mirror of
https://github.com/followmsi/android_kernel_google_msm.git
synced 2024-11-06 23:17:41 +00:00
a10ca0dbc2
commit 33692f27597fcab536d7cbbcc8f52905133e4aa7 upstream. 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 Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org> [bwh: Backported to 3.2: - Adjust filenames, context - Drop arc, metag, nios2 and lustre changes - For sh, patch both 32-bit and 64-bit implementations to use goto bad_area - For s390, pass int_code and trans_exc_code as arguments to do_no_context() and do_sigsegv()] Signed-off-by: Ben Hutchings <ben@decadent.org.uk> [lizf: Backported to 3.4: - adjust context in arch/power/mm/fault.c - apply the original change in upstream commit for s390] Signed-off-by: Zefan Li <lizefan@huawei.com>
235 lines
5.7 KiB
C
235 lines
5.7 KiB
C
/*
|
|
* linux/arch/alpha/mm/fault.c
|
|
*
|
|
* Copyright (C) 1995 Linus Torvalds
|
|
*/
|
|
|
|
#include <linux/sched.h>
|
|
#include <linux/kernel.h>
|
|
#include <linux/mm.h>
|
|
#include <asm/io.h>
|
|
|
|
#define __EXTERN_INLINE inline
|
|
#include <asm/mmu_context.h>
|
|
#include <asm/tlbflush.h>
|
|
#undef __EXTERN_INLINE
|
|
|
|
#include <linux/signal.h>
|
|
#include <linux/errno.h>
|
|
#include <linux/string.h>
|
|
#include <linux/types.h>
|
|
#include <linux/ptrace.h>
|
|
#include <linux/mman.h>
|
|
#include <linux/smp.h>
|
|
#include <linux/interrupt.h>
|
|
#include <linux/module.h>
|
|
|
|
#include <asm/uaccess.h>
|
|
|
|
extern void die_if_kernel(char *,struct pt_regs *,long, unsigned long *);
|
|
|
|
|
|
/*
|
|
* Force a new ASN for a task.
|
|
*/
|
|
|
|
#ifndef CONFIG_SMP
|
|
unsigned long last_asn = ASN_FIRST_VERSION;
|
|
#endif
|
|
|
|
void
|
|
__load_new_mm_context(struct mm_struct *next_mm)
|
|
{
|
|
unsigned long mmc;
|
|
struct pcb_struct *pcb;
|
|
|
|
mmc = __get_new_mm_context(next_mm, smp_processor_id());
|
|
next_mm->context[smp_processor_id()] = mmc;
|
|
|
|
pcb = ¤t_thread_info()->pcb;
|
|
pcb->asn = mmc & HARDWARE_ASN_MASK;
|
|
pcb->ptbr = ((unsigned long) next_mm->pgd - IDENT_ADDR) >> PAGE_SHIFT;
|
|
|
|
__reload_thread(pcb);
|
|
}
|
|
|
|
|
|
/*
|
|
* This routine handles page faults. It determines the address,
|
|
* and the problem, and then passes it off to handle_mm_fault().
|
|
*
|
|
* mmcsr:
|
|
* 0 = translation not valid
|
|
* 1 = access violation
|
|
* 2 = fault-on-read
|
|
* 3 = fault-on-execute
|
|
* 4 = fault-on-write
|
|
*
|
|
* cause:
|
|
* -1 = instruction fetch
|
|
* 0 = load
|
|
* 1 = store
|
|
*
|
|
* Registers $9 through $15 are saved in a block just prior to `regs' and
|
|
* are saved and restored around the call to allow exception code to
|
|
* modify them.
|
|
*/
|
|
|
|
/* Macro for exception fixup code to access integer registers. */
|
|
#define dpf_reg(r) \
|
|
(((unsigned long *)regs)[(r) <= 8 ? (r) : (r) <= 15 ? (r)-16 : \
|
|
(r) <= 18 ? (r)+8 : (r)-10])
|
|
|
|
asmlinkage void
|
|
do_page_fault(unsigned long address, unsigned long mmcsr,
|
|
long cause, struct pt_regs *regs)
|
|
{
|
|
struct vm_area_struct * vma;
|
|
struct mm_struct *mm = current->mm;
|
|
const struct exception_table_entry *fixup;
|
|
int fault, si_code = SEGV_MAPERR;
|
|
siginfo_t info;
|
|
|
|
/* As of EV6, a load into $31/$f31 is a prefetch, and never faults
|
|
(or is suppressed by the PALcode). Support that for older CPUs
|
|
by ignoring such an instruction. */
|
|
if (cause == 0) {
|
|
unsigned int insn;
|
|
__get_user(insn, (unsigned int __user *)regs->pc);
|
|
if ((insn >> 21 & 0x1f) == 0x1f &&
|
|
/* ldq ldl ldt lds ldg ldf ldwu ldbu */
|
|
(1ul << (insn >> 26) & 0x30f00001400ul)) {
|
|
regs->pc += 4;
|
|
return;
|
|
}
|
|
}
|
|
|
|
/* If we're in an interrupt context, or have no user context,
|
|
we must not take the fault. */
|
|
if (!mm || in_atomic())
|
|
goto no_context;
|
|
|
|
#ifdef CONFIG_ALPHA_LARGE_VMALLOC
|
|
if (address >= TASK_SIZE)
|
|
goto vmalloc_fault;
|
|
#endif
|
|
|
|
down_read(&mm->mmap_sem);
|
|
vma = find_vma(mm, address);
|
|
if (!vma)
|
|
goto bad_area;
|
|
if (vma->vm_start <= address)
|
|
goto good_area;
|
|
if (!(vma->vm_flags & VM_GROWSDOWN))
|
|
goto bad_area;
|
|
if (expand_stack(vma, address))
|
|
goto bad_area;
|
|
|
|
/* Ok, we have a good vm_area for this memory access, so
|
|
we can handle it. */
|
|
good_area:
|
|
si_code = SEGV_ACCERR;
|
|
if (cause < 0) {
|
|
if (!(vma->vm_flags & VM_EXEC))
|
|
goto bad_area;
|
|
} else if (!cause) {
|
|
/* Allow reads even for write-only mappings */
|
|
if (!(vma->vm_flags & (VM_READ | VM_WRITE)))
|
|
goto bad_area;
|
|
} else {
|
|
if (!(vma->vm_flags & VM_WRITE))
|
|
goto bad_area;
|
|
}
|
|
|
|
/* 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, cause > 0 ? FAULT_FLAG_WRITE : 0);
|
|
up_read(&mm->mmap_sem);
|
|
if (unlikely(fault & VM_FAULT_ERROR)) {
|
|
if (fault & VM_FAULT_OOM)
|
|
goto out_of_memory;
|
|
else if (fault & VM_FAULT_SIGSEGV)
|
|
goto bad_area;
|
|
else if (fault & VM_FAULT_SIGBUS)
|
|
goto do_sigbus;
|
|
BUG();
|
|
}
|
|
if (fault & VM_FAULT_MAJOR)
|
|
current->maj_flt++;
|
|
else
|
|
current->min_flt++;
|
|
return;
|
|
|
|
/* Something tried to access memory that isn't in our memory map.
|
|
Fix it, but check if it's kernel or user first. */
|
|
bad_area:
|
|
up_read(&mm->mmap_sem);
|
|
|
|
if (user_mode(regs))
|
|
goto do_sigsegv;
|
|
|
|
no_context:
|
|
/* Are we prepared to handle this fault as an exception? */
|
|
if ((fixup = search_exception_tables(regs->pc)) != 0) {
|
|
unsigned long newpc;
|
|
newpc = fixup_exception(dpf_reg, fixup, regs->pc);
|
|
regs->pc = newpc;
|
|
return;
|
|
}
|
|
|
|
/* Oops. The kernel tried to access some bad page. We'll have to
|
|
terminate things with extreme prejudice. */
|
|
printk(KERN_ALERT "Unable to handle kernel paging request at "
|
|
"virtual address %016lx\n", address);
|
|
die_if_kernel("Oops", regs, cause, (unsigned long*)regs - 16);
|
|
do_exit(SIGKILL);
|
|
|
|
/* We ran out of memory, or some other thing happened to us that
|
|
made us unable to handle the page fault gracefully. */
|
|
out_of_memory:
|
|
if (!user_mode(regs))
|
|
goto no_context;
|
|
pagefault_out_of_memory();
|
|
return;
|
|
|
|
do_sigbus:
|
|
/* Send a sigbus, regardless of whether we were in kernel
|
|
or user mode. */
|
|
info.si_signo = SIGBUS;
|
|
info.si_errno = 0;
|
|
info.si_code = BUS_ADRERR;
|
|
info.si_addr = (void __user *) address;
|
|
force_sig_info(SIGBUS, &info, current);
|
|
if (!user_mode(regs))
|
|
goto no_context;
|
|
return;
|
|
|
|
do_sigsegv:
|
|
info.si_signo = SIGSEGV;
|
|
info.si_errno = 0;
|
|
info.si_code = si_code;
|
|
info.si_addr = (void __user *) address;
|
|
force_sig_info(SIGSEGV, &info, current);
|
|
return;
|
|
|
|
#ifdef CONFIG_ALPHA_LARGE_VMALLOC
|
|
vmalloc_fault:
|
|
if (user_mode(regs))
|
|
goto do_sigsegv;
|
|
else {
|
|
/* Synchronize this task's top level page-table
|
|
with the "reference" page table from init. */
|
|
long index = pgd_index(address);
|
|
pgd_t *pgd, *pgd_k;
|
|
|
|
pgd = current->active_mm->pgd + index;
|
|
pgd_k = swapper_pg_dir + index;
|
|
if (!pgd_present(*pgd) && pgd_present(*pgd_k)) {
|
|
pgd_val(*pgd) = pgd_val(*pgd_k);
|
|
return;
|
|
}
|
|
goto no_context;
|
|
}
|
|
#endif
|
|
}
|