linux/arch/s390/include/asm/compat.h

252 lines
5.4 KiB
C
Raw Normal View History

#ifndef _ASM_S390X_COMPAT_H
#define _ASM_S390X_COMPAT_H
/*
* Architecture specific compatibility types
*/
#include <linux/types.h>
#include <linux/sched.h>
#include <linux/thread_info.h>
[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>
2007-02-06 04:18:17 +08:00
#define PSW32_MASK_PER 0x40000000UL
#define PSW32_MASK_DAT 0x04000000UL
#define PSW32_MASK_IO 0x02000000UL
#define PSW32_MASK_EXT 0x01000000UL
#define PSW32_MASK_KEY 0x00F00000UL
#define PSW32_MASK_BASE 0x00080000UL /* Always one */
[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>
2007-02-06 04:18:17 +08:00
#define PSW32_MASK_MCHECK 0x00040000UL
#define PSW32_MASK_WAIT 0x00020000UL
#define PSW32_MASK_PSTATE 0x00010000UL
#define PSW32_MASK_ASC 0x0000C000UL
#define PSW32_MASK_CC 0x00003000UL
#define PSW32_MASK_PM 0x00000f00UL
#define PSW32_MASK_USER 0x00003F00UL
#define PSW32_ADDR_AMODE 0x80000000UL
[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>
2007-02-06 04:18:17 +08:00
#define PSW32_ADDR_INSN 0x7FFFFFFFUL
#define PSW32_DEFAULT_KEY (((u32) PAGE_DEFAULT_ACC) << 20)
[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>
2007-02-06 04:18:17 +08:00
#define PSW32_ASC_PRIMARY 0x00000000UL
#define PSW32_ASC_ACCREG 0x00004000UL
#define PSW32_ASC_SECONDARY 0x00008000UL
#define PSW32_ASC_HOME 0x0000C000UL
extern u32 psw32_user_bits;
[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>
2007-02-06 04:18:17 +08:00
#define COMPAT_USER_HZ 100
#define COMPAT_UTS_MACHINE "s390\0\0\0\0"
typedef u32 compat_size_t;
typedef s32 compat_ssize_t;
typedef s32 compat_time_t;
typedef s32 compat_clock_t;
typedef s32 compat_pid_t;
typedef u16 __compat_uid_t;
typedef u16 __compat_gid_t;
typedef u32 __compat_uid32_t;
typedef u32 __compat_gid32_t;
typedef u16 compat_mode_t;
typedef u32 compat_ino_t;
typedef u16 compat_dev_t;
typedef s32 compat_off_t;
typedef s64 compat_loff_t;
typedef u16 compat_nlink_t;
typedef u16 compat_ipc_pid_t;
typedef s32 compat_daddr_t;
typedef u32 compat_caddr_t;
typedef __kernel_fsid_t compat_fsid_t;
typedef s32 compat_key_t;
typedef s32 compat_timer_t;
typedef s32 compat_int_t;
typedef s32 compat_long_t;
typedef s64 compat_s64;
typedef u32 compat_uint_t;
typedef u32 compat_ulong_t;
typedef u64 compat_u64;
struct compat_timespec {
compat_time_t tv_sec;
s32 tv_nsec;
};
struct compat_timeval {
compat_time_t tv_sec;
s32 tv_usec;
};
struct compat_stat {
compat_dev_t st_dev;
u16 __pad1;
compat_ino_t st_ino;
compat_mode_t st_mode;
compat_nlink_t st_nlink;
__compat_uid_t st_uid;
__compat_gid_t st_gid;
compat_dev_t st_rdev;
u16 __pad2;
u32 st_size;
u32 st_blksize;
u32 st_blocks;
u32 st_atime;
u32 st_atime_nsec;
u32 st_mtime;
u32 st_mtime_nsec;
u32 st_ctime;
u32 st_ctime_nsec;
u32 __unused4;
u32 __unused5;
};
struct compat_flock {
short l_type;
short l_whence;
compat_off_t l_start;
compat_off_t l_len;
compat_pid_t l_pid;
};
#define F_GETLK64 12
#define F_SETLK64 13
#define F_SETLKW64 14
struct compat_flock64 {
short l_type;
short l_whence;
compat_loff_t l_start;
compat_loff_t l_len;
compat_pid_t l_pid;
};
struct compat_statfs {
s32 f_type;
s32 f_bsize;
s32 f_blocks;
s32 f_bfree;
s32 f_bavail;
s32 f_files;
s32 f_ffree;
compat_fsid_t f_fsid;
s32 f_namelen;
s32 f_frsize;
s32 f_flags;
s32 f_spare[5];
};
#define COMPAT_RLIM_OLD_INFINITY 0x7fffffff
#define COMPAT_RLIM_INFINITY 0xffffffff
typedef u32 compat_old_sigset_t; /* at least 32 bits */
#define _COMPAT_NSIG 64
#define _COMPAT_NSIG_BPW 32
typedef u32 compat_sigset_word;
#define COMPAT_OFF_T_MAX 0x7fffffff
#define COMPAT_LOFF_T_MAX 0x7fffffffffffffffL
/*
* A pointer passed in from user mode. This should not
* be used for syscall parameters, just declare them
* as pointers because the syscall entry code will have
* appropriately converted them already.
*/
typedef u32 compat_uptr_t;
static inline void __user *compat_ptr(compat_uptr_t uptr)
{
return (void __user *)(unsigned long)(uptr & 0x7fffffffUL);
}
static inline compat_uptr_t ptr_to_compat(void __user *uptr)
{
return (u32)(unsigned long)uptr;
}
#ifdef CONFIG_COMPAT
static inline int is_compat_task(void)
{
return is_32bit_task();
}
#else
static inline int is_compat_task(void)
{
return 0;
}
#endif
compat: Make compat_alloc_user_space() incorporate the access_ok() compat_alloc_user_space() expects the caller to independently call access_ok() to verify the returned area. A missing call could introduce problems on some architectures. This patch incorporates the access_ok() check into compat_alloc_user_space() and also adds a sanity check on the length. The existing compat_alloc_user_space() implementations are renamed arch_compat_alloc_user_space() and are used as part of the implementation of the new global function. This patch assumes NULL will cause __get_user()/__put_user() to either fail or access userspace on all architectures. This should be followed by checking the return value of compat_access_user_space() for NULL in the callers, at which time the access_ok() in the callers can also be removed. Reported-by: Ben Hawkes <hawkes@sota.gen.nz> Signed-off-by: H. Peter Anvin <hpa@linux.intel.com> Acked-by: Benjamin Herrenschmidt <benh@kernel.crashing.org> Acked-by: Chris Metcalf <cmetcalf@tilera.com> Acked-by: David S. Miller <davem@davemloft.net> Acked-by: Ingo Molnar <mingo@elte.hu> Acked-by: Thomas Gleixner <tglx@linutronix.de> Acked-by: Tony Luck <tony.luck@intel.com> Cc: Andrew Morton <akpm@linux-foundation.org> Cc: Arnd Bergmann <arnd@arndb.de> Cc: Fenghua Yu <fenghua.yu@intel.com> Cc: H. Peter Anvin <hpa@zytor.com> Cc: Heiko Carstens <heiko.carstens@de.ibm.com> Cc: Helge Deller <deller@gmx.de> Cc: James Bottomley <jejb@parisc-linux.org> Cc: Kyle McMartin <kyle@mcmartin.ca> Cc: Martin Schwidefsky <schwidefsky@de.ibm.com> Cc: Paul Mackerras <paulus@samba.org> Cc: Ralf Baechle <ralf@linux-mips.org> Cc: <stable@kernel.org>
2010-09-08 07:16:18 +08:00
static inline void __user *arch_compat_alloc_user_space(long len)
{
unsigned long stack;
stack = KSTK_ESP(current);
if (is_compat_task())
stack &= 0x7fffffffUL;
return (void __user *) (stack - len);
}
struct compat_ipc64_perm {
compat_key_t key;
__compat_uid32_t uid;
__compat_gid32_t gid;
__compat_uid32_t cuid;
__compat_gid32_t cgid;
compat_mode_t mode;
unsigned short __pad1;
unsigned short seq;
unsigned short __pad2;
unsigned int __unused1;
unsigned int __unused2;
};
struct compat_semid64_ds {
struct compat_ipc64_perm sem_perm;
compat_time_t sem_otime;
compat_ulong_t __pad1;
compat_time_t sem_ctime;
compat_ulong_t __pad2;
compat_ulong_t sem_nsems;
compat_ulong_t __unused1;
compat_ulong_t __unused2;
};
struct compat_msqid64_ds {
struct compat_ipc64_perm msg_perm;
compat_time_t msg_stime;
compat_ulong_t __pad1;
compat_time_t msg_rtime;
compat_ulong_t __pad2;
compat_time_t msg_ctime;
compat_ulong_t __pad3;
compat_ulong_t msg_cbytes;
compat_ulong_t msg_qnum;
compat_ulong_t msg_qbytes;
compat_pid_t msg_lspid;
compat_pid_t msg_lrpid;
compat_ulong_t __unused1;
compat_ulong_t __unused2;
};
struct compat_shmid64_ds {
struct compat_ipc64_perm shm_perm;
compat_size_t shm_segsz;
compat_time_t shm_atime;
compat_ulong_t __pad1;
compat_time_t shm_dtime;
compat_ulong_t __pad2;
compat_time_t shm_ctime;
compat_ulong_t __pad3;
compat_pid_t shm_cpid;
compat_pid_t shm_lpid;
compat_ulong_t shm_nattch;
compat_ulong_t __unused1;
compat_ulong_t __unused2;
};
#endif /* _ASM_S390X_COMPAT_H */