diff options
Diffstat (limited to 'arch/riscv/mm')
| -rw-r--r-- | arch/riscv/mm/cacheflush.c | 25 | ||||
| -rw-r--r-- | arch/riscv/mm/dma-noncoherent.c | 8 | ||||
| -rw-r--r-- | arch/riscv/mm/fault.c | 2 | ||||
| -rw-r--r-- | arch/riscv/mm/hugetlbpage.c | 78 | ||||
| -rw-r--r-- | arch/riscv/mm/init.c | 171 | ||||
| -rw-r--r-- | arch/riscv/mm/pmem.c | 4 | ||||
| -rw-r--r-- | arch/riscv/mm/ptdump.c | 53 | ||||
| -rw-r--r-- | arch/riscv/mm/tlbflush.c | 187 |
8 files changed, 289 insertions, 239 deletions
diff --git a/arch/riscv/mm/cacheflush.c b/arch/riscv/mm/cacheflush.c index f1387272a5..55a34f2020 100644 --- a/arch/riscv/mm/cacheflush.c +++ b/arch/riscv/mm/cacheflush.c @@ -3,7 +3,9 @@ * Copyright (C) 2017 SiFive */ +#include <linux/acpi.h> #include <linux/of.h> +#include <asm/acpi.h> #include <asm/cacheflush.h> #ifdef CONFIG_SMP @@ -124,13 +126,24 @@ void __init riscv_init_cbo_blocksizes(void) unsigned long cbom_hartid, cboz_hartid; u32 cbom_block_size = 0, cboz_block_size = 0; struct device_node *node; + struct acpi_table_header *rhct; + acpi_status status; + + if (acpi_disabled) { + for_each_of_cpu_node(node) { + /* set block-size for cbom and/or cboz extension if available */ + cbo_get_block_size(node, "riscv,cbom-block-size", + &cbom_block_size, &cbom_hartid); + cbo_get_block_size(node, "riscv,cboz-block-size", + &cboz_block_size, &cboz_hartid); + } + } else { + status = acpi_get_table(ACPI_SIG_RHCT, 0, &rhct); + if (ACPI_FAILURE(status)) + return; - for_each_of_cpu_node(node) { - /* set block-size for cbom and/or cboz extension if available */ - cbo_get_block_size(node, "riscv,cbom-block-size", - &cbom_block_size, &cbom_hartid); - cbo_get_block_size(node, "riscv,cboz-block-size", - &cboz_block_size, &cboz_hartid); + acpi_get_cbo_block_size(rhct, &cbom_block_size, &cboz_block_size, NULL); + acpi_put_table((struct acpi_table_header *)rhct); } if (cbom_block_size) diff --git a/arch/riscv/mm/dma-noncoherent.c b/arch/riscv/mm/dma-noncoherent.c index 341bd6706b..4e4e469b8d 100644 --- a/arch/riscv/mm/dma-noncoherent.c +++ b/arch/riscv/mm/dma-noncoherent.c @@ -25,7 +25,7 @@ static inline void arch_dma_cache_wback(phys_addr_t paddr, size_t size) return; } #endif - ALT_CMO_OP(clean, vaddr, size, riscv_cbom_block_size); + ALT_CMO_OP(CLEAN, vaddr, size, riscv_cbom_block_size); } static inline void arch_dma_cache_inv(phys_addr_t paddr, size_t size) @@ -39,7 +39,7 @@ static inline void arch_dma_cache_inv(phys_addr_t paddr, size_t size) } #endif - ALT_CMO_OP(inval, vaddr, size, riscv_cbom_block_size); + ALT_CMO_OP(INVAL, vaddr, size, riscv_cbom_block_size); } static inline void arch_dma_cache_wback_inv(phys_addr_t paddr, size_t size) @@ -53,7 +53,7 @@ static inline void arch_dma_cache_wback_inv(phys_addr_t paddr, size_t size) } #endif - ALT_CMO_OP(flush, vaddr, size, riscv_cbom_block_size); + ALT_CMO_OP(FLUSH, vaddr, size, riscv_cbom_block_size); } static inline bool arch_sync_dma_clean_before_fromdevice(void) @@ -125,7 +125,7 @@ void arch_dma_prep_coherent(struct page *page, size_t size) } #endif - ALT_CMO_OP(flush, flush_addr, size, riscv_cbom_block_size); + ALT_CMO_OP(FLUSH, flush_addr, size, riscv_cbom_block_size); } void arch_setup_dma_ops(struct device *dev, u64 dma_base, u64 size, diff --git a/arch/riscv/mm/fault.c b/arch/riscv/mm/fault.c index 90d4ba36d1..081339ddf4 100644 --- a/arch/riscv/mm/fault.c +++ b/arch/riscv/mm/fault.c @@ -304,6 +304,8 @@ void handle_page_fault(struct pt_regs *regs) goto done; } count_vm_vma_lock_event(VMA_LOCK_RETRY); + if (fault & VM_FAULT_MAJOR) + flags |= FAULT_FLAG_TRIED; if (fault_signal_pending(fault, regs)) { if (!user_mode(regs)) diff --git a/arch/riscv/mm/hugetlbpage.c b/arch/riscv/mm/hugetlbpage.c index b52f021048..e7b6928187 100644 --- a/arch/riscv/mm/hugetlbpage.c +++ b/arch/riscv/mm/hugetlbpage.c @@ -125,6 +125,26 @@ pte_t *huge_pte_offset(struct mm_struct *mm, return pte; } +unsigned long hugetlb_mask_last_page(struct hstate *h) +{ + unsigned long hp_size = huge_page_size(h); + + switch (hp_size) { +#ifndef __PAGETABLE_PMD_FOLDED + case PUD_SIZE: + return P4D_SIZE - PUD_SIZE; +#endif + case PMD_SIZE: + return PUD_SIZE - PMD_SIZE; + case napot_cont_size(NAPOT_CONT64KB_ORDER): + return PMD_SIZE - napot_cont_size(NAPOT_CONT64KB_ORDER); + default: + break; + } + + return 0UL; +} + static pte_t get_clear_contig(struct mm_struct *mm, unsigned long addr, pte_t *ptep, @@ -177,13 +197,36 @@ pte_t arch_make_huge_pte(pte_t entry, unsigned int shift, vm_flags_t flags) return entry; } +static void clear_flush(struct mm_struct *mm, + unsigned long addr, + pte_t *ptep, + unsigned long pgsize, + unsigned long ncontig) +{ + struct vm_area_struct vma = TLB_FLUSH_VMA(mm, 0); + unsigned long i, saddr = addr; + + for (i = 0; i < ncontig; i++, addr += pgsize, ptep++) + ptep_get_and_clear(mm, addr, ptep); + + flush_tlb_range(&vma, saddr, addr); +} + +/* + * When dealing with NAPOT mappings, the privileged specification indicates that + * "if an update needs to be made, the OS generally should first mark all of the + * PTEs invalid, then issue SFENCE.VMA instruction(s) covering all 4 KiB regions + * within the range, [...] then update the PTE(s), as described in Section + * 4.2.1.". That's the equivalent of the Break-Before-Make approach used by + * arm64. + */ void set_huge_pte_at(struct mm_struct *mm, unsigned long addr, pte_t *ptep, pte_t pte, unsigned long sz) { - unsigned long hugepage_shift; + unsigned long hugepage_shift, pgsize; int i, pte_num; if (sz >= PGDIR_SIZE) @@ -198,7 +241,22 @@ void set_huge_pte_at(struct mm_struct *mm, hugepage_shift = PAGE_SHIFT; pte_num = sz >> hugepage_shift; - for (i = 0; i < pte_num; i++, ptep++, addr += (1 << hugepage_shift)) + pgsize = 1 << hugepage_shift; + + if (!pte_present(pte)) { + for (i = 0; i < pte_num; i++, ptep++, addr += pgsize) + set_ptes(mm, addr, ptep, pte, 1); + return; + } + + if (!pte_napot(pte)) { + set_ptes(mm, addr, ptep, pte, 1); + return; + } + + clear_flush(mm, addr, ptep, pgsize, pte_num); + + for (i = 0; i < pte_num; i++, ptep++, addr += pgsize) set_pte_at(mm, addr, ptep, pte); } @@ -306,7 +364,7 @@ void huge_pte_clear(struct mm_struct *mm, pte_clear(mm, addr, ptep); } -static __init bool is_napot_size(unsigned long size) +static bool is_napot_size(unsigned long size) { unsigned long order; @@ -334,7 +392,7 @@ arch_initcall(napot_hugetlbpages_init); #else -static __init bool is_napot_size(unsigned long size) +static bool is_napot_size(unsigned long size) { return false; } @@ -351,7 +409,7 @@ int pmd_huge(pmd_t pmd) return pmd_leaf(pmd); } -bool __init arch_hugetlb_valid_size(unsigned long size) +static bool __hugetlb_valid_size(unsigned long size) { if (size == HPAGE_SIZE) return true; @@ -363,6 +421,16 @@ bool __init arch_hugetlb_valid_size(unsigned long size) return false; } +bool __init arch_hugetlb_valid_size(unsigned long size) +{ + return __hugetlb_valid_size(size); +} + +bool arch_hugetlb_migration_supported(struct hstate *h) +{ + return __hugetlb_valid_size(huge_page_size(h)); +} + #ifdef CONFIG_CONTIG_ALLOC static __init int gigantic_pages_init(void) { diff --git a/arch/riscv/mm/init.c b/arch/riscv/mm/init.c index 0798bd861d..ee224fe18d 100644 --- a/arch/riscv/mm/init.c +++ b/arch/riscv/mm/init.c @@ -49,10 +49,12 @@ u64 satp_mode __ro_after_init = SATP_MODE_32; #endif EXPORT_SYMBOL(satp_mode); +#ifdef CONFIG_64BIT bool pgtable_l4_enabled = IS_ENABLED(CONFIG_64BIT) && !IS_ENABLED(CONFIG_XIP_KERNEL); bool pgtable_l5_enabled = IS_ENABLED(CONFIG_64BIT) && !IS_ENABLED(CONFIG_XIP_KERNEL); EXPORT_SYMBOL(pgtable_l4_enabled); EXPORT_SYMBOL(pgtable_l5_enabled); +#endif phys_addr_t phys_ram_base __ro_after_init; EXPORT_SYMBOL(phys_ram_base); @@ -65,7 +67,7 @@ extern char _start[]; void *_dtb_early_va __initdata; uintptr_t _dtb_early_pa __initdata; -static phys_addr_t dma32_phys_limit __initdata; +phys_addr_t dma32_phys_limit __initdata; static void __init zone_sizes_init(void) { @@ -172,6 +174,9 @@ void __init mem_init(void) /* Limit the memory size via mem. */ static phys_addr_t memory_limit; +#ifdef CONFIG_XIP_KERNEL +#define memory_limit (*(phys_addr_t *)XIP_FIXUP(&memory_limit)) +#endif /* CONFIG_XIP_KERNEL */ static int __init early_mem(char *p) { @@ -664,16 +669,16 @@ void __init create_pgd_mapping(pgd_t *pgdp, static uintptr_t __init best_map_size(phys_addr_t pa, uintptr_t va, phys_addr_t size) { - if (!(pa & (PGDIR_SIZE - 1)) && !(va & (PGDIR_SIZE - 1)) && size >= PGDIR_SIZE) - return PGDIR_SIZE; - - if (!(pa & (P4D_SIZE - 1)) && !(va & (P4D_SIZE - 1)) && size >= P4D_SIZE) + if (pgtable_l5_enabled && + !(pa & (P4D_SIZE - 1)) && !(va & (P4D_SIZE - 1)) && size >= P4D_SIZE) return P4D_SIZE; - if (!(pa & (PUD_SIZE - 1)) && !(va & (PUD_SIZE - 1)) && size >= PUD_SIZE) + if (pgtable_l4_enabled && + !(pa & (PUD_SIZE - 1)) && !(va & (PUD_SIZE - 1)) && size >= PUD_SIZE) return PUD_SIZE; - if (!(pa & (PMD_SIZE - 1)) && !(va & (PMD_SIZE - 1)) && size >= PMD_SIZE) + if (IS_ENABLED(CONFIG_64BIT) && + !(pa & (PMD_SIZE - 1)) && !(va & (PMD_SIZE - 1)) && size >= PMD_SIZE) return PMD_SIZE; return PAGE_SIZE; @@ -950,7 +955,7 @@ static void __init create_fdt_early_page_table(uintptr_t fix_fdt_va, * setup_vm_final installs the linear mapping. For 32-bit kernel, as the * kernel is mapped in the linear mapping, that makes no difference. */ - dtb_early_va = kernel_mapping_pa_to_va(XIP_FIXUP(dtb_pa)); + dtb_early_va = kernel_mapping_pa_to_va(dtb_pa); #endif dtb_early_pa = dtb_pa; @@ -1053,9 +1058,13 @@ asmlinkage void __init setup_vm(uintptr_t dtb_pa) #endif kernel_map.virt_addr = KERNEL_LINK_ADDR + kernel_map.virt_offset; - kernel_map.page_offset = _AC(CONFIG_PAGE_OFFSET, UL); #ifdef CONFIG_XIP_KERNEL +#ifdef CONFIG_64BIT + kernel_map.page_offset = PAGE_OFFSET_L3; +#else + kernel_map.page_offset = _AC(CONFIG_PAGE_OFFSET, UL); +#endif kernel_map.xiprom = (uintptr_t)CONFIG_XIP_PHYS_ADDR; kernel_map.xiprom_sz = (uintptr_t)(&_exiprom) - (uintptr_t)(&_xiprom); @@ -1065,6 +1074,7 @@ asmlinkage void __init setup_vm(uintptr_t dtb_pa) kernel_map.va_kernel_xip_pa_offset = kernel_map.virt_addr - kernel_map.xiprom; #else + kernel_map.page_offset = _AC(CONFIG_PAGE_OFFSET, UL); kernel_map.phys_addr = (uintptr_t)(&_start); kernel_map.size = (uintptr_t)(&_end) - kernel_map.phys_addr; #endif @@ -1333,28 +1343,6 @@ static inline void setup_vm_final(void) } #endif /* CONFIG_MMU */ -/* Reserve 128M low memory by default for swiotlb buffer */ -#define DEFAULT_CRASH_KERNEL_LOW_SIZE (128UL << 20) - -static int __init reserve_crashkernel_low(unsigned long long low_size) -{ - unsigned long long low_base; - - low_base = memblock_phys_alloc_range(low_size, PMD_SIZE, 0, dma32_phys_limit); - if (!low_base) { - pr_err("cannot allocate crashkernel low memory (size:0x%llx).\n", low_size); - return -ENOMEM; - } - - pr_info("crashkernel low memory reserved: 0x%016llx - 0x%016llx (%lld MB)\n", - low_base, low_base + low_size, low_size >> 20); - - crashk_low_res.start = low_base; - crashk_low_res.end = low_base + low_size - 1; - - return 0; -} - /* * reserve_crashkernel() - reserves memory for crash kernel * @@ -1362,122 +1350,25 @@ static int __init reserve_crashkernel_low(unsigned long long low_size) * line parameter. The memory reserved is used by dump capture kernel when * primary kernel is crashing. */ -static void __init reserve_crashkernel(void) +static void __init arch_reserve_crashkernel(void) { - unsigned long long crash_base = 0; - unsigned long long crash_size = 0; - unsigned long long crash_low_size = 0; - unsigned long search_start = memblock_start_of_DRAM(); - unsigned long search_end = (unsigned long)dma32_phys_limit; + unsigned long long low_size = 0; + unsigned long long crash_base, crash_size; char *cmdline = boot_command_line; - bool fixed_base = false; bool high = false; - - int ret = 0; + int ret; if (!IS_ENABLED(CONFIG_KEXEC_CORE)) return; - /* - * Don't reserve a region for a crash kernel on a crash kernel - * since it doesn't make much sense and we have limited memory - * resources. - */ - if (is_kdump_kernel()) { - pr_info("crashkernel: ignoring reservation request\n"); - return; - } ret = parse_crashkernel(cmdline, memblock_phys_mem_size(), - &crash_size, &crash_base); - if (ret == -ENOENT) { - /* Fallback to crashkernel=X,[high,low] */ - ret = parse_crashkernel_high(cmdline, 0, &crash_size, &crash_base); - if (ret || !crash_size) - return; - - /* - * crashkernel=Y,low is valid only when crashkernel=X,high - * is passed. - */ - ret = parse_crashkernel_low(cmdline, 0, &crash_low_size, &crash_base); - if (ret == -ENOENT) - crash_low_size = DEFAULT_CRASH_KERNEL_LOW_SIZE; - else if (ret) - return; - - search_start = (unsigned long)dma32_phys_limit; - search_end = memblock_end_of_DRAM(); - high = true; - } else if (ret || !crash_size) { - /* Invalid argument value specified */ + &crash_size, &crash_base, + &low_size, &high); + if (ret) return; - } - - crash_size = PAGE_ALIGN(crash_size); - if (crash_base) { - fixed_base = true; - search_start = crash_base; - search_end = crash_base + crash_size; - } - - /* - * Current riscv boot protocol requires 2MB alignment for - * RV64 and 4MB alignment for RV32 (hugepage size) - * - * Try to alloc from 32bit addressible physical memory so that - * swiotlb can work on the crash kernel. - */ - crash_base = memblock_phys_alloc_range(crash_size, PMD_SIZE, - search_start, search_end); - if (crash_base == 0) { - /* - * For crashkernel=size[KMG]@offset[KMG], print out failure - * message if can't reserve the specified region. - */ - if (fixed_base) { - pr_warn("crashkernel: allocating failed with given size@offset\n"); - return; - } - - if (high) { - /* - * For crashkernel=size[KMG],high, if the first attempt was - * for high memory, fall back to low memory. - */ - search_start = memblock_start_of_DRAM(); - search_end = (unsigned long)dma32_phys_limit; - } else { - /* - * For crashkernel=size[KMG], if the first attempt was for - * low memory, fall back to high memory, the minimum required - * low memory will be reserved later. - */ - search_start = (unsigned long)dma32_phys_limit; - search_end = memblock_end_of_DRAM(); - crash_low_size = DEFAULT_CRASH_KERNEL_LOW_SIZE; - } - - crash_base = memblock_phys_alloc_range(crash_size, PMD_SIZE, - search_start, search_end); - if (crash_base == 0) { - pr_warn("crashkernel: couldn't allocate %lldKB\n", - crash_size >> 10); - return; - } - } - - if ((crash_base >= dma32_phys_limit) && crash_low_size && - reserve_crashkernel_low(crash_low_size)) { - memblock_phys_free(crash_base, crash_size); - return; - } - - pr_info("crashkernel: reserved 0x%016llx - 0x%016llx (%lld MB)\n", - crash_base, crash_base + crash_size, crash_size >> 20); - - crashk_res.start = crash_base; - crashk_res.end = crash_base + crash_size - 1; + reserve_crashkernel_generic(cmdline, crash_size, crash_base, + low_size, high); } void __init paging_init(void) @@ -1494,8 +1385,12 @@ void __init misc_mem_init(void) early_memtest(min_low_pfn << PAGE_SHIFT, max_low_pfn << PAGE_SHIFT); arch_numa_init(); sparse_init(); +#ifdef CONFIG_SPARSEMEM_VMEMMAP + /* The entire VMEMMAP region has been populated. Flush TLB for this region */ + local_flush_tlb_kernel_range(VMEMMAP_START, VMEMMAP_END); +#endif zone_sizes_init(); - reserve_crashkernel(); + arch_reserve_crashkernel(); memblock_dump_all(); } diff --git a/arch/riscv/mm/pmem.c b/arch/riscv/mm/pmem.c index c5fc5ec96f..370a422ede 100644 --- a/arch/riscv/mm/pmem.c +++ b/arch/riscv/mm/pmem.c @@ -17,7 +17,7 @@ void arch_wb_cache_pmem(void *addr, size_t size) return; } #endif - ALT_CMO_OP(clean, addr, size, riscv_cbom_block_size); + ALT_CMO_OP(CLEAN, addr, size, riscv_cbom_block_size); } EXPORT_SYMBOL_GPL(arch_wb_cache_pmem); @@ -29,6 +29,6 @@ void arch_invalidate_pmem(void *addr, size_t size) return; } #endif - ALT_CMO_OP(inval, addr, size, riscv_cbom_block_size); + ALT_CMO_OP(INVAL, addr, size, riscv_cbom_block_size); } EXPORT_SYMBOL_GPL(arch_invalidate_pmem); diff --git a/arch/riscv/mm/ptdump.c b/arch/riscv/mm/ptdump.c index e9090b38f8..657c27bc07 100644 --- a/arch/riscv/mm/ptdump.c +++ b/arch/riscv/mm/ptdump.c @@ -129,55 +129,55 @@ 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 +208,30 @@ 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); } } diff --git a/arch/riscv/mm/tlbflush.c b/arch/riscv/mm/tlbflush.c index 77be59aadc..1f90721d22 100644 --- a/arch/riscv/mm/tlbflush.c +++ b/arch/riscv/mm/tlbflush.c @@ -3,33 +3,56 @@ #include <linux/mm.h> #include <linux/smp.h> #include <linux/sched.h> +#include <linux/hugetlb.h> #include <asm/sbi.h> #include <asm/mmu_context.h> static inline void local_flush_tlb_all_asid(unsigned long asid) { - __asm__ __volatile__ ("sfence.vma x0, %0" - : - : "r" (asid) - : "memory"); + if (asid != FLUSH_TLB_NO_ASID) + __asm__ __volatile__ ("sfence.vma x0, %0" + : + : "r" (asid) + : "memory"); + else + local_flush_tlb_all(); } static inline void local_flush_tlb_page_asid(unsigned long addr, unsigned long asid) { - __asm__ __volatile__ ("sfence.vma %0, %1" - : - : "r" (addr), "r" (asid) - : "memory"); + if (asid != FLUSH_TLB_NO_ASID) + __asm__ __volatile__ ("sfence.vma %0, %1" + : + : "r" (addr), "r" (asid) + : "memory"); + else + local_flush_tlb_page(addr); } -static inline void local_flush_tlb_range(unsigned long start, - unsigned long size, unsigned long stride) +/* + * Flush entire TLB if number of entries to be flushed is greater + * than the threshold below. + */ +static unsigned long tlb_flush_all_threshold __read_mostly = 64; + +static void local_flush_tlb_range_threshold_asid(unsigned long start, + unsigned long size, + unsigned long stride, + unsigned long asid) { - if (size <= stride) - local_flush_tlb_page(start); - else - local_flush_tlb_all(); + unsigned long nr_ptes_in_range = DIV_ROUND_UP(size, stride); + int i; + + if (nr_ptes_in_range > tlb_flush_all_threshold) { + local_flush_tlb_all_asid(asid); + return; + } + + for (i = 0; i < nr_ptes_in_range; ++i) { + local_flush_tlb_page_asid(start, asid); + start += stride; + } } static inline void local_flush_tlb_range_asid(unsigned long start, @@ -37,8 +60,16 @@ static inline void local_flush_tlb_range_asid(unsigned long start, { if (size <= stride) local_flush_tlb_page_asid(start, asid); - else + else if (size == FLUSH_TLB_MAX_SIZE) local_flush_tlb_all_asid(asid); + else + local_flush_tlb_range_threshold_asid(start, size, stride, asid); +} + +/* Flush a range of kernel pages without broadcasting */ +void local_flush_tlb_kernel_range(unsigned long start, unsigned long end) +{ + local_flush_tlb_range_asid(start, end - start, PAGE_SIZE, FLUSH_TLB_NO_ASID); } static void __ipi_flush_tlb_all(void *info) @@ -51,7 +82,7 @@ void flush_tlb_all(void) if (riscv_use_ipi_for_rfence()) on_each_cpu(__ipi_flush_tlb_all, NULL, 1); else - sbi_remote_sfence_vma(NULL, 0, -1); + sbi_remote_sfence_vma_asid(NULL, 0, FLUSH_TLB_MAX_SIZE, FLUSH_TLB_NO_ASID); } struct flush_tlb_range_data { @@ -68,68 +99,62 @@ static void __ipi_flush_tlb_range_asid(void *info) local_flush_tlb_range_asid(d->start, d->size, d->stride, d->asid); } -static void __ipi_flush_tlb_range(void *info) -{ - struct flush_tlb_range_data *d = info; - - local_flush_tlb_range(d->start, d->size, d->stride); -} - static void __flush_tlb_range(struct mm_struct *mm, unsigned long start, unsigned long size, unsigned long stride) { struct flush_tlb_range_data ftd; - struct cpumask *cmask = mm_cpumask(mm); - unsigned int cpuid; + const struct cpumask *cmask; + unsigned long asid = FLUSH_TLB_NO_ASID; bool broadcast; - if (cpumask_empty(cmask)) - return; + if (mm) { + unsigned int cpuid; - cpuid = get_cpu(); - /* check if the tlbflush needs to be sent to other CPUs */ - broadcast = cpumask_any_but(cmask, cpuid) < nr_cpu_ids; - if (static_branch_unlikely(&use_asid_allocator)) { - unsigned long asid = atomic_long_read(&mm->context.id) & asid_mask; - - if (broadcast) { - if (riscv_use_ipi_for_rfence()) { - ftd.asid = asid; - ftd.start = start; - ftd.size = size; - ftd.stride = stride; - on_each_cpu_mask(cmask, - __ipi_flush_tlb_range_asid, - &ftd, 1); - } else - sbi_remote_sfence_vma_asid(cmask, - start, size, asid); - } else { - local_flush_tlb_range_asid(start, size, stride, asid); - } + cmask = mm_cpumask(mm); + if (cpumask_empty(cmask)) + return; + + cpuid = get_cpu(); + /* check if the tlbflush needs to be sent to other CPUs */ + broadcast = cpumask_any_but(cmask, cpuid) < nr_cpu_ids; + + if (static_branch_unlikely(&use_asid_allocator)) + asid = atomic_long_read(&mm->context.id) & asid_mask; } else { - if (broadcast) { - if (riscv_use_ipi_for_rfence()) { - ftd.asid = 0; - ftd.start = start; - ftd.size = size; - ftd.stride = stride; - on_each_cpu_mask(cmask, - __ipi_flush_tlb_range, - &ftd, 1); - } else - sbi_remote_sfence_vma(cmask, start, size); - } else { - local_flush_tlb_range(start, size, stride); - } + cmask = cpu_online_mask; + broadcast = true; } - put_cpu(); + if (broadcast) { + if (riscv_use_ipi_for_rfence()) { + ftd.asid = asid; + ftd.start = start; + ftd.size = size; + ftd.stride = stride; + on_each_cpu_mask(cmask, + __ipi_flush_tlb_range_asid, + &ftd, 1); + } else + sbi_remote_sfence_vma_asid(cmask, + start, size, asid); + } else { + local_flush_tlb_range_asid(start, size, stride, asid); + } + + if (mm) + put_cpu(); } void flush_tlb_mm(struct mm_struct *mm) { - __flush_tlb_range(mm, 0, -1, PAGE_SIZE); + __flush_tlb_range(mm, 0, FLUSH_TLB_MAX_SIZE, PAGE_SIZE); +} + +void flush_tlb_mm_range(struct mm_struct *mm, + unsigned long start, unsigned long end, + unsigned int page_size) +{ + __flush_tlb_range(mm, start, end - start, page_size); } void flush_tlb_page(struct vm_area_struct *vma, unsigned long addr) @@ -140,8 +165,40 @@ void flush_tlb_page(struct vm_area_struct *vma, unsigned long addr) void flush_tlb_range(struct vm_area_struct *vma, unsigned long start, unsigned long end) { - __flush_tlb_range(vma->vm_mm, start, end - start, PAGE_SIZE); + unsigned long stride_size; + + if (!is_vm_hugetlb_page(vma)) { + stride_size = PAGE_SIZE; + } else { + stride_size = huge_page_size(hstate_vma(vma)); + + /* + * As stated in the privileged specification, every PTE in a + * NAPOT region must be invalidated, so reset the stride in that + * case. + */ + if (has_svnapot()) { + if (stride_size >= PGDIR_SIZE) + stride_size = PGDIR_SIZE; + else if (stride_size >= P4D_SIZE) + stride_size = P4D_SIZE; + else if (stride_size >= PUD_SIZE) + stride_size = PUD_SIZE; + else if (stride_size >= PMD_SIZE) + stride_size = PMD_SIZE; + else + stride_size = PAGE_SIZE; + } + } + + __flush_tlb_range(vma->vm_mm, start, end - start, stride_size); } + +void flush_tlb_kernel_range(unsigned long start, unsigned long end) +{ + __flush_tlb_range(NULL, start, end - start, PAGE_SIZE); +} + #ifdef CONFIG_TRANSPARENT_HUGEPAGE void flush_pmd_tlb_range(struct vm_area_struct *vma, unsigned long start, unsigned long end) |