kernel-fxtec-pro1x/arch/s390/mm/fault.c

601 lines
15 KiB
C
Raw Normal View History

/*
* arch/s390/mm/fault.c
*
* S390 version
* Copyright (C) 1999 IBM Deutschland Entwicklung GmbH, IBM Corporation
* Author(s): Hartmut Penner (hp@de.ibm.com)
* Ulrich Weigand (uweigand@de.ibm.com)
*
* Derived from "arch/i386/mm/fault.c"
* Copyright (C) 1995 Linus Torvalds
*/
perf: Do the big rename: Performance Counters -> Performance Events Bye-bye Performance Counters, welcome Performance Events! In the past few months the perfcounters subsystem has grown out its initial role of counting hardware events, and has become (and is becoming) a much broader generic event enumeration, reporting, logging, monitoring, analysis facility. Naming its core object 'perf_counter' and naming the subsystem 'perfcounters' has become more and more of a misnomer. With pending code like hw-breakpoints support the 'counter' name is less and less appropriate. All in one, we've decided to rename the subsystem to 'performance events' and to propagate this rename through all fields, variables and API names. (in an ABI compatible fashion) The word 'event' is also a bit shorter than 'counter' - which makes it slightly more convenient to write/handle as well. Thanks goes to Stephane Eranian who first observed this misnomer and suggested a rename. User-space tooling and ABI compatibility is not affected - this patch should be function-invariant. (Also, defconfigs were not touched to keep the size down.) This patch has been generated via the following script: FILES=$(find * -type f | grep -vE 'oprofile|[^K]config') sed -i \ -e 's/PERF_EVENT_/PERF_RECORD_/g' \ -e 's/PERF_COUNTER/PERF_EVENT/g' \ -e 's/perf_counter/perf_event/g' \ -e 's/nb_counters/nb_events/g' \ -e 's/swcounter/swevent/g' \ -e 's/tpcounter_event/tp_event/g' \ $FILES for N in $(find . -name perf_counter.[ch]); do M=$(echo $N | sed 's/perf_counter/perf_event/g') mv $N $M done FILES=$(find . -name perf_event.*) sed -i \ -e 's/COUNTER_MASK/REG_MASK/g' \ -e 's/COUNTER/EVENT/g' \ -e 's/\<event\>/event_id/g' \ -e 's/counter/event/g' \ -e 's/Counter/Event/g' \ $FILES ... to keep it as correct as possible. This script can also be used by anyone who has pending perfcounters patches - it converts a Linux kernel tree over to the new naming. We tried to time this change to the point in time where the amount of pending patches is the smallest: the end of the merge window. Namespace clashes were fixed up in a preparatory patch - and some stylistic fallout will be fixed up in a subsequent patch. ( NOTE: 'counters' are still the proper terminology when we deal with hardware registers - and these sed scripts are a bit over-eager in renaming them. I've undone some of that, but in case there's something left where 'counter' would be better than 'event' we can undo that on an individual basis instead of touching an otherwise nicely automated patch. ) Suggested-by: Stephane Eranian <eranian@google.com> Acked-by: Peter Zijlstra <a.p.zijlstra@chello.nl> Acked-by: Paul Mackerras <paulus@samba.org> Reviewed-by: Arjan van de Ven <arjan@linux.intel.com> Cc: Mike Galbraith <efault@gmx.de> Cc: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Steven Rostedt <rostedt@goodmis.org> Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org> Cc: David Howells <dhowells@redhat.com> Cc: Kyle McMartin <kyle@mcmartin.ca> Cc: Martin Schwidefsky <schwidefsky@de.ibm.com> Cc: "David S. Miller" <davem@davemloft.net> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: "H. Peter Anvin" <hpa@zytor.com> Cc: <linux-arch@vger.kernel.org> LKML-Reference: <new-submission> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-09-21 04:02:48 -06:00
#include <linux/perf_event.h>
#include <linux/signal.h>
#include <linux/sched.h>
#include <linux/kernel.h>
#include <linux/errno.h>
#include <linux/string.h>
#include <linux/types.h>
#include <linux/ptrace.h>
#include <linux/mman.h>
#include <linux/mm.h>
#include <linux/compat.h>
#include <linux/smp.h>
#include <linux/kdebug.h>
#include <linux/init.h>
#include <linux/console.h>
#include <linux/module.h>
#include <linux/hardirq.h>
#include <linux/kprobes.h>
#include <linux/uaccess.h>
#include <linux/hugetlb.h>
#include <asm/asm-offsets.h>
#include <asm/system.h>
#include <asm/pgtable.h>
#include <asm/s390_ext.h>
#include <asm/mmu_context.h>
#include <asm/compat.h>
#include "../kernel/entry.h"
#ifndef CONFIG_64BIT
#define __FAIL_ADDR_MASK 0x7ffff000
#define __SUBCODE_MASK 0x0200
#define __PF_RES_FIELD 0ULL
#else /* CONFIG_64BIT */
#define __FAIL_ADDR_MASK -4096L
#define __SUBCODE_MASK 0x0600
#define __PF_RES_FIELD 0x8000000000000000ULL
#endif /* CONFIG_64BIT */
#ifdef CONFIG_SYSCTL
extern int sysctl_userprocess_debug;
#endif
#define VM_FAULT_BADCONTEXT 0x010000
#define VM_FAULT_BADMAP 0x020000
#define VM_FAULT_BADACCESS 0x040000
static inline int notify_page_fault(struct pt_regs *regs)
{
int ret = 0;
#ifdef CONFIG_KPROBES
/* kprobe_running() needs smp_processor_id() */
if (!user_mode(regs)) {
preempt_disable();
if (kprobe_running() && kprobe_fault_handler(regs, 14))
ret = 1;
preempt_enable();
}
#endif
return ret;
}
/*
* Unlock any spinlocks which will prevent us from getting the
* message out.
*/
void bust_spinlocks(int yes)
{
if (yes) {
oops_in_progress = 1;
} else {
int loglevel_save = console_loglevel;
console_unblank();
oops_in_progress = 0;
/*
* OK, the message is on the console. Now we call printk()
* without oops_in_progress set so that printk will give klogd
* a poke. Hold onto your hats...
*/
console_loglevel = 15;
printk(" ");
console_loglevel = loglevel_save;
}
}
/*
* Returns the address space associated with the fault.
* Returns 0 for kernel space and 1 for user space.
*/
static inline int user_space_fault(unsigned long trans_exc_code)
{
/*
* The lowest two bits of the translation exception
* identification indicate which paging table was used.
*/
trans_exc_code &= 3;
if (trans_exc_code == 2)
/* Access via secondary space, set_fs setting decides */
return current->thread.mm_segment.ar4;
if (user_mode == HOME_SPACE_MODE)
/* User space if the access has been done via home space. */
return trans_exc_code == 3;
/*
* If the user space is not the home space the kernel runs in home
* space. Access via secondary space has already been covered,
* access via primary space or access register is from user space
* and access via home space is from the kernel.
*/
return trans_exc_code != 3;
}
/*
* Send SIGSEGV to task. This is an external routine
* to keep the stack usage of do_page_fault small.
*/
static noinline void do_sigsegv(struct pt_regs *regs, long int_code,
int si_code, unsigned long trans_exc_code)
{
struct siginfo si;
unsigned long address;
address = trans_exc_code & __FAIL_ADDR_MASK;
current->thread.prot_addr = address;
current->thread.trap_no = int_code;
#if defined(CONFIG_SYSCTL) || defined(CONFIG_PROCESS_DEBUG)
#if defined(CONFIG_SYSCTL)
if (sysctl_userprocess_debug)
#endif
{
printk("User process fault: interruption code 0x%lX\n",
int_code);
printk("failing address: %lX\n", address);
show_regs(regs);
}
#endif
si.si_signo = SIGSEGV;
si.si_code = si_code;
si.si_addr = (void __user *) address;
force_sig_info(SIGSEGV, &si, current);
}
static noinline void do_no_context(struct pt_regs *regs, long int_code,
unsigned long trans_exc_code)
{
const struct exception_table_entry *fixup;
unsigned long address;
/* Are we prepared to handle this kernel fault? */
fixup = search_exception_tables(regs->psw.addr & PSW_ADDR_INSN);
if (fixup) {
regs->psw.addr = fixup->fixup | PSW_ADDR_AMODE;
return;
}
/*
* Oops. The kernel tried to access some bad page. We'll have to
* terminate things with extreme prejudice.
*/
address = trans_exc_code & __FAIL_ADDR_MASK;
if (!user_space_fault(trans_exc_code))
printk(KERN_ALERT "Unable to handle kernel pointer dereference"
" at virtual kernel address %p\n", (void *)address);
else
printk(KERN_ALERT "Unable to handle kernel paging request"
" at virtual user address %p\n", (void *)address);
die("Oops", regs, int_code);
do_exit(SIGKILL);
}
static noinline void do_low_address(struct pt_regs *regs, long int_code,
unsigned long trans_exc_code)
{
/* Low-address protection hit in kernel mode means
NULL pointer write access in kernel mode. */
if (regs->psw.mask & PSW_MASK_PSTATE) {
/* Low-address protection hit in user mode 'cannot happen'. */
die ("Low-address protection", regs, int_code);
do_exit(SIGKILL);
}
do_no_context(regs, int_code, trans_exc_code);
}
static noinline void do_sigbus(struct pt_regs *regs, long int_code,
unsigned long trans_exc_code)
{
struct task_struct *tsk = current;
/*
* Send a sigbus, regardless of whether we were in kernel
* or user mode.
*/
tsk->thread.prot_addr = trans_exc_code & __FAIL_ADDR_MASK;
tsk->thread.trap_no = int_code;
force_sig(SIGBUS, tsk);
}
[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 13:18:17 -07:00
#ifdef CONFIG_S390_EXEC_PROTECT
static noinline int signal_return(struct pt_regs *regs, long int_code,
unsigned long trans_exc_code)
[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 13:18:17 -07:00
{
u16 instruction;
int rc;
rc = __get_user(instruction, (u16 __user *) regs->psw.addr);
if (!rc && instruction == 0x0a77) {
clear_tsk_thread_flag(current, TIF_SINGLE_STEP);
if (is_compat_task())
sys32_sigreturn();
else
sys_sigreturn();
} else if (!rc && instruction == 0x0aad) {
clear_tsk_thread_flag(current, TIF_SINGLE_STEP);
if (is_compat_task())
sys32_rt_sigreturn();
else
sys_rt_sigreturn();
} else
do_sigsegv(regs, int_code, SEGV_MAPERR, trans_exc_code);
[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 13:18:17 -07:00
return 0;
}
#endif /* CONFIG_S390_EXEC_PROTECT */
static noinline void do_fault_error(struct pt_regs *regs, long int_code,
unsigned long trans_exc_code, int fault)
{
int si_code;
switch (fault) {
case VM_FAULT_BADACCESS:
#ifdef CONFIG_S390_EXEC_PROTECT
if ((regs->psw.mask & PSW_MASK_ASC) == PSW_ASC_SECONDARY &&
(trans_exc_code & 3) == 0) {
signal_return(regs, int_code, trans_exc_code);
break;
}
#endif /* CONFIG_S390_EXEC_PROTECT */
case VM_FAULT_BADMAP:
/* Bad memory access. Check if it is kernel or user space. */
if (regs->psw.mask & PSW_MASK_PSTATE) {
/* User mode accesses just cause a SIGSEGV */
si_code = (fault == VM_FAULT_BADMAP) ?
SEGV_MAPERR : SEGV_ACCERR;
do_sigsegv(regs, int_code, si_code, trans_exc_code);
return;
}
case VM_FAULT_BADCONTEXT:
do_no_context(regs, int_code, trans_exc_code);
break;
default: /* fault & VM_FAULT_ERROR */
if (fault & VM_FAULT_OOM)
pagefault_out_of_memory();
else if (fault & VM_FAULT_SIGBUS) {
do_sigbus(regs, int_code, trans_exc_code);
/* Kernel mode? Handle exceptions or die */
if (!(regs->psw.mask & PSW_MASK_PSTATE))
do_no_context(regs, int_code, trans_exc_code);
} else
BUG();
break;
}
}
/*
* This routine handles page faults. It determines the address,
* and the problem, and then passes it off to one of the appropriate
* routines.
*
* interruption code (int_code):
* 04 Protection -> Write-Protection (suprression)
* 10 Segment translation -> Not present (nullification)
* 11 Page translation -> Not present (nullification)
* 3b Region third trans. -> Not present (nullification)
*/
static inline int do_exception(struct pt_regs *regs, int access,
unsigned long trans_exc_code)
{
struct task_struct *tsk;
struct mm_struct *mm;
struct vm_area_struct *vma;
unsigned long address;
mm: fault feedback #2 This patch completes Linus's wish that the fault return codes be made into bit flags, which I agree makes everything nicer. This requires requires all handle_mm_fault callers to be modified (possibly the modifications should go further and do things like fault accounting in handle_mm_fault -- however that would be for another patch). [akpm@linux-foundation.org: fix alpha build] [akpm@linux-foundation.org: fix s390 build] [akpm@linux-foundation.org: fix sparc build] [akpm@linux-foundation.org: fix sparc64 build] [akpm@linux-foundation.org: fix ia64 build] Signed-off-by: Nick Piggin <npiggin@suse.de> Cc: Richard Henderson <rth@twiddle.net> Cc: Ivan Kokshaysky <ink@jurassic.park.msu.ru> Cc: Russell King <rmk@arm.linux.org.uk> Cc: Ian Molton <spyro@f2s.com> Cc: Bryan Wu <bryan.wu@analog.com> Cc: Mikael Starvik <starvik@axis.com> Cc: David Howells <dhowells@redhat.com> Cc: Yoshinori Sato <ysato@users.sourceforge.jp> Cc: "Luck, Tony" <tony.luck@intel.com> Cc: Hirokazu Takata <takata@linux-m32r.org> Cc: Geert Uytterhoeven <geert@linux-m68k.org> Cc: Roman Zippel <zippel@linux-m68k.org> Cc: Greg Ungerer <gerg@uclinux.org> Cc: Matthew Wilcox <willy@debian.org> Cc: Paul Mackerras <paulus@samba.org> Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org> Cc: Heiko Carstens <heiko.carstens@de.ibm.com> Cc: Martin Schwidefsky <schwidefsky@de.ibm.com> Cc: Paul Mundt <lethal@linux-sh.org> Cc: Kazumoto Kojima <kkojima@rr.iij4u.or.jp> Cc: Richard Curnow <rc@rc0.org.uk> Cc: William Lee Irwin III <wli@holomorphy.com> Cc: "David S. Miller" <davem@davemloft.net> Cc: Jeff Dike <jdike@addtoit.com> Cc: Paolo 'Blaisorblade' Giarrusso <blaisorblade@yahoo.it> Cc: Miles Bader <uclinux-v850@lsi.nec.co.jp> Cc: Chris Zankel <chris@zankel.net> Acked-by: Kyle McMartin <kyle@mcmartin.ca> Acked-by: Haavard Skinnemoen <hskinnemoen@atmel.com> Acked-by: Ralf Baechle <ralf@linux-mips.org> Acked-by: Andi Kleen <ak@muc.de> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> [ Still apparently needs some ARM and PPC loving - Linus ] Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2007-07-19 02:47:05 -06:00
int fault;
if (notify_page_fault(regs))
return 0;
tsk = current;
mm = tsk->mm;
/*
* Verify that the fault happened in user space, that
* we are not in an interrupt and that there is a
* user context.
*/
fault = VM_FAULT_BADCONTEXT;
if (unlikely(!user_space_fault(trans_exc_code) || in_atomic() || !mm))
goto out;
address = trans_exc_code & __FAIL_ADDR_MASK;
/*
* When we get here, the fault happened in the current
* task's user address space, so we can switch on the
* interrupts again and then search the VMAs
*/
local_irq_enable();
perf: Do the big rename: Performance Counters -> Performance Events Bye-bye Performance Counters, welcome Performance Events! In the past few months the perfcounters subsystem has grown out its initial role of counting hardware events, and has become (and is becoming) a much broader generic event enumeration, reporting, logging, monitoring, analysis facility. Naming its core object 'perf_counter' and naming the subsystem 'perfcounters' has become more and more of a misnomer. With pending code like hw-breakpoints support the 'counter' name is less and less appropriate. All in one, we've decided to rename the subsystem to 'performance events' and to propagate this rename through all fields, variables and API names. (in an ABI compatible fashion) The word 'event' is also a bit shorter than 'counter' - which makes it slightly more convenient to write/handle as well. Thanks goes to Stephane Eranian who first observed this misnomer and suggested a rename. User-space tooling and ABI compatibility is not affected - this patch should be function-invariant. (Also, defconfigs were not touched to keep the size down.) This patch has been generated via the following script: FILES=$(find * -type f | grep -vE 'oprofile|[^K]config') sed -i \ -e 's/PERF_EVENT_/PERF_RECORD_/g' \ -e 's/PERF_COUNTER/PERF_EVENT/g' \ -e 's/perf_counter/perf_event/g' \ -e 's/nb_counters/nb_events/g' \ -e 's/swcounter/swevent/g' \ -e 's/tpcounter_event/tp_event/g' \ $FILES for N in $(find . -name perf_counter.[ch]); do M=$(echo $N | sed 's/perf_counter/perf_event/g') mv $N $M done FILES=$(find . -name perf_event.*) sed -i \ -e 's/COUNTER_MASK/REG_MASK/g' \ -e 's/COUNTER/EVENT/g' \ -e 's/\<event\>/event_id/g' \ -e 's/counter/event/g' \ -e 's/Counter/Event/g' \ $FILES ... to keep it as correct as possible. This script can also be used by anyone who has pending perfcounters patches - it converts a Linux kernel tree over to the new naming. We tried to time this change to the point in time where the amount of pending patches is the smallest: the end of the merge window. Namespace clashes were fixed up in a preparatory patch - and some stylistic fallout will be fixed up in a subsequent patch. ( NOTE: 'counters' are still the proper terminology when we deal with hardware registers - and these sed scripts are a bit over-eager in renaming them. I've undone some of that, but in case there's something left where 'counter' would be better than 'event' we can undo that on an individual basis instead of touching an otherwise nicely automated patch. ) Suggested-by: Stephane Eranian <eranian@google.com> Acked-by: Peter Zijlstra <a.p.zijlstra@chello.nl> Acked-by: Paul Mackerras <paulus@samba.org> Reviewed-by: Arjan van de Ven <arjan@linux.intel.com> Cc: Mike Galbraith <efault@gmx.de> Cc: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Steven Rostedt <rostedt@goodmis.org> Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org> Cc: David Howells <dhowells@redhat.com> Cc: Kyle McMartin <kyle@mcmartin.ca> Cc: Martin Schwidefsky <schwidefsky@de.ibm.com> Cc: "David S. Miller" <davem@davemloft.net> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: "H. Peter Anvin" <hpa@zytor.com> Cc: <linux-arch@vger.kernel.org> LKML-Reference: <new-submission> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-09-21 04:02:48 -06:00
perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS, 1, 0, regs, address);
down_read(&mm->mmap_sem);
fault = VM_FAULT_BADMAP;
vma = find_vma(mm, address);
if (!vma)
goto out_up;
[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 13:18:17 -07:00
if (unlikely(vma->vm_start > address)) {
if (!(vma->vm_flags & VM_GROWSDOWN))
goto out_up;
if (expand_stack(vma, address))
goto out_up;
}
/*
* Ok, we have a good vm_area for this memory access, so
* we can handle it..
*/
fault = VM_FAULT_BADACCESS;
if (unlikely(!(vma->vm_flags & access)))
goto out_up;
if (is_vm_hugetlb_page(vma))
address &= HPAGE_MASK;
/*
* If for any reason at all we couldn't handle the fault,
* make sure we exit gracefully rather than endlessly redo
* the fault.
*/
fault = handle_mm_fault(mm, vma, address,
(access == VM_WRITE) ? FAULT_FLAG_WRITE : 0);
if (unlikely(fault & VM_FAULT_ERROR))
goto out_up;
if (fault & VM_FAULT_MAJOR) {
mm: fault feedback #2 This patch completes Linus's wish that the fault return codes be made into bit flags, which I agree makes everything nicer. This requires requires all handle_mm_fault callers to be modified (possibly the modifications should go further and do things like fault accounting in handle_mm_fault -- however that would be for another patch). [akpm@linux-foundation.org: fix alpha build] [akpm@linux-foundation.org: fix s390 build] [akpm@linux-foundation.org: fix sparc build] [akpm@linux-foundation.org: fix sparc64 build] [akpm@linux-foundation.org: fix ia64 build] Signed-off-by: Nick Piggin <npiggin@suse.de> Cc: Richard Henderson <rth@twiddle.net> Cc: Ivan Kokshaysky <ink@jurassic.park.msu.ru> Cc: Russell King <rmk@arm.linux.org.uk> Cc: Ian Molton <spyro@f2s.com> Cc: Bryan Wu <bryan.wu@analog.com> Cc: Mikael Starvik <starvik@axis.com> Cc: David Howells <dhowells@redhat.com> Cc: Yoshinori Sato <ysato@users.sourceforge.jp> Cc: "Luck, Tony" <tony.luck@intel.com> Cc: Hirokazu Takata <takata@linux-m32r.org> Cc: Geert Uytterhoeven <geert@linux-m68k.org> Cc: Roman Zippel <zippel@linux-m68k.org> Cc: Greg Ungerer <gerg@uclinux.org> Cc: Matthew Wilcox <willy@debian.org> Cc: Paul Mackerras <paulus@samba.org> Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org> Cc: Heiko Carstens <heiko.carstens@de.ibm.com> Cc: Martin Schwidefsky <schwidefsky@de.ibm.com> Cc: Paul Mundt <lethal@linux-sh.org> Cc: Kazumoto Kojima <kkojima@rr.iij4u.or.jp> Cc: Richard Curnow <rc@rc0.org.uk> Cc: William Lee Irwin III <wli@holomorphy.com> Cc: "David S. Miller" <davem@davemloft.net> Cc: Jeff Dike <jdike@addtoit.com> Cc: Paolo 'Blaisorblade' Giarrusso <blaisorblade@yahoo.it> Cc: Miles Bader <uclinux-v850@lsi.nec.co.jp> Cc: Chris Zankel <chris@zankel.net> Acked-by: Kyle McMartin <kyle@mcmartin.ca> Acked-by: Haavard Skinnemoen <hskinnemoen@atmel.com> Acked-by: Ralf Baechle <ralf@linux-mips.org> Acked-by: Andi Kleen <ak@muc.de> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> [ Still apparently needs some ARM and PPC loving - Linus ] Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2007-07-19 02:47:05 -06:00
tsk->maj_flt++;
perf: Do the big rename: Performance Counters -> Performance Events Bye-bye Performance Counters, welcome Performance Events! In the past few months the perfcounters subsystem has grown out its initial role of counting hardware events, and has become (and is becoming) a much broader generic event enumeration, reporting, logging, monitoring, analysis facility. Naming its core object 'perf_counter' and naming the subsystem 'perfcounters' has become more and more of a misnomer. With pending code like hw-breakpoints support the 'counter' name is less and less appropriate. All in one, we've decided to rename the subsystem to 'performance events' and to propagate this rename through all fields, variables and API names. (in an ABI compatible fashion) The word 'event' is also a bit shorter than 'counter' - which makes it slightly more convenient to write/handle as well. Thanks goes to Stephane Eranian who first observed this misnomer and suggested a rename. User-space tooling and ABI compatibility is not affected - this patch should be function-invariant. (Also, defconfigs were not touched to keep the size down.) This patch has been generated via the following script: FILES=$(find * -type f | grep -vE 'oprofile|[^K]config') sed -i \ -e 's/PERF_EVENT_/PERF_RECORD_/g' \ -e 's/PERF_COUNTER/PERF_EVENT/g' \ -e 's/perf_counter/perf_event/g' \ -e 's/nb_counters/nb_events/g' \ -e 's/swcounter/swevent/g' \ -e 's/tpcounter_event/tp_event/g' \ $FILES for N in $(find . -name perf_counter.[ch]); do M=$(echo $N | sed 's/perf_counter/perf_event/g') mv $N $M done FILES=$(find . -name perf_event.*) sed -i \ -e 's/COUNTER_MASK/REG_MASK/g' \ -e 's/COUNTER/EVENT/g' \ -e 's/\<event\>/event_id/g' \ -e 's/counter/event/g' \ -e 's/Counter/Event/g' \ $FILES ... to keep it as correct as possible. This script can also be used by anyone who has pending perfcounters patches - it converts a Linux kernel tree over to the new naming. We tried to time this change to the point in time where the amount of pending patches is the smallest: the end of the merge window. Namespace clashes were fixed up in a preparatory patch - and some stylistic fallout will be fixed up in a subsequent patch. ( NOTE: 'counters' are still the proper terminology when we deal with hardware registers - and these sed scripts are a bit over-eager in renaming them. I've undone some of that, but in case there's something left where 'counter' would be better than 'event' we can undo that on an individual basis instead of touching an otherwise nicely automated patch. ) Suggested-by: Stephane Eranian <eranian@google.com> Acked-by: Peter Zijlstra <a.p.zijlstra@chello.nl> Acked-by: Paul Mackerras <paulus@samba.org> Reviewed-by: Arjan van de Ven <arjan@linux.intel.com> Cc: Mike Galbraith <efault@gmx.de> Cc: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Steven Rostedt <rostedt@goodmis.org> Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org> Cc: David Howells <dhowells@redhat.com> Cc: Kyle McMartin <kyle@mcmartin.ca> Cc: Martin Schwidefsky <schwidefsky@de.ibm.com> Cc: "David S. Miller" <davem@davemloft.net> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: "H. Peter Anvin" <hpa@zytor.com> Cc: <linux-arch@vger.kernel.org> LKML-Reference: <new-submission> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-09-21 04:02:48 -06:00
perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS_MAJ, 1, 0,
regs, address);
} else {
mm: fault feedback #2 This patch completes Linus's wish that the fault return codes be made into bit flags, which I agree makes everything nicer. This requires requires all handle_mm_fault callers to be modified (possibly the modifications should go further and do things like fault accounting in handle_mm_fault -- however that would be for another patch). [akpm@linux-foundation.org: fix alpha build] [akpm@linux-foundation.org: fix s390 build] [akpm@linux-foundation.org: fix sparc build] [akpm@linux-foundation.org: fix sparc64 build] [akpm@linux-foundation.org: fix ia64 build] Signed-off-by: Nick Piggin <npiggin@suse.de> Cc: Richard Henderson <rth@twiddle.net> Cc: Ivan Kokshaysky <ink@jurassic.park.msu.ru> Cc: Russell King <rmk@arm.linux.org.uk> Cc: Ian Molton <spyro@f2s.com> Cc: Bryan Wu <bryan.wu@analog.com> Cc: Mikael Starvik <starvik@axis.com> Cc: David Howells <dhowells@redhat.com> Cc: Yoshinori Sato <ysato@users.sourceforge.jp> Cc: "Luck, Tony" <tony.luck@intel.com> Cc: Hirokazu Takata <takata@linux-m32r.org> Cc: Geert Uytterhoeven <geert@linux-m68k.org> Cc: Roman Zippel <zippel@linux-m68k.org> Cc: Greg Ungerer <gerg@uclinux.org> Cc: Matthew Wilcox <willy@debian.org> Cc: Paul Mackerras <paulus@samba.org> Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org> Cc: Heiko Carstens <heiko.carstens@de.ibm.com> Cc: Martin Schwidefsky <schwidefsky@de.ibm.com> Cc: Paul Mundt <lethal@linux-sh.org> Cc: Kazumoto Kojima <kkojima@rr.iij4u.or.jp> Cc: Richard Curnow <rc@rc0.org.uk> Cc: William Lee Irwin III <wli@holomorphy.com> Cc: "David S. Miller" <davem@davemloft.net> Cc: Jeff Dike <jdike@addtoit.com> Cc: Paolo 'Blaisorblade' Giarrusso <blaisorblade@yahoo.it> Cc: Miles Bader <uclinux-v850@lsi.nec.co.jp> Cc: Chris Zankel <chris@zankel.net> Acked-by: Kyle McMartin <kyle@mcmartin.ca> Acked-by: Haavard Skinnemoen <hskinnemoen@atmel.com> Acked-by: Ralf Baechle <ralf@linux-mips.org> Acked-by: Andi Kleen <ak@muc.de> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> [ Still apparently needs some ARM and PPC loving - Linus ] Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2007-07-19 02:47:05 -06:00
tsk->min_flt++;
perf: Do the big rename: Performance Counters -> Performance Events Bye-bye Performance Counters, welcome Performance Events! In the past few months the perfcounters subsystem has grown out its initial role of counting hardware events, and has become (and is becoming) a much broader generic event enumeration, reporting, logging, monitoring, analysis facility. Naming its core object 'perf_counter' and naming the subsystem 'perfcounters' has become more and more of a misnomer. With pending code like hw-breakpoints support the 'counter' name is less and less appropriate. All in one, we've decided to rename the subsystem to 'performance events' and to propagate this rename through all fields, variables and API names. (in an ABI compatible fashion) The word 'event' is also a bit shorter than 'counter' - which makes it slightly more convenient to write/handle as well. Thanks goes to Stephane Eranian who first observed this misnomer and suggested a rename. User-space tooling and ABI compatibility is not affected - this patch should be function-invariant. (Also, defconfigs were not touched to keep the size down.) This patch has been generated via the following script: FILES=$(find * -type f | grep -vE 'oprofile|[^K]config') sed -i \ -e 's/PERF_EVENT_/PERF_RECORD_/g' \ -e 's/PERF_COUNTER/PERF_EVENT/g' \ -e 's/perf_counter/perf_event/g' \ -e 's/nb_counters/nb_events/g' \ -e 's/swcounter/swevent/g' \ -e 's/tpcounter_event/tp_event/g' \ $FILES for N in $(find . -name perf_counter.[ch]); do M=$(echo $N | sed 's/perf_counter/perf_event/g') mv $N $M done FILES=$(find . -name perf_event.*) sed -i \ -e 's/COUNTER_MASK/REG_MASK/g' \ -e 's/COUNTER/EVENT/g' \ -e 's/\<event\>/event_id/g' \ -e 's/counter/event/g' \ -e 's/Counter/Event/g' \ $FILES ... to keep it as correct as possible. This script can also be used by anyone who has pending perfcounters patches - it converts a Linux kernel tree over to the new naming. We tried to time this change to the point in time where the amount of pending patches is the smallest: the end of the merge window. Namespace clashes were fixed up in a preparatory patch - and some stylistic fallout will be fixed up in a subsequent patch. ( NOTE: 'counters' are still the proper terminology when we deal with hardware registers - and these sed scripts are a bit over-eager in renaming them. I've undone some of that, but in case there's something left where 'counter' would be better than 'event' we can undo that on an individual basis instead of touching an otherwise nicely automated patch. ) Suggested-by: Stephane Eranian <eranian@google.com> Acked-by: Peter Zijlstra <a.p.zijlstra@chello.nl> Acked-by: Paul Mackerras <paulus@samba.org> Reviewed-by: Arjan van de Ven <arjan@linux.intel.com> Cc: Mike Galbraith <efault@gmx.de> Cc: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Steven Rostedt <rostedt@goodmis.org> Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org> Cc: David Howells <dhowells@redhat.com> Cc: Kyle McMartin <kyle@mcmartin.ca> Cc: Martin Schwidefsky <schwidefsky@de.ibm.com> Cc: "David S. Miller" <davem@davemloft.net> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: "H. Peter Anvin" <hpa@zytor.com> Cc: <linux-arch@vger.kernel.org> LKML-Reference: <new-submission> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-09-21 04:02:48 -06:00
perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS_MIN, 1, 0,
regs, address);
}
/*
* The instruction that caused the program check will
* be repeated. Don't signal single step via SIGTRAP.
*/
clear_tsk_thread_flag(tsk, TIF_SINGLE_STEP);
fault = 0;
out_up:
up_read(&mm->mmap_sem);
out:
return fault;
}
void __kprobes do_protection_exception(struct pt_regs *regs, long int_code)
{
unsigned long trans_exc_code = S390_lowcore.trans_exc_code;
int fault;
/* Protection exception is supressing, decrement psw address. */
regs->psw.addr -= (int_code >> 16);
/*
* Check for low-address protection. This needs to be treated
* as a special case because the translation exception code
* field is not guaranteed to contain valid data in this case.
*/
if (unlikely(!(trans_exc_code & 4))) {
do_low_address(regs, int_code, trans_exc_code);
return;
}
fault = do_exception(regs, VM_WRITE, trans_exc_code);
if (unlikely(fault))
do_fault_error(regs, 4, trans_exc_code, fault);
}
void __kprobes do_dat_exception(struct pt_regs *regs, long int_code)
{
unsigned long trans_exc_code = S390_lowcore.trans_exc_code;
int access, fault;
access = VM_READ | VM_EXEC | VM_WRITE;
#ifdef CONFIG_S390_EXEC_PROTECT
if ((regs->psw.mask & PSW_MASK_ASC) == PSW_ASC_SECONDARY &&
(trans_exc_code & 3) == 0)
access = VM_EXEC;
#endif
fault = do_exception(regs, access, trans_exc_code);
if (unlikely(fault))
do_fault_error(regs, int_code & 255, trans_exc_code, fault);
}
#ifdef CONFIG_64BIT
void __kprobes do_asce_exception(struct pt_regs *regs, long int_code)
{
unsigned long trans_exc_code = S390_lowcore.trans_exc_code;
struct mm_struct *mm = current->mm;
struct vm_area_struct *vma;
if (unlikely(!user_space_fault(trans_exc_code) || in_atomic() || !mm))
goto no_context;
local_irq_enable();
down_read(&mm->mmap_sem);
vma = find_vma(mm, trans_exc_code & __FAIL_ADDR_MASK);
up_read(&mm->mmap_sem);
if (vma) {
update_mm(mm, current);
return;
}
/* User mode accesses just cause a SIGSEGV */
if (regs->psw.mask & PSW_MASK_PSTATE) {
do_sigsegv(regs, int_code, SEGV_MAPERR, trans_exc_code);
return;
}
no_context:
do_no_context(regs, int_code, trans_exc_code);
}
#endif
int __handle_fault(unsigned long uaddr, unsigned long int_code, int write_user)
{
struct pt_regs regs;
int access, fault;
regs.psw.mask = psw_kernel_bits;
if (!irqs_disabled())
regs.psw.mask |= PSW_MASK_IO | PSW_MASK_EXT;
regs.psw.addr = (unsigned long) __builtin_return_address(0);
regs.psw.addr |= PSW_ADDR_AMODE;
uaddr &= PAGE_MASK;
access = write_user ? VM_WRITE : VM_READ;
fault = do_exception(&regs, access, uaddr | 2);
if (unlikely(fault)) {
if (fault & VM_FAULT_OOM) {
pagefault_out_of_memory();
fault = 0;
} else if (fault & VM_FAULT_SIGBUS)
do_sigbus(&regs, int_code, uaddr);
}
return fault ? -EFAULT : 0;
}
#ifdef CONFIG_PFAULT
/*
* 'pfault' pseudo page faults routines.
*/
static ext_int_info_t ext_int_pfault;
static int pfault_disable = 0;
static int __init nopfault(char *str)
{
pfault_disable = 1;
return 1;
}
__setup("nopfault", nopfault);
typedef struct {
__u16 refdiagc;
__u16 reffcode;
__u16 refdwlen;
__u16 refversn;
__u64 refgaddr;
__u64 refselmk;
__u64 refcmpmk;
__u64 reserved;
} __attribute__ ((packed, aligned(8))) pfault_refbk_t;
int pfault_init(void)
{
pfault_refbk_t refbk =
{ 0x258, 0, 5, 2, __LC_CURRENT, 1ULL << 48, 1ULL << 48,
__PF_RES_FIELD };
int rc;
if (!MACHINE_IS_VM || pfault_disable)
return -1;
asm volatile(
" diag %1,%0,0x258\n"
"0: j 2f\n"
"1: la %0,8\n"
"2:\n"
EX_TABLE(0b,1b)
: "=d" (rc) : "a" (&refbk), "m" (refbk) : "cc");
__ctl_set_bit(0, 9);
return rc;
}
void pfault_fini(void)
{
pfault_refbk_t refbk =
{ 0x258, 1, 5, 2, 0ULL, 0ULL, 0ULL, 0ULL };
if (!MACHINE_IS_VM || pfault_disable)
return;
__ctl_clear_bit(0,9);
asm volatile(
" diag %0,0,0x258\n"
"0:\n"
EX_TABLE(0b,0b)
: : "a" (&refbk), "m" (refbk) : "cc");
}
static void pfault_interrupt(__u16 int_code)
{
struct task_struct *tsk;
__u16 subcode;
/*
* Get the external interruption subcode & pfault
* initial/completion signal bit. VM stores this
* in the 'cpu address' field associated with the
* external interrupt.
*/
subcode = S390_lowcore.cpu_addr;
if ((subcode & 0xff00) != __SUBCODE_MASK)
return;
/*
* Get the token (= address of the task structure of the affected task).
*/
tsk = *(struct task_struct **) __LC_PFAULT_INTPARM;
if (subcode & 0x0080) {
/* signal bit is set -> a page has been swapped in by VM */
if (xchg(&tsk->thread.pfault_wait, -1) != 0) {
/* Initial interrupt was faster than the completion
* interrupt. pfault_wait is valid. Set pfault_wait
* back to zero and wake up the process. This can
* safely be done because the task is still sleeping
* and can't produce new pfaults. */
tsk->thread.pfault_wait = 0;
wake_up_process(tsk);
put_task_struct(tsk);
}
} else {
/* signal bit not set -> a real page is missing. */
get_task_struct(tsk);
set_task_state(tsk, TASK_UNINTERRUPTIBLE);
if (xchg(&tsk->thread.pfault_wait, 1) != 0) {
/* Completion interrupt was faster than the initial
* interrupt (swapped in a -1 for pfault_wait). Set
* pfault_wait back to zero and exit. This can be
* done safely because tsk is running in kernel
* mode and can't produce new pfaults. */
tsk->thread.pfault_wait = 0;
set_task_state(tsk, TASK_RUNNING);
put_task_struct(tsk);
} else
set_tsk_need_resched(tsk);
}
}
void __init pfault_irq_init(void)
{
if (!MACHINE_IS_VM)
return;
/*
* Try to get pfault pseudo page faults going.
*/
if (register_early_external_interrupt(0x2603, pfault_interrupt,
&ext_int_pfault) != 0)
panic("Couldn't request external interrupt 0x2603");
if (pfault_init() == 0)
return;
/* Tough luck, no pfault. */
pfault_disable = 1;
unregister_early_external_interrupt(0x2603, pfault_interrupt,
&ext_int_pfault);
}
#endif