From: Peter Zijlstra <peterz@xxxxxxxxxxxxx>
When speculating faults (without holding mmap_sem) we need to validate
that the vma against which we loaded pages is still valid when we're
ready to install the new PTE.
Therefore, replace the pte_offset_map_lock() calls that (re)take the
PTL with pte_map_lock() which can fail in case we find the VMA changed
since we started the fault.
Instead of passing around the endless list of function arguments,
replace the lot with a single structure so we can change context
without endless function signature changes.
Signed-off-by: Peter Zijlstra (Intel) <peterz@xxxxxxxxxxxxx>
[port to 4.10 kernel]
Signed-off-by: Laurent Dufour <ldufour@xxxxxxxxxxxxxxxxxx>
---
include/linux/mm.h | 1 +
mm/memory.c | 57 +++++++++++++++++++++++++++++++++++++++---------------
2 files changed, 42 insertions(+), 16 deletions(-)
diff --git a/include/linux/mm.h b/include/linux/mm.h
index b84615b0f64c..555ac9ac7202 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -280,6 +280,7 @@ extern pgprot_t protection_map[16];
#define FAULT_FLAG_USER 0x40 /* The fault originated in userspace */
#define FAULT_FLAG_REMOTE 0x80 /* faulting for non current tsk/mm */
#define FAULT_FLAG_INSTRUCTION 0x100 /* The fault was during an instruction fetch */
+#define FAULT_FLAG_SPECULATIVE 0x200 /* Speculative fault, not holding mmap_sem */
/*
* vm_fault is filled by the the pagefault handler and passed to the vma's
diff --git a/mm/memory.c b/mm/memory.c
index 374b99de75a5..bce32c9d73c2 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -2100,6 +2100,12 @@ static inline void wp_page_reuse(struct vm_fault *vmf)
pte_unmap_unlock(vmf->pte, vmf->ptl);
}
+static bool pte_map_lock(struct vm_fault *vmf)
+{
+ vmf->pte = pte_offset_map_lock(vmf->vma->vm_mm, vmf->pmd, vmf->address, &vmf->ptl);
+ return true;
+}
+
/*
* Handle the case of a page which we actually need to copy to a new page.
*
@@ -2127,6 +2133,7 @@ static int wp_page_copy(struct vm_fault *vmf)
const unsigned long mmun_start = vmf->address & PAGE_MASK;
const unsigned long mmun_end = mmun_start + PAGE_SIZE;
struct mem_cgroup *memcg;
+ int ret = VM_FAULT_OOM;
if (unlikely(anon_vma_prepare(vma)))
goto oom;
@@ -2154,7 +2161,11 @@ static int wp_page_copy(struct vm_fault *vmf)
/*
* Re-check the pte - we dropped the lock
*/
- vmf->pte = pte_offset_map_lock(mm, vmf->pmd, vmf->address, &vmf->ptl);
+ if (!pte_map_lock(vmf)) {
+ mem_cgroup_cancel_charge(new_page, memcg, false);
+ ret = VM_FAULT_RETRY;
+ goto oom_free_new;
+ }
if (likely(pte_same(*vmf->pte, vmf->orig_pte))) {
if (old_page) {
if (!PageAnon(old_page)) {
@@ -2242,7 +2253,7 @@ static int wp_page_copy(struct vm_fault *vmf)
oom:
if (old_page)
put_page(old_page);
- return VM_FAULT_OOM;
+ return ret;
}
/**
@@ -2263,8 +2274,8 @@ static int wp_page_copy(struct vm_fault *vmf)
int finish_mkwrite_fault(struct vm_fault *vmf)
{
WARN_ON_ONCE(!(vmf->vma->vm_flags & VM_SHARED));
- vmf->pte = pte_offset_map_lock(vmf->vma->vm_mm, vmf->pmd, vmf->address,
- &vmf->ptl);
+ if (!pte_map_lock(vmf))
+ return VM_FAULT_RETRY;
/*
* We might have raced with another page fault while we released the
* pte_offset_map_lock.
@@ -2382,8 +2393,11 @@ static int do_wp_page(struct vm_fault *vmf)
get_page(vmf->page);
pte_unmap_unlock(vmf->pte, vmf->ptl);
lock_page(vmf->page);
- vmf->pte = pte_offset_map_lock(vma->vm_mm, vmf->pmd,
- vmf->address, &vmf->ptl);
+ if (!pte_map_lock(vmf)) {
+ unlock_page(vmf->page);
+ put_page(vmf->page);
+ return VM_FAULT_RETRY;
+ }
if (!pte_same(*vmf->pte, vmf->orig_pte)) {
unlock_page(vmf->page);
pte_unmap_unlock(vmf->pte, vmf->ptl);
@@ -2541,8 +2555,10 @@ int do_swap_page(struct vm_fault *vmf)
* Back out if somebody else faulted in this pte
* while we released the pte lock.
*/
- vmf->pte = pte_offset_map_lock(vma->vm_mm, vmf->pmd,
- vmf->address, &vmf->ptl);
+ if (!pte_map_lock(vmf)) {
+ delayacct_clear_flag(DELAYACCT_PF_SWAPIN);
+ return VM_FAULT_RETRY;
+ }
if (likely(pte_same(*vmf->pte, vmf->orig_pte)))
ret = VM_FAULT_OOM;
delayacct_clear_flag(DELAYACCT_PF_SWAPIN);
@@ -2598,8 +2614,11 @@ int do_swap_page(struct vm_fault *vmf)
/*
* Back out if somebody else already faulted in this pte.
*/
- vmf->pte = pte_offset_map_lock(vma->vm_mm, vmf->pmd, vmf->address,
- &vmf->ptl);
+ if (!pte_map_lock(vmf)) {
+ ret = VM_FAULT_RETRY;
+ mem_cgroup_cancel_charge(page, memcg, false);
+ goto out_page;
+ }
if (unlikely(!pte_same(*vmf->pte, vmf->orig_pte)))
goto out_nomap;
@@ -2763,8 +2782,8 @@ static int do_anonymous_page(struct vm_fault *vmf)
!mm_forbids_zeropage(vma->vm_mm)) {
entry = pte_mkspecial(pfn_pte(my_zero_pfn(vmf->address),
vma->vm_page_prot));
- vmf->pte = pte_offset_map_lock(vma->vm_mm, vmf->pmd,
- vmf->address, &vmf->ptl);
+ if (!pte_map_lock(vmf))
+ return VM_FAULT_RETRY;
if (!pte_none(*vmf->pte))
goto unlock;
/* Deliver the page fault to userland, check inside PT lock */
@@ -2796,8 +2815,12 @@ static int do_anonymous_page(struct vm_fault *vmf)
if (vma->vm_flags & VM_WRITE)
entry = pte_mkwrite(pte_mkdirty(entry));
- vmf->pte = pte_offset_map_lock(vma->vm_mm, vmf->pmd, vmf->address,
- &vmf->ptl);
+ if (!pte_map_lock(vmf)) {
+ /* XXX: should be factorized */
+ mem_cgroup_cancel_charge(page, memcg, false);
+ put_page(page);
+ return VM_FAULT_RETRY;
+ }
if (!pte_none(*vmf->pte))
goto release;
@@ -2897,8 +2920,9 @@ static int pte_alloc_one_map(struct vm_fault *vmf)
if (pmd_trans_unstable(vmf->pmd) || pmd_devmap(*vmf->pmd))
return VM_FAULT_NOPAGE;
- vmf->pte = pte_offset_map_lock(vma->vm_mm, vmf->pmd, vmf->address,
- &vmf->ptl);
+ if (!pte_map_lock(vmf))
+ return VM_FAULT_RETRY;
+
return 0;
}
@@ -3218,6 +3242,7 @@ static int do_read_fault(struct vm_fault *vmf)
* something).
*/
if (vma->vm_ops->map_pages && fault_around_bytes >> PAGE_SHIFT > 1) {
+ /* XXX: is a call to pte_map_lock(fe) required here ? */
ret = do_fault_around(vmf);
if (ret)
return ret;
--
2.7.4
--
To unsubscribe, send a message with 'unsubscribe linux-mm' in
the body to majordomo@xxxxxxxxx. For more info on Linux MM,
see: http://www.linux-mm.org/ .
Don't email: <a href=mailto:"dont@xxxxxxxxx";> email@xxxxxxxxx </a>
