![Sergei Trofimovich](/assets/img/avatar_default.png)
Fix page fault handling code to fixup r16-r18 registers. Before the patch code had off-by-two registers bug. This bug caused overwriting of ps,pc,gp registers instead of fixing intended r16,r17,r18 (see `struct pt_regs`). More details: Initially Dmitry noticed a kernel bug as a failure on strace test suite. Test passes unmapped userspace pointer to io_submit: ```c #include <err.h> #include <unistd.h> #include <sys/mman.h> #include <asm/unistd.h> int main(void) { unsigned long ctx = 0; if (syscall(__NR_io_setup, 1, &ctx)) err(1, "io_setup"); const size_t page_size = sysconf(_SC_PAGESIZE); const size_t size = page_size * 2; void *ptr = mmap(NULL, size, PROT_READ | PROT_WRITE, MAP_PRIVATE | MAP_ANONYMOUS, -1, 0); if (MAP_FAILED == ptr) err(1, "mmap(%zu)", size); if (munmap(ptr, size)) err(1, "munmap"); syscall(__NR_io_submit, ctx, 1, ptr + page_size); syscall(__NR_io_destroy, ctx); return 0; } ``` Running this test causes kernel to crash when handling page fault: ``` Unable to handle kernel paging request at virtual address ffffffffffff9468 CPU 3 aio(26027): Oops 0 pc = [<fffffc00004eddf8>] ra = [<fffffc00004edd5c>] ps = 0000 Not tainted pc is at sys_io_submit+0x108/0x200 ra is at sys_io_submit+0x6c/0x200 v0 = fffffc00c58e6300 t0 = fffffffffffffff2 t1 = 000002000025e000 t2 = fffffc01f159fef8 t3 = fffffc0001009640 t4 = fffffc0000e0f6e0 t5 = 0000020001002e9e t6 = 4c41564e49452031 t7 = fffffc01f159c000 s0 = 0000000000000002 s1 = 000002000025e000 s2 = 0000000000000000 s3 = 0000000000000000 s4 = 0000000000000000 s5 = fffffffffffffff2 s6 = fffffc00c58e6300 a0 = fffffc00c58e6300 a1 = 0000000000000000 a2 = 000002000025e000 a3 = 00000200001ac260 a4 = 00000200001ac1e8 a5 = 0000000000000001 t8 = 0000000000000008 t9 = 000000011f8bce30 t10= 00000200001ac440 t11= 0000000000000000 pv = fffffc00006fd320 at = 0000000000000000 gp = 0000000000000000 sp = 00000000265fd174 Disabling lock debugging due to kernel taint Trace: [<fffffc0000311404>] entSys+0xa4/0xc0 ``` Here `gp` has invalid value. `gp is s overwritten by a fixup for the following page fault handler in `io_submit` syscall handler: ``` __se_sys_io_submit ... ldq a1,0(t1) bne t0,4280 <__se_sys_io_submit+0x180> ``` After a page fault `t0` should contain -EFALUT and `a1` is 0. Instead `gp` was overwritten in place of `a1`. This happens due to a off-by-two bug in `dpf_reg()` for `r16-r18` (aka `a0-a2`). I think the bug went unnoticed for a long time as `gp` is one of scratch registers. Any kernel function call would re-calculate `gp`. Dmitry tracked down the bug origin back to 2.1.32 kernel version where trap_a{0,1,2} fields were inserted into struct pt_regs. And even before that `dpf_reg()` contained off-by-one error. Cc: Richard Henderson <rth@twiddle.net> Cc: Ivan Kokshaysky <ink@jurassic.park.msu.ru> Cc: linux-alpha@vger.kernel.org Cc: linux-kernel@vger.kernel.org Reported-and-reviewed-by: "Dmitry V. Levin" <ldv@altlinux.org> Cc: stable@vger.kernel.org # v2.1.32+ Bug: https://bugs.gentoo.org/672040 Signed-off-by: Sergei Trofimovich <slyfox@gentoo.org> Signed-off-by: Matt Turner <mattst88@gmail.com>
253 lines
6.1 KiB
C
253 lines
6.1 KiB
C
// SPDX-License-Identifier: GPL-2.0
|
|
/*
|
|
* linux/arch/alpha/mm/fault.c
|
|
*
|
|
* Copyright (C) 1995 Linus Torvalds
|
|
*/
|
|
|
|
#include <linux/sched/signal.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/extable.h>
|
|
#include <linux/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)+10 : (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 si_code = SEGV_MAPERR;
|
|
vm_fault_t fault;
|
|
unsigned int flags = FAULT_FLAG_ALLOW_RETRY | FAULT_FLAG_KILLABLE;
|
|
|
|
/* 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 || faulthandler_disabled())
|
|
goto no_context;
|
|
|
|
#ifdef CONFIG_ALPHA_LARGE_VMALLOC
|
|
if (address >= TASK_SIZE)
|
|
goto vmalloc_fault;
|
|
#endif
|
|
if (user_mode(regs))
|
|
flags |= FAULT_FLAG_USER;
|
|
retry:
|
|
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;
|
|
flags |= FAULT_FLAG_WRITE;
|
|
}
|
|
|
|
/* 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(vma, address, flags);
|
|
|
|
if ((fault & VM_FAULT_RETRY) && fatal_signal_pending(current))
|
|
return;
|
|
|
|
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 (flags & FAULT_FLAG_ALLOW_RETRY) {
|
|
if (fault & VM_FAULT_MAJOR)
|
|
current->maj_flt++;
|
|
else
|
|
current->min_flt++;
|
|
if (fault & VM_FAULT_RETRY) {
|
|
flags &= ~FAULT_FLAG_ALLOW_RETRY;
|
|
|
|
/* No need to up_read(&mm->mmap_sem) as we would
|
|
* have already released it in __lock_page_or_retry
|
|
* in mm/filemap.c.
|
|
*/
|
|
|
|
goto retry;
|
|
}
|
|
}
|
|
|
|
up_read(&mm->mmap_sem);
|
|
|
|
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:
|
|
up_read(&mm->mmap_sem);
|
|
if (!user_mode(regs))
|
|
goto no_context;
|
|
pagefault_out_of_memory();
|
|
return;
|
|
|
|
do_sigbus:
|
|
up_read(&mm->mmap_sem);
|
|
/* Send a sigbus, regardless of whether we were in kernel
|
|
or user mode. */
|
|
force_sig_fault(SIGBUS, BUS_ADRERR, (void __user *) address, 0, current);
|
|
if (!user_mode(regs))
|
|
goto no_context;
|
|
return;
|
|
|
|
do_sigsegv:
|
|
force_sig_fault(SIGSEGV, si_code, (void __user *) address, 0, 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
|
|
}
|