diff options
Diffstat (limited to 'arch/powerpc/mm')
-rw-r--r-- | arch/powerpc/mm/Makefile | 7 | ||||
-rw-r--r-- | arch/powerpc/mm/fault.c | 4 | ||||
-rw-r--r-- | arch/powerpc/mm/hash_native_64.c | 42 | ||||
-rw-r--r-- | arch/powerpc/mm/hash_utils_64.c | 136 | ||||
-rw-r--r-- | arch/powerpc/mm/hugetlbpage.c | 7 | ||||
-rw-r--r-- | arch/powerpc/mm/init_32.c | 2 | ||||
-rw-r--r-- | arch/powerpc/mm/mmu_context_iommu.c | 81 | ||||
-rw-r--r-- | arch/powerpc/mm/mmu_context_nohash.c | 56 | ||||
-rw-r--r-- | arch/powerpc/mm/pgtable-book3s64.c | 11 | ||||
-rw-r--r-- | arch/powerpc/mm/pgtable-radix.c | 40 | ||||
-rw-r--r-- | arch/powerpc/mm/pgtable.c | 2 | ||||
-rw-r--r-- | arch/powerpc/mm/slb_low.S | 8 | ||||
-rw-r--r-- | arch/powerpc/mm/tlb-radix.c | 24 |
13 files changed, 299 insertions, 121 deletions
diff --git a/arch/powerpc/mm/Makefile b/arch/powerpc/mm/Makefile index f2cea6d5e764..1a4e570f7894 100644 --- a/arch/powerpc/mm/Makefile +++ b/arch/powerpc/mm/Makefile @@ -7,17 +7,16 @@ subdir-ccflags-$(CONFIG_PPC_WERROR) := -Werror ccflags-$(CONFIG_PPC64) := $(NO_MINIMAL_TOC) obj-y := fault.o mem.o pgtable.o mmap.o \ - init_$(CONFIG_WORD_SIZE).o \ - pgtable_$(CONFIG_WORD_SIZE).o + init_$(BITS).o pgtable_$(BITS).o obj-$(CONFIG_PPC_MMU_NOHASH) += mmu_context_nohash.o tlb_nohash.o \ tlb_nohash_low.o -obj-$(CONFIG_PPC_BOOK3E) += tlb_low_$(CONFIG_WORD_SIZE)e.o +obj-$(CONFIG_PPC_BOOK3E) += tlb_low_$(BITS)e.o hash64-$(CONFIG_PPC_NATIVE) := hash_native_64.o obj-$(CONFIG_PPC_BOOK3E_64) += pgtable-book3e.o obj-$(CONFIG_PPC_STD_MMU_64) += pgtable-hash64.o hash_utils_64.o slb_low.o slb.o $(hash64-y) mmu_context_book3s64.o pgtable-book3s64.o obj-$(CONFIG_PPC_RADIX_MMU) += pgtable-radix.o tlb-radix.o obj-$(CONFIG_PPC_STD_MMU_32) += ppc_mmu_32.o hash_low_32.o mmu_context_hash32.o -obj-$(CONFIG_PPC_STD_MMU) += tlb_hash$(CONFIG_WORD_SIZE).o +obj-$(CONFIG_PPC_STD_MMU) += tlb_hash$(BITS).o ifeq ($(CONFIG_PPC_STD_MMU_64),y) obj-$(CONFIG_PPC_4K_PAGES) += hash64_4k.o obj-$(CONFIG_PPC_64K_PAGES) += hash64_64k.o diff --git a/arch/powerpc/mm/fault.c b/arch/powerpc/mm/fault.c index bb1ffc559f38..d0b137d96df1 100644 --- a/arch/powerpc/mm/fault.c +++ b/arch/powerpc/mm/fault.c @@ -205,7 +205,7 @@ static int mm_fault_error(struct pt_regs *regs, unsigned long addr, int fault) * The return value is 0 if the fault was handled, or the signal * number if this is a kernel fault that can't be handled here. */ -int __kprobes do_page_fault(struct pt_regs *regs, unsigned long address, +int do_page_fault(struct pt_regs *regs, unsigned long address, unsigned long error_code) { enum ctx_state prev_state = exception_enter(); @@ -498,8 +498,8 @@ bad_area_nosemaphore: bail: exception_exit(prev_state); return rc; - } +NOKPROBE_SYMBOL(do_page_fault); /* * bad_page_fault is called when we have a bad access from the kernel. diff --git a/arch/powerpc/mm/hash_native_64.c b/arch/powerpc/mm/hash_native_64.c index 0e4e9654bd2c..83ddc0e171b0 100644 --- a/arch/powerpc/mm/hash_native_64.c +++ b/arch/powerpc/mm/hash_native_64.c @@ -493,36 +493,6 @@ static void native_hugepage_invalidate(unsigned long vsid, } #endif -static inline int __hpte_actual_psize(unsigned int lp, int psize) -{ - int i, shift; - unsigned int mask; - - /* start from 1 ignoring MMU_PAGE_4K */ - for (i = 1; i < MMU_PAGE_COUNT; i++) { - - /* invalid penc */ - if (mmu_psize_defs[psize].penc[i] == -1) - continue; - /* - * encoding bits per actual page size - * PTE LP actual page size - * rrrr rrrz >=8KB - * rrrr rrzz >=16KB - * rrrr rzzz >=32KB - * rrrr zzzz >=64KB - * ....... - */ - shift = mmu_psize_defs[i].shift - LP_SHIFT; - if (shift > LP_BITS) - shift = LP_BITS; - mask = (1 << shift) - 1; - if ((lp & mask) == mmu_psize_defs[psize].penc[i]) - return i; - } - return -1; -} - static void hpte_decode(struct hash_pte *hpte, unsigned long slot, int *psize, int *apsize, int *ssize, unsigned long *vpn) { @@ -538,16 +508,8 @@ static void hpte_decode(struct hash_pte *hpte, unsigned long slot, size = MMU_PAGE_4K; a_size = MMU_PAGE_4K; } else { - for (size = 0; size < MMU_PAGE_COUNT; size++) { - - /* valid entries have a shift value */ - if (!mmu_psize_defs[size].shift) - continue; - - a_size = __hpte_actual_psize(lp, size); - if (a_size != -1) - break; - } + size = hpte_page_sizes[lp] & 0xf; + a_size = hpte_page_sizes[lp] >> 4; } /* This works for all page sizes, and for 256M and 1T segments */ if (cpu_has_feature(CPU_FTR_ARCH_300)) diff --git a/arch/powerpc/mm/hash_utils_64.c b/arch/powerpc/mm/hash_utils_64.c index 0821556e16f4..90480e23fd2c 100644 --- a/arch/powerpc/mm/hash_utils_64.c +++ b/arch/powerpc/mm/hash_utils_64.c @@ -93,6 +93,9 @@ static unsigned long _SDR1; struct mmu_psize_def mmu_psize_defs[MMU_PAGE_COUNT]; EXPORT_SYMBOL_GPL(mmu_psize_defs); +u8 hpte_page_sizes[1 << LP_BITS]; +EXPORT_SYMBOL_GPL(hpte_page_sizes); + struct hash_pte *htab_address; unsigned long htab_size_bytes; unsigned long htab_hash_mask; @@ -564,8 +567,60 @@ static void __init htab_scan_page_sizes(void) #endif /* CONFIG_HUGETLB_PAGE */ } +/* + * Fill in the hpte_page_sizes[] array. + * We go through the mmu_psize_defs[] array looking for all the + * supported base/actual page size combinations. Each combination + * has a unique pagesize encoding (penc) value in the low bits of + * the LP field of the HPTE. For actual page sizes less than 1MB, + * some of the upper LP bits are used for RPN bits, meaning that + * we need to fill in several entries in hpte_page_sizes[]. + * + * In diagrammatic form, with r = RPN bits and z = page size bits: + * PTE LP actual page size + * rrrr rrrz >=8KB + * rrrr rrzz >=16KB + * rrrr rzzz >=32KB + * rrrr zzzz >=64KB + * ... + * + * The zzzz bits are implementation-specific but are chosen so that + * no encoding for a larger page size uses the same value in its + * low-order N bits as the encoding for the 2^(12+N) byte page size + * (if it exists). + */ +static void init_hpte_page_sizes(void) +{ + long int ap, bp; + long int shift, penc; + + for (bp = 0; bp < MMU_PAGE_COUNT; ++bp) { + if (!mmu_psize_defs[bp].shift) + continue; /* not a supported page size */ + for (ap = bp; ap < MMU_PAGE_COUNT; ++ap) { + penc = mmu_psize_defs[bp].penc[ap]; + if (penc == -1) + continue; + shift = mmu_psize_defs[ap].shift - LP_SHIFT; + if (shift <= 0) + continue; /* should never happen */ + /* + * For page sizes less than 1MB, this loop + * replicates the entry for all possible values + * of the rrrr bits. + */ + while (penc < (1 << LP_BITS)) { + hpte_page_sizes[penc] = (ap << 4) | bp; + penc += 1 << shift; + } + } + } +} + static void __init htab_init_page_sizes(void) { + init_hpte_page_sizes(); + if (!debug_pagealloc_enabled()) { /* * Pick a size for the linear mapping. Currently, we only @@ -711,6 +766,29 @@ int remove_section_mapping(unsigned long start, unsigned long end) } #endif /* CONFIG_MEMORY_HOTPLUG */ +static void update_hid_for_hash(void) +{ + unsigned long hid0; + unsigned long rb = 3UL << PPC_BITLSHIFT(53); /* IS = 3 */ + + asm volatile("ptesync": : :"memory"); + /* prs = 0, ric = 2, rs = 0, r = 1 is = 3 */ + asm volatile(PPC_TLBIE_5(%0, %4, %3, %2, %1) + : : "r"(rb), "i"(0), "i"(0), "i"(2), "r"(0) : "memory"); + asm volatile("eieio; tlbsync; ptesync; isync; slbia": : :"memory"); + /* + * now switch the HID + */ + hid0 = mfspr(SPRN_HID0); + hid0 &= ~HID0_POWER9_RADIX; + mtspr(SPRN_HID0, hid0); + asm volatile("isync": : :"memory"); + + /* Wait for it to happen */ + while ((mfspr(SPRN_HID0) & HID0_POWER9_RADIX)) + cpu_relax(); +} + static void __init hash_init_partition_table(phys_addr_t hash_table, unsigned long htab_size) { @@ -737,6 +815,8 @@ static void __init hash_init_partition_table(phys_addr_t hash_table, */ partition_tb->patb1 = 0; pr_info("Partition table %p\n", partition_tb); + if (cpu_has_feature(CPU_FTR_POWER9_DD1)) + update_hid_for_hash(); /* * update partition table control register, * 64 K size. @@ -1460,6 +1540,29 @@ out_exit: local_irq_restore(flags); } +#ifdef CONFIG_PPC_TRANSACTIONAL_MEM +static inline void tm_flush_hash_page(int local) +{ + /* + * Transactions are not aborted by tlbiel, only tlbie. Without, syncing a + * page back to a block device w/PIO could pick up transactional data + * (bad!) so we force an abort here. Before the sync the page will be + * made read-only, which will flush_hash_page. BIG ISSUE here: if the + * kernel uses a page from userspace without unmapping it first, it may + * see the speculated version. + */ + if (local && cpu_has_feature(CPU_FTR_TM) && current->thread.regs && + MSR_TM_ACTIVE(current->thread.regs->msr)) { + tm_enable(); + tm_abort(TM_CAUSE_TLBI); + } +} +#else +static inline void tm_flush_hash_page(int local) +{ +} +#endif + /* WARNING: This is called from hash_low_64.S, if you change this prototype, * do not forget to update the assembly call site ! */ @@ -1486,21 +1589,7 @@ void flush_hash_page(unsigned long vpn, real_pte_t pte, int psize, int ssize, ssize, local); } pte_iterate_hashed_end(); -#ifdef CONFIG_PPC_TRANSACTIONAL_MEM - /* Transactions are not aborted by tlbiel, only tlbie. - * Without, syncing a page back to a block device w/ PIO could pick up - * transactional data (bad!) so we force an abort here. Before the - * sync the page will be made read-only, which will flush_hash_page. - * BIG ISSUE here: if the kernel uses a page from userspace without - * unmapping it first, it may see the speculated version. - */ - if (local && cpu_has_feature(CPU_FTR_TM) && - current->thread.regs && - MSR_TM_ACTIVE(current->thread.regs->msr)) { - tm_enable(); - tm_abort(TM_CAUSE_TLBI); - } -#endif + tm_flush_hash_page(local); } #ifdef CONFIG_TRANSPARENT_HUGEPAGE @@ -1557,22 +1646,7 @@ void flush_hash_hugepage(unsigned long vsid, unsigned long addr, MMU_PAGE_16M, ssize, local); } tm_abort: -#ifdef CONFIG_PPC_TRANSACTIONAL_MEM - /* Transactions are not aborted by tlbiel, only tlbie. - * Without, syncing a page back to a block device w/ PIO could pick up - * transactional data (bad!) so we force an abort here. Before the - * sync the page will be made read-only, which will flush_hash_page. - * BIG ISSUE here: if the kernel uses a page from userspace without - * unmapping it first, it may see the speculated version. - */ - if (local && cpu_has_feature(CPU_FTR_TM) && - current->thread.regs && - MSR_TM_ACTIVE(current->thread.regs->msr)) { - tm_enable(); - tm_abort(TM_CAUSE_TLBI); - } -#endif - return; + tm_flush_hash_page(local); } #endif /* CONFIG_TRANSPARENT_HUGEPAGE */ diff --git a/arch/powerpc/mm/hugetlbpage.c b/arch/powerpc/mm/hugetlbpage.c index 7372ee13eb1e..a5d3ecdabc44 100644 --- a/arch/powerpc/mm/hugetlbpage.c +++ b/arch/powerpc/mm/hugetlbpage.c @@ -1019,8 +1019,15 @@ int gup_hugepte(pte_t *ptep, unsigned long sz, unsigned long addr, pte = READ_ONCE(*ptep); mask = _PAGE_PRESENT | _PAGE_READ; + + /* + * On some CPUs like the 8xx, _PAGE_RW hence _PAGE_WRITE is defined + * as 0 and _PAGE_RO has to be set when a page is not writable + */ if (write) mask |= _PAGE_WRITE; + else + mask |= _PAGE_RO; if ((pte_val(pte) & mask) != mask) return 0; diff --git a/arch/powerpc/mm/init_32.c b/arch/powerpc/mm/init_32.c index 448685fbf27c..8a7c38b8d335 100644 --- a/arch/powerpc/mm/init_32.c +++ b/arch/powerpc/mm/init_32.c @@ -137,7 +137,7 @@ void __init MMU_init(void) if (memblock.memory.cnt > 1) { #ifndef CONFIG_WII memblock_enforce_memory_limit(memblock.memory.regions[0].size); - printk(KERN_WARNING "Only using first contiguous memory region"); + pr_warn("Only using first contiguous memory region\n"); #else wii_memory_fixups(); #endif diff --git a/arch/powerpc/mm/mmu_context_iommu.c b/arch/powerpc/mm/mmu_context_iommu.c index da6a2168ae9e..e0f1c33601dd 100644 --- a/arch/powerpc/mm/mmu_context_iommu.c +++ b/arch/powerpc/mm/mmu_context_iommu.c @@ -15,6 +15,9 @@ #include <linux/rculist.h> #include <linux/vmalloc.h> #include <linux/mutex.h> +#include <linux/migrate.h> +#include <linux/hugetlb.h> +#include <linux/swap.h> #include <asm/mmu_context.h> static DEFINE_MUTEX(mem_list_mutex); @@ -72,6 +75,55 @@ bool mm_iommu_preregistered(void) } EXPORT_SYMBOL_GPL(mm_iommu_preregistered); +/* + * Taken from alloc_migrate_target with changes to remove CMA allocations + */ +struct page *new_iommu_non_cma_page(struct page *page, unsigned long private, + int **resultp) +{ + gfp_t gfp_mask = GFP_USER; + struct page *new_page; + + if (PageHuge(page) || PageTransHuge(page) || PageCompound(page)) + return NULL; + + if (PageHighMem(page)) + gfp_mask |= __GFP_HIGHMEM; + + /* + * We don't want the allocation to force an OOM if possibe + */ + new_page = alloc_page(gfp_mask | __GFP_NORETRY | __GFP_NOWARN); + return new_page; +} + +static int mm_iommu_move_page_from_cma(struct page *page) +{ + int ret = 0; + LIST_HEAD(cma_migrate_pages); + + /* Ignore huge pages for now */ + if (PageHuge(page) || PageTransHuge(page) || PageCompound(page)) + return -EBUSY; + + lru_add_drain(); + ret = isolate_lru_page(page); + if (ret) + return ret; + + list_add(&page->lru, &cma_migrate_pages); + put_page(page); /* Drop the gup reference */ + + ret = migrate_pages(&cma_migrate_pages, new_iommu_non_cma_page, + NULL, 0, MIGRATE_SYNC, MR_CMA); + if (ret) { + if (!list_empty(&cma_migrate_pages)) + putback_movable_pages(&cma_migrate_pages); + } + + return 0; +} + long mm_iommu_get(unsigned long ua, unsigned long entries, struct mm_iommu_table_group_mem_t **pmem) { @@ -124,15 +176,36 @@ long mm_iommu_get(unsigned long ua, unsigned long entries, for (i = 0; i < entries; ++i) { if (1 != get_user_pages_fast(ua + (i << PAGE_SHIFT), 1/* pages */, 1/* iswrite */, &page)) { + ret = -EFAULT; for (j = 0; j < i; ++j) - put_page(pfn_to_page( - mem->hpas[j] >> PAGE_SHIFT)); + put_page(pfn_to_page(mem->hpas[j] >> + PAGE_SHIFT)); vfree(mem->hpas); kfree(mem); - ret = -EFAULT; goto unlock_exit; } - + /* + * If we get a page from the CMA zone, since we are going to + * be pinning these entries, we might as well move them out + * of the CMA zone if possible. NOTE: faulting in + migration + * can be expensive. Batching can be considered later + */ + if (get_pageblock_migratetype(page) == MIGRATE_CMA) { + if (mm_iommu_move_page_from_cma(page)) + goto populate; + if (1 != get_user_pages_fast(ua + (i << PAGE_SHIFT), + 1/* pages */, 1/* iswrite */, + &page)) { + ret = -EFAULT; + for (j = 0; j < i; ++j) + put_page(pfn_to_page(mem->hpas[j] >> + PAGE_SHIFT)); + vfree(mem->hpas); + kfree(mem); + goto unlock_exit; + } + } +populate: mem->hpas[i] = page_to_pfn(page) << PAGE_SHIFT; } diff --git a/arch/powerpc/mm/mmu_context_nohash.c b/arch/powerpc/mm/mmu_context_nohash.c index 7d95bc402dba..c491f2c8f2b9 100644 --- a/arch/powerpc/mm/mmu_context_nohash.c +++ b/arch/powerpc/mm/mmu_context_nohash.c @@ -369,44 +369,34 @@ void destroy_context(struct mm_struct *mm) } #ifdef CONFIG_SMP - -static int mmu_context_cpu_notify(struct notifier_block *self, - unsigned long action, void *hcpu) +static int mmu_ctx_cpu_prepare(unsigned int cpu) { - unsigned int cpu = (unsigned int)(long)hcpu; - /* We don't touch CPU 0 map, it's allocated at aboot and kept * around forever */ if (cpu == boot_cpuid) - return NOTIFY_OK; - - switch (action) { - case CPU_UP_PREPARE: - case CPU_UP_PREPARE_FROZEN: - pr_devel("MMU: Allocating stale context map for CPU %d\n", cpu); - stale_map[cpu] = kzalloc(CTX_MAP_SIZE, GFP_KERNEL); - break; -#ifdef CONFIG_HOTPLUG_CPU - case CPU_UP_CANCELED: - case CPU_UP_CANCELED_FROZEN: - case CPU_DEAD: - case CPU_DEAD_FROZEN: - pr_devel("MMU: Freeing stale context map for CPU %d\n", cpu); - kfree(stale_map[cpu]); - stale_map[cpu] = NULL; - - /* We also clear the cpu_vm_mask bits of CPUs going away */ - clear_tasks_mm_cpumask(cpu); - break; -#endif /* CONFIG_HOTPLUG_CPU */ - } - return NOTIFY_OK; + return 0; + + pr_devel("MMU: Allocating stale context map for CPU %d\n", cpu); + stale_map[cpu] = kzalloc(CTX_MAP_SIZE, GFP_KERNEL); + return 0; } -static struct notifier_block mmu_context_cpu_nb = { - .notifier_call = mmu_context_cpu_notify, -}; +static int mmu_ctx_cpu_dead(unsigned int cpu) +{ +#ifdef CONFIG_HOTPLUG_CPU + if (cpu == boot_cpuid) + return 0; + + pr_devel("MMU: Freeing stale context map for CPU %d\n", cpu); + kfree(stale_map[cpu]); + stale_map[cpu] = NULL; + + /* We also clear the cpu_vm_mask bits of CPUs going away */ + clear_tasks_mm_cpumask(cpu); +#endif + return 0; +} #endif /* CONFIG_SMP */ @@ -469,7 +459,9 @@ void __init mmu_context_init(void) #else stale_map[boot_cpuid] = memblock_virt_alloc(CTX_MAP_SIZE, 0); - register_cpu_notifier(&mmu_context_cpu_nb); + cpuhp_setup_state_nocalls(CPUHP_POWERPC_MMU_CTX_PREPARE, + "powerpc/mmu/ctx:prepare", + mmu_ctx_cpu_prepare, mmu_ctx_cpu_dead); #endif printk(KERN_INFO diff --git a/arch/powerpc/mm/pgtable-book3s64.c b/arch/powerpc/mm/pgtable-book3s64.c index 34079302cc17..f4f437cbabf1 100644 --- a/arch/powerpc/mm/pgtable-book3s64.c +++ b/arch/powerpc/mm/pgtable-book3s64.c @@ -35,7 +35,7 @@ int pmdp_set_access_flags(struct vm_area_struct *vma, unsigned long address, #endif changed = !pmd_same(*(pmdp), entry); if (changed) { - __ptep_set_access_flags(pmdp_ptep(pmdp), pmd_pte(entry)); + __ptep_set_access_flags(vma->vm_mm, pmdp_ptep(pmdp), pmd_pte(entry)); flush_pmd_tlb_range(vma, address, address + HPAGE_PMD_SIZE); } return changed; @@ -116,3 +116,12 @@ void update_mmu_cache_pmd(struct vm_area_struct *vma, unsigned long addr, return; } #endif /* CONFIG_TRANSPARENT_HUGEPAGE */ + +/* For use by kexec */ +void mmu_cleanup_all(void) +{ + if (radix_enabled()) + radix__mmu_cleanup_all(); + else if (mmu_hash_ops.hpte_clear_all) + mmu_hash_ops.hpte_clear_all(); +} diff --git a/arch/powerpc/mm/pgtable-radix.c b/arch/powerpc/mm/pgtable-radix.c index af897d91d09f..ed7bddc456b7 100644 --- a/arch/powerpc/mm/pgtable-radix.c +++ b/arch/powerpc/mm/pgtable-radix.c @@ -294,6 +294,32 @@ found: return; } +static void update_hid_for_radix(void) +{ + unsigned long hid0; + unsigned long rb = 3UL << PPC_BITLSHIFT(53); /* IS = 3 */ + + asm volatile("ptesync": : :"memory"); + /* prs = 0, ric = 2, rs = 0, r = 1 is = 3 */ + asm volatile(PPC_TLBIE_5(%0, %4, %3, %2, %1) + : : "r"(rb), "i"(1), "i"(0), "i"(2), "r"(0) : "memory"); + /* prs = 1, ric = 2, rs = 0, r = 1 is = 3 */ + asm volatile(PPC_TLBIE_5(%0, %4, %3, %2, %1) + : : "r"(rb), "i"(1), "i"(1), "i"(2), "r"(0) : "memory"); + asm volatile("eieio; tlbsync; ptesync; isync; slbia": : :"memory"); + /* + * now switch the HID + */ + hid0 = mfspr(SPRN_HID0); + hid0 |= HID0_POWER9_RADIX; + mtspr(SPRN_HID0, hid0); + asm volatile("isync": : :"memory"); + + /* Wait for it to happen */ + while (!(mfspr(SPRN_HID0) & HID0_POWER9_RADIX)) + cpu_relax(); +} + void __init radix__early_init_mmu(void) { unsigned long lpcr; @@ -345,6 +371,8 @@ void __init radix__early_init_mmu(void) if (!firmware_has_feature(FW_FEATURE_LPAR)) { radix_init_native(); + if (cpu_has_feature(CPU_FTR_POWER9_DD1)) + update_hid_for_radix(); lpcr = mfspr(SPRN_LPCR); mtspr(SPRN_LPCR, lpcr | LPCR_UPRT | LPCR_HR); radix_init_partition_table(); @@ -368,6 +396,18 @@ void radix__early_init_mmu_secondary(void) } } +void radix__mmu_cleanup_all(void) +{ + unsigned long lpcr; + + if (!firmware_has_feature(FW_FEATURE_LPAR)) { + lpcr = mfspr(SPRN_LPCR); + mtspr(SPRN_LPCR, lpcr & ~LPCR_UPRT); + mtspr(SPRN_PTCR, 0); + radix__flush_tlb_all(); + } +} + void radix__setup_initial_memory_limit(phys_addr_t first_memblock_base, phys_addr_t first_memblock_size) { diff --git a/arch/powerpc/mm/pgtable.c b/arch/powerpc/mm/pgtable.c index 0b6fb244d0a1..911fdfb63ec1 100644 --- a/arch/powerpc/mm/pgtable.c +++ b/arch/powerpc/mm/pgtable.c @@ -224,7 +224,7 @@ int ptep_set_access_flags(struct vm_area_struct *vma, unsigned long address, if (changed) { if (!is_vm_hugetlb_page(vma)) assert_pte_locked(vma->vm_mm, address); - __ptep_set_access_flags(ptep, entry); + __ptep_set_access_flags(vma->vm_mm, ptep, entry); flush_tlb_page(vma, address); } return changed; diff --git a/arch/powerpc/mm/slb_low.S b/arch/powerpc/mm/slb_low.S index 9f1983404e1a..e2974fcd20f1 100644 --- a/arch/powerpc/mm/slb_low.S +++ b/arch/powerpc/mm/slb_low.S @@ -178,11 +178,9 @@ BEGIN_FTR_SECTION END_MMU_FTR_SECTION_IFSET(MMU_FTR_1T_SEGMENT) b slb_finish_load -8: /* invalid EA */ - li r10,0 /* BAD_VSID */ - li r9,0 /* BAD_VSID */ - li r11,SLB_VSID_USER /* flags don't much matter */ - b slb_finish_load +8: /* invalid EA - return an error indication */ + crset 4*cr0+eq /* indicate failure */ + blr /* * Finish loading of an SLB entry and return diff --git a/arch/powerpc/mm/tlb-radix.c b/arch/powerpc/mm/tlb-radix.c index 48df05ef5231..0e49ec541ab5 100644 --- a/arch/powerpc/mm/tlb-radix.c +++ b/arch/powerpc/mm/tlb-radix.c @@ -400,3 +400,27 @@ void radix__flush_pmd_tlb_range(struct vm_area_struct *vma, radix__flush_tlb_range_psize(vma->vm_mm, start, end, MMU_PAGE_2M); } EXPORT_SYMBOL(radix__flush_pmd_tlb_range); + +void radix__flush_tlb_all(void) +{ + unsigned long rb,prs,r,rs; + unsigned long ric = RIC_FLUSH_ALL; + + rb = 0x3 << PPC_BITLSHIFT(53); /* IS = 3 */ + prs = 0; /* partition scoped */ + r = 1; /* raidx format */ + rs = 1 & ((1UL << 32) - 1); /* any LPID value to flush guest mappings */ + + asm volatile("ptesync": : :"memory"); + /* + * now flush guest entries by passing PRS = 1 and LPID != 0 + */ + asm volatile(PPC_TLBIE_5(%0, %4, %3, %2, %1) + : : "r"(rb), "i"(r), "i"(1), "i"(ric), "r"(rs) : "memory"); + /* + * now flush host entires by passing PRS = 0 and LPID == 0 + */ + asm volatile(PPC_TLBIE_5(%0, %4, %3, %2, %1) + : : "r"(rb), "i"(r), "i"(prs), "i"(ric), "r"(0) : "memory"); + asm volatile("eieio; tlbsync; ptesync": : :"memory"); +} |