diff options
Diffstat (limited to 'arch/powerpc/mm/book3s64')
| -rw-r--r-- | arch/powerpc/mm/book3s64/hash_4k.c | 5 | ||||
| -rw-r--r-- | arch/powerpc/mm/book3s64/hash_64k.c | 10 | ||||
| -rw-r--r-- | arch/powerpc/mm/book3s64/hash_hugepage.c | 15 | ||||
| -rw-r--r-- | arch/powerpc/mm/book3s64/hash_native.c | 80 | ||||
| -rw-r--r-- | arch/powerpc/mm/book3s64/hash_pgtable.c | 15 | ||||
| -rw-r--r-- | arch/powerpc/mm/book3s64/hash_tlb.c | 6 | ||||
| -rw-r--r-- | arch/powerpc/mm/book3s64/hash_utils.c | 194 | ||||
| -rw-r--r-- | arch/powerpc/mm/book3s64/hugetlbpage.c | 5 | ||||
| -rw-r--r-- | arch/powerpc/mm/book3s64/internal.h | 11 | ||||
| -rw-r--r-- | arch/powerpc/mm/book3s64/iommu_api.c | 4 | ||||
| -rw-r--r-- | arch/powerpc/mm/book3s64/mmu_context.c | 10 | ||||
| -rw-r--r-- | arch/powerpc/mm/book3s64/pgtable.c | 128 | ||||
| -rw-r--r-- | arch/powerpc/mm/book3s64/pkeys.c | 6 | ||||
| -rw-r--r-- | arch/powerpc/mm/book3s64/radix_hugetlbpage.c | 14 | ||||
| -rw-r--r-- | arch/powerpc/mm/book3s64/radix_pgtable.c | 758 | ||||
| -rw-r--r-- | arch/powerpc/mm/book3s64/radix_tlb.c | 377 | ||||
| -rw-r--r-- | arch/powerpc/mm/book3s64/slb.c | 1 | ||||
| -rw-r--r-- | arch/powerpc/mm/book3s64/subpage_prot.c | 18 |
18 files changed, 1241 insertions, 416 deletions
diff --git a/arch/powerpc/mm/book3s64/hash_4k.c b/arch/powerpc/mm/book3s64/hash_4k.c index 7de1a8a0c62a..02acbfd05b46 100644 --- a/arch/powerpc/mm/book3s64/hash_4k.c +++ b/arch/powerpc/mm/book3s64/hash_4k.c @@ -16,6 +16,8 @@ #include <asm/machdep.h> #include <asm/mmu.h> +#include "internal.h" + int __hash_page_4K(unsigned long ea, unsigned long access, unsigned long vsid, pte_t *ptep, unsigned long trap, unsigned long flags, int ssize, int subpg_prot) @@ -118,6 +120,9 @@ repeat: } new_pte = (new_pte & ~_PAGE_HPTEFLAGS) | H_PAGE_HASHPTE; new_pte |= pte_set_hidx(ptep, rpte, 0, slot, PTRS_PER_PTE); + + if (stress_hpt()) + hpt_do_stress(ea, hpte_group); } *ptep = __pte(new_pte & ~H_PAGE_BUSY); return 0; diff --git a/arch/powerpc/mm/book3s64/hash_64k.c b/arch/powerpc/mm/book3s64/hash_64k.c index 998c6817ed47..954af420f358 100644 --- a/arch/powerpc/mm/book3s64/hash_64k.c +++ b/arch/powerpc/mm/book3s64/hash_64k.c @@ -16,6 +16,8 @@ #include <asm/machdep.h> #include <asm/mmu.h> +#include "internal.h" + /* * Return true, if the entry has a slot value which * the software considers as invalid. @@ -216,6 +218,9 @@ repeat: new_pte |= pte_set_hidx(ptep, rpte, subpg_index, slot, PTRS_PER_PTE); new_pte |= H_PAGE_HASHPTE; + if (stress_hpt()) + hpt_do_stress(ea, hpte_group); + *ptep = __pte(new_pte & ~H_PAGE_BUSY); return 0; } @@ -327,7 +332,12 @@ repeat: new_pte = (new_pte & ~_PAGE_HPTEFLAGS) | H_PAGE_HASHPTE; new_pte |= pte_set_hidx(ptep, rpte, 0, slot, PTRS_PER_PTE); + + if (stress_hpt()) + hpt_do_stress(ea, hpte_group); } + *ptep = __pte(new_pte & ~H_PAGE_BUSY); + return 0; } diff --git a/arch/powerpc/mm/book3s64/hash_hugepage.c b/arch/powerpc/mm/book3s64/hash_hugepage.c index c0fabe6c5a12..15d6f3ea7178 100644 --- a/arch/powerpc/mm/book3s64/hash_hugepage.c +++ b/arch/powerpc/mm/book3s64/hash_hugepage.c @@ -59,16 +59,13 @@ int __hash_page_thp(unsigned long ea, unsigned long access, unsigned long vsid, rflags = htab_convert_pte_flags(new_pmd, flags); -#if 0 - if (!cpu_has_feature(CPU_FTR_COHERENT_ICACHE)) { + /* + * THPs are only supported on platforms that can do mixed page size + * segments (MPSS) and all such platforms have coherent icache. Hence we + * don't need to do lazy icache flush (hash_page_do_lazy_icache()) on + * noexecute fault. + */ - /* - * No CPU has hugepages but lacks no execute, so we - * don't need to worry about that case - */ - rflags = hash_page_do_lazy_icache(rflags, __pte(old_pte), trap); - } -#endif /* * Find the slot index details for this ea, using base page size. */ diff --git a/arch/powerpc/mm/book3s64/hash_native.c b/arch/powerpc/mm/book3s64/hash_native.c index 623a7b7ab38b..430d1d935a7c 100644 --- a/arch/powerpc/mm/book3s64/hash_native.c +++ b/arch/powerpc/mm/book3s64/hash_native.c @@ -43,6 +43,29 @@ static DEFINE_RAW_SPINLOCK(native_tlbie_lock); +#ifdef CONFIG_LOCKDEP +static struct lockdep_map hpte_lock_map = + STATIC_LOCKDEP_MAP_INIT("hpte_lock", &hpte_lock_map); + +static void acquire_hpte_lock(void) +{ + lock_map_acquire(&hpte_lock_map); +} + +static void release_hpte_lock(void) +{ + lock_map_release(&hpte_lock_map); +} +#else +static void acquire_hpte_lock(void) +{ +} + +static void release_hpte_lock(void) +{ +} +#endif + static inline unsigned long ___tlbie(unsigned long vpn, int psize, int apsize, int ssize) { @@ -220,6 +243,7 @@ static inline void native_lock_hpte(struct hash_pte *hptep) { unsigned long *word = (unsigned long *)&hptep->v; + acquire_hpte_lock(); while (1) { if (!test_and_set_bit_lock(HPTE_LOCK_BIT, word)) break; @@ -234,6 +258,7 @@ static inline void native_unlock_hpte(struct hash_pte *hptep) { unsigned long *word = (unsigned long *)&hptep->v; + release_hpte_lock(); clear_bit_unlock(HPTE_LOCK_BIT, word); } @@ -243,8 +268,11 @@ static long native_hpte_insert(unsigned long hpte_group, unsigned long vpn, { struct hash_pte *hptep = htab_address + hpte_group; unsigned long hpte_v, hpte_r; + unsigned long flags; int i; + local_irq_save(flags); + if (!(vflags & HPTE_V_BOLTED)) { DBG_LOW(" insert(group=%lx, vpn=%016lx, pa=%016lx," " rflags=%lx, vflags=%lx, psize=%d)\n", @@ -263,8 +291,10 @@ static long native_hpte_insert(unsigned long hpte_group, unsigned long vpn, hptep++; } - if (i == HPTES_PER_GROUP) + if (i == HPTES_PER_GROUP) { + local_irq_restore(flags); return -1; + } hpte_v = hpte_encode_v(vpn, psize, apsize, ssize) | vflags | HPTE_V_VALID; hpte_r = hpte_encode_r(pa, psize, apsize) | rflags; @@ -286,19 +316,24 @@ static long native_hpte_insert(unsigned long hpte_group, unsigned long vpn, * Now set the first dword including the valid bit * NOTE: this also unlocks the hpte */ + release_hpte_lock(); hptep->v = cpu_to_be64(hpte_v); __asm__ __volatile__ ("ptesync" : : : "memory"); + local_irq_restore(flags); + return i | (!!(vflags & HPTE_V_SECONDARY) << 3); } static long native_hpte_remove(unsigned long hpte_group) { + unsigned long hpte_v, flags; struct hash_pte *hptep; int i; int slot_offset; - unsigned long hpte_v; + + local_irq_save(flags); DBG_LOW(" remove(group=%lx)\n", hpte_group); @@ -323,12 +358,16 @@ static long native_hpte_remove(unsigned long hpte_group) slot_offset &= 0x7; } - if (i == HPTES_PER_GROUP) - return -1; + if (i == HPTES_PER_GROUP) { + i = -1; + goto out; + } /* Invalidate the hpte. NOTE: this also unlocks it */ + release_hpte_lock(); hptep->v = 0; - +out: + local_irq_restore(flags); return i; } @@ -339,6 +378,9 @@ static long native_hpte_updatepp(unsigned long slot, unsigned long newpp, struct hash_pte *hptep = htab_address + slot; unsigned long hpte_v, want_v; int ret = 0, local = 0; + unsigned long irqflags; + + local_irq_save(irqflags); want_v = hpte_encode_avpn(vpn, bpsize, ssize); @@ -382,6 +424,8 @@ static long native_hpte_updatepp(unsigned long slot, unsigned long newpp, if (!(flags & HPTE_NOHPTE_UPDATE)) tlbie(vpn, bpsize, apsize, ssize, local); + local_irq_restore(irqflags); + return ret; } @@ -445,6 +489,9 @@ static void native_hpte_updateboltedpp(unsigned long newpp, unsigned long ea, unsigned long vsid; long slot; struct hash_pte *hptep; + unsigned long flags; + + local_irq_save(flags); vsid = get_kernel_vsid(ea, ssize); vpn = hpt_vpn(ea, vsid, ssize); @@ -463,6 +510,8 @@ static void native_hpte_updateboltedpp(unsigned long newpp, unsigned long ea, * actual page size will be same. */ tlbie(vpn, psize, psize, ssize, 0); + + local_irq_restore(flags); } /* @@ -476,6 +525,9 @@ static int native_hpte_removebolted(unsigned long ea, int psize, int ssize) unsigned long vsid; long slot; struct hash_pte *hptep; + unsigned long flags; + + local_irq_save(flags); vsid = get_kernel_vsid(ea, ssize); vpn = hpt_vpn(ea, vsid, ssize); @@ -493,6 +545,9 @@ static int native_hpte_removebolted(unsigned long ea, int psize, int ssize) /* Invalidate the TLB */ tlbie(vpn, psize, psize, ssize, 0); + + local_irq_restore(flags); + return 0; } @@ -517,10 +572,11 @@ static void native_hpte_invalidate(unsigned long slot, unsigned long vpn, /* recheck with locks held */ hpte_v = hpte_get_old_v(hptep); - if (HPTE_V_COMPARE(hpte_v, want_v) && (hpte_v & HPTE_V_VALID)) + if (HPTE_V_COMPARE(hpte_v, want_v) && (hpte_v & HPTE_V_VALID)) { /* Invalidate the hpte. NOTE: this also unlocks it */ + release_hpte_lock(); hptep->v = 0; - else + } else native_unlock_hpte(hptep); } /* @@ -580,10 +636,8 @@ static void native_hugepage_invalidate(unsigned long vsid, hpte_v = hpte_get_old_v(hptep); if (HPTE_V_COMPARE(hpte_v, want_v) && (hpte_v & HPTE_V_VALID)) { - /* - * Invalidate the hpte. NOTE: this also unlocks it - */ - + /* Invalidate the hpte. NOTE: this also unlocks it */ + release_hpte_lock(); hptep->v = 0; } else native_unlock_hpte(hptep); @@ -765,8 +819,10 @@ static void native_flush_hash_range(unsigned long number, int local) if (!HPTE_V_COMPARE(hpte_v, want_v) || !(hpte_v & HPTE_V_VALID)) native_unlock_hpte(hptep); - else + else { + release_hpte_lock(); hptep->v = 0; + } } pte_iterate_hashed_end(); } diff --git a/arch/powerpc/mm/book3s64/hash_pgtable.c b/arch/powerpc/mm/book3s64/hash_pgtable.c index 2e0cad5817ba..988948d69bc1 100644 --- a/arch/powerpc/mm/book3s64/hash_pgtable.c +++ b/arch/powerpc/mm/book3s64/hash_pgtable.c @@ -13,6 +13,7 @@ #include <asm/sections.h> #include <asm/mmu.h> #include <asm/tlb.h> +#include <asm/firmware.h> #include <mm/mmu_decl.h> @@ -213,7 +214,7 @@ unsigned long hash__pmd_hugepage_update(struct mm_struct *mm, unsigned long addr old = be64_to_cpu(old_be); - trace_hugepage_update(addr, old, clr, set); + trace_hugepage_update_pmd(addr, old, clr, set); if (old & H_PAGE_HASHPTE) hpte_do_hugepage_flush(mm, addr, pmdp, old); return old; @@ -255,7 +256,7 @@ pmd_t hash__pmdp_collapse_flush(struct vm_area_struct *vma, unsigned long addres * the __collapse_huge_page_copy can result in copying * the old content. */ - flush_tlb_pmd_range(vma->vm_mm, &pmd, address); + flush_hash_table_pmd_range(vma->vm_mm, &pmd, address); return pmd; } @@ -403,7 +404,8 @@ EXPORT_SYMBOL_GPL(hash__has_transparent_hugepage); struct change_memory_parms { unsigned long start, end, newpp; - unsigned int step, nr_cpus, master_cpu; + unsigned int step, nr_cpus; + atomic_t master_cpu; atomic_t cpu_counter; }; @@ -477,7 +479,8 @@ static int change_memory_range_fn(void *data) { struct change_memory_parms *parms = data; - if (parms->master_cpu != smp_processor_id()) + // First CPU goes through, all others wait. + if (atomic_xchg(&parms->master_cpu, 1) == 1) return chmem_secondary_loop(parms); // Wait for all but one CPU (this one) to call-in @@ -515,7 +518,7 @@ static bool hash__change_memory_range(unsigned long start, unsigned long end, chmem_parms.end = end; chmem_parms.step = step; chmem_parms.newpp = newpp; - chmem_parms.master_cpu = smp_processor_id(); + atomic_set(&chmem_parms.master_cpu, 0); cpus_read_lock(); @@ -540,7 +543,7 @@ void hash__mark_rodata_ro(void) unsigned long start, end, pp; start = (unsigned long)_stext; - end = (unsigned long)__init_begin; + end = (unsigned long)__end_rodata; pp = htab_convert_pte_flags(pgprot_val(PAGE_KERNEL_ROX), HPTE_USE_KERNEL_KEY); diff --git a/arch/powerpc/mm/book3s64/hash_tlb.c b/arch/powerpc/mm/book3s64/hash_tlb.c index eb0bccaf221e..21fcad97ae80 100644 --- a/arch/powerpc/mm/book3s64/hash_tlb.c +++ b/arch/powerpc/mm/book3s64/hash_tlb.c @@ -221,7 +221,7 @@ void __flush_hash_table_range(unsigned long start, unsigned long end) local_irq_restore(flags); } -void flush_tlb_pmd_range(struct mm_struct *mm, pmd_t *pmd, unsigned long addr) +void flush_hash_table_pmd_range(struct mm_struct *mm, pmd_t *pmd, unsigned long addr) { pte_t *pte; pte_t *start_pte; @@ -239,12 +239,16 @@ void flush_tlb_pmd_range(struct mm_struct *mm, pmd_t *pmd, unsigned long addr) local_irq_save(flags); arch_enter_lazy_mmu_mode(); start_pte = pte_offset_map(pmd, addr); + if (!start_pte) + goto out; for (pte = start_pte; pte < start_pte + PTRS_PER_PTE; pte++) { unsigned long pteval = pte_val(*pte); if (pteval & H_PAGE_HASHPTE) hpte_need_flush(mm, addr, pte, pteval, 0); addr += PAGE_SIZE; } + pte_unmap(start_pte); +out: arch_leave_lazy_mmu_mode(); local_irq_restore(flags); } diff --git a/arch/powerpc/mm/book3s64/hash_utils.c b/arch/powerpc/mm/book3s64/hash_utils.c index fc92613dc2bf..01c3b4b65241 100644 --- a/arch/powerpc/mm/book3s64/hash_utils.c +++ b/arch/powerpc/mm/book3s64/hash_utils.c @@ -123,11 +123,8 @@ EXPORT_SYMBOL_GPL(mmu_slb_size); #ifdef CONFIG_PPC_64K_PAGES int mmu_ci_restrictions; #endif -#ifdef CONFIG_DEBUG_PAGEALLOC static u8 *linear_map_hash_slots; static unsigned long linear_map_hash_count; -static DEFINE_SPINLOCK(linear_map_hash_lock); -#endif /* CONFIG_DEBUG_PAGEALLOC */ struct mmu_hash_ops mmu_hash_ops; EXPORT_SYMBOL(mmu_hash_ops); @@ -313,9 +310,16 @@ unsigned long htab_convert_pte_flags(unsigned long pteflags, unsigned long flags else rflags |= 0x3; } + VM_WARN_ONCE(!(pteflags & _PAGE_RWX), "no-access mapping request"); } else { if (pteflags & _PAGE_RWX) rflags |= 0x2; + /* + * We should never hit this in normal fault handling because + * a permission check (check_pte_access()) will bubble this + * to higher level linux handler even for PAGE_NONE. + */ + VM_WARN_ONCE(!(pteflags & _PAGE_RWX), "no-access mapping request"); if (!((pteflags & _PAGE_WRITE) && (pteflags & _PAGE_DIRTY))) rflags |= 0x1; } @@ -408,7 +412,7 @@ repeat: ssize); if (ret == -1) { /* - * Try to to keep bolted entries in primary. + * Try to keep bolted entries in primary. * Remove non bolted entries and try insert again */ ret = mmu_hash_ops.hpte_remove(hpteg); @@ -427,11 +431,9 @@ repeat: break; cond_resched(); -#ifdef CONFIG_DEBUG_PAGEALLOC - if (debug_pagealloc_enabled() && + if (debug_pagealloc_enabled_or_kfence() && (paddr >> PAGE_SHIFT) < linear_map_hash_count) linear_map_hash_slots[paddr >> PAGE_SHIFT] = ret | 0x80; -#endif /* CONFIG_DEBUG_PAGEALLOC */ } return ret < 0 ? ret : 0; } @@ -476,7 +478,7 @@ int htab_remove_mapping(unsigned long vstart, unsigned long vend, return ret; } -static bool disable_1tb_segments = false; +static bool disable_1tb_segments __ro_after_init; static int __init parse_disable_1tb_segments(char *p) { @@ -485,6 +487,40 @@ static int __init parse_disable_1tb_segments(char *p) } early_param("disable_1tb_segments", parse_disable_1tb_segments); +bool stress_hpt_enabled __initdata; + +static int __init parse_stress_hpt(char *p) +{ + stress_hpt_enabled = true; + return 0; +} +early_param("stress_hpt", parse_stress_hpt); + +__ro_after_init DEFINE_STATIC_KEY_FALSE(stress_hpt_key); + +/* + * per-CPU array allocated if we enable stress_hpt. + */ +#define STRESS_MAX_GROUPS 16 +struct stress_hpt_struct { + unsigned long last_group[STRESS_MAX_GROUPS]; +}; + +static inline int stress_nr_groups(void) +{ + /* + * LPAR H_REMOVE flushes TLB, so need some number > 1 of entries + * to allow practical forward progress. Bare metal returns 1, which + * seems to help uncover more bugs. + */ + if (firmware_has_feature(FW_FEATURE_LPAR)) + return STRESS_MAX_GROUPS; + else + return 1; +} + +static struct stress_hpt_struct *stress_hpt_struct; + static int __init htab_dt_scan_seg_sizes(unsigned long node, const char *uname, int depth, void *data) @@ -778,7 +814,7 @@ static void __init htab_init_page_sizes(void) bool aligned = true; init_hpte_page_sizes(); - if (!debug_pagealloc_enabled()) { + if (!debug_pagealloc_enabled_or_kfence()) { /* * Pick a size for the linear mapping. Currently, we only * support 16M, 1M and 4K which is the default @@ -981,6 +1017,23 @@ static void __init hash_init_partition_table(phys_addr_t hash_table, pr_info("Partition table %p\n", partition_tb); } +void hpt_clear_stress(void); +static struct timer_list stress_hpt_timer; +static void stress_hpt_timer_fn(struct timer_list *timer) +{ + int next_cpu; + + hpt_clear_stress(); + if (!firmware_has_feature(FW_FEATURE_LPAR)) + tlbiel_all(); + + next_cpu = cpumask_next(raw_smp_processor_id(), cpu_online_mask); + if (next_cpu >= nr_cpu_ids) + next_cpu = cpumask_first(cpu_online_mask); + stress_hpt_timer.expires = jiffies + msecs_to_jiffies(10); + add_timer_on(&stress_hpt_timer, next_cpu); +} + static void __init htab_initialize(void) { unsigned long table; @@ -1000,6 +1053,21 @@ static void __init htab_initialize(void) if (stress_slb_enabled) static_branch_enable(&stress_slb_key); + if (stress_hpt_enabled) { + unsigned long tmp; + static_branch_enable(&stress_hpt_key); + // Too early to use nr_cpu_ids, so use NR_CPUS + tmp = memblock_phys_alloc_range(sizeof(struct stress_hpt_struct) * NR_CPUS, + __alignof__(struct stress_hpt_struct), + 0, MEMBLOCK_ALLOC_ANYWHERE); + memset((void *)tmp, 0xff, sizeof(struct stress_hpt_struct) * NR_CPUS); + stress_hpt_struct = __va(tmp); + + timer_setup(&stress_hpt_timer, stress_hpt_timer_fn, 0); + stress_hpt_timer.expires = jiffies + msecs_to_jiffies(10); + add_timer(&stress_hpt_timer); + } + /* * Calculate the required size of the htab. We want the number of * PTEGs to equal one half the number of real pages. @@ -1066,8 +1134,7 @@ static void __init htab_initialize(void) prot = pgprot_val(PAGE_KERNEL); -#ifdef CONFIG_DEBUG_PAGEALLOC - if (debug_pagealloc_enabled()) { + if (debug_pagealloc_enabled_or_kfence()) { linear_map_hash_count = memblock_end_of_DRAM() >> PAGE_SHIFT; linear_map_hash_slots = memblock_alloc_try_nid( linear_map_hash_count, 1, MEMBLOCK_LOW_LIMIT, @@ -1076,7 +1143,6 @@ static void __init htab_initialize(void) panic("%s: Failed to allocate %lu bytes max_addr=%pa\n", __func__, linear_map_hash_count, &ppc64_rma_size); } -#endif /* CONFIG_DEBUG_PAGEALLOC */ /* create bolted the linear mapping in the hash table */ for_each_mem_range(i, &base, &end) { @@ -1248,18 +1314,19 @@ void hash__early_init_mmu_secondary(void) */ unsigned int hash_page_do_lazy_icache(unsigned int pp, pte_t pte, int trap) { - struct page *page; + struct folio *folio; if (!pfn_valid(pte_pfn(pte))) return pp; - page = pte_page(pte); + folio = page_folio(pte_page(pte)); /* page is dirty */ - if (!test_bit(PG_dcache_clean, &page->flags) && !PageReserved(page)) { + if (!test_bit(PG_dcache_clean, &folio->flags) && + !folio_test_reserved(folio)) { if (trap == INTERRUPT_INST_STORAGE) { - flush_dcache_icache_page(page); - set_bit(PG_dcache_clean, &page->flags); + flush_dcache_icache_folio(folio); + set_bit(PG_dcache_clean, &folio->flags); } else pp |= HPTE_R_N; } @@ -1781,7 +1848,7 @@ static void hash_preload(struct mm_struct *mm, pte_t *ptep, unsigned long ea, * * This must always be called with the pte lock held. */ -void update_mmu_cache(struct vm_area_struct *vma, unsigned long address, +void __update_mmu_cache(struct vm_area_struct *vma, unsigned long address, pte_t *ptep) { /* @@ -1791,9 +1858,6 @@ void update_mmu_cache(struct vm_area_struct *vma, unsigned long address, unsigned long trap; bool is_exec; - if (radix_enabled()) - return; - /* We only want HPTEs for linux PTEs that have _PAGE_ACCESSED set */ if (!pte_young(*ptep) || address >= TASK_SIZE) return; @@ -1990,7 +2054,72 @@ repeat: return slot; } -#ifdef CONFIG_DEBUG_PAGEALLOC +void hpt_clear_stress(void) +{ + int cpu = raw_smp_processor_id(); + int g; + + for (g = 0; g < stress_nr_groups(); g++) { + unsigned long last_group; + last_group = stress_hpt_struct[cpu].last_group[g]; + + if (last_group != -1UL) { + int i; + for (i = 0; i < HPTES_PER_GROUP; i++) { + if (mmu_hash_ops.hpte_remove(last_group) == -1) + break; + } + stress_hpt_struct[cpu].last_group[g] = -1; + } + } +} + +void hpt_do_stress(unsigned long ea, unsigned long hpte_group) +{ + unsigned long last_group; + int cpu = raw_smp_processor_id(); + + last_group = stress_hpt_struct[cpu].last_group[stress_nr_groups() - 1]; + if (hpte_group == last_group) + return; + + if (last_group != -1UL) { + int i; + /* + * Concurrent CPUs might be inserting into this group, so + * give up after a number of iterations, to prevent a live + * lock. + */ + for (i = 0; i < HPTES_PER_GROUP; i++) { + if (mmu_hash_ops.hpte_remove(last_group) == -1) + break; + } + stress_hpt_struct[cpu].last_group[stress_nr_groups() - 1] = -1; + } + + if (ea >= PAGE_OFFSET) { + /* + * We would really like to prefetch to get the TLB loaded, then + * remove the PTE before returning from fault interrupt, to + * increase the hash fault rate. + * + * Unfortunately QEMU TCG does not model the TLB in a way that + * makes this possible, and systemsim (mambo) emulator does not + * bring in TLBs with prefetches (although loads/stores do + * work for non-CI PTEs). + * + * So remember this PTE and clear it on the next hash fault. + */ + memmove(&stress_hpt_struct[cpu].last_group[1], + &stress_hpt_struct[cpu].last_group[0], + (stress_nr_groups() - 1) * sizeof(unsigned long)); + stress_hpt_struct[cpu].last_group[0] = hpte_group; + } +} + +#if defined(CONFIG_DEBUG_PAGEALLOC) || defined(CONFIG_KFENCE) +static DEFINE_RAW_SPINLOCK(linear_map_hash_lock); + static void kernel_map_linear_page(unsigned long vaddr, unsigned long lmi) { unsigned long hash; @@ -2005,15 +2134,18 @@ static void kernel_map_linear_page(unsigned long vaddr, unsigned long lmi) if (!vsid) return; + if (linear_map_hash_slots[lmi] & 0x80) + return; + ret = hpte_insert_repeating(hash, vpn, __pa(vaddr), mode, HPTE_V_BOLTED, mmu_linear_psize, mmu_kernel_ssize); BUG_ON (ret < 0); - spin_lock(&linear_map_hash_lock); + raw_spin_lock(&linear_map_hash_lock); BUG_ON(linear_map_hash_slots[lmi] & 0x80); linear_map_hash_slots[lmi] = ret | 0x80; - spin_unlock(&linear_map_hash_lock); + raw_spin_unlock(&linear_map_hash_lock); } static void kernel_unmap_linear_page(unsigned long vaddr, unsigned long lmi) @@ -2023,11 +2155,14 @@ static void kernel_unmap_linear_page(unsigned long vaddr, unsigned long lmi) unsigned long vpn = hpt_vpn(vaddr, vsid, mmu_kernel_ssize); hash = hpt_hash(vpn, PAGE_SHIFT, mmu_kernel_ssize); - spin_lock(&linear_map_hash_lock); - BUG_ON(!(linear_map_hash_slots[lmi] & 0x80)); + raw_spin_lock(&linear_map_hash_lock); + if (!(linear_map_hash_slots[lmi] & 0x80)) { + raw_spin_unlock(&linear_map_hash_lock); + return; + } hidx = linear_map_hash_slots[lmi] & 0x7f; linear_map_hash_slots[lmi] = 0; - spin_unlock(&linear_map_hash_lock); + raw_spin_unlock(&linear_map_hash_lock); if (hidx & _PTEIDX_SECONDARY) hash = ~hash; slot = (hash & htab_hash_mask) * HPTES_PER_GROUP; @@ -2037,7 +2172,7 @@ static void kernel_unmap_linear_page(unsigned long vaddr, unsigned long lmi) mmu_kernel_ssize, 0); } -void hash__kernel_map_pages(struct page *page, int numpages, int enable) +int hash__kernel_map_pages(struct page *page, int numpages, int enable) { unsigned long flags, vaddr, lmi; int i; @@ -2054,8 +2189,9 @@ void hash__kernel_map_pages(struct page *page, int numpages, int enable) kernel_unmap_linear_page(vaddr, lmi); } local_irq_restore(flags); + return 0; } -#endif /* CONFIG_DEBUG_PAGEALLOC */ +#endif /* CONFIG_DEBUG_PAGEALLOC || CONFIG_KFENCE */ void hash__setup_initial_memory_limit(phys_addr_t first_memblock_base, phys_addr_t first_memblock_size) diff --git a/arch/powerpc/mm/book3s64/hugetlbpage.c b/arch/powerpc/mm/book3s64/hugetlbpage.c index 3bc0eb21b2a0..5a2e512e96db 100644 --- a/arch/powerpc/mm/book3s64/hugetlbpage.c +++ b/arch/powerpc/mm/book3s64/hugetlbpage.c @@ -143,11 +143,14 @@ pte_t huge_ptep_modify_prot_start(struct vm_area_struct *vma, void huge_ptep_modify_prot_commit(struct vm_area_struct *vma, unsigned long addr, pte_t *ptep, pte_t old_pte, pte_t pte) { + unsigned long psize; if (radix_enabled()) return radix__huge_ptep_modify_prot_commit(vma, addr, ptep, old_pte, pte); - set_huge_pte_at(vma->vm_mm, addr, ptep, pte); + + psize = huge_page_size(hstate_vma(vma)); + set_huge_pte_at(vma->vm_mm, addr, ptep, pte, psize); } void __init hugetlbpage_init_defaultsize(void) diff --git a/arch/powerpc/mm/book3s64/internal.h b/arch/powerpc/mm/book3s64/internal.h index 5045048ce244..a57a25f06a21 100644 --- a/arch/powerpc/mm/book3s64/internal.h +++ b/arch/powerpc/mm/book3s64/internal.h @@ -13,6 +13,17 @@ static inline bool stress_slb(void) return static_branch_unlikely(&stress_slb_key); } +extern bool stress_hpt_enabled; + +DECLARE_STATIC_KEY_FALSE(stress_hpt_key); + +static inline bool stress_hpt(void) +{ + return static_branch_unlikely(&stress_hpt_key); +} + +void hpt_do_stress(unsigned long ea, unsigned long hpte_group); + void slb_setup_new_exec(void); void exit_lazy_flush_tlb(struct mm_struct *mm, bool always_flush); diff --git a/arch/powerpc/mm/book3s64/iommu_api.c b/arch/powerpc/mm/book3s64/iommu_api.c index 7fcfba162e0d..c0e8d597e4cb 100644 --- a/arch/powerpc/mm/book3s64/iommu_api.c +++ b/arch/powerpc/mm/book3s64/iommu_api.c @@ -97,7 +97,7 @@ static long mm_iommu_do_alloc(struct mm_struct *mm, unsigned long ua, } mmap_read_lock(mm); - chunk = (1UL << (PAGE_SHIFT + MAX_ORDER - 1)) / + chunk = (1UL << (PAGE_SHIFT + MAX_PAGE_ORDER)) / sizeof(struct vm_area_struct *); chunk = min(chunk, entries); for (entry = 0; entry < entries; entry += chunk) { @@ -105,7 +105,7 @@ static long mm_iommu_do_alloc(struct mm_struct *mm, unsigned long ua, ret = pin_user_pages(ua + (entry << PAGE_SHIFT), n, FOLL_WRITE | FOLL_LONGTERM, - mem->hpages + entry, NULL); + mem->hpages + entry); if (ret == n) { pinned += n; continue; diff --git a/arch/powerpc/mm/book3s64/mmu_context.c b/arch/powerpc/mm/book3s64/mmu_context.c index c766e4c26e42..1715b07c630c 100644 --- a/arch/powerpc/mm/book3s64/mmu_context.c +++ b/arch/powerpc/mm/book3s64/mmu_context.c @@ -246,15 +246,15 @@ static void destroy_contexts(mm_context_t *ctx) static void pmd_frag_destroy(void *pmd_frag) { int count; - struct page *page; + struct ptdesc *ptdesc; - page = virt_to_page(pmd_frag); + ptdesc = virt_to_ptdesc(pmd_frag); /* drop all the pending references */ count = ((unsigned long)pmd_frag & ~PAGE_MASK) >> PMD_FRAG_SIZE_SHIFT; /* We allow PTE_FRAG_NR fragments from a PTE page */ - if (atomic_sub_and_test(PMD_FRAG_NR - count, &page->pt_frag_refcount)) { - pgtable_pmd_page_dtor(page); - __free_page(page); + if (atomic_sub_and_test(PMD_FRAG_NR - count, &ptdesc->pt_frag_refcount)) { + pagetable_pmd_dtor(ptdesc); + pagetable_free(ptdesc); } } diff --git a/arch/powerpc/mm/book3s64/pgtable.c b/arch/powerpc/mm/book3s64/pgtable.c index 7b9966402b25..83823db3488b 100644 --- a/arch/powerpc/mm/book3s64/pgtable.c +++ b/arch/powerpc/mm/book3s64/pgtable.c @@ -9,6 +9,7 @@ #include <linux/memremap.h> #include <linux/pkeys.h> #include <linux/debugfs.h> +#include <linux/proc_fs.h> #include <misc/cxl-base.h> #include <asm/pgalloc.h> @@ -64,11 +65,39 @@ int pmdp_set_access_flags(struct vm_area_struct *vma, unsigned long address, return changed; } +int pudp_set_access_flags(struct vm_area_struct *vma, unsigned long address, + pud_t *pudp, pud_t entry, int dirty) +{ + int changed; +#ifdef CONFIG_DEBUG_VM + WARN_ON(!pud_devmap(*pudp)); + assert_spin_locked(pud_lockptr(vma->vm_mm, pudp)); +#endif + changed = !pud_same(*(pudp), entry); + if (changed) { + /* + * We can use MMU_PAGE_1G here, because only radix + * path look at the psize. + */ + __ptep_set_access_flags(vma, pudp_ptep(pudp), + pud_pte(entry), address, MMU_PAGE_1G); + } + return changed; +} + + int pmdp_test_and_clear_young(struct vm_area_struct *vma, unsigned long address, pmd_t *pmdp) { return __pmdp_test_and_clear_young(vma->vm_mm, address, pmdp); } + +int pudp_test_and_clear_young(struct vm_area_struct *vma, + unsigned long address, pud_t *pudp) +{ + return __pudp_test_and_clear_young(vma->vm_mm, address, pudp); +} + /* * set a new huge pmd. We should not be called for updating * an existing pmd entry. That should go via pmd_hugepage_update. @@ -84,12 +113,29 @@ void set_pmd_at(struct mm_struct *mm, unsigned long addr, WARN_ON(pte_hw_valid(pmd_pte(*pmdp)) && !pte_protnone(pmd_pte(*pmdp))); assert_spin_locked(pmd_lockptr(mm, pmdp)); - WARN_ON(!(pmd_large(pmd))); + WARN_ON(!(pmd_leaf(pmd))); #endif trace_hugepage_set_pmd(addr, pmd_val(pmd)); return set_pte_at(mm, addr, pmdp_ptep(pmdp), pmd_pte(pmd)); } +void set_pud_at(struct mm_struct *mm, unsigned long addr, + pud_t *pudp, pud_t pud) +{ +#ifdef CONFIG_DEBUG_VM + /* + * Make sure hardware valid bit is not set. We don't do + * tlb flush for this update. + */ + + WARN_ON(pte_hw_valid(pud_pte(*pudp))); + assert_spin_locked(pud_lockptr(mm, pudp)); + WARN_ON(!(pud_leaf(pud))); +#endif + trace_hugepage_set_pud(addr, pud_val(pud)); + return set_pte_at(mm, addr, pudp_ptep(pudp), pud_pte(pud)); +} + static void do_serialize(void *arg) { /* We've taken the IPI, so try to trim the mask while here */ @@ -100,14 +146,14 @@ static void do_serialize(void *arg) } /* - * Serialize against find_current_mm_pte which does lock-less + * Serialize against __find_linux_pte() which does lock-less * lookup in page tables with local interrupts disabled. For huge pages * it casts pmd_t to pte_t. Since format of pte_t is different from * pmd_t we want to prevent transit from pmd pointing to page table * to pmd pointing to huge page (and back) while interrupts are disabled. * We clear pmd to possibly replace it with page table pointer in * different code paths. So make sure we wait for the parallel - * find_current_mm_pte to finish. + * __find_linux_pte() to finish. */ void serialize_against_pte_lookup(struct mm_struct *mm) { @@ -147,11 +193,35 @@ pmd_t pmdp_huge_get_and_clear_full(struct vm_area_struct *vma, return pmd; } +pud_t pudp_huge_get_and_clear_full(struct vm_area_struct *vma, + unsigned long addr, pud_t *pudp, int full) +{ + pud_t pud; + + VM_BUG_ON(addr & ~HPAGE_PMD_MASK); + VM_BUG_ON((pud_present(*pudp) && !pud_devmap(*pudp)) || + !pud_present(*pudp)); + pud = pudp_huge_get_and_clear(vma->vm_mm, addr, pudp); + /* + * if it not a fullmm flush, then we can possibly end up converting + * this PMD pte entry to a regular level 0 PTE by a parallel page fault. + * Make sure we flush the tlb in this case. + */ + if (!full) + flush_pud_tlb_range(vma, addr, addr + HPAGE_PUD_SIZE); + return pud; +} + static pmd_t pmd_set_protbits(pmd_t pmd, pgprot_t pgprot) { return __pmd(pmd_val(pmd) | pgprot_val(pgprot)); } +static pud_t pud_set_protbits(pud_t pud, pgprot_t pgprot) +{ + return __pud(pud_val(pud) | pgprot_val(pgprot)); +} + /* * At some point we should be able to get rid of * pmd_mkhuge() and mk_huge_pmd() when we update all the @@ -166,6 +236,15 @@ pmd_t pfn_pmd(unsigned long pfn, pgprot_t pgprot) return __pmd_mkhuge(pmd_set_protbits(__pmd(pmdv), pgprot)); } +pud_t pfn_pud(unsigned long pfn, pgprot_t pgprot) +{ + unsigned long pudv; + + pudv = (pfn << PAGE_SHIFT) & PTE_RPN_MASK; + + return __pud_mkhuge(pud_set_protbits(__pud(pudv), pgprot)); +} + pmd_t mk_pmd(struct page *page, pgprot_t pgprot) { return pfn_pmd(page_to_pfn(page), pgprot); @@ -306,22 +385,22 @@ static pmd_t *get_pmd_from_cache(struct mm_struct *mm) static pmd_t *__alloc_for_pmdcache(struct mm_struct *mm) { void *ret = NULL; - struct page *page; + struct ptdesc *ptdesc; gfp_t gfp = GFP_KERNEL_ACCOUNT | __GFP_ZERO; if (mm == &init_mm) gfp &= ~__GFP_ACCOUNT; - page = alloc_page(gfp); - if (!page) + ptdesc = pagetable_alloc(gfp, 0); + if (!ptdesc) return NULL; - if (!pgtable_pmd_page_ctor(page)) { - __free_pages(page, 0); + if (!pagetable_pmd_ctor(ptdesc)) { + pagetable_free(ptdesc); return NULL; } - atomic_set(&page->pt_frag_refcount, 1); + atomic_set(&ptdesc->pt_frag_refcount, 1); - ret = page_address(page); + ret = ptdesc_address(ptdesc); /* * if we support only one fragment just return the * allocated page. @@ -331,12 +410,12 @@ static pmd_t *__alloc_for_pmdcache(struct mm_struct *mm) spin_lock(&mm->page_table_lock); /* - * If we find pgtable_page set, we return + * If we find ptdesc_page set, we return * the allocated page with single fragment * count. */ if (likely(!mm->context.pmd_frag)) { - atomic_set(&page->pt_frag_refcount, PMD_FRAG_NR); + atomic_set(&ptdesc->pt_frag_refcount, PMD_FRAG_NR); mm->context.pmd_frag = ret + PMD_FRAG_SIZE; } spin_unlock(&mm->page_table_lock); @@ -357,15 +436,15 @@ pmd_t *pmd_fragment_alloc(struct mm_struct *mm, unsigned long vmaddr) void pmd_fragment_free(unsigned long *pmd) { - struct page *page = virt_to_page(pmd); + struct ptdesc *ptdesc = virt_to_ptdesc(pmd); - if (PageReserved(page)) - return free_reserved_page(page); + if (pagetable_is_reserved(ptdesc)) + return free_reserved_ptdesc(ptdesc); - BUG_ON(atomic_read(&page->pt_frag_refcount) <= 0); - if (atomic_dec_and_test(&page->pt_frag_refcount)) { - pgtable_pmd_page_dtor(page); - __free_page(page); + BUG_ON(atomic_read(&ptdesc->pt_frag_refcount) <= 0); + if (atomic_dec_and_test(&ptdesc->pt_frag_refcount)) { + pagetable_pmd_dtor(ptdesc); + pagetable_free(ptdesc); } } @@ -463,6 +542,7 @@ void ptep_modify_prot_commit(struct vm_area_struct *vma, unsigned long addr, set_pte_at(vma->vm_mm, addr, ptep, pte); } +#ifdef CONFIG_TRANSPARENT_HUGEPAGE /* * For hash translation mode, we use the deposited table to store hash slot * information and they are stored at PTRS_PER_PMD offset from related pmd @@ -484,6 +564,7 @@ int pmd_move_must_withdraw(struct spinlock *new_pmd_ptl, return true; } +#endif /* * Does the CPU support tlbie? @@ -553,8 +634,13 @@ EXPORT_SYMBOL_GPL(memremap_compat_align); pgprot_t vm_get_page_prot(unsigned long vm_flags) { - unsigned long prot = pgprot_val(protection_map[vm_flags & - (VM_READ|VM_WRITE|VM_EXEC|VM_SHARED)]); + unsigned long prot; + + /* Radix supports execute-only, but protection_map maps X -> RX */ + if (!radix_enabled() && ((vm_flags & VM_ACCESS_FLAGS) == VM_EXEC)) + vm_flags |= VM_READ; + + prot = pgprot_val(protection_map[vm_flags & (VM_ACCESS_FLAGS | VM_SHARED)]); if (vm_flags & VM_SAO) prot |= _PAGE_SAO; diff --git a/arch/powerpc/mm/book3s64/pkeys.c b/arch/powerpc/mm/book3s64/pkeys.c index 753e62ba67af..a974baf8f327 100644 --- a/arch/powerpc/mm/book3s64/pkeys.c +++ b/arch/powerpc/mm/book3s64/pkeys.c @@ -10,6 +10,7 @@ #include <asm/mmu.h> #include <asm/setup.h> #include <asm/smp.h> +#include <asm/firmware.h> #include <linux/pkeys.h> #include <linux/of_fdt.h> @@ -88,7 +89,8 @@ static int __init scan_pkey_feature(void) unsigned long pvr = mfspr(SPRN_PVR); if (PVR_VER(pvr) == PVR_POWER8 || PVR_VER(pvr) == PVR_POWER8E || - PVR_VER(pvr) == PVR_POWER8NVL || PVR_VER(pvr) == PVR_POWER9) + PVR_VER(pvr) == PVR_POWER8NVL || PVR_VER(pvr) == PVR_POWER9 || + PVR_VER(pvr) == PVR_HX_C2000) pkeys_total = 32; } } @@ -290,7 +292,7 @@ void setup_kuap(bool disabled) if (smp_processor_id() == boot_cpuid) { pr_info("Activating Kernel Userspace Access Prevention\n"); - cur_cpu_spec->mmu_features |= MMU_FTR_BOOK3S_KUAP; + cur_cpu_spec->mmu_features |= MMU_FTR_KUAP; } /* diff --git a/arch/powerpc/mm/book3s64/radix_hugetlbpage.c b/arch/powerpc/mm/book3s64/radix_hugetlbpage.c index d2fb776febb4..35fd2a95be24 100644 --- a/arch/powerpc/mm/book3s64/radix_hugetlbpage.c +++ b/arch/powerpc/mm/book3s64/radix_hugetlbpage.c @@ -39,6 +39,7 @@ void radix__flush_hugetlb_tlb_range(struct vm_area_struct *vma, unsigned long st radix__flush_tlb_pwc_range_psize(vma->vm_mm, start, end, psize); else radix__flush_tlb_range_psize(vma->vm_mm, start, end, psize); + mmu_notifier_arch_invalidate_secondary_tlbs(vma->vm_mm, start, end); } void radix__huge_ptep_modify_prot_commit(struct vm_area_struct *vma, @@ -46,14 +47,17 @@ void radix__huge_ptep_modify_prot_commit(struct vm_area_struct *vma, pte_t old_pte, pte_t pte) { struct mm_struct *mm = vma->vm_mm; + unsigned long psize = huge_page_size(hstate_vma(vma)); /* - * To avoid NMMU hang while relaxing access we need to flush the tlb before - * we set the new value. + * POWER9 NMMU must flush the TLB after clearing the PTE before + * installing a PTE with more relaxed access permissions, see + * radix__ptep_set_access_flags. */ - if (is_pte_rw_upgrade(pte_val(old_pte), pte_val(pte)) && - (atomic_read(&mm->context.copros) > 0)) + if (!cpu_has_feature(CPU_FTR_ARCH_31) && + is_pte_rw_upgrade(pte_val(old_pte), pte_val(pte)) && + atomic_read(&mm->context.copros) > 0) radix__flush_hugetlb_page(vma, addr); - set_huge_pte_at(vma->vm_mm, addr, ptep, pte); + set_huge_pte_at(vma->vm_mm, addr, ptep, pte, psize); } diff --git a/arch/powerpc/mm/book3s64/radix_pgtable.c b/arch/powerpc/mm/book3s64/radix_pgtable.c index db2f3d193448..15e88f1439ec 100644 --- a/arch/powerpc/mm/book3s64/radix_pgtable.c +++ b/arch/powerpc/mm/book3s64/radix_pgtable.c @@ -30,11 +30,13 @@ #include <asm/trace.h> #include <asm/uaccess.h> #include <asm/ultravisor.h> +#include <asm/set_memory.h> #include <trace/events/thp.h> +#include <mm/mmu_decl.h> + unsigned int mmu_base_pid; -unsigned long radix_mem_block_size __ro_after_init; static __ref void *early_alloc_pgtable(unsigned long size, int nid, unsigned long region_start, unsigned long region_end) @@ -202,14 +204,14 @@ static void radix__change_memory_range(unsigned long start, unsigned long end, pudp = pud_alloc(&init_mm, p4dp, idx); if (!pudp) continue; - if (pud_is_leaf(*pudp)) { + if (pud_leaf(*pudp)) { ptep = (pte_t *)pudp; goto update_the_pte; } pmdp = pmd_alloc(&init_mm, pudp, idx); if (!pmdp) continue; - if (pmd_is_leaf(*pmdp)) { + if (pmd_leaf(*pmdp)) { ptep = pmdp_ptep(pmdp); goto update_the_pte; } @@ -228,9 +230,17 @@ void radix__mark_rodata_ro(void) unsigned long start, end; start = (unsigned long)_stext; - end = (unsigned long)__init_begin; + end = (unsigned long)__end_rodata; radix__change_memory_range(start, end, _PAGE_WRITE); + + for (start = PAGE_OFFSET; start < (unsigned long)_stext; start += PAGE_SIZE) { + end = start + PAGE_SIZE; + if (overlaps_interrupt_vector_text(start, end)) + radix__change_memory_range(start, end, _PAGE_WRITE); + else + break; + } } void radix__mark_initmem_nx(void) @@ -259,21 +269,40 @@ print_mapping(unsigned long start, unsigned long end, unsigned long size, bool e static unsigned long next_boundary(unsigned long addr, unsigned long end) { #ifdef CONFIG_STRICT_KERNEL_RWX - if (addr < __pa_symbol(__init_begin)) - return __pa_symbol(__init_begin); + unsigned long stext_phys; + + stext_phys = __pa_symbol(_stext); + + // Relocatable kernel running at non-zero real address + if (stext_phys != 0) { + // The end of interrupts code at zero is a rodata boundary + unsigned long end_intr = __pa_symbol(__end_interrupts) - stext_phys; + if (addr < end_intr) + return end_intr; + + // Start of relocated kernel text is a rodata boundary + if (addr < stext_phys) + return stext_phys; + } + + if (addr < __pa_symbol(__srwx_boundary)) + return __pa_symbol(__srwx_boundary); #endif return end; } static int __meminit create_physical_mapping(unsigned long start, unsigned long end, - unsigned long max_mapping_size, int nid, pgprot_t _prot) { unsigned long vaddr, addr, mapping_size = 0; bool prev_exec, exec = false; pgprot_t prot; int psize; + unsigned long max_mapping_size = memory_block_size; + + if (debug_pagealloc_enabled_or_kfence()) + max_mapping_size = PAGE_SIZE; start = ALIGN(start, PAGE_SIZE); end = ALIGN_DOWN(end, PAGE_SIZE); @@ -352,7 +381,6 @@ static void __init radix_init_pgtable(void) } WARN_ON(create_physical_mapping(start, end, - radix_mem_block_size, -1, PAGE_KERNEL)); } @@ -473,58 +501,6 @@ static int __init radix_dt_scan_page_sizes(unsigned long node, return 1; } -#ifdef CONFIG_MEMORY_HOTPLUG -static int __init probe_memory_block_size(unsigned long node, const char *uname, int - depth, void *data) -{ - unsigned long *mem_block_size = (unsigned long *)data; - const __be32 *prop; - int len; - - if (depth != 1) - return 0; - - if (strcmp(uname, "ibm,dynamic-reconfiguration-memory")) - return 0; - - prop = of_get_flat_dt_prop(node, "ibm,lmb-size", &len); - - if (!prop || len < dt_root_size_cells * sizeof(__be32)) - /* - * Nothing in the device tree - */ - *mem_block_size = MIN_MEMORY_BLOCK_SIZE; - else - *mem_block_size = of_read_number(prop, dt_root_size_cells); - return 1; -} - -static unsigned long __init radix_memory_block_size(void) -{ - unsigned long mem_block_size = MIN_MEMORY_BLOCK_SIZE; - - /* - * OPAL firmware feature is set by now. Hence we are ok - * to test OPAL feature. - */ - if (firmware_has_feature(FW_FEATURE_OPAL)) - mem_block_size = 1UL * 1024 * 1024 * 1024; - else - of_scan_flat_dt(probe_memory_block_size, &mem_block_size); - - return mem_block_size; -} - -#else /* CONFIG_MEMORY_HOTPLUG */ - -static unsigned long __init radix_memory_block_size(void) -{ - return 1UL * 1024 * 1024 * 1024; -} - -#endif /* CONFIG_MEMORY_HOTPLUG */ - - void __init radix__early_init_devtree(void) { int rc; @@ -548,16 +524,6 @@ void __init radix__early_init_devtree(void) mmu_psize_defs[MMU_PAGE_64K].h_rpt_pgsize = psize_to_rpti_pgsize(MMU_PAGE_64K); } - - /* - * Max mapping size used when mapping pages. We don't use - * ppc_md.memory_block_size() here because this get called - * early and we don't have machine probe called yet. Also - * the pseries implementation only check for ibm,lmb-size. - * All hypervisor supporting radix do expose that device - * tree node. - */ - radix_mem_block_size = radix_memory_block_size(); return; } @@ -572,17 +538,6 @@ void __init radix__early_init_mmu(void) #else mmu_virtual_psize = MMU_PAGE_4K; #endif - -#ifdef CONFIG_SPARSEMEM_VMEMMAP - /* vmemmap mapping */ - if (mmu_psize_defs[MMU_PAGE_2M].shift) { - /* - * map vmemmap using 2M if available - */ - mmu_vmemmap_psize = MMU_PAGE_2M; - } else - mmu_vmemmap_psize = mmu_virtual_psize; -#endif #endif /* * initialize page table size @@ -715,10 +670,60 @@ static void free_pud_table(pud_t *pud_start, p4d_t *p4d) p4d_clear(p4d); } -static void remove_pte_table(pte_t *pte_start, unsigned long addr, - unsigned long end) +#ifdef CONFIG_SPARSEMEM_VMEMMAP +static bool __meminit vmemmap_pmd_is_unused(unsigned long addr, unsigned long end) { - unsigned long next; + unsigned long start = ALIGN_DOWN(addr, PMD_SIZE); + + return !vmemmap_populated(start, PMD_SIZE); +} + +static bool __meminit vmemmap_page_is_unused(unsigned long addr, unsigned long end) +{ + unsigned long start = ALIGN_DOWN(addr, PAGE_SIZE); + + return !vmemmap_populated(start, PAGE_SIZE); + +} +#endif + +static void __meminit free_vmemmap_pages(struct page *page, + struct vmem_altmap *altmap, + int order) +{ + unsigned int nr_pages = 1 << order; + + if (altmap) { + unsigned long alt_start, alt_end; + unsigned long base_pfn = page_to_pfn(page); + + /* + * with 2M vmemmap mmaping we can have things setup + * such that even though atlmap is specified we never + * used altmap. + */ + alt_start = altmap->base_pfn; + alt_end = altmap->base_pfn + altmap->reserve + altmap->free; + + if (base_pfn >= alt_start && base_pfn < alt_end) { + vmem_altmap_free(altmap, nr_pages); + return; + } + } + + if (PageReserved(page)) { + /* allocated from memblock */ + while (nr_pages--) + free_reserved_page(page++); + } else + free_pages((unsigned long)page_address(page), order); +} + +static void __meminit remove_pte_table(pte_t *pte_start, unsigned long addr, + unsigned long end, bool direct, + struct vmem_altmap *altmap) +{ + unsigned long next, pages = 0; pte_t *pte; pte = pte_start + pte_index(addr); @@ -730,23 +735,28 @@ static void remove_pte_table(pte_t *pte_start, unsigned long addr, if (!pte_present(*pte)) continue; - if (!PAGE_ALIGNED(addr) || !PAGE_ALIGNED(next)) { - /* - * The vmemmap_free() and remove_section_mapping() - * codepaths call us with aligned addresses. - */ - WARN_ONCE(1, "%s: unaligned range\n", __func__); - continue; + if (PAGE_ALIGNED(addr) && PAGE_ALIGNED(next)) { + if (!direct) + free_vmemmap_pages(pte_page(*pte), altmap, 0); + pte_clear(&init_mm, addr, pte); + pages++; } - - pte_clear(&init_mm, addr, pte); +#ifdef CONFIG_SPARSEMEM_VMEMMAP + else if (!direct && vmemmap_page_is_unused(addr, next)) { + free_vmemmap_pages(pte_page(*pte), altmap, 0); + pte_clear(&init_mm, addr, pte); + } +#endif } + if (direct) + update_page_count(mmu_virtual_psize, -pages); } static void __meminit remove_pmd_table(pmd_t *pmd_start, unsigned long addr, - unsigned long end) + unsigned long end, bool direct, + struct vmem_altmap *altmap) { - unsigned long next; + unsigned long next, pages = 0; pte_t *pte_base; pmd_t *pmd; @@ -757,26 +767,36 @@ static void __meminit remove_pmd_table(pmd_t *pmd_start, unsigned long addr, if (!pmd_present(*pmd)) continue; - if (pmd_is_leaf(*pmd)) { - if (!IS_ALIGNED(addr, PMD_SIZE) || - !IS_ALIGNED(next, PMD_SIZE)) { - WARN_ONCE(1, "%s: unaligned range\n", __func__); - continue; + if (pmd_leaf(*pmd)) { + if (IS_ALIGNED(addr, PMD_SIZE) && + IS_ALIGNED(next, PMD_SIZE)) { + if (!direct) + free_vmemmap_pages(pmd_page(*pmd), altmap, get_order(PMD_SIZE)); + pte_clear(&init_mm, addr, (pte_t *)pmd); + pages++; } - pte_clear(&init_mm, addr, (pte_t *)pmd); +#ifdef CONFIG_SPARSEMEM_VMEMMAP + else if (!direct && vmemmap_pmd_is_unused(addr, next)) { + free_vmemmap_pages(pmd_page(*pmd), altmap, get_order(PMD_SIZE)); + pte_clear(&init_mm, addr, (pte_t *)pmd); + } +#endif continue; } pte_base = (pte_t *)pmd_page_vaddr(*pmd); - remove_pte_table(pte_base, addr, next); + remove_pte_table(pte_base, addr, next, direct, altmap); free_pte_table(pte_base, pmd); } + if (direct) + update_page_count(MMU_PAGE_2M, -pages); } static void __meminit remove_pud_table(pud_t *pud_start, unsigned long addr, - unsigned long end) + unsigned long end, bool direct, + struct vmem_altmap *altmap) { - unsigned long next; + unsigned long next, pages = 0; pmd_t *pmd_base; pud_t *pud; @@ -787,23 +807,28 @@ static void __meminit remove_pud_table(pud_t *pud_start, unsigned long addr, if (!pud_present(*pud)) continue; - if (pud_is_leaf(*pud)) { + if (pud_leaf(*pud)) { if (!IS_ALIGNED(addr, PUD_SIZE) || !IS_ALIGNED(next, PUD_SIZE)) { WARN_ONCE(1, "%s: unaligned range\n", __func__); continue; } pte_clear(&init_mm, addr, (pte_t *)pud); + pages++; continue; } pmd_base = pud_pgtable(*pud); - remove_pmd_table(pmd_base, addr, next); + remove_pmd_table(pmd_base, addr, next, direct, altmap); free_pmd_table(pmd_base, pud); } + if (direct) + update_page_count(MMU_PAGE_1G, -pages); } -static void __meminit remove_pagetable(unsigned long start, unsigned long end) +static void __meminit +remove_pagetable(unsigned long start, unsigned long end, bool direct, + struct vmem_altmap *altmap) { unsigned long addr, next; pud_t *pud_base; @@ -820,7 +845,7 @@ static void __meminit remove_pagetable(unsigned long start, unsigned long end) if (!p4d_present(*p4d)) continue; - if (p4d_is_leaf(*p4d)) { + if (p4d_leaf(*p4d)) { if (!IS_ALIGNED(addr, P4D_SIZE) || !IS_ALIGNED(next, P4D_SIZE)) { WARN_ONCE(1, "%s: unaligned range\n", __func__); @@ -832,7 +857,7 @@ static void __meminit remove_pagetable(unsigned long start, unsigned long end) } pud_base = p4d_pgtable(*p4d); - remove_pud_table(pud_base, addr, next); + remove_pud_table(pud_base, addr, next, direct, altmap); free_pud_table(pud_base, p4d); } @@ -850,12 +875,12 @@ int __meminit radix__create_section_mapping(unsigned long start, } return create_physical_mapping(__pa(start), __pa(end), - radix_mem_block_size, nid, prot); + nid, prot); } int __meminit radix__remove_section_mapping(unsigned long start, unsigned long end) { - remove_pagetable(start, end); + remove_pagetable(start, end, true, NULL); return 0; } #endif /* CONFIG_MEMORY_HOTPLUG */ @@ -873,7 +898,6 @@ int __meminit radix__vmemmap_create_mapping(unsigned long start, unsigned long phys) { /* Create a PTE encoding */ - unsigned long flags = _PAGE_PRESENT | _PAGE_ACCESSED | _PAGE_KERNEL_RW; int nid = early_pfn_to_nid(phys >> PAGE_SHIFT); int ret; @@ -882,26 +906,438 @@ int __meminit radix__vmemmap_create_mapping(unsigned long start, return -1; } - ret = __map_kernel_page_nid(start, phys, __pgprot(flags), page_size, nid); + ret = __map_kernel_page_nid(start, phys, PAGE_KERNEL, page_size, nid); BUG_ON(ret); return 0; } + +bool vmemmap_can_optimize(struct vmem_altmap *altmap, struct dev_pagemap *pgmap) +{ + if (radix_enabled()) + return __vmemmap_can_optimize(altmap, pgmap); + + return false; +} + +int __meminit vmemmap_check_pmd(pmd_t *pmdp, int node, + unsigned long addr, unsigned long next) +{ + int large = pmd_leaf(*pmdp); + + if (large) + vmemmap_verify(pmdp_ptep(pmdp), node, addr, next); + + return large; +} + +void __meminit vmemmap_set_pmd(pmd_t *pmdp, void *p, int node, + unsigned long addr, unsigned long next) +{ + pte_t entry; + pte_t *ptep = pmdp_ptep(pmdp); + + VM_BUG_ON(!IS_ALIGNED(addr, PMD_SIZE)); + entry = pfn_pte(__pa(p) >> PAGE_SHIFT, PAGE_KERNEL); + set_pte_at(&init_mm, addr, ptep, entry); + asm volatile("ptesync": : :"memory"); + + vmemmap_verify(ptep, node, addr, next); +} + +static pte_t * __meminit radix__vmemmap_pte_populate(pmd_t *pmdp, unsigned long addr, + int node, + struct vmem_altmap *altmap, + struct page *reuse) +{ + pte_t *pte = pte_offset_kernel(pmdp, addr); + + if (pte_none(*pte)) { + pte_t entry; + void *p; + + if (!reuse) { + /* + * make sure we don't create altmap mappings + * covering things outside the device. + */ + if (altmap && altmap_cross_boundary(altmap, addr, PAGE_SIZE)) + altmap = NULL; + + p = vmemmap_alloc_block_buf(PAGE_SIZE, node, altmap); + if (!p && altmap) + p = vmemmap_alloc_block_buf(PAGE_SIZE, node, NULL); + if (!p) + return NULL; + pr_debug("PAGE_SIZE vmemmap mapping\n"); + } else { + /* + * When a PTE/PMD entry is freed from the init_mm + * there's a free_pages() call to this page allocated + * above. Thus this get_page() is paired with the + * put_page_testzero() on the freeing path. + * This can only called by certain ZONE_DEVICE path, + * and through vmemmap_populate_compound_pages() when + * slab is available. + */ + get_page(reuse); + p = page_to_virt(reuse); + pr_debug("Tail page reuse vmemmap mapping\n"); + } + + VM_BUG_ON(!PAGE_ALIGNED(addr)); + entry = pfn_pte(__pa(p) >> PAGE_SHIFT, PAGE_KERNEL); + set_pte_at(&init_mm, addr, pte, entry); + asm volatile("ptesync": : :"memory"); + } + return pte; +} + +static inline pud_t *vmemmap_pud_alloc(p4d_t *p4dp, int node, + unsigned long address) +{ + pud_t *pud; + + /* All early vmemmap mapping to keep simple do it at PAGE_SIZE */ + if (unlikely(p4d_none(*p4dp))) { + if (unlikely(!slab_is_available())) { + pud = early_alloc_pgtable(PAGE_SIZE, node, 0, 0); + p4d_populate(&init_mm, p4dp, pud); + /* go to the pud_offset */ + } else + return pud_alloc(&init_mm, p4dp, address); + } + return pud_offset(p4dp, address); +} + +static inline pmd_t *vmemmap_pmd_alloc(pud_t *pudp, int node, + unsigned long address) +{ + pmd_t *pmd; + + /* All early vmemmap mapping to keep simple do it at PAGE_SIZE */ + if (unlikely(pud_none(*pudp))) { + if (unlikely(!slab_is_available())) { + pmd = early_alloc_pgtable(PAGE_SIZE, node, 0, 0); + pud_populate(&init_mm, pudp, pmd); + } else + return pmd_alloc(&init_mm, pudp, address); + } + return pmd_offset(pudp, address); +} + +static inline pte_t *vmemmap_pte_alloc(pmd_t *pmdp, int node, + unsigned long address) +{ + pte_t *pte; + + /* All early vmemmap mapping to keep simple do it at PAGE_SIZE */ + if (unlikely(pmd_none(*pmdp))) { + if (unlikely(!slab_is_available())) { + pte = early_alloc_pgtable(PAGE_SIZE, node, 0, 0); + pmd_populate(&init_mm, pmdp, pte); + } else + return pte_alloc_kernel(pmdp, address); + } + return pte_offset_kernel(pmdp, address); +} + + + +int __meminit radix__vmemmap_populate(unsigned long start, unsigned long end, int node, + struct vmem_altmap *altmap) +{ + unsigned long addr; + unsigned long next; + pgd_t *pgd; + p4d_t *p4d; + pud_t *pud; + pmd_t *pmd; + pte_t *pte; + + for (addr = start; addr < end; addr = next) { + next = pmd_addr_end(addr, end); + + pgd = pgd_offset_k(addr); + p4d = p4d_offset(pgd, addr); + pud = vmemmap_pud_alloc(p4d, node, addr); + if (!pud) + return -ENOMEM; + pmd = vmemmap_pmd_alloc(pud, node, addr); + if (!pmd) + return -ENOMEM; + + if (pmd_none(READ_ONCE(*pmd))) { + void *p; + + /* + * keep it simple by checking addr PMD_SIZE alignment + * and verifying the device boundary condition. + * For us to use a pmd mapping, both addr and pfn should + * be aligned. We skip if addr is not aligned and for + * pfn we hope we have extra area in the altmap that + * can help to find an aligned block. This can result + * in altmap block allocation failures, in which case + * we fallback to RAM for vmemmap allocation. + */ + if (altmap && (!IS_ALIGNED(addr, PMD_SIZE) || + altmap_cross_boundary(altmap, addr, PMD_SIZE))) { + /* + * make sure we don't create altmap mappings + * covering things outside the device. + */ + goto base_mapping; + } + + p = vmemmap_alloc_block_buf(PMD_SIZE, node, altmap); + if (p) { + vmemmap_set_pmd(pmd, p, node, addr, next); + pr_debug("PMD_SIZE vmemmap mapping\n"); + continue; + } else if (altmap) { + /* + * A vmemmap block allocation can fail due to + * alignment requirements and we trying to align + * things aggressively there by running out of + * space. Try base mapping on failure. + */ + goto base_mapping; + } + } else if (vmemmap_check_pmd(pmd, node, addr, next)) { + /* + * If a huge mapping exist due to early call to + * vmemmap_populate, let's try to use that. + */ + continue; + } +base_mapping: + /* + * Not able allocate higher order memory to back memmap + * or we found a pointer to pte page. Allocate base page + * size vmemmap + */ + pte = vmemmap_pte_alloc(pmd, node, addr); + if (!pte) + return -ENOMEM; + + pte = radix__vmemmap_pte_populate(pmd, addr, node, altmap, NULL); + if (!pte) + return -ENOMEM; + + vmemmap_verify(pte, node, addr, addr + PAGE_SIZE); + next = addr + PAGE_SIZE; + } + return 0; +} + +static pte_t * __meminit radix__vmemmap_populate_address(unsigned long addr, int node, + struct vmem_altmap *altmap, + struct page *reuse) +{ + pgd_t *pgd; + p4d_t *p4d; + pud_t *pud; + pmd_t *pmd; + pte_t *pte; + + pgd = pgd_offset_k(addr); + p4d = p4d_offset(pgd, addr); + pud = vmemmap_pud_alloc(p4d, node, addr); + if (!pud) + return NULL; + pmd = vmemmap_pmd_alloc(pud, node, addr); + if (!pmd) + return NULL; + if (pmd_leaf(*pmd)) + /* + * The second page is mapped as a hugepage due to a nearby request. + * Force our mapping to page size without deduplication + */ + return NULL; + pte = vmemmap_pte_alloc(pmd, node, addr); + if (!pte) + return NULL; + radix__vmemmap_pte_populate(pmd, addr, node, NULL, NULL); + vmemmap_verify(pte, node, addr, addr + PAGE_SIZE); + + return pte; +} + +static pte_t * __meminit vmemmap_compound_tail_page(unsigned long addr, + unsigned long pfn_offset, int node) +{ + pgd_t *pgd; + p4d_t *p4d; + pud_t *pud; + pmd_t *pmd; + pte_t *pte; + unsigned long map_addr; + + /* the second vmemmap page which we use for duplication */ + map_addr = addr - pfn_offset * sizeof(struct page) + PAGE_SIZE; + pgd = pgd_offset_k(map_addr); + p4d = p4d_offset(pgd, map_addr); + pud = vmemmap_pud_alloc(p4d, node, map_addr); + if (!pud) + return NULL; + pmd = vmemmap_pmd_alloc(pud, node, map_addr); + if (!pmd) + return NULL; + if (pmd_leaf(*pmd)) + /* + * The second page is mapped as a hugepage due to a nearby request. + * Force our mapping to page size without deduplication + */ + return NULL; + pte = vmemmap_pte_alloc(pmd, node, map_addr); + if (!pte) + return NULL; + /* + * Check if there exist a mapping to the left + */ + if (pte_none(*pte)) { + /* + * Populate the head page vmemmap page. + * It can fall in different pmd, hence + * vmemmap_populate_address() + */ + pte = radix__vmemmap_populate_address(map_addr - PAGE_SIZE, node, NULL, NULL); + if (!pte) + return NULL; + /* + * Populate the tail pages vmemmap page + */ + pte = radix__vmemmap_pte_populate(pmd, map_addr, node, NULL, NULL); + if (!pte) + return NULL; + vmemmap_verify(pte, node, map_addr, map_addr + PAGE_SIZE); + return pte; + } + return pte; +} + +int __meminit vmemmap_populate_compound_pages(unsigned long start_pfn, + unsigned long start, + unsigned long end, int node, + struct dev_pagemap *pgmap) +{ + /* + * we want to map things as base page size mapping so that + * we can save space in vmemmap. We could have huge mapping + * covering out both edges. + */ + unsigned long addr; + unsigned long addr_pfn = start_pfn; + unsigned long next; + pgd_t *pgd; + p4d_t *p4d; + pud_t *pud; + pmd_t *pmd; + pte_t *pte; + + for (addr = start; addr < end; addr = next) { + + pgd = pgd_offset_k(addr); + p4d = p4d_offset(pgd, addr); + pud = vmemmap_pud_alloc(p4d, node, addr); + if (!pud) + return -ENOMEM; + pmd = vmemmap_pmd_alloc(pud, node, addr); + if (!pmd) + return -ENOMEM; + + if (pmd_leaf(READ_ONCE(*pmd))) { + /* existing huge mapping. Skip the range */ + addr_pfn += (PMD_SIZE >> PAGE_SHIFT); + next = pmd_addr_end(addr, end); + continue; + } + pte = vmemmap_pte_alloc(pmd, node, addr); + if (!pte) + return -ENOMEM; + if (!pte_none(*pte)) { + /* + * This could be because we already have a compound + * page whose VMEMMAP_RESERVE_NR pages were mapped and + * this request fall in those pages. + */ + addr_pfn += 1; + next = addr + PAGE_SIZE; + continue; + } else { + unsigned long nr_pages = pgmap_vmemmap_nr(pgmap); + unsigned long pfn_offset = addr_pfn - ALIGN_DOWN(addr_pfn, nr_pages); + pte_t *tail_page_pte; + + /* + * if the address is aligned to huge page size it is the + * head mapping. + */ + if (pfn_offset == 0) { + /* Populate the head page vmemmap page */ + pte = radix__vmemmap_pte_populate(pmd, addr, node, NULL, NULL); + if (!pte) + return -ENOMEM; + vmemmap_verify(pte, node, addr, addr + PAGE_SIZE); + + /* + * Populate the tail pages vmemmap page + * It can fall in different pmd, hence + * vmemmap_populate_address() + */ + pte = radix__vmemmap_populate_address(addr + PAGE_SIZE, node, NULL, NULL); + if (!pte) + return -ENOMEM; + + addr_pfn += 2; + next = addr + 2 * PAGE_SIZE; + continue; + } + /* + * get the 2nd mapping details + * Also create it if that doesn't exist + */ + tail_page_pte = vmemmap_compound_tail_page(addr, pfn_offset, node); + if (!tail_page_pte) { + + pte = radix__vmemmap_pte_populate(pmd, addr, node, NULL, NULL); + if (!pte) + return -ENOMEM; + vmemmap_verify(pte, node, addr, addr + PAGE_SIZE); + + addr_pfn += 1; + next = addr + PAGE_SIZE; + continue; + } + + pte = radix__vmemmap_pte_populate(pmd, addr, node, NULL, pte_page(*tail_page_pte)); + if (!pte) + return -ENOMEM; + vmemmap_verify(pte, node, addr, addr + PAGE_SIZE); + + addr_pfn += 1; + next = addr + PAGE_SIZE; + continue; + } + } + return 0; +} + + #ifdef CONFIG_MEMORY_HOTPLUG void __meminit radix__vmemmap_remove_mapping(unsigned long start, unsigned long page_size) { - remove_pagetable(start, start + page_size); + remove_pagetable(start, start + page_size, true, NULL); } -#endif -#endif -#ifdef CONFIG_DEBUG_PAGEALLOC -void radix__kernel_map_pages(struct page *page, int numpages, int enable) +void __ref radix__vmemmap_free(unsigned long start, unsigned long end, + struct vmem_altmap *altmap) { - pr_warn_once("DEBUG_PAGEALLOC not supported in radix mode\n"); + remove_pagetable(start, end, false, altmap); } #endif +#endif #ifdef CONFIG_TRANSPARENT_HUGEPAGE @@ -916,8 +1352,25 @@ unsigned long radix__pmd_hugepage_update(struct mm_struct *mm, unsigned long add assert_spin_locked(pmd_lockptr(mm, pmdp)); #endif - old = radix__pte_update(mm, addr, (pte_t *)pmdp, clr, set, 1); - trace_hugepage_update(addr, old, clr, set); + old = radix__pte_update(mm, addr, pmdp_ptep(pmdp), clr, set, 1); + trace_hugepage_update_pmd(addr, old, clr, set); + + return old; +} + +unsigned long radix__pud_hugepage_update(struct mm_struct *mm, unsigned long addr, + pud_t *pudp, unsigned long clr, + unsigned long set) +{ + unsigned long old; + +#ifdef CONFIG_DEBUG_VM + WARN_ON(!pud_devmap(*pudp)); + assert_spin_locked(pud_lockptr(mm, pudp)); +#endif + + old = radix__pte_update(mm, addr, pudp_ptep(pudp), clr, set, 1); + trace_hugepage_update_pud(addr, old, clr, set); return old; } @@ -937,15 +1390,6 @@ pmd_t radix__pmdp_collapse_flush(struct vm_area_struct *vma, unsigned long addre pmd = *pmdp; pmd_clear(pmdp); - /* - * pmdp collapse_flush need to ensure that there are no parallel gup - * walk after this call. This is needed so that we can have stable - * page ref count when collapsing a page. We don't allow a collapse page - * if we have gup taken on the page. We can ensure that by sending IPI - * because gup walk happens with IRQ disabled. - */ - serialize_against_pte_lookup(vma->vm_mm); - radix__flush_tlb_collapsed_pmd(vma->vm_mm, address); return pmd; @@ -1007,27 +1451,43 @@ pmd_t radix__pmdp_huge_get_and_clear(struct mm_struct *mm, return old_pmd; } +pud_t radix__pudp_huge_get_and_clear(struct mm_struct *mm, + unsigned long addr, pud_t *pudp) +{ + pud_t old_pud; + unsigned long old; + + old = radix__pud_hugepage_update(mm, addr, pudp, ~0UL, 0); + old_pud = __pud(old); + return old_pud; +} + #endif /* CONFIG_TRANSPARENT_HUGEPAGE */ void radix__ptep_set_access_flags(struct vm_area_struct *vma, pte_t *ptep, pte_t entry, unsigned long address, int psize) { struct mm_struct *mm = vma->vm_mm; - unsigned long set = pte_val(entry) & (_PAGE_DIRTY | _PAGE_ACCESSED | - _PAGE_RW | _PAGE_EXEC); + unsigned long set = pte_val(entry) & (_PAGE_DIRTY | _PAGE_SOFT_DIRTY | + _PAGE_ACCESSED | _PAGE_RW | _PAGE_EXEC); unsigned long change = pte_val(entry) ^ pte_val(*ptep); /* - * To avoid NMMU hang while relaxing access, we need mark - * the pte invalid in between. + * On POWER9, the NMMU is not able to relax PTE access permissions + * for a translation with a TLB. The PTE must be invalidated, TLB + * flushed before the new PTE is installed. + * + * This only needs to be done for radix, because hash translation does + * flush when updating the linux pte (and we don't support NMMU + * accelerators on HPT on POWER9 anyway XXX: do we?). + * + * POWER10 (and P9P) NMMU does behave as per ISA. */ - if ((change & _PAGE_RW) && atomic_read(&mm->context.copros) > 0) { + if (!cpu_has_feature(CPU_FTR_ARCH_31) && (change & _PAGE_RW) && + atomic_read(&mm->context.copros) > 0) { unsigned long old_pte, new_pte; old_pte = __radix_pte_update(ptep, _PAGE_PRESENT, _PAGE_INVALID); - /* - * new value of pte - */ new_pte = old_pte | set; radix__flush_tlb_page_psize(mm, address, psize); __radix_pte_update(ptep, _PAGE_INVALID, new_pte); @@ -1035,9 +1495,12 @@ void radix__ptep_set_access_flags(struct vm_area_struct *vma, pte_t *ptep, __radix_pte_update(ptep, 0, set); /* * Book3S does not require a TLB flush when relaxing access - * restrictions when the address space is not attached to a - * NMMU, because the core MMU will reload the pte after taking - * an access fault, which is defined by the architecture. + * restrictions when the address space (modulo the POWER9 nest + * MMU issue above) because the MMU will reload the PTE after + * taking an access fault, as defined by the architecture. See + * "Setting a Reference or Change Bit or Upgrading Access + * Authority (PTE Subject to Atomic Hardware Updates)" in + * Power ISA Version 3.1B. */ } /* See ptesync comment in radix__set_pte_at */ @@ -1050,11 +1513,12 @@ void radix__ptep_modify_prot_commit(struct vm_area_struct *vma, struct mm_struct *mm = vma->vm_mm; /* - * To avoid NMMU hang while relaxing access we need to flush the tlb before - * we set the new value. We need to do this only for radix, because hash - * translation does flush when updating the linux pte. + * POWER9 NMMU must flush the TLB after clearing the PTE before + * installing a PTE with more relaxed access permissions, see + * radix__ptep_set_access_flags. */ - if (is_pte_rw_upgrade(pte_val(old_pte), pte_val(pte)) && + if (!cpu_has_feature(CPU_FTR_ARCH_31) && + is_pte_rw_upgrade(pte_val(old_pte), pte_val(pte)) && (atomic_read(&mm->context.copros) > 0)) radix__flush_tlb_page(vma, addr); @@ -1076,7 +1540,7 @@ int pud_set_huge(pud_t *pud, phys_addr_t addr, pgprot_t prot) int pud_clear_huge(pud_t *pud) { - if (pud_is_leaf(*pud)) { + if (pud_leaf(*pud)) { pud_clear(pud); return 1; } @@ -1123,7 +1587,7 @@ int pmd_set_huge(pmd_t *pmd, phys_addr_t addr, pgprot_t prot) int pmd_clear_huge(pmd_t *pmd) { - if (pmd_is_leaf(*pmd)) { + if (pmd_leaf(*pmd)) { pmd_clear(pmd); return 1; } diff --git a/arch/powerpc/mm/book3s64/radix_tlb.c b/arch/powerpc/mm/book3s64/radix_tlb.c index dda51fef2d2e..9e1f6558d026 100644 --- a/arch/powerpc/mm/book3s64/radix_tlb.c +++ b/arch/powerpc/mm/book3s64/radix_tlb.c @@ -127,21 +127,6 @@ static __always_inline void __tlbie_pid(unsigned long pid, unsigned long ric) trace_tlbie(0, 0, rb, rs, ric, prs, r); } -static __always_inline void __tlbie_pid_lpid(unsigned long pid, - unsigned long lpid, - unsigned long ric) -{ - unsigned long rb, rs, prs, r; - - rb = PPC_BIT(53); /* IS = 1 */ - rs = (pid << PPC_BITLSHIFT(31)) | (lpid & ~(PPC_BITMASK(0, 31))); - prs = 1; /* process scoped */ - r = 1; /* radix format */ - - asm volatile(PPC_TLBIE_5(%0, %4, %3, %2, %1) - : : "r"(rb), "i"(r), "i"(prs), "i"(ric), "r"(rs) : "memory"); - trace_tlbie(0, 0, rb, rs, ric, prs, r); -} static __always_inline void __tlbie_lpid(unsigned long lpid, unsigned long ric) { unsigned long rb,rs,prs,r; @@ -202,23 +187,6 @@ static __always_inline void __tlbie_va(unsigned long va, unsigned long pid, trace_tlbie(0, 0, rb, rs, ric, prs, r); } -static __always_inline void __tlbie_va_lpid(unsigned long va, unsigned long pid, - unsigned long lpid, - unsigned long ap, unsigned long ric) -{ - unsigned long rb, rs, prs, r; - - rb = va & ~(PPC_BITMASK(52, 63)); - rb |= ap << PPC_BITLSHIFT(58); - rs = (pid << PPC_BITLSHIFT(31)) | (lpid & ~(PPC_BITMASK(0, 31))); - prs = 1; /* process scoped */ - r = 1; /* radix format */ - - asm volatile(PPC_TLBIE_5(%0, %4, %3, %2, %1) - : : "r"(rb), "i"(r), "i"(prs), "i"(ric), "r"(rs) : "memory"); - trace_tlbie(0, 0, rb, rs, ric, prs, r); -} - static __always_inline void __tlbie_lpid_va(unsigned long va, unsigned long lpid, unsigned long ap, unsigned long ric) { @@ -264,22 +232,6 @@ static inline void fixup_tlbie_va_range(unsigned long va, unsigned long pid, } } -static inline void fixup_tlbie_va_range_lpid(unsigned long va, - unsigned long pid, - unsigned long lpid, - unsigned long ap) -{ - if (cpu_has_feature(CPU_FTR_P9_TLBIE_ERAT_BUG)) { - asm volatile("ptesync" : : : "memory"); - __tlbie_pid_lpid(0, lpid, RIC_FLUSH_TLB); - } - - if (cpu_has_feature(CPU_FTR_P9_TLBIE_STQ_BUG)) { - asm volatile("ptesync" : : : "memory"); - __tlbie_va_lpid(va, pid, lpid, ap, RIC_FLUSH_TLB); - } -} - static inline void fixup_tlbie_pid(unsigned long pid) { /* @@ -299,26 +251,6 @@ static inline void fixup_tlbie_pid(unsigned long pid) } } -static inline void fixup_tlbie_pid_lpid(unsigned long pid, unsigned long lpid) -{ - /* - * We can use any address for the invalidation, pick one which is - * probably unused as an optimisation. - */ - unsigned long va = ((1UL << 52) - 1); - - if (cpu_has_feature(CPU_FTR_P9_TLBIE_ERAT_BUG)) { - asm volatile("ptesync" : : : "memory"); - __tlbie_pid_lpid(0, lpid, RIC_FLUSH_TLB); - } - - if (cpu_has_feature(CPU_FTR_P9_TLBIE_STQ_BUG)) { - asm volatile("ptesync" : : : "memory"); - __tlbie_va_lpid(va, pid, lpid, mmu_get_ap(MMU_PAGE_64K), - RIC_FLUSH_TLB); - } -} - static inline void fixup_tlbie_lpid_va(unsigned long va, unsigned long lpid, unsigned long ap) { @@ -416,31 +348,6 @@ static inline void _tlbie_pid(unsigned long pid, unsigned long ric) asm volatile("eieio; tlbsync; ptesync": : :"memory"); } -static inline void _tlbie_pid_lpid(unsigned long pid, unsigned long lpid, - unsigned long ric) -{ - asm volatile("ptesync" : : : "memory"); - - /* - * Workaround the fact that the "ric" argument to __tlbie_pid - * must be a compile-time contraint to match the "i" constraint - * in the asm statement. - */ - switch (ric) { - case RIC_FLUSH_TLB: - __tlbie_pid_lpid(pid, lpid, RIC_FLUSH_TLB); - fixup_tlbie_pid_lpid(pid, lpid); - break; - case RIC_FLUSH_PWC: - __tlbie_pid_lpid(pid, lpid, RIC_FLUSH_PWC); - break; - case RIC_FLUSH_ALL: - default: - __tlbie_pid_lpid(pid, lpid, RIC_FLUSH_ALL); - fixup_tlbie_pid_lpid(pid, lpid); - } - asm volatile("eieio; tlbsync; ptesync" : : : "memory"); -} struct tlbiel_pid { unsigned long pid; unsigned long ric; @@ -566,20 +473,6 @@ static inline void __tlbie_va_range(unsigned long start, unsigned long end, fixup_tlbie_va_range(addr - page_size, pid, ap); } -static inline void __tlbie_va_range_lpid(unsigned long start, unsigned long end, - unsigned long pid, unsigned long lpid, - unsigned long page_size, - unsigned long psize) -{ - unsigned long addr; - unsigned long ap = mmu_get_ap(psize); - - for (addr = start; addr < end; addr += page_size) - __tlbie_va_lpid(addr, pid, lpid, ap, RIC_FLUSH_TLB); - - fixup_tlbie_va_range_lpid(addr - page_size, pid, lpid, ap); -} - static __always_inline void _tlbie_va(unsigned long va, unsigned long pid, unsigned long psize, unsigned long ric) { @@ -660,18 +553,6 @@ static inline void _tlbie_va_range(unsigned long start, unsigned long end, asm volatile("eieio; tlbsync; ptesync": : :"memory"); } -static inline void _tlbie_va_range_lpid(unsigned long start, unsigned long end, - unsigned long pid, unsigned long lpid, - unsigned long page_size, - unsigned long psize, bool also_pwc) -{ - asm volatile("ptesync" : : : "memory"); - if (also_pwc) - __tlbie_pid_lpid(pid, lpid, RIC_FLUSH_PWC); - __tlbie_va_range_lpid(start, end, pid, lpid, page_size, psize); - asm volatile("eieio; tlbsync; ptesync" : : : "memory"); -} - static inline void _tlbiel_va_range_multicast(struct mm_struct *mm, unsigned long start, unsigned long end, unsigned long pid, unsigned long page_size, @@ -700,12 +581,13 @@ static inline void _tlbiel_va_range_multicast(struct mm_struct *mm, */ void radix__local_flush_tlb_mm(struct mm_struct *mm) { - unsigned long pid; + unsigned long pid = mm->context.id; + + if (WARN_ON_ONCE(pid == MMU_NO_CONTEXT)) + return; preempt_disable(); - pid = mm->context.id; - if (pid != MMU_NO_CONTEXT) - _tlbiel_pid(pid, RIC_FLUSH_TLB); + _tlbiel_pid(pid, RIC_FLUSH_TLB); preempt_enable(); } EXPORT_SYMBOL(radix__local_flush_tlb_mm); @@ -713,12 +595,13 @@ EXPORT_SYMBOL(radix__local_flush_tlb_mm); #ifndef CONFIG_SMP void radix__local_flush_all_mm(struct mm_struct *mm) { - unsigned long pid; + unsigned long pid = mm->context.id; + + if (WARN_ON_ONCE(pid == MMU_NO_CONTEXT)) + return; preempt_disable(); - pid = mm->context.id; - if (pid != MMU_NO_CONTEXT) - _tlbiel_pid(pid, RIC_FLUSH_ALL); + _tlbiel_pid(pid, RIC_FLUSH_ALL); preempt_enable(); } EXPORT_SYMBOL(radix__local_flush_all_mm); @@ -732,12 +615,13 @@ static void __flush_all_mm(struct mm_struct *mm, bool fullmm) void radix__local_flush_tlb_page_psize(struct mm_struct *mm, unsigned long vmaddr, int psize) { - unsigned long pid; + unsigned long pid = mm->context.id; + + if (WARN_ON_ONCE(pid == MMU_NO_CONTEXT)) + return; preempt_disable(); - pid = mm->context.id; - if (pid != MMU_NO_CONTEXT) - _tlbiel_va(vmaddr, pid, psize, RIC_FLUSH_TLB); + _tlbiel_va(vmaddr, pid, psize, RIC_FLUSH_TLB); preempt_enable(); } @@ -755,10 +639,18 @@ EXPORT_SYMBOL(radix__local_flush_tlb_page); static bool mm_needs_flush_escalation(struct mm_struct *mm) { /* - * P9 nest MMU has issues with the page walk cache - * caching PTEs and not flushing them properly when - * RIC = 0 for a PID/LPID invalidate + * The P9 nest MMU has issues with the page walk cache caching PTEs + * and not flushing them when RIC = 0 for a PID/LPID invalidate. + * + * This may have been fixed in shipping firmware (by disabling PWC + * or preventing it from caching PTEs), but until that is confirmed, + * this workaround is required - escalate all RIC=0 IS=1/2/3 flushes + * to RIC=2. + * + * POWER10 (and P9P) does not have this problem. */ + if (cpu_has_feature(CPU_FTR_ARCH_31)) + return false; if (atomic_read(&mm->context.copros) > 0) return true; return false; @@ -784,12 +676,20 @@ void exit_lazy_flush_tlb(struct mm_struct *mm, bool always_flush) goto out; if (current->active_mm == mm) { + unsigned long flags; + WARN_ON_ONCE(current->mm != NULL); - /* Is a kernel thread and is using mm as the lazy tlb */ - mmgrab(&init_mm); + /* + * It is a kernel thread and is using mm as the lazy tlb, so + * switch it to init_mm. This is not always called from IPI + * (e.g., flush_type_needed), so must disable irqs. + */ + local_irq_save(flags); + mmgrab_lazy_tlb(&init_mm); current->active_mm = &init_mm; switch_mm_irqs_off(mm, &init_mm, current); - mmdrop(mm); + mmdrop_lazy_tlb(mm); + local_irq_restore(flags); } /* @@ -801,7 +701,7 @@ void exit_lazy_flush_tlb(struct mm_struct *mm, bool always_flush) * that's what the caller expects. */ if (cpumask_test_cpu(cpu, mm_cpumask(mm))) { - atomic_dec(&mm->context.active_cpus); + dec_mm_active_cpus(mm); cpumask_clear_cpu(cpu, mm_cpumask(mm)); always_flush = true; } @@ -937,7 +837,7 @@ void radix__flush_tlb_mm(struct mm_struct *mm) enum tlb_flush_type type; pid = mm->context.id; - if (unlikely(pid == MMU_NO_CONTEXT)) + if (WARN_ON_ONCE(pid == MMU_NO_CONTEXT)) return; preempt_disable(); @@ -968,6 +868,7 @@ void radix__flush_tlb_mm(struct mm_struct *mm) } } preempt_enable(); + mmu_notifier_arch_invalidate_secondary_tlbs(mm, 0, -1UL); } EXPORT_SYMBOL(radix__flush_tlb_mm); @@ -977,7 +878,7 @@ static void __flush_all_mm(struct mm_struct *mm, bool fullmm) enum tlb_flush_type type; pid = mm->context.id; - if (unlikely(pid == MMU_NO_CONTEXT)) + if (WARN_ON_ONCE(pid == MMU_NO_CONTEXT)) return; preempt_disable(); @@ -1001,6 +902,7 @@ static void __flush_all_mm(struct mm_struct *mm, bool fullmm) _tlbiel_pid_multicast(mm, pid, RIC_FLUSH_ALL); } preempt_enable(); + mmu_notifier_arch_invalidate_secondary_tlbs(mm, 0, -1UL); } void radix__flush_all_mm(struct mm_struct *mm) @@ -1016,7 +918,7 @@ void radix__flush_tlb_page_psize(struct mm_struct *mm, unsigned long vmaddr, enum tlb_flush_type type; pid = mm->context.id; - if (unlikely(pid == MMU_NO_CONTEXT)) + if (WARN_ON_ONCE(pid == MMU_NO_CONTEXT)) return; preempt_disable(); @@ -1096,6 +998,9 @@ void radix__flush_tlb_kernel_range(unsigned long start, unsigned long end) } EXPORT_SYMBOL(radix__flush_tlb_kernel_range); +/* + * Doesn't appear to be used anywhere. Remove. + */ #define TLB_FLUSH_ALL -1UL /* @@ -1117,23 +1022,22 @@ static inline void __radix__flush_tlb_range(struct mm_struct *mm, unsigned int page_shift = mmu_psize_defs[mmu_virtual_psize].shift; unsigned long page_size = 1UL << page_shift; unsigned long nr_pages = (end - start) >> page_shift; - bool fullmm = (end == TLB_FLUSH_ALL); bool flush_pid, flush_pwc = false; enum tlb_flush_type type; pid = mm->context.id; - if (unlikely(pid == MMU_NO_CONTEXT)) + if (WARN_ON_ONCE(pid == MMU_NO_CONTEXT)) return; + WARN_ON_ONCE(end == TLB_FLUSH_ALL); + preempt_disable(); smp_mb(); /* see radix__flush_tlb_mm */ - type = flush_type_needed(mm, fullmm); + type = flush_type_needed(mm, false); if (type == FLUSH_TYPE_NONE) goto out; - if (fullmm) - flush_pid = true; - else if (type == FLUSH_TYPE_GLOBAL) + if (type == FLUSH_TYPE_GLOBAL) flush_pid = nr_pages > tlb_single_page_flush_ceiling; else flush_pid = nr_pages > tlb_local_single_page_flush_ceiling; @@ -1171,15 +1075,12 @@ static inline void __radix__flush_tlb_range(struct mm_struct *mm, } } } else { - bool hflush = false; + bool hflush; unsigned long hstart, hend; - if (IS_ENABLED(CONFIG_TRANSPARENT_HUGEPAGE)) { - hstart = (start + PMD_SIZE - 1) & PMD_MASK; - hend = end & PMD_MASK; - if (hstart < hend) - hflush = true; - } + hstart = (start + PMD_SIZE - 1) & PMD_MASK; + hend = end & PMD_MASK; + hflush = IS_ENABLED(CONFIG_TRANSPARENT_HUGEPAGE) && hstart < hend; if (type == FLUSH_TYPE_LOCAL) { asm volatile("ptesync": : :"memory"); @@ -1210,6 +1111,7 @@ static inline void __radix__flush_tlb_range(struct mm_struct *mm, } out: preempt_enable(); + mmu_notifier_arch_invalidate_secondary_tlbs(mm, start, end); } void radix__flush_tlb_range(struct vm_area_struct *vma, unsigned long start, @@ -1294,8 +1196,29 @@ void radix__tlb_flush(struct mmu_gather *tlb) * that flushes the process table entry cache upon process teardown. * See the comment for radix in arch_exit_mmap(). */ - if (tlb->fullmm || tlb->need_flush_all) { - __flush_all_mm(mm, true); + if (tlb->fullmm) { + if (IS_ENABLED(CONFIG_MMU_LAZY_TLB_SHOOTDOWN)) { + /* + * Shootdown based lazy tlb mm refcounting means we + * have to IPI everyone in the mm_cpumask anyway soon + * when the mm goes away, so might as well do it as + * part of the final flush now. + * + * If lazy shootdown was improved to reduce IPIs (e.g., + * by batching), then it may end up being better to use + * tlbies here instead. + */ + preempt_disable(); + + smp_mb(); /* see radix__flush_tlb_mm */ + exit_flush_lazy_tlbs(mm); + __flush_all_mm(mm, true); + + preempt_enable(); + } else { + __flush_all_mm(mm, true); + } + } else if ( (psize = radix_get_mmu_psize(page_size)) == -1) { if (!tlb->freed_tables) radix__flush_tlb_mm(mm); @@ -1317,25 +1240,22 @@ static void __radix__flush_tlb_range_psize(struct mm_struct *mm, unsigned int page_shift = mmu_psize_defs[psize].shift; unsigned long page_size = 1UL << page_shift; unsigned long nr_pages = (end - start) >> page_shift; - bool fullmm = (end == TLB_FLUSH_ALL); bool flush_pid; enum tlb_flush_type type; pid = mm->context.id; - if (unlikely(pid == MMU_NO_CONTEXT)) + if (WARN_ON_ONCE(pid == MMU_NO_CONTEXT)) return; - fullmm = (end == TLB_FLUSH_ALL); + WARN_ON_ONCE(end == TLB_FLUSH_ALL); preempt_disable(); smp_mb(); /* see radix__flush_tlb_mm */ - type = flush_type_needed(mm, fullmm); + type = flush_type_needed(mm, false); if (type == FLUSH_TYPE_NONE) goto out; - if (fullmm) - flush_pid = true; - else if (type == FLUSH_TYPE_GLOBAL) + if (type == FLUSH_TYPE_GLOBAL) flush_pid = nr_pages > tlb_single_page_flush_ceiling; else flush_pid = nr_pages > tlb_local_single_page_flush_ceiling; @@ -1377,6 +1297,7 @@ static void __radix__flush_tlb_range_psize(struct mm_struct *mm, } out: preempt_enable(); + mmu_notifier_arch_invalidate_secondary_tlbs(mm, start, end); } void radix__flush_tlb_range_psize(struct mm_struct *mm, unsigned long start, @@ -1398,7 +1319,7 @@ void radix__flush_tlb_collapsed_pmd(struct mm_struct *mm, unsigned long addr) enum tlb_flush_type type; pid = mm->context.id; - if (unlikely(pid == MMU_NO_CONTEXT)) + if (WARN_ON_ONCE(pid == MMU_NO_CONTEXT)) return; /* 4k page size, just blow the world */ @@ -1446,6 +1367,13 @@ void radix__flush_pmd_tlb_range(struct vm_area_struct *vma, } EXPORT_SYMBOL(radix__flush_pmd_tlb_range); +void radix__flush_pud_tlb_range(struct vm_area_struct *vma, + unsigned long start, unsigned long end) +{ + radix__flush_tlb_range_psize(vma->vm_mm, start, end, MMU_PAGE_1G); +} +EXPORT_SYMBOL(radix__flush_pud_tlb_range); + void radix__flush_tlb_all(void) { unsigned long rb,prs,r,rs; @@ -1471,6 +1399,127 @@ void radix__flush_tlb_all(void) } #ifdef CONFIG_KVM_BOOK3S_HV_POSSIBLE +static __always_inline void __tlbie_pid_lpid(unsigned long pid, + unsigned long lpid, + unsigned long ric) +{ + unsigned long rb, rs, prs, r; + + rb = PPC_BIT(53); /* IS = 1 */ + rs = (pid << PPC_BITLSHIFT(31)) | (lpid & ~(PPC_BITMASK(0, 31))); + prs = 1; /* process scoped */ + r = 1; /* radix format */ + + asm volatile(PPC_TLBIE_5(%0, %4, %3, %2, %1) + : : "r"(rb), "i"(r), "i"(prs), "i"(ric), "r"(rs) : "memory"); + trace_tlbie(0, 0, rb, rs, ric, prs, r); +} + +static __always_inline void __tlbie_va_lpid(unsigned long va, unsigned long pid, + unsigned long lpid, + unsigned long ap, unsigned long ric) +{ + unsigned long rb, rs, prs, r; + + rb = va & ~(PPC_BITMASK(52, 63)); + rb |= ap << PPC_BITLSHIFT(58); + rs = (pid << PPC_BITLSHIFT(31)) | (lpid & ~(PPC_BITMASK(0, 31))); + prs = 1; /* process scoped */ + r = 1; /* radix format */ + + asm volatile(PPC_TLBIE_5(%0, %4, %3, %2, %1) + : : "r"(rb), "i"(r), "i"(prs), "i"(ric), "r"(rs) : "memory"); + trace_tlbie(0, 0, rb, rs, ric, prs, r); +} + +static inline void fixup_tlbie_pid_lpid(unsigned long pid, unsigned long lpid) +{ + /* + * We can use any address for the invalidation, pick one which is + * probably unused as an optimisation. + */ + unsigned long va = ((1UL << 52) - 1); + + if (cpu_has_feature(CPU_FTR_P9_TLBIE_ERAT_BUG)) { + asm volatile("ptesync" : : : "memory"); + __tlbie_pid_lpid(0, lpid, RIC_FLUSH_TLB); + } + + if (cpu_has_feature(CPU_FTR_P9_TLBIE_STQ_BUG)) { + asm volatile("ptesync" : : : "memory"); + __tlbie_va_lpid(va, pid, lpid, mmu_get_ap(MMU_PAGE_64K), + RIC_FLUSH_TLB); + } +} + +static inline void _tlbie_pid_lpid(unsigned long pid, unsigned long lpid, + unsigned long ric) +{ + asm volatile("ptesync" : : : "memory"); + + /* + * Workaround the fact that the "ric" argument to __tlbie_pid + * must be a compile-time contraint to match the "i" constraint + * in the asm statement. + */ + switch (ric) { + case RIC_FLUSH_TLB: + __tlbie_pid_lpid(pid, lpid, RIC_FLUSH_TLB); + fixup_tlbie_pid_lpid(pid, lpid); + break; + case RIC_FLUSH_PWC: + __tlbie_pid_lpid(pid, lpid, RIC_FLUSH_PWC); + break; + case RIC_FLUSH_ALL: + default: + __tlbie_pid_lpid(pid, lpid, RIC_FLUSH_ALL); + fixup_tlbie_pid_lpid(pid, lpid); + } + asm volatile("eieio; tlbsync; ptesync" : : : "memory"); +} + +static inline void fixup_tlbie_va_range_lpid(unsigned long va, + unsigned long pid, + unsigned long lpid, + unsigned long ap) +{ + if (cpu_has_feature(CPU_FTR_P9_TLBIE_ERAT_BUG)) { + asm volatile("ptesync" : : : "memory"); + __tlbie_pid_lpid(0, lpid, RIC_FLUSH_TLB); + } + + if (cpu_has_feature(CPU_FTR_P9_TLBIE_STQ_BUG)) { + asm volatile("ptesync" : : : "memory"); + __tlbie_va_lpid(va, pid, lpid, ap, RIC_FLUSH_TLB); + } +} + +static inline void __tlbie_va_range_lpid(unsigned long start, unsigned long end, + unsigned long pid, unsigned long lpid, + unsigned long page_size, + unsigned long psize) +{ + unsigned long addr; + unsigned long ap = mmu_get_ap(psize); + + for (addr = start; addr < end; addr += page_size) + __tlbie_va_lpid(addr, pid, lpid, ap, RIC_FLUSH_TLB); + + fixup_tlbie_va_range_lpid(addr - page_size, pid, lpid, ap); +} + +static inline void _tlbie_va_range_lpid(unsigned long start, unsigned long end, + unsigned long pid, unsigned long lpid, + unsigned long page_size, + unsigned long psize, bool also_pwc) +{ + asm volatile("ptesync" : : : "memory"); + if (also_pwc) + __tlbie_pid_lpid(pid, lpid, RIC_FLUSH_PWC); + __tlbie_va_range_lpid(start, end, pid, lpid, page_size, psize); + asm volatile("eieio; tlbsync; ptesync" : : : "memory"); +} + /* * Performs process-scoped invalidations for a given LPID * as part of H_RPT_INVALIDATE hcall. diff --git a/arch/powerpc/mm/book3s64/slb.c b/arch/powerpc/mm/book3s64/slb.c index 6956f637a38c..f2708c8629a5 100644 --- a/arch/powerpc/mm/book3s64/slb.c +++ b/arch/powerpc/mm/book3s64/slb.c @@ -13,6 +13,7 @@ #include <asm/mmu.h> #include <asm/mmu_context.h> #include <asm/paca.h> +#include <asm/lppaca.h> #include <asm/ppc-opcode.h> #include <asm/cputable.h> #include <asm/cacheflush.h> diff --git a/arch/powerpc/mm/book3s64/subpage_prot.c b/arch/powerpc/mm/book3s64/subpage_prot.c index 60c6ea16a972..ec98e526167e 100644 --- a/arch/powerpc/mm/book3s64/subpage_prot.c +++ b/arch/powerpc/mm/book3s64/subpage_prot.c @@ -71,6 +71,8 @@ static void hpte_flush_range(struct mm_struct *mm, unsigned long addr, if (pmd_none(*pmd)) return; pte = pte_offset_map_lock(mm, pmd, addr, &ptl); + if (!pte) + return; arch_enter_lazy_mmu_mode(); for (; npages > 0; --npages) { pte_update(mm, addr, pte, 0, 0, 0); @@ -143,30 +145,22 @@ static int subpage_walk_pmd_entry(pmd_t *pmd, unsigned long addr, static const struct mm_walk_ops subpage_walk_ops = { .pmd_entry = subpage_walk_pmd_entry, + .walk_lock = PGWALK_WRLOCK_VERIFY, }; static void subpage_mark_vma_nohuge(struct mm_struct *mm, unsigned long addr, unsigned long len) { struct vm_area_struct *vma; + VMA_ITERATOR(vmi, mm, addr); /* * We don't try too hard, we just mark all the vma in that range * VM_NOHUGEPAGE and split them. */ - vma = find_vma(mm, addr); - /* - * If the range is in unmapped range, just return - */ - if (vma && ((addr + len) <= vma->vm_start)) - return; - - while (vma) { - if (vma->vm_start >= (addr + len)) - break; - vma->vm_flags |= VM_NOHUGEPAGE; + for_each_vma_range(vmi, vma, addr + len) { + vm_flags_set(vma, VM_NOHUGEPAGE); walk_page_vma(vma, &subpage_walk_ops, NULL); - vma = vma->vm_next; } } #else |