diff mbox series

[RFC,6/7] arm64: Enable LPA2 at boot if supported by the system

Message ID 20221117132423.1252942-7-ardb@kernel.org (mailing list archive)
State New, archived
Headers show
Series arm64: Enable LPA2 support for 16k pages | expand

Commit Message

Ard Biesheuvel Nov. 17, 2022, 1:24 p.m. UTC
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, 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 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, we have to pivot through another
temporary mapping. This avoids reintroducing manipulations of the page
tables with the MMU and caches disabled, which is something we generally
try to avoid.

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>
---
 arch/arm64/kernel/image-vars.h    |   2 +
 arch/arm64/kernel/pi/map_kernel.c | 101 +++++++++++++++++++-
 arch/arm64/mm/proc.S              |   3 +
 3 files changed, 103 insertions(+), 3 deletions(-)
diff mbox series

Patch

diff --git a/arch/arm64/kernel/image-vars.h b/arch/arm64/kernel/image-vars.h
index 82bafa1f869c3a8b..f48b6f09d278d3bf 100644
--- a/arch/arm64/kernel/image-vars.h
+++ b/arch/arm64/kernel/image-vars.h
@@ -56,6 +56,8 @@  PROVIDE(__pi_arm64_sw_feature_override	= arm64_sw_feature_override);
 PROVIDE(__pi_arm64_use_ng_mappings	= arm64_use_ng_mappings);
 PROVIDE(__pi__ctype			= _ctype);
 
+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);
diff --git a/arch/arm64/kernel/pi/map_kernel.c b/arch/arm64/kernel/pi/map_kernel.c
index 3b0b3fecf2bd533b..71cc32cd2545b85a 100644
--- a/arch/arm64/kernel/pi/map_kernel.c
+++ b/arch/arm64/kernel/pi/map_kernel.c
@@ -137,6 +137,22 @@  static bool __init arm64_early_this_cpu_has_lva(void)
 						    ID_AA64MMFR2_EL1_VARange_SHIFT);
 }
 
+static bool __init arm64_early_this_cpu_has_lpa2(void)
+{
+	bool gran4k = IS_ENABLED(CONFIG_ARM64_4K_PAGES);
+	u64 mmfr0;
+	int feat;
+
+	mmfr0 = read_sysreg(id_aa64mmfr0_el1);
+	mmfr0 &= ~id_aa64mmfr0_override.mask;
+	mmfr0 |= id_aa64mmfr0_override.val;
+	feat = cpuid_feature_extract_field(mmfr0, ID_AA64MMFR0_EL1_TGRAN_SHIFT,
+					   gran4k /* signed */);
+
+	return gran4k ? feat >= ID_AA64MMFR0_EL1_TGRAN4_52_BIT
+		      : feat >= ID_AA64MMFR0_EL1_TGRAN16_52_BIT;
+}
+
 static bool __init arm64_early_this_cpu_has_pac(void)
 {
 	u64 isar1, isar2;
@@ -279,6 +295,74 @@  static void noinline __section(".idmap.text") disable_wxn(void)
 	    ::	"r"(sctlr & ~SCTLR_ELx_M), "r"(sctlr));
 }
 
+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 remap_idmap_for_lpa2(void)
+{
+	extern pgd_t init_idmap_pg_dir[], init_idmap_pg_end[];
+	pgd_t *pgdp = (void *)init_pg_dir + PAGE_SIZE;
+	pgprot_t text_prot = PAGE_KERNEL_ROX;
+	pgprot_t data_prot = PAGE_KERNEL;
+
+	/* clear the bits that change meaning once LPA2 is turned on */
+	pgprot_val(text_prot) &= ~PTE_SHARED;
+	pgprot_val(data_prot) &= ~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.
+	 */
+	map_segment(init_pg_dir, &pgdp, 0, _stext, __inittext_end, text_prot, false);
+	map_segment(init_pg_dir, &pgdp, 0, __initdata_begin, _end, data_prot, false);
+	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);
+
+	pgdp = (void *)init_idmap_pg_dir + PAGE_SIZE;
+	map_segment(init_idmap_pg_dir, &pgdp, 0,
+		    PTR_ALIGN_DOWN(&_stext[0], INIT_IDMAP_BLOCK_SIZE),
+		    PTR_ALIGN_DOWN(&__bss_start[0], INIT_IDMAP_BLOCK_SIZE),
+		    text_prot, false);
+	map_segment(init_idmap_pg_dir, &pgdp, 0,
+		    PTR_ALIGN_DOWN(&__bss_start[0], INIT_IDMAP_BLOCK_SIZE),
+		    PTR_ALIGN(&_end[0], INIT_IDMAP_BLOCK_SIZE),
+		    data_prot, false);
+	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);
+}
+
 asmlinkage void __init early_map_kernel(u64 boot_status, void *fdt)
 {
 	static char const chosen_str[] __initconst = "/chosen";
@@ -292,9 +376,6 @@  asmlinkage void __init early_map_kernel(u64 boot_status, void *fdt)
 	/* Parse the command line for CPU feature overrides */
 	init_feature_override(boot_status, fdt, chosen);
 
-	if (VA_BITS > VA_BITS_MIN && arm64_early_this_cpu_has_lva())
-		sysreg_clear_set(tcr_el1, TCR_T1SZ_MASK, TCR_T1SZ(VA_BITS));
-
 	if (IS_ENABLED(CONFIG_ARM64_WXN) &&
 	    cpuid_feature_extract_unsigned_field(arm64_sw_feature_override.val,
 						 ARM64_SW_FEATURE_OVERRIDE_NOWXN))
@@ -322,6 +403,20 @@  asmlinkage void __init early_map_kernel(u64 boot_status, void *fdt)
 			arm64_use_ng_mappings = true;
 	}
 
+	if (VA_BITS > VA_BITS_MIN) {
+		bool va52 = false;
+
+		if (IS_ENABLED(CONFIG_ARM64_64K_PAGES)) {
+			va52 = arm64_early_this_cpu_has_lva();
+		} else if (arm64_early_this_cpu_has_lpa2()) {
+			remap_idmap_for_lpa2();
+			va52 = true;
+		}
+		if (va52)
+			sysreg_clear_set(tcr_el1, TCR_T1SZ_MASK,
+					 TCR_T1SZ(VA_BITS));
+	}
+
 	va_base = KIMAGE_VADDR + kaslr_offset;
 	map_kernel(kaslr_offset, va_base - pa_base);
 }
diff --git a/arch/arm64/mm/proc.S b/arch/arm64/mm/proc.S
index c747a2ef478cabec..8197663a54f63c9d 100644
--- a/arch/arm64/mm/proc.S
+++ b/arch/arm64/mm/proc.S
@@ -443,6 +443,9 @@  SYM_FUNC_START(__cpu_setup)
 #if VA_BITS > VA_BITS_MIN
 alternative_if ARM64_HAS_LVA
 	eor		tcr, tcr, #TCR_T1SZ(VA_BITS) ^ TCR_T1SZ(VA_BITS_MIN)
+#ifndef CONFIG_ARM64_64K_PAGES
+	orr		tcr, tcr, #TCR_DS
+#endif
 alternative_else_nop_endif
 #elif VA_BITS < 48
 	idmap_get_t0sz	x9