The patch titled
Subject: mm: wrap calls to set_pte_at_notify with invalidate_range_start and invalidate_range_end
has been added to the -mm tree. Its filename is
mm-wrap-calls-to-set_pte_at_notify-with-invalidate_range_start-and-invalidate_range_end.patch
Before you just go and hit "reply", please:
a) Consider who else should be cc'ed
b) Prefer to cc a suitable mailing list as well
c) Ideally: find the original patch on the mailing list and do a
reply-to-all to that, adding suitable additional cc's
*** Remember to use Documentation/SubmitChecklist when testing your code ***
The -mm tree is included into linux-next and is updated
there every 3-4 working days
------------------------------------------------------
From: Haggai Eran <haggaie@xxxxxxxxxxxx>
Subject: mm: wrap calls to set_pte_at_notify with invalidate_range_start and invalidate_range_end
In order to allow sleeping during invalidate_page mmu notifier calls, we
need to avoid calling when holding the PT lock. In addition to its direct
calls, invalidate_page can also be called as a substitute for a change_pte
call, in case the notifier client hasn't implemented change_pte.
This patch drops the invalidate_page call from change_pte, and instead
wraps all calls to change_pte with invalidate_range_start and
invalidate_range_end calls.
Note that change_pte still cannot sleep after this patch, and that clients
implementing change_pte should not take action on it in case the number of
outstanding invalidate_range_start calls is larger than one, otherwise
they might miss a later invalidation.
Signed-off-by: Haggai Eran <haggaie@xxxxxxxxxxxx>
Cc: Andrea Arcangeli <andrea@xxxxxxxxxxxx>
Cc: Sagi Grimberg <sagig@xxxxxxxxxxxx>
Cc: Peter Zijlstra <a.p.zijlstra@xxxxxxxxx>
Cc: Xiao Guangrong <xiaoguangrong@xxxxxxxxxxxxxxxxxx>
Cc: Or Gerlitz <ogerlitz@xxxxxxxxxxxx>
Cc: Haggai Eran <haggaie@xxxxxxxxxxxx>
Cc: Shachar Raindel <raindel@xxxxxxxxxxxx>
Cc: Liran Liss <liranl@xxxxxxxxxxxx>
Cc: Christoph Lameter <cl@xxxxxxxxxxxxxxxxxxxx>
Cc: Avi Kivity <avi@xxxxxxxxxx>
Cc: Hugh Dickins <hughd@xxxxxxxxxx>
Signed-off-by: Andrew Morton <akpm@xxxxxxxxxxxxxxxxxxxx>
---
kernel/events/uprobes.c | 5 +++++
mm/ksm.c | 21 +++++++++++++++++++--
mm/memory.c | 17 +++++++++++------
mm/mmu_notifier.c | 6 ------
4 files changed, 35 insertions(+), 14 deletions(-)
diff -puN kernel/events/uprobes.c~mm-wrap-calls-to-set_pte_at_notify-with-invalidate_range_start-and-invalidate_range_end kernel/events/uprobes.c
--- a/kernel/events/uprobes.c~mm-wrap-calls-to-set_pte_at_notify-with-invalidate_range_start-and-invalidate_range_end
+++ a/kernel/events/uprobes.c
@@ -141,10 +141,14 @@ static int __replace_page(struct vm_area
spinlock_t *ptl;
pte_t *ptep;
int err;
+ /* For mmu_notifiers */
+ const unsigned long mmun_start = addr;
+ const unsigned long mmun_end = addr + PAGE_SIZE;
/* For try_to_free_swap() and munlock_vma_page() below */
lock_page(page);
+ mmu_notifier_invalidate_range_start(mm, mmun_start, mmun_end);
err = -EAGAIN;
ptep = page_check_address(page, mm, addr, &ptl, 0);
if (!ptep)
@@ -173,6 +177,7 @@ static int __replace_page(struct vm_area
err = 0;
unlock:
+ mmu_notifier_invalidate_range_end(mm, mmun_start, mmun_end);
unlock_page(page);
return err;
}
diff -puN mm/ksm.c~mm-wrap-calls-to-set_pte_at_notify-with-invalidate_range_start-and-invalidate_range_end mm/ksm.c
--- a/mm/ksm.c~mm-wrap-calls-to-set_pte_at_notify-with-invalidate_range_start-and-invalidate_range_end
+++ a/mm/ksm.c
@@ -709,15 +709,22 @@ static int write_protect_page(struct vm_
spinlock_t *ptl;
int swapped;
int err = -EFAULT;
+ unsigned long mmun_start; /* For mmu_notifiers */
+ unsigned long mmun_end; /* For mmu_notifiers */
addr = page_address_in_vma(page, vma);
if (addr == -EFAULT)
goto out;
BUG_ON(PageTransCompound(page));
+
+ mmun_start = addr;
+ mmun_end = addr + PAGE_SIZE;
+ mmu_notifier_invalidate_range_start(mm, mmun_start, mmun_end);
+
ptep = page_check_address(page, mm, addr, &ptl, 0);
if (!ptep)
- goto out;
+ goto out_mn;
if (pte_write(*ptep) || pte_dirty(*ptep)) {
pte_t entry;
@@ -752,6 +759,8 @@ static int write_protect_page(struct vm_
out_unlock:
pte_unmap_unlock(ptep, ptl);
+out_mn:
+ mmu_notifier_invalidate_range_end(mm, mmun_start, mmun_end);
out:
return err;
}
@@ -776,6 +785,8 @@ static int replace_page(struct vm_area_s
spinlock_t *ptl;
unsigned long addr;
int err = -EFAULT;
+ unsigned long mmun_start; /* For mmu_notifiers */
+ unsigned long mmun_end; /* For mmu_notifiers */
addr = page_address_in_vma(page, vma);
if (addr == -EFAULT)
@@ -794,10 +805,14 @@ static int replace_page(struct vm_area_s
if (!pmd_present(*pmd))
goto out;
+ mmun_start = addr;
+ mmun_end = addr + PAGE_SIZE;
+ mmu_notifier_invalidate_range_start(mm, mmun_start, mmun_end);
+
ptep = pte_offset_map_lock(mm, pmd, addr, &ptl);
if (!pte_same(*ptep, orig_pte)) {
pte_unmap_unlock(ptep, ptl);
- goto out;
+ goto out_mn;
}
get_page(kpage);
@@ -814,6 +829,8 @@ static int replace_page(struct vm_area_s
pte_unmap_unlock(ptep, ptl);
err = 0;
+out_mn:
+ mmu_notifier_invalidate_range_end(mm, mmun_start, mmun_end);
out:
return err;
}
diff -puN mm/memory.c~mm-wrap-calls-to-set_pte_at_notify-with-invalidate_range_start-and-invalidate_range_end mm/memory.c
--- a/mm/memory.c~mm-wrap-calls-to-set_pte_at_notify-with-invalidate_range_start-and-invalidate_range_end
+++ a/mm/memory.c
@@ -2527,6 +2527,8 @@ static int do_wp_page(struct mm_struct *
int ret = 0;
int page_mkwrite = 0;
struct page *dirty_page = NULL;
+ unsigned long mmun_start; /* For mmu_notifiers */
+ unsigned long mmun_end; /* For mmu_notifiers */
old_page = vm_normal_page(vma, address, orig_pte);
if (!old_page) {
@@ -2704,6 +2706,10 @@ gotten:
if (mem_cgroup_newpage_charge(new_page, mm, GFP_KERNEL))
goto oom_free_new;
+ mmun_start = address & PAGE_MASK;
+ mmun_end = (address & PAGE_MASK) + PAGE_SIZE;
+ mmu_notifier_invalidate_range_start(mm, mmun_start, mmun_end);
+
/*
* Re-check the pte - we dropped the lock
*/
@@ -2766,14 +2772,13 @@ gotten:
} else
mem_cgroup_uncharge_page(new_page);
+ if (new_page)
+ page_cache_release(new_page);
unlock:
pte_unmap_unlock(page_table, ptl);
- if (new_page) {
- if (new_page == old_page)
- /* cow happened, notify before releasing old_page */
- mmu_notifier_invalidate_page(mm, address);
- page_cache_release(new_page);
- }
+ if (new_page)
+ /* Only call the end notifier if the begin was called. */
+ mmu_notifier_invalidate_range_end(mm, mmun_start, mmun_end);
if (old_page) {
/*
* Don't let another task, with possibly unlocked vma,
diff -puN mm/mmu_notifier.c~mm-wrap-calls-to-set_pte_at_notify-with-invalidate_range_start-and-invalidate_range_end mm/mmu_notifier.c
--- a/mm/mmu_notifier.c~mm-wrap-calls-to-set_pte_at_notify-with-invalidate_range_start-and-invalidate_range_end
+++ a/mm/mmu_notifier.c
@@ -137,12 +137,6 @@ void __mmu_notifier_change_pte(struct mm
hlist_for_each_entry_rcu(mn, n, &mm->mmu_notifier_mm->list, hlist) {
if (mn->ops->change_pte)
mn->ops->change_pte(mn, mm, address, pte);
- /*
- * Some drivers don't have change_pte,
- * so we must call invalidate_page in that case.
- */
- else if (mn->ops->invalidate_page)
- mn->ops->invalidate_page(mn, mm, address);
}
srcu_read_unlock(&srcu, id);
}
_
Patches currently in -mm which might be from haggaie@xxxxxxxxxxxx are
linux-next.patch
mm-mmu_notifier-have-mmu_notifiers-use-a-global-srcu-so-they-may-safely-schedule.patch
mm-mmu_notifier-init-notifier-if-necessary.patch
mm-mmu_notifier-make-the-mmu_notifier-srcu-static.patch
mm-move-all-mmu-notifier-invocations-to-be-done-outside-the-pt-lock.patch
mm-wrap-calls-to-set_pte_at_notify-with-invalidate_range_start-and-invalidate_range_end.patch
mm-wrap-calls-to-set_pte_at_notify-with-invalidate_range_start-and-invalidate_range_end-fix.patch
--
To unsubscribe from this list: send the line "unsubscribe mm-commits" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
