linux/include/asm-s390/pgalloc.h

161 lines
4.2 KiB
C
Raw Normal View History

/*
* include/asm-s390/pgalloc.h
*
* S390 version
* Copyright (C) 1999,2000 IBM Deutschland Entwicklung GmbH, IBM Corporation
* Author(s): Hartmut Penner (hp@de.ibm.com)
* Martin Schwidefsky (schwidefsky@de.ibm.com)
*
* Derived from "include/asm-i386/pgalloc.h"
* Copyright (C) 1994 Linus Torvalds
*/
#ifndef _S390_PGALLOC_H
#define _S390_PGALLOC_H
#include <linux/threads.h>
#include <linux/gfp.h>
#include <linux/mm.h>
#define check_pgt_cache() do {} while (0)
unsigned long *crst_table_alloc(struct mm_struct *, int);
void crst_table_free(unsigned long *);
unsigned long *page_table_alloc(int);
void page_table_free(unsigned long *);
static inline void clear_table(unsigned long *s, unsigned long val, size_t n)
{
*s = val;
n = (n / 256) - 1;
asm volatile(
#ifdef CONFIG_64BIT
" mvc 8(248,%0),0(%0)\n"
#else
" mvc 4(252,%0),0(%0)\n"
#endif
"0: mvc 256(256,%0),0(%0)\n"
" la %0,256(%0)\n"
" brct %1,0b\n"
: "+a" (s), "+d" (n));
}
static inline void crst_table_init(unsigned long *crst, unsigned long entry)
{
clear_table(crst, entry, sizeof(unsigned long)*2048);
crst = get_shadow_table(crst);
if (crst)
clear_table(crst, entry, sizeof(unsigned long)*2048);
}
#ifndef __s390x__
static inline unsigned long pgd_entry_type(struct mm_struct *mm)
{
return _SEGMENT_ENTRY_EMPTY;
}
#define pud_alloc_one(mm,address) ({ BUG(); ((pud_t *)2); })
#define pud_free(mm, x) do { } while (0)
#define pmd_alloc_one(mm,address) ({ BUG(); ((pmd_t *)2); })
#define pmd_free(mm, x) do { } while (0)
#define pgd_populate(mm, pgd, pud) BUG()
#define pgd_populate_kernel(mm, pgd, pud) BUG()
#define pud_populate(mm, pud, pmd) BUG()
#define pud_populate_kernel(mm, pud, pmd) BUG()
#else /* __s390x__ */
static inline unsigned long pgd_entry_type(struct mm_struct *mm)
{
return _REGION3_ENTRY_EMPTY;
}
#define pud_alloc_one(mm,address) ({ BUG(); ((pud_t *)2); })
#define pud_free(mm, x) do { } while (0)
static inline pmd_t *pmd_alloc_one(struct mm_struct *mm, unsigned long vmaddr)
{
unsigned long *crst = crst_table_alloc(mm, s390_noexec);
if (crst)
crst_table_init(crst, _SEGMENT_ENTRY_EMPTY);
return (pmd_t *) crst;
}
#define pmd_free(mm, pmd) crst_table_free((unsigned long *)pmd)
#define pgd_populate(mm, pgd, pud) BUG()
#define pgd_populate_kernel(mm, pgd, pud) BUG()
static inline void pud_populate_kernel(struct mm_struct *mm,
pud_t *pud, pmd_t *pmd)
{
pud_val(*pud) = _REGION3_ENTRY | __pa(pmd);
}
static inline void pud_populate(struct mm_struct *mm, pud_t *pud, pmd_t *pmd)
[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 21:18:17 +01:00
{
pud_t *shadow_pud = get_shadow_table(pud);
pmd_t *shadow_pmd = get_shadow_table(pmd);
[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 21:18:17 +01:00
if (shadow_pud && shadow_pmd)
pud_populate_kernel(mm, shadow_pud, shadow_pmd);
pud_populate_kernel(mm, pud, pmd);
[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 21:18:17 +01:00
}
#endif /* __s390x__ */
static inline pgd_t *pgd_alloc(struct mm_struct *mm)
{
unsigned long *crst = crst_table_alloc(mm, s390_noexec);
if (crst)
crst_table_init(crst, pgd_entry_type(mm));
return (pgd_t *) crst;
}
#define pgd_free(mm, pgd) crst_table_free((unsigned long *) pgd)
static inline void
pmd_populate_kernel(struct mm_struct *mm, pmd_t *pmd, pte_t *pte)
{
#ifndef __s390x__
pmd_val(pmd[0]) = _SEGMENT_ENTRY + __pa(pte);
pmd_val(pmd[1]) = _SEGMENT_ENTRY + __pa(pte+256);
pmd_val(pmd[2]) = _SEGMENT_ENTRY + __pa(pte+512);
pmd_val(pmd[3]) = _SEGMENT_ENTRY + __pa(pte+768);
#else /* __s390x__ */
pmd_val(*pmd) = _SEGMENT_ENTRY + __pa(pte);
pmd_val1(*pmd) = _SEGMENT_ENTRY + __pa(pte+256);
#endif /* __s390x__ */
}
static inline void
CONFIG_HIGHPTE vs. sub-page page tables. Background: I've implemented 1K/2K page tables for s390. These sub-page page tables are required to properly support the s390 virtualization instruction with KVM. The SIE instruction requires that the page tables have 256 page table entries (pte) followed by 256 page status table entries (pgste). The pgstes are only required if the process is using the SIE instruction. The pgstes are updated by the hardware and by the hypervisor for a number of reasons, one of them is dirty and reference bit tracking. To avoid wasting memory the standard pte table allocation should return 1K/2K (31/64 bit) and 2K/4K if the process is using SIE. Problem: Page size on s390 is 4K, page table size is 1K or 2K. That means the s390 version for pte_alloc_one cannot return a pointer to a struct page. Trouble is that with the CONFIG_HIGHPTE feature on x86 pte_alloc_one cannot return a pointer to a pte either, since that would require more than 32 bit for the return value of pte_alloc_one (and the pte * would not be accessible since its not kmapped). Solution: The only solution I found to this dilemma is a new typedef: a pgtable_t. For s390 pgtable_t will be a (pte *) - to be introduced with a later patch. For everybody else it will be a (struct page *). The additional problem with the initialization of the ptl lock and the NR_PAGETABLE accounting is solved with a constructor pgtable_page_ctor and a destructor pgtable_page_dtor. The page table allocation and free functions need to call these two whenever a page table page is allocated or freed. pmd_populate will get a pgtable_t instead of a struct page pointer. To get the pgtable_t back from a pmd entry that has been installed with pmd_populate a new function pmd_pgtable is added. It replaces the pmd_page call in free_pte_range and apply_to_pte_range. Signed-off-by: Martin Schwidefsky <schwidefsky@de.ibm.com> Cc: <linux-arch@vger.kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-02-08 13:22:04 +01:00
pmd_populate(struct mm_struct *mm, pmd_t *pmd, pgtable_t page)
{
[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 21:18:17 +01:00
pte_t *pte = (pte_t *)page_to_phys(page);
pmd_t *shadow_pmd = get_shadow_table(pmd);
[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 21:18:17 +01:00
pte_t *shadow_pte = get_shadow_pte(pte);
pmd_populate_kernel(mm, pmd, pte);
if (shadow_pmd && shadow_pte)
pmd_populate_kernel(mm, shadow_pmd, shadow_pte);
}
CONFIG_HIGHPTE vs. sub-page page tables. Background: I've implemented 1K/2K page tables for s390. These sub-page page tables are required to properly support the s390 virtualization instruction with KVM. The SIE instruction requires that the page tables have 256 page table entries (pte) followed by 256 page status table entries (pgste). The pgstes are only required if the process is using the SIE instruction. The pgstes are updated by the hardware and by the hypervisor for a number of reasons, one of them is dirty and reference bit tracking. To avoid wasting memory the standard pte table allocation should return 1K/2K (31/64 bit) and 2K/4K if the process is using SIE. Problem: Page size on s390 is 4K, page table size is 1K or 2K. That means the s390 version for pte_alloc_one cannot return a pointer to a struct page. Trouble is that with the CONFIG_HIGHPTE feature on x86 pte_alloc_one cannot return a pointer to a pte either, since that would require more than 32 bit for the return value of pte_alloc_one (and the pte * would not be accessible since its not kmapped). Solution: The only solution I found to this dilemma is a new typedef: a pgtable_t. For s390 pgtable_t will be a (pte *) - to be introduced with a later patch. For everybody else it will be a (struct page *). The additional problem with the initialization of the ptl lock and the NR_PAGETABLE accounting is solved with a constructor pgtable_page_ctor and a destructor pgtable_page_dtor. The page table allocation and free functions need to call these two whenever a page table page is allocated or freed. pmd_populate will get a pgtable_t instead of a struct page pointer. To get the pgtable_t back from a pmd entry that has been installed with pmd_populate a new function pmd_pgtable is added. It replaces the pmd_page call in free_pte_range and apply_to_pte_range. Signed-off-by: Martin Schwidefsky <schwidefsky@de.ibm.com> Cc: <linux-arch@vger.kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-02-08 13:22:04 +01:00
#define pmd_pgtable(pmd) pmd_page(pmd)
/*
* page table entry allocation/free routines.
*/
#define pte_alloc_one_kernel(mm, vmaddr) \
((pte_t *) page_table_alloc(s390_noexec))
#define pte_alloc_one(mm, vmaddr) \
virt_to_page(page_table_alloc(s390_noexec))
#define pte_free_kernel(mm, pte) \
page_table_free((unsigned long *) pte)
#define pte_free(mm, pte) \
page_table_free((unsigned long *) page_to_phys((struct page *) pte))
#endif /* _S390_PGALLOC_H */