linux/arch/s390/mm/vmem.c
Linus Torvalds d60a540ac5 Merge branch 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/s390/linux
Pull s390 updates from Heiko Carstens:
 "Since Martin is on vacation you get the s390 pull request for the
  v4.15 merge window this time from me.

  Besides a lot of cleanups and bug fixes these are the most important
  changes:

   - a new regset for runtime instrumentation registers

   - hardware accelerated AES-GCM support for the aes_s390 module

   - support for the new CEX6S crypto cards

   - support for FORTIFY_SOURCE

   - addition of missing z13 and new z14 instructions to the in-kernel
     disassembler

   - generate opcode tables for the in-kernel disassembler out of a
     simple text file instead of having to manually maintain those
     tables

   - fast memset16, memset32 and memset64 implementations

   - removal of named saved segment support

   - hardware counter support for z14

   - queued spinlocks and queued rwlocks implementations for s390

   - use the stack_depth tracking feature for s390 BPF JIT

   - a new s390_sthyi system call which emulates the sthyi (store
     hypervisor information) instruction

   - removal of the old KVM virtio transport

   - an s390 specific CPU alternatives implementation which is used in
     the new spinlock code"

* 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/s390/linux: (88 commits)
  MAINTAINERS: add virtio-ccw.h to virtio/s390 section
  s390/noexec: execute kexec datamover without DAT
  s390: fix transactional execution control register handling
  s390/bpf: take advantage of stack_depth tracking
  s390: simplify transactional execution elf hwcap handling
  s390/zcrypt: Rework struct ap_qact_ap_info.
  s390/virtio: remove unused header file kvm_virtio.h
  s390: avoid undefined behaviour
  s390/disassembler: generate opcode tables from text file
  s390/disassembler: remove insn_to_mnemonic()
  s390/dasd: avoid calling do_gettimeofday()
  s390: vfio-ccw: Do not attempt to free no-op, test and tic cda.
  s390: remove named saved segment support
  s390/archrandom: Reconsider s390 arch random implementation
  s390/pci: do not require AIS facility
  s390/qdio: sanitize put_indicator
  s390/qdio: use atomic_cmpxchg
  s390/nmi: avoid using long-displacement facility
  s390: pass endianness info to sparse
  s390/decompressor: remove informational messages
  ...
2017-11-13 11:47:01 -08:00

442 lines
10 KiB
C

// SPDX-License-Identifier: GPL-2.0
/*
* Copyright IBM Corp. 2006
* Author(s): Heiko Carstens <heiko.carstens@de.ibm.com>
*/
#include <linux/bootmem.h>
#include <linux/pfn.h>
#include <linux/mm.h>
#include <linux/init.h>
#include <linux/list.h>
#include <linux/hugetlb.h>
#include <linux/slab.h>
#include <linux/memblock.h>
#include <asm/cacheflush.h>
#include <asm/pgalloc.h>
#include <asm/pgtable.h>
#include <asm/setup.h>
#include <asm/tlbflush.h>
#include <asm/sections.h>
#include <asm/set_memory.h>
static DEFINE_MUTEX(vmem_mutex);
struct memory_segment {
struct list_head list;
unsigned long start;
unsigned long size;
};
static LIST_HEAD(mem_segs);
static void __ref *vmem_alloc_pages(unsigned int order)
{
unsigned long size = PAGE_SIZE << order;
if (slab_is_available())
return (void *)__get_free_pages(GFP_KERNEL, order);
return (void *) memblock_alloc(size, size);
}
void *vmem_crst_alloc(unsigned long val)
{
unsigned long *table;
table = vmem_alloc_pages(CRST_ALLOC_ORDER);
if (table)
crst_table_init(table, val);
return table;
}
pte_t __ref *vmem_pte_alloc(void)
{
unsigned long size = PTRS_PER_PTE * sizeof(pte_t);
pte_t *pte;
if (slab_is_available())
pte = (pte_t *) page_table_alloc(&init_mm);
else
pte = (pte_t *) memblock_alloc(size, size);
if (!pte)
return NULL;
memset64((u64 *)pte, _PAGE_INVALID, PTRS_PER_PTE);
return pte;
}
/*
* Add a physical memory range to the 1:1 mapping.
*/
static int vmem_add_mem(unsigned long start, unsigned long size)
{
unsigned long pgt_prot, sgt_prot, r3_prot;
unsigned long pages4k, pages1m, pages2g;
unsigned long end = start + size;
unsigned long address = start;
pgd_t *pg_dir;
p4d_t *p4_dir;
pud_t *pu_dir;
pmd_t *pm_dir;
pte_t *pt_dir;
int ret = -ENOMEM;
pgt_prot = pgprot_val(PAGE_KERNEL);
sgt_prot = pgprot_val(SEGMENT_KERNEL);
r3_prot = pgprot_val(REGION3_KERNEL);
if (!MACHINE_HAS_NX) {
pgt_prot &= ~_PAGE_NOEXEC;
sgt_prot &= ~_SEGMENT_ENTRY_NOEXEC;
r3_prot &= ~_REGION_ENTRY_NOEXEC;
}
pages4k = pages1m = pages2g = 0;
while (address < end) {
pg_dir = pgd_offset_k(address);
if (pgd_none(*pg_dir)) {
p4_dir = vmem_crst_alloc(_REGION2_ENTRY_EMPTY);
if (!p4_dir)
goto out;
pgd_populate(&init_mm, pg_dir, p4_dir);
}
p4_dir = p4d_offset(pg_dir, address);
if (p4d_none(*p4_dir)) {
pu_dir = vmem_crst_alloc(_REGION3_ENTRY_EMPTY);
if (!pu_dir)
goto out;
p4d_populate(&init_mm, p4_dir, pu_dir);
}
pu_dir = pud_offset(p4_dir, address);
if (MACHINE_HAS_EDAT2 && pud_none(*pu_dir) && address &&
!(address & ~PUD_MASK) && (address + PUD_SIZE <= end) &&
!debug_pagealloc_enabled()) {
pud_val(*pu_dir) = address | r3_prot;
address += PUD_SIZE;
pages2g++;
continue;
}
if (pud_none(*pu_dir)) {
pm_dir = vmem_crst_alloc(_SEGMENT_ENTRY_EMPTY);
if (!pm_dir)
goto out;
pud_populate(&init_mm, pu_dir, pm_dir);
}
pm_dir = pmd_offset(pu_dir, address);
if (MACHINE_HAS_EDAT1 && pmd_none(*pm_dir) && address &&
!(address & ~PMD_MASK) && (address + PMD_SIZE <= end) &&
!debug_pagealloc_enabled()) {
pmd_val(*pm_dir) = address | sgt_prot;
address += PMD_SIZE;
pages1m++;
continue;
}
if (pmd_none(*pm_dir)) {
pt_dir = vmem_pte_alloc();
if (!pt_dir)
goto out;
pmd_populate(&init_mm, pm_dir, pt_dir);
}
pt_dir = pte_offset_kernel(pm_dir, address);
pte_val(*pt_dir) = address | pgt_prot;
address += PAGE_SIZE;
pages4k++;
}
ret = 0;
out:
update_page_count(PG_DIRECT_MAP_4K, pages4k);
update_page_count(PG_DIRECT_MAP_1M, pages1m);
update_page_count(PG_DIRECT_MAP_2G, pages2g);
return ret;
}
/*
* Remove a physical memory range from the 1:1 mapping.
* Currently only invalidates page table entries.
*/
static void vmem_remove_range(unsigned long start, unsigned long size)
{
unsigned long pages4k, pages1m, pages2g;
unsigned long end = start + size;
unsigned long address = start;
pgd_t *pg_dir;
p4d_t *p4_dir;
pud_t *pu_dir;
pmd_t *pm_dir;
pte_t *pt_dir;
pages4k = pages1m = pages2g = 0;
while (address < end) {
pg_dir = pgd_offset_k(address);
if (pgd_none(*pg_dir)) {
address += PGDIR_SIZE;
continue;
}
p4_dir = p4d_offset(pg_dir, address);
if (p4d_none(*p4_dir)) {
address += P4D_SIZE;
continue;
}
pu_dir = pud_offset(p4_dir, address);
if (pud_none(*pu_dir)) {
address += PUD_SIZE;
continue;
}
if (pud_large(*pu_dir)) {
pud_clear(pu_dir);
address += PUD_SIZE;
pages2g++;
continue;
}
pm_dir = pmd_offset(pu_dir, address);
if (pmd_none(*pm_dir)) {
address += PMD_SIZE;
continue;
}
if (pmd_large(*pm_dir)) {
pmd_clear(pm_dir);
address += PMD_SIZE;
pages1m++;
continue;
}
pt_dir = pte_offset_kernel(pm_dir, address);
pte_clear(&init_mm, address, pt_dir);
address += PAGE_SIZE;
pages4k++;
}
flush_tlb_kernel_range(start, end);
update_page_count(PG_DIRECT_MAP_4K, -pages4k);
update_page_count(PG_DIRECT_MAP_1M, -pages1m);
update_page_count(PG_DIRECT_MAP_2G, -pages2g);
}
/*
* Add a backed mem_map array to the virtual mem_map array.
*/
int __meminit vmemmap_populate(unsigned long start, unsigned long end, int node)
{
unsigned long pgt_prot, sgt_prot;
unsigned long address = start;
pgd_t *pg_dir;
p4d_t *p4_dir;
pud_t *pu_dir;
pmd_t *pm_dir;
pte_t *pt_dir;
int ret = -ENOMEM;
pgt_prot = pgprot_val(PAGE_KERNEL);
sgt_prot = pgprot_val(SEGMENT_KERNEL);
if (!MACHINE_HAS_NX) {
pgt_prot &= ~_PAGE_NOEXEC;
sgt_prot &= ~_SEGMENT_ENTRY_NOEXEC;
}
for (address = start; address < end;) {
pg_dir = pgd_offset_k(address);
if (pgd_none(*pg_dir)) {
p4_dir = vmem_crst_alloc(_REGION2_ENTRY_EMPTY);
if (!p4_dir)
goto out;
pgd_populate(&init_mm, pg_dir, p4_dir);
}
p4_dir = p4d_offset(pg_dir, address);
if (p4d_none(*p4_dir)) {
pu_dir = vmem_crst_alloc(_REGION3_ENTRY_EMPTY);
if (!pu_dir)
goto out;
p4d_populate(&init_mm, p4_dir, pu_dir);
}
pu_dir = pud_offset(p4_dir, address);
if (pud_none(*pu_dir)) {
pm_dir = vmem_crst_alloc(_SEGMENT_ENTRY_EMPTY);
if (!pm_dir)
goto out;
pud_populate(&init_mm, pu_dir, pm_dir);
}
pm_dir = pmd_offset(pu_dir, address);
if (pmd_none(*pm_dir)) {
/* Use 1MB frames for vmemmap if available. We always
* use large frames even if they are only partially
* used.
* Otherwise we would have also page tables since
* vmemmap_populate gets called for each section
* separately. */
if (MACHINE_HAS_EDAT1) {
void *new_page;
new_page = vmemmap_alloc_block(PMD_SIZE, node);
if (!new_page)
goto out;
pmd_val(*pm_dir) = __pa(new_page) | sgt_prot;
address = (address + PMD_SIZE) & PMD_MASK;
continue;
}
pt_dir = vmem_pte_alloc();
if (!pt_dir)
goto out;
pmd_populate(&init_mm, pm_dir, pt_dir);
} else if (pmd_large(*pm_dir)) {
address = (address + PMD_SIZE) & PMD_MASK;
continue;
}
pt_dir = pte_offset_kernel(pm_dir, address);
if (pte_none(*pt_dir)) {
void *new_page;
new_page = vmemmap_alloc_block(PAGE_SIZE, node);
if (!new_page)
goto out;
pte_val(*pt_dir) = __pa(new_page) | pgt_prot;
}
address += PAGE_SIZE;
}
ret = 0;
out:
return ret;
}
void vmemmap_free(unsigned long start, unsigned long end)
{
}
/*
* Add memory segment to the segment list if it doesn't overlap with
* an already present segment.
*/
static int insert_memory_segment(struct memory_segment *seg)
{
struct memory_segment *tmp;
if (seg->start + seg->size > VMEM_MAX_PHYS ||
seg->start + seg->size < seg->start)
return -ERANGE;
list_for_each_entry(tmp, &mem_segs, list) {
if (seg->start >= tmp->start + tmp->size)
continue;
if (seg->start + seg->size <= tmp->start)
continue;
return -ENOSPC;
}
list_add(&seg->list, &mem_segs);
return 0;
}
/*
* Remove memory segment from the segment list.
*/
static void remove_memory_segment(struct memory_segment *seg)
{
list_del(&seg->list);
}
static void __remove_shared_memory(struct memory_segment *seg)
{
remove_memory_segment(seg);
vmem_remove_range(seg->start, seg->size);
}
int vmem_remove_mapping(unsigned long start, unsigned long size)
{
struct memory_segment *seg;
int ret;
mutex_lock(&vmem_mutex);
ret = -ENOENT;
list_for_each_entry(seg, &mem_segs, list) {
if (seg->start == start && seg->size == size)
break;
}
if (seg->start != start || seg->size != size)
goto out;
ret = 0;
__remove_shared_memory(seg);
kfree(seg);
out:
mutex_unlock(&vmem_mutex);
return ret;
}
int vmem_add_mapping(unsigned long start, unsigned long size)
{
struct memory_segment *seg;
int ret;
mutex_lock(&vmem_mutex);
ret = -ENOMEM;
seg = kzalloc(sizeof(*seg), GFP_KERNEL);
if (!seg)
goto out;
seg->start = start;
seg->size = size;
ret = insert_memory_segment(seg);
if (ret)
goto out_free;
ret = vmem_add_mem(start, size);
if (ret)
goto out_remove;
goto out;
out_remove:
__remove_shared_memory(seg);
out_free:
kfree(seg);
out:
mutex_unlock(&vmem_mutex);
return ret;
}
/*
* map whole physical memory to virtual memory (identity mapping)
* we reserve enough space in the vmalloc area for vmemmap to hotplug
* additional memory segments.
*/
void __init vmem_map_init(void)
{
struct memblock_region *reg;
for_each_memblock(memory, reg)
vmem_add_mem(reg->base, reg->size);
__set_memory((unsigned long)_stext,
(unsigned long)(_etext - _stext) >> PAGE_SHIFT,
SET_MEMORY_RO | SET_MEMORY_X);
__set_memory((unsigned long)_etext,
(unsigned long)(__end_rodata - _etext) >> PAGE_SHIFT,
SET_MEMORY_RO);
__set_memory((unsigned long)_sinittext,
(unsigned long)(_einittext - _sinittext) >> PAGE_SHIFT,
SET_MEMORY_RO | SET_MEMORY_X);
pr_info("Write protected kernel read-only data: %luk\n",
(unsigned long)(__end_rodata - _stext) >> 10);
}
/*
* Convert memblock.memory to a memory segment list so there is a single
* list that contains all memory segments.
*/
static int __init vmem_convert_memory_chunk(void)
{
struct memblock_region *reg;
struct memory_segment *seg;
mutex_lock(&vmem_mutex);
for_each_memblock(memory, reg) {
seg = kzalloc(sizeof(*seg), GFP_KERNEL);
if (!seg)
panic("Out of memory...\n");
seg->start = reg->base;
seg->size = reg->size;
insert_memory_segment(seg);
}
mutex_unlock(&vmem_mutex);
return 0;
}
core_initcall(vmem_convert_memory_chunk);