summaryrefslogtreecommitdiffstats
path: root/mm/hugetlb.c
diff options
context:
space:
mode:
authorMike Kravetz <mike.kravetz@oracle.com>2020-11-01 17:07:27 -0800
committerLinus Torvalds <torvalds@linux-foundation.org>2020-11-02 12:14:18 -0800
commit79aa925bf239c234be8586780e482872dc4690dd (patch)
treec7899dba5dfb86761617f67cc78ac4fe48039fce /mm/hugetlb.c
parent46b1ee38b2ba1a9524c8e886ad078bd3ca40de2a (diff)
downloadlinux-79aa925bf239c234be8586780e482872dc4690dd.tar.bz2
hugetlb_cgroup: fix reservation accounting
Michal Privoznik was using "free page reporting" in QEMU/virtio-balloon with hugetlbfs and hit the warning below. QEMU with free page hinting uses fallocate(FALLOC_FL_PUNCH_HOLE) to discard pages that are reported as free by a VM. The reporting granularity is in pageblock granularity. So when the guest reports 2M chunks, we fallocate(FALLOC_FL_PUNCH_HOLE) one huge page in QEMU. WARNING: CPU: 7 PID: 6636 at mm/page_counter.c:57 page_counter_uncharge+0x4b/0x50 Modules linked in: ... CPU: 7 PID: 6636 Comm: qemu-system-x86 Not tainted 5.9.0 #137 Hardware name: Gigabyte Technology Co., Ltd. X570 AORUS PRO/X570 AORUS PRO, BIOS F21 07/31/2020 RIP: 0010:page_counter_uncharge+0x4b/0x50 ... Call Trace: hugetlb_cgroup_uncharge_file_region+0x4b/0x80 region_del+0x1d3/0x300 hugetlb_unreserve_pages+0x39/0xb0 remove_inode_hugepages+0x1a8/0x3d0 hugetlbfs_fallocate+0x3c4/0x5c0 vfs_fallocate+0x146/0x290 __x64_sys_fallocate+0x3e/0x70 do_syscall_64+0x33/0x40 entry_SYSCALL_64_after_hwframe+0x44/0xa9 Investigation of the issue uncovered bugs in hugetlb cgroup reservation accounting. This patch addresses the found issues. Fixes: 075a61d07a8e ("hugetlb_cgroup: add accounting for shared mappings") Reported-by: Michal Privoznik <mprivozn@redhat.com> Co-developed-by: David Hildenbrand <david@redhat.com> Signed-off-by: David Hildenbrand <david@redhat.com> Signed-off-by: Mike Kravetz <mike.kravetz@oracle.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Tested-by: Michal Privoznik <mprivozn@redhat.com> Reviewed-by: Mina Almasry <almasrymina@google.com> Acked-by: Michael S. Tsirkin <mst@redhat.com> Cc: <stable@vger.kernel.org> Cc: David Hildenbrand <david@redhat.com> Cc: Michal Hocko <mhocko@kernel.org> Cc: Muchun Song <songmuchun@bytedance.com> Cc: "Aneesh Kumar K . V" <aneesh.kumar@linux.vnet.ibm.com> Cc: Tejun Heo <tj@kernel.org> Link: https://lkml.kernel.org/r/20201021204426.36069-1-mike.kravetz@oracle.com Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Diffstat (limited to 'mm/hugetlb.c')
-rw-r--r--mm/hugetlb.c20
1 files changed, 11 insertions, 9 deletions
diff --git a/mm/hugetlb.c b/mm/hugetlb.c
index fe76f8fd5a73..5a620f690911 100644
--- a/mm/hugetlb.c
+++ b/mm/hugetlb.c
@@ -648,6 +648,8 @@ retry:
}
del += t - f;
+ hugetlb_cgroup_uncharge_file_region(
+ resv, rg, t - f);
/* New entry for end of split region */
nrg->from = t;
@@ -660,9 +662,6 @@ retry:
/* Original entry is trimmed */
rg->to = f;
- hugetlb_cgroup_uncharge_file_region(
- resv, rg, nrg->to - nrg->from);
-
list_add(&nrg->link, &rg->link);
nrg = NULL;
break;
@@ -678,17 +677,17 @@ retry:
}
if (f <= rg->from) { /* Trim beginning of region */
- del += t - rg->from;
- rg->from = t;
-
hugetlb_cgroup_uncharge_file_region(resv, rg,
t - rg->from);
- } else { /* Trim end of region */
- del += rg->to - f;
- rg->to = f;
+ del += t - rg->from;
+ rg->from = t;
+ } else { /* Trim end of region */
hugetlb_cgroup_uncharge_file_region(resv, rg,
rg->to - f);
+
+ del += rg->to - f;
+ rg->to = f;
}
}
@@ -2443,6 +2442,9 @@ struct page *alloc_huge_page(struct vm_area_struct *vma,
rsv_adjust = hugepage_subpool_put_pages(spool, 1);
hugetlb_acct_memory(h, -rsv_adjust);
+ if (deferred_reserve)
+ hugetlb_cgroup_uncharge_page_rsvd(hstate_index(h),
+ pages_per_huge_page(h), page);
}
return page;