
+	adr_l	flag_ptr, __idmap_kpti_flag
 
 	cbnz	cpu, __idmap_kpti_secondary
 
@@ -396,6 +398,8 @@ SYM_FUNC_END(idmap_kpti_install_ng_mappings)
  *
  *	Initialise the processor for turning the MMU on.
  *
+ * Input:
+ *	x0 - actual number of VA bits (ignored unless VA_BITS > 48)
  * Output:
  *	Return in x0 the value of the SCTLR_EL1 register.
  */
@@ -465,12 +469,11 @@ SYM_FUNC_START(__cpu_setup)
 	tcr_clear_errata_bits tcr, x9, x5
 
 #ifdef CONFIG_ARM64_VA_BITS_52
-	ldr_l		x9, vabits_actual
-	sub		x9, xzr, x9
+	sub		x9, xzr, x0
 	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