mm/filemap: remove hugetlb special casing in filemap.c

Remove special cased hugetlb handling code within the page cache by
changing the granularity of ->index to the base page size rather than the
huge page size.  The motivation of this patch is to reduce complexity
within the filemap code while also increasing performance by removing
branches that are evaluated on every page cache lookup.

To support the change in index, new wrappers for hugetlb page cache
interactions are added.  These wrappers perform the conversion to a linear
index which is now expected by the page cache for huge pages.

========================= PERFORMANCE ======================================

Perf was used to check the performance differences after the patch. 
Overall the performance is similar to mainline with a very small larger
overhead that occurs in __filemap_add_folio() and
hugetlb_add_to_page_cache().  This is because of the larger overhead that
occurs in xa_load() and xa_store() as the xarray is now using more entries
to store hugetlb folios in the page cache.

Timing

aarch64
    2MB Page Size
        6.5-rc3 + this patch:
            [root@sidhakum-ol9-1 hugepages]# time fallocate -l 700GB test.txt
            real    1m49.568s
            user    0m0.000s
            sys     1m49.461s

        6.5-rc3:
            [root]# time fallocate -l 700GB test.txt
            real    1m47.495s
            user    0m0.000s
            sys     1m47.370s
    1GB Page Size
        6.5-rc3 + this patch:
            [root@sidhakum-ol9-1 hugepages1G]# time fallocate -l 700GB test.txt
            real    1m47.024s
            user    0m0.000s
            sys     1m46.921s

        6.5-rc3:
            [root@sidhakum-ol9-1 hugepages1G]# time fallocate -l 700GB test.txt
            real    1m44.551s
            user    0m0.000s
            sys     1m44.438s

x86
    2MB Page Size
        6.5-rc3 + this patch:
            [root@sidhakum-ol9-2 hugepages]# time fallocate -l 100GB test.txt
            real    0m22.383s
            user    0m0.000s
            sys     0m22.255s

        6.5-rc3:
            [opc@sidhakum-ol9-2 hugepages]$ time sudo fallocate -l 100GB /dev/hugepages/test.txt
            real    0m22.735s
            user    0m0.038s
            sys     0m22.567s

    1GB Page Size
        6.5-rc3 + this patch:
            [root@sidhakum-ol9-2 hugepages1GB]# time fallocate -l 100GB test.txt
            real    0m25.786s
            user    0m0.001s
            sys     0m25.589s

        6.5-rc3:
            [root@sidhakum-ol9-2 hugepages1G]# time fallocate -l 100GB test.txt
            real    0m33.454s
            user    0m0.001s
            sys     0m33.193s

aarch64:
    workload - fallocate a 700GB file backed by huge pages

    6.5-rc3 + this patch:
        2MB Page Size:
            --100.00%--__arm64_sys_fallocate
                          ksys_fallocate
                          vfs_fallocate
                          hugetlbfs_fallocate
                          |
                          |--95.04%--__pi_clear_page
                          |
                          |--3.57%--clear_huge_page
                          |          |
                          |          |--2.63%--rcu_all_qs
                          |          |
                          |           --0.91%--__cond_resched
                          |
                           --0.67%--__cond_resched
            0.17%     0.00%             0  fallocate  [kernel.vmlinux]       [k] hugetlb_add_to_page_cache
            0.14%     0.10%            11  fallocate  [kernel.vmlinux]       [k] __filemap_add_folio

    6.5-rc3
        2MB Page Size:
                --100.00%--__arm64_sys_fallocate
                          ksys_fallocate
                          vfs_fallocate
                          hugetlbfs_fallocate
                          |
                          |--94.91%--__pi_clear_page
                          |
                          |--4.11%--clear_huge_page
                          |          |
                          |          |--3.00%--rcu_all_qs
                          |          |
                          |           --1.10%--__cond_resched
                          |
                           --0.59%--__cond_resched
            0.08%     0.01%             1  fallocate  [kernel.kallsyms]  [k] hugetlb_add_to_page_cache
            0.05%     0.03%             3  fallocate  [kernel.kallsyms]  [k] __filemap_add_folio

x86
    workload - fallocate a 100GB file backed by huge pages

    6.5-rc3 + this patch:
        2MB Page Size:
            hugetlbfs_fallocate
            |
            --99.57%--clear_huge_page
                |
                --98.47%--clear_page_erms
                    |
                    --0.53%--asm_sysvec_apic_timer_interrupt

            0.04%     0.04%             1  fallocate  [kernel.kallsyms]     [k] xa_load
            0.04%     0.00%             0  fallocate  [kernel.kallsyms]     [k] hugetlb_add_to_page_cache
            0.04%     0.00%             0  fallocate  [kernel.kallsyms]     [k] __filemap_add_folio
            0.04%     0.00%             0  fallocate  [kernel.kallsyms]     [k] xas_store

    6.5-rc3
        2MB Page Size:
                --99.93%--__x64_sys_fallocate
                          vfs_fallocate
                          hugetlbfs_fallocate
                          |
                           --99.38%--clear_huge_page
                                     |
                                     |--98.40%--clear_page_erms
                                     |
                                      --0.59%--__cond_resched
            0.03%     0.03%             1  fallocate  [kernel.kallsyms]  [k] __filemap_add_folio

========================= TESTING ======================================

This patch passes libhugetlbfs tests and LTP hugetlb tests

********** TEST SUMMARY
*                      2M
*                      32-bit 64-bit
*     Total testcases:   110    113
*             Skipped:     0      0
*                PASS:   107    113
*                FAIL:     0      0
*    Killed by signal:     3      0
*   Bad configuration:     0      0
*       Expected FAIL:     0      0
*     Unexpected PASS:     0      0
*    Test not present:     0      0
* Strange test result:     0      0
**********

    Done executing testcases.
    LTP Version:  20220527-178-g2761a81c4

page migration was also tested using Mike Kravetz's test program.[8]

[dan.carpenter@linaro.org: fix an NULL vs IS_ERR() bug]
  Link: https://lkml.kernel.org/r/1772c296-1417-486f-8eef-171af2192681@moroto.mountain
Link: https://lkml.kernel.org/r/20230926192017.98183-1-sidhartha.kumar@oracle.com
Signed-off-by: Sidhartha Kumar <sidhartha.kumar@oracle.com>
Signed-off-by: Dan Carpenter <dan.carpenter@linaro.org>
Reported-and-tested-by: syzbot+c225dea486da4d5592bd@syzkaller.appspotmail.com
Closes: https://syzkaller.appspot.com/bug?extid=c225dea486da4d5592bd
Cc: Matthew Wilcox (Oracle) <willy@infradead.org>
Cc: Mike Kravetz <mike.kravetz@oracle.com>
Cc: Muchun Song <songmuchun@bytedance.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>

1 files changed, 19 insertions, 18 deletions

diff --git a/fs/hugetlbfs/inode.c b/fs/hugetlbfs/inode.c
index 60fce26ff937..926d01c493fb 100644
--- a/fs/hugetlbfs/inode.c
+++ b/fs/hugetlbfs/inode.c
@@ -334,7 +334,7 @@ static ssize_t hugetlbfs_read_iter(struct kiocb *iocb, struct iov_iter *to)
 	ssize_t retval = 0;
 
 	while (iov_iter_count(to)) {
-		struct page *page;
+		struct folio *folio;
 		size_t nr, copied, want;
 
 		/* nr is the maximum number of bytes to copy from this page */
@@ -352,18 +352,18 @@ static ssize_t hugetlbfs_read_iter(struct kiocb *iocb, struct iov_iter *to)
 		}
 		nr = nr - offset;
 
-		/* Find the page */
-		page = find_lock_page(mapping, index);
-		if (unlikely(page == NULL)) {
+		/* Find the folio */
+		folio = filemap_lock_hugetlb_folio(h, mapping, index);
+		if (IS_ERR(folio)) {
 			/*
 			 * We have a HOLE, zero out the user-buffer for the
 			 * length of the hole or request.
 			 */
 			copied = iov_iter_zero(nr, to);
 		} else {
-			unlock_page(page);
+			folio_unlock(folio);
 
-			if (!PageHWPoison(page))
+			if (!folio_test_has_hwpoisoned(folio))
 				want = nr;
 			else {
 				/*
@@ -371,19 +371,19 @@ static ssize_t hugetlbfs_read_iter(struct kiocb *iocb, struct iov_iter *to)
 				 * touching the 1st raw HWPOISON subpage after
 				 * offset.
 				 */
-				want = adjust_range_hwpoison(page, offset, nr);
+				want = adjust_range_hwpoison(&folio->page, offset, nr);
 				if (want == 0) {
-					put_page(page);
+					folio_put(folio);
 					retval = -EIO;
 					break;
 				}
 			}
 
 			/*
-			 * We have the page, copy it to user space buffer.
+			 * We have the folio, copy it to user space buffer.
 			 */
-			copied = copy_page_to_iter(page, offset, want, to);
-			put_page(page);
+			copied = copy_folio_to_iter(folio, offset, want, to);
+			folio_put(folio);
 		}
 		offset += copied;
 		retval += copied;
@@ -661,21 +661,20 @@ static void remove_inode_hugepages(struct inode *inode, loff_t lstart,
 {
 	struct hstate *h = hstate_inode(inode);
 	struct address_space *mapping = &inode->i_data;
-	const pgoff_t start = lstart >> huge_page_shift(h);
-	const pgoff_t end = lend >> huge_page_shift(h);
+	const pgoff_t end = lend >> PAGE_SHIFT;
 	struct folio_batch fbatch;
 	pgoff_t next, index;
 	int i, freed = 0;
 	bool truncate_op = (lend == LLONG_MAX);
 
 	folio_batch_init(&fbatch);
-	next = start;
+	next = lstart >> PAGE_SHIFT;
 	while (filemap_get_folios(mapping, &next, end - 1, &fbatch)) {
 		for (i = 0; i < folio_batch_count(&fbatch); ++i) {
 			struct folio *folio = fbatch.folios[i];
 			u32 hash = 0;
 
-			index = folio->index;
+			index = folio->index >> huge_page_order(h);
 			hash = hugetlb_fault_mutex_hash(mapping, index);
 			mutex_lock(&hugetlb_fault_mutex_table[hash]);
 
@@ -693,7 +692,9 @@ static void remove_inode_hugepages(struct inode *inode, loff_t lstart,
 	}
 
 	if (truncate_op)
-		(void)hugetlb_unreserve_pages(inode, start, LONG_MAX, freed);
+		(void)hugetlb_unreserve_pages(inode,
+				lstart >> huge_page_shift(h),
+				LONG_MAX, freed);
 }
 
 static void hugetlbfs_evict_inode(struct inode *inode)
@@ -741,7 +742,7 @@ static void hugetlbfs_zero_partial_page(struct hstate *h,
 	pgoff_t idx = start >> huge_page_shift(h);
 	struct folio *folio;
 
-	folio = filemap_lock_folio(mapping, idx);
+	folio = filemap_lock_hugetlb_folio(h, mapping, idx);
 	if (IS_ERR(folio))
 		return;
 
@@ -886,7 +887,7 @@ static long hugetlbfs_fallocate(struct file *file, int mode, loff_t offset,
 		mutex_lock(&hugetlb_fault_mutex_table[hash]);
 
 		/* See if already present in mapping to avoid alloc/free */
-		folio = filemap_get_folio(mapping, index);
+		folio = filemap_get_folio(mapping, index << huge_page_order(h));
 		if (!IS_ERR(folio)) {
 			folio_put(folio);
 			mutex_unlock(&hugetlb_fault_mutex_table[hash]);