History

mm: delay page_remove_rmap() until after the TLB has been flushed

When we remove a page table entry, we are very careful to only free the page after we have flushed the TLB, because other CPUs could still be using the page through stale TLB entries until after the flush. However, we have removed the rmap entry for that page early, which means that functions like folio_mkclean() would end up not serializing with the page table lock because the page had already been made invisible to rmap. And that is a problem, because while the TLB entry exists, we could end up with the following situation: (a) one CPU could come in and clean it, never seeing our mapping of the page (b) another CPU could continue to use the stale and dirty TLB entry and continue to write to said page resulting in a page that has been dirtied, but then marked clean again, all while another CPU might have dirtied it some more. End result: possibly lost dirty data. This extends our current TLB gather infrastructure to optionally track a "should I do a delayed page_remove_rmap() for this page after flushing the TLB". It uses the newly introduced 'encoded page pointer' to do that without having to keep separate data around. Note, this is complicated by a couple of issues: - we want to delay the rmap removal, but not past the page table lock, because that simplifies the memcg accounting - only SMP configurations want to delay TLB flushing, since on UP there are obviously no remote TLBs to worry about, and the page table lock means there are no preemption issues either - s390 has its own mmu_gather model that doesn't delay TLB flushing, and as a result also does not want the delayed rmap. As such, we can treat S390 like the UP case and use a common fallback for the "no delays" case. - we can track an enormous number of pages in our mmu_gather structure, with MAX_GATHER_BATCH_COUNT batches of MAX_TABLE_BATCH pages each, all set up to be approximately 10k pending pages. We do not want to have a huge number of batched pages that we then need to check for delayed rmap handling inside the page table lock. Particularly that last point results in a noteworthy detail, where the normal page batch gathering is limited once we have delayed rmaps pending, in such a way that only the last batch (the so-called "active batch") in the mmu_gather structure can have any delayed entries. NOTE! While the "possibly lost dirty data" sounds catastrophic, for this all to happen you need to have a user thread doing either madvise() with MADV_DONTNEED or a full re-mmap() of the area concurrently with another thread continuing to use said mapping. So arguably this is about user space doing crazy things, but from a VM consistency standpoint it's better if we track the dirty bit properly even when user space goes off the rails. [akpm@linux-foundation.org: fix UP build, per Linus] Link: https://lore.kernel.org/all/B88D3073-440A-41C7-95F4-895D3F657EF2@gmail.com/ Link: https://lkml.kernel.org/r/20221109203051.1835763-4-torvalds@linux-foundation.org Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org> Acked-by: Johannes Weiner <hannes@cmpxchg.org> Acked-by: Hugh Dickins <hughd@google.com> Reported-by: Nadav Amit <nadav.amit@gmail.com> Tested-by: Nadav Amit <nadav.amit@gmail.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org>

Linus Torvalds committed 4 years ago

Commit 5df397d1 parent 7cc8f9c4 files · +82 −8Browse files

Showing the changes to include/asm-generic (1 of 4 files). Show all

Unified · Split

include/asm-generic/tlb.h+29−2
@@ -263,6 +263,28 @@ struct mmu_gather_batch { · 262 unmodified lines
263263 extern bool __tlb_remove_page_size(struct mmu_gather *tlb,
264264 struct encoded_page *page,
265265 int page_size);
266+
267+#ifdef CONFIG_SMP
268+/*
269+ * This both sets 'delayed_rmap', and returns true. It would be an inline
270+ * function, except we define it before the 'struct mmu_gather'.
271+ */
272+#define tlb_delay_rmap(tlb) (((tlb)->delayed_rmap = 1), true)
273+extern void tlb_flush_rmaps(struct mmu_gather *tlb, struct vm_area_struct *vma);
274+#endif
275+
276+#endif
277+
278+/*
279+ * We have a no-op version of the rmap removal that doesn't
280+ * delay anything. That is used on S390, which flushes remote
281+ * TLBs synchronously, and on UP, which doesn't have any
282+ * remote TLBs to flush and is not preemptible due to this
283+ * all happening under the page table lock.
284+ */
285+#ifndef tlb_delay_rmap
286+#define tlb_delay_rmap(tlb) (false)
287+static inline void tlb_flush_rmaps(struct mmu_gather *tlb, struct vm_area_struct *vma) { }
266288 #endif
267289
268290 /*
@@ -295,6 +317,11 @@ struct mmu_gather { · 26 unmodified lines
295317 */
296318 unsigned int freed_tables : 1;
297319
320+ /*
321+ * Do we have pending delayed rmap removals?
322+ */
323+ unsigned int delayed_rmap : 1;
324+
298325 /*
299326 * at which levels have we cleared entries?
300327 */
@@ -440,9 +467,9 @@ static inline void tlb_remove_page_size(struct mmu_gather *tlb, · 139 unmodified lines
440467 tlb_flush_mmu(tlb);
441468 }
442469
443−static inline bool __tlb_remove_page(struct mmu_gather *tlb, struct page *page)
470+static __always_inline bool __tlb_remove_page(struct mmu_gather *tlb, struct page *page, unsigned int flags)
444471 {
445− return __tlb_remove_page_size(tlb, encode_page(page, 0), PAGE_SIZE);
472+ return __tlb_remove_page_size(tlb, encode_page(page, flags), PAGE_SIZE);
446473 }
447474
448475 /* tlb_remove_page

Keyboard shortcuts

General

Show keyboard shortcuts
?
Focus the current search
/

Issues and pull requests

Open filters
f

Issues, pull requests and Inbox

Select next item
j↓
Select previous item
k↑
Open selected item
Enter
Dismiss filters or clear selection
Esc

Repository code

Go to file
t