mm: mmu_gather rework
Rework the existing mmu_gather infrastructure.
The direct purpose of these patches was to allow preemptible mmu_gather,
but even without that I think these patches provide an improvement to the
status quo.
The first 9 patches rework the mmu_gather infrastructure. For review
purpose I've split them into generic and per-arch patches with the last of
those a generic cleanup.
The next patch provides generic RCU page-table freeing, and the followup
is a patch converting s390 to use this. I've also got 4 patches from
DaveM lined up (not included in this series) that uses this to implement
gup_fast() for sparc64.
Then there is one patch that extends the generic mmu_gather batching.
After that follow the mm preemptibility patches, these make part of the mm
a lot more preemptible. It converts i_mmap_lock and anon_vma->lock to
mutexes which together with the mmu_gather rework makes mmu_gather
preemptible as well.
Making i_mmap_lock a mutex also enables a clean-up of the truncate code.
This also allows for preemptible mmu_notifiers, something that XPMEM I
think wants.
Furthermore, it removes the new and universially detested unmap_mutex.
This patch:
Remove the first obstacle towards a fully preemptible mmu_gather.
The current scheme assumes mmu_gather is always done with preemption
disabled and uses per-cpu storage for the page batches. Change this to
try and allocate a page for batching and in case of failure, use a small
on-stack array to make some progress.
Preemptible mmu_gather is desired in general and usable once i_mmap_lock
becomes a mutex. Doing it before the mutex conversion saves us from
having to rework the code by moving the mmu_gather bits inside the
pte_lock.
Also avoid flushing the tlb batches from under the pte lock, this is
useful even without the i_mmap_lock conversion as it significantly reduces
pte lock hold times.
[akpm@linux-foundation.org: fix comment tpyo]
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Cc: David Miller <davem@davemloft.net>
Cc: Martin Schwidefsky <schwidefsky@de.ibm.com>
Cc: Russell King <rmk@arm.linux.org.uk>
Cc: Paul Mundt <lethal@linux-sh.org>
Cc: Jeff Dike <jdike@addtoit.com>
Cc: Richard Weinberger <richard@nod.at>
Cc: Tony Luck <tony.luck@intel.com>
Reviewed-by: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com>
Acked-by: Hugh Dickins <hughd@google.com>
Acked-by: Mel Gorman <mel@csn.ul.ie>
Cc: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com>
Cc: Nick Piggin <npiggin@kernel.dk>
Cc: Namhyung Kim <namhyung@gmail.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
diff --git a/mm/memory.c b/mm/memory.c
index 4c6ea10..19b2d44 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -912,12 +912,13 @@
long *zap_work, struct zap_details *details)
{
struct mm_struct *mm = tlb->mm;
+ int force_flush = 0;
pte_t *pte;
spinlock_t *ptl;
int rss[NR_MM_COUNTERS];
init_rss_vec(rss);
-
+again:
pte = pte_offset_map_lock(mm, pmd, addr, &ptl);
arch_enter_lazy_mmu_mode();
do {
@@ -974,7 +975,9 @@
page_remove_rmap(page);
if (unlikely(page_mapcount(page) < 0))
print_bad_pte(vma, addr, ptent, page);
- tlb_remove_page(tlb, page);
+ force_flush = !__tlb_remove_page(tlb, page);
+ if (force_flush)
+ break;
continue;
}
/*
@@ -1001,6 +1004,18 @@
arch_leave_lazy_mmu_mode();
pte_unmap_unlock(pte - 1, ptl);
+ /*
+ * mmu_gather ran out of room to batch pages, we break out of
+ * the PTE lock to avoid doing the potential expensive TLB invalidate
+ * and page-free while holding it.
+ */
+ if (force_flush) {
+ force_flush = 0;
+ tlb_flush_mmu(tlb);
+ if (addr != end)
+ goto again;
+ }
+
return addr;
}
@@ -1121,17 +1136,14 @@
* ensure that any thus-far unmapped pages are flushed before unmap_vmas()
* drops the lock and schedules.
*/
-unsigned long unmap_vmas(struct mmu_gather **tlbp,
+unsigned long unmap_vmas(struct mmu_gather *tlb,
struct vm_area_struct *vma, unsigned long start_addr,
unsigned long end_addr, unsigned long *nr_accounted,
struct zap_details *details)
{
long zap_work = ZAP_BLOCK_SIZE;
- unsigned long tlb_start = 0; /* For tlb_finish_mmu */
- int tlb_start_valid = 0;
unsigned long start = start_addr;
spinlock_t *i_mmap_lock = details? details->i_mmap_lock: NULL;
- int fullmm = (*tlbp)->fullmm;
struct mm_struct *mm = vma->vm_mm;
mmu_notifier_invalidate_range_start(mm, start_addr, end_addr);
@@ -1152,11 +1164,6 @@
untrack_pfn_vma(vma, 0, 0);
while (start != end) {
- if (!tlb_start_valid) {
- tlb_start = start;
- tlb_start_valid = 1;
- }
-
if (unlikely(is_vm_hugetlb_page(vma))) {
/*
* It is undesirable to test vma->vm_file as it
@@ -1177,7 +1184,7 @@
start = end;
} else
- start = unmap_page_range(*tlbp, vma,
+ start = unmap_page_range(tlb, vma,
start, end, &zap_work, details);
if (zap_work > 0) {
@@ -1185,19 +1192,13 @@
break;
}
- tlb_finish_mmu(*tlbp, tlb_start, start);
-
if (need_resched() ||
(i_mmap_lock && spin_needbreak(i_mmap_lock))) {
- if (i_mmap_lock) {
- *tlbp = NULL;
+ if (i_mmap_lock)
goto out;
- }
cond_resched();
}
- *tlbp = tlb_gather_mmu(vma->vm_mm, fullmm);
- tlb_start_valid = 0;
zap_work = ZAP_BLOCK_SIZE;
}
}
@@ -1217,16 +1218,15 @@
unsigned long size, struct zap_details *details)
{
struct mm_struct *mm = vma->vm_mm;
- struct mmu_gather *tlb;
+ struct mmu_gather tlb;
unsigned long end = address + size;
unsigned long nr_accounted = 0;
lru_add_drain();
- tlb = tlb_gather_mmu(mm, 0);
+ tlb_gather_mmu(&tlb, mm, 0);
update_hiwater_rss(mm);
end = unmap_vmas(&tlb, vma, address, end, &nr_accounted, details);
- if (tlb)
- tlb_finish_mmu(tlb, address, end);
+ tlb_finish_mmu(&tlb, address, end);
return end;
}