From bf74bb73cd87c64bd5afc1fd4b749029997b6170 Mon Sep 17 00:00:00 2001 From: Ard Biesheuvel Date: Thu, 12 Dec 2024 09:18:43 +0100 Subject: [PATCH 1/8] arm64/mm: Reduce PA space to 48 bits when LPA2 is not enabled Currently, LPA2 kernel support implies support for up to 52 bits of physical addressing, and this is reflected in global definitions such as PHYS_MASK_SHIFT and MAX_PHYSMEM_BITS. This is potentially problematic, given that LPA2 hardware support is modeled as a CPU feature which can be overridden, and with LPA2 hardware support turned off, attempting to map physical regions with address bits [51:48] set (which may exist on LPA2 capable systems booting with arm64.nolva) will result in corrupted mappings with a truncated output address and bogus shareability attributes. This means that the accepted physical address range in the mapping routines should be at most 48 bits wide when LPA2 support is configured but not enabled at runtime. Fixes: 352b0395b505 ("arm64: Enable 52-bit virtual addressing for 4k and 16k granule configs") Cc: stable@vger.kernel.org Reviewed-by: Anshuman Khandual Signed-off-by: Ard Biesheuvel Acked-by: Marc Zyngier Link: https://lore.kernel.org/r/20241212081841.2168124-9-ardb+git@google.com Signed-off-by: Will Deacon --- arch/arm64/include/asm/pgtable-hwdef.h | 6 ------ arch/arm64/include/asm/pgtable-prot.h | 7 +++++++ arch/arm64/include/asm/sparsemem.h | 5 ++++- 3 files changed, 11 insertions(+), 7 deletions(-) diff --git a/arch/arm64/include/asm/pgtable-hwdef.h b/arch/arm64/include/asm/pgtable-hwdef.h index c78a988cca93..a9136cc551cc 100644 --- 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 index 9f9cf13bbd95..a95f1f77bb39 100644 --- 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/sparsemem.h b/arch/arm64/include/asm/sparsemem.h index 8a8acc220371..84783efdc9d1 100644 --- 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 + +#define MAX_PHYSMEM_BITS PHYS_MASK_SHIFT +#define MAX_POSSIBLE_PHYSMEM_BITS (52) /* * Section size must be at least 512MB for 64K base From 62cffa496aac0c2c4eeca00d080058affd7a0172 Mon Sep 17 00:00:00 2001 From: Ard Biesheuvel Date: Thu, 12 Dec 2024 09:18:44 +0100 Subject: [PATCH 2/8] arm64/mm: Override PARange for !LPA2 and use it consistently When FEAT_LPA{,2} are not implemented, the ID_AA64MMFR0_EL1.PARange and TCR.IPS values corresponding with 52-bit physical addressing are reserved. Setting the TCR.IPS field to 0b110 (52-bit physical addressing) has side effects, such as how the TTBRn_ELx.BADDR fields are interpreted, and so it is important that disabling FEAT_LPA2 (by overriding the ID_AA64MMFR0.TGran fields) also presents a PARange field consistent with that. So limit the field to 48 bits unless LPA2 is enabled, and update existing references to use the override consistently. Fixes: 352b0395b505 ("arm64: Enable 52-bit virtual addressing for 4k and 16k granule configs") Cc: stable@vger.kernel.org Signed-off-by: Ard Biesheuvel Acked-by: Marc Zyngier Link: https://lore.kernel.org/r/20241212081841.2168124-10-ardb+git@google.com Signed-off-by: Will Deacon --- arch/arm64/include/asm/assembler.h | 5 +++++ arch/arm64/kernel/cpufeature.c | 2 +- arch/arm64/kernel/pi/idreg-override.c | 9 +++++++++ arch/arm64/kernel/pi/map_kernel.c | 6 ++++++ arch/arm64/mm/init.c | 7 ++++++- 5 files changed, 27 insertions(+), 2 deletions(-) diff --git a/arch/arm64/include/asm/assembler.h b/arch/arm64/include/asm/assembler.h index 3d8d534a7a77..ad63457a05c5 100644 --- 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/kernel/cpufeature.c b/arch/arm64/kernel/cpufeature.c index 6ce71f444ed8..f8cb8a6ab98a 100644 --- a/arch/arm64/kernel/cpufeature.c +++ b/arch/arm64/kernel/cpufeature.c @@ -3478,7 +3478,7 @@ 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 index 22159251eb3a..c6b185b885f7 100644 --- 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 index f374a3e5a5fe..e57b043f324b 100644 --- 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/mm/init.c b/arch/arm64/mm/init.c index ccdef53872a0..9c0b8d9558fc 100644 --- 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 - From f0da16992aef7e246b2f3bba1492e3a52c38ca0e Mon Sep 17 00:00:00 2001 From: Ard Biesheuvel Date: Thu, 12 Dec 2024 09:18:45 +0100 Subject: [PATCH 3/8] arm64/kvm: Configure HYP TCR.PS/DS based on host stage1 When the host stage1 is configured for LPA2, the value currently being programmed into TCR_EL2.T0SZ may be invalid unless LPA2 is configured at HYP as well. This means kvm_lpa2_is_enabled() is not the right condition to test when setting TCR_EL2.DS, as it will return false if LPA2 is only available for stage 1 but not for stage 2. Similary, programming TCR_EL2.PS based on a limited IPA range due to lack of stage2 LPA2 support could potentially result in problems. So use lpa2_is_enabled() instead, and set the PS field according to the host's IPS, which is capped at 48 bits if LPA2 support is absent or disabled. Whether or not we can make meaningful use of such a configuration is a different question. Cc: stable@vger.kernel.org Signed-off-by: Ard Biesheuvel Acked-by: Marc Zyngier Link: https://lore.kernel.org/r/20241212081841.2168124-11-ardb+git@google.com Signed-off-by: Will Deacon --- arch/arm64/kvm/arm.c | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) diff --git a/arch/arm64/kvm/arm.c b/arch/arm64/kvm/arm.c index a102c3aebdbc..7b2735ad32e9 100644 --- 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; From 9d86c3c974348eb4220b637fae1a2466232078b7 Mon Sep 17 00:00:00 2001 From: Ard Biesheuvel Date: Thu, 12 Dec 2024 09:18:46 +0100 Subject: [PATCH 4/8] arm64/kvm: Avoid invalid physical addresses to signal owner updates The pKVM stage2 mapping code relies on an invalid physical address to signal to the internal API that only the annotations of descriptors should be updated, and these are stored in the high bits of invalid descriptors covering memory that has been donated to protected guests, and is therefore unmapped from the host stage-2 page tables. Given that these invalid PAs are never stored into the descriptors, it is better to rely on an explicit flag, to clarify the API and to avoid confusion regarding whether or not the output address of a descriptor can ever be invalid to begin with (which is not the case with LPA2). That removes a dependency on the logic that reasons about the maximum PA range, which differs on LPA2 capable CPUs based on whether LPA2 is enabled or not, and will be further clarified in subsequent patches. Cc: Quentin Perret Signed-off-by: Ard Biesheuvel Reviewed-by: Quentin Perret Acked-by: Marc Zyngier Link: https://lore.kernel.org/r/20241212081841.2168124-12-ardb+git@google.com Signed-off-by: Will Deacon --- arch/arm64/kvm/hyp/pgtable.c | 33 ++++++++++----------------------- 1 file changed, 10 insertions(+), 23 deletions(-) diff --git a/arch/arm64/kvm/hyp/pgtable.c b/arch/arm64/kvm/hyp/pgtable.c index 40bd55966540..d2b6fa051d6b 100644 --- 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, From 92b6919d7fb29691a8bc5aca49044056683542ca Mon Sep 17 00:00:00 2001 From: Ard Biesheuvel Date: Thu, 12 Dec 2024 09:18:47 +0100 Subject: [PATCH 5/8] arm64: Kconfig: force ARM64_PAN=y when enabling TTBR0 sw PAN There are a couple of instances of Kconfig constraints where PAN must be enabled too if TTBR0 sw PAN is enabled, primarily to avoid dealing with the modified TTBR0_EL1 sysreg format that is used when 52-bit physical addressing and/or CnP are enabled (support for either implies support for hardware PAN as well, which will supersede PAN emulation if both are available) Let's simplify this, and always enable ARM64_PAN when enabling TTBR0 sw PAN. This decouples the PAN configuration from the VA size selection, permitting us to simplify the latter in subsequent patches. (Note that PAN and TTBR0 sw PAN can still be disabled after this patch, but not independently) To avoid a convoluted circular Kconfig dependency involving KCSAN, make ARM64_MTE select ARM64_PAN too, instead of depending on it. Signed-off-by: Ard Biesheuvel Acked-by: Marc Zyngier Link: https://lore.kernel.org/r/20241212081841.2168124-13-ardb+git@google.com Signed-off-by: Will Deacon --- arch/arm64/Kconfig | 6 ++---- 1 file changed, 2 insertions(+), 4 deletions(-) diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig index 100570a048c5..c1ca21adddc1 100644 --- 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 From 169226583097ee52089e2268c09e3dc241e7a972 Mon Sep 17 00:00:00 2001 From: Anshuman Khandual Date: Tue, 7 Jan 2025 08:00:16 +0530 Subject: [PATCH 6/8] arm64/mm: Rename pte_mkpresent() as pte_mkvalid() pte_present() is no longer synonymous with pte_valid() as it also tests for pte_present_invalid() as well. Hence pte_mkpresent() is misleading, because all that does is make an entry mapped, via setting PTE_VALID. Hence rename the helper as pte_mkvalid() which reflects its functionality appropriately. Cc: Catalin Marinas Cc: Will Deacon Cc: Ard Biesheuvel Cc: Ryan Roberts Cc: Mark Rutland Cc: linux-arm-kernel@lists.infradead.org Cc: linux-kernel@vger.kernel.org Signed-off-by: Anshuman Khandual Acked-by: Catalin Marinas Link: https://lore.kernel.org/r/20250107023016.829416-1-anshuman.khandual@arm.com Signed-off-by: Will Deacon --- arch/arm64/include/asm/pgtable.h | 2 +- arch/arm64/mm/trans_pgd.c | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-) diff --git a/arch/arm64/include/asm/pgtable.h b/arch/arm64/include/asm/pgtable.h index 6986345b537a..612bc1ef500d 100644 --- 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/mm/trans_pgd.c b/arch/arm64/mm/trans_pgd.c index 0f7b484cb2ff..19c67ed1a21f 100644 --- 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))); } } From fe2169f556a1dd06e81ecab4ec25ce19f3f99cbd Mon Sep 17 00:00:00 2001 From: Anshuman Khandual Date: Tue, 7 Jan 2025 07:25:29 +0530 Subject: [PATCH 7/8] arm64/mm: Replace open encodings with PXD_TABLE_BIT [pgd|p4d]_bad() helpers have open encodings for their respective table bits which can be replaced with corresponding macros. This makes things clearer, thus improving their readability as well. Cc: Catalin Marinas Cc: Will Deacon Cc: Ard Biesheuvel Cc: Ryan Roberts Cc: Mark Rutland Cc: linux-arm-kernel@lists.infradead.org Cc: linux-kernel@vger.kernel.org Signed-off-by: Anshuman Khandual Acked-by: Catalin Marinas Reviewed-by: Ryan Roberts Reviewed-by: Gavin Shan Link: https://lore.kernel.org/r/20250107015529.798319-1-anshuman.khandual@arm.com Signed-off-by: Will Deacon --- arch/arm64/include/asm/pgtable.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/arch/arm64/include/asm/pgtable.h b/arch/arm64/include/asm/pgtable.h index 612bc1ef500d..f0ba0f47f61a 100644 --- a/arch/arm64/include/asm/pgtable.h +++ b/arch/arm64/include/asm/pgtable.h @@ -896,7 +896,7 @@ static inline bool mm_pud_folded(const struct mm_struct *mm) pr_err("%s:%d: bad pud %016llx.\n", __FILE__, __LINE__, pud_val(e)) #define p4d_none(p4d) (pgtable_l4_enabled() && !p4d_val(p4d)) -#define p4d_bad(p4d) (pgtable_l4_enabled() && !(p4d_val(p4d) & 2)) +#define p4d_bad(p4d) (pgtable_l4_enabled() && !(p4d_val(p4d) & P4D_TABLE_BIT)) #define p4d_present(p4d) (!p4d_none(p4d)) static inline void set_p4d(p4d_t *p4dp, p4d_t p4d) @@ -1023,7 +1023,7 @@ static inline bool mm_p4d_folded(const struct mm_struct *mm) pr_err("%s:%d: bad p4d %016llx.\n", __FILE__, __LINE__, p4d_val(e)) #define pgd_none(pgd) (pgtable_l5_enabled() && !pgd_val(pgd)) -#define pgd_bad(pgd) (pgtable_l5_enabled() && !(pgd_val(pgd) & 2)) +#define pgd_bad(pgd) (pgtable_l5_enabled() && !(pgd_val(pgd) & PGD_TABLE_BIT)) #define pgd_present(pgd) (!pgd_none(pgd)) static inline void set_pgd(pgd_t *pgdp, pgd_t pgd) From 9ab2601dc4c145279dc518bca00349dc1abe77ed Mon Sep 17 00:00:00 2001 From: Zhenhua Huang Date: Thu, 2 Jan 2025 15:40:47 +0800 Subject: [PATCH 8/8] arm64: mm: Test for pmd_sect() in vmemmap_check_pmd() Commit 2045a3b8911b ("mm/sparse-vmemmap: generalise vmemmap_populate_hugepages()") introduces the vmemmap_check_pmd() while does not verify if the entry is a section mapping, as is already done for Loongarch & X86. The update includes a check for pmd_sect(). Only if pmd_sect() returns true, further vmemmap population for the addr is skipped. Signed-off-by: Zhenhua Huang Reviewed-by: Anshuman Khandual Link: https://lore.kernel.org/r/20250102074047.674156-1-quic_zhenhuah@quicinc.com Signed-off-by: Will Deacon --- arch/arm64/mm/mmu.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/arch/arm64/mm/mmu.c b/arch/arm64/mm/mmu.c index e2739b69e11b..b4df5bc5b1b8 100644 --- 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,