Commit ac53c4fc authored by David Daney's avatar David Daney Committed by Ralf Baechle

MIPS: Avoid mcheck by flushing page range in huge_ptep_set_access_flags()

Problem:

1) Huge page mapping of anonymous memory is initially invalid.  Will be
   faulted in by copy-on-write mechanism.

2) Userspace attempts store at the end of the huge mapping.

3) TLB Refill exception handler fill TLB with a normal (4K sized)
   invalid page at the end of the huge mapping virtual address range.

4) Userspace restarted, and re-attempts the store at the end of the
   huge mapping.

5) Page from #3 is invalid, we get a fault and go to the hugepage
   fault handler.  This tries to map a huge page and calls
   huge_ptep_set_access_flags() to install the mapping.

6) We just call the generic ptep_set_access_flags() to set up the page
   tables, but the flush there assumes a normal (4K sized) page and
   only tries to flush the first part of the huge page virtual address
   out of the TLB, since the existing entry from step #3 doesn't
   conflict, nothing is flushed.

7) We attempt to load the mapping into the TLB, but because it
   conflicts with the entry from step #3, we get a Machine Check
   exception.

The fix: Flush the entire rage covered by the huge page in
huge_ptep_set_access_flags(), and remove the optimization in
local_flush_tlb_range() so that the flush actually does the correct
thing.
Signed-off-by: default avatarDavid Daney <david.daney@cavium.com>
Cc: linux-mips@linux-mips.org
Cc: linux-kernel@vger.kernel.org
Cc: Hillf Danton <dhillf@gmail.com>
Patchwork: https://patchwork.linux-mips.org/patch/4661/Signed-off-by: default avatarRalf Baechle <ralf@linux-mips.org>
(cherry picked from commit dd617f258cc39d36be26afee9912624a2d23112c)
parent 9489e9dc
...@@ -95,7 +95,17 @@ static inline int huge_ptep_set_access_flags(struct vm_area_struct *vma, ...@@ -95,7 +95,17 @@ static inline int huge_ptep_set_access_flags(struct vm_area_struct *vma,
pte_t *ptep, pte_t pte, pte_t *ptep, pte_t pte,
int dirty) int dirty)
{ {
return ptep_set_access_flags(vma, addr, ptep, pte, dirty); int changed = !pte_same(*ptep, pte);
if (changed) {
set_pte_at(vma->vm_mm, addr, ptep, pte);
/*
* There could be some standard sized pages in there,
* get them all.
*/
flush_tlb_range(vma, addr, addr + HPAGE_SIZE);
}
return changed;
} }
static inline pte_t huge_ptep_get(pte_t *ptep) static inline pte_t huge_ptep_get(pte_t *ptep)
......
...@@ -120,18 +120,11 @@ void local_flush_tlb_range(struct vm_area_struct *vma, unsigned long start, ...@@ -120,18 +120,11 @@ void local_flush_tlb_range(struct vm_area_struct *vma, unsigned long start,
if (cpu_context(cpu, mm) != 0) { if (cpu_context(cpu, mm) != 0) {
unsigned long size, flags; unsigned long size, flags;
int huge = is_vm_hugetlb_page(vma);
ENTER_CRITICAL(flags); ENTER_CRITICAL(flags);
if (huge) { start = round_down(start, PAGE_SIZE << 1);
start = round_down(start, HPAGE_SIZE); end = round_up(end, PAGE_SIZE << 1);
end = round_up(end, HPAGE_SIZE); size = (end - start) >> (PAGE_SHIFT + 1);
size = (end - start) >> HPAGE_SHIFT;
} else {
start = round_down(start, PAGE_SIZE << 1);
end = round_up(end, PAGE_SIZE << 1);
size = (end - start) >> (PAGE_SHIFT + 1);
}
if (size <= current_cpu_data.tlbsize/2) { if (size <= current_cpu_data.tlbsize/2) {
int oldpid = read_c0_entryhi(); int oldpid = read_c0_entryhi();
int newpid = cpu_asid(cpu, mm); int newpid = cpu_asid(cpu, mm);
...@@ -140,10 +133,7 @@ void local_flush_tlb_range(struct vm_area_struct *vma, unsigned long start, ...@@ -140,10 +133,7 @@ void local_flush_tlb_range(struct vm_area_struct *vma, unsigned long start,
int idx; int idx;
write_c0_entryhi(start | newpid); write_c0_entryhi(start | newpid);
if (huge) start += (PAGE_SIZE << 1);
start += HPAGE_SIZE;
else
start += (PAGE_SIZE << 1);
mtc0_tlbw_hazard(); mtc0_tlbw_hazard();
tlb_probe(); tlb_probe();
tlb_probe_hazard(); tlb_probe_hazard();
......
Markdown is supported
0%
or
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment