arm64: Enable LPA2 at boot if supported by the system

Update the early kernel mapping code to take 52-bit virtual addressing
into account based on the LPA2 feature. This is a bit more involved than
LVA (which is supported with 64k pages only), given that some page table
descriptor bits change meaning in this case.

To keep the handling in asm to a minimum, the initial ID map is still
created with 48-bit virtual addressing, which implies that the kernel
image must be loaded into 48-bit addressable physical memory. This is
currently required by the boot protocol, even though we happen to
support placement outside of that for LVA/64k based configurations.

Enabling LPA2 involves more than setting TCR.T1SZ to a lower value,
there is also a DS bit in TCR that needs to be set, and which changes
the meaning of bits [9:8] in all page table descriptors. Since we cannot
enable DS and every live page table descriptor at the same time, let's
pivot through another temporary mapping. This avoids the need to
reintroduce manipulations of the page tables with the MMU and caches
disabled.

To permit the LPA2 feature to be overridden on the kernel command line,
which may be necessary to work around silicon errata, or to deal with
mismatched features on heterogeneous SoC designs, test for CPU feature
overrides first, and only then enable LPA2.

Signed-off-by: Ard Biesheuvel <ardb@kernel.org>
Link: https://lore.kernel.org/r/20240214122845.2033971-78-ardb+git@google.com
Signed-off-by: Catalin Marinas <catalin.marinas@arm.com>

arch/arm64/include/asm/assembler.h

@@ -581,11 +581,17 @@ alternative_endif
  * but we have to add an offset so that the TTBR1 address corresponds with the
  * pgdir entry that covers the lowest 48-bit addressable VA.
  *
+ * Note that this trick is only used for LVA/64k pages - LPA2/4k pages uses an
+ * additional paging level, and on LPA2/16k pages, we would end up with a root
+ * level table with only 2 entries, which is suboptimal in terms of TLB
+ * utilization, so there we fall back to 47 bits of translation if LPA2 is not
+ * supported.
+ *
  * orr is used as it can cover the immediate value (and is idempotent).
  * 	ttbr: Value of ttbr to set, modified.
  */
 	.macro	offset_ttbr1, ttbr, tmp
-#ifdef CONFIG_ARM64_VA_BITS_52
+#if defined(CONFIG_ARM64_VA_BITS_52) && !defined(CONFIG_ARM64_LPA2)
 	mrs	\tmp, tcr_el1
 	and	\tmp, \tmp, #TCR_T1SZ_MASK
 	cmp	\tmp, #TCR_T1SZ(VA_BITS_MIN)

arch/arm64/include/asm/cpufeature.h

@@ -1008,6 +1008,24 @@ static inline bool cpu_has_lva(void)
 						    ID_AA64MMFR2_EL1_VARange_SHIFT);
 }
 
+static inline bool cpu_has_lpa2(void)
+{
+#ifdef CONFIG_ARM64_LPA2
+	u64 mmfr0;
+	int feat;
+
+	mmfr0 = read_sysreg(id_aa64mmfr0_el1);
+	mmfr0 &= ~id_aa64mmfr0_override.mask;
+	mmfr0 |= id_aa64mmfr0_override.val;
+	feat = cpuid_feature_extract_signed_field(mmfr0,
+						  ID_AA64MMFR0_EL1_TGRAN_SHIFT);
+
+	return feat >= ID_AA64MMFR0_EL1_TGRAN_LPA2;
+#else
+	return false;
+#endif
+}
+
 #endif /* __ASSEMBLY__ */
 
 #endif

arch/arm64/include/asm/memory.h

@@ -54,7 +54,11 @@
 #define FIXADDR_TOP		(-UL(SZ_8M))
 
 #if VA_BITS > 48
+#ifdef CONFIG_ARM64_16K_PAGES
+#define VA_BITS_MIN		(47)
+#else
 #define VA_BITS_MIN		(48)
+#endif
 #else
 #define VA_BITS_MIN		(VA_BITS)
 #endif

arch/arm64/kernel/head.S

@@ -89,6 +89,7 @@ SYM_CODE_START(primary_entry)
 	mov	sp, x1
 	mov	x29, xzr
 	adrp	x0, init_idmap_pg_dir
+	mov	x1, xzr
 	bl	__pi_create_init_idmap
 
 	/*
@@ -473,9 +474,16 @@ SYM_FUNC_END(__enable_mmu)
 
 #ifdef CONFIG_ARM64_VA_BITS_52
 SYM_FUNC_START(__cpu_secondary_check52bitva)
+#ifndef CONFIG_ARM64_LPA2
 	mrs_s	x0, SYS_ID_AA64MMFR2_EL1
 	and	x0, x0, ID_AA64MMFR2_EL1_VARange_MASK
 	cbnz	x0, 2f
+#else
+	mrs	x0, id_aa64mmfr0_el1
+	sbfx	x0, x0, #ID_AA64MMFR0_EL1_TGRAN_SHIFT, 4
+	cmp	x0, #ID_AA64MMFR0_EL1_TGRAN_LPA2
+	b.ge	2f
+#endif
 
 	update_early_cpu_boot_status \
 		CPU_STUCK_IN_KERNEL | CPU_STUCK_REASON_52_BIT_VA, x0, x1

arch/arm64/kernel/image-vars.h

@@ -54,6 +54,7 @@ PROVIDE(__pi__ctype			= _ctype);
 PROVIDE(__pi_memstart_offset_seed	= memstart_offset_seed);
 
 PROVIDE(__pi_init_idmap_pg_dir		= init_idmap_pg_dir);
+PROVIDE(__pi_init_idmap_pg_end		= init_idmap_pg_end);
 PROVIDE(__pi_init_pg_dir		= init_pg_dir);
 PROVIDE(__pi_init_pg_end		= init_pg_end);
 PROVIDE(__pi_swapper_pg_dir		= swapper_pg_dir);

arch/arm64/kernel/pi/map_kernel.c

@@ -127,11 +127,64 @@ static void __init map_kernel(u64 kaslr_offset, u64 va_offset, int root_level)
 	}
 
 	/* Copy the root page table to its final location */
-	memcpy((void *)swapper_pg_dir + va_offset, init_pg_dir, PGD_SIZE);
+	memcpy((void *)swapper_pg_dir + va_offset, init_pg_dir, PAGE_SIZE);
 	dsb(ishst);
 	idmap_cpu_replace_ttbr1(swapper_pg_dir);
 }
 
+static void noinline __section(".idmap.text") set_ttbr0_for_lpa2(u64 ttbr)
+{
+	u64 sctlr = read_sysreg(sctlr_el1);
+	u64 tcr = read_sysreg(tcr_el1) | TCR_DS;
+
+	asm("	msr	sctlr_el1, %0		;"
+	    "	isb				;"
+	    "   msr     ttbr0_el1, %1		;"
+	    "   msr     tcr_el1, %2		;"
+	    "	isb				;"
+	    "	tlbi    vmalle1			;"
+	    "	dsb     nsh			;"
+	    "	isb				;"
+	    "	msr     sctlr_el1, %3		;"
+	    "	isb				;"
+	    ::	"r"(sctlr & ~SCTLR_ELx_M), "r"(ttbr), "r"(tcr), "r"(sctlr));
+}
+
+static void __init remap_idmap_for_lpa2(void)
+{
+	/* clear the bits that change meaning once LPA2 is turned on */
+	pteval_t mask = PTE_SHARED;
+
+	/*
+	 * We have to clear bits [9:8] in all block or page descriptors in the
+	 * initial ID map, as otherwise they will be (mis)interpreted as
+	 * physical address bits once we flick the LPA2 switch (TCR.DS). Since
+	 * we cannot manipulate live descriptors in that way without creating
+	 * potential TLB conflicts, let's create another temporary ID map in a
+	 * LPA2 compatible fashion, and update the initial ID map while running
+	 * from that.
+	 */
+	create_init_idmap(init_pg_dir, mask);
+	dsb(ishst);
+	set_ttbr0_for_lpa2((u64)init_pg_dir);
+
+	/*
+	 * Recreate the initial ID map with the same granularity as before.
+	 * Don't bother with the FDT, we no longer need it after this.
+	 */
+	memset(init_idmap_pg_dir, 0,
+	       (u64)init_idmap_pg_dir - (u64)init_idmap_pg_end);
+
+	create_init_idmap(init_idmap_pg_dir, mask);
+	dsb(ishst);
+
+	/* switch back to the updated initial ID map */
+	set_ttbr0_for_lpa2((u64)init_idmap_pg_dir);
+
+	/* wipe the temporary ID map from memory */
+	memset(init_pg_dir, 0, (u64)init_pg_end - (u64)init_pg_dir);
+}
+
 static void __init map_fdt(u64 fdt)
 {
 	static u8 ptes[INIT_IDMAP_FDT_SIZE] __initdata __aligned(PAGE_SIZE);
@@ -154,6 +207,7 @@ asmlinkage void __init early_map_kernel(u64 boot_status, void *fdt)
 	u64 va_base, pa_base = (u64)&_text;
 	u64 kaslr_offset = pa_base % MIN_KIMG_ALIGN;
 	int root_level = 4 - CONFIG_PGTABLE_LEVELS;
+	int va_bits = VA_BITS;
 	int chosen;
 
 	map_fdt((u64)fdt);
@@ -165,8 +219,15 @@ asmlinkage void __init early_map_kernel(u64 boot_status, void *fdt)
 	chosen = fdt_path_offset(fdt, chosen_str);
 	init_feature_override(boot_status, fdt, chosen);
 
-	if (VA_BITS > VA_BITS_MIN && cpu_has_lva())
-		sysreg_clear_set(tcr_el1, TCR_T1SZ_MASK, TCR_T1SZ(VA_BITS));
+	if (IS_ENABLED(CONFIG_ARM64_64K_PAGES) && !cpu_has_lva()) {
+		va_bits = VA_BITS_MIN;
+	} else if (IS_ENABLED(CONFIG_ARM64_LPA2) && !cpu_has_lpa2()) {
+		va_bits = VA_BITS_MIN;
+		root_level++;
+	}
+
+	if (va_bits > VA_BITS_MIN)
+		sysreg_clear_set(tcr_el1, TCR_T1SZ_MASK, TCR_T1SZ(va_bits));
 
 	/*
 	 * The virtual KASLR displacement modulo 2MiB is decided by the
@@ -184,6 +245,9 @@ asmlinkage void __init early_map_kernel(u64 boot_status, void *fdt)
 		kaslr_offset |= kaslr_seed & ~(MIN_KIMG_ALIGN - 1);
 	}
 
+	if (IS_ENABLED(CONFIG_ARM64_LPA2) && va_bits > VA_BITS_MIN)
+		remap_idmap_for_lpa2();
+
 	va_base = KIMAGE_VADDR + kaslr_offset;
 	map_kernel(kaslr_offset, va_base - pa_base, root_level);
 }

arch/arm64/kernel/pi/map_range.c

@@ -87,14 +87,19 @@ void __init map_range(u64 *pte, u64 start, u64 end, u64 pa, pgprot_t prot,
 	}
 }
 
-asmlinkage u64 __init create_init_idmap(pgd_t *pg_dir)
+asmlinkage u64 __init create_init_idmap(pgd_t *pg_dir, pteval_t clrmask)
 {
 	u64 ptep = (u64)pg_dir + PAGE_SIZE;
+	pgprot_t text_prot = PAGE_KERNEL_ROX;
+	pgprot_t data_prot = PAGE_KERNEL;
+
+	pgprot_val(text_prot) &= ~clrmask;
+	pgprot_val(data_prot) &= ~clrmask;
 
 	map_range(&ptep, (u64)_stext, (u64)__initdata_begin, (u64)_stext,
-		  PAGE_KERNEL_ROX, IDMAP_ROOT_LEVEL, (pte_t *)pg_dir, false, 0);
+		  text_prot, IDMAP_ROOT_LEVEL, (pte_t *)pg_dir, false, 0);
 	map_range(&ptep, (u64)__initdata_begin, (u64)_end, (u64)__initdata_begin,
-		  PAGE_KERNEL, IDMAP_ROOT_LEVEL, (pte_t *)pg_dir, false, 0);
+		  data_prot, IDMAP_ROOT_LEVEL, (pte_t *)pg_dir, false, 0);
 
 	return ptep;
 }

arch/arm64/kernel/pi/pi.h

@@ -21,7 +21,7 @@ static inline void *prel64_to_pointer(const prel64_t *offset)
 
 extern bool dynamic_scs_is_enabled;
 
-extern pgd_t init_idmap_pg_dir[];
+extern pgd_t init_idmap_pg_dir[], init_idmap_pg_end[];
 
 void init_feature_override(u64 boot_status, const void *fdt, int chosen);
 u64 kaslr_early_init(void *fdt, int chosen);
@@ -33,4 +33,4 @@ void map_range(u64 *pgd, u64 start, u64 end, u64 pa, pgprot_t prot,
 
 asmlinkage void early_map_kernel(u64 boot_status, void *fdt);
 
-asmlinkage u64 create_init_idmap(pgd_t *pgd);
+asmlinkage u64 create_init_idmap(pgd_t *pgd, pteval_t clrmask);

arch/arm64/mm/init.c

@@ -238,7 +238,7 @@ void __init arm64_memblock_init(void)
 	 * physical address of PAGE_OFFSET, we have to *subtract* from it.
 	 */
 	if (IS_ENABLED(CONFIG_ARM64_VA_BITS_52) && (vabits_actual != 52))
-		memstart_addr -= _PAGE_OFFSET(48) - _PAGE_OFFSET(52);
+		memstart_addr -= _PAGE_OFFSET(vabits_actual) - _PAGE_OFFSET(52);
 
 	/*
 	 * Apply the memory limit if it was set. Since the kernel may be loaded

arch/arm64/mm/mmu.c

@@ -582,8 +582,12 @@ static void __init map_mem(pgd_t *pgdp)
 	 * entries at any level are being shared between the linear region and
 	 * the vmalloc region. Check whether this is true for the PGD level, in
 	 * which case it is guaranteed to be true for all other levels as well.
+	 * (Unless we are running with support for LPA2, in which case the
+	 * entire reduced VA space is covered by a single pgd_t which will have
+	 * been populated without the PXNTable attribute by the time we get here.)
 	 */
-	BUILD_BUG_ON(pgd_index(direct_map_end - 1) == pgd_index(direct_map_end));
+	BUILD_BUG_ON(pgd_index(direct_map_end - 1) == pgd_index(direct_map_end) &&
+		     pgd_index(_PAGE_OFFSET(VA_BITS_MIN)) != PTRS_PER_PGD - 1);
 
 	early_kfence_pool = arm64_kfence_alloc_pool();
 

arch/arm64/mm/proc.S

@@ -488,6 +488,9 @@ SYM_FUNC_START(__cpu_setup)
 	mov		x9, #64 - VA_BITS
 alternative_if ARM64_HAS_VA52
 	tcr_set_t1sz	tcr, x9
+#ifdef CONFIG_ARM64_LPA2
+	orr		tcr, tcr, #TCR_DS
+#endif
 alternative_else_nop_endif
 #endif