nagai/kernel
3
0
Fork 0
forked from mirrors/linux
Code Pull requests Activity

swap: remove remnants of polling from read_swap_cache_async

Browse source 
Patch series "Per-VMA lock support for swap and userfaults", v7.

When per-VMA locks were introduced in [1] several types of page faults
would still fall back to mmap_lock to keep the patchset simple.  Among
them are swap and userfault pages.  The main reason for skipping those
cases was the fact that mmap_lock could be dropped while handling these
faults and that required additional logic to be implemented.  Implement
the mechanism to allow per-VMA locks to be dropped for these cases.

First, change handle_mm_fault to drop per-VMA locks when returning
VM_FAULT_RETRY or VM_FAULT_COMPLETED to be consistent with the way
mmap_lock is handled.  Then change folio_lock_or_retry to accept vm_fault
and return vm_fault_t which simplifies later patches.  Finally allow swap
and uffd page faults to be handled under per-VMA locks by dropping per-VMA
and retrying, the same way it's done under mmap_lock.  Naturally, once VMA
lock is dropped that VMA should be assumed unstable and can't be used.


This patch (of 6):

Commit [1] introduced IO polling support duding swapin to reduce swap read
latency for block devices that can be polled.  However later commit [2]
removed polling support.  Therefore it seems safe to remove do_poll
parameter in read_swap_cache_async and always call swap_readpage with
synchronous=false waiting for IO completion in folio_lock_or_retry.

[1] commit 23955622ff ("swap: add block io poll in swapin path")
[2] commit 9650b453a3 ("block: ignore RWF_HIPRI hint for sync dio")

Link: https://lkml.kernel.org/r/20230630211957.1341547-1-surenb@google.com
Link: https://lkml.kernel.org/r/20230630211957.1341547-2-surenb@google.com
Signed-off-by: Suren Baghdasaryan <surenb@google.com>
Suggested-by: "Huang, Ying" <ying.huang@intel.com>
Reviewed-by: "Huang, Ying" <ying.huang@intel.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Cc: Alistair Popple <apopple@nvidia.com>
Cc: Al Viro <viro@zeniv.linux.org.uk>
Cc: Christian Brauner <brauner@kernel.org>
Cc: David Hildenbrand <david@redhat.com>
Cc: David Howells <dhowells@redhat.com>
Cc: Davidlohr Bueso <dave@stgolabs.net>
Cc: Hillf Danton <hdanton@sina.com>
Cc: Hugh Dickins <hughd@google.com>
Cc: Jan Kara <jack@suse.cz>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: Josef Bacik <josef@toxicpanda.com>
Cc: Laurent Dufour <ldufour@linux.ibm.com>
Cc: Liam R. Howlett <Liam.Howlett@oracle.com>
Cc: Lorenzo Stoakes <lstoakes@gmail.com>
Cc: Matthew Wilcox <willy@infradead.org>
Cc: Michal Hocko <mhocko@suse.com>
Cc: Michel Lespinasse <michel@lespinasse.org>
Cc: Minchan Kim <minchan@google.com>
Cc: Pavel Tatashin <pasha.tatashin@soleen.com>
Cc: Peter Xu <peterx@redhat.com>
Cc: Punit Agrawal <punit.agrawal@bytedance.com>
Cc: Vlastimil Babka <vbabka@suse.cz>
Cc: Yu Zhao <yuzhao@google.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
This commit is contained in:
Suren Baghdasaryan 2023-06-30 14:19:52 -07:00 committed by Andrew Morton
parent d51b68469b
commit b243dcbf2f
3 changed files with 7 additions and 10 deletions
repo.diff.show_diff_stats Download patch file Download diff file Expand all files Collapse all files

4
mm/madvise.c
View file

@ -217,7 +217,7 @@ static int swapin_walk_pmd_entry(pmd_t *pmd, unsigned long start,
ptep = NULL; ptep = NULL;
page = read_swap_cache_async(entry, GFP_HIGHUSER_MOVABLE, page = read_swap_cache_async(entry, GFP_HIGHUSER_MOVABLE,
vma, addr, false, &splug); vma, addr, &splug);
if (page) if (page)
put_page(page); put_page(page);
} }
@ -262,7 +262,7 @@ static void shmem_swapin_range(struct vm_area_struct *vma,
rcu_read_unlock(); rcu_read_unlock();
page = read_swap_cache_async(entry, mapping_gfp_mask(mapping), page = read_swap_cache_async(entry, mapping_gfp_mask(mapping),
vma, addr, false, &splug); vma, addr, &splug);
if (page) if (page)
put_page(page); put_page(page);

1
mm/swap.h
View file

@ -46,7 +46,6 @@ struct folio *filemap_get_incore_folio(struct address_space *mapping,
struct page *read_swap_cache_async(swp_entry_t entry, gfp_t gfp_mask, struct page *read_swap_cache_async(swp_entry_t entry, gfp_t gfp_mask,
struct vm_area_struct *vma, struct vm_area_struct *vma,
unsigned long addr, unsigned long addr,
bool do_poll,
struct swap_iocb **plug); struct swap_iocb **plug);
struct page *__read_swap_cache_async(swp_entry_t entry, gfp_t gfp_mask, struct page *__read_swap_cache_async(swp_entry_t entry, gfp_t gfp_mask,
struct vm_area_struct *vma, struct vm_area_struct *vma,

12
mm/swap_state.c
View file

@ -526,15 +526,14 @@ struct page *__read_swap_cache_async(swp_entry_t entry, gfp_t gfp_mask,
*/ */
struct page *read_swap_cache_async(swp_entry_t entry, gfp_t gfp_mask, struct page *read_swap_cache_async(swp_entry_t entry, gfp_t gfp_mask,
struct vm_area_struct *vma, struct vm_area_struct *vma,
unsigned long addr, bool do_poll, unsigned long addr, struct swap_iocb **plug)
struct swap_iocb **plug)
{ {
bool page_was_allocated; bool page_was_allocated;
struct page *retpage = __read_swap_cache_async(entry, gfp_mask, struct page *retpage = __read_swap_cache_async(entry, gfp_mask,
vma, addr, &page_was_allocated); vma, addr, &page_was_allocated);
if (page_was_allocated) if (page_was_allocated)
swap_readpage(retpage, do_poll, plug); swap_readpage(retpage, false, plug);
return retpage; return retpage;
} }
@ -629,7 +628,7 @@ struct page *swap_cluster_readahead(swp_entry_t entry, gfp_t gfp_mask,
struct swap_info_struct *si = swp_swap_info(entry); struct swap_info_struct *si = swp_swap_info(entry);
struct blk_plug plug; struct blk_plug plug;
struct swap_iocb *splug = NULL; struct swap_iocb *splug = NULL;
bool do_poll = true, page_allocated; bool page_allocated;
struct vm_area_struct *vma = vmf->vma; struct vm_area_struct *vma = vmf->vma;
unsigned long addr = vmf->address; unsigned long addr = vmf->address;
@ -637,7 +636,6 @@ struct page *swap_cluster_readahead(swp_entry_t entry, gfp_t gfp_mask,
if (!mask) if (!mask)
goto skip; goto skip;
do_poll = false;
/* Read a page_cluster sized and aligned cluster around offset. */ /* Read a page_cluster sized and aligned cluster around offset. */
start_offset = offset & ~mask; start_offset = offset & ~mask;
end_offset = offset | mask; end_offset = offset | mask;
@ -669,7 +667,7 @@ struct page *swap_cluster_readahead(swp_entry_t entry, gfp_t gfp_mask,
lru_add_drain(); /* Push any new pages onto the LRU now */ lru_add_drain(); /* Push any new pages onto the LRU now */
skip: skip:
/* The page was likely read above, so no need for plugging here */ /* The page was likely read above, so no need for plugging here */
return read_swap_cache_async(entry, gfp_mask, vma, addr, do_poll, NULL); return read_swap_cache_async(entry, gfp_mask, vma, addr, NULL);
} }
int init_swap_address_space(unsigned int type, unsigned long nr_pages) int init_swap_address_space(unsigned int type, unsigned long nr_pages)
@ -837,7 +835,7 @@ static struct page *swap_vma_readahead(swp_entry_t fentry, gfp_t gfp_mask,
skip: skip:
/* The page was likely read above, so no need for plugging here */ /* The page was likely read above, so no need for plugging here */
return read_swap_cache_async(fentry, gfp_mask, vma, vmf->address, return read_swap_cache_async(fentry, gfp_mask, vma, vmf->address,
ra_info.win == 1, NULL); NULL);
} }
/** /**