diff options
Diffstat (limited to 'arch/powerpc/mm/pgtable-radix.c')
| -rw-r--r-- | arch/powerpc/mm/pgtable-radix.c | 67 |
1 files changed, 58 insertions, 9 deletions
diff --git a/arch/powerpc/mm/pgtable-radix.c b/arch/powerpc/mm/pgtable-radix.c index 5cc50d47ce3f..39c252b54d16 100644 --- a/arch/powerpc/mm/pgtable-radix.c +++ b/arch/powerpc/mm/pgtable-radix.c @@ -8,10 +8,15 @@ * as published by the Free Software Foundation; either version * 2 of the License, or (at your option) any later version. */ + +#define pr_fmt(fmt) "radix-mmu: " fmt + +#include <linux/kernel.h> #include <linux/sched/mm.h> #include <linux/memblock.h> #include <linux/of_fdt.h> #include <linux/mm.h> +#include <linux/string_helpers.h> #include <asm/pgtable.h> #include <asm/pgalloc.h> @@ -25,12 +30,19 @@ #include <trace/events/thp.h> +unsigned int mmu_pid_bits; +unsigned int mmu_base_pid; + static int native_register_process_table(unsigned long base, unsigned long pg_sz, unsigned long table_size) { - unsigned long patb1 = base | table_size | PATB_GR; + unsigned long patb0, patb1; + + patb0 = be64_to_cpu(partition_tb[0].patb0); + patb1 = base | table_size | PATB_GR; + + mmu_partition_table_set_entry(0, patb0, patb1); - partition_tb->patb1 = cpu_to_be64(patb1); return 0; } @@ -176,10 +188,14 @@ static inline void __meminit print_mapping(unsigned long start, unsigned long end, unsigned long size) { + char buf[10]; + if (end <= start) return; - pr_info("Mapped range 0x%lx - 0x%lx with 0x%lx\n", start, end, size); + string_get_size(size, 1, STRING_UNITS_2, buf, sizeof(buf)); + + pr_info("Mapped 0x%016lx-0x%016lx with %s pages\n", start, end, buf); } static int __meminit create_physical_mapping(unsigned long start, @@ -261,11 +277,34 @@ static void __init radix_init_pgtable(void) for_each_memblock(memory, reg) WARN_ON(create_physical_mapping(reg->base, reg->base + reg->size)); + + /* Find out how many PID bits are supported */ + if (cpu_has_feature(CPU_FTR_HVMODE)) { + if (!mmu_pid_bits) + mmu_pid_bits = 20; +#ifdef CONFIG_KVM_BOOK3S_HV_POSSIBLE + /* + * When KVM is possible, we only use the top half of the + * PID space to avoid collisions between host and guest PIDs + * which can cause problems due to prefetch when exiting the + * guest with AIL=3 + */ + mmu_base_pid = 1 << (mmu_pid_bits - 1); +#else + mmu_base_pid = 1; +#endif + } else { + /* The guest uses the bottom half of the PID space */ + if (!mmu_pid_bits) + mmu_pid_bits = 19; + mmu_base_pid = 1; + } + /* * Allocate Partition table and process table for the * host. */ - BUILD_BUG_ON_MSG((PRTB_SIZE_SHIFT > 36), "Process table size too large."); + BUG_ON(PRTB_SIZE_SHIFT > 36); process_tb = early_alloc_pgtable(1UL << PRTB_SIZE_SHIFT); /* * Fill in the process table. @@ -339,6 +378,12 @@ static int __init radix_dt_scan_page_sizes(unsigned long node, if (type == NULL || strcmp(type, "cpu") != 0) return 0; + /* Find MMU PID size */ + prop = of_get_flat_dt_prop(node, "ibm,mmu-pid-bits", &size); + if (prop && size == 4) + mmu_pid_bits = be32_to_cpup(prop); + + /* Grab page size encodings */ prop = of_get_flat_dt_prop(node, "ibm,processor-radix-AP-encodings", &size); if (!prop) return 0; @@ -494,6 +539,7 @@ void __init radix__early_init_mmu(void) __kernel_virt_size = RADIX_KERN_VIRT_SIZE; __vmalloc_start = RADIX_VMALLOC_START; __vmalloc_end = RADIX_VMALLOC_END; + __kernel_io_start = RADIX_KERN_IO_START; vmemmap = (struct page *)RADIX_VMEMMAP_BASE; ioremap_bot = IOREMAP_BASE; @@ -804,9 +850,12 @@ pmd_t radix__pmdp_collapse_flush(struct vm_area_struct *vma, unsigned long addre */ pmd = *pmdp; pmd_clear(pmdp); + /*FIXME!! Verify whether we need this kick below */ - kick_all_cpus_sync(); - flush_tlb_range(vma, address, address + HPAGE_PMD_SIZE); + serialize_against_pte_lookup(vma->vm_mm); + + radix__flush_tlb_collapsed_pmd(vma->vm_mm, address); + return pmd; } @@ -865,16 +914,16 @@ pmd_t radix__pmdp_huge_get_and_clear(struct mm_struct *mm, old = radix__pmd_hugepage_update(mm, addr, pmdp, ~0UL, 0); old_pmd = __pmd(old); /* - * Serialize against find_linux_pte_or_hugepte which does lock-less + * Serialize against find_current_mm_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_linux_pte_or_hugepage to finish. + * find_current_mm_pte to finish. */ - kick_all_cpus_sync(); + serialize_against_pte_lookup(mm); return old_pmd; } |
