2006-09-27 06:13:36 +00:00
|
|
|
/*
|
|
|
|
* Page fault handler for SH with an MMU.
|
2005-04-16 22:20:36 +00:00
|
|
|
*
|
|
|
|
* Copyright (C) 1999 Niibe Yutaka
|
2012-05-14 01:27:34 +00:00
|
|
|
* Copyright (C) 2003 - 2012 Paul Mundt
|
2005-04-16 22:20:36 +00:00
|
|
|
*
|
|
|
|
* Based on linux/arch/i386/mm/fault.c:
|
|
|
|
* Copyright (C) 1995 Linus Torvalds
|
2006-09-27 06:13:36 +00:00
|
|
|
*
|
|
|
|
* This file is subject to the terms and conditions of the GNU General Public
|
|
|
|
* License. See the file "COPYING" in the main directory of this archive
|
|
|
|
* for more details.
|
2005-04-16 22:20:36 +00:00
|
|
|
*/
|
|
|
|
#include <linux/kernel.h>
|
|
|
|
#include <linux/mm.h>
|
2017-02-08 17:51:30 +00:00
|
|
|
#include <linux/sched/signal.h>
|
2006-09-27 08:03:56 +00:00
|
|
|
#include <linux/hardirq.h>
|
|
|
|
#include <linux/kprobes.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 10:02:48 +00:00
|
|
|
#include <linux/perf_event.h>
|
2012-05-14 01:27:34 +00:00
|
|
|
#include <linux/kdebug.h>
|
2015-05-11 15:52:11 +00:00
|
|
|
#include <linux/uaccess.h>
|
2008-02-07 11:18:21 +00:00
|
|
|
#include <asm/io_trapped.h>
|
2005-04-16 22:20:36 +00:00
|
|
|
#include <asm/mmu_context.h>
|
2007-02-14 05:13:10 +00:00
|
|
|
#include <asm/tlbflush.h>
|
2012-03-28 17:30:03 +00:00
|
|
|
#include <asm/traps.h>
|
2005-04-16 22:20:36 +00:00
|
|
|
|
2012-05-14 01:27:34 +00:00
|
|
|
static void
|
2019-02-06 00:38:15 +00:00
|
|
|
force_sig_info_fault(int si_signo, int si_code, unsigned long address)
|
2012-05-14 01:27:34 +00:00
|
|
|
{
|
2019-05-23 16:04:24 +00:00
|
|
|
force_sig_fault(si_signo, si_code, (void __user *)address);
|
2012-05-14 01:27:34 +00:00
|
|
|
}
|
|
|
|
|
2012-04-19 08:25:03 +00:00
|
|
|
/*
|
|
|
|
* This is useful to dump out the page tables associated with
|
|
|
|
* 'addr' in mm 'mm'.
|
|
|
|
*/
|
|
|
|
static void show_pte(struct mm_struct *mm, unsigned long addr)
|
|
|
|
{
|
|
|
|
pgd_t *pgd;
|
|
|
|
|
2012-07-24 04:15:54 +00:00
|
|
|
if (mm) {
|
2012-04-19 08:25:03 +00:00
|
|
|
pgd = mm->pgd;
|
2012-07-24 04:15:54 +00:00
|
|
|
} else {
|
2012-04-19 08:25:03 +00:00
|
|
|
pgd = get_TTB();
|
|
|
|
|
2012-07-24 04:15:54 +00:00
|
|
|
if (unlikely(!pgd))
|
|
|
|
pgd = swapper_pg_dir;
|
|
|
|
}
|
|
|
|
|
2020-06-04 23:46:48 +00:00
|
|
|
pr_alert("pgd = %p\n", pgd);
|
2012-04-19 08:25:03 +00:00
|
|
|
pgd += pgd_index(addr);
|
2020-06-04 23:46:48 +00:00
|
|
|
pr_alert("[%08lx] *pgd=%0*llx", addr, (u32)(sizeof(*pgd) * 2),
|
|
|
|
(u64)pgd_val(*pgd));
|
2012-04-19 08:25:03 +00:00
|
|
|
|
|
|
|
do {
|
2020-06-04 23:46:56 +00:00
|
|
|
p4d_t *p4d;
|
2012-04-19 08:25:03 +00:00
|
|
|
pud_t *pud;
|
|
|
|
pmd_t *pmd;
|
|
|
|
pte_t *pte;
|
|
|
|
|
|
|
|
if (pgd_none(*pgd))
|
|
|
|
break;
|
|
|
|
|
|
|
|
if (pgd_bad(*pgd)) {
|
2020-06-04 23:46:48 +00:00
|
|
|
pr_cont("(bad)");
|
2012-04-19 08:25:03 +00:00
|
|
|
break;
|
|
|
|
}
|
|
|
|
|
2020-06-04 23:46:56 +00:00
|
|
|
p4d = p4d_offset(pgd, addr);
|
|
|
|
if (PTRS_PER_P4D != 1)
|
|
|
|
pr_cont(", *p4d=%0*Lx", (u32)(sizeof(*p4d) * 2),
|
|
|
|
(u64)p4d_val(*p4d));
|
|
|
|
|
|
|
|
if (p4d_none(*p4d))
|
|
|
|
break;
|
|
|
|
|
|
|
|
if (p4d_bad(*p4d)) {
|
|
|
|
pr_cont("(bad)");
|
|
|
|
break;
|
|
|
|
}
|
|
|
|
|
|
|
|
pud = pud_offset(p4d, addr);
|
2012-04-19 08:25:03 +00:00
|
|
|
if (PTRS_PER_PUD != 1)
|
2020-06-04 23:46:48 +00:00
|
|
|
pr_cont(", *pud=%0*llx", (u32)(sizeof(*pud) * 2),
|
|
|
|
(u64)pud_val(*pud));
|
2012-04-19 08:25:03 +00:00
|
|
|
|
|
|
|
if (pud_none(*pud))
|
|
|
|
break;
|
|
|
|
|
|
|
|
if (pud_bad(*pud)) {
|
2020-06-04 23:46:48 +00:00
|
|
|
pr_cont("(bad)");
|
2012-04-19 08:25:03 +00:00
|
|
|
break;
|
|
|
|
}
|
|
|
|
|
|
|
|
pmd = pmd_offset(pud, addr);
|
|
|
|
if (PTRS_PER_PMD != 1)
|
2020-06-04 23:46:48 +00:00
|
|
|
pr_cont(", *pmd=%0*llx", (u32)(sizeof(*pmd) * 2),
|
|
|
|
(u64)pmd_val(*pmd));
|
2012-04-19 08:25:03 +00:00
|
|
|
|
|
|
|
if (pmd_none(*pmd))
|
|
|
|
break;
|
|
|
|
|
|
|
|
if (pmd_bad(*pmd)) {
|
2020-06-04 23:46:48 +00:00
|
|
|
pr_cont("(bad)");
|
2012-04-19 08:25:03 +00:00
|
|
|
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_kernel(pmd, addr);
|
2020-06-04 23:46:48 +00:00
|
|
|
pr_cont(", *pte=%0*llx", (u32)(sizeof(*pte) * 2),
|
|
|
|
(u64)pte_val(*pte));
|
2012-04-19 08:25:03 +00:00
|
|
|
} while (0);
|
|
|
|
|
2020-06-04 23:46:48 +00:00
|
|
|
pr_cont("\n");
|
2012-04-19 08:25:03 +00:00
|
|
|
}
|
|
|
|
|
2009-07-04 18:18:47 +00:00
|
|
|
static inline pmd_t *vmalloc_sync_one(pgd_t *pgd, unsigned long address)
|
|
|
|
{
|
|
|
|
unsigned index = pgd_index(address);
|
|
|
|
pgd_t *pgd_k;
|
2020-06-04 23:46:56 +00:00
|
|
|
p4d_t *p4d, *p4d_k;
|
2009-07-04 18:18:47 +00:00
|
|
|
pud_t *pud, *pud_k;
|
|
|
|
pmd_t *pmd, *pmd_k;
|
|
|
|
|
|
|
|
pgd += index;
|
|
|
|
pgd_k = init_mm.pgd + index;
|
|
|
|
|
|
|
|
if (!pgd_present(*pgd_k))
|
|
|
|
return NULL;
|
|
|
|
|
2020-06-04 23:46:56 +00:00
|
|
|
p4d = p4d_offset(pgd, address);
|
|
|
|
p4d_k = p4d_offset(pgd_k, address);
|
|
|
|
if (!p4d_present(*p4d_k))
|
|
|
|
return NULL;
|
|
|
|
|
|
|
|
pud = pud_offset(p4d, address);
|
|
|
|
pud_k = pud_offset(p4d_k, address);
|
2009-07-04 18:18:47 +00:00
|
|
|
if (!pud_present(*pud_k))
|
|
|
|
return NULL;
|
|
|
|
|
2009-12-13 14:38:50 +00:00
|
|
|
if (!pud_present(*pud))
|
|
|
|
set_pud(pud, *pud_k);
|
|
|
|
|
2009-07-04 18:18:47 +00:00
|
|
|
pmd = pmd_offset(pud, address);
|
|
|
|
pmd_k = pmd_offset(pud_k, address);
|
|
|
|
if (!pmd_present(*pmd_k))
|
|
|
|
return NULL;
|
|
|
|
|
|
|
|
if (!pmd_present(*pmd))
|
|
|
|
set_pmd(pmd, *pmd_k);
|
2009-07-13 11:38:04 +00:00
|
|
|
else {
|
|
|
|
/*
|
|
|
|
* The page tables are fully synchronised so there must
|
|
|
|
* be another reason for the fault. Return NULL here to
|
|
|
|
* signal that we have not taken care of the fault.
|
|
|
|
*/
|
2009-07-04 18:18:47 +00:00
|
|
|
BUG_ON(pmd_page(*pmd) != pmd_page(*pmd_k));
|
2009-07-13 11:38:04 +00:00
|
|
|
return NULL;
|
|
|
|
}
|
2009-07-04 18:18:47 +00:00
|
|
|
|
|
|
|
return pmd_k;
|
|
|
|
}
|
|
|
|
|
2012-05-18 11:01:16 +00:00
|
|
|
#ifdef CONFIG_SH_STORE_QUEUES
|
|
|
|
#define __FAULT_ADDR_LIMIT P3_ADDR_MAX
|
|
|
|
#else
|
|
|
|
#define __FAULT_ADDR_LIMIT VMALLOC_END
|
|
|
|
#endif
|
|
|
|
|
2009-07-04 18:18:47 +00:00
|
|
|
/*
|
|
|
|
* Handle a fault on the vmalloc or module mapping area
|
|
|
|
*/
|
|
|
|
static noinline int vmalloc_fault(unsigned long address)
|
|
|
|
{
|
|
|
|
pgd_t *pgd_k;
|
|
|
|
pmd_t *pmd_k;
|
|
|
|
pte_t *pte_k;
|
|
|
|
|
2012-05-18 10:30:05 +00:00
|
|
|
/* Make sure we are in vmalloc/module/P3 area: */
|
2012-05-18 11:01:16 +00:00
|
|
|
if (!(address >= VMALLOC_START && address < __FAULT_ADDR_LIMIT))
|
2009-07-04 18:18:47 +00:00
|
|
|
return -1;
|
|
|
|
|
|
|
|
/*
|
|
|
|
* Synchronize this task's top level page-table
|
|
|
|
* with the 'reference' page table.
|
|
|
|
*
|
|
|
|
* Do _not_ use "current" here. We might be inside
|
|
|
|
* an interrupt in the middle of a task switch..
|
|
|
|
*/
|
|
|
|
pgd_k = get_TTB();
|
2009-07-13 11:38:04 +00:00
|
|
|
pmd_k = vmalloc_sync_one(pgd_k, address);
|
2009-07-04 18:18:47 +00:00
|
|
|
if (!pmd_k)
|
|
|
|
return -1;
|
|
|
|
|
|
|
|
pte_k = pte_offset_kernel(pmd_k, address);
|
|
|
|
if (!pte_present(*pte_k))
|
|
|
|
return -1;
|
|
|
|
|
|
|
|
return 0;
|
|
|
|
}
|
|
|
|
|
2012-05-14 01:27:34 +00:00
|
|
|
static void
|
|
|
|
show_fault_oops(struct pt_regs *regs, unsigned long address)
|
|
|
|
{
|
|
|
|
if (!oops_may_print())
|
|
|
|
return;
|
|
|
|
|
2020-06-04 23:46:48 +00:00
|
|
|
pr_alert("BUG: unable to handle kernel %s at %08lx\n",
|
|
|
|
address < PAGE_SIZE ? "NULL pointer dereference"
|
|
|
|
: "paging request",
|
|
|
|
address);
|
|
|
|
pr_alert("PC:");
|
2020-06-17 14:36:32 +00:00
|
|
|
printk_address(regs->pc, 1);
|
2012-05-14 01:27:34 +00:00
|
|
|
|
|
|
|
show_pte(NULL, address);
|
|
|
|
}
|
|
|
|
|
|
|
|
static noinline void
|
2012-05-14 05:57:28 +00:00
|
|
|
no_context(struct pt_regs *regs, unsigned long error_code,
|
2012-05-14 01:27:34 +00:00
|
|
|
unsigned long address)
|
|
|
|
{
|
|
|
|
/* Are we prepared to handle this kernel fault? */
|
|
|
|
if (fixup_exception(regs))
|
|
|
|
return;
|
|
|
|
|
|
|
|
if (handle_trapped_io(regs, address))
|
|
|
|
return;
|
|
|
|
|
|
|
|
/*
|
|
|
|
* Oops. The kernel tried to access some bad page. We'll have to
|
|
|
|
* terminate things with extreme prejudice.
|
|
|
|
*/
|
|
|
|
bust_spinlocks(1);
|
|
|
|
|
|
|
|
show_fault_oops(regs, address);
|
|
|
|
|
2012-05-14 05:57:28 +00:00
|
|
|
die("Oops", regs, error_code);
|
2012-05-14 01:27:34 +00:00
|
|
|
}
|
|
|
|
|
|
|
|
static void
|
2012-05-14 05:57:28 +00:00
|
|
|
__bad_area_nosemaphore(struct pt_regs *regs, unsigned long error_code,
|
2012-05-14 01:27:34 +00:00
|
|
|
unsigned long address, int si_code)
|
|
|
|
{
|
|
|
|
/* User mode accesses just cause a SIGSEGV */
|
|
|
|
if (user_mode(regs)) {
|
|
|
|
/*
|
|
|
|
* It's possible to have interrupts off here:
|
|
|
|
*/
|
|
|
|
local_irq_enable();
|
|
|
|
|
2019-02-06 00:38:15 +00:00
|
|
|
force_sig_info_fault(SIGSEGV, si_code, address);
|
2012-05-14 01:27:34 +00:00
|
|
|
|
|
|
|
return;
|
|
|
|
}
|
|
|
|
|
2012-05-14 05:57:28 +00:00
|
|
|
no_context(regs, error_code, address);
|
2012-05-14 01:27:34 +00:00
|
|
|
}
|
|
|
|
|
|
|
|
static noinline void
|
2012-05-14 05:57:28 +00:00
|
|
|
bad_area_nosemaphore(struct pt_regs *regs, unsigned long error_code,
|
2012-05-14 01:27:34 +00:00
|
|
|
unsigned long address)
|
|
|
|
{
|
2012-05-14 05:57:28 +00:00
|
|
|
__bad_area_nosemaphore(regs, error_code, address, SEGV_MAPERR);
|
2012-05-14 01:27:34 +00:00
|
|
|
}
|
|
|
|
|
|
|
|
static void
|
2012-05-14 05:57:28 +00:00
|
|
|
__bad_area(struct pt_regs *regs, unsigned long error_code,
|
2012-05-14 01:27:34 +00:00
|
|
|
unsigned long address, int si_code)
|
|
|
|
{
|
|
|
|
struct mm_struct *mm = current->mm;
|
|
|
|
|
|
|
|
/*
|
|
|
|
* Something tried to access memory that isn't in our memory map..
|
|
|
|
* Fix it, but check if it's kernel or user first..
|
|
|
|
*/
|
2020-06-09 04:33:25 +00:00
|
|
|
mmap_read_unlock(mm);
|
2012-05-14 01:27:34 +00:00
|
|
|
|
2012-05-14 05:57:28 +00:00
|
|
|
__bad_area_nosemaphore(regs, error_code, address, si_code);
|
2012-05-14 01:27:34 +00:00
|
|
|
}
|
|
|
|
|
|
|
|
static noinline void
|
2012-05-14 05:57:28 +00:00
|
|
|
bad_area(struct pt_regs *regs, unsigned long error_code, unsigned long address)
|
2012-05-14 01:27:34 +00:00
|
|
|
{
|
2012-05-14 05:57:28 +00:00
|
|
|
__bad_area(regs, error_code, address, SEGV_MAPERR);
|
2012-05-14 01:27:34 +00:00
|
|
|
}
|
|
|
|
|
|
|
|
static noinline void
|
2012-05-14 05:57:28 +00:00
|
|
|
bad_area_access_error(struct pt_regs *regs, unsigned long error_code,
|
2012-05-14 01:27:34 +00:00
|
|
|
unsigned long address)
|
|
|
|
{
|
2012-05-14 05:57:28 +00:00
|
|
|
__bad_area(regs, error_code, address, SEGV_ACCERR);
|
2012-05-14 01:27:34 +00:00
|
|
|
}
|
|
|
|
|
|
|
|
static void
|
2012-05-14 05:57:28 +00:00
|
|
|
do_sigbus(struct pt_regs *regs, unsigned long error_code, unsigned long address)
|
2012-05-14 01:27:34 +00:00
|
|
|
{
|
|
|
|
struct task_struct *tsk = current;
|
|
|
|
struct mm_struct *mm = tsk->mm;
|
|
|
|
|
2020-06-09 04:33:25 +00:00
|
|
|
mmap_read_unlock(mm);
|
2012-05-14 01:27:34 +00:00
|
|
|
|
|
|
|
/* Kernel mode? Handle exceptions or die: */
|
|
|
|
if (!user_mode(regs))
|
2012-05-14 05:57:28 +00:00
|
|
|
no_context(regs, error_code, address);
|
2012-05-14 01:27:34 +00:00
|
|
|
|
2019-02-06 00:38:15 +00:00
|
|
|
force_sig_info_fault(SIGBUS, BUS_ADRERR, address);
|
2012-05-14 01:27:34 +00:00
|
|
|
}
|
|
|
|
|
|
|
|
static noinline int
|
2012-05-14 05:57:28 +00:00
|
|
|
mm_fault_error(struct pt_regs *regs, unsigned long error_code,
|
2018-08-17 22:44:47 +00:00
|
|
|
unsigned long address, vm_fault_t fault)
|
2012-05-14 01:27:34 +00:00
|
|
|
{
|
|
|
|
/*
|
|
|
|
* Pagefault was interrupted by SIGKILL. We have no reason to
|
|
|
|
* continue pagefault.
|
|
|
|
*/
|
2020-04-02 04:08:25 +00:00
|
|
|
if (fault_signal_pending(fault, regs)) {
|
2012-05-14 01:27:34 +00:00
|
|
|
if (!user_mode(regs))
|
2012-05-14 05:57:28 +00:00
|
|
|
no_context(regs, error_code, address);
|
2012-05-14 01:27:34 +00:00
|
|
|
return 1;
|
|
|
|
}
|
|
|
|
|
2020-06-09 04:33:54 +00:00
|
|
|
/* Release mmap_lock first if necessary */
|
2020-04-02 04:08:25 +00:00
|
|
|
if (!(fault & VM_FAULT_RETRY))
|
2020-06-09 04:33:25 +00:00
|
|
|
mmap_read_unlock(current->mm);
|
2020-04-02 04:08:25 +00:00
|
|
|
|
2012-05-14 01:27:34 +00:00
|
|
|
if (!(fault & VM_FAULT_ERROR))
|
|
|
|
return 0;
|
|
|
|
|
|
|
|
if (fault & VM_FAULT_OOM) {
|
|
|
|
/* Kernel mode? Handle exceptions or die: */
|
|
|
|
if (!user_mode(regs)) {
|
2012-05-14 05:57:28 +00:00
|
|
|
no_context(regs, error_code, address);
|
2012-05-14 01:27:34 +00:00
|
|
|
return 1;
|
|
|
|
}
|
|
|
|
|
2012-12-12 21:52:10 +00:00
|
|
|
/*
|
|
|
|
* We ran out of memory, call the OOM killer, and return the
|
|
|
|
* userspace (which will retry the fault, or kill us if we got
|
|
|
|
* oom-killed):
|
|
|
|
*/
|
|
|
|
pagefault_out_of_memory();
|
2012-05-14 01:27:34 +00:00
|
|
|
} else {
|
|
|
|
if (fault & VM_FAULT_SIGBUS)
|
2012-05-14 05:57:28 +00:00
|
|
|
do_sigbus(regs, error_code, address);
|
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>
2015-01-29 18:51:32 +00:00
|
|
|
else if (fault & VM_FAULT_SIGSEGV)
|
|
|
|
bad_area(regs, error_code, address);
|
2012-05-14 01:27:34 +00:00
|
|
|
else
|
|
|
|
BUG();
|
|
|
|
}
|
|
|
|
|
|
|
|
return 1;
|
|
|
|
}
|
|
|
|
|
2012-05-14 06:33:28 +00:00
|
|
|
static inline int access_error(int error_code, struct vm_area_struct *vma)
|
2012-05-14 01:27:34 +00:00
|
|
|
{
|
2012-05-14 06:33:28 +00:00
|
|
|
if (error_code & FAULT_CODE_WRITE) {
|
2012-05-14 01:27:34 +00:00
|
|
|
/* write, present and write, not present: */
|
|
|
|
if (unlikely(!(vma->vm_flags & VM_WRITE)))
|
|
|
|
return 1;
|
|
|
|
return 0;
|
|
|
|
}
|
|
|
|
|
2012-05-14 06:33:28 +00:00
|
|
|
/* ITLB miss on NX page */
|
|
|
|
if (unlikely((error_code & FAULT_CODE_ITLB) &&
|
|
|
|
!(vma->vm_flags & VM_EXEC)))
|
|
|
|
return 1;
|
|
|
|
|
2012-05-14 01:27:34 +00:00
|
|
|
/* read, not present: */
|
2020-04-07 03:03:47 +00:00
|
|
|
if (unlikely(!vma_is_accessible(vma)))
|
2012-05-14 01:27:34 +00:00
|
|
|
return 1;
|
|
|
|
|
|
|
|
return 0;
|
|
|
|
}
|
|
|
|
|
2009-07-04 18:18:47 +00:00
|
|
|
static int fault_in_kernel_space(unsigned long address)
|
|
|
|
{
|
|
|
|
return address >= TASK_SIZE;
|
|
|
|
}
|
|
|
|
|
2005-04-16 22:20:36 +00:00
|
|
|
/*
|
|
|
|
* This routine handles page faults. It determines the address,
|
|
|
|
* and the problem, and then passes it off to one of the appropriate
|
|
|
|
* routines.
|
|
|
|
*/
|
2006-11-21 04:34:04 +00:00
|
|
|
asmlinkage void __kprobes do_page_fault(struct pt_regs *regs,
|
2012-05-14 05:57:28 +00:00
|
|
|
unsigned long error_code,
|
2006-11-21 04:34:04 +00:00
|
|
|
unsigned long address)
|
2005-04-16 22:20:36 +00:00
|
|
|
{
|
2009-07-04 18:18:47 +00:00
|
|
|
unsigned long vec;
|
2005-04-16 22:20:36 +00:00
|
|
|
struct task_struct *tsk;
|
|
|
|
struct mm_struct *mm;
|
|
|
|
struct vm_area_struct * vma;
|
2018-08-17 22:44:47 +00:00
|
|
|
vm_fault_t fault;
|
2020-04-02 04:08:37 +00:00
|
|
|
unsigned int flags = FAULT_FLAG_DEFAULT;
|
2005-04-16 22:20:36 +00:00
|
|
|
|
|
|
|
tsk = current;
|
2009-07-04 18:18:47 +00:00
|
|
|
mm = tsk->mm;
|
|
|
|
vec = lookup_exception_vector();
|
2005-04-16 22:20:36 +00:00
|
|
|
|
2009-07-04 18:18:47 +00:00
|
|
|
/*
|
|
|
|
* We fault-in kernel-space virtual memory on-demand. The
|
|
|
|
* 'reference' page table is init_mm.pgd.
|
|
|
|
*
|
|
|
|
* 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.
|
|
|
|
*/
|
|
|
|
if (unlikely(fault_in_kernel_space(address))) {
|
|
|
|
if (vmalloc_fault(address) >= 0)
|
2006-11-21 06:38:05 +00:00
|
|
|
return;
|
2019-07-16 23:28:00 +00:00
|
|
|
if (kprobe_page_fault(regs, vec))
|
2008-09-05 07:17:15 +00:00
|
|
|
return;
|
2006-11-21 06:38:05 +00:00
|
|
|
|
2012-05-14 05:57:28 +00:00
|
|
|
bad_area_nosemaphore(regs, error_code, address);
|
2012-05-14 01:27:34 +00:00
|
|
|
return;
|
2006-11-21 06:38:05 +00:00
|
|
|
}
|
|
|
|
|
2019-07-16 23:28:00 +00:00
|
|
|
if (unlikely(kprobe_page_fault(regs, vec)))
|
2009-06-24 17:30:10 +00:00
|
|
|
return;
|
|
|
|
|
2008-07-02 08:51:23 +00:00
|
|
|
/* Only enable interrupts if they were on before the fault */
|
2009-06-24 17:30:10 +00:00
|
|
|
if ((regs->sr & SR_IMASK) != SR_IMASK)
|
2008-07-02 08:51:23 +00:00
|
|
|
local_irq_enable();
|
|
|
|
|
2011-06-27 12:41:57 +00:00
|
|
|
perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS, 1, regs, address);
|
2008-07-02 08:51:23 +00:00
|
|
|
|
2005-04-16 22:20:36 +00:00
|
|
|
/*
|
2009-07-04 18:18:47 +00:00
|
|
|
* If we're in an interrupt, have no user context or are running
|
2015-05-11 15:52:11 +00:00
|
|
|
* with pagefaults disabled then we must not take the fault:
|
2005-04-16 22:20:36 +00:00
|
|
|
*/
|
2015-05-11 15:52:11 +00:00
|
|
|
if (unlikely(faulthandler_disabled() || !mm)) {
|
2012-05-14 05:57:28 +00:00
|
|
|
bad_area_nosemaphore(regs, error_code, address);
|
2012-05-14 01:27:34 +00:00
|
|
|
return;
|
|
|
|
}
|
2005-04-16 22:20:36 +00:00
|
|
|
|
2012-03-31 12:06:11 +00:00
|
|
|
retry:
|
2020-06-09 04:33:25 +00:00
|
|
|
mmap_read_lock(mm);
|
2005-04-16 22:20:36 +00:00
|
|
|
|
|
|
|
vma = find_vma(mm, address);
|
2012-05-14 01:27:34 +00:00
|
|
|
if (unlikely(!vma)) {
|
2012-05-14 05:57:28 +00:00
|
|
|
bad_area(regs, error_code, address);
|
2012-05-14 01:27:34 +00:00
|
|
|
return;
|
|
|
|
}
|
|
|
|
if (likely(vma->vm_start <= address))
|
2005-04-16 22:20:36 +00:00
|
|
|
goto good_area;
|
2012-05-14 01:27:34 +00:00
|
|
|
if (unlikely(!(vma->vm_flags & VM_GROWSDOWN))) {
|
2012-05-14 05:57:28 +00:00
|
|
|
bad_area(regs, error_code, address);
|
2012-05-14 01:27:34 +00:00
|
|
|
return;
|
|
|
|
}
|
|
|
|
if (unlikely(expand_stack(vma, address))) {
|
2012-05-14 05:57:28 +00:00
|
|
|
bad_area(regs, error_code, address);
|
2012-05-14 01:27:34 +00:00
|
|
|
return;
|
|
|
|
}
|
2009-07-04 18:18:47 +00:00
|
|
|
|
|
|
|
/*
|
|
|
|
* Ok, we have a good vm_area for this memory access, so
|
|
|
|
* we can handle it..
|
|
|
|
*/
|
2005-04-16 22:20:36 +00:00
|
|
|
good_area:
|
2012-05-14 05:57:28 +00:00
|
|
|
if (unlikely(access_error(error_code, vma))) {
|
|
|
|
bad_area_access_error(regs, error_code, address);
|
2012-05-14 01:27:34 +00:00
|
|
|
return;
|
2005-04-16 22:20:36 +00:00
|
|
|
}
|
|
|
|
|
2012-05-14 05:57:28 +00:00
|
|
|
set_thread_fault_code(error_code);
|
|
|
|
|
2013-09-12 22:13:39 +00:00
|
|
|
if (user_mode(regs))
|
|
|
|
flags |= FAULT_FLAG_USER;
|
|
|
|
if (error_code & FAULT_CODE_WRITE)
|
|
|
|
flags |= FAULT_FLAG_WRITE;
|
|
|
|
|
2005-04-16 22:20:36 +00:00
|
|
|
/*
|
|
|
|
* If for any reason at all we couldn't handle the fault,
|
|
|
|
* make sure we exit gracefully rather than endlessly redo
|
|
|
|
* the fault.
|
|
|
|
*/
|
2020-08-12 01:38:40 +00:00
|
|
|
fault = handle_mm_fault(vma, address, flags, regs);
|
2012-03-31 12:06:11 +00:00
|
|
|
|
2012-05-14 01:27:34 +00:00
|
|
|
if (unlikely(fault & (VM_FAULT_RETRY | VM_FAULT_ERROR)))
|
2012-05-14 05:57:28 +00:00
|
|
|
if (mm_fault_error(regs, error_code, address, fault))
|
2012-05-14 01:27:34 +00:00
|
|
|
return;
|
2012-03-31 12:06:11 +00:00
|
|
|
|
2022-01-14 22:05:51 +00:00
|
|
|
if (fault & VM_FAULT_RETRY) {
|
|
|
|
flags |= FAULT_FLAG_TRIED;
|
|
|
|
|
|
|
|
/*
|
|
|
|
* No need to mmap_read_unlock(mm) as we would
|
|
|
|
* have already released it in __lock_page_or_retry
|
|
|
|
* in mm/filemap.c.
|
|
|
|
*/
|
|
|
|
goto retry;
|
2009-06-24 17:30:10 +00:00
|
|
|
}
|
2005-04-16 22:20:36 +00:00
|
|
|
|
2020-06-09 04:33:25 +00:00
|
|
|
mmap_read_unlock(mm);
|
2005-04-16 22:20:36 +00:00
|
|
|
}
|