Remove READ_ONLY_THP_FOR_FS
Subsystems (8)
Zi Yan
reviewercover Remove READ_ONLY_THP_FOR_FS
Hi all,
After Willy's heads-up on the removal of CONFIG_READ_ONLY_THP_FOR_FS[1]. This patchset is an attempt of removing it.
The patchset does the removal in the following steps:
1. remove READ_ONLY_THP_FOR_FS Kconfig
2. remove collapse_file() code on READ_ONLY_THP_FOR_FS
3. remove filemap_nr_thps*() functions
4. remove file_thp_enabled()
5. remove related folio splittable checks
6. replace try_folio_split_to_order() with folio_split() in truncate_inode_partial_folio().
6. remove related fs code
7. clean up selftests code
It seems that NR_FILE_THPS is also used for fs with large folio support, so it is kept.
Let me know if I miss anything. Comments and suggestions are welcome.
Zi Yan (11):
mm: remove READ_ONLY_THP_FOR_FS Kconfig option mm/khugepaged: remove READ_ONLY_THP_FOR_FS code in collapse_file()
mm: remove filemap_nr_thps*() functions
mm/huge_memory: remove file_thp_enabled() and its caller. mm/huge_memory: remove folio split check for READ_ONLY_THP_FOR_FS mm/truncate: use folio_split() in truncate_inode_partial_folio()
fs: remove nr_thp from struct address_space
fs: remove READ_ONLY_THP_FOR_FS code
fs/btrfs: remove a comment referring to READ_ONLY_THP_FOR_FS selftests/mm: remove READ_ONLY_THP_FOR_FS test in khugepaged selftests/mm: remove READ_ONLY_THP_FOR_FS test in guard-regions
fs/btrfs/defrag.c | 3 - fs/inode.c | 3 - fs/open.c | 27 --- include/linux/fs.h | 5 - include/linux/huge_mm.h | 28 --- include/linux/pagemap.h | 29 --- mm/Kconfig | 11 -- mm/filemap.c | 1 - mm/huge_memory.c | 44 ----- mm/khugepaged.c | 159 ++++------------- mm/truncate.c | 8 +- tools/testing/selftests/mm/guard-regions.c | 148 +--------------- tools/testing/selftests/mm/khugepaged.c | 197 +-------------------- 13 files changed, 42 insertions(+), 621 deletions(-)
Signature · 1 line
2.43.0
Zi Yan
reviewerRFC PATCH 1/11 mm: remove READ_ONLY_THP_FOR_FS Kconfig option
No one will be able to use it, so the related code can be removed in the coming commits.
--- mm/Kconfig | 11 ----------- 1 file changed, 11 deletions(-)
mm/Kconfig +0 -11
@@ -937,17 +937,6 @@ config THP_SWAP For selection by architectures with reasonable THP sizes. -config READ_ONLY_THP_FOR_FS - bool "Read-only THP for filesystems (EXPERIMENTAL)" - depends on TRANSPARENT_HUGEPAGE - - help - Allow khugepaged to put read-only file-backed pages in THP. - - This is marked experimental because it is a new feature. Write - support of file THPs will be developed in the next few release - cycles. - config NO_PAGE_MAPCOUNT bool "No per-page mapcount (EXPERIMENTAL)" help
Signature · 1 line
2.43.0
Zi Yan
reviewerRFC PATCH 2/11 mm/khugepaged: remove READ_ONLY_THP_FOR_FS code in collapse_file()
In reply to Zi YanREAD_ONLY_THP_FOR_FS is no longer present, remove corresponding code.
--- mm/khugepaged.c | 159 +++++++++++------------------------------------- 1 file changed, 34 insertions(+), 125 deletions(-)
mm/khugepaged.c +34 -125
@@ -1899,7 +1899,7 @@ static enum scan_result collapse_file(struct mm_struct *mm, unsigned long addr,int nr_none =0 ;bool is_shmem =shmem_file (file); -VM_BUG_ON (!IS_ENABLED (CONFIG_READ_ONLY_THP_FOR_FS ) && !is_shmem); +VM_WARN_ON_ONCE (!is_shmem);VM_BUG_ON (start & (HPAGE_PMD_NR -1 )); result =alloc_charge_folio (&new_folio, mm, cc);
@@ -1909,8 +1909,7 @@ static enum scan_result collapse_file(struct mm_struct *mm, unsigned long addr,mapping_set_update (&xas, mapping);__folio_set_locked (new_folio); -if (is_shmem) -__folio_set_swapbacked (new_folio); +__folio_set_swapbacked (new_folio); new_folio->index = start; new_folio->mapping = mapping;
@@ -1935,83 +1934,39 @@ static enum scan_result collapse_file(struct mm_struct *mm, unsigned long addr, folio =xas_load (&xas);VM_BUG_ON (index != xas.xa_index); -if (is_shmem) { -if (!folio) { -/* -* Stop if extent has been truncated or -* hole-punched, and is now completely -* empty. -*/ -if (index == start) { -if (!xas_next_entry (&xas, end -1 )) { - result =SCAN_TRUNCATED ; - goto xa_locked; - } +if (!folio) { +/* +* Stop if extent has been truncated or +* hole-punched, and is now completely +* empty. +*/ +if (index == start) { +if (!xas_next_entry (&xas, end -1 )) { + result =SCAN_TRUNCATED ; + goto xa_locked; } - nr_none++; - index++; -continue ; } + nr_none++; + index++; +continue ; + } -if (xa_is_value (folio) || !folio_test_uptodate (folio)) { -xas_unlock_irq (&xas); -/* swap in or instantiate fallocated page */ -if (shmem_get_folio (mapping->host, index,0 , - &folio,SGP_NOALLOC )) { - result =SCAN_FAIL ; - goto xa_unlocked; - } -/* drain lru cache to help folio_isolate_lru() */ -lru_add_drain (); - }else if (folio_trylock (folio)) { -folio_get (folio); -xas_unlock_irq (&xas); - }else { - result =SCAN_PAGE_LOCK ; - goto xa_locked; - } - }else {/* !is_shmem */ -if (!folio ||xa_is_value (folio)) { -xas_unlock_irq (&xas); -page_cache_sync_readahead (mapping, &file->f_ra, - file, index, - end - index); -/* drain lru cache to help folio_isolate_lru() */ -lru_add_drain (); - folio =filemap_lock_folio (mapping, index); -if (IS_ERR (folio)) { - result =SCAN_FAIL ; - goto xa_unlocked; - } - }else if (folio_test_dirty (folio)) { -/* -* khugepaged only works on read-only fd, -* so this page is dirty because it hasn't -* been flushed since first write. There -* won't be new dirty pages. -* -* Trigger async flush here and hope the -* writeback is done when khugepaged -* revisits this page. -* -* This is a one-off situation. We are not -* forcing writeback in loop. -*/ -xas_unlock_irq (&xas); -filemap_flush (mapping); - result =SCAN_PAGE_DIRTY_OR_WRITEBACK ; - goto xa_unlocked; - }else if (folio_test_writeback (folio)) { -xas_unlock_irq (&xas); - result =SCAN_PAGE_DIRTY_OR_WRITEBACK ; +if (xa_is_value (folio) || !folio_test_uptodate (folio)) { +xas_unlock_irq (&xas); +/* swap in or instantiate fallocated page */ +if (shmem_get_folio (mapping->host, index,0 , + &folio,SGP_NOALLOC )) { + result =SCAN_FAIL ; goto xa_unlocked; - }else if (folio_trylock (folio)) { -folio_get (folio); -xas_unlock_irq (&xas); - }else { - result =SCAN_PAGE_LOCK ; - goto xa_locked; } +/* drain lru cache to help folio_isolate_lru() */ +lru_add_drain (); + }else if (folio_trylock (folio)) { +folio_get (folio); +xas_unlock_irq (&xas); + }else { + result =SCAN_PAGE_LOCK ; + goto xa_locked; }/*
@@ -2041,17 +1996,6 @@ static enum scan_result collapse_file(struct mm_struct *mm, unsigned long addr, goto out_unlock; } -if (!is_shmem && (folio_test_dirty (folio) || -folio_test_writeback (folio))) { -/* -* khugepaged only works on read-only fd, so this -* folio is dirty because it hasn't been flushed -* since first write. -*/ - result =SCAN_PAGE_DIRTY_OR_WRITEBACK ; - goto out_unlock; - } -if (!folio_isolate_lru (folio)) { result =SCAN_DEL_PAGE_LRU ; goto out_unlock;
@@ -2101,21 +2045,6 @@ static enum scan_result collapse_file(struct mm_struct *mm, unsigned long addr, goto xa_unlocked; } -if (!is_shmem) { -filemap_nr_thps_inc (mapping); -/* -* Paired with the fence in do_dentry_open() -> get_write_access() -* to ensure i_writecount is up to date and the update to nr_thps -* is visible. Ensures the page cache will be truncated if the -* file is opened writable. -*/ -smp_mb (); -if (inode_is_open_for_write (mapping->host)) { - result =SCAN_FAIL ; -filemap_nr_thps_dec (mapping); - } - } - xa_locked:xas_unlock_irq (&xas); xa_unlocked:
@@ -2224,12 +2153,8 @@ static enum scan_result collapse_file(struct mm_struct *mm, unsigned long addr,xas_lock_irq (&xas); } -if (is_shmem) { -lruvec_stat_mod_folio (new_folio,NR_SHMEM ,HPAGE_PMD_NR ); -lruvec_stat_mod_folio (new_folio,NR_SHMEM_THPS ,HPAGE_PMD_NR ); - }else { -lruvec_stat_mod_folio (new_folio,NR_FILE_THPS ,HPAGE_PMD_NR ); - } +lruvec_stat_mod_folio (new_folio,NR_SHMEM ,HPAGE_PMD_NR ); +lruvec_stat_mod_folio (new_folio,NR_SHMEM_THPS ,HPAGE_PMD_NR );lruvec_stat_mod_folio (new_folio,NR_FILE_PAGES ,HPAGE_PMD_NR );/*
@@ -2240,8 +2165,7 @@ static enum scan_result collapse_file(struct mm_struct *mm, unsigned long addr,folio_mark_uptodate (new_folio);folio_ref_add (new_folio,HPAGE_PMD_NR -1 ); -if (is_shmem) -folio_mark_dirty (new_folio); +folio_mark_dirty (new_folio);folio_add_lru (new_folio);/* Join all the small entries into a single multi-index entry. */
@@ -2266,9 +2190,7 @@ static enum scan_result collapse_file(struct mm_struct *mm, unsigned long addr,list_del (&folio->lru);lruvec_stat_mod_folio (folio,NR_FILE_PAGES , -folio_nr_pages (folio)); -if (is_shmem) -lruvec_stat_mod_folio (folio,NR_SHMEM , - -folio_nr_pages (folio)); +lruvec_stat_mod_folio (folio,NR_SHMEM , -folio_nr_pages (folio)); folio->mapping =NULL ;folio_clear_active (folio);folio_clear_unevictable (folio);
@@ -2293,19 +2215,6 @@ static enum scan_result collapse_file(struct mm_struct *mm, unsigned long addr,folio_putback_lru (folio);folio_put (folio); } -/* -* Undo the updates of filemap_nr_thps_inc for non-SHMEM -* file only. This undo is not needed unless failure is -* due to SCAN_COPY_MC. -*/ -if (!is_shmem && result ==SCAN_COPY_MC ) { -filemap_nr_thps_dec (mapping); -/* -* Paired with the fence in do_dentry_open() -> get_write_access() -* to ensure the update to nr_thps is visible. -*/ -smp_mb (); - } new_folio->mapping =NULL ;
Signature · 1 line
2.43.0
David Hildenbrand (Arm)
maintainerRe: [RFC PATCH 02/11] mm/khugepaged: remove READ_ONLY_THP_FOR_FS code in collapse_file()
Quoted 12 lines · Zi Yan
READ_ONLY_THP_FOR_FSis no longer present, remove corresponding code.Signed-off-by Zi Yan <[email protected]>--- mm/khugepaged.c | 159 +++++++++++------------------------------------- 1 file changed, 34 insertions(+), 125 deletions(-)mm/khugepaged.c +0
-0
mm/khugepaged.c static enum scan_result collapse_file(struct mm_struct *mm, unsigned long addr, · line 1902
Quoted 5 lines
mm/khugepaged.c +1
-1@@ -1899,7 +1899,7 @@ static enum scan_result collapse_file(struct mm_struct *mm, unsigned long addr,int nr_none =0 ;bool is_shmem =shmem_file (file); -VM_BUG_ON (!IS_ENABLED (CONFIG_READ_ONLY_THP_FOR_FS ) && !is_shmem); +VM_WARN_ON_ONCE (!is_shmem);
Oh, but if that means that khugepaged cannot collapse large folios in FSes anymore, then this is the wrong approach I suppose?
I would have assumed that we would now collapse for any files that support large folios (in PMD size), not stopping to collapse entirely.
Signature · 3 lines
Cheers, David
Zi Yan
reviewerRe: [RFC PATCH 02/11] mm/khugepaged: remove READ_ONLY_THP_FOR_FS code in collapse_file()
Quoted 16 lines · David Hildenbrand (Arm)
Quoted 15 lines · Zi Yan
READ_ONLY_THP_FOR_FSis no longer present, remove corresponding code.Signed-off-by Zi Yan <[email protected]>--- mm/khugepaged.c | 159 +++++++++++------------------------------------- 1 file changed, 34 insertions(+), 125 deletions(-)mm/khugepaged.c +0
-0@@ -1899,7 +1899,7 @@ static enum scan_result collapse_file(struct mm_struct *mm, unsigned long addr,int nr_none =0 ;bool is_shmem =shmem_file (file);
Quoted 8 lines
mm/khugepaged.c static enum scan_result collapse_file(struct mm_struct *mm, unsigned long addr, · line 1902
Quoted 2 lines
mm/khugepaged.c +1
-1-VM_BUG_ON (!IS_ENABLED (CONFIG_READ_ONLY_THP_FOR_FS ) && !is_shmem); +VM_WARN_ON_ONCE (!is_shmem);Oh, but if that means that khugepaged cannot collapse large folios in FSes anymore, then this is the wrong approach I suppose?
I would have assumed that we would now collapse for any files that support large folios (in PMD size), not stopping to collapse entirely.
My understanding is that collapse_file() is only used for READ_ONLY_THP_FOR_FS. If FSes with large folio support also use it, I can replace IS_ENABLE with mapping_large_folio_support().
Best Regards,
Yan, Zi
David Hildenbrand (Arm)
maintainerRe: [RFC PATCH 02/11] mm/khugepaged: remove READ_ONLY_THP_FOR_FS code in collapse_file()
Quoted 24 lines · Zi Yan
Quoted 22 lines · David Hildenbrand (Arm)
Quoted 12 lines · Zi Yan
READ_ONLY_THP_FOR_FSis no longer present, remove corresponding code.Signed-off-by Zi Yan <[email protected]>--- mm/khugepaged.c | 159 +++++++++++------------------------------------- 1 file changed, 34 insertions(+), 125 deletions(-)mm/khugepaged.c +0
-0mm/khugepaged.c static enum scan_result collapse_file(struct mm_struct *mm, unsigned long addr, · line 1902
Quoted 5 lines
mm/khugepaged.c +1
-1@@ -1899,7 +1899,7 @@ static enum scan_result collapse_file(struct mm_struct *mm, unsigned long addr,int nr_none =0 ;bool is_shmem =shmem_file (file); -VM_BUG_ON (!IS_ENABLED (CONFIG_READ_ONLY_THP_FOR_FS ) && !is_shmem); +VM_WARN_ON_ONCE (!is_shmem);Oh, but if that means that khugepaged cannot collapse large folios in FSes anymore, then this is the wrong approach I suppose?
Quoted 6 lines
Quoted 2 lines
I would have assumed that we would now collapse for any files that support large folios (in PMD size), not stopping to collapse entirely.
My understanding is that
collapse_file()is only used forREAD_ONLY_THP_FOR_FS. If FSes with large folio support also use it, I can replaceIS_ENABLEwithmapping_large_folio_support().
Otherwise we'd be losing support for THP collapse in files? We'd have to cross fingers that readahead gives us some.
So we have to be a bit careful here. We want khugepaged to collapse THPs in filesystems that support large folios even without READ_ONLY_THP_FOR_FS.
Signature · 3 lines
Cheers, David
Zi Yan
reviewerRe: [RFC PATCH 02/11] mm/khugepaged: remove READ_ONLY_THP_FOR_FS code in collapse_file()
Quoted 32 lines · David Hildenbrand (Arm)
Quoted 24 lines · Zi Yan
Quoted 22 lines · David Hildenbrand (Arm)
Quoted 12 lines · Zi Yan
READ_ONLY_THP_FOR_FSis no longer present, remove corresponding code.Signed-off-by Zi Yan <[email protected]>--- mm/khugepaged.c | 159 +++++++++++------------------------------------- 1 file changed, 34 insertions(+), 125 deletions(-)mm/khugepaged.c +0
-0mm/khugepaged.c static enum scan_result collapse_file(struct mm_struct *mm, unsigned long addr, · line 1902
Quoted 5 lines
mm/khugepaged.c +1
-1@@ -1899,7 +1899,7 @@ static enum scan_result collapse_file(struct mm_struct *mm, unsigned long addr,int nr_none =0 ;bool is_shmem =shmem_file (file); -VM_BUG_ON (!IS_ENABLED (CONFIG_READ_ONLY_THP_FOR_FS ) && !is_shmem); +VM_WARN_ON_ONCE (!is_shmem);Oh, but if that means that khugepaged cannot collapse large folios in FSes anymore, then this is the wrong approach I suppose?
Quoted 6 lines
Quoted 2 lines
I would have assumed that we would now collapse for any files that support large folios (in PMD size), not stopping to collapse entirely.
My understanding is that
collapse_file()is only used forREAD_ONLY_THP_FOR_FS. If FSes with large folio support also use it, I can replaceIS_ENABLEwithmapping_large_folio_support().
Quoted 5 lines
Otherwise we'd be losing support for THP collapse in files? We'd have to cross fingers that readahead gives us some.
So we have to be a bit careful here. We want khugepaged to collapse THPs in filesystems that support large folios even without
READ_ONLY_THP_FOR_FS.
Based on[1], collapse_file() only works on read-only fd. So it is not as general as all files. If we do what you suggested, the function will be collapse read-only folios from FSes with large folio support.
BTW, has anyone used/relied on collapse_file() on any FS with large folio support?
[1] https://elixir.bootlin.com/linux/v6.19.9/source/mm/khugepaged.c#L1956
Best Regards,
Yan, Zi
David Hildenbrand (Arm)
maintainerRe: [RFC PATCH 02/11] mm/khugepaged: remove READ_ONLY_THP_FOR_FS code in collapse_file()
Quoted 12 lines · Zi Yan
Quoted 10 lines · David Hildenbrand (Arm)
Quoted 5 lines · Zi Yan
My understanding is that
collapse_file()is only used forREAD_ONLY_THP_FOR_FS. If FSes with large folio support also use it, I can replaceIS_ENABLEwithmapping_large_folio_support().Otherwise we'd be losing support for THP collapse in files? We'd have to cross fingers that readahead gives us some.
Quoted 6 lines
Quoted 2 lines
So we have to be a bit careful here. We want khugepaged to collapse THPs in filesystems that support large folios even without
READ_ONLY_THP_FOR_FS.Based on[1],
collapse_file()only works on read-only fd. So it is not as general as all files. If we do what you suggested, the function will be collapse read-only folios from FSes with large folio support.
Right, I think that's the first step to keep the existing use case working. Long term, I suspect we might want to extend that to writable files etc.
Quoted 3 lines
BTW, has anyone used/relied on
collapse_file()on any FS with large folio support?
I assume so, because for executables you would have to be lucky to get a PMD THP? So I don't see the non-khugepaged large folio support on par with khugepaged support.
Signature · 3 lines
Cheers, David
Zi Yan
reviewerRe: [RFC PATCH 02/11] mm/khugepaged: remove READ_ONLY_THP_FOR_FS code in collapse_file()
Quoted 25 lines · David Hildenbrand (Arm)
Quoted 12 lines · Zi Yan
Quoted 10 lines · David Hildenbrand (Arm)
Quoted 5 lines · Zi Yan
My understanding is that
collapse_file()is only used forREAD_ONLY_THP_FOR_FS. If FSes with large folio support also use it, I can replaceIS_ENABLEwithmapping_large_folio_support().Otherwise we'd be losing support for THP collapse in files? We'd have to cross fingers that readahead gives us some.
Quoted 6 lines
Quoted 2 lines
So we have to be a bit careful here. We want khugepaged to collapse THPs in filesystems that support large folios even without
READ_ONLY_THP_FOR_FS.Based on[1],
collapse_file()only works on read-only fd. So it is not as general as all files. If we do what you suggested, the function will be collapse read-only folios from FSes with large folio support.Right, I think that's the first step to keep the existing use case working. Long term, I suspect we might want to extend that to writable files etc.
Quoted 1 line
Quoted 6 lines
Quoted 2 lines
BTW, has anyone used/relied on
collapse_file()on any FS with large folio support?I assume so, because for executables you would have to be lucky to get a PMD THP? So I don't see the non-khugepaged large folio support on par with khugepaged support.
It is more like turning on READ_ONLY_THP_FOR_FS by default for FS with large folio support instead of removing it.
OK, I will give it another try.
Best Regards,
Yan, Zi
Matthew Wilcox
maintainerRe: [RFC PATCH 02/11] mm/khugepaged: remove READ_ONLY_THP_FOR_FS code in collapse_file()
Quoted 4 lines · Zi Yan
Quoted 3 lines · David Hildenbrand (Arm)
I assume so, because for executables you would have to be lucky to get a PMD THP? So I don't see the non-khugepaged large folio support on par with khugepaged support.
Not necessarily that lucky; if you set VM_HUGEPAGE, do_sync_mmap_readahead() will allocate PMD-sized folios automatically. On busy database servers (and is there any other kind?), khugepaged takes too long to run and find opportunities to collapse text pages. Like, days.
Quoted 4 lines
It is more like turning on
READ_ONLY_THP_FOR_FSby default for FS with large folio support instead of removing it.OK, I will give it another try.
I think the test needs to be:
if (mapping_max_folio_order(mapping) >= PMD_ORDER)
as there can be cases of filesystems which support up to, say, 64KiB, but not all the way up to 2MiB. I disapprove of this situation, but this is where we are right now.
David Hildenbrand (Arm)
maintainerRe: [RFC PATCH 02/11] mm/khugepaged: remove READ_ONLY_THP_FOR_FS code in collapse_file()
Quoted 11 lines · Matthew Wilcox
Quoted 4 lines · Zi Yan
Quoted 3 lines · David Hildenbrand (Arm)
I assume so, because for executables you would have to be lucky to get a PMD THP? So I don't see the non-khugepaged large folio support on par with khugepaged support.
Not necessarily that lucky; if you set
VM_HUGEPAGE,do_sync_mmap_readahead()will allocate PMD-sized folios automatically. On busy database servers (and is there any other kind?), khugepaged takes too long to run and find opportunities to collapse text pages. Like, days.
Yes, in particular given that the default khugepaged settings are awful.
Quoted 6 lines
Quoted 5 lines
It is more like turning on
READ_ONLY_THP_FOR_FSby default for FS with large folio support instead of removing it.OK, I will give it another try.
Quoted 7 lines
I think the test needs to be:
if (
mapping_max_folio_order(mapping)>=PMD_ORDER)as there can be cases of filesystems which support up to, say, 64KiB, but not all the way up to 2MiB. I disapprove of this situation, but this is where we are right now.
Right, that's what I had in mind.
Signature · 3 lines
Cheers, David
Zi Yan
reviewerRe: [RFC PATCH 02/11] mm/khugepaged: remove READ_ONLY_THP_FOR_FS code in collapse_file()
Quoted 7 lines · David Hildenbrand (Arm)
Quoted 6 lines · Matthew Wilcox
Quoted 4 lines · Zi Yan
Quoted 3 lines · David Hildenbrand (Arm)
I assume so, because for executables you would have to be lucky to get a PMD THP? So I don't see the non-khugepaged large folio support on par with khugepaged support.
Quoted 17 lines
Quoted 5 lines
Not necessarily that lucky; if you set
VM_HUGEPAGE,do_sync_mmap_readahead()will allocate PMD-sized folios automatically. On busy database servers (and is there any other kind?), khugepaged takes too long to run and find opportunities to collapse text pages. Like, days.Yes, in particular given that the default khugepaged settings are awful.
Quoted 9 lines
Quoted 5 lines
It is more like turning on
READ_ONLY_THP_FOR_FSby default for FS with large folio support instead of removing it.OK, I will give it another try.
I think the test needs to be:
if (
mapping_max_folio_order(mapping)>=PMD_ORDER)
This is very helpful, since I was thinking about using mapping_large_folio_support().
Quoted 6 lines
Quoted 4 lines
as there can be cases of filesystems which support up to, say, 64KiB, but not all the way up to 2MiB. I disapprove of this situation, but this is where we are right now.
Right, that's what I had in mind.
Does Nico’s mTHP support for khugepaged include changes to collapse_file()? That might change the above test.
Best Regards,
Yan, Zi
David Hildenbrand (Arm)
maintainerRe: [RFC PATCH 02/11] mm/khugepaged: remove READ_ONLY_THP_FOR_FS code in collapse_file()
Quoted 22 lines · Zi Yan
Quoted 15 lines · David Hildenbrand (Arm)
Quoted 6 lines · Matthew Wilcox
Not necessarily that lucky; if you set
VM_HUGEPAGE,do_sync_mmap_readahead()will allocate PMD-sized folios automatically. On busy database servers (and is there any other kind?), khugepaged takes too long to run and find opportunities to collapse text pages. Like, days.Yes, in particular given that the default khugepaged settings are awful.
Quoted 5 lines
I think the test needs to be:
if (
mapping_max_folio_order(mapping)>=PMD_ORDER)This is very helpful, since I was thinking about using
mapping_large_folio_support().Quoted 1 line
Quoted 1 line
Quoted 8 lines
Quoted 5 lines
Quoted 3 lines
as there can be cases of filesystems which support up to, say, 64KiB, but not all the way up to 2MiB. I disapprove of this situation, but this is where we are right now.
Right, that's what I had in mind.
Does Nico’s mTHP support for khugepaged include changes to
collapse_file()? That might change the above test.
At least not regarding adding support for other folio sizes. Baolin (IIRC) had a version for shmem support, but that will come after Nico's series was merged.
Signature · 3 lines
Cheers, David
Zi Yan
reviewerRe: [RFC PATCH 02/11] mm/khugepaged: remove READ_ONLY_THP_FOR_FS code in collapse_file()
Quoted 27 lines · David Hildenbrand (Arm)
Quoted 26 lines · Zi Yan
Quoted 15 lines · David Hildenbrand (Arm)
Quoted 6 lines · Matthew Wilcox
Not necessarily that lucky; if you set
VM_HUGEPAGE,do_sync_mmap_readahead()will allocate PMD-sized folios automatically. On busy database servers (and is there any other kind?), khugepaged takes too long to run and find opportunities to collapse text pages. Like, days.Yes, in particular given that the default khugepaged settings are awful.
Quoted 5 lines
I think the test needs to be:
if (
mapping_max_folio_order(mapping)>=PMD_ORDER)This is very helpful, since I was thinking about using
mapping_large_folio_support().Quoted 5 lines
Quoted 4 lines
as there can be cases of filesystems which support up to, say, 64KiB, but not all the way up to 2MiB. I disapprove of this situation, but this is where we are right now.
Quoted 8 lines
Quoted 4 lines
Quoted 1 line
Right, that's what I had in mind.
Does Nico’s mTHP support for khugepaged include changes to
collapse_file()? That might change the above test.At least not regarding adding support for other folio sizes. Baolin (IIRC) had a version for shmem support, but that will come after Nico's series was merged.
Great. That makes my life easier. Thanks.
Best Regards,
Yan, Zi
Baolin Wang
reviewerRe: [RFC PATCH 02/11] mm/khugepaged: remove READ_ONLY_THP_FOR_FS code in collapse_file()
Quoted 29 lines · Zi Yan
Quoted 27 lines · David Hildenbrand (Arm)
Quoted 26 lines · Zi Yan
Quoted 15 lines · David Hildenbrand (Arm)
Quoted 6 lines · Matthew Wilcox
Not necessarily that lucky; if you set
VM_HUGEPAGE,do_sync_mmap_readahead()will allocate PMD-sized folios automatically. On busy database servers (and is there any other kind?), khugepaged takes too long to run and find opportunities to collapse text pages. Like, days.Yes, in particular given that the default khugepaged settings are awful.
Quoted 5 lines
I think the test needs to be:
if (
mapping_max_folio_order(mapping)>=PMD_ORDER)This is very helpful, since I was thinking about using
mapping_large_folio_support().Quoted 5 lines
Quoted 4 lines
as there can be cases of filesystems which support up to, say, 64KiB, but not all the way up to 2MiB. I disapprove of this situation, but this is where we are right now.
Quoted 8 lines
Quoted 8 lines
Quoted 4 lines
Quoted 1 line
Right, that's what I had in mind.
Does Nico’s mTHP support for khugepaged include changes to
collapse_file()? That might change the above test.At least not regarding adding support for other folio sizes. Baolin (IIRC) had a version for shmem support, but that will come after Nico's series was merged.
Right. Here is the link to the RFC version:
https://lore.kernel.org/all/[email protected]/
Moreover, I have further updated my local tree based on Nico's series. I will send out the new version once his series is merged.
Zi Yan
reviewerRFC PATCH 3/11 mm: remove filemap_nr_thps*() functions
In reply to Zi YanThey are used by READ_ONLY_THP_FOR_FS and no longer needed.
--- include/linux/pagemap.h | 29 ----------------------------- mm/filemap.c | 1 - mm/huge_memory.c | 1 - 3 files changed, 31 deletions(-)
include/linux/pagemap.h +0 -29
@@ -530,35 +530,6 @@ static inline size_t mapping_max_folio_size(const struct address_space *mapping)return PAGE_SIZE <<mapping_max_folio_order (mapping); } -static inline int filemap_nr_thps (const struct address_space *mapping) -{ -#ifdef CONFIG_READ_ONLY_THP_FOR_FS -return atomic_read (&mapping->nr_thps); -#else -return 0 ; -#endif -} - -static inline void filemap_nr_thps_inc (struct address_space *mapping) -{ -#ifdef CONFIG_READ_ONLY_THP_FOR_FS -if (!mapping_large_folio_support (mapping)) -atomic_inc (&mapping->nr_thps); -#else -WARN_ON_ONCE (mapping_large_folio_support (mapping) ==0 ); -#endif -} - -static inline void filemap_nr_thps_dec (struct address_space *mapping) -{ -#ifdef CONFIG_READ_ONLY_THP_FOR_FS -if (!mapping_large_folio_support (mapping)) -atomic_dec (&mapping->nr_thps); -#else -WARN_ON_ONCE (mapping_large_folio_support (mapping) ==0 ); -#endif -} -struct address_space *folio_mapping (const struct folio *folio);/**
mm/filemap.c +0 -1
@@ -189,7 +189,6 @@ static void filemap_unaccount_folio(struct address_space *mapping,lruvec_stat_mod_folio (folio,NR_SHMEM_THPS , -nr); }else if (folio_test_pmd_mappable (folio)) {lruvec_stat_mod_folio (folio,NR_FILE_THPS , -nr); -filemap_nr_thps_dec (mapping); }if (test_bit (AS_KERNEL_FILE , &folio->mapping->flags)) mod_node_page_state(folio_pgdat(folio),
mm/huge_memory.c +0 -1
@@ -3832,7 +3832,6 @@ static int __folio_freeze_and_split_unmapped(struct folio *folio, unsigned int n }else {lruvec_stat_mod_folio (folio,NR_FILE_THPS , -nr); -filemap_nr_thps_dec (mapping); } } }
Signature · 1 line
2.43.0
Zi Yan
reviewerRFC PATCH 4/11 mm/huge_memory: remove file_thp_enabled() and its caller.
In reply to Zi YanIt is used by no-long-exist READ_ONLY_THP_FOR_FS.
--- mm/huge_memory.c | 21 --------------------- 1 file changed, 21 deletions(-)
mm/huge_memory.c +0 -21
@@ -85,24 +85,6 @@ unsigned long huge_anon_orders_madvise __read_mostly;unsigned long huge_anon_orders_inherit__read_mostly ;static bool anon_orders_configured__initdata ; -static inline bool file_thp_enabled (struct vm_area_struct *vma) -{ -struct inode *inode; - -if (!IS_ENABLED (CONFIG_READ_ONLY_THP_FOR_FS )) -return false; - -if (!vma->vm_file) -return false; - - inode =file_inode (vma->vm_file); - -if (IS_ANON_FILE (inode)) -return false; - -return !inode_is_open_for_write (inode) &&S_ISREG (inode->i_mode); -} -/* If returns true, we are unable to access the VMA's folios. */ static bool vma_is_special_huge (const struct vm_area_struct *vma) {
@@ -199,9 +181,6 @@ unsigned long __thp_vma_allowable_orders(struct vm_area_struct *vma,*/ if (((in_pf || smaps)) && vma->vm_ops->huge_fault)return orders; -/* Only regular file is valid in collapse path */ -if (((!in_pf || smaps)) &&file_thp_enabled (vma)) -return orders;return 0 ; }
Signature · 1 line
2.43.0
Zi Yan
reviewerRFC PATCH 5/11 mm/huge_memory: remove folio split check for READ_ONLY_THP_FOR_FS
In reply to Zi YanWithout READ_ONLY_THP_FOR_FS, large file-backed folios cannot be created by a FS without large folio support. The check is no longer needed.
--- mm/huge_memory.c | 22 ---------------------- 1 file changed, 22 deletions(-)
mm/huge_memory.c +0 -22
@@ -3710,28 +3710,6 @@ int folio_check_splittable(struct folio *folio, unsigned int new_order,/* order-1 is not supported for anonymous THP. */ if (new_order ==1 )return -EINVAL ; - }else if (split_type ==SPLIT_TYPE_NON_UNIFORM || new_order) { -if (IS_ENABLED (CONFIG_READ_ONLY_THP_FOR_FS ) && - !mapping_large_folio_support (folio->mapping)) { -/* -* We can always split a folio down to a single page -* (new_order == 0) uniformly. -* -* For any other scenario -* a) uniform split targeting a large folio -* (new_order > 0) -* b) any non-uniform split -* we must confirm that the file system supports large -* folios. -* -* Note that we might still have THPs in such -* mappings, which is created from khugepaged when -* CONFIG_READ_ONLY_THP_FOR_FS is enabled. But in that -* case, the mapping does not actually support large -* folios properly. -*/ -return -EINVAL ; - } }/*
Signature · 1 line
2.43.0
Zi Yan
reviewerRFC PATCH 6/11 mm/truncate: use folio_split() in truncate_inode_partial_folio()
In reply to Zi YanAfter READ_ONLY_THP_FOR_FS is removed, FS either supports large folio or not. folio_split() can be used on a FS with large folio support without worrying about getting a THP on a FS without large folio support.
--- include/linux/huge_mm.h | 28 ---------------------------- mm/truncate.c | 8 ++++---- 2 files changed, 4 insertions(+), 32 deletions(-)
include/linux/huge_mm.h +0 -28
@@ -389,27 +389,6 @@ static inline int split_huge_page_to_order(struct page *page, unsigned int new_oreturn split_huge_page_to_list_to_order (page,NULL , new_order); } -/** -* try_folio_split_to_order() - try to split a @folio at @page to @new_order -* using non uniform split. -* @folio: folio to be split -* @page: split to @new_order at the given page -* @new_order: the target split order -* -* Try to split a @folio at @page using non uniform split to @new_order, if -* non uniform split is not supported, fall back to uniform split. After-split -* folios are put back to LRU list. Use min_order_for_split() to get the lower -* bound of @new_order. -* -* Return: 0 - split is successful, otherwise split failed. -*/ -static inline int try_folio_split_to_order (struct folio *folio, -struct page *page,unsigned int new_order) -{ -if (folio_check_splittable (folio, new_order,SPLIT_TYPE_NON_UNIFORM )) -return split_huge_page_to_order (&folio->page, new_order); -return folio_split (folio, new_order, page,NULL ); -}static inline int split_huge_page (struct page *page) {return split_huge_page_to_list_to_order (page,NULL ,0 );
@@ -641,13 +620,6 @@ static inline int split_folio_to_list(struct folio *folio, struct list_head *lisreturn -EINVAL ; } -static inline int try_folio_split_to_order (struct folio *folio, -struct page *page,unsigned int new_order) -{ -VM_WARN_ON_ONCE_FOLIO (1 , folio); -return -EINVAL ; -} -static inline void deferred_split_folio (struct folio *folio,bool partially_mapped) {}#define split_huge_pmd (__vma, __pmd, __address) \ do { } while (0)
mm/truncate.c +4 -4
@@ -177,7 +177,7 @@ int truncate_inode_folio(struct address_space *mapping, struct folio *folio)return 0 ; } -static int try_folio_split_or_unmap (struct folio *folio,struct page *split_at, +static int folio_split_or_unmap (struct folio *folio,struct page *split_at,unsigned long min_order) { enum ttu_flags ttu_flags =
@@ -186,7 +186,7 @@ static int try_folio_split_or_unmap(struct folio *folio, struct page *split_at,TTU_IGNORE_MLOCK ;int ret; - ret =try_folio_split_to_order (folio, split_at, min_order); + ret =folio_split (folio, min_order, split_at,NULL );/* * If the split fails, unmap the folio, so it will be refaulted
@@ -252,7 +252,7 @@ bool truncate_inode_partial_folio(struct folio *folio, loff_t start, loff_t end) min_order =mapping_min_folio_order (folio->mapping); split_at =folio_page (folio,PAGE_ALIGN_DOWN (offset) /PAGE_SIZE ); -if (!try_folio_split_or_unmap (folio, split_at, min_order)) { +if (!folio_split_or_unmap (folio, split_at, min_order)) {/* * try to split at offset + length to make sure folios within * the range can be dropped, especially to avoid memory waste
@@ -279,7 +279,7 @@ bool truncate_inode_partial_folio(struct folio *folio, loff_t start, loff_t end)/* make sure folio2 is large and does not change its mapping */ if (folio_test_large (folio2) && folio2->mapping == folio->mapping) -try_folio_split_or_unmap (folio2, split_at2, min_order); +folio_split_or_unmap (folio2, split_at2, min_order);folio_unlock (folio2); out:
Signature · 1 line
2.43.0
kernel test robot
build botRe: [RFC PATCH 06/11] mm/truncate: use folio_split() in truncate_inode_partial_folio()
kernel test robot noticed the following build errors:
Hi Zi,
[This is a private test report for your RFC patch.] kernel test robot noticed the following build errors:
[auto build test ERROR on akpm-mm/mm-everything]
[cannot apply to brauner-vfs/vfs.all kdave/for-next linus/master v7.0-rc5 next-20260323] [If your patch is applied to the wrong git tree, kindly drop us a note. And when submitting patch, we suggest to use '--base' as documented in
https://git-scm.com/docs/git-format-patch#_base_tree_information]
url: https://github.com/intel-lab-lkp/linux/commits/Zi-Yan/mm-remove-READ_ONLY_THP_FOR_FS-Kconfig-option/20260324-043510 base: https://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm.git mm-everything patch link: https://lore.kernel.org/r/20260323190644.1714379-7-ziy%40nvidia.com patch subject: [RFC PATCH 06/11] mm/truncate: use folio_split() in truncate_inode_partial_folio() config: x86_64-allnoconfig (https://download.01.org/0day-ci/archive/20260325/[email protected]/config) compiler: clang version 20.1.8 (https://github.com/llvm/llvm-project 87f0227cb60147a26a1eeb4fb06e3b505e9c7261) reproduce (this is a W=1 build): (https://download.01.org/0day-ci/archive/20260325/[email protected]/reproduce)
If you fix the issue in a separate patch/commit (i.e. not just a new version of the same patch/commit), kindly add following tags
| Reported-by: kernel test robot <[email protected]>
| Closes: https://lore.kernel.org/oe-kbuild-all/[email protected]/
All errors (new ones prefixed by >>):
>> mm/truncate.c:189:8: error: call to undeclared function 'folio_split'; ISO C99 and later do not support implicit function declarations [-Wimplicit-function-declaration]
189 | ret = folio_split(folio, min_order, split_at, NULL);
| ^1 error generated.
vim +/folio_split +189 mm/truncate.c
179
180 static int folio_split_or_unmap(struct folio *folio, struct page *split_at,
181 unsigned long min_order)
182 {
183 enum ttu_flags ttu_flags =
184 TTU_SYNC |
185 TTU_SPLIT_HUGE_PMD |
186 TTU_IGNORE_MLOCK;
187 int ret;
188
> 189 ret = folio_split(folio, min_order, split_at, NULL);
190
191 /*
192 * If the split fails, unmap the folio, so it will be refaulted
193 * with PTEs to respect SIGBUS semantics.
194 *
195 * Make an exception for shmem/tmpfs that for long time
196 * intentionally mapped with PMDs across i_size.
197 */
198 if (ret && !shmem_mapping(folio->mapping)) {
199 try_to_unmap(folio, ttu_flags);
200 WARN_ON(folio_mapped(folio));
201 }
202
203 return ret;
204 }
205
Signature · 2 lines
0-DAY CI Kernel Test Service https://github.com/intel/lkp-tests/wiki
kernel test robot
build botRe: [RFC PATCH 06/11] mm/truncate: use folio_split() in truncate_inode_partial_folio()
In reply to Zi Yankernel test robot noticed the following build errors:
Hi Zi,
[This is a private test report for your RFC patch.] kernel test robot noticed the following build errors:
[auto build test ERROR on akpm-mm/mm-everything]
[cannot apply to brauner-vfs/vfs.all kdave/for-next linus/master v7.0-rc5 next-20260323] [If your patch is applied to the wrong git tree, kindly drop us a note. And when submitting patch, we suggest to use '--base' as documented in
https://git-scm.com/docs/git-format-patch#_base_tree_information]
url: https://github.com/intel-lab-lkp/linux/commits/Zi-Yan/mm-remove-READ_ONLY_THP_FOR_FS-Kconfig-option/20260324-043510 base: https://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm.git mm-everything patch link: https://lore.kernel.org/r/20260323190644.1714379-7-ziy%40nvidia.com patch subject: [RFC PATCH 06/11] mm/truncate: use folio_split() in truncate_inode_partial_folio() config: nios2-allnoconfig (https://download.01.org/0day-ci/archive/20260325/[email protected]/config) compiler: nios2-linux-gcc (GCC) 11.5.0 reproduce (this is a W=1 build): (https://download.01.org/0day-ci/archive/20260325/[email protected]/reproduce)
If you fix the issue in a separate patch/commit (i.e. not just a new version of the same patch/commit), kindly add following tags
| Reported-by: kernel test robot <[email protected]>
| Closes: https://lore.kernel.org/oe-kbuild-all/[email protected]/
All errors (new ones prefixed by >>):
mm/truncate.c: In function 'folio_split_or_unmap':
>> mm/truncate.c:189:15: error: implicit declaration of function 'folio_split'; did you mean 'folio_shift'? [-Werror=implicit-function-declaration]
189 | ret = folio_split(folio, min_order, split_at, NULL);
| ^~~~~~~~~~~
| folio_shiftcc1: some warnings being treated as errors
vim +189 mm/truncate.c
179
180 static int folio_split_or_unmap(struct folio *folio, struct page *split_at,
181 unsigned long min_order)
182 {
183 enum ttu_flags ttu_flags =
184 TTU_SYNC |
185 TTU_SPLIT_HUGE_PMD |
186 TTU_IGNORE_MLOCK;
187 int ret;
188
> 189 ret = folio_split(folio, min_order, split_at, NULL);
190
191 /*
192 * If the split fails, unmap the folio, so it will be refaulted
193 * with PTEs to respect SIGBUS semantics.
194 *
195 * Make an exception for shmem/tmpfs that for long time
196 * intentionally mapped with PMDs across i_size.
197 */
198 if (ret && !shmem_mapping(folio->mapping)) {
199 try_to_unmap(folio, ttu_flags);
200 WARN_ON(folio_mapped(folio));
201 }
202
203 return ret;
204 }
205
Signature · 2 lines
0-DAY CI Kernel Test Service https://github.com/intel/lkp-tests/wiki
Zi Yan
reviewerRFC PATCH 7/11 fs: remove nr_thp from struct address_space
In reply to Zi YanREAD_ONLY_THP_FOR_FS is removed, the related field is no longer needed.
--- fs/inode.c | 3 --- include/linux/fs.h | 5 ----- 2 files changed, 8 deletions(-)
fs/inode.c +0 -3
@@ -280,9 +280,6 @@ int inode_init_always_gfp(struct super_block *sb, struct inode *inode, gfp_t gfp mapping->flags =0 ; mapping->wb_err =0 ;atomic_set (&mapping->i_mmap_writable,0 ); -#ifdef CONFIG_READ_ONLY_THP_FOR_FS -atomic_set (&mapping->nr_thps,0 ); -#endif mapping_set_gfp_mask (mapping,GFP_HIGHUSER_MOVABLE ); mapping->i_private_data =NULL ; mapping->writeback_index =0 ;
include/linux/fs.h +0 -5
@@ -455,7 +455,6 @@ extern const struct address_space_operations empty_aops;* memory mappings. * @gfp_mask: Memory allocation flags to use for allocating pages. * @i_mmap_writable: Number of VM_SHARED, VM_MAYWRITE mappings. -* @nr_thps: Number of THPs in the pagecache (non-shmem only). * @i_mmap: Tree of private and shared mappings. * @i_mmap_rwsem: Protects @i_mmap and @i_mmap_writable. * @nrpages: Number of page entries, protected by the i_pages lock.
@@ -473,10 +472,6 @@ struct address_space {struct rw_semaphore invalidate_lock;gfp_t gfp_mask;atomic_t i_mmap_writable; -#ifdef CONFIG_READ_ONLY_THP_FOR_FS -/* number of thp, only for non-shmem files */ -atomic_t nr_thps; -#endif struct rb_root_cached i_mmap;unsigned long nrpages;pgoff_t writeback_index;
Signature · 1 line
2.43.0
Zi Yan
reviewerRFC PATCH 8/11 fs: remove READ_ONLY_THP_FOR_FS code
In reply to Zi YanREAD_ONLY_THP_FOR_FS is no longer present, delete related code.
--- fs/open.c | 27 --------------------------- 1 file changed, 27 deletions(-)
fs/open.c +0 -27
@@ -970,33 +970,6 @@ static int do_dentry_open(struct file *f,if ((f->f_flags &O_DIRECT ) && !(f->f_mode &FMODE_CAN_ODIRECT ))return -EINVAL ; -/* -* XXX: Huge page cache doesn't support writing yet. Drop all page -* cache for this file before processing writes. -*/ -if (f->f_mode &FMODE_WRITE ) { -/* -* Depends on full fence from get_write_access() to synchronize -* against collapse_file() regarding i_writecount and nr_thps -* updates. Ensures subsequent insertion of THPs into the page -* cache will fail. -*/ -if (filemap_nr_thps (inode->i_mapping)) { -struct address_space *mapping = inode->i_mapping; - -filemap_invalidate_lock (inode->i_mapping); -/* -* unmap_mapping_range just need to be called once -* here, because the private pages is not need to be -* unmapped mapping (e.g. data segment of dynamic -* shared libraries here). -*/ -unmap_mapping_range (mapping,0 ,0 ,0 ); -truncate_inode_pages (mapping,0 ); -filemap_invalidate_unlock (inode->i_mapping); - } - } -return 0 ; cleanup_all:
Signature · 1 line
2.43.0
Zi Yan
reviewerRFC PATCH 9/11 fs/btrfs: remove a comment referring to READ_ONLY_THP_FOR_FS
In reply to Zi YanREAD_ONLY_THP_FOR_FS is no longer present, remove related comment.
--- fs/btrfs/defrag.c | 3 --- 1 file changed, 3 deletions(-)
fs/btrfs/defrag.c +0 -3
@@ -860,9 +860,6 @@ static struct folio *defrag_prepare_one_folio(struct btrfs_inode *inode, pgoff_treturn folio;/* -* Since we can defragment files opened read-only, we can encounter -* transparent huge pages here (see CONFIG_READ_ONLY_THP_FOR_FS). -* * The IO for such large folios is not fully tested, thus return * an error to reject such folios unless it's an experimental build. *
Signature · 1 line
2.43.0
Re: [RFC PATCH 09/11] fs/btrfs: remove a comment referring to READ_ONLY_THP_FOR_FS
Quoted 3 lines · Zi Yan
READ_ONLY_THP_FOR_FSis no longer present, remove related comment.Signed-off-by Zi Yan <[email protected]>
Zi Yan
reviewerRFC PATCH 10/11 selftests/mm: remove READ_ONLY_THP_FOR_FS test in khugepaged
In reply to Zi YanREAD_ONLY_THP_FOR_FS is no longer present, remove related test.
--- tools/testing/selftests/mm/khugepaged.c | 197 +----------------------- 1 file changed, 3 insertions(+), 194 deletions(-)
tools/testing/selftests/mm/khugepaged.c +3 -194
@@ -37,7 +37,6 @@ static int anon_order;enum vma_type {VMA_ANON , -VMA_FILE ,VMA_SHMEM , };
@@ -49,7 +48,6 @@ struct mem_ops {const char *name; }; -static struct mem_ops *file_ops;static struct mem_ops *anon_ops;static struct mem_ops *shmem_ops;
@@ -112,8 +110,6 @@ static void restore_settings(int sig)static void save_settings (void ) {printf ("Save THP and khugepaged settings..." ); -if (file_ops && finfo.type ==VMA_FILE ) -thp_set_read_ahead_path (finfo.dev_queue_read_ahead_path);thp_save_settings ();success ("OK" );
@@ -125,89 +121,6 @@ static void save_settings(void)signal (SIGQUIT , restore_settings); } -static void get_finfo (const char *dir) -{ -struct stat path_stat; -struct statfs fs; -char buf[1 <<10 ]; -char path[PATH_MAX ]; -char *str, *end; - - finfo.dir = dir; -stat (finfo.dir, &path_stat); -if (!S_ISDIR (path_stat.st_mode)) { -printf ("%s: Not a directory (%s)\n" , __func__, finfo.dir); -exit (EXIT_FAILURE ); - } -if (snprintf (finfo.path,sizeof (finfo.path),"%s/" TEST_FILE , - finfo.dir) >=sizeof (finfo.path)) { -printf ("%s: Pathname is too long\n" , __func__); -exit (EXIT_FAILURE ); - } -if (statfs (finfo.dir, &fs)) { -perror ("statfs()" ); -exit (EXIT_FAILURE ); - } - finfo.type = fs.f_type ==TMPFS_MAGIC ?VMA_SHMEM :VMA_FILE ; -if (finfo.type ==VMA_SHMEM ) -return ; - -/* Find owning device's queue/read_ahead_kb control */ -if (snprintf (path,sizeof (path),"/sys/dev/block/%d:%d/uevent" , -major (path_stat.st_dev),minor (path_stat.st_dev)) - >=sizeof (path)) { -printf ("%s: Pathname is too long\n" , __func__); -exit (EXIT_FAILURE ); - } -if (read_file (path, buf,sizeof (buf)) <0 ) { -perror ("read_file(read_num)" ); -exit (EXIT_FAILURE ); - } -if (strstr (buf,"DEVTYPE=disk" )) { -/* Found it */ -if (snprintf (finfo.dev_queue_read_ahead_path, -sizeof (finfo.dev_queue_read_ahead_path), -"/sys/dev/block/%d:%d/queue/read_ahead_kb" , -major (path_stat.st_dev),minor (path_stat.st_dev)) - >=sizeof (finfo.dev_queue_read_ahead_path)) { -printf ("%s: Pathname is too long\n" , __func__); -exit (EXIT_FAILURE ); - } -return ; - } -if (!strstr (buf,"DEVTYPE=partition" )) { -printf ("%s: Unknown device type: %s\n" , __func__, path); -exit (EXIT_FAILURE ); - } -/* -* Partition of block device - need to find actual device. -* Using naming convention that devnameN is partition of -* device devname. -*/ - str =strstr (buf,"DEVNAME=" ); -if (!str) { -printf ("%s: Could not read: %s" , __func__, path); -exit (EXIT_FAILURE ); - } - str +=8 ; - end = str; -while (*end) { -if (isdigit (*end)) { - *end ='\0' ; -if (snprintf (finfo.dev_queue_read_ahead_path, -sizeof (finfo.dev_queue_read_ahead_path), -"/sys/block/%s/queue/read_ahead_kb" , - str) >=sizeof (finfo.dev_queue_read_ahead_path)) { -printf ("%s: Pathname is too long\n" , __func__); -exit (EXIT_FAILURE ); - } -return ; - } - ++end; - } -printf ("%s: Could not read: %s\n" , __func__, path); -exit (EXIT_FAILURE ); -}static bool check_swap (void *addr,unsigned long size) {
@@ -364,77 +277,6 @@ static bool anon_check_huge(void *addr, int nr_hpages)return check_huge_anon (addr, nr_hpages, hpage_pmd_size); } -static void *file_setup_area (int nr_hpages) -{ -int fd; -void *p; -unsigned long size; - -unlink (finfo.path);/* Cleanup from previous failed tests */ -printf ("Creating %s for collapse%s..." , finfo.path, - finfo.type ==VMA_SHMEM ?" (tmpfs)" :"" ); - fd =open (finfo.path,O_DSYNC |O_CREAT |O_RDWR |O_TRUNC |O_EXCL , -777 ); -if (fd <0 ) { -perror ("open()" ); -exit (EXIT_FAILURE ); - } - - size = nr_hpages * hpage_pmd_size; - p =alloc_mapping (nr_hpages); -fill_memory (p,0 , size); -write (fd, p, size); -close (fd); -munmap (p, size); -success ("OK" ); - -printf ("Opening %s read only for collapse..." , finfo.path); - finfo.fd =open (finfo.path,O_RDONLY ,777 ); -if (finfo.fd <0 ) { -perror ("open()" ); -exit (EXIT_FAILURE ); - } - p =mmap (BASE_ADDR , size,PROT_READ , -MAP_PRIVATE , finfo.fd,0 ); -if (p ==MAP_FAILED || p !=BASE_ADDR ) { -perror ("mmap()" ); -exit (EXIT_FAILURE ); - } - -/* Drop page cache */ -write_file ("/proc/sys/vm/drop_caches" ,"3" ,2 ); -success ("OK" ); -return p; -} - -static void file_cleanup_area (void *p,unsigned long size) -{ -munmap (p, size); -close (finfo.fd); -unlink (finfo.path); -} - -static void file_fault (void *p,unsigned long start,unsigned long end) -{ -if (madvise (((char *)p) + start, end - start,MADV_POPULATE_READ )) { -perror ("madvise(MADV_POPULATE_READ" ); -exit (EXIT_FAILURE ); - } -} - -static bool file_check_huge (void *addr,int nr_hpages) -{ -switch (finfo.type) { -case VMA_FILE : -return check_huge_file (addr, nr_hpages, hpage_pmd_size); -case VMA_SHMEM : -return check_huge_shmem (addr, nr_hpages, hpage_pmd_size); -default : -exit (EXIT_FAILURE ); -return false; - } -} -static void *shmem_setup_area (int nr_hpages) {void *p;
@@ -477,14 +319,6 @@ static struct mem_ops __anon_ops = { .name = "anon", }; -static struct mem_ops __file_ops = { - .setup_area = &file_setup_area, - .cleanup_area = &file_cleanup_area, - .fault = &file_fault, - .check_huge = &file_check_huge, - .name ="file" , -}; -static struct mem_ops __shmem_ops = { .setup_area = &shmem_setup_area, .cleanup_area = &shmem_cleanup_area,
@@ -576,7 +410,7 @@ static void khugepaged_collapse(const char *msg, char *p, int nr_hpages, }/* -* For file and shmem memory, khugepaged only retracts pte entries after +* For shmem memory, khugepaged only retracts pte entries after * putting the new hugepage in the page cache. The hugepage must be * subsequently refaulted to install the pmd mapping for the mm. */
@@ -603,7 +437,7 @@ static struct collapse_context __madvise_context = {static bool is_tmpfs (struct mem_ops *ops) { -return ops == &__file_ops && finfo.type ==VMA_SHMEM ; +return finfo.type ==VMA_SHMEM ; }static bool is_anon (struct mem_ops *ops)
@@ -1084,10 +918,7 @@ static void usage(void)fprintf (stderr,"\nUsage: ./khugepaged [OPTIONS] <test type> [dir]\n\n" );fprintf (stderr,"\t<test type>\t: <context>:<mem_type>\n" );fprintf (stderr,"\t<context>\t: [all|khugepaged|madvise]\n" ); -fprintf (stderr,"\t<mem_type>\t: [all|anon|file|shmem]\n" ); -fprintf (stderr,"\n\t\"file,all\" mem_type requires [dir] argument\n" ); -fprintf (stderr,"\n\t\"file,all\" mem_type requires kernel built with\n" ); -fprintf (stderr,"\tCONFIG_READ_ONLY_THP_FOR_FS=y\n" ); +fprintf (stderr,"\t<mem_type>\t: [all|anon|shmem]\n" );fprintf (stderr,"\n\tif [dir] is a (sub)directory of a tmpfs mount, tmpfs must be\n" );fprintf (stderr,"\tmounted with huge=advise option for khugepaged tests to work\n" );fprintf (stderr,"\n\tSupported Options:\n" );
@@ -1143,26 +974,16 @@ static void parse_test_type(int argc, char **argv)usage ();if (!strcmp (buf,"all" )) { - file_ops = &__file_ops; anon_ops = &__anon_ops; shmem_ops = &__shmem_ops; }else if (!strcmp (buf,"anon" )) { anon_ops = &__anon_ops; - }else if (!strcmp (buf,"file" )) { - file_ops = &__file_ops; }else if (!strcmp (buf,"shmem" )) { shmem_ops = &__shmem_ops; }else {usage (); } -if (!file_ops) -return ; - -if (argc !=2 ) -usage (); - -get_finfo (argv[1 ]); }int main (int argc,char **argv)
@@ -1228,37 +1049,27 @@ int main(int argc, char **argv) }while (0 )TEST (collapse_full, khugepaged_context, anon_ops); -TEST (collapse_full, khugepaged_context, file_ops);TEST (collapse_full, khugepaged_context, shmem_ops);TEST (collapse_full, madvise_context, anon_ops); -TEST (collapse_full, madvise_context, file_ops);TEST (collapse_full, madvise_context, shmem_ops);TEST (collapse_empty, khugepaged_context, anon_ops);TEST (collapse_empty, madvise_context, anon_ops);TEST (collapse_single_pte_entry, khugepaged_context, anon_ops); -TEST (collapse_single_pte_entry, khugepaged_context, file_ops);TEST (collapse_single_pte_entry, khugepaged_context, shmem_ops);TEST (collapse_single_pte_entry, madvise_context, anon_ops); -TEST (collapse_single_pte_entry, madvise_context, file_ops);TEST (collapse_single_pte_entry, madvise_context, shmem_ops);TEST (collapse_max_ptes_none, khugepaged_context, anon_ops); -TEST (collapse_max_ptes_none, khugepaged_context, file_ops);TEST (collapse_max_ptes_none, madvise_context, anon_ops); -TEST (collapse_max_ptes_none, madvise_context, file_ops);TEST (collapse_single_pte_entry_compound, khugepaged_context, anon_ops); -TEST (collapse_single_pte_entry_compound, khugepaged_context, file_ops);TEST (collapse_single_pte_entry_compound, madvise_context, anon_ops); -TEST (collapse_single_pte_entry_compound, madvise_context, file_ops);TEST (collapse_full_of_compound, khugepaged_context, anon_ops); -TEST (collapse_full_of_compound, khugepaged_context, file_ops);TEST (collapse_full_of_compound, khugepaged_context, shmem_ops);TEST (collapse_full_of_compound, madvise_context, anon_ops); -TEST (collapse_full_of_compound, madvise_context, file_ops);TEST (collapse_full_of_compound, madvise_context, shmem_ops);TEST (collapse_compound_extreme, khugepaged_context, anon_ops);
@@ -1280,10 +1091,8 @@ int main(int argc, char **argv)TEST (collapse_max_ptes_shared, madvise_context, anon_ops);TEST (madvise_collapse_existing_thps, madvise_context, anon_ops); -TEST (madvise_collapse_existing_thps, madvise_context, file_ops);TEST (madvise_collapse_existing_thps, madvise_context, shmem_ops); -TEST (madvise_retracted_page_tables, madvise_context, file_ops);TEST (madvise_retracted_page_tables, madvise_context, shmem_ops);restore_settings (0 );
Signature · 1 line
2.43.0
Matthew Wilcox
maintainerRe: [RFC PATCH 10/11] selftests/mm: remove READ_ONLY_THP_FOR_FS test in khugepaged
Quoted 1 line · Zi Yan
READ_ONLY_THP_FOR_FSis no longer present, remove related test.
Um, surely we want to keep the test? It's no longer conditional on READ_ONLY_THP_FOR_FS being enabled, but we still want to collapse mapped files.
David Hildenbrand (Arm)
maintainerRe: [RFC PATCH 10/11] selftests/mm: remove READ_ONLY_THP_FOR_FS test in khugepaged
Quoted 6 lines · Matthew Wilcox
Quoted 1 line · Zi Yan
READ_ONLY_THP_FOR_FSis no longer present, remove related test.Um, surely we want to keep the test? It's no longer conditional on
READ_ONLY_THP_FOR_FSbeing enabled, but we still want to collapse mapped files.
Right, in particular this patch would also remove MADV_COLLAPSE support (not just khugepaged support).
Signature · 3 lines
Cheers, David
Zi Yan
reviewerRe: [RFC PATCH 10/11] selftests/mm: remove READ_ONLY_THP_FOR_FS test in khugepaged
Quoted 10 lines · David Hildenbrand (Arm)
Quoted 6 lines · Matthew Wilcox
Quoted 1 line · Zi Yan
READ_ONLY_THP_FOR_FSis no longer present, remove related test.Um, surely we want to keep the test? It's no longer conditional on
READ_ONLY_THP_FOR_FSbeing enabled, but we still want to collapse mapped files.Right, in particular this patch would also remove
MADV_COLLAPSEsupport (not just khugepaged support).
I will keep these selftests in the new version, since the new one aims to enable READ_ONLY_THP_FOR_FS by default for all FSes supporting large folio.
Best Regards,
Yan, Zi
Zi Yan
reviewerRFC PATCH 11/11 selftests/mm: remove READ_ONLY_THP_FOR_FS test in guard-regions
In reply to Zi YanREAD_ONLY_THP_FOR_FS is no longer present, remove related test.
--- tools/testing/selftests/mm/guard-regions.c | 148 +-------------------- 1 file changed, 1 insertion(+), 147 deletions(-)
tools/testing/selftests/mm/guard-regions.c +1 -147
@@ -42,7 +42,6 @@ static sigjmp_buf signal_jmp_buf;enum backing_type {ANON_BACKED ,SHMEM_BACKED , -LOCAL_FILE_BACKED , };FIXTURE (guard_regions)
@@ -67,11 +66,6 @@ FIXTURE_VARIANT_ADD(guard_regions, shmem) .backing = SHMEM_BACKED, }; -FIXTURE_VARIANT_ADD (guard_regions, file) -{ - .backing = LOCAL_FILE_BACKED, -}; -static bool is_anon_backed (const FIXTURE_VARIANT (guard_regions) * variant) {switch (variant->backing) {
@@ -98,7 +92,6 @@ static void *mmap_(FIXTURE_DATA(guard_regions) * self, offset =0 ;break ;case SHMEM_BACKED : -case LOCAL_FILE_BACKED : flags |=MAP_SHARED ; fd = self->fd;break ;
@@ -198,18 +191,6 @@ static void teardown_sighandler(void)sigaction (SIGSEGV , &act,NULL ); } -static int open_file (const char *prefix,char *path) -{ -int fd; - -snprintf (path,PATH_MAX ,"%sguard_regions_test_file_XXXXXX" , prefix); - fd =mkstemp (path); -if (fd <0 ) -ksft_exit_fail_perror ("mkstemp" ); - -return fd; -} -/* Establish a varying pattern in a buffer. */ static void set_pattern (char *ptr,size_t num_pages,size_t page_size) {
@@ -262,54 +243,6 @@ static bool is_buf_eq(char *buf, size_t size, char chr)return true; } -/* -* Some file systems have issues with merging due to changing merge-sensitive -* parameters in the .mmap callback, and prior to .mmap_prepare being -* implemented everywhere this will now result in an unexpected failure to -* merge (e.g. - overlayfs). -* -* Perform a simple test to see if the local file system suffers from this, if -* it does then we can skip test logic that assumes local file system merging is -* sane. -*/ -static bool local_fs_has_sane_mmap (FIXTURE_DATA (guard_regions) * self, -const FIXTURE_VARIANT (guard_regions) * variant) -{ -const unsigned long page_size = self->page_size; -char *ptr, *ptr2; -struct procmap_fd procmap; - -if (variant->backing !=LOCAL_FILE_BACKED ) -return true; - -/* Map 10 pages. */ - ptr =mmap_ (self, variant,NULL ,10 * page_size,PROT_READ |PROT_WRITE ,0 ,0 ); -if (ptr ==MAP_FAILED ) -return false; -/* Unmap the middle. */ -munmap (&ptr[5 * page_size], page_size); - -/* Map again. */ - ptr2 =mmap_ (self, variant, &ptr[5 * page_size], page_size,PROT_READ |PROT_WRITE , -MAP_FIXED ,5 * page_size); - -if (ptr2 ==MAP_FAILED ) -return false; - -/* Now make sure they all merged. */ -if (open_self_procmap (&procmap) !=0 ) -return false; -if (!find_vma_procmap (&procmap, ptr)) -return false; -if (procmap.query.vma_start != (unsigned long )ptr) -return false; -if (procmap.query.vma_end != (unsigned long )ptr +10 * page_size) -return false; -close_procmap (&procmap); - -return true; -} -FIXTURE_SETUP (guard_regions) { self->page_size = (unsigned long )sysconf (_SC_PAGESIZE);
@@ -318,9 +251,6 @@ FIXTURE_SETUP(guard_regions)switch (variant->backing) {case ANON_BACKED :return ; -case LOCAL_FILE_BACKED : - self->fd =open_file ("" , self->path); -break ;case SHMEM_BACKED : self->fd =memfd_create (self->path,0 );break ;
@@ -1750,55 +1680,6 @@ TEST_F(guard_regions, map_private)ASSERT_EQ (munmap (ptr_private,10 * page_size),0 ); } -/* Test that guard regions established over a read-only mapping function correctly. */ -TEST_F(guard_regions, readonly_file) -{ -const unsigned long page_size = self->page_size; -char *ptr; -int i; - -if (variant->backing !=LOCAL_FILE_BACKED ) -SKIP (return,"Read-only test specific to file-backed" ); - -/* Map shared so we can populate with pattern, populate it, unmap. */ - ptr =mmap_ (self, variant,NULL ,10 * page_size, -PROT_READ |PROT_WRITE ,0 ,0 ); -ASSERT_NE (ptr,MAP_FAILED ); -set_pattern (ptr,10 , page_size); -ASSERT_EQ (munmap (ptr,10 * page_size),0 ); -/* Close the fd so we can re-open read-only. */ -ASSERT_EQ (close (self->fd),0 ); - -/* Re-open read-only. */ - self->fd =open (self->path,O_RDONLY ); -ASSERT_NE (self->fd,-1 ); -/* Re-map read-only. */ - ptr =mmap_ (self, variant,NULL ,10 * page_size,PROT_READ ,0 ,0 ); -ASSERT_NE (ptr,MAP_FAILED ); - -/* Mark every other page guarded. */ -for (i =0 ; i <10 ; i +=2 ) { -char *ptr_pg = &ptr[i * page_size]; - -ASSERT_EQ (madvise (ptr_pg, page_size,MADV_GUARD_INSTALL ),0 ); - } - -/* Assert that the guard regions are in place.*/ -for (i =0 ; i <10 ; i++) { -char *ptr_pg = &ptr[i * page_size]; - -ASSERT_EQ (try_read_buf (ptr_pg), i %2 !=0 ); - } - -/* Remove guard regions. */ -ASSERT_EQ (madvise (ptr,10 * page_size,MADV_GUARD_REMOVE ),0 ); - -/* Ensure the data is as expected. */ -ASSERT_TRUE (check_pattern (ptr,10 , page_size)); - -ASSERT_EQ (munmap (ptr,10 * page_size),0 ); -} - TEST_F(guard_regions, fault_around) {const unsigned long page_size = self->page_size;
@@ -2203,17 +2084,6 @@ TEST_F(guard_regions, collapse)if (variant->backing !=ANON_BACKED )ASSERT_EQ (ftruncate (self->fd, size),0 ); -/* -* We must close and re-open local-file backed as read-only for -* CONFIG_READ_ONLY_THP_FOR_FS to work. -*/ -if (variant->backing ==LOCAL_FILE_BACKED ) { -ASSERT_EQ (close (self->fd),0 ); - - self->fd =open (self->path,O_RDONLY ); -ASSERT_GE (self->fd,0 ); - } - ptr =mmap_ (self, variant,NULL , size,PROT_READ ,0 ,0 );ASSERT_NE (ptr,MAP_FAILED );
@@ -2234,13 +2104,7 @@ TEST_F(guard_regions, collapse)/* Allow huge page throughout region. */ ASSERT_EQ (madvise (ptr, size,MADV_HUGEPAGE ),0 ); -/* -* Now collapse the entire region. This should fail in all cases. -* -* The madvise() call will also fail if CONFIG_READ_ONLY_THP_FOR_FS is -* not set for the local file case, but we can't differentiate whether -* this occurred or if the collapse was rightly rejected. -*/ +/* Now collapse the entire region. This should fail in all cases. */ EXPECT_NE (madvise (ptr, size,MADV_COLLAPSE ),0 );/*
@@ -2298,16 +2162,6 @@ TEST_F(guard_regions, smaps)ASSERT_TRUE (check_vmflag_guard (ptr));ASSERT_TRUE (check_vmflag_guard (&ptr[5 * page_size])); -/* -* If the local file system is unable to merge VMAs due to having -* unusual characteristics, there is no point in asserting merge -* behaviour. -*/ -if (!local_fs_has_sane_mmap (self, variant)) { -TH_LOG ("local filesystem does not support sane merging skipping merge test" ); -return ; - } -/* Map a fresh VMA between the two split VMAs. */ ptr2 =mmap_ (self, variant, &ptr[4 * page_size], page_size,PROT_READ |PROT_WRITE ,MAP_FIXED ,4 * page_size);
Signature · 1 line
2.43.0