diff --git a/anolis/configs/L0-MANDATORY/riscv/CONFIG_MEMORY_HOTPLUG b/anolis/configs/L0-MANDATORY/riscv/CONFIG_MEMORY_HOTPLUG deleted file mode 100644 index 19580d50e40b0b4c3799d914b51cdcad41bae06e..0000000000000000000000000000000000000000 --- a/anolis/configs/L0-MANDATORY/riscv/CONFIG_MEMORY_HOTPLUG +++ /dev/null @@ -1 +0,0 @@ -# CONFIG_MEMORY_HOTPLUG is not set diff --git a/anolis/configs/L0-MANDATORY/riscv/CONFIG_MEMORY_HOTPLUG_DEFAULT_ONLINE b/anolis/configs/L0-MANDATORY/riscv/CONFIG_MEMORY_HOTPLUG_DEFAULT_ONLINE deleted file mode 100644 index e7fe50c39b78c50f662e75f4631dee418a8774fd..0000000000000000000000000000000000000000 --- a/anolis/configs/L0-MANDATORY/riscv/CONFIG_MEMORY_HOTPLUG_DEFAULT_ONLINE +++ /dev/null @@ -1 +0,0 @@ -# CONFIG_MEMORY_HOTPLUG_DEFAULT_ONLINE is not set diff --git a/anolis/configs/L0-MANDATORY/riscv/CONFIG_VIRTIO_MEM b/anolis/configs/L0-MANDATORY/riscv/CONFIG_VIRTIO_MEM deleted file mode 100644 index a04c19497763fe191365c043ac9bebad94e0d27a..0000000000000000000000000000000000000000 --- a/anolis/configs/L0-MANDATORY/riscv/CONFIG_VIRTIO_MEM +++ /dev/null @@ -1 +0,0 @@ -# CONFIG_VIRTIO_MEM is not set diff --git a/anolis/configs/L1-RECOMMEND/riscv/CONFIG_MEMORY_HOTREMOVE b/anolis/configs/L1-RECOMMEND/riscv/CONFIG_MEMORY_HOTREMOVE deleted file mode 100644 index 9fcd5f374e7574f78d8a5bf3b47768ca1f77e8c1..0000000000000000000000000000000000000000 --- a/anolis/configs/L1-RECOMMEND/riscv/CONFIG_MEMORY_HOTREMOVE +++ /dev/null @@ -1 +0,0 @@ -# CONFIG_MEMORY_HOTREMOVE is not set diff --git a/arch/riscv/Kconfig b/arch/riscv/Kconfig index 2ce16e7090af19628871f9a0cd39e008ac84da62..9626d0d487e2f90801f1684762482026f44c94c0 100644 --- a/arch/riscv/Kconfig +++ b/arch/riscv/Kconfig @@ -19,6 +19,8 @@ config RISCV select ACPI_SPCR_TABLE if ACPI select ARCH_DMA_DEFAULT_COHERENT select ARCH_ENABLE_HUGEPAGE_MIGRATION if HUGETLB_PAGE && MIGRATION + select ARCH_ENABLE_MEMORY_HOTPLUG if SPARSEMEM_VMEMMAP + select ARCH_ENABLE_MEMORY_HOTREMOVE if MEMORY_HOTPLUG select ARCH_ENABLE_SPLIT_PMD_PTLOCK if PGTABLE_LEVELS > 2 select ARCH_ENABLE_THP_MIGRATION if TRANSPARENT_HUGEPAGE select ARCH_HAS_BINFMT_FLAT @@ -35,6 +37,7 @@ config RISCV select ARCH_HAS_MMIOWB select ARCH_HAS_NON_OVERLAPPING_ADDRESS_SPACE select ARCH_HAS_PMEM_API + select ARCH_HAS_PTE_DEVMAP if 64BIT && MMU select ARCH_HAS_PTE_SPECIAL select ARCH_HAS_SET_DIRECT_MAP if MMU select ARCH_HAS_SET_MEMORY if MMU @@ -45,6 +48,7 @@ config RISCV select ARCH_HAS_UBSAN_SANITIZE_ALL select ARCH_HAS_VDSO_DATA select ARCH_KEEP_MEMBLOCK + select ARCH_MHP_MEMMAP_ON_MEMORY_ENABLE if 64BIT && MMU select ARCH_OPTIONAL_KERNEL_RWX if ARCH_HAS_STRICT_KERNEL_RWX select ARCH_OPTIONAL_KERNEL_RWX_DEFAULT select ARCH_STACKWALK @@ -63,6 +67,7 @@ config RISCV select ARCH_WANT_GENERAL_HUGETLB if !RISCV_ISA_SVNAPOT select ARCH_WANT_HUGE_PMD_SHARE if 64BIT select ARCH_WANT_LD_ORPHAN_WARN if !XIP_KERNEL + select ARCH_WANT_OPTIMIZE_DAX_VMEMMAP select ARCH_WANT_OPTIMIZE_HUGETLB_VMEMMAP select ARCH_WANTS_THP_SWAP if HAVE_ARCH_TRANSPARENT_HUGEPAGE select ARCH_WEAK_RELEASE_ACQUIRE if ARCH_USE_QUEUED_SPINLOCKS diff --git a/arch/riscv/include/asm/kasan.h b/arch/riscv/include/asm/kasan.h index 0b85e363e778c9fb15fd4f1052049f54b4b1a4e4..e6a0071bdb56c4105d37f4e41ad912429e81ba58 100644 --- a/arch/riscv/include/asm/kasan.h +++ b/arch/riscv/include/asm/kasan.h @@ -6,8 +6,6 @@ #ifndef __ASSEMBLY__ -#ifdef CONFIG_KASAN - /* * The following comment was copied from arm64: * KASAN_SHADOW_START: beginning of the kernel virtual addresses. @@ -34,6 +32,8 @@ */ #define KASAN_SHADOW_START ((KASAN_SHADOW_END - KASAN_SHADOW_SIZE) & PGDIR_MASK) #define KASAN_SHADOW_END MODULES_LOWEST_VADDR + +#ifdef CONFIG_KASAN #define KASAN_SHADOW_OFFSET _AC(CONFIG_KASAN_SHADOW_OFFSET, UL) void kasan_init(void); diff --git a/arch/riscv/include/asm/mmu.h b/arch/riscv/include/asm/mmu.h index fcc7e64e6870af7bbffe8be3c9676b93a113092a..ba911fea92d1ed93f18ecbbad35d2c044d709aa0 100644 --- a/arch/riscv/include/asm/mmu.h +++ b/arch/riscv/include/asm/mmu.h @@ -33,8 +33,8 @@ typedef struct { /* Lock the pointer masking mode because this mm is multithreaded */ #define MM_CONTEXT_LOCK_PMLEN 0 -void __init create_pgd_mapping(pgd_t *pgdp, uintptr_t va, phys_addr_t pa, - phys_addr_t sz, pgprot_t prot); +void __meminit create_pgd_mapping(pgd_t *pgdp, uintptr_t va, phys_addr_t pa, phys_addr_t sz, + pgprot_t prot); #endif /* __ASSEMBLY__ */ #endif /* _ASM_RISCV_MMU_H */ diff --git a/arch/riscv/include/asm/page.h b/arch/riscv/include/asm/page.h index cd189b20bd41d1bd6a83afdc725aff47a7bfc644..ae8541cf6577860fb5fecfd1eeee764ec516827d 100644 --- a/arch/riscv/include/asm/page.h +++ b/arch/riscv/include/asm/page.h @@ -185,6 +185,11 @@ extern phys_addr_t __phys_addr_symbol(unsigned long x); unsigned long kaslr_offset(void); +static __always_inline void *pfn_to_kaddr(unsigned long pfn) +{ + return __va(pfn << PAGE_SHIFT); +} + #endif /* __ASSEMBLY__ */ #define virt_addr_valid(vaddr) ({ \ diff --git a/arch/riscv/include/asm/pgtable-64.h b/arch/riscv/include/asm/pgtable-64.h index b99bd66107a69038c835ead6b77725aaeaf882c3..2705aeaeaad40966e40e290ce0c1e94d7ad67240 100644 --- a/arch/riscv/include/asm/pgtable-64.h +++ b/arch/riscv/include/asm/pgtable-64.h @@ -400,4 +400,24 @@ static inline struct page *pgd_page(pgd_t pgd) #define p4d_offset p4d_offset p4d_t *p4d_offset(pgd_t *pgd, unsigned long address); +#ifdef CONFIG_TRANSPARENT_HUGEPAGE +static inline int pte_devmap(pte_t pte); +static inline pte_t pmd_pte(pmd_t pmd); + +static inline int pmd_devmap(pmd_t pmd) +{ + return pte_devmap(pmd_pte(pmd)); +} + +static inline int pud_devmap(pud_t pud) +{ + return 0; +} + +static inline int pgd_devmap(pgd_t pgd) +{ + return 0; +} +#endif + #endif /* _ASM_RISCV_PGTABLE_64_H */ diff --git a/arch/riscv/include/asm/pgtable-bits.h b/arch/riscv/include/asm/pgtable-bits.h index f896708e833127d12e4cb9851b0890a8d7c5d922..a8f5205cea54fad655c6b875183a2e3a9e49861e 100644 --- a/arch/riscv/include/asm/pgtable-bits.h +++ b/arch/riscv/include/asm/pgtable-bits.h @@ -16,9 +16,10 @@ #define _PAGE_GLOBAL (1 << 5) /* Global */ #define _PAGE_ACCESSED (1 << 6) /* Set by hardware on any access */ #define _PAGE_DIRTY (1 << 7) /* Set by hardware on any write */ -#define _PAGE_SOFT (1 << 8) /* Reserved for software */ +#define _PAGE_SOFT (3 << 8) /* Reserved for software */ -#define _PAGE_SPECIAL _PAGE_SOFT +#define _PAGE_SPECIAL (1 << 8) /* RSW: 0x1 */ +#define _PAGE_DEVMAP (1 << 9) /* RSW, devmap */ #define _PAGE_TABLE _PAGE_PRESENT /* diff --git a/arch/riscv/include/asm/pgtable.h b/arch/riscv/include/asm/pgtable.h index 93533f9e74ee55518f992194732c525bf03b6e59..d9ae2f9fdcc3fc2460a0c0b8278800fb537b8222 100644 --- a/arch/riscv/include/asm/pgtable.h +++ b/arch/riscv/include/asm/pgtable.h @@ -169,7 +169,7 @@ struct pt_alloc_ops { #endif }; -extern struct pt_alloc_ops pt_ops __initdata; +extern struct pt_alloc_ops pt_ops __meminitdata; #ifdef CONFIG_MMU /* Number of PGD entries that a user-mode program can use */ @@ -393,6 +393,13 @@ static inline int pte_special(pte_t pte) return pte_val(pte) & _PAGE_SPECIAL; } +#ifdef CONFIG_ARCH_HAS_PTE_DEVMAP +static inline int pte_devmap(pte_t pte) +{ + return pte_val(pte) & _PAGE_DEVMAP; +} +#endif + /* static inline pte_t pte_rdprotect(pte_t pte) */ static inline pte_t pte_wrprotect(pte_t pte) @@ -434,6 +441,11 @@ static inline pte_t pte_mkspecial(pte_t pte) return __pte(pte_val(pte) | _PAGE_SPECIAL); } +static inline pte_t pte_mkdevmap(pte_t pte) +{ + return __pte(pte_val(pte) | _PAGE_DEVMAP); +} + static inline pte_t pte_mkhuge(pte_t pte) { return pte; @@ -731,6 +743,11 @@ static inline pmd_t pmd_mkdirty(pmd_t pmd) return pte_pmd(pte_mkdirty(pmd_pte(pmd))); } +static inline pmd_t pmd_mkdevmap(pmd_t pmd) +{ + return pte_pmd(pte_mkdevmap(pmd_pte(pmd))); +} + static inline void set_pmd_at(struct mm_struct *mm, unsigned long addr, pmd_t *pmdp, pmd_t pmd) { diff --git a/arch/riscv/mm/init.c b/arch/riscv/mm/init.c index be2305f625c963f9ac5a0d46f829f8e325fb4732..ece882f785721bdc463b747412e0d2a53bf317c2 100644 --- a/arch/riscv/mm/init.c +++ b/arch/riscv/mm/init.c @@ -27,6 +27,7 @@ #include #include +#include #include #include #include @@ -303,7 +304,7 @@ static void __init setup_bootmem(void) } #ifdef CONFIG_MMU -struct pt_alloc_ops pt_ops __initdata; +struct pt_alloc_ops pt_ops __meminitdata; pgd_t swapper_pg_dir[PTRS_PER_PGD] __page_aligned_bss; pgd_t trampoline_pg_dir[PTRS_PER_PGD] __page_aligned_bss; @@ -365,7 +366,7 @@ static inline pte_t *__init get_pte_virt_fixmap(phys_addr_t pa) return (pte_t *)set_fixmap_offset(FIX_PTE, pa); } -static inline pte_t *__init get_pte_virt_late(phys_addr_t pa) +static inline pte_t *__meminit get_pte_virt_late(phys_addr_t pa) { return (pte_t *) __va(pa); } @@ -384,7 +385,7 @@ static inline phys_addr_t __init alloc_pte_fixmap(uintptr_t va) return memblock_phys_alloc(PAGE_SIZE, PAGE_SIZE); } -static phys_addr_t __init alloc_pte_late(uintptr_t va) +static phys_addr_t __meminit alloc_pte_late(uintptr_t va) { struct ptdesc *ptdesc = pagetable_alloc(GFP_KERNEL & ~__GFP_HIGHMEM, 0); @@ -392,9 +393,8 @@ static phys_addr_t __init alloc_pte_late(uintptr_t va) return __pa((pte_t *)ptdesc_address(ptdesc)); } -static void __init create_pte_mapping(pte_t *ptep, - uintptr_t va, phys_addr_t pa, - phys_addr_t sz, pgprot_t prot) +static void __meminit create_pte_mapping(pte_t *ptep, uintptr_t va, phys_addr_t pa, phys_addr_t sz, + pgprot_t prot) { uintptr_t pte_idx = pte_index(va); @@ -448,7 +448,7 @@ static pmd_t *__init get_pmd_virt_fixmap(phys_addr_t pa) return (pmd_t *)set_fixmap_offset(FIX_PMD, pa); } -static pmd_t *__init get_pmd_virt_late(phys_addr_t pa) +static pmd_t *__meminit get_pmd_virt_late(phys_addr_t pa) { return (pmd_t *) __va(pa); } @@ -465,7 +465,7 @@ static phys_addr_t __init alloc_pmd_fixmap(uintptr_t va) return memblock_phys_alloc(PAGE_SIZE, PAGE_SIZE); } -static phys_addr_t __init alloc_pmd_late(uintptr_t va) +static phys_addr_t __meminit alloc_pmd_late(uintptr_t va) { struct ptdesc *ptdesc = pagetable_alloc(GFP_KERNEL & ~__GFP_HIGHMEM, 0); @@ -473,9 +473,9 @@ static phys_addr_t __init alloc_pmd_late(uintptr_t va) return __pa((pmd_t *)ptdesc_address(ptdesc)); } -static void __init create_pmd_mapping(pmd_t *pmdp, - uintptr_t va, phys_addr_t pa, - phys_addr_t sz, pgprot_t prot) +static void __meminit create_pmd_mapping(pmd_t *pmdp, + uintptr_t va, phys_addr_t pa, + phys_addr_t sz, pgprot_t prot) { pte_t *ptep; phys_addr_t pte_phys; @@ -511,7 +511,7 @@ static pud_t *__init get_pud_virt_fixmap(phys_addr_t pa) return (pud_t *)set_fixmap_offset(FIX_PUD, pa); } -static pud_t *__init get_pud_virt_late(phys_addr_t pa) +static pud_t *__meminit get_pud_virt_late(phys_addr_t pa) { return (pud_t *)__va(pa); } @@ -529,7 +529,7 @@ static phys_addr_t __init alloc_pud_fixmap(uintptr_t va) return memblock_phys_alloc(PAGE_SIZE, PAGE_SIZE); } -static phys_addr_t alloc_pud_late(uintptr_t va) +static phys_addr_t __meminit alloc_pud_late(uintptr_t va) { unsigned long vaddr; @@ -549,7 +549,7 @@ static p4d_t *__init get_p4d_virt_fixmap(phys_addr_t pa) return (p4d_t *)set_fixmap_offset(FIX_P4D, pa); } -static p4d_t *__init get_p4d_virt_late(phys_addr_t pa) +static p4d_t *__meminit get_p4d_virt_late(phys_addr_t pa) { return (p4d_t *)__va(pa); } @@ -567,7 +567,7 @@ static phys_addr_t __init alloc_p4d_fixmap(uintptr_t va) return memblock_phys_alloc(PAGE_SIZE, PAGE_SIZE); } -static phys_addr_t alloc_p4d_late(uintptr_t va) +static phys_addr_t __meminit alloc_p4d_late(uintptr_t va) { unsigned long vaddr; @@ -576,9 +576,8 @@ static phys_addr_t alloc_p4d_late(uintptr_t va) return __pa(vaddr); } -static void __init create_pud_mapping(pud_t *pudp, - uintptr_t va, phys_addr_t pa, - phys_addr_t sz, pgprot_t prot) +static void __meminit create_pud_mapping(pud_t *pudp, uintptr_t va, phys_addr_t pa, phys_addr_t sz, + pgprot_t prot) { pmd_t *nextp; phys_addr_t next_phys; @@ -603,9 +602,8 @@ static void __init create_pud_mapping(pud_t *pudp, create_pmd_mapping(nextp, va, pa, sz, prot); } -static void __init create_p4d_mapping(p4d_t *p4dp, - uintptr_t va, phys_addr_t pa, - phys_addr_t sz, pgprot_t prot) +static void __meminit create_p4d_mapping(p4d_t *p4dp, uintptr_t va, phys_addr_t pa, phys_addr_t sz, + pgprot_t prot) { pud_t *nextp; phys_addr_t next_phys; @@ -661,9 +659,8 @@ static void __init create_p4d_mapping(p4d_t *p4dp, #define create_pmd_mapping(__pmdp, __va, __pa, __sz, __prot) do {} while(0) #endif /* __PAGETABLE_PMD_FOLDED */ -void __init create_pgd_mapping(pgd_t *pgdp, - uintptr_t va, phys_addr_t pa, - phys_addr_t sz, pgprot_t prot) +void __meminit create_pgd_mapping(pgd_t *pgdp, uintptr_t va, phys_addr_t pa, phys_addr_t sz, + pgprot_t prot) { pgd_next_t *nextp; phys_addr_t next_phys; @@ -688,8 +685,7 @@ void __init create_pgd_mapping(pgd_t *pgdp, create_pgd_next_mapping(nextp, va, pa, sz, prot); } -static uintptr_t __init best_map_size(phys_addr_t pa, uintptr_t va, - phys_addr_t size) +static uintptr_t __meminit best_map_size(phys_addr_t pa, uintptr_t va, phys_addr_t size) { if (debug_pagealloc_enabled()) return PAGE_SIZE; @@ -725,7 +721,7 @@ asmlinkage void __init __copy_data(void) #endif #ifdef CONFIG_STRICT_KERNEL_RWX -static __init pgprot_t pgprot_from_va(uintptr_t va) +static __meminit pgprot_t pgprot_from_va(uintptr_t va) { if (is_va_kernel_text(va)) return PAGE_KERNEL_READ_EXEC; @@ -752,7 +748,7 @@ void mark_rodata_ro(void) debug_checkwx(); } #else -static __init pgprot_t pgprot_from_va(uintptr_t va) +static __meminit pgprot_t pgprot_from_va(uintptr_t va) { if (IS_ENABLED(CONFIG_64BIT) && !is_kernel_mapping(va)) return PAGE_KERNEL; @@ -1235,9 +1231,8 @@ asmlinkage void __init setup_vm(uintptr_t dtb_pa) pt_ops_set_fixmap(); } -static void __init create_linear_mapping_range(phys_addr_t start, - phys_addr_t end, - uintptr_t fixed_map_size) +static void __meminit create_linear_mapping_range(phys_addr_t start, phys_addr_t end, + uintptr_t fixed_map_size, const pgprot_t *pgprot) { phys_addr_t pa; uintptr_t va, map_size; @@ -1248,7 +1243,7 @@ static void __init create_linear_mapping_range(phys_addr_t start, best_map_size(pa, va, end - pa); create_pgd_mapping(swapper_pg_dir, va, pa, map_size, - pgprot_from_va(va)); + pgprot ? *pgprot : pgprot_from_va(va)); } } @@ -1290,22 +1285,19 @@ static void __init create_linear_mapping_page_table(void) __pa(PAGE_OFFSET) < end) start = __pa(PAGE_OFFSET); - create_linear_mapping_range(start, end, 0); + create_linear_mapping_range(start, end, 0, NULL); } #ifdef CONFIG_STRICT_KERNEL_RWX - create_linear_mapping_range(ktext_start, ktext_start + ktext_size, 0); - create_linear_mapping_range(krodata_start, - krodata_start + krodata_size, 0); + create_linear_mapping_range(ktext_start, ktext_start + ktext_size, 0, NULL); + create_linear_mapping_range(krodata_start, krodata_start + krodata_size, 0, NULL); memblock_clear_nomap(ktext_start, ktext_size); memblock_clear_nomap(krodata_start, krodata_size); #endif #ifdef CONFIG_KFENCE - create_linear_mapping_range(kfence_pool, - kfence_pool + KFENCE_POOL_SIZE, - PAGE_SIZE); + create_linear_mapping_range(kfence_pool, kfence_pool + KFENCE_POOL_SIZE, PAGE_SIZE, NULL); memblock_clear_nomap(kfence_pool, KFENCE_POOL_SIZE); #endif @@ -1534,10 +1526,29 @@ void __init misc_mem_init(void) } #ifdef CONFIG_SPARSEMEM_VMEMMAP +void __meminit vmemmap_set_pmd(pmd_t *pmd, void *p, int node, + unsigned long addr, unsigned long next) +{ + pmd_set_huge(pmd, virt_to_phys(p), PAGE_KERNEL); +} + +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; +} + int __meminit vmemmap_populate(unsigned long start, unsigned long end, int node, struct vmem_altmap *altmap) { - return vmemmap_populate_basepages(start, end, node, NULL); + /* + * Note that SPARSEMEM_VMEMMAP is only selected for rv64 and that we + * can't use hugepage mappings for 2-level page table because in case of + * memory hotplug, we are not able to update all the page tables with + * the new PMDs. + */ + return vmemmap_populate_hugepages(start, end, node, altmap); } #endif @@ -1591,10 +1602,285 @@ static void __init preallocate_pgd_pages_range(unsigned long start, unsigned lon panic("Failed to pre-allocate %s pages for %s area\n", lvl, area); } +#define PAGE_END KASAN_SHADOW_START + void __init pgtable_cache_init(void) { preallocate_pgd_pages_range(VMALLOC_START, VMALLOC_END, "vmalloc"); if (IS_ENABLED(CONFIG_MODULES)) preallocate_pgd_pages_range(MODULES_VADDR, MODULES_END, "bpf/modules"); + if (IS_ENABLED(CONFIG_MEMORY_HOTPLUG)) { + preallocate_pgd_pages_range(VMEMMAP_START, VMEMMAP_END, "vmemmap"); + preallocate_pgd_pages_range(PAGE_OFFSET, PAGE_END, "direct map"); + if (IS_ENABLED(CONFIG_KASAN)) + preallocate_pgd_pages_range(KASAN_SHADOW_START, KASAN_SHADOW_END, "kasan"); + } } #endif + +#ifdef CONFIG_MEMORY_HOTPLUG +static void __meminit free_pte_table(pte_t *pte_start, pmd_t *pmd) +{ + struct page *page = pmd_page(*pmd); + struct ptdesc *ptdesc = page_ptdesc(page); + pte_t *pte; + int i; + + for (i = 0; i < PTRS_PER_PTE; i++) { + pte = pte_start + i; + if (!pte_none(*pte)) + return; + } + + pagetable_dtor(ptdesc); + if (PageReserved(page)) + free_reserved_page(page); + else + pagetable_free(ptdesc); + pmd_clear(pmd); +} + +static void __meminit free_pmd_table(pmd_t *pmd_start, pud_t *pud) +{ + struct page *page = pud_page(*pud); + struct ptdesc *ptdesc = page_ptdesc(page); + pmd_t *pmd; + int i; + + for (i = 0; i < PTRS_PER_PMD; i++) { + pmd = pmd_start + i; + if (!pmd_none(*pmd)) + return; + } + + pagetable_dtor(ptdesc); + if (PageReserved(page)) + free_reserved_page(page); + else + pagetable_free(ptdesc); + pud_clear(pud); +} + +static void __meminit free_pud_table(pud_t *pud_start, p4d_t *p4d) +{ + struct page *page = p4d_page(*p4d); + pud_t *pud; + int i; + + for (i = 0; i < PTRS_PER_PUD; i++) { + pud = pud_start + i; + if (!pud_none(*pud)) + return; + } + + if (PageReserved(page)) + free_reserved_page(page); + else + free_pages((unsigned long)page_address(page), 0); + p4d_clear(p4d); +} + +static void __meminit free_vmemmap_storage(struct page *page, size_t size, + struct vmem_altmap *altmap) +{ + int order = get_order(size); + + if (altmap) { + vmem_altmap_free(altmap, size >> PAGE_SHIFT); + return; + } + + if (PageReserved(page)) { + unsigned int nr_pages = 1 << order; + + while (nr_pages--) + free_reserved_page(page++); + return; + } + + free_pages((unsigned long)page_address(page), order); +} + +static void __meminit remove_pte_mapping(pte_t *pte_base, unsigned long addr, unsigned long end, + bool is_vmemmap, struct vmem_altmap *altmap) +{ + unsigned long next; + pte_t *ptep, pte; + + for (; addr < end; addr = next) { + next = (addr + PAGE_SIZE) & PAGE_MASK; + if (next > end) + next = end; + + ptep = pte_base + pte_index(addr); + pte = ptep_get(ptep); + if (!pte_present(*ptep)) + continue; + + pte_clear(&init_mm, addr, ptep); + if (is_vmemmap) + free_vmemmap_storage(pte_page(pte), PAGE_SIZE, altmap); + } +} + +static void __meminit remove_pmd_mapping(pmd_t *pmd_base, unsigned long addr, unsigned long end, + bool is_vmemmap, struct vmem_altmap *altmap) +{ + unsigned long next; + pte_t *pte_base; + pmd_t *pmdp, pmd; + + for (; addr < end; addr = next) { + next = pmd_addr_end(addr, end); + pmdp = pmd_base + pmd_index(addr); + pmd = pmdp_get(pmdp); + if (!pmd_present(pmd)) + continue; + + if (pmd_leaf(pmd)) { + pmd_clear(pmdp); + if (is_vmemmap) + free_vmemmap_storage(pmd_page(pmd), PMD_SIZE, altmap); + continue; + } + + pte_base = (pte_t *)pmd_page_vaddr(*pmdp); + remove_pte_mapping(pte_base, addr, next, is_vmemmap, altmap); + free_pte_table(pte_base, pmdp); + } +} + +static void __meminit remove_pud_mapping(pud_t *pud_base, unsigned long addr, unsigned long end, + bool is_vmemmap, struct vmem_altmap *altmap) +{ + unsigned long next; + pud_t *pudp, pud; + pmd_t *pmd_base; + + for (; addr < end; addr = next) { + next = pud_addr_end(addr, end); + pudp = pud_base + pud_index(addr); + pud = pudp_get(pudp); + if (!pud_present(pud)) + continue; + + if (pud_leaf(pud)) { + if (pgtable_l4_enabled) { + pud_clear(pudp); + if (is_vmemmap) + free_vmemmap_storage(pud_page(pud), PUD_SIZE, altmap); + } + continue; + } + + pmd_base = pmd_offset(pudp, 0); + remove_pmd_mapping(pmd_base, addr, next, is_vmemmap, altmap); + + if (pgtable_l4_enabled) + free_pmd_table(pmd_base, pudp); + } +} + +static void __meminit remove_p4d_mapping(p4d_t *p4d_base, unsigned long addr, unsigned long end, + bool is_vmemmap, struct vmem_altmap *altmap) +{ + unsigned long next; + p4d_t *p4dp, p4d; + pud_t *pud_base; + + for (; addr < end; addr = next) { + next = p4d_addr_end(addr, end); + p4dp = p4d_base + p4d_index(addr); + p4d = p4dp_get(p4dp); + if (!p4d_present(p4d)) + continue; + + if (p4d_leaf(p4d)) { + if (pgtable_l5_enabled) { + p4d_clear(p4dp); + if (is_vmemmap) + free_vmemmap_storage(p4d_page(p4d), P4D_SIZE, altmap); + } + continue; + } + + pud_base = pud_offset(p4dp, 0); + remove_pud_mapping(pud_base, addr, next, is_vmemmap, altmap); + + if (pgtable_l5_enabled) + free_pud_table(pud_base, p4dp); + } +} + +static void __meminit remove_pgd_mapping(unsigned long va, unsigned long end, bool is_vmemmap, + struct vmem_altmap *altmap) +{ + unsigned long addr, next; + p4d_t *p4d_base; + pgd_t *pgd; + + for (addr = va; addr < end; addr = next) { + next = pgd_addr_end(addr, end); + pgd = pgd_offset_k(addr); + + if (!pgd_present(*pgd)) + continue; + + if (pgd_leaf(*pgd)) + continue; + + p4d_base = p4d_offset(pgd, 0); + remove_p4d_mapping(p4d_base, addr, next, is_vmemmap, altmap); + } + + flush_tlb_all(); +} + +static void __meminit remove_linear_mapping(phys_addr_t start, u64 size) +{ + unsigned long va = (unsigned long)__va(start); + unsigned long end = (unsigned long)__va(start + size); + + remove_pgd_mapping(va, end, false, NULL); +} + +struct range arch_get_mappable_range(void) +{ + struct range mhp_range; + + mhp_range.start = __pa(PAGE_OFFSET); + mhp_range.end = __pa(PAGE_END - 1); + return mhp_range; +} + +int __ref arch_add_memory(int nid, u64 start, u64 size, struct mhp_params *params) +{ + int ret = 0; + + create_linear_mapping_range(start, start + size, 0, ¶ms->pgprot); + ret = __add_pages(nid, start >> PAGE_SHIFT, size >> PAGE_SHIFT, params); + if (ret) { + remove_linear_mapping(start, size); + goto out; + } + + max_pfn = PFN_UP(start + size); + max_low_pfn = max_pfn; + + out: + flush_tlb_all(); + return ret; +} + +void __ref arch_remove_memory(u64 start, u64 size, struct vmem_altmap *altmap) +{ + __remove_pages(start >> PAGE_SHIFT, size >> PAGE_SHIFT, altmap); + remove_linear_mapping(start, size); + flush_tlb_all(); +} + +void __ref vmemmap_free(unsigned long start, unsigned long end, struct vmem_altmap *altmap) +{ + remove_pgd_mapping(start, end, true, altmap); +} +#endif /* CONFIG_MEMORY_HOTPLUG */ diff --git a/arch/riscv/mm/ptdump.c b/arch/riscv/mm/ptdump.c index e9090b38f8117c992984560c68fa28668fe722e6..1516265ea3e661085df25fe184f1a1090878b897 100644 --- a/arch/riscv/mm/ptdump.c +++ b/arch/riscv/mm/ptdump.c @@ -6,6 +6,7 @@ #include #include #include +#include #include #include @@ -129,55 +130,55 @@ static struct ptd_mm_info efi_ptd_info = { /* Page Table Entry */ struct prot_bits { u64 mask; - u64 val; const char *set; const char *clear; }; static const struct prot_bits pte_bits[] = { { +#ifdef CONFIG_64BIT + .mask = _PAGE_NAPOT, + .set = "N", + .clear = ".", + }, { + .mask = _PAGE_MTMASK_SVPBMT, + .set = "MT(%s)", + .clear = " .. ", + }, { +#endif .mask = _PAGE_SOFT, - .val = _PAGE_SOFT, - .set = "RSW", - .clear = " ", + .set = "RSW(%d)", + .clear = " .. ", }, { .mask = _PAGE_DIRTY, - .val = _PAGE_DIRTY, .set = "D", .clear = ".", }, { .mask = _PAGE_ACCESSED, - .val = _PAGE_ACCESSED, .set = "A", .clear = ".", }, { .mask = _PAGE_GLOBAL, - .val = _PAGE_GLOBAL, .set = "G", .clear = ".", }, { .mask = _PAGE_USER, - .val = _PAGE_USER, .set = "U", .clear = ".", }, { .mask = _PAGE_EXEC, - .val = _PAGE_EXEC, .set = "X", .clear = ".", }, { .mask = _PAGE_WRITE, - .val = _PAGE_WRITE, .set = "W", .clear = ".", }, { .mask = _PAGE_READ, - .val = _PAGE_READ, .set = "R", .clear = ".", }, { .mask = _PAGE_PRESENT, - .val = _PAGE_PRESENT, .set = "V", .clear = ".", } @@ -208,15 +209,30 @@ static void dump_prot(struct pg_state *st) unsigned int i; for (i = 0; i < ARRAY_SIZE(pte_bits); i++) { - const char *s; + char s[7]; + unsigned long val; - if ((st->current_prot & pte_bits[i].mask) == pte_bits[i].val) - s = pte_bits[i].set; - else - s = pte_bits[i].clear; + val = st->current_prot & pte_bits[i].mask; + if (val) { + if (pte_bits[i].mask == _PAGE_SOFT) + sprintf(s, pte_bits[i].set, val >> 8); +#ifdef CONFIG_64BIT + else if (pte_bits[i].mask == _PAGE_MTMASK_SVPBMT) { + if (val == _PAGE_NOCACHE_SVPBMT) + sprintf(s, pte_bits[i].set, "NC"); + else if (val == _PAGE_IO_SVPBMT) + sprintf(s, pte_bits[i].set, "IO"); + else + sprintf(s, pte_bits[i].set, "??"); + } +#endif + else + sprintf(s, "%s", pte_bits[i].set); + } else { + sprintf(s, "%s", pte_bits[i].clear); + } - if (s) - pt_dump_seq_printf(st->seq, " %s", s); + pt_dump_seq_printf(st->seq, " %s", s); } } @@ -351,7 +367,9 @@ void ptdump_check_wx(void) static int ptdump_show(struct seq_file *m, void *v) { + get_online_mems(); ptdump_walk(m, m->private); + put_online_mems(); return 0; } diff --git a/drivers/virtio/Kconfig b/drivers/virtio/Kconfig index da89d498d14eeea7874286ee8618a06f222ad655..3d81d3f848a149f91fefcd93d382e23b64719af4 100644 --- a/drivers/virtio/Kconfig +++ b/drivers/virtio/Kconfig @@ -117,7 +117,7 @@ config VIRTIO_BALLOON config VIRTIO_MEM tristate "Virtio mem driver" - depends on X86_64 || ARM64 || SW64 + depends on X86_64 || ARM64 || SW64 || RISCV depends on VIRTIO depends on MEMORY_HOTPLUG depends on MEMORY_HOTREMOVE