The patch titled
Subject: mm/mmu_gather: define ENCODED_PAGE_FLAG_DELAY_RMAP
has been added to the -mm mm-unstable branch. Its filename is
mm-mmu_gather-define-encoded_page_flag_delay_rmap.patch
This patch will shortly appear at
https://git.kernel.org/pub/scm/linux/kernel/git/akpm/25-new.git/tree/patches/mm-mmu_gather-define-encoded_page_flag_delay_rmap.patch
This patch will later appear in the mm-unstable branch at
git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm
Before you just go and hit "reply", please:
a) Consider who else should be cc'ed
b) Prefer to cc a suitable mailing list as well
c) Ideally: find the original patch on the mailing list and do a
reply-to-all to that, adding suitable additional cc's
*** Remember to use Documentation/process/submit-checklist.rst when testing your code ***
The -mm tree is included into linux-next via the mm-everything
branch at git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm
and is updated there every 2-3 working days
------------------------------------------------------
From: David Hildenbrand <david@xxxxxxxxxx>
Subject: mm/mmu_gather: define ENCODED_PAGE_FLAG_DELAY_RMAP
Date: Wed, 14 Feb 2024 21:44:31 +0100
Nowadays, encoded pages are only used in mmu_gather handling. Let's
update the documentation, and define ENCODED_PAGE_BIT_DELAY_RMAP. While
at it, rename ENCODE_PAGE_BITS to ENCODED_PAGE_BITS.
If encoded page pointers would ever be used in other context again, we'd
likely want to change the defines to reflect their context (e.g.,
ENCODED_PAGE_FLAG_MMU_GATHER_DELAY_RMAP). For now, let's keep it simple.
This is a preparation for using the remaining spare bit to indicate that
the next item in an array of encoded pages is a "nr_pages" argument and
not an encoded page.
Link: https://lkml.kernel.org/r/20240214204435.167852-7-david@xxxxxxxxxx
Signed-off-by: David Hildenbrand <david@xxxxxxxxxx>
Reviewed-by: Ryan Roberts <ryan.roberts@xxxxxxx>
Cc: Alexander Gordeev <agordeev@xxxxxxxxxxxxx>
Cc: Aneesh Kumar K.V <aneesh.kumar@xxxxxxxxxxxxx>
Cc: Arnd Bergmann <arnd@xxxxxxxx>
Cc: Catalin Marinas <catalin.marinas@xxxxxxx>
Cc: Christian Borntraeger <borntraeger@xxxxxxxxxxxxx>
Cc: Christophe Leroy <christophe.leroy@xxxxxxxxxx>
Cc: Heiko Carstens <hca@xxxxxxxxxxxxx>
Cc: Matthew Wilcox (Oracle) <willy@xxxxxxxxxxxxx>
Cc: Michael Ellerman <mpe@xxxxxxxxxxxxxx>
Cc: Michal Hocko <mhocko@xxxxxxxx>
Cc: "Naveen N. Rao" <naveen.n.rao@xxxxxxxxxxxxx>
Cc: Nicholas Piggin <npiggin@xxxxxxxxx>
Cc: Peter Zijlstra (Intel) <peterz@xxxxxxxxxxxxx>
Cc: Sven Schnelle <svens@xxxxxxxxxxxxx>
Cc: Vasily Gorbik <gor@xxxxxxxxxxxxx>
Cc: Will Deacon <will@xxxxxxxxxx>
Cc: Yin Fengwei <fengwei.yin@xxxxxxxxx>
Signed-off-by: Andrew Morton <akpm@xxxxxxxxxxxxxxxxxxxx>
---
include/linux/mm_types.h | 17 +++++++++++------
mm/mmu_gather.c | 5 +++--
2 files changed, 14 insertions(+), 8 deletions(-)
--- a/include/linux/mm_types.h~mm-mmu_gather-define-encoded_page_flag_delay_rmap
+++ a/include/linux/mm_types.h
@@ -210,8 +210,8 @@ struct page {
*
* An 'encoded_page' pointer is a pointer to a regular 'struct page', but
* with the low bits of the pointer indicating extra context-dependent
- * information. Not super-common, but happens in mmu_gather and mlock
- * handling, and this acts as a type system check on that use.
+ * information. Only used in mmu_gather handling, and this acts as a type
+ * system check on that use.
*
* We only really have two guaranteed bits in general, although you could
* play with 'struct page' alignment (see CONFIG_HAVE_ALIGNED_STRUCT_PAGE)
@@ -220,21 +220,26 @@ struct page {
* Use the supplied helper functions to endcode/decode the pointer and bits.
*/
struct encoded_page;
-#define ENCODE_PAGE_BITS 3ul
+
+#define ENCODED_PAGE_BITS 3ul
+
+/* Perform rmap removal after we have flushed the TLB. */
+#define ENCODED_PAGE_BIT_DELAY_RMAP 1ul
+
static __always_inline struct encoded_page *encode_page(struct page *page, unsigned long flags)
{
- BUILD_BUG_ON(flags > ENCODE_PAGE_BITS);
+ BUILD_BUG_ON(flags > ENCODED_PAGE_BITS);
return (struct encoded_page *)(flags | (unsigned long)page);
}
static inline unsigned long encoded_page_flags(struct encoded_page *page)
{
- return ENCODE_PAGE_BITS & (unsigned long)page;
+ return ENCODED_PAGE_BITS & (unsigned long)page;
}
static inline struct page *encoded_page_ptr(struct encoded_page *page)
{
- return (struct page *)(~ENCODE_PAGE_BITS & (unsigned long)page);
+ return (struct page *)(~ENCODED_PAGE_BITS & (unsigned long)page);
}
/*
--- a/mm/mmu_gather.c~mm-mmu_gather-define-encoded_page_flag_delay_rmap
+++ a/mm/mmu_gather.c
@@ -53,7 +53,7 @@ static void tlb_flush_rmap_batch(struct
for (int i = 0; i < batch->nr; i++) {
struct encoded_page *enc = batch->encoded_pages[i];
- if (encoded_page_flags(enc)) {
+ 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);
}
@@ -119,6 +119,7 @@ static void tlb_batch_list_free(struct m
bool __tlb_remove_page_size(struct mmu_gather *tlb, struct page *page,
bool delay_rmap, int page_size)
{
+ int flags = delay_rmap ? ENCODED_PAGE_BIT_DELAY_RMAP : 0;
struct mmu_gather_batch *batch;
VM_BUG_ON(!tlb->end);
@@ -132,7 +133,7 @@ bool __tlb_remove_page_size(struct mmu_g
* Add the page and check if we are full. If so
* force a flush.
*/
- batch->encoded_pages[batch->nr++] = encode_page(page, delay_rmap);
+ batch->encoded_pages[batch->nr++] = encode_page(page, flags);
if (batch->nr == batch->max) {
if (!tlb_next_batch(tlb))
return true;
_
Patches currently in -mm which might be from david@xxxxxxxxxx are
arm-pgtable-define-pfn_pte_shift.patch
nios2-pgtable-define-pfn_pte_shift.patch
powerpc-pgtable-define-pfn_pte_shift.patch
riscv-pgtable-define-pfn_pte_shift.patch
s390-pgtable-define-pfn_pte_shift.patch
sparc-pgtable-define-pfn_pte_shift.patch
mm-pgtable-make-pte_next_pfn-independent-of-set_ptes.patch
arm-mm-use-pte_next_pfn-in-set_ptes.patch
powerpc-mm-use-pte_next_pfn-in-set_ptes.patch
mm-memory-factor-out-copying-the-actual-pte-in-copy_present_pte.patch
mm-memory-pass-pte-to-copy_present_pte.patch
mm-memory-optimize-fork-with-pte-mapped-thp.patch
mm-memory-ignore-dirty-accessed-soft-dirty-bits-in-folio_pte_batch.patch
mm-memory-ignore-writable-bit-in-folio_pte_batch.patch
mm-memory-factor-out-zapping-of-present-pte-into-zap_present_pte.patch
mm-memory-handle-page-case-in-zap_present_pte-separately.patch
mm-memory-further-separate-anon-and-pagecache-folio-handling-in-zap_present_pte.patch
mm-memory-factor-out-zapping-folio-pte-into-zap_present_folio_pte.patch
mm-mmu_gather-pass-delay_rmap-instead-of-encoded-page-to-__tlb_remove_page_size.patch
mm-mmu_gather-define-encoded_page_flag_delay_rmap.patch
mm-mmu_gather-add-tlb_remove_tlb_entries.patch
mm-mmu_gather-add-__tlb_remove_folio_pages.patch
mm-mmu_gather-improve-cond_resched-handling-with-large-folios-and-expensive-page-freeing.patch
mm-memory-optimize-unmap-zap-with-pte-mapped-thp.patch
