diff options
author | 2023-09-26 12:20:17 -0700 | |
---|---|---|
committer | 2023-10-16 15:44:38 -0700 | |
commit | a08c7193e4f18dc8508f2d07d0de2c5b94cb39a3 (patch) | |
tree | 1dd25134be4b0c4457a0601c66166d55652ad066 /mm/hugetlb.c | |
parent | mm/ksm: test case for prctl fork/exec workflow (diff) | |
download | linux-a08c7193e4f18dc8508f2d07d0de2c5b94cb39a3.tar.gz linux-a08c7193e4f18dc8508f2d07d0de2c5b94cb39a3.tar.bz2 linux-a08c7193e4f18dc8508f2d07d0de2c5b94cb39a3.zip |
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>
Diffstat (limited to 'mm/hugetlb.c')
-rw-r--r-- | mm/hugetlb.c | 32 |
1 files changed, 6 insertions, 26 deletions
diff --git a/mm/hugetlb.c b/mm/hugetlb.c index de220e3ff8be..0aaf28ce32e5 100644 --- a/mm/hugetlb.c +++ b/mm/hugetlb.c @@ -952,7 +952,7 @@ static long region_count(struct resv_map *resv, long f, long t) /* * Convert the address within this vma to the page offset within - * the mapping, in pagecache page units; huge pages here. + * the mapping, huge page units here. */ static pgoff_t vma_hugecache_offset(struct hstate *h, struct vm_area_struct *vma, unsigned long address) @@ -961,13 +961,6 @@ static pgoff_t vma_hugecache_offset(struct hstate *h, (vma->vm_pgoff >> huge_page_order(h)); } -pgoff_t linear_hugepage_index(struct vm_area_struct *vma, - unsigned long address) -{ - return vma_hugecache_offset(hstate_vma(vma), vma, address); -} -EXPORT_SYMBOL_GPL(linear_hugepage_index); - /** * vma_kernel_pagesize - Page size granularity for this VMA. * @vma: The user mapping. @@ -2074,20 +2067,6 @@ struct address_space *hugetlb_page_mapping_lock_write(struct page *hpage) return NULL; } -pgoff_t hugetlb_basepage_index(struct page *page) -{ - struct page *page_head = compound_head(page); - pgoff_t index = page_index(page_head); - unsigned long compound_idx; - - if (compound_order(page_head) > MAX_ORDER) - compound_idx = page_to_pfn(page) - page_to_pfn(page_head); - else - compound_idx = page - page_head; - - return (index << compound_order(page_head)) + compound_idx; -} - static struct folio *alloc_buddy_hugetlb_folio(struct hstate *h, gfp_t gfp_mask, int nid, nodemask_t *nmask, nodemask_t *node_alloc_noretry) @@ -5772,7 +5751,7 @@ static bool hugetlbfs_pagecache_present(struct hstate *h, struct vm_area_struct *vma, unsigned long address) { struct address_space *mapping = vma->vm_file->f_mapping; - pgoff_t idx = vma_hugecache_offset(h, vma, address); + pgoff_t idx = linear_page_index(vma, address); struct folio *folio; folio = filemap_get_folio(mapping, idx); @@ -5789,6 +5768,7 @@ int hugetlb_add_to_page_cache(struct folio *folio, struct address_space *mapping struct hstate *h = hstate_inode(inode); int err; + idx <<= huge_page_order(h); __folio_set_locked(folio); err = __filemap_add_folio(mapping, folio, idx, GFP_KERNEL, NULL); @@ -5896,7 +5876,7 @@ static vm_fault_t hugetlb_no_page(struct mm_struct *mm, * before we get page_table_lock. */ new_folio = false; - folio = filemap_lock_folio(mapping, idx); + folio = filemap_lock_hugetlb_folio(h, mapping, idx); if (IS_ERR(folio)) { size = i_size_read(mapping->host) >> huge_page_shift(h); if (idx >= size) @@ -6205,7 +6185,7 @@ vm_fault_t hugetlb_fault(struct mm_struct *mm, struct vm_area_struct *vma, /* Just decrements count, does not deallocate */ vma_end_reservation(h, vma, haddr); - pagecache_folio = filemap_lock_folio(mapping, idx); + pagecache_folio = filemap_lock_hugetlb_folio(h, mapping, idx); if (IS_ERR(pagecache_folio)) pagecache_folio = NULL; } @@ -6338,7 +6318,7 @@ int hugetlb_mfill_atomic_pte(pte_t *dst_pte, if (is_continue) { ret = -EFAULT; - folio = filemap_lock_folio(mapping, idx); + folio = filemap_lock_hugetlb_folio(h, mapping, idx); if (IS_ERR(folio)) goto out; folio_in_pagecache = true; |