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 31/32] mm/swap: swap_vma_readahead() do the pte_offset_map()
Date: Thu, 8 Jun 2023 18:52:17 -0700 (PDT) [thread overview]
Message-ID: <b7c64ab3-9e44-aac0-d2b-c57de578af1c@google.com> (raw)
In-Reply-To: <c1c9a74a-bc5b-15ea-e5d2-8ec34bc921d@google.com>
swap_vma_readahead() has been proceeding in an unconventional way, its
preliminary swap_ra_info() doing the pte_offset_map() and pte_unmap(),
then relying on that pte pointer even after the pte_unmap() - in its
CONFIG_64BIT case (I think !CONFIG_HIGHPTE was intended; whereas 32-bit
copied ptes to stack while they were mapped, but had to limit how many).
Though it would be difficult to construct a failing testcase, accessing
page table after pte_unmap() will become bad practice, even on 64-bit:
an rcu_read_unlock() in pte_unmap() will allow page table to be freed.
Move relevant definitions from include/linux/swap.h to mm/swap_state.c,
nothing else used them. Delete the CONFIG_64BIT distinction and buffer,
delete all reference to ptes from swap_ra_info(), use pte_offset_map()
repeatedly in swap_vma_readahead(), breaking from the loop if it fails.
(Will the repeated "map" and "unmap" show up as a slowdown anywhere?
If so, maybe modify __read_swap_cache_async() to do the pte_unmap()
only when it does not find the page already in the swapcache.)
Use ptep_get_lockless(), mainly for its READ_ONCE(). Correctly advance
the address passed down to each call of __read__swap_cache_async().
Signed-off-by: Hugh Dickins <hughd@google.com>
---
include/linux/swap.h | 19 -------------------
mm/swap_state.c | 45 +++++++++++++++++++++++---------------------
2 files changed, 24 insertions(+), 40 deletions(-)
diff --git a/include/linux/swap.h b/include/linux/swap.h
index 3c69cb653cb9..1b9f2d92fc10 100644
--- a/include/linux/swap.h
+++ b/include/linux/swap.h
@@ -337,25 +337,6 @@ struct swap_info_struct {
*/
};
-#ifdef CONFIG_64BIT
-#define SWAP_RA_ORDER_CEILING 5
-#else
-/* Avoid stack overflow, because we need to save part of page table */
-#define SWAP_RA_ORDER_CEILING 3
-#define SWAP_RA_PTE_CACHE_SIZE (1 << SWAP_RA_ORDER_CEILING)
-#endif
-
-struct vma_swap_readahead {
- unsigned short win;
- unsigned short offset;
- unsigned short nr_pte;
-#ifdef CONFIG_64BIT
- pte_t *ptes;
-#else
- pte_t ptes[SWAP_RA_PTE_CACHE_SIZE];
-#endif
-};
-
static inline swp_entry_t folio_swap_entry(struct folio *folio)
{
swp_entry_t entry = { .val = page_private(&folio->page) };
diff --git a/mm/swap_state.c b/mm/swap_state.c
index b76a65ac28b3..a43b41975da2 100644
--- a/mm/swap_state.c
+++ b/mm/swap_state.c
@@ -698,6 +698,14 @@ void exit_swap_address_space(unsigned int type)
swapper_spaces[type] = NULL;
}
+#define SWAP_RA_ORDER_CEILING 5
+
+struct vma_swap_readahead {
+ unsigned short win;
+ unsigned short offset;
+ unsigned short nr_pte;
+};
+
static void swap_ra_info(struct vm_fault *vmf,
struct vma_swap_readahead *ra_info)
{
@@ -705,11 +713,7 @@ static void swap_ra_info(struct vm_fault *vmf,
unsigned long ra_val;
unsigned long faddr, pfn, fpfn, lpfn, rpfn;
unsigned long start, end;
- pte_t *pte, *orig_pte;
unsigned int max_win, hits, prev_win, win;
-#ifndef CONFIG_64BIT
- pte_t *tpte;
-#endif
max_win = 1 << min_t(unsigned int, READ_ONCE(page_cluster),
SWAP_RA_ORDER_CEILING);
@@ -728,12 +732,9 @@ static void swap_ra_info(struct vm_fault *vmf,
max_win, prev_win);
atomic_long_set(&vma->swap_readahead_info,
SWAP_RA_VAL(faddr, win, 0));
-
if (win == 1)
return;
- /* Copy the PTEs because the page table may be unmapped */
- orig_pte = pte = pte_offset_map(vmf->pmd, faddr);
if (fpfn == pfn + 1) {
lpfn = fpfn;
rpfn = fpfn + win;
@@ -753,15 +754,6 @@ static void swap_ra_info(struct vm_fault *vmf,
ra_info->nr_pte = end - start;
ra_info->offset = fpfn - start;
- pte -= ra_info->offset;
-#ifdef CONFIG_64BIT
- ra_info->ptes = pte;
-#else
- tpte = ra_info->ptes;
- for (pfn = start; pfn != end; pfn++)
- *tpte++ = *pte++;
-#endif
- pte_unmap(orig_pte);
}
/**
@@ -785,7 +777,8 @@ static struct page *swap_vma_readahead(swp_entry_t fentry, gfp_t gfp_mask,
struct swap_iocb *splug = NULL;
struct vm_area_struct *vma = vmf->vma;
struct page *page;
- pte_t *pte, pentry;
+ pte_t *pte = NULL, pentry;
+ unsigned long addr;
swp_entry_t entry;
unsigned int i;
bool page_allocated;
@@ -797,17 +790,25 @@ static struct page *swap_vma_readahead(swp_entry_t fentry, gfp_t gfp_mask,
if (ra_info.win == 1)
goto skip;
+ addr = vmf->address - (ra_info.offset * PAGE_SIZE);
+
blk_start_plug(&plug);
- for (i = 0, pte = ra_info.ptes; i < ra_info.nr_pte;
- i++, pte++) {
- pentry = *pte;
+ for (i = 0; i < ra_info.nr_pte; i++, addr += PAGE_SIZE) {
+ if (!pte++) {
+ pte = pte_offset_map(vmf->pmd, addr);
+ if (!pte)
+ break;
+ }
+ pentry = ptep_get_lockless(pte);
if (!is_swap_pte(pentry))
continue;
entry = pte_to_swp_entry(pentry);
if (unlikely(non_swap_entry(entry)))
continue;
+ pte_unmap(pte);
+ pte = NULL;
page = __read_swap_cache_async(entry, gfp_mask, vma,
- vmf->address, &page_allocated);
+ addr, &page_allocated);
if (!page)
continue;
if (page_allocated) {
@@ -819,6 +820,8 @@ static struct page *swap_vma_readahead(swp_entry_t fentry, gfp_t gfp_mask,
}
put_page(page);
}
+ if (pte)
+ pte_unmap(pte);
blk_finish_plug(&plug);
swap_read_unplug(splug);
lru_add_drain();
--
2.35.3
next prev parent reply other threads:[~2023-06-09 1:52 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 ` [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 ` Hugh Dickins [this message]
2023-06-12 8:03 ` [PATCH v2 31/32] mm/swap: swap_vma_readahead() do the pte_offset_map() 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=b7c64ab3-9e44-aac0-d2b-c57de578af1c@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 read-only IMAP folder(s) and NNTP newsgroup(s).