2
0
mirror of https://github.com/edk2-porting/linux-next.git synced 2024-12-24 13:13:57 +08:00
linux-next/arch/s390/mm/fault.c

790 lines
20 KiB
C
Raw Normal View History

/*
* S390 version
* Copyright IBM Corp. 1999
* 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
*/
#include <linux/kernel_stat.h>
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 18:02:48 +08:00
#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/diag.h>
#include <asm/pgtable.h>
#include <asm/gmap.h>
#include <asm/irq.h>
#include <asm/mmu_context.h>
#include <asm/facility.h>
#include "../kernel/entry.h"
#define __FAIL_ADDR_MASK -4096L
#define __SUBCODE_MASK 0x0600
#define __PF_RES_FIELD 0x8000000000000000ULL
#define VM_FAULT_BADCONTEXT 0x010000
#define VM_FAULT_BADMAP 0x020000
#define VM_FAULT_BADACCESS 0x040000
#define VM_FAULT_SIGNAL 0x080000
#define VM_FAULT_PFAULT 0x100000
static unsigned long store_indication __read_mostly;
static int __init fault_init(void)
{
if (test_facility(75))
store_indication = 0xc00;
return 0;
}
early_initcall(fault_init);
static inline int notify_page_fault(struct pt_regs *regs)
{
int ret = 0;
/* kprobe_running() needs smp_processor_id() */
if (kprobes_built_in() && !user_mode(regs)) {
preempt_disable();
if (kprobe_running() && kprobe_fault_handler(regs, 14))
ret = 1;
preempt_enable();
}
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.
*/
s390/uaccess: rework uaccess code - fix locking issues The current uaccess code uses a page table walk in some circumstances, e.g. in case of the in atomic futex operations or if running on old hardware which doesn't support the mvcos instruction. However it turned out that the page table walk code does not correctly lock page tables when accessing page table entries. In other words: a different cpu may invalidate a page table entry while the current cpu inspects the pte. This may lead to random data corruption. Adding correct locking however isn't trivial for all uaccess operations. Especially copy_in_user() is problematic since that requires to hold at least two locks, but must be protected against ABBA deadlock when a different cpu also performs a copy_in_user() operation. So the solution is a different approach where we change address spaces: User space runs in primary address mode, or access register mode within vdso code, like it currently already does. The kernel usually also runs in home space mode, however when accessing user space the kernel switches to primary or secondary address mode if the mvcos instruction is not available or if a compare-and-swap (futex) instruction on a user space address is performed. KVM however is special, since that requires the kernel to run in home address space while implicitly accessing user space with the sie instruction. So we end up with: User space: - runs in primary or access register mode - cr1 contains the user asce - cr7 contains the user asce - cr13 contains the kernel asce Kernel space: - runs in home space mode - cr1 contains the user or kernel asce -> the kernel asce is loaded when a uaccess requires primary or secondary address mode - cr7 contains the user or kernel asce, (changed with set_fs()) - cr13 contains the kernel asce In case of uaccess the kernel changes to: - primary space mode in case of a uaccess (copy_to_user) and uses e.g. the mvcp instruction to access user space. However the kernel will stay in home space mode if the mvcos instruction is available - secondary space mode in case of futex atomic operations, so that the instructions come from primary address space and data from secondary space In case of kvm the kernel runs in home space mode, but cr1 gets switched to contain the gmap asce before the sie instruction gets executed. When the sie instruction is finished cr1 will be switched back to contain the user asce. A context switch between two processes will always load the kernel asce for the next process in cr1. So the first exit to user space is a bit more expensive (one extra load control register instruction) than before, however keeps the code rather simple. In sum this means there is no need to perform any error prone page table walks anymore when accessing user space. The patch seems to be rather large, however it mainly removes the the page table walk code and restores the previously deleted "standard" uaccess code, with a couple of changes. The uaccess without mvcos mode can be enforced with the "uaccess_primary" kernel parameter. Reported-by: Christian Borntraeger <borntraeger@de.ibm.com> Signed-off-by: Heiko Carstens <heiko.carstens@de.ibm.com> Signed-off-by: Martin Schwidefsky <schwidefsky@de.ibm.com>
2014-03-21 17:42:25 +08:00
static inline int user_space_fault(struct pt_regs *regs)
{
s390/uaccess: rework uaccess code - fix locking issues The current uaccess code uses a page table walk in some circumstances, e.g. in case of the in atomic futex operations or if running on old hardware which doesn't support the mvcos instruction. However it turned out that the page table walk code does not correctly lock page tables when accessing page table entries. In other words: a different cpu may invalidate a page table entry while the current cpu inspects the pte. This may lead to random data corruption. Adding correct locking however isn't trivial for all uaccess operations. Especially copy_in_user() is problematic since that requires to hold at least two locks, but must be protected against ABBA deadlock when a different cpu also performs a copy_in_user() operation. So the solution is a different approach where we change address spaces: User space runs in primary address mode, or access register mode within vdso code, like it currently already does. The kernel usually also runs in home space mode, however when accessing user space the kernel switches to primary or secondary address mode if the mvcos instruction is not available or if a compare-and-swap (futex) instruction on a user space address is performed. KVM however is special, since that requires the kernel to run in home address space while implicitly accessing user space with the sie instruction. So we end up with: User space: - runs in primary or access register mode - cr1 contains the user asce - cr7 contains the user asce - cr13 contains the kernel asce Kernel space: - runs in home space mode - cr1 contains the user or kernel asce -> the kernel asce is loaded when a uaccess requires primary or secondary address mode - cr7 contains the user or kernel asce, (changed with set_fs()) - cr13 contains the kernel asce In case of uaccess the kernel changes to: - primary space mode in case of a uaccess (copy_to_user) and uses e.g. the mvcp instruction to access user space. However the kernel will stay in home space mode if the mvcos instruction is available - secondary space mode in case of futex atomic operations, so that the instructions come from primary address space and data from secondary space In case of kvm the kernel runs in home space mode, but cr1 gets switched to contain the gmap asce before the sie instruction gets executed. When the sie instruction is finished cr1 will be switched back to contain the user asce. A context switch between two processes will always load the kernel asce for the next process in cr1. So the first exit to user space is a bit more expensive (one extra load control register instruction) than before, however keeps the code rather simple. In sum this means there is no need to perform any error prone page table walks anymore when accessing user space. The patch seems to be rather large, however it mainly removes the the page table walk code and restores the previously deleted "standard" uaccess code, with a couple of changes. The uaccess without mvcos mode can be enforced with the "uaccess_primary" kernel parameter. Reported-by: Christian Borntraeger <borntraeger@de.ibm.com> Signed-off-by: Heiko Carstens <heiko.carstens@de.ibm.com> Signed-off-by: Martin Schwidefsky <schwidefsky@de.ibm.com>
2014-03-21 17:42:25 +08:00
unsigned long trans_exc_code;
/*
* The lowest two bits of the translation exception
* identification indicate which paging table was used.
*/
s390/uaccess: rework uaccess code - fix locking issues The current uaccess code uses a page table walk in some circumstances, e.g. in case of the in atomic futex operations or if running on old hardware which doesn't support the mvcos instruction. However it turned out that the page table walk code does not correctly lock page tables when accessing page table entries. In other words: a different cpu may invalidate a page table entry while the current cpu inspects the pte. This may lead to random data corruption. Adding correct locking however isn't trivial for all uaccess operations. Especially copy_in_user() is problematic since that requires to hold at least two locks, but must be protected against ABBA deadlock when a different cpu also performs a copy_in_user() operation. So the solution is a different approach where we change address spaces: User space runs in primary address mode, or access register mode within vdso code, like it currently already does. The kernel usually also runs in home space mode, however when accessing user space the kernel switches to primary or secondary address mode if the mvcos instruction is not available or if a compare-and-swap (futex) instruction on a user space address is performed. KVM however is special, since that requires the kernel to run in home address space while implicitly accessing user space with the sie instruction. So we end up with: User space: - runs in primary or access register mode - cr1 contains the user asce - cr7 contains the user asce - cr13 contains the kernel asce Kernel space: - runs in home space mode - cr1 contains the user or kernel asce -> the kernel asce is loaded when a uaccess requires primary or secondary address mode - cr7 contains the user or kernel asce, (changed with set_fs()) - cr13 contains the kernel asce In case of uaccess the kernel changes to: - primary space mode in case of a uaccess (copy_to_user) and uses e.g. the mvcp instruction to access user space. However the kernel will stay in home space mode if the mvcos instruction is available - secondary space mode in case of futex atomic operations, so that the instructions come from primary address space and data from secondary space In case of kvm the kernel runs in home space mode, but cr1 gets switched to contain the gmap asce before the sie instruction gets executed. When the sie instruction is finished cr1 will be switched back to contain the user asce. A context switch between two processes will always load the kernel asce for the next process in cr1. So the first exit to user space is a bit more expensive (one extra load control register instruction) than before, however keeps the code rather simple. In sum this means there is no need to perform any error prone page table walks anymore when accessing user space. The patch seems to be rather large, however it mainly removes the the page table walk code and restores the previously deleted "standard" uaccess code, with a couple of changes. The uaccess without mvcos mode can be enforced with the "uaccess_primary" kernel parameter. Reported-by: Christian Borntraeger <borntraeger@de.ibm.com> Signed-off-by: Heiko Carstens <heiko.carstens@de.ibm.com> Signed-off-by: Martin Schwidefsky <schwidefsky@de.ibm.com>
2014-03-21 17:42:25 +08:00
trans_exc_code = regs->int_parm_long & 3;
if (trans_exc_code == 3) /* home space -> kernel */
return 0;
if (user_mode(regs))
return 1;
if (trans_exc_code == 2) /* secondary space -> set_fs */
return current->thread.mm_segment.ar4;
s390/uaccess: rework uaccess code - fix locking issues The current uaccess code uses a page table walk in some circumstances, e.g. in case of the in atomic futex operations or if running on old hardware which doesn't support the mvcos instruction. However it turned out that the page table walk code does not correctly lock page tables when accessing page table entries. In other words: a different cpu may invalidate a page table entry while the current cpu inspects the pte. This may lead to random data corruption. Adding correct locking however isn't trivial for all uaccess operations. Especially copy_in_user() is problematic since that requires to hold at least two locks, but must be protected against ABBA deadlock when a different cpu also performs a copy_in_user() operation. So the solution is a different approach where we change address spaces: User space runs in primary address mode, or access register mode within vdso code, like it currently already does. The kernel usually also runs in home space mode, however when accessing user space the kernel switches to primary or secondary address mode if the mvcos instruction is not available or if a compare-and-swap (futex) instruction on a user space address is performed. KVM however is special, since that requires the kernel to run in home address space while implicitly accessing user space with the sie instruction. So we end up with: User space: - runs in primary or access register mode - cr1 contains the user asce - cr7 contains the user asce - cr13 contains the kernel asce Kernel space: - runs in home space mode - cr1 contains the user or kernel asce -> the kernel asce is loaded when a uaccess requires primary or secondary address mode - cr7 contains the user or kernel asce, (changed with set_fs()) - cr13 contains the kernel asce In case of uaccess the kernel changes to: - primary space mode in case of a uaccess (copy_to_user) and uses e.g. the mvcp instruction to access user space. However the kernel will stay in home space mode if the mvcos instruction is available - secondary space mode in case of futex atomic operations, so that the instructions come from primary address space and data from secondary space In case of kvm the kernel runs in home space mode, but cr1 gets switched to contain the gmap asce before the sie instruction gets executed. When the sie instruction is finished cr1 will be switched back to contain the user asce. A context switch between two processes will always load the kernel asce for the next process in cr1. So the first exit to user space is a bit more expensive (one extra load control register instruction) than before, however keeps the code rather simple. In sum this means there is no need to perform any error prone page table walks anymore when accessing user space. The patch seems to be rather large, however it mainly removes the the page table walk code and restores the previously deleted "standard" uaccess code, with a couple of changes. The uaccess without mvcos mode can be enforced with the "uaccess_primary" kernel parameter. Reported-by: Christian Borntraeger <borntraeger@de.ibm.com> Signed-off-by: Heiko Carstens <heiko.carstens@de.ibm.com> Signed-off-by: Martin Schwidefsky <schwidefsky@de.ibm.com>
2014-03-21 17:42:25 +08:00
if (current->flags & PF_VCPU)
return 1;
return 0;
}
static int bad_address(void *p)
{
unsigned long dummy;
return probe_kernel_address((unsigned long *)p, dummy);
}
static void dump_pagetable(unsigned long asce, unsigned long address)
{
unsigned long *table = __va(asce & PAGE_MASK);
pr_alert("AS:%016lx ", asce);
switch (asce & _ASCE_TYPE_MASK) {
case _ASCE_TYPE_REGION1:
table = table + ((address >> 53) & 0x7ff);
if (bad_address(table))
goto bad;
pr_cont("R1:%016lx ", *table);
if (*table & _REGION_ENTRY_INVALID)
goto out;
table = (unsigned long *)(*table & _REGION_ENTRY_ORIGIN);
/* fallthrough */
case _ASCE_TYPE_REGION2:
table = table + ((address >> 42) & 0x7ff);
if (bad_address(table))
goto bad;
pr_cont("R2:%016lx ", *table);
if (*table & _REGION_ENTRY_INVALID)
goto out;
table = (unsigned long *)(*table & _REGION_ENTRY_ORIGIN);
/* fallthrough */
case _ASCE_TYPE_REGION3:
table = table + ((address >> 31) & 0x7ff);
if (bad_address(table))
goto bad;
pr_cont("R3:%016lx ", *table);
if (*table & (_REGION_ENTRY_INVALID | _REGION3_ENTRY_LARGE))
goto out;
table = (unsigned long *)(*table & _REGION_ENTRY_ORIGIN);
/* fallthrough */
case _ASCE_TYPE_SEGMENT:
table = table + ((address >> 20) & 0x7ff);
if (bad_address(table))
goto bad;
pr_cont("S:%016lx ", *table);
if (*table & (_SEGMENT_ENTRY_INVALID | _SEGMENT_ENTRY_LARGE))
goto out;
table = (unsigned long *)(*table & _SEGMENT_ENTRY_ORIGIN);
}
table = table + ((address >> 12) & 0xff);
if (bad_address(table))
goto bad;
pr_cont("P:%016lx ", *table);
out:
pr_cont("\n");
return;
bad:
pr_cont("BAD\n");
}
static void dump_fault_info(struct pt_regs *regs)
{
unsigned long asce;
pr_alert("Failing address: %016lx TEID: %016lx\n",
regs->int_parm_long & __FAIL_ADDR_MASK, regs->int_parm_long);
pr_alert("Fault in ");
switch (regs->int_parm_long & 3) {
case 3:
pr_cont("home space ");
break;
case 2:
pr_cont("secondary space ");
break;
case 1:
pr_cont("access register ");
break;
case 0:
pr_cont("primary space ");
break;
}
pr_cont("mode while using ");
if (!user_space_fault(regs)) {
asce = S390_lowcore.kernel_asce;
pr_cont("kernel ");
}
#ifdef CONFIG_PGSTE
else if ((current->flags & PF_VCPU) && S390_lowcore.gmap) {
struct gmap *gmap = (struct gmap *)S390_lowcore.gmap;
asce = gmap->asce;
pr_cont("gmap ");
}
#endif
else {
asce = S390_lowcore.user_asce;
pr_cont("user ");
}
pr_cont("ASCE.\n");
dump_pagetable(asce, regs->int_parm_long & __FAIL_ADDR_MASK);
}
int show_unhandled_signals = 1;
void report_user_fault(struct pt_regs *regs, long signr, int is_mm_fault)
{
if ((task_pid_nr(current) > 1) && !show_unhandled_signals)
return;
if (!unhandled_signal(current, signr))
return;
if (!printk_ratelimit())
return;
printk(KERN_ALERT "User process fault: interruption code %04x ilc:%d ",
regs->int_code & 0xffff, regs->int_code >> 17);
print_vma_addr(KERN_CONT "in ", regs->psw.addr);
printk(KERN_CONT "\n");
if (is_mm_fault)
dump_fault_info(regs);
show_regs(regs);
}
/*
* 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, int si_code)
{
struct siginfo si;
report_user_fault(regs, SIGSEGV, 1);
si.si_signo = SIGSEGV;
si.si_errno = 0;
si.si_code = si_code;
si.si_addr = (void __user *)(regs->int_parm_long & __FAIL_ADDR_MASK);
force_sig_info(SIGSEGV, &si, current);
}
static noinline void do_no_context(struct pt_regs *regs)
{
const struct exception_table_entry *fixup;
/* Are we prepared to handle this kernel fault? */
fixup = search_exception_tables(regs->psw.addr);
if (fixup) {
regs->psw.addr = extable_fixup(fixup);
return;
}
/*
* Oops. The kernel tried to access some bad page. We'll have to
* terminate things with extreme prejudice.
*/
s390/uaccess: rework uaccess code - fix locking issues The current uaccess code uses a page table walk in some circumstances, e.g. in case of the in atomic futex operations or if running on old hardware which doesn't support the mvcos instruction. However it turned out that the page table walk code does not correctly lock page tables when accessing page table entries. In other words: a different cpu may invalidate a page table entry while the current cpu inspects the pte. This may lead to random data corruption. Adding correct locking however isn't trivial for all uaccess operations. Especially copy_in_user() is problematic since that requires to hold at least two locks, but must be protected against ABBA deadlock when a different cpu also performs a copy_in_user() operation. So the solution is a different approach where we change address spaces: User space runs in primary address mode, or access register mode within vdso code, like it currently already does. The kernel usually also runs in home space mode, however when accessing user space the kernel switches to primary or secondary address mode if the mvcos instruction is not available or if a compare-and-swap (futex) instruction on a user space address is performed. KVM however is special, since that requires the kernel to run in home address space while implicitly accessing user space with the sie instruction. So we end up with: User space: - runs in primary or access register mode - cr1 contains the user asce - cr7 contains the user asce - cr13 contains the kernel asce Kernel space: - runs in home space mode - cr1 contains the user or kernel asce -> the kernel asce is loaded when a uaccess requires primary or secondary address mode - cr7 contains the user or kernel asce, (changed with set_fs()) - cr13 contains the kernel asce In case of uaccess the kernel changes to: - primary space mode in case of a uaccess (copy_to_user) and uses e.g. the mvcp instruction to access user space. However the kernel will stay in home space mode if the mvcos instruction is available - secondary space mode in case of futex atomic operations, so that the instructions come from primary address space and data from secondary space In case of kvm the kernel runs in home space mode, but cr1 gets switched to contain the gmap asce before the sie instruction gets executed. When the sie instruction is finished cr1 will be switched back to contain the user asce. A context switch between two processes will always load the kernel asce for the next process in cr1. So the first exit to user space is a bit more expensive (one extra load control register instruction) than before, however keeps the code rather simple. In sum this means there is no need to perform any error prone page table walks anymore when accessing user space. The patch seems to be rather large, however it mainly removes the the page table walk code and restores the previously deleted "standard" uaccess code, with a couple of changes. The uaccess without mvcos mode can be enforced with the "uaccess_primary" kernel parameter. Reported-by: Christian Borntraeger <borntraeger@de.ibm.com> Signed-off-by: Heiko Carstens <heiko.carstens@de.ibm.com> Signed-off-by: Martin Schwidefsky <schwidefsky@de.ibm.com>
2014-03-21 17:42:25 +08:00
if (!user_space_fault(regs))
printk(KERN_ALERT "Unable to handle kernel pointer dereference"
" in virtual kernel address space\n");
else
printk(KERN_ALERT "Unable to handle kernel paging request"
" in virtual user address space\n");
dump_fault_info(regs);
die(regs, "Oops");
do_exit(SIGKILL);
}
static noinline void do_low_address(struct pt_regs *regs)
{
/* 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 (regs, "Low-address protection");
do_exit(SIGKILL);
}
do_no_context(regs);
}
static noinline void do_sigbus(struct pt_regs *regs)
{
struct task_struct *tsk = current;
struct siginfo si;
/*
* Send a sigbus, regardless of whether we were in kernel
* or user mode.
*/
si.si_signo = SIGBUS;
si.si_errno = 0;
si.si_code = BUS_ADRERR;
si.si_addr = (void __user *)(regs->int_parm_long & __FAIL_ADDR_MASK);
force_sig_info(SIGBUS, &si, tsk);
}
static noinline void do_fault_error(struct pt_regs *regs, int fault)
{
int si_code;
switch (fault) {
case VM_FAULT_BADACCESS:
case VM_FAULT_BADMAP:
/* Bad memory access. Check if it is kernel or user space. */
if (user_mode(regs)) {
/* User mode accesses just cause a SIGSEGV */
si_code = (fault == VM_FAULT_BADMAP) ?
SEGV_MAPERR : SEGV_ACCERR;
do_sigsegv(regs, si_code);
return;
}
case VM_FAULT_BADCONTEXT:
case VM_FAULT_PFAULT:
do_no_context(regs);
break;
case VM_FAULT_SIGNAL:
if (!user_mode(regs))
do_no_context(regs);
break;
default: /* fault & VM_FAULT_ERROR */
if (fault & VM_FAULT_OOM) {
if (!user_mode(regs))
do_no_context(regs);
else
pagefault_out_of_memory();
vm: add VM_FAULT_SIGSEGV handling support The core VM already knows about VM_FAULT_SIGBUS, but cannot return a "you should SIGSEGV" error, because the SIGSEGV case was generally handled by the caller - usually the architecture fault handler. That results in lots of duplication - all the architecture fault handlers end up doing very similar "look up vma, check permissions, do retries etc" - but it generally works. However, there are cases where the VM actually wants to SIGSEGV, and applications _expect_ SIGSEGV. In particular, when accessing the stack guard page, libsigsegv expects a SIGSEGV. And it usually got one, because the stack growth is handled by that duplicated architecture fault handler. However, when the generic VM layer started propagating the error return from the stack expansion in commit fee7e49d4514 ("mm: propagate error from stack expansion even for guard page"), that now exposed the existing VM_FAULT_SIGBUS result to user space. And user space really expected SIGSEGV, not SIGBUS. To fix that case, we need to add a VM_FAULT_SIGSEGV, and teach all those duplicate architecture fault handlers about it. They all already have the code to handle SIGSEGV, so it's about just tying that new return value to the existing code, but it's all a bit annoying. This is the mindless minimal patch to do this. A more extensive patch would be to try to gather up the mostly shared fault handling logic into one generic helper routine, and long-term we really should do that cleanup. Just from this patch, you can generally see that most architectures just copied (directly or indirectly) the old x86 way of doing things, but in the meantime that original x86 model has been improved to hold the VM semaphore for shorter times etc and to handle VM_FAULT_RETRY and other "newer" things, so it would be a good idea to bring all those improvements to the generic case and teach other architectures about them too. Reported-and-tested-by: Takashi Iwai <tiwai@suse.de> Tested-by: Jan Engelhardt <jengelh@inai.de> Acked-by: Heiko Carstens <heiko.carstens@de.ibm.com> # "s390 still compiles and boots" Cc: linux-arch@vger.kernel.org Cc: stable@vger.kernel.org Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2015-01-30 02:51:32 +08:00
} else if (fault & VM_FAULT_SIGSEGV) {
/* Kernel mode? Handle exceptions or die */
if (!user_mode(regs))
do_no_context(regs);
else
do_sigsegv(regs, SEGV_MAPERR);
} else if (fault & VM_FAULT_SIGBUS) {
/* Kernel mode? Handle exceptions or die */
if (!user_mode(regs))
do_no_context(regs);
else
do_sigbus(regs);
} 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)
{
#ifdef CONFIG_PGSTE
struct gmap *gmap;
#endif
struct task_struct *tsk;
struct mm_struct *mm;
struct vm_area_struct *vma;
unsigned long trans_exc_code;
unsigned long address;
unsigned int flags;
int fault;
tsk = current;
/*
* The instruction that caused the program check has
* been nullified. Don't signal single step via SIGTRAP.
*/
clear_pt_regs_flag(regs, PIF_PER_TRAP);
if (notify_page_fault(regs))
return 0;
mm = tsk->mm;
trans_exc_code = regs->int_parm_long;
/*
* 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;
mm/fault, arch: Use pagefault_disable() to check for disabled pagefaults in the handler Introduce faulthandler_disabled() and use it to check for irq context and disabled pagefaults (via pagefault_disable()) in the pagefault handlers. Please note that we keep the in_atomic() checks in place - to detect whether in irq context (in which case preemption is always properly disabled). In contrast, preempt_disable() should never be used to disable pagefaults. With !CONFIG_PREEMPT_COUNT, preempt_disable() doesn't modify the preempt counter, and therefore the result of in_atomic() differs. We validate that condition by using might_fault() checks when calling might_sleep(). Therefore, add a comment to faulthandler_disabled(), describing why this is needed. faulthandler_disabled() and pagefault_disable() are defined in linux/uaccess.h, so let's properly add that include to all relevant files. This patch is based on a patch from Thomas Gleixner. Reviewed-and-tested-by: Thomas Gleixner <tglx@linutronix.de> Signed-off-by: David Hildenbrand <dahi@linux.vnet.ibm.com> Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org> Cc: David.Laight@ACULAB.COM Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: airlied@linux.ie Cc: akpm@linux-foundation.org Cc: benh@kernel.crashing.org Cc: bigeasy@linutronix.de Cc: borntraeger@de.ibm.com Cc: daniel.vetter@intel.com Cc: heiko.carstens@de.ibm.com Cc: herbert@gondor.apana.org.au Cc: hocko@suse.cz Cc: hughd@google.com Cc: mst@redhat.com Cc: paulus@samba.org Cc: ralf@linux-mips.org Cc: schwidefsky@de.ibm.com Cc: yang.shi@windriver.com Link: http://lkml.kernel.org/r/1431359540-32227-7-git-send-email-dahi@linux.vnet.ibm.com Signed-off-by: Ingo Molnar <mingo@kernel.org>
2015-05-11 23:52:11 +08:00
if (unlikely(!user_space_fault(regs) || faulthandler_disabled() || !mm))
goto out;
address = trans_exc_code & __FAIL_ADDR_MASK;
perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS, 1, regs, address);
flags = FAULT_FLAG_ALLOW_RETRY | FAULT_FLAG_KILLABLE;
if (user_mode(regs))
flags |= FAULT_FLAG_USER;
if (access == VM_WRITE || (trans_exc_code & store_indication) == 0x400)
flags |= FAULT_FLAG_WRITE;
down_read(&mm->mmap_sem);
#ifdef CONFIG_PGSTE
gmap = (current->flags & PF_VCPU) ?
(struct gmap *) S390_lowcore.gmap : NULL;
if (gmap) {
current->thread.gmap_addr = address;
s390/mm: add shadow gmap support For a nested KVM guest the outer KVM host needs to create shadow page tables for the nested guest. This patch adds the basic support to the guest address space (gmap) code. For each guest address space the inner KVM host creates, the first outer KVM host needs to create shadow page tables. The address space is identified by the ASCE loaded into the control register 1 at the time the inner SIE instruction for the second nested KVM guest is executed. The outer KVM host creates the shadow tables starting with the table identified by the ASCE on a on-demand basis. The outer KVM host will get repeated faults for all the shadow tables needed to run the second KVM guest. While a shadow page table for the second KVM guest is active the access to the origin region, segment and page tables needs to be restricted for the first KVM guest. For region and segment and page tables the first KVM guest may read the memory, but write attempt has to lead to an unshadow. This is done using the page invalid and read-only bits in the page table of the first KVM guest. If the first guest re-accesses one of the origin pages of a shadow, it gets a fault and the affected parts of the shadow page table hierarchy needs to be removed again. PGSTE tables don't have to be shadowed, as all interpretation assist can't deal with the invalid bits in the shadow pte being set differently than the original ones provided by the first KVM guest. Many bug fixes and improvements by David Hildenbrand. Reviewed-by: David Hildenbrand <dahi@linux.vnet.ibm.com> Signed-off-by: Martin Schwidefsky <schwidefsky@de.ibm.com> Signed-off-by: Christian Borntraeger <borntraeger@de.ibm.com>
2016-03-08 19:12:18 +08:00
current->thread.gmap_write_flag = !!(flags & FAULT_FLAG_WRITE);
current->thread.gmap_int_code = regs->int_code & 0xffff;
address = __gmap_translate(gmap, address);
if (address == -EFAULT) {
fault = VM_FAULT_BADMAP;
goto out_up;
}
if (gmap->pfault_enabled)
flags |= FAULT_FLAG_RETRY_NOWAIT;
}
#endif
retry:
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>
2007-02-06 04:18:17 +08:00
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, flags);
/* No reason to continue if interrupted by SIGKILL. */
if ((fault & VM_FAULT_RETRY) && fatal_signal_pending(current)) {
fault = VM_FAULT_SIGNAL;
goto out;
}
if (unlikely(fault & VM_FAULT_ERROR))
goto out_up;
/*
* Major/minor page fault accounting is only done on the
* initial attempt. If we go through a retry, it is extremely
* likely that the page will be found in page cache at that point.
*/
if (flags & FAULT_FLAG_ALLOW_RETRY) {
if (fault & VM_FAULT_MAJOR) {
tsk->maj_flt++;
perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS_MAJ, 1,
regs, address);
} else {
tsk->min_flt++;
perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS_MIN, 1,
regs, address);
}
if (fault & VM_FAULT_RETRY) {
#ifdef CONFIG_PGSTE
if (gmap && (flags & FAULT_FLAG_RETRY_NOWAIT)) {
/* FAULT_FLAG_RETRY_NOWAIT has been set,
* mmap_sem has not been released */
current->thread.gmap_pfault = 1;
fault = VM_FAULT_PFAULT;
goto out_up;
}
#endif
/* Clear FAULT_FLAG_ALLOW_RETRY to avoid any risk
* of starvation. */
flags &= ~(FAULT_FLAG_ALLOW_RETRY |
FAULT_FLAG_RETRY_NOWAIT);
flags |= FAULT_FLAG_TRIED;
down_read(&mm->mmap_sem);
goto retry;
}
}
#ifdef CONFIG_PGSTE
if (gmap) {
address = __gmap_link(gmap, current->thread.gmap_addr,
address);
if (address == -EFAULT) {
fault = VM_FAULT_BADMAP;
goto out_up;
}
if (address == -ENOMEM) {
fault = VM_FAULT_OOM;
goto out_up;
}
}
#endif
fault = 0;
out_up:
up_read(&mm->mmap_sem);
out:
return fault;
}
void do_protection_exception(struct pt_regs *regs)
{
unsigned long trans_exc_code;
int fault;
trans_exc_code = regs->int_parm_long;
/*
* Protection exceptions are suppressing, decrement psw address.
* The exception to this rule are aborted transactions, for these
* the PSW already points to the correct location.
*/
if (!(regs->int_code & 0x200))
regs->psw.addr = __rewind_psw(regs->psw, regs->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);
return;
}
fault = do_exception(regs, VM_WRITE);
if (unlikely(fault))
do_fault_error(regs, fault);
}
NOKPROBE_SYMBOL(do_protection_exception);
void do_dat_exception(struct pt_regs *regs)
{
int access, fault;
access = VM_READ | VM_EXEC | VM_WRITE;
fault = do_exception(regs, access);
if (unlikely(fault))
do_fault_error(regs, fault);
}
NOKPROBE_SYMBOL(do_dat_exception);
#ifdef CONFIG_PFAULT
/*
* 'pfault' pseudo page faults routines.
*/
static int pfault_disable;
static int __init nopfault(char *str)
{
pfault_disable = 1;
return 1;
}
__setup("nopfault", nopfault);
struct pfault_refbk {
u16 refdiagc;
u16 reffcode;
u16 refdwlen;
u16 refversn;
u64 refgaddr;
u64 refselmk;
u64 refcmpmk;
u64 reserved;
} __attribute__ ((packed, aligned(8)));
int pfault_init(void)
{
struct pfault_refbk refbk = {
.refdiagc = 0x258,
.reffcode = 0,
.refdwlen = 5,
.refversn = 2,
.refgaddr = __LC_LPP,
.refselmk = 1ULL << 48,
.refcmpmk = 1ULL << 48,
.reserved = __PF_RES_FIELD };
int rc;
if (pfault_disable)
return -1;
diag_stat_inc(DIAG_STAT_X258);
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");
return rc;
}
void pfault_fini(void)
{
struct pfault_refbk refbk = {
.refdiagc = 0x258,
.reffcode = 1,
.refdwlen = 5,
.refversn = 2,
};
if (pfault_disable)
return;
diag_stat_inc(DIAG_STAT_X258);
asm volatile(
" diag %0,0,0x258\n"
"0:\n"
EX_TABLE(0b,0b)
: : "a" (&refbk), "m" (refbk) : "cc");
}
static DEFINE_SPINLOCK(pfault_lock);
static LIST_HEAD(pfault_list);
#define PF_COMPLETE 0x0080
/*
* The mechanism of our pfault code: if Linux is running as guest, runs a user
* space process and the user space process accesses a page that the host has
* paged out we get a pfault interrupt.
*
* This allows us, within the guest, to schedule a different process. Without
* this mechanism the host would have to suspend the whole virtual cpu until
* the page has been paged in.
*
* So when we get such an interrupt then we set the state of the current task
* to uninterruptible and also set the need_resched flag. Both happens within
* interrupt context(!). If we later on want to return to user space we
* recognize the need_resched flag and then call schedule(). It's not very
* obvious how this works...
*
* Of course we have a lot of additional fun with the completion interrupt (->
* host signals that a page of a process has been paged in and the process can
* continue to run). This interrupt can arrive on any cpu and, since we have
* virtual cpus, actually appear before the interrupt that signals that a page
* is missing.
*/
static void pfault_interrupt(struct ext_code ext_code,
unsigned int param32, unsigned long param64)
{
struct task_struct *tsk;
__u16 subcode;
pid_t pid;
/*
* Get the external interruption subcode & pfault initial/completion
* signal bit. VM stores this in the 'cpu address' field associated
* with the external interrupt.
*/
subcode = ext_code.subcode;
if ((subcode & 0xff00) != __SUBCODE_MASK)
return;
inc_irq_stat(IRQEXT_PFL);
/* Get the token (= pid of the affected task). */
pid = param64 & LPP_PFAULT_PID_MASK;
rcu_read_lock();
tsk = find_task_by_pid_ns(pid, &init_pid_ns);
if (tsk)
get_task_struct(tsk);
rcu_read_unlock();
if (!tsk)
return;
spin_lock(&pfault_lock);
if (subcode & PF_COMPLETE) {
/* signal bit is set -> a page has been swapped in by VM */
if (tsk->thread.pfault_wait == 1) {
/* 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;
list_del(&tsk->thread.list);
wake_up_process(tsk);
put_task_struct(tsk);
} else {
/* Completion interrupt was faster than initial
* interrupt. Set pfault_wait to -1 so the initial
* interrupt doesn't put the task to sleep.
* If the task is not running, ignore the completion
* interrupt since it must be a leftover of a PFAULT
* CANCEL operation which didn't remove all pending
* completion interrupts. */
if (tsk->state == TASK_RUNNING)
tsk->thread.pfault_wait = -1;
}
} else {
/* signal bit not set -> a real page is missing. */
if (WARN_ON_ONCE(tsk != current))
goto out;
if (tsk->thread.pfault_wait == 1) {
/* Already on the list with a reference: put to sleep */
goto block;
} else if (tsk->thread.pfault_wait == -1) {
/* Completion interrupt was faster than the initial
* interrupt (pfault_wait == -1). Set pfault_wait
* back to zero and exit. */
tsk->thread.pfault_wait = 0;
} else {
/* Initial interrupt arrived before completion
* interrupt. Let the task sleep.
* An extra task reference is needed since a different
* cpu may set the task state to TASK_RUNNING again
* before the scheduler is reached. */
get_task_struct(tsk);
tsk->thread.pfault_wait = 1;
list_add(&tsk->thread.list, &pfault_list);
block:
/* Since this must be a userspace fault, there
* is no kernel task state to trample. Rely on the
* return to userspace schedule() to block. */
__set_current_state(TASK_UNINTERRUPTIBLE);
set_tsk_need_resched(tsk);
}
}
out:
spin_unlock(&pfault_lock);
put_task_struct(tsk);
}
2013-06-19 05:04:52 +08:00
static int pfault_cpu_notify(struct notifier_block *self, unsigned long action,
void *hcpu)
{
struct thread_struct *thread, *next;
struct task_struct *tsk;
switch (action & ~CPU_TASKS_FROZEN) {
case CPU_DEAD:
spin_lock_irq(&pfault_lock);
list_for_each_entry_safe(thread, next, &pfault_list, list) {
thread->pfault_wait = 0;
list_del(&thread->list);
tsk = container_of(thread, struct task_struct, thread);
wake_up_process(tsk);
put_task_struct(tsk);
}
spin_unlock_irq(&pfault_lock);
break;
default:
break;
}
return NOTIFY_OK;
}
static int __init pfault_irq_init(void)
{
int rc;
rc = register_external_irq(EXT_IRQ_CP_SERVICE, pfault_interrupt);
if (rc)
goto out_extint;
rc = pfault_init() == 0 ? 0 : -EOPNOTSUPP;
if (rc)
goto out_pfault;
irq_subclass_register(IRQ_SUBCLASS_SERVICE_SIGNAL);
hotcpu_notifier(pfault_cpu_notify, 0);
return 0;
out_pfault:
unregister_external_irq(EXT_IRQ_CP_SERVICE, pfault_interrupt);
out_extint:
pfault_disable = 1;
return rc;
}
early_initcall(pfault_irq_init);
#endif /* CONFIG_PFAULT */