mm/mmu_gather: add __tlb_remove_folio_pages()

Add __tlb_remove_folio_pages(), which will remove multiple consecutive
pages that belong to the same large folio, instead of only a single page. 
We'll be using this function when optimizing unmapping/zapping of large
folios that are mapped by PTEs.

We're using the remaining spare bit in an encoded_page to indicate that
the next enoced page in an array contains actually shifted "nr_pages". 
Teach swap/freeing code about putting multiple folio references, and
delayed rmap handling to remove page ranges of a folio.

This extension allows for still gathering almost as many small folios as
we used to (-1, because we have to prepare for a possibly bigger next
entry), but still allows for gathering consecutive pages that belong to
the same large folio.

Note that we don't pass the folio pointer, because it is not required for
now.  Further, we don't support page_size != PAGE_SIZE, it won't be
required for simple PTE batching.

We have to provide a separate s390 implementation, but it's fairly
straight forward.

Another, more invasive and likely more expensive, approach would be to use
folio+range or a PFN range instead of page+nr_pages.  But, we should do
that consistently for the whole mmu_gather.  For now, let's keep it simple
and add "nr_pages" only.

Note that it is now possible to gather significantly more pages: In the
past, we were able to gather ~10000 pages, now we can also gather ~5000
folio fragments that span multiple pages.  A folio fragment on x86-64 can
span up to 512 pages (2 MiB THP) and on arm64 with 64k in theory 8192
pages (512 MiB THP).  Gathering more memory is not considered something we
should worry about, especially because these are already corner cases.

While we can gather more total memory, we won't free more folio fragments.
As long as page freeing time primarily only depends on the number of
involved folios, there is no effective change for !preempt configurations.
However, we'll adjust tlb_batch_pages_flush() separately to handle corner
cases where page freeing time grows proportionally with the actual memory
size.

Link: https://lkml.kernel.org/r/20240214204435.167852-9-david@redhat.com
Signed-off-by: David Hildenbrand <david@redhat.com>
Reviewed-by: Ryan Roberts <ryan.roberts@arm.com>
Cc: Alexander Gordeev <agordeev@linux.ibm.com>
Cc: Aneesh Kumar K.V <aneesh.kumar@linux.ibm.com>
Cc: Arnd Bergmann <arnd@arndb.de>
Cc: Catalin Marinas <catalin.marinas@arm.com>
Cc: Christian Borntraeger <borntraeger@linux.ibm.com>
Cc: Christophe Leroy <christophe.leroy@csgroup.eu>
Cc: Heiko Carstens <hca@linux.ibm.com>
Cc: Matthew Wilcox (Oracle) <willy@infradead.org>
Cc: Michael Ellerman <mpe@ellerman.id.au>
Cc: Michal Hocko <mhocko@suse.com>
Cc: "Naveen N. Rao" <naveen.n.rao@linux.ibm.com>
Cc: Nicholas Piggin <npiggin@gmail.com>
Cc: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: Sven Schnelle <svens@linux.ibm.com>
Cc: Vasily Gorbik <gor@linux.ibm.com>
Cc: Will Deacon <will@kernel.org>
Cc: Yin Fengwei <fengwei.yin@intel.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>

3 files changed, 74 insertions, 14 deletions

diff --git a/mm/mmu_gather.c b/mm/mmu_gather.c
index 6540c99c6758..d175c0f1e2c8 100644
--- a/mm/mmu_gather.c
+++ b/mm/mmu_gather.c
@@ -50,12 +50,21 @@ static bool tlb_next_batch(struct mmu_gather *tlb)
 #ifdef CONFIG_SMP
 static void tlb_flush_rmap_batch(struct mmu_gather_batch *batch, struct vm_area_struct *vma)
 {
+	struct encoded_page **pages = batch->encoded_pages;
+
 	for (int i = 0; i < batch->nr; i++) {
-		struct encoded_page *enc = batch->encoded_pages[i];
+		struct encoded_page *enc = pages[i];
 
 		if (encoded_page_flags(enc) & ENCODED_PAGE_BIT_DELAY_RMAP) {
 			struct page *page = encoded_page_ptr(enc);
-			folio_remove_rmap_pte(page_folio(page), page, vma);
+			unsigned int nr_pages = 1;
+
+			if (unlikely(encoded_page_flags(enc) &
+				     ENCODED_PAGE_BIT_NR_PAGES_NEXT))
+				nr_pages = encoded_nr_pages(pages[++i]);
+
+			folio_remove_rmap_ptes(page_folio(page), page, nr_pages,
+					       vma);
 		}
 	}
 }
@@ -89,18 +98,26 @@ static void tlb_batch_pages_flush(struct mmu_gather *tlb)
 	for (batch = &tlb->local; batch && batch->nr; batch = batch->next) {
 		struct encoded_page **pages = batch->encoded_pages;
 
-		do {
+		while (batch->nr) {
 			/*
 			 * limit free batch count when PAGE_SIZE > 4K
 			 */
 			unsigned int nr = min(512U, batch->nr);
 
+			/*
+			 * Make sure we cover page + nr_pages, and don't leave
+			 * nr_pages behind when capping the number of entries.
+			 */
+			if (unlikely(encoded_page_flags(pages[nr - 1]) &
+				     ENCODED_PAGE_BIT_NR_PAGES_NEXT))
+				nr++;
+
 			free_pages_and_swap_cache(pages, nr);
 			pages += nr;
 			batch->nr -= nr;
 
 			cond_resched();
-		} while (batch->nr);
+		}
 	}
 	tlb->active = &tlb->local;
 }
@@ -116,8 +133,9 @@ static void tlb_batch_list_free(struct mmu_gather *tlb)
 	tlb->local.next = NULL;
 }
 
-bool __tlb_remove_page_size(struct mmu_gather *tlb, struct page *page,
-		bool delay_rmap, int page_size)
+static bool __tlb_remove_folio_pages_size(struct mmu_gather *tlb,
+		struct page *page, unsigned int nr_pages, bool delay_rmap,
+		int page_size)
 {
 	int flags = delay_rmap ? ENCODED_PAGE_BIT_DELAY_RMAP : 0;
 	struct mmu_gather_batch *batch;
@@ -126,6 +144,8 @@ bool __tlb_remove_page_size(struct mmu_gather *tlb, struct page *page,
 
 #ifdef CONFIG_MMU_GATHER_PAGE_SIZE
 	VM_WARN_ON(tlb->page_size != page_size);
+	VM_WARN_ON_ONCE(nr_pages != 1 && page_size != PAGE_SIZE);
+	VM_WARN_ON_ONCE(page_folio(page) != page_folio(page + nr_pages - 1));
 #endif
 
 	batch = tlb->active;
@@ -133,17 +153,40 @@ bool __tlb_remove_page_size(struct mmu_gather *tlb, struct page *page,
 	 * Add the page and check if we are full. If so
 	 * force a flush.
 	 */
-	batch->encoded_pages[batch->nr++] = encode_page(page, flags);
-	if (batch->nr == batch->max) {
+	if (likely(nr_pages == 1)) {
+		batch->encoded_pages[batch->nr++] = encode_page(page, flags);
+	} else {
+		flags |= ENCODED_PAGE_BIT_NR_PAGES_NEXT;
+		batch->encoded_pages[batch->nr++] = encode_page(page, flags);
+		batch->encoded_pages[batch->nr++] = encode_nr_pages(nr_pages);
+	}
+	/*
+	 * Make sure that we can always add another "page" + "nr_pages",
+	 * requiring two entries instead of only a single one.
+	 */
+	if (batch->nr >= batch->max - 1) {
 		if (!tlb_next_batch(tlb))
 			return true;
 		batch = tlb->active;
 	}
-	VM_BUG_ON_PAGE(batch->nr > batch->max, page);
+	VM_BUG_ON_PAGE(batch->nr > batch->max - 1, page);
 
 	return false;
 }
 
+bool __tlb_remove_folio_pages(struct mmu_gather *tlb, struct page *page,
+		unsigned int nr_pages, bool delay_rmap)
+{
+	return __tlb_remove_folio_pages_size(tlb, page, nr_pages, delay_rmap,
+					     PAGE_SIZE);
+}
+
+bool __tlb_remove_page_size(struct mmu_gather *tlb, struct page *page,
+		bool delay_rmap, int page_size)
+{
+	return __tlb_remove_folio_pages_size(tlb, page, 1, delay_rmap, page_size);
+}
+
 #endif /* MMU_GATHER_NO_GATHER */
 
 #ifdef CONFIG_MMU_GATHER_TABLE_FREE
diff --git a/mm/swap.c b/mm/swap.c
index cd8f0150ba3a..e5380d732c0d 100644
--- a/mm/swap.c
+++ b/mm/swap.c
@@ -967,11 +967,17 @@ void release_pages(release_pages_arg arg, int nr)
 	unsigned int lock_batch;
 
 	for (i = 0; i < nr; i++) {
+		unsigned int nr_refs = 1;
 		struct folio *folio;
 
 		/* Turn any of the argument types into a folio */
 		folio = page_folio(encoded_page_ptr(encoded[i]));
 
+		/* Is our next entry actually "nr_pages" -> "nr_refs" ? */
+		if (unlikely(encoded_page_flags(encoded[i]) &
+			     ENCODED_PAGE_BIT_NR_PAGES_NEXT))
+			nr_refs = encoded_nr_pages(encoded[++i]);
+
 		/*
 		 * Make sure the IRQ-safe lock-holding time does not get
 		 * excessive with a continuous string of pages from the
@@ -990,14 +996,14 @@ void release_pages(release_pages_arg arg, int nr)
 				unlock_page_lruvec_irqrestore(lruvec, flags);
 				lruvec = NULL;
 			}
-			if (put_devmap_managed_page(&folio->page))
+			if (put_devmap_managed_page_refs(&folio->page, nr_refs))
 				continue;
-			if (folio_put_testzero(folio))
+			if (folio_ref_sub_and_test(folio, nr_refs))
 				free_zone_device_page(&folio->page);
 			continue;
 		}
 
-		if (!folio_put_testzero(folio))
+		if (!folio_ref_sub_and_test(folio, nr_refs))
 			continue;
 
 		if (folio_test_large(folio)) {
diff --git a/mm/swap_state.c b/mm/swap_state.c
index 7255c01a1e4e..2f540748f7c0 100644
--- a/mm/swap_state.c
+++ b/mm/swap_state.c
@@ -311,8 +311,19 @@ void free_page_and_swap_cache(struct page *page)
 void free_pages_and_swap_cache(struct encoded_page **pages, int nr)
 {
 	lru_add_drain();
-	for (int i = 0; i < nr; i++)
-		free_swap_cache(encoded_page_ptr(pages[i]));
+	for (int i = 0; i < nr; i++) {
+		struct page *page = encoded_page_ptr(pages[i]);
+
+		/*
+		 * Skip over the "nr_pages" entry. It's sufficient to call
+		 * free_swap_cache() only once per folio.
+		 */
+		if (unlikely(encoded_page_flags(pages[i]) &
+			     ENCODED_PAGE_BIT_NR_PAGES_NEXT))
+			i++;
+
+		free_swap_cache(page);
+	}
 	release_pages(pages, nr);
 }