linux/arch/arm/mm/fault.c
Kautuk Consul 8878a539ff ARM: 7178/1: fault.c: Port OOM changes into do_page_fault
Commit d065bd810b
(mm: retry page fault when blocking on disk transfer) and
commit 37b23e0525
(x86,mm: make pagefault killable)

The above commits introduced changes into the x86 pagefault handler
for making the page fault handler retryable as well as killable.

These changes reduce the mmap_sem hold time, which is crucial
during OOM killer invocation.

Port these changes to ARM.

Without these changes, my ARM board encounters many hang and livelock
scenarios.
After applying this patch, OOM feature performance improves according to
my testing.

Signed-off-by: Kautuk Consul <consul.kautuk@gmail.com>
Signed-off-by: Russell King <rmk+kernel@arm.linux.org.uk>
2011-12-06 11:15:26 +00:00

686 lines
18 KiB
C

/*
* linux/arch/arm/mm/fault.c
*
* Copyright (C) 1995 Linus Torvalds
* Modifications for ARM processor (c) 1995-2004 Russell King
*
* This program is free software; you can redistribute it and/or modify
* it under the terms of the GNU General Public License version 2 as
* published by the Free Software Foundation.
*/
#include <linux/module.h>
#include <linux/signal.h>
#include <linux/mm.h>
#include <linux/hardirq.h>
#include <linux/init.h>
#include <linux/kprobes.h>
#include <linux/uaccess.h>
#include <linux/page-flags.h>
#include <linux/sched.h>
#include <linux/highmem.h>
#include <linux/perf_event.h>
#include <asm/exception.h>
#include <asm/system.h>
#include <asm/pgtable.h>
#include <asm/tlbflush.h>
#include "fault.h"
/*
* Fault status register encodings. We steal bit 31 for our own purposes.
*/
#define FSR_LNX_PF (1 << 31)
#define FSR_WRITE (1 << 11)
#define FSR_FS4 (1 << 10)
#define FSR_FS3_0 (15)
static inline int fsr_fs(unsigned int fsr)
{
return (fsr & FSR_FS3_0) | (fsr & FSR_FS4) >> 6;
}
#ifdef CONFIG_MMU
#ifdef CONFIG_KPROBES
static inline int notify_page_fault(struct pt_regs *regs, unsigned int fsr)
{
int ret = 0;
if (!user_mode(regs)) {
/* kprobe_running() needs smp_processor_id() */
preempt_disable();
if (kprobe_running() && kprobe_fault_handler(regs, fsr))
ret = 1;
preempt_enable();
}
return ret;
}
#else
static inline int notify_page_fault(struct pt_regs *regs, unsigned int fsr)
{
return 0;
}
#endif
/*
* This is useful to dump out the page tables associated with
* 'addr' in mm 'mm'.
*/
void show_pte(struct mm_struct *mm, unsigned long addr)
{
pgd_t *pgd;
if (!mm)
mm = &init_mm;
printk(KERN_ALERT "pgd = %p\n", mm->pgd);
pgd = pgd_offset(mm, addr);
printk(KERN_ALERT "[%08lx] *pgd=%08llx",
addr, (long long)pgd_val(*pgd));
do {
pud_t *pud;
pmd_t *pmd;
pte_t *pte;
if (pgd_none(*pgd))
break;
if (pgd_bad(*pgd)) {
printk("(bad)");
break;
}
pud = pud_offset(pgd, addr);
if (PTRS_PER_PUD != 1)
printk(", *pud=%08llx", (long long)pud_val(*pud));
if (pud_none(*pud))
break;
if (pud_bad(*pud)) {
printk("(bad)");
break;
}
pmd = pmd_offset(pud, addr);
if (PTRS_PER_PMD != 1)
printk(", *pmd=%08llx", (long long)pmd_val(*pmd));
if (pmd_none(*pmd))
break;
if (pmd_bad(*pmd)) {
printk("(bad)");
break;
}
/* We must not map this if we have highmem enabled */
if (PageHighMem(pfn_to_page(pmd_val(*pmd) >> PAGE_SHIFT)))
break;
pte = pte_offset_map(pmd, addr);
printk(", *pte=%08llx", (long long)pte_val(*pte));
printk(", *ppte=%08llx",
(long long)pte_val(pte[PTE_HWTABLE_PTRS]));
pte_unmap(pte);
} while(0);
printk("\n");
}
#else /* CONFIG_MMU */
void show_pte(struct mm_struct *mm, unsigned long addr)
{ }
#endif /* CONFIG_MMU */
/*
* Oops. The kernel tried to access some page that wasn't present.
*/
static void
__do_kernel_fault(struct mm_struct *mm, unsigned long addr, unsigned int fsr,
struct pt_regs *regs)
{
/*
* Are we prepared to handle this kernel fault?
*/
if (fixup_exception(regs))
return;
/*
* No handler, we'll have to terminate things with extreme prejudice.
*/
bust_spinlocks(1);
printk(KERN_ALERT
"Unable to handle kernel %s at virtual address %08lx\n",
(addr < PAGE_SIZE) ? "NULL pointer dereference" :
"paging request", addr);
show_pte(mm, addr);
die("Oops", regs, fsr);
bust_spinlocks(0);
do_exit(SIGKILL);
}
/*
* Something tried to access memory that isn't in our memory map..
* User mode accesses just cause a SIGSEGV
*/
static void
__do_user_fault(struct task_struct *tsk, unsigned long addr,
unsigned int fsr, unsigned int sig, int code,
struct pt_regs *regs)
{
struct siginfo si;
#ifdef CONFIG_DEBUG_USER
if (user_debug & UDBG_SEGV) {
printk(KERN_DEBUG "%s: unhandled page fault (%d) at 0x%08lx, code 0x%03x\n",
tsk->comm, sig, addr, fsr);
show_pte(tsk->mm, addr);
show_regs(regs);
}
#endif
tsk->thread.address = addr;
tsk->thread.error_code = fsr;
tsk->thread.trap_no = 14;
si.si_signo = sig;
si.si_errno = 0;
si.si_code = code;
si.si_addr = (void __user *)addr;
force_sig_info(sig, &si, tsk);
}
void do_bad_area(unsigned long addr, unsigned int fsr, struct pt_regs *regs)
{
struct task_struct *tsk = current;
struct mm_struct *mm = tsk->active_mm;
/*
* If we are in kernel mode at this point, we
* have no context to handle this fault with.
*/
if (user_mode(regs))
__do_user_fault(tsk, addr, fsr, SIGSEGV, SEGV_MAPERR, regs);
else
__do_kernel_fault(mm, addr, fsr, regs);
}
#ifdef CONFIG_MMU
#define VM_FAULT_BADMAP 0x010000
#define VM_FAULT_BADACCESS 0x020000
/*
* Check that the permissions on the VMA allow for the fault which occurred.
* If we encountered a write fault, we must have write permission, otherwise
* we allow any permission.
*/
static inline bool access_error(unsigned int fsr, struct vm_area_struct *vma)
{
unsigned int mask = VM_READ | VM_WRITE | VM_EXEC;
if (fsr & FSR_WRITE)
mask = VM_WRITE;
if (fsr & FSR_LNX_PF)
mask = VM_EXEC;
return vma->vm_flags & mask ? false : true;
}
static int __kprobes
__do_page_fault(struct mm_struct *mm, unsigned long addr, unsigned int fsr,
unsigned int flags, struct task_struct *tsk)
{
struct vm_area_struct *vma;
int fault;
vma = find_vma(mm, addr);
fault = VM_FAULT_BADMAP;
if (unlikely(!vma))
goto out;
if (unlikely(vma->vm_start > addr))
goto check_stack;
/*
* Ok, we have a good vm_area for this
* memory access, so we can handle it.
*/
good_area:
if (access_error(fsr, vma)) {
fault = VM_FAULT_BADACCESS;
goto out;
}
return handle_mm_fault(mm, vma, addr & PAGE_MASK, flags);
check_stack:
if (vma->vm_flags & VM_GROWSDOWN && !expand_stack(vma, addr))
goto good_area;
out:
return fault;
}
static int __kprobes
do_page_fault(unsigned long addr, unsigned int fsr, struct pt_regs *regs)
{
struct task_struct *tsk;
struct mm_struct *mm;
int fault, sig, code;
int write = fsr & FSR_WRITE;
unsigned int flags = FAULT_FLAG_ALLOW_RETRY | FAULT_FLAG_KILLABLE |
(write ? FAULT_FLAG_WRITE : 0);
if (notify_page_fault(regs, fsr))
return 0;
tsk = current;
mm = tsk->mm;
/* Enable interrupts if they were enabled in the parent context. */
if (interrupts_enabled(regs))
local_irq_enable();
/*
* If we're in an interrupt or have no user
* context, we must not take the fault..
*/
if (in_atomic() || !mm)
goto no_context;
/*
* As per x86, we may deadlock here. However, since the kernel only
* validly references user space from well defined areas of the code,
* we can bug out early if this is from code which shouldn't.
*/
if (!down_read_trylock(&mm->mmap_sem)) {
if (!user_mode(regs) && !search_exception_tables(regs->ARM_pc))
goto no_context;
retry:
down_read(&mm->mmap_sem);
} else {
/*
* The above down_read_trylock() might have succeeded in
* which case, we'll have missed the might_sleep() from
* down_read()
*/
might_sleep();
#ifdef CONFIG_DEBUG_VM
if (!user_mode(regs) &&
!search_exception_tables(regs->ARM_pc))
goto no_context;
#endif
}
fault = __do_page_fault(mm, addr, fsr, flags, tsk);
/* If we need to retry but a fatal signal is pending, handle the
* signal first. We do not need to release the mmap_sem because
* it would already be released in __lock_page_or_retry in
* mm/filemap.c. */
if ((fault & VM_FAULT_RETRY) && fatal_signal_pending(current))
return 0;
/*
* 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.
*/
perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS, 1, regs, addr);
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, addr);
} else {
tsk->min_flt++;
perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS_MIN, 1,
regs, addr);
}
if (fault & VM_FAULT_RETRY) {
/* Clear FAULT_FLAG_ALLOW_RETRY to avoid any risk
* of starvation. */
flags &= ~FAULT_FLAG_ALLOW_RETRY;
goto retry;
}
}
up_read(&mm->mmap_sem);
/*
* Handle the "normal" case first - VM_FAULT_MAJOR / VM_FAULT_MINOR
*/
if (likely(!(fault & (VM_FAULT_ERROR | VM_FAULT_BADMAP | VM_FAULT_BADACCESS))))
return 0;
if (fault & VM_FAULT_OOM) {
/*
* We ran out of memory, call the OOM killer, and return to
* userspace (which will retry the fault, or kill us if we
* got oom-killed)
*/
pagefault_out_of_memory();
return 0;
}
/*
* If we are in kernel mode at this point, we
* have no context to handle this fault with.
*/
if (!user_mode(regs))
goto no_context;
if (fault & VM_FAULT_SIGBUS) {
/*
* We had some memory, but were unable to
* successfully fix up this page fault.
*/
sig = SIGBUS;
code = BUS_ADRERR;
} else {
/*
* Something tried to access memory that
* isn't in our memory map..
*/
sig = SIGSEGV;
code = fault == VM_FAULT_BADACCESS ?
SEGV_ACCERR : SEGV_MAPERR;
}
__do_user_fault(tsk, addr, fsr, sig, code, regs);
return 0;
no_context:
__do_kernel_fault(mm, addr, fsr, regs);
return 0;
}
#else /* CONFIG_MMU */
static int
do_page_fault(unsigned long addr, unsigned int fsr, struct pt_regs *regs)
{
return 0;
}
#endif /* CONFIG_MMU */
/*
* First Level Translation Fault Handler
*
* We enter here because the first level page table doesn't contain
* a valid entry for the address.
*
* If the address is in kernel space (>= TASK_SIZE), then we are
* probably faulting in the vmalloc() area.
*
* If the init_task's first level page tables contains the relevant
* entry, we copy the it to this task. If not, we send the process
* a signal, fixup the exception, or oops the kernel.
*
* NOTE! We MUST NOT take any locks for this case. We may be in an
* interrupt or a critical region, and should only copy the information
* from the master page table, nothing more.
*/
#ifdef CONFIG_MMU
static int __kprobes
do_translation_fault(unsigned long addr, unsigned int fsr,
struct pt_regs *regs)
{
unsigned int index;
pgd_t *pgd, *pgd_k;
pud_t *pud, *pud_k;
pmd_t *pmd, *pmd_k;
if (addr < TASK_SIZE)
return do_page_fault(addr, fsr, regs);
if (user_mode(regs))
goto bad_area;
index = pgd_index(addr);
/*
* FIXME: CP15 C1 is write only on ARMv3 architectures.
*/
pgd = cpu_get_pgd() + index;
pgd_k = init_mm.pgd + index;
if (pgd_none(*pgd_k))
goto bad_area;
if (!pgd_present(*pgd))
set_pgd(pgd, *pgd_k);
pud = pud_offset(pgd, addr);
pud_k = pud_offset(pgd_k, addr);
if (pud_none(*pud_k))
goto bad_area;
if (!pud_present(*pud))
set_pud(pud, *pud_k);
pmd = pmd_offset(pud, addr);
pmd_k = pmd_offset(pud_k, addr);
/*
* On ARM one Linux PGD entry contains two hardware entries (see page
* tables layout in pgtable.h). We normally guarantee that we always
* fill both L1 entries. But create_mapping() doesn't follow the rule.
* It can create inidividual L1 entries, so here we have to call
* pmd_none() check for the entry really corresponded to address, not
* for the first of pair.
*/
index = (addr >> SECTION_SHIFT) & 1;
if (pmd_none(pmd_k[index]))
goto bad_area;
copy_pmd(pmd, pmd_k);
return 0;
bad_area:
do_bad_area(addr, fsr, regs);
return 0;
}
#else /* CONFIG_MMU */
static int
do_translation_fault(unsigned long addr, unsigned int fsr,
struct pt_regs *regs)
{
return 0;
}
#endif /* CONFIG_MMU */
/*
* Some section permission faults need to be handled gracefully.
* They can happen due to a __{get,put}_user during an oops.
*/
static int
do_sect_fault(unsigned long addr, unsigned int fsr, struct pt_regs *regs)
{
do_bad_area(addr, fsr, regs);
return 0;
}
/*
* This abort handler always returns "fault".
*/
static int
do_bad(unsigned long addr, unsigned int fsr, struct pt_regs *regs)
{
return 1;
}
static struct fsr_info {
int (*fn)(unsigned long addr, unsigned int fsr, struct pt_regs *regs);
int sig;
int code;
const char *name;
} fsr_info[] = {
/*
* The following are the standard ARMv3 and ARMv4 aborts. ARMv5
* defines these to be "precise" aborts.
*/
{ do_bad, SIGSEGV, 0, "vector exception" },
{ do_bad, SIGBUS, BUS_ADRALN, "alignment exception" },
{ do_bad, SIGKILL, 0, "terminal exception" },
{ do_bad, SIGBUS, BUS_ADRALN, "alignment exception" },
{ do_bad, SIGBUS, 0, "external abort on linefetch" },
{ do_translation_fault, SIGSEGV, SEGV_MAPERR, "section translation fault" },
{ do_bad, SIGBUS, 0, "external abort on linefetch" },
{ do_page_fault, SIGSEGV, SEGV_MAPERR, "page translation fault" },
{ do_bad, SIGBUS, 0, "external abort on non-linefetch" },
{ do_bad, SIGSEGV, SEGV_ACCERR, "section domain fault" },
{ do_bad, SIGBUS, 0, "external abort on non-linefetch" },
{ do_bad, SIGSEGV, SEGV_ACCERR, "page domain fault" },
{ do_bad, SIGBUS, 0, "external abort on translation" },
{ do_sect_fault, SIGSEGV, SEGV_ACCERR, "section permission fault" },
{ do_bad, SIGBUS, 0, "external abort on translation" },
{ do_page_fault, SIGSEGV, SEGV_ACCERR, "page permission fault" },
/*
* The following are "imprecise" aborts, which are signalled by bit
* 10 of the FSR, and may not be recoverable. These are only
* supported if the CPU abort handler supports bit 10.
*/
{ do_bad, SIGBUS, 0, "unknown 16" },
{ do_bad, SIGBUS, 0, "unknown 17" },
{ do_bad, SIGBUS, 0, "unknown 18" },
{ do_bad, SIGBUS, 0, "unknown 19" },
{ do_bad, SIGBUS, 0, "lock abort" }, /* xscale */
{ do_bad, SIGBUS, 0, "unknown 21" },
{ do_bad, SIGBUS, BUS_OBJERR, "imprecise external abort" }, /* xscale */
{ do_bad, SIGBUS, 0, "unknown 23" },
{ do_bad, SIGBUS, 0, "dcache parity error" }, /* xscale */
{ do_bad, SIGBUS, 0, "unknown 25" },
{ do_bad, SIGBUS, 0, "unknown 26" },
{ do_bad, SIGBUS, 0, "unknown 27" },
{ do_bad, SIGBUS, 0, "unknown 28" },
{ do_bad, SIGBUS, 0, "unknown 29" },
{ do_bad, SIGBUS, 0, "unknown 30" },
{ do_bad, SIGBUS, 0, "unknown 31" }
};
void __init
hook_fault_code(int nr, int (*fn)(unsigned long, unsigned int, struct pt_regs *),
int sig, int code, const char *name)
{
if (nr < 0 || nr >= ARRAY_SIZE(fsr_info))
BUG();
fsr_info[nr].fn = fn;
fsr_info[nr].sig = sig;
fsr_info[nr].code = code;
fsr_info[nr].name = name;
}
/*
* Dispatch a data abort to the relevant handler.
*/
asmlinkage void __exception
do_DataAbort(unsigned long addr, unsigned int fsr, struct pt_regs *regs)
{
const struct fsr_info *inf = fsr_info + fsr_fs(fsr);
struct siginfo info;
if (!inf->fn(addr, fsr & ~FSR_LNX_PF, regs))
return;
printk(KERN_ALERT "Unhandled fault: %s (0x%03x) at 0x%08lx\n",
inf->name, fsr, addr);
info.si_signo = inf->sig;
info.si_errno = 0;
info.si_code = inf->code;
info.si_addr = (void __user *)addr;
arm_notify_die("", regs, &info, fsr, 0);
}
static struct fsr_info ifsr_info[] = {
{ do_bad, SIGBUS, 0, "unknown 0" },
{ do_bad, SIGBUS, 0, "unknown 1" },
{ do_bad, SIGBUS, 0, "debug event" },
{ do_bad, SIGSEGV, SEGV_ACCERR, "section access flag fault" },
{ do_bad, SIGBUS, 0, "unknown 4" },
{ do_translation_fault, SIGSEGV, SEGV_MAPERR, "section translation fault" },
{ do_bad, SIGSEGV, SEGV_ACCERR, "page access flag fault" },
{ do_page_fault, SIGSEGV, SEGV_MAPERR, "page translation fault" },
{ do_bad, SIGBUS, 0, "external abort on non-linefetch" },
{ do_bad, SIGSEGV, SEGV_ACCERR, "section domain fault" },
{ do_bad, SIGBUS, 0, "unknown 10" },
{ do_bad, SIGSEGV, SEGV_ACCERR, "page domain fault" },
{ do_bad, SIGBUS, 0, "external abort on translation" },
{ do_sect_fault, SIGSEGV, SEGV_ACCERR, "section permission fault" },
{ do_bad, SIGBUS, 0, "external abort on translation" },
{ do_page_fault, SIGSEGV, SEGV_ACCERR, "page permission fault" },
{ do_bad, SIGBUS, 0, "unknown 16" },
{ do_bad, SIGBUS, 0, "unknown 17" },
{ do_bad, SIGBUS, 0, "unknown 18" },
{ do_bad, SIGBUS, 0, "unknown 19" },
{ do_bad, SIGBUS, 0, "unknown 20" },
{ do_bad, SIGBUS, 0, "unknown 21" },
{ do_bad, SIGBUS, 0, "unknown 22" },
{ do_bad, SIGBUS, 0, "unknown 23" },
{ do_bad, SIGBUS, 0, "unknown 24" },
{ do_bad, SIGBUS, 0, "unknown 25" },
{ do_bad, SIGBUS, 0, "unknown 26" },
{ do_bad, SIGBUS, 0, "unknown 27" },
{ do_bad, SIGBUS, 0, "unknown 28" },
{ do_bad, SIGBUS, 0, "unknown 29" },
{ do_bad, SIGBUS, 0, "unknown 30" },
{ do_bad, SIGBUS, 0, "unknown 31" },
};
void __init
hook_ifault_code(int nr, int (*fn)(unsigned long, unsigned int, struct pt_regs *),
int sig, int code, const char *name)
{
if (nr < 0 || nr >= ARRAY_SIZE(ifsr_info))
BUG();
ifsr_info[nr].fn = fn;
ifsr_info[nr].sig = sig;
ifsr_info[nr].code = code;
ifsr_info[nr].name = name;
}
asmlinkage void __exception
do_PrefetchAbort(unsigned long addr, unsigned int ifsr, struct pt_regs *regs)
{
const struct fsr_info *inf = ifsr_info + fsr_fs(ifsr);
struct siginfo info;
if (!inf->fn(addr, ifsr | FSR_LNX_PF, regs))
return;
printk(KERN_ALERT "Unhandled prefetch abort: %s (0x%03x) at 0x%08lx\n",
inf->name, ifsr, addr);
info.si_signo = inf->sig;
info.si_errno = 0;
info.si_code = inf->code;
info.si_addr = (void __user *)addr;
arm_notify_die("", regs, &info, ifsr, 0);
}
static int __init exceptions_init(void)
{
if (cpu_architecture() >= CPU_ARCH_ARMv6) {
hook_fault_code(4, do_translation_fault, SIGSEGV, SEGV_MAPERR,
"I-cache maintenance fault");
}
if (cpu_architecture() >= CPU_ARCH_ARMv7) {
/*
* TODO: Access flag faults introduced in ARMv6K.
* Runtime check for 'K' extension is needed
*/
hook_fault_code(3, do_bad, SIGSEGV, SEGV_MAPERR,
"section access flag fault");
hook_fault_code(6, do_bad, SIGSEGV, SEGV_MAPERR,
"section access flag fault");
}
return 0;
}
arch_initcall(exceptions_init);