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 09/32] mm/pagewalkers: ACTION_AGAIN if pte_offset_map_lock() fails
Date: Thu, 8 Jun 2023 18:17:26 -0700 (PDT) [thread overview]
Message-ID: <c77d9d10-3aad-e3ce-4896-99e91c7947f3@google.com> (raw)
In-Reply-To: <c1c9a74a-bc5b-15ea-e5d2-8ec34bc921d@google.com>
Simple walk_page_range() users should set ACTION_AGAIN to retry when
pte_offset_map_lock() fails.
No need to check pmd_trans_unstable(): that was precisely to avoid the
possiblity of calling pte_offset_map() on a racily removed or inserted
THP entry, but such cases are now safely handled inside it. Likewise
there is no need to check pmd_none() or pmd_bad() before calling it.
Signed-off-by: Hugh Dickins <hughd@google.com>
Reviewed-by: SeongJae Park <sj@kernel.org> for mm/damon part
---
fs/proc/task_mmu.c | 32 ++++++++++++++++----------------
mm/damon/vaddr.c | 12 ++++++++----
mm/mempolicy.c | 7 ++++---
mm/mincore.c | 9 ++++-----
mm/mlock.c | 4 ++++
5 files changed, 36 insertions(+), 28 deletions(-)
diff --git a/fs/proc/task_mmu.c b/fs/proc/task_mmu.c
index 420510f6a545..dba5052ce09b 100644
--- a/fs/proc/task_mmu.c
+++ b/fs/proc/task_mmu.c
@@ -631,14 +631,11 @@ static int smaps_pte_range(pmd_t *pmd, unsigned long addr, unsigned long end,
goto out;
}
- if (pmd_trans_unstable(pmd))
- goto out;
- /*
- * The mmap_lock held all the way back in m_start() is what
- * keeps khugepaged out of here and from collapsing things
- * in here.
- */
pte = pte_offset_map_lock(vma->vm_mm, pmd, addr, &ptl);
+ if (!pte) {
+ walk->action = ACTION_AGAIN;
+ return 0;
+ }
for (; addr != end; pte++, addr += PAGE_SIZE)
smaps_pte_entry(pte, addr, walk);
pte_unmap_unlock(pte - 1, ptl);
@@ -1191,10 +1188,11 @@ static int clear_refs_pte_range(pmd_t *pmd, unsigned long addr,
return 0;
}
- if (pmd_trans_unstable(pmd))
- return 0;
-
pte = pte_offset_map_lock(vma->vm_mm, pmd, addr, &ptl);
+ if (!pte) {
+ walk->action = ACTION_AGAIN;
+ return 0;
+ }
for (; addr != end; pte++, addr += PAGE_SIZE) {
ptent = *pte;
@@ -1538,9 +1536,6 @@ static int pagemap_pmd_range(pmd_t *pmdp, unsigned long addr, unsigned long end,
spin_unlock(ptl);
return err;
}
-
- if (pmd_trans_unstable(pmdp))
- return 0;
#endif /* CONFIG_TRANSPARENT_HUGEPAGE */
/*
@@ -1548,6 +1543,10 @@ static int pagemap_pmd_range(pmd_t *pmdp, unsigned long addr, unsigned long end,
* goes beyond vma->vm_end.
*/
orig_pte = pte = pte_offset_map_lock(walk->mm, pmdp, addr, &ptl);
+ if (!pte) {
+ walk->action = ACTION_AGAIN;
+ return err;
+ }
for (; addr < end; pte++, addr += PAGE_SIZE) {
pagemap_entry_t pme;
@@ -1887,11 +1886,12 @@ static int gather_pte_stats(pmd_t *pmd, unsigned long addr,
spin_unlock(ptl);
return 0;
}
-
- if (pmd_trans_unstable(pmd))
- return 0;
#endif
orig_pte = pte = pte_offset_map_lock(walk->mm, pmd, addr, &ptl);
+ if (!pte) {
+ walk->action = ACTION_AGAIN;
+ return 0;
+ }
do {
struct page *page = can_gather_numa_stats(*pte, vma, addr);
if (!page)
diff --git a/mm/damon/vaddr.c b/mm/damon/vaddr.c
index 1fec16d7263e..b8762ff15c3c 100644
--- a/mm/damon/vaddr.c
+++ b/mm/damon/vaddr.c
@@ -318,9 +318,11 @@ static int damon_mkold_pmd_entry(pmd_t *pmd, unsigned long addr,
spin_unlock(ptl);
}
- if (pmd_none(*pmd) || unlikely(pmd_bad(*pmd)))
- return 0;
pte = pte_offset_map_lock(walk->mm, pmd, addr, &ptl);
+ if (!pte) {
+ walk->action = ACTION_AGAIN;
+ return 0;
+ }
if (!pte_present(*pte))
goto out;
damon_ptep_mkold(pte, walk->mm, addr);
@@ -464,9 +466,11 @@ static int damon_young_pmd_entry(pmd_t *pmd, unsigned long addr,
regular_page:
#endif /* CONFIG_TRANSPARENT_HUGEPAGE */
- if (pmd_none(*pmd) || unlikely(pmd_bad(*pmd)))
- return -EINVAL;
pte = pte_offset_map_lock(walk->mm, pmd, addr, &ptl);
+ if (!pte) {
+ walk->action = ACTION_AGAIN;
+ return 0;
+ }
if (!pte_present(*pte))
goto out;
folio = damon_get_folio(pte_pfn(*pte));
diff --git a/mm/mempolicy.c b/mm/mempolicy.c
index 1756389a0609..4d0bcf6f0d52 100644
--- a/mm/mempolicy.c
+++ b/mm/mempolicy.c
@@ -514,10 +514,11 @@ static int queue_folios_pte_range(pmd_t *pmd, unsigned long addr,
if (ptl)
return queue_folios_pmd(pmd, ptl, addr, end, walk);
- if (pmd_trans_unstable(pmd))
- return 0;
-
mapped_pte = pte = pte_offset_map_lock(walk->mm, pmd, addr, &ptl);
+ if (!pte) {
+ walk->action = ACTION_AGAIN;
+ return 0;
+ }
for (; addr != end; pte++, addr += PAGE_SIZE) {
if (!pte_present(*pte))
continue;
diff --git a/mm/mincore.c b/mm/mincore.c
index 2d5be013a25a..f33f6a0b1ded 100644
--- a/mm/mincore.c
+++ b/mm/mincore.c
@@ -113,12 +113,11 @@ static int mincore_pte_range(pmd_t *pmd, unsigned long addr, unsigned long end,
goto out;
}
- if (pmd_trans_unstable(pmd)) {
- __mincore_unmapped_range(addr, end, vma, vec);
- goto out;
- }
-
ptep = pte_offset_map_lock(walk->mm, pmd, addr, &ptl);
+ if (!ptep) {
+ walk->action = ACTION_AGAIN;
+ return 0;
+ }
for (; addr != end; ptep++, addr += PAGE_SIZE) {
pte_t pte = *ptep;
diff --git a/mm/mlock.c b/mm/mlock.c
index 40b43f8740df..9f2b1173b1b1 100644
--- a/mm/mlock.c
+++ b/mm/mlock.c
@@ -329,6 +329,10 @@ static int mlock_pte_range(pmd_t *pmd, unsigned long addr,
}
start_pte = pte_offset_map_lock(vma->vm_mm, pmd, addr, &ptl);
+ if (!start_pte) {
+ walk->action = ACTION_AGAIN;
+ return 0;
+ }
for (pte = start_pte; addr != end; pte++, addr += PAGE_SIZE) {
if (!pte_present(*pte))
continue;
--
2.35.3
next prev parent reply other threads:[~2023-06-09 1:17 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 ` [PATCH v2 01/32] mm: use pmdp_get_lockless() without surplus barrier() Hugh Dickins
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 ` Hugh Dickins [this message]
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=c77d9d10-3aad-e3ce-4896-99e91c7947f3@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).