mm/hugetlb: code refine and simplification
Subsystems (2)
v3 cover mm/hugetlb: code refine and simplification
Following are some cleanup for hugetlb.
Simple test with tools/testing/selftests/vm/map_hugetlb pass.
v3:
* rebase on v5.9-rc2 which adjust the last patch a little
v2:
* drop 5/6/10 since similar patches are merged or under review.
* adjust 2 based on comment from Mike Kravetz
Wei Yang (7):
mm/hugetlb: not necessary to coalesce regions recursively mm/hugetlb: remove VM_BUG_ON(!nrg) in
get_file_region_entry_from_cache()
mm/hugetlb: use list_splice to merge two list at once mm/hugetlb: count file_region to be added when regions_needed != NULL mm/hugetlb: a page from buddy is not on any list mm/hugetlb: narrow the hugetlb_lock protection area during preparing
huge page
mm/hugetlb: take the free hpage during the iteration directly
mm/hugetlb.c | 71 ++++++++++++++++++++++------------------------------ 1 file changed, 30 insertions(+), 41 deletions(-)
Signature · 1 line
2.20.1 (Apple Git-117)
PATCH v3 1/7 mm/hugetlb: not necessary to coalesce regions recursively
Per my understanding, we keep the regions ordered and would always coalesce regions properly. So the task to keep this property is just to coalesce its neighbour.
Let's simplify this.
--- mm/hugetlb.c | 6 +----- 1 file changed, 1 insertion(+), 5 deletions(-)
mm/hugetlb.c +1 -5
@@ -309,8 +309,7 @@ static void coalesce_file_region(struct resv_map *resv, struct file_region *rg)list_del (&rg->link);kfree (rg); -coalesce_file_region (resv, prg); -return ; + rg = prg; } nrg =list_next_entry (rg, link);
@@ -320,9 +319,6 @@ static void coalesce_file_region(struct resv_map *resv, struct file_region *rg)list_del (&rg->link);kfree (rg); - -coalesce_file_region (resv, nrg); -return ; } }
Signature · 1 line
2.20.1 (Apple Git-117)
PATCH v3 2/7 mm/hugetlb: remove VM_BUG_ON(!nrg) in get_file_region_entry_from_cache()
In reply to Wei YangWe are sure to get a valid file_region, otherwise the VM_BUG_ON(resv->region_cache_count <= 0) at the very beginning would be triggered.
Let's remove the redundant one.
--- mm/hugetlb.c | 1 - 1 file changed, 1 deletion(-)
mm/hugetlb.c +0 -1
@@ -240,7 +240,6 @@ get_file_region_entry_from_cache(struct resv_map *resv, long from, long to) resv->region_cache_count--; nrg = list_first_entry(&resv->region_cache, struct file_region, link); -VM_BUG_ON (!nrg);list_del (&nrg->link); nrg->from = from;
Signature · 1 line
2.20.1 (Apple Git-117)
PATCH v3 3/7 mm/hugetlb: use list_splice to merge two list at once
In reply to Wei YangInstead of add allocated file_region one by one to region_cache, we could use list_splice to merge two list at once.
Also we know the number of entries in the list, increase the number directly.
--- mm/hugetlb.c | 7 ++----- 1 file changed, 2 insertions(+), 5 deletions(-)
mm/hugetlb.c +2 -5
@@ -443,11 +443,8 @@ static int allocate_file_region_entries(struct resv_map *resv,spin_lock (&resv->lock); -list_for_each_entry_safe (rg, trg, &allocated_regions, link) { -list_del (&rg->link); -list_add (&rg->link, &resv->region_cache); - resv->region_cache_count++; - } +list_splice (&allocated_regions, &resv->region_cache); + resv->region_cache_count += to_allocate; }return 0 ;
Signature · 1 line
2.20.1 (Apple Git-117)
PATCH v3 4/7 mm/hugetlb: count file_region to be added when regions_needed != NULL
In reply to Wei YangThere are only two cases of function add_reservation_in_range()
* count file_region and return the number in regions_needed
* do the real list operation without counting
This means it is not necessary to have two parameters to classify these two cases.
Just use regions_needed to separate them.
--- mm/hugetlb.c | 33 +++++++++++++++++---------------- 1 file changed, 17 insertions(+), 16 deletions(-)
mm/hugetlb.c +17 -16
@@ -321,16 +321,17 @@ static void coalesce_file_region(struct resv_map *resv, struct file_region *rg) } } -/* Must be called with resv->lock held. Calling this with count_only == true -* will count the number of pages to be added but will not modify the linked -* list. If regions_needed != NULL and count_only == true, then regions_needed -* will indicate the number of file_regions needed in the cache to carry out to -* add the regions for this range. +/* +* Must be called with resv->lock held. +* +* Calling this with regions_needed != NULL will count the number of pages +* to be added but will not modify the linked list. And regions_needed will +* indicate the number of file_regions needed in the cache to carry out to add +* the regions for this range. */ static long add_reservation_in_range (struct resv_map *resv,long f,long t,struct hugetlb_cgroup *h_cg, -struct hstate *h,long *regions_needed, -bool count_only) +struct hstate *h,long *regions_needed) {long add =0 ;struct list_head *head = &resv->regions;
@@ -366,14 +367,14 @@ static long add_reservation_in_range(struct resv_map *resv, long f, long t,*/ if (rg->from > last_accounted_offset) { add += rg->from - last_accounted_offset; -if (!count_only) { +if (!regions_needed) { nrg =get_file_region_entry_from_cache ( resv, last_accounted_offset, rg->from);record_hugetlb_cgroup_uncharge_info (h_cg, h, resv, nrg);list_add (&nrg->link, rg->link.prev);coalesce_file_region (resv, nrg); - }else if (regions_needed) + }else *regions_needed +=1 ; }
@@ -385,13 +386,13 @@ static long add_reservation_in_range(struct resv_map *resv, long f, long t,*/ if (last_accounted_offset < t) { add += t - last_accounted_offset; -if (!count_only) { +if (!regions_needed) { nrg =get_file_region_entry_from_cache ( resv, last_accounted_offset, t);record_hugetlb_cgroup_uncharge_info (h_cg, h, resv, nrg);list_add (&nrg->link, rg->link.prev);coalesce_file_region (resv, nrg); - }else if (regions_needed) + }else *regions_needed +=1 ; }
@@ -484,8 +485,8 @@ static long region_add(struct resv_map *resv, long f, long t, retry:/* Count how many regions are actually needed to execute this add. */ -add_reservation_in_range (resv, f, t,NULL ,NULL , &actual_regions_needed, - true); +add_reservation_in_range (resv, f, t,NULL ,NULL , + &actual_regions_needed);/* * Check for sufficient descriptors in the cache to accommodate
@@ -513,7 +514,7 @@ static long region_add(struct resv_map *resv, long f, long t, goto retry; } - add =add_reservation_in_range (resv, f, t, h_cg, h,NULL , false); + add =add_reservation_in_range (resv, f, t, h_cg, h,NULL ); resv->adds_in_progress -= in_regions_needed;
@@ -549,9 +550,9 @@ static long region_chg(struct resv_map *resv, long f, long t,spin_lock (&resv->lock); -/* Count how many hugepages in this range are NOT respresented. */ +/* Count how many hugepages in this range are NOT represented. */ chg =add_reservation_in_range (resv, f, t,NULL ,NULL , - out_regions_needed, true); + out_regions_needed);if (*out_regions_needed ==0 ) *out_regions_needed =1 ;
Signature · 1 line
2.20.1 (Apple Git-117)
PATCH v3 5/7 mm/hugetlb: a page from buddy is not on any list
In reply to Wei YangThe page allocated from buddy is not on any list, so just use list_add() is enough.
--- mm/hugetlb.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)
mm/hugetlb.c +1 -1
@@ -2405,7 +2405,7 @@ struct page *alloc_huge_page(struct vm_area_struct *vma, h->resv_huge_pages--; }spin_lock (&hugetlb_lock); -list_move (&page->lru, &h->hugepage_activelist); +list_add (&page->lru, &h->hugepage_activelist);/* Fall through */ }hugetlb_cgroup_commit_charge (idx,pages_per_huge_page (h), h_cg, page);
Signature · 1 line
2.20.1 (Apple Git-117)
PATCH v3 6/7 mm/hugetlb: narrow the hugetlb_lock protection area during preparing huge page
In reply to Wei Yangset_hugetlb_cgroup_[rsvd] just manipulate page local data, which is not necessary to be protected by hugetlb_lock.
Let's take this out.
--- mm/hugetlb.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)
mm/hugetlb.c +1 -1
@@ -1493,9 +1493,9 @@ static void prep_new_huge_page(struct hstate *h, struct page *page, int nid) {INIT_LIST_HEAD (&page->lru);set_compound_page_dtor (page,HUGETLB_PAGE_DTOR ); -spin_lock (&hugetlb_lock);set_hugetlb_cgroup (page,NULL );set_hugetlb_cgroup_rsvd (page,NULL ); +spin_lock (&hugetlb_lock); h->nr_huge_pages++; h->nr_huge_pages_node[nid]++;spin_unlock (&hugetlb_lock);
Signature · 1 line
2.20.1 (Apple Git-117)
PATCH v3 7/7 mm/hugetlb: take the free hpage during the iteration directly
In reply to Wei YangFunction dequeue_huge_page_node_exact() iterates the free list and return the first valid free hpage.
Instead of break and check the loop variant, we could return in the loop directly. This could reduce some redundant check.
--- mm/hugetlb.c | 20 ++++++++------------ 1 file changed, 8 insertions(+), 12 deletions(-)
mm/hugetlb.c +8 -12
@@ -1040,21 +1040,17 @@ static struct page *dequeue_huge_page_node_exact(struct hstate *h, int nid)if (nocma &&is_migrate_cma_page (page))continue ; -if (!PageHWPoison (page)) +if (PageHWPoison (page))break ; + +list_move (&page->lru, &h->hugepage_activelist); +set_page_refcounted (page); + h->free_huge_pages--; + h->free_huge_pages_node[nid]--; +return page; } -/* -* if 'non-isolated free hugepage' not found on the list, -* the allocation fails. -*/ -if (&h->hugepage_freelists[nid] == &page->lru) -return NULL ; -list_move (&page->lru, &h->hugepage_activelist); -set_page_refcounted (page); - h->free_huge_pages--; - h->free_huge_pages_node[nid]--; -return page; +return NULL ; } static struct page *dequeue_huge_page_nodemask(struct hstate *h, gfp_t gfp_mask, int nid,
Signature · 1 line
2.20.1 (Apple Git-117)
Re: [Patch v3 7/7] mm/hugetlb: take the free hpage during the iteration directly
Quoted 16 lines · Wei Yang
Function
dequeue_huge_page_node_exact()iterates the free list and return the first valid free hpage.Instead of break and check the loop variant, we could return in the loop directly. This could reduce some redundant check.
Signed-off-by Wei Yang <[email protected]>--- mm/hugetlb.c | 20 ++++++++------------ 1 file changed, 8 insertions(+), 12 deletions(-)mm/hugetlb.c +0
-0
mm/hugetlb.c static struct page *dequeue_huge_page_node_exact(struct hstate *h, int nid) · line 1044
Quoted 6 lines
mm/hugetlb.c +1
-1@@ -1040,21 +1040,17 @@ static struct page *dequeue_huge_page_node_exact(struct hstate *h, int nid)if (nocma &&is_migrate_cma_page (page))continue ; -if (!PageHWPoison (page)) +if (PageHWPoison (page))break ;
Previously, when encountering a PageHWPoison(page) the loop would continue and check the next page in the list. It now breaks the loop and returns NULL. Is not this a change in behavior? Perhaps you want to change that break to a continue. Or, restructure in some other way.
Signature · 1 line
Mike Kravetz
Quoted 24 lines
mm/hugetlb.c +7
-11+ +list_move (&page->lru, &h->hugepage_activelist); +set_page_refcounted (page); + h->free_huge_pages--; + h->free_huge_pages_node[nid]--; +return page; } -/* -* if 'non-isolated free hugepage' not found on the list, -* the allocation fails. -*/ -if (&h->hugepage_freelists[nid] == &page->lru) -return NULL ; -list_move (&page->lru, &h->hugepage_activelist); -set_page_refcounted (page); - h->free_huge_pages--; - h->free_huge_pages_node[nid]--; -return page; +return NULL ; } static struct page *dequeue_huge_page_nodemask(struct hstate *h, gfp_t gfp_mask, int nid,
Re: [Patch v3 7/7] mm/hugetlb: take the free hpage during the iteration directly
Quoted 20 lines · Mike Kravetz
Quoted 19 lines · Wei Yang
Function
dequeue_huge_page_node_exact()iterates the free list and return the first valid free hpage.Instead of break and check the loop variant, we could return in the loop directly. This could reduce some redundant check.
Signed-off-by Wei Yang <[email protected]>--- mm/hugetlb.c | 20 ++++++++------------ 1 file changed, 8 insertions(+), 12 deletions(-)mm/hugetlb.c +0
-0@@ -1040,21 +1040,17 @@ static struct page *dequeue_huge_page_node_exact(struct hstate *h, int nid)if (nocma &&is_migrate_cma_page (page))continue ;
Quoted 8 lines
mm/hugetlb.c static struct page *dequeue_huge_page_node_exact(struct hstate *h, int nid) · line 1044
Quoted 3 lines
mm/hugetlb.c +1
-1-if (!PageHWPoison (page)) +if (PageHWPoison (page))break ;Previously, when encountering a PageHWPoison(page) the loop would continue and check the next page in the list. It now breaks the loop and returns NULL. Is not this a change in behavior? Perhaps you want to change that break to a continue. Or, restructure in some other way.
Shame on me. You are right. I should change it to continue.
Andrew,
Sorry for the inconvenience.
Quoted 27 lines
Signature · 1 line
Mike KravetzQuoted 24 lines
mm/hugetlb.c +7
-11+ +list_move (&page->lru, &h->hugepage_activelist); +set_page_refcounted (page); + h->free_huge_pages--; + h->free_huge_pages_node[nid]--; +return page; } -/* -* if 'non-isolated free hugepage' not found on the list, -* the allocation fails. -*/ -if (&h->hugepage_freelists[nid] == &page->lru) -return NULL ; -list_move (&page->lru, &h->hugepage_activelist); -set_page_refcounted (page); - h->free_huge_pages--; - h->free_huge_pages_node[nid]--; -return page; +return NULL ; } static struct page *dequeue_huge_page_nodemask(struct hstate *h, gfp_t gfp_mask, int nid,
Signature · 2 lines
Wei Yang Help you, Help me