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 gather
also gather ~5000 folio fragments that span multiple pages. A folio
fragement on x86-64 can be 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.
Signed-off-by: David Hildenbrand <david@xxxxxxxxxx>
---
arch/s390/include/asm/tlb.h | 17 +++++++++++
include/asm-generic/tlb.h | 8 +++++
include/linux/mm_types.h | 20 ++++++++++++
mm/mmu_gather.c | 61 +++++++++++++++++++++++++++++++------
mm/swap.c | 12 ++++++--
mm/swap_state.c | 15 +++++++--
6 files changed, 119 insertions(+), 14 deletions(-)
diff --git a/arch/s390/include/asm/tlb.h b/arch/s390/include/asm/tlb.h
index 48df896d5b79..e95b2c8081eb 100644
--- a/arch/s390/include/asm/tlb.h
+++ b/arch/s390/include/asm/tlb.h
@@ -26,6 +26,8 @@ void __tlb_remove_table(void *_table);
static inline void tlb_flush(struct mmu_gather *tlb);
static inline bool __tlb_remove_page_size(struct mmu_gather *tlb,
struct page *page, bool delay_rmap, int page_size);
+static inline bool __tlb_remove_folio_pages(struct mmu_gather *tlb,
+ struct page *page, unsigned int nr_pages, bool delay_rmap);
#define tlb_flush tlb_flush
#define pte_free_tlb pte_free_tlb
@@ -52,6 +54,21 @@ static inline bool __tlb_remove_page_size(struct mmu_gather *tlb,
return false;
}
+static inline bool __tlb_remove_folio_pages(struct mmu_gather *tlb,
+ struct page *page, unsigned int nr_pages, bool delay_rmap)
+{
+ struct encoded_page *encoded_pages[] = {
+ encode_page(page, ENCODED_PAGE_BIT_NR_PAGES_NEXT),
+ encode_nr_pages(nr_pages),
+ };
+
+ VM_WARN_ON_ONCE(delay_rmap);
+ VM_WARN_ON_ONCE(page_folio(page) != page_folio(page + nr_pages - 1));
+
+ free_pages_and_swap_cache(encoded_pages, ARRAY_SIZE(encoded_pages));
+ return false;
+}
+
static inline void tlb_flush(struct mmu_gather *tlb)
{
__tlb_flush_mm_lazy(tlb->mm);
diff --git a/include/asm-generic/tlb.h b/include/asm-generic/tlb.h
index 95d60a4f468a..bd00dd238b79 100644
--- a/include/asm-generic/tlb.h
+++ b/include/asm-generic/tlb.h
@@ -69,6 +69,7 @@
*
* - tlb_remove_page() / __tlb_remove_page()
* - tlb_remove_page_size() / __tlb_remove_page_size()
+ * - __tlb_remove_folio_pages()
*
* __tlb_remove_page_size() is the basic primitive that queues a page for
* freeing. __tlb_remove_page() assumes PAGE_SIZE. Both will return a
@@ -78,6 +79,11 @@
* tlb_remove_page() and tlb_remove_page_size() imply the call to
* tlb_flush_mmu() when required and has no return value.
*
+ * __tlb_remove_folio_pages() is similar to __tlb_remove_page(), however,
+ * instead of removing a single page, remove the given number of consecutive
+ * pages that are all part of the same (large) folio: just like calling
+ * __tlb_remove_page() on each page individually.
+ *
* - tlb_change_page_size()
*
* call before __tlb_remove_page*() to set the current page-size; implies a
@@ -262,6 +268,8 @@ struct mmu_gather_batch {
extern bool __tlb_remove_page_size(struct mmu_gather *tlb, struct page *page,
bool delay_rmap, int page_size);
+bool __tlb_remove_folio_pages(struct mmu_gather *tlb, struct page *page,
+ unsigned int nr_pages, bool delay_rmap);
#ifdef CONFIG_SMP
/*
diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h
index 1b89eec0d6df..a7223ba3ea1e 100644
--- a/include/linux/mm_types.h
+++ b/include/linux/mm_types.h
@@ -226,6 +226,15 @@ struct encoded_page;
/* Perform rmap removal after we have flushed the TLB. */
#define ENCODED_PAGE_BIT_DELAY_RMAP 1ul
+/*
+ * The next item in an encoded_page array is the "nr_pages" argument, specifying
+ * the number of consecutive pages starting from this page, that all belong to
+ * the same folio. For example, "nr_pages" corresponds to the number of folio
+ * references that must be dropped. If this bit is not set, "nr_pages" is
+ * implicitly 1.
+ */
+#define ENCODED_PAGE_BIT_NR_PAGES_NEXT 2ul
+
static __always_inline struct encoded_page *encode_page(struct page *page, unsigned long flags)
{
BUILD_BUG_ON(flags > ENCODED_PAGE_BITS);
@@ -242,6 +251,17 @@ static inline struct page *encoded_page_ptr(struct encoded_page *page)
return (struct page *)(~ENCODED_PAGE_BITS & (unsigned long)page);
}
+static __always_inline struct encoded_page *encode_nr_pages(unsigned long nr)
+{
+ VM_WARN_ON_ONCE((nr << 2) >> 2 != nr);
+ return (struct encoded_page *)(nr << 2);
+}
+
+static __always_inline unsigned long encoded_nr_pages(struct encoded_page *page)
+{
+ return ((unsigned long)page) >> 2;
+}
+
/*
* A swap entry has to fit into a "unsigned long", as the entry is hidden
* in the "index" field of the swapper address space.
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));
