From: Hugh Dickins <hughd@google.com>
To: Andrew Morton <akpm@linux-foundation.org>
Cc: Mike Kravetz <mike.kravetz@oracle.com>,
Mike Rapoport <rppt@kernel.org>,
"Kirill A. Shutemov" <kirill.shutemov@linux.intel.com>,
Matthew Wilcox <willy@infradead.org>,
David Hildenbrand <david@redhat.com>,
Suren Baghdasaryan <surenb@google.com>,
Qi Zheng <zhengqi.arch@bytedance.com>,
Yang Shi <shy828301@gmail.com>,
Mel Gorman <mgorman@techsingularity.net>,
Peter Xu <peterx@redhat.com>,
Peter Zijlstra <peterz@infradead.org>,
Will Deacon <will@kernel.org>, Yu Zhao <yuzhao@google.com>,
Alistair Popple <apopple@nvidia.com>,
Ralph Campbell <rcampbell@nvidia.com>,
Ira Weiny <ira.weiny@intel.com>,
Steven Price <steven.price@arm.com>,
SeongJae Park <sj@kernel.org>,
Lorenzo Stoakes <lstoakes@gmail.com>,
Huang Ying <ying.huang@intel.com>,
Naoya Horiguchi <naoya.horiguchi@nec.com>,
Christophe Leroy <christophe.leroy@csgroup.eu>,
Zack Rusin <zackr@vmware.com>, Jason Gunthorpe <jgg@ziepe.ca>,
Axel Rasmussen <axelrasmussen@google.com>,
Anshuman Khandual <anshuman.khandual@arm.com>,
Pasha Tatashin <pasha.tatashin@soleen.com>,
Miaohe Lin <linmiaohe@huawei.com>,
Minchan Kim <minchan@kernel.org>,
Christoph Hellwig <hch@infradead.org>,
Song Liu <song@kernel.org>,
Thomas Hellstrom <thomas.hellstrom@linux.intel.com>,
Ryan Roberts <ryan.roberts@arm.com>,
linux-kernel@vger.kernel.org, linux-mm@kvack.org
Subject: [PATCH v2 01/32] mm: use pmdp_get_lockless() without surplus barrier()
Date: Thu, 8 Jun 2023 18:06:53 -0700 (PDT) [thread overview]
Message-ID: <f35279a9-9ac0-de22-d245-591afbfb4dc@google.com> (raw)
In-Reply-To: <c1c9a74a-bc5b-15ea-e5d2-8ec34bc921d@google.com>
Use pmdp_get_lockless() in preference to READ_ONCE(*pmdp), to get a more
reliable result with PAE (or READ_ONCE as before without PAE); and remove
the unnecessary extra barrier()s which got left behind in its callers.
HOWEVER: Note the small print in linux/pgtable.h, where it was designed
specifically for fast GUP, and depends on interrupts being disabled for
its full guarantee: most callers which have been added (here and before)
do NOT have interrupts disabled, so there is still some need for caution.
Signed-off-by: Hugh Dickins <hughd@google.com>
Acked-by: Yu Zhao <yuzhao@google.com>
Acked-by: Peter Xu <peterx@redhat.com>
---
fs/userfaultfd.c | 10 +---------
include/linux/pgtable.h | 17 -----------------
mm/gup.c | 6 +-----
mm/hmm.c | 2 +-
mm/khugepaged.c | 5 -----
mm/ksm.c | 3 +--
mm/memory.c | 14 ++------------
mm/mprotect.c | 5 -----
mm/page_vma_mapped.c | 2 +-
9 files changed, 7 insertions(+), 57 deletions(-)
diff --git a/fs/userfaultfd.c b/fs/userfaultfd.c
index 0fd96d6e39ce..f7a0817b1ec0 100644
--- a/fs/userfaultfd.c
+++ b/fs/userfaultfd.c
@@ -349,15 +349,7 @@ static inline bool userfaultfd_must_wait(struct userfaultfd_ctx *ctx,
if (!pud_present(*pud))
goto out;
pmd = pmd_offset(pud, address);
- /*
- * READ_ONCE must function as a barrier with narrower scope
- * and it must be equivalent to:
- * _pmd = *pmd; barrier();
- *
- * This is to deal with the instability (as in
- * pmd_trans_unstable) of the pmd.
- */
- _pmd = READ_ONCE(*pmd);
+ _pmd = pmdp_get_lockless(pmd);
if (pmd_none(_pmd))
goto out;
diff --git a/include/linux/pgtable.h b/include/linux/pgtable.h
index c5a51481bbb9..8ec27fe69dc8 100644
--- a/include/linux/pgtable.h
+++ b/include/linux/pgtable.h
@@ -1344,23 +1344,6 @@ static inline int pud_trans_unstable(pud_t *pud)
static inline int pmd_none_or_trans_huge_or_clear_bad(pmd_t *pmd)
{
pmd_t pmdval = pmdp_get_lockless(pmd);
- /*
- * The barrier will stabilize the pmdval in a register or on
- * the stack so that it will stop changing under the code.
- *
- * When CONFIG_TRANSPARENT_HUGEPAGE=y on x86 32bit PAE,
- * pmdp_get_lockless is allowed to return a not atomic pmdval
- * (for example pointing to an hugepage that has never been
- * mapped in the pmd). The below checks will only care about
- * the low part of the pmd with 32bit PAE x86 anyway, with the
- * exception of pmd_none(). So the important thing is that if
- * the low part of the pmd is found null, the high part will
- * be also null or the pmd_none() check below would be
- * confused.
- */
-#ifdef CONFIG_TRANSPARENT_HUGEPAGE
- barrier();
-#endif
/*
* !pmd_present() checks for pmd migration entries
*
diff --git a/mm/gup.c b/mm/gup.c
index bbe416236593..3bd5d3854c51 100644
--- a/mm/gup.c
+++ b/mm/gup.c
@@ -653,11 +653,7 @@ static struct page *follow_pmd_mask(struct vm_area_struct *vma,
struct mm_struct *mm = vma->vm_mm;
pmd = pmd_offset(pudp, address);
- /*
- * The READ_ONCE() will stabilize the pmdval in a register or
- * on the stack so that it will stop changing under the code.
- */
- pmdval = READ_ONCE(*pmd);
+ pmdval = pmdp_get_lockless(pmd);
if (pmd_none(pmdval))
return no_page_table(vma, flags);
if (!pmd_present(pmdval))
diff --git a/mm/hmm.c b/mm/hmm.c
index 6a151c09de5e..e23043345615 100644
--- a/mm/hmm.c
+++ b/mm/hmm.c
@@ -332,7 +332,7 @@ static int hmm_vma_walk_pmd(pmd_t *pmdp,
pmd_t pmd;
again:
- pmd = READ_ONCE(*pmdp);
+ pmd = pmdp_get_lockless(pmdp);
if (pmd_none(pmd))
return hmm_vma_walk_hole(start, end, -1, walk);
diff --git a/mm/khugepaged.c b/mm/khugepaged.c
index 6b9d39d65b73..732f9ac393fc 100644
--- a/mm/khugepaged.c
+++ b/mm/khugepaged.c
@@ -961,11 +961,6 @@ static int find_pmd_or_thp_or_none(struct mm_struct *mm,
return SCAN_PMD_NULL;
pmde = pmdp_get_lockless(*pmd);
-
-#ifdef CONFIG_TRANSPARENT_HUGEPAGE
- /* See comments in pmd_none_or_trans_huge_or_clear_bad() */
- barrier();
-#endif
if (pmd_none(pmde))
return SCAN_PMD_NONE;
if (!pmd_present(pmde))
diff --git a/mm/ksm.c b/mm/ksm.c
index 0156bded3a66..df2aa281d49d 100644
--- a/mm/ksm.c
+++ b/mm/ksm.c
@@ -1194,8 +1194,7 @@ static int replace_page(struct vm_area_struct *vma, struct page *page,
* without holding anon_vma lock for write. So when looking for a
* genuine pmde (in which to find pte), test present and !THP together.
*/
- pmde = *pmd;
- barrier();
+ pmde = pmdp_get_lockless(pmd);
if (!pmd_present(pmde) || pmd_trans_huge(pmde))
goto out;
diff --git a/mm/memory.c b/mm/memory.c
index f69fbc251198..2eb54c0d5d3c 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -4925,18 +4925,9 @@ static vm_fault_t handle_pte_fault(struct vm_fault *vmf)
* So now it's safe to run pte_offset_map().
*/
vmf->pte = pte_offset_map(vmf->pmd, vmf->address);
- vmf->orig_pte = *vmf->pte;
+ vmf->orig_pte = ptep_get_lockless(vmf->pte);
vmf->flags |= FAULT_FLAG_ORIG_PTE_VALID;
- /*
- * some architectures can have larger ptes than wordsize,
- * e.g.ppc44x-defconfig has CONFIG_PTE_64BIT=y and
- * CONFIG_32BIT=y, so READ_ONCE cannot guarantee atomic
- * accesses. The code below just needs a consistent view
- * for the ifs and we later double check anyway with the
- * ptl lock held. So here a barrier will do.
- */
- barrier();
if (pte_none(vmf->orig_pte)) {
pte_unmap(vmf->pte);
vmf->pte = NULL;
@@ -5060,9 +5051,8 @@ static vm_fault_t __handle_mm_fault(struct vm_area_struct *vma,
if (!(ret & VM_FAULT_FALLBACK))
return ret;
} else {
- vmf.orig_pmd = *vmf.pmd;
+ vmf.orig_pmd = pmdp_get_lockless(vmf.pmd);
- barrier();
if (unlikely(is_swap_pmd(vmf.orig_pmd))) {
VM_BUG_ON(thp_migration_supported() &&
!is_pmd_migration_entry(vmf.orig_pmd));
diff --git a/mm/mprotect.c b/mm/mprotect.c
index 92d3d3ca390a..c5a13c0f1017 100644
--- a/mm/mprotect.c
+++ b/mm/mprotect.c
@@ -309,11 +309,6 @@ static inline int pmd_none_or_clear_bad_unless_trans_huge(pmd_t *pmd)
{
pmd_t pmdval = pmdp_get_lockless(pmd);
- /* See pmd_none_or_trans_huge_or_clear_bad for info on barrier */
-#ifdef CONFIG_TRANSPARENT_HUGEPAGE
- barrier();
-#endif
-
if (pmd_none(pmdval))
return 1;
if (pmd_trans_huge(pmdval))
diff --git a/mm/page_vma_mapped.c b/mm/page_vma_mapped.c
index 4e448cfbc6ef..64aff6718bdb 100644
--- a/mm/page_vma_mapped.c
+++ b/mm/page_vma_mapped.c
@@ -210,7 +210,7 @@ bool page_vma_mapped_walk(struct page_vma_mapped_walk *pvmw)
* compiler and used as a stale value after we've observed a
* subsequent update.
*/
- pmde = READ_ONCE(*pvmw->pmd);
+ pmde = pmdp_get_lockless(pvmw->pmd);
if (pmd_trans_huge(pmde) || is_pmd_migration_entry(pmde) ||
(pmd_present(pmde) && pmd_devmap(pmde))) {
--
2.35.3
next prev parent reply other threads:[~2023-06-09 1:07 UTC|newest]
Thread overview: 67+ messages / expand[flat|nested] mbox.gz Atom feed top
2023-06-09 0:54 [PATCH v2 00/32] mm: allow pte_offset_map[_lock]() to fail Hugh Dickins
2023-06-09 1:06 ` Hugh Dickins [this message]
2023-06-09 1:08 ` [PATCH v2 02/32] mm/migrate: remove cruft from migration_entry_wait()s Hugh Dickins
2023-06-09 1:09 ` [PATCH v2 03/32] mm/pgtable: kmap_local_page() instead of kmap_atomic() Hugh Dickins
2023-06-09 1:10 ` [PATCH v2 04/32] mm/pgtable: allow pte_offset_map[_lock]() to fail Hugh Dickins
2023-07-11 1:23 ` Zi Yan
2023-07-28 13:53 ` Yongqin Liu
2023-07-28 14:05 ` Matthew Wilcox
2023-07-28 16:58 ` Hugh Dickins
2023-08-05 16:06 ` Yongqin Liu
2023-08-05 17:07 ` Matthew Wilcox
2023-08-08 0:29 ` John Hubbard
2023-06-09 1:11 ` [PATCH v2 05/32] mm/filemap: allow pte_offset_map_lock() " Hugh Dickins
2023-07-11 1:34 ` Zi Yan
2023-07-11 5:21 ` Hugh Dickins
2023-06-09 1:12 ` [PATCH v2 06/32] mm/page_vma_mapped: delete bogosity in page_vma_mapped_walk() Hugh Dickins
2023-07-11 1:47 ` Zi Yan
2023-06-09 1:14 ` [PATCH v2 07/32] mm/page_vma_mapped: reformat map_pte() with less indentation Hugh Dickins
2023-07-11 1:56 ` Zi Yan
2023-06-09 1:15 ` [PATCH v2 08/32] mm/page_vma_mapped: pte_offset_map_nolock() not pte_lockptr() Hugh Dickins
2023-06-09 1:17 ` [PATCH v2 09/32] mm/pagewalkers: ACTION_AGAIN if pte_offset_map_lock() fails Hugh Dickins
2023-06-09 1:18 ` [PATCH v2 10/32] mm/pagewalk: walk_pte_range() allow for pte_offset_map() Hugh Dickins
2023-06-09 1:20 ` [PATCH v2 11/32] mm/vmwgfx: simplify pmd & pud mapping dirty helpers Hugh Dickins
2023-06-09 1:21 ` [PATCH v2 12/32] mm/vmalloc: vmalloc_to_page() use pte_offset_kernel() Hugh Dickins
2023-07-10 14:42 ` Mark Brown
2023-07-10 17:18 ` Lorenzo Stoakes
2023-07-10 17:33 ` Mark Brown
2023-07-11 4:34 ` Hugh Dickins
2023-07-11 15:34 ` Mark Brown
2023-07-11 16:13 ` Hugh Dickins
2023-07-11 16:34 ` Mark Brown
2023-07-11 17:57 ` Mark Brown
2023-07-13 11:19 ` Linux regression tracking #update (Thorsten Leemhuis)
2023-07-20 10:32 ` Will Deacon
2023-07-20 12:06 ` Mark Brown
2023-08-08 5:52 ` Linux regression tracking (Thorsten Leemhuis)
2023-08-08 11:09 ` Mark Brown
2023-08-11 8:00 ` Linux regression tracking #update (Thorsten Leemhuis)
2023-07-11 14:48 ` Linux regression tracking #adding (Thorsten Leemhuis)
2023-06-09 1:23 ` [PATCH v2 13/32] mm/hmm: retry if pte_offset_map() fails Hugh Dickins
2023-06-09 1:24 ` [PATCH v2 14/32] mm/userfaultfd: " Hugh Dickins
2023-06-09 1:26 ` [PATCH v2 15/32] mm/userfaultfd: allow pte_offset_map_lock() to fail Hugh Dickins
2023-06-09 1:27 ` [PATCH v2 16/32] mm/debug_vm_pgtable,page_table_check: warn pte map fails Hugh Dickins
2023-06-09 1:29 ` [PATCH v2 17/32] mm/various: give up if pte_offset_map[_lock]() fails Hugh Dickins
2023-06-09 1:30 ` [PATCH v2 18/32] mm/mprotect: delete pmd_none_or_clear_bad_unless_trans_huge() Hugh Dickins
2023-06-09 1:32 ` [PATCH v2 19/32] mm/mremap: retry if either pte_offset_map_*lock() fails Hugh Dickins
2023-06-09 1:34 ` [PATCH v2 20/32] mm/madvise: clean up pte_offset_map_lock() scans Hugh Dickins
2023-06-09 1:35 ` [PATCH v2 21/32] mm/madvise: clean up force_shm_swapin_readahead() Hugh Dickins
2023-06-09 1:36 ` [PATCH v2 22/32] mm/swapoff: allow pte_offset_map[_lock]() to fail Hugh Dickins
2023-06-09 1:37 ` [PATCH v2 23/32] mm/mglru: allow pte_offset_map_nolock() " Hugh Dickins
2023-06-09 1:38 ` [PATCH v2 24/32] mm/migrate_device: allow pte_offset_map_lock() " Hugh Dickins
2023-06-09 1:39 ` [PATCH v2 25/32] mm/gup: remove FOLL_SPLIT_PMD use of pmd_trans_unstable() Hugh Dickins
2023-06-09 18:24 ` Yang Shi
2023-06-09 1:41 ` [PATCH v2 26/32] mm/huge_memory: split huge pmd under one pte_offset_map() Hugh Dickins
2023-06-09 1:42 ` [PATCH v2 27/32] mm/khugepaged: allow pte_offset_map[_lock]() to fail Hugh Dickins
2023-06-09 1:43 ` [PATCH v2 28/32] mm/memory: " Hugh Dickins
2023-06-09 20:06 ` Andrew Morton
2023-06-09 20:11 ` Hugh Dickins
2023-06-12 9:10 ` Ryan Roberts
2023-06-15 23:10 ` [PATCH v2 28/32 fix] mm/memory: allow pte_offset_map[_lock]() to fail: fix Hugh Dickins
2023-06-09 1:45 ` [PATCH v2 29/32] mm/memory: handle_pte_fault() use pte_offset_map_nolock() Hugh Dickins
2023-06-09 1:50 ` [PATCH v2 30/32] mm/pgtable: delete pmd_trans_unstable() and friends Hugh Dickins
2023-06-09 1:52 ` [PATCH v2 31/32] mm/swap: swap_vma_readahead() do the pte_offset_map() Hugh Dickins
2023-06-12 8:03 ` Huang, Ying
2023-06-14 3:58 ` Hugh Dickins
2023-06-09 1:53 ` [PATCH v2 32/32] perf/core: Allow pte_offset_map() to fail Hugh Dickins
2023-06-20 6:50 ` [PATCH] mm/swapfile: delete outdated pte_offset_map() comment Hugh Dickins
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=f35279a9-9ac0-de22-d245-591afbfb4dc@google.com \
--to=hughd@google.com \
--cc=akpm@linux-foundation.org \
--cc=anshuman.khandual@arm.com \
--cc=apopple@nvidia.com \
--cc=axelrasmussen@google.com \
--cc=christophe.leroy@csgroup.eu \
--cc=david@redhat.com \
--cc=hch@infradead.org \
--cc=ira.weiny@intel.com \
--cc=jgg@ziepe.ca \
--cc=kirill.shutemov@linux.intel.com \
--cc=linmiaohe@huawei.com \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-mm@kvack.org \
--cc=lstoakes@gmail.com \
--cc=mgorman@techsingularity.net \
--cc=mike.kravetz@oracle.com \
--cc=minchan@kernel.org \
--cc=naoya.horiguchi@nec.com \
--cc=pasha.tatashin@soleen.com \
--cc=peterx@redhat.com \
--cc=peterz@infradead.org \
--cc=rcampbell@nvidia.com \
--cc=rppt@kernel.org \
--cc=ryan.roberts@arm.com \
--cc=shy828301@gmail.com \
--cc=sj@kernel.org \
--cc=song@kernel.org \
--cc=steven.price@arm.com \
--cc=surenb@google.com \
--cc=thomas.hellstrom@linux.intel.com \
--cc=will@kernel.org \
--cc=willy@infradead.org \
--cc=ying.huang@intel.com \
--cc=yuzhao@google.com \
--cc=zackr@vmware.com \
--cc=zhengqi.arch@bytedance.com \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).