linux/arch/s390/mm/vmem.c

432 lines
9.8 KiB
C
Raw Normal View History

/*
* 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/module.h>
#include <linux/list.h>
#include <linux/hugetlb.h>
include cleanup: Update gfp.h and slab.h includes to prepare for breaking implicit slab.h inclusion from percpu.h percpu.h is included by sched.h and module.h and thus ends up being included when building most .c files. percpu.h includes slab.h which in turn includes gfp.h making everything defined by the two files universally available and complicating inclusion dependencies. percpu.h -> slab.h dependency is about to be removed. Prepare for this change by updating users of gfp and slab facilities include those headers directly instead of assuming availability. As this conversion needs to touch large number of source files, the following script is used as the basis of conversion. http://userweb.kernel.org/~tj/misc/slabh-sweep.py The script does the followings. * Scan files for gfp and slab usages and update includes such that only the necessary includes are there. ie. if only gfp is used, gfp.h, if slab is used, slab.h. * When the script inserts a new include, it looks at the include blocks and try to put the new include such that its order conforms to its surrounding. It's put in the include block which contains core kernel includes, in the same order that the rest are ordered - alphabetical, Christmas tree, rev-Xmas-tree or at the end if there doesn't seem to be any matching order. * If the script can't find a place to put a new include (mostly because the file doesn't have fitting include block), it prints out an error message indicating which .h file needs to be added to the file. The conversion was done in the following steps. 1. The initial automatic conversion of all .c files updated slightly over 4000 files, deleting around 700 includes and adding ~480 gfp.h and ~3000 slab.h inclusions. The script emitted errors for ~400 files. 2. Each error was manually checked. Some didn't need the inclusion, some needed manual addition while adding it to implementation .h or embedding .c file was more appropriate for others. This step added inclusions to around 150 files. 3. The script was run again and the output was compared to the edits from #2 to make sure no file was left behind. 4. Several build tests were done and a couple of problems were fixed. e.g. lib/decompress_*.c used malloc/free() wrappers around slab APIs requiring slab.h to be added manually. 5. The script was run on all .h files but without automatically editing them as sprinkling gfp.h and slab.h inclusions around .h files could easily lead to inclusion dependency hell. Most gfp.h inclusion directives were ignored as stuff from gfp.h was usually wildly available and often used in preprocessor macros. Each slab.h inclusion directive was examined and added manually as necessary. 6. percpu.h was updated not to include slab.h. 7. Build test were done on the following configurations and failures were fixed. CONFIG_GCOV_KERNEL was turned off for all tests (as my distributed build env didn't work with gcov compiles) and a few more options had to be turned off depending on archs to make things build (like ipr on powerpc/64 which failed due to missing writeq). * x86 and x86_64 UP and SMP allmodconfig and a custom test config. * powerpc and powerpc64 SMP allmodconfig * sparc and sparc64 SMP allmodconfig * ia64 SMP allmodconfig * s390 SMP allmodconfig * alpha SMP allmodconfig * um on x86_64 SMP allmodconfig 8. percpu.h modifications were reverted so that it could be applied as a separate patch and serve as bisection point. Given the fact that I had only a couple of failures from tests on step 6, I'm fairly confident about the coverage of this conversion patch. If there is a breakage, it's likely to be something in one of the arch headers which should be easily discoverable easily on most builds of the specific arch. Signed-off-by: Tejun Heo <tj@kernel.org> Guess-its-ok-by: Christoph Lameter <cl@linux-foundation.org> Cc: Ingo Molnar <mingo@redhat.com> Cc: Lee Schermerhorn <Lee.Schermerhorn@hp.com>
2010-03-24 08:04:11 +00:00
#include <linux/slab.h>
#include <asm/pgalloc.h>
#include <asm/pgtable.h>
#include <asm/setup.h>
#include <asm/tlbflush.h>
#include <asm/sections.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)
{
if (slab_is_available())
return (void *)__get_free_pages(GFP_KERNEL, order);
return alloc_bootmem_pages((1 << order) * PAGE_SIZE);
}
static inline pud_t *vmem_pud_alloc(void)
{
pud_t *pud = NULL;
#ifdef CONFIG_64BIT
pud = vmem_alloc_pages(2);
if (!pud)
return NULL;
clear_table((unsigned long *) pud, _REGION3_ENTRY_EMPTY, PAGE_SIZE * 4);
#endif
return pud;
}
static inline pmd_t *vmem_pmd_alloc(void)
{
pmd_t *pmd = NULL;
#ifdef CONFIG_64BIT
pmd = vmem_alloc_pages(2);
if (!pmd)
return NULL;
clear_table((unsigned long *) pmd, _SEGMENT_ENTRY_EMPTY, PAGE_SIZE * 4);
#endif
return pmd;
}
static pte_t __ref *vmem_pte_alloc(unsigned long address)
{
pte_t *pte;
if (slab_is_available())
pte = (pte_t *) page_table_alloc(&init_mm, address);
else
pte = alloc_bootmem(PTRS_PER_PTE * sizeof(pte_t));
if (!pte)
return NULL;
clear_table((unsigned long *) pte, _PAGE_TYPE_EMPTY,
PTRS_PER_PTE * sizeof(pte_t));
return pte;
}
/*
* Add a physical memory range to the 1:1 mapping.
*/
static int vmem_add_mem(unsigned long start, unsigned long size, int ro)
{
unsigned long end = start + size;
unsigned long address = start;
pgd_t *pg_dir;
pud_t *pu_dir;
pmd_t *pm_dir;
pte_t *pt_dir;
pte_t pte;
int ret = -ENOMEM;
while (address < end) {
pte = mk_pte_phys(address, __pgprot(ro ? _PAGE_RO : 0));
pg_dir = pgd_offset_k(address);
if (pgd_none(*pg_dir)) {
pu_dir = vmem_pud_alloc();
if (!pu_dir)
goto out;
pgd_populate(&init_mm, pg_dir, pu_dir);
}
pu_dir = pud_offset(pg_dir, address);
#if defined(CONFIG_64BIT) && !defined(CONFIG_DEBUG_PAGEALLOC)
if (MACHINE_HAS_EDAT2 && pud_none(*pu_dir) && address &&
!(address & ~PUD_MASK) && (address + PUD_SIZE <= end)) {
pte_val(pte) |= _REGION3_ENTRY_LARGE;
pte_val(pte) |= _REGION_ENTRY_TYPE_R3;
pud_val(*pu_dir) = pte_val(pte);
address += PUD_SIZE;
continue;
}
#endif
if (pud_none(*pu_dir)) {
pm_dir = vmem_pmd_alloc();
if (!pm_dir)
goto out;
pud_populate(&init_mm, pu_dir, pm_dir);
}
pm_dir = pmd_offset(pu_dir, address);
#if defined(CONFIG_64BIT) && !defined(CONFIG_DEBUG_PAGEALLOC)
if (MACHINE_HAS_EDAT1 && pmd_none(*pm_dir) && address &&
!(address & ~PMD_MASK) && (address + PMD_SIZE <= end)) {
pte_val(pte) |= _SEGMENT_ENTRY_LARGE;
pmd_val(*pm_dir) = pte_val(pte);
address += PMD_SIZE;
continue;
}
#endif
if (pmd_none(*pm_dir)) {
pt_dir = vmem_pte_alloc(address);
if (!pt_dir)
goto out;
pmd_populate(&init_mm, pm_dir, pt_dir);
}
pt_dir = pte_offset_kernel(pm_dir, address);
[S390] noexec protection This provides a noexec protection on s390 hardware. Our hardware does not have any bits left in the pte for a hw noexec bit, so this is a different approach using shadow page tables and a special addressing mode that allows separate address spaces for code and data. As a special feature of our "secondary-space" addressing mode, separate page tables can be specified for the translation of data addresses (storage operands) and instruction addresses. The shadow page table is used for the instruction addresses and the standard page table for the data addresses. The shadow page table is linked to the standard page table by a pointer in page->lru.next of the struct page corresponding to the page that contains the standard page table (since page->private is not really private with the pte_lock and the page table pages are not in the LRU list). Depending on the software bits of a pte, it is either inserted into both page tables or just into the standard (data) page table. Pages of a vma that does not have the VM_EXEC bit set get mapped only in the data address space. Any try to execute code on such a page will cause a page translation exception. The standard reaction to this is a SIGSEGV with two exceptions: the two system call opcodes 0x0a77 (sys_sigreturn) and 0x0aad (sys_rt_sigreturn) are allowed. They are stored by the kernel to the signal stack frame. Unfortunately, the signal return mechanism cannot be modified to use an SA_RESTORER because the exception unwinding code depends on the system call opcode stored behind the signal stack frame. This feature requires that user space is executed in secondary-space mode and the kernel in home-space mode, which means that the addressing modes need to be switched and that the noexec protection only works for user space. After switching the addressing modes, we cannot use the mvcp/mvcs instructions anymore to copy between kernel and user space. A new mvcos instruction has been added to the z9 EC/BC hardware which allows to copy between arbitrary address spaces, but on older hardware the page tables need to be walked manually. Signed-off-by: Gerald Schaefer <geraldsc@de.ibm.com> Signed-off-by: Martin Schwidefsky <schwidefsky@de.ibm.com>
2007-02-05 20:18:17 +00:00
*pt_dir = pte;
address += PAGE_SIZE;
}
ret = 0;
out:
flush_tlb_kernel_range(start, end);
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 end = start + size;
unsigned long address = start;
pgd_t *pg_dir;
pud_t *pu_dir;
pmd_t *pm_dir;
pte_t *pt_dir;
pte_t pte;
pte_val(pte) = _PAGE_TYPE_EMPTY;
while (address < end) {
pg_dir = pgd_offset_k(address);
if (pgd_none(*pg_dir)) {
address += PGDIR_SIZE;
continue;
}
pu_dir = pud_offset(pg_dir, address);
if (pud_none(*pu_dir)) {
address += PUD_SIZE;
continue;
}
if (pud_large(*pu_dir)) {
pud_clear(pu_dir);
address += PUD_SIZE;
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;
continue;
}
pt_dir = pte_offset_kernel(pm_dir, address);
[S390] noexec protection This provides a noexec protection on s390 hardware. Our hardware does not have any bits left in the pte for a hw noexec bit, so this is a different approach using shadow page tables and a special addressing mode that allows separate address spaces for code and data. As a special feature of our "secondary-space" addressing mode, separate page tables can be specified for the translation of data addresses (storage operands) and instruction addresses. The shadow page table is used for the instruction addresses and the standard page table for the data addresses. The shadow page table is linked to the standard page table by a pointer in page->lru.next of the struct page corresponding to the page that contains the standard page table (since page->private is not really private with the pte_lock and the page table pages are not in the LRU list). Depending on the software bits of a pte, it is either inserted into both page tables or just into the standard (data) page table. Pages of a vma that does not have the VM_EXEC bit set get mapped only in the data address space. Any try to execute code on such a page will cause a page translation exception. The standard reaction to this is a SIGSEGV with two exceptions: the two system call opcodes 0x0a77 (sys_sigreturn) and 0x0aad (sys_rt_sigreturn) are allowed. They are stored by the kernel to the signal stack frame. Unfortunately, the signal return mechanism cannot be modified to use an SA_RESTORER because the exception unwinding code depends on the system call opcode stored behind the signal stack frame. This feature requires that user space is executed in secondary-space mode and the kernel in home-space mode, which means that the addressing modes need to be switched and that the noexec protection only works for user space. After switching the addressing modes, we cannot use the mvcp/mvcs instructions anymore to copy between kernel and user space. A new mvcos instruction has been added to the z9 EC/BC hardware which allows to copy between arbitrary address spaces, but on older hardware the page tables need to be walked manually. Signed-off-by: Gerald Schaefer <geraldsc@de.ibm.com> Signed-off-by: Martin Schwidefsky <schwidefsky@de.ibm.com>
2007-02-05 20:18:17 +00:00
*pt_dir = pte;
address += PAGE_SIZE;
}
flush_tlb_kernel_range(start, end);
}
/*
* Add a backed mem_map array to the virtual mem_map array.
*/
int __meminit vmemmap_populate(struct page *start, unsigned long nr, int node)
{
unsigned long address, start_addr, end_addr;
pgd_t *pg_dir;
pud_t *pu_dir;
pmd_t *pm_dir;
pte_t *pt_dir;
pte_t pte;
int ret = -ENOMEM;
start_addr = (unsigned long) start;
end_addr = (unsigned long) (start + nr);
for (address = start_addr; address < end_addr;) {
pg_dir = pgd_offset_k(address);
if (pgd_none(*pg_dir)) {
pu_dir = vmem_pud_alloc();
if (!pu_dir)
goto out;
pgd_populate(&init_mm, pg_dir, pu_dir);
}
pu_dir = pud_offset(pg_dir, address);
if (pud_none(*pu_dir)) {
pm_dir = vmem_pmd_alloc();
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)) {
#ifdef CONFIG_64BIT
/* 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;
pte = mk_pte_phys(__pa(new_page), PAGE_RW);
pte_val(pte) |= _SEGMENT_ENTRY_LARGE;
pmd_val(*pm_dir) = pte_val(pte);
address = (address + PMD_SIZE) & PMD_MASK;
continue;
}
#endif
pt_dir = vmem_pte_alloc(address);
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)) {
unsigned long new_page;
new_page =__pa(vmem_alloc_pages(0));
if (!new_page)
goto out;
pte = pfn_pte(new_page >> PAGE_SHIFT, PAGE_KERNEL);
[S390] noexec protection This provides a noexec protection on s390 hardware. Our hardware does not have any bits left in the pte for a hw noexec bit, so this is a different approach using shadow page tables and a special addressing mode that allows separate address spaces for code and data. As a special feature of our "secondary-space" addressing mode, separate page tables can be specified for the translation of data addresses (storage operands) and instruction addresses. The shadow page table is used for the instruction addresses and the standard page table for the data addresses. The shadow page table is linked to the standard page table by a pointer in page->lru.next of the struct page corresponding to the page that contains the standard page table (since page->private is not really private with the pte_lock and the page table pages are not in the LRU list). Depending on the software bits of a pte, it is either inserted into both page tables or just into the standard (data) page table. Pages of a vma that does not have the VM_EXEC bit set get mapped only in the data address space. Any try to execute code on such a page will cause a page translation exception. The standard reaction to this is a SIGSEGV with two exceptions: the two system call opcodes 0x0a77 (sys_sigreturn) and 0x0aad (sys_rt_sigreturn) are allowed. They are stored by the kernel to the signal stack frame. Unfortunately, the signal return mechanism cannot be modified to use an SA_RESTORER because the exception unwinding code depends on the system call opcode stored behind the signal stack frame. This feature requires that user space is executed in secondary-space mode and the kernel in home-space mode, which means that the addressing modes need to be switched and that the noexec protection only works for user space. After switching the addressing modes, we cannot use the mvcp/mvcs instructions anymore to copy between kernel and user space. A new mvcos instruction has been added to the z9 EC/BC hardware which allows to copy between arbitrary address spaces, but on older hardware the page tables need to be walked manually. Signed-off-by: Gerald Schaefer <geraldsc@de.ibm.com> Signed-off-by: Martin Schwidefsky <schwidefsky@de.ibm.com>
2007-02-05 20:18:17 +00:00
*pt_dir = pte;
}
address += PAGE_SIZE;
}
memset(start, 0, nr * sizeof(struct page));
ret = 0;
out:
flush_tlb_kernel_range(start_addr, end_addr);
return ret;
}
/*
* 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, 0);
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)
{
unsigned long ro_start, ro_end;
unsigned long start, end;
int i;
ro_start = PFN_ALIGN((unsigned long)&_stext);
ro_end = (unsigned long)&_eshared & PAGE_MASK;
for (i = 0; i < MEMORY_CHUNKS && memory_chunk[i].size > 0; i++) {
if (memory_chunk[i].type == CHUNK_CRASHK ||
memory_chunk[i].type == CHUNK_OLDMEM)
continue;
start = memory_chunk[i].addr;
end = memory_chunk[i].addr + memory_chunk[i].size;
if (start >= ro_end || end <= ro_start)
vmem_add_mem(start, end - start, 0);
else if (start >= ro_start && end <= ro_end)
vmem_add_mem(start, end - start, 1);
else if (start >= ro_start) {
vmem_add_mem(start, ro_end - start, 1);
vmem_add_mem(ro_end, end - ro_end, 0);
} else if (end < ro_end) {
vmem_add_mem(start, ro_start - start, 0);
vmem_add_mem(ro_start, end - ro_start, 1);
} else {
vmem_add_mem(start, ro_start - start, 0);
vmem_add_mem(ro_start, ro_end - ro_start, 1);
vmem_add_mem(ro_end, end - ro_end, 0);
}
}
}
/*
* Convert memory chunk array to a memory segment list so there is a single
* list that contains both r/w memory and shared memory segments.
*/
static int __init vmem_convert_memory_chunk(void)
{
struct memory_segment *seg;
int i;
mutex_lock(&vmem_mutex);
for (i = 0; i < MEMORY_CHUNKS; i++) {
if (!memory_chunk[i].size)
continue;
if (memory_chunk[i].type == CHUNK_CRASHK ||
memory_chunk[i].type == CHUNK_OLDMEM)
continue;
seg = kzalloc(sizeof(*seg), GFP_KERNEL);
if (!seg)
panic("Out of memory...\n");
seg->start = memory_chunk[i].addr;
seg->size = memory_chunk[i].size;
insert_memory_segment(seg);
}
mutex_unlock(&vmem_mutex);
return 0;
}
core_initcall(vmem_convert_memory_chunk);