mm: shmem: improve the tmpfs large folio read performance

tmpfs already supports PMD-sized large folios, but the tmpfs read
operation still performs copying at PAGE_SIZE granularity, which is
unreasonable.  This patch changes tmpfs to copy data at folio granularity,
which can improve the read performance, as well as changing to use folio
related functions.

Moreover, if a large folio has a subpage that is hwpoisoned, it will
still fall back to page granularity copying.

Use 'fio bs=64k' to read a 1G tmpfs file populated with 2M THPs, and I can
see about 20% performance improvement, and no regression with bs=4k.
Before the patch:
READ: bw=10.0GiB/s

After the patch:
READ: bw=12.0GiB/s

Link: https://lkml.kernel.org/r/2129a21a5b9f77d3bb7ddec152c009ce7c5653c4.1729218573.git.baolin.wang@linux.alibaba.com
Signed-off-by: Baolin Wang <baolin.wang@linux.alibaba.com>
Reviewed-by: Yang Shi <shy828301@gmail.com>
Cc: David Hildenbrand <david@redhat.com>
Cc: Hugh Dickins <hughd@google.com>
Cc: Kefeng Wang <wangkefeng.wang@huawei.com>
Cc: Matthew Wilcox <willy@infradead.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>

diff --git a/mm/shmem.c b/mm/shmem.c
index 26aaddc52fd1da4b834f13d9f0c245ba887663f2..06da05f984dabb225f2645534f1f026ce833f377 100644 (file)
--- a/mm/shmem.c
+++ b/mm/shmem.c
@@ -3094,13 +3094,13 @@ static ssize_t shmem_file_read_iter(struct kiocb *iocb, struct iov_iter *to)
        int error = 0;
        ssize_t retval = 0;
 
-       offset = iocb->ki_pos & ~PAGE_MASK;
-
        for (;;) {
                struct folio *folio = NULL;
                struct page *page = NULL;
                unsigned long nr, ret;
                loff_t end_offset, i_size = i_size_read(inode);
+               bool fallback_page_copy = false;
+               size_t fsize;
 
                if (unlikely(iocb->ki_pos >= i_size))
                        break;
@@ -3121,6 +3121,10 @@ static ssize_t shmem_file_read_iter(struct kiocb *iocb, struct iov_iter *to)
                                error = -EIO;
                                break;
                        }
+
+                       if (folio_test_large(folio) &&
+                           folio_test_has_hwpoisoned(folio))
+                               fallback_page_copy = true;
                }
 
                /*
@@ -3134,7 +3138,12 @@ static ssize_t shmem_file_read_iter(struct kiocb *iocb, struct iov_iter *to)
                        break;
                }
                end_offset = min_t(loff_t, i_size, iocb->ki_pos + to->count);
-               nr = min_t(loff_t, end_offset - iocb->ki_pos, PAGE_SIZE - offset);
+               if (folio && likely(!fallback_page_copy))
+                       fsize = folio_size(folio);
+               else
+                       fsize = PAGE_SIZE;
+               offset = iocb->ki_pos & (fsize - 1);
+               nr = min_t(loff_t, end_offset - iocb->ki_pos, fsize - offset);
 
                if (folio) {
                        /*
@@ -3142,10 +3151,15 @@ static ssize_t shmem_file_read_iter(struct kiocb *iocb, struct iov_iter *to)
                         * virtual addresses, take care about potential aliasing
                         * before reading the page on the kernel side.
                         */
-                       if (mapping_writably_mapped(mapping))
-                               flush_dcache_page(page);
+                       if (mapping_writably_mapped(mapping)) {
+                               if (likely(!fallback_page_copy))
+                                       flush_dcache_folio(folio);
+                               else
+                                       flush_dcache_page(page);
+                       }
+
                        /*
-                        * Mark the page accessed if we read the beginning.
+                        * Mark the folio accessed if we read the beginning.
                         */
                        if (!offset)
                                folio_mark_accessed(folio);
@@ -3153,9 +3167,11 @@ static ssize_t shmem_file_read_iter(struct kiocb *iocb, struct iov_iter *to)
                         * Ok, we have the page, and it's up-to-date, so
                         * now we can copy it to user space...
                         */
-                       ret = copy_page_to_iter(page, offset, nr, to);
+                       if (likely(!fallback_page_copy))
+                               ret = copy_folio_to_iter(folio, offset, nr, to);
+                       else
+                               ret = copy_page_to_iter(page, offset, nr, to);
                        folio_put(folio);
-
                } else if (user_backed_iter(to)) {
                        /*
                         * Copy to user tends to be so well optimized, but
@@ -3173,8 +3189,6 @@ static ssize_t shmem_file_read_iter(struct kiocb *iocb, struct iov_iter *to)
                }
 
                retval += ret;
-               offset += ret;
-               offset &= ~PAGE_MASK;
                iocb->ki_pos += ret;
 
                if (!iov_iter_count(to))