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

willdeacon · willdeacon · commit 602ffd4ce3a6 · 2025-01-17T13:52:33.000Z
* for-next/mm:
  arm64: mm: Test for pmd_sect() in vmemmap_check_pmd()
  arm64/mm: Replace open encodings with PXD_TABLE_BIT
  arm64/mm: Rename pte_mkpresent() as pte_mkvalid()
  arm64: Kconfig: force ARM64_PAN=y when enabling TTBR0 sw PAN
  arm64/kvm: Avoid invalid physical addresses to signal owner updates
  arm64/kvm: Configure HYP TCR.PS/DS based on host stage1
  arm64/mm: Override PARange for !LPA2 and use it consistently
  arm64/mm: Reduce PA space to 48 bits when LPA2 is not enabled
diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig
@@ -1379,7 +1379,6 @@ config ARM64_VA_BITS_48
 
 config ARM64_VA_BITS_52
 	bool "52-bit"
-	depends on ARM64_PAN || !ARM64_SW_TTBR0_PAN
 	help
 	  Enable 52-bit virtual addressing for userspace when explicitly
 	  requested via a hint to mmap(). The kernel will also use 52-bit
@@ -1431,7 +1430,6 @@ config ARM64_PA_BITS_48
 config ARM64_PA_BITS_52
 	bool "52-bit"
 	depends on ARM64_64K_PAGES || ARM64_VA_BITS_52
-	depends on ARM64_PAN || !ARM64_SW_TTBR0_PAN
 	help
 	  Enable support for a 52-bit physical address space, introduced as
 	  part of the ARMv8.2-LPA extension.
@@ -1681,6 +1679,7 @@ config RODATA_FULL_DEFAULT_ENABLED
 config ARM64_SW_TTBR0_PAN
 	bool "Emulate Privileged Access Never using TTBR0_EL1 switching"
 	depends on !KCSAN
+	select ARM64_PAN
 	help
 	  Enabling this option prevents the kernel from accessing
 	  user-space memory directly by pointing TTBR0_EL1 to a reserved
@@ -1937,7 +1936,6 @@ config ARM64_RAS_EXTN
 config ARM64_CNP
 	bool "Enable support for Common Not Private (CNP) translations"
 	default y
-	depends on ARM64_PAN || !ARM64_SW_TTBR0_PAN
 	help
 	  Common Not Private (CNP) allows translation table entries to
 	  be shared between different PEs in the same inner shareable
@@ -2132,7 +2130,7 @@ config ARM64_MTE
 	depends on AS_HAS_ARMV8_5
 	depends on AS_HAS_LSE_ATOMICS
 	# Required for tag checking in the uaccess routines
-	depends on ARM64_PAN
+	select ARM64_PAN
 	select ARCH_HAS_SUBPAGE_FAULTS
 	select ARCH_USES_HIGH_VMA_FLAGS
 	select ARCH_USES_PG_ARCH_2
diff --git a/arch/arm64/include/asm/assembler.h b/arch/arm64/include/asm/assembler.h
@@ -343,6 +343,11 @@ alternative_cb_end
 	// Narrow PARange to fit the PS field in TCR_ELx
 	ubfx	\tmp0, \tmp0, #ID_AA64MMFR0_EL1_PARANGE_SHIFT, #3
 	mov	\tmp1, #ID_AA64MMFR0_EL1_PARANGE_MAX
+#ifdef CONFIG_ARM64_LPA2
+alternative_if_not ARM64_HAS_VA52
+	mov	\tmp1, #ID_AA64MMFR0_EL1_PARANGE_48
+alternative_else_nop_endif
+#endif
 	cmp	\tmp0, \tmp1
 	csel	\tmp0, \tmp1, \tmp0, hi
 	bfi	\tcr, \tmp0, \pos, #3
diff --git a/arch/arm64/include/asm/pgtable-hwdef.h b/arch/arm64/include/asm/pgtable-hwdef.h
@@ -222,12 +222,6 @@
  */
 #define S1_TABLE_AP		(_AT(pmdval_t, 3) << 61)
 
-/*
- * Highest possible physical address supported.
- */
-#define PHYS_MASK_SHIFT		(CONFIG_ARM64_PA_BITS)
-#define PHYS_MASK		((UL(1) << PHYS_MASK_SHIFT) - 1)
-
 #define TTBR_CNP_BIT		(UL(1) << 0)
 
 /*
diff --git a/arch/arm64/include/asm/pgtable-prot.h b/arch/arm64/include/asm/pgtable-prot.h
@@ -81,6 +81,7 @@ extern unsigned long prot_ns_shared;
 #define lpa2_is_enabled()	false
 #define PTE_MAYBE_SHARED	PTE_SHARED
 #define PMD_MAYBE_SHARED	PMD_SECT_S
+#define PHYS_MASK_SHIFT		(CONFIG_ARM64_PA_BITS)
 #else
 static inline bool __pure lpa2_is_enabled(void)
 {
@@ -89,8 +90,14 @@ static inline bool __pure lpa2_is_enabled(void)
 
 #define PTE_MAYBE_SHARED	(lpa2_is_enabled() ? 0 : PTE_SHARED)
 #define PMD_MAYBE_SHARED	(lpa2_is_enabled() ? 0 : PMD_SECT_S)
+#define PHYS_MASK_SHIFT		(lpa2_is_enabled() ? CONFIG_ARM64_PA_BITS : 48)
 #endif
 
+/*
+ * Highest possible physical address supported.
+ */
+#define PHYS_MASK		((UL(1) << PHYS_MASK_SHIFT) - 1)
+
 /*
  * If we have userspace only BTI we don't want to mark kernel pages
  * guarded even if the system does support BTI.
diff --git a/arch/arm64/include/asm/pgtable.h b/arch/arm64/include/asm/pgtable.h
@@ -273,7 +273,7 @@ static inline pte_t pte_mknoncont(pte_t pte)
 	return clear_pte_bit(pte, __pgprot(PTE_CONT));
 }
 
-static inline pte_t pte_mkpresent(pte_t pte)
+static inline pte_t pte_mkvalid(pte_t pte)
 {
 	return set_pte_bit(pte, __pgprot(PTE_VALID));
 }
diff --git a/arch/arm64/include/asm/sparsemem.h b/arch/arm64/include/asm/sparsemem.h
@@ -5,7 +5,10 @@
 #ifndef __ASM_SPARSEMEM_H
 #define __ASM_SPARSEMEM_H
 
-#define MAX_PHYSMEM_BITS	CONFIG_ARM64_PA_BITS
+#include <asm/pgtable-prot.h>
+
+#define MAX_PHYSMEM_BITS		PHYS_MASK_SHIFT
+#define MAX_POSSIBLE_PHYSMEM_BITS	(52)
 
 /*
  * Section size must be at least 512MB for 64K base
diff --git a/arch/arm64/kernel/cpufeature.c b/arch/arm64/kernel/cpufeature.c
@@ -3509,7 +3509,7 @@ static void verify_hyp_capabilities(void)
 		return;
 
 	safe_mmfr1 = read_sanitised_ftr_reg(SYS_ID_AA64MMFR1_EL1);
-	mmfr0 = read_cpuid(ID_AA64MMFR0_EL1);
+	mmfr0 = read_sanitised_ftr_reg(SYS_ID_AA64MMFR0_EL1);
 	mmfr1 = read_cpuid(ID_AA64MMFR1_EL1);
 
 	/* Verify VMID bits */
diff --git a/arch/arm64/kernel/pi/idreg-override.c b/arch/arm64/kernel/pi/idreg-override.c
@@ -83,6 +83,15 @@ static bool __init mmfr2_varange_filter(u64 val)
 		id_aa64mmfr0_override.val |=
 			(ID_AA64MMFR0_EL1_TGRAN_LPA2 - 1) << ID_AA64MMFR0_EL1_TGRAN_SHIFT;
 		id_aa64mmfr0_override.mask |= 0xfU << ID_AA64MMFR0_EL1_TGRAN_SHIFT;
+
+		/*
+		 * Override PARange to 48 bits - the override will just be
+		 * ignored if the actual PARange is smaller, but this is
+		 * unlikely to be the case for LPA2 capable silicon.
+		 */
+		id_aa64mmfr0_override.val |=
+			ID_AA64MMFR0_EL1_PARANGE_48 << ID_AA64MMFR0_EL1_PARANGE_SHIFT;
+		id_aa64mmfr0_override.mask |= 0xfU << ID_AA64MMFR0_EL1_PARANGE_SHIFT;
 	}
 #endif
 	return true;
diff --git a/arch/arm64/kernel/pi/map_kernel.c b/arch/arm64/kernel/pi/map_kernel.c
@@ -136,6 +136,12 @@ 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;
+	u64 mmfr0 = read_sysreg(id_aa64mmfr0_el1);
+	u64 parange = cpuid_feature_extract_unsigned_field(mmfr0,
+							   ID_AA64MMFR0_EL1_PARANGE_SHIFT);
+
+	tcr &= ~TCR_IPS_MASK;
+	tcr |= parange << TCR_IPS_SHIFT;
 
 	asm("	msr	sctlr_el1, %0		;"
 	    "	isb				;"
diff --git a/arch/arm64/kvm/arm.c b/arch/arm64/kvm/arm.c
@@ -1990,8 +1990,7 @@ static int kvm_init_vector_slots(void)
 static void __init cpu_prepare_hyp_mode(int cpu, u32 hyp_va_bits)
 {
 	struct kvm_nvhe_init_params *params = per_cpu_ptr_nvhe_sym(kvm_init_params, cpu);
-	u64 mmfr0 = read_sanitised_ftr_reg(SYS_ID_AA64MMFR0_EL1);
-	unsigned long tcr;
+	unsigned long tcr, ips;
 
 	/*
 	 * Calculate the raw per-cpu offset without a translation from the
@@ -2005,6 +2004,7 @@ static void __init cpu_prepare_hyp_mode(int cpu, u32 hyp_va_bits)
 	params->mair_el2 = read_sysreg(mair_el1);
 
 	tcr = read_sysreg(tcr_el1);
+	ips = FIELD_GET(TCR_IPS_MASK, tcr);
 	if (cpus_have_final_cap(ARM64_KVM_HVHE)) {
 		tcr |= TCR_EPD1_MASK;
 	} else {
@@ -2014,8 +2014,8 @@ static void __init cpu_prepare_hyp_mode(int cpu, u32 hyp_va_bits)
 	tcr &= ~TCR_T0SZ_MASK;
 	tcr |= TCR_T0SZ(hyp_va_bits);
 	tcr &= ~TCR_EL2_PS_MASK;
-	tcr |= FIELD_PREP(TCR_EL2_PS_MASK, kvm_get_parange(mmfr0));
-	if (kvm_lpa2_is_enabled())
+	tcr |= FIELD_PREP(TCR_EL2_PS_MASK, ips);
+	if (lpa2_is_enabled())
 		tcr |= TCR_EL2_DS;
 	params->tcr_el2 = tcr;
 
diff --git a/arch/arm64/kvm/hyp/pgtable.c b/arch/arm64/kvm/hyp/pgtable.c
@@ -35,14 +35,6 @@ static bool kvm_pgtable_walk_skip_cmo(const struct kvm_pgtable_visit_ctx *ctx)
 	return unlikely(ctx->flags & KVM_PGTABLE_WALK_SKIP_CMO);
 }
 
-static bool kvm_phys_is_valid(u64 phys)
-{
-	u64 parange_max = kvm_get_parange_max();
-	u8 shift = id_aa64mmfr0_parange_to_phys_shift(parange_max);
-
-	return phys < BIT(shift);
-}
-
 static bool kvm_block_mapping_supported(const struct kvm_pgtable_visit_ctx *ctx, u64 phys)
 {
 	u64 granule = kvm_granule_size(ctx->level);
@@ -53,7 +45,7 @@ static bool kvm_block_mapping_supported(const struct kvm_pgtable_visit_ctx *ctx,
 	if (granule > (ctx->end - ctx->addr))
 		return false;
 
-	if (kvm_phys_is_valid(phys) && !IS_ALIGNED(phys, granule))
+	if (!IS_ALIGNED(phys, granule))
 		return false;
 
 	return IS_ALIGNED(ctx->addr, granule);
@@ -587,6 +579,9 @@ struct stage2_map_data {
 
 	/* Force mappings to page granularity */
 	bool				force_pte;
+
+	/* Walk should update owner_id only */
+	bool				annotation;
 };
 
 u64 kvm_get_vtcr(u64 mmfr0, u64 mmfr1, u32 phys_shift)
@@ -885,18 +880,7 @@ static u64 stage2_map_walker_phys_addr(const struct kvm_pgtable_visit_ctx *ctx,
 {
 	u64 phys = data->phys;
 
-	/*
-	 * Stage-2 walks to update ownership data are communicated to the map
-	 * walker using an invalid PA. Avoid offsetting an already invalid PA,
-	 * which could overflow and make the address valid again.
-	 */
-	if (!kvm_phys_is_valid(phys))
-		return phys;
-
-	/*
-	 * Otherwise, work out the correct PA based on how far the walk has
-	 * gotten.
-	 */
+	/* Work out the correct PA based on how far the walk has gotten */
 	return phys + (ctx->addr - ctx->start);
 }
 
@@ -908,6 +892,9 @@ static bool stage2_leaf_mapping_allowed(const struct kvm_pgtable_visit_ctx *ctx,
 	if (data->force_pte && ctx->level < KVM_PGTABLE_LAST_LEVEL)
 		return false;
 
+	if (data->annotation)
+		return true;
+
 	return kvm_block_mapping_supported(ctx, phys);
 }
 
@@ -923,7 +910,7 @@ static int stage2_map_walker_try_leaf(const struct kvm_pgtable_visit_ctx *ctx,
 	if (!stage2_leaf_mapping_allowed(ctx, data))
 		return -E2BIG;
 
-	if (kvm_phys_is_valid(phys))
+	if (!data->annotation)
 		new = kvm_init_valid_leaf_pte(phys, data->attr, ctx->level);
 	else
 		new = kvm_init_invalid_leaf_owner(data->owner_id);
@@ -1085,11 +1072,11 @@ int kvm_pgtable_stage2_set_owner(struct kvm_pgtable *pgt, u64 addr, u64 size,
 {
 	int ret;
 	struct stage2_map_data map_data = {
-		.phys		= KVM_PHYS_INVALID,
 		.mmu		= pgt->mmu,
 		.memcache	= mc,
 		.owner_id	= owner_id,
 		.force_pte	= true,
+		.annotation	= true,
 	};
 	struct kvm_pgtable_walker walker = {
 		.cb		= stage2_map_walker,
diff --git a/arch/arm64/mm/init.c b/arch/arm64/mm/init.c
@@ -279,7 +279,12 @@ void __init arm64_memblock_init(void)
 
 	if (IS_ENABLED(CONFIG_RANDOMIZE_BASE)) {
 		extern u16 memstart_offset_seed;
-		u64 mmfr0 = read_cpuid(ID_AA64MMFR0_EL1);
+
+		/*
+		 * Use the sanitised version of id_aa64mmfr0_el1 so that linear
+		 * map randomization can be enabled by shrinking the IPA space.
+		 */
+		u64 mmfr0 = read_sanitised_ftr_reg(SYS_ID_AA64MMFR0_EL1);
 		int parange = cpuid_feature_extract_unsigned_field(
 					mmfr0, ID_AA64MMFR0_EL1_PARANGE_SHIFT);
 		s64 range = linear_region_size -
diff --git a/arch/arm64/mm/mmu.c b/arch/arm64/mm/mmu.c
@@ -1169,7 +1169,8 @@ int __meminit vmemmap_check_pmd(pmd_t *pmdp, int node,
 				unsigned long addr, unsigned long next)
 {
 	vmemmap_verify((pte_t *)pmdp, node, addr, next);
-	return 1;
+
+	return pmd_sect(READ_ONCE(*pmdp));
 }
 
 int __meminit vmemmap_populate(unsigned long start, unsigned long end, int node,
diff --git a/arch/arm64/mm/trans_pgd.c b/arch/arm64/mm/trans_pgd.c
@@ -57,7 +57,7 @@ static void _copy_pte(pte_t *dst_ptep, pte_t *src_ptep, unsigned long addr)
 		 */
 		BUG_ON(!pfn_valid(pte_pfn(pte)));
 
-		__set_pte(dst_ptep, pte_mkpresent(pte_mkwrite_novma(pte)));
+		__set_pte(dst_ptep, pte_mkvalid(pte_mkwrite_novma(pte)));
 	}
 }
 

Original file line number	Diff line number	Diff line change
`@@ -273,7 +273,7 @@ static inline pte_t pte_mknoncont(pte_t pte)`
`273`	`273`	`return clear_pte_bit(pte, __pgprot(PTE_CONT));`
`274`	`274`	`}`
`275`	`275`
`276`		`-static inline pte_t pte_mkpresent(pte_t pte)`
	`276`	`+static inline pte_t pte_mkvalid(pte_t pte)`
`277`	`277`	`{`
`278`	`278`	`return set_pte_bit(pte, __pgprot(PTE_VALID));`
`279`	`279`	`}`