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>

2 files changed, 50 insertions, 6 deletions

diff --git a/mm/memory.c b/mm/memory.c
index 1749c638734f..6c85cba02113 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -1374,6 +1374,8 @@ again:
 			break;
 
 		if (pte_present(ptent)) {
+			unsigned int delay_rmap;
+
 			page = vm_normal_page(vma, addr, ptent);
 			if (unlikely(!should_zap_page(details, page)))
 				continue;
@@ -1385,20 +1387,26 @@ again:
 			if (unlikely(!page))
 				continue;
 
+			delay_rmap = 0;
 			if (!PageAnon(page)) {
 				if (pte_dirty(ptent)) {
-					force_flush = 1;
 					set_page_dirty(page);
+					if (tlb_delay_rmap(tlb)) {
+						delay_rmap = 1;
+						force_flush = 1;
+					}
 				}
 				if (pte_young(ptent) &&
 				    likely(!(vma->vm_flags & VM_SEQ_READ)))
 					mark_page_accessed(page);
 			}
 			rss[mm_counter(page)]--;
-			page_remove_rmap(page, vma, false);
-			if (unlikely(page_mapcount(page) < 0))
-				print_bad_pte(vma, addr, ptent, page);
-			if (unlikely(__tlb_remove_page(tlb, page))) {
+			if (!delay_rmap) {
+				page_remove_rmap(page, vma, false);
+				if (unlikely(page_mapcount(page) < 0))
+					print_bad_pte(vma, addr, ptent, page);
+			}
+			if (unlikely(__tlb_remove_page(tlb, page, delay_rmap))) {
 				force_flush = 1;
 				addr += PAGE_SIZE;
 				break;
@@ -1455,8 +1463,11 @@ again:
 	arch_leave_lazy_mmu_mode();
 
 	/* Do the actual TLB flush before dropping ptl */
-	if (force_flush)
+	if (force_flush) {
 		tlb_flush_mmu_tlbonly(tlb);
+		if (tlb->delayed_rmap)
+			tlb_flush_rmaps(tlb, vma);
+	}
 	pte_unmap_unlock(start_pte, ptl);
 
 	/*
diff --git a/mm/mmu_gather.c b/mm/mmu_gather.c
index 382581c4a9f6..1de1cf9ba581 100644
--- a/mm/mmu_gather.c
+++ b/mm/mmu_gather.c
@@ -9,6 +9,7 @@
 #include <linux/rcupdate.h>
 #include <linux/smp.h>
 #include <linux/swap.h>
+#include <linux/rmap.h>
 
 #include <asm/pgalloc.h>
 #include <asm/tlb.h>
@@ -19,6 +20,10 @@ static bool tlb_next_batch(struct mmu_gather *tlb)
 {
 	struct mmu_gather_batch *batch;
 
+	/* No more batching if we have delayed rmaps pending */
+	if (tlb->delayed_rmap)
+		return false;
+
 	batch = tlb->active;
 	if (batch->next) {
 		tlb->active = batch->next;
@@ -43,6 +48,33 @@ static bool tlb_next_batch(struct mmu_gather *tlb)
 	return true;
 }
 
+#ifdef CONFIG_SMP
+/**
+ * tlb_flush_rmaps - do pending rmap removals after we have flushed the TLB
+ * @tlb: the current mmu_gather
+ *
+ * Note that because of how tlb_next_batch() above works, we will
+ * never start new batches with pending delayed rmaps, so we only
+ * need to walk through the current active batch.
+ */
+void tlb_flush_rmaps(struct mmu_gather *tlb, struct vm_area_struct *vma)
+{
+	struct mmu_gather_batch *batch;
+
+	batch = tlb->active;
+	for (int i = 0; i < batch->nr; i++) {
+		struct encoded_page *enc = batch->encoded_pages[i];
+
+		if (encoded_page_flags(enc)) {
+			struct page *page = encoded_page_ptr(enc);
+			page_remove_rmap(page, vma, false);
+		}
+	}
+
+	tlb->delayed_rmap = 0;
+}
+#endif
+
 static void tlb_batch_pages_flush(struct mmu_gather *tlb)
 {
 	struct mmu_gather_batch *batch;
@@ -284,6 +316,7 @@ static void __tlb_gather_mmu(struct mmu_gather *tlb, struct mm_struct *mm,
 	tlb->active     = &tlb->local;
 	tlb->batch_count = 0;
 #endif
+	tlb->delayed_rmap = 0;
 
 	tlb_table_init(tlb);
 #ifdef CONFIG_MMU_GATHER_PAGE_SIZE