diff --git a/include/linux/hugetlb_cgroup.h b/include/linux/hugetlb_cgroup.h index 2ad6e92f124a..0bff345c4bc6 100644 --- a/include/linux/hugetlb_cgroup.h +++ b/include/linux/hugetlb_cgroup.h @@ -113,6 +113,11 @@ static inline bool hugetlb_cgroup_disabled(void) return !cgroup_subsys_enabled(hugetlb_cgrp_subsys); } +static inline void hugetlb_cgroup_put_rsvd_cgroup(struct hugetlb_cgroup *h_cg) +{ + css_put(&h_cg->css); +} + extern int hugetlb_cgroup_charge_cgroup(int idx, unsigned long nr_pages, struct hugetlb_cgroup **ptr); extern int hugetlb_cgroup_charge_cgroup_rsvd(int idx, unsigned long nr_pages, @@ -138,7 +143,8 @@ extern void hugetlb_cgroup_uncharge_counter(struct resv_map *resv, extern void hugetlb_cgroup_uncharge_file_region(struct resv_map *resv, struct file_region *rg, - unsigned long nr_pages); + unsigned long nr_pages, + bool region_del); extern void hugetlb_cgroup_file_init(void) __init; extern void hugetlb_cgroup_migrate(struct page *oldhpage, @@ -147,7 +153,8 @@ extern void hugetlb_cgroup_migrate(struct page *oldhpage, #else static inline void hugetlb_cgroup_uncharge_file_region(struct resv_map *resv, struct file_region *rg, - unsigned long nr_pages) + unsigned long nr_pages, + bool region_del) { } @@ -185,6 +192,10 @@ static inline bool hugetlb_cgroup_disabled(void) return true; } +static inline void hugetlb_cgroup_put_rsvd_cgroup(struct hugetlb_cgroup *h_cg) +{ +} + static inline int hugetlb_cgroup_charge_cgroup(int idx, unsigned long nr_pages, struct hugetlb_cgroup **ptr) { diff --git a/mm/hugetlb.c b/mm/hugetlb.c index 94c6b3d4df96..573f1a0183be 100644 --- a/mm/hugetlb.c +++ b/mm/hugetlb.c @@ -285,6 +285,17 @@ static void record_hugetlb_cgroup_uncharge_info(struct hugetlb_cgroup *h_cg, nrg->reservation_counter = &h_cg->rsvd_hugepage[hstate_index(h)]; nrg->css = &h_cg->css; + /* + * The caller will hold exactly one h_cg->css reference for the + * whole contiguous reservation region. But this area might be + * scattered when there are already some file_regions reside in + * it. As a result, many file_regions may share only one css + * reference. In order to ensure that one file_region must hold + * exactly one h_cg->css reference, we should do css_get for + * each file_region and leave the reference held by caller + * untouched. + */ + css_get(&h_cg->css); if (!resv->pages_per_hpage) resv->pages_per_hpage = pages_per_huge_page(h); /* pages_per_hpage should be the same for all entries in @@ -298,6 +309,14 @@ static void record_hugetlb_cgroup_uncharge_info(struct hugetlb_cgroup *h_cg, #endif } +static void put_uncharge_info(struct file_region *rg) +{ +#ifdef CONFIG_CGROUP_HUGETLB + if (rg->css) + css_put(rg->css); +#endif +} + static bool has_same_uncharge_info(struct file_region *rg, struct file_region *org) { @@ -321,6 +340,7 @@ static void coalesce_file_region(struct resv_map *resv, struct file_region *rg) prg->to = rg->to; list_del(&rg->link); + put_uncharge_info(rg); kfree(rg); rg = prg; @@ -332,6 +352,7 @@ static void coalesce_file_region(struct resv_map *resv, struct file_region *rg) nrg->from = rg->from; list_del(&rg->link); + put_uncharge_info(rg); kfree(rg); } } @@ -664,7 +685,7 @@ static long region_del(struct resv_map *resv, long f, long t) del += t - f; hugetlb_cgroup_uncharge_file_region( - resv, rg, t - f); + resv, rg, t - f, false); /* New entry for end of split region */ nrg->from = t; @@ -685,7 +706,7 @@ static long region_del(struct resv_map *resv, long f, long t) if (f <= rg->from && t >= rg->to) { /* Remove entire region */ del += rg->to - rg->from; hugetlb_cgroup_uncharge_file_region(resv, rg, - rg->to - rg->from); + rg->to - rg->from, true); list_del(&rg->link); kfree(rg); continue; @@ -693,13 +714,13 @@ static long region_del(struct resv_map *resv, long f, long t) if (f <= rg->from) { /* Trim beginning of region */ hugetlb_cgroup_uncharge_file_region(resv, rg, - t - rg->from); + t - rg->from, false); del += t - rg->from; rg->from = t; } else { /* Trim end of region */ hugetlb_cgroup_uncharge_file_region(resv, rg, - rg->to - f); + rg->to - f, false); del += rg->to - f; rg->to = f; @@ -5189,6 +5210,10 @@ int hugetlb_reserve_pages(struct inode *inode, */ long rsv_adjust; + /* + * hugetlb_cgroup_uncharge_cgroup_rsvd() will put the + * reference to h_cg->css. See comment below for detail. + */ hugetlb_cgroup_uncharge_cgroup_rsvd( hstate_index(h), (chg - add) * pages_per_huge_page(h), h_cg); @@ -5196,6 +5221,14 @@ int hugetlb_reserve_pages(struct inode *inode, rsv_adjust = hugepage_subpool_put_pages(spool, chg - add); hugetlb_acct_memory(h, -rsv_adjust); + } else if (h_cg) { + /* + * The file_regions will hold their own reference to + * h_cg->css. So we should release the reference held + * via hugetlb_cgroup_charge_cgroup_rsvd() when we are + * done. + */ + hugetlb_cgroup_put_rsvd_cgroup(h_cg); } } return 0; diff --git a/mm/hugetlb_cgroup.c b/mm/hugetlb_cgroup.c index 9182848dda3e..1348819f546c 100644 --- a/mm/hugetlb_cgroup.c +++ b/mm/hugetlb_cgroup.c @@ -391,7 +391,8 @@ void hugetlb_cgroup_uncharge_counter(struct resv_map *resv, unsigned long start, void hugetlb_cgroup_uncharge_file_region(struct resv_map *resv, struct file_region *rg, - unsigned long nr_pages) + unsigned long nr_pages, + bool region_del) { if (hugetlb_cgroup_disabled() || !resv || !rg || !nr_pages) return; @@ -400,7 +401,12 @@ void hugetlb_cgroup_uncharge_file_region(struct resv_map *resv, !resv->reservation_counter) { page_counter_uncharge(rg->reservation_counter, nr_pages * resv->pages_per_hpage); - css_put(rg->css); + /* + * Only do css_put(rg->css) when we delete the entire region + * because one file_region must hold exactly one css reference. + */ + if (region_del) + css_put(rg->css); } }